diff options
Diffstat (limited to 'drivers/net/ethernet/intel/ice')
82 files changed, 16917 insertions, 8639 deletions
diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile index c36faa7d1471..9183d480b70b 100644 --- a/drivers/net/ethernet/intel/ice/Makefile +++ b/drivers/net/ethernet/intel/ice/Makefile @@ -18,8 +18,12 @@ ice-y := ice_main.o \ ice_txrx_lib.o \ ice_txrx.o \ ice_fltr.o \ + ice_pf_vsi_vlan_ops.o \ + ice_vsi_vlan_ops.o \ + ice_vsi_vlan_lib.o \ ice_fdir.o \ ice_ethtool_fdir.o \ + ice_vlan_mode.o \ ice_flex_pipe.o \ ice_flow.o \ ice_idc.o \ @@ -29,9 +33,16 @@ ice-y := ice_main.o \ ice_ethtool.o \ ice_repr.o \ ice_tc_lib.o -ice-$(CONFIG_PCI_IOV) += ice_virtchnl_allowlist.o -ice-$(CONFIG_PCI_IOV) += ice_virtchnl_pf.o ice_sriov.o ice_virtchnl_fdir.o +ice-$(CONFIG_PCI_IOV) += \ + ice_sriov.o \ + ice_virtchnl.o \ + ice_virtchnl_allowlist.o \ + ice_virtchnl_fdir.o \ + ice_vf_mbx.o \ + ice_vf_vsi_vlan_ops.o \ + ice_vf_lib.o ice-$(CONFIG_PTP_1588_CLOCK) += ice_ptp.o ice_ptp_hw.o +ice-$(CONFIG_TTY) += ice_gnss.o ice-$(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 diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 4e16d185077d..001500afc4a6 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -51,9 +51,8 @@ #include <net/gre.h> #include <net/udp_tunnel.h> #include <net/vxlan.h> -#if IS_ENABLED(CONFIG_DCB) -#include <scsi/iscsi_proto.h> -#endif /* CONFIG_DCB */ +#include <net/gtp.h> +#include <linux/ppp_defs.h> #include "ice_devids.h" #include "ice_type.h" #include "ice_txrx.h" @@ -63,8 +62,8 @@ #include "ice_flow.h" #include "ice_sched.h" #include "ice_idc_int.h" -#include "ice_virtchnl_pf.h" #include "ice_sriov.h" +#include "ice_vf_mbx.h" #include "ice_ptp.h" #include "ice_fdir.h" #include "ice_xsk.h" @@ -72,6 +71,8 @@ #include "ice_repr.h" #include "ice_eswitch.h" #include "ice_lag.h" +#include "ice_vsi_vlan_ops.h" +#include "ice_gnss.h" #define ICE_BAR0 0 #define ICE_REQ_DESC_MULTIPLE 32 @@ -107,7 +108,6 @@ /* All VF control VSIs share the same IRQ, so assign a unique ID for them */ #define ICE_RES_VF_CTRL_VEC_ID (ICE_RES_RDMA_VEC_ID - 1) #define ICE_INVAL_Q_INDEX 0xffff -#define ICE_INVAL_VFID 256 #define ICE_MAX_RXQS_PER_TC 256 /* Used when setting VSI context per TC Rx queues */ @@ -182,7 +182,9 @@ enum ice_feature { ICE_F_DSCP, + ICE_F_PTP_EXTTS, ICE_F_SMA_CTRL, + ICE_F_GNSS, ICE_F_MAX }; @@ -246,8 +248,6 @@ struct ice_sw { struct ice_pf *pf; u16 sw_id; /* switch ID for this switch */ u16 bridge_mode; /* VEB/VEPA/Port Virtualizer */ - struct ice_vsi *dflt_vsi; /* default VSI for this switch */ - u8 dflt_vsi_ena:1; /* true if above dflt_vsi is enabled */ }; enum ice_pf_state { @@ -280,7 +280,6 @@ enum ice_pf_state { ICE_VFLR_EVENT_PENDING, ICE_FLTR_OVERFLOW_PROMISC, ICE_VF_DIS, - ICE_VF_DEINIT_IN_PROGRESS, ICE_CFG_BUSY, ICE_SERVICE_SCHED, ICE_SERVICE_DIS, @@ -291,6 +290,7 @@ enum ice_pf_state { ICE_LINK_DEFAULT_OVERRIDE_PENDING, ICE_PHY_INIT_COMPLETE, ICE_FD_VF_FLUSH_CTX, /* set at FD Rx IRQ or timeout */ + ICE_AUX_ERR_PENDING, ICE_STATE_NBITS /* must be last */ }; @@ -301,7 +301,6 @@ enum ice_vsi_state { ICE_VSI_NETDEV_REGISTERED, ICE_VSI_UMAC_FLTR_CHANGED, ICE_VSI_MMAC_FLTR_CHANGED, - ICE_VSI_VLAN_FLTR_CHANGED, ICE_VSI_PROMISC_CHANGED, ICE_VSI_STATE_NBITS /* must be last */ }; @@ -331,7 +330,7 @@ struct ice_vsi { u16 vsi_num; /* HW (absolute) index of this VSI */ u16 idx; /* software index in pf->vsi[] */ - s16 vf_id; /* VF ID for SR-IOV VSIs */ + struct ice_vf *vf; /* VF associated with this VSI */ u16 ethtype; /* Ethernet protocol for pause frame */ u16 num_gfltr; @@ -368,6 +367,8 @@ struct ice_vsi { u8 irqs_ready:1; u8 current_isup:1; /* Sync 'link up' logging */ u8 stat_offsets_loaded:1; + struct ice_vsi_vlan_ops inner_vlan_ops; + struct ice_vsi_vlan_ops outer_vlan_ops; u16 num_vlan; /* queue information */ @@ -468,7 +469,6 @@ enum ice_pf_flags { ICE_FLAG_FD_ENA, ICE_FLAG_PTP_SUPPORTED, /* PTP is supported by NVM */ ICE_FLAG_PTP, /* PTP is enabled by software */ - ICE_FLAG_AUX_ENA, ICE_FLAG_ADV_FEATURES, ICE_FLAG_TC_MQPRIO, /* support for Multi queue TC */ ICE_FLAG_CLS_FLOWER, @@ -482,7 +482,11 @@ enum ice_pf_flags { ICE_FLAG_LEGACY_RX, ICE_FLAG_VF_TRUE_PROMISC_ENA, ICE_FLAG_MDD_AUTO_RESET_VF, + ICE_FLAG_VF_VLAN_PRUNING, ICE_FLAG_LINK_LENIENT_MODE_ENA, + ICE_FLAG_PLUG_AUX_DEV, + ICE_FLAG_MTU_CHANGED, + ICE_FLAG_GNSS, /* GNSS successfully initialized */ ICE_PF_FLAGS_NBITS /* must be last */ }; @@ -523,15 +527,7 @@ struct ice_pf { struct ice_vsi **vsi; /* VSIs created by the driver */ struct ice_sw *first_sw; /* first switch created by firmware */ u16 eswitch_mode; /* current mode of eswitch */ - /* Virtchnl/SR-IOV config info */ - struct ice_vf *vf; - u16 num_alloc_vfs; /* actual number of VFs allocated */ - u16 num_vfs_supported; /* num VFs supported for this PF */ - u16 num_qps_per_vf; - u16 num_msix_per_vf; - /* used to ratelimit the MDD event logging */ - unsigned long last_printed_mdd_jiffies; - DECLARE_BITMAP(malvfs, ICE_MAX_VF_COUNT); + struct ice_vfs vfs; DECLARE_BITMAP(features, ICE_F_MAX); DECLARE_BITMAP(state, ICE_STATE_NBITS); DECLARE_BITMAP(flags, ICE_PF_FLAGS_NBITS); @@ -544,8 +540,12 @@ struct ice_pf { struct mutex avail_q_mutex; /* protects access to avail_[rx|tx]qs */ 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 */ u32 msg_enable; struct ice_ptp ptp; + struct tty_driver *ice_gnss_tty_driver; + struct tty_port *gnss_tty_port[ICE_GNSS_TTY_MINOR_DEVICES]; + struct gnss_serial *gnss_serial[ICE_GNSS_TTY_MINOR_DEVICES]; u16 num_rdma_msix; /* Total MSIX vectors for RDMA driver */ u16 rdma_base_vector; @@ -558,6 +558,7 @@ struct ice_pf { wait_queue_head_t reset_wait_queue; u32 hw_csum_rx_error; + u32 oicr_err_reg; u16 oicr_idx; /* Other interrupt cause MSIX vector index */ u16 num_avail_sw_msix; /* remaining MSIX SW vectors left unclaimed */ u16 max_pf_txqs; /* Total Tx queues PF wide */ @@ -671,7 +672,7 @@ static inline struct ice_pf *ice_netdev_to_pf(struct net_device *netdev) static inline bool ice_is_xdp_ena_vsi(struct ice_vsi *vsi) { - return !!vsi->xdp_prog; + return !!READ_ONCE(vsi->xdp_prog); } static inline void ice_set_ring_xdp(struct ice_tx_ring *ring) @@ -683,8 +684,8 @@ static inline void ice_set_ring_xdp(struct ice_tx_ring *ring) * ice_xsk_pool - get XSK buffer pool bound to a ring * @ring: Rx ring to use * - * Returns a pointer to xdp_umem structure if there is a buffer pool present, - * NULL otherwise. + * Returns a pointer to xsk_buff_pool structure if there is a buffer pool + * present, NULL otherwise. */ static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_rx_ring *ring) { @@ -698,23 +699,33 @@ static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_rx_ring *ring) } /** - * ice_tx_xsk_pool - get XSK buffer pool bound to a ring - * @ring: Tx ring to use + * ice_tx_xsk_pool - assign XSK buff pool to XDP ring + * @vsi: pointer to VSI + * @qid: index of a queue to look at XSK buff pool presence * - * Returns a pointer to xdp_umem structure if there is a buffer pool present, - * NULL otherwise. Tx equivalent of ice_xsk_pool. + * Sets XSK buff pool pointer on XDP ring. + * + * XDP ring is picked from Rx ring, whereas Rx ring is picked based on provided + * queue id. Reason for doing so is that queue vectors might have assigned more + * than one XDP ring, e.g. when user reduced the queue count on netdev; Rx ring + * carries a pointer to one of these XDP rings for its own purposes, such as + * handling XDP_TX action, therefore we can piggyback here on the + * rx_ring->xdp_ring assignment that was done during XDP rings initialization. */ -static inline struct xsk_buff_pool *ice_tx_xsk_pool(struct ice_tx_ring *ring) +static inline void ice_tx_xsk_pool(struct ice_vsi *vsi, u16 qid) { - struct ice_vsi *vsi = ring->vsi; - u16 qid; + struct ice_tx_ring *ring; - qid = ring->q_index - vsi->num_xdp_txq; + ring = vsi->rx_rings[qid]->xdp_ring; + if (!ring) + return; - if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps)) - return NULL; + if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps)) { + ring->xsk_pool = NULL; + return; + } - return xsk_get_pool_from_qid(vsi->netdev, qid); + ring->xsk_pool = xsk_get_pool_from_qid(vsi->netdev, qid); } /** @@ -758,6 +769,21 @@ static inline struct ice_vsi *ice_get_ctrl_vsi(struct ice_pf *pf) } /** + * ice_find_vsi - Find the VSI from VSI ID + * @pf: The PF pointer to search in + * @vsi_num: The VSI ID to search for + */ +static inline struct ice_vsi *ice_find_vsi(struct ice_pf *pf, u16 vsi_num) +{ + int i; + + ice_for_each_vsi(pf, i) + if (pf->vsi[i] && pf->vsi[i]->vsi_num == vsi_num) + return pf->vsi[i]; + return NULL; +} + +/** * ice_is_switchdev_running - check if switchdev is configured * @pf: pointer to PF structure * @@ -833,8 +859,12 @@ u16 ice_get_avail_rxq_count(struct ice_pf *pf); int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx); void ice_update_vsi_stats(struct ice_vsi *vsi); void ice_update_pf_stats(struct ice_pf *pf); +void +ice_fetch_u64_stats_per_ring(struct u64_stats_sync *syncp, + struct ice_q_stats stats, u64 *pkts, u64 *bytes); int ice_up(struct ice_vsi *vsi); int ice_down(struct ice_vsi *vsi); +int ice_down_up(struct ice_vsi *vsi); int ice_vsi_cfg(struct ice_vsi *vsi); struct ice_vsi *ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi); int ice_vsi_determine_xdp_res(struct ice_vsi *vsi); @@ -886,8 +916,7 @@ static inline void ice_set_rdma_cap(struct ice_pf *pf) { if (pf->hw.func_caps.common_cap.rdma && pf->num_rdma_msix) { set_bit(ICE_FLAG_RDMA_ENA, pf->flags); - set_bit(ICE_FLAG_AUX_ENA, pf->flags); - ice_plug_aux_dev(pf); + set_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags); } } @@ -897,8 +926,16 @@ static inline void ice_set_rdma_cap(struct ice_pf *pf) */ static inline void ice_clear_rdma_cap(struct ice_pf *pf) { - ice_unplug_aux_dev(pf); + /* We can directly unplug aux device here only if the flag bit + * ICE_FLAG_PLUG_AUX_DEV is not set because ice_unplug_aux_dev() + * could race with ice_plug_aux_dev() called from + * ice_service_task(). In this case we only clear that bit now and + * aux device will be unplugged later once ice_plug_aux_device() + * called from ice_service_task() finishes (see ice_service_task()). + */ + if (!test_and_clear_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags)) + ice_unplug_aux_dev(pf); + clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); - clear_bit(ICE_FLAG_AUX_ENA, pf->flags); } #endif /* _ICE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index ad1dcfa5ff65..1bdc70aa979d 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -226,6 +226,15 @@ struct ice_aqc_get_sw_cfg_resp_elem { #define ICE_AQC_GET_SW_CONF_RESP_IS_VF BIT(15) }; +/* Set Port parameters, (direct, 0x0203) */ +struct ice_aqc_set_port_params { + __le16 cmd_flags; +#define ICE_AQC_SET_P_PARAMS_DOUBLE_VLAN_ENA BIT(2) + __le16 bad_frame_vsi; + __le16 swid; + u8 reserved[10]; +}; + /* These resource type defines are used for all switch resource * commands where a resource type is required, such as: * Get Resource Allocation command (indirect 0x0204) @@ -283,6 +292,40 @@ struct ice_aqc_alloc_free_res_elem { struct ice_aqc_res_elem elem[]; }; +/* Request buffer for Set VLAN Mode AQ command (indirect 0x020C) */ +struct ice_aqc_set_vlan_mode { + u8 reserved; + u8 l2tag_prio_tagging; +#define ICE_AQ_VLAN_PRIO_TAG_S 0 +#define ICE_AQ_VLAN_PRIO_TAG_M (0x7 << ICE_AQ_VLAN_PRIO_TAG_S) +#define ICE_AQ_VLAN_PRIO_TAG_NOT_SUPPORTED 0x0 +#define ICE_AQ_VLAN_PRIO_TAG_STAG 0x1 +#define ICE_AQ_VLAN_PRIO_TAG_OUTER_CTAG 0x2 +#define ICE_AQ_VLAN_PRIO_TAG_OUTER_VLAN 0x3 +#define ICE_AQ_VLAN_PRIO_TAG_INNER_CTAG 0x4 +#define ICE_AQ_VLAN_PRIO_TAG_MAX 0x4 +#define ICE_AQ_VLAN_PRIO_TAG_ERROR 0x7 + u8 l2tag_reserved[64]; + u8 rdma_packet; +#define ICE_AQ_VLAN_RDMA_TAG_S 0 +#define ICE_AQ_VLAN_RDMA_TAG_M (0x3F << ICE_AQ_VLAN_RDMA_TAG_S) +#define ICE_AQ_SVM_VLAN_RDMA_PKT_FLAG_SETTING 0x10 +#define ICE_AQ_DVM_VLAN_RDMA_PKT_FLAG_SETTING 0x1A + u8 rdma_reserved[2]; + u8 mng_vlan_prot_id; +#define ICE_AQ_VLAN_MNG_PROTOCOL_ID_OUTER 0x10 +#define ICE_AQ_VLAN_MNG_PROTOCOL_ID_INNER 0x11 + u8 prot_id_reserved[30]; +}; + +/* Response buffer for Get VLAN Mode AQ command (indirect 0x020D) */ +struct ice_aqc_get_vlan_mode { + u8 vlan_mode; +#define ICE_AQ_VLAN_MODE_DVM_ENA BIT(0) + u8 l2tag_prio_tagging; + u8 reserved[98]; +}; + /* Add VSI (indirect 0x0210) * Update VSI (indirect 0x0211) * Get VSI (indirect 0x0212) @@ -343,108 +386,113 @@ struct ice_aqc_vsi_props { #define ICE_AQ_VSI_SW_FLAG_SRC_PRUNE BIT(7) u8 sw_flags2; #define ICE_AQ_VSI_SW_FLAG_RX_PRUNE_EN_S 0 -#define ICE_AQ_VSI_SW_FLAG_RX_PRUNE_EN_M \ - (0xF << ICE_AQ_VSI_SW_FLAG_RX_PRUNE_EN_S) +#define ICE_AQ_VSI_SW_FLAG_RX_PRUNE_EN_M (0xF << ICE_AQ_VSI_SW_FLAG_RX_PRUNE_EN_S) #define ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA BIT(0) #define ICE_AQ_VSI_SW_FLAG_LAN_ENA BIT(4) u8 veb_stat_id; #define ICE_AQ_VSI_SW_VEB_STAT_ID_S 0 -#define ICE_AQ_VSI_SW_VEB_STAT_ID_M (0x1F << ICE_AQ_VSI_SW_VEB_STAT_ID_S) +#define ICE_AQ_VSI_SW_VEB_STAT_ID_M (0x1F << ICE_AQ_VSI_SW_VEB_STAT_ID_S) #define ICE_AQ_VSI_SW_VEB_STAT_ID_VALID BIT(5) /* security section */ u8 sec_flags; #define ICE_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD BIT(0) #define ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF BIT(2) -#define ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S 4 -#define ICE_AQ_VSI_SEC_TX_PRUNE_ENA_M (0xF << ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S) +#define ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S 4 +#define ICE_AQ_VSI_SEC_TX_PRUNE_ENA_M (0xF << ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S) #define ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA BIT(0) u8 sec_reserved; /* VLAN section */ - __le16 pvid; /* VLANS include priority bits */ - u8 pvlan_reserved[2]; - u8 vlan_flags; -#define ICE_AQ_VSI_VLAN_MODE_S 0 -#define ICE_AQ_VSI_VLAN_MODE_M (0x3 << ICE_AQ_VSI_VLAN_MODE_S) -#define ICE_AQ_VSI_VLAN_MODE_UNTAGGED 0x1 -#define ICE_AQ_VSI_VLAN_MODE_TAGGED 0x2 -#define ICE_AQ_VSI_VLAN_MODE_ALL 0x3 -#define ICE_AQ_VSI_PVLAN_INSERT_PVID BIT(2) -#define ICE_AQ_VSI_VLAN_EMOD_S 3 -#define ICE_AQ_VSI_VLAN_EMOD_M (0x3 << ICE_AQ_VSI_VLAN_EMOD_S) -#define ICE_AQ_VSI_VLAN_EMOD_STR_BOTH (0x0 << ICE_AQ_VSI_VLAN_EMOD_S) -#define ICE_AQ_VSI_VLAN_EMOD_STR_UP (0x1 << ICE_AQ_VSI_VLAN_EMOD_S) -#define ICE_AQ_VSI_VLAN_EMOD_STR (0x2 << ICE_AQ_VSI_VLAN_EMOD_S) -#define ICE_AQ_VSI_VLAN_EMOD_NOTHING (0x3 << ICE_AQ_VSI_VLAN_EMOD_S) - u8 pvlan_reserved2[3]; + __le16 port_based_inner_vlan; /* VLANS include priority bits */ + u8 inner_vlan_reserved[2]; + u8 inner_vlan_flags; +#define ICE_AQ_VSI_INNER_VLAN_TX_MODE_S 0 +#define ICE_AQ_VSI_INNER_VLAN_TX_MODE_M (0x3 << ICE_AQ_VSI_INNER_VLAN_TX_MODE_S) +#define ICE_AQ_VSI_INNER_VLAN_TX_MODE_ACCEPTUNTAGGED 0x1 +#define ICE_AQ_VSI_INNER_VLAN_TX_MODE_ACCEPTTAGGED 0x2 +#define ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL 0x3 +#define ICE_AQ_VSI_INNER_VLAN_INSERT_PVID BIT(2) +#define ICE_AQ_VSI_INNER_VLAN_EMODE_S 3 +#define ICE_AQ_VSI_INNER_VLAN_EMODE_M (0x3 << ICE_AQ_VSI_INNER_VLAN_EMODE_S) +#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR_BOTH (0x0 << ICE_AQ_VSI_INNER_VLAN_EMODE_S) +#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR_UP (0x1 << ICE_AQ_VSI_INNER_VLAN_EMODE_S) +#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR (0x2 << ICE_AQ_VSI_INNER_VLAN_EMODE_S) +#define ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING (0x3 << ICE_AQ_VSI_INNER_VLAN_EMODE_S) + u8 inner_vlan_reserved2[3]; /* ingress egress up sections */ __le32 ingress_table; /* bitmap, 3 bits per up */ -#define ICE_AQ_VSI_UP_TABLE_UP0_S 0 -#define ICE_AQ_VSI_UP_TABLE_UP0_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP0_S) -#define ICE_AQ_VSI_UP_TABLE_UP1_S 3 -#define ICE_AQ_VSI_UP_TABLE_UP1_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP1_S) -#define ICE_AQ_VSI_UP_TABLE_UP2_S 6 -#define ICE_AQ_VSI_UP_TABLE_UP2_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP2_S) -#define ICE_AQ_VSI_UP_TABLE_UP3_S 9 -#define ICE_AQ_VSI_UP_TABLE_UP3_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP3_S) -#define ICE_AQ_VSI_UP_TABLE_UP4_S 12 -#define ICE_AQ_VSI_UP_TABLE_UP4_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP4_S) -#define ICE_AQ_VSI_UP_TABLE_UP5_S 15 -#define ICE_AQ_VSI_UP_TABLE_UP5_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP5_S) -#define ICE_AQ_VSI_UP_TABLE_UP6_S 18 -#define ICE_AQ_VSI_UP_TABLE_UP6_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP6_S) -#define ICE_AQ_VSI_UP_TABLE_UP7_S 21 -#define ICE_AQ_VSI_UP_TABLE_UP7_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP7_S) +#define ICE_AQ_VSI_UP_TABLE_UP0_S 0 +#define ICE_AQ_VSI_UP_TABLE_UP0_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP0_S) +#define ICE_AQ_VSI_UP_TABLE_UP1_S 3 +#define ICE_AQ_VSI_UP_TABLE_UP1_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP1_S) +#define ICE_AQ_VSI_UP_TABLE_UP2_S 6 +#define ICE_AQ_VSI_UP_TABLE_UP2_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP2_S) +#define ICE_AQ_VSI_UP_TABLE_UP3_S 9 +#define ICE_AQ_VSI_UP_TABLE_UP3_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP3_S) +#define ICE_AQ_VSI_UP_TABLE_UP4_S 12 +#define ICE_AQ_VSI_UP_TABLE_UP4_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP4_S) +#define ICE_AQ_VSI_UP_TABLE_UP5_S 15 +#define ICE_AQ_VSI_UP_TABLE_UP5_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP5_S) +#define ICE_AQ_VSI_UP_TABLE_UP6_S 18 +#define ICE_AQ_VSI_UP_TABLE_UP6_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP6_S) +#define ICE_AQ_VSI_UP_TABLE_UP7_S 21 +#define ICE_AQ_VSI_UP_TABLE_UP7_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP7_S) __le32 egress_table; /* same defines as for ingress table */ /* outer tags section */ - __le16 outer_tag; - u8 outer_tag_flags; -#define ICE_AQ_VSI_OUTER_TAG_MODE_S 0 -#define ICE_AQ_VSI_OUTER_TAG_MODE_M (0x3 << ICE_AQ_VSI_OUTER_TAG_MODE_S) -#define ICE_AQ_VSI_OUTER_TAG_NOTHING 0x0 -#define ICE_AQ_VSI_OUTER_TAG_REMOVE 0x1 -#define ICE_AQ_VSI_OUTER_TAG_COPY 0x2 -#define ICE_AQ_VSI_OUTER_TAG_TYPE_S 2 -#define ICE_AQ_VSI_OUTER_TAG_TYPE_M (0x3 << ICE_AQ_VSI_OUTER_TAG_TYPE_S) -#define ICE_AQ_VSI_OUTER_TAG_NONE 0x0 -#define ICE_AQ_VSI_OUTER_TAG_STAG 0x1 -#define ICE_AQ_VSI_OUTER_TAG_VLAN_8100 0x2 -#define ICE_AQ_VSI_OUTER_TAG_VLAN_9100 0x3 -#define ICE_AQ_VSI_OUTER_TAG_INSERT BIT(4) -#define ICE_AQ_VSI_OUTER_TAG_ACCEPT_HOST BIT(6) - u8 outer_tag_reserved; + __le16 port_based_outer_vlan; + u8 outer_vlan_flags; +#define ICE_AQ_VSI_OUTER_VLAN_EMODE_S 0 +#define ICE_AQ_VSI_OUTER_VLAN_EMODE_M (0x3 << ICE_AQ_VSI_OUTER_VLAN_EMODE_S) +#define ICE_AQ_VSI_OUTER_VLAN_EMODE_SHOW_BOTH 0x0 +#define ICE_AQ_VSI_OUTER_VLAN_EMODE_SHOW_UP 0x1 +#define ICE_AQ_VSI_OUTER_VLAN_EMODE_SHOW 0x2 +#define ICE_AQ_VSI_OUTER_VLAN_EMODE_NOTHING 0x3 +#define ICE_AQ_VSI_OUTER_TAG_TYPE_S 2 +#define ICE_AQ_VSI_OUTER_TAG_TYPE_M (0x3 << ICE_AQ_VSI_OUTER_TAG_TYPE_S) +#define ICE_AQ_VSI_OUTER_TAG_NONE 0x0 +#define ICE_AQ_VSI_OUTER_TAG_STAG 0x1 +#define ICE_AQ_VSI_OUTER_TAG_VLAN_8100 0x2 +#define ICE_AQ_VSI_OUTER_TAG_VLAN_9100 0x3 +#define ICE_AQ_VSI_OUTER_VLAN_PORT_BASED_INSERT BIT(4) +#define ICE_AQ_VSI_OUTER_VLAN_TX_MODE_S 5 +#define ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M (0x3 << ICE_AQ_VSI_OUTER_VLAN_TX_MODE_S) +#define ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ACCEPTUNTAGGED 0x1 +#define ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ACCEPTTAGGED 0x2 +#define ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL 0x3 +#define ICE_AQ_VSI_OUTER_VLAN_BLOCK_TX_DESC BIT(7) + u8 outer_vlan_reserved; /* queue mapping section */ __le16 mapping_flags; -#define ICE_AQ_VSI_Q_MAP_CONTIG 0x0 -#define ICE_AQ_VSI_Q_MAP_NONCONTIG BIT(0) +#define ICE_AQ_VSI_Q_MAP_CONTIG 0x0 +#define ICE_AQ_VSI_Q_MAP_NONCONTIG BIT(0) __le16 q_mapping[16]; -#define ICE_AQ_VSI_Q_S 0 -#define ICE_AQ_VSI_Q_M (0x7FF << ICE_AQ_VSI_Q_S) +#define ICE_AQ_VSI_Q_S 0 +#define ICE_AQ_VSI_Q_M (0x7FF << ICE_AQ_VSI_Q_S) __le16 tc_mapping[8]; -#define ICE_AQ_VSI_TC_Q_OFFSET_S 0 -#define ICE_AQ_VSI_TC_Q_OFFSET_M (0x7FF << ICE_AQ_VSI_TC_Q_OFFSET_S) -#define ICE_AQ_VSI_TC_Q_NUM_S 11 -#define ICE_AQ_VSI_TC_Q_NUM_M (0xF << ICE_AQ_VSI_TC_Q_NUM_S) +#define ICE_AQ_VSI_TC_Q_OFFSET_S 0 +#define ICE_AQ_VSI_TC_Q_OFFSET_M (0x7FF << ICE_AQ_VSI_TC_Q_OFFSET_S) +#define ICE_AQ_VSI_TC_Q_NUM_S 11 +#define ICE_AQ_VSI_TC_Q_NUM_M (0xF << ICE_AQ_VSI_TC_Q_NUM_S) /* queueing option section */ u8 q_opt_rss; -#define ICE_AQ_VSI_Q_OPT_RSS_LUT_S 0 -#define ICE_AQ_VSI_Q_OPT_RSS_LUT_M (0x3 << ICE_AQ_VSI_Q_OPT_RSS_LUT_S) -#define ICE_AQ_VSI_Q_OPT_RSS_LUT_VSI 0x0 -#define ICE_AQ_VSI_Q_OPT_RSS_LUT_PF 0x2 -#define ICE_AQ_VSI_Q_OPT_RSS_LUT_GBL 0x3 -#define ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_S 2 -#define ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_M (0xF << ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_S) -#define ICE_AQ_VSI_Q_OPT_RSS_HASH_S 6 -#define ICE_AQ_VSI_Q_OPT_RSS_HASH_M (0x3 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) -#define ICE_AQ_VSI_Q_OPT_RSS_TPLZ (0x0 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) -#define ICE_AQ_VSI_Q_OPT_RSS_SYM_TPLZ (0x1 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) -#define ICE_AQ_VSI_Q_OPT_RSS_XOR (0x2 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) -#define ICE_AQ_VSI_Q_OPT_RSS_JHASH (0x3 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) +#define ICE_AQ_VSI_Q_OPT_RSS_LUT_S 0 +#define ICE_AQ_VSI_Q_OPT_RSS_LUT_M (0x3 << ICE_AQ_VSI_Q_OPT_RSS_LUT_S) +#define ICE_AQ_VSI_Q_OPT_RSS_LUT_VSI 0x0 +#define ICE_AQ_VSI_Q_OPT_RSS_LUT_PF 0x2 +#define ICE_AQ_VSI_Q_OPT_RSS_LUT_GBL 0x3 +#define ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_S 2 +#define ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_M (0xF << ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_S) +#define ICE_AQ_VSI_Q_OPT_RSS_HASH_S 6 +#define ICE_AQ_VSI_Q_OPT_RSS_HASH_M (0x3 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) +#define ICE_AQ_VSI_Q_OPT_RSS_TPLZ (0x0 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) +#define ICE_AQ_VSI_Q_OPT_RSS_SYM_TPLZ (0x1 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) +#define ICE_AQ_VSI_Q_OPT_RSS_XOR (0x2 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) +#define ICE_AQ_VSI_Q_OPT_RSS_JHASH (0x3 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) u8 q_opt_tc; -#define ICE_AQ_VSI_Q_OPT_TC_OVR_S 0 -#define ICE_AQ_VSI_Q_OPT_TC_OVR_M (0x1F << ICE_AQ_VSI_Q_OPT_TC_OVR_S) -#define ICE_AQ_VSI_Q_OPT_PROF_TC_OVR BIT(7) +#define ICE_AQ_VSI_Q_OPT_TC_OVR_S 0 +#define ICE_AQ_VSI_Q_OPT_TC_OVR_M (0x1F << ICE_AQ_VSI_Q_OPT_TC_OVR_S) +#define ICE_AQ_VSI_Q_OPT_PROF_TC_OVR BIT(7) u8 q_opt_flags; -#define ICE_AQ_VSI_Q_OPT_PE_FLTR_EN BIT(0) +#define ICE_AQ_VSI_Q_OPT_PE_FLTR_EN BIT(0) u8 q_opt_reserved[3]; /* outer up section */ __le32 outer_up_table; /* same structure and defines as ingress tbl */ @@ -452,27 +500,27 @@ struct ice_aqc_vsi_props { __le16 sect_10_reserved; /* flow director section */ __le16 fd_options; -#define ICE_AQ_VSI_FD_ENABLE BIT(0) -#define ICE_AQ_VSI_FD_TX_AUTO_ENABLE BIT(1) -#define ICE_AQ_VSI_FD_PROG_ENABLE BIT(3) +#define ICE_AQ_VSI_FD_ENABLE BIT(0) +#define ICE_AQ_VSI_FD_TX_AUTO_ENABLE BIT(1) +#define ICE_AQ_VSI_FD_PROG_ENABLE BIT(3) __le16 max_fd_fltr_dedicated; __le16 max_fd_fltr_shared; __le16 fd_def_q; -#define ICE_AQ_VSI_FD_DEF_Q_S 0 -#define ICE_AQ_VSI_FD_DEF_Q_M (0x7FF << ICE_AQ_VSI_FD_DEF_Q_S) -#define ICE_AQ_VSI_FD_DEF_GRP_S 12 -#define ICE_AQ_VSI_FD_DEF_GRP_M (0x7 << ICE_AQ_VSI_FD_DEF_GRP_S) +#define ICE_AQ_VSI_FD_DEF_Q_S 0 +#define ICE_AQ_VSI_FD_DEF_Q_M (0x7FF << ICE_AQ_VSI_FD_DEF_Q_S) +#define ICE_AQ_VSI_FD_DEF_GRP_S 12 +#define ICE_AQ_VSI_FD_DEF_GRP_M (0x7 << ICE_AQ_VSI_FD_DEF_GRP_S) __le16 fd_report_opt; -#define ICE_AQ_VSI_FD_REPORT_Q_S 0 -#define ICE_AQ_VSI_FD_REPORT_Q_M (0x7FF << ICE_AQ_VSI_FD_REPORT_Q_S) -#define ICE_AQ_VSI_FD_DEF_PRIORITY_S 12 -#define ICE_AQ_VSI_FD_DEF_PRIORITY_M (0x7 << ICE_AQ_VSI_FD_DEF_PRIORITY_S) -#define ICE_AQ_VSI_FD_DEF_DROP BIT(15) +#define ICE_AQ_VSI_FD_REPORT_Q_S 0 +#define ICE_AQ_VSI_FD_REPORT_Q_M (0x7FF << ICE_AQ_VSI_FD_REPORT_Q_S) +#define ICE_AQ_VSI_FD_DEF_PRIORITY_S 12 +#define ICE_AQ_VSI_FD_DEF_PRIORITY_M (0x7 << ICE_AQ_VSI_FD_DEF_PRIORITY_S) +#define ICE_AQ_VSI_FD_DEF_DROP BIT(15) /* PASID section */ __le32 pasid_id; -#define ICE_AQ_VSI_PASID_ID_S 0 -#define ICE_AQ_VSI_PASID_ID_M (0xFFFFF << ICE_AQ_VSI_PASID_ID_S) -#define ICE_AQ_VSI_PASID_ID_VALID BIT(31) +#define ICE_AQ_VSI_PASID_ID_S 0 +#define ICE_AQ_VSI_PASID_ID_M (0xFFFFF << ICE_AQ_VSI_PASID_ID_S) +#define ICE_AQ_VSI_PASID_ID_VALID BIT(31) u8 reserved[24]; }; @@ -489,9 +537,13 @@ struct ice_aqc_add_get_recipe { struct ice_aqc_recipe_content { u8 rid; +#define ICE_AQ_RECIPE_ID_S 0 +#define ICE_AQ_RECIPE_ID_M (0x3F << ICE_AQ_RECIPE_ID_S) #define ICE_AQ_RECIPE_ID_IS_ROOT BIT(7) #define ICE_AQ_SW_ID_LKUP_IDX 0 u8 lkup_indx[5]; +#define ICE_AQ_RECIPE_LKUP_DATA_S 0 +#define ICE_AQ_RECIPE_LKUP_DATA_M (0x3F << ICE_AQ_RECIPE_LKUP_DATA_S) #define ICE_AQ_RECIPE_LKUP_IGNORE BIT(7) #define ICE_AQ_SW_ID_LKUP_MASK 0x00FF __le16 mask[5]; @@ -502,15 +554,25 @@ struct ice_aqc_recipe_content { u8 rsvd0[3]; u8 act_ctrl_join_priority; u8 act_ctrl_fwd_priority; +#define ICE_AQ_RECIPE_FWD_PRIORITY_S 0 +#define ICE_AQ_RECIPE_FWD_PRIORITY_M (0xF << ICE_AQ_RECIPE_FWD_PRIORITY_S) u8 act_ctrl; +#define ICE_AQ_RECIPE_ACT_NEED_PASS_L2 BIT(0) +#define ICE_AQ_RECIPE_ACT_ALLOW_PASS_L2 BIT(1) #define ICE_AQ_RECIPE_ACT_INV_ACT BIT(2) +#define ICE_AQ_RECIPE_ACT_PRUNE_INDX_S 4 +#define ICE_AQ_RECIPE_ACT_PRUNE_INDX_M (0x3 << ICE_AQ_RECIPE_ACT_PRUNE_INDX_S) u8 rsvd1; __le32 dflt_act; +#define ICE_AQ_RECIPE_DFLT_ACT_S 0 +#define ICE_AQ_RECIPE_DFLT_ACT_M (0x7FFFF << ICE_AQ_RECIPE_DFLT_ACT_S) +#define ICE_AQ_RECIPE_DFLT_ACT_VALID BIT(31) }; struct ice_aqc_recipe_data_elem { u8 recipe_indx; u8 resp_bits; +#define ICE_AQ_RECIPE_WAS_UPDATED BIT(0) u8 rsvd0[2]; u8 recipe_bitmap[8]; u8 rsvd1[4]; @@ -539,12 +601,30 @@ struct ice_aqc_sw_rules { __le32 addr_low; }; +/* Add switch rule response: + * Content of return buffer is same as the input buffer. The status field and + * LUT index are updated as part of the response + */ +struct ice_aqc_sw_rules_elem_hdr { + __le16 type; /* Switch rule type, one of T_... */ +#define ICE_AQC_SW_RULES_T_LKUP_RX 0x0 +#define ICE_AQC_SW_RULES_T_LKUP_TX 0x1 +#define ICE_AQC_SW_RULES_T_LG_ACT 0x2 +#define ICE_AQC_SW_RULES_T_VSI_LIST_SET 0x3 +#define ICE_AQC_SW_RULES_T_VSI_LIST_CLEAR 0x4 +#define ICE_AQC_SW_RULES_T_PRUNE_LIST_SET 0x5 +#define ICE_AQC_SW_RULES_T_PRUNE_LIST_CLEAR 0x6 + __le16 status; +} __packed __aligned(sizeof(__le16)); + /* Add/Update/Get/Remove lookup Rx/Tx command/response entry * This structures describes the lookup rules and associated actions. "index" * is returned as part of a response to a successful Add command, and can be * used to identify the rule for Update/Get/Remove commands. */ struct ice_sw_rule_lkup_rx_tx { + struct ice_aqc_sw_rules_elem_hdr hdr; + __le16 recipe_id; #define ICE_SW_RECIPE_LOGICAL_PORT_FWD 10 /* Source port for LOOKUP_RX and source VSI in case of LOOKUP_TX */ @@ -621,14 +701,16 @@ struct ice_sw_rule_lkup_rx_tx { * lookup-type */ __le16 hdr_len; - u8 hdr[]; -}; + u8 hdr_data[]; +} __packed __aligned(sizeof(__le16)); /* Add/Update/Remove large action command/response entry * "index" is returned as part of a response to a successful Add command, and * can be used to identify the action for Update/Get/Remove commands. */ struct ice_sw_rule_lg_act { + struct ice_aqc_sw_rules_elem_hdr hdr; + __le16 index; /* Index in large action table */ __le16 size; /* Max number of large actions */ @@ -682,45 +764,19 @@ struct ice_sw_rule_lg_act { #define ICE_LG_ACT_STAT_COUNT_S 3 #define ICE_LG_ACT_STAT_COUNT_M (0x7F << ICE_LG_ACT_STAT_COUNT_S) __le32 act[]; /* array of size for actions */ -}; +} __packed __aligned(sizeof(__le16)); /* Add/Update/Remove VSI list command/response entry * "index" is returned as part of a response to a successful Add command, and * can be used to identify the VSI list for Update/Get/Remove commands. */ struct ice_sw_rule_vsi_list { + struct ice_aqc_sw_rules_elem_hdr hdr; + __le16 index; /* Index of VSI/Prune list */ __le16 number_vsi; __le16 vsi[]; /* Array of number_vsi VSI numbers */ -}; - -/* Query VSI list command/response entry */ -struct ice_sw_rule_vsi_list_query { - __le16 index; - DECLARE_BITMAP(vsi_list, ICE_MAX_VSI); -} __packed; - -/* Add switch rule response: - * Content of return buffer is same as the input buffer. The status field and - * LUT index are updated as part of the response - */ -struct ice_aqc_sw_rules_elem { - __le16 type; /* Switch rule type, one of T_... */ -#define ICE_AQC_SW_RULES_T_LKUP_RX 0x0 -#define ICE_AQC_SW_RULES_T_LKUP_TX 0x1 -#define ICE_AQC_SW_RULES_T_LG_ACT 0x2 -#define ICE_AQC_SW_RULES_T_VSI_LIST_SET 0x3 -#define ICE_AQC_SW_RULES_T_VSI_LIST_CLEAR 0x4 -#define ICE_AQC_SW_RULES_T_PRUNE_LIST_SET 0x5 -#define ICE_AQC_SW_RULES_T_PRUNE_LIST_CLEAR 0x6 - __le16 status; - union { - struct ice_sw_rule_lkup_rx_tx lkup_tx_rx; - struct ice_sw_rule_lg_act lg_act; - struct ice_sw_rule_vsi_list vsi_list; - struct ice_sw_rule_vsi_list_query vsi_list_query; - } __packed pdata; -}; +} __packed __aligned(sizeof(__le16)); /* Query PFC Mode (direct 0x0302) * Set PFC Mode (direct 0x0303) @@ -1339,6 +1395,24 @@ struct ice_aqc_get_link_topo { u8 rsvd[9]; }; +/* Read/Write I2C (direct, 0x06E2/0x06E3) */ +struct ice_aqc_i2c { + struct ice_aqc_link_topo_addr topo_addr; + __le16 i2c_addr; + u8 i2c_params; +#define ICE_AQC_I2C_DATA_SIZE_M GENMASK(3, 0) +#define ICE_AQC_I2C_USE_REPEATED_START BIT(7) + + u8 rsvd; + __le16 i2c_bus_addr; + u8 i2c_data[4]; /* Used only by write command, reserved in read. */ +}; + +/* Read I2C Response (direct, 0x06E2) */ +struct ice_aqc_read_i2c_resp { + u8 i2c_data[16]; +}; + /* Set Port Identification LED (direct, 0x06E9) */ struct ice_aqc_set_port_id_led { u8 lport_num; @@ -1349,6 +1423,56 @@ struct ice_aqc_set_port_id_led { u8 rsvd[13]; }; +/* Get Port Options (indirect, 0x06EA) */ +struct ice_aqc_get_port_options { + u8 lport_num; + u8 lport_num_valid; + u8 port_options_count; +#define ICE_AQC_PORT_OPT_COUNT_M GENMASK(3, 0) +#define ICE_AQC_PORT_OPT_MAX 16 + + u8 innermost_phy_index; + u8 port_options; +#define ICE_AQC_PORT_OPT_ACTIVE_M GENMASK(3, 0) +#define ICE_AQC_PORT_OPT_VALID BIT(7) + + u8 pending_port_option_status; +#define ICE_AQC_PENDING_PORT_OPT_IDX_M GENMASK(3, 0) +#define ICE_AQC_PENDING_PORT_OPT_VALID BIT(7) + + u8 rsvd[2]; + __le32 addr_high; + __le32 addr_low; +}; + +struct ice_aqc_get_port_options_elem { + u8 pmd; +#define ICE_AQC_PORT_OPT_PMD_COUNT_M GENMASK(3, 0) + + u8 max_lane_speed; +#define ICE_AQC_PORT_OPT_MAX_LANE_M GENMASK(3, 0) +#define ICE_AQC_PORT_OPT_MAX_LANE_100M 0 +#define ICE_AQC_PORT_OPT_MAX_LANE_1G 1 +#define ICE_AQC_PORT_OPT_MAX_LANE_2500M 2 +#define ICE_AQC_PORT_OPT_MAX_LANE_5G 3 +#define ICE_AQC_PORT_OPT_MAX_LANE_10G 4 +#define ICE_AQC_PORT_OPT_MAX_LANE_25G 5 +#define ICE_AQC_PORT_OPT_MAX_LANE_50G 6 +#define ICE_AQC_PORT_OPT_MAX_LANE_100G 7 + + u8 global_scid[2]; + u8 phy_scid[2]; + u8 pf2port_cid[2]; +}; + +/* Set Port Option (direct, 0x06EB) */ +struct ice_aqc_set_port_option { + u8 lport_num; + u8 lport_num_valid; + u8 selected_port_option; + u8 rsvd[13]; +}; + /* Set/Get GPIO (direct, 0x06EC/0x06ED) */ struct ice_aqc_gpio { __le16 gpio_ctrl_handle; @@ -1415,6 +1539,12 @@ struct ice_aqc_nvm { #define ICE_AQC_NVM_PERST_FLAG 1 #define ICE_AQC_NVM_EMPR_FLAG 2 #define ICE_AQC_NVM_EMPR_ENA BIT(0) /* Write Activate reply only */ + /* For Write Activate, several flags are sent as part of a separate + * flags2 field using a separate byte. For simplicity of the software + * interface, we pass the flags as a 16 bit value so these flags are + * all offset by 8 bits + */ +#define ICE_AQC_NVM_ACTIV_REQ_EMPR BIT(8) /* NVM Write Activate only */ __le16 module_typeid; __le16 length; #define ICE_AQC_NVM_ERASE_LEN 0xFFFF @@ -1883,7 +2013,7 @@ struct ice_aqc_get_clear_fw_log { }; /* Download Package (indirect 0x0C40) */ -/* Also used for Update Package (indirect 0x0C42) */ +/* Also used for Update Package (indirect 0x0C41 and 0x0C42) */ struct ice_aqc_download_pkg { u8 flags; #define ICE_AQC_DOWNLOAD_PKG_LAST_BUF 0x01 @@ -2008,7 +2138,10 @@ struct ice_aq_desc { 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; + struct ice_aqc_get_port_options get_port_options; + struct ice_aqc_set_port_option set_port_option; struct ice_aqc_get_sw_cfg get_sw_conf; + struct ice_aqc_set_port_params set_port_params; struct ice_aqc_sw_rules sw_rules; struct ice_aqc_add_get_recipe add_get_recipe; struct ice_aqc_recipe_to_profile recipe_to_profile; @@ -2049,6 +2182,8 @@ struct ice_aq_desc { struct ice_aqc_get_link_status get_link_status; struct ice_aqc_event_lan_overflow lan_overflow; struct ice_aqc_get_link_topo get_link_topo; + struct ice_aqc_i2c read_write_i2c; + struct ice_aqc_read_i2c_resp read_i2c_resp; } params; }; @@ -2110,10 +2245,13 @@ enum ice_adminq_opc { /* internal switch commands */ ice_aqc_opc_get_sw_cfg = 0x0200, + ice_aqc_opc_set_port_params = 0x0203, /* Alloc/Free/Get Resources */ ice_aqc_opc_alloc_res = 0x0208, ice_aqc_opc_free_res = 0x0209, + ice_aqc_opc_set_vlan_mode_parameters = 0x020C, + ice_aqc_opc_get_vlan_mode_parameters = 0x020D, /* VSI commands */ ice_aqc_opc_add_vsi = 0x0210, @@ -2160,7 +2298,11 @@ enum ice_adminq_opc { ice_aqc_opc_set_event_mask = 0x0613, ice_aqc_opc_set_mac_lb = 0x0620, ice_aqc_opc_get_link_topo = 0x06E0, + ice_aqc_opc_read_i2c = 0x06E2, + ice_aqc_opc_write_i2c = 0x06E3, ice_aqc_opc_set_port_id_led = 0x06E9, + ice_aqc_opc_get_port_options = 0x06EA, + ice_aqc_opc_set_port_option = 0x06EB, ice_aqc_opc_set_gpio = 0x06EC, ice_aqc_opc_get_gpio = 0x06ED, ice_aqc_opc_sff_eeprom = 0x06EE, @@ -2204,6 +2346,7 @@ enum ice_adminq_opc { /* package commands */ ice_aqc_opc_download_pkg = 0x0C40, + ice_aqc_opc_upload_section = 0x0C41, ice_aqc_opc_update_pkg = 0x0C42, ice_aqc_opc_get_pkg_info_list = 0x0C43, diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c index 5daade32ea62..fba178e07600 100644 --- a/drivers/net/ethernet/intel/ice/ice_arfs.c +++ b/drivers/net/ethernet/intel/ice/ice_arfs.c @@ -577,7 +577,7 @@ void ice_free_cpu_rx_rmap(struct ice_vsi *vsi) { struct net_device *netdev; - if (!vsi || vsi->type != ICE_VSI_PF || !vsi->arfs_fltr_list) + if (!vsi || vsi->type != ICE_VSI_PF) return; netdev = vsi->netdev; @@ -599,7 +599,7 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi) int base_idx, i; if (!vsi || vsi->type != ICE_VSI_PF) - return -EINVAL; + return 0; pf = vsi->back; netdev = vsi->netdev; @@ -636,7 +636,6 @@ void ice_remove_arfs(struct ice_pf *pf) if (!pf_vsi) return; - ice_free_cpu_rx_rmap(pf_vsi); ice_clear_arfs(pf_vsi); } @@ -653,9 +652,5 @@ void ice_rebuild_arfs(struct ice_pf *pf) return; ice_remove_arfs(pf); - if (ice_set_cpu_rx_rmap(pf_vsi)) { - dev_err(ice_pf_to_dev(pf), "Failed to rebuild aRFS\n"); - return; - } ice_init_arfs(pf_vsi); } diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.h b/drivers/net/ethernet/intel/ice/ice_arfs.h index 80ed76f0cace..9669ad9bf7b5 100644 --- a/drivers/net/ethernet/intel/ice/ice_arfs.h +++ b/drivers/net/ethernet/intel/ice/ice_arfs.h @@ -3,6 +3,9 @@ #ifndef _ICE_ARFS_H_ #define _ICE_ARFS_H_ + +#include "ice_fdir.h" + enum ice_arfs_fltr_state { ICE_ARFS_INACTIVE, ICE_ARFS_ACTIVE, diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 1a5ece3bce79..e864634d66bc 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -5,18 +5,7 @@ #include "ice_base.h" #include "ice_lib.h" #include "ice_dcb_lib.h" - -static bool ice_alloc_rx_buf_zc(struct ice_rx_ring *rx_ring) -{ - rx_ring->xdp_buf = kcalloc(rx_ring->count, sizeof(*rx_ring->xdp_buf), GFP_KERNEL); - return !!rx_ring->xdp_buf; -} - -static bool ice_alloc_rx_buf(struct ice_rx_ring *rx_ring) -{ - rx_ring->rx_buf = kcalloc(rx_ring->count, sizeof(*rx_ring->rx_buf), GFP_KERNEL); - return !!rx_ring->rx_buf; -} +#include "ice_sriov.h" /** * __ice_vsi_get_qs_contig - Assign a contiguous chunk of queues to VSI @@ -141,8 +130,7 @@ static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, u16 v_idx) * handler here (i.e. resume, reset/rebuild, etc.) */ if (vsi->netdev) - netif_napi_add(vsi->netdev, &q_vector->napi, ice_napi_poll, - NAPI_POLL_WEIGHT); + netif_napi_add(vsi->netdev, &q_vector->napi, ice_napi_poll); out: /* tie q_vector and VSI together */ @@ -322,7 +310,7 @@ ice_setup_tx_ctx(struct ice_tx_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf break; case ICE_VSI_VF: /* Firmware expects vmvf_num to be absolute VF ID */ - tlan_ctx->vmvf_num = hw->func_caps.vf_base_id + vsi->vf_id; + tlan_ctx->vmvf_num = hw->func_caps.vf_base_id + vsi->vf->vf_id; tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_VF; break; case ICE_VSI_SWITCHDEV_CTRL: @@ -416,10 +404,24 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) /* Strip the Ethernet CRC bytes before the packet is posted to host * memory. */ - rlan_ctx.crcstrip = 1; - - /* L2TSEL flag defines the reported L2 Tags in the receive descriptor */ - rlan_ctx.l2tsel = 1; + rlan_ctx.crcstrip = !(ring->flags & ICE_RX_FLAGS_CRC_STRIP_DIS); + + /* L2TSEL flag defines the reported L2 Tags in the receive descriptor + * and it needs to remain 1 for non-DVM capable configurations to not + * break backward compatibility for VF drivers. Setting this field to 0 + * will cause the single/outer VLAN tag to be stripped to the L2TAG2_2ND + * field in the Rx descriptor. Setting it to 1 allows the VLAN tag to + * be stripped in L2TAG1 of the Rx descriptor, which is where VFs will + * check for the tag + */ + if (ice_is_dvm_ena(hw)) + if (vsi->type == ICE_VSI_VF && + ice_vf_is_port_vlan_ena(vsi->vf)) + rlan_ctx.l2tsel = 1; + else + rlan_ctx.l2tsel = 0; + else + rlan_ctx.l2tsel = 1; rlan_ctx.dtype = ICE_RX_DTYPE_NO_SPLIT; rlan_ctx.hsplit_0 = ICE_RLAN_RX_HSPLIT_0_NO_SPLIT; @@ -504,11 +506,8 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, ring->q_index, ring->q_vector->napi.napi_id); - kfree(ring->rx_buf); ring->xsk_pool = ice_xsk_pool(ring); if (ring->xsk_pool) { - if (!ice_alloc_rx_buf_zc(ring)) - return -ENOMEM; xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); ring->rx_buf_len = @@ -523,8 +522,6 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n", ring->q_index); } else { - if (!ice_alloc_rx_buf(ring)) - return -ENOMEM; if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) /* coverity[check_return] */ xdp_rxq_info_reg(&ring->xdp_rxq, @@ -961,7 +958,7 @@ ice_vsi_stop_tx_ring(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, * associated to the queue to schedule NAPI handler */ q_vector = ring->q_vector; - if (q_vector) + if (q_vector && !(vsi->vf && ice_is_vf_disabled(vsi->vf))) ice_trigger_sw_intr(hw, q_vector); status = ice_dis_vsi_txq(vsi->port_info, txq_meta->vsi_idx, diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 408d15a5b0e3..039342a0ed15 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -8,6 +8,108 @@ #define ICE_PF_RESET_WAIT_COUNT 300 +static const char * const ice_link_mode_str_low[] = { + [0] = "100BASE_TX", + [1] = "100M_SGMII", + [2] = "1000BASE_T", + [3] = "1000BASE_SX", + [4] = "1000BASE_LX", + [5] = "1000BASE_KX", + [6] = "1G_SGMII", + [7] = "2500BASE_T", + [8] = "2500BASE_X", + [9] = "2500BASE_KX", + [10] = "5GBASE_T", + [11] = "5GBASE_KR", + [12] = "10GBASE_T", + [13] = "10G_SFI_DA", + [14] = "10GBASE_SR", + [15] = "10GBASE_LR", + [16] = "10GBASE_KR_CR1", + [17] = "10G_SFI_AOC_ACC", + [18] = "10G_SFI_C2C", + [19] = "25GBASE_T", + [20] = "25GBASE_CR", + [21] = "25GBASE_CR_S", + [22] = "25GBASE_CR1", + [23] = "25GBASE_SR", + [24] = "25GBASE_LR", + [25] = "25GBASE_KR", + [26] = "25GBASE_KR_S", + [27] = "25GBASE_KR1", + [28] = "25G_AUI_AOC_ACC", + [29] = "25G_AUI_C2C", + [30] = "40GBASE_CR4", + [31] = "40GBASE_SR4", + [32] = "40GBASE_LR4", + [33] = "40GBASE_KR4", + [34] = "40G_XLAUI_AOC_ACC", + [35] = "40G_XLAUI", + [36] = "50GBASE_CR2", + [37] = "50GBASE_SR2", + [38] = "50GBASE_LR2", + [39] = "50GBASE_KR2", + [40] = "50G_LAUI2_AOC_ACC", + [41] = "50G_LAUI2", + [42] = "50G_AUI2_AOC_ACC", + [43] = "50G_AUI2", + [44] = "50GBASE_CP", + [45] = "50GBASE_SR", + [46] = "50GBASE_FR", + [47] = "50GBASE_LR", + [48] = "50GBASE_KR_PAM4", + [49] = "50G_AUI1_AOC_ACC", + [50] = "50G_AUI1", + [51] = "100GBASE_CR4", + [52] = "100GBASE_SR4", + [53] = "100GBASE_LR4", + [54] = "100GBASE_KR4", + [55] = "100G_CAUI4_AOC_ACC", + [56] = "100G_CAUI4", + [57] = "100G_AUI4_AOC_ACC", + [58] = "100G_AUI4", + [59] = "100GBASE_CR_PAM4", + [60] = "100GBASE_KR_PAM4", + [61] = "100GBASE_CP2", + [62] = "100GBASE_SR2", + [63] = "100GBASE_DR", +}; + +static const char * const ice_link_mode_str_high[] = { + [0] = "100GBASE_KR2_PAM4", + [1] = "100G_CAUI2_AOC_ACC", + [2] = "100G_CAUI2", + [3] = "100G_AUI2_AOC_ACC", + [4] = "100G_AUI2", +}; + +/** + * ice_dump_phy_type - helper function to dump phy_type + * @hw: pointer to the HW structure + * @low: 64 bit value for phy_type_low + * @high: 64 bit value for phy_type_high + * @prefix: prefix string to differentiate multiple dumps + */ +static void +ice_dump_phy_type(struct ice_hw *hw, u64 low, u64 high, const char *prefix) +{ + ice_debug(hw, ICE_DBG_PHY, "%s: phy_type_low: 0x%016llx\n", prefix, low); + + for (u32 i = 0; i < BITS_PER_TYPE(typeof(low)); i++) { + if (low & BIT_ULL(i)) + ice_debug(hw, ICE_DBG_PHY, "%s: bit(%d): %s\n", + prefix, i, ice_link_mode_str_low[i]); + } + + ice_debug(hw, ICE_DBG_PHY, "%s: phy_type_high: 0x%016llx\n", prefix, high); + + for (u32 i = 0; i < BITS_PER_TYPE(typeof(high)); i++) { + if (high & BIT_ULL(i)) + ice_debug(hw, ICE_DBG_PHY, "%s: bit(%d): %s\n", + prefix, i, ice_link_mode_str_high[i]); + } +} + /** * ice_set_mac_type - Sets MAC type * @hw: pointer to the HW structure @@ -80,9 +182,23 @@ bool ice_is_e810t(struct ice_hw *hw) { switch (hw->device_id) { case ICE_DEV_ID_E810C_SFP: - if (hw->subsystem_device_id == ICE_SUBDEV_ID_E810T || - hw->subsystem_device_id == ICE_SUBDEV_ID_E810T2) + switch (hw->subsystem_device_id) { + case ICE_SUBDEV_ID_E810T: + case ICE_SUBDEV_ID_E810T2: + case ICE_SUBDEV_ID_E810T3: + case ICE_SUBDEV_ID_E810T4: + case ICE_SUBDEV_ID_E810T6: + case ICE_SUBDEV_ID_E810T7: return true; + } + break; + case ICE_DEV_ID_E810C_QSFP: + switch (hw->subsystem_device_id) { + case ICE_SUBDEV_ID_E810T2: + case ICE_SUBDEV_ID_E810T3: + case ICE_SUBDEV_ID_E810T5: + return true; + } break; default: break; @@ -183,6 +299,7 @@ ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode, struct ice_aqc_get_phy_caps *cmd; u16 pcaps_size = sizeof(*pcaps); struct ice_aq_desc desc; + const char *prefix; struct ice_hw *hw; int status; @@ -204,29 +321,48 @@ ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode, cmd->param0 |= cpu_to_le16(report_mode); status = ice_aq_send_cmd(hw, &desc, pcaps, pcaps_size, cd); - ice_debug(hw, ICE_DBG_LINK, "get phy caps - report_mode = 0x%x\n", - report_mode); - ice_debug(hw, ICE_DBG_LINK, " phy_type_low = 0x%llx\n", - (unsigned long long)le64_to_cpu(pcaps->phy_type_low)); - ice_debug(hw, ICE_DBG_LINK, " phy_type_high = 0x%llx\n", - (unsigned long long)le64_to_cpu(pcaps->phy_type_high)); - ice_debug(hw, ICE_DBG_LINK, " caps = 0x%x\n", pcaps->caps); - ice_debug(hw, ICE_DBG_LINK, " low_power_ctrl_an = 0x%x\n", + ice_debug(hw, ICE_DBG_LINK, "get phy caps dump\n"); + + switch (report_mode) { + case ICE_AQC_REPORT_TOPO_CAP_MEDIA: + prefix = "phy_caps_media"; + break; + case ICE_AQC_REPORT_TOPO_CAP_NO_MEDIA: + prefix = "phy_caps_no_media"; + break; + case ICE_AQC_REPORT_ACTIVE_CFG: + prefix = "phy_caps_active"; + break; + case ICE_AQC_REPORT_DFLT_CFG: + prefix = "phy_caps_default"; + break; + default: + prefix = "phy_caps_invalid"; + } + + ice_dump_phy_type(hw, le64_to_cpu(pcaps->phy_type_low), + le64_to_cpu(pcaps->phy_type_high), prefix); + + ice_debug(hw, ICE_DBG_LINK, "%s: report_mode = 0x%x\n", + prefix, report_mode); + ice_debug(hw, ICE_DBG_LINK, "%s: caps = 0x%x\n", prefix, pcaps->caps); + ice_debug(hw, ICE_DBG_LINK, "%s: low_power_ctrl_an = 0x%x\n", prefix, pcaps->low_power_ctrl_an); - ice_debug(hw, ICE_DBG_LINK, " eee_cap = 0x%x\n", pcaps->eee_cap); - ice_debug(hw, ICE_DBG_LINK, " eeer_value = 0x%x\n", + ice_debug(hw, ICE_DBG_LINK, "%s: eee_cap = 0x%x\n", prefix, + pcaps->eee_cap); + ice_debug(hw, ICE_DBG_LINK, "%s: eeer_value = 0x%x\n", prefix, pcaps->eeer_value); - ice_debug(hw, ICE_DBG_LINK, " link_fec_options = 0x%x\n", + ice_debug(hw, ICE_DBG_LINK, "%s: link_fec_options = 0x%x\n", prefix, pcaps->link_fec_options); - ice_debug(hw, ICE_DBG_LINK, " module_compliance_enforcement = 0x%x\n", - pcaps->module_compliance_enforcement); - ice_debug(hw, ICE_DBG_LINK, " extended_compliance_code = 0x%x\n", - pcaps->extended_compliance_code); - ice_debug(hw, ICE_DBG_LINK, " module_type[0] = 0x%x\n", + ice_debug(hw, ICE_DBG_LINK, "%s: module_compliance_enforcement = 0x%x\n", + prefix, pcaps->module_compliance_enforcement); + ice_debug(hw, ICE_DBG_LINK, "%s: extended_compliance_code = 0x%x\n", + prefix, pcaps->extended_compliance_code); + ice_debug(hw, ICE_DBG_LINK, "%s: module_type[0] = 0x%x\n", prefix, pcaps->module_type[0]); - ice_debug(hw, ICE_DBG_LINK, " module_type[1] = 0x%x\n", + ice_debug(hw, ICE_DBG_LINK, "%s: module_type[1] = 0x%x\n", prefix, pcaps->module_type[1]); - ice_debug(hw, ICE_DBG_LINK, " module_type[2] = 0x%x\n", + ice_debug(hw, ICE_DBG_LINK, "%s: module_type[2] = 0x%x\n", prefix, pcaps->module_type[2]); if (!status && report_mode == ICE_AQC_REPORT_TOPO_CAP_MEDIA) { @@ -1518,16 +1654,27 @@ ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf, /* When a package download is in process (i.e. when the firmware's * Global Configuration Lock resource is held), only the Download - * Package, Get Version, Get Package Info List and Release Resource - * (with resource ID set to Global Config Lock) AdminQ commands are - * allowed; all others must block until the package download completes - * and the Global Config Lock is released. See also - * ice_acquire_global_cfg_lock(). + * Package, Get Version, Get Package Info List, Upload Section, + * Update Package, Set Port Parameters, Get/Set VLAN Mode Parameters, + * Add Recipe, Set Recipes to Profile Association, Get Recipe, and Get + * Recipes to Profile Association, and Release Resource (with resource + * ID set to Global Config Lock) AdminQ commands are allowed; all others + * must block until the package download completes and the Global Config + * Lock is released. See also ice_acquire_global_cfg_lock(). */ switch (le16_to_cpu(desc->opcode)) { case ice_aqc_opc_download_pkg: case ice_aqc_opc_get_pkg_info_list: case ice_aqc_opc_get_ver: + case ice_aqc_opc_upload_section: + case ice_aqc_opc_update_pkg: + case ice_aqc_opc_set_port_params: + case ice_aqc_opc_get_vlan_mode_parameters: + case ice_aqc_opc_set_vlan_mode_parameters: + case ice_aqc_opc_add_recipe: + case ice_aqc_opc_recipe_to_profile: + case ice_aqc_opc_get_recipe: + case ice_aqc_opc_get_recipe_to_profile: break; case ice_aqc_opc_release_res: if (le16_to_cpu(cmd->res_id) == ICE_AQC_RES_ID_GLBL_LOCK) @@ -2386,6 +2533,8 @@ ice_parse_1588_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, info->tmr1_owned = ((number & ICE_TS_TMR1_OWND_M) != 0); info->tmr1_ena = ((number & ICE_TS_TMR1_ENA_M) != 0); + info->ts_ll_read = ((number & ICE_TS_LL_TX_TS_READ_M) != 0); + info->ena_ports = logical_id; info->tmr_own_map = phys_id; @@ -2403,6 +2552,8 @@ ice_parse_1588_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, info->tmr1_owned); ice_debug(hw, ICE_DBG_INIT, "dev caps: tmr1_ena = %u\n", info->tmr1_ena); + ice_debug(hw, ICE_DBG_INIT, "dev caps: ts_ll_read = %u\n", + info->ts_ll_read); ice_debug(hw, ICE_DBG_INIT, "dev caps: ieee_1588 ena_ports = %u\n", info->ena_ports); ice_debug(hw, ICE_DBG_INIT, "dev caps: tmr_own_map = %u\n", @@ -2737,6 +2888,54 @@ void ice_clear_pxe_mode(struct ice_hw *hw) } /** + * ice_aq_set_port_params - set physical port parameters. + * @pi: pointer to the port info struct + * @double_vlan: if set double VLAN is enabled + * @cd: pointer to command details structure or NULL + * + * Set Physical port parameters (0x0203) + */ +int +ice_aq_set_port_params(struct ice_port_info *pi, bool double_vlan, + struct ice_sq_cd *cd) + +{ + struct ice_aqc_set_port_params *cmd; + struct ice_hw *hw = pi->hw; + struct ice_aq_desc desc; + u16 cmd_flags = 0; + + cmd = &desc.params.set_port_params; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_port_params); + if (double_vlan) + cmd_flags |= ICE_AQC_SET_P_PARAMS_DOUBLE_VLAN_ENA; + cmd->cmd_flags = cpu_to_le16(cmd_flags); + + return ice_aq_send_cmd(hw, &desc, NULL, 0, cd); +} + +/** + * ice_is_100m_speed_supported + * @hw: pointer to the HW struct + * + * returns true if 100M speeds are supported by the device, + * false otherwise. + */ +bool ice_is_100m_speed_supported(struct ice_hw *hw) +{ + switch (hw->device_id) { + case ICE_DEV_ID_E822C_SGMII: + case ICE_DEV_ID_E822L_SGMII: + case ICE_DEV_ID_E823L_1GBE: + case ICE_DEV_ID_E823C_SGMII: + return true; + default: + return false; + } +} + +/** * ice_get_link_speed_based_on_phy_type - returns link speed * @phy_type_low: lower part of phy_type * @phy_type_high: higher part of phy_type @@ -3340,9 +3539,10 @@ ice_cfg_phy_fec(struct ice_port_info *pi, struct ice_aqc_set_phy_cfg_data *cfg, if (fec == ICE_FEC_AUTO && ice_fw_supports_link_override(hw) && !ice_fw_supports_report_dflt_cfg(hw)) { - struct ice_link_default_override_tlv tlv; + struct ice_link_default_override_tlv tlv = { 0 }; - if (ice_get_link_default_override(&tlv, pi)) + status = ice_get_link_default_override(&tlv, pi); + if (status) goto out; if (!(tlv.options & ICE_LINK_OVERRIDE_STRICT_MODE) && @@ -3495,6 +3695,121 @@ ice_aq_set_port_id_led(struct ice_port_info *pi, bool is_orig_mode, } /** + * ice_aq_get_port_options + * @hw: pointer to the HW struct + * @options: buffer for the resultant port options + * @option_count: input - size of the buffer in port options structures, + * output - number of returned port options + * @lport: logical port to call the command with (optional) + * @lport_valid: when false, FW uses port owned by the PF instead of lport, + * when PF owns more than 1 port it must be true + * @active_option_idx: index of active port option in returned buffer + * @active_option_valid: active option in returned buffer is valid + * @pending_option_idx: index of pending port option in returned buffer + * @pending_option_valid: pending option in returned buffer is valid + * + * Calls Get Port Options AQC (0x06ea) and verifies result. + */ +int +ice_aq_get_port_options(struct ice_hw *hw, + struct ice_aqc_get_port_options_elem *options, + u8 *option_count, u8 lport, bool lport_valid, + u8 *active_option_idx, bool *active_option_valid, + u8 *pending_option_idx, bool *pending_option_valid) +{ + struct ice_aqc_get_port_options *cmd; + struct ice_aq_desc desc; + int status; + u8 i; + + /* options buffer shall be able to hold max returned options */ + if (*option_count < ICE_AQC_PORT_OPT_COUNT_M) + return -EINVAL; + + cmd = &desc.params.get_port_options; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_port_options); + + if (lport_valid) + cmd->lport_num = lport; + cmd->lport_num_valid = lport_valid; + + status = ice_aq_send_cmd(hw, &desc, options, + *option_count * sizeof(*options), NULL); + if (status) + return status; + + /* verify direct FW response & set output parameters */ + *option_count = FIELD_GET(ICE_AQC_PORT_OPT_COUNT_M, + cmd->port_options_count); + ice_debug(hw, ICE_DBG_PHY, "options: %x\n", *option_count); + *active_option_valid = FIELD_GET(ICE_AQC_PORT_OPT_VALID, + cmd->port_options); + if (*active_option_valid) { + *active_option_idx = FIELD_GET(ICE_AQC_PORT_OPT_ACTIVE_M, + cmd->port_options); + if (*active_option_idx > (*option_count - 1)) + return -EIO; + ice_debug(hw, ICE_DBG_PHY, "active idx: %x\n", + *active_option_idx); + } + + *pending_option_valid = FIELD_GET(ICE_AQC_PENDING_PORT_OPT_VALID, + cmd->pending_port_option_status); + if (*pending_option_valid) { + *pending_option_idx = FIELD_GET(ICE_AQC_PENDING_PORT_OPT_IDX_M, + cmd->pending_port_option_status); + if (*pending_option_idx > (*option_count - 1)) + return -EIO; + ice_debug(hw, ICE_DBG_PHY, "pending idx: %x\n", + *pending_option_idx); + } + + /* mask output options fields */ + for (i = 0; i < *option_count; i++) { + options[i].pmd = FIELD_GET(ICE_AQC_PORT_OPT_PMD_COUNT_M, + options[i].pmd); + options[i].max_lane_speed = FIELD_GET(ICE_AQC_PORT_OPT_MAX_LANE_M, + options[i].max_lane_speed); + ice_debug(hw, ICE_DBG_PHY, "pmds: %x max speed: %x\n", + options[i].pmd, options[i].max_lane_speed); + } + + return 0; +} + +/** + * ice_aq_set_port_option + * @hw: pointer to the HW struct + * @lport: logical port to call the command with + * @lport_valid: when false, FW uses port owned by the PF instead of lport, + * when PF owns more than 1 port it must be true + * @new_option: new port option to be written + * + * Calls Set Port Options AQC (0x06eb). + */ +int +ice_aq_set_port_option(struct ice_hw *hw, u8 lport, u8 lport_valid, + u8 new_option) +{ + struct ice_aqc_set_port_option *cmd; + struct ice_aq_desc desc; + + if (new_option > ICE_AQC_PORT_OPT_COUNT_M) + return -EINVAL; + + cmd = &desc.params.set_port_option; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_port_option); + + if (lport_valid) + cmd->lport_num = lport; + + cmd->lport_num_valid = lport_valid; + cmd->selected_port_option = new_option; + + return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); +} + +/** * ice_aq_sff_eeprom * @hw: pointer to the HW struct * @lport: bits [7:0] = logical port, bit [8] = logical port valid @@ -4758,6 +5073,104 @@ ice_sched_query_elem(struct ice_hw *hw, u32 node_teid, } /** + * ice_aq_read_i2c + * @hw: pointer to the hw struct + * @topo_addr: topology address for a device to communicate with + * @bus_addr: 7-bit I2C bus address + * @addr: I2C memory address (I2C offset) with up to 16 bits + * @params: I2C parameters: bit [7] - Repeated start, + * bits [6:5] data offset size, + * bit [4] - I2C address type, + * bits [3:0] - data size to read (0-16 bytes) + * @data: pointer to data (0 to 16 bytes) to be read from the I2C device + * @cd: pointer to command details structure or NULL + * + * Read I2C (0x06E2) + */ +int +ice_aq_read_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr, + u16 bus_addr, __le16 addr, u8 params, u8 *data, + struct ice_sq_cd *cd) +{ + struct ice_aq_desc desc = { 0 }; + struct ice_aqc_i2c *cmd; + u8 data_size; + int status; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_read_i2c); + cmd = &desc.params.read_write_i2c; + + if (!data) + return -EINVAL; + + data_size = FIELD_GET(ICE_AQC_I2C_DATA_SIZE_M, params); + + cmd->i2c_bus_addr = cpu_to_le16(bus_addr); + cmd->topo_addr = topo_addr; + cmd->i2c_params = params; + cmd->i2c_addr = addr; + + status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd); + if (!status) { + struct ice_aqc_read_i2c_resp *resp; + u8 i; + + resp = &desc.params.read_i2c_resp; + for (i = 0; i < data_size; i++) { + *data = resp->i2c_data[i]; + data++; + } + } + + return status; +} + +/** + * ice_aq_write_i2c + * @hw: pointer to the hw struct + * @topo_addr: topology address for a device to communicate with + * @bus_addr: 7-bit I2C bus address + * @addr: I2C memory address (I2C offset) with up to 16 bits + * @params: I2C parameters: bit [4] - I2C address type, bits [3:0] - data size to write (0-7 bytes) + * @data: pointer to data (0 to 4 bytes) to be written to the I2C device + * @cd: pointer to command details structure or NULL + * + * Write I2C (0x06E3) + * + * * Return: + * * 0 - Successful write to the i2c device + * * -EINVAL - Data size greater than 4 bytes + * * -EIO - FW error + */ +int +ice_aq_write_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr, + u16 bus_addr, __le16 addr, u8 params, u8 *data, + struct ice_sq_cd *cd) +{ + struct ice_aq_desc desc = { 0 }; + struct ice_aqc_i2c *cmd; + u8 data_size; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_write_i2c); + cmd = &desc.params.read_write_i2c; + + data_size = FIELD_GET(ICE_AQC_I2C_DATA_SIZE_M, params); + + /* data_size limited to 4 */ + if (data_size > 4) + return -EINVAL; + + cmd->i2c_bus_addr = cpu_to_le16(bus_addr); + cmd->topo_addr = topo_addr; + cmd->i2c_params = params; + cmd->i2c_addr = addr; + + memcpy(cmd->i2c_data, data, data_size); + + return ice_aq_send_cmd(hw, &desc, NULL, 0, cd); +} + +/** * ice_aq_set_driver_param - Set driver parameter to share via firmware * @hw: pointer to the HW struct * @idx: parameter index to set @@ -4891,20 +5304,22 @@ ice_aq_get_gpio(struct ice_hw *hw, u16 gpio_ctrl_handle, u8 pin_idx, } /** - * ice_fw_supports_link_override + * ice_is_fw_api_min_ver * @hw: pointer to the hardware structure + * @maj: major version + * @min: minor version + * @patch: patch version * - * Checks if the firmware supports link override + * Checks if the firmware API is minimum version */ -bool ice_fw_supports_link_override(struct ice_hw *hw) +static bool ice_is_fw_api_min_ver(struct ice_hw *hw, u8 maj, u8 min, u8 patch) { - if (hw->api_maj_ver == ICE_FW_API_LINK_OVERRIDE_MAJ) { - if (hw->api_min_ver > ICE_FW_API_LINK_OVERRIDE_MIN) + if (hw->api_maj_ver == maj) { + if (hw->api_min_ver > min) return true; - if (hw->api_min_ver == ICE_FW_API_LINK_OVERRIDE_MIN && - hw->api_patch >= ICE_FW_API_LINK_OVERRIDE_PATCH) + if (hw->api_min_ver == min && hw->api_patch >= patch) return true; - } else if (hw->api_maj_ver > ICE_FW_API_LINK_OVERRIDE_MAJ) { + } else if (hw->api_maj_ver > maj) { return true; } @@ -4912,6 +5327,19 @@ bool ice_fw_supports_link_override(struct ice_hw *hw) } /** + * ice_fw_supports_link_override + * @hw: pointer to the hardware structure + * + * Checks if the firmware supports link override + */ +bool ice_fw_supports_link_override(struct ice_hw *hw) +{ + return ice_is_fw_api_min_ver(hw, ICE_FW_API_LINK_OVERRIDE_MAJ, + ICE_FW_API_LINK_OVERRIDE_MIN, + ICE_FW_API_LINK_OVERRIDE_PATCH); +} + +/** * ice_get_link_default_override * @ldo: pointer to the link default override struct * @pi: pointer to the port info struct @@ -5041,16 +5469,9 @@ bool ice_fw_supports_lldp_fltr_ctrl(struct ice_hw *hw) if (hw->mac_type != ICE_MAC_E810) return false; - if (hw->api_maj_ver == ICE_FW_API_LLDP_FLTR_MAJ) { - if (hw->api_min_ver > ICE_FW_API_LLDP_FLTR_MIN) - return true; - if (hw->api_min_ver == ICE_FW_API_LLDP_FLTR_MIN && - hw->api_patch >= ICE_FW_API_LLDP_FLTR_PATCH) - return true; - } else if (hw->api_maj_ver > ICE_FW_API_LLDP_FLTR_MAJ) { - return true; - } - return false; + return ice_is_fw_api_min_ver(hw, ICE_FW_API_LLDP_FLTR_MAJ, + ICE_FW_API_LLDP_FLTR_MIN, + ICE_FW_API_LLDP_FLTR_PATCH); } /** @@ -5087,14 +5508,7 @@ ice_lldp_fltr_add_remove(struct ice_hw *hw, u16 vsi_num, bool add) */ bool ice_fw_supports_report_dflt_cfg(struct ice_hw *hw) { - if (hw->api_maj_ver == ICE_FW_API_REPORT_DFLT_CFG_MAJ) { - if (hw->api_min_ver > ICE_FW_API_REPORT_DFLT_CFG_MIN) - return true; - if (hw->api_min_ver == ICE_FW_API_REPORT_DFLT_CFG_MIN && - hw->api_patch >= ICE_FW_API_REPORT_DFLT_CFG_PATCH) - return true; - } else if (hw->api_maj_ver > ICE_FW_API_REPORT_DFLT_CFG_MAJ) { - return true; - } - return false; + return ice_is_fw_api_min_ver(hw, ICE_FW_API_REPORT_DFLT_CFG_MAJ, + ICE_FW_API_REPORT_DFLT_CFG_MIN, + ICE_FW_API_REPORT_DFLT_CFG_PATCH); } diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 1c57097ddf0b..8b6712b92e84 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -4,12 +4,14 @@ #ifndef _ICE_COMMON_H_ #define _ICE_COMMON_H_ -#include "ice.h" +#include <linux/bitfield.h> + #include "ice_type.h" #include "ice_nvm.h" #include "ice_flex_pipe.h" -#include "ice_switch.h" #include <linux/avf/virtchnl.h> +#include "ice_switch.h" +#include "ice_fdir.h" #define ICE_SQ_SEND_DELAY_TIME_MS 10 #define ICE_SQ_SEND_MAX_EXECUTE 3 @@ -85,6 +87,9 @@ int ice_aq_send_driver_ver(struct ice_hw *hw, struct ice_driver_ver *dv, struct ice_sq_cd *cd); int +ice_aq_set_port_params(struct ice_port_info *pi, bool double_vlan, + struct ice_sq_cd *cd); +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); @@ -146,6 +151,15 @@ int ice_aq_set_port_id_led(struct ice_port_info *pi, bool is_orig_mode, struct ice_sq_cd *cd); int +ice_aq_get_port_options(struct ice_hw *hw, + struct ice_aqc_get_port_options_elem *options, + u8 *option_count, u8 lport, bool lport_valid, + u8 *active_option_idx, bool *active_option_valid, + u8 *pending_option_idx, bool *pending_option_valid); +int +ice_aq_set_port_option(struct ice_hw *hw, u8 lport, u8 lport_valid, + u8 new_option); +int ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr, u16 mem_addr, u8 page, u8 set_page, u8 *data, u8 length, bool write, struct ice_sq_cd *cd); @@ -199,11 +213,20 @@ ice_aq_set_gpio(struct ice_hw *hw, u16 gpio_ctrl_handle, u8 pin_idx, bool value, int ice_aq_get_gpio(struct ice_hw *hw, u16 gpio_ctrl_handle, u8 pin_idx, bool *value, struct ice_sq_cd *cd); +bool ice_is_100m_speed_supported(struct ice_hw *hw); int ice_aq_set_lldp_mib(struct ice_hw *hw, u8 mib_type, void *buf, u16 buf_size, struct ice_sq_cd *cd); bool ice_fw_supports_lldp_fltr_ctrl(struct ice_hw *hw); int ice_lldp_fltr_add_remove(struct ice_hw *hw, u16 vsi_num, bool add); +int +ice_aq_read_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr, + u16 bus_addr, __le16 addr, u8 params, u8 *data, + struct ice_sq_cd *cd); +int +ice_aq_write_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr, + u16 bus_addr, __le16 addr, u8 params, u8 *data, + struct ice_sq_cd *cd); bool ice_fw_supports_report_dflt_cfg(struct ice_hw *hw); #endif /* _ICE_COMMON_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.h b/drivers/net/ethernet/intel/ice/ice_dcb.h index d73348f279f7..6abf28a14291 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb.h +++ b/drivers/net/ethernet/intel/ice/ice_dcb.h @@ -5,6 +5,7 @@ #define _ICE_DCB_H_ #include "ice_type.h" +#include <scsi/iscsi_proto.h> #define ICE_DCBX_STATUS_NOT_STARTED 0 #define ICE_DCBX_STATUS_IN_PROGRESS 1 diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index b94d8daeaa58..add90e75f05c 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -916,7 +916,8 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring, return; /* Insert 802.1p priority into VLAN header */ - if ((first->tx_flags & ICE_TX_FLAGS_HW_VLAN) || + if ((first->tx_flags & ICE_TX_FLAGS_HW_VLAN || + first->tx_flags & ICE_TX_FLAGS_HW_OUTER_SINGLE_VLAN) || skb->priority != TC_PRIO_CONTROL) { first->tx_flags &= ~ICE_TX_FLAGS_VLAN_PR_M; /* Mask the lower 3 bits to set the 802.1p priority */ @@ -925,7 +926,10 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring, /* if this is not already set it means a VLAN 0 + priority needs * to be offloaded */ - first->tx_flags |= ICE_TX_FLAGS_HW_VLAN; + if (tx_ring->flags & ICE_TX_FLAGS_RING_VLAN_L2TAG2) + first->tx_flags |= ICE_TX_FLAGS_HW_OUTER_SINGLE_VLAN; + else + first->tx_flags |= ICE_TX_FLAGS_HW_VLAN; } } diff --git a/drivers/net/ethernet/intel/ice/ice_devids.h b/drivers/net/ethernet/intel/ice/ice_devids.h index 61dd2f18dee8..6d560d1c74a4 100644 --- a/drivers/net/ethernet/intel/ice/ice_devids.h +++ b/drivers/net/ethernet/intel/ice/ice_devids.h @@ -5,6 +5,7 @@ #define _ICE_DEVIDS_H_ /* Device IDs */ +#define ICE_DEV_ID_E822_SI_DFLT 0x1888 /* Intel(R) Ethernet Connection E823-L for backplane */ #define ICE_DEV_ID_E823L_BACKPLANE 0x124C /* Intel(R) Ethernet Connection E823-L for SFP */ @@ -23,6 +24,11 @@ #define ICE_DEV_ID_E810C_SFP 0x1593 #define ICE_SUBDEV_ID_E810T 0x000E #define ICE_SUBDEV_ID_E810T2 0x000F +#define ICE_SUBDEV_ID_E810T3 0x0010 +#define ICE_SUBDEV_ID_E810T4 0x0011 +#define ICE_SUBDEV_ID_E810T5 0x0012 +#define ICE_SUBDEV_ID_E810T6 0x02E9 +#define ICE_SUBDEV_ID_E810T7 0x02EA /* Intel(R) Ethernet Controller E810-XXV for backplane */ #define ICE_DEV_ID_E810_XXV_BACKPLANE 0x1599 /* Intel(R) Ethernet Controller E810-XXV for QSFP */ diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c index a230edb38466..e6ec20079ced 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.c +++ b/drivers/net/ethernet/intel/ice/ice_devlink.c @@ -9,6 +9,8 @@ #include "ice_eswitch.h" #include "ice_fw_update.h" +static int ice_active_port_option = -1; + /* context for devlink info version reporting */ struct ice_info_ctx { char buf[128]; @@ -466,12 +468,259 @@ ice_devlink_reload_empr_finish(struct devlink *devlink, return 0; } +/** + * ice_devlink_port_opt_speed_str - convert speed to a string + * @speed: speed value + */ +static const char *ice_devlink_port_opt_speed_str(u8 speed) +{ + switch (speed & ICE_AQC_PORT_OPT_MAX_LANE_M) { + case ICE_AQC_PORT_OPT_MAX_LANE_100M: + return "0.1"; + case ICE_AQC_PORT_OPT_MAX_LANE_1G: + return "1"; + case ICE_AQC_PORT_OPT_MAX_LANE_2500M: + return "2.5"; + case ICE_AQC_PORT_OPT_MAX_LANE_5G: + return "5"; + case ICE_AQC_PORT_OPT_MAX_LANE_10G: + return "10"; + case ICE_AQC_PORT_OPT_MAX_LANE_25G: + return "25"; + case ICE_AQC_PORT_OPT_MAX_LANE_50G: + return "50"; + case ICE_AQC_PORT_OPT_MAX_LANE_100G: + return "100"; + } + + return "-"; +} + +#define ICE_PORT_OPT_DESC_LEN 50 +/** + * ice_devlink_port_options_print - Print available port split options + * @pf: the PF to print split port options + * + * Prints a table with available port split options and max port speeds + */ +static void ice_devlink_port_options_print(struct ice_pf *pf) +{ + u8 i, j, options_count, cnt, speed, pending_idx, active_idx; + struct ice_aqc_get_port_options_elem *options, *opt; + struct device *dev = ice_pf_to_dev(pf); + bool active_valid, pending_valid; + char desc[ICE_PORT_OPT_DESC_LEN]; + const char *str; + int status; + + options = kcalloc(ICE_AQC_PORT_OPT_MAX * ICE_MAX_PORT_PER_PCI_DEV, + sizeof(*options), GFP_KERNEL); + if (!options) + return; + + for (i = 0; i < ICE_MAX_PORT_PER_PCI_DEV; i++) { + opt = options + i * ICE_AQC_PORT_OPT_MAX; + options_count = ICE_AQC_PORT_OPT_MAX; + active_valid = 0; + + status = ice_aq_get_port_options(&pf->hw, opt, &options_count, + i, true, &active_idx, + &active_valid, &pending_idx, + &pending_valid); + if (status) { + dev_dbg(dev, "Couldn't read port option for port %d, err %d\n", + i, status); + goto err; + } + } + + dev_dbg(dev, "Available port split options and max port speeds (Gbps):\n"); + dev_dbg(dev, "Status Split Quad 0 Quad 1\n"); + dev_dbg(dev, " count L0 L1 L2 L3 L4 L5 L6 L7\n"); + + for (i = 0; i < options_count; i++) { + cnt = 0; + + if (i == ice_active_port_option) + str = "Active"; + else if ((i == pending_idx) && pending_valid) + str = "Pending"; + else + str = ""; + + cnt += snprintf(&desc[cnt], ICE_PORT_OPT_DESC_LEN - cnt, + "%-8s", str); + + cnt += snprintf(&desc[cnt], ICE_PORT_OPT_DESC_LEN - cnt, + "%-6u", options[i].pmd); + + for (j = 0; j < ICE_MAX_PORT_PER_PCI_DEV; ++j) { + speed = options[i + j * ICE_AQC_PORT_OPT_MAX].max_lane_speed; + str = ice_devlink_port_opt_speed_str(speed); + cnt += snprintf(&desc[cnt], ICE_PORT_OPT_DESC_LEN - cnt, + "%3s ", str); + } + + dev_dbg(dev, "%s\n", desc); + } + +err: + kfree(options); +} + +/** + * ice_devlink_aq_set_port_option - Send set port option admin queue command + * @pf: the PF to print split port options + * @option_idx: selected port option + * @extack: extended netdev ack structure + * + * Sends set port option admin queue command with selected port option and + * calls NVM write activate. + */ +static int +ice_devlink_aq_set_port_option(struct ice_pf *pf, u8 option_idx, + struct netlink_ext_ack *extack) +{ + struct device *dev = ice_pf_to_dev(pf); + int status; + + status = ice_aq_set_port_option(&pf->hw, 0, true, option_idx); + if (status) { + dev_dbg(dev, "ice_aq_set_port_option, err %d aq_err %d\n", + status, pf->hw.adminq.sq_last_status); + NL_SET_ERR_MSG_MOD(extack, "Port split request failed"); + return -EIO; + } + + status = ice_acquire_nvm(&pf->hw, ICE_RES_WRITE); + if (status) { + dev_dbg(dev, "ice_acquire_nvm failed, err %d aq_err %d\n", + status, pf->hw.adminq.sq_last_status); + NL_SET_ERR_MSG_MOD(extack, "Failed to acquire NVM semaphore"); + return -EIO; + } + + status = ice_nvm_write_activate(&pf->hw, ICE_AQC_NVM_ACTIV_REQ_EMPR, NULL); + if (status) { + dev_dbg(dev, "ice_nvm_write_activate failed, err %d aq_err %d\n", + status, pf->hw.adminq.sq_last_status); + NL_SET_ERR_MSG_MOD(extack, "Port split request failed to save data"); + ice_release_nvm(&pf->hw); + return -EIO; + } + + ice_release_nvm(&pf->hw); + + NL_SET_ERR_MSG_MOD(extack, "Reboot required to finish port split"); + return 0; +} + +/** + * ice_devlink_port_split - .port_split devlink handler + * @devlink: devlink instance structure + * @port: devlink port structure + * @count: number of ports to split to + * @extack: extended netdev ack structure + * + * Callback for the devlink .port_split operation. + * + * Unfortunately, the devlink expression of available options is limited + * to just a number, so search for an FW port option which supports + * the specified number. As there could be multiple FW port options with + * the same port split count, allow switching between them. When the same + * port split count request is issued again, switch to the next FW port + * option with the same port split count. + * + * Return: zero on success or an error code on failure. + */ +static int +ice_devlink_port_split(struct devlink *devlink, struct devlink_port *port, + unsigned int count, struct netlink_ext_ack *extack) +{ + struct ice_aqc_get_port_options_elem options[ICE_AQC_PORT_OPT_MAX]; + u8 i, j, active_idx, pending_idx, new_option; + struct ice_pf *pf = devlink_priv(devlink); + u8 option_count = ICE_AQC_PORT_OPT_MAX; + struct device *dev = ice_pf_to_dev(pf); + bool active_valid, pending_valid; + int status; + + status = ice_aq_get_port_options(&pf->hw, options, &option_count, + 0, true, &active_idx, &active_valid, + &pending_idx, &pending_valid); + if (status) { + dev_dbg(dev, "Couldn't read port split options, err = %d\n", + status); + NL_SET_ERR_MSG_MOD(extack, "Failed to get available port split options"); + return -EIO; + } + + new_option = ICE_AQC_PORT_OPT_MAX; + active_idx = pending_valid ? pending_idx : active_idx; + for (i = 1; i <= option_count; i++) { + /* In order to allow switching between FW port options with + * the same port split count, search for a new option starting + * from the active/pending option (with array wrap around). + */ + j = (active_idx + i) % option_count; + + if (count == options[j].pmd) { + new_option = j; + break; + } + } + + if (new_option == active_idx) { + dev_dbg(dev, "request to split: count: %u is already set and there are no other options\n", + count); + NL_SET_ERR_MSG_MOD(extack, "Requested split count is already set"); + ice_devlink_port_options_print(pf); + return -EINVAL; + } + + if (new_option == ICE_AQC_PORT_OPT_MAX) { + dev_dbg(dev, "request to split: count: %u not found\n", count); + NL_SET_ERR_MSG_MOD(extack, "Port split requested unsupported port config"); + ice_devlink_port_options_print(pf); + return -EINVAL; + } + + status = ice_devlink_aq_set_port_option(pf, new_option, extack); + if (status) + return status; + + ice_devlink_port_options_print(pf); + + return 0; +} + +/** + * ice_devlink_port_unsplit - .port_unsplit devlink handler + * @devlink: devlink instance structure + * @port: devlink port structure + * @extack: extended netdev ack structure + * + * Callback for the devlink .port_unsplit operation. + * Calls ice_devlink_port_split with split count set to 1. + * There could be no FW option available with split count 1. + * + * Return: zero on success or an error code on failure. + */ +static int +ice_devlink_port_unsplit(struct devlink *devlink, struct devlink_port *port, + struct netlink_ext_ack *extack) +{ + return ice_devlink_port_split(devlink, port, 1, extack); +} + static const struct devlink_ops ice_devlink_ops = { .supported_flash_update_params = DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK, .reload_actions = BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE), /* The ice driver currently does not support driver reinit */ .reload_down = ice_devlink_reload_empr_start, .reload_up = ice_devlink_reload_empr_finish, + .port_split = ice_devlink_port_split, + .port_unsplit = ice_devlink_port_unsplit, .eswitch_mode_get = ice_eswitch_mode_get, .eswitch_mode_set = ice_eswitch_mode_set, .info_get = ice_devlink_info_get, @@ -647,6 +896,23 @@ void ice_devlink_unregister(struct ice_pf *pf) devlink_unregister(priv_to_devlink(pf)); } +/** + * ice_devlink_set_switch_id - Set unique switch id based on pci dsn + * @pf: the PF to create a devlink port for + * @ppid: struct with switch id information + */ +static void +ice_devlink_set_switch_id(struct ice_pf *pf, struct netdev_phys_item_id *ppid) +{ + struct pci_dev *pdev = pf->pdev; + u64 id; + + id = pci_get_dsn(pdev); + + ppid->id_len = sizeof(id); + put_unaligned_be64(id, &ppid->id); +} + int ice_devlink_register_params(struct ice_pf *pf) { struct devlink *devlink = priv_to_devlink(pf); @@ -678,6 +944,39 @@ void ice_devlink_unregister_params(struct ice_pf *pf) } /** + * ice_devlink_set_port_split_options - Set port split options + * @pf: the PF to set port split options + * @attrs: devlink attributes + * + * Sets devlink port split options based on available FW port options + */ +static void +ice_devlink_set_port_split_options(struct ice_pf *pf, + struct devlink_port_attrs *attrs) +{ + struct ice_aqc_get_port_options_elem options[ICE_AQC_PORT_OPT_MAX]; + u8 i, active_idx, pending_idx, option_count = ICE_AQC_PORT_OPT_MAX; + bool active_valid, pending_valid; + int status; + + status = ice_aq_get_port_options(&pf->hw, options, &option_count, + 0, true, &active_idx, &active_valid, + &pending_idx, &pending_valid); + if (status) { + dev_dbg(ice_pf_to_dev(pf), "Couldn't read port split options, err = %d\n", + status); + return; + } + + /* find the biggest available port split count */ + for (i = 0; i < option_count; i++) + attrs->lanes = max_t(int, attrs->lanes, options[i].pmd); + + attrs->splittable = attrs->lanes ? 1 : 0; + ice_active_port_option = active_idx; +} + +/** * ice_devlink_create_pf_port - Create a devlink port for this PF * @pf: the PF to create a devlink port for * @@ -704,6 +1003,15 @@ int ice_devlink_create_pf_port(struct ice_pf *pf) attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; attrs.phys.port_number = pf->hw.bus.func; + + /* As FW supports only port split options for whole device, + * set port split options only for first PF. + */ + if (pf->hw.pf_id == 0) + ice_devlink_set_port_split_options(pf, &attrs); + + ice_devlink_set_switch_id(pf, &attrs.switch_id); + devlink_port_attrs_set(devlink_port, &attrs); devlink = priv_to_devlink(pf); @@ -753,13 +1061,18 @@ int ice_devlink_create_vf_port(struct ice_vf *vf) pf = vf->pf; dev = ice_pf_to_dev(pf); - vsi = ice_get_vf_vsi(vf); devlink_port = &vf->devlink_port; + vsi = ice_get_vf_vsi(vf); + if (!vsi) + return -EINVAL; + attrs.flavour = DEVLINK_PORT_FLAVOUR_PCI_VF; attrs.pci_vf.pf = pf->hw.bus.func; attrs.pci_vf.vf = vf->vf_id; + ice_devlink_set_switch_id(pf, &attrs.switch_id); + devlink_port_attrs_set(devlink_port, &attrs); devlink = priv_to_devlink(pf); @@ -789,6 +1102,8 @@ void ice_devlink_destroy_vf_port(struct ice_vf *vf) devlink_port_unregister(devlink_port); } +#define ICE_DEVLINK_READ_BLK_SIZE (1024 * 1024) + /** * ice_devlink_nvm_snapshot - Capture a snapshot of the NVM flash contents * @devlink: the devlink instance @@ -815,8 +1130,9 @@ static int ice_devlink_nvm_snapshot(struct devlink *devlink, struct ice_pf *pf = devlink_priv(devlink); struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; - void *nvm_data; - u32 nvm_size; + u8 *nvm_data, *tmp, i; + u32 nvm_size, left; + s8 num_blks; int status; nvm_size = hw->flash.flash_size; @@ -824,26 +1140,44 @@ static int ice_devlink_nvm_snapshot(struct devlink *devlink, if (!nvm_data) return -ENOMEM; - status = ice_acquire_nvm(hw, ICE_RES_READ); - if (status) { - dev_dbg(dev, "ice_acquire_nvm failed, err %d aq_err %d\n", - status, hw->adminq.sq_last_status); - NL_SET_ERR_MSG_MOD(extack, "Failed to acquire NVM semaphore"); - vfree(nvm_data); - return status; - } - status = ice_read_flat_nvm(hw, 0, &nvm_size, nvm_data, false); - if (status) { - dev_dbg(dev, "ice_read_flat_nvm failed after reading %u bytes, err %d aq_err %d\n", - nvm_size, status, hw->adminq.sq_last_status); - NL_SET_ERR_MSG_MOD(extack, "Failed to read NVM contents"); + num_blks = DIV_ROUND_UP(nvm_size, ICE_DEVLINK_READ_BLK_SIZE); + tmp = nvm_data; + left = nvm_size; + + /* Some systems take longer to read the NVM than others which causes the + * FW to reclaim the NVM lock before the entire NVM has been read. Fix + * this by breaking the reads of the NVM into smaller chunks that will + * probably not take as long. This has some overhead since we are + * increasing the number of AQ commands, but it should always work + */ + for (i = 0; i < num_blks; i++) { + u32 read_sz = min_t(u32, ICE_DEVLINK_READ_BLK_SIZE, left); + + status = ice_acquire_nvm(hw, ICE_RES_READ); + if (status) { + dev_dbg(dev, "ice_acquire_nvm failed, err %d aq_err %d\n", + status, hw->adminq.sq_last_status); + NL_SET_ERR_MSG_MOD(extack, "Failed to acquire NVM semaphore"); + vfree(nvm_data); + return -EIO; + } + + status = ice_read_flat_nvm(hw, i * ICE_DEVLINK_READ_BLK_SIZE, + &read_sz, tmp, false); + if (status) { + dev_dbg(dev, "ice_read_flat_nvm failed after reading %u bytes, err %d aq_err %d\n", + read_sz, status, hw->adminq.sq_last_status); + NL_SET_ERR_MSG_MOD(extack, "Failed to read NVM contents"); + ice_release_nvm(hw); + vfree(nvm_data); + return -EIO; + } ice_release_nvm(hw); - vfree(nvm_data); - return status; - } - ice_release_nvm(hw); + tmp += read_sz; + left -= read_sz; + } *data = nvm_data; diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index 864692b157b6..f9f15acae90a 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -44,6 +44,7 @@ ice_eswitch_add_vf_mac_rule(struct ice_pf *pf, struct ice_vf *vf, const u8 *mac) ctrl_vsi->rxq_map[vf->vf_id]; rule_info.flags_info.act |= ICE_SINGLE_ACT_LB_ENABLE; rule_info.flags_info.act_valid = true; + rule_info.tun_type = ICE_SW_TUN_AND_NON_TUN; err = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, vf->repr->mac_rule); @@ -115,9 +116,12 @@ static int ice_eswitch_setup_env(struct ice_pf *pf) struct ice_vsi *uplink_vsi = pf->switchdev.uplink_vsi; struct net_device *uplink_netdev = uplink_vsi->netdev; struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi; + struct ice_vsi_vlan_ops *vlan_ops; bool rule_added = false; - ice_vsi_manage_vlan_stripping(ctrl_vsi, 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); @@ -126,11 +130,11 @@ static int ice_eswitch_setup_env(struct ice_pf *pf) __dev_mc_unsync(uplink_netdev, NULL); netif_addr_unlock_bh(uplink_netdev); - if (ice_vsi_add_vlan(uplink_vsi, 0, ICE_FWD_TO_VSI)) + if (ice_vsi_add_vlan_zero(uplink_vsi)) goto err_def_rx; - if (!ice_is_dflt_vsi_in_use(uplink_vsi->vsw)) { - if (ice_set_dflt_vsi(uplink_vsi->vsw, uplink_vsi)) + if (!ice_is_dflt_vsi_in_use(uplink_vsi->port_info)) { + if (ice_set_dflt_vsi(uplink_vsi)) goto err_def_rx; rule_added = true; } @@ -147,7 +151,7 @@ err_override_control: ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override); err_override_uplink: if (rule_added) - ice_clear_dflt_vsi(uplink_vsi->vsw); + ice_clear_dflt_vsi(uplink_vsi); err_def_rx: ice_fltr_add_mac_and_broadcast(uplink_vsi, uplink_vsi->port_info->mac.perm_addr, @@ -172,10 +176,20 @@ static void ice_eswitch_remap_rings_to_vectors(struct ice_pf *pf) int q_id; ice_for_each_txq(vsi, q_id) { - struct ice_repr *repr = pf->vf[q_id].repr; - struct ice_q_vector *q_vector = repr->q_vector; - struct ice_tx_ring *tx_ring = vsi->tx_rings[q_id]; - struct ice_rx_ring *rx_ring = vsi->rx_rings[q_id]; + struct ice_q_vector *q_vector; + struct ice_tx_ring *tx_ring; + struct ice_rx_ring *rx_ring; + struct ice_repr *repr; + struct ice_vf *vf; + + vf = ice_get_vf_by_id(pf, q_id); + if (WARN_ON(!vf)) + continue; + + repr = vf->repr; + q_vector = repr->q_vector; + tx_ring = vsi->tx_rings[q_id]; + rx_ring = vsi->rx_rings[q_id]; q_vector->vsi = vsi; q_vector->reg_idx = vsi->q_vectors[0]->reg_idx; @@ -195,6 +209,38 @@ static void ice_eswitch_remap_rings_to_vectors(struct ice_pf *pf) rx_ring->q_vector = q_vector; rx_ring->next = NULL; rx_ring->netdev = repr->netdev; + + ice_put_vf(vf); + } +} + +/** + * ice_eswitch_release_reprs - clear PR VSIs configuration + * @pf: poiner to PF struct + * @ctrl_vsi: pointer to switchdev control VSI + */ +static void +ice_eswitch_release_reprs(struct ice_pf *pf, struct ice_vsi *ctrl_vsi) +{ + struct ice_vf *vf; + unsigned int bkt; + + lockdep_assert_held(&pf->vfs.table_lock); + + ice_for_each_vf(pf, bkt, vf) { + struct ice_vsi *vsi = vf->repr->src_vsi; + + /* Skip VFs that aren't configured */ + if (!vf->repr->dst) + continue; + + ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof); + metadata_dst_free(vf->repr->dst); + vf->repr->dst = NULL; + ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr.addr, + ICE_FWD_TO_VSI); + + netif_napi_del(&vf->repr->q_vector->napi); } } @@ -206,11 +252,13 @@ static int ice_eswitch_setup_reprs(struct ice_pf *pf) { struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi; int max_vsi_num = 0; - int i; + struct ice_vf *vf; + unsigned int bkt; + + lockdep_assert_held(&pf->vfs.table_lock); - ice_for_each_vf(pf, i) { - struct ice_vsi *vsi = pf->vf[i].repr->src_vsi; - struct ice_vf *vf = &pf->vf[i]; + ice_for_each_vf(pf, bkt, vf) { + struct ice_vsi *vsi = vf->repr->src_vsi; ice_remove_vsi_fltr(&pf->hw, vsi->idx); vf->repr->dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX, @@ -227,14 +275,16 @@ static int ice_eswitch_setup_reprs(struct ice_pf *pf) vf->hw_lan_addr.addr, ICE_FWD_TO_VSI); metadata_dst_free(vf->repr->dst); + vf->repr->dst = NULL; goto err; } - if (ice_vsi_add_vlan(vsi, 0, ICE_FWD_TO_VSI)) { + if (ice_vsi_add_vlan_zero(vsi)) { ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr.addr, ICE_FWD_TO_VSI); metadata_dst_free(vf->repr->dst); + vf->repr->dst = NULL; ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof); goto err; } @@ -242,14 +292,14 @@ static int ice_eswitch_setup_reprs(struct ice_pf *pf) if (max_vsi_num < vsi->vsi_num) max_vsi_num = vsi->vsi_num; - netif_napi_add(vf->repr->netdev, &vf->repr->q_vector->napi, ice_napi_poll, - NAPI_POLL_WEIGHT); + netif_napi_add(vf->repr->netdev, &vf->repr->q_vector->napi, + ice_napi_poll); netif_keep_dst(vf->repr->netdev); } - ice_for_each_vf(pf, i) { - struct ice_repr *repr = pf->vf[i].repr; + ice_for_each_vf(pf, bkt, vf) { + struct ice_repr *repr = vf->repr; struct ice_vsi *vsi = repr->src_vsi; struct metadata_dst *dst; @@ -262,43 +312,12 @@ static int ice_eswitch_setup_reprs(struct ice_pf *pf) return 0; err: - for (i = i - 1; i >= 0; i--) { - struct ice_vsi *vsi = pf->vf[i].repr->src_vsi; - struct ice_vf *vf = &pf->vf[i]; - - ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof); - metadata_dst_free(vf->repr->dst); - ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr.addr, - ICE_FWD_TO_VSI); - } + ice_eswitch_release_reprs(pf, ctrl_vsi); return -ENODEV; } /** - * ice_eswitch_release_reprs - clear PR VSIs configuration - * @pf: poiner to PF struct - * @ctrl_vsi: pointer to switchdev control VSI - */ -static void -ice_eswitch_release_reprs(struct ice_pf *pf, struct ice_vsi *ctrl_vsi) -{ - int i; - - ice_for_each_vf(pf, i) { - struct ice_vsi *vsi = pf->vf[i].repr->src_vsi; - struct ice_vf *vf = &pf->vf[i]; - - ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof); - metadata_dst_free(vf->repr->dst); - ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr.addr, - ICE_FWD_TO_VSI); - - netif_napi_del(&vf->repr->q_vector->napi); - } -} - -/** * ice_eswitch_update_repr - reconfigure VF port representor * @vsi: VF VSI for which port representor is configured */ @@ -312,7 +331,7 @@ void ice_eswitch_update_repr(struct ice_vsi *vsi) if (!ice_is_switchdev_running(pf)) return; - vf = &pf->vf[vsi->vf_id]; + vf = vsi->vf; repr = vf->repr; repr->src_vsi = vsi; repr->dst->u.port_info.port_id = vsi->vsi_num; @@ -320,7 +339,8 @@ void ice_eswitch_update_repr(struct ice_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.addr, ICE_FWD_TO_VSI); - dev_err(ice_pf_to_dev(pf), "Failed to update VF %d port representor", vsi->vf_id); + dev_err(ice_pf_to_dev(pf), "Failed to update VF %d port representor", + vsi->vf->vf_id); } } @@ -341,7 +361,8 @@ ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev) np = netdev_priv(netdev); vsi = np->vsi; - if (ice_is_reset_in_progress(vsi->back->state)) + if (ice_is_reset_in_progress(vsi->back->state) || + test_bit(ICE_VF_DIS, vsi->back->state)) return NETDEV_TX_BUSY; repr = ice_netdev_to_repr(netdev); @@ -390,7 +411,7 @@ static void ice_eswitch_release_env(struct ice_pf *pf) ice_vsi_update_security(ctrl_vsi, ice_vsi_ctx_clear_allow_override); ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override); - ice_clear_dflt_vsi(uplink_vsi->vsw); + ice_clear_dflt_vsi(uplink_vsi); ice_fltr_add_mac_and_broadcast(uplink_vsi, uplink_vsi->port_info->mac.perm_addr, ICE_FWD_TO_VSI); @@ -404,7 +425,7 @@ static void ice_eswitch_release_env(struct ice_pf *pf) static struct ice_vsi * ice_eswitch_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) { - return ice_vsi_setup(pf, pi, ICE_VSI_SWITCHDEV_CTRL, ICE_INVAL_VFID, NULL); + return ice_vsi_setup(pf, pi, ICE_VSI_SWITCHDEV_CTRL, NULL, NULL); } /** @@ -413,10 +434,13 @@ ice_eswitch_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) */ static void ice_eswitch_napi_del(struct ice_pf *pf) { - int i; + struct ice_vf *vf; + unsigned int bkt; - ice_for_each_vf(pf, i) - netif_napi_del(&pf->vf[i].repr->q_vector->napi); + lockdep_assert_held(&pf->vfs.table_lock); + + ice_for_each_vf(pf, bkt, vf) + netif_napi_del(&vf->repr->q_vector->napi); } /** @@ -425,10 +449,13 @@ static void ice_eswitch_napi_del(struct ice_pf *pf) */ static void ice_eswitch_napi_enable(struct ice_pf *pf) { - int i; + struct ice_vf *vf; + unsigned int bkt; + + lockdep_assert_held(&pf->vfs.table_lock); - ice_for_each_vf(pf, i) - napi_enable(&pf->vf[i].repr->q_vector->napi); + ice_for_each_vf(pf, bkt, vf) + napi_enable(&vf->repr->q_vector->napi); } /** @@ -437,10 +464,13 @@ static void ice_eswitch_napi_enable(struct ice_pf *pf) */ static void ice_eswitch_napi_disable(struct ice_pf *pf) { - int i; + struct ice_vf *vf; + unsigned int bkt; + + lockdep_assert_held(&pf->vfs.table_lock); - ice_for_each_vf(pf, i) - napi_disable(&pf->vf[i].repr->q_vector->napi); + ice_for_each_vf(pf, bkt, vf) + napi_disable(&vf->repr->q_vector->napi); } /** @@ -518,7 +548,7 @@ ice_eswitch_mode_set(struct devlink *devlink, u16 mode, if (pf->eswitch_mode == mode) return 0; - if (pf->num_alloc_vfs) { + if (ice_has_vfs(pf)) { dev_info(ice_pf_to_dev(pf), "Changing eswitch mode is allowed only if there is no VFs created"); NL_SET_ERR_MSG_MOD(extack, "Changing eswitch mode is allowed only if there is no VFs created"); return -EOPNOTSUPP; @@ -609,16 +639,17 @@ int ice_eswitch_configure(struct ice_pf *pf) */ static void ice_eswitch_start_all_tx_queues(struct ice_pf *pf) { - struct ice_repr *repr; - int i; + struct ice_vf *vf; + unsigned int bkt; + + lockdep_assert_held(&pf->vfs.table_lock); if (test_bit(ICE_DOWN, pf->state)) return; - ice_for_each_vf(pf, i) { - repr = pf->vf[i].repr; - if (repr) - ice_repr_start_tx_queues(repr); + ice_for_each_vf(pf, bkt, vf) { + if (vf->repr) + ice_repr_start_tx_queues(vf->repr); } } @@ -628,16 +659,17 @@ static void ice_eswitch_start_all_tx_queues(struct ice_pf *pf) */ void ice_eswitch_stop_all_tx_queues(struct ice_pf *pf) { - struct ice_repr *repr; - int i; + struct ice_vf *vf; + unsigned int bkt; + + lockdep_assert_held(&pf->vfs.table_lock); if (test_bit(ICE_DOWN, pf->state)) return; - ice_for_each_vf(pf, i) { - repr = pf->vf[i].repr; - if (repr) - ice_repr_stop_tx_queues(repr); + ice_for_each_vf(pf, bkt, vf) { + if (vf->repr) + ice_repr_stop_tx_queues(vf->repr); } } diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.h b/drivers/net/ethernet/intel/ice/ice_eswitch.h index bd58d9d2e565..6a413331572b 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.h +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.h @@ -52,7 +52,7 @@ static inline void ice_eswitch_update_repr(struct ice_vsi *vsi) { } static inline int ice_eswitch_configure(struct ice_pf *pf) { - return -EOPNOTSUPP; + return 0; } static inline int ice_eswitch_rebuild(struct ice_pf *pf) diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index e2e3ef7fba7f..b7be84bbe72d 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -136,6 +136,11 @@ static const struct ice_stats ice_gstrings_pf_stats[] = { ICE_PF_STAT("mac_remote_faults.nic", stats.mac_remote_faults), ICE_PF_STAT("fdir_sb_match.nic", stats.fd_sb_match), ICE_PF_STAT("fdir_sb_status.nic", stats.fd_sb_status), + ICE_PF_STAT("tx_hwtstamp_skipped", ptp.tx_hwtstamp_skipped), + ICE_PF_STAT("tx_hwtstamp_timeouts", ptp.tx_hwtstamp_timeouts), + ICE_PF_STAT("tx_hwtstamp_flushed", ptp.tx_hwtstamp_flushed), + ICE_PF_STAT("tx_hwtstamp_discarded", ptp.tx_hwtstamp_discarded), + ICE_PF_STAT("late_cached_phc_updates", ptp.late_cached_phc_updates), }; static const u32 ice_regs_dump_list[] = { @@ -164,6 +169,7 @@ static const struct ice_priv_flag ice_gstrings_priv_flags[] = { ICE_PRIV_FLAG("vf-true-promisc-support", ICE_FLAG_VF_TRUE_PROMISC_ENA), ICE_PRIV_FLAG("mdd-auto-reset-vf", ICE_FLAG_MDD_AUTO_RESET_VF), + ICE_PRIV_FLAG("vf-vlan-pruning", ICE_FLAG_VF_VLAN_PRUNING), ICE_PRIV_FLAG("legacy-rx", ICE_FLAG_LEGACY_RX), }; @@ -189,19 +195,17 @@ __ice_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo, snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%x.%02x 0x%x %d.%d.%d", nvm->major, nvm->minor, nvm->eetrack, orom->major, orom->build, orom->patch); + + strscpy(drvinfo->bus_info, pci_name(pf->pdev), + sizeof(drvinfo->bus_info)); } static void ice_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) { struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_pf *pf = np->vsi->back; __ice_get_drvinfo(netdev, drvinfo, np->vsi); - - strscpy(drvinfo->bus_info, pci_name(pf->pdev), - sizeof(drvinfo->bus_info)); - drvinfo->n_priv_flags = ICE_PRIV_FLAG_ARRAY_SIZE; } @@ -315,16 +319,20 @@ out: */ static bool ice_active_vfs(struct ice_pf *pf) { - unsigned int i; + bool active = false; + struct ice_vf *vf; + unsigned int bkt; - ice_for_each_vf(pf, i) { - struct ice_vf *vf = &pf->vf[i]; - - if (test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) - return true; + rcu_read_lock(); + ice_for_each_vf_rcu(pf, bkt, vf) { + if (test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + active = true; + break; + } } + rcu_read_unlock(); - return false; + return active; } /** @@ -655,7 +663,8 @@ static int ice_lbtest_receive_frames(struct ice_rx_ring *rx_ring) rx_desc = ICE_RX_DESC(rx_ring, i); if (!(rx_desc->wb.status_error0 & - cpu_to_le16(ICE_TX_DESC_CMD_EOP | ICE_TX_DESC_CMD_RS))) + (cpu_to_le16(BIT(ICE_RX_FLEX_DESC_STATUS0_DD_S)) | + cpu_to_le16(BIT(ICE_RX_FLEX_DESC_STATUS0_EOF_S))))) continue; rx_buf = &rx_ring->rx_buf[i]; @@ -1280,21 +1289,26 @@ static int ice_set_priv_flags(struct net_device *netdev, u32 flags) } if (test_bit(ICE_FLAG_LEGACY_RX, change_flags)) { /* down and up VSI so that changes of Rx cfg are reflected. */ - if (!test_and_set_bit(ICE_VSI_DOWN, vsi->state)) { - ice_down(vsi); - ice_up(vsi); - } + ice_down_up(vsi); } /* don't allow modification of this flag when a single VF is in * promiscuous mode because it's not supported */ if (test_bit(ICE_FLAG_VF_TRUE_PROMISC_ENA, change_flags) && - ice_is_any_vf_in_promisc(pf)) { + ice_is_any_vf_in_unicast_promisc(pf)) { dev_err(dev, "Changing vf-true-promisc-support flag while VF(s) are in promiscuous mode not supported\n"); /* toggle bit back to previous state */ change_bit(ICE_FLAG_VF_TRUE_PROMISC_ENA, pf->flags); ret = -EAGAIN; } + + if (test_bit(ICE_FLAG_VF_VLAN_PRUNING, change_flags) && + ice_has_vfs(pf)) { + dev_err(dev, "vf-vlan-pruning: VLAN pruning cannot be changed while VFs are active.\n"); + /* toggle bit back to previous state */ + change_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags); + ret = -EOPNOTSUPP; + } ethtool_exit: clear_bit(ICE_FLAG_ETHTOOL_CTXT, pf->flags); return ret; @@ -1456,20 +1470,22 @@ ice_get_ethtool_stats(struct net_device *netdev, /** * ice_mask_min_supported_speeds + * @hw: pointer to the HW structure * @phy_types_high: PHY type high * @phy_types_low: PHY type low to apply minimum supported speeds mask * * Apply minimum supported speeds mask to PHY type low. These are the speeds * for ethtool supported link mode. */ -static -void ice_mask_min_supported_speeds(u64 phy_types_high, u64 *phy_types_low) +static void +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) *phy_types_low &= ~ICE_PHY_TYPE_LOW_MASK_MIN_25G; - else + else if (!ice_is_100m_speed_supported(hw)) *phy_types_low &= ~ICE_PHY_TYPE_LOW_MASK_MIN_1G; } @@ -1519,7 +1535,8 @@ ice_phy_type_to_ethtool(struct net_device *netdev, phy_types_low = le64_to_cpu(pf->nvm_phy_type_lo); phy_types_high = le64_to_cpu(pf->nvm_phy_type_hi); - ice_mask_min_supported_speeds(phy_types_high, &phy_types_low); + ice_mask_min_supported_speeds(&pf->hw, phy_types_high, + &phy_types_low); /* determine advertised modes based on link override only * if it's supported and if the FW doesn't abstract the * driver from having to account for link overrides @@ -2179,6 +2196,42 @@ ice_setup_autoneg(struct ice_port_info *p, struct ethtool_link_ksettings *ks, } /** + * ice_set_phy_type_from_speed - set phy_types based on speeds + * and advertised modes + * @ks: ethtool link ksettings struct + * @phy_type_low: pointer to the lower part of phy_type + * @phy_type_high: pointer to the higher part of phy_type + * @adv_link_speed: targeted link speeds bitmap + */ +static void +ice_set_phy_type_from_speed(const struct ethtool_link_ksettings *ks, + u64 *phy_type_low, u64 *phy_type_high, + u16 adv_link_speed) +{ + /* Handle 1000M speed in a special way because ice_update_phy_type + * enables all link modes, but having mixed copper and optical + * standards is not supported. + */ + adv_link_speed &= ~ICE_AQ_LINK_SPEED_1000MB; + + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 1000baseT_Full)) + *phy_type_low |= ICE_PHY_TYPE_LOW_1000BASE_T | + ICE_PHY_TYPE_LOW_1G_SGMII; + + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 1000baseKX_Full)) + *phy_type_low |= ICE_PHY_TYPE_LOW_1000BASE_KX; + + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 1000baseX_Full)) + *phy_type_low |= ICE_PHY_TYPE_LOW_1000BASE_SX | + ICE_PHY_TYPE_LOW_1000BASE_LX; + + ice_update_phy_type(phy_type_low, phy_type_high, adv_link_speed); +} + +/** * ice_set_link_ksettings - Set Speed and Duplex * @netdev: network interface device structure * @ks: ethtool ksettings @@ -2298,7 +2351,7 @@ ice_set_link_ksettings(struct net_device *netdev, if (err) goto done; - curr_link_speed = pi->phy.link_info.link_speed; + curr_link_speed = pi->phy.curr_user_speed_req; adv_link_speed = ice_ksettings_find_adv_link_speed(ks); /* If speed didn't get set, set it to what it currently is. @@ -2309,7 +2362,8 @@ ice_set_link_ksettings(struct net_device *netdev, adv_link_speed = curr_link_speed; /* Convert the advertise link speeds to their corresponded PHY_TYPE */ - ice_update_phy_type(&phy_type_low, &phy_type_high, adv_link_speed); + ice_set_phy_type_from_speed(ks, &phy_type_low, &phy_type_high, + adv_link_speed); if (!autoneg_changed && adv_link_speed == curr_link_speed) { netdev_info(netdev, "Nothing changed, exiting without setting anything.\n"); @@ -2777,6 +2831,7 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, tx_rings[i].count = new_tx_cnt; tx_rings[i].desc = NULL; tx_rings[i].tx_buf = NULL; + tx_rings[i].tx_tstamps = &pf->ptp.port.tx; err = ice_setup_tx_ring(&tx_rings[i]); if (err) { while (i--) @@ -2803,6 +2858,8 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, /* clone ring and setup updated count */ xdp_rings[i] = *vsi->xdp_rings[i]; xdp_rings[i].count = new_tx_cnt; + xdp_rings[i].next_dd = ICE_RING_QUARTER(&xdp_rings[i]) - 1; + xdp_rings[i].next_rs = ICE_RING_QUARTER(&xdp_rings[i]) - 1; xdp_rings[i].desc = NULL; xdp_rings[i].tx_buf = NULL; err = ice_setup_tx_ring(&xdp_rings[i]); @@ -2833,6 +2890,7 @@ process_rx: /* clone ring and setup updated count */ rx_rings[i] = *vsi->rx_rings[i]; rx_rings[i].count = new_rx_cnt; + rx_rings[i].cached_phctime = pf->ptp.cached_phc_time; rx_rings[i].desc = NULL; rx_rings[i].rx_buf = NULL; /* this is to allow wr32 to have something to write to @@ -3098,36 +3156,47 @@ static u32 ice_get_rxfh_indir_size(struct net_device *netdev) return np->vsi->rss_table_size; } -/** - * ice_get_rxfh - get the Rx flow hash indirection table - * @netdev: network interface device structure - * @indir: indirection table - * @key: hash key - * @hfunc: hash function - * - * Reads the indirection table directly from the hardware. - */ static int -ice_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, u8 *hfunc) +ice_get_rxfh_context(struct net_device *netdev, u32 *indir, + u8 *key, u8 *hfunc, u32 rss_context) { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; - int err, i; + u16 qcount, offset; + int err, num_tc, i; u8 *lut; + if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) { + netdev_warn(netdev, "RSS is not supported on this VSI!\n"); + return -EOPNOTSUPP; + } + + if (rss_context && !ice_is_adq_active(pf)) { + netdev_err(netdev, "RSS context cannot be non-zero when ADQ is not configured.\n"); + return -EINVAL; + } + + qcount = vsi->mqprio_qopt.qopt.count[rss_context]; + offset = vsi->mqprio_qopt.qopt.offset[rss_context]; + + if (rss_context && ice_is_adq_active(pf)) { + num_tc = vsi->mqprio_qopt.qopt.num_tc; + if (rss_context >= num_tc) { + netdev_err(netdev, "RSS context:%d > num_tc:%d\n", + rss_context, num_tc); + return -EINVAL; + } + /* Use channel VSI of given TC */ + vsi = vsi->tc_map_vsi[rss_context]; + } + if (hfunc) *hfunc = ETH_RSS_HASH_TOP; if (!indir) return 0; - if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) { - /* RSS not supported return error here */ - netdev_warn(netdev, "RSS is not configured on this VSI!\n"); - return -EIO; - } - lut = kzalloc(vsi->rss_table_size, GFP_KERNEL); if (!lut) return -ENOMEM; @@ -3140,8 +3209,14 @@ ice_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, u8 *hfunc) if (err) goto out; + if (ice_is_adq_active(pf)) { + for (i = 0; i < vsi->rss_table_size; i++) + indir[i] = offset + lut[i] % qcount; + goto out; + } + for (i = 0; i < vsi->rss_table_size; i++) - indir[i] = (u32)(lut[i]); + indir[i] = lut[i]; out: kfree(lut); @@ -3149,6 +3224,21 @@ out: } /** + * ice_get_rxfh - get the Rx flow hash indirection table + * @netdev: network interface device structure + * @indir: indirection table + * @key: hash key + * @hfunc: hash function + * + * Reads the indirection table directly from the hardware. + */ +static int +ice_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, u8 *hfunc) +{ + return ice_get_rxfh_context(netdev, indir, key, hfunc, 0); +} + +/** * ice_set_rxfh - set the Rx flow hash indirection table * @netdev: network interface device structure * @indir: indirection table @@ -3425,6 +3515,16 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch) new_rx = ch->combined_count + ch->rx_count; new_tx = ch->combined_count + ch->tx_count; + if (new_rx < vsi->tc_cfg.numtc) { + netdev_err(dev, "Cannot set less Rx channels, than Traffic Classes you have (%u)\n", + vsi->tc_cfg.numtc); + return -EINVAL; + } + if (new_tx < vsi->tc_cfg.numtc) { + netdev_err(dev, "Cannot set less Tx channels, than Traffic Classes you have (%u)\n", + vsi->tc_cfg.numtc); + return -EINVAL; + } if (new_rx > ice_get_max_rxq(pf)) { netdev_err(dev, "Maximum allowed Rx channels is %d\n", ice_get_max_rxq(pf)); @@ -4089,6 +4189,7 @@ static const struct ethtool_ops ice_ethtool_ops = { .set_pauseparam = ice_set_pauseparam, .get_rxfh_key_size = ice_get_rxfh_key_size, .get_rxfh_indir_size = ice_get_rxfh_indir_size, + .get_rxfh_context = ice_get_rxfh_context, .get_rxfh = ice_get_rxfh, .set_rxfh = ice_set_rxfh, .get_channels = ice_get_channels, diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c index 5d10c4f84a36..ead6d50fc0ad 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c @@ -852,7 +852,7 @@ ice_create_init_fdir_rule(struct ice_pf *pf, enum ice_fltr_ptype flow) if (!seg) return -ENOMEM; - tun_seg = devm_kcalloc(dev, sizeof(*seg), ICE_FD_HW_SEG_MAX, + tun_seg = devm_kcalloc(dev, ICE_FD_HW_SEG_MAX, sizeof(*tun_seg), GFP_KERNEL); if (!tun_seg) { devm_kfree(dev, seg); @@ -1214,7 +1214,7 @@ ice_cfg_fdir_xtrct_seq(struct ice_pf *pf, struct ethtool_rx_flow_spec *fsp, if (!seg) return -ENOMEM; - tun_seg = devm_kcalloc(dev, sizeof(*seg), ICE_FD_HW_SEG_MAX, + tun_seg = devm_kcalloc(dev, ICE_FD_HW_SEG_MAX, sizeof(*tun_seg), GFP_KERNEL); if (!tun_seg) { devm_kfree(dev, seg); diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c index 4deb2c9446ec..4b3bb19e1d06 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c @@ -4,10 +4,19 @@ #include "ice_common.h" #include "ice_flex_pipe.h" #include "ice_flow.h" +#include "ice.h" + +/* For supporting double VLAN mode, it is necessary to enable or disable certain + * boost tcam entries. The metadata labels names that match the following + * prefixes will be saved to allow enabling double VLAN mode. + */ +#define ICE_DVM_PRE "BOOST_MAC_VLAN_DVM" /* enable these entries */ +#define ICE_SVM_PRE "BOOST_MAC_VLAN_SVM" /* disable these entries */ /* To support tunneling entries by PF, the package will append the PF number to * the label; for example TNL_VXLAN_PF0, TNL_VXLAN_PF1, TNL_VXLAN_PF2, etc. */ +#define ICE_TNL_PRE "TNL_" static const struct ice_tunnel_type_scan tnls[] = { { TNL_VXLAN, "TNL_VXLAN_PF" }, { TNL_GENEVE, "TNL_GENEVE_PF" }, @@ -523,6 +532,55 @@ ice_enum_labels(struct ice_seg *ice_seg, u32 type, struct ice_pkg_enum *state, } /** + * ice_add_tunnel_hint + * @hw: pointer to the HW structure + * @label_name: label text + * @val: value of the tunnel port boost entry + */ +static void ice_add_tunnel_hint(struct ice_hw *hw, char *label_name, u16 val) +{ + if (hw->tnl.count < ICE_TUNNEL_MAX_ENTRIES) { + u16 i; + + for (i = 0; tnls[i].type != TNL_LAST; i++) { + size_t len = strlen(tnls[i].label_prefix); + + /* Look for matching label start, before continuing */ + if (strncmp(label_name, tnls[i].label_prefix, len)) + continue; + + /* Make sure this label matches our PF. Note that the PF + * character ('0' - '7') will be located where our + * prefix string's null terminator is located. + */ + if ((label_name[len] - '0') == hw->pf_id) { + hw->tnl.tbl[hw->tnl.count].type = tnls[i].type; + hw->tnl.tbl[hw->tnl.count].valid = false; + hw->tnl.tbl[hw->tnl.count].boost_addr = val; + hw->tnl.tbl[hw->tnl.count].port = 0; + hw->tnl.count++; + break; + } + } + } +} + +/** + * ice_add_dvm_hint + * @hw: pointer to the HW structure + * @val: value of the boost entry + * @enable: true if entry needs to be enabled, or false if needs to be disabled + */ +static void ice_add_dvm_hint(struct ice_hw *hw, u16 val, bool enable) +{ + if (hw->dvm_upd.count < ICE_DVM_MAX_ENTRIES) { + hw->dvm_upd.tbl[hw->dvm_upd.count].boost_addr = val; + hw->dvm_upd.tbl[hw->dvm_upd.count].enable = enable; + hw->dvm_upd.count++; + } +} + +/** * ice_init_pkg_hints * @hw: pointer to the HW structure * @ice_seg: pointer to the segment of the package scan (non-NULL) @@ -548,32 +606,23 @@ static void ice_init_pkg_hints(struct ice_hw *hw, struct ice_seg *ice_seg) label_name = ice_enum_labels(ice_seg, ICE_SID_LBL_RXPARSER_TMEM, &state, &val); - while (label_name && hw->tnl.count < ICE_TUNNEL_MAX_ENTRIES) { - for (i = 0; tnls[i].type != TNL_LAST; i++) { - size_t len = strlen(tnls[i].label_prefix); + while (label_name) { + if (!strncmp(label_name, ICE_TNL_PRE, strlen(ICE_TNL_PRE))) + /* check for a tunnel entry */ + ice_add_tunnel_hint(hw, label_name, val); - /* Look for matching label start, before continuing */ - if (strncmp(label_name, tnls[i].label_prefix, len)) - continue; + /* check for a dvm mode entry */ + else if (!strncmp(label_name, ICE_DVM_PRE, strlen(ICE_DVM_PRE))) + ice_add_dvm_hint(hw, val, true); - /* Make sure this label matches our PF. Note that the PF - * character ('0' - '7') will be located where our - * prefix string's null terminator is located. - */ - if ((label_name[len] - '0') == hw->pf_id) { - hw->tnl.tbl[hw->tnl.count].type = tnls[i].type; - hw->tnl.tbl[hw->tnl.count].valid = false; - hw->tnl.tbl[hw->tnl.count].boost_addr = val; - hw->tnl.tbl[hw->tnl.count].port = 0; - hw->tnl.count++; - break; - } - } + /* check for a svm mode entry */ + else if (!strncmp(label_name, ICE_SVM_PRE, strlen(ICE_SVM_PRE))) + ice_add_dvm_hint(hw, val, false); label_name = ice_enum_labels(NULL, 0, &state, &val); } - /* Cache the appropriate boost TCAM entry pointers */ + /* Cache the appropriate boost TCAM entry pointers for tunnels */ for (i = 0; i < hw->tnl.count; i++) { ice_find_boost_entry(ice_seg, hw->tnl.tbl[i].boost_addr, &hw->tnl.tbl[i].boost_entry); @@ -583,6 +632,11 @@ static void ice_init_pkg_hints(struct ice_hw *hw, struct ice_seg *ice_seg) hw->tnl.valid_count[hw->tnl.tbl[i].type]++; } } + + /* Cache the appropriate boost TCAM entry pointers for DVM and SVM */ + for (i = 0; i < hw->dvm_upd.count; i++) + ice_find_boost_entry(ice_seg, hw->dvm_upd.tbl[i].boost_addr, + &hw->dvm_upd.tbl[i].boost_entry); } /* Key creation */ @@ -874,6 +928,27 @@ ice_aq_download_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_aq_update_pkg * @hw: pointer to the hardware structure * @pkg_buf: the package cmd buffer @@ -957,25 +1032,21 @@ ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type, } /** - * ice_update_pkg + * ice_update_pkg_no_lock * @hw: pointer to the hardware structure * @bufs: pointer to an array of buffers * @count: the number of buffers in the array - * - * Obtains change lock and updates package. */ -static int ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count) +static int +ice_update_pkg_no_lock(struct ice_hw *hw, struct ice_buf *bufs, u32 count) { - u32 offset, info, i; - int status; - - status = ice_acquire_change_lock(hw, ICE_RES_WRITE); - if (status) - return status; + int status = 0; + u32 i; for (i = 0; i < count; i++) { struct ice_buf_hdr *bh = (struct ice_buf_hdr *)(bufs + i); bool last = ((i + 1) == count); + u32 offset, info; status = ice_aq_update_pkg(hw, bh, le16_to_cpu(bh->data_end), last, &offset, &info, NULL); @@ -987,6 +1058,27 @@ static int ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count) } } + return status; +} + +/** + * ice_update_pkg + * @hw: pointer to the hardware structure + * @bufs: pointer to an array of buffers + * @count: the number of buffers in the array + * + * Obtains change lock and updates package. + */ +static int ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count) +{ + int status; + + status = ice_acquire_change_lock(hw, ICE_RES_WRITE); + if (status) + return status; + + status = ice_update_pkg_no_lock(hw, bufs, count); + ice_release_change_lock(hw); return status; @@ -1080,6 +1172,13 @@ ice_dwnld_cfg_bufs(struct ice_hw *hw, struct ice_buf *bufs, u32 count) 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); + } + ice_release_global_cfg_lock(hw); return state; @@ -1117,6 +1216,7 @@ static enum ice_ddp_state ice_download_pkg(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, @@ -1133,8 +1233,12 @@ ice_download_pkg(struct ice_hw *hw, struct ice_seg *ice_seg) ice_debug(hw, ICE_DBG_PKG, "Seg buf count: %d\n", le32_to_cpu(ice_buf_tbl->buf_count)); - return ice_dwnld_cfg_bufs(hw, ice_buf_tbl->buf_array, - 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; } /** @@ -1701,16 +1805,43 @@ static struct ice_buf_build *ice_pkg_buf_alloc(struct ice_hw *hw) return bld; } +static bool ice_is_gtp_u_profile(u16 prof_idx) +{ + return (prof_idx >= ICE_PROFID_IPV6_GTPU_TEID && + prof_idx <= ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER) || + prof_idx == ICE_PROFID_IPV4_GTPU_TEID; +} + +static bool ice_is_gtp_c_profile(u16 prof_idx) +{ + switch (prof_idx) { + case ICE_PROFID_IPV4_GTPC_TEID: + case ICE_PROFID_IPV4_GTPC_NO_TEID: + case ICE_PROFID_IPV6_GTPC_TEID: + case ICE_PROFID_IPV6_GTPC_NO_TEID: + return true; + default: + return false; + } +} + /** * ice_get_sw_prof_type - determine switch profile type * @hw: pointer to the HW structure * @fv: pointer to the switch field vector + * @prof_idx: profile index to check */ static enum ice_prof_type -ice_get_sw_prof_type(struct ice_hw *hw, struct ice_fv *fv) +ice_get_sw_prof_type(struct ice_hw *hw, struct ice_fv *fv, u32 prof_idx) { u16 i; + if (ice_is_gtp_c_profile(prof_idx)) + return ICE_PROF_TUN_GTPC; + + if (ice_is_gtp_u_profile(prof_idx)) + return ICE_PROF_TUN_GTPU; + for (i = 0; i < hw->blk[ICE_BLK_SW].es.fvw; i++) { /* UDP tunnel will have UDP_OF protocol ID and VNI offset */ if (fv->ew[i].prot_id == (u8)ICE_PROT_UDP_OF && @@ -1757,7 +1888,7 @@ ice_get_sw_fv_bitmap(struct ice_hw *hw, enum ice_prof_type req_profs, if (fv) { /* Determine field vector type */ - prof_type = ice_get_sw_prof_type(hw, fv); + prof_type = ice_get_sw_prof_type(hw, fv, offset); if (req_profs & prof_type) set_bit((u16)offset, bm); @@ -1768,20 +1899,19 @@ ice_get_sw_fv_bitmap(struct ice_hw *hw, enum ice_prof_type req_profs, /** * ice_get_sw_fv_list * @hw: pointer to the HW structure - * @prot_ids: field vector to search for with a given protocol ID - * @ids_cnt: lookup/protocol count + * @lkups: list of protocol types * @bm: bitmap of field vectors to consider * @fv_list: Head of a list * * Finds all the field vector entries from switch block that contain - * a given protocol ID and returns a list of structures of type + * a given protocol ID and offset and returns a list of structures of type * "ice_sw_fv_list_entry". Every structure in the list has a field vector * definition and profile ID information * NOTE: The caller of the function is responsible for freeing the memory * allocated for every list entry. */ int -ice_get_sw_fv_list(struct ice_hw *hw, u8 *prot_ids, u16 ids_cnt, +ice_get_sw_fv_list(struct ice_hw *hw, struct ice_prot_lkup_ext *lkups, unsigned long *bm, struct list_head *fv_list) { struct ice_sw_fv_list_entry *fvl; @@ -1793,7 +1923,7 @@ ice_get_sw_fv_list(struct ice_hw *hw, u8 *prot_ids, u16 ids_cnt, memset(&state, 0, sizeof(state)); - if (!ids_cnt || !hw->seg) + if (!lkups->n_val_words || !hw->seg) return -EINVAL; ice_seg = hw->seg; @@ -1812,20 +1942,17 @@ ice_get_sw_fv_list(struct ice_hw *hw, u8 *prot_ids, u16 ids_cnt, if (!test_bit((u16)offset, bm)) continue; - for (i = 0; i < ids_cnt; i++) { + for (i = 0; i < lkups->n_val_words; i++) { int j; - /* This code assumes that if a switch field vector line - * has a matching protocol, then this line will contain - * the entries necessary to represent every field in - * that protocol header. - */ for (j = 0; j < hw->blk[ICE_BLK_SW].es.fvw; j++) - if (fv->ew[j].prot_id == prot_ids[i]) + if (fv->ew[j].prot_id == + lkups->fv_words[i].prot_id && + fv->ew[j].off == lkups->fv_words[i].off) break; if (j >= hw->blk[ICE_BLK_SW].es.fvw) break; - if (i + 1 == ids_cnt) { + if (i + 1 == lkups->n_val_words) { fvl = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*fvl), GFP_KERNEL); if (!fvl) @@ -1837,8 +1964,11 @@ ice_get_sw_fv_list(struct ice_hw *hw, u8 *prot_ids, u16 ids_cnt, } } } while (fv); - if (list_empty(fv_list)) + if (list_empty(fv_list)) { + dev_warn(ice_hw_to_dev(hw), "Required profiles not found in currently loaded DDP package"); return -EIO; + } + return 0; err: @@ -1897,7 +2027,7 @@ void ice_init_prof_result_bm(struct ice_hw *hw) * * Frees a package buffer */ -static void ice_pkg_buf_free(struct ice_hw *hw, struct ice_buf_build *bld) +void ice_pkg_buf_free(struct ice_hw *hw, struct ice_buf_build *bld) { devm_kfree(ice_hw_to_dev(hw), bld); } @@ -1997,6 +2127,43 @@ ice_pkg_buf_alloc_section(struct ice_buf_build *bld, u32 type, u16 size) } /** + * ice_pkg_buf_alloc_single_section + * @hw: pointer to the HW structure + * @type: the section type value + * @size: the size of the section to reserve (in bytes) + * @section: returns pointer to the section + * + * Allocates a package buffer with a single section. + * Note: all package contents must be in Little Endian form. + */ +struct ice_buf_build * +ice_pkg_buf_alloc_single_section(struct ice_hw *hw, u32 type, u16 size, + void **section) +{ + struct ice_buf_build *buf; + + if (!section) + return NULL; + + buf = ice_pkg_buf_alloc(hw); + if (!buf) + return NULL; + + if (ice_pkg_buf_reserve_section(buf, 1)) + goto ice_pkg_buf_alloc_single_section_err; + + *section = ice_pkg_buf_alloc_section(buf, type, size); + if (!*section) + goto ice_pkg_buf_alloc_single_section_err; + + return buf; + +ice_pkg_buf_alloc_single_section_err: + ice_pkg_buf_free(hw, buf); + return NULL; +} + +/** * ice_pkg_buf_get_active_sections * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc()) * @@ -2023,7 +2190,7 @@ static u16 ice_pkg_buf_get_active_sections(struct ice_buf_build *bld) * * Return a pointer to the buffer's header */ -static struct ice_buf *ice_pkg_buf(struct ice_buf_build *bld) +struct ice_buf *ice_pkg_buf(struct ice_buf_build *bld) { if (!bld) return NULL; @@ -2060,6 +2227,89 @@ ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port, } /** + * ice_upd_dvm_boost_entry + * @hw: pointer to the HW structure + * @entry: pointer to double vlan boost entry info + */ +static int +ice_upd_dvm_boost_entry(struct ice_hw *hw, struct ice_dvm_entry *entry) +{ + struct ice_boost_tcam_section *sect_rx, *sect_tx; + int status = -ENOSPC; + struct ice_buf_build *bld; + u8 val, dc, nm; + + bld = ice_pkg_buf_alloc(hw); + if (!bld) + return -ENOMEM; + + /* allocate 2 sections, one for Rx parser, one for Tx parser */ + if (ice_pkg_buf_reserve_section(bld, 2)) + goto ice_upd_dvm_boost_entry_err; + + sect_rx = ice_pkg_buf_alloc_section(bld, ICE_SID_RXPARSER_BOOST_TCAM, + struct_size(sect_rx, tcam, 1)); + if (!sect_rx) + goto ice_upd_dvm_boost_entry_err; + sect_rx->count = cpu_to_le16(1); + + sect_tx = ice_pkg_buf_alloc_section(bld, ICE_SID_TXPARSER_BOOST_TCAM, + struct_size(sect_tx, tcam, 1)); + if (!sect_tx) + goto ice_upd_dvm_boost_entry_err; + sect_tx->count = cpu_to_le16(1); + + /* copy original boost entry to update package buffer */ + memcpy(sect_rx->tcam, entry->boost_entry, sizeof(*sect_rx->tcam)); + + /* re-write the don't care and never match bits accordingly */ + if (entry->enable) { + /* all bits are don't care */ + val = 0x00; + dc = 0xFF; + nm = 0x00; + } else { + /* disable, one never match bit, the rest are don't care */ + val = 0x00; + dc = 0xF7; + nm = 0x08; + } + + ice_set_key((u8 *)§_rx->tcam[0].key, sizeof(sect_rx->tcam[0].key), + &val, NULL, &dc, &nm, 0, sizeof(u8)); + + /* exact copy of entry to Tx section entry */ + memcpy(sect_tx->tcam, sect_rx->tcam, sizeof(*sect_tx->tcam)); + + status = ice_update_pkg_no_lock(hw, ice_pkg_buf(bld), 1); + +ice_upd_dvm_boost_entry_err: + ice_pkg_buf_free(hw, bld); + + return status; +} + +/** + * ice_set_dvm_boost_entries + * @hw: pointer to the HW structure + * + * Enable double vlan by updating the appropriate boost tcam entries. + */ +int ice_set_dvm_boost_entries(struct ice_hw *hw) +{ + int status; + u16 i; + + for (i = 0; i < hw->dvm_upd.count; i++) { + status = ice_upd_dvm_boost_entry(hw, &hw->dvm_upd.tbl[i]); + if (status) + return status; + } + + return 0; +} + +/** * ice_tunnel_idx_to_entry - convert linear index to the sparse one * @hw: pointer to the HW structure * @type: type of tunnel @@ -2392,7 +2642,7 @@ ice_ptg_remove_ptype(struct ice_hw *hw, enum ice_block blk, u16 ptype, u8 ptg) * * This function will either add or move a ptype to a particular PTG depending * on if the ptype is already part of another group. Note that using a - * a destination PTG ID of ICE_DEFAULT_PTG (0) will move the ptype to the + * destination PTG ID of ICE_DEFAULT_PTG (0) will move the ptype to the * default PTG. */ static int diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h index 6cbc29bcb02f..9c530c86703e 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h @@ -87,8 +87,14 @@ ice_get_sw_fv_bitmap(struct ice_hw *hw, enum ice_prof_type type, void ice_init_prof_result_bm(struct ice_hw *hw); int -ice_get_sw_fv_list(struct ice_hw *hw, u8 *prot_ids, u16 ids_cnt, +ice_get_sw_fv_list(struct ice_hw *hw, struct ice_prot_lkup_ext *lkups, unsigned long *bm, struct list_head *fv_list); +int +ice_pkg_buf_unreserve_section(struct ice_buf_build *bld, u16 count); +u16 ice_pkg_buf_get_free_space(struct ice_buf_build *bld); +int +ice_aq_upload_section(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, + u16 buf_size, struct ice_sq_cd *cd); bool ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port, enum ice_tunnel_type type); @@ -96,6 +102,7 @@ int ice_udp_tunnel_set_port(struct net_device *netdev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti); int ice_udp_tunnel_unset_port(struct net_device *netdev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti); +int ice_set_dvm_boost_entries(struct ice_hw *hw); /* Rx parser PTYPE functions */ bool ice_hw_ptype_ena(struct ice_hw *hw, u16 ptype); @@ -119,4 +126,10 @@ void ice_fill_blk_tbls(struct ice_hw *hw); void ice_clear_hw_tbls(struct ice_hw *hw); void ice_free_hw_tbls(struct ice_hw *hw); int ice_rem_prof(struct ice_hw *hw, enum ice_block blk, u64 id); +struct ice_buf_build * +ice_pkg_buf_alloc_single_section(struct ice_hw *hw, u32 type, u16 size, + void **section); +struct ice_buf *ice_pkg_buf(struct ice_buf_build *bld); +void ice_pkg_buf_free(struct ice_hw *hw, struct ice_buf_build *bld); + #endif /* _ICE_FLEX_PIPE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_flex_type.h b/drivers/net/ethernet/intel/ice/ice_flex_type.h index fc087e0b5292..974d14a83b2e 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_type.h +++ b/drivers/net/ethernet/intel/ice/ice_flex_type.h @@ -162,6 +162,7 @@ struct ice_meta_sect { #define ICE_SID_RXPARSER_MARKER_PTYPE 55 #define ICE_SID_RXPARSER_BOOST_TCAM 56 +#define ICE_SID_RXPARSER_METADATA_INIT 58 #define ICE_SID_TXPARSER_BOOST_TCAM 66 #define ICE_SID_XLT0_PE 80 @@ -416,6 +417,8 @@ enum ice_tunnel_type { TNL_VXLAN = 0, TNL_GENEVE, TNL_GRETAP, + TNL_GTPC, + TNL_GTPU, __TNL_TYPE_CNT, TNL_LAST = 0xFF, TNL_ALL = 0xFF, @@ -442,6 +445,19 @@ struct ice_tunnel_table { u16 valid_count[__TNL_TYPE_CNT]; }; +struct ice_dvm_entry { + u16 boost_addr; + u16 enable; + struct ice_boost_tcam_entry *boost_entry; +}; + +#define ICE_DVM_MAX_ENTRIES 48 + +struct ice_dvm_table { + struct ice_dvm_entry tbl[ICE_DVM_MAX_ENTRIES]; + u16 count; +}; + struct ice_pkg_es { __le16 count; __le16 offset; @@ -659,7 +675,35 @@ enum ice_prof_type { ICE_PROF_NON_TUN = 0x1, ICE_PROF_TUN_UDP = 0x2, ICE_PROF_TUN_GRE = 0x4, - ICE_PROF_TUN_ALL = 0x6, + ICE_PROF_TUN_GTPU = 0x8, + ICE_PROF_TUN_GTPC = 0x10, + ICE_PROF_TUN_ALL = 0x1E, ICE_PROF_ALL = 0xFF, }; + +/* Number of bits/bytes contained in meta init entry. Note, this should be a + * multiple of 32 bits. + */ +#define ICE_META_INIT_BITS 192 +#define ICE_META_INIT_DW_CNT (ICE_META_INIT_BITS / (sizeof(__le32) * \ + BITS_PER_BYTE)) + +/* The meta init Flag field starts at this bit */ +#define ICE_META_FLAGS_ST 123 + +/* The entry and bit to check for Double VLAN Mode (DVM) support */ +#define ICE_META_VLAN_MODE_ENTRY 0 +#define ICE_META_FLAG_VLAN_MODE 60 +#define ICE_META_VLAN_MODE_BIT (ICE_META_FLAGS_ST + \ + ICE_META_FLAG_VLAN_MODE) + +struct ice_meta_init_entry { + __le32 bm[ICE_META_INIT_DW_CNT]; +}; + +struct ice_meta_init_section { + __le16 count; + __le16 offset; + struct ice_meta_init_entry entry; +}; #endif /* _ICE_FLEX_TYPE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_flow.c b/drivers/net/ethernet/intel/ice/ice_flow.c index beed4838dcbe..ef103e47a8dc 100644 --- a/drivers/net/ethernet/intel/ice/ice_flow.c +++ b/drivers/net/ethernet/intel/ice/ice_flow.c @@ -3,6 +3,7 @@ #include "ice_common.h" #include "ice_flow.h" +#include <net/gre.h> /* Describe properties of a protocol header field */ struct ice_flow_field_info { diff --git a/drivers/net/ethernet/intel/ice/ice_flow.h b/drivers/net/ethernet/intel/ice/ice_flow.h index 84b6e4464a21..b465d27d9b80 100644 --- a/drivers/net/ethernet/intel/ice/ice_flow.h +++ b/drivers/net/ethernet/intel/ice/ice_flow.h @@ -4,6 +4,8 @@ #ifndef _ICE_FLOW_H_ #define _ICE_FLOW_H_ +#include "ice_flex_type.h" + #define ICE_FLOW_ENTRY_HANDLE_INVAL 0 #define ICE_FLOW_FLD_OFF_INVAL 0xffff diff --git a/drivers/net/ethernet/intel/ice/ice_fltr.c b/drivers/net/ethernet/intel/ice/ice_fltr.c index c29177c6bb9d..40e678cfb507 100644 --- a/drivers/net/ethernet/intel/ice/ice_fltr.c +++ b/drivers/net/ethernet/intel/ice/ice_fltr.c @@ -58,7 +58,16 @@ int ice_fltr_set_vlan_vsi_promisc(struct ice_hw *hw, struct ice_vsi *vsi, u8 promisc_mask) { - return ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, false); + struct ice_pf *pf = hw->back; + int result; + + result = ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, false); + if (result && result != -EEXIST) + dev_err(ice_pf_to_dev(pf), + "Error setting promisc mode on VSI %i (rc=%d)\n", + vsi->vsi_num, result); + + return result; } /** @@ -73,7 +82,16 @@ int ice_fltr_clear_vlan_vsi_promisc(struct ice_hw *hw, struct ice_vsi *vsi, u8 promisc_mask) { - return ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, true); + struct ice_pf *pf = hw->back; + int result; + + result = ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, true); + if (result && result != -EEXIST) + dev_err(ice_pf_to_dev(pf), + "Error clearing promisc mode on VSI %i (rc=%d)\n", + vsi->vsi_num, result); + + return result; } /** @@ -87,7 +105,16 @@ int ice_fltr_clear_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, u16 vid) { - return ice_clear_vsi_promisc(hw, vsi_handle, promisc_mask, vid); + struct ice_pf *pf = hw->back; + int result; + + result = ice_clear_vsi_promisc(hw, vsi_handle, promisc_mask, vid); + if (result && result != -EEXIST) + dev_err(ice_pf_to_dev(pf), + "Error clearing promisc mode on VSI %i for VID %u (rc=%d)\n", + ice_get_hw_vsi_num(hw, vsi_handle), vid, result); + + return result; } /** @@ -101,7 +128,16 @@ int ice_fltr_set_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, u16 vid) { - return ice_set_vsi_promisc(hw, vsi_handle, promisc_mask, vid); + struct ice_pf *pf = hw->back; + int result; + + result = ice_set_vsi_promisc(hw, vsi_handle, promisc_mask, vid); + if (result && result != -EEXIST) + dev_err(ice_pf_to_dev(pf), + "Error setting promisc mode on VSI %i for VID %u (rc=%d)\n", + ice_get_hw_vsi_num(hw, vsi_handle), vid, result); + + return result; } /** @@ -203,21 +239,22 @@ ice_fltr_add_mac_to_list(struct ice_vsi *vsi, struct list_head *list, * ice_fltr_add_vlan_to_list - add VLAN filter info to exsisting list * @vsi: pointer to VSI struct * @list: list to add filter info to - * @vlan_id: VLAN ID to add - * @action: filter action + * @vlan: VLAN filter details */ static int ice_fltr_add_vlan_to_list(struct ice_vsi *vsi, struct list_head *list, - u16 vlan_id, enum ice_sw_fwd_act_type action) + struct ice_vlan *vlan) { struct ice_fltr_info info = { 0 }; info.flag = ICE_FLTR_TX; info.src_id = ICE_SRC_ID_VSI; info.lkup_type = ICE_SW_LKUP_VLAN; - info.fltr_act = action; + info.fltr_act = ICE_FWD_TO_VSI; info.vsi_handle = vsi->idx; - info.l_data.vlan.vlan_id = vlan_id; + info.l_data.vlan.vlan_id = vlan->vid; + info.l_data.vlan.tpid = vlan->tpid; + info.l_data.vlan.tpid_valid = true; return ice_fltr_add_entry_to_list(ice_pf_to_dev(vsi->back), &info, list); @@ -310,19 +347,17 @@ ice_fltr_prepare_mac_and_broadcast(struct ice_vsi *vsi, const u8 *mac, /** * ice_fltr_prepare_vlan - add or remove VLAN filter * @vsi: pointer to VSI struct - * @vlan_id: VLAN ID to add - * @action: action to be performed on filter match + * @vlan: VLAN filter details * @vlan_action: pointer to add or remove VLAN function */ static int -ice_fltr_prepare_vlan(struct ice_vsi *vsi, u16 vlan_id, - enum ice_sw_fwd_act_type action, +ice_fltr_prepare_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan, int (*vlan_action)(struct ice_vsi *, struct list_head *)) { LIST_HEAD(tmp_list); int result; - if (ice_fltr_add_vlan_to_list(vsi, &tmp_list, vlan_id, action)) + if (ice_fltr_add_vlan_to_list(vsi, &tmp_list, vlan)) return -ENOMEM; result = vlan_action(vsi, &tmp_list); @@ -395,27 +430,21 @@ int ice_fltr_remove_mac(struct ice_vsi *vsi, const u8 *mac, /** * ice_fltr_add_vlan - add single VLAN filter * @vsi: pointer to VSI struct - * @vlan_id: VLAN ID to add - * @action: action to be performed on filter match + * @vlan: VLAN filter details */ -int ice_fltr_add_vlan(struct ice_vsi *vsi, u16 vlan_id, - enum ice_sw_fwd_act_type action) +int ice_fltr_add_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) { - return ice_fltr_prepare_vlan(vsi, vlan_id, action, - ice_fltr_add_vlan_list); + return ice_fltr_prepare_vlan(vsi, vlan, ice_fltr_add_vlan_list); } /** * ice_fltr_remove_vlan - remove VLAN filter * @vsi: pointer to VSI struct - * @vlan_id: filter VLAN to remove - * @action: action to remove + * @vlan: VLAN filter details */ -int ice_fltr_remove_vlan(struct ice_vsi *vsi, u16 vlan_id, - enum ice_sw_fwd_act_type action) +int ice_fltr_remove_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) { - return ice_fltr_prepare_vlan(vsi, vlan_id, action, - ice_fltr_remove_vlan_list); + return ice_fltr_prepare_vlan(vsi, vlan, ice_fltr_remove_vlan_list); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_fltr.h b/drivers/net/ethernet/intel/ice/ice_fltr.h index 3eb42479175f..0f3dbc308eec 100644 --- a/drivers/net/ethernet/intel/ice/ice_fltr.h +++ b/drivers/net/ethernet/intel/ice/ice_fltr.h @@ -4,6 +4,8 @@ #ifndef _ICE_FLTR_H_ #define _ICE_FLTR_H_ +#include "ice_vlan.h" + void ice_fltr_free_list(struct device *dev, struct list_head *h); int ice_fltr_set_vlan_vsi_promisc(struct ice_hw *hw, struct ice_vsi *vsi, @@ -32,12 +34,8 @@ ice_fltr_remove_mac(struct ice_vsi *vsi, const u8 *mac, enum ice_sw_fwd_act_type action); int ice_fltr_remove_mac_list(struct ice_vsi *vsi, struct list_head *list); -int -ice_fltr_add_vlan(struct ice_vsi *vsi, u16 vid, - enum ice_sw_fwd_act_type action); -int -ice_fltr_remove_vlan(struct ice_vsi *vsi, u16 vid, - enum ice_sw_fwd_act_type action); +int ice_fltr_add_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan); +int ice_fltr_remove_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan); int ice_fltr_add_eth(struct ice_vsi *vsi, u16 ethertype, u16 flag, diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.c b/drivers/net/ethernet/intel/ice/ice_fw_update.c index 665a344fb9c0..3dc5662d62a6 100644 --- a/drivers/net/ethernet/intel/ice/ice_fw_update.c +++ b/drivers/net/ethernet/intel/ice/ice_fw_update.c @@ -736,7 +736,87 @@ static int ice_finalize_update(struct pldmfw *context) return 0; } -static const struct pldmfw_ops ice_fwu_ops = { +struct ice_pldm_pci_record_id { + u32 vendor; + u32 device; + u32 subsystem_vendor; + u32 subsystem_device; +}; + +/** + * ice_op_pci_match_record - Check if a PCI device matches the record + * @context: PLDM fw update structure + * @record: list of records extracted from the PLDM image + * + * Determine if the PCI device associated with this device matches the record + * data provided. + * + * Searches the descriptor TLVs and extracts the relevant descriptor data into + * a pldm_pci_record_id. This is then compared against the PCI device ID + * information. + * + * Returns: true if the device matches the record, false otherwise. + */ +static bool +ice_op_pci_match_record(struct pldmfw *context, struct pldmfw_record *record) +{ + struct pci_dev *pdev = to_pci_dev(context->dev); + struct ice_pldm_pci_record_id id = { + .vendor = PCI_ANY_ID, + .device = PCI_ANY_ID, + .subsystem_vendor = PCI_ANY_ID, + .subsystem_device = PCI_ANY_ID, + }; + struct pldmfw_desc_tlv *desc; + + list_for_each_entry(desc, &record->descs, entry) { + u16 value; + int *ptr; + + switch (desc->type) { + case PLDM_DESC_ID_PCI_VENDOR_ID: + ptr = &id.vendor; + break; + case PLDM_DESC_ID_PCI_DEVICE_ID: + ptr = &id.device; + break; + case PLDM_DESC_ID_PCI_SUBVENDOR_ID: + ptr = &id.subsystem_vendor; + break; + case PLDM_DESC_ID_PCI_SUBDEV_ID: + ptr = &id.subsystem_device; + break; + default: + /* Skip unrelated TLVs */ + continue; + } + + value = get_unaligned_le16(desc->data); + /* A value of zero for one of the descriptors is sometimes + * used when the record should ignore this field when matching + * device. For example if the record applies to any subsystem + * device or vendor. + */ + if (value) + *ptr = value; + else + *ptr = PCI_ANY_ID; + } + + /* the E822 device can have a generic device ID so check for that */ + if ((id.vendor == PCI_ANY_ID || id.vendor == pdev->vendor) && + (id.device == PCI_ANY_ID || id.device == pdev->device || + id.device == ICE_DEV_ID_E822_SI_DFLT) && + (id.subsystem_vendor == PCI_ANY_ID || + id.subsystem_vendor == pdev->subsystem_vendor) && + (id.subsystem_device == PCI_ANY_ID || + id.subsystem_device == pdev->subsystem_device)) + return true; + + return false; +} + +static const struct pldmfw_ops ice_fwu_ops_e810 = { .match_record = &pldmfw_op_pci_match_record, .send_package_data = &ice_send_package_data, .send_component_table = &ice_send_component_table, @@ -744,6 +824,14 @@ static const struct pldmfw_ops ice_fwu_ops = { .finalize_update = &ice_finalize_update, }; +static const struct pldmfw_ops ice_fwu_ops_e822 = { + .match_record = &ice_op_pci_match_record, + .send_package_data = &ice_send_package_data, + .send_component_table = &ice_send_component_table, + .flash_component = &ice_flash_component, + .finalize_update = &ice_finalize_update, +}; + /** * ice_get_pending_updates - Check if the component has a pending update * @pf: the PF driver structure @@ -921,7 +1009,11 @@ int ice_devlink_flash_update(struct devlink *devlink, memset(&priv, 0, sizeof(priv)); - priv.context.ops = &ice_fwu_ops; + /* the E822 device needs a slightly different ops */ + if (hw->mac_type == ICE_MAC_GENERIC) + priv.context.ops = &ice_fwu_ops_e822; + else + priv.context.ops = &ice_fwu_ops_e810; priv.context.dev = dev; priv.extack = extack; priv.pf = pf; diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.c b/drivers/net/ethernet/intel/ice/ice_gnss.c new file mode 100644 index 000000000000..b5a7f246d230 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_gnss.c @@ -0,0 +1,566 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2021-2022, Intel Corporation. */ + +#include "ice.h" +#include "ice_lib.h" +#include <linux/tty_driver.h> + +/** + * ice_gnss_do_write - Write data to internal GNSS + * @pf: board private structure + * @buf: command buffer + * @size: command buffer size + * + * Write UBX command data to the GNSS receiver + */ +static unsigned int +ice_gnss_do_write(struct ice_pf *pf, unsigned char *buf, unsigned int size) +{ + struct ice_aqc_link_topo_addr link_topo; + struct ice_hw *hw = &pf->hw; + unsigned int offset = 0; + int err = 0; + + memset(&link_topo, 0, sizeof(struct ice_aqc_link_topo_addr)); + link_topo.topo_params.index = ICE_E810T_GNSS_I2C_BUS; + link_topo.topo_params.node_type_ctx |= + FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, + ICE_AQC_LINK_TOPO_NODE_CTX_OVERRIDE); + + /* It's not possible to write a single byte to u-blox. + * Write all bytes in a loop until there are 6 or less bytes left. If + * there are exactly 6 bytes left, the last write would be only a byte. + * In this case, do 4+2 bytes writes instead of 5+1. Otherwise, do the + * last 2 to 5 bytes write. + */ + while (size - offset > ICE_GNSS_UBX_WRITE_BYTES + 1) { + err = ice_aq_write_i2c(hw, link_topo, ICE_GNSS_UBX_I2C_BUS_ADDR, + cpu_to_le16(buf[offset]), + ICE_MAX_I2C_WRITE_BYTES, + &buf[offset + 1], NULL); + if (err) + goto err_out; + + offset += ICE_GNSS_UBX_WRITE_BYTES; + } + + /* Single byte would be written. Write 4 bytes instead of 5. */ + if (size - offset == ICE_GNSS_UBX_WRITE_BYTES + 1) { + err = ice_aq_write_i2c(hw, link_topo, ICE_GNSS_UBX_I2C_BUS_ADDR, + cpu_to_le16(buf[offset]), + ICE_MAX_I2C_WRITE_BYTES - 1, + &buf[offset + 1], NULL); + if (err) + goto err_out; + + offset += ICE_GNSS_UBX_WRITE_BYTES - 1; + } + + /* Do the last write, 2 to 5 bytes. */ + err = ice_aq_write_i2c(hw, link_topo, ICE_GNSS_UBX_I2C_BUS_ADDR, + cpu_to_le16(buf[offset]), size - offset - 1, + &buf[offset + 1], NULL); + if (err) + goto err_out; + + return size; + +err_out: + dev_err(ice_pf_to_dev(pf), "GNSS failed to write, offset=%u, size=%u, err=%d\n", + offset, size, err); + + return offset; +} + +/** + * ice_gnss_write_pending - Write all pending data to internal GNSS + * @work: GNSS write work structure + */ +static void ice_gnss_write_pending(struct kthread_work *work) +{ + struct gnss_serial *gnss = container_of(work, struct gnss_serial, + write_work); + struct ice_pf *pf = gnss->back; + + if (!list_empty(&gnss->queue)) { + struct gnss_write_buf *write_buf = NULL; + unsigned int bytes; + + write_buf = list_first_entry(&gnss->queue, + struct gnss_write_buf, queue); + + bytes = ice_gnss_do_write(pf, write_buf->buf, write_buf->size); + dev_dbg(ice_pf_to_dev(pf), "%u bytes written to GNSS\n", bytes); + + list_del(&write_buf->queue); + kfree(write_buf->buf); + kfree(write_buf); + } +} + +/** + * ice_gnss_read - Read data from internal GNSS module + * @work: GNSS read work structure + * + * Read the data from internal GNSS receiver, number of bytes read will be + * returned in *read_data parameter. + */ +static void ice_gnss_read(struct kthread_work *work) +{ + struct gnss_serial *gnss = container_of(work, struct gnss_serial, + read_work.work); + struct ice_aqc_link_topo_addr link_topo; + unsigned int i, bytes_read, data_len; + struct tty_port *port; + struct ice_pf *pf; + struct ice_hw *hw; + __be16 data_len_b; + char *buf = NULL; + u8 i2c_params; + int err = 0; + + pf = gnss->back; + if (!pf || !gnss->tty || !gnss->tty->port) { + err = -EFAULT; + goto exit; + } + + hw = &pf->hw; + port = gnss->tty->port; + + buf = (char *)get_zeroed_page(GFP_KERNEL); + if (!buf) { + err = -ENOMEM; + goto exit; + } + + memset(&link_topo, 0, sizeof(struct ice_aqc_link_topo_addr)); + link_topo.topo_params.index = ICE_E810T_GNSS_I2C_BUS; + link_topo.topo_params.node_type_ctx |= + FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, + ICE_AQC_LINK_TOPO_NODE_CTX_OVERRIDE); + + i2c_params = ICE_GNSS_UBX_DATA_LEN_WIDTH | + ICE_AQC_I2C_USE_REPEATED_START; + + /* Read data length in a loop, when it's not 0 the data is ready */ + for (i = 0; i < ICE_MAX_UBX_READ_TRIES; i++) { + err = ice_aq_read_i2c(hw, link_topo, ICE_GNSS_UBX_I2C_BUS_ADDR, + cpu_to_le16(ICE_GNSS_UBX_DATA_LEN_H), + i2c_params, (u8 *)&data_len_b, NULL); + if (err) + goto exit_buf; + + data_len = be16_to_cpu(data_len_b); + if (data_len != 0 && data_len != U16_MAX) + break; + + mdelay(10); + } + + data_len = min_t(typeof(data_len), data_len, PAGE_SIZE); + data_len = tty_buffer_request_room(port, data_len); + if (!data_len) { + err = -ENOMEM; + goto exit_buf; + } + + /* Read received data */ + for (i = 0; i < data_len; i += bytes_read) { + unsigned int bytes_left = data_len - i; + + bytes_read = min_t(typeof(bytes_left), bytes_left, + ICE_MAX_I2C_DATA_SIZE); + + err = ice_aq_read_i2c(hw, link_topo, ICE_GNSS_UBX_I2C_BUS_ADDR, + cpu_to_le16(ICE_GNSS_UBX_EMPTY_DATA), + bytes_read, &buf[i], NULL); + if (err) + goto exit_buf; + } + + /* Send the data to the tty layer for users to read. This doesn't + * actually push the data through unless tty->low_latency is set. + */ + tty_insert_flip_string(port, buf, i); + tty_flip_buffer_push(port); + +exit_buf: + free_page((unsigned long)buf); + kthread_queue_delayed_work(gnss->kworker, &gnss->read_work, + ICE_GNSS_TIMER_DELAY_TIME); +exit: + if (err) + dev_dbg(ice_pf_to_dev(pf), "GNSS failed to read err=%d\n", err); +} + +/** + * ice_gnss_struct_init - Initialize GNSS structure for the TTY + * @pf: Board private structure + * @index: TTY device index + */ +static struct gnss_serial *ice_gnss_struct_init(struct ice_pf *pf, int index) +{ + struct device *dev = ice_pf_to_dev(pf); + struct kthread_worker *kworker; + struct gnss_serial *gnss; + + gnss = kzalloc(sizeof(*gnss), GFP_KERNEL); + if (!gnss) + return NULL; + + mutex_init(&gnss->gnss_mutex); + gnss->open_count = 0; + gnss->back = pf; + pf->gnss_serial[index] = gnss; + + kthread_init_delayed_work(&gnss->read_work, ice_gnss_read); + INIT_LIST_HEAD(&gnss->queue); + kthread_init_work(&gnss->write_work, ice_gnss_write_pending); + /* Allocate a kworker for handling work required for the GNSS TTY + * writes. + */ + kworker = kthread_create_worker(0, "ice-gnss-%s", dev_name(dev)); + if (IS_ERR(kworker)) { + kfree(gnss); + return NULL; + } + + gnss->kworker = kworker; + + return gnss; +} + +/** + * ice_gnss_tty_open - Initialize GNSS structures on TTY device open + * @tty: pointer to the tty_struct + * @filp: pointer to the file + * + * This routine is mandatory. If this routine is not filled in, the attempted + * open will fail with ENODEV. + */ +static int ice_gnss_tty_open(struct tty_struct *tty, struct file *filp) +{ + struct gnss_serial *gnss; + struct ice_pf *pf; + + pf = (struct ice_pf *)tty->driver->driver_state; + if (!pf) + return -EFAULT; + + /* Clear the pointer in case something fails */ + tty->driver_data = NULL; + + /* Get the serial object associated with this tty pointer */ + gnss = pf->gnss_serial[tty->index]; + if (!gnss) { + /* Initialize GNSS struct on the first device open */ + gnss = ice_gnss_struct_init(pf, tty->index); + if (!gnss) + return -ENOMEM; + } + + mutex_lock(&gnss->gnss_mutex); + + /* Save our structure within the tty structure */ + tty->driver_data = gnss; + gnss->tty = tty; + gnss->open_count++; + kthread_queue_delayed_work(gnss->kworker, &gnss->read_work, 0); + + mutex_unlock(&gnss->gnss_mutex); + + return 0; +} + +/** + * ice_gnss_tty_close - Cleanup GNSS structures on tty device close + * @tty: pointer to the tty_struct + * @filp: pointer to the file + */ +static void ice_gnss_tty_close(struct tty_struct *tty, struct file *filp) +{ + struct gnss_serial *gnss = tty->driver_data; + struct ice_pf *pf; + + if (!gnss) + return; + + pf = (struct ice_pf *)tty->driver->driver_state; + if (!pf) + return; + + mutex_lock(&gnss->gnss_mutex); + + if (!gnss->open_count) { + /* Port was never opened */ + dev_err(ice_pf_to_dev(pf), "GNSS port not opened\n"); + goto exit; + } + + gnss->open_count--; + if (gnss->open_count <= 0) { + /* Port is in shutdown state */ + kthread_cancel_delayed_work_sync(&gnss->read_work); + } +exit: + mutex_unlock(&gnss->gnss_mutex); +} + +/** + * ice_gnss_tty_write - Write GNSS data + * @tty: pointer to the tty_struct + * @buf: pointer to the user data + * @count: the number of characters queued to be sent to the HW + * + * The write function call is called by the user when there is data to be sent + * to the hardware. First the tty core receives the call, and then it passes the + * data on to the tty driver's write function. The tty core also tells the tty + * driver the size of the data being sent. + * If any errors happen during the write call, a negative error value should be + * returned instead of the number of characters queued to be written. + */ +static int +ice_gnss_tty_write(struct tty_struct *tty, const unsigned char *buf, int count) +{ + struct gnss_write_buf *write_buf; + struct gnss_serial *gnss; + unsigned char *cmd_buf; + struct ice_pf *pf; + int err = count; + + /* We cannot write a single byte using our I2C implementation. */ + if (count <= 1 || count > ICE_GNSS_TTY_WRITE_BUF) + return -EINVAL; + + gnss = tty->driver_data; + if (!gnss) + return -EFAULT; + + pf = (struct ice_pf *)tty->driver->driver_state; + if (!pf) + return -EFAULT; + + /* Only allow to write on TTY 0 */ + if (gnss != pf->gnss_serial[0]) + return -EIO; + + mutex_lock(&gnss->gnss_mutex); + + if (!gnss->open_count) { + err = -EINVAL; + goto exit; + } + + cmd_buf = kcalloc(count, sizeof(*buf), GFP_KERNEL); + if (!cmd_buf) { + err = -ENOMEM; + goto exit; + } + + memcpy(cmd_buf, buf, count); + + /* Send the data out to a hardware port */ + write_buf = kzalloc(sizeof(*write_buf), GFP_KERNEL); + if (!write_buf) { + err = -ENOMEM; + goto exit; + } + + write_buf->buf = cmd_buf; + write_buf->size = count; + INIT_LIST_HEAD(&write_buf->queue); + list_add_tail(&write_buf->queue, &gnss->queue); + kthread_queue_work(gnss->kworker, &gnss->write_work); +exit: + mutex_unlock(&gnss->gnss_mutex); + return err; +} + +/** + * ice_gnss_tty_write_room - Returns the numbers of characters to be written. + * @tty: pointer to the tty_struct + * + * This routine returns the numbers of characters the tty driver will accept + * for queuing to be written or 0 if either the TTY is not open or user + * tries to write to the TTY other than the first. + */ +static unsigned int ice_gnss_tty_write_room(struct tty_struct *tty) +{ + struct gnss_serial *gnss = tty->driver_data; + + /* Only allow to write on TTY 0 */ + if (!gnss || gnss != gnss->back->gnss_serial[0]) + return 0; + + mutex_lock(&gnss->gnss_mutex); + + if (!gnss->open_count) { + mutex_unlock(&gnss->gnss_mutex); + return 0; + } + + mutex_unlock(&gnss->gnss_mutex); + return ICE_GNSS_TTY_WRITE_BUF; +} + +static const struct tty_operations tty_gps_ops = { + .open = ice_gnss_tty_open, + .close = ice_gnss_tty_close, + .write = ice_gnss_tty_write, + .write_room = ice_gnss_tty_write_room, +}; + +/** + * ice_gnss_create_tty_driver - Create a TTY driver for GNSS + * @pf: Board private structure + */ +static struct tty_driver *ice_gnss_create_tty_driver(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + const int ICE_TTYDRV_NAME_MAX = 14; + struct tty_driver *tty_driver; + char *ttydrv_name; + unsigned int i; + int err; + + tty_driver = tty_alloc_driver(ICE_GNSS_TTY_MINOR_DEVICES, + TTY_DRIVER_REAL_RAW); + if (IS_ERR(tty_driver)) { + dev_err(dev, "Failed to allocate memory for GNSS TTY\n"); + return NULL; + } + + ttydrv_name = kzalloc(ICE_TTYDRV_NAME_MAX, GFP_KERNEL); + if (!ttydrv_name) { + tty_driver_kref_put(tty_driver); + return NULL; + } + + snprintf(ttydrv_name, ICE_TTYDRV_NAME_MAX, "ttyGNSS_%02x%02x_", + (u8)pf->pdev->bus->number, (u8)PCI_SLOT(pf->pdev->devfn)); + + /* Initialize the tty driver*/ + tty_driver->owner = THIS_MODULE; + tty_driver->driver_name = dev_driver_string(dev); + tty_driver->name = (const char *)ttydrv_name; + tty_driver->type = TTY_DRIVER_TYPE_SERIAL; + tty_driver->subtype = SERIAL_TYPE_NORMAL; + tty_driver->init_termios = tty_std_termios; + tty_driver->init_termios.c_iflag &= ~INLCR; + tty_driver->init_termios.c_iflag |= IGNCR; + tty_driver->init_termios.c_oflag &= ~OPOST; + tty_driver->init_termios.c_lflag &= ~ICANON; + tty_driver->init_termios.c_cflag &= ~(CSIZE | CBAUD | CBAUDEX); + /* baud rate 9600 */ + tty_termios_encode_baud_rate(&tty_driver->init_termios, 9600, 9600); + tty_driver->driver_state = pf; + tty_set_operations(tty_driver, &tty_gps_ops); + + for (i = 0; i < ICE_GNSS_TTY_MINOR_DEVICES; i++) { + pf->gnss_tty_port[i] = kzalloc(sizeof(*pf->gnss_tty_port[i]), + GFP_KERNEL); + pf->gnss_serial[i] = NULL; + + tty_port_init(pf->gnss_tty_port[i]); + tty_port_link_device(pf->gnss_tty_port[i], tty_driver, i); + } + + err = tty_register_driver(tty_driver); + if (err) { + dev_err(dev, "Failed to register TTY driver err=%d\n", err); + + for (i = 0; i < ICE_GNSS_TTY_MINOR_DEVICES; i++) { + tty_port_destroy(pf->gnss_tty_port[i]); + kfree(pf->gnss_tty_port[i]); + } + kfree(ttydrv_name); + tty_driver_kref_put(pf->ice_gnss_tty_driver); + + return NULL; + } + + for (i = 0; i < ICE_GNSS_TTY_MINOR_DEVICES; i++) + dev_info(dev, "%s%d registered\n", ttydrv_name, i); + + return tty_driver; +} + +/** + * ice_gnss_init - Initialize GNSS TTY support + * @pf: Board private structure + */ +void ice_gnss_init(struct ice_pf *pf) +{ + struct tty_driver *tty_driver; + + tty_driver = ice_gnss_create_tty_driver(pf); + if (!tty_driver) + return; + + pf->ice_gnss_tty_driver = tty_driver; + + set_bit(ICE_FLAG_GNSS, pf->flags); + dev_info(ice_pf_to_dev(pf), "GNSS TTY init successful\n"); +} + +/** + * ice_gnss_exit - Disable GNSS TTY support + * @pf: Board private structure + */ +void ice_gnss_exit(struct ice_pf *pf) +{ + unsigned int i; + + if (!test_bit(ICE_FLAG_GNSS, pf->flags) || !pf->ice_gnss_tty_driver) + return; + + for (i = 0; i < ICE_GNSS_TTY_MINOR_DEVICES; i++) { + if (pf->gnss_tty_port[i]) { + tty_port_destroy(pf->gnss_tty_port[i]); + kfree(pf->gnss_tty_port[i]); + } + + if (pf->gnss_serial[i]) { + struct gnss_serial *gnss = pf->gnss_serial[i]; + + kthread_cancel_work_sync(&gnss->write_work); + kthread_cancel_delayed_work_sync(&gnss->read_work); + kfree(gnss); + pf->gnss_serial[i] = NULL; + } + } + + tty_unregister_driver(pf->ice_gnss_tty_driver); + kfree(pf->ice_gnss_tty_driver->name); + tty_driver_kref_put(pf->ice_gnss_tty_driver); + pf->ice_gnss_tty_driver = NULL; +} + +/** + * ice_gnss_is_gps_present - Check if GPS HW is present + * @hw: pointer to HW struct + */ +bool ice_gnss_is_gps_present(struct ice_hw *hw) +{ + if (!hw->func_caps.ts_func_info.src_tmr_owned) + return false; + +#if IS_ENABLED(CONFIG_PTP_1588_CLOCK) + if (ice_is_e810t(hw)) { + int err; + u8 data; + + err = ice_read_pca9575_reg_e810t(hw, ICE_PCA9575_P0_IN, &data); + if (err || !!(data & ICE_E810T_P0_GNSS_PRSNT_N)) + return false; + } else { + return false; + } +#else + if (!ice_is_e810t(hw)) + return false; +#endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ + + return true; +} diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.h b/drivers/net/ethernet/intel/ice/ice_gnss.h new file mode 100644 index 000000000000..f454dd1d9285 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_gnss.h @@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2021-2022, Intel Corporation. */ + +#ifndef _ICE_GNSS_H_ +#define _ICE_GNSS_H_ + +#include <linux/tty.h> +#include <linux/tty_flip.h> + +#define ICE_E810T_GNSS_I2C_BUS 0x2 +#define ICE_GNSS_TIMER_DELAY_TIME (HZ / 10) /* 0.1 second per message */ +/* Create 2 minor devices, both using the same GNSS module. First one is RW, + * second one RO. + */ +#define ICE_GNSS_TTY_MINOR_DEVICES 2 +#define ICE_GNSS_TTY_WRITE_BUF 250 +#define ICE_MAX_I2C_DATA_SIZE FIELD_MAX(ICE_AQC_I2C_DATA_SIZE_M) +#define ICE_MAX_I2C_WRITE_BYTES 4 + +/* u-blox ZED-F9T specific definitions */ +#define ICE_GNSS_UBX_I2C_BUS_ADDR 0x42 +/* Data length register is big endian */ +#define ICE_GNSS_UBX_DATA_LEN_H 0xFD +#define ICE_GNSS_UBX_DATA_LEN_WIDTH 2 +#define ICE_GNSS_UBX_EMPTY_DATA 0xFF +/* For u-blox writes are performed without address so the first byte to write is + * passed as I2C addr parameter. + */ +#define ICE_GNSS_UBX_WRITE_BYTES (ICE_MAX_I2C_WRITE_BYTES + 1) +#define ICE_MAX_UBX_READ_TRIES 255 +#define ICE_MAX_UBX_ACK_READ_TRIES 4095 + +struct gnss_write_buf { + struct list_head queue; + unsigned int size; + unsigned char *buf; +}; + + +/** + * struct gnss_serial - data used to initialize GNSS TTY port + * @back: back pointer to PF + * @tty: pointer to the tty for this device + * @open_count: number of times this port has been opened + * @gnss_mutex: gnss_mutex used to protect GNSS serial operations + * @kworker: kwork thread for handling periodic work + * @read_work: read_work function for handling GNSS reads + * @write_work: write_work function for handling GNSS writes + * @queue: write buffers queue + */ +struct gnss_serial { + struct ice_pf *back; + struct tty_struct *tty; + int open_count; + struct mutex gnss_mutex; /* protects GNSS serial structure */ + struct kthread_worker *kworker; + struct kthread_delayed_work read_work; + struct kthread_work write_work; + struct list_head queue; +}; + +#if IS_ENABLED(CONFIG_TTY) +void ice_gnss_init(struct ice_pf *pf); +void ice_gnss_exit(struct ice_pf *pf); +bool ice_gnss_is_gps_present(struct ice_hw *hw); +#else +static inline void ice_gnss_init(struct ice_pf *pf) { } +static inline void ice_gnss_exit(struct ice_pf *pf) { } +static inline bool ice_gnss_is_gps_present(struct ice_hw *hw) +{ + return false; +} +#endif /* IS_ENABLED(CONFIG_TTY) */ +#endif /* _ICE_GNSS_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c index fc3580167e7b..895c32bcc8b5 100644 --- a/drivers/net/ethernet/intel/ice/ice_idc.c +++ b/drivers/net/ethernet/intel/ice/ice_idc.c @@ -34,29 +34,20 @@ void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_event *event) { struct iidc_auxiliary_drv *iadrv; - if (!pf->adev) + if (WARN_ON_ONCE(!in_task())) return; + mutex_lock(&pf->adev_mutex); + if (!pf->adev) + goto finish; + device_lock(&pf->adev->dev); iadrv = ice_get_auxiliary_drv(pf); if (iadrv && iadrv->event_handler) iadrv->event_handler(pf, event); device_unlock(&pf->adev->dev); -} - -/** - * ice_find_vsi - Find the VSI from VSI ID - * @pf: The PF pointer to search in - * @vsi_num: The VSI ID to search for - */ -static struct ice_vsi *ice_find_vsi(struct ice_pf *pf, u16 vsi_num) -{ - int i; - - ice_for_each_vsi(pf, i) - if (pf->vsi[i] && pf->vsi[i]->vsi_num == vsi_num) - return pf->vsi[i]; - return NULL; +finish: + mutex_unlock(&pf->adev_mutex); } /** @@ -79,7 +70,7 @@ int ice_add_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset) dev = ice_pf_to_dev(pf); - if (!test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) + if (!ice_is_rdma_ena(pf)) return -EINVAL; vsi = ice_get_main_vsi(pf); @@ -227,6 +218,11 @@ void ice_get_qos_params(struct ice_pf *pf, struct iidc_qos_params *qos) for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) qos->tc_info[i].rel_bw = dcbx_cfg->etscfg.tcbwtable[i]; + + qos->pfc_mode = dcbx_cfg->pfc_mode; + if (qos->pfc_mode == IIDC_DSCP_PFC_MODE) + for (i = 0; i < IIDC_MAX_DSCP_MAPPING; i++) + qos->dscp_map[i] = dcbx_cfg->dscp_map[i]; } EXPORT_SYMBOL_GPL(ice_get_qos_params); @@ -236,7 +232,7 @@ EXPORT_SYMBOL_GPL(ice_get_qos_params); */ static int ice_reserve_rdma_qvector(struct ice_pf *pf) { - if (test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) { + if (ice_is_rdma_ena(pf)) { int index; index = ice_get_res(pf, pf->irq_tracker, pf->num_rdma_msix, @@ -274,7 +270,7 @@ int ice_plug_aux_dev(struct ice_pf *pf) /* if this PF doesn't support a technology that requires auxiliary * devices, then gracefully exit */ - if (!ice_is_aux_ena(pf)) + if (!ice_is_rdma_ena(pf)) return 0; iadev = kzalloc(sizeof(*iadev), GFP_KERNEL); @@ -282,7 +278,6 @@ int ice_plug_aux_dev(struct ice_pf *pf) return -ENOMEM; adev = &iadev->adev; - pf->adev = adev; iadev->pf = pf; adev->id = pf->aux_idx; @@ -292,18 +287,20 @@ int ice_plug_aux_dev(struct ice_pf *pf) ret = auxiliary_device_init(adev); if (ret) { - pf->adev = NULL; kfree(iadev); return ret; } ret = auxiliary_device_add(adev); if (ret) { - pf->adev = NULL; auxiliary_device_uninit(adev); return ret; } + mutex_lock(&pf->adev_mutex); + pf->adev = adev; + mutex_unlock(&pf->adev_mutex); + return 0; } @@ -312,12 +309,17 @@ int ice_plug_aux_dev(struct ice_pf *pf) */ void ice_unplug_aux_dev(struct ice_pf *pf) { - if (!pf->adev) - return; + struct auxiliary_device *adev; - auxiliary_device_delete(pf->adev); - auxiliary_device_uninit(pf->adev); + mutex_lock(&pf->adev_mutex); + adev = pf->adev; pf->adev = NULL; + mutex_unlock(&pf->adev_mutex); + + if (adev) { + auxiliary_device_delete(adev); + auxiliary_device_uninit(adev); + } } /** diff --git a/drivers/net/ethernet/intel/ice/ice_idc_int.h b/drivers/net/ethernet/intel/ice/ice_idc_int.h index b7796b8aecbd..4b0c86757df9 100644 --- a/drivers/net/ethernet/intel/ice/ice_idc_int.h +++ b/drivers/net/ethernet/intel/ice/ice_idc_int.h @@ -5,7 +5,6 @@ #define _ICE_IDC_INT_H_ #include <linux/net/intel/iidc.h> -#include "ice.h" struct ice_pf; diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c index e375ac849aec..ee5b36941ba3 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.c +++ b/drivers/net/ethernet/intel/ice/ice_lag.c @@ -61,13 +61,13 @@ static void ice_lag_set_backup(struct ice_lag *lag) */ static void ice_display_lag_info(struct ice_lag *lag) { - const char *name, *peer, *upper, *role, *bonded, *master; + const char *name, *peer, *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"; - master = lag->master ? "TRUE" : "FALSE"; + primary = lag->primary ? "TRUE" : "FALSE"; bonded = lag->bonded ? "BONDED" : "UNBONDED"; switch (lag->role) { @@ -87,8 +87,8 @@ static void ice_display_lag_info(struct ice_lag *lag) role = "ERROR"; } - dev_dbg(dev, "%s %s, peer:%s, upper:%s, role:%s, master:%s\n", name, - bonded, peer, upper, role, master); + dev_dbg(dev, "%s %s, peer:%s, upper:%s, role:%s, primary:%s\n", name, + bonded, peer, upper, role, primary); } /** @@ -119,7 +119,7 @@ static void ice_lag_info_event(struct ice_lag *lag, void *ptr) } if (strcmp(bonding_info->slave.slave_name, lag_netdev_name)) { - netdev_dbg(lag->netdev, "Bonding event recv, but slave info not for us\n"); + netdev_dbg(lag->netdev, "Bonding event recv, but secondary info not for us\n"); goto lag_out; } @@ -164,8 +164,8 @@ ice_lag_link(struct ice_lag *lag, struct netdev_notifier_changeupper_info *info) lag->bonded = true; lag->role = ICE_LAG_UNSET; - /* if this is the first element in an LAG mark as master */ - lag->master = !!(peers == 1); + /* if this is the first element in an LAG mark as primary */ + lag->primary = !!(peers == 1); } /** @@ -204,11 +204,7 @@ ice_lag_unlink(struct ice_lag *lag, lag->upper_netdev = NULL; } - if (lag->peer_netdev) { - dev_put(lag->peer_netdev); - lag->peer_netdev = NULL; - } - + lag->peer_netdev = NULL; ice_set_sriov_cap(pf); ice_set_rdma_cap(pf); lag->bonded = false; @@ -216,6 +212,32 @@ ice_lag_unlink(struct ice_lag *lag, } /** + * ice_lag_unregister - handle netdev unregister events + * @lag: LAG info struct + * @netdev: netdev reporting the event + */ +static void ice_lag_unregister(struct ice_lag *lag, struct net_device *netdev) +{ + struct ice_pf *pf = lag->pf; + + /* check to see if this event is for this netdev + * check that we are in an aggregate + */ + if (netdev != lag->netdev || !lag->bonded) + return; + + if (lag->upper_netdev) { + dev_put(lag->upper_netdev); + lag->upper_netdev = NULL; + ice_set_sriov_cap(pf); + ice_set_rdma_cap(pf); + } + /* perform some cleanup in case we come back */ + lag->bonded = false; + lag->role = ICE_LAG_NONE; +} + +/** * ice_lag_changeupper_event - handle LAG changeupper event * @lag: LAG info struct * @ptr: opaque pointer data @@ -242,7 +264,7 @@ static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr) netdev_dbg(netdev, "bonding %s\n", info->linking ? "LINK" : "UNLINK"); if (!netif_is_lag_master(info->upper_dev)) { - netdev_dbg(netdev, "changeupper rcvd, but not master. bail\n"); + netdev_dbg(netdev, "changeupper rcvd, but not primary. bail\n"); return; } @@ -307,7 +329,7 @@ ice_lag_event_handler(struct notifier_block *notif_blk, unsigned long event, ice_lag_info_event(lag, ptr); break; case NETDEV_UNREGISTER: - ice_lag_unlink(lag, ptr); + ice_lag_unregister(lag, netdev); break; default: break; @@ -425,11 +447,9 @@ void ice_deinit_lag(struct ice_pf *pf) if (lag->pf) ice_unregister_lag_handler(lag); - if (lag->upper_netdev) - dev_put(lag->upper_netdev); + dev_put(lag->upper_netdev); - if (lag->peer_netdev) - dev_put(lag->peer_netdev); + dev_put(lag->peer_netdev); kfree(lag); diff --git a/drivers/net/ethernet/intel/ice/ice_lag.h b/drivers/net/ethernet/intel/ice/ice_lag.h index c2e3688dd8fd..51b5cf467ce2 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.h +++ b/drivers/net/ethernet/intel/ice/ice_lag.h @@ -24,7 +24,7 @@ struct ice_lag { struct net_device *upper_netdev; /* upper bonding netdev */ struct notifier_block notif_block; u8 bonded:1; /* currently bonded */ - u8 master:1; /* this is a master */ + u8 primary:1; /* this is primary */ u8 handler:1; /* did we register a rx_netdev_handler */ /* each thing blocking bonding will increment this value by one. * If this value is zero, then bonding is allowed. diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h index d981dc6f2323..b3baf7c3f910 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -424,6 +424,8 @@ enum ice_rx_flex_desc_status_error_0_bits { enum ice_rx_flex_desc_status_error_1_bits { /* Note: These are predefined bit offsets */ ICE_RX_FLEX_DESC_STATUS1_NAT_S = 4, + /* [10:5] reserved */ + ICE_RX_FLEX_DESC_STATUS1_L2TAG2P_S = 11, ICE_RX_FLEX_DESC_STATUS1_LAST /* this entry must be last!!! */ }; @@ -568,6 +570,7 @@ struct ice_tx_ctx_desc { (0x3FFFFULL << ICE_TXD_CTX_QW1_TSO_LEN_S) #define ICE_TXD_CTX_QW1_MSS_S 50 +#define ICE_TXD_CTX_MIN_MSS 64 #define ICE_TXD_CTX_QW1_VSI_S 50 #define ICE_TXD_CTX_QW1_VSI_M (0x3FFULL << ICE_TXD_CTX_QW1_VSI_S) diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 0c187cf04fcf..7276badfa19e 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -8,6 +8,7 @@ #include "ice_fltr.h" #include "ice_dcb_lib.h" #include "ice_devlink.h" +#include "ice_vsi_vlan_ops.h" /** * ice_vsi_type_str - maps VSI type enum to string equivalents @@ -165,21 +166,19 @@ static void ice_vsi_set_num_desc(struct ice_vsi *vsi) /** * ice_vsi_set_num_qs - Set number of queues, descriptors and vectors for a VSI * @vsi: the VSI being configured - * @vf_id: ID of the VF being configured + * @vf: the VF associated with this VSI, if any * * Return 0 on success and a negative value on error */ -static void ice_vsi_set_num_qs(struct ice_vsi *vsi, u16 vf_id) +static void ice_vsi_set_num_qs(struct ice_vsi *vsi, struct ice_vf *vf) { + enum ice_vsi_type vsi_type = vsi->type; struct ice_pf *pf = vsi->back; - struct ice_vf *vf = NULL; - if (vsi->type == ICE_VSI_VF) - vsi->vf_id = vf_id; - else - vsi->vf_id = ICE_INVAL_VFID; + if (WARN_ON(vsi_type == ICE_VSI_VF && !vf)) + return; - switch (vsi->type) { + switch (vsi_type) { case ICE_VSI_PF: if (vsi->req_txq) { vsi->alloc_txq = vsi->req_txq; @@ -216,22 +215,21 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi, u16 vf_id) /* The number of queues for ctrl VSI is equal to number of VFs. * Each ring is associated to the corresponding VF_PR netdev. */ - vsi->alloc_txq = pf->num_alloc_vfs; - vsi->alloc_rxq = pf->num_alloc_vfs; + vsi->alloc_txq = ice_get_num_vfs(pf); + vsi->alloc_rxq = vsi->alloc_txq; vsi->num_q_vectors = 1; break; case ICE_VSI_VF: - vf = &pf->vf[vsi->vf_id]; if (vf->num_req_qs) vf->num_vf_qs = vf->num_req_qs; vsi->alloc_txq = vf->num_vf_qs; vsi->alloc_rxq = vf->num_vf_qs; - /* pf->num_msix_per_vf includes (VF miscellaneous vector + + /* pf->vfs.num_msix_per includes (VF miscellaneous vector + * data queue interrupts). Since vsi->num_q_vectors is number * of queues vectors, subtract 1 (ICE_NONQ_VECS_VF) from the * original vector count */ - vsi->num_q_vectors = pf->num_msix_per_vf - ICE_NONQ_VECS_VF; + vsi->num_q_vectors = pf->vfs.num_msix_per - ICE_NONQ_VECS_VF; break; case ICE_VSI_CTRL: vsi->alloc_txq = 1; @@ -247,7 +245,7 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi, u16 vf_id) vsi->alloc_rxq = 1; break; default: - dev_warn(ice_pf_to_dev(pf), "Unknown VSI type %d\n", vsi->type); + dev_warn(ice_pf_to_dev(pf), "Unknown VSI type %d\n", vsi_type); break; } @@ -298,7 +296,7 @@ void ice_vsi_delete(struct ice_vsi *vsi) return; if (vsi->type == ICE_VSI_VF) - ctxt->vf_num = vsi->vf_id; + ctxt->vf_num = vsi->vf->vf_id; ctxt->vsi_num = vsi->vsi_num; memcpy(&ctxt->info, &vsi->info, sizeof(ctxt->info)); @@ -383,8 +381,7 @@ int ice_vsi_clear(struct ice_vsi *vsi) pf->vsi[vsi->idx] = NULL; if (vsi->idx < pf->next_vsi && vsi->type != ICE_VSI_CTRL) pf->next_vsi = vsi->idx; - if (vsi->idx < pf->next_vsi && vsi->type == ICE_VSI_CTRL && - vsi->vf_id != ICE_INVAL_VFID) + if (vsi->idx < pf->next_vsi && vsi->type == ICE_VSI_CTRL && vsi->vf) pf->next_vsi = vsi->idx; ice_vsi_free_arrays(vsi); @@ -436,13 +433,16 @@ static irqreturn_t ice_eswitch_msix_clean_rings(int __always_unused irq, void *d { struct ice_q_vector *q_vector = (struct ice_q_vector *)data; struct ice_pf *pf = q_vector->vsi->back; - int i; + struct ice_vf *vf; + unsigned int bkt; if (!q_vector->tx.tx_ring && !q_vector->rx.rx_ring) return IRQ_HANDLED; - ice_for_each_vf(pf, i) - napi_schedule(&pf->vf[i].repr->q_vector->napi); + rcu_read_lock(); + ice_for_each_vf_rcu(pf, bkt, vf) + napi_schedule(&vf->repr->q_vector->napi); + rcu_read_unlock(); return IRQ_HANDLED; } @@ -452,17 +452,24 @@ static irqreturn_t ice_eswitch_msix_clean_rings(int __always_unused irq, void *d * @pf: board private structure * @vsi_type: type of VSI * @ch: ptr to channel - * @vf_id: ID of the VF being configured + * @vf: VF for ICE_VSI_VF and ICE_VSI_CTRL + * + * The VF pointer is used for ICE_VSI_VF and ICE_VSI_CTRL. For ICE_VSI_CTRL, + * it may be NULL in the case there is no association with a VF. For + * ICE_VSI_VF the VF pointer *must not* be NULL. * * returns a pointer to a VSI on success, NULL on failure. */ static struct ice_vsi * ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type vsi_type, - struct ice_channel *ch, u16 vf_id) + struct ice_channel *ch, struct ice_vf *vf) { struct device *dev = ice_pf_to_dev(pf); struct ice_vsi *vsi = NULL; + if (WARN_ON(vsi_type == ICE_VSI_VF && !vf)) + return NULL; + /* Need to protect the allocation of the VSIs at the PF level */ mutex_lock(&pf->sw_mutex); @@ -484,9 +491,9 @@ ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type vsi_type, set_bit(ICE_VSI_DOWN, vsi->state); if (vsi_type == ICE_VSI_VF) - ice_vsi_set_num_qs(vsi, vf_id); + ice_vsi_set_num_qs(vsi, vf); else if (vsi_type != ICE_VSI_CHNL) - ice_vsi_set_num_qs(vsi, ICE_INVAL_VFID); + ice_vsi_set_num_qs(vsi, NULL); switch (vsi->type) { case ICE_VSI_SWITCHDEV_CTRL: @@ -509,10 +516,16 @@ ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type vsi_type, /* Setup ctrl VSI MSIX irq handler */ vsi->irq_handler = ice_msix_clean_ctrl_vsi; + + /* For the PF control VSI this is NULL, for the VF control VSI + * this will be the first VF to allocate it. + */ + vsi->vf = vf; break; case ICE_VSI_VF: if (ice_vsi_alloc_arrays(vsi)) goto err_rings; + vsi->vf = vf; break; case ICE_VSI_CHNL: if (!ch) @@ -530,7 +543,7 @@ ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type vsi_type, goto unlock_pf; } - if (vsi->type == ICE_VSI_CTRL && vf_id == ICE_INVAL_VFID) { + if (vsi->type == ICE_VSI_CTRL && !vf) { /* Use the last VSI slot as the index for PF control VSI */ vsi->idx = pf->num_alloc_vsi - 1; pf->ctrl_vsi_idx = vsi->idx; @@ -545,8 +558,8 @@ ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type vsi_type, pf->next_vsi); } - if (vsi->type == ICE_VSI_CTRL && vf_id != ICE_INVAL_VFID) - pf->vf[vf_id].ctrl_vsi_idx = vsi->idx; + if (vsi->type == ICE_VSI_CTRL && vf) + vf->ctrl_vsi_idx = vsi->idx; goto unlock_pf; err_rings: @@ -732,14 +745,14 @@ bool ice_is_safe_mode(struct ice_pf *pf) } /** - * ice_is_aux_ena + * ice_is_rdma_ena * @pf: pointer to the PF struct * - * returns true if AUX devices/drivers are supported, false otherwise + * returns true if RDMA is currently supported, false otherwise */ -bool ice_is_aux_ena(struct ice_pf *pf) +bool ice_is_rdma_ena(struct ice_pf *pf) { - return test_bit(ICE_FLAG_AUX_ENA, pf->flags); + return test_bit(ICE_FLAG_RDMA_ENA, pf->flags); } /** @@ -838,11 +851,12 @@ static void ice_vsi_set_rss_params(struct ice_vsi *vsi) /** * ice_set_dflt_vsi_ctx - Set default VSI context before adding a VSI + * @hw: HW structure used to determine the VLAN mode of the device * @ctxt: the VSI context being set * * This initializes a default VSI context for all sections except the Queues. */ -static void ice_set_dflt_vsi_ctx(struct ice_vsi_ctx *ctxt) +static void ice_set_dflt_vsi_ctx(struct ice_hw *hw, struct ice_vsi_ctx *ctxt) { u32 table = 0; @@ -853,13 +867,30 @@ static void ice_set_dflt_vsi_ctx(struct ice_vsi_ctx *ctxt) ctxt->info.sw_flags = ICE_AQ_VSI_SW_FLAG_SRC_PRUNE; /* Traffic from VSI can be sent to LAN */ ctxt->info.sw_flags2 = ICE_AQ_VSI_SW_FLAG_LAN_ENA; - /* By default bits 3 and 4 in vlan_flags are 0's which results in legacy - * behavior (show VLAN, DEI, and UP) in descriptor. Also, allow all - * packets untagged/tagged. + /* allow all untagged/tagged packets by default on Tx */ + ctxt->info.inner_vlan_flags = ((ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL & + ICE_AQ_VSI_INNER_VLAN_TX_MODE_M) >> + ICE_AQ_VSI_INNER_VLAN_TX_MODE_S); + /* SVM - by default bits 3 and 4 in inner_vlan_flags are 0's which + * results in legacy behavior (show VLAN, DEI, and UP) in descriptor. + * + * DVM - leave inner VLAN in packet by default */ - ctxt->info.vlan_flags = ((ICE_AQ_VSI_VLAN_MODE_ALL & - ICE_AQ_VSI_VLAN_MODE_M) >> - ICE_AQ_VSI_VLAN_MODE_S); + if (ice_is_dvm_ena(hw)) { + ctxt->info.inner_vlan_flags |= + ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING; + ctxt->info.outer_vlan_flags = + (ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL << + ICE_AQ_VSI_OUTER_VLAN_TX_MODE_S) & + ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M; + ctxt->info.outer_vlan_flags |= + (ICE_AQ_VSI_OUTER_TAG_VLAN_8100 << + ICE_AQ_VSI_OUTER_TAG_TYPE_S) & + ICE_AQ_VSI_OUTER_TAG_TYPE_M; + ctxt->info.outer_vlan_flags |= + FIELD_PREP(ICE_AQ_VSI_OUTER_VLAN_EMODE_M, + ICE_AQ_VSI_OUTER_VLAN_EMODE_NOTHING); + } /* Have 1:1 UP mapping for both ingress/egress tables */ table |= ICE_UP_TABLE_TRANSLATE(0, 0); table |= ICE_UP_TABLE_TRANSLATE(1, 1); @@ -881,9 +912,9 @@ static void ice_set_dflt_vsi_ctx(struct ice_vsi_ctx *ctxt) * @vsi: the VSI being configured * @ctxt: VSI context structure */ -static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) +static int ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) { - u16 offset = 0, qmap = 0, tx_count = 0, pow = 0; + u16 offset = 0, qmap = 0, tx_count = 0, rx_count = 0, pow = 0; u16 num_txq_per_tc, num_rxq_per_tc; u16 qcount_tx = vsi->alloc_txq; u16 qcount_rx = vsi->alloc_rxq; @@ -950,11 +981,24 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) * at least 1) */ if (offset) - vsi->num_rxq = offset; + rx_count = offset; else - vsi->num_rxq = num_rxq_per_tc; + rx_count = num_rxq_per_tc; + + if (rx_count > vsi->alloc_rxq) { + dev_err(ice_pf_to_dev(vsi->back), "Trying to use more Rx queues (%u), than were allocated (%u)!\n", + rx_count, vsi->alloc_rxq); + return -EINVAL; + } + + if (tx_count > vsi->alloc_txq) { + dev_err(ice_pf_to_dev(vsi->back), "Trying to use more Tx queues (%u), than were allocated (%u)!\n", + tx_count, vsi->alloc_txq); + return -EINVAL; + } vsi->num_txq = tx_count; + vsi->num_rxq = rx_count; if (vsi->type == ICE_VSI_VF && vsi->num_txq != vsi->num_rxq) { dev_dbg(ice_pf_to_dev(vsi->back), "VF VSI should have same number of Tx and Rx queues. Hence making them equal\n"); @@ -972,6 +1016,8 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) */ ctxt->info.q_mapping[0] = cpu_to_le16(vsi->rxq_map[0]); ctxt->info.q_mapping[1] = cpu_to_le16(vsi->num_rxq); + + return 0; } /** @@ -1114,7 +1160,7 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi) case ICE_VSI_VF: ctxt->flags = ICE_AQ_VSI_TYPE_VF; /* VF number here is the absolute VF number (0-255) */ - ctxt->vf_num = vsi->vf_id + hw->func_caps.vf_base_id; + ctxt->vf_num = vsi->vf->vf_id + hw->func_caps.vf_base_id; break; default: ret = -ENODEV; @@ -1136,7 +1182,7 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi) ~ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; } - ice_set_dflt_vsi_ctx(ctxt); + ice_set_dflt_vsi_ctx(hw, ctxt); if (test_bit(ICE_FLAG_FD_ENA, pf->flags)) ice_set_fd_vsi_ctx(ctxt, vsi); /* if the switch is in VEB mode, allow VSI loopback */ @@ -1159,7 +1205,10 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi) if (vsi->type == ICE_VSI_CHNL) { ice_chnl_vsi_setup_q_map(vsi, ctxt); } else { - ice_vsi_setup_q_map(vsi, ctxt); + ret = ice_vsi_setup_q_map(vsi, ctxt); + if (ret) + goto out; + if (!init_vsi) /* means VSI being updated */ /* must to indicate which section of VSI context are * being modified @@ -1168,25 +1217,6 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi) cpu_to_le16(ICE_AQ_VSI_PROP_RXQ_MAP_VALID); } - /* enable/disable MAC and VLAN anti-spoof when spoofchk is on/off - * respectively - */ - if (vsi->type == ICE_VSI_VF) { - ctxt->info.valid_sections |= - cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID); - if (pf->vf[vsi->vf_id].spoofchk) { - ctxt->info.sec_flags |= - ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF | - (ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA << - ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S); - } else { - ctxt->info.sec_flags &= - ~(ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF | - (ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA << - ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S)); - } - } - /* Allow control frames out of main VSI */ if (vsi->type == ICE_VSI_PF) { ctxt->info.sec_flags |= ICE_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD; @@ -1325,6 +1355,36 @@ ice_get_res(struct ice_pf *pf, struct ice_res_tracker *res, u16 needed, u16 id) } /** + * ice_get_vf_ctrl_res - Get VF control VSI resource + * @pf: pointer to the PF structure + * @vsi: the VSI to allocate a resource for + * + * Look up whether another VF has already allocated the control VSI resource. + * If so, re-use this resource so that we share it among all VFs. + * + * Otherwise, allocate the resource and return it. + */ +static int ice_get_vf_ctrl_res(struct ice_pf *pf, struct ice_vsi *vsi) +{ + struct ice_vf *vf; + unsigned int bkt; + int base; + + rcu_read_lock(); + ice_for_each_vf_rcu(pf, bkt, vf) { + if (vf != vsi->vf && vf->ctrl_vsi_idx != ICE_NO_VSI) { + base = pf->vsi[vf->ctrl_vsi_idx]->base_vector; + rcu_read_unlock(); + return base; + } + } + rcu_read_unlock(); + + return ice_get_res(pf, pf->irq_tracker, vsi->num_q_vectors, + ICE_RES_VF_CTRL_VEC_ID); +} + +/** * ice_vsi_setup_vector_base - Set up the base vector for the given VSI * @vsi: ptr to the VSI * @@ -1356,20 +1416,8 @@ static int ice_vsi_setup_vector_base(struct ice_vsi *vsi) num_q_vectors = vsi->num_q_vectors; /* reserve slots from OS requested IRQs */ - if (vsi->type == ICE_VSI_CTRL && vsi->vf_id != ICE_INVAL_VFID) { - int i; - - ice_for_each_vf(pf, i) { - struct ice_vf *vf = &pf->vf[i]; - - if (i != vsi->vf_id && vf->ctrl_vsi_idx != ICE_NO_VSI) { - base = pf->vsi[vf->ctrl_vsi_idx]->base_vector; - break; - } - } - if (i == pf->num_alloc_vfs) - base = ice_get_res(pf, pf->irq_tracker, num_q_vectors, - ICE_RES_VF_CTRL_VEC_ID); + if (vsi->type == ICE_VSI_CTRL && vsi->vf) { + base = ice_get_vf_ctrl_res(pf, vsi); } else { base = ice_get_res(pf, pf->irq_tracker, num_q_vectors, vsi->idx); @@ -1431,6 +1479,7 @@ static void ice_vsi_clear_rings(struct ice_vsi *vsi) */ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) { + bool dvm_ena = ice_is_dvm_ena(&vsi->back->hw); struct ice_pf *pf = vsi->back; struct device *dev; u16 i; @@ -1452,6 +1501,11 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) ring->tx_tstamps = &pf->ptp.port.tx; ring->dev = dev; ring->count = vsi->num_tx_desc; + ring->txq_teid = ICE_INVAL_TEID; + if (dvm_ena) + ring->flags |= ICE_TX_FLAGS_RING_VLAN_L2TAG2; + else + ring->flags |= ICE_TX_FLAGS_RING_VLAN_L2TAG1; WRITE_ONCE(vsi->tx_rings[i], ring); } @@ -1470,6 +1524,7 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) ring->netdev = vsi->netdev; ring->dev = dev; ring->count = vsi->num_rx_desc; + ring->cached_phctime = pf->ptp.cached_phc_time; WRITE_ONCE(vsi->rx_rings[i], ring); } @@ -1510,6 +1565,22 @@ void ice_vsi_manage_rss_lut(struct ice_vsi *vsi, bool ena) } /** + * ice_vsi_cfg_crc_strip - Configure CRC stripping for a VSI + * @vsi: VSI to be configured + * @disable: set to true to have FCS / CRC in the frame data + */ +void ice_vsi_cfg_crc_strip(struct ice_vsi *vsi, bool disable) +{ + int i; + + ice_for_each_rxq(vsi, i) + if (disable) + vsi->rx_rings[i]->flags |= ICE_RX_FLAGS_CRC_STRIP_DIS; + else + vsi->rx_rings[i]->flags &= ~ICE_RX_FLAGS_CRC_STRIP_DIS; +} + +/** * ice_vsi_cfg_rss_lut_key - Configure RSS params for a VSI * @vsi: VSI to be configured */ @@ -1684,6 +1755,12 @@ static void ice_vsi_set_rss_flow_fld(struct ice_vsi *vsi) if (status) dev_dbg(dev, "ice_add_rss_cfg failed for sctp6 flow, vsi = %d, error = %d\n", vsi_num, status); + + status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_ESP_SPI, + ICE_FLOW_SEG_HDR_ESP); + if (status) + dev_dbg(dev, "ice_add_rss_cfg failed for esp/spi flow, vsi = %d, error = %d\n", + vsi_num, status); } /** @@ -1757,62 +1834,6 @@ void ice_update_eth_stats(struct ice_vsi *vsi) } /** - * ice_vsi_add_vlan - Add VSI membership for given VLAN - * @vsi: the VSI being configured - * @vid: VLAN ID to be added - * @action: filter action to be performed on match - */ -int -ice_vsi_add_vlan(struct ice_vsi *vsi, u16 vid, enum ice_sw_fwd_act_type action) -{ - struct ice_pf *pf = vsi->back; - struct device *dev; - int err = 0; - - dev = ice_pf_to_dev(pf); - - if (!ice_fltr_add_vlan(vsi, vid, action)) { - vsi->num_vlan++; - } else { - err = -ENODEV; - dev_err(dev, "Failure Adding VLAN %d on VSI %i\n", vid, - vsi->vsi_num); - } - - return err; -} - -/** - * ice_vsi_kill_vlan - Remove VSI membership for a given VLAN - * @vsi: the VSI being configured - * @vid: VLAN ID to be removed - * - * Returns 0 on success and negative on failure - */ -int ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid) -{ - struct ice_pf *pf = vsi->back; - struct device *dev; - int err; - - dev = ice_pf_to_dev(pf); - - err = ice_fltr_remove_vlan(vsi, vid, ICE_FWD_TO_VSI); - if (!err) { - vsi->num_vlan--; - } else if (err == -ENOENT) { - dev_dbg(dev, "Failed to remove VLAN %d on VSI %i, it does not exist, error: %d\n", - vid, vsi->vsi_num, err); - err = 0; - } else { - dev_err(dev, "Error removing VLAN %d on vsi %i error: %d\n", - vid, vsi->vsi_num, err); - } - - return err; -} - -/** * ice_vsi_cfg_frame_size - setup max frame size and Rx buffer length * @vsi: VSI */ @@ -1984,8 +2005,8 @@ int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi) if (ret) return ret; - ice_for_each_xdp_txq(vsi, i) - vsi->xdp_rings[i]->xsk_pool = ice_tx_xsk_pool(vsi->xdp_rings[i]); + ice_for_each_rxq(vsi, i) + ice_tx_xsk_pool(vsi, i); return ret; } @@ -2140,95 +2161,6 @@ void ice_vsi_cfg_msix(struct ice_vsi *vsi) } /** - * ice_vsi_manage_vlan_insertion - Manage VLAN insertion for the VSI for Tx - * @vsi: the VSI being changed - */ -int ice_vsi_manage_vlan_insertion(struct ice_vsi *vsi) -{ - struct ice_hw *hw = &vsi->back->hw; - struct ice_vsi_ctx *ctxt; - int ret; - - ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); - if (!ctxt) - return -ENOMEM; - - /* Here we are configuring the VSI to let the driver add VLAN tags by - * setting vlan_flags to ICE_AQ_VSI_VLAN_MODE_ALL. The actual VLAN tag - * insertion happens in the Tx hot path, in ice_tx_map. - */ - ctxt->info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_ALL; - - /* Preserve existing VLAN strip setting */ - ctxt->info.vlan_flags |= (vsi->info.vlan_flags & - ICE_AQ_VSI_VLAN_EMOD_M); - - ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID); - - ret = ice_update_vsi(hw, vsi->idx, ctxt, NULL); - if (ret) { - dev_err(ice_pf_to_dev(vsi->back), "update VSI for VLAN insert failed, err %d aq_err %s\n", - ret, ice_aq_str(hw->adminq.sq_last_status)); - goto out; - } - - vsi->info.vlan_flags = ctxt->info.vlan_flags; -out: - kfree(ctxt); - return ret; -} - -/** - * ice_vsi_manage_vlan_stripping - Manage VLAN stripping for the VSI for Rx - * @vsi: the VSI being changed - * @ena: boolean value indicating if this is a enable or disable request - */ -int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena) -{ - struct ice_hw *hw = &vsi->back->hw; - struct ice_vsi_ctx *ctxt; - int ret; - - /* do not allow modifying VLAN stripping when a port VLAN is configured - * on this VSI - */ - if (vsi->info.pvid) - return 0; - - ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); - if (!ctxt) - return -ENOMEM; - - /* Here we are configuring what the VSI should do with the VLAN tag in - * the Rx packet. We can either leave the tag in the packet or put it in - * the Rx descriptor. - */ - if (ena) - /* Strip VLAN tag from Rx packet and put it in the desc */ - ctxt->info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_STR_BOTH; - else - /* Disable stripping. Leave tag in packet */ - ctxt->info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_NOTHING; - - /* Allow all packets untagged/tagged */ - ctxt->info.vlan_flags |= ICE_AQ_VSI_VLAN_MODE_ALL; - - ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID); - - ret = ice_update_vsi(hw, vsi->idx, ctxt, NULL); - if (ret) { - dev_err(ice_pf_to_dev(vsi->back), "update VSI for VLAN strip failed, ena = %d err %d aq_err %s\n", - ena, ret, ice_aq_str(hw->adminq.sq_last_status)); - goto out; - } - - vsi->info.vlan_flags = ctxt->info.vlan_flags; -out: - kfree(ctxt); - return ret; -} - -/** * ice_vsi_start_all_rx_rings - start/enable all of a VSI's Rx rings * @vsi: the VSI whose rings are to be enabled * @@ -2308,72 +2240,42 @@ int ice_vsi_stop_xdp_tx_rings(struct ice_vsi *vsi) } /** - * 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. + * ice_vsi_is_rx_queue_active + * @vsi: the VSI being configured * - * returns true if Rx VLAN pruning is enabled and false otherwise. + * Return true if at least one queue is active. */ -bool ice_vsi_is_vlan_pruning_ena(struct ice_vsi *vsi) +bool ice_vsi_is_rx_queue_active(struct ice_vsi *vsi) { - if (!vsi) - return false; + struct ice_pf *pf = vsi->back; + struct ice_hw *hw = &pf->hw; + int i; - return (vsi->info.sw_flags2 & ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA); + ice_for_each_rxq(vsi, i) { + u32 rx_reg; + int pf_q; + + pf_q = vsi->rxq_map[i]; + rx_reg = rd32(hw, QRX_CTRL(pf_q)); + if (rx_reg & QRX_CTRL_QENA_STAT_M) + return true; + } + + return false; } /** - * ice_cfg_vlan_pruning - enable or disable VLAN pruning on the VSI - * @vsi: VSI to enable or disable VLAN pruning on - * @ena: set to true to enable VLAN pruning and false to disable it + * 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 0 if VSI is updated, negative otherwise + * returns true if Rx VLAN pruning is enabled and false otherwise. */ -int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena) +bool ice_vsi_is_vlan_pruning_ena(struct ice_vsi *vsi) { - struct ice_vsi_ctx *ctxt; - struct ice_pf *pf; - int status; - if (!vsi) - return -EINVAL; - - /* Don't enable VLAN pruning if the netdev is currently in promiscuous - * mode. VLAN pruning will be enabled when the interface exits - * promiscuous mode if any VLAN filters are active. - */ - if (vsi->netdev && vsi->netdev->flags & IFF_PROMISC && ena) - return 0; - - pf = vsi->back; - ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); - if (!ctxt) - return -ENOMEM; - - ctxt->info = vsi->info; - - if (ena) - ctxt->info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; - else - ctxt->info.sw_flags2 &= ~ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; - - ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SW_VALID); - - status = ice_update_vsi(&pf->hw, vsi->idx, ctxt, NULL); - if (status) { - netdev_err(vsi->netdev, "%sabling VLAN pruning on VSI handle: %d, VSI HW ID: %d failed, err = %d, aq_err = %s\n", - ena ? "En" : "Dis", vsi->idx, vsi->vsi_num, - status, ice_aq_str(pf->hw.adminq.sq_last_status)); - goto err_out; - } - - vsi->info.sw_flags2 = ctxt->info.sw_flags2; - - kfree(ctxt); - return 0; + return false; -err_out: - kfree(ctxt); - return -EIO; + 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) @@ -2410,7 +2312,7 @@ ice_vsi_set_q_vectors_reg_idx(struct ice_vsi *vsi) } if (vsi->type == ICE_VSI_VF) { - struct ice_vf *vf = &vsi->back->vf[vsi->vf_id]; + struct ice_vf *vf = vsi->vf; q_vector->reg_idx = ice_calc_vf_reg_idx(vf, q_vector); } else { @@ -2564,7 +2466,7 @@ static void ice_set_agg_vsi(struct ice_vsi *vsi) agg_id); return; } - /* aggregator node is created, store the neeeded info */ + /* aggregator node is created, store the needed info */ agg_node->valid = true; agg_node->agg_id = agg_id; } @@ -2595,9 +2497,8 @@ static void ice_set_agg_vsi(struct ice_vsi *vsi) * @pf: board private structure * @pi: pointer to the port_info instance * @vsi_type: VSI type - * @vf_id: defines VF ID to which this VSI connects. This field is meant to be - * used only for ICE_VSI_VF VSI type. For other VSI types, should - * fill-in ICE_INVAL_VFID as input. + * @vf: pointer to VF to which this VSI connects. This field is used primarily + * for the ICE_VSI_VF type. Other VSI types should pass NULL. * @ch: ptr to channel * * This allocates the sw VSI structure and its queue resources. @@ -2607,7 +2508,8 @@ static void ice_set_agg_vsi(struct ice_vsi *vsi) */ struct ice_vsi * ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, - enum ice_vsi_type vsi_type, u16 vf_id, struct ice_channel *ch) + enum ice_vsi_type vsi_type, struct ice_vf *vf, + struct ice_channel *ch) { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; struct device *dev = ice_pf_to_dev(pf); @@ -2615,11 +2517,11 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, int ret, i; if (vsi_type == ICE_VSI_CHNL) - vsi = ice_vsi_alloc(pf, vsi_type, ch, ICE_INVAL_VFID); + vsi = ice_vsi_alloc(pf, vsi_type, ch, NULL); else if (vsi_type == ICE_VSI_VF || vsi_type == ICE_VSI_CTRL) - vsi = ice_vsi_alloc(pf, vsi_type, NULL, vf_id); + vsi = ice_vsi_alloc(pf, vsi_type, NULL, vf); else - vsi = ice_vsi_alloc(pf, vsi_type, NULL, ICE_INVAL_VFID); + vsi = ice_vsi_alloc(pf, vsi_type, NULL, NULL); if (!vsi) { dev_err(dev, "could not allocate VSI\n"); @@ -2631,9 +2533,6 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, if (vsi->type == ICE_VSI_PF) vsi->ethtype = ETH_P_PAUSE; - if (vsi->type == ICE_VSI_VF || vsi->type == ICE_VSI_CTRL) - vsi->vf_id = vf_id; - ice_alloc_fd_res(vsi); if (vsi_type != ICE_VSI_CHNL) { @@ -2655,6 +2554,8 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, if (ret) goto unroll_get_qs; + ice_vsi_init_vlan_ops(vsi); + switch (vsi->type) { case ICE_VSI_CTRL: case ICE_VSI_SWITCHDEV_CTRL: @@ -2675,17 +2576,6 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, if (ret) goto unroll_vector_base; - /* Always add VLAN ID 0 switch rule by default. This is needed - * in order to allow all untagged and 0 tagged priority traffic - * if Rx VLAN pruning is enabled. Also there are cases where we - * don't get the call to add VLAN 0 via ice_vlan_rx_add_vid() - * so this handles those cases (i.e. adding the PF to a bridge - * without the 8021q module loaded). - */ - ret = ice_vsi_add_vlan(vsi, 0, ICE_FWD_TO_VSI); - if (ret) - goto unroll_clear_rings; - ice_vsi_map_rings_to_vectors(vsi); /* ICE_VSI_CTRL does not need RSS so skip RSS processing */ @@ -2862,6 +2752,8 @@ void ice_vsi_free_irq(struct ice_vsi *vsi) return; vsi->irqs_ready = false; + ice_free_cpu_rx_rmap(vsi); + ice_for_each_q_vector(vsi, i) { u16 vector = i + base; int irq_num; @@ -2875,7 +2767,8 @@ void ice_vsi_free_irq(struct ice_vsi *vsi) continue; /* clear the affinity notifier in the IRQ descriptor */ - irq_set_affinity_notifier(irq_num, NULL); + if (!IS_ENABLED(CONFIG_RFS_ACCEL)) + irq_set_affinity_notifier(irq_num, NULL); /* clear the affinity_mask in the IRQ descriptor */ irq_set_affinity_hint(irq_num, NULL); @@ -3063,6 +2956,37 @@ void ice_napi_del(struct ice_vsi *vsi) } /** + * ice_free_vf_ctrl_res - Free the VF control VSI resource + * @pf: pointer to PF structure + * @vsi: the VSI to free resources for + * + * Check if the VF control VSI resource is still in use. If no VF is using it + * any more, release the VSI resource. Otherwise, leave it to be cleaned up + * once no other VF uses it. + */ +static void ice_free_vf_ctrl_res(struct ice_pf *pf, struct ice_vsi *vsi) +{ + struct ice_vf *vf; + unsigned int bkt; + + rcu_read_lock(); + ice_for_each_vf_rcu(pf, bkt, vf) { + if (vf != vsi->vf && vf->ctrl_vsi_idx != ICE_NO_VSI) { + rcu_read_unlock(); + return; + } + } + rcu_read_unlock(); + + /* No other VFs left that have control VSI. It is now safe to reclaim + * SW interrupts back to the common pool. + */ + ice_free_res(pf->irq_tracker, vsi->base_vector, + ICE_RES_VF_CTRL_VEC_ID); + pf->num_avail_sw_msix += vsi->num_q_vectors; +} + +/** * ice_vsi_release - Delete a VSI and free its resources * @vsi: the VSI being removed * @@ -3089,9 +3013,6 @@ int ice_vsi_release(struct ice_vsi *vsi) clear_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state); } - if (vsi->type == ICE_VSI_PF) - ice_devlink_destroy_pf_port(pf); - if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) ice_rss_clean(vsi); @@ -3105,23 +3026,8 @@ int ice_vsi_release(struct ice_vsi *vsi) * many interrupts each VF needs. SR-IOV MSIX resources are also * cleared in the same manner. */ - if (vsi->type == ICE_VSI_CTRL && vsi->vf_id != ICE_INVAL_VFID) { - int i; - - ice_for_each_vf(pf, i) { - struct ice_vf *vf = &pf->vf[i]; - - if (i != vsi->vf_id && vf->ctrl_vsi_idx != ICE_NO_VSI) - break; - } - if (i == pf->num_alloc_vfs) { - /* No other VFs left that have control VSI, reclaim SW - * interrupts back to the common pool - */ - ice_free_res(pf->irq_tracker, vsi->base_vector, - ICE_RES_VF_CTRL_VEC_ID); - pf->num_avail_sw_msix += vsi->num_q_vectors; - } + if (vsi->type == ICE_VSI_CTRL && vsi->vf) { + ice_free_vf_ctrl_res(pf, vsi); } else if (vsi->type != ICE_VSI_VF) { /* reclaim SW interrupts back to the common pool */ ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx); @@ -3141,6 +3047,8 @@ int ice_vsi_release(struct ice_vsi *vsi) } } + if (ice_is_vsi_dflt_vsi(vsi)) + ice_clear_dflt_vsi(vsi); ice_fltr_remove_all(vsi); ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx); err = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx); @@ -3162,6 +3070,9 @@ int ice_vsi_release(struct ice_vsi *vsi) } } + if (vsi->type == ICE_VSI_PF) + ice_devlink_destroy_pf_port(pf); + if (vsi->type == ICE_VSI_VF && vsi->agg_node && vsi->agg_node->valid) vsi->agg_node->num_vsis--; @@ -3195,8 +3106,8 @@ ice_vsi_rebuild_get_coalesce(struct ice_vsi *vsi, ice_for_each_q_vector(vsi, i) { struct ice_q_vector *q_vector = vsi->q_vectors[i]; - coalesce[i].itr_tx = q_vector->tx.itr_setting; - coalesce[i].itr_rx = q_vector->rx.itr_setting; + coalesce[i].itr_tx = q_vector->tx.itr_settings; + coalesce[i].itr_rx = q_vector->rx.itr_settings; coalesce[i].intrl = q_vector->intrl; if (i < vsi->num_txq) @@ -3252,21 +3163,21 @@ ice_vsi_rebuild_set_coalesce(struct ice_vsi *vsi, */ if (i < vsi->alloc_rxq && coalesce[i].rx_valid) { rc = &vsi->q_vectors[i]->rx; - rc->itr_setting = coalesce[i].itr_rx; + rc->itr_settings = coalesce[i].itr_rx; ice_write_itr(rc, rc->itr_setting); } else if (i < vsi->alloc_rxq) { rc = &vsi->q_vectors[i]->rx; - rc->itr_setting = coalesce[0].itr_rx; + rc->itr_settings = coalesce[0].itr_rx; ice_write_itr(rc, rc->itr_setting); } if (i < vsi->alloc_txq && coalesce[i].tx_valid) { rc = &vsi->q_vectors[i]->tx; - rc->itr_setting = coalesce[i].itr_tx; + rc->itr_settings = coalesce[i].itr_tx; ice_write_itr(rc, rc->itr_setting); } else if (i < vsi->alloc_txq) { rc = &vsi->q_vectors[i]->tx; - rc->itr_setting = coalesce[0].itr_tx; + rc->itr_settings = coalesce[0].itr_tx; ice_write_itr(rc, rc->itr_setting); } @@ -3280,12 +3191,12 @@ ice_vsi_rebuild_set_coalesce(struct ice_vsi *vsi, for (; i < vsi->num_q_vectors; i++) { /* transmit */ rc = &vsi->q_vectors[i]->tx; - rc->itr_setting = coalesce[0].itr_tx; + rc->itr_settings = coalesce[0].itr_tx; ice_write_itr(rc, rc->itr_setting); /* receive */ rc = &vsi->q_vectors[i]->rx; - rc->itr_setting = coalesce[0].itr_rx; + rc->itr_settings = coalesce[0].itr_rx; ice_write_itr(rc, rc->itr_setting); vsi->q_vectors[i]->intrl = coalesce[0].intrl; @@ -3305,7 +3216,6 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; struct ice_coalesce_stored *coalesce; int prev_num_q_vectors = 0; - struct ice_vf *vf = NULL; enum ice_vsi_type vtype; struct ice_pf *pf; int ret, i; @@ -3315,8 +3225,10 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) pf = vsi->back; vtype = vsi->type; - if (vtype == ICE_VSI_VF) - vf = &pf->vf[vsi->vf_id]; + if (WARN_ON(vtype == ICE_VSI_VF && !vsi->vf)) + return -EINVAL; + + ice_vsi_init_vlan_ops(vsi); coalesce = kcalloc(vsi->num_q_vectors, sizeof(struct ice_coalesce_stored), GFP_KERNEL); @@ -3353,9 +3265,9 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) ice_vsi_clear_rings(vsi); ice_vsi_free_arrays(vsi); if (vtype == ICE_VSI_VF) - ice_vsi_set_num_qs(vsi, vf->vf_id); + ice_vsi_set_num_qs(vsi, vsi->vf); else - ice_vsi_set_num_qs(vsi, ICE_INVAL_VFID); + ice_vsi_set_num_qs(vsi, NULL); ret = ice_vsi_alloc_arrays(vsi); if (ret < 0) @@ -3408,6 +3320,12 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) */ if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) ice_vsi_cfg_rss_lut_key(vsi); + + /* disable or enable CRC stripping */ + if (vsi->netdev) + ice_vsi_cfg_crc_strip(vsi, !!(vsi->netdev->features & + NETIF_F_RXFCS)); + break; case ICE_VSI_VF: ret = ice_vsi_alloc_q_vectors(vsi); @@ -3615,13 +3533,14 @@ void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc) * * Prepares VSI tc_config to have queue configurations based on MQPRIO options. */ -static void +static int ice_vsi_setup_q_map_mqprio(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt, u8 ena_tc) { u16 pow, offset = 0, qcount_tx = 0, qcount_rx = 0, qmap; u16 tc0_offset = vsi->mqprio_qopt.qopt.offset[0]; int tc0_qcount = vsi->mqprio_qopt.qopt.count[0]; + u16 new_txq, new_rxq; u8 netdev_tc = 0; int i; @@ -3662,9 +3581,23 @@ ice_vsi_setup_q_map_mqprio(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt, } } + new_txq = offset + qcount_tx; + if (new_txq > vsi->alloc_txq) { + dev_err(ice_pf_to_dev(vsi->back), "Trying to use more Tx queues (%u), than were allocated (%u)!\n", + new_txq, vsi->alloc_txq); + return -EINVAL; + } + + new_rxq = offset + qcount_rx; + if (new_rxq > vsi->alloc_rxq) { + dev_err(ice_pf_to_dev(vsi->back), "Trying to use more Rx queues (%u), than were allocated (%u)!\n", + new_rxq, vsi->alloc_rxq); + return -EINVAL; + } + /* Set actual Tx/Rx queue pairs */ - vsi->num_txq = offset + qcount_tx; - vsi->num_rxq = offset + qcount_rx; + vsi->num_txq = new_txq; + vsi->num_rxq = new_rxq; /* Setup queue TC[0].qmap for given VSI context */ ctxt->info.tc_mapping[0] = cpu_to_le16(qmap); @@ -3682,6 +3615,8 @@ ice_vsi_setup_q_map_mqprio(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt, dev_dbg(ice_pf_to_dev(vsi->back), "vsi->num_rxq = %d\n", vsi->num_rxq); dev_dbg(ice_pf_to_dev(vsi->back), "all_numtc %u, all_enatc: 0x%04x, tc_cfg.numtc %u\n", vsi->all_numtc, vsi->all_enatc, vsi->tc_cfg.numtc); + + return 0; } /** @@ -3695,6 +3630,7 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc) { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; struct ice_pf *pf = vsi->back; + struct ice_tc_cfg old_tc_cfg; struct ice_vsi_ctx *ctx; struct device *dev; int i, ret = 0; @@ -3719,6 +3655,7 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc) max_txqs[i] = vsi->num_txq; } + memcpy(&old_tc_cfg, &vsi->tc_cfg, sizeof(old_tc_cfg)); vsi->tc_cfg.ena_tc = ena_tc; vsi->tc_cfg.numtc = num_tc; @@ -3731,9 +3668,14 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc) if (vsi->type == ICE_VSI_PF && test_bit(ICE_FLAG_TC_MQPRIO, pf->flags)) - ice_vsi_setup_q_map_mqprio(vsi, ctx, ena_tc); + ret = ice_vsi_setup_q_map_mqprio(vsi, ctx, ena_tc); else - ice_vsi_setup_q_map(vsi, ctx); + ret = ice_vsi_setup_q_map(vsi, ctx); + + if (ret) { + memcpy(&vsi->tc_cfg, &old_tc_cfg, sizeof(vsi->tc_cfg)); + goto out; + } /* must to indicate which section of VSI context are being modified */ ctx->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_RXQ_MAP_VALID); @@ -3806,116 +3748,97 @@ void ice_update_rx_ring_stats(struct ice_rx_ring *rx_ring, u64 pkts, u64 bytes) /** * ice_is_dflt_vsi_in_use - check if the default forwarding VSI is being used - * @sw: switch to check if its default forwarding VSI is free + * @pi: port info of the switch with default VSI * - * Return true if the default forwarding VSI is already being used, else returns - * false signalling that it's available to use. + * Return true if the there is a single VSI in default forwarding VSI list */ -bool ice_is_dflt_vsi_in_use(struct ice_sw *sw) +bool ice_is_dflt_vsi_in_use(struct ice_port_info *pi) { - return (sw->dflt_vsi && sw->dflt_vsi_ena); + bool exists = false; + + ice_check_if_dflt_vsi(pi, 0, &exists); + return exists; } /** * ice_is_vsi_dflt_vsi - check if the VSI passed in is the default VSI - * @sw: switch for the default forwarding VSI to compare against * @vsi: VSI to compare against default forwarding VSI * * If this VSI passed in is the default forwarding VSI then return true, else * return false */ -bool ice_is_vsi_dflt_vsi(struct ice_sw *sw, struct ice_vsi *vsi) +bool ice_is_vsi_dflt_vsi(struct ice_vsi *vsi) { - return (sw->dflt_vsi == vsi && sw->dflt_vsi_ena); + return ice_check_if_dflt_vsi(vsi->port_info, vsi->idx, NULL); } /** * ice_set_dflt_vsi - set the default forwarding VSI - * @sw: switch used to assign the default forwarding VSI * @vsi: VSI getting set as the default forwarding VSI on the switch * * If the VSI passed in is already the default VSI and it's enabled just return * success. * - * If there is already a default VSI on the switch and it's enabled then return - * -EEXIST since there can only be one default VSI per switch. - * - * Otherwise try to set the VSI passed in as the switch's default VSI and - * return the result. + * Otherwise try to set the VSI passed in as the switch's default VSI and + * return the result. */ -int ice_set_dflt_vsi(struct ice_sw *sw, struct ice_vsi *vsi) +int ice_set_dflt_vsi(struct ice_vsi *vsi) { struct device *dev; int status; - if (!sw || !vsi) + if (!vsi) return -EINVAL; dev = ice_pf_to_dev(vsi->back); /* the VSI passed in is already the default VSI */ - if (ice_is_vsi_dflt_vsi(sw, 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", vsi->vsi_num); return 0; } - /* another VSI is already the default VSI for this switch */ - if (ice_is_dflt_vsi_in_use(sw)) { - dev_err(dev, "Default forwarding VSI %d already in use, disable it and try again\n", - sw->dflt_vsi->vsi_num); - return -EEXIST; - } - - status = ice_cfg_dflt_vsi(&vsi->back->hw, vsi->idx, true, ICE_FLTR_RX); + status = ice_cfg_dflt_vsi(vsi->port_info, vsi->idx, true, ICE_FLTR_RX); if (status) { dev_err(dev, "Failed to set VSI %d as the default forwarding VSI, error %d\n", vsi->vsi_num, status); return status; } - sw->dflt_vsi = vsi; - sw->dflt_vsi_ena = true; - return 0; } /** * ice_clear_dflt_vsi - clear the default forwarding VSI - * @sw: switch used to clear the default VSI + * @vsi: VSI to remove from filter list * * If the switch has no default VSI or it's not enabled then return error. * * Otherwise try to clear the default VSI and return the result. */ -int ice_clear_dflt_vsi(struct ice_sw *sw) +int ice_clear_dflt_vsi(struct ice_vsi *vsi) { - struct ice_vsi *dflt_vsi; struct device *dev; int status; - if (!sw) + if (!vsi) return -EINVAL; - dev = ice_pf_to_dev(sw->pf); - - dflt_vsi = sw->dflt_vsi; + dev = ice_pf_to_dev(vsi->back); /* there is no default VSI configured */ - if (!ice_is_dflt_vsi_in_use(sw)) + if (!ice_is_dflt_vsi_in_use(vsi->port_info)) return -ENODEV; - status = ice_cfg_dflt_vsi(&dflt_vsi->back->hw, dflt_vsi->idx, false, + status = ice_cfg_dflt_vsi(vsi->port_info, vsi->idx, false, ICE_FLTR_RX); if (status) { dev_err(dev, "Failed to clear the default forwarding VSI %d, error %d\n", - dflt_vsi->vsi_num, status); + vsi->vsi_num, status); return -EIO; } - sw->dflt_vsi = NULL; - sw->dflt_vsi_ena = false; - return 0; } @@ -4117,9 +4040,9 @@ int ice_set_link(struct ice_vsi *vsi, bool ena) */ if (status == -EIO) { if (hw->adminq.sq_last_status == ICE_AQ_RC_EMODE) - dev_warn(dev, "can't set link to %s, err %d aq_err %s. not fatal, continuing\n", - (ena ? "ON" : "OFF"), status, - ice_aq_str(hw->adminq.sq_last_status)); + dev_dbg(dev, "can't set link to %s, err %d aq_err %s. not fatal, continuing\n", + (ena ? "ON" : "OFF"), status, + ice_aq_str(hw->adminq.sq_last_status)); } else if (status) { dev_err(dev, "can't set link to %s, err %d aq_err %s\n", (ena ? "ON" : "OFF"), status, @@ -4131,6 +4054,124 @@ int ice_set_link(struct ice_vsi *vsi, bool ena) } /** + * ice_vsi_add_vlan_zero - add VLAN 0 filter(s) for this VSI + * @vsi: VSI used to add VLAN filters + * + * In Single VLAN Mode (SVM), single VLAN filters via ICE_SW_LKUP_VLAN are based + * on the inner VLAN ID, so the VLAN TPID (i.e. 0x8100 or 0x888a8) doesn't + * matter. In Double VLAN Mode (DVM), outer/single VLAN filters via + * ICE_SW_LKUP_VLAN are based on the outer/single VLAN ID + VLAN TPID. + * + * For both modes add a VLAN 0 + no VLAN TPID filter to handle untagged traffic + * when VLAN pruning is enabled. Also, this handles VLAN 0 priority tagged + * traffic in SVM, since the VLAN TPID isn't part of filtering. + * + * If DVM is enabled then an explicit VLAN 0 + VLAN TPID filter needs to be + * added to allow VLAN 0 priority tagged traffic in DVM, since the VLAN TPID is + * part of filtering. + */ +int ice_vsi_add_vlan_zero(struct ice_vsi *vsi) +{ + struct ice_vsi_vlan_ops *vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); + struct ice_vlan vlan; + int err; + + vlan = ICE_VLAN(0, 0, 0); + err = vlan_ops->add_vlan(vsi, &vlan); + if (err && err != -EEXIST) + return err; + + /* in SVM both VLAN 0 filters are identical */ + if (!ice_is_dvm_ena(&vsi->back->hw)) + return 0; + + vlan = ICE_VLAN(ETH_P_8021Q, 0, 0); + err = vlan_ops->add_vlan(vsi, &vlan); + if (err && err != -EEXIST) + return err; + + return 0; +} + +/** + * ice_vsi_del_vlan_zero - delete VLAN 0 filter(s) for this VSI + * @vsi: VSI used to add VLAN filters + * + * Delete the VLAN 0 filters in the same manner that they were added in + * ice_vsi_add_vlan_zero. + */ +int ice_vsi_del_vlan_zero(struct ice_vsi *vsi) +{ + struct ice_vsi_vlan_ops *vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); + struct ice_vlan vlan; + int err; + + vlan = ICE_VLAN(0, 0, 0); + err = vlan_ops->del_vlan(vsi, &vlan); + if (err && err != -EEXIST) + return err; + + /* in SVM both VLAN 0 filters are identical */ + if (!ice_is_dvm_ena(&vsi->back->hw)) + return 0; + + vlan = ICE_VLAN(ETH_P_8021Q, 0, 0); + err = vlan_ops->del_vlan(vsi, &vlan); + if (err && err != -EEXIST) + return err; + + /* when deleting the last VLAN filter, make sure to disable the VLAN + * promisc mode so the filter isn't left by accident + */ + return ice_clear_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_VLAN_PROMISC_BITS, 0); +} + +/** + * ice_vsi_num_zero_vlans - get number of VLAN 0 filters based on VLAN mode + * @vsi: VSI used to get the VLAN mode + * + * If DVM is enabled then 2 VLAN 0 filters are added, else if SVM is enabled + * then 1 VLAN 0 filter is added. See ice_vsi_add_vlan_zero for more details. + */ +static u16 ice_vsi_num_zero_vlans(struct ice_vsi *vsi) +{ +#define ICE_DVM_NUM_ZERO_VLAN_FLTRS 2 +#define ICE_SVM_NUM_ZERO_VLAN_FLTRS 1 + /* no VLAN 0 filter is created when a port VLAN is active */ + if (vsi->type == ICE_VSI_VF) { + if (WARN_ON(!vsi->vf)) + return 0; + + if (ice_vf_is_port_vlan_ena(vsi->vf)) + return 0; + } + + if (ice_is_dvm_ena(&vsi->back->hw)) + return ICE_DVM_NUM_ZERO_VLAN_FLTRS; + else + return ICE_SVM_NUM_ZERO_VLAN_FLTRS; +} + +/** + * ice_vsi_has_non_zero_vlans - check if VSI has any non-zero VLANs + * @vsi: VSI used to determine if any non-zero VLANs have been added + */ +bool ice_vsi_has_non_zero_vlans(struct ice_vsi *vsi) +{ + return (vsi->num_vlan > ice_vsi_num_zero_vlans(vsi)); +} + +/** + * ice_vsi_num_non_zero_vlans - get the number of non-zero VLANs for this VSI + * @vsi: VSI used to get the number of non-zero VLANs added + */ +u16 ice_vsi_num_non_zero_vlans(struct ice_vsi *vsi) +{ + return (vsi->num_vlan - ice_vsi_num_zero_vlans(vsi)); +} + +/** * ice_is_feature_supported * @pf: pointer to the struct ice_pf instance * @f: feature enum to be checked @@ -4184,8 +4225,12 @@ void ice_init_feature_support(struct ice_pf *pf) case ICE_DEV_ID_E810C_QSFP: case ICE_DEV_ID_E810C_SFP: ice_set_feature_support(pf, ICE_F_DSCP); - if (ice_is_e810t(&pf->hw)) + ice_set_feature_support(pf, ICE_F_PTP_EXTTS); + if (ice_is_e810t(&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); + } break; default: break; diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index b2ed189527d6..dcdf69a693e9 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -5,6 +5,7 @@ #define _ICE_LIB_H_ #include "ice.h" +#include "ice_vlan.h" const char *ice_vsi_type_str(enum ice_vsi_type vsi_type); @@ -22,15 +23,6 @@ int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi); void ice_vsi_cfg_msix(struct ice_vsi *vsi); -int -ice_vsi_add_vlan(struct ice_vsi *vsi, u16 vid, enum ice_sw_fwd_act_type action); - -int ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid); - -int ice_vsi_manage_vlan_insertion(struct ice_vsi *vsi); - -int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena); - int ice_vsi_start_all_rx_rings(struct ice_vsi *vsi); int ice_vsi_stop_all_rx_rings(struct ice_vsi *vsi); @@ -45,8 +37,6 @@ int ice_vsi_stop_xdp_tx_rings(struct ice_vsi *vsi); bool ice_vsi_is_vlan_pruning_ena(struct ice_vsi *vsi); -int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena); - void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create); int ice_set_link(struct ice_vsi *vsi, bool ena); @@ -62,7 +52,8 @@ 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_port_info *pi, - enum ice_vsi_type vsi_type, u16 vf_id, struct ice_channel *ch); + enum ice_vsi_type vsi_type, struct ice_vf *vf, + struct ice_channel *ch); void ice_napi_del(struct ice_vsi *vsi); @@ -98,6 +89,8 @@ void ice_vsi_free_tx_rings(struct ice_vsi *vsi); void ice_vsi_manage_rss_lut(struct ice_vsi *vsi, bool ena); +void ice_vsi_cfg_crc_strip(struct ice_vsi *vsi, bool disable); + 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); @@ -110,14 +103,11 @@ void ice_set_q_vector_intrl(struct ice_q_vector *q_vector); int ice_vsi_cfg_mac_fltr(struct ice_vsi *vsi, const u8 *macaddr, bool set); bool ice_is_safe_mode(struct ice_pf *pf); -bool ice_is_aux_ena(struct ice_pf *pf); -bool ice_is_dflt_vsi_in_use(struct ice_sw *sw); - -bool ice_is_vsi_dflt_vsi(struct ice_sw *sw, struct ice_vsi *vsi); - -int ice_set_dflt_vsi(struct ice_sw *sw, struct ice_vsi *vsi); - -int ice_clear_dflt_vsi(struct ice_sw *sw); +bool ice_is_rdma_ena(struct ice_pf *pf); +bool ice_is_dflt_vsi_in_use(struct ice_port_info *pi); +bool ice_is_vsi_dflt_vsi(struct ice_vsi *vsi); +int ice_set_dflt_vsi(struct ice_vsi *vsi); +int ice_clear_dflt_vsi(struct ice_vsi *vsi); int ice_set_min_bw_limit(struct ice_vsi *vsi, u64 min_tx_rate); int ice_set_max_bw_limit(struct ice_vsi *vsi, u64 max_tx_rate); int ice_get_link_speed_kbps(struct ice_vsi *vsi); @@ -132,8 +122,12 @@ 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_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_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); #endif /* !_ICE_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 30814435f779..0f6718719453 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -21,6 +21,7 @@ #include "ice_trace.h" #include "ice_eswitch.h" #include "ice_tc_lib.h" +#include "ice_vsi_vlan_ops.h" #define DRV_SUMMARY "Intel(R) Ethernet Connection E800 Series Linux Driver" static const char ice_driver_string[] = DRV_SUMMARY; @@ -47,6 +48,21 @@ static DEFINE_IDA(ice_aux_ida); DEFINE_STATIC_KEY_FALSE(ice_xdp_locking_key); EXPORT_SYMBOL(ice_xdp_locking_key); +/** + * ice_hw_to_dev - Get device pointer from the hardware structure + * @hw: pointer to the device HW structure + * + * Used to access the device pointer from compilation units which can't easily + * include the definition of struct ice_pf without leading to circular header + * dependencies. + */ +struct device *ice_hw_to_dev(struct ice_hw *hw) +{ + struct ice_pf *pf = container_of(hw, struct ice_pf, hw); + + return &pf->pdev->dev; +} + static struct workqueue_struct *ice_wq; static const struct net_device_ops ice_netdev_safe_mode_ops; static const struct net_device_ops ice_netdev_ops; @@ -227,8 +243,7 @@ static int ice_add_mac_to_unsync_list(struct net_device *netdev, const u8 *addr) static bool ice_vsi_fltr_changed(struct ice_vsi *vsi) { return test_bit(ICE_VSI_UMAC_FLTR_CHANGED, vsi->state) || - test_bit(ICE_VSI_MMAC_FLTR_CHANGED, vsi->state) || - test_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); + test_bit(ICE_VSI_MMAC_FLTR_CHANGED, vsi->state); } /** @@ -244,11 +259,18 @@ static int ice_set_promisc(struct ice_vsi *vsi, u8 promisc_m) if (vsi->type != ICE_VSI_PF) return 0; - if (vsi->num_vlan > 1) - status = ice_fltr_set_vlan_vsi_promisc(&vsi->back->hw, vsi, promisc_m); - else - status = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, promisc_m, 0); - return status; + if (ice_vsi_has_non_zero_vlans(vsi)) { + promisc_m |= (ICE_PROMISC_VLAN_RX | ICE_PROMISC_VLAN_TX); + status = ice_fltr_set_vlan_vsi_promisc(&vsi->back->hw, vsi, + promisc_m); + } else { + status = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, + promisc_m, 0); + } + if (status && status != -EEXIST) + return status; + + return 0; } /** @@ -264,14 +286,33 @@ static int ice_clear_promisc(struct ice_vsi *vsi, u8 promisc_m) if (vsi->type != ICE_VSI_PF) return 0; - if (vsi->num_vlan > 1) - status = ice_fltr_clear_vlan_vsi_promisc(&vsi->back->hw, vsi, promisc_m); - else - status = ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, promisc_m, 0); + if (ice_vsi_has_non_zero_vlans(vsi)) { + promisc_m |= (ICE_PROMISC_VLAN_RX | ICE_PROMISC_VLAN_TX); + status = ice_fltr_clear_vlan_vsi_promisc(&vsi->back->hw, vsi, + promisc_m); + } else { + status = ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, + promisc_m, 0); + } + return status; } /** + * ice_get_devlink_port - Get devlink port from netdev + * @netdev: the netdevice structure + */ +static struct devlink_port *ice_get_devlink_port(struct net_device *netdev) +{ + struct ice_pf *pf = ice_netdev_to_pf(netdev); + + if (!ice_is_switchdev_running(pf)) + return NULL; + + return &pf->devlink_port; +} + +/** * ice_vsi_sync_fltr - Update the VSI filter list to the HW * @vsi: ptr to the VSI * @@ -279,13 +320,13 @@ static int ice_clear_promisc(struct ice_vsi *vsi, u8 promisc_m) */ static int ice_vsi_sync_fltr(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(vsi->back); struct net_device *netdev = vsi->netdev; bool promisc_forced_on = false; struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; u32 changed_flags = 0; - u8 promisc_m; int err; if (!vsi->netdev) @@ -303,7 +344,6 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) if (ice_vsi_fltr_changed(vsi)) { clear_bit(ICE_VSI_UMAC_FLTR_CHANGED, vsi->state); clear_bit(ICE_VSI_MMAC_FLTR_CHANGED, vsi->state); - clear_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); /* grab the netdev's addr_list_lock */ netif_addr_lock_bh(netdev); @@ -352,29 +392,15 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) /* check for changes in promiscuous modes */ if (changed_flags & IFF_ALLMULTI) { if (vsi->current_netdev_flags & IFF_ALLMULTI) { - if (vsi->num_vlan > 1) - promisc_m = ICE_MCAST_VLAN_PROMISC_BITS; - else - promisc_m = ICE_MCAST_PROMISC_BITS; - - err = ice_set_promisc(vsi, promisc_m); + err = ice_set_promisc(vsi, ICE_MCAST_PROMISC_BITS); if (err) { - netdev_err(netdev, "Error setting Multicast promiscuous mode on VSI %i\n", - vsi->vsi_num); vsi->current_netdev_flags &= ~IFF_ALLMULTI; goto out_promisc; } } else { /* !(vsi->current_netdev_flags & IFF_ALLMULTI) */ - if (vsi->num_vlan > 1) - promisc_m = ICE_MCAST_VLAN_PROMISC_BITS; - else - promisc_m = ICE_MCAST_PROMISC_BITS; - - err = ice_clear_promisc(vsi, promisc_m); + err = ice_clear_promisc(vsi, ICE_MCAST_PROMISC_BITS); if (err) { - netdev_err(netdev, "Error clearing Multicast promiscuous mode on VSI %i\n", - vsi->vsi_num); vsi->current_netdev_flags |= IFF_ALLMULTI; goto out_promisc; } @@ -386,8 +412,8 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) clear_bit(ICE_VSI_PROMISC_CHANGED, vsi->state); if (vsi->current_netdev_flags & IFF_PROMISC) { /* Apply Rx filter rule to get traffic from wire */ - if (!ice_is_dflt_vsi_in_use(pf->first_sw)) { - err = ice_set_dflt_vsi(pf->first_sw, vsi); + if (!ice_is_dflt_vsi_in_use(vsi->port_info)) { + err = ice_set_dflt_vsi(vsi); if (err && err != -EEXIST) { netdev_err(netdev, "Error %d setting default VSI %i Rx rule\n", err, vsi->vsi_num); @@ -396,12 +422,12 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) goto out_promisc; } err = 0; - ice_cfg_vlan_pruning(vsi, false); + vlan_ops->dis_rx_filtering(vsi); } } else { /* Clear Rx filter to remove traffic from wire */ - if (ice_is_vsi_dflt_vsi(pf->first_sw, vsi)) { - err = ice_clear_dflt_vsi(pf->first_sw); + if (ice_is_vsi_dflt_vsi(vsi)) { + err = ice_clear_dflt_vsi(vsi); if (err) { netdev_err(netdev, "Error %d clearing default VSI %i Rx rule\n", err, vsi->vsi_num); @@ -409,8 +435,9 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) IFF_PROMISC; goto out_promisc; } - if (vsi->num_vlan > 1) - ice_cfg_vlan_pruning(vsi, true); + if (vsi->netdev->features & + NETIF_F_HW_VLAN_CTAG_FILTER) + vlan_ops->ena_rx_filtering(vsi); } } } @@ -502,7 +529,8 @@ ice_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type) { struct ice_hw *hw = &pf->hw; struct ice_vsi *vsi; - unsigned int i; + struct ice_vf *vf; + unsigned int bkt; dev_dbg(ice_pf_to_dev(pf), "reset_type=%d\n", reset_type); @@ -517,8 +545,10 @@ ice_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type) ice_vc_notify_reset(pf); /* Disable VFs until reset is completed */ - ice_for_each_vf(pf, i) - ice_set_vf_state_qs_dis(&pf->vf[i]); + mutex_lock(&pf->vfs.table_lock); + ice_for_each_vf(pf, bkt, vf) + ice_set_vf_state_qs_dis(vf); + mutex_unlock(&pf->vfs.table_lock); if (ice_is_eswitch_mode_switchdev(pf)) { if (reset_type != ICE_RESET_PFR) @@ -565,6 +595,9 @@ skip: if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) ice_ptp_prepare_for_reset(pf); + if (ice_is_feature_supported(pf, ICE_F_GNSS)) + ice_gnss_exit(pf); + if (hw->port_info) ice_sched_clear_port(hw->port_info); @@ -610,7 +643,7 @@ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type) clear_bit(ICE_PREPARED_FOR_RESET, pf->state); clear_bit(ICE_PFR_REQ, pf->state); wake_up(&pf->reset_wait_queue); - ice_reset_all_vfs(pf, true); + ice_reset_all_vfs(pf); } } @@ -661,7 +694,7 @@ static void ice_reset_subtask(struct ice_pf *pf) clear_bit(ICE_CORER_REQ, pf->state); clear_bit(ICE_GLOBR_REQ, pf->state); wake_up(&pf->reset_wait_queue); - ice_reset_all_vfs(pf, true); + ice_reset_all_vfs(pf); } return; @@ -1660,7 +1693,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf) { struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; - unsigned int i; + struct ice_vf *vf; + unsigned int bkt; u32 reg; if (!test_and_clear_bit(ICE_MDD_EVENT_PENDING, pf->state)) { @@ -1748,47 +1782,46 @@ static void ice_handle_mdd_event(struct ice_pf *pf) /* Check to see if one of the VFs caused an MDD event, and then * increment counters and set print pending */ - ice_for_each_vf(pf, i) { - struct ice_vf *vf = &pf->vf[i]; - - reg = rd32(hw, VP_MDET_TX_PQM(i)); + mutex_lock(&pf->vfs.table_lock); + ice_for_each_vf(pf, bkt, vf) { + reg = rd32(hw, VP_MDET_TX_PQM(vf->vf_id)); if (reg & VP_MDET_TX_PQM_VALID_M) { - wr32(hw, VP_MDET_TX_PQM(i), 0xFFFF); + wr32(hw, VP_MDET_TX_PQM(vf->vf_id), 0xFFFF); vf->mdd_tx_events.count++; set_bit(ICE_MDD_VF_PRINT_PENDING, pf->state); if (netif_msg_tx_err(pf)) dev_info(dev, "Malicious Driver Detection event TX_PQM detected on VF %d\n", - i); + vf->vf_id); } - reg = rd32(hw, VP_MDET_TX_TCLAN(i)); + reg = rd32(hw, VP_MDET_TX_TCLAN(vf->vf_id)); if (reg & VP_MDET_TX_TCLAN_VALID_M) { - wr32(hw, VP_MDET_TX_TCLAN(i), 0xFFFF); + wr32(hw, VP_MDET_TX_TCLAN(vf->vf_id), 0xFFFF); vf->mdd_tx_events.count++; set_bit(ICE_MDD_VF_PRINT_PENDING, pf->state); if (netif_msg_tx_err(pf)) dev_info(dev, "Malicious Driver Detection event TX_TCLAN detected on VF %d\n", - i); + vf->vf_id); } - reg = rd32(hw, VP_MDET_TX_TDPU(i)); + reg = rd32(hw, VP_MDET_TX_TDPU(vf->vf_id)); if (reg & VP_MDET_TX_TDPU_VALID_M) { - wr32(hw, VP_MDET_TX_TDPU(i), 0xFFFF); + wr32(hw, VP_MDET_TX_TDPU(vf->vf_id), 0xFFFF); vf->mdd_tx_events.count++; set_bit(ICE_MDD_VF_PRINT_PENDING, pf->state); if (netif_msg_tx_err(pf)) dev_info(dev, "Malicious Driver Detection event TX_TDPU detected on VF %d\n", - i); + vf->vf_id); } - reg = rd32(hw, VP_MDET_RX(i)); + reg = rd32(hw, VP_MDET_RX(vf->vf_id)); if (reg & VP_MDET_RX_VALID_M) { - wr32(hw, VP_MDET_RX(i), 0xFFFF); + wr32(hw, VP_MDET_RX(vf->vf_id), 0xFFFF); vf->mdd_rx_events.count++; set_bit(ICE_MDD_VF_PRINT_PENDING, pf->state); if (netif_msg_rx_err(pf)) dev_info(dev, "Malicious Driver Detection event RX detected on VF %d\n", - i); + vf->vf_id); /* Since the queue is disabled on VF Rx MDD events, the * PF can be configured to reset the VF through ethtool @@ -1799,10 +1832,11 @@ static void ice_handle_mdd_event(struct ice_pf *pf) * reset, so print the event prior to reset. */ ice_print_vf_rx_mdd_event(vf); - ice_reset_vf(&pf->vf[i], false); + ice_reset_vf(vf, ICE_VF_RESET_LOCK); } } } + mutex_unlock(&pf->vfs.table_lock); ice_print_vfs_mdd_events(pf); } @@ -2253,6 +2287,43 @@ static void ice_service_task(struct work_struct *work) return; } + if (test_and_clear_bit(ICE_AUX_ERR_PENDING, pf->state)) { + struct iidc_event *event; + + event = kzalloc(sizeof(*event), GFP_KERNEL); + if (event) { + set_bit(IIDC_EVENT_CRIT_ERR, event->type); + /* report the entire OICR value to AUX driver */ + swap(event->reg, pf->oicr_err_reg); + ice_send_event_to_aux(pf, event); + kfree(event); + } + } + + if (test_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags)) { + /* Plug aux device per request */ + ice_plug_aux_dev(pf); + + /* Mark plugging as done but check whether unplug was + * requested during ice_plug_aux_dev() call + * (e.g. from ice_clear_rdma_cap()) and if so then + * plug aux device. + */ + if (!test_and_clear_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags)) + ice_unplug_aux_dev(pf); + } + + if (test_and_clear_bit(ICE_FLAG_MTU_CHANGED, pf->flags)) { + struct iidc_event *event; + + event = kzalloc(sizeof(*event), GFP_KERNEL); + if (event) { + set_bit(IIDC_EVENT_AFTER_MTU_CHANGE, event->type); + ice_send_event_to_aux(pf, event); + kfree(event); + } + } + ice_clean_adminq_subtask(pf); ice_check_media_subtask(pf); ice_check_for_hang_subtask(pf); @@ -2328,8 +2399,6 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset) return -EBUSY; } - ice_unplug_aux_dev(pf); - switch (reset) { case ICE_RESET_PFR: set_bit(ICE_PFR_REQ, pf->state); @@ -2428,7 +2497,7 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) /* skip this unused q_vector */ continue; } - if (vsi->type == ICE_VSI_CTRL && vsi->vf_id != ICE_INVAL_VFID) + if (vsi->type == ICE_VSI_CTRL && vsi->vf) err = devm_request_irq(dev, irq_num, vsi->irq_handler, IRQF_SHARED, q_vector->name, q_vector); @@ -2455,6 +2524,13 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) irq_set_affinity_hint(irq_num, &q_vector->affinity_mask); } + err = ice_set_cpu_rx_rmap(vsi); + if (err) { + netdev_err(vsi->netdev, "Failed to setup CPU RMAP on VSI %u: %pe\n", + vsi->vsi_num, ERR_PTR(err)); + goto free_q_irqs; + } + vsi->irqs_ready = true; return 0; @@ -2495,29 +2571,21 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi) xdp_ring->reg_idx = vsi->txq_map[xdp_q_idx]; xdp_ring->vsi = vsi; xdp_ring->netdev = NULL; - xdp_ring->next_dd = ICE_TX_THRESH - 1; - xdp_ring->next_rs = ICE_TX_THRESH - 1; xdp_ring->dev = dev; xdp_ring->count = vsi->num_tx_desc; + xdp_ring->next_dd = ICE_RING_QUARTER(xdp_ring) - 1; + xdp_ring->next_rs = ICE_RING_QUARTER(xdp_ring) - 1; WRITE_ONCE(vsi->xdp_rings[i], xdp_ring); if (ice_setup_tx_ring(xdp_ring)) goto free_xdp_rings; ice_set_ring_xdp(xdp_ring); - xdp_ring->xsk_pool = ice_tx_xsk_pool(xdp_ring); spin_lock_init(&xdp_ring->tx_lock); for (j = 0; j < xdp_ring->count; j++) { tx_desc = ICE_TX_DESC(xdp_ring, j); - tx_desc->cmd_type_offset_bsz = cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE); + tx_desc->cmd_type_offset_bsz = 0; } } - ice_for_each_rxq(vsi, i) { - if (static_key_enabled(&ice_xdp_locking_key)) - vsi->rx_rings[i]->xdp_ring = vsi->xdp_rings[i % vsi->num_xdp_txq]; - else - vsi->rx_rings[i]->xdp_ring = vsi->xdp_rings[i]; - } - return 0; free_xdp_rings: @@ -2607,6 +2675,23 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) xdp_rings_rem -= xdp_rings_per_v; } + ice_for_each_rxq(vsi, i) { + if (static_key_enabled(&ice_xdp_locking_key)) { + vsi->rx_rings[i]->xdp_ring = vsi->xdp_rings[i % vsi->num_xdp_txq]; + } else { + struct ice_q_vector *q_vector = vsi->rx_rings[i]->q_vector; + struct ice_tx_ring *ring; + + ice_for_each_tx_ring(ring, q_vector->tx) { + if (ice_ring_is_xdp(ring)) { + vsi->rx_rings[i]->xdp_ring = ring; + break; + } + } + } + ice_tx_xsk_pool(vsi, i); + } + /* omit the scheduler update if in reset path; XDP queues will be * taken into account at the end of ice_vsi_rebuild, where * ice_cfg_vsi_lan is being called @@ -2703,8 +2788,10 @@ free_qmap: ice_for_each_xdp_txq(vsi, i) if (vsi->xdp_rings[i]) { - if (vsi->xdp_rings[i]->desc) + if (vsi->xdp_rings[i]->desc) { + synchronize_rcu(); ice_free_tx_ring(vsi->xdp_rings[i]); + } kfree_rcu(vsi->xdp_rings[i], rcu); vsi->xdp_rings[i] = NULL; } @@ -2809,10 +2896,18 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, if (xdp_ring_err) NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Tx resources failed"); } + /* reallocate Rx queues that are used for zero-copy */ + xdp_ring_err = ice_realloc_zc_buf(vsi, true); + if (xdp_ring_err) + NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Rx resources failed"); } else if (ice_is_xdp_ena_vsi(vsi) && !prog) { xdp_ring_err = ice_destroy_xdp_rings(vsi); if (xdp_ring_err) NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Tx resources failed"); + /* reallocate Rx queues that were used for zero-copy */ + xdp_ring_err = ice_realloc_zc_buf(vsi, false); + if (xdp_ring_err) + NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Rx resources failed"); } else { /* safe to call even when prog == vsi->xdp_prog as * dev_xdp_install in net/core/dev.c incremented prog's @@ -2998,7 +3093,8 @@ 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; - ice_ptp_process_ts(pf); + if (!hw->reset_ongoing) + ret = IRQ_WAKE_THREAD; } if (oicr & PFINT_OICR_TSYN_EVNT_M) { @@ -3015,17 +3111,9 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) #define ICE_AUX_CRIT_ERR (PFINT_OICR_PE_CRITERR_M | PFINT_OICR_HMC_ERR_M | PFINT_OICR_PE_PUSH_M) if (oicr & ICE_AUX_CRIT_ERR) { - struct iidc_event *event; - + pf->oicr_err_reg |= oicr; + set_bit(ICE_AUX_ERR_PENDING, pf->state); ena_mask &= ~ICE_AUX_CRIT_ERR; - event = kzalloc(sizeof(*event), GFP_KERNEL); - if (event) { - set_bit(IIDC_EVENT_CRIT_ERR, event->type); - /* report the entire OICR value to AUX driver */ - event->reg = oicr; - ice_send_event_to_aux(pf, event); - kfree(event); - } } /* Report any remaining unexpected interrupts */ @@ -3041,7 +3129,8 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) ice_service_task_schedule(pf); } } - ret = IRQ_HANDLED; + if (!ret) + ret = IRQ_HANDLED; ice_service_task_schedule(pf); ice_irq_dynamic_ena(hw, NULL, NULL); @@ -3050,6 +3139,24 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) } /** + * ice_misc_intr_thread_fn - misc interrupt thread function + * @irq: interrupt number + * @data: pointer to a q_vector + */ +static irqreturn_t ice_misc_intr_thread_fn(int __always_unused irq, void *data) +{ + irqreturn_t ret = IRQ_HANDLED; + struct ice_pf *pf = data; + bool irq_handled; + + irq_handled = ice_ptp_process_ts(pf); + if (!irq_handled) + ret = IRQ_WAKE_THREAD; + + return ret; +} + +/** * ice_dis_ctrlq_interrupts - disable control queue interrupts * @hw: pointer to HW structure */ @@ -3161,10 +3268,12 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf) pf->num_avail_sw_msix -= 1; pf->oicr_idx = (u16)oicr_idx; - err = devm_request_irq(dev, pf->msix_entries[pf->oicr_idx].vector, - ice_misc_intr, 0, pf->int_name, pf); + err = devm_request_threaded_irq(dev, + pf->msix_entries[pf->oicr_idx].vector, + ice_misc_intr, ice_misc_intr_thread_fn, + 0, pf->int_name, pf); if (err) { - dev_err(dev, "devm_request_irq for %s failed: %d\n", + dev_err(dev, "devm_request_threaded_irq for %s failed: %d\n", pf->int_name, err); ice_free_res(pf->irq_tracker, 1, ICE_RES_MISC_VEC_ID); pf->num_avail_sw_msix += 1; @@ -3201,7 +3310,7 @@ static void ice_napi_add(struct ice_vsi *vsi) ice_for_each_q_vector(vsi, v_idx) netif_napi_add(vsi->netdev, &vsi->q_vectors[v_idx]->napi, - ice_napi_poll, NAPI_POLL_WEIGHT); + ice_napi_poll); } /** @@ -3230,6 +3339,7 @@ static void ice_set_ops(struct net_device *netdev) static void ice_set_netdev_features(struct net_device *netdev) { struct ice_pf *pf = ice_netdev_to_pf(netdev); + bool is_dvm_ena = ice_is_dvm_ena(&pf->hw); netdev_features_t csumo_features; netdev_features_t vlano_features; netdev_features_t dflt_features; @@ -3256,6 +3366,10 @@ static void ice_set_netdev_features(struct net_device *netdev) NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; + /* Enable CTAG/STAG filtering by default in Double VLAN Mode (DVM) */ + if (is_dvm_ena) + vlano_features |= NETIF_F_HW_VLAN_STAG_FILTER; + tso_features = NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6 | @@ -3275,18 +3389,35 @@ static void ice_set_netdev_features(struct net_device *netdev) vlano_features | tso_features; /* add support for HW_CSUM on packets with MPLS header */ - netdev->mpls_features = NETIF_F_HW_CSUM; + netdev->mpls_features = NETIF_F_HW_CSUM | + NETIF_F_TSO | + NETIF_F_TSO6; /* enable features */ netdev->features |= netdev->hw_features; netdev->hw_features |= NETIF_F_HW_TC; + netdev->hw_features |= NETIF_F_LOOPBACK; /* encap and VLAN devices inherit default, csumo and tso features */ netdev->hw_enc_features |= dflt_features | csumo_features | tso_features; netdev->vlan_features |= dflt_features | csumo_features | tso_features; + + /* advertise support but don't enable by default since only one type of + * VLAN offload can be enabled at a time (i.e. CTAG or STAG). When one + * type turns on the other has to be turned off. This is enforced by the + * ice_fix_features() ndo callback. + */ + if (is_dvm_ena) + netdev->hw_features |= NETIF_F_HW_VLAN_STAG_RX | + NETIF_F_HW_VLAN_STAG_TX; + + /* Leave CRC / FCS stripping enabled by default, but allow the value to + * be changed at runtime + */ + netdev->hw_features |= NETIF_F_RXFCS; } /** @@ -3361,14 +3492,14 @@ void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size) static struct ice_vsi * ice_pf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) { - return ice_vsi_setup(pf, pi, ICE_VSI_PF, ICE_INVAL_VFID, NULL); + return ice_vsi_setup(pf, pi, ICE_VSI_PF, NULL, NULL); } static struct ice_vsi * ice_chnl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, struct ice_channel *ch) { - return ice_vsi_setup(pf, pi, ICE_VSI_CHNL, ICE_INVAL_VFID, ch); + return ice_vsi_setup(pf, pi, ICE_VSI_CHNL, NULL, ch); } /** @@ -3382,7 +3513,7 @@ ice_chnl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, static struct ice_vsi * ice_ctrl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) { - return ice_vsi_setup(pf, pi, ICE_VSI_CTRL, ICE_INVAL_VFID, NULL); + return ice_vsi_setup(pf, pi, ICE_VSI_CTRL, NULL, NULL); } /** @@ -3396,42 +3527,68 @@ ice_ctrl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) struct ice_vsi * ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) { - return ice_vsi_setup(pf, pi, ICE_VSI_LB, ICE_INVAL_VFID, NULL); + return ice_vsi_setup(pf, pi, ICE_VSI_LB, NULL, NULL); } /** * ice_vlan_rx_add_vid - Add a VLAN ID filter to HW offload * @netdev: network interface to be adjusted - * @proto: unused protocol + * @proto: VLAN TPID * @vid: VLAN ID to be added * * net_device_ops implementation for adding VLAN IDs */ static int -ice_vlan_rx_add_vid(struct net_device *netdev, __always_unused __be16 proto, - u16 vid) +ice_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) { struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_vsi_vlan_ops *vlan_ops; struct ice_vsi *vsi = np->vsi; + struct ice_vlan vlan; int ret; /* VLAN 0 is added by default during load/reset */ if (!vid) return 0; - /* Enable VLAN pruning when a VLAN other than 0 is added */ - if (!ice_vsi_is_vlan_pruning_ena(vsi)) { - ret = ice_cfg_vlan_pruning(vsi, true); + while (test_and_set_bit(ICE_CFG_BUSY, vsi->state)) + usleep_range(1000, 2000); + + /* Add multicast promisc rule for the VLAN ID to be added if + * all-multicast is currently enabled. + */ + if (vsi->current_netdev_flags & IFF_ALLMULTI) { + ret = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_VLAN_PROMISC_BITS, + vid); if (ret) - return ret; + goto finish; } + vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); + /* Add a switch rule for this VLAN ID so its corresponding VLAN tagged * packets aren't pruned by the device's internal switch on Rx */ - ret = ice_vsi_add_vlan(vsi, vid, ICE_FWD_TO_VSI); - if (!ret) - set_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); + vlan = ICE_VLAN(be16_to_cpu(proto), vid, 0); + ret = vlan_ops->add_vlan(vsi, &vlan); + if (ret) + goto finish; + + /* If all-multicast is currently enabled and this VLAN ID is only one + * besides VLAN-0 we have to update look-up type of multicast promisc + * rule for VLAN-0 from ICE_SW_LKUP_PROMISC to ICE_SW_LKUP_PROMISC_VLAN. + */ + if ((vsi->current_netdev_flags & IFF_ALLMULTI) && + ice_vsi_num_non_zero_vlans(vsi) == 1) { + ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_PROMISC_BITS, 0); + ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_VLAN_PROMISC_BITS, 0); + } + +finish: + clear_bit(ICE_CFG_BUSY, vsi->state); return ret; } @@ -3439,35 +3596,69 @@ ice_vlan_rx_add_vid(struct net_device *netdev, __always_unused __be16 proto, /** * ice_vlan_rx_kill_vid - Remove a VLAN ID filter from HW offload * @netdev: network interface to be adjusted - * @proto: unused protocol + * @proto: VLAN TPID * @vid: VLAN ID to be removed * * net_device_ops implementation for removing VLAN IDs */ static int -ice_vlan_rx_kill_vid(struct net_device *netdev, __always_unused __be16 proto, - u16 vid) +ice_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) { struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_vsi_vlan_ops *vlan_ops; struct ice_vsi *vsi = np->vsi; + struct ice_vlan vlan; int ret; /* don't allow removal of VLAN 0 */ if (!vid) return 0; - /* Make sure ice_vsi_kill_vlan is successful before updating VLAN + while (test_and_set_bit(ICE_CFG_BUSY, vsi->state)) + usleep_range(1000, 2000); + + ret = ice_clear_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_VLAN_PROMISC_BITS, vid); + if (ret) { + netdev_err(netdev, "Error clearing multicast promiscuous mode on VSI %i\n", + vsi->vsi_num); + vsi->current_netdev_flags |= IFF_ALLMULTI; + } + + vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); + + /* Make sure VLAN delete is successful before updating VLAN * information */ - ret = ice_vsi_kill_vlan(vsi, vid); + vlan = ICE_VLAN(be16_to_cpu(proto), vid, 0); + ret = vlan_ops->del_vlan(vsi, &vlan); if (ret) - return ret; + goto finish; + + /* Remove multicast promisc rule for the removed VLAN ID if + * all-multicast is enabled. + */ + if (vsi->current_netdev_flags & IFF_ALLMULTI) + ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_VLAN_PROMISC_BITS, vid); + + if (!ice_vsi_has_non_zero_vlans(vsi)) { + /* Update look-up type of multicast promisc rule for VLAN 0 + * from ICE_SW_LKUP_PROMISC_VLAN to ICE_SW_LKUP_PROMISC when + * all-multicast is enabled and VLAN 0 is the only VLAN rule. + */ + if (vsi->current_netdev_flags & IFF_ALLMULTI) { + ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_VLAN_PROMISC_BITS, + 0); + ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_PROMISC_BITS, 0); + } + } - /* Disable pruning when VLAN 0 is the only VLAN rule */ - if (vsi->num_vlan == 1 && ice_vsi_is_vlan_pruning_ena(vsi)) - ret = ice_cfg_vlan_pruning(vsi, false); +finish: + clear_bit(ICE_CFG_BUSY, vsi->state); - set_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); return ret; } @@ -3537,12 +3728,17 @@ static int ice_tc_indir_block_register(struct ice_vsi *vsi) static int ice_setup_pf_sw(struct ice_pf *pf) { struct device *dev = ice_pf_to_dev(pf); + bool dvm = ice_is_dvm_ena(&pf->hw); struct ice_vsi *vsi; int status; if (ice_is_reset_in_progress(pf->state)) return -EBUSY; + status = ice_aq_set_port_params(pf->hw.port_info, dvm, NULL); + if (status) + return -EIO; + vsi = ice_pf_vsi_setup(pf, pf->hw.port_info); if (!vsi) return -ENOMEM; @@ -3572,20 +3768,12 @@ static int ice_setup_pf_sw(struct ice_pf *pf) */ ice_napi_add(vsi); - status = ice_set_cpu_rx_rmap(vsi); - if (status) { - dev_err(dev, "Failed to set CPU Rx map VSI %d error %d\n", - vsi->vsi_num, status); - goto unroll_napi_add; - } status = ice_init_mac_fltr(pf); if (status) - goto free_cpu_rx_map; + goto unroll_napi_add; return 0; -free_cpu_rx_map: - ice_free_cpu_rx_rmap(vsi); unroll_napi_add: ice_tc_indir_block_unregister(vsi); unroll_cfg_netdev: @@ -3650,9 +3838,11 @@ 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->adev_mutex); mutex_destroy(&pf->sw_mutex); mutex_destroy(&pf->tc_mutex); mutex_destroy(&pf->avail_q_mutex); + mutex_destroy(&pf->vfs.table_lock); if (pf->avail_txqs) { bitmap_free(pf->avail_txqs); @@ -3677,19 +3867,16 @@ static void ice_set_pf_caps(struct ice_pf *pf) struct ice_hw_func_caps *func_caps = &pf->hw.func_caps; clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); - clear_bit(ICE_FLAG_AUX_ENA, pf->flags); - if (func_caps->common_cap.rdma) { + if (func_caps->common_cap.rdma) set_bit(ICE_FLAG_RDMA_ENA, pf->flags); - set_bit(ICE_FLAG_AUX_ENA, pf->flags); - } clear_bit(ICE_FLAG_DCB_CAPABLE, pf->flags); if (func_caps->common_cap.dcb) set_bit(ICE_FLAG_DCB_CAPABLE, pf->flags); clear_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags); if (func_caps->common_cap.sr_iov_1_1) { set_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags); - pf->num_vfs_supported = min_t(int, func_caps->num_allocd_vfs, - ICE_MAX_VF_COUNT); + pf->vfs.num_supported = min_t(int, func_caps->num_allocd_vfs, + ICE_MAX_SRIOV_VFS); } clear_bit(ICE_FLAG_RSS_ENA, pf->flags); if (func_caps->common_cap.rss_table_size) @@ -3730,6 +3917,7 @@ static int ice_init_pf(struct ice_pf *pf) mutex_init(&pf->sw_mutex); mutex_init(&pf->tc_mutex); + mutex_init(&pf->adev_mutex); INIT_HLIST_HEAD(&pf->aq_wait_list); spin_lock_init(&pf->aq_wait_lock); @@ -3750,96 +3938,146 @@ static int ice_init_pf(struct ice_pf *pf) pf->avail_rxqs = bitmap_zalloc(pf->max_pf_rxqs, GFP_KERNEL); if (!pf->avail_rxqs) { - devm_kfree(ice_pf_to_dev(pf), pf->avail_txqs); + bitmap_free(pf->avail_txqs); pf->avail_txqs = NULL; return -ENOMEM; } + mutex_init(&pf->vfs.table_lock); + hash_init(pf->vfs.table); + return 0; } /** + * ice_reduce_msix_usage - Reduce usage of MSI-X vectors + * @pf: board private structure + * @v_remain: number of remaining MSI-X vectors to be distributed + * + * Reduce the usage of MSI-X vectors when entire request cannot be fulfilled. + * pf->num_lan_msix and pf->num_rdma_msix values are set based on number of + * remaining vectors. + */ +static void ice_reduce_msix_usage(struct ice_pf *pf, int v_remain) +{ + int v_rdma; + + if (!ice_is_rdma_ena(pf)) { + pf->num_lan_msix = v_remain; + return; + } + + /* RDMA needs at least 1 interrupt in addition to AEQ MSIX */ + v_rdma = ICE_RDMA_NUM_AEQ_MSIX + 1; + + if (v_remain < ICE_MIN_LAN_TXRX_MSIX + ICE_MIN_RDMA_MSIX) { + dev_warn(ice_pf_to_dev(pf), "Not enough MSI-X vectors to support RDMA.\n"); + clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); + + pf->num_rdma_msix = 0; + pf->num_lan_msix = ICE_MIN_LAN_TXRX_MSIX; + } else if ((v_remain < ICE_MIN_LAN_TXRX_MSIX + v_rdma) || + (v_remain - v_rdma < v_rdma)) { + /* Support minimum RDMA and give remaining vectors to LAN MSIX */ + pf->num_rdma_msix = ICE_MIN_RDMA_MSIX; + pf->num_lan_msix = v_remain - ICE_MIN_RDMA_MSIX; + } else { + /* Split remaining MSIX with RDMA after accounting for AEQ MSIX + */ + pf->num_rdma_msix = (v_remain - ICE_RDMA_NUM_AEQ_MSIX) / 2 + + ICE_RDMA_NUM_AEQ_MSIX; + pf->num_lan_msix = v_remain - pf->num_rdma_msix; + } +} + +/** * ice_ena_msix_range - Request a range of MSIX vectors from the OS * @pf: board private structure * - * compute the number of MSIX vectors required (v_budget) and request from - * the OS. Return the number of vectors reserved or negative on failure + * Compute the number of MSIX vectors wanted and request from the OS. Adjust + * device usage if there are not enough vectors. Return the number of vectors + * reserved or negative on failure. */ static int ice_ena_msix_range(struct ice_pf *pf) { - int num_cpus, v_left, v_actual, v_other, v_budget = 0; + int num_cpus, hw_num_msix, v_other, v_wanted, v_actual; struct device *dev = ice_pf_to_dev(pf); - int needed, err, i; + int err, i; - v_left = pf->hw.func_caps.common_cap.num_msix_vectors; + hw_num_msix = pf->hw.func_caps.common_cap.num_msix_vectors; num_cpus = num_online_cpus(); - /* reserve for LAN miscellaneous handler */ - needed = ICE_MIN_LAN_OICR_MSIX; - if (v_left < needed) - goto no_hw_vecs_left_err; - v_budget += needed; - v_left -= needed; + /* LAN miscellaneous handler */ + v_other = ICE_MIN_LAN_OICR_MSIX; - /* reserve for flow director */ - if (test_bit(ICE_FLAG_FD_ENA, pf->flags)) { - needed = ICE_FDIR_MSIX; - if (v_left < needed) - goto no_hw_vecs_left_err; - v_budget += needed; - v_left -= needed; - } - - /* reserve for switchdev */ - needed = ICE_ESWITCH_MSIX; - if (v_left < needed) - goto no_hw_vecs_left_err; - v_budget += needed; - v_left -= needed; - - /* total used for non-traffic vectors */ - v_other = v_budget; - - /* reserve vectors for LAN traffic */ - needed = num_cpus; - if (v_left < needed) - goto no_hw_vecs_left_err; - pf->num_lan_msix = needed; - v_budget += needed; - v_left -= needed; - - /* reserve vectors for RDMA auxiliary driver */ - if (test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) { - needed = num_cpus + ICE_RDMA_NUM_AEQ_MSIX; - if (v_left < needed) - goto no_hw_vecs_left_err; - pf->num_rdma_msix = needed; - v_budget += needed; - v_left -= needed; - } - - pf->msix_entries = devm_kcalloc(dev, v_budget, + /* Flow Director */ + if (test_bit(ICE_FLAG_FD_ENA, pf->flags)) + v_other += ICE_FDIR_MSIX; + + /* switchdev */ + v_other += ICE_ESWITCH_MSIX; + + v_wanted = v_other; + + /* LAN traffic */ + pf->num_lan_msix = num_cpus; + v_wanted += pf->num_lan_msix; + + /* RDMA auxiliary driver */ + if (ice_is_rdma_ena(pf)) { + pf->num_rdma_msix = num_cpus + ICE_RDMA_NUM_AEQ_MSIX; + v_wanted += pf->num_rdma_msix; + } + + if (v_wanted > hw_num_msix) { + int v_remain; + + dev_warn(dev, "not enough device MSI-X vectors. wanted = %d, available = %d\n", + v_wanted, hw_num_msix); + + if (hw_num_msix < ICE_MIN_MSIX) { + err = -ERANGE; + goto exit_err; + } + + v_remain = hw_num_msix - v_other; + if (v_remain < ICE_MIN_LAN_TXRX_MSIX) { + v_other = ICE_MIN_MSIX - ICE_MIN_LAN_TXRX_MSIX; + v_remain = ICE_MIN_LAN_TXRX_MSIX; + } + + ice_reduce_msix_usage(pf, v_remain); + v_wanted = pf->num_lan_msix + pf->num_rdma_msix + v_other; + + dev_notice(dev, "Reducing request to %d MSI-X vectors for LAN traffic.\n", + pf->num_lan_msix); + if (ice_is_rdma_ena(pf)) + dev_notice(dev, "Reducing request to %d MSI-X vectors for RDMA.\n", + pf->num_rdma_msix); + } + + pf->msix_entries = devm_kcalloc(dev, v_wanted, sizeof(*pf->msix_entries), GFP_KERNEL); if (!pf->msix_entries) { err = -ENOMEM; goto exit_err; } - for (i = 0; i < v_budget; i++) + for (i = 0; i < v_wanted; i++) pf->msix_entries[i].entry = i; /* actually reserve the vectors */ v_actual = pci_enable_msix_range(pf->pdev, pf->msix_entries, - ICE_MIN_MSIX, v_budget); + ICE_MIN_MSIX, v_wanted); if (v_actual < 0) { dev_err(dev, "unable to reserve MSI-X vectors\n"); err = v_actual; goto msix_err; } - if (v_actual < v_budget) { + if (v_actual < v_wanted) { dev_warn(dev, "not enough OS MSI-X vectors. requested = %d, obtained = %d\n", - v_budget, v_actual); + v_wanted, v_actual); if (v_actual < ICE_MIN_MSIX) { /* error if we can't get minimum vectors */ @@ -3848,43 +4086,16 @@ static int ice_ena_msix_range(struct ice_pf *pf) goto msix_err; } else { int v_remain = v_actual - v_other; - int v_rdma = 0, v_min_rdma = 0; - if (test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) { - /* Need at least 1 interrupt in addition to - * AEQ MSIX - */ - v_rdma = ICE_RDMA_NUM_AEQ_MSIX + 1; - v_min_rdma = ICE_MIN_RDMA_MSIX; - } + if (v_remain < ICE_MIN_LAN_TXRX_MSIX) + v_remain = ICE_MIN_LAN_TXRX_MSIX; - if (v_actual == ICE_MIN_MSIX || - v_remain < ICE_MIN_LAN_TXRX_MSIX + v_min_rdma) { - dev_warn(dev, "Not enough MSI-X vectors to support RDMA.\n"); - clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); - - pf->num_rdma_msix = 0; - pf->num_lan_msix = ICE_MIN_LAN_TXRX_MSIX; - } else if ((v_remain < ICE_MIN_LAN_TXRX_MSIX + v_rdma) || - (v_remain - v_rdma < v_rdma)) { - /* Support minimum RDMA and give remaining - * vectors to LAN MSIX - */ - pf->num_rdma_msix = v_min_rdma; - pf->num_lan_msix = v_remain - v_min_rdma; - } else { - /* Split remaining MSIX with RDMA after - * accounting for AEQ MSIX - */ - pf->num_rdma_msix = (v_remain - ICE_RDMA_NUM_AEQ_MSIX) / 2 + - ICE_RDMA_NUM_AEQ_MSIX; - pf->num_lan_msix = v_remain - pf->num_rdma_msix; - } + ice_reduce_msix_usage(pf, v_remain); dev_notice(dev, "Enabled %d MSI-X vectors for LAN traffic.\n", pf->num_lan_msix); - if (test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) + if (ice_is_rdma_ena(pf)) dev_notice(dev, "Enabled %d MSI-X vectors for RDMA.\n", pf->num_rdma_msix); } @@ -3894,12 +4105,7 @@ static int ice_ena_msix_range(struct ice_pf *pf) msix_err: devm_kfree(dev, pf->msix_entries); - goto exit_err; -no_hw_vecs_left_err: - dev_err(dev, "not enough device MSI-X vectors. requested = %d, available = %d\n", - needed, v_left); - err = -ERANGE; exit_err: pf->num_rdma_msix = 0; pf->num_lan_msix = 0; @@ -4064,8 +4270,8 @@ static void ice_set_safe_mode_vlan_cfg(struct ice_pf *pf) ctxt->info.sw_flags2 &= ~ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; /* allow all VLANs on Tx and don't strip on Rx */ - ctxt->info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_ALL | - ICE_AQ_VSI_VLAN_EMOD_NOTHING; + ctxt->info.inner_vlan_flags = ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL | + ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING; status = ice_update_vsi(hw, vsi->idx, ctxt, NULL); if (status) { @@ -4074,7 +4280,7 @@ static void ice_set_safe_mode_vlan_cfg(struct ice_pf *pf) } else { vsi->info.sec_flags = ctxt->info.sec_flags; vsi->info.sw_flags2 = ctxt->info.sw_flags2; - vsi->info.vlan_flags = ctxt->info.vlan_flags; + vsi->info.inner_vlan_flags = ctxt->info.inner_vlan_flags; } kfree(ctxt); @@ -4393,6 +4599,10 @@ static int ice_register_netdev(struct ice_pf *pf) if (!vsi || !vsi->netdev) return -EIO; + err = ice_devlink_create_pf_port(pf); + if (err) + goto err_devlink_create; + err = register_netdev(vsi->netdev); if (err) goto err_register_netdev; @@ -4400,17 +4610,13 @@ static int ice_register_netdev(struct ice_pf *pf) set_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state); netif_carrier_off(vsi->netdev); netif_tx_stop_all_queues(vsi->netdev); - err = ice_devlink_create_pf_port(pf); - if (err) - goto err_devlink_create; devlink_port_type_eth_set(&pf->devlink_port, vsi->netdev); return 0; -err_devlink_create: - unregister_netdev(vsi->netdev); - clear_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state); err_register_netdev: + ice_devlink_destroy_pf_port(pf); +err_devlink_create: free_netdev(vsi->netdev); vsi->netdev = NULL; clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); @@ -4459,8 +4665,6 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) /* set up for high or low DMA */ err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)); - if (err) - err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32)); if (err) { dev_err(dev, "DMA configuration failed: 0x%x\n", err); return err; @@ -4683,6 +4887,9 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) ice_ptp_init(pf); + if (ice_is_feature_supported(pf, ICE_F_GNSS)) + ice_gnss_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"); @@ -4712,7 +4919,7 @@ probe_done: /* ready to go, so clear down state bit */ clear_bit(ICE_DOWN, pf->state); - if (ice_is_aux_ena(pf)) { + if (ice_is_rdma_ena(pf)) { pf->aux_idx = ida_alloc(&ice_aux_ida, GFP_KERNEL); if (pf->aux_idx < 0) { dev_err(dev, "Failed to allocate device ID for AUX driver\n"); @@ -4854,14 +5061,16 @@ static void ice_remove(struct pci_dev *pdev) ice_devlink_unregister_params(pf); set_bit(ICE_DOWN, pf->state); - mutex_destroy(&(&pf->hw)->fdir_fltr_lock); ice_deinit_lag(pf); if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) ice_ptp_release(pf); + if (ice_is_feature_supported(pf, ICE_F_GNSS)) + ice_gnss_exit(pf); if (!ice_is_safe_mode(pf)) ice_remove_arfs(pf); ice_setup_mc_magic_wake(pf); ice_vsi_release_all(pf); + mutex_destroy(&(&pf->hw)->fdir_fltr_lock); ice_set_wake(pf); ice_free_irq_msix_misc(pf); ice_for_each_vsi(pf, i) { @@ -5043,7 +5252,6 @@ static int __maybe_unused ice_suspend(struct device *dev) continue; ice_vsi_free_q_vectors(pf->vsi[v]); } - ice_free_cpu_rx_rmap(ice_get_main_vsi(pf)); ice_clear_interrupt_scheme(pf); pci_save_state(pdev); @@ -5173,12 +5381,6 @@ static pci_ers_result_t ice_pci_err_slot_reset(struct pci_dev *pdev) result = PCI_ERS_RESULT_DISCONNECT; } - err = pci_aer_clear_nonfatal_status(pdev); - if (err) - dev_dbg(&pdev->dev, "pci_aer_clear_nonfatal_status() failed, error %d\n", - err); - /* non-fatal, continue */ - return result; } @@ -5273,6 +5475,7 @@ static const struct pci_device_id ice_pci_tbl[] = { { 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 }, /* required last entry */ { 0, } }; @@ -5401,16 +5604,19 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi) /* Add filter for new MAC. If filter exists, return success */ err = ice_fltr_add_mac(vsi, mac, ICE_FWD_TO_VSI); - if (err == -EEXIST) + if (err == -EEXIST) { /* Although this MAC filter is already present in hardware it's * possible in some cases (e.g. bonding) that dev_addr was * modified outside of the driver and needs to be restored back * to this value. */ netdev_dbg(netdev, "filter for MAC %pM already exists\n", mac); - else if (err) + + return 0; + } else if (err) { /* error if the new filter addition failed */ err = -EADDRNOTAVAIL; + } err_update_filters: if (err) { @@ -5547,11 +5753,12 @@ ice_fdb_add(struct ndmsg *ndm, struct nlattr __always_unused *tb[], * @dev: the net device pointer * @addr: the MAC address entry being added * @vid: VLAN ID + * @extack: netlink extended ack */ static int ice_fdb_del(struct ndmsg *ndm, __always_unused struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, - __always_unused u16 vid) + __always_unused u16 vid, struct netlink_ext_ack *extack) { int err; @@ -5570,6 +5777,251 @@ ice_fdb_del(struct ndmsg *ndm, __always_unused struct nlattr *tb[], return err; } +#define NETIF_VLAN_OFFLOAD_FEATURES (NETIF_F_HW_VLAN_CTAG_RX | \ + NETIF_F_HW_VLAN_CTAG_TX | \ + NETIF_F_HW_VLAN_STAG_RX | \ + NETIF_F_HW_VLAN_STAG_TX) + +#define NETIF_VLAN_STRIPPING_FEATURES (NETIF_F_HW_VLAN_CTAG_RX | \ + NETIF_F_HW_VLAN_STAG_RX) + +#define NETIF_VLAN_FILTERING_FEATURES (NETIF_F_HW_VLAN_CTAG_FILTER | \ + NETIF_F_HW_VLAN_STAG_FILTER) + +/** + * ice_fix_features - fix the netdev features flags based on device limitations + * @netdev: ptr to the netdev that flags are being fixed on + * @features: features that need to be checked and possibly fixed + * + * Make sure any fixups are made to features in this callback. This enables the + * driver to not have to check unsupported configurations throughout the driver + * because that's the responsiblity of this callback. + * + * Single VLAN Mode (SVM) Supported Features: + * NETIF_F_HW_VLAN_CTAG_FILTER + * NETIF_F_HW_VLAN_CTAG_RX + * NETIF_F_HW_VLAN_CTAG_TX + * + * Double VLAN Mode (DVM) Supported Features: + * NETIF_F_HW_VLAN_CTAG_FILTER + * NETIF_F_HW_VLAN_CTAG_RX + * NETIF_F_HW_VLAN_CTAG_TX + * + * NETIF_F_HW_VLAN_STAG_FILTER + * NETIF_HW_VLAN_STAG_RX + * NETIF_HW_VLAN_STAG_TX + * + * Features that need fixing: + * Cannot simultaneously enable CTAG and STAG stripping and/or insertion. + * These are mutually exlusive as the VSI context cannot support multiple + * VLAN ethertypes simultaneously for stripping and/or insertion. If this + * is not done, then default to clearing the requested STAG offload + * settings. + * + * All supported filtering has to be enabled or disabled together. For + * example, in DVM, CTAG and STAG filtering have to be enabled and disabled + * together. If this is not done, then default to VLAN filtering disabled. + * These are mutually exclusive as there is currently no way to + * enable/disable VLAN filtering based on VLAN ethertype when using VLAN + * prune rules. + */ +static netdev_features_t +ice_fix_features(struct net_device *netdev, netdev_features_t features) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + netdev_features_t req_vlan_fltr, cur_vlan_fltr; + bool cur_ctag, cur_stag, req_ctag, req_stag; + + cur_vlan_fltr = netdev->features & NETIF_VLAN_FILTERING_FEATURES; + cur_ctag = cur_vlan_fltr & NETIF_F_HW_VLAN_CTAG_FILTER; + cur_stag = cur_vlan_fltr & NETIF_F_HW_VLAN_STAG_FILTER; + + req_vlan_fltr = features & NETIF_VLAN_FILTERING_FEATURES; + req_ctag = req_vlan_fltr & NETIF_F_HW_VLAN_CTAG_FILTER; + req_stag = req_vlan_fltr & NETIF_F_HW_VLAN_STAG_FILTER; + + if (req_vlan_fltr != cur_vlan_fltr) { + if (ice_is_dvm_ena(&np->vsi->back->hw)) { + if (req_ctag && req_stag) { + features |= NETIF_VLAN_FILTERING_FEATURES; + } else if (!req_ctag && !req_stag) { + features &= ~NETIF_VLAN_FILTERING_FEATURES; + } else if ((!cur_ctag && req_ctag && !cur_stag) || + (!cur_stag && req_stag && !cur_ctag)) { + features |= NETIF_VLAN_FILTERING_FEATURES; + netdev_warn(netdev, "802.1Q and 802.1ad VLAN filtering must be either both on or both off. VLAN filtering has been enabled for both types.\n"); + } else if ((cur_ctag && !req_ctag && cur_stag) || + (cur_stag && !req_stag && cur_ctag)) { + features &= ~NETIF_VLAN_FILTERING_FEATURES; + netdev_warn(netdev, "802.1Q and 802.1ad VLAN filtering must be either both on or both off. VLAN filtering has been disabled for both types.\n"); + } + } else { + if (req_vlan_fltr & NETIF_F_HW_VLAN_STAG_FILTER) + netdev_warn(netdev, "cannot support requested 802.1ad filtering setting in SVM mode\n"); + + if (req_vlan_fltr & NETIF_F_HW_VLAN_CTAG_FILTER) + features |= NETIF_F_HW_VLAN_CTAG_FILTER; + } + } + + if ((features & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_TX)) && + (features & (NETIF_F_HW_VLAN_STAG_RX | NETIF_F_HW_VLAN_STAG_TX))) { + netdev_warn(netdev, "cannot support CTAG and STAG VLAN stripping and/or insertion simultaneously since CTAG and STAG offloads are mutually exclusive, clearing STAG offload settings\n"); + features &= ~(NETIF_F_HW_VLAN_STAG_RX | + NETIF_F_HW_VLAN_STAG_TX); + } + + if (!(netdev->features & NETIF_F_RXFCS) && + (features & NETIF_F_RXFCS) && + (features & NETIF_VLAN_STRIPPING_FEATURES) && + !ice_vsi_has_non_zero_vlans(np->vsi)) { + netdev_warn(netdev, "Disabling VLAN stripping as FCS/CRC stripping is also disabled and there is no VLAN configured\n"); + features &= ~NETIF_VLAN_STRIPPING_FEATURES; + } + + return features; +} + +/** + * ice_set_vlan_offload_features - set VLAN offload features for the PF VSI + * @vsi: PF's VSI + * @features: features used to determine VLAN offload settings + * + * First, determine the vlan_ethertype based on the VLAN offload bits in + * features. Then determine if stripping and insertion should be enabled or + * disabled. Finally enable or disable VLAN stripping and insertion. + */ +static int +ice_set_vlan_offload_features(struct ice_vsi *vsi, netdev_features_t features) +{ + bool enable_stripping = true, enable_insertion = true; + struct ice_vsi_vlan_ops *vlan_ops; + int strip_err = 0, insert_err = 0; + u16 vlan_ethertype = 0; + + vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); + + if (features & (NETIF_F_HW_VLAN_STAG_RX | NETIF_F_HW_VLAN_STAG_TX)) + vlan_ethertype = ETH_P_8021AD; + else if (features & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_TX)) + vlan_ethertype = ETH_P_8021Q; + + if (!(features & (NETIF_F_HW_VLAN_STAG_RX | NETIF_F_HW_VLAN_CTAG_RX))) + enable_stripping = false; + if (!(features & (NETIF_F_HW_VLAN_STAG_TX | NETIF_F_HW_VLAN_CTAG_TX))) + enable_insertion = false; + + if (enable_stripping) + strip_err = vlan_ops->ena_stripping(vsi, vlan_ethertype); + else + strip_err = vlan_ops->dis_stripping(vsi); + + if (enable_insertion) + insert_err = vlan_ops->ena_insertion(vsi, vlan_ethertype); + else + insert_err = vlan_ops->dis_insertion(vsi); + + if (strip_err || insert_err) + return -EIO; + + return 0; +} + +/** + * ice_set_vlan_filtering_features - set VLAN filtering features for the PF VSI + * @vsi: PF's VSI + * @features: features used to determine VLAN filtering settings + * + * Enable or disable Rx VLAN filtering based on the VLAN filtering bits in the + * features. + */ +static int +ice_set_vlan_filtering_features(struct ice_vsi *vsi, netdev_features_t features) +{ + struct ice_vsi_vlan_ops *vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); + int err = 0; + + /* support Single VLAN Mode (SVM) and Double VLAN Mode (DVM) by checking + * if either bit is set + */ + if (features & + (NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER)) + err = vlan_ops->ena_rx_filtering(vsi); + else + err = vlan_ops->dis_rx_filtering(vsi); + + return err; +} + +/** + * ice_set_vlan_features - set VLAN settings based on suggested feature set + * @netdev: ptr to the netdev being adjusted + * @features: the feature set that the stack is suggesting + * + * Only update VLAN settings if the requested_vlan_features are different than + * the current_vlan_features. + */ +static int +ice_set_vlan_features(struct net_device *netdev, netdev_features_t features) +{ + netdev_features_t current_vlan_features, requested_vlan_features; + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_vsi *vsi = np->vsi; + int err; + + current_vlan_features = netdev->features & NETIF_VLAN_OFFLOAD_FEATURES; + requested_vlan_features = features & NETIF_VLAN_OFFLOAD_FEATURES; + if (current_vlan_features ^ requested_vlan_features) { + if ((features & NETIF_F_RXFCS) && + (features & NETIF_VLAN_STRIPPING_FEATURES)) { + dev_err(ice_pf_to_dev(vsi->back), + "To enable VLAN stripping, you must first enable FCS/CRC stripping\n"); + return -EIO; + } + + err = ice_set_vlan_offload_features(vsi, features); + if (err) + return err; + } + + current_vlan_features = netdev->features & + NETIF_VLAN_FILTERING_FEATURES; + requested_vlan_features = features & NETIF_VLAN_FILTERING_FEATURES; + if (current_vlan_features ^ requested_vlan_features) { + err = ice_set_vlan_filtering_features(vsi, features); + if (err) + return err; + } + + return 0; +} + +/** + * ice_set_loopback - turn on/off loopback mode on underlying PF + * @vsi: ptr to VSI + * @ena: flag to indicate the on/off setting + */ +static int ice_set_loopback(struct ice_vsi *vsi, bool ena) +{ + bool if_running = netif_running(vsi->netdev); + int ret; + + if (if_running && !test_and_set_bit(ICE_VSI_DOWN, vsi->state)) { + ret = ice_down(vsi); + if (ret) { + netdev_err(vsi->netdev, "Preparing device to toggle loopback failed\n"); + return ret; + } + } + ret = ice_aq_set_mac_loopback(&vsi->back->hw, ena, NULL); + if (ret) + netdev_err(vsi->netdev, "Failed to toggle loopback state\n"); + if (if_running) + ret = ice_up(vsi); + + return ret; +} + /** * ice_set_features - set the netdev feature flags * @netdev: ptr to the netdev being adjusted @@ -5578,61 +6030,58 @@ ice_fdb_del(struct ndmsg *ndm, __always_unused struct nlattr *tb[], static int ice_set_features(struct net_device *netdev, netdev_features_t features) { + netdev_features_t changed = netdev->features ^ features; struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; int ret = 0; /* Don't set any netdev advanced features with device in Safe Mode */ - if (ice_is_safe_mode(vsi->back)) { - dev_err(ice_pf_to_dev(vsi->back), "Device is in Safe Mode - not enabling advanced netdev features\n"); + if (ice_is_safe_mode(pf)) { + dev_err(ice_pf_to_dev(pf), + "Device is in Safe Mode - not enabling advanced netdev features\n"); return ret; } /* Do not change setting during reset */ if (ice_is_reset_in_progress(pf->state)) { - dev_err(ice_pf_to_dev(vsi->back), "Device is resetting, changing advanced netdev features temporarily unavailable.\n"); + dev_err(ice_pf_to_dev(pf), + "Device is resetting, changing advanced netdev features temporarily unavailable.\n"); return -EBUSY; } /* Multiple features can be changed in one call so keep features in * separate if/else statements to guarantee each feature is checked */ - if (features & NETIF_F_RXHASH && !(netdev->features & NETIF_F_RXHASH)) - ice_vsi_manage_rss_lut(vsi, true); - else if (!(features & NETIF_F_RXHASH) && - netdev->features & NETIF_F_RXHASH) - ice_vsi_manage_rss_lut(vsi, false); - - if ((features & NETIF_F_HW_VLAN_CTAG_RX) && - !(netdev->features & NETIF_F_HW_VLAN_CTAG_RX)) - ret = ice_vsi_manage_vlan_stripping(vsi, true); - else if (!(features & NETIF_F_HW_VLAN_CTAG_RX) && - (netdev->features & NETIF_F_HW_VLAN_CTAG_RX)) - ret = ice_vsi_manage_vlan_stripping(vsi, false); - - if ((features & NETIF_F_HW_VLAN_CTAG_TX) && - !(netdev->features & NETIF_F_HW_VLAN_CTAG_TX)) - ret = ice_vsi_manage_vlan_insertion(vsi); - else if (!(features & NETIF_F_HW_VLAN_CTAG_TX) && - (netdev->features & NETIF_F_HW_VLAN_CTAG_TX)) - ret = ice_vsi_manage_vlan_insertion(vsi); - - if ((features & NETIF_F_HW_VLAN_CTAG_FILTER) && - !(netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) - ret = ice_cfg_vlan_pruning(vsi, true); - else if (!(features & NETIF_F_HW_VLAN_CTAG_FILTER) && - (netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) - ret = ice_cfg_vlan_pruning(vsi, false); - - if ((features & NETIF_F_NTUPLE) && - !(netdev->features & NETIF_F_NTUPLE)) { - ice_vsi_manage_fdir(vsi, true); - ice_init_arfs(vsi); - } else if (!(features & NETIF_F_NTUPLE) && - (netdev->features & NETIF_F_NTUPLE)) { - ice_vsi_manage_fdir(vsi, false); - ice_clear_arfs(vsi); + if (changed & NETIF_F_RXHASH) + ice_vsi_manage_rss_lut(vsi, !!(features & NETIF_F_RXHASH)); + + ret = ice_set_vlan_features(netdev, features); + if (ret) + return ret; + + /* Turn on receive of FCS aka CRC, and after setting this + * flag the packet data will have the 4 byte CRC appended + */ + if (changed & NETIF_F_RXFCS) { + if ((features & NETIF_F_RXFCS) && + (features & NETIF_VLAN_STRIPPING_FEATURES)) { + dev_err(ice_pf_to_dev(vsi->back), + "To disable FCS/CRC stripping, you must first disable VLAN stripping\n"); + return -EIO; + } + + ice_vsi_cfg_crc_strip(vsi, !!(features & NETIF_F_RXFCS)); + ret = ice_down_up(vsi); + if (ret) + return ret; + } + + if (changed & NETIF_F_NTUPLE) { + bool ena = !!(features & NETIF_F_NTUPLE); + + ice_vsi_manage_fdir(vsi, ena); + ena ? ice_init_arfs(vsi) : ice_clear_arfs(vsi); } /* don't turn off hw_tc_offload when ADQ is already enabled */ @@ -5641,29 +6090,36 @@ ice_set_features(struct net_device *netdev, netdev_features_t features) return -EACCES; } - if ((features & NETIF_F_HW_TC) && - !(netdev->features & NETIF_F_HW_TC)) - set_bit(ICE_FLAG_CLS_FLOWER, pf->flags); - else - clear_bit(ICE_FLAG_CLS_FLOWER, pf->flags); + if (changed & NETIF_F_HW_TC) { + bool ena = !!(features & NETIF_F_HW_TC); + + ena ? set_bit(ICE_FLAG_CLS_FLOWER, pf->flags) : + clear_bit(ICE_FLAG_CLS_FLOWER, pf->flags); + } + + if (changed & NETIF_F_LOOPBACK) + ret = ice_set_loopback(vsi, !!(features & NETIF_F_LOOPBACK)); return ret; } /** - * ice_vsi_vlan_setup - Setup VLAN offload properties on a VSI + * ice_vsi_vlan_setup - Setup VLAN offload properties on a PF VSI * @vsi: VSI to setup VLAN properties for */ static int ice_vsi_vlan_setup(struct ice_vsi *vsi) { - int ret = 0; + int err; - if (vsi->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) - ret = ice_vsi_manage_vlan_stripping(vsi, true); - if (vsi->netdev->features & NETIF_F_HW_VLAN_CTAG_TX) - ret = ice_vsi_manage_vlan_insertion(vsi); + err = ice_set_vlan_offload_features(vsi, vsi->netdev->features); + if (err) + return err; - return ret; + err = ice_set_vlan_filtering_features(vsi, vsi->netdev->features); + if (err) + return err; + + return ice_vsi_add_vlan_zero(vsi); } /** @@ -5679,10 +6135,12 @@ int ice_vsi_cfg(struct ice_vsi *vsi) if (vsi->netdev) { ice_set_rx_mode(vsi->netdev); - err = ice_vsi_vlan_setup(vsi); + if (vsi->type != ICE_VSI_LB) { + err = ice_vsi_vlan_setup(vsi); - if (err) - return err; + if (err) + return err; + } } ice_vsi_cfg_dcb_rings(vsi); @@ -5871,9 +6329,10 @@ static int ice_up_complete(struct ice_vsi *vsi) ice_ptp_link_change(pf, pf->hw.pf_id, true); } - /* clear this now, and the first stats read will be used as baseline */ - vsi->stat_offsets_loaded = false; - + /* Perform an initial read of the statistics registers now to + * set the baseline so counters are ready when interface is up + */ + ice_update_eth_stats(vsi); ice_service_task_schedule(pf); return 0; @@ -5904,9 +6363,9 @@ int ice_up(struct ice_vsi *vsi) * This function fetches stats from the ring considering the atomic operations * that needs to be performed to read u64 values in 32 bit machine. */ -static void -ice_fetch_u64_stats_per_ring(struct u64_stats_sync *syncp, struct ice_q_stats stats, - u64 *pkts, u64 *bytes) +void +ice_fetch_u64_stats_per_ring(struct u64_stats_sync *syncp, + struct ice_q_stats stats, u64 *pkts, u64 *bytes) { unsigned int start; @@ -5936,8 +6395,9 @@ ice_update_vsi_tx_ring_stats(struct ice_vsi *vsi, u64 pkts = 0, bytes = 0; ring = READ_ONCE(rings[i]); - if (ring) - ice_fetch_u64_stats_per_ring(&ring->syncp, ring->stats, &pkts, &bytes); + if (!ring) + continue; + ice_fetch_u64_stats_per_ring(&ring->syncp, ring->stats, &pkts, &bytes); vsi_stats->tx_packets += pkts; vsi_stats->tx_bytes += bytes; vsi->tx_restart += ring->tx_stats.restart_q; @@ -6264,11 +6724,12 @@ static void ice_napi_disable_all(struct ice_vsi *vsi) */ int ice_down(struct ice_vsi *vsi) { - int i, tx_err, rx_err, link_err = 0; + int i, tx_err, rx_err, vlan_err = 0; WARN_ON(!test_bit(ICE_VSI_DOWN, vsi->state)); if (vsi->netdev && vsi->type == ICE_VSI_PF) { + vlan_err = ice_vsi_del_vlan_zero(vsi); if (!ice_is_e810(&vsi->back->hw)) ice_ptp_link_change(vsi->back, vsi->back->hw.pf_id, false); netif_carrier_off(vsi->netdev); @@ -6297,20 +6758,13 @@ int ice_down(struct ice_vsi *vsi) ice_napi_disable_all(vsi); - if (test_bit(ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, vsi->back->flags)) { - link_err = ice_force_phys_link_state(vsi, false); - if (link_err) - netdev_err(vsi->netdev, "Failed to set physical link down, VSI %d error %d\n", - vsi->vsi_num, link_err); - } - ice_for_each_txq(vsi, i) ice_clean_tx_ring(vsi->tx_rings[i]); ice_for_each_rxq(vsi, i) ice_clean_rx_ring(vsi->rx_rings[i]); - if (tx_err || rx_err || link_err) { + if (tx_err || rx_err || vlan_err) { netdev_err(vsi->netdev, "Failed to close VSI 0x%04X on switch 0x%04X\n", vsi->vsi_num, vsi->vsw->sw_id); return -EIO; @@ -6320,6 +6774,31 @@ int ice_down(struct ice_vsi *vsi) } /** + * ice_down_up - shutdown the VSI connection and bring it up + * @vsi: the VSI to be reconnected + */ +int ice_down_up(struct ice_vsi *vsi) +{ + int ret; + + /* if DOWN already set, nothing to do */ + if (test_and_set_bit(ICE_VSI_DOWN, vsi->state)) + return 0; + + ret = ice_down(vsi); + if (ret) + return ret; + + ret = ice_up(vsi); + if (ret) { + netdev_err(vsi->netdev, "reallocating resources failed during netdev features change, may need to reload driver\n"); + return ret; + } + + return 0; +} + +/** * ice_vsi_setup_tx_rings - Allocate VSI Tx queue resources * @vsi: VSI having resources allocated * @@ -6472,6 +6951,8 @@ int ice_vsi_open(struct ice_vsi *vsi) if (err) goto err_setup_rx; + ice_vsi_cfg_netdev_tc(vsi, vsi->tc_cfg.ena_tc); + if (vsi->type == ICE_VSI_PF) { /* Notify the stack of the actual queue counts. */ err = netif_set_real_num_tx_queues(vsi->netdev, vsi->num_txq); @@ -6620,6 +7101,7 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) { struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; + bool dvm; int err; if (test_bit(ICE_DOWN, pf->state)) @@ -6627,12 +7109,15 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) dev_dbg(dev, "rebuilding PF after reset_type=%d\n", reset_type); +#define ICE_EMP_RESET_SLEEP_MS 5000 if (reset_type == ICE_RESET_EMPR) { /* If an EMP reset has occurred, any previously pending flash * update will have completed. We no longer know whether or * not the NVM update EMP reset is restricted. */ pf->fw_emp_reset_disabled = false; + + msleep(ICE_EMP_RESET_SLEEP_MS); } err = ice_init_all_ctrlq(hw); @@ -6657,12 +7142,6 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) goto err_init_ctrlq; } - if (pf->first_sw->dflt_vsi_ena) - dev_info(dev, "Clearing default VSI, re-enable after reset completes\n"); - /* clear the default VSI configuration if it exists */ - pf->first_sw->dflt_vsi = NULL; - pf->first_sw->dflt_vsi_ena = false; - ice_clear_pxe_mode(hw); err = ice_init_nvm(hw); @@ -6683,6 +7162,12 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) goto err_init_ctrlq; } + dvm = ice_is_dvm_ena(hw); + + err = ice_aq_set_port_params(pf->hw.port_info, dvm, NULL); + if (err) + goto err_init_ctrlq; + err = ice_sched_init_port(hw->port_info); if (err) goto err_sched_init_port; @@ -6719,6 +7204,9 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) ice_ptp_reset(pf); + if (ice_is_feature_supported(pf, ICE_F_GNSS)) + ice_gnss_init(pf); + /* rebuild PF VSI */ err = ice_vsi_rebuild_by_type(pf, ICE_VSI_PF); if (err) { @@ -6817,7 +7305,6 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; - struct iidc_event *event; u8 count = 0; int err = 0; @@ -6852,14 +7339,6 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) return -EBUSY; } - event = kzalloc(sizeof(*event), GFP_KERNEL); - if (!event) - return -ENOMEM; - - set_bit(IIDC_EVENT_BEFORE_MTU_CHANGE, event->type); - ice_send_event_to_aux(pf, event); - clear_bit(IIDC_EVENT_BEFORE_MTU_CHANGE, event->type); - netdev->mtu = (unsigned int)new_mtu; /* if VSI is up, bring it down and then back up */ @@ -6867,21 +7346,18 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) err = ice_down(vsi); if (err) { netdev_err(netdev, "change MTU if_down err %d\n", err); - goto event_after; + return err; } err = ice_up(vsi); if (err) { netdev_err(netdev, "change MTU if_up err %d\n", err); - goto event_after; + return err; } } netdev_dbg(netdev, "changed MTU to %d\n", new_mtu); -event_after: - set_bit(IIDC_EVENT_AFTER_MTU_CHANGE, event->type); - ice_send_event_to_aux(pf, event); - kfree(event); + set_bit(ICE_FLAG_MTU_CHANGED, pf->flags); return err; } @@ -8509,6 +8985,16 @@ int ice_stop(struct net_device *netdev) return -EBUSY; } + if (test_bit(ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, vsi->back->flags)) { + int link_err = ice_force_phys_link_state(vsi, false); + + if (link_err) { + netdev_err(vsi->netdev, "Failed to set physical link down, VSI %d error %d\n", + vsi->vsi_num, link_err); + return -EIO; + } + } + ice_vsi_close(vsi); return 0; @@ -8525,6 +9011,7 @@ ice_features_check(struct sk_buff *skb, struct net_device __always_unused *netdev, netdev_features_t features) { + bool gso = skb_is_gso(skb); size_t len; /* No point in doing any of this if neither checksum nor GSO are @@ -8537,24 +9024,32 @@ ice_features_check(struct sk_buff *skb, /* We cannot support GSO if the MSS is going to be less than * 64 bytes. If it is then we need to drop support for GSO. */ - if (skb_is_gso(skb) && (skb_shinfo(skb)->gso_size < 64)) + if (gso && (skb_shinfo(skb)->gso_size < ICE_TXD_CTX_MIN_MSS)) features &= ~NETIF_F_GSO_MASK; - len = skb_network_header(skb) - skb->data; + len = skb_network_offset(skb); if (len > ICE_TXD_MACLEN_MAX || len & 0x1) goto out_rm_features; - len = skb_transport_header(skb) - skb_network_header(skb); + len = skb_network_header_len(skb); if (len > ICE_TXD_IPLEN_MAX || len & 0x1) goto out_rm_features; if (skb->encapsulation) { - len = skb_inner_network_header(skb) - skb_transport_header(skb); - if (len > ICE_TXD_L4LEN_MAX || len & 0x1) - goto out_rm_features; + /* this must work for VXLAN frames AND IPIP/SIT frames, and in + * the case of IPIP frames, the transport header pointer is + * after the inner header! So check to make sure that this + * is a GRE or UDP_TUNNEL frame before doing that math. + */ + if (gso && (skb_shinfo(skb)->gso_type & + (SKB_GSO_GRE | SKB_GSO_UDP_TUNNEL))) { + len = skb_inner_network_header(skb) - + skb_transport_header(skb); + if (len > ICE_TXD_L4LEN_MAX || len & 0x1) + goto out_rm_features; + } - len = skb_inner_transport_header(skb) - - skb_inner_network_header(skb); + len = skb_inner_network_header_len(skb); if (len > ICE_TXD_IPLEN_MAX || len & 0x1) goto out_rm_features; } @@ -8582,6 +9077,7 @@ static const struct net_device_ops ice_netdev_ops = { .ndo_start_xmit = ice_start_xmit, .ndo_select_queue = ice_select_queue, .ndo_features_check = ice_features_check, + .ndo_fix_features = ice_fix_features, .ndo_set_rx_mode = ice_set_rx_mode, .ndo_set_mac_address = ice_set_mac_address, .ndo_validate_addr = eth_validate_addr, @@ -8612,4 +9108,5 @@ static const struct net_device_ops ice_netdev_ops = { .ndo_bpf = ice_xdp, .ndo_xdp_xmit = ice_xdp_xmit, .ndo_xsk_wakeup = ice_xsk_wakeup, + .ndo_get_devlink_port = ice_get_devlink_port, }; diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c index 4eb0599714f4..c262dc886e6a 100644 --- a/drivers/net/ethernet/intel/ice/ice_nvm.c +++ b/drivers/net/ethernet/intel/ice/ice_nvm.c @@ -641,6 +641,7 @@ ice_get_orom_civd_data(struct ice_hw *hw, enum ice_bank_select bank, status = ice_read_flash_module(hw, bank, ICE_SR_1ST_OROM_BANK_PTR, 0, orom_data, hw->flash.banks.orom_size); if (status) { + vfree(orom_data); ice_debug(hw, ICE_DBG_NVM, "Unable to read Option ROM data\n"); return status; } @@ -1113,14 +1114,18 @@ int ice_nvm_validate_checksum(struct ice_hw *hw) * Update the control word with the required banks' validity bits * and dumps the Shadow RAM to flash (0x0707) * - * cmd_flags controls which banks to activate, and the preservation level to - * use when activating the NVM bank. + * cmd_flags controls which banks to activate, the preservation level to use + * when activating the NVM bank, and whether an EMP reset is required for + * activation. + * + * Note that the 16bit cmd_flags value is split between two separate 1 byte + * flag values in the descriptor. * * On successful return of the firmware command, the response_flags variable * is updated with the flags reported by firmware indicating certain status, * such as whether EMP reset is enabled. */ -int ice_nvm_write_activate(struct ice_hw *hw, u8 cmd_flags, u8 *response_flags) +int ice_nvm_write_activate(struct ice_hw *hw, u16 cmd_flags, u8 *response_flags) { struct ice_aqc_nvm *cmd; struct ice_aq_desc desc; @@ -1129,7 +1134,8 @@ int ice_nvm_write_activate(struct ice_hw *hw, u8 cmd_flags, u8 *response_flags) cmd = &desc.params.nvm; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_nvm_write_activate); - cmd->cmd_flags = cmd_flags; + cmd->cmd_flags = (u8)(cmd_flags & 0xFF); + cmd->offset_high = (u8)((cmd_flags >> 8) & 0xFF); err = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); if (!err && response_flags) diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.h b/drivers/net/ethernet/intel/ice/ice_nvm.h index 856d1ad4398b..774c2317967d 100644 --- a/drivers/net/ethernet/intel/ice/ice_nvm.h +++ b/drivers/net/ethernet/intel/ice/ice_nvm.h @@ -34,7 +34,7 @@ ice_aq_update_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset, int ice_aq_erase_nvm(struct ice_hw *hw, u16 module_typeid, struct ice_sq_cd *cd); int ice_nvm_validate_checksum(struct ice_hw *hw); -int ice_nvm_write_activate(struct ice_hw *hw, u8 cmd_flags, u8 *response_flags); +int ice_nvm_write_activate(struct ice_hw *hw, u16 cmd_flags, u8 *response_flags); int ice_aq_nvm_update_empr(struct ice_hw *hw); int ice_nvm_set_pkg_data(struct ice_hw *hw, bool del_pkg_data_flag, u8 *data, diff --git a/drivers/net/ethernet/intel/ice/ice_osdep.h b/drivers/net/ethernet/intel/ice/ice_osdep.h index f57c414bc0a9..82bc54fec7f3 100644 --- a/drivers/net/ethernet/intel/ice/ice_osdep.h +++ b/drivers/net/ethernet/intel/ice/ice_osdep.h @@ -5,10 +5,18 @@ #define _ICE_OSDEP_H_ #include <linux/types.h> +#include <linux/ctype.h> +#include <linux/delay.h> #include <linux/io.h> +#include <linux/bitops.h> +#include <linux/ethtool.h> +#include <linux/etherdevice.h> +#include <linux/if_ether.h> +#include <linux/pci_ids.h> #ifndef CONFIG_64BIT #include <linux/io-64-nonatomic-lo-hi.h> #endif +#include <net/udp_tunnel.h> #define wr32(a, reg, value) writel((value), ((a)->hw_addr + (reg))) #define rd32(a, reg) readl((a)->hw_addr + (reg)) @@ -24,8 +32,8 @@ struct ice_dma_mem { size_t size; }; -#define ice_hw_to_dev(ptr) \ - (&(container_of((ptr), struct ice_pf, hw))->pdev->dev) +struct ice_hw; +struct device *ice_hw_to_dev(struct ice_hw *hw); #ifdef CONFIG_DYNAMIC_DEBUG #define ice_debug(hw, type, fmt, args...) \ diff --git a/drivers/net/ethernet/intel/ice/ice_pf_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_pf_vsi_vlan_ops.c new file mode 100644 index 000000000000..976a03d3bdd5 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_pf_vsi_vlan_ops.c @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#include "ice_vsi_vlan_ops.h" +#include "ice_vsi_vlan_lib.h" +#include "ice_vlan_mode.h" +#include "ice.h" +#include "ice_pf_vsi_vlan_ops.h" + +void ice_pf_vsi_init_vlan_ops(struct ice_vsi *vsi) +{ + struct ice_vsi_vlan_ops *vlan_ops; + + if (ice_is_dvm_ena(&vsi->back->hw)) { + vlan_ops = &vsi->outer_vlan_ops; + + vlan_ops->add_vlan = ice_vsi_add_vlan; + 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; + vlan_ops->ena_rx_filtering = ice_vsi_ena_rx_vlan_filtering; + vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering; + } else { + vlan_ops = &vsi->inner_vlan_ops; + + vlan_ops->add_vlan = ice_vsi_add_vlan; + 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->ena_rx_filtering = ice_vsi_ena_rx_vlan_filtering; + vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering; + } +} + diff --git a/drivers/net/ethernet/intel/ice/ice_pf_vsi_vlan_ops.h b/drivers/net/ethernet/intel/ice/ice_pf_vsi_vlan_ops.h new file mode 100644 index 000000000000..6741ec8c5f6b --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_pf_vsi_vlan_ops.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#ifndef _ICE_PF_VSI_VLAN_OPS_H_ +#define _ICE_PF_VSI_VLAN_OPS_H_ + +#include "ice_vsi_vlan_ops.h" + +struct ice_vsi; + +void ice_pf_vsi_init_vlan_ops(struct ice_vsi *vsi); + +#endif /* _ICE_PF_VSI_VLAN_OPS_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_protocol_type.h b/drivers/net/ethernet/intel/ice/ice_protocol_type.h index dc1b0e9e6df5..02a4e1cf624e 100644 --- a/drivers/net/ethernet/intel/ice/ice_protocol_type.h +++ b/drivers/net/ethernet/intel/ice/ice_protocol_type.h @@ -29,6 +29,7 @@ enum ice_protocol_type { ICE_MAC_OFOS = 0, ICE_MAC_IL, ICE_ETYPE_OL, + ICE_ETYPE_IL, ICE_VLAN_OFOS, ICE_IPV4_OFOS, ICE_IPV4_IL, @@ -40,6 +41,12 @@ enum ice_protocol_type { ICE_VXLAN, ICE_GENEVE, ICE_NVGRE, + ICE_GTP, + ICE_GTP_NO_PAY, + ICE_PPPOE, + ICE_L2TPV3, + ICE_VLAN_EX, + ICE_VLAN_IN, ICE_VXLAN_GPE, ICE_SCTP_IL, ICE_PROTOCOL_LAST @@ -47,9 +54,12 @@ enum ice_protocol_type { enum ice_sw_tunnel_type { ICE_NON_TUN = 0, + ICE_SW_TUN_AND_NON_TUN, ICE_SW_TUN_VXLAN, ICE_SW_TUN_GENEVE, ICE_SW_TUN_NVGRE, + ICE_SW_TUN_GTPU, + ICE_SW_TUN_GTPC, ICE_ALL_TUNNELS /* All tunnel types including NVGRE */ }; @@ -91,6 +101,7 @@ enum ice_prot_id { #define ICE_MAC_OFOS_HW 1 #define ICE_MAC_IL_HW 4 #define ICE_ETYPE_OL_HW 9 +#define ICE_ETYPE_IL_HW 10 #define ICE_VLAN_OF_HW 16 #define ICE_VLAN_OL_HW 17 #define ICE_IPV4_OFOS_HW 32 @@ -100,15 +111,22 @@ enum ice_prot_id { #define ICE_TCP_IL_HW 49 #define ICE_UDP_ILOS_HW 53 #define ICE_GRE_OF_HW 64 +#define ICE_PPPOE_HW 103 +#define ICE_L2TPV3_HW 104 #define ICE_UDP_OF_HW 52 /* UDP Tunnels */ -#define ICE_META_DATA_ID_HW 255 /* this is used for tunnel type */ +#define ICE_META_DATA_ID_HW 255 /* this is used for tunnel and VLAN type */ #define ICE_MDID_SIZE 2 + #define ICE_TUN_FLAG_MDID 21 #define ICE_TUN_FLAG_MDID_OFF (ICE_MDID_SIZE * ICE_TUN_FLAG_MDID) #define ICE_TUN_FLAG_MASK 0xFF +#define ICE_VLAN_FLAG_MDID 20 +#define ICE_VLAN_FLAG_MDID_OFF (ICE_MDID_SIZE * ICE_VLAN_FLAG_MDID) +#define ICE_PKT_FLAGS_0_TO_15_VLAN_FLAGS_MASK 0xD000 + #define ICE_TUN_FLAG_FV_IND 2 /* Mapping of software defined protocol ID to hardware defined protocol ID */ @@ -179,6 +197,33 @@ struct ice_udp_tnl_hdr { __be32 vni; /* only use lower 24-bits */ }; +struct ice_udp_gtp_hdr { + u8 flags; + u8 msg_type; + __be16 rsrvd_len; + __be32 teid; + __be16 rsrvd_seq_nbr; + u8 rsrvd_n_pdu_nbr; + u8 rsrvd_next_ext; + u8 rsvrd_ext_len; + u8 pdu_type; + u8 qfi; + u8 rsvrd; +}; + +struct ice_pppoe_hdr { + u8 rsrvd_ver_type; + u8 rsrvd_code; + __be16 session_id; + __be16 length; + __be16 ppp_prot_id; /* control and data only */ +}; + +struct ice_l2tpv3_sess_hdr { + __be32 session_id; + __be64 cookie; +}; + struct ice_nvgre_hdr { __be16 flags; __be16 protocol; @@ -195,6 +240,9 @@ union ice_prot_hdr { struct ice_sctp_hdr sctp_hdr; struct ice_udp_tnl_hdr tnl_hdr; struct ice_nvgre_hdr nvgre_hdr; + struct ice_udp_gtp_hdr gtp_hdr; + struct ice_pppoe_hdr pppoe_hdr; + struct ice_l2tpv3_sess_hdr l2tpv3_sess_hdr; }; /* This is mapping table entry that maps every word within a given protocol diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index ae291d442539..011b727ab190 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -3,6 +3,7 @@ #include "ice.h" #include "ice_lib.h" +#include "ice_trace.h" #define E810_OUT_PROP_DELAY_NS 1 @@ -490,46 +491,6 @@ ice_ptp_read_src_clk_reg(struct ice_pf *pf, struct ptp_system_timestamp *sts) } /** - * ice_ptp_update_cached_phctime - Update the cached PHC time values - * @pf: Board specific private structure - * - * This function updates the system time values which are cached in the PF - * structure and the Rx rings. - * - * This function must be called periodically to ensure that the cached value - * is never more than 2 seconds old. It must also be called whenever the PHC - * time has been changed. - */ -static void ice_ptp_update_cached_phctime(struct ice_pf *pf) -{ - u64 systime; - int i; - - /* Read the current PHC time */ - systime = ice_ptp_read_src_clk_reg(pf, NULL); - - /* Update the cached PHC time stored in the PF structure */ - WRITE_ONCE(pf->ptp.cached_phc_time, systime); - - ice_for_each_vsi(pf, i) { - struct ice_vsi *vsi = pf->vsi[i]; - int j; - - if (!vsi) - continue; - - if (vsi->type != ICE_VSI_PF) - continue; - - ice_for_each_rxq(vsi, j) { - if (!vsi->rx_rings[j]) - continue; - WRITE_ONCE(vsi->rx_rings[j]->cached_phctime, systime); - } - } -} - -/** * ice_ptp_extend_32b_ts - Convert a 32b nanoseconds timestamp to 64b * @cached_phc_time: recently cached copy of PHC time * @in_tstamp: Ingress/egress 32b nanoseconds timestamp value @@ -625,12 +586,400 @@ static u64 ice_ptp_extend_32b_ts(u64 cached_phc_time, u32 in_tstamp) static u64 ice_ptp_extend_40b_ts(struct ice_pf *pf, u64 in_tstamp) { const u64 mask = GENMASK_ULL(31, 0); + unsigned long discard_time; + + /* Discard the hardware timestamp if the cached PHC time is too old */ + discard_time = pf->ptp.cached_phc_jiffies + msecs_to_jiffies(2000); + if (time_is_before_jiffies(discard_time)) { + pf->ptp.tx_hwtstamp_discarded++; + return 0; + } return ice_ptp_extend_32b_ts(pf->ptp.cached_phc_time, (in_tstamp >> 8) & mask); } /** + * ice_ptp_tx_tstamp - Process Tx timestamps for a port + * @tx: the PTP Tx timestamp tracker + * + * Process timestamps captured by the PHY associated with this port. To do + * this, loop over each index with a waiting skb. + * + * If a given index has a valid timestamp, perform the following steps: + * + * 1) copy the timestamp out of the PHY register + * 4) clear the timestamp valid bit in the PHY register + * 5) unlock the index by clearing the associated in_use bit. + * 2) extend the 40b timestamp value to get a 64bit timestamp + * 3) send that timestamp to the stack + * + * After looping, if we still have waiting SKBs, return true. This may cause us + * effectively poll even when not strictly necessary. We do this because it's + * possible a new timestamp was requested around the same time as the interrupt. + * In some cases hardware might not interrupt us again when the timestamp is + * captured. + * + * Note that we only take the tracking lock when clearing the bit and when + * checking if we need to re-queue this task. The only place where bits can be + * set is the hard xmit routine where an SKB has a request flag set. The only + * places where we clear bits are this work function, or the periodic cleanup + * thread. If the cleanup thread clears a bit we're processing we catch it + * when we lock to clear the bit and then grab the SKB pointer. If a Tx thread + * starts a new timestamp, we might not begin processing it right away but we + * will notice it at the end when we re-queue the task. If a Tx thread starts + * a new timestamp just after this function exits without re-queuing, + * the interrupt when the timestamp finishes should trigger. Avoiding holding + * the lock for the entire function is important in order to ensure that Tx + * threads do not get blocked while waiting for the lock. + */ +static bool ice_ptp_tx_tstamp(struct ice_ptp_tx *tx) +{ + struct ice_ptp_port *ptp_port; + bool ts_handled = true; + struct ice_pf *pf; + u8 idx; + + if (!tx->init) + return false; + + ptp_port = container_of(tx, struct ice_ptp_port, tx); + pf = ptp_port_to_pf(ptp_port); + + for_each_set_bit(idx, tx->in_use, tx->len) { + struct skb_shared_hwtstamps shhwtstamps = {}; + u8 phy_idx = idx + tx->quad_offset; + u64 raw_tstamp, tstamp; + struct sk_buff *skb; + int err; + + ice_trace(tx_tstamp_fw_req, tx->tstamps[idx].skb, idx); + + err = ice_read_phy_tstamp(&pf->hw, tx->quad, phy_idx, + &raw_tstamp); + if (err) + continue; + + ice_trace(tx_tstamp_fw_done, tx->tstamps[idx].skb, idx); + + /* Check if the timestamp is invalid or stale */ + if (!(raw_tstamp & ICE_PTP_TS_VALID) || + raw_tstamp == tx->tstamps[idx].cached_tstamp) + continue; + + /* The timestamp is valid, so we'll go ahead and clear this + * index and then send the timestamp up to the stack. + */ + spin_lock(&tx->lock); + tx->tstamps[idx].cached_tstamp = raw_tstamp; + clear_bit(idx, tx->in_use); + skb = tx->tstamps[idx].skb; + tx->tstamps[idx].skb = NULL; + spin_unlock(&tx->lock); + + /* it's (unlikely but) possible we raced with the cleanup + * thread for discarding old timestamp requests. + */ + if (!skb) + continue; + + /* Extend the timestamp using cached PHC time */ + tstamp = ice_ptp_extend_40b_ts(pf, raw_tstamp); + if (tstamp) { + shhwtstamps.hwtstamp = ns_to_ktime(tstamp); + ice_trace(tx_tstamp_complete, skb, idx); + } + + skb_tstamp_tx(skb, &shhwtstamps); + dev_kfree_skb_any(skb); + } + + /* Check if we still have work to do. If so, re-queue this task to + * poll for remaining timestamps. + */ + spin_lock(&tx->lock); + if (!bitmap_empty(tx->in_use, tx->len)) + ts_handled = false; + spin_unlock(&tx->lock); + + return ts_handled; +} + +/** + * ice_ptp_alloc_tx_tracker - Initialize tracking for Tx timestamps + * @tx: Tx tracking structure to initialize + * + * Assumes that the length has already been initialized. Do not call directly, + * use the ice_ptp_init_tx_e822 or ice_ptp_init_tx_e810 instead. + */ +static int +ice_ptp_alloc_tx_tracker(struct ice_ptp_tx *tx) +{ + tx->tstamps = kcalloc(tx->len, sizeof(*tx->tstamps), GFP_KERNEL); + if (!tx->tstamps) + return -ENOMEM; + + tx->in_use = bitmap_zalloc(tx->len, GFP_KERNEL); + if (!tx->in_use) { + kfree(tx->tstamps); + tx->tstamps = NULL; + return -ENOMEM; + } + + spin_lock_init(&tx->lock); + + tx->init = 1; + + return 0; +} + +/** + * ice_ptp_flush_tx_tracker - Flush any remaining timestamps from the tracker + * @pf: Board private structure + * @tx: the tracker to flush + */ +static void +ice_ptp_flush_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx) +{ + u8 idx; + + for (idx = 0; idx < tx->len; idx++) { + u8 phy_idx = idx + tx->quad_offset; + + spin_lock(&tx->lock); + if (tx->tstamps[idx].skb) { + dev_kfree_skb_any(tx->tstamps[idx].skb); + tx->tstamps[idx].skb = NULL; + pf->ptp.tx_hwtstamp_flushed++; + } + clear_bit(idx, tx->in_use); + spin_unlock(&tx->lock); + + /* Clear any potential residual timestamp in the PHY block */ + if (!pf->hw.reset_ongoing) + ice_clear_phy_tstamp(&pf->hw, tx->quad, phy_idx); + } +} + +/** + * ice_ptp_release_tx_tracker - Release allocated memory for Tx tracker + * @pf: Board private structure + * @tx: Tx tracking structure to release + * + * Free memory associated with the Tx timestamp tracker. + */ +static void +ice_ptp_release_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx) +{ + tx->init = 0; + + ice_ptp_flush_tx_tracker(pf, tx); + + kfree(tx->tstamps); + tx->tstamps = NULL; + + bitmap_free(tx->in_use); + tx->in_use = NULL; + + tx->len = 0; +} + +/** + * ice_ptp_init_tx_e822 - Initialize tracking for Tx timestamps + * @pf: Board private structure + * @tx: the Tx tracking structure to initialize + * @port: the port this structure tracks + * + * Initialize the Tx timestamp tracker for this port. For generic MAC devices, + * the timestamp block is shared for all ports in the same quad. To avoid + * ports using the same timestamp index, logically break the block of + * registers into chunks based on the port number. + */ +static int +ice_ptp_init_tx_e822(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port) +{ + tx->quad = port / ICE_PORTS_PER_QUAD; + tx->quad_offset = (port % ICE_PORTS_PER_QUAD) * INDEX_PER_PORT; + tx->len = INDEX_PER_PORT; + + return ice_ptp_alloc_tx_tracker(tx); +} + +/** + * ice_ptp_init_tx_e810 - Initialize tracking for Tx timestamps + * @pf: Board private structure + * @tx: the Tx tracking structure to initialize + * + * Initialize the Tx timestamp tracker for this PF. For E810 devices, each + * port has its own block of timestamps, independent of the other ports. + */ +static int +ice_ptp_init_tx_e810(struct ice_pf *pf, struct ice_ptp_tx *tx) +{ + tx->quad = pf->hw.port_info->lport; + tx->quad_offset = 0; + tx->len = INDEX_PER_QUAD; + + return ice_ptp_alloc_tx_tracker(tx); +} + +/** + * ice_ptp_tx_tstamp_cleanup - Cleanup old timestamp requests that got dropped + * @pf: pointer to the PF struct + * @tx: PTP Tx tracker to clean up + * + * Loop through the Tx timestamp requests and see if any of them have been + * waiting for a long time. Discard any SKBs that have been waiting for more + * than 2 seconds. This is long enough to be reasonably sure that the + * timestamp will never be captured. This might happen if the packet gets + * discarded before it reaches the PHY timestamping block. + */ +static void ice_ptp_tx_tstamp_cleanup(struct ice_pf *pf, struct ice_ptp_tx *tx) +{ + struct ice_hw *hw = &pf->hw; + u8 idx; + + if (!tx->init) + return; + + for_each_set_bit(idx, tx->in_use, tx->len) { + struct sk_buff *skb; + u64 raw_tstamp; + + /* Check if this SKB has been waiting for too long */ + if (time_is_after_jiffies(tx->tstamps[idx].start + 2 * HZ)) + continue; + + /* Read tstamp to be able to use this register again */ + ice_read_phy_tstamp(hw, tx->quad, idx + tx->quad_offset, + &raw_tstamp); + + spin_lock(&tx->lock); + skb = tx->tstamps[idx].skb; + tx->tstamps[idx].skb = NULL; + clear_bit(idx, tx->in_use); + spin_unlock(&tx->lock); + + /* Count the number of Tx timestamps which have timed out */ + pf->ptp.tx_hwtstamp_timeouts++; + + /* Free the SKB after we've cleared the bit */ + dev_kfree_skb_any(skb); + } +} + +/** + * ice_ptp_update_cached_phctime - Update the cached PHC time values + * @pf: Board specific private structure + * + * This function updates the system time values which are cached in the PF + * structure and the Rx rings. + * + * This function must be called periodically to ensure that the cached value + * is never more than 2 seconds old. + * + * Note that the cached copy in the PF PTP structure is always updated, even + * if we can't update the copy in the Rx rings. + * + * Return: + * * 0 - OK, successfully updated + * * -EAGAIN - PF was busy, need to reschedule the update + */ +static int ice_ptp_update_cached_phctime(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + unsigned long update_before; + u64 systime; + int i; + + update_before = pf->ptp.cached_phc_jiffies + msecs_to_jiffies(2000); + if (pf->ptp.cached_phc_time && + time_is_before_jiffies(update_before)) { + unsigned long time_taken = jiffies - pf->ptp.cached_phc_jiffies; + + dev_warn(dev, "%u msecs passed between update to cached PHC time\n", + jiffies_to_msecs(time_taken)); + pf->ptp.late_cached_phc_updates++; + } + + /* Read the current PHC time */ + systime = ice_ptp_read_src_clk_reg(pf, NULL); + + /* Update the cached PHC time stored in the PF structure */ + WRITE_ONCE(pf->ptp.cached_phc_time, systime); + WRITE_ONCE(pf->ptp.cached_phc_jiffies, jiffies); + + if (test_and_set_bit(ICE_CFG_BUSY, pf->state)) + return -EAGAIN; + + ice_for_each_vsi(pf, i) { + struct ice_vsi *vsi = pf->vsi[i]; + int j; + + if (!vsi) + continue; + + if (vsi->type != ICE_VSI_PF) + continue; + + ice_for_each_rxq(vsi, j) { + if (!vsi->rx_rings[j]) + continue; + WRITE_ONCE(vsi->rx_rings[j]->cached_phctime, systime); + } + } + clear_bit(ICE_CFG_BUSY, pf->state); + + return 0; +} + +/** + * ice_ptp_reset_cached_phctime - Reset cached PHC time after an update + * @pf: Board specific private structure + * + * This function must be called when the cached PHC time is no longer valid, + * such as after a time adjustment. It discards any outstanding Tx timestamps, + * and updates the cached PHC time for both the PF and Rx rings. If updating + * the PHC time cannot be done immediately, a warning message is logged and + * the work item is scheduled. + * + * These steps are required in order to ensure that we do not accidentally + * report a timestamp extended by the wrong PHC cached copy. Note that we + * do not directly update the cached timestamp here because it is possible + * this might produce an error when ICE_CFG_BUSY is set. If this occurred, we + * would have to try again. During that time window, timestamps might be + * requested and returned with an invalid extension. Thus, on failure to + * immediately update the cached PHC time we would need to zero the value + * anyways. For this reason, we just zero the value immediately and queue the + * update work item. + */ +static void ice_ptp_reset_cached_phctime(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + int err; + + /* Update the cached PHC time immediately if possible, otherwise + * schedule the work item to execute soon. + */ + err = ice_ptp_update_cached_phctime(pf); + if (err) { + /* If another thread is updating the Rx rings, we won't + * properly reset them here. This could lead to reporting of + * invalid timestamps, but there isn't much we can do. + */ + dev_warn(dev, "%s: ICE_CFG_BUSY, unable to immediately update cached PHC time\n", + __func__); + + /* Queue the work item to update the Rx rings when possible */ + kthread_queue_delayed_work(pf->ptp.kworker, &pf->ptp.work, + msecs_to_jiffies(10)); + } + + /* Flush any outstanding Tx timestamps */ + ice_ptp_flush_tx_tracker(pf, &pf->ptp.port.tx); +} + +/** * ice_ptp_read_time - Read the time from the device * @pf: Board private structure * @ts: timespec structure to hold the current time value @@ -889,6 +1238,9 @@ static void ice_ptp_wait_for_offset_valid(struct kthread_work *work) hw = &pf->hw; dev = ice_pf_to_dev(pf); + if (ice_is_reset_in_progress(pf->state)) + return; + if (ice_ptp_check_offset_valid(port)) { /* Offsets not ready yet, try again later */ kthread_queue_delayed_work(pf->ptp.kworker, @@ -1091,9 +1443,8 @@ static void ice_ptp_reset_phy_timestamping(struct ice_pf *pf) static int ice_ptp_adjfine(struct ptp_clock_info *info, long scaled_ppm) { struct ice_pf *pf = ptp_info_to_pf(info); - u64 freq, divisor = 1000000ULL; struct ice_hw *hw = &pf->hw; - s64 incval, diff; + u64 incval, diff; int neg_adj = 0; int err; @@ -1104,17 +1455,8 @@ static int ice_ptp_adjfine(struct ptp_clock_info *info, long scaled_ppm) scaled_ppm = -scaled_ppm; } - while ((u64)scaled_ppm > div64_u64(U64_MAX, incval)) { - /* handle overflow by scaling down the scaled_ppm and - * the divisor, losing some precision - */ - scaled_ppm >>= 2; - divisor >>= 2; - } - - freq = (incval * (u64)scaled_ppm) >> 16; - diff = div_u64(freq, divisor); - + diff = mul_u64_u64_div_u64(incval, (u64)scaled_ppm, + 1000000ULL << 16); if (neg_adj) incval -= diff; else @@ -1508,7 +1850,7 @@ ice_ptp_settime64(struct ptp_clock_info *info, const struct timespec64 *ts) ice_ptp_unlock(hw); if (!err) - ice_ptp_update_cached_phctime(pf); + ice_ptp_reset_cached_phctime(pf); /* Reenable periodic outputs */ ice_ptp_enable_all_clkout(pf); @@ -1533,9 +1875,12 @@ exit: static int ice_ptp_adjtime_nonatomic(struct ptp_clock_info *info, s64 delta) { struct timespec64 now, then; + int ret; then = ns_to_timespec64(delta); - ice_ptp_gettimex64(info, &now, NULL); + ret = ice_ptp_gettimex64(info, &now, NULL); + if (ret) + return ret; now = timespec64_add(now, then); return ice_ptp_settime64(info, (const struct timespec64 *)&now); @@ -1584,7 +1929,7 @@ static int ice_ptp_adjtime(struct ptp_clock_info *info, s64 delta) return err; } - ice_ptp_update_cached_phctime(pf); + ice_ptp_reset_cached_phctime(pf); return 0; } @@ -1792,26 +2137,31 @@ void ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb) { + struct skb_shared_hwtstamps *hwtstamps; + u64 ts_ns, cached_time; u32 ts_high; - u64 ts_ns; - /* Populate timesync data into skb */ - if (rx_desc->wb.time_stamp_low & ICE_PTP_TS_VALID) { - struct skb_shared_hwtstamps *hwtstamps; + if (!(rx_desc->wb.time_stamp_low & ICE_PTP_TS_VALID)) + return; - /* Use ice_ptp_extend_32b_ts directly, using the ring-specific - * cached PHC value, rather than accessing the PF. This also - * allows us to simply pass the upper 32bits of nanoseconds - * directly. Calling ice_ptp_extend_40b_ts is unnecessary as - * it would just discard these bits itself. - */ - ts_high = le32_to_cpu(rx_desc->wb.flex_ts.ts_high); - ts_ns = ice_ptp_extend_32b_ts(rx_ring->cached_phctime, ts_high); + cached_time = READ_ONCE(rx_ring->cached_phctime); - hwtstamps = skb_hwtstamps(skb); - memset(hwtstamps, 0, sizeof(*hwtstamps)); - hwtstamps->hwtstamp = ns_to_ktime(ts_ns); - } + /* Do not report a timestamp if we don't have a cached PHC time */ + if (!cached_time) + return; + + /* Use ice_ptp_extend_32b_ts directly, using the ring-specific cached + * PHC value, rather than accessing the PF. This also allows us to + * simply pass the upper 32bits of nanoseconds directly. Calling + * ice_ptp_extend_40b_ts is unnecessary as it would just discard these + * bits itself. + */ + ts_high = le32_to_cpu(rx_desc->wb.flex_ts.ts_high); + ts_ns = ice_ptp_extend_32b_ts(cached_time, ts_high); + + hwtstamps = skb_hwtstamps(skb); + memset(hwtstamps, 0, sizeof(*hwtstamps)); + hwtstamps->hwtstamp = ns_to_ktime(ts_ns); } /** @@ -1867,41 +2217,26 @@ ice_ptp_setup_sma_pins_e810t(struct ice_pf *pf, struct ptp_clock_info *info) } /** - * ice_ptp_setup_pins_e810t - Setup PTP pins in sysfs + * ice_ptp_setup_pins_e810 - Setup PTP pins in sysfs * @pf: pointer to the PF instance * @info: PTP clock capabilities */ static void -ice_ptp_setup_pins_e810t(struct ice_pf *pf, struct ptp_clock_info *info) +ice_ptp_setup_pins_e810(struct ice_pf *pf, struct ptp_clock_info *info) { - /* Check if SMA controller is in the netlist */ - if (ice_is_feature_supported(pf, ICE_F_SMA_CTRL) && - !ice_is_pca9575_present(&pf->hw)) - ice_clear_feature_support(pf, ICE_F_SMA_CTRL); - - if (!ice_is_feature_supported(pf, ICE_F_SMA_CTRL)) { - info->n_ext_ts = N_EXT_TS_E810_NO_SMA; - info->n_per_out = N_PER_OUT_E810T_NO_SMA; - return; - } + info->n_per_out = N_PER_OUT_E810; - info->n_per_out = N_PER_OUT_E810T; - info->n_ext_ts = N_EXT_TS_E810; - info->n_pins = NUM_PTP_PINS_E810T; - info->verify = ice_verify_pin_e810t; + if (ice_is_feature_supported(pf, ICE_F_PTP_EXTTS)) + info->n_ext_ts = N_EXT_TS_E810; - /* Complete setup of the SMA pins */ - ice_ptp_setup_sma_pins_e810t(pf, info); -} + if (ice_is_feature_supported(pf, ICE_F_SMA_CTRL)) { + info->n_ext_ts = N_EXT_TS_E810; + info->n_pins = NUM_PTP_PINS_E810T; + info->verify = ice_verify_pin_e810t; -/** - * ice_ptp_setup_pins_e810 - Setup PTP pins in sysfs - * @info: PTP clock capabilities - */ -static void ice_ptp_setup_pins_e810(struct ptp_clock_info *info) -{ - info->n_per_out = N_PER_OUT_E810; - info->n_ext_ts = N_EXT_TS_E810; + /* Complete setup of the SMA pins */ + ice_ptp_setup_sma_pins_e810t(pf, info); + } } /** @@ -1938,11 +2273,7 @@ static void ice_ptp_set_funcs_e810(struct ice_pf *pf, struct ptp_clock_info *info) { info->enable = ice_ptp_gpio_enable_e810; - - if (ice_is_e810t(&pf->hw)) - ice_ptp_setup_pins_e810t(pf, info); - else - ice_ptp_setup_pins_e810(info); + ice_ptp_setup_pins_e810(pf, info); } /** @@ -2004,106 +2335,6 @@ static long ice_ptp_create_clock(struct ice_pf *pf) } /** - * ice_ptp_tx_tstamp_work - Process Tx timestamps for a port - * @work: pointer to the kthread_work struct - * - * Process timestamps captured by the PHY associated with this port. To do - * this, loop over each index with a waiting skb. - * - * If a given index has a valid timestamp, perform the following steps: - * - * 1) copy the timestamp out of the PHY register - * 4) clear the timestamp valid bit in the PHY register - * 5) unlock the index by clearing the associated in_use bit. - * 2) extend the 40b timestamp value to get a 64bit timestamp - * 3) send that timestamp to the stack - * - * After looping, if we still have waiting SKBs, then re-queue the work. This - * may cause us effectively poll even when not strictly necessary. We do this - * because it's possible a new timestamp was requested around the same time as - * the interrupt. In some cases hardware might not interrupt us again when the - * timestamp is captured. - * - * Note that we only take the tracking lock when clearing the bit and when - * checking if we need to re-queue this task. The only place where bits can be - * set is the hard xmit routine where an SKB has a request flag set. The only - * places where we clear bits are this work function, or the periodic cleanup - * thread. If the cleanup thread clears a bit we're processing we catch it - * when we lock to clear the bit and then grab the SKB pointer. If a Tx thread - * starts a new timestamp, we might not begin processing it right away but we - * will notice it at the end when we re-queue the work item. If a Tx thread - * starts a new timestamp just after this function exits without re-queuing, - * the interrupt when the timestamp finishes should trigger. Avoiding holding - * the lock for the entire function is important in order to ensure that Tx - * threads do not get blocked while waiting for the lock. - */ -static void ice_ptp_tx_tstamp_work(struct kthread_work *work) -{ - struct ice_ptp_port *ptp_port; - struct ice_ptp_tx *tx; - struct ice_pf *pf; - struct ice_hw *hw; - u8 idx; - - tx = container_of(work, struct ice_ptp_tx, work); - if (!tx->init) - return; - - ptp_port = container_of(tx, struct ice_ptp_port, tx); - pf = ptp_port_to_pf(ptp_port); - hw = &pf->hw; - - for_each_set_bit(idx, tx->in_use, tx->len) { - struct skb_shared_hwtstamps shhwtstamps = {}; - u8 phy_idx = idx + tx->quad_offset; - u64 raw_tstamp, tstamp; - struct sk_buff *skb; - int err; - - err = ice_read_phy_tstamp(hw, tx->quad, phy_idx, - &raw_tstamp); - if (err) - continue; - - /* Check if the timestamp is invalid or stale */ - if (!(raw_tstamp & ICE_PTP_TS_VALID) || - raw_tstamp == tx->tstamps[idx].cached_tstamp) - continue; - - /* The timestamp is valid, so we'll go ahead and clear this - * index and then send the timestamp up to the stack. - */ - spin_lock(&tx->lock); - tx->tstamps[idx].cached_tstamp = raw_tstamp; - clear_bit(idx, tx->in_use); - skb = tx->tstamps[idx].skb; - tx->tstamps[idx].skb = NULL; - spin_unlock(&tx->lock); - - /* it's (unlikely but) possible we raced with the cleanup - * thread for discarding old timestamp requests. - */ - if (!skb) - continue; - - /* Extend the timestamp using cached PHC time */ - tstamp = ice_ptp_extend_40b_ts(pf, raw_tstamp); - shhwtstamps.hwtstamp = ns_to_ktime(tstamp); - - skb_tstamp_tx(skb, &shhwtstamps); - dev_kfree_skb_any(skb); - } - - /* Check if we still have work to do. If so, re-queue this task to - * poll for remaining timestamps. - */ - spin_lock(&tx->lock); - if (!bitmap_empty(tx->in_use, tx->len)) - kthread_queue_work(pf->ptp.kworker, &tx->work); - spin_unlock(&tx->lock); -} - -/** * ice_ptp_request_ts - Request an available Tx timestamp index * @tx: the PTP Tx timestamp tracker to request from * @skb: the SKB to associate with this timestamp request @@ -2128,6 +2359,7 @@ s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb) tx->tstamps[idx].start = jiffies; tx->tstamps[idx].skb = skb_get(skb); skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + ice_trace(tx_tstamp_request, skb, idx); } spin_unlock(&tx->lock); @@ -2142,188 +2374,35 @@ s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb) } /** - * ice_ptp_process_ts - Spawn kthread work to handle timestamps + * ice_ptp_process_ts - Process the PTP Tx timestamps * @pf: Board private structure * - * Queue work required to process the PTP Tx timestamps outside of interrupt - * context. + * Returns true if timestamps are processed. */ -void ice_ptp_process_ts(struct ice_pf *pf) +bool ice_ptp_process_ts(struct ice_pf *pf) { if (pf->ptp.port.tx.init) - kthread_queue_work(pf->ptp.kworker, &pf->ptp.port.tx.work); -} - -/** - * ice_ptp_alloc_tx_tracker - Initialize tracking for Tx timestamps - * @tx: Tx tracking structure to initialize - * - * Assumes that the length has already been initialized. Do not call directly, - * use the ice_ptp_init_tx_e822 or ice_ptp_init_tx_e810 instead. - */ -static int -ice_ptp_alloc_tx_tracker(struct ice_ptp_tx *tx) -{ - tx->tstamps = kcalloc(tx->len, sizeof(*tx->tstamps), GFP_KERNEL); - if (!tx->tstamps) - return -ENOMEM; - - tx->in_use = bitmap_zalloc(tx->len, GFP_KERNEL); - if (!tx->in_use) { - kfree(tx->tstamps); - tx->tstamps = NULL; - return -ENOMEM; - } - - spin_lock_init(&tx->lock); - kthread_init_work(&tx->work, ice_ptp_tx_tstamp_work); - - tx->init = 1; - - return 0; -} - -/** - * ice_ptp_flush_tx_tracker - Flush any remaining timestamps from the tracker - * @pf: Board private structure - * @tx: the tracker to flush - */ -static void -ice_ptp_flush_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx) -{ - u8 idx; + return ice_ptp_tx_tstamp(&pf->ptp.port.tx); - for (idx = 0; idx < tx->len; idx++) { - u8 phy_idx = idx + tx->quad_offset; - - spin_lock(&tx->lock); - if (tx->tstamps[idx].skb) { - dev_kfree_skb_any(tx->tstamps[idx].skb); - tx->tstamps[idx].skb = NULL; - } - clear_bit(idx, tx->in_use); - spin_unlock(&tx->lock); - - /* Clear any potential residual timestamp in the PHY block */ - if (!pf->hw.reset_ongoing) - ice_clear_phy_tstamp(&pf->hw, tx->quad, phy_idx); - } -} - -/** - * ice_ptp_release_tx_tracker - Release allocated memory for Tx tracker - * @pf: Board private structure - * @tx: Tx tracking structure to release - * - * Free memory associated with the Tx timestamp tracker. - */ -static void -ice_ptp_release_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx) -{ - tx->init = 0; - - kthread_cancel_work_sync(&tx->work); - - ice_ptp_flush_tx_tracker(pf, tx); - - kfree(tx->tstamps); - tx->tstamps = NULL; - - bitmap_free(tx->in_use); - tx->in_use = NULL; - - tx->len = 0; -} - -/** - * ice_ptp_init_tx_e822 - Initialize tracking for Tx timestamps - * @pf: Board private structure - * @tx: the Tx tracking structure to initialize - * @port: the port this structure tracks - * - * Initialize the Tx timestamp tracker for this port. For generic MAC devices, - * the timestamp block is shared for all ports in the same quad. To avoid - * ports using the same timestamp index, logically break the block of - * registers into chunks based on the port number. - */ -static int -ice_ptp_init_tx_e822(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port) -{ - tx->quad = port / ICE_PORTS_PER_QUAD; - tx->quad_offset = tx->quad * INDEX_PER_PORT; - tx->len = INDEX_PER_PORT; - - return ice_ptp_alloc_tx_tracker(tx); -} - -/** - * ice_ptp_init_tx_e810 - Initialize tracking for Tx timestamps - * @pf: Board private structure - * @tx: the Tx tracking structure to initialize - * - * Initialize the Tx timestamp tracker for this PF. For E810 devices, each - * port has its own block of timestamps, independent of the other ports. - */ -static int -ice_ptp_init_tx_e810(struct ice_pf *pf, struct ice_ptp_tx *tx) -{ - tx->quad = pf->hw.port_info->lport; - tx->quad_offset = 0; - tx->len = INDEX_PER_QUAD; - - return ice_ptp_alloc_tx_tracker(tx); -} - -/** - * ice_ptp_tx_tstamp_cleanup - Cleanup old timestamp requests that got dropped - * @tx: PTP Tx tracker to clean up - * - * Loop through the Tx timestamp requests and see if any of them have been - * waiting for a long time. Discard any SKBs that have been waiting for more - * than 2 seconds. This is long enough to be reasonably sure that the - * timestamp will never be captured. This might happen if the packet gets - * discarded before it reaches the PHY timestamping block. - */ -static void ice_ptp_tx_tstamp_cleanup(struct ice_ptp_tx *tx) -{ - u8 idx; - - if (!tx->init) - return; - - for_each_set_bit(idx, tx->in_use, tx->len) { - struct sk_buff *skb; - - /* Check if this SKB has been waiting for too long */ - if (time_is_after_jiffies(tx->tstamps[idx].start + 2 * HZ)) - continue; - - spin_lock(&tx->lock); - skb = tx->tstamps[idx].skb; - tx->tstamps[idx].skb = NULL; - clear_bit(idx, tx->in_use); - spin_unlock(&tx->lock); - - /* Free the SKB after we've cleared the bit */ - dev_kfree_skb_any(skb); - } + return false; } static void ice_ptp_periodic_work(struct kthread_work *work) { struct ice_ptp *ptp = container_of(work, struct ice_ptp, work.work); struct ice_pf *pf = container_of(ptp, struct ice_pf, ptp); + int err; if (!test_bit(ICE_FLAG_PTP, pf->flags)) return; - ice_ptp_update_cached_phctime(pf); + err = ice_ptp_update_cached_phctime(pf); - ice_ptp_tx_tstamp_cleanup(&pf->ptp.port.tx); + ice_ptp_tx_tstamp_cleanup(pf, &pf->ptp.port.tx); - /* Run twice a second */ + /* Run twice a second or reschedule if phc update failed */ kthread_queue_delayed_work(ptp->kworker, &ptp->work, - msecs_to_jiffies(500)); + msecs_to_jiffies(err ? 10 : 500)); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h index afd048d69959..028349295b71 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp.h @@ -49,6 +49,37 @@ struct ice_perout_channel { * To allow multiple ports to access the shared register block independently, * the blocks are split up so that indexes are assigned to each port based on * hardware logical port number. + * + * The timestamp blocks are handled differently for E810- and E822-based + * devices. In E810 devices, each port has its own block of timestamps, while in + * E822 there is a need to logically break the block of registers into smaller + * chunks based on the port number to avoid collisions. + * + * Example for port 5 in E810: + * +--------+--------+--------+--------+--------+--------+--------+--------+ + * |register|register|register|register|register|register|register|register| + * | block | block | block | block | block | block | block | block | + * | for | for | for | for | for | for | for | for | + * | port 0 | port 1 | port 2 | port 3 | port 4 | port 5 | port 6 | port 7 | + * +--------+--------+--------+--------+--------+--------+--------+--------+ + * ^^ + * || + * |--- quad offset is always 0 + * ---- quad number + * + * Example for port 5 in E822: + * +-----------------------------+-----------------------------+ + * | register block for quad 0 | register block for quad 1 | + * |+------+------+------+------+|+------+------+------+------+| + * ||port 0|port 1|port 2|port 3|||port 0|port 1|port 2|port 3|| + * |+------+------+------+------+|+------+------+------+------+| + * +-----------------------------+-------^---------------------+ + * ^ | + * | --- quad offset* + * ---- quad number + * + * * PHY port 5 is port 1 in quad 1 + * */ /** @@ -74,7 +105,6 @@ struct ice_tx_tstamp { /** * struct ice_ptp_tx - Tracking structure for all Tx timestamp requests on a port - * @work: work function to handle processing of Tx timestamps * @lock: lock to prevent concurrent write to in_use bitmap * @tstamps: array of len to store outstanding requests * @in_use: bitmap of len to indicate which slots are in use @@ -86,7 +116,6 @@ struct ice_tx_tstamp { * window, timestamps are temporarily disabled. */ struct ice_ptp_tx { - struct kthread_work work; spinlock_t lock; /* lock protecting in_use bitmap */ struct ice_tx_tstamp *tstamps; unsigned long *in_use; @@ -132,6 +161,7 @@ struct ice_ptp_port { * @work: delayed work function for periodic tasks * @extts_work: work function for handling external Tx timestamps * @cached_phc_time: a cached copy of the PHC time for timestamp extension + * @cached_phc_jiffies: jiffies when cached_phc_time was last updated * @ext_ts_chan: the external timestamp channel in use * @ext_ts_irq: the external timestamp IRQ in use * @kworker: kwork thread for handling periodic work @@ -140,12 +170,19 @@ struct ice_ptp_port { * @clock: pointer to registered PTP clock device * @tstamp_config: hardware timestamping configuration * @reset_time: kernel time after clock stop on reset + * @tx_hwtstamp_skipped: number of Tx time stamp requests skipped + * @tx_hwtstamp_timeouts: number of Tx skbs discarded with no time stamp + * @tx_hwtstamp_flushed: number of Tx skbs flushed due to interface closed + * @tx_hwtstamp_discarded: number of Tx skbs discarded due to cached PHC time + * being too old to correctly extend timestamp + * @late_cached_phc_updates: number of times cached PHC update is late */ struct ice_ptp { struct ice_ptp_port port; struct kthread_delayed_work work; struct kthread_work extts_work; u64 cached_phc_time; + unsigned long cached_phc_jiffies; u8 ext_ts_chan; u8 ext_ts_irq; struct kthread_worker *kworker; @@ -154,6 +191,11 @@ struct ice_ptp { struct ptp_clock *clock; struct hwtstamp_config tstamp_config; u64 reset_time; + u32 tx_hwtstamp_skipped; + u32 tx_hwtstamp_timeouts; + u32 tx_hwtstamp_flushed; + u32 tx_hwtstamp_discarded; + u32 late_cached_phc_updates; }; #define __ptp_port_to_ptp(p) \ @@ -193,8 +235,8 @@ struct ice_ptp { #define N_EXT_TS_E810 3 #define N_PER_OUT_E810 4 #define N_PER_OUT_E810T 3 -#define N_PER_OUT_E810T_NO_SMA 2 -#define N_EXT_TS_E810_NO_SMA 2 +#define N_PER_OUT_NO_SMA_E810T 2 +#define N_EXT_TS_NO_SMA_E810T 2 #define ETH_GLTSYN_ENA(_i) (0x03000348 + ((_i) * 4)) #if IS_ENABLED(CONFIG_PTP_1588_CLOCK) @@ -205,7 +247,7 @@ void ice_ptp_cfg_timestamp(struct ice_pf *pf, bool ena); int ice_get_ptp_clock_index(struct ice_pf *pf); s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb); -void ice_ptp_process_ts(struct ice_pf *pf); +bool ice_ptp_process_ts(struct ice_pf *pf); void ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring, @@ -238,7 +280,10 @@ ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb) return -1; } -static inline void ice_ptp_process_ts(struct ice_pf *pf) { } +static inline bool ice_ptp_process_ts(struct ice_pf *pf) +{ + return true; +} static inline void ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb) { } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index ec8450f034e6..772b1f566d6e 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) 2021, Intel Corporation. */ +#include <linux/delay.h> #include "ice_common.h" #include "ice_ptp_hw.h" #include "ice_ptp_consts.h" @@ -2587,38 +2588,113 @@ static int ice_write_phy_reg_e810(struct ice_hw *hw, u32 addr, u32 val) } /** - * ice_read_phy_tstamp_e810 - Read a PHY timestamp out of the external PHY + * ice_read_phy_tstamp_ll_e810 - Read a PHY timestamp registers through the FW + * @hw: pointer to the HW struct + * @idx: the timestamp index to read + * @hi: 8 bit timestamp high value + * @lo: 32 bit timestamp low value + * + * Read a 8bit timestamp high value and 32 bit timestamp low value out of the + * timestamp block of the external PHY on the E810 device using the low latency + * timestamp read. + */ +static int +ice_read_phy_tstamp_ll_e810(struct ice_hw *hw, u8 idx, u8 *hi, u32 *lo) +{ + u32 val; + u8 i; + + /* Write TS index to read to the PF register so the FW can read it */ + val = FIELD_PREP(TS_LL_READ_TS_IDX, idx) | TS_LL_READ_TS; + wr32(hw, PF_SB_ATQBAL, val); + + /* Read the register repeatedly until the FW provides us the TS */ + for (i = TS_LL_READ_RETRIES; i > 0; i--) { + val = rd32(hw, PF_SB_ATQBAL); + + /* When the bit is cleared, the TS is ready in the register */ + if (!(FIELD_GET(TS_LL_READ_TS, val))) { + /* High 8 bit value of the TS is on the bits 16:23 */ + *hi = FIELD_GET(TS_LL_READ_TS_HIGH, val); + + /* Read the low 32 bit value and set the TS valid bit */ + *lo = rd32(hw, PF_SB_ATQBAH) | TS_VALID; + return 0; + } + + udelay(10); + } + + /* FW failed to provide the TS in time */ + ice_debug(hw, ICE_DBG_PTP, "Failed to read PTP timestamp using low latency read\n"); + return -EINVAL; +} + +/** + * ice_read_phy_tstamp_sbq_e810 - Read a PHY timestamp registers through the sbq * @hw: pointer to the HW struct * @lport: the lport to read from * @idx: the timestamp index to read - * @tstamp: on return, the 40bit timestamp value + * @hi: 8 bit timestamp high value + * @lo: 32 bit timestamp low value * - * Read a 40bit timestamp value out of the timestamp block of the external PHY - * on the E810 device. + * Read a 8bit timestamp high value and 32 bit timestamp low value out of the + * timestamp block of the external PHY on the E810 device using sideband queue. */ static int -ice_read_phy_tstamp_e810(struct ice_hw *hw, u8 lport, u8 idx, u64 *tstamp) +ice_read_phy_tstamp_sbq_e810(struct ice_hw *hw, u8 lport, u8 idx, u8 *hi, + u32 *lo) { - u32 lo_addr, hi_addr, lo, hi; + u32 hi_addr = TS_EXT(HIGH_TX_MEMORY_BANK_START, lport, idx); + u32 lo_addr = TS_EXT(LOW_TX_MEMORY_BANK_START, lport, idx); + u32 lo_val, hi_val; int 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_read_phy_reg_e810(hw, lo_addr, &lo); + err = ice_read_phy_reg_e810(hw, lo_addr, &lo_val); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to read low PTP timestamp register, err %d\n", err); return err; } - err = ice_read_phy_reg_e810(hw, hi_addr, &hi); + err = ice_read_phy_reg_e810(hw, hi_addr, &hi_val); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to read high PTP timestamp register, err %d\n", err); return err; } + *lo = lo_val; + *hi = (u8)hi_val; + + return 0; +} + +/** + * ice_read_phy_tstamp_e810 - Read a PHY timestamp out of the external PHY + * @hw: pointer to the HW struct + * @lport: the lport to read from + * @idx: the timestamp index to read + * @tstamp: on return, the 40bit timestamp value + * + * Read a 40bit timestamp value out of the timestamp block of the external PHY + * on the E810 device. + */ +static int +ice_read_phy_tstamp_e810(struct ice_hw *hw, u8 lport, u8 idx, u64 *tstamp) +{ + u32 lo = 0; + u8 hi = 0; + int err; + + if (hw->dev_caps.ts_dev_info.ts_ll_read) + err = ice_read_phy_tstamp_ll_e810(hw, idx, &hi, &lo); + else + err = ice_read_phy_tstamp_sbq_e810(hw, lport, idx, &hi, &lo); + + if (err) + return err; + /* For E810 devices, the timestamp is reported with the lower 32 bits * in the low register, and the upper 8 bits in the high register. */ @@ -3251,6 +3327,37 @@ int ice_write_sma_ctrl_e810t(struct ice_hw *hw, u8 data) } /** + * 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); +} + +/** * ice_is_pca9575_present * @hw: pointer to the hw struct * diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h index 519e75462e67..2bda64c76abc 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h @@ -191,6 +191,7 @@ int ice_phy_exit_bypass_e822(struct ice_hw *hw, u8 port); int ice_ptp_init_phy_e810(struct ice_hw *hw); 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); #define PFTSYN_SEM_BYTES 4 @@ -401,6 +402,7 @@ bool ice_is_pca9575_present(struct ice_hw *hw); #define INCVAL_HIGH_M 0xFF /* Timestamp block macros */ +#define TS_VALID BIT(0) #define TS_LOW_M 0xFFFFFFFF #define TS_HIGH_M 0xFF #define TS_HIGH_S 32 @@ -412,6 +414,12 @@ bool ice_is_pca9575_present(struct ice_hw *hw); #define BYTES_PER_IDX_ADDR_L_U 8 #define BYTES_PER_IDX_ADDR_L 4 +/* Tx timestamp low latency read definitions */ +#define TS_LL_READ_RETRIES 200 +#define TS_LL_READ_TS_HIGH GENMASK(23, 16) +#define TS_LL_READ_TS_IDX GENMASK(29, 24) +#define TS_LL_READ_TS BIT(31) + /* Internal PHY timestamp address */ #define TS_L(a, idx) ((a) + ((idx) * BYTES_PER_IDX_ADDR_L_U)) #define TS_H(a, idx) ((a) + ((idx) * BYTES_PER_IDX_ADDR_L_U + \ @@ -443,4 +451,10 @@ bool ice_is_pca9575_present(struct ice_hw *hw); #define ICE_SMA_MAX_BIT_E810T 7 #define ICE_PCA9575_P1_OFFSET 8 +/* E810T PCA9575 IO controller registers */ +#define ICE_PCA9575_P0_IN 0x0 + +/* E810T PCA9575 IO controller pin control */ +#define ICE_E810T_P0_GNSS_PRSNT_N BIT(4) + #endif /* _ICE_PTP_HW_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c index dcc310e29300..bd31748aae1b 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.c +++ b/drivers/net/ethernet/intel/ice/ice_repr.c @@ -4,7 +4,7 @@ #include "ice.h" #include "ice_eswitch.h" #include "ice_devlink.h" -#include "ice_virtchnl_pf.h" +#include "ice_sriov.h" #include "ice_tc_lib.h" /** @@ -142,6 +142,59 @@ ice_repr_get_devlink_port(struct net_device *netdev) return &repr->vf->devlink_port; } +/** + * ice_repr_sp_stats64 - get slow path stats for port representor + * @dev: network interface device structure + * @stats: netlink stats structure + * + * RX/TX stats are being swapped here to be consistent with VF stats. In slow + * path, port representor receives data when the corresponding VF is sending it + * (and vice versa), TX and RX bytes/packets are effectively swapped on port + * representor. + */ +static int +ice_repr_sp_stats64(const struct net_device *dev, + struct rtnl_link_stats64 *stats) +{ + struct ice_netdev_priv *np = netdev_priv(dev); + int vf_id = np->repr->vf->vf_id; + struct ice_tx_ring *tx_ring; + struct ice_rx_ring *rx_ring; + u64 pkts, bytes; + + tx_ring = np->vsi->tx_rings[vf_id]; + ice_fetch_u64_stats_per_ring(&tx_ring->syncp, tx_ring->stats, + &pkts, &bytes); + stats->rx_packets = pkts; + stats->rx_bytes = bytes; + + rx_ring = np->vsi->rx_rings[vf_id]; + ice_fetch_u64_stats_per_ring(&rx_ring->syncp, rx_ring->stats, + &pkts, &bytes); + stats->tx_packets = pkts; + stats->tx_bytes = bytes; + stats->tx_dropped = rx_ring->rx_stats.alloc_page_failed + + rx_ring->rx_stats.alloc_buf_failed; + + return 0; +} + +static bool +ice_repr_ndo_has_offload_stats(const struct net_device *dev, int attr_id) +{ + return attr_id == IFLA_OFFLOAD_XSTATS_CPU_HIT; +} + +static int +ice_repr_ndo_get_offload_stats(int attr_id, const struct net_device *dev, + void *sp) +{ + if (attr_id == IFLA_OFFLOAD_XSTATS_CPU_HIT) + return ice_repr_sp_stats64(dev, (struct rtnl_link_stats64 *)sp); + + return -EINVAL; +} + static int ice_repr_setup_tc_cls_flower(struct ice_repr *repr, struct flow_cls_offload *flower) @@ -199,6 +252,8 @@ static const struct net_device_ops ice_repr_netdev_ops = { .ndo_start_xmit = ice_eswitch_port_start_xmit, .ndo_get_devlink_port = ice_repr_get_devlink_port, .ndo_setup_tc = ice_repr_setup_tc, + .ndo_has_offload_stats = ice_repr_ndo_has_offload_stats, + .ndo_get_offload_stats = ice_repr_ndo_get_offload_stats, }; /** @@ -238,8 +293,13 @@ static int ice_repr_add(struct ice_vf *vf) struct ice_q_vector *q_vector; struct ice_netdev_priv *np; struct ice_repr *repr; + struct ice_vsi *vsi; int err; + vsi = ice_get_vf_vsi(vf); + if (!vsi) + return -EINVAL; + repr = kzalloc(sizeof(*repr), GFP_KERNEL); if (!repr) return -ENOMEM; @@ -258,7 +318,7 @@ static int ice_repr_add(struct ice_vf *vf) goto err_alloc; } - repr->src_vsi = ice_get_vf_vsi(vf); + repr->src_vsi = vsi; repr->vf = vf; vf->repr = repr; np = netdev_priv(repr->netdev); @@ -278,12 +338,15 @@ static int ice_repr_add(struct ice_vf *vf) repr->netdev->min_mtu = ETH_MIN_MTU; repr->netdev->max_mtu = ICE_MAX_MTU; + SET_NETDEV_DEV(repr->netdev, ice_pf_to_dev(vf->pf)); err = ice_repr_reg_netdev(repr->netdev); if (err) goto err_netdev; devlink_port_type_eth_set(&vf->devlink_port, repr->netdev); + ice_virtchnl_set_repr_ops(vf); + return 0; err_netdev: @@ -311,10 +374,13 @@ err_alloc_rule: */ static void ice_repr_rem(struct ice_vf *vf) { - ice_devlink_destroy_vf_port(vf); + if (!vf->repr) + return; + kfree(vf->repr->q_vector); vf->repr->q_vector = NULL; unregister_netdev(vf->repr->netdev); + ice_devlink_destroy_vf_port(vf); free_netdev(vf->repr->netdev); vf->repr->netdev = NULL; #ifdef CONFIG_ICE_SWITCHDEV @@ -323,6 +389,23 @@ static void ice_repr_rem(struct ice_vf *vf) #endif kfree(vf->repr); vf->repr = NULL; + + ice_virtchnl_set_dflt_ops(vf); +} + +/** + * ice_repr_rem_from_all_vfs - remove port representor for all VFs + * @pf: pointer to PF structure + */ +void ice_repr_rem_from_all_vfs(struct ice_pf *pf) +{ + struct ice_vf *vf; + unsigned int bkt; + + lockdep_assert_held(&pf->vfs.table_lock); + + ice_for_each_vf(pf, bkt, vf) + ice_repr_rem(vf); } /** @@ -331,49 +414,27 @@ static void ice_repr_rem(struct ice_vf *vf) */ int ice_repr_add_for_all_vfs(struct ice_pf *pf) { + struct ice_vf *vf; + unsigned int bkt; int err; - int i; - ice_for_each_vf(pf, i) { - struct ice_vf *vf = &pf->vf[i]; + lockdep_assert_held(&pf->vfs.table_lock); + ice_for_each_vf(pf, bkt, vf) { err = ice_repr_add(vf); if (err) goto err; - - ice_vc_change_ops_to_repr(&vf->vc_ops); } return 0; err: - for (i = i - 1; i >= 0; i--) { - struct ice_vf *vf = &pf->vf[i]; - - ice_repr_rem(vf); - ice_vc_set_dflt_vf_ops(&vf->vc_ops); - } + ice_repr_rem_from_all_vfs(pf); return err; } /** - * ice_repr_rem_from_all_vfs - remove port representor for all VFs - * @pf: pointer to PF structure - */ -void ice_repr_rem_from_all_vfs(struct ice_pf *pf) -{ - int i; - - ice_for_each_vf(pf, i) { - struct ice_vf *vf = &pf->vf[i]; - - ice_repr_rem(vf); - ice_vc_set_dflt_vf_ops(&vf->vc_ops); - } -} - -/** * ice_repr_start_tx_queues - start Tx queues of port representor * @repr: pointer to repr structure */ diff --git a/drivers/net/ethernet/intel/ice/ice_repr.h b/drivers/net/ethernet/intel/ice/ice_repr.h index 0c77ff050d15..378a45bfa256 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.h +++ b/drivers/net/ethernet/intel/ice/ice_repr.h @@ -5,7 +5,6 @@ #define _ICE_REPR_H_ #include <net/dst_metadata.h> -#include "ice.h" struct ice_repr { struct ice_vsi *src_vsi; diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index 7947223536e3..118595763bba 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -1212,7 +1212,7 @@ int ice_sched_init_port(struct ice_port_info *pi) hw = pi->hw; /* Query the Default Topology from FW */ - buf = devm_kzalloc(ice_hw_to_dev(hw), ICE_AQ_MAX_BUF_LEN, GFP_KERNEL); + buf = kzalloc(ICE_AQ_MAX_BUF_LEN, GFP_KERNEL); if (!buf) return -ENOMEM; @@ -1290,7 +1290,7 @@ err_init_port: pi->root = NULL; } - devm_kfree(ice_hw_to_dev(hw), buf); + kfree(buf); return status; } diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index 52c6bac41bf7..3ba1408c56a9 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -1,532 +1,1895 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2018, Intel Corporation. */ -#include "ice_common.h" -#include "ice_sriov.h" +#include "ice.h" +#include "ice_vf_lib_private.h" +#include "ice_base.h" +#include "ice_lib.h" +#include "ice_fltr.h" +#include "ice_dcb_lib.h" +#include "ice_flow.h" +#include "ice_eswitch.h" +#include "ice_virtchnl_allowlist.h" +#include "ice_flex_pipe.h" +#include "ice_vf_vsi_vlan_ops.h" +#include "ice_vlan.h" /** - * ice_aq_send_msg_to_vf - * @hw: pointer to the hardware structure - * @vfid: VF ID to send msg - * @v_opcode: opcodes for VF-PF communication - * @v_retval: return error code - * @msg: pointer to the msg buffer - * @msglen: msg length - * @cd: pointer to command details + * ice_free_vf_entries - Free all VF entries from the hash table + * @pf: pointer to the PF structure * - * Send message to VF driver (0x0802) using mailbox - * queue and asynchronously sending message via - * ice_sq_send_cmd() function + * Iterate over the VF hash table, removing and releasing all VF entries. + * Called during VF teardown or as cleanup during failed VF initialization. */ -int -ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval, - u8 *msg, u16 msglen, struct ice_sq_cd *cd) +static void ice_free_vf_entries(struct ice_pf *pf) +{ + struct ice_vfs *vfs = &pf->vfs; + struct hlist_node *tmp; + struct ice_vf *vf; + unsigned int bkt; + + /* Remove all VFs from the hash table and release their main + * reference. Once all references to the VF are dropped, ice_put_vf() + * will call ice_release_vf which will remove the VF memory. + */ + lockdep_assert_held(&vfs->table_lock); + + hash_for_each_safe(vfs->table, bkt, tmp, vf, entry) { + hash_del_rcu(&vf->entry); + ice_put_vf(vf); + } +} + +/** + * ice_vf_vsi_release - invalidate the VF's VSI after freeing it + * @vf: invalidate this VF's VSI after freeing it + */ +static void ice_vf_vsi_release(struct ice_vf *vf) +{ + struct ice_vsi *vsi = ice_get_vf_vsi(vf); + + if (WARN_ON(!vsi)) + return; + + ice_vsi_release(vsi); + ice_vf_invalidate_vsi(vf); +} + +/** + * ice_free_vf_res - Free a VF's resources + * @vf: pointer to the VF info + */ +static void ice_free_vf_res(struct ice_vf *vf) { - struct ice_aqc_pf_vf_msg *cmd; - struct ice_aq_desc desc; + struct ice_pf *pf = vf->pf; + int i, last_vector_idx; - ice_fill_dflt_direct_cmd_desc(&desc, ice_mbx_opc_send_msg_to_vf); + /* First, disable VF's configuration API to prevent OS from + * accessing the VF's VSI after it's freed or invalidated. + */ + clear_bit(ICE_VF_STATE_INIT, vf->vf_states); + ice_vf_fdir_exit(vf); + /* free VF control VSI */ + if (vf->ctrl_vsi_idx != ICE_NO_VSI) + ice_vf_ctrl_vsi_release(vf); + + /* free VSI and disconnect it from the parent uplink */ + if (vf->lan_vsi_idx != ICE_NO_VSI) { + ice_vf_vsi_release(vf); + vf->num_mac = 0; + } + + last_vector_idx = vf->first_vector_idx + pf->vfs.num_msix_per - 1; + + /* clear VF MDD event information */ + memset(&vf->mdd_tx_events, 0, sizeof(vf->mdd_tx_events)); + memset(&vf->mdd_rx_events, 0, sizeof(vf->mdd_rx_events)); + + /* Disable interrupts so that VF starts in a known state */ + for (i = vf->first_vector_idx; i <= last_vector_idx; i++) { + wr32(&pf->hw, GLINT_DYN_CTL(i), GLINT_DYN_CTL_CLEARPBA_M); + ice_flush(&pf->hw); + } + /* reset some of the state variables keeping track of the resources */ + clear_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states); + clear_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states); +} + +/** + * ice_dis_vf_mappings + * @vf: pointer to the VF structure + */ +static void ice_dis_vf_mappings(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + struct device *dev; + int first, last, v; + struct ice_hw *hw; - cmd = &desc.params.virt; - cmd->id = cpu_to_le32(vfid); + hw = &pf->hw; + vsi = ice_get_vf_vsi(vf); + if (WARN_ON(!vsi)) + return; - desc.cookie_high = cpu_to_le32(v_opcode); - desc.cookie_low = cpu_to_le32(v_retval); + dev = ice_pf_to_dev(pf); + wr32(hw, VPINT_ALLOC(vf->vf_id), 0); + wr32(hw, VPINT_ALLOC_PCI(vf->vf_id), 0); - if (msglen) - desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + first = vf->first_vector_idx; + last = first + pf->vfs.num_msix_per - 1; + for (v = first; v <= last; v++) { + u32 reg; - return ice_sq_send_cmd(hw, &hw->mailboxq, &desc, msg, msglen, cd); + reg = (((1 << GLINT_VECT2FUNC_IS_PF_S) & + GLINT_VECT2FUNC_IS_PF_M) | + ((hw->pf_id << GLINT_VECT2FUNC_PF_NUM_S) & + GLINT_VECT2FUNC_PF_NUM_M)); + wr32(hw, GLINT_VECT2FUNC(v), reg); + } + + if (vsi->tx_mapping_mode == ICE_VSI_MAP_CONTIG) + wr32(hw, VPLAN_TX_QBASE(vf->vf_id), 0); + else + dev_err(dev, "Scattered mode for VF Tx queues is not yet implemented\n"); + + if (vsi->rx_mapping_mode == ICE_VSI_MAP_CONTIG) + wr32(hw, VPLAN_RX_QBASE(vf->vf_id), 0); + else + dev_err(dev, "Scattered mode for VF Rx queues is not yet implemented\n"); } /** - * ice_conv_link_speed_to_virtchnl - * @adv_link_support: determines the format of the returned link speed - * @link_speed: variable containing the link_speed to be converted + * ice_sriov_free_msix_res - Reset/free any used MSIX resources + * @pf: pointer to the PF structure * - * Convert link speed supported by HW to link speed supported by virtchnl. - * If adv_link_support is true, then return link speed in Mbps. Else return - * link speed as a VIRTCHNL_LINK_SPEED_* casted to a u32. Note that the caller - * needs to cast back to an enum virtchnl_link_speed in the case where - * adv_link_support is false, but when adv_link_support is true the caller can - * expect the speed in Mbps. + * Since no MSIX entries are taken from the pf->irq_tracker then just clear + * the pf->sriov_base_vector. + * + * Returns 0 on success, and -EINVAL on error. */ -u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed) +static int ice_sriov_free_msix_res(struct ice_pf *pf) { - u32 speed; + struct ice_res_tracker *res; - if (adv_link_support) - switch (link_speed) { - case ICE_AQ_LINK_SPEED_10MB: - speed = ICE_LINK_SPEED_10MBPS; - break; - case ICE_AQ_LINK_SPEED_100MB: - speed = ICE_LINK_SPEED_100MBPS; - break; - case ICE_AQ_LINK_SPEED_1000MB: - speed = ICE_LINK_SPEED_1000MBPS; - break; - case ICE_AQ_LINK_SPEED_2500MB: - speed = ICE_LINK_SPEED_2500MBPS; - break; - case ICE_AQ_LINK_SPEED_5GB: - speed = ICE_LINK_SPEED_5000MBPS; - break; - case ICE_AQ_LINK_SPEED_10GB: - speed = ICE_LINK_SPEED_10000MBPS; - break; - case ICE_AQ_LINK_SPEED_20GB: - speed = ICE_LINK_SPEED_20000MBPS; - break; - case ICE_AQ_LINK_SPEED_25GB: - speed = ICE_LINK_SPEED_25000MBPS; - break; - case ICE_AQ_LINK_SPEED_40GB: - speed = ICE_LINK_SPEED_40000MBPS; - break; - case ICE_AQ_LINK_SPEED_50GB: - speed = ICE_LINK_SPEED_50000MBPS; - break; - case ICE_AQ_LINK_SPEED_100GB: - speed = ICE_LINK_SPEED_100000MBPS; - break; - default: - speed = ICE_LINK_SPEED_UNKNOWN; - break; - } + if (!pf) + return -EINVAL; + + res = pf->irq_tracker; + if (!res) + return -EINVAL; + + /* give back irq_tracker resources used */ + WARN_ON(pf->sriov_base_vector < res->num_entries); + + pf->sriov_base_vector = 0; + + return 0; +} + +/** + * ice_free_vfs - Free all VFs + * @pf: pointer to the PF structure + */ +void ice_free_vfs(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + struct ice_vfs *vfs = &pf->vfs; + struct ice_hw *hw = &pf->hw; + struct ice_vf *vf; + unsigned int bkt; + + if (!ice_has_vfs(pf)) + return; + + while (test_and_set_bit(ICE_VF_DIS, pf->state)) + usleep_range(1000, 2000); + + /* Disable IOV before freeing resources. This lets any VF drivers + * running in the host get themselves cleaned up before we yank + * the carpet out from underneath their feet. + */ + if (!pci_vfs_assigned(pf->pdev)) + pci_disable_sriov(pf->pdev); else - /* Virtchnl speeds are not defined for every speed supported in - * the hardware. To maintain compatibility with older AVF - * drivers, while reporting the speed the new speed values are - * resolved to the closest known virtchnl speeds - */ - switch (link_speed) { - case ICE_AQ_LINK_SPEED_10MB: - case ICE_AQ_LINK_SPEED_100MB: - speed = (u32)VIRTCHNL_LINK_SPEED_100MB; - break; - case ICE_AQ_LINK_SPEED_1000MB: - case ICE_AQ_LINK_SPEED_2500MB: - case ICE_AQ_LINK_SPEED_5GB: - speed = (u32)VIRTCHNL_LINK_SPEED_1GB; - break; - case ICE_AQ_LINK_SPEED_10GB: - speed = (u32)VIRTCHNL_LINK_SPEED_10GB; - break; - case ICE_AQ_LINK_SPEED_20GB: - speed = (u32)VIRTCHNL_LINK_SPEED_20GB; - break; - case ICE_AQ_LINK_SPEED_25GB: - speed = (u32)VIRTCHNL_LINK_SPEED_25GB; - break; - case ICE_AQ_LINK_SPEED_40GB: - case ICE_AQ_LINK_SPEED_50GB: - case ICE_AQ_LINK_SPEED_100GB: - speed = (u32)VIRTCHNL_LINK_SPEED_40GB; - break; - default: - speed = (u32)VIRTCHNL_LINK_SPEED_UNKNOWN; - break; + dev_warn(dev, "VFs are assigned - not disabling SR-IOV\n"); + + mutex_lock(&vfs->table_lock); + + ice_eswitch_release(pf); + + ice_for_each_vf(pf, bkt, vf) { + mutex_lock(&vf->cfg_lock); + + ice_dis_vf_qs(vf); + + if (test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { + /* disable VF qp mappings and set VF disable state */ + ice_dis_vf_mappings(vf); + set_bit(ICE_VF_STATE_DIS, vf->vf_states); + ice_free_vf_res(vf); + } + + if (!pci_vfs_assigned(pf->pdev)) { + u32 reg_idx, bit_idx; + + reg_idx = (hw->func_caps.vf_base_id + vf->vf_id) / 32; + bit_idx = (hw->func_caps.vf_base_id + vf->vf_id) % 32; + wr32(hw, GLGEN_VFLRSTAT(reg_idx), BIT(bit_idx)); } - return speed; + /* clear malicious info since the VF is getting released */ + if (ice_mbx_clear_malvf(&hw->mbx_snapshot, pf->vfs.malvfs, + ICE_MAX_SRIOV_VFS, vf->vf_id)) + dev_dbg(dev, "failed to clear malicious VF state for VF %u\n", + vf->vf_id); + + mutex_unlock(&vf->cfg_lock); + } + + if (ice_sriov_free_msix_res(pf)) + dev_err(dev, "Failed to free MSIX resources used by SR-IOV\n"); + + vfs->num_qps_per = 0; + ice_free_vf_entries(pf); + + mutex_unlock(&vfs->table_lock); + + clear_bit(ICE_VF_DIS, pf->state); + clear_bit(ICE_FLAG_SRIOV_ENA, pf->flags); +} + +/** + * ice_vf_vsi_setup - Set up a VF VSI + * @vf: VF to setup VSI for + * + * Returns pointer to the successfully allocated VSI struct on success, + * otherwise returns NULL on failure. + */ +static struct ice_vsi *ice_vf_vsi_setup(struct ice_vf *vf) +{ + struct ice_port_info *pi = ice_vf_get_port_info(vf); + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + + vsi = ice_vsi_setup(pf, pi, ICE_VSI_VF, vf, NULL); + + if (!vsi) { + dev_err(ice_pf_to_dev(pf), "Failed to create VF VSI\n"); + ice_vf_invalidate_vsi(vf); + return NULL; + } + + vf->lan_vsi_idx = vsi->idx; + vf->lan_vsi_num = vsi->vsi_num; + + 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 + * @vf: VF to enable MSIX mappings for + * + * Some of the registers need to be indexed/configured using hardware global + * device values and other registers need 0-based values, which represent PF + * based values. + */ +static void ice_ena_vf_msix_mappings(struct ice_vf *vf) +{ + int device_based_first_msix, device_based_last_msix; + int pf_based_first_msix, pf_based_last_msix, v; + struct ice_pf *pf = vf->pf; + int device_based_vf_id; + struct ice_hw *hw; + u32 reg; + + 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; + + 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_vf_id = vf->vf_id + hw->func_caps.vf_base_id; + + reg = (((device_based_first_msix << VPINT_ALLOC_FIRST_S) & + VPINT_ALLOC_FIRST_M) | + ((device_based_last_msix << VPINT_ALLOC_LAST_S) & + VPINT_ALLOC_LAST_M) | VPINT_ALLOC_VALID_M); + wr32(hw, VPINT_ALLOC(vf->vf_id), reg); + + reg = (((device_based_first_msix << VPINT_ALLOC_PCI_FIRST_S) + & VPINT_ALLOC_PCI_FIRST_M) | + ((device_based_last_msix << VPINT_ALLOC_PCI_LAST_S) & + VPINT_ALLOC_PCI_LAST_M) | VPINT_ALLOC_PCI_VALID_M); + wr32(hw, VPINT_ALLOC_PCI(vf->vf_id), reg); + + /* map the interrupts to its functions */ + for (v = pf_based_first_msix; v <= pf_based_last_msix; v++) { + reg = (((device_based_vf_id << GLINT_VECT2FUNC_VF_NUM_S) & + GLINT_VECT2FUNC_VF_NUM_M) | + ((hw->pf_id << GLINT_VECT2FUNC_PF_NUM_S) & + GLINT_VECT2FUNC_PF_NUM_M)); + wr32(hw, GLINT_VECT2FUNC(v), reg); + } + + /* Map mailbox interrupt to VF MSI-X vector 0 */ + wr32(hw, VPINT_MBX_CTL(device_based_vf_id), VPINT_MBX_CTL_CAUSE_ENA_M); +} + +/** + * ice_ena_vf_q_mappings - enable Rx/Tx queue mappings for a VF + * @vf: VF to enable the mappings for + * @max_txq: max Tx queues allowed on the VF's VSI + * @max_rxq: max Rx queues allowed on the VF's VSI + */ +static void ice_ena_vf_q_mappings(struct ice_vf *vf, u16 max_txq, u16 max_rxq) +{ + struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_vsi *vsi = ice_get_vf_vsi(vf); + struct ice_hw *hw = &vf->pf->hw; + u32 reg; + + if (WARN_ON(!vsi)) + return; + + /* set regardless of mapping mode */ + wr32(hw, VPLAN_TXQ_MAPENA(vf->vf_id), VPLAN_TXQ_MAPENA_TX_ENA_M); + + /* VF Tx queues allocation */ + if (vsi->tx_mapping_mode == ICE_VSI_MAP_CONTIG) { + /* set the VF PF Tx queue range + * VFNUMQ value should be set to (number of queues - 1). A value + * of 0 means 1 queue and a value of 255 means 256 queues + */ + reg = (((vsi->txq_map[0] << VPLAN_TX_QBASE_VFFIRSTQ_S) & + VPLAN_TX_QBASE_VFFIRSTQ_M) | + (((max_txq - 1) << VPLAN_TX_QBASE_VFNUMQ_S) & + VPLAN_TX_QBASE_VFNUMQ_M)); + wr32(hw, VPLAN_TX_QBASE(vf->vf_id), reg); + } else { + dev_err(dev, "Scattered mode for VF Tx queues is not yet implemented\n"); + } + + /* set regardless of mapping mode */ + wr32(hw, VPLAN_RXQ_MAPENA(vf->vf_id), VPLAN_RXQ_MAPENA_RX_ENA_M); + + /* VF Rx queues allocation */ + if (vsi->rx_mapping_mode == ICE_VSI_MAP_CONTIG) { + /* set the VF PF Rx queue range + * VFNUMQ value should be set to (number of queues - 1). A value + * of 0 means 1 queue and a value of 255 means 256 queues + */ + reg = (((vsi->rxq_map[0] << VPLAN_RX_QBASE_VFFIRSTQ_S) & + VPLAN_RX_QBASE_VFFIRSTQ_M) | + (((max_rxq - 1) << VPLAN_RX_QBASE_VFNUMQ_S) & + VPLAN_RX_QBASE_VFNUMQ_M)); + wr32(hw, VPLAN_RX_QBASE(vf->vf_id), reg); + } else { + dev_err(dev, "Scattered mode for VF Rx queues is not yet implemented\n"); + } +} + +/** + * ice_ena_vf_mappings - enable VF MSIX and queue mapping + * @vf: pointer to the VF structure + */ +static void ice_ena_vf_mappings(struct ice_vf *vf) +{ + struct ice_vsi *vsi = ice_get_vf_vsi(vf); + + if (WARN_ON(!vsi)) + return; + + ice_ena_vf_msix_mappings(vf); + ice_ena_vf_q_mappings(vf, vsi->alloc_txq, vsi->alloc_rxq); +} + +/** + * ice_calc_vf_reg_idx - Calculate the VF's register index in the PF space + * @vf: VF to calculate the register index for + * @q_vector: a q_vector associated to the 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; +} + +/** + * ice_get_max_valid_res_idx - Get the max valid resource index + * @res: pointer to the resource to find the max valid index for + * + * Start from the end of the ice_res_tracker and return right when we find the + * first res->list entry with the ICE_RES_VALID_BIT set. This function is only + * valid for SR-IOV because it is the only consumer that manipulates the + * res->end and this is always called when res->end is set to res->num_entries. + */ +static int ice_get_max_valid_res_idx(struct ice_res_tracker *res) +{ + int i; + + if (!res) + return -EINVAL; + + for (i = res->num_entries - 1; i >= 0; i--) + if (res->list[i] & ICE_RES_VALID_BIT) + return i; + + return 0; } -/* The mailbox overflow detection algorithm helps to check if there - * is a possibility of a malicious VF transmitting too many MBX messages to the - * PF. - * 1. The mailbox snapshot structure, ice_mbx_snapshot, is initialized during - * driver initialization in ice_init_hw() using ice_mbx_init_snapshot(). - * The struct ice_mbx_snapshot helps to track and traverse a static window of - * messages within the mailbox queue while looking for a malicious VF. +/** + * ice_sriov_set_msix_res - Set any used MSIX resources + * @pf: pointer to PF structure + * @num_msix_needed: number of MSIX vectors needed for all SR-IOV VFs * - * 2. When the caller starts processing its mailbox queue in response to an - * interrupt, the structure ice_mbx_snapshot is expected to be cleared before - * the algorithm can be run for the first time for that interrupt. This can be - * done via ice_mbx_reset_snapshot(). + * This function allows SR-IOV resources to be taken from the end of the PF's + * allowed HW MSIX vectors so that the irq_tracker will not be affected. We + * just set the pf->sriov_base_vector and return success. * - * 3. For every message read by the caller from the MBX Queue, the caller must - * call the detection algorithm's entry function ice_mbx_vf_state_handler(). - * Before every call to ice_mbx_vf_state_handler() the struct ice_mbx_data is - * filled as it is required to be passed to the algorithm. + * If there are not enough resources available, return an error. This should + * always be caught by ice_set_per_vf_res(). * - * 4. Every time a message is read from the MBX queue, a VFId is received which - * is passed to the state handler. The boolean output is_malvf of the state - * handler ice_mbx_vf_state_handler() serves as an indicator to the caller - * whether this VF is malicious or not. + * Return 0 on success, and -EINVAL when there are not enough MSIX vectors + * in the PF's space available for SR-IOV. + */ +static int ice_sriov_set_msix_res(struct ice_pf *pf, u16 num_msix_needed) +{ + u16 total_vectors = pf->hw.func_caps.common_cap.num_msix_vectors; + int vectors_used = pf->irq_tracker->num_entries; + int sriov_base_vector; + + sriov_base_vector = total_vectors - num_msix_needed; + + /* make sure we only grab irq_tracker entries from the list end and + * that we have enough available MSIX vectors + */ + if (sriov_base_vector < vectors_used) + return -EINVAL; + + pf->sriov_base_vector = sriov_base_vector; + + return 0; +} + +/** + * ice_set_per_vf_res - check if vectors and queues are available + * @pf: pointer to the PF structure + * @num_vfs: the number of SR-IOV VFs being configured * - * 5. When a VF is identified to be malicious, the caller can send a message - * to the system administrator. The caller can invoke ice_mbx_report_malvf() - * to help determine if a malicious VF is to be reported or not. This function - * requires the caller to maintain a global bitmap to track all malicious VFs - * and pass that to ice_mbx_report_malvf() along with the VFID which was identified - * to be malicious by ice_mbx_vf_state_handler(). + * First, determine HW interrupts from common pool. If we allocate fewer VFs, we + * get more vectors and can enable more queues per VF. Note that this does not + * grab any vectors from the SW pool already allocated. Also note, that all + * vector counts include one for each VF's miscellaneous interrupt vector + * (i.e. OICR). * - * 6. The global bitmap maintained by PF can be cleared completely if PF is in - * reset or the bit corresponding to a VF can be cleared if that VF is in reset. - * When a VF is shut down and brought back up, we assume that the new VF - * brought up is not malicious and hence report it if found malicious. + * Minimum VFs - 2 vectors, 1 queue pair + * Small VFs - 5 vectors, 4 queue pairs + * Medium VFs - 17 vectors, 16 queue pairs * - * 7. The function ice_mbx_reset_snapshot() is called to reset the information - * in ice_mbx_snapshot for every new mailbox interrupt handled. + * Second, determine number of queue pairs per VF by starting with a pre-defined + * maximum each VF supports. If this is not possible, then we adjust based on + * queue pairs available on the device. * - * 8. The memory allocated for variables in ice_mbx_snapshot is de-allocated - * when driver is unloaded. + * Lastly, set queue and MSI-X VF variables tracked by the PF so it can be used + * by each VF during VF initialization and reset. */ -#define ICE_RQ_DATA_MASK(rq_data) ((rq_data) & PF_MBX_ARQH_ARQH_M) -/* Using the highest value for an unsigned 16-bit value 0xFFFF to indicate that - * the max messages check must be ignored in the algorithm +static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs) +{ + int max_valid_res_idx = ice_get_max_valid_res_idx(pf->irq_tracker); + u16 num_msix_per_vf, num_txq, num_rxq, avail_qs; + int msix_avail_per_vf, msix_avail_for_sriov; + struct device *dev = ice_pf_to_dev(pf); + int err; + + lockdep_assert_held(&pf->vfs.table_lock); + + if (!num_vfs) + return -EINVAL; + + if (max_valid_res_idx < 0) + return -ENOSPC; + + /* determine MSI-X resources per VF */ + msix_avail_for_sriov = pf->hw.func_caps.common_cap.num_msix_vectors - + pf->irq_tracker->num_entries; + msix_avail_per_vf = msix_avail_for_sriov / num_vfs; + if (msix_avail_per_vf >= ICE_NUM_VF_MSIX_MED) { + num_msix_per_vf = ICE_NUM_VF_MSIX_MED; + } else if (msix_avail_per_vf >= ICE_NUM_VF_MSIX_SMALL) { + num_msix_per_vf = ICE_NUM_VF_MSIX_SMALL; + } else if (msix_avail_per_vf >= ICE_NUM_VF_MSIX_MULTIQ_MIN) { + num_msix_per_vf = ICE_NUM_VF_MSIX_MULTIQ_MIN; + } else if (msix_avail_per_vf >= ICE_MIN_INTR_PER_VF) { + num_msix_per_vf = ICE_MIN_INTR_PER_VF; + } else { + dev_err(dev, "Only %d MSI-X interrupts available for SR-IOV. Not enough to support minimum of %d MSI-X interrupts per VF for %d VFs\n", + msix_avail_for_sriov, ICE_MIN_INTR_PER_VF, + num_vfs); + return -ENOSPC; + } + + num_txq = min_t(u16, num_msix_per_vf - ICE_NONQ_VECS_VF, + ICE_MAX_RSS_QS_PER_VF); + avail_qs = ice_get_avail_txq_count(pf) / num_vfs; + if (!avail_qs) + num_txq = 0; + else if (num_txq > avail_qs) + num_txq = rounddown_pow_of_two(avail_qs); + + num_rxq = min_t(u16, num_msix_per_vf - ICE_NONQ_VECS_VF, + ICE_MAX_RSS_QS_PER_VF); + avail_qs = ice_get_avail_rxq_count(pf) / num_vfs; + if (!avail_qs) + num_rxq = 0; + else if (num_rxq > avail_qs) + num_rxq = rounddown_pow_of_two(avail_qs); + + if (num_txq < ICE_MIN_QS_PER_VF || num_rxq < ICE_MIN_QS_PER_VF) { + dev_err(dev, "Not enough queues to support minimum of %d queue pairs per VF for %d VFs\n", + ICE_MIN_QS_PER_VF, num_vfs); + return -ENOSPC; + } + + err = ice_sriov_set_msix_res(pf, num_msix_per_vf * num_vfs); + if (err) { + dev_err(dev, "Unable to set MSI-X resources for %d VFs, err %d\n", + num_vfs, err); + return err; + } + + /* only allow equal Tx/Rx queue count (i.e. queue pairs) */ + pf->vfs.num_qps_per = min_t(int, num_txq, num_rxq); + pf->vfs.num_msix_per = num_msix_per_vf; + dev_info(dev, "Enabling %d VFs with %d vectors and %d queues per VF\n", + num_vfs, pf->vfs.num_msix_per, pf->vfs.num_qps_per); + + return 0; +} + +/** + * ice_init_vf_vsi_res - initialize/setup VF VSI resources + * @vf: VF to initialize/setup the VSI for + * + * This function creates a VSI for the VF, adds a VLAN 0 filter, and sets up the + * VF VSI's broadcast filter and is only used during initial VF creation. */ -#define ICE_IGNORE_MAX_MSG_CNT 0xFFFF +static int ice_init_vf_vsi_res(struct ice_vf *vf) +{ + struct ice_vsi_vlan_ops *vlan_ops; + struct ice_pf *pf = vf->pf; + u8 broadcast[ETH_ALEN]; + struct ice_vsi *vsi; + struct device *dev; + int err; + + vf->first_vector_idx = ice_calc_vf_first_vector_idx(pf, vf); + + dev = ice_pf_to_dev(pf); + vsi = ice_vf_vsi_setup(vf); + if (!vsi) + return -ENOMEM; + + err = ice_vsi_add_vlan_zero(vsi); + if (err) { + dev_warn(dev, "Failed to add VLAN 0 filter for VF %d\n", + vf->vf_id); + goto release_vsi; + } + + vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); + err = vlan_ops->ena_rx_filtering(vsi); + if (err) { + dev_warn(dev, "Failed to enable Rx VLAN filtering for VF %d\n", + vf->vf_id); + goto release_vsi; + } + + eth_broadcast_addr(broadcast); + err = ice_fltr_add_mac(vsi, broadcast, ICE_FWD_TO_VSI); + if (err) { + dev_err(dev, "Failed to add broadcast MAC filter for VF %d, error %d\n", + vf->vf_id, err); + goto release_vsi; + } + + err = ice_vsi_apply_spoofchk(vsi, vf->spoofchk); + if (err) { + dev_warn(dev, "Failed to initialize spoofchk setting for VF %d\n", + vf->vf_id); + goto release_vsi; + } + + vf->num_mac = 1; + + return 0; + +release_vsi: + ice_vf_vsi_release(vf); + return err; +} /** - * ice_mbx_traverse - Pass through mailbox snapshot - * @hw: pointer to the HW struct - * @new_state: new algorithm state + * ice_start_vfs - start VFs so they are ready to be used by SR-IOV + * @pf: PF the VFs are associated with + */ +static int ice_start_vfs(struct ice_pf *pf) +{ + struct ice_hw *hw = &pf->hw; + unsigned int bkt, it_cnt; + struct ice_vf *vf; + int retval; + + lockdep_assert_held(&pf->vfs.table_lock); + + it_cnt = 0; + ice_for_each_vf(pf, bkt, vf) { + vf->vf_ops->clear_reset_trigger(vf); + + retval = ice_init_vf_vsi_res(vf); + if (retval) { + dev_err(ice_pf_to_dev(pf), "Failed to initialize VSI resources for VF %d, error %d\n", + vf->vf_id, retval); + goto teardown; + } + + set_bit(ICE_VF_STATE_INIT, vf->vf_states); + ice_ena_vf_mappings(vf); + wr32(hw, VFGEN_RSTAT(vf->vf_id), VIRTCHNL_VFR_VFACTIVE); + it_cnt++; + } + + ice_flush(hw); + return 0; + +teardown: + ice_for_each_vf(pf, bkt, vf) { + if (it_cnt == 0) + break; + + ice_dis_vf_mappings(vf); + ice_vf_vsi_release(vf); + it_cnt--; + } + + return retval; +} + +/** + * ice_sriov_free_vf - Free VF memory after all references are dropped + * @vf: pointer to VF to free * - * Traversing the mailbox static snapshot without checking - * for malicious VFs. + * Called by ice_put_vf through ice_release_vf once the last reference to a VF + * structure has been dropped. */ -static void -ice_mbx_traverse(struct ice_hw *hw, - enum ice_mbx_snapshot_state *new_state) +static void ice_sriov_free_vf(struct ice_vf *vf) { - struct ice_mbx_snap_buffer_data *snap_buf; - u32 num_iterations; + mutex_destroy(&vf->cfg_lock); - snap_buf = &hw->mbx_snapshot.mbx_buf; + kfree_rcu(vf, rcu); +} - /* As mailbox buffer is circular, applying a mask - * on the incremented iteration count. - */ - num_iterations = ICE_RQ_DATA_MASK(++snap_buf->num_iterations); - - /* Checking either of the below conditions to exit snapshot traversal: - * Condition-1: If the number of iterations in the mailbox is equal to - * the mailbox head which would indicate that we have reached the end - * of the static snapshot. - * Condition-2: If the maximum messages serviced in the mailbox for a - * given interrupt is the highest possible value then there is no need - * to check if the number of messages processed is equal to it. If not - * check if the number of messages processed is greater than or equal - * to the maximum number of mailbox entries serviced in current work item. +/** + * ice_sriov_clear_mbx_register - clears SRIOV VF's mailbox registers + * @vf: the vf to configure + */ +static void ice_sriov_clear_mbx_register(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + + wr32(&pf->hw, VF_MBX_ARQLEN(vf->vf_id), 0); + wr32(&pf->hw, VF_MBX_ATQLEN(vf->vf_id), 0); +} + +/** + * ice_sriov_trigger_reset_register - trigger VF reset for SRIOV VF + * @vf: pointer to VF structure + * @is_vflr: true if reset occurred due to VFLR + * + * Trigger and cleanup after a VF reset for a SR-IOV VF. + */ +static void ice_sriov_trigger_reset_register(struct ice_vf *vf, bool is_vflr) +{ + struct ice_pf *pf = vf->pf; + u32 reg, reg_idx, bit_idx; + unsigned int vf_abs_id, i; + struct device *dev; + struct ice_hw *hw; + + dev = ice_pf_to_dev(pf); + hw = &pf->hw; + vf_abs_id = vf->vf_id + hw->func_caps.vf_base_id; + + /* In the case of a VFLR, HW has already reset the VF and we just need + * to clean up. Otherwise we must first trigger the reset using the + * VFRTRIG register. */ - if (num_iterations == snap_buf->head || - (snap_buf->max_num_msgs_mbx < ICE_IGNORE_MAX_MSG_CNT && - ++snap_buf->num_msg_proc >= snap_buf->max_num_msgs_mbx)) - *new_state = ICE_MAL_VF_DETECT_STATE_NEW_SNAPSHOT; + if (!is_vflr) { + reg = rd32(hw, VPGEN_VFRTRIG(vf->vf_id)); + reg |= VPGEN_VFRTRIG_VFSWR_M; + wr32(hw, VPGEN_VFRTRIG(vf->vf_id), reg); + } + + /* clear the VFLR bit in GLGEN_VFLRSTAT */ + reg_idx = (vf_abs_id) / 32; + bit_idx = (vf_abs_id) % 32; + wr32(hw, GLGEN_VFLRSTAT(reg_idx), BIT(bit_idx)); + ice_flush(hw); + + wr32(hw, PF_PCI_CIAA, + VF_DEVICE_STATUS | (vf_abs_id << PF_PCI_CIAA_VF_NUM_S)); + for (i = 0; i < ICE_PCI_CIAD_WAIT_COUNT; i++) { + reg = rd32(hw, PF_PCI_CIAD); + /* no transactions pending so stop polling */ + if ((reg & VF_TRANS_PENDING_M) == 0) + break; + + dev_err(dev, "VF %u PCI transactions stuck\n", vf->vf_id); + udelay(ICE_PCI_CIAD_WAIT_DELAY_US); + } } /** - * ice_mbx_detect_malvf - Detect malicious VF in snapshot - * @hw: pointer to the HW struct - * @vf_id: relative virtual function ID - * @new_state: new algorithm state - * @is_malvf: boolean output to indicate if VF is malicious + * ice_sriov_poll_reset_status - poll SRIOV VF reset status + * @vf: pointer to VF structure * - * This function tracks the number of asynchronous messages - * sent per VF and marks the VF as malicious if it exceeds - * the permissible number of messages to send. + * Returns true when reset is successful, else returns false */ -static int -ice_mbx_detect_malvf(struct ice_hw *hw, u16 vf_id, - enum ice_mbx_snapshot_state *new_state, - bool *is_malvf) +static bool ice_sriov_poll_reset_status(struct ice_vf *vf) { - struct ice_mbx_snapshot *snap = &hw->mbx_snapshot; + struct ice_pf *pf = vf->pf; + unsigned int i; + u32 reg; - if (vf_id >= snap->mbx_vf.vfcntr_len) - return -EIO; + for (i = 0; i < 10; i++) { + /* VF reset requires driver to first reset the VF and then + * poll the status register to make sure that the reset + * completed successfully. + */ + reg = rd32(&pf->hw, VPGEN_VFRSTAT(vf->vf_id)); + if (reg & VPGEN_VFRSTAT_VFRD_M) + return true; - /* increment the message count in the VF array */ - snap->mbx_vf.vf_cntr[vf_id]++; + /* only sleep if the reset is not done */ + usleep_range(10, 20); + } + return false; +} - if (snap->mbx_vf.vf_cntr[vf_id] >= ICE_ASYNC_VF_MSG_THRESHOLD) - *is_malvf = true; +/** + * ice_sriov_clear_reset_trigger - enable VF to access hardware + * @vf: VF to enabled hardware access for + */ +static void ice_sriov_clear_reset_trigger(struct ice_vf *vf) +{ + struct ice_hw *hw = &vf->pf->hw; + u32 reg; + + reg = rd32(hw, VPGEN_VFRTRIG(vf->vf_id)); + reg &= ~VPGEN_VFRTRIG_VFSWR_M; + wr32(hw, VPGEN_VFRTRIG(vf->vf_id), reg); + ice_flush(hw); +} + +/** + * ice_sriov_vsi_rebuild - release and rebuild VF's VSI + * @vf: VF to release and setup the VSI for + * + * This is only called when a single VF is being reset (i.e. VFR, VFLR, host VF + * configuration change, etc.). + */ +static int ice_sriov_vsi_rebuild(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; - /* continue to iterate through the mailbox snapshot */ - ice_mbx_traverse(hw, new_state); + ice_vf_vsi_release(vf); + if (!ice_vf_vsi_setup(vf)) { + dev_err(ice_pf_to_dev(pf), + "Failed to release and setup the VF%u's VSI\n", + vf->vf_id); + return -ENOMEM; + } return 0; } /** - * ice_mbx_reset_snapshot - Reset mailbox snapshot structure - * @snap: pointer to mailbox snapshot structure in the ice_hw struct + * ice_sriov_post_vsi_rebuild - tasks to do after the VF's VSI have been rebuilt + * @vf: VF to perform tasks on + */ +static void ice_sriov_post_vsi_rebuild(struct ice_vf *vf) +{ + ice_vf_rebuild_host_cfg(vf); + ice_vf_set_initialized(vf); + ice_ena_vf_mappings(vf); + wr32(&vf->pf->hw, VFGEN_RSTAT(vf->vf_id), VIRTCHNL_VFR_VFACTIVE); +} + +static const struct ice_vf_ops ice_sriov_vf_ops = { + .reset_type = ICE_VF_RESET, + .free = ice_sriov_free_vf, + .clear_mbx_register = ice_sriov_clear_mbx_register, + .trigger_reset_register = ice_sriov_trigger_reset_register, + .poll_reset_status = ice_sriov_poll_reset_status, + .clear_reset_trigger = ice_sriov_clear_reset_trigger, + .vsi_rebuild = ice_sriov_vsi_rebuild, + .post_vsi_rebuild = ice_sriov_post_vsi_rebuild, +}; + +/** + * ice_create_vf_entries - Allocate and insert VF entries + * @pf: pointer to the PF structure + * @num_vfs: the number of VFs to allocate + * + * Allocate new VF entries and insert them into the hash table. Set some + * basic default fields for initializing the new VFs. * - * Reset the mailbox snapshot structure and clear VF counter array. + * After this function exits, the hash table will have num_vfs entries + * inserted. + * + * Returns 0 on success or an integer error code on failure. */ -static void ice_mbx_reset_snapshot(struct ice_mbx_snapshot *snap) +static int ice_create_vf_entries(struct ice_pf *pf, u16 num_vfs) { - u32 vfcntr_len; + struct ice_vfs *vfs = &pf->vfs; + struct ice_vf *vf; + u16 vf_id; + int err; + + lockdep_assert_held(&vfs->table_lock); + + for (vf_id = 0; vf_id < num_vfs; vf_id++) { + vf = kzalloc(sizeof(*vf), GFP_KERNEL); + if (!vf) { + err = -ENOMEM; + goto err_free_entries; + } + kref_init(&vf->refcnt); + + vf->pf = pf; + vf->vf_id = vf_id; + + /* set sriov vf ops for VFs created during SRIOV flow */ + vf->vf_ops = &ice_sriov_vf_ops; - if (!snap || !snap->mbx_vf.vf_cntr) + vf->vf_sw_id = pf->first_sw; + /* assign default capabilities */ + vf->spoofchk = true; + vf->num_vf_qs = pf->vfs.num_qps_per; + ice_vc_set_default_allowlist(vf); + + /* ctrl_vsi_idx will be set to a valid value only when VF + * creates its first fdir rule. + */ + ice_vf_ctrl_invalidate_vsi(vf); + ice_vf_fdir_init(vf); + + ice_virtchnl_set_dflt_ops(vf); + + mutex_init(&vf->cfg_lock); + + hash_add_rcu(vfs->table, &vf->entry, vf_id); + } + + return 0; + +err_free_entries: + ice_free_vf_entries(pf); + return err; +} + +/** + * ice_ena_vfs - enable VFs so they are ready to be used + * @pf: pointer to the PF structure + * @num_vfs: number of VFs to enable + */ +static int ice_ena_vfs(struct ice_pf *pf, u16 num_vfs) +{ + struct device *dev = ice_pf_to_dev(pf); + struct ice_hw *hw = &pf->hw; + int ret; + + /* Disable global interrupt 0 so we don't try to handle the VFLR. */ + wr32(hw, GLINT_DYN_CTL(pf->oicr_idx), + ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S); + set_bit(ICE_OICR_INTR_DIS, pf->state); + ice_flush(hw); + + ret = pci_enable_sriov(pf->pdev, num_vfs); + if (ret) + goto err_unroll_intr; + + mutex_lock(&pf->vfs.table_lock); + + ret = ice_set_per_vf_res(pf, num_vfs); + if (ret) { + dev_err(dev, "Not enough resources for %d VFs, err %d. Try with fewer number of VFs\n", + num_vfs, ret); + goto err_unroll_sriov; + } + + ret = ice_create_vf_entries(pf, num_vfs); + if (ret) { + dev_err(dev, "Failed to allocate VF entries for %d VFs\n", + num_vfs); + goto err_unroll_sriov; + } + + ret = ice_start_vfs(pf); + if (ret) { + dev_err(dev, "Failed to start %d VFs, err %d\n", num_vfs, ret); + ret = -EAGAIN; + goto err_unroll_vf_entries; + } + + clear_bit(ICE_VF_DIS, pf->state); + + ret = ice_eswitch_configure(pf); + if (ret) { + dev_err(dev, "Failed to configure eswitch, err %d\n", ret); + goto err_unroll_sriov; + } + + /* rearm global interrupts */ + if (test_and_clear_bit(ICE_OICR_INTR_DIS, pf->state)) + ice_irq_dynamic_ena(hw, NULL, NULL); + + mutex_unlock(&pf->vfs.table_lock); + + return 0; + +err_unroll_vf_entries: + ice_free_vf_entries(pf); +err_unroll_sriov: + mutex_unlock(&pf->vfs.table_lock); + pci_disable_sriov(pf->pdev); +err_unroll_intr: + /* rearm interrupts here */ + ice_irq_dynamic_ena(hw, NULL, NULL); + clear_bit(ICE_OICR_INTR_DIS, pf->state); + return ret; +} + +/** + * ice_pci_sriov_ena - Enable or change number of VFs + * @pf: pointer to the PF structure + * @num_vfs: number of VFs to allocate + * + * Returns 0 on success and negative on failure + */ +static int ice_pci_sriov_ena(struct ice_pf *pf, int num_vfs) +{ + int pre_existing_vfs = pci_num_vf(pf->pdev); + struct device *dev = ice_pf_to_dev(pf); + int err; + + if (pre_existing_vfs && pre_existing_vfs != num_vfs) + ice_free_vfs(pf); + else if (pre_existing_vfs && pre_existing_vfs == num_vfs) + return 0; + + if (num_vfs > pf->vfs.num_supported) { + dev_err(dev, "Can't enable %d VFs, max VFs supported is %d\n", + num_vfs, pf->vfs.num_supported); + return -EOPNOTSUPP; + } + + dev_info(dev, "Enabling %d VFs\n", num_vfs); + err = ice_ena_vfs(pf, num_vfs); + if (err) { + dev_err(dev, "Failed to enable SR-IOV: %d\n", err); + return err; + } + + set_bit(ICE_FLAG_SRIOV_ENA, pf->flags); + return 0; +} + +/** + * ice_check_sriov_allowed - check if SR-IOV is allowed based on various checks + * @pf: PF to enabled SR-IOV on + */ +static int ice_check_sriov_allowed(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + + if (!test_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags)) { + dev_err(dev, "This device is not capable of SR-IOV\n"); + return -EOPNOTSUPP; + } + + if (ice_is_safe_mode(pf)) { + dev_err(dev, "SR-IOV cannot be configured - Device is in Safe Mode\n"); + return -EOPNOTSUPP; + } + + if (!ice_pf_state_is_nominal(pf)) { + dev_err(dev, "Cannot enable SR-IOV, device not ready\n"); + return -EBUSY; + } + + return 0; +} + +/** + * 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 + * + * This function is called when the user updates the number of VFs in sysfs. On + * success return whatever num_vfs was set to by the caller. Return negative on + * failure. + */ +int ice_sriov_configure(struct pci_dev *pdev, int num_vfs) +{ + struct ice_pf *pf = pci_get_drvdata(pdev); + struct device *dev = ice_pf_to_dev(pf); + int err; + + err = ice_check_sriov_allowed(pf); + if (err) + return err; + + if (!num_vfs) { + if (!pci_vfs_assigned(pdev)) { + ice_free_vfs(pf); + ice_mbx_deinit_snapshot(&pf->hw); + if (pf->lag) + ice_enable_lag(pf->lag); + return 0; + } + + dev_err(dev, "can't free VFs because some are assigned to VMs.\n"); + return -EBUSY; + } + + err = ice_mbx_init_snapshot(&pf->hw, num_vfs); + if (err) + return err; + + err = ice_pci_sriov_ena(pf, num_vfs); + if (err) { + ice_mbx_deinit_snapshot(&pf->hw); + return err; + } + + if (pf->lag) + ice_disable_lag(pf->lag); + return num_vfs; +} + +/** + * ice_process_vflr_event - Free VF resources via IRQ calls + * @pf: pointer to the PF structure + * + * called from the VFLR IRQ handler to + * free up VF resources and state variables + */ +void ice_process_vflr_event(struct ice_pf *pf) +{ + struct ice_hw *hw = &pf->hw; + struct ice_vf *vf; + unsigned int bkt; + u32 reg; + + if (!test_and_clear_bit(ICE_VFLR_EVENT_PENDING, pf->state) || + !ice_has_vfs(pf)) return; - /* Clear VF counters. */ - vfcntr_len = snap->mbx_vf.vfcntr_len; - if (vfcntr_len) - memset(snap->mbx_vf.vf_cntr, 0, - (vfcntr_len * sizeof(*snap->mbx_vf.vf_cntr))); - - /* Reset mailbox snapshot for a new capture. */ - memset(&snap->mbx_buf, 0, sizeof(snap->mbx_buf)); - snap->mbx_buf.state = ICE_MAL_VF_DETECT_STATE_NEW_SNAPSHOT; -} - -/** - * ice_mbx_vf_state_handler - Handle states of the overflow algorithm - * @hw: pointer to the HW struct - * @mbx_data: pointer to structure containing mailbox data - * @vf_id: relative virtual function (VF) ID - * @is_malvf: boolean output to indicate if VF is malicious - * - * The function serves as an entry point for the malicious VF - * detection algorithm by handling the different states and state - * transitions of the algorithm: - * New snapshot: This state is entered when creating a new static - * snapshot. The data from any previous mailbox snapshot is - * cleared and a new capture of the mailbox head and tail is - * logged. This will be the new static snapshot to detect - * asynchronous messages sent by VFs. On capturing the snapshot - * and depending on whether the number of pending messages in that - * snapshot exceed the watermark value, the state machine enters - * traverse or detect states. - * Traverse: If pending message count is below watermark then iterate - * through the snapshot without any action on VF. - * Detect: If pending message count exceeds watermark traverse - * the static snapshot and look for a malicious VF. + mutex_lock(&pf->vfs.table_lock); + ice_for_each_vf(pf, bkt, vf) { + u32 reg_idx, bit_idx; + + reg_idx = (hw->func_caps.vf_base_id + vf->vf_id) / 32; + bit_idx = (hw->func_caps.vf_base_id + vf->vf_id) % 32; + /* read GLGEN_VFLRSTAT register to find out the flr VFs */ + reg = rd32(hw, GLGEN_VFLRSTAT(reg_idx)); + if (reg & BIT(bit_idx)) + /* GLGEN_VFLRSTAT bit will be cleared in ice_reset_vf */ + ice_reset_vf(vf, ICE_VF_RESET_VFLR | ICE_VF_RESET_LOCK); + } + mutex_unlock(&pf->vfs.table_lock); +} + +/** + * ice_get_vf_from_pfq - get the VF who owns the PF space queue passed in + * @pf: PF used to index all VFs + * @pfq: queue index relative to the PF's function space + * + * If no VF is found who owns the pfq then return NULL, otherwise return a + * pointer to the VF who owns the pfq + * + * If this function returns non-NULL, it acquires a reference count of the VF + * structure. The caller is responsible for calling ice_put_vf() to drop this + * reference. + */ +static struct ice_vf *ice_get_vf_from_pfq(struct ice_pf *pf, u16 pfq) +{ + struct ice_vf *vf; + unsigned int bkt; + + rcu_read_lock(); + ice_for_each_vf_rcu(pf, bkt, vf) { + struct ice_vsi *vsi; + u16 rxq_idx; + + vsi = ice_get_vf_vsi(vf); + if (!vsi) + continue; + + ice_for_each_rxq(vsi, rxq_idx) + if (vsi->rxq_map[rxq_idx] == pfq) { + struct ice_vf *found; + + if (kref_get_unless_zero(&vf->refcnt)) + found = vf; + else + found = NULL; + rcu_read_unlock(); + return found; + } + } + rcu_read_unlock(); + + return NULL; +} + +/** + * ice_globalq_to_pfq - convert from global queue index to PF space queue index + * @pf: PF used for conversion + * @globalq: global queue index used to convert to PF space queue index + */ +static u32 ice_globalq_to_pfq(struct ice_pf *pf, u32 globalq) +{ + return globalq - pf->hw.func_caps.common_cap.rxq_first_id; +} + +/** + * ice_vf_lan_overflow_event - handle LAN overflow event for a VF + * @pf: PF that the LAN overflow event happened on + * @event: structure holding the event information for the LAN overflow event + * + * Determine if the LAN overflow event was caused by a VF queue. If it was not + * caused by a VF, do nothing. If a VF caused this LAN overflow event trigger a + * reset on the offending VF. + */ +void +ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event) +{ + u32 gldcb_rtctq, queue; + struct ice_vf *vf; + + gldcb_rtctq = le32_to_cpu(event->desc.params.lan_overflow.prtdcb_ruptq); + dev_dbg(ice_pf_to_dev(pf), "GLDCB_RTCTQ: 0x%08x\n", gldcb_rtctq); + + /* event returns device global Rx queue number */ + queue = (gldcb_rtctq & GLDCB_RTCTQ_RXQNUM_M) >> + GLDCB_RTCTQ_RXQNUM_S; + + vf = ice_get_vf_from_pfq(pf, ice_globalq_to_pfq(pf, queue)); + if (!vf) + return; + + ice_reset_vf(vf, ICE_VF_RESET_NOTIFY | ICE_VF_RESET_LOCK); + ice_put_vf(vf); +} + +/** + * ice_set_vf_spoofchk + * @netdev: network interface device structure + * @vf_id: VF identifier + * @ena: flag to enable or disable feature + * + * Enable or disable VF spoof checking + */ +int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_pf *pf = np->vsi->back; + struct ice_vsi *vf_vsi; + struct device *dev; + struct ice_vf *vf; + int ret; + + dev = ice_pf_to_dev(pf); + + vf = ice_get_vf_by_id(pf, vf_id); + if (!vf) + return -EINVAL; + + ret = ice_check_vf_ready_for_cfg(vf); + if (ret) + goto out_put_vf; + + vf_vsi = ice_get_vf_vsi(vf); + if (!vf_vsi) { + netdev_err(netdev, "VSI %d for VF %d is null\n", + vf->lan_vsi_idx, vf->vf_id); + ret = -EINVAL; + goto out_put_vf; + } + + if (vf_vsi->type != ICE_VSI_VF) { + netdev_err(netdev, "Type %d of VSI %d for VF %d is no ICE_VSI_VF\n", + vf_vsi->type, vf_vsi->vsi_num, vf->vf_id); + ret = -ENODEV; + goto out_put_vf; + } + + if (ena == vf->spoofchk) { + dev_dbg(dev, "VF spoofchk already %s\n", ena ? "ON" : "OFF"); + ret = 0; + goto out_put_vf; + } + + ret = ice_vsi_apply_spoofchk(vf_vsi, ena); + if (ret) + dev_err(dev, "Failed to set spoofchk %s for VF %d VSI %d\n error %d\n", + ena ? "ON" : "OFF", vf->vf_id, vf_vsi->vsi_num, ret); + else + vf->spoofchk = ena; + +out_put_vf: + ice_put_vf(vf); + return ret; +} + +/** + * ice_get_vf_cfg + * @netdev: network interface device structure + * @vf_id: VF identifier + * @ivi: VF configuration structure + * + * return VF configuration */ int -ice_mbx_vf_state_handler(struct ice_hw *hw, - struct ice_mbx_data *mbx_data, u16 vf_id, - bool *is_malvf) +ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi) { - struct ice_mbx_snapshot *snap = &hw->mbx_snapshot; - struct ice_mbx_snap_buffer_data *snap_buf; - struct ice_ctl_q_info *cq = &hw->mailboxq; - enum ice_mbx_snapshot_state new_state; - int status = 0; + struct ice_pf *pf = ice_netdev_to_pf(netdev); + struct ice_vf *vf; + int ret; - if (!is_malvf || !mbx_data) + vf = ice_get_vf_by_id(pf, vf_id); + if (!vf) return -EINVAL; - /* When entering the mailbox state machine assume that the VF - * is not malicious until detected. - */ - *is_malvf = false; + ret = ice_check_vf_ready_for_cfg(vf); + if (ret) + goto out_put_vf; - /* Checking if max messages allowed to be processed while servicing current - * interrupt is not less than the defined AVF message threshold. - */ - if (mbx_data->max_num_msgs_mbx <= ICE_ASYNC_VF_MSG_THRESHOLD) + ivi->vf = vf_id; + ether_addr_copy(ivi->mac, vf->hw_lan_addr.addr); + + /* VF configuration for VLAN and applicable QoS */ + ivi->vlan = ice_vf_get_port_vlan_id(vf); + ivi->qos = ice_vf_get_port_vlan_prio(vf); + if (ice_vf_is_port_vlan_ena(vf)) + ivi->vlan_proto = cpu_to_be16(ice_vf_get_port_vlan_tpid(vf)); + + ivi->trusted = vf->trusted; + ivi->spoofchk = vf->spoofchk; + if (!vf->link_forced) + ivi->linkstate = IFLA_VF_LINK_STATE_AUTO; + else if (vf->link_up) + ivi->linkstate = IFLA_VF_LINK_STATE_ENABLE; + else + ivi->linkstate = IFLA_VF_LINK_STATE_DISABLE; + ivi->max_tx_rate = vf->max_tx_rate; + ivi->min_tx_rate = vf->min_tx_rate; + +out_put_vf: + ice_put_vf(vf); + return ret; +} + +/** + * ice_set_vf_mac + * @netdev: network interface device structure + * @vf_id: VF identifier + * @mac: MAC address + * + * program VF MAC address + */ +int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) +{ + struct ice_pf *pf = ice_netdev_to_pf(netdev); + struct ice_vf *vf; + int ret; + + if (is_multicast_ether_addr(mac)) { + netdev_err(netdev, "%pM not a valid unicast address\n", mac); + return -EINVAL; + } + + vf = ice_get_vf_by_id(pf, vf_id); + if (!vf) return -EINVAL; - /* The watermark value should not be lesser than the threshold limit - * set for the number of asynchronous messages a VF can send to mailbox - * nor should it be greater than the maximum number of messages in the - * mailbox serviced in current interrupt. + /* nothing left to do, unicast MAC already set */ + if (ether_addr_equal(vf->dev_lan_addr.addr, mac) && + ether_addr_equal(vf->hw_lan_addr.addr, mac)) { + ret = 0; + goto out_put_vf; + } + + ret = ice_check_vf_ready_for_cfg(vf); + if (ret) + goto out_put_vf; + + mutex_lock(&vf->cfg_lock); + + /* VF is notified of its new MAC via the PF's response to the + * VIRTCHNL_OP_GET_VF_RESOURCES message after the VF has been reset */ - if (mbx_data->async_watermark_val < ICE_ASYNC_VF_MSG_THRESHOLD || - mbx_data->async_watermark_val > mbx_data->max_num_msgs_mbx) + ether_addr_copy(vf->dev_lan_addr.addr, mac); + ether_addr_copy(vf->hw_lan_addr.addr, mac); + if (is_zero_ether_addr(mac)) { + /* VF will send VIRTCHNL_OP_ADD_ETH_ADDR message with its MAC */ + vf->pf_set_mac = false; + netdev_info(netdev, "Removing MAC on VF %d. VF driver will be reinitialized\n", + vf->vf_id); + } else { + /* PF will add MAC rule for the VF */ + vf->pf_set_mac = true; + netdev_info(netdev, "Setting MAC %pM on VF %d. VF driver will be reinitialized\n", + mac, vf_id); + } + + ice_reset_vf(vf, ICE_VF_RESET_NOTIFY); + mutex_unlock(&vf->cfg_lock); + +out_put_vf: + ice_put_vf(vf); + return ret; +} + +/** + * ice_set_vf_trust + * @netdev: network interface device structure + * @vf_id: VF identifier + * @trusted: Boolean value to enable/disable trusted VF + * + * Enable or disable a given VF as trusted + */ +int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted) +{ + struct ice_pf *pf = ice_netdev_to_pf(netdev); + struct ice_vf *vf; + int ret; + + if (ice_is_eswitch_mode_switchdev(pf)) { + dev_info(ice_pf_to_dev(pf), "Trusted VF is forbidden in switchdev mode\n"); + return -EOPNOTSUPP; + } + + vf = ice_get_vf_by_id(pf, vf_id); + if (!vf) return -EINVAL; - new_state = ICE_MAL_VF_DETECT_STATE_INVALID; - snap_buf = &snap->mbx_buf; + ret = ice_check_vf_ready_for_cfg(vf); + if (ret) + goto out_put_vf; - switch (snap_buf->state) { - case ICE_MAL_VF_DETECT_STATE_NEW_SNAPSHOT: - /* Clear any previously held data in mailbox snapshot structure. */ - ice_mbx_reset_snapshot(snap); + /* Check if already trusted */ + if (trusted == vf->trusted) { + ret = 0; + goto out_put_vf; + } - /* Collect the pending ARQ count, number of messages processed and - * the maximum number of messages allowed to be processed from the - * Mailbox for current interrupt. - */ - snap_buf->num_pending_arq = mbx_data->num_pending_arq; - snap_buf->num_msg_proc = mbx_data->num_msg_proc; - snap_buf->max_num_msgs_mbx = mbx_data->max_num_msgs_mbx; + mutex_lock(&vf->cfg_lock); - /* Capture a new static snapshot of the mailbox by logging the - * head and tail of snapshot and set num_iterations to the tail - * value to mark the start of the iteration through the snapshot. - */ - snap_buf->head = ICE_RQ_DATA_MASK(cq->rq.next_to_clean + - mbx_data->num_pending_arq); - snap_buf->tail = ICE_RQ_DATA_MASK(cq->rq.next_to_clean - 1); - snap_buf->num_iterations = snap_buf->tail; - - /* Pending ARQ messages returned by ice_clean_rq_elem - * is the difference between the head and tail of the - * mailbox queue. Comparing this value against the watermark - * helps to check if we potentially have malicious VFs. - */ - if (snap_buf->num_pending_arq >= - mbx_data->async_watermark_val) { - new_state = ICE_MAL_VF_DETECT_STATE_DETECT; - status = ice_mbx_detect_malvf(hw, vf_id, &new_state, is_malvf); - } else { - new_state = ICE_MAL_VF_DETECT_STATE_TRAVERSE; - ice_mbx_traverse(hw, &new_state); - } - break; + vf->trusted = trusted; + ice_reset_vf(vf, ICE_VF_RESET_NOTIFY); + dev_info(ice_pf_to_dev(pf), "VF %u is now %strusted\n", + vf_id, trusted ? "" : "un"); - case ICE_MAL_VF_DETECT_STATE_TRAVERSE: - new_state = ICE_MAL_VF_DETECT_STATE_TRAVERSE; - ice_mbx_traverse(hw, &new_state); - break; + mutex_unlock(&vf->cfg_lock); - case ICE_MAL_VF_DETECT_STATE_DETECT: - new_state = ICE_MAL_VF_DETECT_STATE_DETECT; - status = ice_mbx_detect_malvf(hw, vf_id, &new_state, is_malvf); - break; +out_put_vf: + ice_put_vf(vf); + return ret; +} + +/** + * ice_set_vf_link_state + * @netdev: network interface device structure + * @vf_id: VF identifier + * @link_state: required link state + * + * Set VF's link state, irrespective of physical link state status + */ +int ice_set_vf_link_state(struct net_device *netdev, int vf_id, int link_state) +{ + struct ice_pf *pf = ice_netdev_to_pf(netdev); + struct ice_vf *vf; + int ret; + vf = ice_get_vf_by_id(pf, vf_id); + if (!vf) + return -EINVAL; + + ret = ice_check_vf_ready_for_cfg(vf); + if (ret) + goto out_put_vf; + + switch (link_state) { + case IFLA_VF_LINK_STATE_AUTO: + vf->link_forced = false; + break; + case IFLA_VF_LINK_STATE_ENABLE: + vf->link_forced = true; + vf->link_up = true; + break; + case IFLA_VF_LINK_STATE_DISABLE: + vf->link_forced = true; + vf->link_up = false; + break; default: - new_state = ICE_MAL_VF_DETECT_STATE_INVALID; - status = -EIO; + ret = -EINVAL; + goto out_put_vf; } - snap_buf->state = new_state; + ice_vc_notify_vf_link_state(vf); - return status; +out_put_vf: + ice_put_vf(vf); + return ret; } /** - * ice_mbx_report_malvf - Track and note malicious VF - * @hw: pointer to the HW struct - * @all_malvfs: all malicious VFs tracked by PF - * @bitmap_len: length of bitmap in bits - * @vf_id: relative virtual function ID of the malicious VF - * @report_malvf: boolean to indicate if malicious VF must be reported + * ice_calc_all_vfs_min_tx_rate - calculate cumulative min Tx rate on all VFs + * @pf: PF associated with VFs + */ +static int ice_calc_all_vfs_min_tx_rate(struct ice_pf *pf) +{ + struct ice_vf *vf; + unsigned int bkt; + int rate = 0; + + rcu_read_lock(); + ice_for_each_vf_rcu(pf, bkt, vf) + rate += vf->min_tx_rate; + rcu_read_unlock(); + + return rate; +} + +/** + * ice_min_tx_rate_oversubscribed - check if min Tx rate causes oversubscription + * @vf: VF trying to configure min_tx_rate + * @min_tx_rate: min Tx rate in Mbps + * + * Check if the min_tx_rate being passed in will cause oversubscription of total + * min_tx_rate based on the current link speed and all other VFs configured + * min_tx_rate * - * This function will update a bitmap that keeps track of the malicious - * VFs attached to the PF. A malicious VF must be reported only once if - * discovered between VF resets or loading so the function checks - * the input vf_id against the bitmap to verify if the VF has been - * detected in any previous mailbox iterations. + * Return true if the passed min_tx_rate would cause oversubscription, else + * return false + */ +static bool +ice_min_tx_rate_oversubscribed(struct ice_vf *vf, int min_tx_rate) +{ + struct ice_vsi *vsi = ice_get_vf_vsi(vf); + int all_vfs_min_tx_rate; + int link_speed_mbps; + + if (WARN_ON(!vsi)) + return false; + + link_speed_mbps = ice_get_link_speed_mbps(vsi); + all_vfs_min_tx_rate = ice_calc_all_vfs_min_tx_rate(vf->pf); + + /* this VF's previous rate is being overwritten */ + all_vfs_min_tx_rate -= vf->min_tx_rate; + + if (all_vfs_min_tx_rate + min_tx_rate > link_speed_mbps) { + dev_err(ice_pf_to_dev(vf->pf), "min_tx_rate of %d Mbps on VF %u would cause oversubscription of %d Mbps based on the current link speed %d Mbps\n", + min_tx_rate, vf->vf_id, + all_vfs_min_tx_rate + min_tx_rate - link_speed_mbps, + link_speed_mbps); + return true; + } + + return false; +} + +/** + * ice_set_vf_bw - set min/max VF bandwidth + * @netdev: network interface device structure + * @vf_id: VF identifier + * @min_tx_rate: Minimum Tx rate in Mbps + * @max_tx_rate: Maximum Tx rate in Mbps */ int -ice_mbx_report_malvf(struct ice_hw *hw, unsigned long *all_malvfs, - u16 bitmap_len, u16 vf_id, bool *report_malvf) +ice_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, + int max_tx_rate) { - if (!all_malvfs || !report_malvf) + struct ice_pf *pf = ice_netdev_to_pf(netdev); + struct ice_vsi *vsi; + struct device *dev; + struct ice_vf *vf; + int ret; + + dev = ice_pf_to_dev(pf); + + vf = ice_get_vf_by_id(pf, vf_id); + if (!vf) return -EINVAL; - *report_malvf = false; + ret = ice_check_vf_ready_for_cfg(vf); + if (ret) + goto out_put_vf; + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + ret = -EINVAL; + goto out_put_vf; + } + + if (min_tx_rate && ice_is_dcb_active(pf)) { + dev_err(dev, "DCB on PF is currently enabled. VF min Tx rate limiting not allowed on this PF.\n"); + ret = -EOPNOTSUPP; + goto out_put_vf; + } + + if (ice_min_tx_rate_oversubscribed(vf, min_tx_rate)) { + ret = -EINVAL; + goto out_put_vf; + } + + if (vf->min_tx_rate != (unsigned int)min_tx_rate) { + ret = ice_set_min_bw_limit(vsi, (u64)min_tx_rate * 1000); + if (ret) { + dev_err(dev, "Unable to set min-tx-rate for VF %d\n", + vf->vf_id); + goto out_put_vf; + } + + vf->min_tx_rate = min_tx_rate; + } + + if (vf->max_tx_rate != (unsigned int)max_tx_rate) { + ret = ice_set_max_bw_limit(vsi, (u64)max_tx_rate * 1000); + if (ret) { + dev_err(dev, "Unable to set max-tx-rate for VF %d\n", + vf->vf_id); + goto out_put_vf; + } + + vf->max_tx_rate = max_tx_rate; + } + +out_put_vf: + ice_put_vf(vf); + return ret; +} + +/** + * ice_get_vf_stats - populate some stats for the VF + * @netdev: the netdev of the PF + * @vf_id: the host OS identifier (0-255) + * @vf_stats: pointer to the OS memory to be initialized + */ +int ice_get_vf_stats(struct net_device *netdev, int vf_id, + struct ifla_vf_stats *vf_stats) +{ + struct ice_pf *pf = ice_netdev_to_pf(netdev); + struct ice_eth_stats *stats; + struct ice_vsi *vsi; + struct ice_vf *vf; + int ret; - if (bitmap_len < hw->mbx_snapshot.mbx_vf.vfcntr_len) + vf = ice_get_vf_by_id(pf, vf_id); + if (!vf) return -EINVAL; - if (vf_id >= bitmap_len) - return -EIO; + ret = ice_check_vf_ready_for_cfg(vf); + if (ret) + goto out_put_vf; - /* If the vf_id is found in the bitmap set bit and boolean to true */ - if (!test_and_set_bit(vf_id, all_malvfs)) - *report_malvf = true; + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + ret = -EINVAL; + goto out_put_vf; + } - return 0; + ice_update_eth_stats(vsi); + stats = &vsi->eth_stats; + + memset(vf_stats, 0, sizeof(*vf_stats)); + + vf_stats->rx_packets = stats->rx_unicast + stats->rx_broadcast + + stats->rx_multicast; + vf_stats->tx_packets = stats->tx_unicast + stats->tx_broadcast + + stats->tx_multicast; + vf_stats->rx_bytes = stats->rx_bytes; + vf_stats->tx_bytes = stats->tx_bytes; + vf_stats->broadcast = stats->rx_broadcast; + vf_stats->multicast = stats->rx_multicast; + vf_stats->rx_dropped = stats->rx_discards; + vf_stats->tx_dropped = stats->tx_discards; + +out_put_vf: + ice_put_vf(vf); + return ret; +} + +/** + * ice_is_supported_port_vlan_proto - make sure the vlan_proto is supported + * @hw: hardware structure used to check the VLAN mode + * @vlan_proto: VLAN TPID being checked + * + * If the device is configured in Double VLAN Mode (DVM), then both ETH_P_8021Q + * and ETH_P_8021AD are supported. If the device is configured in Single VLAN + * Mode (SVM), then only ETH_P_8021Q is supported. + */ +static bool +ice_is_supported_port_vlan_proto(struct ice_hw *hw, u16 vlan_proto) +{ + bool is_supported = false; + + switch (vlan_proto) { + case ETH_P_8021Q: + is_supported = true; + break; + case ETH_P_8021AD: + if (ice_is_dvm_ena(hw)) + is_supported = true; + break; + } + + return is_supported; } /** - * ice_mbx_clear_malvf - Clear VF bitmap and counter for VF ID - * @snap: pointer to the mailbox snapshot structure - * @all_malvfs: all malicious VFs tracked by PF - * @bitmap_len: length of bitmap in bits - * @vf_id: relative virtual function ID of the malicious VF + * ice_set_vf_port_vlan + * @netdev: network interface device structure + * @vf_id: VF identifier + * @vlan_id: VLAN ID being set + * @qos: priority setting + * @vlan_proto: VLAN protocol * - * In case of a VF reset, this function can be called to clear - * the bit corresponding to the VF ID in the bitmap tracking all - * malicious VFs attached to the PF. The function also clears the - * VF counter array at the index of the VF ID. This is to ensure - * that the new VF loaded is not considered malicious before going - * through the overflow detection algorithm. + * program VF Port VLAN ID and/or QoS */ int -ice_mbx_clear_malvf(struct ice_mbx_snapshot *snap, unsigned long *all_malvfs, - u16 bitmap_len, u16 vf_id) +ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, + __be16 vlan_proto) { - if (!snap || !all_malvfs) + struct ice_pf *pf = ice_netdev_to_pf(netdev); + u16 local_vlan_proto = ntohs(vlan_proto); + struct device *dev; + struct ice_vf *vf; + int ret; + + dev = ice_pf_to_dev(pf); + + if (vlan_id >= VLAN_N_VID || qos > 7) { + dev_err(dev, "Invalid Port VLAN parameters for VF %d, ID %d, QoS %d\n", + vf_id, vlan_id, qos); return -EINVAL; + } - if (bitmap_len < snap->mbx_vf.vfcntr_len) + if (!ice_is_supported_port_vlan_proto(&pf->hw, local_vlan_proto)) { + dev_err(dev, "VF VLAN protocol 0x%04x is not supported\n", + local_vlan_proto); + return -EPROTONOSUPPORT; + } + + vf = ice_get_vf_by_id(pf, vf_id); + if (!vf) return -EINVAL; - /* Ensure VF ID value is not larger than bitmap or VF counter length */ - if (vf_id >= bitmap_len || vf_id >= snap->mbx_vf.vfcntr_len) - return -EIO; + ret = ice_check_vf_ready_for_cfg(vf); + if (ret) + goto out_put_vf; - /* Clear VF ID bit in the bitmap tracking malicious VFs attached to PF */ - clear_bit(vf_id, all_malvfs); + if (ice_vf_get_port_vlan_prio(vf) == qos && + ice_vf_get_port_vlan_tpid(vf) == local_vlan_proto && + ice_vf_get_port_vlan_id(vf) == vlan_id) { + /* duplicate request, so just return success */ + dev_dbg(dev, "Duplicate port VLAN %u, QoS %u, TPID 0x%04x request\n", + vlan_id, qos, local_vlan_proto); + ret = 0; + goto out_put_vf; + } - /* Clear the VF counter in the mailbox snapshot structure for that VF ID. - * This is to ensure that if a VF is unloaded and a new one brought back - * up with the same VF ID for a snapshot currently in traversal or detect - * state the counter for that VF ID does not increment on top of existing - * values in the mailbox overflow detection algorithm. - */ - snap->mbx_vf.vf_cntr[vf_id] = 0; + mutex_lock(&vf->cfg_lock); - return 0; + vf->port_vlan_info = ICE_VLAN(local_vlan_proto, vlan_id, qos); + if (ice_vf_is_port_vlan_ena(vf)) + dev_info(dev, "Setting VLAN %u, QoS %u, TPID 0x%04x on VF %d\n", + vlan_id, qos, local_vlan_proto, vf_id); + else + dev_info(dev, "Clearing port VLAN on VF %d\n", vf_id); + + ice_reset_vf(vf, ICE_VF_RESET_NOTIFY); + mutex_unlock(&vf->cfg_lock); + +out_put_vf: + ice_put_vf(vf); + return ret; } /** - * ice_mbx_init_snapshot - Initialize mailbox snapshot structure - * @hw: pointer to the hardware structure - * @vf_count: number of VFs allocated on a PF - * - * Clear the mailbox snapshot structure and allocate memory - * for the VF counter array based on the number of VFs allocated - * on that PF. + * ice_print_vf_rx_mdd_event - print VF Rx malicious driver detect event + * @vf: pointer to the VF structure + */ +void ice_print_vf_rx_mdd_event(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + struct device *dev; + + dev = ice_pf_to_dev(pf); + + dev_info(dev, "%d Rx Malicious Driver Detection events detected on PF %d VF %d MAC %pM. mdd-auto-reset-vfs=%s\n", + vf->mdd_rx_events.count, pf->hw.pf_id, vf->vf_id, + vf->dev_lan_addr.addr, + test_bit(ICE_FLAG_MDD_AUTO_RESET_VF, pf->flags) + ? "on" : "off"); +} + +/** + * ice_print_vfs_mdd_events - print VFs malicious driver detect event + * @pf: pointer to the PF structure * - * Assumption: This function will assume ice_get_caps() has already been - * called to ensure that the vf_count can be compared against the number - * of VFs supported as defined in the functional capabilities of the device. + * Called from ice_handle_mdd_event to rate limit and print VFs MDD events. */ -int ice_mbx_init_snapshot(struct ice_hw *hw, u16 vf_count) +void ice_print_vfs_mdd_events(struct ice_pf *pf) { - struct ice_mbx_snapshot *snap = &hw->mbx_snapshot; + struct device *dev = ice_pf_to_dev(pf); + struct ice_hw *hw = &pf->hw; + struct ice_vf *vf; + unsigned int bkt; - /* Ensure that the number of VFs allocated is non-zero and - * is not greater than the number of supported VFs defined in - * the functional capabilities of the PF. - */ - if (!vf_count || vf_count > hw->func_caps.num_allocd_vfs) - return -EINVAL; + /* check that there are pending MDD events to print */ + if (!test_and_clear_bit(ICE_MDD_VF_PRINT_PENDING, pf->state)) + return; - snap->mbx_vf.vf_cntr = devm_kcalloc(ice_hw_to_dev(hw), vf_count, - sizeof(*snap->mbx_vf.vf_cntr), - GFP_KERNEL); - if (!snap->mbx_vf.vf_cntr) - return -ENOMEM; + /* VF MDD event logs are rate limited to one second intervals */ + if (time_is_after_jiffies(pf->vfs.last_printed_mdd_jiffies + HZ * 1)) + return; - /* Setting the VF counter length to the number of allocated - * VFs for given PF's functional capabilities. - */ - snap->mbx_vf.vfcntr_len = vf_count; + pf->vfs.last_printed_mdd_jiffies = jiffies; - /* Clear mbx_buf in the mailbox snaphot structure and setting the - * mailbox snapshot state to a new capture. - */ - memset(&snap->mbx_buf, 0, sizeof(snap->mbx_buf)); - snap->mbx_buf.state = ICE_MAL_VF_DETECT_STATE_NEW_SNAPSHOT; + mutex_lock(&pf->vfs.table_lock); + ice_for_each_vf(pf, bkt, vf) { + /* only print Rx MDD event message if there are new events */ + if (vf->mdd_rx_events.count != vf->mdd_rx_events.last_printed) { + vf->mdd_rx_events.last_printed = + vf->mdd_rx_events.count; + ice_print_vf_rx_mdd_event(vf); + } - return 0; + /* only print Tx MDD event message if there are new events */ + if (vf->mdd_tx_events.count != vf->mdd_tx_events.last_printed) { + vf->mdd_tx_events.last_printed = + vf->mdd_tx_events.count; + + dev_info(dev, "%d Tx Malicious Driver Detection events detected on PF %d VF %d MAC %pM.\n", + vf->mdd_tx_events.count, hw->pf_id, vf->vf_id, + vf->dev_lan_addr.addr); + } + } + mutex_unlock(&pf->vfs.table_lock); } /** - * ice_mbx_deinit_snapshot - Free mailbox snapshot structure - * @hw: pointer to the hardware structure + * ice_restore_all_vfs_msi_state - restore VF MSI state after PF FLR + * @pdev: pointer to a pci_dev structure * - * Clear the mailbox snapshot structure and free the VF counter array. + * Called when recovering from a PF FLR to restore interrupt capability to + * the VFs. */ -void ice_mbx_deinit_snapshot(struct ice_hw *hw) +void ice_restore_all_vfs_msi_state(struct pci_dev *pdev) { - struct ice_mbx_snapshot *snap = &hw->mbx_snapshot; + u16 vf_id; + int pos; - /* Free VF counter array and reset VF counter length */ - devm_kfree(ice_hw_to_dev(hw), snap->mbx_vf.vf_cntr); - snap->mbx_vf.vfcntr_len = 0; + if (!pci_num_vf(pdev)) + return; + + 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_is_malicious_vf - helper function to detect a malicious VF + * @pf: ptr to struct ice_pf + * @event: pointer to the AQ event + * @num_msg_proc: the number of messages processed so far + * @num_msg_pending: the number of messages peinding in admin queue + */ +bool +ice_is_malicious_vf(struct ice_pf *pf, struct ice_rq_event_info *event, + u16 num_msg_proc, u16 num_msg_pending) +{ + s16 vf_id = le16_to_cpu(event->desc.retval); + struct device *dev = ice_pf_to_dev(pf); + struct ice_mbx_data mbxdata; + bool malvf = false; + struct ice_vf *vf; + int status; + + vf = ice_get_vf_by_id(pf, vf_id); + if (!vf) + return false; + + if (test_bit(ICE_VF_STATE_DIS, vf->vf_states)) + goto out_put_vf; + + mbxdata.num_msg_proc = num_msg_proc; + mbxdata.num_pending_arq = num_msg_pending; + mbxdata.max_num_msgs_mbx = pf->hw.mailboxq.num_rq_entries; +#define ICE_MBX_OVERFLOW_WATERMARK 64 + mbxdata.async_watermark_val = ICE_MBX_OVERFLOW_WATERMARK; + + /* check to see if we have a malicious VF */ + status = ice_mbx_vf_state_handler(&pf->hw, &mbxdata, vf_id, &malvf); + if (status) + goto out_put_vf; + + if (malvf) { + bool report_vf = false; + + /* if the VF is malicious and we haven't let the user + * know about it, then let them know now + */ + status = ice_mbx_report_malvf(&pf->hw, pf->vfs.malvfs, + ICE_MAX_SRIOV_VFS, vf_id, + &report_vf); + if (status) + dev_dbg(dev, "Error reporting malicious VF\n"); + + if (report_vf) { + struct ice_vsi *pf_vsi = ice_get_main_vsi(pf); + + if (pf_vsi) + dev_warn(dev, "VF MAC %pM on PF MAC %pM is generating asynchronous messages and may be overflowing the PF message queue. Please see the Adapter User Guide for more information\n", + &vf->dev_lan_addr.addr[0], + pf_vsi->netdev->dev_addr); + } + } - /* Clear mbx_buf in the mailbox snaphot structure */ - memset(&snap->mbx_buf, 0, sizeof(snap->mbx_buf)); +out_put_vf: + ice_put_vf(vf); + return malvf; } diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.h b/drivers/net/ethernet/intel/ice/ice_sriov.h index 68686a3fd7e8..955ab810a198 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.h +++ b/drivers/net/ethernet/intel/ice/ice_sriov.h @@ -3,50 +3,159 @@ #ifndef _ICE_SRIOV_H_ #define _ICE_SRIOV_H_ +#include "ice_virtchnl_fdir.h" +#include "ice_vf_lib.h" +#include "ice_virtchnl.h" -#include "ice_type.h" -#include "ice_controlq.h" +/* Static VF transaction/status register def */ +#define VF_DEVICE_STATUS 0xAA +#define VF_TRANS_PENDING_M 0x20 -/* Defining the mailbox message threshold as 63 asynchronous - * pending messages. Normal VF functionality does not require - * sending more than 63 asynchronous pending message. - */ -#define ICE_ASYNC_VF_MSG_THRESHOLD 63 +/* wait defines for polling PF_PCI_CIAD register status */ +#define ICE_PCI_CIAD_WAIT_COUNT 100 +#define ICE_PCI_CIAD_WAIT_DELAY_US 1 + +/* VF resource constraints */ +#define ICE_MIN_QS_PER_VF 1 +#define ICE_NONQ_VECS_VF 1 +#define ICE_NUM_VF_MSIX_MED 17 +#define ICE_NUM_VF_MSIX_SMALL 5 +#define ICE_NUM_VF_MSIX_MULTIQ_MIN 3 +#define ICE_MIN_INTR_PER_VF (ICE_MIN_QS_PER_VF + 1) +#define ICE_MAX_VF_RESET_TRIES 40 +#define ICE_MAX_VF_RESET_SLEEP_MS 20 #ifdef CONFIG_PCI_IOV +void ice_process_vflr_event(struct ice_pf *pf); +int ice_sriov_configure(struct pci_dev *pdev, int num_vfs); +int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac); int -ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval, - u8 *msg, u16 msglen, struct ice_sq_cd *cd); +ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi); + +void ice_free_vfs(struct ice_pf *pf); +void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event); +void ice_restore_all_vfs_msi_state(struct pci_dev *pdev); +bool +ice_is_malicious_vf(struct ice_pf *pf, struct ice_rq_event_info *event, + u16 num_msg_proc, u16 num_msg_pending); -u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed); int -ice_mbx_vf_state_handler(struct ice_hw *hw, struct ice_mbx_data *mbx_data, - u16 vf_id, bool *is_mal_vf); +ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, + __be16 vlan_proto); + int -ice_mbx_clear_malvf(struct ice_mbx_snapshot *snap, unsigned long *all_malvfs, - u16 bitmap_len, u16 vf_id); -int ice_mbx_init_snapshot(struct ice_hw *hw, u16 vf_count); -void ice_mbx_deinit_snapshot(struct ice_hw *hw); +ice_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, + int max_tx_rate); + +int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted); + +int ice_set_vf_link_state(struct net_device *netdev, int vf_id, int link_state); + +int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena); + +int ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector); + int -ice_mbx_report_malvf(struct ice_hw *hw, unsigned long *all_malvfs, - u16 bitmap_len, u16 vf_id, bool *report_malvf); +ice_get_vf_stats(struct net_device *netdev, int vf_id, + struct ifla_vf_stats *vf_stats); +void +ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event); +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); #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) { } +static inline +void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) { } +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 bool +ice_is_malicious_vf(struct ice_pf __always_unused *pf, + struct ice_rq_event_info __always_unused *event, + u16 __always_unused num_msg_proc, + u16 __always_unused num_msg_pending) +{ + return false; +} + static inline int -ice_aq_send_msg_to_vf(struct ice_hw __always_unused *hw, - u16 __always_unused vfid, u32 __always_unused v_opcode, - u32 __always_unused v_retval, u8 __always_unused *msg, - u16 __always_unused msglen, - struct ice_sq_cd __always_unused *cd) +ice_sriov_configure(struct pci_dev __always_unused *pdev, + int __always_unused num_vfs) { - return 0; + return -EOPNOTSUPP; +} + +static inline int +ice_set_vf_mac(struct net_device __always_unused *netdev, + int __always_unused vf_id, u8 __always_unused *mac) +{ + return -EOPNOTSUPP; } -static inline u32 -ice_conv_link_speed_to_virtchnl(bool __always_unused adv_link_support, - u16 __always_unused link_speed) +static inline int +ice_get_vf_cfg(struct net_device __always_unused *netdev, + int __always_unused vf_id, + struct ifla_vf_info __always_unused *ivi) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_set_vf_trust(struct net_device __always_unused *netdev, + int __always_unused vf_id, bool __always_unused trusted) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_set_vf_port_vlan(struct net_device __always_unused *netdev, + int __always_unused vf_id, u16 __always_unused vid, + u8 __always_unused qos, __be16 __always_unused v_proto) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_set_vf_spoofchk(struct net_device __always_unused *netdev, + int __always_unused vf_id, bool __always_unused ena) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_set_vf_link_state(struct net_device __always_unused *netdev, + int __always_unused vf_id, int __always_unused link_state) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_set_vf_bw(struct net_device __always_unused *netdev, + int __always_unused vf_id, int __always_unused min_tx_rate, + int __always_unused max_tx_rate) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_calc_vf_reg_idx(struct ice_vf __always_unused *vf, + struct ice_q_vector __always_unused *q_vector) { return 0; } +static inline int +ice_get_vf_stats(struct net_device __always_unused *netdev, + int __always_unused vf_id, + struct ifla_vf_stats __always_unused *vf_stats) +{ + 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 11ae0bee3590..9b762f7972ce 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -30,23 +30,80 @@ 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}; +enum { + ICE_PKT_OUTER_IPV6 = BIT(0), + ICE_PKT_TUN_GTPC = BIT(1), + ICE_PKT_TUN_GTPU = BIT(2), + ICE_PKT_TUN_NVGRE = BIT(3), + ICE_PKT_TUN_UDP = BIT(4), + ICE_PKT_INNER_IPV6 = BIT(5), + ICE_PKT_INNER_TCP = BIT(6), + ICE_PKT_INNER_UDP = BIT(7), + ICE_PKT_GTP_NOPAY = BIT(8), + ICE_PKT_KMALLOC = BIT(9), + ICE_PKT_PPPOE = BIT(10), + ICE_PKT_L2TPV3 = BIT(11), +}; + struct ice_dummy_pkt_offsets { enum ice_protocol_type type; u16 offset; /* ICE_PROTOCOL_LAST indicates end of list */ }; -static const struct ice_dummy_pkt_offsets dummy_gre_tcp_packet_offsets[] = { +struct ice_dummy_pkt_profile { + const struct ice_dummy_pkt_offsets *offsets; + const u8 *pkt; + u32 match; + u16 pkt_len; + u16 offsets_len; +}; + +#define ICE_DECLARE_PKT_OFFSETS(type) \ + static const struct ice_dummy_pkt_offsets \ + ice_dummy_##type##_packet_offsets[] + +#define ICE_DECLARE_PKT_TEMPLATE(type) \ + static const u8 ice_dummy_##type##_packet[] + +#define ICE_PKT_PROFILE(type, m) { \ + .match = (m), \ + .pkt = ice_dummy_##type##_packet, \ + .pkt_len = sizeof(ice_dummy_##type##_packet), \ + .offsets = ice_dummy_##type##_packet_offsets, \ + .offsets_len = sizeof(ice_dummy_##type##_packet_offsets), \ +} + +ICE_DECLARE_PKT_OFFSETS(vlan) = { + { ICE_VLAN_OFOS, 12 }, +}; + +ICE_DECLARE_PKT_TEMPLATE(vlan) = { + 0x81, 0x00, 0x00, 0x00, /* ICE_VLAN_OFOS 12 */ +}; + +ICE_DECLARE_PKT_OFFSETS(qinq) = { + { ICE_VLAN_EX, 12 }, + { ICE_VLAN_IN, 16 }, +}; + +ICE_DECLARE_PKT_TEMPLATE(qinq) = { + 0x91, 0x00, 0x00, 0x00, /* ICE_VLAN_EX 12 */ + 0x81, 0x00, 0x00, 0x00, /* ICE_VLAN_IN 16 */ +}; + +ICE_DECLARE_PKT_OFFSETS(gre_tcp) = { { ICE_MAC_OFOS, 0 }, { ICE_ETYPE_OL, 12 }, { ICE_IPV4_OFOS, 14 }, { ICE_NVGRE, 34 }, { ICE_MAC_IL, 42 }, + { ICE_ETYPE_IL, 54 }, { ICE_IPV4_IL, 56 }, { ICE_TCP_IL, 76 }, { ICE_PROTOCOL_LAST, 0 }, }; -static const u8 dummy_gre_tcp_packet[] = { +ICE_DECLARE_PKT_TEMPLATE(gre_tcp) = { 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, @@ -65,7 +122,8 @@ static const u8 dummy_gre_tcp_packet[] = { 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_IL 42 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, - 0x08, 0x00, + + 0x08, 0x00, /* ICE_ETYPE_IL 54 */ 0x45, 0x00, 0x00, 0x14, /* ICE_IPV4_IL 56 */ 0x00, 0x00, 0x00, 0x00, @@ -80,18 +138,19 @@ static const u8 dummy_gre_tcp_packet[] = { 0x00, 0x00, 0x00, 0x00 }; -static const struct ice_dummy_pkt_offsets dummy_gre_udp_packet_offsets[] = { +ICE_DECLARE_PKT_OFFSETS(gre_udp) = { { ICE_MAC_OFOS, 0 }, { ICE_ETYPE_OL, 12 }, { ICE_IPV4_OFOS, 14 }, { ICE_NVGRE, 34 }, { ICE_MAC_IL, 42 }, + { ICE_ETYPE_IL, 54 }, { ICE_IPV4_IL, 56 }, { ICE_UDP_ILOS, 76 }, { ICE_PROTOCOL_LAST, 0 }, }; -static const u8 dummy_gre_udp_packet[] = { +ICE_DECLARE_PKT_TEMPLATE(gre_udp) = { 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, @@ -110,7 +169,8 @@ static const u8 dummy_gre_udp_packet[] = { 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_IL 42 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, - 0x08, 0x00, + + 0x08, 0x00, /* ICE_ETYPE_IL 54 */ 0x45, 0x00, 0x00, 0x14, /* ICE_IPV4_IL 56 */ 0x00, 0x00, 0x00, 0x00, @@ -122,7 +182,7 @@ static const u8 dummy_gre_udp_packet[] = { 0x00, 0x08, 0x00, 0x00, }; -static const struct ice_dummy_pkt_offsets dummy_udp_tun_tcp_packet_offsets[] = { +ICE_DECLARE_PKT_OFFSETS(udp_tun_tcp) = { { ICE_MAC_OFOS, 0 }, { ICE_ETYPE_OL, 12 }, { ICE_IPV4_OFOS, 14 }, @@ -131,12 +191,13 @@ static const struct ice_dummy_pkt_offsets dummy_udp_tun_tcp_packet_offsets[] = { { ICE_GENEVE, 42 }, { ICE_VXLAN_GPE, 42 }, { ICE_MAC_IL, 50 }, + { ICE_ETYPE_IL, 62 }, { ICE_IPV4_IL, 64 }, { ICE_TCP_IL, 84 }, { ICE_PROTOCOL_LAST, 0 }, }; -static const u8 dummy_udp_tun_tcp_packet[] = { +ICE_DECLARE_PKT_TEMPLATE(udp_tun_tcp) = { 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, @@ -158,7 +219,8 @@ static const u8 dummy_udp_tun_tcp_packet[] = { 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_IL 50 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, - 0x08, 0x00, + + 0x08, 0x00, /* ICE_ETYPE_IL 62 */ 0x45, 0x00, 0x00, 0x28, /* ICE_IPV4_IL 64 */ 0x00, 0x01, 0x00, 0x00, @@ -173,7 +235,7 @@ static const u8 dummy_udp_tun_tcp_packet[] = { 0x00, 0x00, 0x00, 0x00 }; -static const struct ice_dummy_pkt_offsets dummy_udp_tun_udp_packet_offsets[] = { +ICE_DECLARE_PKT_OFFSETS(udp_tun_udp) = { { ICE_MAC_OFOS, 0 }, { ICE_ETYPE_OL, 12 }, { ICE_IPV4_OFOS, 14 }, @@ -182,12 +244,13 @@ static const struct ice_dummy_pkt_offsets dummy_udp_tun_udp_packet_offsets[] = { { ICE_GENEVE, 42 }, { ICE_VXLAN_GPE, 42 }, { ICE_MAC_IL, 50 }, + { ICE_ETYPE_IL, 62 }, { ICE_IPV4_IL, 64 }, { ICE_UDP_ILOS, 84 }, { ICE_PROTOCOL_LAST, 0 }, }; -static const u8 dummy_udp_tun_udp_packet[] = { +ICE_DECLARE_PKT_TEMPLATE(udp_tun_udp) = { 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, @@ -209,7 +272,8 @@ static const u8 dummy_udp_tun_udp_packet[] = { 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_IL 50 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, - 0x08, 0x00, + + 0x08, 0x00, /* ICE_ETYPE_IL 62 */ 0x45, 0x00, 0x00, 0x1c, /* ICE_IPV4_IL 64 */ 0x00, 0x01, 0x00, 0x00, @@ -221,69 +285,251 @@ static const u8 dummy_udp_tun_udp_packet[] = { 0x00, 0x08, 0x00, 0x00, }; -/* offset info for MAC + IPv4 + UDP dummy packet */ -static const struct ice_dummy_pkt_offsets dummy_udp_packet_offsets[] = { +ICE_DECLARE_PKT_OFFSETS(gre_ipv6_tcp) = { { ICE_MAC_OFOS, 0 }, { ICE_ETYPE_OL, 12 }, { ICE_IPV4_OFOS, 14 }, - { ICE_UDP_ILOS, 34 }, + { ICE_NVGRE, 34 }, + { ICE_MAC_IL, 42 }, + { ICE_ETYPE_IL, 54 }, + { ICE_IPV6_IL, 56 }, + { ICE_TCP_IL, 96 }, { ICE_PROTOCOL_LAST, 0 }, }; -/* Dummy packet for MAC + IPv4 + UDP */ -static const u8 dummy_udp_packet[] = { +ICE_DECLARE_PKT_TEMPLATE(gre_ipv6_tcp) = { 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x08, 0x00, /* ICE_ETYPE_OL 12 */ - 0x45, 0x00, 0x00, 0x1c, /* ICE_IPV4_OFOS 14 */ + 0x45, 0x00, 0x00, 0x66, /* ICE_IPV4_OFOS 14 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x2F, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x80, 0x00, 0x65, 0x58, /* ICE_NVGRE 34 */ + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_IL 42 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x86, 0xdd, /* ICE_ETYPE_IL 54 */ + + 0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_IL 56 */ + 0x00, 0x08, 0x06, 0x40, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_TCP_IL 96 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x50, 0x02, 0x20, 0x00, + 0x00, 0x00, 0x00, 0x00 +}; + +ICE_DECLARE_PKT_OFFSETS(gre_ipv6_udp) = { + { ICE_MAC_OFOS, 0 }, + { ICE_ETYPE_OL, 12 }, + { ICE_IPV4_OFOS, 14 }, + { ICE_NVGRE, 34 }, + { ICE_MAC_IL, 42 }, + { ICE_ETYPE_IL, 54 }, + { ICE_IPV6_IL, 56 }, + { ICE_UDP_ILOS, 96 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +ICE_DECLARE_PKT_TEMPLATE(gre_ipv6_udp) = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x08, 0x00, /* ICE_ETYPE_OL 12 */ + + 0x45, 0x00, 0x00, 0x5a, /* ICE_IPV4_OFOS 14 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x2F, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x80, 0x00, 0x65, 0x58, /* ICE_NVGRE 34 */ + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_IL 42 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x86, 0xdd, /* ICE_ETYPE_IL 54 */ + + 0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_IL 56 */ + 0x00, 0x08, 0x11, 0x40, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_UDP_ILOS 96 */ + 0x00, 0x08, 0x00, 0x00, +}; + +ICE_DECLARE_PKT_OFFSETS(udp_tun_ipv6_tcp) = { + { ICE_MAC_OFOS, 0 }, + { ICE_ETYPE_OL, 12 }, + { ICE_IPV4_OFOS, 14 }, + { ICE_UDP_OF, 34 }, + { ICE_VXLAN, 42 }, + { ICE_GENEVE, 42 }, + { ICE_VXLAN_GPE, 42 }, + { ICE_MAC_IL, 50 }, + { ICE_ETYPE_IL, 62 }, + { ICE_IPV6_IL, 64 }, + { ICE_TCP_IL, 104 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +ICE_DECLARE_PKT_TEMPLATE(udp_tun_ipv6_tcp) = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x08, 0x00, /* ICE_ETYPE_OL 12 */ + + 0x45, 0x00, 0x00, 0x6e, /* ICE_IPV4_OFOS 14 */ + 0x00, 0x01, 0x00, 0x00, + 0x40, 0x11, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x12, 0xb5, /* ICE_UDP_OF 34 */ + 0x00, 0x5a, 0x00, 0x00, + + 0x00, 0x00, 0x65, 0x58, /* ICE_VXLAN 42 */ + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_IL 50 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x86, 0xdd, /* ICE_ETYPE_IL 62 */ + + 0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_IL 64 */ + 0x00, 0x08, 0x06, 0x40, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_TCP_IL 104 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x50, 0x02, 0x20, 0x00, + 0x00, 0x00, 0x00, 0x00 +}; + +ICE_DECLARE_PKT_OFFSETS(udp_tun_ipv6_udp) = { + { ICE_MAC_OFOS, 0 }, + { ICE_ETYPE_OL, 12 }, + { ICE_IPV4_OFOS, 14 }, + { ICE_UDP_OF, 34 }, + { ICE_VXLAN, 42 }, + { ICE_GENEVE, 42 }, + { ICE_VXLAN_GPE, 42 }, + { ICE_MAC_IL, 50 }, + { ICE_ETYPE_IL, 62 }, + { ICE_IPV6_IL, 64 }, + { ICE_UDP_ILOS, 104 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +ICE_DECLARE_PKT_TEMPLATE(udp_tun_ipv6_udp) = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x08, 0x00, /* ICE_ETYPE_OL 12 */ + + 0x45, 0x00, 0x00, 0x62, /* ICE_IPV4_OFOS 14 */ 0x00, 0x01, 0x00, 0x00, 0x00, 0x11, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, - 0x00, 0x00, 0x00, 0x00, /* ICE_UDP_ILOS 34 */ - 0x00, 0x08, 0x00, 0x00, + 0x00, 0x00, 0x12, 0xb5, /* ICE_UDP_OF 34 */ + 0x00, 0x4e, 0x00, 0x00, - 0x00, 0x00, /* 2 bytes for 4 byte alignment */ + 0x00, 0x00, 0x65, 0x58, /* ICE_VXLAN 42 */ + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_IL 50 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x86, 0xdd, /* ICE_ETYPE_IL 62 */ + + 0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_IL 64 */ + 0x00, 0x08, 0x11, 0x40, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_UDP_ILOS 104 */ + 0x00, 0x08, 0x00, 0x00, }; -/* offset info for MAC + VLAN + IPv4 + UDP dummy packet */ -static const struct ice_dummy_pkt_offsets dummy_vlan_udp_packet_offsets[] = { +/* offset info for MAC + IPv4 + UDP dummy packet */ +ICE_DECLARE_PKT_OFFSETS(udp) = { { ICE_MAC_OFOS, 0 }, - { ICE_VLAN_OFOS, 12 }, - { ICE_ETYPE_OL, 16 }, - { ICE_IPV4_OFOS, 18 }, - { ICE_UDP_ILOS, 38 }, + { ICE_ETYPE_OL, 12 }, + { ICE_IPV4_OFOS, 14 }, + { ICE_UDP_ILOS, 34 }, { ICE_PROTOCOL_LAST, 0 }, }; -/* C-tag (801.1Q), IPv4:UDP dummy packet */ -static const u8 dummy_vlan_udp_packet[] = { +/* Dummy packet for MAC + IPv4 + UDP */ +ICE_DECLARE_PKT_TEMPLATE(udp) = { 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, - 0x81, 0x00, 0x00, 0x00, /* ICE_VLAN_OFOS 12 */ - - 0x08, 0x00, /* ICE_ETYPE_OL 16 */ + 0x08, 0x00, /* ICE_ETYPE_OL 12 */ - 0x45, 0x00, 0x00, 0x1c, /* ICE_IPV4_OFOS 18 */ + 0x45, 0x00, 0x00, 0x1c, /* ICE_IPV4_OFOS 14 */ 0x00, 0x01, 0x00, 0x00, 0x00, 0x11, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, - 0x00, 0x00, 0x00, 0x00, /* ICE_UDP_ILOS 38 */ + 0x00, 0x00, 0x00, 0x00, /* ICE_UDP_ILOS 34 */ 0x00, 0x08, 0x00, 0x00, 0x00, 0x00, /* 2 bytes for 4 byte alignment */ }; /* offset info for MAC + IPv4 + TCP dummy packet */ -static const struct ice_dummy_pkt_offsets dummy_tcp_packet_offsets[] = { +ICE_DECLARE_PKT_OFFSETS(tcp) = { { ICE_MAC_OFOS, 0 }, { ICE_ETYPE_OL, 12 }, { ICE_IPV4_OFOS, 14 }, @@ -292,7 +538,7 @@ static const struct ice_dummy_pkt_offsets dummy_tcp_packet_offsets[] = { }; /* Dummy packet for MAC + IPv4 + TCP */ -static const u8 dummy_tcp_packet[] = { +ICE_DECLARE_PKT_TEMPLATE(tcp) = { 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, @@ -314,50 +560,52 @@ static const u8 dummy_tcp_packet[] = { 0x00, 0x00, /* 2 bytes for 4 byte alignment */ }; -/* offset info for MAC + VLAN (C-tag, 802.1Q) + IPv4 + TCP dummy packet */ -static const struct ice_dummy_pkt_offsets dummy_vlan_tcp_packet_offsets[] = { +ICE_DECLARE_PKT_OFFSETS(tcp_ipv6) = { { ICE_MAC_OFOS, 0 }, - { ICE_VLAN_OFOS, 12 }, - { ICE_ETYPE_OL, 16 }, - { ICE_IPV4_OFOS, 18 }, - { ICE_TCP_IL, 38 }, + { ICE_ETYPE_OL, 12 }, + { ICE_IPV6_OFOS, 14 }, + { ICE_TCP_IL, 54 }, { ICE_PROTOCOL_LAST, 0 }, }; -/* C-tag (801.1Q), IPv4:TCP dummy packet */ -static const u8 dummy_vlan_tcp_packet[] = { +ICE_DECLARE_PKT_TEMPLATE(tcp_ipv6) = { 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, - 0x81, 0x00, 0x00, 0x00, /* ICE_VLAN_OFOS 12 */ - - 0x08, 0x00, /* ICE_ETYPE_OL 16 */ + 0x86, 0xDD, /* ICE_ETYPE_OL 12 */ - 0x45, 0x00, 0x00, 0x28, /* ICE_IPV4_OFOS 18 */ - 0x00, 0x01, 0x00, 0x00, - 0x00, 0x06, 0x00, 0x00, + 0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_OFOS 40 */ + 0x00, 0x14, 0x06, 0x00, /* Next header is TCP */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, - 0x00, 0x00, 0x00, 0x00, /* ICE_TCP_IL 38 */ + 0x00, 0x00, 0x00, 0x00, /* ICE_TCP_IL 54 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x50, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, - 0x00, 0x00, /* 2 bytes for 4 byte alignment */ + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ }; -static const struct ice_dummy_pkt_offsets dummy_tcp_ipv6_packet_offsets[] = { +/* IPv6 + UDP */ +ICE_DECLARE_PKT_OFFSETS(udp_ipv6) = { { ICE_MAC_OFOS, 0 }, { ICE_ETYPE_OL, 12 }, { ICE_IPV6_OFOS, 14 }, - { ICE_TCP_IL, 54 }, + { ICE_UDP_ILOS, 54 }, { ICE_PROTOCOL_LAST, 0 }, }; -static const u8 dummy_tcp_ipv6_packet[] = { +/* IPv6 + UDP dummy packet */ +ICE_DECLARE_PKT_TEMPLATE(udp_ipv6) = { 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, @@ -365,7 +613,7 @@ static const u8 dummy_tcp_ipv6_packet[] = { 0x86, 0xDD, /* ICE_ETYPE_OL 12 */ 0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_OFOS 40 */ - 0x00, 0x14, 0x06, 0x00, /* Next header is TCP */ + 0x00, 0x10, 0x11, 0x00, /* Next header UDP */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, @@ -375,7 +623,55 @@ static const u8 dummy_tcp_ipv6_packet[] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, - 0x00, 0x00, 0x00, 0x00, /* ICE_TCP_IL 54 */ + 0x00, 0x00, 0x00, 0x00, /* ICE_UDP_ILOS 54 */ + 0x00, 0x10, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* needed for ESP packets */ + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ +}; + +/* Outer IPv4 + Outer UDP + GTP + Inner IPv4 + Inner TCP */ +ICE_DECLARE_PKT_OFFSETS(ipv4_gtpu_ipv4_tcp) = { + { ICE_MAC_OFOS, 0 }, + { ICE_IPV4_OFOS, 14 }, + { ICE_UDP_OF, 34 }, + { ICE_GTP, 42 }, + { ICE_IPV4_IL, 62 }, + { ICE_TCP_IL, 82 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +ICE_DECLARE_PKT_TEMPLATE(ipv4_gtpu_ipv4_tcp) = { + 0x00, 0x00, 0x00, 0x00, /* Ethernet 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x08, 0x00, + + 0x45, 0x00, 0x00, 0x58, /* IP 14 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x11, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x08, 0x68, /* UDP 34 */ + 0x00, 0x44, 0x00, 0x00, + + 0x34, 0xff, 0x00, 0x34, /* ICE_GTP Header 42 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x85, + + 0x02, 0x00, 0x00, 0x00, /* GTP_PDUSession_ExtensionHeader 54 */ + 0x00, 0x00, 0x00, 0x00, + + 0x45, 0x00, 0x00, 0x28, /* IP 62 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x06, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* TCP 82 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x50, 0x00, 0x00, 0x00, @@ -384,39 +680,96 @@ static const u8 dummy_tcp_ipv6_packet[] = { 0x00, 0x00, /* 2 bytes for 4 byte alignment */ }; -/* C-tag (802.1Q): IPv6 + TCP */ -static const struct ice_dummy_pkt_offsets -dummy_vlan_tcp_ipv6_packet_offsets[] = { +/* Outer IPv4 + Outer UDP + GTP + Inner IPv4 + Inner UDP */ +ICE_DECLARE_PKT_OFFSETS(ipv4_gtpu_ipv4_udp) = { { ICE_MAC_OFOS, 0 }, - { ICE_VLAN_OFOS, 12 }, - { ICE_ETYPE_OL, 16 }, - { ICE_IPV6_OFOS, 18 }, - { ICE_TCP_IL, 58 }, + { ICE_IPV4_OFOS, 14 }, + { ICE_UDP_OF, 34 }, + { ICE_GTP, 42 }, + { ICE_IPV4_IL, 62 }, + { ICE_UDP_ILOS, 82 }, { ICE_PROTOCOL_LAST, 0 }, }; -/* C-tag (802.1Q), IPv6 + TCP dummy packet */ -static const u8 dummy_vlan_tcp_ipv6_packet[] = { - 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ +ICE_DECLARE_PKT_TEMPLATE(ipv4_gtpu_ipv4_udp) = { + 0x00, 0x00, 0x00, 0x00, /* Ethernet 0 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x08, 0x00, - 0x81, 0x00, 0x00, 0x00, /* ICE_VLAN_OFOS 12 */ + 0x45, 0x00, 0x00, 0x4c, /* IP 14 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x11, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, - 0x86, 0xDD, /* ICE_ETYPE_OL 16 */ + 0x00, 0x00, 0x08, 0x68, /* UDP 34 */ + 0x00, 0x38, 0x00, 0x00, - 0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_OFOS 18 */ - 0x00, 0x14, 0x06, 0x00, /* Next header is TCP */ + 0x34, 0xff, 0x00, 0x28, /* ICE_GTP Header 42 */ 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x85, + + 0x02, 0x00, 0x00, 0x00, /* GTP_PDUSession_ExtensionHeader 54 */ 0x00, 0x00, 0x00, 0x00, + + 0x45, 0x00, 0x00, 0x1c, /* IP 62 */ 0x00, 0x00, 0x00, 0x00, + 0x00, 0x11, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* UDP 82 */ + 0x00, 0x08, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ +}; + +/* Outer IPv6 + Outer UDP + GTP + Inner IPv4 + Inner TCP */ +ICE_DECLARE_PKT_OFFSETS(ipv4_gtpu_ipv6_tcp) = { + { ICE_MAC_OFOS, 0 }, + { ICE_IPV4_OFOS, 14 }, + { ICE_UDP_OF, 34 }, + { ICE_GTP, 42 }, + { ICE_IPV6_IL, 62 }, + { ICE_TCP_IL, 102 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +ICE_DECLARE_PKT_TEMPLATE(ipv4_gtpu_ipv6_tcp) = { + 0x00, 0x00, 0x00, 0x00, /* Ethernet 0 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x08, 0x00, + + 0x45, 0x00, 0x00, 0x6c, /* IP 14 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x11, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x08, 0x68, /* UDP 34 */ + 0x00, 0x58, 0x00, 0x00, + + 0x34, 0xff, 0x00, 0x48, /* ICE_GTP Header 42 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x85, - 0x00, 0x00, 0x00, 0x00, /* ICE_TCP_IL 58 */ + 0x02, 0x00, 0x00, 0x00, /* GTP_PDUSession_ExtensionHeader 54 */ + 0x00, 0x00, 0x00, 0x00, + + 0x60, 0x00, 0x00, 0x00, /* IPv6 62 */ + 0x00, 0x14, 0x06, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* TCP 102 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x50, 0x00, 0x00, 0x00, @@ -425,66 +778,231 @@ static const u8 dummy_vlan_tcp_ipv6_packet[] = { 0x00, 0x00, /* 2 bytes for 4 byte alignment */ }; -/* IPv6 + UDP */ -static const struct ice_dummy_pkt_offsets dummy_udp_ipv6_packet_offsets[] = { +ICE_DECLARE_PKT_OFFSETS(ipv4_gtpu_ipv6_udp) = { + { ICE_MAC_OFOS, 0 }, + { ICE_IPV4_OFOS, 14 }, + { ICE_UDP_OF, 34 }, + { ICE_GTP, 42 }, + { ICE_IPV6_IL, 62 }, + { ICE_UDP_ILOS, 102 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +ICE_DECLARE_PKT_TEMPLATE(ipv4_gtpu_ipv6_udp) = { + 0x00, 0x00, 0x00, 0x00, /* Ethernet 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x08, 0x00, + + 0x45, 0x00, 0x00, 0x60, /* IP 14 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x11, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x08, 0x68, /* UDP 34 */ + 0x00, 0x4c, 0x00, 0x00, + + 0x34, 0xff, 0x00, 0x3c, /* ICE_GTP Header 42 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x85, + + 0x02, 0x00, 0x00, 0x00, /* GTP_PDUSession_ExtensionHeader 54 */ + 0x00, 0x00, 0x00, 0x00, + + 0x60, 0x00, 0x00, 0x00, /* IPv6 62 */ + 0x00, 0x08, 0x11, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* UDP 102 */ + 0x00, 0x08, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ +}; + +ICE_DECLARE_PKT_OFFSETS(ipv6_gtpu_ipv4_tcp) = { { ICE_MAC_OFOS, 0 }, - { ICE_ETYPE_OL, 12 }, { ICE_IPV6_OFOS, 14 }, - { ICE_UDP_ILOS, 54 }, + { ICE_UDP_OF, 54 }, + { ICE_GTP, 62 }, + { ICE_IPV4_IL, 82 }, + { ICE_TCP_IL, 102 }, { ICE_PROTOCOL_LAST, 0 }, }; -/* IPv6 + UDP dummy packet */ -static const u8 dummy_udp_ipv6_packet[] = { - 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ +ICE_DECLARE_PKT_TEMPLATE(ipv6_gtpu_ipv4_tcp) = { + 0x00, 0x00, 0x00, 0x00, /* Ethernet 0 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x86, 0xdd, - 0x86, 0xDD, /* ICE_ETYPE_OL 12 */ + 0x60, 0x00, 0x00, 0x00, /* IPv6 14 */ + 0x00, 0x44, 0x11, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, - 0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_OFOS 40 */ - 0x00, 0x10, 0x11, 0x00, /* Next header UDP */ + 0x00, 0x00, 0x08, 0x68, /* UDP 54 */ + 0x00, 0x44, 0x00, 0x00, + + 0x34, 0xff, 0x00, 0x34, /* ICE_GTP Header 62 */ 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x85, + + 0x02, 0x00, 0x00, 0x00, /* GTP_PDUSession_ExtensionHeader 74 */ 0x00, 0x00, 0x00, 0x00, + + 0x45, 0x00, 0x00, 0x28, /* IP 82 */ 0x00, 0x00, 0x00, 0x00, + 0x00, 0x06, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* TCP 102 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x50, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, - 0x00, 0x00, 0x00, 0x00, /* ICE_UDP_ILOS 54 */ - 0x00, 0x10, 0x00, 0x00, + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ +}; - 0x00, 0x00, 0x00, 0x00, /* needed for ESP packets */ +ICE_DECLARE_PKT_OFFSETS(ipv6_gtpu_ipv4_udp) = { + { ICE_MAC_OFOS, 0 }, + { ICE_IPV6_OFOS, 14 }, + { ICE_UDP_OF, 54 }, + { ICE_GTP, 62 }, + { ICE_IPV4_IL, 82 }, + { ICE_UDP_ILOS, 102 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +ICE_DECLARE_PKT_TEMPLATE(ipv6_gtpu_ipv4_udp) = { + 0x00, 0x00, 0x00, 0x00, /* Ethernet 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x86, 0xdd, + + 0x60, 0x00, 0x00, 0x00, /* IPv6 14 */ + 0x00, 0x38, 0x11, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x08, 0x68, /* UDP 54 */ + 0x00, 0x38, 0x00, 0x00, + + 0x34, 0xff, 0x00, 0x28, /* ICE_GTP Header 62 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x85, + + 0x02, 0x00, 0x00, 0x00, /* GTP_PDUSession_ExtensionHeader 74 */ + 0x00, 0x00, 0x00, 0x00, + + 0x45, 0x00, 0x00, 0x1c, /* IP 82 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x11, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, /* UDP 102 */ + 0x00, 0x08, 0x00, 0x00, + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ }; -/* C-tag (802.1Q): IPv6 + UDP */ -static const struct ice_dummy_pkt_offsets -dummy_vlan_udp_ipv6_packet_offsets[] = { +ICE_DECLARE_PKT_OFFSETS(ipv6_gtpu_ipv6_tcp) = { { ICE_MAC_OFOS, 0 }, - { ICE_VLAN_OFOS, 12 }, - { ICE_ETYPE_OL, 16 }, - { ICE_IPV6_OFOS, 18 }, - { ICE_UDP_ILOS, 58 }, + { ICE_IPV6_OFOS, 14 }, + { ICE_UDP_OF, 54 }, + { ICE_GTP, 62 }, + { ICE_IPV6_IL, 82 }, + { ICE_TCP_IL, 122 }, { ICE_PROTOCOL_LAST, 0 }, }; -/* C-tag (802.1Q), IPv6 + UDP dummy packet */ -static const u8 dummy_vlan_udp_ipv6_packet[] = { - 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ +ICE_DECLARE_PKT_TEMPLATE(ipv6_gtpu_ipv6_tcp) = { + 0x00, 0x00, 0x00, 0x00, /* Ethernet 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x86, 0xdd, + + 0x60, 0x00, 0x00, 0x00, /* IPv6 14 */ + 0x00, 0x58, 0x11, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x08, 0x68, /* UDP 54 */ + 0x00, 0x58, 0x00, 0x00, + + 0x34, 0xff, 0x00, 0x48, /* ICE_GTP Header 62 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x85, + + 0x02, 0x00, 0x00, 0x00, /* GTP_PDUSession_ExtensionHeader 74 */ + 0x00, 0x00, 0x00, 0x00, + + 0x60, 0x00, 0x00, 0x00, /* IPv6 82 */ + 0x00, 0x14, 0x06, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* TCP 122 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x50, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, - 0x81, 0x00, 0x00, 0x00,/* ICE_VLAN_OFOS 12 */ + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ +}; - 0x86, 0xDD, /* ICE_ETYPE_OL 16 */ +ICE_DECLARE_PKT_OFFSETS(ipv6_gtpu_ipv6_udp) = { + { ICE_MAC_OFOS, 0 }, + { ICE_IPV6_OFOS, 14 }, + { ICE_UDP_OF, 54 }, + { ICE_GTP, 62 }, + { ICE_IPV6_IL, 82 }, + { ICE_UDP_ILOS, 122 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +ICE_DECLARE_PKT_TEMPLATE(ipv6_gtpu_ipv6_udp) = { + 0x00, 0x00, 0x00, 0x00, /* Ethernet 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x86, 0xdd, - 0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_OFOS 18 */ - 0x00, 0x08, 0x11, 0x00, /* Next header UDP */ + 0x60, 0x00, 0x00, 0x00, /* IPv6 14 */ + 0x00, 0x4c, 0x11, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, @@ -494,24 +1012,370 @@ static const u8 dummy_vlan_udp_ipv6_packet[] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, - 0x00, 0x00, 0x00, 0x00, /* ICE_UDP_ILOS 58 */ + 0x00, 0x00, 0x08, 0x68, /* UDP 54 */ + 0x00, 0x4c, 0x00, 0x00, + + 0x34, 0xff, 0x00, 0x3c, /* ICE_GTP Header 62 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x85, + + 0x02, 0x00, 0x00, 0x00, /* GTP_PDUSession_ExtensionHeader 74 */ + 0x00, 0x00, 0x00, 0x00, + + 0x60, 0x00, 0x00, 0x00, /* IPv6 82 */ + 0x00, 0x08, 0x11, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* UDP 122 */ 0x00, 0x08, 0x00, 0x00, 0x00, 0x00, /* 2 bytes for 4 byte alignment */ }; -#define ICE_SW_RULE_RX_TX_ETH_HDR_SIZE \ - (offsetof(struct ice_aqc_sw_rules_elem, pdata.lkup_tx_rx.hdr) + \ - (DUMMY_ETH_HDR_LEN * \ - sizeof(((struct ice_sw_rule_lkup_rx_tx *)0)->hdr[0]))) -#define ICE_SW_RULE_RX_TX_NO_HDR_SIZE \ - (offsetof(struct ice_aqc_sw_rules_elem, pdata.lkup_tx_rx.hdr)) -#define ICE_SW_RULE_LG_ACT_SIZE(n) \ - (offsetof(struct ice_aqc_sw_rules_elem, pdata.lg_act.act) + \ - ((n) * sizeof(((struct ice_sw_rule_lg_act *)0)->act[0]))) -#define ICE_SW_RULE_VSI_LIST_SIZE(n) \ - (offsetof(struct ice_aqc_sw_rules_elem, pdata.vsi_list.vsi) + \ - ((n) * sizeof(((struct ice_sw_rule_vsi_list *)0)->vsi[0]))) +ICE_DECLARE_PKT_OFFSETS(ipv4_gtpu_ipv4) = { + { ICE_MAC_OFOS, 0 }, + { ICE_IPV4_OFOS, 14 }, + { ICE_UDP_OF, 34 }, + { ICE_GTP_NO_PAY, 42 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +ICE_DECLARE_PKT_TEMPLATE(ipv4_gtpu_ipv4) = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x08, 0x00, + + 0x45, 0x00, 0x00, 0x44, /* ICE_IPV4_OFOS 14 */ + 0x00, 0x00, 0x40, 0x00, + 0x40, 0x11, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x08, 0x68, 0x08, 0x68, /* ICE_UDP_OF 34 */ + 0x00, 0x00, 0x00, 0x00, + + 0x34, 0xff, 0x00, 0x28, /* ICE_GTP 42 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x85, + + 0x02, 0x00, 0x00, 0x00, /* PDU Session extension header */ + 0x00, 0x00, 0x00, 0x00, + + 0x45, 0x00, 0x00, 0x14, /* ICE_IPV4_IL 62 */ + 0x00, 0x00, 0x40, 0x00, + 0x40, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, +}; + +ICE_DECLARE_PKT_OFFSETS(ipv6_gtp) = { + { ICE_MAC_OFOS, 0 }, + { ICE_IPV6_OFOS, 14 }, + { ICE_UDP_OF, 54 }, + { ICE_GTP_NO_PAY, 62 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +ICE_DECLARE_PKT_TEMPLATE(ipv6_gtp) = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x86, 0xdd, + + 0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_OFOS 14 */ + 0x00, 0x6c, 0x11, 0x00, /* Next header UDP*/ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x08, 0x68, 0x08, 0x68, /* ICE_UDP_OF 54 */ + 0x00, 0x00, 0x00, 0x00, + + 0x30, 0x00, 0x00, 0x28, /* ICE_GTP 62 */ + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, +}; + +ICE_DECLARE_PKT_OFFSETS(pppoe_ipv4_tcp) = { + { ICE_MAC_OFOS, 0 }, + { ICE_ETYPE_OL, 12 }, + { ICE_PPPOE, 14 }, + { ICE_IPV4_OFOS, 22 }, + { ICE_TCP_IL, 42 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +ICE_DECLARE_PKT_TEMPLATE(pppoe_ipv4_tcp) = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x88, 0x64, /* ICE_ETYPE_OL 12 */ + + 0x11, 0x00, 0x00, 0x00, /* ICE_PPPOE 14 */ + 0x00, 0x16, + + 0x00, 0x21, /* PPP Link Layer 20 */ + + 0x45, 0x00, 0x00, 0x28, /* ICE_IPV4_OFOS 22 */ + 0x00, 0x01, 0x00, 0x00, + 0x00, 0x06, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_TCP_IL 42 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x50, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 bytes alignment */ +}; + +ICE_DECLARE_PKT_OFFSETS(pppoe_ipv4_udp) = { + { ICE_MAC_OFOS, 0 }, + { ICE_ETYPE_OL, 12 }, + { ICE_PPPOE, 14 }, + { ICE_IPV4_OFOS, 22 }, + { ICE_UDP_ILOS, 42 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +ICE_DECLARE_PKT_TEMPLATE(pppoe_ipv4_udp) = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x88, 0x64, /* ICE_ETYPE_OL 12 */ + + 0x11, 0x00, 0x00, 0x00, /* ICE_PPPOE 14 */ + 0x00, 0x16, + + 0x00, 0x21, /* PPP Link Layer 20 */ + + 0x45, 0x00, 0x00, 0x1c, /* ICE_IPV4_OFOS 22 */ + 0x00, 0x01, 0x00, 0x00, + 0x00, 0x11, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_UDP_ILOS 42 */ + 0x00, 0x08, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 bytes alignment */ +}; + +ICE_DECLARE_PKT_OFFSETS(pppoe_ipv6_tcp) = { + { ICE_MAC_OFOS, 0 }, + { ICE_ETYPE_OL, 12 }, + { ICE_PPPOE, 14 }, + { ICE_IPV6_OFOS, 22 }, + { ICE_TCP_IL, 62 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +ICE_DECLARE_PKT_TEMPLATE(pppoe_ipv6_tcp) = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x88, 0x64, /* ICE_ETYPE_OL 12 */ + + 0x11, 0x00, 0x00, 0x00, /* ICE_PPPOE 14 */ + 0x00, 0x2a, + + 0x00, 0x57, /* PPP Link Layer 20 */ + + 0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_OFOS 22 */ + 0x00, 0x14, 0x06, 0x00, /* Next header is TCP */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_TCP_IL 62 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x50, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 bytes alignment */ +}; + +ICE_DECLARE_PKT_OFFSETS(pppoe_ipv6_udp) = { + { ICE_MAC_OFOS, 0 }, + { ICE_ETYPE_OL, 12 }, + { ICE_PPPOE, 14 }, + { ICE_IPV6_OFOS, 22 }, + { ICE_UDP_ILOS, 62 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +ICE_DECLARE_PKT_TEMPLATE(pppoe_ipv6_udp) = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x88, 0x64, /* ICE_ETYPE_OL 12 */ + + 0x11, 0x00, 0x00, 0x00, /* ICE_PPPOE 14 */ + 0x00, 0x2a, + + 0x00, 0x57, /* PPP Link Layer 20 */ + + 0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_OFOS 22 */ + 0x00, 0x08, 0x11, 0x00, /* Next header UDP*/ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_UDP_ILOS 62 */ + 0x00, 0x08, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 bytes alignment */ +}; + +ICE_DECLARE_PKT_OFFSETS(ipv4_l2tpv3) = { + { ICE_MAC_OFOS, 0 }, + { ICE_ETYPE_OL, 12 }, + { ICE_IPV4_OFOS, 14 }, + { ICE_L2TPV3, 34 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +ICE_DECLARE_PKT_TEMPLATE(ipv4_l2tpv3) = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x08, 0x00, /* ICE_ETYPE_OL 12 */ + + 0x45, 0x00, 0x00, 0x20, /* ICE_IPV4_IL 14 */ + 0x00, 0x00, 0x40, 0x00, + 0x40, 0x73, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_L2TPV3 34 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, /* 2 bytes for 4 bytes alignment */ +}; + +ICE_DECLARE_PKT_OFFSETS(ipv6_l2tpv3) = { + { ICE_MAC_OFOS, 0 }, + { ICE_ETYPE_OL, 12 }, + { ICE_IPV6_OFOS, 14 }, + { ICE_L2TPV3, 54 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +ICE_DECLARE_PKT_TEMPLATE(ipv6_l2tpv3) = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x86, 0xDD, /* ICE_ETYPE_OL 12 */ + + 0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_IL 14 */ + 0x00, 0x0c, 0x73, 0x40, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_L2TPV3 54 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, /* 2 bytes for 4 bytes alignment */ +}; + +static const struct ice_dummy_pkt_profile ice_dummy_pkt_profiles[] = { + ICE_PKT_PROFILE(ipv6_gtp, ICE_PKT_TUN_GTPU | ICE_PKT_OUTER_IPV6 | + ICE_PKT_GTP_NOPAY), + ICE_PKT_PROFILE(ipv6_gtpu_ipv6_udp, ICE_PKT_TUN_GTPU | + ICE_PKT_OUTER_IPV6 | + ICE_PKT_INNER_IPV6 | + ICE_PKT_INNER_UDP), + ICE_PKT_PROFILE(ipv6_gtpu_ipv6_tcp, ICE_PKT_TUN_GTPU | + ICE_PKT_OUTER_IPV6 | + ICE_PKT_INNER_IPV6), + ICE_PKT_PROFILE(ipv6_gtpu_ipv4_udp, ICE_PKT_TUN_GTPU | + ICE_PKT_OUTER_IPV6 | + ICE_PKT_INNER_UDP), + ICE_PKT_PROFILE(ipv6_gtpu_ipv4_tcp, ICE_PKT_TUN_GTPU | + ICE_PKT_OUTER_IPV6), + ICE_PKT_PROFILE(ipv4_gtpu_ipv4, ICE_PKT_TUN_GTPU | ICE_PKT_GTP_NOPAY), + ICE_PKT_PROFILE(ipv4_gtpu_ipv6_udp, ICE_PKT_TUN_GTPU | + ICE_PKT_INNER_IPV6 | + ICE_PKT_INNER_UDP), + ICE_PKT_PROFILE(ipv4_gtpu_ipv6_tcp, ICE_PKT_TUN_GTPU | + ICE_PKT_INNER_IPV6), + ICE_PKT_PROFILE(ipv4_gtpu_ipv4_udp, ICE_PKT_TUN_GTPU | + ICE_PKT_INNER_UDP), + ICE_PKT_PROFILE(ipv4_gtpu_ipv4_tcp, ICE_PKT_TUN_GTPU), + ICE_PKT_PROFILE(ipv6_gtp, ICE_PKT_TUN_GTPC | ICE_PKT_OUTER_IPV6), + ICE_PKT_PROFILE(ipv4_gtpu_ipv4, ICE_PKT_TUN_GTPC), + ICE_PKT_PROFILE(pppoe_ipv6_udp, ICE_PKT_PPPOE | ICE_PKT_OUTER_IPV6 | + ICE_PKT_INNER_UDP), + ICE_PKT_PROFILE(pppoe_ipv6_tcp, ICE_PKT_PPPOE | ICE_PKT_OUTER_IPV6), + ICE_PKT_PROFILE(pppoe_ipv4_udp, ICE_PKT_PPPOE | ICE_PKT_INNER_UDP), + ICE_PKT_PROFILE(pppoe_ipv4_tcp, ICE_PKT_PPPOE), + ICE_PKT_PROFILE(gre_ipv6_tcp, ICE_PKT_TUN_NVGRE | ICE_PKT_INNER_IPV6 | + ICE_PKT_INNER_TCP), + ICE_PKT_PROFILE(gre_tcp, ICE_PKT_TUN_NVGRE | ICE_PKT_INNER_TCP), + ICE_PKT_PROFILE(gre_ipv6_udp, ICE_PKT_TUN_NVGRE | ICE_PKT_INNER_IPV6), + ICE_PKT_PROFILE(gre_udp, ICE_PKT_TUN_NVGRE), + ICE_PKT_PROFILE(udp_tun_ipv6_tcp, ICE_PKT_TUN_UDP | + ICE_PKT_INNER_IPV6 | + ICE_PKT_INNER_TCP), + ICE_PKT_PROFILE(ipv6_l2tpv3, ICE_PKT_L2TPV3 | ICE_PKT_OUTER_IPV6), + ICE_PKT_PROFILE(ipv4_l2tpv3, ICE_PKT_L2TPV3), + ICE_PKT_PROFILE(udp_tun_tcp, ICE_PKT_TUN_UDP | ICE_PKT_INNER_TCP), + ICE_PKT_PROFILE(udp_tun_ipv6_udp, ICE_PKT_TUN_UDP | + ICE_PKT_INNER_IPV6), + ICE_PKT_PROFILE(udp_tun_udp, ICE_PKT_TUN_UDP), + ICE_PKT_PROFILE(udp_ipv6, ICE_PKT_OUTER_IPV6 | ICE_PKT_INNER_UDP), + ICE_PKT_PROFILE(udp, ICE_PKT_INNER_UDP), + ICE_PKT_PROFILE(tcp_ipv6, ICE_PKT_OUTER_IPV6), + 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], @@ -960,7 +1824,8 @@ ice_aq_alloc_free_vsi_list(struct ice_hw *hw, u16 *vsi_list_id, lkup_type == ICE_SW_LKUP_ETHERTYPE || lkup_type == ICE_SW_LKUP_ETHERTYPE_MAC || lkup_type == ICE_SW_LKUP_PROMISC || - lkup_type == ICE_SW_LKUP_PROMISC_VLAN) { + lkup_type == ICE_SW_LKUP_PROMISC_VLAN || + 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 = @@ -1097,6 +1962,64 @@ ice_aq_get_recipe(struct ice_hw *hw, } /** + * ice_update_recipe_lkup_idx - update a default recipe based on the lkup_idx + * @hw: pointer to the HW struct + * @params: parameters used to update the default recipe + * + * This function only supports updating default recipes and it only supports + * updating a single recipe based on the lkup_idx at a time. + * + * This is done as a read-modify-write operation. First, get the current recipe + * contents based on the recipe's ID. Then modify the field vector index and + * mask if it's valid at the lkup_idx. Finally, use the add recipe AQ to update + * the pre-existing recipe with the modifications. + */ +int +ice_update_recipe_lkup_idx(struct ice_hw *hw, + struct ice_update_recipe_lkup_idx_params *params) +{ + struct ice_aqc_recipe_data_elem *rcp_list; + u16 num_recps = ICE_MAX_NUM_RECIPES; + int status; + + rcp_list = kcalloc(num_recps, sizeof(*rcp_list), GFP_KERNEL); + if (!rcp_list) + return -ENOMEM; + + /* read current recipe list from firmware */ + rcp_list->recipe_indx = params->rid; + status = ice_aq_get_recipe(hw, rcp_list, &num_recps, params->rid, NULL); + if (status) { + ice_debug(hw, ICE_DBG_SW, "Failed to get recipe %d, status %d\n", + params->rid, status); + goto error_out; + } + + /* only modify existing recipe's lkup_idx and mask if valid, while + * leaving all other fields the same, then update the recipe firmware + */ + rcp_list->content.lkup_indx[params->lkup_idx] = params->fv_idx; + if (params->mask_valid) + rcp_list->content.mask[params->lkup_idx] = + cpu_to_le16(params->mask); + + if (params->ignore_valid) + rcp_list->content.lkup_indx[params->lkup_idx] |= + ICE_AQ_RECIPE_LKUP_IGNORE; + + status = ice_aq_add_recipe(hw, &rcp_list[0], 1, NULL); + if (status) + ice_debug(hw, ICE_DBG_SW, "Failed to update recipe %d lkup_idx %d fv_idx %d mask %d mask_valid %s, status %d\n", + params->rid, params->lkup_idx, params->fv_idx, + params->mask, params->mask_valid ? "true" : "false", + status); + +error_out: + kfree(rcp_list); + return status; +} + +/** * ice_aq_map_recipe_to_profile - Map recipe to packet profile * @hw: pointer to the HW struct * @profile_id: package profile ID to associate the recipe with @@ -1395,8 +2318,6 @@ ice_init_port_info(struct ice_port_info *pi, u16 vsi_port_num, u8 type, pi->sw_id = swid; pi->pf_vf_num = pf_vf_num; pi->is_vf = is_vf; - pi->dflt_tx_vsi_num = ICE_DFLT_VSI_INVAL; - pi->dflt_rx_vsi_num = ICE_DFLT_VSI_INVAL; break; default: ice_debug(pi->hw, ICE_DBG_SW, "incorrect VSI/port type received\n"); @@ -1415,9 +2336,7 @@ int ice_get_initial_sw_cfg(struct ice_hw *hw) int status; u16 i; - rbuf = devm_kzalloc(ice_hw_to_dev(hw), ICE_SW_CFG_MAX_BUF_LEN, - GFP_KERNEL); - + rbuf = kzalloc(ICE_SW_CFG_MAX_BUF_LEN, GFP_KERNEL); if (!rbuf) return -ENOMEM; @@ -1465,7 +2384,7 @@ int ice_get_initial_sw_cfg(struct ice_hw *hw) } } while (req_desc && !status); - devm_kfree(ice_hw_to_dev(hw), rbuf); + kfree(rbuf); return status; } @@ -1536,9 +2455,11 @@ static void ice_fill_sw_info(struct ice_hw *hw, struct ice_fltr_info *fi) */ static void ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, - struct ice_aqc_sw_rules_elem *s_rule, enum ice_adminq_opc opc) + struct ice_sw_rule_lkup_rx_tx *s_rule, + enum ice_adminq_opc opc) { u16 vlan_id = ICE_MAX_VLAN_ID + 1; + u16 vlan_tpid = ETH_P_8021Q; void *daddr = NULL; u16 eth_hdr_sz; u8 *eth_hdr; @@ -1547,15 +2468,14 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, u8 q_rgn; if (opc == ice_aqc_opc_remove_sw_rules) { - s_rule->pdata.lkup_tx_rx.act = 0; - s_rule->pdata.lkup_tx_rx.index = - cpu_to_le16(f_info->fltr_rule_id); - s_rule->pdata.lkup_tx_rx.hdr_len = 0; + s_rule->act = 0; + s_rule->index = cpu_to_le16(f_info->fltr_rule_id); + s_rule->hdr_len = 0; return; } eth_hdr_sz = sizeof(dummy_eth_header); - eth_hdr = s_rule->pdata.lkup_tx_rx.hdr; + eth_hdr = s_rule->hdr_data; /* initialize the ether header with a dummy header */ memcpy(eth_hdr, dummy_eth_header, eth_hdr_sz); @@ -1611,6 +2531,8 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, break; case ICE_SW_LKUP_VLAN: vlan_id = f_info->l_data.vlan.vlan_id; + if (f_info->l_data.vlan.tpid_valid) + vlan_tpid = f_info->l_data.vlan.tpid; if (f_info->fltr_act == ICE_FWD_TO_VSI || f_info->fltr_act == ICE_FWD_TO_VSI_LIST) { act |= ICE_SINGLE_ACT_PRUNE; @@ -1638,14 +2560,14 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, break; } - s_rule->type = (f_info->flag & ICE_FLTR_RX) ? + s_rule->hdr.type = (f_info->flag & ICE_FLTR_RX) ? cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX) : cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_TX); /* Recipe set depending on lookup type */ - s_rule->pdata.lkup_tx_rx.recipe_id = cpu_to_le16(f_info->lkup_type); - s_rule->pdata.lkup_tx_rx.src = cpu_to_le16(f_info->src); - s_rule->pdata.lkup_tx_rx.act = cpu_to_le32(act); + s_rule->recipe_id = cpu_to_le16(f_info->lkup_type); + s_rule->src = cpu_to_le16(f_info->src); + s_rule->act = cpu_to_le32(act); if (daddr) ether_addr_copy(eth_hdr + ICE_ETH_DA_OFFSET, daddr); @@ -1653,11 +2575,13 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, if (!(vlan_id > ICE_MAX_VLAN_ID)) { off = (__force __be16 *)(eth_hdr + ICE_ETH_VLAN_TCI_OFFSET); *off = cpu_to_be16(vlan_id); + off = (__force __be16 *)(eth_hdr + ICE_ETH_ETHTYPE_OFFSET); + *off = cpu_to_be16(vlan_tpid); } /* Create the switch rule with the final dummy Ethernet header */ if (opc != ice_aqc_opc_update_sw_rules) - s_rule->pdata.lkup_tx_rx.hdr_len = cpu_to_le16(eth_hdr_sz); + s_rule->hdr_len = cpu_to_le16(eth_hdr_sz); } /** @@ -1674,7 +2598,8 @@ static int ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent, u16 sw_marker, u16 l_id) { - struct ice_aqc_sw_rules_elem *lg_act, *rx_tx; + struct ice_sw_rule_lkup_rx_tx *rx_tx; + struct ice_sw_rule_lg_act *lg_act; /* For software marker we need 3 large actions * 1. FWD action: FWD TO VSI or VSI LIST * 2. GENERIC VALUE action to hold the profile ID @@ -1695,18 +2620,18 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent, * 1. Large Action * 2. Look up Tx Rx */ - lg_act_size = (u16)ICE_SW_RULE_LG_ACT_SIZE(num_lg_acts); - rules_size = lg_act_size + ICE_SW_RULE_RX_TX_ETH_HDR_SIZE; + lg_act_size = (u16)ICE_SW_RULE_LG_ACT_SIZE(lg_act, num_lg_acts); + rules_size = lg_act_size + ICE_SW_RULE_RX_TX_ETH_HDR_SIZE(rx_tx); lg_act = devm_kzalloc(ice_hw_to_dev(hw), rules_size, GFP_KERNEL); if (!lg_act) return -ENOMEM; - rx_tx = (struct ice_aqc_sw_rules_elem *)((u8 *)lg_act + lg_act_size); + rx_tx = (typeof(rx_tx))((u8 *)lg_act + lg_act_size); /* Fill in the first switch rule i.e. large action */ - lg_act->type = cpu_to_le16(ICE_AQC_SW_RULES_T_LG_ACT); - lg_act->pdata.lg_act.index = cpu_to_le16(l_id); - lg_act->pdata.lg_act.size = cpu_to_le16(num_lg_acts); + lg_act->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_LG_ACT); + lg_act->index = cpu_to_le16(l_id); + lg_act->size = cpu_to_le16(num_lg_acts); /* First action VSI forwarding or VSI list forwarding depending on how * many VSIs @@ -1718,13 +2643,13 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent, act |= (id << ICE_LG_ACT_VSI_LIST_ID_S) & ICE_LG_ACT_VSI_LIST_ID_M; if (m_ent->vsi_count > 1) act |= ICE_LG_ACT_VSI_LIST; - lg_act->pdata.lg_act.act[0] = cpu_to_le32(act); + lg_act->act[0] = cpu_to_le32(act); /* Second action descriptor type */ act = ICE_LG_ACT_GENERIC; act |= (1 << ICE_LG_ACT_GENERIC_VALUE_S) & ICE_LG_ACT_GENERIC_VALUE_M; - lg_act->pdata.lg_act.act[1] = cpu_to_le32(act); + lg_act->act[1] = cpu_to_le32(act); act = (ICE_LG_ACT_GENERIC_OFF_RX_DESC_PROF_IDX << ICE_LG_ACT_GENERIC_OFFSET_S) & ICE_LG_ACT_GENERIC_OFFSET_M; @@ -1734,24 +2659,22 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent, act |= (sw_marker << ICE_LG_ACT_GENERIC_VALUE_S) & ICE_LG_ACT_GENERIC_VALUE_M; - lg_act->pdata.lg_act.act[2] = cpu_to_le32(act); + lg_act->act[2] = cpu_to_le32(act); /* call the fill switch rule to fill the lookup Tx Rx structure */ ice_fill_sw_rule(hw, &m_ent->fltr_info, rx_tx, ice_aqc_opc_update_sw_rules); /* Update the action to point to the large action ID */ - rx_tx->pdata.lkup_tx_rx.act = - cpu_to_le32(ICE_SINGLE_ACT_PTR | - ((l_id << ICE_SINGLE_ACT_PTR_VAL_S) & - ICE_SINGLE_ACT_PTR_VAL_M)); + rx_tx->act = cpu_to_le32(ICE_SINGLE_ACT_PTR | + ((l_id << ICE_SINGLE_ACT_PTR_VAL_S) & + ICE_SINGLE_ACT_PTR_VAL_M)); /* Use the filter rule ID of the previously created rule with single * act. Once the update happens, hardware will treat this as large * action */ - rx_tx->pdata.lkup_tx_rx.index = - cpu_to_le16(m_ent->fltr_info.fltr_rule_id); + rx_tx->index = cpu_to_le16(m_ent->fltr_info.fltr_rule_id); status = ice_aq_sw_rules(hw, lg_act, rules_size, 2, ice_aqc_opc_update_sw_rules, NULL); @@ -1813,7 +2736,7 @@ ice_update_vsi_list_rule(struct ice_hw *hw, u16 *vsi_handle_arr, u16 num_vsi, u16 vsi_list_id, bool remove, enum ice_adminq_opc opc, enum ice_sw_lkup_type lkup_type) { - struct ice_aqc_sw_rules_elem *s_rule; + struct ice_sw_rule_vsi_list *s_rule; u16 s_rule_size; u16 rule_type; int status; @@ -1827,7 +2750,8 @@ ice_update_vsi_list_rule(struct ice_hw *hw, u16 *vsi_handle_arr, u16 num_vsi, lkup_type == ICE_SW_LKUP_ETHERTYPE || lkup_type == ICE_SW_LKUP_ETHERTYPE_MAC || lkup_type == ICE_SW_LKUP_PROMISC || - lkup_type == ICE_SW_LKUP_PROMISC_VLAN) + lkup_type == ICE_SW_LKUP_PROMISC_VLAN || + lkup_type == ICE_SW_LKUP_DFLT) rule_type = remove ? ICE_AQC_SW_RULES_T_VSI_LIST_CLEAR : ICE_AQC_SW_RULES_T_VSI_LIST_SET; else if (lkup_type == ICE_SW_LKUP_VLAN) @@ -1836,7 +2760,7 @@ ice_update_vsi_list_rule(struct ice_hw *hw, u16 *vsi_handle_arr, u16 num_vsi, else return -EINVAL; - s_rule_size = (u16)ICE_SW_RULE_VSI_LIST_SIZE(num_vsi); + s_rule_size = (u16)ICE_SW_RULE_VSI_LIST_SIZE(s_rule, num_vsi); s_rule = devm_kzalloc(ice_hw_to_dev(hw), s_rule_size, GFP_KERNEL); if (!s_rule) return -ENOMEM; @@ -1846,13 +2770,13 @@ ice_update_vsi_list_rule(struct ice_hw *hw, u16 *vsi_handle_arr, u16 num_vsi, goto exit; } /* AQ call requires hw_vsi_id(s) */ - s_rule->pdata.vsi_list.vsi[i] = + s_rule->vsi[i] = cpu_to_le16(ice_get_hw_vsi_num(hw, vsi_handle_arr[i])); } - s_rule->type = cpu_to_le16(rule_type); - s_rule->pdata.vsi_list.number_vsi = cpu_to_le16(num_vsi); - s_rule->pdata.vsi_list.index = cpu_to_le16(vsi_list_id); + s_rule->hdr.type = cpu_to_le16(rule_type); + s_rule->number_vsi = cpu_to_le16(num_vsi); + s_rule->index = cpu_to_le16(vsi_list_id); status = ice_aq_sw_rules(hw, s_rule, s_rule_size, 1, opc, NULL); @@ -1900,13 +2824,14 @@ ice_create_pkt_fwd_rule(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry) { struct ice_fltr_mgmt_list_entry *fm_entry; - struct ice_aqc_sw_rules_elem *s_rule; + struct ice_sw_rule_lkup_rx_tx *s_rule; enum ice_sw_lkup_type l_type; struct ice_sw_recipe *recp; int status; s_rule = devm_kzalloc(ice_hw_to_dev(hw), - ICE_SW_RULE_RX_TX_ETH_HDR_SIZE, GFP_KERNEL); + ICE_SW_RULE_RX_TX_ETH_HDR_SIZE(s_rule), + GFP_KERNEL); if (!s_rule) return -ENOMEM; fm_entry = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*fm_entry), @@ -1927,17 +2852,16 @@ ice_create_pkt_fwd_rule(struct ice_hw *hw, ice_fill_sw_rule(hw, &fm_entry->fltr_info, s_rule, ice_aqc_opc_add_sw_rules); - status = ice_aq_sw_rules(hw, s_rule, ICE_SW_RULE_RX_TX_ETH_HDR_SIZE, 1, + status = ice_aq_sw_rules(hw, s_rule, + ICE_SW_RULE_RX_TX_ETH_HDR_SIZE(s_rule), 1, ice_aqc_opc_add_sw_rules, NULL); if (status) { devm_kfree(ice_hw_to_dev(hw), fm_entry); goto ice_create_pkt_fwd_rule_exit; } - f_entry->fltr_info.fltr_rule_id = - le16_to_cpu(s_rule->pdata.lkup_tx_rx.index); - fm_entry->fltr_info.fltr_rule_id = - le16_to_cpu(s_rule->pdata.lkup_tx_rx.index); + f_entry->fltr_info.fltr_rule_id = le16_to_cpu(s_rule->index); + fm_entry->fltr_info.fltr_rule_id = le16_to_cpu(s_rule->index); /* The book keeping entries will get removed when base driver * calls remove filter AQ command @@ -1962,20 +2886,22 @@ ice_create_pkt_fwd_rule_exit: static int ice_update_pkt_fwd_rule(struct ice_hw *hw, struct ice_fltr_info *f_info) { - struct ice_aqc_sw_rules_elem *s_rule; + struct ice_sw_rule_lkup_rx_tx *s_rule; int status; s_rule = devm_kzalloc(ice_hw_to_dev(hw), - ICE_SW_RULE_RX_TX_ETH_HDR_SIZE, GFP_KERNEL); + ICE_SW_RULE_RX_TX_ETH_HDR_SIZE(s_rule), + GFP_KERNEL); if (!s_rule) return -ENOMEM; ice_fill_sw_rule(hw, f_info, s_rule, ice_aqc_opc_update_sw_rules); - s_rule->pdata.lkup_tx_rx.index = cpu_to_le16(f_info->fltr_rule_id); + s_rule->index = cpu_to_le16(f_info->fltr_rule_id); /* Update switch rule with new rule set to forward VSI list */ - status = ice_aq_sw_rules(hw, s_rule, ICE_SW_RULE_RX_TX_ETH_HDR_SIZE, 1, + status = ice_aq_sw_rules(hw, s_rule, + ICE_SW_RULE_RX_TX_ETH_HDR_SIZE(s_rule), 1, ice_aqc_opc_update_sw_rules, NULL); devm_kfree(ice_hw_to_dev(hw), s_rule); @@ -2259,17 +3185,17 @@ static int ice_remove_vsi_list_rule(struct ice_hw *hw, u16 vsi_list_id, enum ice_sw_lkup_type lkup_type) { - struct ice_aqc_sw_rules_elem *s_rule; + struct ice_sw_rule_vsi_list *s_rule; u16 s_rule_size; int status; - s_rule_size = (u16)ICE_SW_RULE_VSI_LIST_SIZE(0); + s_rule_size = (u16)ICE_SW_RULE_VSI_LIST_SIZE(s_rule, 0); s_rule = devm_kzalloc(ice_hw_to_dev(hw), s_rule_size, GFP_KERNEL); if (!s_rule) return -ENOMEM; - s_rule->type = cpu_to_le16(ICE_AQC_SW_RULES_T_VSI_LIST_CLEAR); - s_rule->pdata.vsi_list.index = cpu_to_le16(vsi_list_id); + s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_VSI_LIST_CLEAR); + s_rule->index = cpu_to_le16(vsi_list_id); /* Free the vsi_list resource that we allocated. It is assumed that the * list is empty at this point. @@ -2429,10 +3355,10 @@ ice_remove_rule_internal(struct ice_hw *hw, u8 recp_id, if (remove_rule) { /* Remove the lookup rule */ - struct ice_aqc_sw_rules_elem *s_rule; + struct ice_sw_rule_lkup_rx_tx *s_rule; s_rule = devm_kzalloc(ice_hw_to_dev(hw), - ICE_SW_RULE_RX_TX_NO_HDR_SIZE, + ICE_SW_RULE_RX_TX_NO_HDR_SIZE(s_rule), GFP_KERNEL); if (!s_rule) { status = -ENOMEM; @@ -2443,8 +3369,8 @@ ice_remove_rule_internal(struct ice_hw *hw, u8 recp_id, ice_aqc_opc_remove_sw_rules); status = ice_aq_sw_rules(hw, s_rule, - ICE_SW_RULE_RX_TX_NO_HDR_SIZE, 1, - ice_aqc_opc_remove_sw_rules, NULL); + ICE_SW_RULE_RX_TX_NO_HDR_SIZE(s_rule), + 1, ice_aqc_opc_remove_sw_rules, NULL); /* Remove a book keeping from the list */ devm_kfree(ice_hw_to_dev(hw), s_rule); @@ -2583,31 +3509,15 @@ bool ice_vlan_fltr_exist(struct ice_hw *hw, u16 vlan_id, u16 vsi_handle) * ice_add_mac - Add a MAC address based filter rule * @hw: pointer to the hardware structure * @m_list: list of MAC addresses and forwarding information - * - * IMPORTANT: When the ucast_shared flag is set to false and m_list has - * multiple unicast addresses, the function assumes that all the - * addresses are unique in a given add_mac call. It doesn't - * check for duplicates in this case, removing duplicates from a given - * list should be taken care of in the caller of this function. */ int ice_add_mac(struct ice_hw *hw, struct list_head *m_list) { - struct ice_aqc_sw_rules_elem *s_rule, *r_iter; struct ice_fltr_list_entry *m_list_itr; - struct list_head *rule_head; - u16 total_elem_left, s_rule_size; - struct ice_switch_info *sw; - struct mutex *rule_lock; /* Lock to protect filter rule list */ - u16 num_unicast = 0; int status = 0; - u8 elem_sent; if (!m_list || !hw) return -EINVAL; - s_rule = NULL; - sw = hw->switch_info; - rule_lock = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rule_lock; list_for_each_entry(m_list_itr, m_list, list_entry) { u8 *add = &m_list_itr->fltr_info.l_data.mac.mac_addr[0]; u16 vsi_handle; @@ -2626,109 +3536,13 @@ int ice_add_mac(struct ice_hw *hw, struct list_head *m_list) if (m_list_itr->fltr_info.lkup_type != ICE_SW_LKUP_MAC || is_zero_ether_addr(add)) return -EINVAL; - if (is_unicast_ether_addr(add) && !hw->ucast_shared) { - /* Don't overwrite the unicast address */ - mutex_lock(rule_lock); - if (ice_find_rule_entry(hw, ICE_SW_LKUP_MAC, - &m_list_itr->fltr_info)) { - mutex_unlock(rule_lock); - return -EEXIST; - } - mutex_unlock(rule_lock); - num_unicast++; - } else if (is_multicast_ether_addr(add) || - (is_unicast_ether_addr(add) && hw->ucast_shared)) { - m_list_itr->status = - ice_add_rule_internal(hw, ICE_SW_LKUP_MAC, - m_list_itr); - if (m_list_itr->status) - return m_list_itr->status; - } - } - - mutex_lock(rule_lock); - /* Exit if no suitable entries were found for adding bulk switch rule */ - if (!num_unicast) { - status = 0; - goto ice_add_mac_exit; - } - rule_head = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rules; - - /* Allocate switch rule buffer for the bulk update for unicast */ - s_rule_size = ICE_SW_RULE_RX_TX_ETH_HDR_SIZE; - s_rule = devm_kcalloc(ice_hw_to_dev(hw), num_unicast, s_rule_size, - GFP_KERNEL); - if (!s_rule) { - status = -ENOMEM; - goto ice_add_mac_exit; + m_list_itr->status = ice_add_rule_internal(hw, ICE_SW_LKUP_MAC, + m_list_itr); + if (m_list_itr->status) + return m_list_itr->status; } - r_iter = s_rule; - list_for_each_entry(m_list_itr, m_list, list_entry) { - struct ice_fltr_info *f_info = &m_list_itr->fltr_info; - u8 *mac_addr = &f_info->l_data.mac.mac_addr[0]; - - if (is_unicast_ether_addr(mac_addr)) { - ice_fill_sw_rule(hw, &m_list_itr->fltr_info, r_iter, - ice_aqc_opc_add_sw_rules); - r_iter = (struct ice_aqc_sw_rules_elem *) - ((u8 *)r_iter + s_rule_size); - } - } - - /* Call AQ bulk switch rule update for all unicast addresses */ - r_iter = s_rule; - /* Call AQ switch rule in AQ_MAX chunk */ - for (total_elem_left = num_unicast; total_elem_left > 0; - total_elem_left -= elem_sent) { - struct ice_aqc_sw_rules_elem *entry = r_iter; - - elem_sent = min_t(u8, total_elem_left, - (ICE_AQ_MAX_BUF_LEN / s_rule_size)); - status = ice_aq_sw_rules(hw, entry, elem_sent * s_rule_size, - elem_sent, ice_aqc_opc_add_sw_rules, - NULL); - if (status) - goto ice_add_mac_exit; - r_iter = (struct ice_aqc_sw_rules_elem *) - ((u8 *)r_iter + (elem_sent * s_rule_size)); - } - - /* Fill up rule ID based on the value returned from FW */ - r_iter = s_rule; - list_for_each_entry(m_list_itr, m_list, list_entry) { - struct ice_fltr_info *f_info = &m_list_itr->fltr_info; - u8 *mac_addr = &f_info->l_data.mac.mac_addr[0]; - struct ice_fltr_mgmt_list_entry *fm_entry; - - if (is_unicast_ether_addr(mac_addr)) { - f_info->fltr_rule_id = - le16_to_cpu(r_iter->pdata.lkup_tx_rx.index); - f_info->fltr_act = ICE_FWD_TO_VSI; - /* Create an entry to track this MAC address */ - fm_entry = devm_kzalloc(ice_hw_to_dev(hw), - sizeof(*fm_entry), GFP_KERNEL); - if (!fm_entry) { - status = -ENOMEM; - goto ice_add_mac_exit; - } - fm_entry->fltr_info = *f_info; - fm_entry->vsi_count = 1; - /* The book keeping entries will get removed when - * base driver calls remove filter AQ command - */ - - list_add(&fm_entry->list_entry, rule_head); - r_iter = (struct ice_aqc_sw_rules_elem *) - ((u8 *)r_iter + s_rule_size); - } - } - -ice_add_mac_exit: - mutex_unlock(rule_lock); - if (s_rule) - devm_kfree(ice_hw_to_dev(hw), s_rule); return status; } @@ -3010,7 +3824,7 @@ ice_rem_adv_rule_info(struct ice_hw *hw, struct list_head *rule_head) /** * ice_cfg_dflt_vsi - change state of VSI to set/clear default - * @hw: pointer to the hardware structure + * @pi: pointer to the port_info structure * @vsi_handle: VSI handle to set as default * @set: true to add the above mentioned switch rule, false to remove it * @direction: ICE_FLTR_RX or ICE_FLTR_TX @@ -3018,25 +3832,20 @@ ice_rem_adv_rule_info(struct ice_hw *hw, struct list_head *rule_head) * add filter rule to set/unset given VSI as default VSI for the switch * (represented by swid) */ -int ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_handle, bool set, u8 direction) +int +ice_cfg_dflt_vsi(struct ice_port_info *pi, u16 vsi_handle, bool set, + u8 direction) { - struct ice_aqc_sw_rules_elem *s_rule; + struct ice_fltr_list_entry f_list_entry; struct ice_fltr_info f_info; - enum ice_adminq_opc opcode; - u16 s_rule_size; + struct ice_hw *hw = pi->hw; u16 hw_vsi_id; int status; if (!ice_is_vsi_valid(hw, vsi_handle)) return -EINVAL; - hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); - s_rule_size = set ? ICE_SW_RULE_RX_TX_ETH_HDR_SIZE : - ICE_SW_RULE_RX_TX_NO_HDR_SIZE; - - s_rule = devm_kzalloc(ice_hw_to_dev(hw), s_rule_size, GFP_KERNEL); - if (!s_rule) - return -ENOMEM; + hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); memset(&f_info, 0, sizeof(f_info)); @@ -3044,86 +3853,80 @@ int ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_handle, bool set, u8 direction) f_info.flag = direction; f_info.fltr_act = ICE_FWD_TO_VSI; f_info.fwd_id.hw_vsi_id = hw_vsi_id; + f_info.vsi_handle = vsi_handle; if (f_info.flag & ICE_FLTR_RX) { f_info.src = hw->port_info->lport; f_info.src_id = ICE_SRC_ID_LPORT; - if (!set) - f_info.fltr_rule_id = - hw->port_info->dflt_rx_vsi_rule_id; } else if (f_info.flag & ICE_FLTR_TX) { f_info.src_id = ICE_SRC_ID_VSI; f_info.src = hw_vsi_id; - if (!set) - f_info.fltr_rule_id = - hw->port_info->dflt_tx_vsi_rule_id; } + f_list_entry.fltr_info = f_info; if (set) - opcode = ice_aqc_opc_add_sw_rules; + status = ice_add_rule_internal(hw, ICE_SW_LKUP_DFLT, + &f_list_entry); else - opcode = ice_aqc_opc_remove_sw_rules; - - ice_fill_sw_rule(hw, &f_info, s_rule, opcode); - - status = ice_aq_sw_rules(hw, s_rule, s_rule_size, 1, opcode, NULL); - if (status || !(f_info.flag & ICE_FLTR_TX_RX)) - goto out; - if (set) { - u16 index = le16_to_cpu(s_rule->pdata.lkup_tx_rx.index); - - if (f_info.flag & ICE_FLTR_TX) { - hw->port_info->dflt_tx_vsi_num = hw_vsi_id; - hw->port_info->dflt_tx_vsi_rule_id = index; - } else if (f_info.flag & ICE_FLTR_RX) { - hw->port_info->dflt_rx_vsi_num = hw_vsi_id; - hw->port_info->dflt_rx_vsi_rule_id = index; - } - } else { - if (f_info.flag & ICE_FLTR_TX) { - hw->port_info->dflt_tx_vsi_num = ICE_DFLT_VSI_INVAL; - hw->port_info->dflt_tx_vsi_rule_id = ICE_INVAL_ACT; - } else if (f_info.flag & ICE_FLTR_RX) { - hw->port_info->dflt_rx_vsi_num = ICE_DFLT_VSI_INVAL; - hw->port_info->dflt_rx_vsi_rule_id = ICE_INVAL_ACT; - } - } + status = ice_remove_rule_internal(hw, ICE_SW_LKUP_DFLT, + &f_list_entry); -out: - devm_kfree(ice_hw_to_dev(hw), s_rule); return status; } /** - * ice_find_ucast_rule_entry - Search for a unicast MAC filter rule entry - * @hw: pointer to the hardware structure - * @recp_id: lookup type for which the specified rule needs to be searched - * @f_info: rule information - * - * Helper function to search for a unicast rule entry - this is to be used - * to remove unicast MAC filter that is not shared with other VSIs on the - * PF switch. + * ice_vsi_uses_fltr - Determine if given VSI uses specified filter + * @fm_entry: filter entry to inspect + * @vsi_handle: VSI handle to compare with filter info + */ +static bool +ice_vsi_uses_fltr(struct ice_fltr_mgmt_list_entry *fm_entry, u16 vsi_handle) +{ + return ((fm_entry->fltr_info.fltr_act == ICE_FWD_TO_VSI && + fm_entry->fltr_info.vsi_handle == vsi_handle) || + (fm_entry->fltr_info.fltr_act == ICE_FWD_TO_VSI_LIST && + fm_entry->vsi_list_info && + (test_bit(vsi_handle, fm_entry->vsi_list_info->vsi_map)))); +} + +/** + * ice_check_if_dflt_vsi - check if VSI is default VSI + * @pi: pointer to the port_info structure + * @vsi_handle: vsi handle to check for in filter list + * @rule_exists: indicates if there are any VSI's in the rule list * - * Returns pointer to entry storing the rule if found + * checks if the VSI is in a default VSI list, and also indicates + * if the default VSI list is empty */ -static struct ice_fltr_mgmt_list_entry * -ice_find_ucast_rule_entry(struct ice_hw *hw, u8 recp_id, - struct ice_fltr_info *f_info) +bool +ice_check_if_dflt_vsi(struct ice_port_info *pi, u16 vsi_handle, + bool *rule_exists) { - struct ice_switch_info *sw = hw->switch_info; - struct ice_fltr_mgmt_list_entry *list_itr; - struct list_head *list_head; + struct ice_fltr_mgmt_list_entry *fm_entry; + struct ice_sw_recipe *recp_list; + struct list_head *rule_head; + struct mutex *rule_lock; /* Lock to protect filter rule list */ + bool ret = false; - list_head = &sw->recp_list[recp_id].filt_rules; - list_for_each_entry(list_itr, list_head, list_entry) { - if (!memcmp(&f_info->l_data, &list_itr->fltr_info.l_data, - sizeof(f_info->l_data)) && - f_info->fwd_id.hw_vsi_id == - list_itr->fltr_info.fwd_id.hw_vsi_id && - f_info->flag == list_itr->fltr_info.flag) - return list_itr; + recp_list = &pi->hw->switch_info->recp_list[ICE_SW_LKUP_DFLT]; + rule_lock = &recp_list->filt_rule_lock; + rule_head = &recp_list->filt_rules; + + mutex_lock(rule_lock); + + if (rule_exists && !list_empty(rule_head)) + *rule_exists = true; + + list_for_each_entry(fm_entry, rule_head, list_entry) { + if (ice_vsi_uses_fltr(fm_entry, vsi_handle)) { + ret = true; + break; + } } - return NULL; + + mutex_unlock(rule_lock); + + return ret; } /** @@ -3142,15 +3945,12 @@ ice_find_ucast_rule_entry(struct ice_hw *hw, u8 recp_id, int ice_remove_mac(struct ice_hw *hw, struct list_head *m_list) { struct ice_fltr_list_entry *list_itr, *tmp; - struct mutex *rule_lock; /* Lock to protect filter rule list */ if (!m_list) return -EINVAL; - rule_lock = &hw->switch_info->recp_list[ICE_SW_LKUP_MAC].filt_rule_lock; list_for_each_entry_safe(list_itr, tmp, m_list, list_entry) { enum ice_sw_lkup_type l_type = list_itr->fltr_info.lkup_type; - u8 *add = &list_itr->fltr_info.l_data.mac.mac_addr[0]; u16 vsi_handle; if (l_type != ICE_SW_LKUP_MAC) @@ -3162,19 +3962,7 @@ int ice_remove_mac(struct ice_hw *hw, struct list_head *m_list) list_itr->fltr_info.fwd_id.hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); - if (is_unicast_ether_addr(add) && !hw->ucast_shared) { - /* Don't remove the unicast address that belongs to - * another VSI on the switch, since it is not being - * shared... - */ - mutex_lock(rule_lock); - if (!ice_find_ucast_rule_entry(hw, ICE_SW_LKUP_MAC, - &list_itr->fltr_info)) { - mutex_unlock(rule_lock); - return -ENOENT; - } - mutex_unlock(rule_lock); - } + list_itr->status = ice_remove_rule_internal(hw, ICE_SW_LKUP_MAC, list_itr); @@ -3211,21 +3999,6 @@ int ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list) } /** - * ice_vsi_uses_fltr - Determine if given VSI uses specified filter - * @fm_entry: filter entry to inspect - * @vsi_handle: VSI handle to compare with filter info - */ -static bool -ice_vsi_uses_fltr(struct ice_fltr_mgmt_list_entry *fm_entry, u16 vsi_handle) -{ - return ((fm_entry->fltr_info.fltr_act == ICE_FWD_TO_VSI && - fm_entry->fltr_info.vsi_handle == vsi_handle) || - (fm_entry->fltr_info.fltr_act == ICE_FWD_TO_VSI_LIST && - fm_entry->vsi_list_info && - (test_bit(vsi_handle, fm_entry->vsi_list_info->vsi_map)))); -} - -/** * ice_add_entry_to_vsi_fltr_list - Add copy of fltr_list_entry to remove list * @hw: pointer to the hardware structure * @vsi_handle: VSI handle to remove filters from @@ -3576,6 +4349,13 @@ ice_set_vlan_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, goto free_fltr_list; list_for_each_entry(list_itr, &vsi_list_head, list_entry) { + /* Avoid enabling or disabling VLAN zero twice when in double + * VLAN mode + */ + if (ice_is_dvm_ena(hw) && + list_itr->fltr_info.l_data.vlan.tpid == 0) + continue; + vlan_id = list_itr->fltr_info.l_data.vlan.vlan_id; if (rm_vlan_promisc) status = ice_clear_vsi_promisc(hw, vsi_handle, @@ -3583,7 +4363,7 @@ ice_set_vlan_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, else status = ice_set_vsi_promisc(hw, vsi_handle, promisc_mask, vlan_id); - if (status) + if (status && status != -EEXIST) break; } @@ -3755,6 +4535,7 @@ static const struct ice_prot_ext_tbl_entry ice_prot_ext[ICE_PROTOCOL_LAST] = { { ICE_MAC_OFOS, { 0, 2, 4, 6, 8, 10, 12 } }, { ICE_MAC_IL, { 0, 2, 4, 6, 8, 10, 12 } }, { ICE_ETYPE_OL, { 0 } }, + { ICE_ETYPE_IL, { 0 } }, { ICE_VLAN_OFOS, { 2, 0 } }, { ICE_IPV4_OFOS, { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18 } }, { ICE_IPV4_IL, { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18 } }, @@ -3767,13 +4548,20 @@ static const struct ice_prot_ext_tbl_entry ice_prot_ext[ICE_PROTOCOL_LAST] = { { ICE_UDP_ILOS, { 0, 2 } }, { ICE_VXLAN, { 8, 10, 12, 14 } }, { ICE_GENEVE, { 8, 10, 12, 14 } }, - { ICE_NVGRE, { 0, 2, 4, 6 } }, + { ICE_NVGRE, { 0, 2, 4, 6 } }, + { ICE_GTP, { 8, 10, 12, 14, 16, 18, 20, 22 } }, + { ICE_GTP_NO_PAY, { 8, 10, 12, 14 } }, + { ICE_PPPOE, { 0, 2, 4, 6 } }, + { ICE_L2TPV3, { 0, 2, 4, 6, 8, 10 } }, + { ICE_VLAN_EX, { 2, 0 } }, + { ICE_VLAN_IN, { 2, 0 } }, }; static struct ice_protocol_entry ice_prot_id_tbl[ICE_PROTOCOL_LAST] = { { ICE_MAC_OFOS, ICE_MAC_OFOS_HW }, { ICE_MAC_IL, ICE_MAC_IL_HW }, { ICE_ETYPE_OL, ICE_ETYPE_OL_HW }, + { ICE_ETYPE_IL, ICE_ETYPE_IL_HW }, { ICE_VLAN_OFOS, ICE_VLAN_OL_HW }, { ICE_IPV4_OFOS, ICE_IPV4_OFOS_HW }, { ICE_IPV4_IL, ICE_IPV4_IL_HW }, @@ -3784,7 +4572,13 @@ static struct ice_protocol_entry ice_prot_id_tbl[ICE_PROTOCOL_LAST] = { { ICE_UDP_ILOS, ICE_UDP_ILOS_HW }, { ICE_VXLAN, ICE_UDP_OF_HW }, { ICE_GENEVE, ICE_UDP_OF_HW }, - { ICE_NVGRE, ICE_GRE_OF_HW }, + { ICE_NVGRE, ICE_GRE_OF_HW }, + { ICE_GTP, ICE_UDP_OF_HW }, + { ICE_GTP_NO_PAY, ICE_UDP_ILOS_HW }, + { ICE_PPPOE, ICE_PPPOE_HW }, + { ICE_L2TPV3, ICE_L2TPV3_HW }, + { ICE_VLAN_EX, ICE_VLAN_OF_HW }, + { ICE_VLAN_IN, ICE_VLAN_OL_HW }, }; /** @@ -3868,6 +4662,23 @@ ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts, } /** + * ice_change_proto_id_to_dvm - change proto id in prot_id_tbl + * + * As protocol id for outer vlan is different in dvm and svm, if dvm is + * supported protocol array record for outer vlan has to be modified to + * reflect the value proper for DVM. + */ +void ice_change_proto_id_to_dvm(void) +{ + u8 i; + + for (i = 0; i < ARRAY_SIZE(ice_prot_id_tbl); i++) + if (ice_prot_id_tbl[i].type == ICE_VLAN_OFOS && + ice_prot_id_tbl[i].protocol_id != ICE_VLAN_OF_HW) + ice_prot_id_tbl[i].protocol_id = ICE_VLAN_OF_HW; +} + +/** * ice_prot_type_to_id - get protocol ID from protocol type * @type: protocol type * @id: pointer to variable that will receive the ID @@ -4073,7 +4884,7 @@ ice_find_free_recp_res_idx(struct ice_hw *hw, const unsigned long *profiles, bitmap_zero(recipes, ICE_MAX_NUM_RECIPES); bitmap_zero(used_idx, ICE_MAX_FV_WORDS); - bitmap_set(possible_idx, 0, ICE_MAX_FV_WORDS); + bitmap_fill(possible_idx, ICE_MAX_FV_WORDS); /* For each profile we are going to associate the recipe with, add the * recipes that are associated with that profile. This will give us @@ -4427,41 +5238,6 @@ ice_create_recipe_group(struct ice_hw *hw, struct ice_sw_recipe *rm, } /** - * ice_get_fv - get field vectors/extraction sequences for spec. lookup types - * @hw: pointer to hardware structure - * @lkups: lookup elements or match criteria for the advanced recipe, one - * structure per protocol header - * @lkups_cnt: number of protocols - * @bm: bitmap of field vectors to consider - * @fv_list: pointer to a list that holds the returned field vectors - */ -static int -ice_get_fv(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, - unsigned long *bm, struct list_head *fv_list) -{ - u8 *prot_ids; - int status; - u16 i; - - prot_ids = kcalloc(lkups_cnt, sizeof(*prot_ids), GFP_KERNEL); - if (!prot_ids) - return -ENOMEM; - - for (i = 0; i < lkups_cnt; i++) - if (!ice_prot_type_to_id(lkups[i].type, &prot_ids[i])) { - status = -EIO; - goto free_mem; - } - - /* Find field vectors that include all specified protocol types */ - status = ice_get_sw_fv_list(hw, prot_ids, lkups_cnt, bm, fv_list); - -free_mem: - kfree(prot_ids); - return status; -} - -/** * ice_tun_type_match_word - determine if tun type needs a match mask * @tun_type: tunnel type * @mask: mask to be used for the tunnel @@ -4472,6 +5248,8 @@ static bool ice_tun_type_match_word(enum ice_sw_tunnel_type tun_type, u16 *mask) case ICE_SW_TUN_GENEVE: case ICE_SW_TUN_VXLAN: case ICE_SW_TUN_NVGRE: + case ICE_SW_TUN_GTPU: + case ICE_SW_TUN_GTPC: *mask = ICE_TUN_FLAG_MASK; return true; @@ -4485,10 +5263,11 @@ static bool ice_tun_type_match_word(enum ice_sw_tunnel_type tun_type, u16 *mask) * ice_add_special_words - Add words that are not protocols, such as metadata * @rinfo: other information regarding the rule e.g. priority and action info * @lkup_exts: lookup word structure + * @dvm_ena: is double VLAN mode enabled */ static int ice_add_special_words(struct ice_adv_rule_info *rinfo, - struct ice_prot_lkup_ext *lkup_exts) + struct ice_prot_lkup_ext *lkup_exts, bool dvm_ena) { u16 mask; @@ -4507,6 +5286,19 @@ ice_add_special_words(struct ice_adv_rule_info *rinfo, } } + if (rinfo->vlan_type != 0 && dvm_ena) { + if (lkup_exts->n_val_words < ICE_MAX_CHAIN_WORDS) { + u8 word = lkup_exts->n_val_words++; + + lkup_exts->fv_words[word].prot_id = ICE_META_DATA_ID_HW; + lkup_exts->fv_words[word].off = ICE_VLAN_FLAG_MDID_OFF; + lkup_exts->field_mask[word] = + ICE_PKT_FLAGS_0_TO_15_VLAN_FLAGS_MASK; + } else { + return -ENOSPC; + } + } + return 0; } @@ -4537,6 +5329,13 @@ ice_get_compat_fv_bitmap(struct ice_hw *hw, struct ice_adv_rule_info *rinfo, case ICE_SW_TUN_NVGRE: prof_type = ICE_PROF_TUN_GRE; break; + case ICE_SW_TUN_GTPU: + prof_type = ICE_PROF_TUN_GTPU; + break; + case ICE_SW_TUN_GTPC: + prof_type = ICE_PROF_TUN_GTPC; + break; + case ICE_SW_TUN_AND_NON_TUN: default: prof_type = ICE_PROF_ALL; break; @@ -4608,18 +5407,18 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, /* Get bitmap of field vectors (profiles) that are compatible with the * rule request; only these will be searched in the subsequent call to - * ice_get_fv. + * ice_get_sw_fv_list. */ ice_get_compat_fv_bitmap(hw, rinfo, fv_bitmap); - status = ice_get_fv(hw, lkups, lkups_cnt, fv_bitmap, &rm->fv_list); + status = ice_get_sw_fv_list(hw, lkup_exts, fv_bitmap, &rm->fv_list); if (status) goto err_unroll; /* Create any special protocol/offset pairs, such as looking at tunnel * bits by extracting metadata */ - status = ice_add_special_words(rinfo, lkup_exts); + status = ice_add_special_words(rinfo, lkup_exts, ice_is_dvm_ena(hw)); if (status) goto err_free_lkup_exts; @@ -4720,115 +5519,158 @@ err_free_lkup_exts: } /** + * ice_dummy_packet_add_vlan - insert VLAN header to dummy pkt + * + * @dummy_pkt: dummy packet profile pattern to which VLAN tag(s) will be added + * @num_vlan: number of VLAN tags + */ +static struct ice_dummy_pkt_profile * +ice_dummy_packet_add_vlan(const struct ice_dummy_pkt_profile *dummy_pkt, + u32 num_vlan) +{ + struct ice_dummy_pkt_profile *profile; + struct ice_dummy_pkt_offsets *offsets; + u32 buf_len, off, etype_off, i; + u8 *pkt; + + if (num_vlan < 1 || num_vlan > 2) + return ERR_PTR(-EINVAL); + + off = num_vlan * VLAN_HLEN; + + buf_len = array_size(num_vlan, sizeof(ice_dummy_vlan_packet_offsets)) + + dummy_pkt->offsets_len; + offsets = kzalloc(buf_len, GFP_KERNEL); + if (!offsets) + return ERR_PTR(-ENOMEM); + + offsets[0] = dummy_pkt->offsets[0]; + if (num_vlan == 2) { + offsets[1] = ice_dummy_qinq_packet_offsets[0]; + offsets[2] = ice_dummy_qinq_packet_offsets[1]; + } else if (num_vlan == 1) { + offsets[1] = ice_dummy_vlan_packet_offsets[0]; + } + + for (i = 1; dummy_pkt->offsets[i].type != ICE_PROTOCOL_LAST; i++) { + offsets[i + num_vlan].type = dummy_pkt->offsets[i].type; + offsets[i + num_vlan].offset = + dummy_pkt->offsets[i].offset + off; + } + offsets[i + num_vlan] = dummy_pkt->offsets[i]; + + etype_off = dummy_pkt->offsets[1].offset; + + buf_len = array_size(num_vlan, sizeof(ice_dummy_vlan_packet)) + + dummy_pkt->pkt_len; + pkt = kzalloc(buf_len, GFP_KERNEL); + if (!pkt) { + kfree(offsets); + return ERR_PTR(-ENOMEM); + } + + memcpy(pkt, dummy_pkt->pkt, etype_off); + memcpy(pkt + etype_off, + num_vlan == 2 ? ice_dummy_qinq_packet : ice_dummy_vlan_packet, + off); + memcpy(pkt + etype_off + off, dummy_pkt->pkt + etype_off, + dummy_pkt->pkt_len - etype_off); + + profile = kzalloc(sizeof(*profile), GFP_KERNEL); + if (!profile) { + kfree(offsets); + kfree(pkt); + return ERR_PTR(-ENOMEM); + } + + profile->offsets = offsets; + profile->pkt = pkt; + profile->pkt_len = buf_len; + profile->match |= ICE_PKT_KMALLOC; + + return profile; +} + +/** * ice_find_dummy_packet - find dummy packet * * @lkups: lookup elements or match criteria for the advanced recipe, one * structure per protocol header * @lkups_cnt: number of protocols * @tun_type: tunnel type - * @pkt: dummy packet to fill according to filter match criteria - * @pkt_len: packet length of dummy packet - * @offsets: pointer to receive the pointer to the offsets for the packet + * + * Returns the &ice_dummy_pkt_profile corresponding to these lookup params. */ -static void +static const struct ice_dummy_pkt_profile * ice_find_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, - enum ice_sw_tunnel_type tun_type, - const u8 **pkt, u16 *pkt_len, - const struct ice_dummy_pkt_offsets **offsets) + enum ice_sw_tunnel_type tun_type) { - bool tcp = false, udp = false, ipv6 = false, vlan = false; + const struct ice_dummy_pkt_profile *ret = ice_dummy_pkt_profiles; + u32 match = 0, vlan_count = 0; u16 i; + switch (tun_type) { + case ICE_SW_TUN_GTPC: + match |= ICE_PKT_TUN_GTPC; + break; + case ICE_SW_TUN_GTPU: + match |= ICE_PKT_TUN_GTPU; + break; + case ICE_SW_TUN_NVGRE: + match |= ICE_PKT_TUN_NVGRE; + break; + case ICE_SW_TUN_GENEVE: + case ICE_SW_TUN_VXLAN: + match |= ICE_PKT_TUN_UDP; + break; + default: + break; + } + for (i = 0; i < lkups_cnt; i++) { if (lkups[i].type == ICE_UDP_ILOS) - udp = true; + match |= ICE_PKT_INNER_UDP; else if (lkups[i].type == ICE_TCP_IL) - tcp = true; + match |= ICE_PKT_INNER_TCP; else if (lkups[i].type == ICE_IPV6_OFOS) - ipv6 = true; - else if (lkups[i].type == ICE_VLAN_OFOS) - vlan = true; + match |= ICE_PKT_OUTER_IPV6; + else if (lkups[i].type == ICE_VLAN_OFOS || + lkups[i].type == ICE_VLAN_EX) + vlan_count++; + else if (lkups[i].type == ICE_VLAN_IN) + vlan_count++; else if (lkups[i].type == ICE_ETYPE_OL && lkups[i].h_u.ethertype.ethtype_id == cpu_to_be16(ICE_IPV6_ETHER_ID) && lkups[i].m_u.ethertype.ethtype_id == - cpu_to_be16(0xFFFF)) - ipv6 = true; - } - - if (tun_type == ICE_SW_TUN_NVGRE) { - if (tcp) { - *pkt = dummy_gre_tcp_packet; - *pkt_len = sizeof(dummy_gre_tcp_packet); - *offsets = dummy_gre_tcp_packet_offsets; - return; - } - - *pkt = dummy_gre_udp_packet; - *pkt_len = sizeof(dummy_gre_udp_packet); - *offsets = dummy_gre_udp_packet_offsets; - return; + cpu_to_be16(0xFFFF)) + match |= ICE_PKT_OUTER_IPV6; + else if (lkups[i].type == ICE_ETYPE_IL && + lkups[i].h_u.ethertype.ethtype_id == + cpu_to_be16(ICE_IPV6_ETHER_ID) && + lkups[i].m_u.ethertype.ethtype_id == + cpu_to_be16(0xFFFF)) + match |= ICE_PKT_INNER_IPV6; + else if (lkups[i].type == ICE_IPV6_IL) + match |= ICE_PKT_INNER_IPV6; + else if (lkups[i].type == ICE_GTP_NO_PAY) + match |= ICE_PKT_GTP_NOPAY; + else if (lkups[i].type == ICE_PPPOE) { + match |= ICE_PKT_PPPOE; + if (lkups[i].h_u.pppoe_hdr.ppp_prot_id == + htons(PPP_IPV6)) + match |= ICE_PKT_OUTER_IPV6; + } else if (lkups[i].type == ICE_L2TPV3) + match |= ICE_PKT_L2TPV3; } - if (tun_type == ICE_SW_TUN_VXLAN || - tun_type == ICE_SW_TUN_GENEVE) { - if (tcp) { - *pkt = dummy_udp_tun_tcp_packet; - *pkt_len = sizeof(dummy_udp_tun_tcp_packet); - *offsets = dummy_udp_tun_tcp_packet_offsets; - return; - } - - *pkt = dummy_udp_tun_udp_packet; - *pkt_len = sizeof(dummy_udp_tun_udp_packet); - *offsets = dummy_udp_tun_udp_packet_offsets; - return; - } + while (ret->match && (match & ret->match) != ret->match) + ret++; - if (udp && !ipv6) { - if (vlan) { - *pkt = dummy_vlan_udp_packet; - *pkt_len = sizeof(dummy_vlan_udp_packet); - *offsets = dummy_vlan_udp_packet_offsets; - return; - } - *pkt = dummy_udp_packet; - *pkt_len = sizeof(dummy_udp_packet); - *offsets = dummy_udp_packet_offsets; - return; - } else if (udp && ipv6) { - if (vlan) { - *pkt = dummy_vlan_udp_ipv6_packet; - *pkt_len = sizeof(dummy_vlan_udp_ipv6_packet); - *offsets = dummy_vlan_udp_ipv6_packet_offsets; - return; - } - *pkt = dummy_udp_ipv6_packet; - *pkt_len = sizeof(dummy_udp_ipv6_packet); - *offsets = dummy_udp_ipv6_packet_offsets; - return; - } else if ((tcp && ipv6) || ipv6) { - if (vlan) { - *pkt = dummy_vlan_tcp_ipv6_packet; - *pkt_len = sizeof(dummy_vlan_tcp_ipv6_packet); - *offsets = dummy_vlan_tcp_ipv6_packet_offsets; - return; - } - *pkt = dummy_tcp_ipv6_packet; - *pkt_len = sizeof(dummy_tcp_ipv6_packet); - *offsets = dummy_tcp_ipv6_packet_offsets; - return; - } + if (vlan_count != 0) + ret = ice_dummy_packet_add_vlan(ret, vlan_count); - if (vlan) { - *pkt = dummy_vlan_tcp_packet; - *pkt_len = sizeof(dummy_vlan_tcp_packet); - *offsets = dummy_vlan_tcp_packet_offsets; - } else { - *pkt = dummy_tcp_packet; - *pkt_len = sizeof(dummy_tcp_packet); - *offsets = dummy_tcp_packet_offsets; - } + return ret; } /** @@ -4838,15 +5680,12 @@ ice_find_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, * structure per protocol header * @lkups_cnt: number of protocols * @s_rule: stores rule information from the match criteria - * @dummy_pkt: dummy packet to fill according to filter match criteria - * @pkt_len: packet length of dummy packet - * @offsets: offset info for the dummy packet + * @profile: dummy packet profile (the template, its size and header offsets) */ static int ice_fill_adv_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, - struct ice_aqc_sw_rules_elem *s_rule, - const u8 *dummy_pkt, u16 pkt_len, - const struct ice_dummy_pkt_offsets *offsets) + struct ice_sw_rule_lkup_rx_tx *s_rule, + const struct ice_dummy_pkt_profile *profile) { u8 *pkt; u16 i; @@ -4854,11 +5693,12 @@ ice_fill_adv_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, /* Start with a packet with a pre-defined/dummy content. Then, fill * in the header values to be looked up or matched. */ - pkt = s_rule->pdata.lkup_tx_rx.hdr; + pkt = s_rule->hdr_data; - memcpy(pkt, dummy_pkt, pkt_len); + memcpy(pkt, profile->pkt, profile->pkt_len); for (i = 0; i < lkups_cnt; i++) { + const struct ice_dummy_pkt_offsets *offsets = profile->offsets; enum ice_protocol_type type; u16 offset = 0, len = 0, j; bool found = false; @@ -4884,9 +5724,12 @@ ice_fill_adv_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, len = sizeof(struct ice_ether_hdr); break; case ICE_ETYPE_OL: + case ICE_ETYPE_IL: len = sizeof(struct ice_ethtype_hdr); break; case ICE_VLAN_OFOS: + case ICE_VLAN_EX: + case ICE_VLAN_IN: len = sizeof(struct ice_vlan_hdr); break; case ICE_IPV4_OFOS: @@ -4912,6 +5755,16 @@ ice_fill_adv_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, case ICE_GENEVE: len = sizeof(struct ice_udp_tnl_hdr); break; + case ICE_GTP_NO_PAY: + case ICE_GTP: + len = sizeof(struct ice_udp_gtp_hdr); + break; + case ICE_PPPOE: + len = sizeof(struct ice_pppoe_hdr); + break; + case ICE_L2TPV3: + len = sizeof(struct ice_l2tpv3_sess_hdr); + break; default: return -EINVAL; } @@ -4927,16 +5780,18 @@ ice_fill_adv_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, * indicated by the mask to make sure we don't improperly write * over any significant packet data. */ - for (j = 0; j < len / sizeof(u16); j++) - if (((u16 *)&lkups[i].m_u)[j]) - ((u16 *)(pkt + offset))[j] = - (((u16 *)(pkt + offset))[j] & - ~((u16 *)&lkups[i].m_u)[j]) | - (((u16 *)&lkups[i].h_u)[j] & - ((u16 *)&lkups[i].m_u)[j]); + for (j = 0; j < len / sizeof(u16); j++) { + u16 *ptr = (u16 *)(pkt + offset); + u16 mask = lkups[i].m_raw[j]; + + if (!mask) + continue; + + ptr[j] = (ptr[j] & ~mask) | (lkups[i].h_raw[j] & mask); + } } - s_rule->pdata.lkup_tx_rx.hdr_len = cpu_to_le16(pkt_len); + s_rule->hdr_len = cpu_to_le16(profile->pkt_len); return 0; } @@ -4986,6 +5841,36 @@ ice_fill_adv_packet_tun(struct ice_hw *hw, enum ice_sw_tunnel_type tun_type, } /** + * ice_fill_adv_packet_vlan - fill dummy packet with VLAN tag type + * @vlan_type: VLAN tag type + * @pkt: dummy packet to fill in + * @offsets: offset info for the dummy packet + */ +static int +ice_fill_adv_packet_vlan(u16 vlan_type, u8 *pkt, + const struct ice_dummy_pkt_offsets *offsets) +{ + u16 i; + + /* Find VLAN header and insert VLAN TPID */ + for (i = 0; offsets[i].type != ICE_PROTOCOL_LAST; i++) { + if (offsets[i].type == ICE_VLAN_OFOS || + offsets[i].type == ICE_VLAN_EX) { + struct ice_vlan_hdr *hdr; + u16 offset; + + offset = offsets[i].offset; + hdr = (struct ice_vlan_hdr *)&pkt[offset]; + hdr->type = cpu_to_be16(vlan_type); + + return 0; + } + } + + return -EIO; +} + +/** * ice_find_adv_rule_entry - Search a rule entry * @hw: pointer to the hardware structure * @lkups: lookup elements or match criteria for the advanced recipe, one @@ -5020,6 +5905,7 @@ ice_find_adv_rule_entry(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, } if (rinfo->sw_act.flag == list_itr->rule_info.sw_act.flag && rinfo->tun_type == list_itr->rule_info.tun_type && + rinfo->vlan_type == list_itr->rule_info.vlan_type && lkups_matched) return list_itr; } @@ -5159,12 +6045,11 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, struct ice_rule_query_data *added_entry) { struct ice_adv_fltr_mgmt_list_entry *m_entry, *adv_fltr = NULL; - u16 rid = 0, i, pkt_len, rule_buf_sz, vsi_handle; - const struct ice_dummy_pkt_offsets *pkt_offsets; - struct ice_aqc_sw_rules_elem *s_rule = NULL; + struct ice_sw_rule_lkup_rx_tx *s_rule = NULL; + const struct ice_dummy_pkt_profile *profile; + u16 rid = 0, i, rule_buf_sz, vsi_handle; struct list_head *rule_head; struct ice_switch_info *sw; - const u8 *pkt = NULL; u16 word_cnt; u32 act = 0; int status; @@ -5182,34 +6067,37 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, /* get # of words we need to match */ word_cnt = 0; for (i = 0; i < lkups_cnt; i++) { - u16 j, *ptr; + u16 j; - ptr = (u16 *)&lkups[i].m_u; - for (j = 0; j < sizeof(lkups->m_u) / sizeof(u16); j++) - if (ptr[j] != 0) + for (j = 0; j < ARRAY_SIZE(lkups->m_raw); j++) + if (lkups[i].m_raw[j]) word_cnt++; } - if (!word_cnt || word_cnt > ICE_MAX_CHAIN_WORDS) + if (!word_cnt) return -EINVAL; - /* make sure that we can locate a dummy packet */ - ice_find_dummy_packet(lkups, lkups_cnt, rinfo->tun_type, &pkt, &pkt_len, - &pkt_offsets); - if (!pkt) { - status = -EINVAL; - goto err_ice_add_adv_rule; - } + if (word_cnt > ICE_MAX_CHAIN_WORDS) + return -ENOSPC; + + /* locate a dummy packet */ + profile = ice_find_dummy_packet(lkups, lkups_cnt, rinfo->tun_type); + if (IS_ERR(profile)) + return PTR_ERR(profile); 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)) - return -EIO; + rinfo->sw_act.fltr_act == ICE_DROP_PACKET)) { + status = -EIO; + goto free_pkt_profile; + } vsi_handle = rinfo->sw_act.vsi_handle; - if (!ice_is_vsi_valid(hw, vsi_handle)) - return -EINVAL; + if (!ice_is_vsi_valid(hw, vsi_handle)) { + status = -EINVAL; + goto free_pkt_profile; + } if (rinfo->sw_act.fltr_act == ICE_FWD_TO_VSI) rinfo->sw_act.fwd_id.hw_vsi_id = @@ -5219,7 +6107,7 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, status = ice_add_adv_recipe(hw, lkups, lkups_cnt, rinfo, &rid); if (status) - return status; + goto free_pkt_profile; m_entry = ice_find_adv_rule_entry(hw, lkups, lkups_cnt, rid, rinfo); if (m_entry) { /* we have to add VSI to VSI_LIST and increment vsi_count. @@ -5238,12 +6126,14 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, added_entry->rule_id = m_entry->rule_info.fltr_rule_id; added_entry->vsi_handle = rinfo->sw_act.vsi_handle; } - return status; + goto free_pkt_profile; } - rule_buf_sz = ICE_SW_RULE_RX_TX_NO_HDR_SIZE + pkt_len; + rule_buf_sz = ICE_SW_RULE_RX_TX_HDR_SIZE(s_rule, profile->pkt_len); s_rule = kzalloc(rule_buf_sz, GFP_KERNEL); - if (!s_rule) - return -ENOMEM; + if (!s_rule) { + status = -ENOMEM; + goto free_pkt_profile; + } if (!rinfo->flags_info.act_valid) { act |= ICE_SINGLE_ACT_LAN_ENABLE; act |= ICE_SINGLE_ACT_LB_ENABLE; @@ -5289,26 +6179,33 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, * by caller) */ if (rinfo->rx) { - s_rule->type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX); - s_rule->pdata.lkup_tx_rx.src = - cpu_to_le16(hw->port_info->lport); + s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX); + s_rule->src = cpu_to_le16(hw->port_info->lport); } else { - s_rule->type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_TX); - s_rule->pdata.lkup_tx_rx.src = cpu_to_le16(rinfo->sw_act.src); + s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_TX); + s_rule->src = cpu_to_le16(rinfo->sw_act.src); } - s_rule->pdata.lkup_tx_rx.recipe_id = cpu_to_le16(rid); - s_rule->pdata.lkup_tx_rx.act = cpu_to_le32(act); + s_rule->recipe_id = cpu_to_le16(rid); + s_rule->act = cpu_to_le32(act); - status = ice_fill_adv_dummy_packet(lkups, lkups_cnt, s_rule, pkt, - pkt_len, pkt_offsets); + status = ice_fill_adv_dummy_packet(lkups, lkups_cnt, s_rule, profile); if (status) goto err_ice_add_adv_rule; - if (rinfo->tun_type != ICE_NON_TUN) { + if (rinfo->tun_type != ICE_NON_TUN && + rinfo->tun_type != ICE_SW_TUN_AND_NON_TUN) { status = ice_fill_adv_packet_tun(hw, rinfo->tun_type, - s_rule->pdata.lkup_tx_rx.hdr, - pkt_offsets); + s_rule->hdr_data, + profile->offsets); + if (status) + goto err_ice_add_adv_rule; + } + + if (rinfo->vlan_type != 0 && ice_is_dvm_ena(hw)) { + status = ice_fill_adv_packet_vlan(rinfo->vlan_type, + s_rule->hdr_data, + profile->offsets); if (status) goto err_ice_add_adv_rule; } @@ -5335,8 +6232,7 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, adv_fltr->lkups_cnt = lkups_cnt; adv_fltr->rule_info = *rinfo; - adv_fltr->rule_info.fltr_rule_id = - le16_to_cpu(s_rule->pdata.lkup_tx_rx.index); + adv_fltr->rule_info.fltr_rule_id = le16_to_cpu(s_rule->index); sw = hw->switch_info; sw->recp_list[rid].adv_rule = true; rule_head = &sw->recp_list[rid].filt_rules; @@ -5359,6 +6255,13 @@ err_ice_add_adv_rule: kfree(s_rule); +free_pkt_profile: + if (profile->match & ICE_PKT_KMALLOC) { + kfree(profile->offsets); + kfree(profile->pkt); + kfree(profile); + } + return status; } @@ -5551,7 +6454,7 @@ ice_rem_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, /* Create any special protocol/offset pairs, such as looking at tunnel * bits by extracting metadata */ - status = ice_add_special_words(rinfo, &lkup_exts); + status = ice_add_special_words(rinfo, &lkup_exts, ice_is_dvm_ena(hw)); if (status) return status; @@ -5584,17 +6487,16 @@ ice_rem_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, } mutex_unlock(rule_lock); if (remove_rule) { - struct ice_aqc_sw_rules_elem *s_rule; + struct ice_sw_rule_lkup_rx_tx *s_rule; u16 rule_buf_sz; - rule_buf_sz = ICE_SW_RULE_RX_TX_NO_HDR_SIZE; + rule_buf_sz = ICE_SW_RULE_RX_TX_NO_HDR_SIZE(s_rule); s_rule = kzalloc(rule_buf_sz, GFP_KERNEL); if (!s_rule) return -ENOMEM; - s_rule->pdata.lkup_tx_rx.act = 0; - s_rule->pdata.lkup_tx_rx.index = - cpu_to_le16(list_elem->rule_info.fltr_rule_id); - s_rule->pdata.lkup_tx_rx.hdr_len = 0; + s_rule->act = 0; + s_rule->index = cpu_to_le16(list_elem->rule_info.fltr_rule_id); + s_rule->hdr_len = 0; status = ice_aq_sw_rules(hw, (struct ice_aqc_sw_rules *)s_rule, rule_buf_sz, 1, ice_aqc_opc_remove_sw_rules, NULL); diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h index d8334beaaa8a..68d8e8a6a189 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.h +++ b/drivers/net/ethernet/intel/ice/ice_switch.h @@ -14,8 +14,14 @@ #define ICE_VSI_INVAL_ID 0xffff #define ICE_INVAL_Q_HANDLE 0xFFFF -#define ICE_SW_RULE_RX_TX_NO_HDR_SIZE \ - (offsetof(struct ice_aqc_sw_rules_elem, pdata.lkup_tx_rx.hdr)) +/* Switch Profile IDs for Profile related switch rules */ +#define ICE_PROFID_IPV4_GTPC_TEID 41 +#define ICE_PROFID_IPV4_GTPC_NO_TEID 42 +#define ICE_PROFID_IPV4_GTPU_TEID 43 +#define ICE_PROFID_IPV6_GTPC_TEID 44 +#define ICE_PROFID_IPV6_GTPC_NO_TEID 45 +#define ICE_PROFID_IPV6_GTPU_TEID 46 +#define ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER 70 /* VSI context structure for add/get/update/free operations */ struct ice_vsi_ctx { @@ -33,15 +39,6 @@ struct ice_vsi_ctx { struct ice_q_ctx *rdma_q_ctx[ICE_MAX_TRAFFIC_CLASS]; }; -enum ice_sw_fwd_act_type { - ICE_FWD_TO_VSI = 0, - ICE_FWD_TO_VSI_LIST, /* Do not use this when adding filter */ - ICE_FWD_TO_Q, - ICE_FWD_TO_QGRP, - ICE_DROP_PACKET, - ICE_INVAL_ACT -}; - /* Switch recipe ID enum values are specific to hardware */ enum ice_sw_lkup_type { ICE_SW_LKUP_ETHERTYPE = 0, @@ -86,6 +83,8 @@ struct ice_fltr_info { } mac_vlan; struct { u16 vlan_id; + u16 tpid; + u8 tpid_valid; } vlan; /* Set lkup_type as ICE_SW_LKUP_ETHERTYPE * if just using ethertype as filter. Set lkup_type as @@ -125,10 +124,27 @@ struct ice_fltr_info { u8 lan_en; /* Indicate if packet can be forwarded to the uplink */ }; +struct ice_update_recipe_lkup_idx_params { + u16 rid; + u16 fv_idx; + bool ignore_valid; + u16 mask; + bool mask_valid; + u8 lkup_idx; +}; + struct ice_adv_lkup_elem { enum ice_protocol_type type; - union ice_prot_hdr h_u; /* Header values */ - union ice_prot_hdr m_u; /* Mask of header values to match */ + union { + union ice_prot_hdr h_u; /* Header values */ + /* Used to iterate over the headers */ + u16 h_raw[sizeof(union ice_prot_hdr) / sizeof(u16)]; + }; + union { + union ice_prot_hdr m_u; /* Mask of header values to match */ + /* Used to iterate over header mask */ + u16 m_raw[sizeof(union ice_prot_hdr) / sizeof(u16)]; + }; }; struct ice_sw_act_ctrl { @@ -176,6 +192,7 @@ struct ice_adv_rule_info { u32 priority; u8 rx; /* true means LOOKUP_RX otherwise LOOKUP_TX */ u16 fltr_rule_id; + u16 vlan_type; struct ice_adv_rule_flags_info flags_info; }; @@ -342,7 +359,13 @@ int ice_cfg_rdma_fltr(struct ice_hw *hw, u16 vsi_handle, bool enable); void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_handle); /* Promisc/defport setup for VSIs */ -int ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_handle, bool set, u8 direction); +int +ice_cfg_dflt_vsi(struct ice_port_info *pi, u16 vsi_handle, bool set, + u8 direction); +bool +ice_check_if_dflt_vsi(struct ice_port_info *pi, u16 vsi_handle, + bool *rule_exists); + int ice_set_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, u16 vid); @@ -367,4 +390,8 @@ void ice_rm_all_sw_replay_rule_info(struct ice_hw *hw); int ice_aq_sw_rules(struct ice_hw *hw, void *rule_list, u16 rule_list_sz, u8 num_rules, enum ice_adminq_opc opc, struct ice_sq_cd *cd); +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); #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 e8aab664270a..f68c555be4e9 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -24,18 +24,26 @@ ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers, if (flags & ICE_TC_FLWR_FIELD_TENANT_ID) lkups_cnt++; + if (flags & ICE_TC_FLWR_FIELD_ENC_DST_MAC) + lkups_cnt++; + + if (flags & ICE_TC_FLWR_FIELD_ENC_OPTS) + lkups_cnt++; + if (flags & (ICE_TC_FLWR_FIELD_ENC_SRC_IPV4 | ICE_TC_FLWR_FIELD_ENC_DEST_IPV4 | ICE_TC_FLWR_FIELD_ENC_SRC_IPV6 | ICE_TC_FLWR_FIELD_ENC_DEST_IPV6)) lkups_cnt++; + if (flags & (ICE_TC_FLWR_FIELD_ENC_IP_TOS | + ICE_TC_FLWR_FIELD_ENC_IP_TTL)) + lkups_cnt++; + if (flags & ICE_TC_FLWR_FIELD_ENC_DEST_L4_PORT) lkups_cnt++; - /* currently inner etype filter isn't supported */ - if ((flags & ICE_TC_FLWR_FIELD_ETH_TYPE_ID) && - fltr->tunnel_type == TNL_LAST) + if (flags & ICE_TC_FLWR_FIELD_ETH_TYPE_ID) lkups_cnt++; /* are MAC fields specified? */ @@ -43,7 +51,16 @@ ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers, lkups_cnt++; /* is VLAN specified? */ - if (flags & ICE_TC_FLWR_FIELD_VLAN) + if (flags & (ICE_TC_FLWR_FIELD_VLAN | ICE_TC_FLWR_FIELD_VLAN_PRIO)) + lkups_cnt++; + + /* is CVLAN specified? */ + if (flags & (ICE_TC_FLWR_FIELD_CVLAN | ICE_TC_FLWR_FIELD_CVLAN_PRIO)) + lkups_cnt++; + + /* are PPPoE options specified? */ + if (flags & (ICE_TC_FLWR_FIELD_PPPOE_SESSID | + ICE_TC_FLWR_FIELD_PPP_PROTO)) lkups_cnt++; /* are IPv[4|6] fields specified? */ @@ -51,6 +68,13 @@ ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers, ICE_TC_FLWR_FIELD_DEST_IPV6 | ICE_TC_FLWR_FIELD_SRC_IPV6)) lkups_cnt++; + if (flags & (ICE_TC_FLWR_FIELD_IP_TOS | ICE_TC_FLWR_FIELD_IP_TTL)) + lkups_cnt++; + + /* are L2TPv3 options specified? */ + if (flags & ICE_TC_FLWR_FIELD_L2TPV3_SESSID) + lkups_cnt++; + /* is L4 (TCP/UDP/any other L4 protocol fields) specified? */ if (flags & (ICE_TC_FLWR_FIELD_DEST_L4_PORT | ICE_TC_FLWR_FIELD_SRC_L4_PORT)) @@ -64,6 +88,11 @@ static enum ice_protocol_type ice_proto_type_from_mac(bool inner) return inner ? ICE_MAC_IL : ICE_MAC_OFOS; } +static enum ice_protocol_type ice_proto_type_from_etype(bool inner) +{ + return inner ? ICE_ETYPE_IL : ICE_ETYPE_OL; +} + static enum ice_protocol_type ice_proto_type_from_ipv4(bool inner) { return inner ? ICE_IPV4_IL : ICE_IPV4_OFOS; @@ -96,6 +125,11 @@ ice_proto_type_from_tunnel(enum ice_tunnel_type type) return ICE_GENEVE; case TNL_GRETAP: return ICE_NVGRE; + case TNL_GTPU: + /* NO_PAY profiles will not work with GTP-U */ + return ICE_GTP; + case TNL_GTPC: + return ICE_GTP_NO_PAY; default: return 0; } @@ -111,11 +145,27 @@ ice_sw_type_from_tunnel(enum ice_tunnel_type type) return ICE_SW_TUN_GENEVE; case TNL_GRETAP: return ICE_SW_TUN_NVGRE; + case TNL_GTPU: + return ICE_SW_TUN_GTPU; + case TNL_GTPC: + return ICE_SW_TUN_GTPC; default: return ICE_NON_TUN; } } +static u16 ice_check_supported_vlan_tpid(u16 vlan_tpid) +{ + switch (vlan_tpid) { + case ETH_P_8021Q: + case ETH_P_8021AD: + case ETH_P_QINQ1: + return vlan_tpid; + default: + return 0; + } +} + static int ice_tc_fill_tunnel_outer(u32 flags, struct ice_tc_flower_fltr *fltr, struct ice_adv_lkup_elem *list) @@ -137,7 +187,15 @@ ice_tc_fill_tunnel_outer(u32 flags, struct ice_tc_flower_fltr *fltr, break; case TNL_GRETAP: list[i].h_u.nvgre_hdr.tni_flow = fltr->tenant_id; - memcpy(&list[i].m_u.nvgre_hdr.tni_flow, "\xff\xff\xff\xff", 4); + memcpy(&list[i].m_u.nvgre_hdr.tni_flow, + "\xff\xff\xff\xff", 4); + i++; + break; + case TNL_GTPC: + case TNL_GTPU: + list[i].h_u.gtp_hdr.teid = fltr->tenant_id; + memcpy(&list[i].m_u.gtp_hdr.teid, + "\xff\xff\xff\xff", 4); i++; break; default: @@ -145,6 +203,33 @@ ice_tc_fill_tunnel_outer(u32 flags, struct ice_tc_flower_fltr *fltr, } } + if (flags & ICE_TC_FLWR_FIELD_ENC_DST_MAC) { + list[i].type = ice_proto_type_from_mac(false); + ether_addr_copy(list[i].h_u.eth_hdr.dst_addr, + hdr->l2_key.dst_mac); + ether_addr_copy(list[i].m_u.eth_hdr.dst_addr, + hdr->l2_mask.dst_mac); + i++; + } + + if (flags & ICE_TC_FLWR_FIELD_ENC_OPTS && + (fltr->tunnel_type == TNL_GTPU || fltr->tunnel_type == TNL_GTPC)) { + list[i].type = ice_proto_type_from_tunnel(fltr->tunnel_type); + + if (fltr->gtp_pdu_info_masks.pdu_type) { + list[i].h_u.gtp_hdr.pdu_type = + fltr->gtp_pdu_info_keys.pdu_type << 4; + memcpy(&list[i].m_u.gtp_hdr.pdu_type, "\xf0", 1); + } + + if (fltr->gtp_pdu_info_masks.qfi) { + list[i].h_u.gtp_hdr.qfi = fltr->gtp_pdu_info_keys.qfi; + memcpy(&list[i].m_u.gtp_hdr.qfi, "\x3f", 1); + } + + i++; + } + if (flags & (ICE_TC_FLWR_FIELD_ENC_SRC_IPV4 | ICE_TC_FLWR_FIELD_ENC_DEST_IPV4)) { list[i].type = ice_proto_type_from_ipv4(false); @@ -183,6 +268,50 @@ ice_tc_fill_tunnel_outer(u32 flags, struct ice_tc_flower_fltr *fltr, i++; } + if (fltr->inner_headers.l2_key.n_proto == htons(ETH_P_IP) && + (flags & (ICE_TC_FLWR_FIELD_ENC_IP_TOS | + ICE_TC_FLWR_FIELD_ENC_IP_TTL))) { + list[i].type = ice_proto_type_from_ipv4(false); + + if (flags & ICE_TC_FLWR_FIELD_ENC_IP_TOS) { + list[i].h_u.ipv4_hdr.tos = hdr->l3_key.tos; + list[i].m_u.ipv4_hdr.tos = hdr->l3_mask.tos; + } + + if (flags & ICE_TC_FLWR_FIELD_ENC_IP_TTL) { + list[i].h_u.ipv4_hdr.time_to_live = hdr->l3_key.ttl; + list[i].m_u.ipv4_hdr.time_to_live = hdr->l3_mask.ttl; + } + + i++; + } + + if (fltr->inner_headers.l2_key.n_proto == htons(ETH_P_IPV6) && + (flags & (ICE_TC_FLWR_FIELD_ENC_IP_TOS | + ICE_TC_FLWR_FIELD_ENC_IP_TTL))) { + struct ice_ipv6_hdr *hdr_h, *hdr_m; + + hdr_h = &list[i].h_u.ipv6_hdr; + hdr_m = &list[i].m_u.ipv6_hdr; + list[i].type = ice_proto_type_from_ipv6(false); + + if (flags & ICE_TC_FLWR_FIELD_ENC_IP_TOS) { + be32p_replace_bits(&hdr_h->be_ver_tc_flow, + hdr->l3_key.tos, + ICE_IPV6_HDR_TC_MASK); + be32p_replace_bits(&hdr_m->be_ver_tc_flow, + hdr->l3_mask.tos, + ICE_IPV6_HDR_TC_MASK); + } + + if (flags & ICE_TC_FLWR_FIELD_ENC_IP_TTL) { + hdr_h->hop_limit = hdr->l3_key.ttl; + hdr_m->hop_limit = hdr->l3_mask.ttl; + } + + i++; + } + if ((flags & ICE_TC_FLWR_FIELD_ENC_DEST_L4_PORT) && hdr->l3_key.ip_proto == IPPROTO_UDP) { list[i].type = ICE_UDP_OF; @@ -216,16 +345,21 @@ 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; + rule_info->vlan_type = vlan_tpid; + 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); headers = &tc_fltr->inner_headers; inner = true; - } else if (flags & ICE_TC_FLWR_FIELD_ETH_TYPE_ID) { - list[i].type = ICE_ETYPE_OL; + } + + if (flags & ICE_TC_FLWR_FIELD_ETH_TYPE_ID) { + list[i].type = ice_proto_type_from_etype(inner); list[i].h_u.ethertype.ethtype_id = headers->l2_key.n_proto; list[i].m_u.ethertype.ethtype_id = headers->l2_mask.n_proto; i++; @@ -255,10 +389,76 @@ ice_tc_fill_rules(struct ice_hw *hw, u32 flags, } /* copy VLAN info */ - if (flags & ICE_TC_FLWR_FIELD_VLAN) { - list[i].type = ICE_VLAN_OFOS; - list[i].h_u.vlan_hdr.vlan = headers->vlan_hdr.vlan_id; - list[i].m_u.vlan_hdr.vlan = cpu_to_be16(0xFFFF); + if (flags & (ICE_TC_FLWR_FIELD_VLAN | ICE_TC_FLWR_FIELD_VLAN_PRIO)) { + vlan_tpid = be16_to_cpu(headers->vlan_hdr.vlan_tpid); + rule_info->vlan_type = + ice_check_supported_vlan_tpid(vlan_tpid); + + if (flags & ICE_TC_FLWR_FIELD_CVLAN) + list[i].type = ICE_VLAN_EX; + else + list[i].type = ICE_VLAN_OFOS; + + if (flags & ICE_TC_FLWR_FIELD_VLAN) { + list[i].h_u.vlan_hdr.vlan = headers->vlan_hdr.vlan_id; + list[i].m_u.vlan_hdr.vlan = cpu_to_be16(0x0FFF); + } + + if (flags & ICE_TC_FLWR_FIELD_VLAN_PRIO) { + if (flags & ICE_TC_FLWR_FIELD_VLAN) { + list[i].m_u.vlan_hdr.vlan = cpu_to_be16(0xEFFF); + } else { + list[i].m_u.vlan_hdr.vlan = cpu_to_be16(0xE000); + list[i].h_u.vlan_hdr.vlan = 0; + } + list[i].h_u.vlan_hdr.vlan |= + headers->vlan_hdr.vlan_prio; + } + + i++; + } + + if (flags & (ICE_TC_FLWR_FIELD_CVLAN | ICE_TC_FLWR_FIELD_CVLAN_PRIO)) { + list[i].type = ICE_VLAN_IN; + + if (flags & ICE_TC_FLWR_FIELD_CVLAN) { + list[i].h_u.vlan_hdr.vlan = headers->cvlan_hdr.vlan_id; + list[i].m_u.vlan_hdr.vlan = cpu_to_be16(0x0FFF); + } + + if (flags & ICE_TC_FLWR_FIELD_CVLAN_PRIO) { + if (flags & ICE_TC_FLWR_FIELD_CVLAN) { + list[i].m_u.vlan_hdr.vlan = cpu_to_be16(0xEFFF); + } else { + list[i].m_u.vlan_hdr.vlan = cpu_to_be16(0xE000); + list[i].h_u.vlan_hdr.vlan = 0; + } + list[i].h_u.vlan_hdr.vlan |= + headers->cvlan_hdr.vlan_prio; + } + + i++; + } + + if (flags & (ICE_TC_FLWR_FIELD_PPPOE_SESSID | + ICE_TC_FLWR_FIELD_PPP_PROTO)) { + struct ice_pppoe_hdr *vals, *masks; + + vals = &list[i].h_u.pppoe_hdr; + masks = &list[i].m_u.pppoe_hdr; + + list[i].type = ICE_PPPOE; + + if (flags & ICE_TC_FLWR_FIELD_PPPOE_SESSID) { + vals->session_id = headers->pppoe_hdr.session_id; + masks->session_id = cpu_to_be16(0xFFFF); + } + + if (flags & ICE_TC_FLWR_FIELD_PPP_PROTO) { + vals->ppp_prot_id = headers->pppoe_hdr.ppp_proto; + masks->ppp_prot_id = cpu_to_be16(0xFFFF); + } + i++; } @@ -305,6 +505,61 @@ ice_tc_fill_rules(struct ice_hw *hw, u32 flags, i++; } + if (headers->l2_key.n_proto == htons(ETH_P_IP) && + (flags & (ICE_TC_FLWR_FIELD_IP_TOS | ICE_TC_FLWR_FIELD_IP_TTL))) { + list[i].type = ice_proto_type_from_ipv4(inner); + + if (flags & ICE_TC_FLWR_FIELD_IP_TOS) { + list[i].h_u.ipv4_hdr.tos = headers->l3_key.tos; + list[i].m_u.ipv4_hdr.tos = headers->l3_mask.tos; + } + + if (flags & ICE_TC_FLWR_FIELD_IP_TTL) { + list[i].h_u.ipv4_hdr.time_to_live = + headers->l3_key.ttl; + list[i].m_u.ipv4_hdr.time_to_live = + headers->l3_mask.ttl; + } + + i++; + } + + if (headers->l2_key.n_proto == htons(ETH_P_IPV6) && + (flags & (ICE_TC_FLWR_FIELD_IP_TOS | ICE_TC_FLWR_FIELD_IP_TTL))) { + struct ice_ipv6_hdr *hdr_h, *hdr_m; + + hdr_h = &list[i].h_u.ipv6_hdr; + hdr_m = &list[i].m_u.ipv6_hdr; + list[i].type = ice_proto_type_from_ipv6(inner); + + if (flags & ICE_TC_FLWR_FIELD_IP_TOS) { + be32p_replace_bits(&hdr_h->be_ver_tc_flow, + headers->l3_key.tos, + ICE_IPV6_HDR_TC_MASK); + be32p_replace_bits(&hdr_m->be_ver_tc_flow, + headers->l3_mask.tos, + ICE_IPV6_HDR_TC_MASK); + } + + if (flags & ICE_TC_FLWR_FIELD_IP_TTL) { + hdr_h->hop_limit = headers->l3_key.ttl; + hdr_m->hop_limit = headers->l3_mask.ttl; + } + + i++; + } + + if (flags & ICE_TC_FLWR_FIELD_L2TPV3_SESSID) { + list[i].type = ICE_L2TPV3; + + list[i].h_u.l2tpv3_sess_hdr.session_id = + headers->l2tpv3_hdr.session_id; + list[i].m_u.l2tpv3_sess_hdr.session_id = + cpu_to_be32(0xFFFFFFFF); + + i++; + } + /* copy L4 (src, dest) port */ if (flags & (ICE_TC_FLWR_FIELD_DEST_L4_PORT | ICE_TC_FLWR_FIELD_SRC_L4_PORT)) { @@ -344,6 +599,12 @@ static int ice_tc_tun_get_type(struct net_device *tunnel_dev) if (netif_is_gretap(tunnel_dev) || netif_is_ip6gretap(tunnel_dev)) return TNL_GRETAP; + + /* Assume GTP-U by default in case of GTP netdev. + * GTP-C may be selected later, based on enc_dst_port. + */ + if (netif_is_gtp(tunnel_dev)) + return TNL_GTPU; return TNL_LAST; } @@ -463,6 +724,7 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) */ fltr->rid = rule_added.rid; fltr->rule_id = rule_added.rule_id; + fltr->dest_id = rule_added.vsi_handle; exit: kfree(list); @@ -561,7 +823,6 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi, } else if (ret) { NL_SET_ERR_MSG_MOD(tc_fltr->extack, "Unable to add filter due to error"); - ret = -EIO; goto exit; } @@ -600,6 +861,31 @@ exit: } /** + * ice_tc_set_pppoe - Parse PPPoE fields from TC flower filter + * @match: Pointer to flow match structure + * @fltr: Pointer to filter structure + * @headers: Pointer to outer header fields + * @returns PPP protocol used in filter (ppp_ses or ppp_disc) + */ +static u16 +ice_tc_set_pppoe(struct flow_match_pppoe *match, + struct ice_tc_flower_fltr *fltr, + struct ice_tc_flower_lyr_2_4_hdrs *headers) +{ + if (match->mask->session_id) { + fltr->flags |= ICE_TC_FLWR_FIELD_PPPOE_SESSID; + headers->pppoe_hdr.session_id = match->key->session_id; + } + + if (match->mask->ppp_proto) { + fltr->flags |= ICE_TC_FLWR_FIELD_PPP_PROTO; + headers->pppoe_hdr.ppp_proto = match->key->ppp_proto; + } + + return be16_to_cpu(match->key->type); +} + +/** * ice_tc_set_ipv4 - Parse IPv4 addresses from TC flower filter * @match: Pointer to flow match structure * @fltr: Pointer to filter structure @@ -693,6 +979,40 @@ ice_tc_set_ipv6(struct flow_match_ipv6_addrs *match, } /** + * ice_tc_set_tos_ttl - Parse IP ToS/TTL from TC flower filter + * @match: Pointer to flow match structure + * @fltr: Pointer to filter structure + * @headers: inner or outer header fields + * @is_encap: set true for tunnel + */ +static void +ice_tc_set_tos_ttl(struct flow_match_ip *match, + struct ice_tc_flower_fltr *fltr, + struct ice_tc_flower_lyr_2_4_hdrs *headers, + bool is_encap) +{ + if (match->mask->tos) { + if (is_encap) + fltr->flags |= ICE_TC_FLWR_FIELD_ENC_IP_TOS; + else + fltr->flags |= ICE_TC_FLWR_FIELD_IP_TOS; + + headers->l3_key.tos = match->key->tos; + headers->l3_mask.tos = match->mask->tos; + } + + if (match->mask->ttl) { + if (is_encap) + fltr->flags |= ICE_TC_FLWR_FIELD_ENC_IP_TTL; + else + fltr->flags |= ICE_TC_FLWR_FIELD_IP_TTL; + + headers->l3_key.ttl = match->key->ttl; + headers->l3_mask.ttl = match->mask->ttl; + } +} + +/** * ice_tc_set_port - Parse ports from TC flower filter * @match: Flow match structure * @fltr: Pointer to filter structure @@ -709,7 +1029,7 @@ ice_tc_set_port(struct flow_match_ports match, fltr->flags |= ICE_TC_FLWR_FIELD_ENC_DEST_L4_PORT; else fltr->flags |= ICE_TC_FLWR_FIELD_DEST_L4_PORT; - fltr->flags |= ICE_TC_FLWR_FIELD_DEST_L4_PORT; + headers->l4_key.dst_port = match.key->dst; headers->l4_mask.dst_port = match.mask->dst; } @@ -718,7 +1038,7 @@ ice_tc_set_port(struct flow_match_ports match, fltr->flags |= ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT; else fltr->flags |= ICE_TC_FLWR_FIELD_SRC_L4_PORT; - fltr->flags |= ICE_TC_FLWR_FIELD_SRC_L4_PORT; + headers->l4_key.src_port = match.key->src; headers->l4_mask.src_port = match.mask->src; } @@ -743,6 +1063,40 @@ ice_get_tunnel_device(struct net_device *dev, struct flow_rule *rule) return NULL; } +/** + * ice_parse_gtp_type - Sets GTP tunnel type to GTP-U or GTP-C + * @match: Flow match structure + * @fltr: Pointer to filter structure + * + * GTP-C/GTP-U is selected based on destination port number (enc_dst_port). + * Before calling this funtcion, fltr->tunnel_type should be set to TNL_GTPU, + * therefore making GTP-U the default choice (when destination port number is + * not specified). + */ +static int +ice_parse_gtp_type(struct flow_match_ports match, + struct ice_tc_flower_fltr *fltr) +{ + u16 dst_port; + + if (match.key->dst) { + dst_port = be16_to_cpu(match.key->dst); + + switch (dst_port) { + case 2152: + break; + case 2123: + fltr->tunnel_type = TNL_GTPC; + break; + default: + NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported GTP port number"); + return -EINVAL; + } + } + + return 0; +} + static int ice_parse_tunnel_attr(struct net_device *dev, struct flow_rule *rule, struct ice_tc_flower_fltr *fltr) @@ -787,10 +1141,7 @@ ice_parse_tunnel_attr(struct net_device *dev, struct flow_rule *rule, struct flow_match_ip match; flow_rule_match_enc_ip(rule, &match); - headers->l3_key.tos = match.key->tos; - headers->l3_key.ttl = match.key->ttl; - headers->l3_mask.tos = match.mask->tos; - headers->l3_mask.ttl = match.mask->ttl; + ice_tc_set_tos_ttl(&match, fltr, headers, true); } if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS) && @@ -798,8 +1149,28 @@ ice_parse_tunnel_attr(struct net_device *dev, struct flow_rule *rule, struct flow_match_ports match; flow_rule_match_enc_ports(rule, &match); - if (ice_tc_set_port(match, fltr, headers, true)) - return -EINVAL; + + if (fltr->tunnel_type != TNL_GTPU) { + if (ice_tc_set_port(match, fltr, headers, true)) + return -EINVAL; + } else { + if (ice_parse_gtp_type(match, fltr)) + return -EINVAL; + } + } + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_OPTS)) { + struct flow_match_enc_opts match; + + flow_rule_match_enc_opts(rule, &match); + + memcpy(&fltr->gtp_pdu_info_keys, &match.key->data[0], + sizeof(struct gtp_pdu_session_info)); + + memcpy(&fltr->gtp_pdu_info_masks, &match.mask->data[0], + sizeof(struct gtp_pdu_session_info)); + + fltr->flags |= ICE_TC_FLWR_FIELD_ENC_OPTS; } return 0; @@ -830,6 +1201,7 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, 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) | @@ -837,8 +1209,12 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, 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_PORTS) | + BIT(FLOW_DISSECTOR_KEY_PPPOE) | + BIT(FLOW_DISSECTOR_KEY_L2TPV3))) { NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported key used"); return -EOPNOTSUPP; } @@ -878,7 +1254,9 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, n_proto_key = ntohs(match.key->n_proto); n_proto_mask = ntohs(match.mask->n_proto); - if (n_proto_key == ETH_P_ALL || n_proto_key == 0) { + if (n_proto_key == ETH_P_ALL || n_proto_key == 0 || + fltr->tunnel_type == TNL_GTPU || + fltr->tunnel_type == TNL_GTPC) { n_proto_key = 0; n_proto_mask = 0; } else { @@ -932,16 +1310,71 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, if (match.mask->vlan_id) { if (match.mask->vlan_id == VLAN_VID_MASK) { fltr->flags |= ICE_TC_FLWR_FIELD_VLAN; + headers->vlan_hdr.vlan_id = + cpu_to_be16(match.key->vlan_id & + VLAN_VID_MASK); } else { NL_SET_ERR_MSG_MOD(fltr->extack, "Bad VLAN mask"); return -EINVAL; } } - headers->vlan_hdr.vlan_id = - cpu_to_be16(match.key->vlan_id & VLAN_VID_MASK); - if (match.mask->vlan_priority) - headers->vlan_hdr.vlan_prio = match.key->vlan_priority; + if (match.mask->vlan_priority) { + fltr->flags |= ICE_TC_FLWR_FIELD_VLAN_PRIO; + headers->vlan_hdr.vlan_prio = + cpu_to_be16((match.key->vlan_priority << + VLAN_PRIO_SHIFT) & VLAN_PRIO_MASK); + } + + if (match.mask->vlan_tpid) + headers->vlan_hdr.vlan_tpid = match.key->vlan_tpid; + } + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CVLAN)) { + struct flow_match_vlan match; + + if (!ice_is_dvm_ena(&vsi->back->hw)) { + NL_SET_ERR_MSG_MOD(fltr->extack, "Double VLAN mode is not enabled"); + return -EINVAL; + } + + flow_rule_match_cvlan(rule, &match); + + if (match.mask->vlan_id) { + if (match.mask->vlan_id == VLAN_VID_MASK) { + fltr->flags |= ICE_TC_FLWR_FIELD_CVLAN; + headers->cvlan_hdr.vlan_id = + cpu_to_be16(match.key->vlan_id & + VLAN_VID_MASK); + } else { + NL_SET_ERR_MSG_MOD(fltr->extack, + "Bad CVLAN mask"); + return -EINVAL; + } + } + + if (match.mask->vlan_priority) { + fltr->flags |= ICE_TC_FLWR_FIELD_CVLAN_PRIO; + headers->cvlan_hdr.vlan_prio = + cpu_to_be16((match.key->vlan_priority << + VLAN_PRIO_SHIFT) & VLAN_PRIO_MASK); + } + } + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PPPOE)) { + struct flow_match_pppoe match; + + flow_rule_match_pppoe(rule, &match); + n_proto_key = ice_tc_set_pppoe(&match, fltr, headers); + + /* If ethertype equals ETH_P_PPP_SES, n_proto might be + * overwritten by encapsulated protocol (ppp_proto field) or set + * to 0. To correct this, flow_match_pppoe provides the type + * field, which contains the actual ethertype (ETH_P_PPP_SES). + */ + headers->l2_key.n_proto = cpu_to_be16(n_proto_key); + headers->l2_mask.n_proto = cpu_to_be16(0xFFFF); + fltr->flags |= ICE_TC_FLWR_FIELD_ETH_TYPE_ID; } if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { @@ -968,6 +1401,22 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, return -EINVAL; } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) { + struct flow_match_ip match; + + flow_rule_match_ip(rule, &match); + ice_tc_set_tos_ttl(&match, fltr, headers, false); + } + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_L2TPV3)) { + struct flow_match_l2tpv3 match; + + flow_rule_match_l2tpv3(rule, &match); + + fltr->flags |= ICE_TC_FLWR_FIELD_L2TPV3_SESSID; + headers->l2tpv3_hdr.session_id = match.key->session_id; + } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) { struct flow_match_ports match; @@ -1059,12 +1508,24 @@ ice_handle_tclass_action(struct ice_vsi *vsi, * this code won't do anything * 2. For non-tunnel, if user didn't specify MAC address, add implicit * dest MAC to be lower netdev's active unicast MAC address + * 3. For tunnel, as of now TC-filter through flower classifier doesn't + * have provision for user to specify outer DMAC, hence driver to + * implicitly add outer dest MAC to be lower netdev's active unicast + * MAC address. */ - if (!(fltr->flags & ICE_TC_FLWR_FIELD_DST_MAC)) { + if (fltr->tunnel_type != TNL_LAST && + !(fltr->flags & ICE_TC_FLWR_FIELD_ENC_DST_MAC)) + fltr->flags |= ICE_TC_FLWR_FIELD_ENC_DST_MAC; + + if (fltr->tunnel_type == TNL_LAST && + !(fltr->flags & ICE_TC_FLWR_FIELD_DST_MAC)) + fltr->flags |= ICE_TC_FLWR_FIELD_DST_MAC; + + if (fltr->flags & (ICE_TC_FLWR_FIELD_DST_MAC | + ICE_TC_FLWR_FIELD_ENC_DST_MAC)) { ether_addr_copy(fltr->outer_headers.l2_key.dst_mac, - main_vsi->netdev->dev_addr); + vsi->netdev->dev_addr); eth_broadcast_addr(fltr->outer_headers.l2_mask.dst_mac); - fltr->flags |= ICE_TC_FLWR_FIELD_DST_MAC; } /* validate specified dest MAC address, make sure either it belongs to diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.h b/drivers/net/ethernet/intel/ice/ice_tc_lib.h index 319049477959..92642faad595 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.h @@ -22,9 +22,22 @@ #define ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT BIT(15) #define ICE_TC_FLWR_FIELD_ENC_DST_MAC BIT(16) #define ICE_TC_FLWR_FIELD_ETH_TYPE_ID BIT(17) +#define ICE_TC_FLWR_FIELD_ENC_OPTS BIT(18) +#define ICE_TC_FLWR_FIELD_CVLAN BIT(19) +#define ICE_TC_FLWR_FIELD_PPPOE_SESSID BIT(20) +#define ICE_TC_FLWR_FIELD_PPP_PROTO BIT(21) +#define ICE_TC_FLWR_FIELD_IP_TOS BIT(22) +#define ICE_TC_FLWR_FIELD_IP_TTL BIT(23) +#define ICE_TC_FLWR_FIELD_ENC_IP_TOS BIT(24) +#define ICE_TC_FLWR_FIELD_ENC_IP_TTL BIT(25) +#define ICE_TC_FLWR_FIELD_L2TPV3_SESSID BIT(26) +#define ICE_TC_FLWR_FIELD_VLAN_PRIO BIT(27) +#define ICE_TC_FLWR_FIELD_CVLAN_PRIO BIT(28) #define ICE_TC_FLOWER_MASK_32 0xFFFFFFFF +#define ICE_IPV6_HDR_TC_MASK 0xFF00000 + struct ice_indr_block_priv { struct net_device *netdev; struct ice_netdev_priv *np; @@ -38,7 +51,13 @@ struct ice_tc_flower_action { struct ice_tc_vlan_hdr { __be16 vlan_id; /* Only last 12 bits valid */ - u16 vlan_prio; /* Only last 3 bits valid (valid values: 0..7) */ + __be16 vlan_prio; /* Only last 3 bits valid (valid values: 0..7) */ + __be16 vlan_tpid; +}; + +struct ice_tc_pppoe_hdr { + __be16 session_id; + __be16 ppp_proto; }; struct ice_tc_l2_hdr { @@ -70,6 +89,10 @@ struct ice_tc_l3_hdr { u8 ttl; }; +struct ice_tc_l2tpv3_hdr { + __be32 session_id; +}; + struct ice_tc_l4_hdr { __be16 dst_port; __be16 src_port; @@ -80,6 +103,9 @@ struct ice_tc_flower_lyr_2_4_hdrs { struct ice_tc_l2_hdr l2_key; struct ice_tc_l2_hdr l2_mask; struct ice_tc_vlan_hdr vlan_hdr; + struct ice_tc_vlan_hdr cvlan_hdr; + struct ice_tc_pppoe_hdr pppoe_hdr; + struct ice_tc_l2tpv3_hdr l2tpv3_hdr; /* L3 (IPv4[6]) layer fields with their mask */ struct ice_tc_l3_hdr l3_key; struct ice_tc_l3_hdr l3_mask; @@ -119,6 +145,8 @@ struct ice_tc_flower_fltr { struct ice_tc_flower_lyr_2_4_hdrs inner_headers; struct ice_vsi *src_vsi; __be32 tenant_id; + struct gtp_pdu_session_info gtp_pdu_info_keys; + struct gtp_pdu_session_info gtp_pdu_info_masks; u32 flags; u8 tunnel_type; struct ice_tc_flower_action action; diff --git a/drivers/net/ethernet/intel/ice/ice_trace.h b/drivers/net/ethernet/intel/ice/ice_trace.h index cf685247c07a..ae98d5a8ff60 100644 --- a/drivers/net/ethernet/intel/ice/ice_trace.h +++ b/drivers/net/ethernet/intel/ice/ice_trace.h @@ -216,6 +216,30 @@ DEFINE_EVENT(ice_xmit_template, name, \ DEFINE_XMIT_TEMPLATE_OP_EVENT(ice_xmit_frame_ring); DEFINE_XMIT_TEMPLATE_OP_EVENT(ice_xmit_frame_ring_drop); +DECLARE_EVENT_CLASS(ice_tx_tstamp_template, + TP_PROTO(struct sk_buff *skb, int idx), + + TP_ARGS(skb, idx), + + TP_STRUCT__entry(__field(void *, skb) + __field(int, idx)), + + TP_fast_assign(__entry->skb = skb; + __entry->idx = idx;), + + TP_printk("skb %pK idx %d", + __entry->skb, __entry->idx) +); +#define DEFINE_TX_TSTAMP_OP_EVENT(name) \ +DEFINE_EVENT(ice_tx_tstamp_template, name, \ + TP_PROTO(struct sk_buff *skb, int idx), \ + TP_ARGS(skb, idx)) + +DEFINE_TX_TSTAMP_OP_EVENT(ice_tx_tstamp_request); +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); + /* 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 3e38695f1c9d..dbe80e5053a8 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -8,6 +8,7 @@ #include <linux/prefetch.h> #include <linux/bpf_trace.h> #include <net/dsfield.h> +#include <net/mpls.h> #include <net/xdp.h> #include "ice_txrx_lib.h" #include "ice_lib.h" @@ -173,6 +174,8 @@ tx_skip_free: tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; + tx_ring->next_dd = ICE_RING_QUARTER(tx_ring) - 1; + tx_ring->next_rs = ICE_RING_QUARTER(tx_ring) - 1; if (!tx_ring->netdev) return; @@ -221,8 +224,7 @@ static bool ice_clean_tx_irq(struct ice_tx_ring *tx_ring, int napi_budget) struct ice_tx_buf *tx_buf; /* get the bql data ready */ - if (!ice_ring_is_xdp(tx_ring)) - netdev_txq_bql_complete_prefetchw(txring_txq(tx_ring)); + netdev_txq_bql_complete_prefetchw(txring_txq(tx_ring)); tx_buf = &tx_ring->tx_buf[i]; tx_desc = ICE_TX_DESC(tx_ring, i); @@ -311,10 +313,6 @@ static bool ice_clean_tx_irq(struct ice_tx_ring *tx_ring, int napi_budget) tx_ring->next_to_clean = i; ice_update_tx_ring_stats(tx_ring, total_pkts, total_bytes); - - if (ice_ring_is_xdp(tx_ring)) - return !!budget; - netdev_tx_completed_queue(txring_txq(tx_ring), total_pkts, total_bytes); #define TX_WAKE_THRESHOLD ((s16)(DESC_NEEDED * 2)) @@ -612,7 +610,7 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, if (test_bit(ICE_VSI_DOWN, vsi->state)) return -ENETDOWN; - if (!ice_is_xdp_ena_vsi(vsi) || queue_index >= vsi->num_xdp_txq) + if (!ice_is_xdp_ena_vsi(vsi)) return -ENXIO; if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) @@ -623,6 +621,9 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, xdp_ring = vsi->xdp_rings[queue_index]; spin_lock(&xdp_ring->tx_lock); } else { + /* Generally, should not happen */ + if (unlikely(queue_index >= vsi->num_xdp_txq)) + return -ENXIO; xdp_ring = vsi->xdp_rings[queue_index]; } @@ -983,15 +984,17 @@ static struct sk_buff * ice_construct_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf, struct xdp_buff *xdp) { + unsigned int metasize = xdp->data - xdp->data_meta; unsigned int size = xdp->data_end - xdp->data; unsigned int headlen; struct sk_buff *skb; /* prefetch first cache line of first page */ - net_prefetch(xdp->data); + net_prefetch(xdp->data_meta); /* allocate a skb to store the frags */ - skb = __napi_alloc_skb(&rx_ring->q_vector->napi, ICE_RX_HDR_SIZE, + skb = __napi_alloc_skb(&rx_ring->q_vector->napi, + ICE_RX_HDR_SIZE + metasize, GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL; @@ -1003,8 +1006,13 @@ ice_construct_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf, headlen = eth_get_headlen(skb->dev, xdp->data, ICE_RX_HDR_SIZE); /* align pull length to size of long to optimize memcpy performance */ - memcpy(__skb_put(skb, headlen), xdp->data, ALIGN(headlen, - sizeof(long))); + memcpy(__skb_put(skb, headlen + metasize), xdp->data_meta, + ALIGN(headlen + metasize, sizeof(long))); + + if (metasize) { + skb_metadata_set(skb, metasize); + __skb_pull(skb, metasize); + } /* if we exhaust the linear part then add what is left as a frag */ size -= headlen; @@ -1080,7 +1088,7 @@ ice_is_non_eop(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc) { /* if we are the last buffer then there is nothing else to do */ #define ICE_RXD_EOF BIT(ICE_RX_FLEX_DESC_STATUS0_EOF_S) - if (likely(ice_test_staterr(rx_desc, ICE_RXD_EOF))) + if (likely(ice_test_staterr(rx_desc->wb.status_error0, ICE_RXD_EOF))) return false; rx_ring->rx_stats.non_eop_descs++; @@ -1142,7 +1150,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) * hardware wrote DD then it will be non-zero */ stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_DD_S); - if (!ice_test_staterr(rx_desc, stat_err_bits)) + if (!ice_test_staterr(rx_desc->wb.status_error0, stat_err_bits)) break; /* This memory barrier is needed to keep us from reading @@ -1156,7 +1164,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) struct ice_vsi *ctrl_vsi = rx_ring->vsi; if (rx_desc->wb.rxdid == FDIR_DESC_RXDID && - ctrl_vsi->vf_id != ICE_INVAL_VFID) + ctrl_vsi->vf) ice_vc_fdir_irq_handler(ctrl_vsi, rx_desc); ice_put_rx_buf(rx_ring, NULL, 0); cleaned_count++; @@ -1228,14 +1236,13 @@ construct_skb: continue; stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S); - if (unlikely(ice_test_staterr(rx_desc, stat_err_bits))) { + if (unlikely(ice_test_staterr(rx_desc->wb.status_error0, + stat_err_bits))) { dev_kfree_skb_any(skb); continue; } - stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_L2TAG1P_S); - if (ice_test_staterr(rx_desc, stat_err_bits)) - vlan_tag = le16_to_cpu(rx_desc->wb.l2tag1); + vlan_tag = ice_get_vlan_tag_from_rx_desc(rx_desc); /* pad the skb if needed, to make a valid ethernet frame */ if (eth_skb_pad(skb)) { @@ -1460,7 +1467,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget) bool wd; if (tx_ring->xsk_pool) - wd = ice_clean_tx_irq_zc(tx_ring, budget); + wd = ice_xmit_zc(tx_ring); else if (ice_ring_is_xdp(tx_ring)) wd = true; else @@ -1513,7 +1520,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget) /* Exit the polling mode, but don't re-enable interrupts if stack might * poll us due to busy-polling */ - if (likely(napi_complete_done(napi, work_done))) { + if (napi_complete_done(napi, work_done)) { ice_net_dim(q_vector); ice_enable_interrupt(q_vector); } else { @@ -1745,18 +1752,26 @@ int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off) if (skb->ip_summed != CHECKSUM_PARTIAL) return 0; - ip.hdr = skb_network_header(skb); - l4.hdr = skb_transport_header(skb); + protocol = vlan_get_protocol(skb); + + if (eth_p_mpls(protocol)) { + ip.hdr = skb_inner_network_header(skb); + l4.hdr = skb_checksum_start(skb); + } else { + ip.hdr = skb_network_header(skb); + l4.hdr = skb_transport_header(skb); + } /* compute outer L2 header size */ l2_len = ip.hdr - skb->data; offset = (l2_len / 2) << ICE_TX_DESC_LEN_MACLEN_S; - protocol = vlan_get_protocol(skb); - - if (protocol == htons(ETH_P_IP)) + /* set the tx_flags to indicate the IP protocol type. this is + * required so that checksum header computation below is accurate. + */ + if (ip.v4->version == 4) first->tx_flags |= ICE_TX_FLAGS_IPV4; - else if (protocol == htons(ETH_P_IPV6)) + else if (ip.v6->version == 6) first->tx_flags |= ICE_TX_FLAGS_IPV6; if (skb->encapsulation) { @@ -1917,12 +1932,16 @@ ice_tx_prepare_vlan_flags(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first) if (!skb_vlan_tag_present(skb) && eth_type_vlan(skb->protocol)) return; - /* currently, we always assume 802.1Q for VLAN insertion as VLAN - * insertion for 802.1AD is not supported + /* the VLAN ethertype/tpid is determined by VSI configuration and netdev + * feature flags, which the driver only allows either 802.1Q or 802.1ad + * VLAN offloads exclusively so we only care about the VLAN ID here */ if (skb_vlan_tag_present(skb)) { first->tx_flags |= skb_vlan_tag_get(skb) << ICE_TX_FLAGS_VLAN_S; - first->tx_flags |= ICE_TX_FLAGS_HW_VLAN; + if (tx_ring->flags & ICE_TX_FLAGS_RING_VLAN_L2TAG2) + first->tx_flags |= ICE_TX_FLAGS_HW_OUTER_SINGLE_VLAN; + else + first->tx_flags |= ICE_TX_FLAGS_HW_VLAN; } ice_tx_prepare_vlan_flags_dcb(tx_ring, first); @@ -1950,6 +1969,7 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off) unsigned char *hdr; } l4; u64 cd_mss, cd_tso_len; + __be16 protocol; u32 paylen; u8 l4_start; int err; @@ -1965,8 +1985,13 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off) return err; /* cppcheck-suppress unreadVariable */ - ip.hdr = skb_network_header(skb); - l4.hdr = skb_transport_header(skb); + protocol = vlan_get_protocol(skb); + + if (eth_p_mpls(protocol)) + ip.hdr = skb_inner_network_header(skb); + else + ip.hdr = skb_network_header(skb); + l4.hdr = skb_checksum_start(skb); /* initialize outer IP header fields */ if (ip.v4->version == 4) { @@ -2233,8 +2258,10 @@ ice_tstamp(struct ice_tx_ring *tx_ring, struct sk_buff *skb, /* Grab an open timestamp slot */ idx = ice_ptp_request_ts(tx_ring->tx_tstamps, skb); - if (idx < 0) + if (idx < 0) { + tx_ring->vsi->back->ptp.tx_hwtstamp_skipped++; return; + } off->cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX | (ICE_TX_CTX_DESC_TSYN << ICE_TXD_CTX_QW1_CMD_S) | @@ -2295,6 +2322,13 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring) /* prepare the VLAN tagging flags for Tx */ ice_tx_prepare_vlan_flags(tx_ring, first); + if (first->tx_flags & ICE_TX_FLAGS_HW_OUTER_SINGLE_VLAN) { + offload.cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX | + (ICE_TX_CTX_DESC_IL2TAG2 << + ICE_TXD_CTX_QW1_CMD_S)); + offload.cd_l2tag2 = (first->tx_flags & ICE_TX_FLAGS_VLAN_M) >> + ICE_TX_FLAGS_VLAN_S; + } /* set up TSO offload */ tso = ice_tso(first, &offload); diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index b7b3bd4816f0..932b5661ec4d 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -13,7 +13,6 @@ #define ICE_MAX_CHAINED_RX_BUFS 5 #define ICE_MAX_BUF_TXD 8 #define ICE_MIN_TX_LEN 17 -#define ICE_TX_THRESH 32 /* The size limit for a transmit buffer in a descriptor is (16K - 1). * In order to align with the read requests we will align the value to @@ -111,6 +110,8 @@ static inline int ice_skb_pad(void) (u16)((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \ (R)->next_to_clean - (R)->next_to_use - 1) +#define ICE_RING_QUARTER(R) ((R)->count >> 2) + #define ICE_TX_FLAGS_TSO BIT(0) #define ICE_TX_FLAGS_HW_VLAN BIT(1) #define ICE_TX_FLAGS_SW_VLAN BIT(2) @@ -122,6 +123,7 @@ static inline int ice_skb_pad(void) #define ICE_TX_FLAGS_IPV4 BIT(5) #define ICE_TX_FLAGS_IPV6 BIT(6) #define ICE_TX_FLAGS_TUNNEL BIT(7) +#define ICE_TX_FLAGS_HW_OUTER_SINGLE_VLAN BIT(8) #define ICE_TX_FLAGS_VLAN_M 0xffff0000 #define ICE_TX_FLAGS_VLAN_PR_M 0xe0000000 #define ICE_TX_FLAGS_VLAN_PR_S 29 @@ -131,6 +133,7 @@ static inline int ice_skb_pad(void) #define ICE_XDP_CONSUMED BIT(0) #define ICE_XDP_TX BIT(1) #define ICE_XDP_REDIR BIT(2) +#define ICE_XDP_EXIT BIT(3) #define ICE_RX_DMA_ATTR \ (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) @@ -292,10 +295,11 @@ struct ice_rx_ring { struct xsk_buff_pool *xsk_pool; struct sk_buff *skb; dma_addr_t dma; /* physical address of ring */ -#define ICE_RX_FLAGS_RING_BUILD_SKB BIT(1) u64 cached_phctime; u8 dcb_tc; /* Traffic class of ring */ u8 ptp_rx; +#define ICE_RX_FLAGS_RING_BUILD_SKB BIT(1) +#define ICE_RX_FLAGS_CRC_STRIP_DIS BIT(2) u8 flags; } ____cacheline_internodealigned_in_smp; @@ -321,18 +325,21 @@ struct ice_tx_ring { u16 count; /* Number of descriptors */ u16 q_index; /* Queue number of ring */ /* stats structs */ - struct ice_q_stats stats; - struct u64_stats_sync syncp; struct ice_txq_stats tx_stats; - /* CL3 - 3rd cacheline starts here */ + struct ice_q_stats stats; + struct u64_stats_sync syncp; struct rcu_head rcu; /* to avoid race on free */ DECLARE_BITMAP(xps_state, ICE_TX_NBITS); /* XPS Config State */ struct ice_channel *ch; struct ice_ptp_tx *tx_tstamps; spinlock_t tx_lock; u32 txq_teid; /* Added Tx queue TEID */ + /* CL4 - 4th cacheline starts here */ + u16 xdp_tx_active; #define ICE_TX_FLAGS_RING_XDP BIT(0) +#define ICE_TX_FLAGS_RING_VLAN_L2TAG1 BIT(1) +#define ICE_TX_FLAGS_RING_VLAN_L2TAG2 BIT(2) u8 flags; u8 dcb_tc; /* Traffic class of ring */ u8 ptp_tx; @@ -379,9 +386,14 @@ struct ice_ring_container { /* this matches the maximum number of ITR bits, but in usec * values, so it is shifted left one bit (bit zero is ignored) */ - u16 itr_setting:13; - u16 itr_reserved:2; - u16 itr_mode:1; + union { + struct { + u16 itr_setting:13; + u16 itr_reserved:2; + u16 itr_mode:1; + }; + u16 itr_settings; + }; enum ice_container_type type; }; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c index 0e87b98e0966..7ee38d02d1e5 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c @@ -209,9 +209,14 @@ ice_process_skb_fields(struct ice_rx_ring *rx_ring, void ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag) { - if ((rx_ring->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) && - (vlan_tag & VLAN_VID_MASK)) + netdev_features_t features = rx_ring->netdev->features; + bool non_zero_vlan = !!(vlan_tag & VLAN_VID_MASK); + + if ((features & NETIF_F_HW_VLAN_CTAG_RX) && non_zero_vlan) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tag); + else if ((features & NETIF_F_HW_VLAN_STAG_RX) && non_zero_vlan) + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021AD), vlan_tag); + napi_gro_receive(&rx_ring->q_vector->napi, skb); } @@ -222,6 +227,7 @@ ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag) static void ice_clean_xdp_irq(struct ice_tx_ring *xdp_ring) { unsigned int total_bytes = 0, total_pkts = 0; + u16 tx_thresh = ICE_RING_QUARTER(xdp_ring); u16 ntc = xdp_ring->next_to_clean; struct ice_tx_desc *next_dd_desc; u16 next_dd = xdp_ring->next_dd; @@ -233,7 +239,7 @@ static void ice_clean_xdp_irq(struct ice_tx_ring *xdp_ring) cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE))) return; - for (i = 0; i < ICE_TX_THRESH; i++) { + for (i = 0; i < tx_thresh; i++) { tx_buf = &xdp_ring->tx_buf[ntc]; total_bytes += tx_buf->bytecount; @@ -254,9 +260,9 @@ static void ice_clean_xdp_irq(struct ice_tx_ring *xdp_ring) } next_dd_desc->cmd_type_offset_bsz = 0; - xdp_ring->next_dd = xdp_ring->next_dd + ICE_TX_THRESH; + xdp_ring->next_dd = xdp_ring->next_dd + tx_thresh; if (xdp_ring->next_dd > xdp_ring->count) - xdp_ring->next_dd = ICE_TX_THRESH - 1; + xdp_ring->next_dd = tx_thresh - 1; xdp_ring->next_to_clean = ntc; ice_update_tx_ring_stats(xdp_ring, total_pkts, total_bytes); } @@ -269,12 +275,13 @@ static void ice_clean_xdp_irq(struct ice_tx_ring *xdp_ring) */ int ice_xmit_xdp_ring(void *data, u16 size, struct ice_tx_ring *xdp_ring) { + u16 tx_thresh = ICE_RING_QUARTER(xdp_ring); u16 i = 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_TX_THRESH) + if (ICE_DESC_UNUSED(xdp_ring) < tx_thresh) ice_clean_xdp_irq(xdp_ring); if (!unlikely(ICE_DESC_UNUSED(xdp_ring))) { @@ -300,13 +307,14 @@ int ice_xmit_xdp_ring(void *data, u16 size, struct ice_tx_ring *xdp_ring) tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP, 0, size, 0); + xdp_ring->xdp_tx_active++; i++; if (i == xdp_ring->count) { i = 0; tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_rs); tx_desc->cmd_type_offset_bsz |= cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S); - xdp_ring->next_rs = ICE_TX_THRESH - 1; + xdp_ring->next_rs = tx_thresh - 1; } xdp_ring->next_to_use = i; @@ -314,7 +322,7 @@ int ice_xmit_xdp_ring(void *data, u16 size, struct ice_tx_ring *xdp_ring) tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_rs); tx_desc->cmd_type_offset_bsz |= cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S); - xdp_ring->next_rs += ICE_TX_THRESH; + xdp_ring->next_rs += tx_thresh; } return ICE_XDP_TX; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h index 11b6c1601986..c7d2954dc9ea 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h @@ -7,7 +7,7 @@ /** * ice_test_staterr - tests bits in Rx descriptor status and error fields - * @rx_desc: pointer to receive descriptor (in le64 format) + * @status_err_n: Rx descriptor status_error0 or status_error1 bits * @stat_err_bits: value to mask * * This function does some fast chicanery in order to return the @@ -16,9 +16,9 @@ * at offset zero. */ static inline bool -ice_test_staterr(union ice_32b_rx_flex_desc *rx_desc, const u16 stat_err_bits) +ice_test_staterr(__le16 status_err_n, const u16 stat_err_bits) { - return !!(rx_desc->wb.status_error0 & cpu_to_le16(stat_err_bits)); + return !!(status_err_n & cpu_to_le16(stat_err_bits)); } static inline __le64 @@ -32,6 +32,30 @@ ice_build_ctob(u64 td_cmd, u64 td_offset, unsigned int size, u64 td_tag) } /** + * ice_get_vlan_tag_from_rx_desc - get VLAN from Rx flex descriptor + * @rx_desc: Rx 32b flex descriptor with RXDID=2 + * + * The OS and current PF implementation only support stripping a single VLAN tag + * at a time, so there should only ever be 0 or 1 tags in the l2tag* fields. If + * one is found return the tag, else return 0 to mean no VLAN tag was found. + */ +static inline u16 +ice_get_vlan_tag_from_rx_desc(union ice_32b_rx_flex_desc *rx_desc) +{ + u16 stat_err_bits; + + stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_L2TAG1P_S); + if (ice_test_staterr(rx_desc->wb.status_error0, stat_err_bits)) + return le16_to_cpu(rx_desc->wb.l2tag1); + + stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS1_L2TAG2P_S); + if (ice_test_staterr(rx_desc->wb.status_error1, stat_err_bits)) + return le16_to_cpu(rx_desc->wb.l2tag2_2nd); + + return 0; +} + +/** * ice_xdp_ring_update_tail - Updates the XDP Tx ring tail register * @xdp_ring: XDP Tx ring * diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index 546145dd1f02..e1abfcee96dc 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -9,12 +9,14 @@ #define ICE_CHNL_MAX_TC 16 #include "ice_hw_autogen.h" +#include "ice_devids.h" #include "ice_osdep.h" #include "ice_controlq.h" #include "ice_lan_tx_rx.h" #include "ice_flex_type.h" #include "ice_protocol_type.h" #include "ice_sbq_cmd.h" +#include "ice_vlan_mode.h" static inline bool ice_is_tc_ena(unsigned long bitmap, u8 tc) { @@ -54,6 +56,11 @@ static inline u32 ice_round_to_num(u32 N, u32 R) #define ICE_DBG_AQ_DESC BIT_ULL(25) #define ICE_DBG_AQ_DESC_BUF BIT_ULL(26) #define ICE_DBG_AQ_CMD BIT_ULL(27) +#define ICE_DBG_AQ (ICE_DBG_AQ_MSG | \ + ICE_DBG_AQ_DESC | \ + ICE_DBG_AQ_DESC_BUF | \ + ICE_DBG_AQ_CMD) + #define ICE_DBG_USER BIT_ULL(31) enum ice_aq_res_ids { @@ -340,6 +347,7 @@ struct ice_ts_func_info { #define ICE_TS_DEV_ENA_M BIT(24) #define ICE_TS_TMR0_ENA_M BIT(25) #define ICE_TS_TMR1_ENA_M BIT(26) +#define ICE_TS_LL_TX_TS_READ_M BIT(28) struct ice_ts_dev_info { /* Device specific info */ @@ -352,6 +360,7 @@ struct ice_ts_dev_info { u8 ena; u8 tmr0_ena; u8 tmr1_ena; + u8 ts_ll_read; }; /* Function specific capabilities */ @@ -557,6 +566,8 @@ enum ice_rl_type { #define ICE_SCHED_INVAL_PROF_ID 0xFFFF #define ICE_SCHED_DFLT_BURST_SIZE (15 * 1024) /* in bytes (15k) */ +#define ICE_MAX_PORT_PER_PCI_DEV 8 + /* Data structure for saving BW information */ enum ice_bw_type { ICE_BW_TYPE_PRIO, @@ -686,10 +697,6 @@ struct ice_port_info { #define ICE_SCHED_PORT_STATE_READY 0x1 u8 lport; #define ICE_LPORT_MASK 0xff - u16 dflt_tx_vsi_rule_id; - u16 dflt_tx_vsi_num; - u16 dflt_rx_vsi_rule_id; - u16 dflt_rx_vsi_num; struct ice_fc_info fc; struct ice_mac_info mac; struct ice_phy_info phy; @@ -882,8 +889,6 @@ struct ice_hw { /* INTRL granularity in 1 us */ u8 intrl_gran; - u8 ucast_shared; /* true if VSIs can share unicast addr */ - #define ICE_PHY_PER_NAC 1 #define ICE_MAX_QUAD 2 #define ICE_NUM_QUAD_TYPE 2 @@ -920,6 +925,9 @@ struct ice_hw { struct udp_tunnel_nic_shared udp_tunnel_shared; struct udp_tunnel_nic_info udp_tunnel_nic; + /* dvm boost update information */ + struct ice_dvm_table dvm_upd; + /* HW block tables */ struct ice_blk_info blk[ICE_BLK_COUNT]; struct mutex fl_profs_locks[ICE_BLK_COUNT]; /* lock fltr profiles */ @@ -943,6 +951,7 @@ struct ice_hw { struct list_head rss_list_head; struct ice_mbx_snapshot mbx_snapshot; DECLARE_BITMAP(hw_ptype, ICE_FLOW_PTYPE_MAX); + u8 dvm_ena; u16 io_expander_handle; }; @@ -1008,6 +1017,15 @@ struct ice_hw_port_stats { u64 fd_sb_match; }; +enum ice_sw_fwd_act_type { + ICE_FWD_TO_VSI = 0, + ICE_FWD_TO_VSI_LIST, /* Do not use this when adding filter */ + ICE_FWD_TO_Q, + ICE_FWD_TO_QGRP, + ICE_DROP_PACKET, + 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 */ diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c new file mode 100644 index 000000000000..1c51778db951 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -0,0 +1,1132 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2022, Intel Corporation. */ + +#include "ice_vf_lib_private.h" +#include "ice.h" +#include "ice_lib.h" +#include "ice_fltr.h" +#include "ice_virtchnl_allowlist.h" + +/* Public functions which may be accessed by all driver files */ + +/** + * ice_get_vf_by_id - Get pointer to VF by ID + * @pf: the PF private structure + * @vf_id: the VF ID to locate + * + * Locate and return a pointer to the VF structure associated with a given ID. + * Returns NULL if the ID does not have a valid VF structure associated with + * it. + * + * This function takes a reference to the VF, which must be released by + * calling ice_put_vf() once the caller is finished accessing the VF structure + * returned. + */ +struct ice_vf *ice_get_vf_by_id(struct ice_pf *pf, u16 vf_id) +{ + struct ice_vf *vf; + + rcu_read_lock(); + hash_for_each_possible_rcu(pf->vfs.table, vf, entry, vf_id) { + if (vf->vf_id == vf_id) { + struct ice_vf *found; + + if (kref_get_unless_zero(&vf->refcnt)) + found = vf; + else + found = NULL; + + rcu_read_unlock(); + return found; + } + } + rcu_read_unlock(); + + return NULL; +} + +/** + * ice_release_vf - Release VF associated with a refcount + * @ref: the kref decremented to zero + * + * Callback function for kref_put to release a VF once its reference count has + * hit zero. + */ +static void ice_release_vf(struct kref *ref) +{ + struct ice_vf *vf = container_of(ref, struct ice_vf, refcnt); + + vf->vf_ops->free(vf); +} + +/** + * ice_put_vf - Release a reference to a VF + * @vf: the VF structure to decrease reference count on + * + * Decrease the reference count for a VF, and free the entry if it is no + * longer in use. + * + * This must be called after ice_get_vf_by_id() once the reference to the VF + * structure is no longer used. Otherwise, the VF structure will never be + * freed. + */ +void ice_put_vf(struct ice_vf *vf) +{ + kref_put(&vf->refcnt, ice_release_vf); +} + +/** + * ice_has_vfs - Return true if the PF has any associated VFs + * @pf: the PF private structure + * + * Return whether or not the PF has any allocated VFs. + * + * Note that this function only guarantees that there are no VFs at the point + * of calling it. It does not guarantee that no more VFs will be added. + */ +bool ice_has_vfs(struct ice_pf *pf) +{ + /* A simple check that the hash table is not empty does not require + * the mutex or rcu_read_lock. + */ + return !hash_empty(pf->vfs.table); +} + +/** + * ice_get_num_vfs - Get number of allocated VFs + * @pf: the PF private structure + * + * Return the total number of allocated VFs. NOTE: VF IDs are not guaranteed + * to be contiguous. Do not assume that a VF ID is guaranteed to be less than + * the output of this function. + */ +u16 ice_get_num_vfs(struct ice_pf *pf) +{ + struct ice_vf *vf; + unsigned int bkt; + u16 num_vfs = 0; + + rcu_read_lock(); + ice_for_each_vf_rcu(pf, bkt, vf) + num_vfs++; + rcu_read_unlock(); + + return num_vfs; +} + +/** + * ice_get_vf_vsi - get VF's VSI based on the stored index + * @vf: VF used to get VSI + */ +struct ice_vsi *ice_get_vf_vsi(struct ice_vf *vf) +{ + if (vf->lan_vsi_idx == ICE_NO_VSI) + return NULL; + + return vf->pf->vsi[vf->lan_vsi_idx]; +} + +/** + * ice_is_vf_disabled + * @vf: pointer to the VF info + * + * If the PF has been disabled, there is no need resetting VF until PF is + * active again. Similarly, if the VF has been disabled, this means something + * else is resetting the VF, so we shouldn't continue. + * + * Returns true if the caller should consider the VF as disabled whether + * because that single VF is explicitly disabled or because the PF is + * currently disabled. + */ +bool ice_is_vf_disabled(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + + return (test_bit(ICE_VF_DIS, pf->state) || + test_bit(ICE_VF_STATE_DIS, vf->vf_states)); +} + +/** + * ice_wait_on_vf_reset - poll to make sure a given VF is ready after reset + * @vf: The VF being resseting + * + * The max poll time is about ~800ms, which is about the maximum time it takes + * for a VF to be reset and/or a VF driver to be removed. + */ +static void ice_wait_on_vf_reset(struct ice_vf *vf) +{ + int i; + + for (i = 0; i < ICE_MAX_VF_RESET_TRIES; i++) { + if (test_bit(ICE_VF_STATE_INIT, vf->vf_states)) + break; + msleep(ICE_MAX_VF_RESET_SLEEP_MS); + } +} + +/** + * ice_check_vf_ready_for_cfg - check if VF is ready to be configured/queried + * @vf: VF to check if it's ready to be configured/queried + * + * The purpose of this function is to make sure the VF is not in reset, not + * disabled, and initialized so it can be configured and/or queried by a host + * administrator. + */ +int ice_check_vf_ready_for_cfg(struct ice_vf *vf) +{ + ice_wait_on_vf_reset(vf); + + if (ice_is_vf_disabled(vf)) + return -EINVAL; + + if (ice_check_vf_init(vf)) + return -EBUSY; + + return 0; +} + +/** + * ice_trigger_vf_reset - Reset a VF on HW + * @vf: pointer to the VF structure + * @is_vflr: true if VFLR was issued, false if not + * @is_pfr: true if the reset was triggered due to a previous PFR + * + * Trigger hardware to start a reset for a particular VF. Expects the caller + * to wait the proper amount of time to allow hardware to reset the VF before + * it cleans up and restores VF functionality. + */ +static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr, bool is_pfr) +{ + /* Inform VF that it is no longer active, as a warning */ + clear_bit(ICE_VF_STATE_ACTIVE, vf->vf_states); + + /* Disable VF's configuration API during reset. The flag is re-enabled + * when it's safe again to access VF's VSI. + */ + clear_bit(ICE_VF_STATE_INIT, vf->vf_states); + + /* VF_MBX_ARQLEN and VF_MBX_ATQLEN are cleared by PFR, so the driver + * needs to clear them in the case of VFR/VFLR. If this is done for + * PFR, it can mess up VF resets because the VF driver may already + * have started cleanup by the time we get here. + */ + if (!is_pfr) + vf->vf_ops->clear_mbx_register(vf); + + vf->vf_ops->trigger_reset_register(vf, is_vflr); +} + +static void ice_vf_clear_counters(struct ice_vf *vf) +{ + struct ice_vsi *vsi = ice_get_vf_vsi(vf); + + if (vsi) + vsi->num_vlan = 0; + + vf->num_mac = 0; + memset(&vf->mdd_tx_events, 0, sizeof(vf->mdd_tx_events)); + memset(&vf->mdd_rx_events, 0, sizeof(vf->mdd_rx_events)); +} + +/** + * ice_vf_pre_vsi_rebuild - tasks to be done prior to VSI rebuild + * @vf: VF to perform pre VSI rebuild tasks + * + * These tasks are items that don't need to be amortized since they are most + * likely called in a for loop with all VF(s) in the reset_all_vfs() case. + */ +static void ice_vf_pre_vsi_rebuild(struct ice_vf *vf) +{ + ice_vf_clear_counters(vf); + vf->vf_ops->clear_reset_trigger(vf); +} + +/** + * ice_vf_rebuild_vsi - rebuild the VF's VSI + * @vf: VF to rebuild the VSI for + * + * This is only called when all VF(s) are being reset (i.e. PCIe Reset on the + * host, PFR, CORER, etc.). + */ +static int ice_vf_rebuild_vsi(struct ice_vf *vf) +{ + struct ice_vsi *vsi = ice_get_vf_vsi(vf); + struct ice_pf *pf = vf->pf; + + if (WARN_ON(!vsi)) + return -EINVAL; + + if (ice_vsi_rebuild(vsi, true)) { + dev_err(ice_pf_to_dev(pf), "failed to rebuild VF %d VSI\n", + vf->vf_id); + return -EIO; + } + /* vsi->idx will remain the same in this case so don't update + * vf->lan_vsi_idx + */ + vsi->vsi_num = ice_get_hw_vsi_num(&pf->hw, vsi->idx); + vf->lan_vsi_num = vsi->vsi_num; + + return 0; +} + +/** + * ice_is_any_vf_in_unicast_promisc - check if any VF(s) + * are in unicast promiscuous mode + * @pf: PF structure for accessing VF(s) + * + * Return false if no VF(s) are in unicast promiscuous mode, + * else return true + */ +bool ice_is_any_vf_in_unicast_promisc(struct ice_pf *pf) +{ + bool is_vf_promisc = false; + struct ice_vf *vf; + unsigned int bkt; + + rcu_read_lock(); + ice_for_each_vf_rcu(pf, bkt, vf) { + /* found a VF that has promiscuous mode configured */ + if (test_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states)) { + is_vf_promisc = true; + break; + } + } + rcu_read_unlock(); + + return is_vf_promisc; +} + +/** + * ice_vf_get_promisc_masks - Calculate masks for promiscuous modes + * @vf: the VF pointer + * @vsi: the VSI to configure + * @ucast_m: promiscuous mask to apply to unicast + * @mcast_m: promiscuous mask to apply to multicast + * + * Decide which mask should be used for unicast and multicast filter, + * based on presence of VLANs + */ +void +ice_vf_get_promisc_masks(struct ice_vf *vf, struct ice_vsi *vsi, + u8 *ucast_m, u8 *mcast_m) +{ + if (ice_vf_is_port_vlan_ena(vf) || + ice_vsi_has_non_zero_vlans(vsi)) { + *mcast_m = ICE_MCAST_VLAN_PROMISC_BITS; + *ucast_m = ICE_UCAST_VLAN_PROMISC_BITS; + } else { + *mcast_m = ICE_MCAST_PROMISC_BITS; + *ucast_m = ICE_UCAST_PROMISC_BITS; + } +} + +/** + * ice_vf_clear_all_promisc_modes - Clear promisc/allmulticast on VF VSI + * @vf: the VF pointer + * @vsi: the VSI to configure + * + * Clear all promiscuous/allmulticast filters for a VF + */ +static int +ice_vf_clear_all_promisc_modes(struct ice_vf *vf, struct ice_vsi *vsi) +{ + struct ice_pf *pf = vf->pf; + u8 ucast_m, mcast_m; + int ret = 0; + + ice_vf_get_promisc_masks(vf, vsi, &ucast_m, &mcast_m); + if (test_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states)) { + if (!test_bit(ICE_FLAG_VF_TRUE_PROMISC_ENA, pf->flags)) { + if (ice_is_dflt_vsi_in_use(vsi->port_info)) + ret = ice_clear_dflt_vsi(vsi); + } else { + ret = ice_vf_clear_vsi_promisc(vf, vsi, ucast_m); + } + + if (ret) { + dev_err(ice_pf_to_dev(vf->pf), "Disabling promiscuous mode failed\n"); + } else { + clear_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states); + dev_info(ice_pf_to_dev(vf->pf), "Disabling promiscuous mode succeeded\n"); + } + } + + if (test_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states)) { + ret = ice_vf_clear_vsi_promisc(vf, vsi, mcast_m); + if (ret) { + dev_err(ice_pf_to_dev(vf->pf), "Disabling allmulticast mode failed\n"); + } else { + clear_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states); + dev_info(ice_pf_to_dev(vf->pf), "Disabling allmulticast mode succeeded\n"); + } + } + return ret; +} + +/** + * ice_vf_set_vsi_promisc - Enable promiscuous mode for a VF VSI + * @vf: the VF to configure + * @vsi: the VF's VSI + * @promisc_m: the promiscuous mode to enable + */ +int +ice_vf_set_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m) +{ + struct ice_hw *hw = &vsi->back->hw; + int status; + + if (ice_vf_is_port_vlan_ena(vf)) + status = ice_fltr_set_vsi_promisc(hw, vsi->idx, promisc_m, + ice_vf_get_port_vlan_id(vf)); + else if (ice_vsi_has_non_zero_vlans(vsi)) + status = ice_fltr_set_vlan_vsi_promisc(hw, vsi, promisc_m); + else + status = ice_fltr_set_vsi_promisc(hw, vsi->idx, promisc_m, 0); + + if (status && status != -EEXIST) { + dev_err(ice_pf_to_dev(vsi->back), "enable Tx/Rx filter promiscuous mode on VF-%u failed, error: %d\n", + vf->vf_id, status); + return status; + } + + return 0; +} + +/** + * ice_vf_clear_vsi_promisc - Disable promiscuous mode for a VF VSI + * @vf: the VF to configure + * @vsi: the VF's VSI + * @promisc_m: the promiscuous mode to disable + */ +int +ice_vf_clear_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m) +{ + struct ice_hw *hw = &vsi->back->hw; + int status; + + if (ice_vf_is_port_vlan_ena(vf)) + status = ice_fltr_clear_vsi_promisc(hw, vsi->idx, promisc_m, + ice_vf_get_port_vlan_id(vf)); + else if (ice_vsi_has_non_zero_vlans(vsi)) + status = ice_fltr_clear_vlan_vsi_promisc(hw, vsi, promisc_m); + else + status = ice_fltr_clear_vsi_promisc(hw, vsi->idx, promisc_m, 0); + + if (status && status != -ENOENT) { + dev_err(ice_pf_to_dev(vsi->back), "disable Tx/Rx filter promiscuous mode on VF-%u failed, error: %d\n", + vf->vf_id, status); + return status; + } + + return 0; +} + +/** + * ice_reset_all_vfs - reset all allocated VFs in one go + * @pf: pointer to the PF structure + * + * Reset all VFs at once, in response to a PF or other device reset. + * + * First, tell the hardware to reset each VF, then do all the waiting in one + * chunk, and finally finish restoring each VF after the wait. This is useful + * during PF routines which need to reset all VFs, as otherwise it must perform + * these resets in a serialized fashion. + */ +void ice_reset_all_vfs(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + struct ice_hw *hw = &pf->hw; + struct ice_vf *vf; + unsigned int bkt; + + /* If we don't have any VFs, then there is nothing to reset */ + if (!ice_has_vfs(pf)) + return; + + mutex_lock(&pf->vfs.table_lock); + + /* clear all malicious info if the VFs are getting reset */ + ice_for_each_vf(pf, bkt, vf) + if (ice_mbx_clear_malvf(&hw->mbx_snapshot, pf->vfs.malvfs, + ICE_MAX_SRIOV_VFS, vf->vf_id)) + dev_dbg(dev, "failed to clear malicious VF state for VF %u\n", + vf->vf_id); + + /* If VFs have been disabled, there is no need to reset */ + if (test_and_set_bit(ICE_VF_DIS, pf->state)) { + mutex_unlock(&pf->vfs.table_lock); + return; + } + + /* Begin reset on all VFs at once */ + ice_for_each_vf(pf, bkt, vf) + ice_trigger_vf_reset(vf, true, true); + + /* HW requires some time to make sure it can flush the FIFO for a VF + * when it resets it. Now that we've triggered all of the VFs, iterate + * the table again and wait for each VF to complete. + */ + ice_for_each_vf(pf, bkt, vf) { + if (!vf->vf_ops->poll_reset_status(vf)) { + /* Display a warning if at least one VF didn't manage + * to reset in time, but continue on with the + * operation. + */ + dev_warn(dev, "VF %u reset check timeout\n", vf->vf_id); + break; + } + } + + /* free VF resources to begin resetting the VSI state */ + ice_for_each_vf(pf, bkt, vf) { + mutex_lock(&vf->cfg_lock); + + vf->driver_caps = 0; + ice_vc_set_default_allowlist(vf); + + ice_vf_fdir_exit(vf); + ice_vf_fdir_init(vf); + /* clean VF control VSI when resetting VFs since it should be + * setup only when VF creates its first FDIR rule. + */ + if (vf->ctrl_vsi_idx != ICE_NO_VSI) + ice_vf_ctrl_invalidate_vsi(vf); + + ice_vf_pre_vsi_rebuild(vf); + ice_vf_rebuild_vsi(vf); + vf->vf_ops->post_vsi_rebuild(vf); + + mutex_unlock(&vf->cfg_lock); + } + + if (ice_is_eswitch_mode_switchdev(pf)) + if (ice_eswitch_rebuild(pf)) + dev_warn(dev, "eswitch rebuild failed\n"); + + ice_flush(hw); + clear_bit(ICE_VF_DIS, pf->state); + + mutex_unlock(&pf->vfs.table_lock); +} + +/** + * ice_notify_vf_reset - Notify VF of a reset event + * @vf: pointer to the VF structure + */ +static void ice_notify_vf_reset(struct ice_vf *vf) +{ + struct ice_hw *hw = &vf->pf->hw; + struct virtchnl_pf_event pfe; + + /* Bail out if VF is in disabled state, neither initialized, nor active + * state - otherwise proceed with notifications + */ + if ((!test_bit(ICE_VF_STATE_INIT, vf->vf_states) && + !test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) || + test_bit(ICE_VF_STATE_DIS, vf->vf_states)) + return; + + pfe.event = VIRTCHNL_EVENT_RESET_IMPENDING; + pfe.severity = PF_EVENT_SEVERITY_CERTAIN_DOOM; + ice_aq_send_msg_to_vf(hw, vf->vf_id, VIRTCHNL_OP_EVENT, + VIRTCHNL_STATUS_SUCCESS, (u8 *)&pfe, sizeof(pfe), + NULL); +} + +/** + * ice_reset_vf - Reset a particular VF + * @vf: pointer to the VF structure + * @flags: flags controlling behavior of the reset + * + * Flags: + * ICE_VF_RESET_VFLR - Indicates a reset is due to VFLR event + * ICE_VF_RESET_NOTIFY - Send VF a notification prior to reset + * ICE_VF_RESET_LOCK - Acquire VF cfg_lock before resetting + * + * Returns 0 if the VF is currently in reset, if resets are disabled, or if + * the VF resets successfully. Returns an error code if the VF fails to + * rebuild. + */ +int ice_reset_vf(struct ice_vf *vf, u32 flags) +{ + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + struct device *dev; + struct ice_hw *hw; + int err = 0; + bool rsd; + + dev = ice_pf_to_dev(pf); + hw = &pf->hw; + + if (flags & ICE_VF_RESET_NOTIFY) + ice_notify_vf_reset(vf); + + if (test_bit(ICE_VF_RESETS_DISABLED, pf->state)) { + dev_dbg(dev, "Trying to reset VF %d, but all VF resets are disabled\n", + vf->vf_id); + return 0; + } + + if (ice_is_vf_disabled(vf)) { + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + dev_dbg(dev, "VF is already removed\n"); + return -EINVAL; + } + ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, vf->vf_id); + + if (ice_vsi_is_rx_queue_active(vsi)) + ice_vsi_stop_all_rx_rings(vsi); + + dev_dbg(dev, "VF is already disabled, there is no need for resetting it, telling VM, all is fine %d\n", + vf->vf_id); + return 0; + } + + if (flags & ICE_VF_RESET_LOCK) + mutex_lock(&vf->cfg_lock); + else + lockdep_assert_held(&vf->cfg_lock); + + /* Set VF disable bit state here, before triggering reset */ + set_bit(ICE_VF_STATE_DIS, vf->vf_states); + ice_trigger_vf_reset(vf, flags & ICE_VF_RESET_VFLR, false); + + vsi = ice_get_vf_vsi(vf); + if (WARN_ON(!vsi)) { + err = -EIO; + goto out_unlock; + } + + ice_dis_vf_qs(vf); + + /* Call Disable LAN Tx queue AQ whether or not queues are + * enabled. This is needed for successful completion of VFR. + */ + ice_dis_vsi_txq(vsi->port_info, vsi->idx, 0, 0, NULL, NULL, + NULL, vf->vf_ops->reset_type, vf->vf_id, NULL); + + /* poll VPGEN_VFRSTAT reg to make sure + * that reset is complete + */ + rsd = vf->vf_ops->poll_reset_status(vf); + + /* Display a warning if VF didn't manage to reset in time, but need to + * continue on with the operation. + */ + if (!rsd) + dev_warn(dev, "VF reset check timeout on VF %d\n", vf->vf_id); + + vf->driver_caps = 0; + ice_vc_set_default_allowlist(vf); + + /* disable promiscuous modes in case they were enabled + * ignore any error if disabling process failed + */ + ice_vf_clear_all_promisc_modes(vf, vsi); + + ice_eswitch_del_vf_mac_rule(vf); + + ice_vf_fdir_exit(vf); + ice_vf_fdir_init(vf); + /* clean VF control VSI when resetting VF since it should be setup + * only when VF creates its first FDIR rule. + */ + if (vf->ctrl_vsi_idx != ICE_NO_VSI) + ice_vf_ctrl_vsi_release(vf); + + ice_vf_pre_vsi_rebuild(vf); + + if (vf->vf_ops->vsi_rebuild(vf)) { + dev_err(dev, "Failed to release and setup the VF%u's VSI\n", + vf->vf_id); + err = -EFAULT; + goto out_unlock; + } + + vf->vf_ops->post_vsi_rebuild(vf); + vsi = ice_get_vf_vsi(vf); + if (WARN_ON(!vsi)) { + err = -EINVAL; + goto out_unlock; + } + + ice_eswitch_update_repr(vsi); + ice_eswitch_replay_vf_mac_rule(vf); + + /* if the VF has been reset allow it to come up again */ + if (ice_mbx_clear_malvf(&hw->mbx_snapshot, pf->vfs.malvfs, + ICE_MAX_SRIOV_VFS, vf->vf_id)) + dev_dbg(dev, "failed to clear malicious VF state for VF %u\n", + vf->vf_id); + +out_unlock: + if (flags & ICE_VF_RESET_LOCK) + mutex_unlock(&vf->cfg_lock); + + return err; +} + +/** + * ice_set_vf_state_qs_dis - Set VF queues state to disabled + * @vf: pointer to the VF structure + */ +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); +} + +/* Private functions only accessed from other virtualization files */ + +/** + * ice_dis_vf_qs - Disable the VF queues + * @vf: pointer to the VF structure + */ +void ice_dis_vf_qs(struct ice_vf *vf) +{ + struct ice_vsi *vsi = ice_get_vf_vsi(vf); + + if (WARN_ON(!vsi)) + return; + + ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, vf->vf_id); + ice_vsi_stop_all_rx_rings(vsi); + ice_set_vf_state_qs_dis(vf); +} + +/** + * ice_check_vf_init - helper to check if VF init complete + * @vf: the pointer to the VF to check + */ +int ice_check_vf_init(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { + dev_err(ice_pf_to_dev(pf), "VF ID: %u in reset. Try again.\n", + vf->vf_id); + return -EBUSY; + } + return 0; +} + +/** + * ice_vf_get_port_info - Get the VF's port info structure + * @vf: VF used to get the port info structure for + */ +struct ice_port_info *ice_vf_get_port_info(struct ice_vf *vf) +{ + return vf->pf->hw.port_info; +} + +/** + * ice_cfg_mac_antispoof - Configure MAC antispoof checking behavior + * @vsi: the VSI to configure + * @enable: whether to enable or disable the spoof checking + * + * Configure a VSI to enable (or disable) spoof checking behavior. + */ +static int ice_cfg_mac_antispoof(struct ice_vsi *vsi, bool enable) +{ + struct ice_vsi_ctx *ctx; + int err; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->info.sec_flags = vsi->info.sec_flags; + ctx->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID); + + if (enable) + ctx->info.sec_flags |= ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF; + else + ctx->info.sec_flags &= ~ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF; + + err = ice_update_vsi(&vsi->back->hw, vsi->idx, ctx, NULL); + if (err) + dev_err(ice_pf_to_dev(vsi->back), "Failed to configure Tx MAC anti-spoof %s for VSI %d, error %d\n", + enable ? "ON" : "OFF", vsi->vsi_num, err); + else + vsi->info.sec_flags = ctx->info.sec_flags; + + kfree(ctx); + + return err; +} + +/** + * ice_vsi_ena_spoofchk - enable Tx spoof checking for this VSI + * @vsi: VSI to enable Tx spoof checking for + */ +static int ice_vsi_ena_spoofchk(struct ice_vsi *vsi) +{ + struct ice_vsi_vlan_ops *vlan_ops; + int err = 0; + + vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); + + /* Allow VF with VLAN 0 only to send all tagged traffic */ + if (vsi->type != ICE_VSI_VF || ice_vsi_has_non_zero_vlans(vsi)) { + err = vlan_ops->ena_tx_filtering(vsi); + if (err) + return err; + } + + return ice_cfg_mac_antispoof(vsi, true); +} + +/** + * ice_vsi_dis_spoofchk - disable Tx spoof checking for this VSI + * @vsi: VSI to disable Tx spoof checking for + */ +static int ice_vsi_dis_spoofchk(struct ice_vsi *vsi) +{ + struct ice_vsi_vlan_ops *vlan_ops; + int err; + + vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); + + err = vlan_ops->dis_tx_filtering(vsi); + if (err) + return err; + + return ice_cfg_mac_antispoof(vsi, false); +} + +/** + * ice_vsi_apply_spoofchk - Apply Tx spoof checking setting to a VSI + * @vsi: VSI associated to the VF + * @enable: whether to enable or disable the spoof checking + */ +int ice_vsi_apply_spoofchk(struct ice_vsi *vsi, bool enable) +{ + int err; + + if (enable) + err = ice_vsi_ena_spoofchk(vsi); + else + err = ice_vsi_dis_spoofchk(vsi); + + return err; +} + +/** + * ice_is_vf_trusted + * @vf: pointer to the VF info + */ +bool ice_is_vf_trusted(struct ice_vf *vf) +{ + return test_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps); +} + +/** + * ice_vf_has_no_qs_ena - check if the VF has any Rx or Tx queues enabled + * @vf: the VF to check + * + * Returns true if the VF has no Rx and no Tx queues enabled and returns false + * otherwise + */ +bool ice_vf_has_no_qs_ena(struct ice_vf *vf) +{ + return (!bitmap_weight(vf->rxq_ena, ICE_MAX_RSS_QS_PER_VF) && + !bitmap_weight(vf->txq_ena, ICE_MAX_RSS_QS_PER_VF)); +} + +/** + * ice_is_vf_link_up - check if the VF's link is up + * @vf: VF to check if link is up + */ +bool ice_is_vf_link_up(struct ice_vf *vf) +{ + struct ice_port_info *pi = ice_vf_get_port_info(vf); + + if (ice_check_vf_init(vf)) + return false; + + if (ice_vf_has_no_qs_ena(vf)) + return false; + else if (vf->link_forced) + return vf->link_up; + else + return pi->phy.link_info.link_info & + ICE_AQ_LINK_UP; +} + +/** + * 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.addr)) { + status = ice_fltr_add_mac(vsi, vf->hw_lan_addr.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.addr[0], vf->vf_id, + status); + return status; + } + vf->num_mac++; + + ether_addr_copy(vf->dev_lan_addr.addr, vf->hw_lan_addr.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 + */ +void ice_vf_ctrl_invalidate_vsi(struct ice_vf *vf) +{ + vf->ctrl_vsi_idx = ICE_NO_VSI; +} + +/** + * ice_vf_ctrl_vsi_release - invalidate the VF's control VSI after freeing it + * @vf: VF that control VSI is being released on + */ +void ice_vf_ctrl_vsi_release(struct ice_vf *vf) +{ + ice_vsi_release(vf->pf->vsi[vf->ctrl_vsi_idx]); + ice_vf_ctrl_invalidate_vsi(vf); +} + +/** + * ice_vf_ctrl_vsi_setup - Set up a VF control VSI + * @vf: VF to setup control VSI for + * + * Returns pointer to the successfully allocated VSI struct on success, + * otherwise returns NULL on failure. + */ +struct ice_vsi *ice_vf_ctrl_vsi_setup(struct ice_vf *vf) +{ + struct ice_port_info *pi = ice_vf_get_port_info(vf); + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + + vsi = ice_vsi_setup(pf, pi, ICE_VSI_CTRL, vf, NULL); + if (!vsi) { + dev_err(ice_pf_to_dev(pf), "Failed to create VF control VSI\n"); + ice_vf_ctrl_invalidate_vsi(vf); + } + + return vsi; +} + +/** + * ice_vf_invalidate_vsi - invalidate vsi_idx/vsi_num to remove VSI access + * @vf: VF to remove access to VSI for + */ +void ice_vf_invalidate_vsi(struct ice_vf *vf) +{ + vf->lan_vsi_idx = ICE_NO_VSI; + vf->lan_vsi_num = ICE_NO_VSI; +} + +/** + * 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)); +} diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h new file mode 100644 index 000000000000..52bd9a3816bf --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h @@ -0,0 +1,293 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2018-2021, Intel Corporation. */ + +#ifndef _ICE_VF_LIB_H_ +#define _ICE_VF_LIB_H_ + +#include <linux/types.h> +#include <linux/hashtable.h> +#include <linux/bitmap.h> +#include <linux/mutex.h> +#include <linux/pci.h> +#include <net/devlink.h> +#include <linux/avf/virtchnl.h> +#include "ice_type.h" +#include "ice_virtchnl_fdir.h" +#include "ice_vsi_vlan_ops.h" + +#define ICE_MAX_SRIOV_VFS 256 + +/* VF resource constraints */ +#define ICE_MAX_RSS_QS_PER_VF 16 + +struct ice_pf; +struct ice_vf; +struct ice_virtchnl_ops; + +/* VF capabilities */ +enum ice_virtchnl_cap { + ICE_VIRTCHNL_VF_CAP_PRIVILEGE = 0, +}; + +/* Specific VF states */ +enum ice_vf_states { + ICE_VF_STATE_INIT = 0, /* PF is initializing VF */ + ICE_VF_STATE_ACTIVE, /* VF resources are allocated for use */ + ICE_VF_STATE_QS_ENA, /* VF queue(s) enabled */ + ICE_VF_STATE_DIS, + ICE_VF_STATE_MC_PROMISC, + ICE_VF_STATE_UC_PROMISC, + ICE_VF_STATES_NBITS +}; + +struct ice_time_mac { + unsigned long time_modified; + u8 addr[ETH_ALEN]; +}; + +/* VF MDD events print structure */ +struct ice_mdd_vf_events { + u16 count; /* total count of Rx|Tx events */ + /* count number of the last printed event */ + u16 last_printed; +}; + +/* VF operations */ +struct ice_vf_ops { + enum ice_disq_rst_src reset_type; + void (*free)(struct ice_vf *vf); + void (*clear_mbx_register)(struct ice_vf *vf); + void (*trigger_reset_register)(struct ice_vf *vf, bool is_vflr); + bool (*poll_reset_status)(struct ice_vf *vf); + void (*clear_reset_trigger)(struct ice_vf *vf); + int (*vsi_rebuild)(struct ice_vf *vf); + void (*post_vsi_rebuild)(struct ice_vf *vf); +}; + +/* Virtchnl/SR-IOV config info */ +struct ice_vfs { + DECLARE_HASHTABLE(table, 8); /* table of VF entries */ + 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 */ + unsigned long last_printed_mdd_jiffies; /* MDD message rate limit */ + DECLARE_BITMAP(malvfs, ICE_MAX_SRIOV_VFS); /* malicious VF indicator */ +}; + +/* VF information structure */ +struct ice_vf { + struct hlist_node entry; + struct rcu_head rcu; + struct kref refcnt; + struct ice_pf *pf; + + /* Used during virtchnl message handling and NDO ops against the VF + * that will trigger a VFR + */ + struct mutex cfg_lock; + + u16 vf_id; /* VF ID in the PF space */ + u16 lan_vsi_idx; /* index into PF struct */ + u16 ctrl_vsi_idx; + struct ice_vf_fdir fdir; + /* first vector index of this VF in the PF space */ + int first_vector_idx; + struct ice_sw *vf_sw_id; /* switch ID the VF VSIs connect to */ + struct virtchnl_version_info vf_ver; + u32 driver_caps; /* reported by VF driver */ + struct virtchnl_ether_addr dev_lan_addr; + struct virtchnl_ether_addr hw_lan_addr; + struct ice_time_mac legacy_last_added_umac; + DECLARE_BITMAP(txq_ena, ICE_MAX_RSS_QS_PER_VF); + DECLARE_BITMAP(rxq_ena, ICE_MAX_RSS_QS_PER_VF); + struct ice_vlan port_vlan_info; /* Port VLAN ID, QoS, and TPID */ + struct virtchnl_vlan_caps vlan_v2_caps; + u8 pf_set_mac:1; /* VF MAC address set by VMM admin */ + u8 trusted:1; + u8 spoofchk:1; + u8 link_forced:1; + u8 link_up:1; /* only valid if VF link is forced */ + /* VSI indices - actual VSI pointers are maintained in the PF structure + * When assigned, these will be non-zero, because VSI 0 is always + * the main LAN VSI for the PF. + */ + u16 lan_vsi_num; /* ID as used by firmware */ + unsigned int min_tx_rate; /* Minimum Tx bandwidth limit in Mbps */ + unsigned int max_tx_rate; /* Maximum Tx bandwidth limit in Mbps */ + DECLARE_BITMAP(vf_states, ICE_VF_STATES_NBITS); /* VF runtime states */ + + unsigned long vf_caps; /* VF's adv. capabilities */ + u8 num_req_qs; /* num of queue pairs requested by VF */ + u16 num_mac; + u16 num_vf_qs; /* num of queue configured per VF */ + struct ice_mdd_vf_events mdd_rx_events; + struct ice_mdd_vf_events mdd_tx_events; + DECLARE_BITMAP(opcodes_allowlist, VIRTCHNL_OP_MAX); + + struct ice_repr *repr; + const struct ice_virtchnl_ops *virtchnl_ops; + const struct ice_vf_ops *vf_ops; + + /* devlink port data */ + struct devlink_port devlink_port; +}; + +/* Flags for controlling behavior of ice_reset_vf */ +enum ice_vf_reset_flags { + ICE_VF_RESET_VFLR = BIT(0), /* Indicate a VFLR reset */ + ICE_VF_RESET_NOTIFY = BIT(1), /* Notify VF prior to reset */ + ICE_VF_RESET_LOCK = BIT(2), /* Acquire the VF cfg_lock */ +}; + +static inline u16 ice_vf_get_port_vlan_id(struct ice_vf *vf) +{ + return vf->port_vlan_info.vid; +} + +static inline u8 ice_vf_get_port_vlan_prio(struct ice_vf *vf) +{ + return vf->port_vlan_info.prio; +} + +static inline bool ice_vf_is_port_vlan_ena(struct ice_vf *vf) +{ + return (ice_vf_get_port_vlan_id(vf) || ice_vf_get_port_vlan_prio(vf)); +} + +static inline u16 ice_vf_get_port_vlan_tpid(struct ice_vf *vf) +{ + return vf->port_vlan_info.tpid; +} + +/* VF Hash Table access functions + * + * These functions provide abstraction for interacting with the VF hash table. + * In general, direct access to the hash table should be avoided outside of + * these functions where possible. + * + * The VF entries in the hash table are protected by reference counting to + * track lifetime of accesses from the table. The ice_get_vf_by_id() function + * obtains a reference to the VF structure which must be dropped by using + * ice_put_vf(). + */ + +/** + * ice_for_each_vf - Iterate over each VF entry + * @pf: pointer to the PF private structure + * @bkt: bucket index used for iteration + * @vf: pointer to the VF entry currently being processed in the loop + * + * The bkt variable is an unsigned integer iterator used to traverse the VF + * entries. It is *not* guaranteed to be the VF's vf_id. Do not assume it is. + * Use vf->vf_id to get the id number if needed. + * + * The caller is expected to be under the table_lock mutex for the entire + * loop. Use this iterator if your loop is long or if it might sleep. + */ +#define ice_for_each_vf(pf, bkt, vf) \ + hash_for_each((pf)->vfs.table, (bkt), (vf), entry) + +/** + * ice_for_each_vf_rcu - Iterate over each VF entry protected by RCU + * @pf: pointer to the PF private structure + * @bkt: bucket index used for iteration + * @vf: pointer to the VF entry currently being processed in the loop + * + * The bkt variable is an unsigned integer iterator used to traverse the VF + * entries. It is *not* guaranteed to be the VF's vf_id. Do not assume it is. + * Use vf->vf_id to get the id number if needed. + * + * The caller is expected to be under rcu_read_lock() for the entire loop. + * Only use this iterator if your loop is short and you can guarantee it does + * not sleep. + */ +#define ice_for_each_vf_rcu(pf, bkt, vf) \ + hash_for_each_rcu((pf)->vfs.table, (bkt), (vf), entry) + +#ifdef CONFIG_PCI_IOV +struct ice_vf *ice_get_vf_by_id(struct ice_pf *pf, u16 vf_id); +void ice_put_vf(struct ice_vf *vf); +bool ice_has_vfs(struct ice_pf *pf); +u16 ice_get_num_vfs(struct ice_pf *pf); +struct ice_vsi *ice_get_vf_vsi(struct ice_vf *vf); +bool ice_is_vf_disabled(struct ice_vf *vf); +int ice_check_vf_ready_for_cfg(struct ice_vf *vf); +void ice_set_vf_state_qs_dis(struct ice_vf *vf); +bool ice_is_any_vf_in_unicast_promisc(struct ice_pf *pf); +void +ice_vf_get_promisc_masks(struct ice_vf *vf, struct ice_vsi *vsi, + u8 *ucast_m, u8 *mcast_m); +int +ice_vf_set_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m); +int +ice_vf_clear_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m); +int ice_reset_vf(struct ice_vf *vf, u32 flags); +void ice_reset_all_vfs(struct ice_pf *pf); +#else /* CONFIG_PCI_IOV */ +static inline struct ice_vf *ice_get_vf_by_id(struct ice_pf *pf, u16 vf_id) +{ + return NULL; +} + +static inline void ice_put_vf(struct ice_vf *vf) +{ +} + +static inline bool ice_has_vfs(struct ice_pf *pf) +{ + return false; +} + +static inline u16 ice_get_num_vfs(struct ice_pf *pf) +{ + return 0; +} + +static inline struct ice_vsi *ice_get_vf_vsi(struct ice_vf *vf) +{ + return NULL; +} + +static inline bool ice_is_vf_disabled(struct ice_vf *vf) +{ + return true; +} + +static inline int ice_check_vf_ready_for_cfg(struct ice_vf *vf) +{ + return -EOPNOTSUPP; +} + +static inline void ice_set_vf_state_qs_dis(struct ice_vf *vf) +{ +} + +static inline bool ice_is_any_vf_in_unicast_promisc(struct ice_pf *pf) +{ + return false; +} + +static inline int +ice_vf_set_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_vf_clear_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m) +{ + return -EOPNOTSUPP; +} + +static inline int ice_reset_vf(struct ice_vf *vf, u32 flags) +{ + return 0; +} + +static inline void ice_reset_all_vfs(struct ice_pf *pf) +{ +} +#endif /* !CONFIG_PCI_IOV */ + +#endif /* _ICE_VF_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h new file mode 100644 index 000000000000..15887e772c76 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2018-2021, Intel Corporation. */ + +#ifndef _ICE_VF_LIB_PRIVATE_H_ +#define _ICE_VF_LIB_PRIVATE_H_ + +#include "ice_vf_lib.h" + +/* This header file is for exposing functions in ice_vf_lib.c to other files + * which are also conditionally compiled depending on CONFIG_PCI_IOV. + * Functions which may be used by other files should be exposed as part of + * ice_vf_lib.h + * + * Functions in this file are exposed only when CONFIG_PCI_IOV is enabled, and + * thus this header must not be included by .c files which may be compiled + * with CONFIG_PCI_IOV disabled. + * + * To avoid this, only include this header file directly within .c files that + * are conditionally enabled in the "ice-$(CONFIG_PCI_IOV)" block. + */ + +#ifndef CONFIG_PCI_IOV +#warning "Only include ice_vf_lib_private.h in CONFIG_PCI_IOV virtualization files" +#endif + +void ice_dis_vf_qs(struct ice_vf *vf); +int ice_check_vf_init(struct ice_vf *vf); +struct ice_port_info *ice_vf_get_port_info(struct ice_vf *vf); +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); +void ice_vf_invalidate_vsi(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_mbx.c b/drivers/net/ethernet/intel/ice/ice_vf_mbx.c new file mode 100644 index 000000000000..fc8c93fa4455 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_vf_mbx.c @@ -0,0 +1,532 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018, Intel Corporation. */ + +#include "ice_common.h" +#include "ice_vf_mbx.h" + +/** + * ice_aq_send_msg_to_vf + * @hw: pointer to the hardware structure + * @vfid: VF ID to send msg + * @v_opcode: opcodes for VF-PF communication + * @v_retval: return error code + * @msg: pointer to the msg buffer + * @msglen: msg length + * @cd: pointer to command details + * + * Send message to VF driver (0x0802) using mailbox + * queue and asynchronously sending message via + * ice_sq_send_cmd() function + */ +int +ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval, + u8 *msg, u16 msglen, struct ice_sq_cd *cd) +{ + struct ice_aqc_pf_vf_msg *cmd; + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_mbx_opc_send_msg_to_vf); + + cmd = &desc.params.virt; + cmd->id = cpu_to_le32(vfid); + + desc.cookie_high = cpu_to_le32(v_opcode); + desc.cookie_low = cpu_to_le32(v_retval); + + if (msglen) + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + return ice_sq_send_cmd(hw, &hw->mailboxq, &desc, msg, msglen, cd); +} + +/** + * ice_conv_link_speed_to_virtchnl + * @adv_link_support: determines the format of the returned link speed + * @link_speed: variable containing the link_speed to be converted + * + * Convert link speed supported by HW to link speed supported by virtchnl. + * If adv_link_support is true, then return link speed in Mbps. Else return + * link speed as a VIRTCHNL_LINK_SPEED_* casted to a u32. Note that the caller + * needs to cast back to an enum virtchnl_link_speed in the case where + * adv_link_support is false, but when adv_link_support is true the caller can + * expect the speed in Mbps. + */ +u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed) +{ + u32 speed; + + if (adv_link_support) + switch (link_speed) { + case ICE_AQ_LINK_SPEED_10MB: + speed = ICE_LINK_SPEED_10MBPS; + break; + case ICE_AQ_LINK_SPEED_100MB: + speed = ICE_LINK_SPEED_100MBPS; + break; + case ICE_AQ_LINK_SPEED_1000MB: + speed = ICE_LINK_SPEED_1000MBPS; + break; + case ICE_AQ_LINK_SPEED_2500MB: + speed = ICE_LINK_SPEED_2500MBPS; + break; + case ICE_AQ_LINK_SPEED_5GB: + speed = ICE_LINK_SPEED_5000MBPS; + break; + case ICE_AQ_LINK_SPEED_10GB: + speed = ICE_LINK_SPEED_10000MBPS; + break; + case ICE_AQ_LINK_SPEED_20GB: + speed = ICE_LINK_SPEED_20000MBPS; + break; + case ICE_AQ_LINK_SPEED_25GB: + speed = ICE_LINK_SPEED_25000MBPS; + break; + case ICE_AQ_LINK_SPEED_40GB: + speed = ICE_LINK_SPEED_40000MBPS; + break; + case ICE_AQ_LINK_SPEED_50GB: + speed = ICE_LINK_SPEED_50000MBPS; + break; + case ICE_AQ_LINK_SPEED_100GB: + speed = ICE_LINK_SPEED_100000MBPS; + break; + default: + speed = ICE_LINK_SPEED_UNKNOWN; + break; + } + else + /* Virtchnl speeds are not defined for every speed supported in + * the hardware. To maintain compatibility with older AVF + * drivers, while reporting the speed the new speed values are + * resolved to the closest known virtchnl speeds + */ + switch (link_speed) { + case ICE_AQ_LINK_SPEED_10MB: + case ICE_AQ_LINK_SPEED_100MB: + speed = (u32)VIRTCHNL_LINK_SPEED_100MB; + break; + case ICE_AQ_LINK_SPEED_1000MB: + case ICE_AQ_LINK_SPEED_2500MB: + case ICE_AQ_LINK_SPEED_5GB: + speed = (u32)VIRTCHNL_LINK_SPEED_1GB; + break; + case ICE_AQ_LINK_SPEED_10GB: + speed = (u32)VIRTCHNL_LINK_SPEED_10GB; + break; + case ICE_AQ_LINK_SPEED_20GB: + speed = (u32)VIRTCHNL_LINK_SPEED_20GB; + break; + case ICE_AQ_LINK_SPEED_25GB: + speed = (u32)VIRTCHNL_LINK_SPEED_25GB; + break; + case ICE_AQ_LINK_SPEED_40GB: + case ICE_AQ_LINK_SPEED_50GB: + case ICE_AQ_LINK_SPEED_100GB: + speed = (u32)VIRTCHNL_LINK_SPEED_40GB; + break; + default: + speed = (u32)VIRTCHNL_LINK_SPEED_UNKNOWN; + break; + } + + return speed; +} + +/* The mailbox overflow detection algorithm helps to check if there + * is a possibility of a malicious VF transmitting too many MBX messages to the + * PF. + * 1. The mailbox snapshot structure, ice_mbx_snapshot, is initialized during + * driver initialization in ice_init_hw() using ice_mbx_init_snapshot(). + * The struct ice_mbx_snapshot helps to track and traverse a static window of + * messages within the mailbox queue while looking for a malicious VF. + * + * 2. When the caller starts processing its mailbox queue in response to an + * interrupt, the structure ice_mbx_snapshot is expected to be cleared before + * the algorithm can be run for the first time for that interrupt. This can be + * done via ice_mbx_reset_snapshot(). + * + * 3. For every message read by the caller from the MBX Queue, the caller must + * call the detection algorithm's entry function ice_mbx_vf_state_handler(). + * Before every call to ice_mbx_vf_state_handler() the struct ice_mbx_data is + * filled as it is required to be passed to the algorithm. + * + * 4. Every time a message is read from the MBX queue, a VFId is received which + * is passed to the state handler. The boolean output is_malvf of the state + * handler ice_mbx_vf_state_handler() serves as an indicator to the caller + * whether this VF is malicious or not. + * + * 5. When a VF is identified to be malicious, the caller can send a message + * to the system administrator. The caller can invoke ice_mbx_report_malvf() + * to help determine if a malicious VF is to be reported or not. This function + * requires the caller to maintain a global bitmap to track all malicious VFs + * and pass that to ice_mbx_report_malvf() along with the VFID which was identified + * to be malicious by ice_mbx_vf_state_handler(). + * + * 6. The global bitmap maintained by PF can be cleared completely if PF is in + * reset or the bit corresponding to a VF can be cleared if that VF is in reset. + * When a VF is shut down and brought back up, we assume that the new VF + * brought up is not malicious and hence report it if found malicious. + * + * 7. The function ice_mbx_reset_snapshot() is called to reset the information + * in ice_mbx_snapshot for every new mailbox interrupt handled. + * + * 8. The memory allocated for variables in ice_mbx_snapshot is de-allocated + * when driver is unloaded. + */ +#define ICE_RQ_DATA_MASK(rq_data) ((rq_data) & PF_MBX_ARQH_ARQH_M) +/* Using the highest value for an unsigned 16-bit value 0xFFFF to indicate that + * the max messages check must be ignored in the algorithm + */ +#define ICE_IGNORE_MAX_MSG_CNT 0xFFFF + +/** + * ice_mbx_traverse - Pass through mailbox snapshot + * @hw: pointer to the HW struct + * @new_state: new algorithm state + * + * Traversing the mailbox static snapshot without checking + * for malicious VFs. + */ +static void +ice_mbx_traverse(struct ice_hw *hw, + enum ice_mbx_snapshot_state *new_state) +{ + struct ice_mbx_snap_buffer_data *snap_buf; + u32 num_iterations; + + snap_buf = &hw->mbx_snapshot.mbx_buf; + + /* As mailbox buffer is circular, applying a mask + * on the incremented iteration count. + */ + num_iterations = ICE_RQ_DATA_MASK(++snap_buf->num_iterations); + + /* Checking either of the below conditions to exit snapshot traversal: + * Condition-1: If the number of iterations in the mailbox is equal to + * the mailbox head which would indicate that we have reached the end + * of the static snapshot. + * Condition-2: If the maximum messages serviced in the mailbox for a + * given interrupt is the highest possible value then there is no need + * to check if the number of messages processed is equal to it. If not + * check if the number of messages processed is greater than or equal + * to the maximum number of mailbox entries serviced in current work item. + */ + if (num_iterations == snap_buf->head || + (snap_buf->max_num_msgs_mbx < ICE_IGNORE_MAX_MSG_CNT && + ++snap_buf->num_msg_proc >= snap_buf->max_num_msgs_mbx)) + *new_state = ICE_MAL_VF_DETECT_STATE_NEW_SNAPSHOT; +} + +/** + * ice_mbx_detect_malvf - Detect malicious VF in snapshot + * @hw: pointer to the HW struct + * @vf_id: relative virtual function ID + * @new_state: new algorithm state + * @is_malvf: boolean output to indicate if VF is malicious + * + * This function tracks the number of asynchronous messages + * sent per VF and marks the VF as malicious if it exceeds + * the permissible number of messages to send. + */ +static int +ice_mbx_detect_malvf(struct ice_hw *hw, u16 vf_id, + enum ice_mbx_snapshot_state *new_state, + bool *is_malvf) +{ + struct ice_mbx_snapshot *snap = &hw->mbx_snapshot; + + if (vf_id >= snap->mbx_vf.vfcntr_len) + return -EIO; + + /* increment the message count in the VF array */ + snap->mbx_vf.vf_cntr[vf_id]++; + + if (snap->mbx_vf.vf_cntr[vf_id] >= ICE_ASYNC_VF_MSG_THRESHOLD) + *is_malvf = true; + + /* continue to iterate through the mailbox snapshot */ + ice_mbx_traverse(hw, new_state); + + return 0; +} + +/** + * ice_mbx_reset_snapshot - Reset mailbox snapshot structure + * @snap: pointer to mailbox snapshot structure in the ice_hw struct + * + * Reset the mailbox snapshot structure and clear VF counter array. + */ +static void ice_mbx_reset_snapshot(struct ice_mbx_snapshot *snap) +{ + u32 vfcntr_len; + + if (!snap || !snap->mbx_vf.vf_cntr) + return; + + /* Clear VF counters. */ + vfcntr_len = snap->mbx_vf.vfcntr_len; + if (vfcntr_len) + memset(snap->mbx_vf.vf_cntr, 0, + (vfcntr_len * sizeof(*snap->mbx_vf.vf_cntr))); + + /* Reset mailbox snapshot for a new capture. */ + memset(&snap->mbx_buf, 0, sizeof(snap->mbx_buf)); + snap->mbx_buf.state = ICE_MAL_VF_DETECT_STATE_NEW_SNAPSHOT; +} + +/** + * ice_mbx_vf_state_handler - Handle states of the overflow algorithm + * @hw: pointer to the HW struct + * @mbx_data: pointer to structure containing mailbox data + * @vf_id: relative virtual function (VF) ID + * @is_malvf: boolean output to indicate if VF is malicious + * + * The function serves as an entry point for the malicious VF + * detection algorithm by handling the different states and state + * transitions of the algorithm: + * New snapshot: This state is entered when creating a new static + * snapshot. The data from any previous mailbox snapshot is + * cleared and a new capture of the mailbox head and tail is + * logged. This will be the new static snapshot to detect + * asynchronous messages sent by VFs. On capturing the snapshot + * and depending on whether the number of pending messages in that + * snapshot exceed the watermark value, the state machine enters + * traverse or detect states. + * Traverse: If pending message count is below watermark then iterate + * through the snapshot without any action on VF. + * Detect: If pending message count exceeds watermark traverse + * the static snapshot and look for a malicious VF. + */ +int +ice_mbx_vf_state_handler(struct ice_hw *hw, + struct ice_mbx_data *mbx_data, u16 vf_id, + bool *is_malvf) +{ + struct ice_mbx_snapshot *snap = &hw->mbx_snapshot; + struct ice_mbx_snap_buffer_data *snap_buf; + struct ice_ctl_q_info *cq = &hw->mailboxq; + enum ice_mbx_snapshot_state new_state; + int status = 0; + + if (!is_malvf || !mbx_data) + return -EINVAL; + + /* When entering the mailbox state machine assume that the VF + * is not malicious until detected. + */ + *is_malvf = false; + + /* Checking if max messages allowed to be processed while servicing current + * interrupt is not less than the defined AVF message threshold. + */ + if (mbx_data->max_num_msgs_mbx <= ICE_ASYNC_VF_MSG_THRESHOLD) + return -EINVAL; + + /* The watermark value should not be lesser than the threshold limit + * set for the number of asynchronous messages a VF can send to mailbox + * nor should it be greater than the maximum number of messages in the + * mailbox serviced in current interrupt. + */ + if (mbx_data->async_watermark_val < ICE_ASYNC_VF_MSG_THRESHOLD || + mbx_data->async_watermark_val > mbx_data->max_num_msgs_mbx) + return -EINVAL; + + new_state = ICE_MAL_VF_DETECT_STATE_INVALID; + snap_buf = &snap->mbx_buf; + + switch (snap_buf->state) { + case ICE_MAL_VF_DETECT_STATE_NEW_SNAPSHOT: + /* Clear any previously held data in mailbox snapshot structure. */ + ice_mbx_reset_snapshot(snap); + + /* Collect the pending ARQ count, number of messages processed and + * the maximum number of messages allowed to be processed from the + * Mailbox for current interrupt. + */ + snap_buf->num_pending_arq = mbx_data->num_pending_arq; + snap_buf->num_msg_proc = mbx_data->num_msg_proc; + snap_buf->max_num_msgs_mbx = mbx_data->max_num_msgs_mbx; + + /* Capture a new static snapshot of the mailbox by logging the + * head and tail of snapshot and set num_iterations to the tail + * value to mark the start of the iteration through the snapshot. + */ + snap_buf->head = ICE_RQ_DATA_MASK(cq->rq.next_to_clean + + mbx_data->num_pending_arq); + snap_buf->tail = ICE_RQ_DATA_MASK(cq->rq.next_to_clean - 1); + snap_buf->num_iterations = snap_buf->tail; + + /* Pending ARQ messages returned by ice_clean_rq_elem + * is the difference between the head and tail of the + * mailbox queue. Comparing this value against the watermark + * helps to check if we potentially have malicious VFs. + */ + if (snap_buf->num_pending_arq >= + mbx_data->async_watermark_val) { + new_state = ICE_MAL_VF_DETECT_STATE_DETECT; + status = ice_mbx_detect_malvf(hw, vf_id, &new_state, is_malvf); + } else { + new_state = ICE_MAL_VF_DETECT_STATE_TRAVERSE; + ice_mbx_traverse(hw, &new_state); + } + break; + + case ICE_MAL_VF_DETECT_STATE_TRAVERSE: + new_state = ICE_MAL_VF_DETECT_STATE_TRAVERSE; + ice_mbx_traverse(hw, &new_state); + break; + + case ICE_MAL_VF_DETECT_STATE_DETECT: + new_state = ICE_MAL_VF_DETECT_STATE_DETECT; + status = ice_mbx_detect_malvf(hw, vf_id, &new_state, is_malvf); + break; + + default: + new_state = ICE_MAL_VF_DETECT_STATE_INVALID; + status = -EIO; + } + + snap_buf->state = new_state; + + return status; +} + +/** + * ice_mbx_report_malvf - Track and note malicious VF + * @hw: pointer to the HW struct + * @all_malvfs: all malicious VFs tracked by PF + * @bitmap_len: length of bitmap in bits + * @vf_id: relative virtual function ID of the malicious VF + * @report_malvf: boolean to indicate if malicious VF must be reported + * + * This function will update a bitmap that keeps track of the malicious + * VFs attached to the PF. A malicious VF must be reported only once if + * discovered between VF resets or loading so the function checks + * the input vf_id against the bitmap to verify if the VF has been + * detected in any previous mailbox iterations. + */ +int +ice_mbx_report_malvf(struct ice_hw *hw, unsigned long *all_malvfs, + u16 bitmap_len, u16 vf_id, bool *report_malvf) +{ + if (!all_malvfs || !report_malvf) + return -EINVAL; + + *report_malvf = false; + + if (bitmap_len < hw->mbx_snapshot.mbx_vf.vfcntr_len) + return -EINVAL; + + if (vf_id >= bitmap_len) + return -EIO; + + /* If the vf_id is found in the bitmap set bit and boolean to true */ + if (!test_and_set_bit(vf_id, all_malvfs)) + *report_malvf = true; + + return 0; +} + +/** + * ice_mbx_clear_malvf - Clear VF bitmap and counter for VF ID + * @snap: pointer to the mailbox snapshot structure + * @all_malvfs: all malicious VFs tracked by PF + * @bitmap_len: length of bitmap in bits + * @vf_id: relative virtual function ID of the malicious VF + * + * In case of a VF reset, this function can be called to clear + * the bit corresponding to the VF ID in the bitmap tracking all + * malicious VFs attached to the PF. The function also clears the + * VF counter array at the index of the VF ID. This is to ensure + * that the new VF loaded is not considered malicious before going + * through the overflow detection algorithm. + */ +int +ice_mbx_clear_malvf(struct ice_mbx_snapshot *snap, unsigned long *all_malvfs, + u16 bitmap_len, u16 vf_id) +{ + if (!snap || !all_malvfs) + return -EINVAL; + + if (bitmap_len < snap->mbx_vf.vfcntr_len) + return -EINVAL; + + /* Ensure VF ID value is not larger than bitmap or VF counter length */ + if (vf_id >= bitmap_len || vf_id >= snap->mbx_vf.vfcntr_len) + return -EIO; + + /* Clear VF ID bit in the bitmap tracking malicious VFs attached to PF */ + clear_bit(vf_id, all_malvfs); + + /* Clear the VF counter in the mailbox snapshot structure for that VF ID. + * This is to ensure that if a VF is unloaded and a new one brought back + * up with the same VF ID for a snapshot currently in traversal or detect + * state the counter for that VF ID does not increment on top of existing + * values in the mailbox overflow detection algorithm. + */ + snap->mbx_vf.vf_cntr[vf_id] = 0; + + return 0; +} + +/** + * ice_mbx_init_snapshot - Initialize mailbox snapshot structure + * @hw: pointer to the hardware structure + * @vf_count: number of VFs allocated on a PF + * + * Clear the mailbox snapshot structure and allocate memory + * for the VF counter array based on the number of VFs allocated + * on that PF. + * + * Assumption: This function will assume ice_get_caps() has already been + * called to ensure that the vf_count can be compared against the number + * of VFs supported as defined in the functional capabilities of the device. + */ +int ice_mbx_init_snapshot(struct ice_hw *hw, u16 vf_count) +{ + struct ice_mbx_snapshot *snap = &hw->mbx_snapshot; + + /* Ensure that the number of VFs allocated is non-zero and + * is not greater than the number of supported VFs defined in + * the functional capabilities of the PF. + */ + if (!vf_count || vf_count > hw->func_caps.num_allocd_vfs) + return -EINVAL; + + snap->mbx_vf.vf_cntr = devm_kcalloc(ice_hw_to_dev(hw), vf_count, + sizeof(*snap->mbx_vf.vf_cntr), + GFP_KERNEL); + if (!snap->mbx_vf.vf_cntr) + return -ENOMEM; + + /* Setting the VF counter length to the number of allocated + * VFs for given PF's functional capabilities. + */ + snap->mbx_vf.vfcntr_len = vf_count; + + /* Clear mbx_buf in the mailbox snaphot structure and setting the + * mailbox snapshot state to a new capture. + */ + memset(&snap->mbx_buf, 0, sizeof(snap->mbx_buf)); + snap->mbx_buf.state = ICE_MAL_VF_DETECT_STATE_NEW_SNAPSHOT; + + return 0; +} + +/** + * ice_mbx_deinit_snapshot - Free mailbox snapshot structure + * @hw: pointer to the hardware structure + * + * Clear the mailbox snapshot structure and free the VF counter array. + */ +void ice_mbx_deinit_snapshot(struct ice_hw *hw) +{ + struct ice_mbx_snapshot *snap = &hw->mbx_snapshot; + + /* Free VF counter array and reset VF counter length */ + devm_kfree(ice_hw_to_dev(hw), snap->mbx_vf.vf_cntr); + snap->mbx_vf.vfcntr_len = 0; + + /* Clear mbx_buf in the mailbox snaphot structure */ + memset(&snap->mbx_buf, 0, sizeof(snap->mbx_buf)); +} diff --git a/drivers/net/ethernet/intel/ice/ice_vf_mbx.h b/drivers/net/ethernet/intel/ice/ice_vf_mbx.h new file mode 100644 index 000000000000..582716e6d5f9 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_vf_mbx.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018, Intel Corporation. */ + +#ifndef _ICE_VF_MBX_H_ +#define _ICE_VF_MBX_H_ + +#include "ice_type.h" +#include "ice_controlq.h" + +/* Defining the mailbox message threshold as 63 asynchronous + * pending messages. Normal VF functionality does not require + * sending more than 63 asynchronous pending message. + */ +#define ICE_ASYNC_VF_MSG_THRESHOLD 63 + +#ifdef CONFIG_PCI_IOV +int +ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval, + u8 *msg, u16 msglen, struct ice_sq_cd *cd); + +u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed); +int +ice_mbx_vf_state_handler(struct ice_hw *hw, struct ice_mbx_data *mbx_data, + u16 vf_id, bool *is_mal_vf); +int +ice_mbx_clear_malvf(struct ice_mbx_snapshot *snap, unsigned long *all_malvfs, + u16 bitmap_len, u16 vf_id); +int ice_mbx_init_snapshot(struct ice_hw *hw, u16 vf_count); +void ice_mbx_deinit_snapshot(struct ice_hw *hw); +int +ice_mbx_report_malvf(struct ice_hw *hw, unsigned long *all_malvfs, + u16 bitmap_len, u16 vf_id, bool *report_malvf); +#else /* CONFIG_PCI_IOV */ +static inline int +ice_aq_send_msg_to_vf(struct ice_hw __always_unused *hw, + u16 __always_unused vfid, u32 __always_unused v_opcode, + u32 __always_unused v_retval, u8 __always_unused *msg, + u16 __always_unused msglen, + struct ice_sq_cd __always_unused *cd) +{ + return 0; +} + +static inline u32 +ice_conv_link_speed_to_virtchnl(bool __always_unused adv_link_support, + u16 __always_unused link_speed) +{ + return 0; +} + +#endif /* CONFIG_PCI_IOV */ +#endif /* _ICE_VF_MBX_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 new file mode 100644 index 000000000000..5ecc0ee9a78e --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c @@ -0,0 +1,211 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#include "ice_vsi_vlan_ops.h" +#include "ice_vsi_vlan_lib.h" +#include "ice_vlan_mode.h" +#include "ice.h" +#include "ice_vf_vsi_vlan_ops.h" +#include "ice_sriov.h" + +static int +noop_vlan_arg(struct ice_vsi __always_unused *vsi, + struct ice_vlan __always_unused *vlan) +{ + return 0; +} + +static int +noop_vlan(struct ice_vsi __always_unused *vsi) +{ + return 0; +} + +/** + * ice_vf_vsi_init_vlan_ops - Initialize default VSI VLAN ops for VF VSI + * @vsi: VF's VSI being configured + * + * If Double VLAN Mode (DVM) is enabled, assume that the VF supports the new + * VIRTCHNL_VF_VLAN_OFFLOAD_V2 capability and set up the VLAN ops accordingly. + * If SVM is enabled maintain the same level of VLAN support previous to + * VIRTCHNL_VF_VLAN_OFFLOAD_V2. + */ +void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi) +{ + struct ice_vsi_vlan_ops *vlan_ops; + struct ice_pf *pf = vsi->back; + struct ice_vf *vf = vsi->vf; + + if (WARN_ON(!vf)) + return; + + if (ice_is_dvm_ena(&pf->hw)) { + vlan_ops = &vsi->outer_vlan_ops; + + /* outer 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)) { + /* setup outer VLAN ops */ + vlan_ops->set_port_vlan = ice_vsi_set_outer_port_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 { + 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; + + /* 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; + } else { + 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; + } + } +} + +/** + * ice_vf_vsi_cfg_dvm_legacy_vlan_mode - Config VLAN mode for old VFs in DVM + * @vsi: VF's VSI being configured + * + * This should only be called when Double VLAN Mode (DVM) is enabled, there + * is not a port VLAN enabled on this VF, and the VF negotiates + * VIRTCHNL_VF_OFFLOAD_VLAN. + * + * This function sets up the VF VSI's inner and outer ice_vsi_vlan_ops and also + * initializes software only VLAN mode (i.e. allow all VLANs). Also, use no-op + * implementations for any functions that may be called during the lifetime of + * the VF so these methods do nothing and succeed. + */ +void ice_vf_vsi_cfg_dvm_legacy_vlan_mode(struct ice_vsi *vsi) +{ + struct ice_vsi_vlan_ops *vlan_ops; + struct ice_vf *vf = vsi->vf; + struct device *dev; + + if (WARN_ON(!vf)) + return; + + dev = ice_pf_to_dev(vf->pf); + + if (!ice_is_dvm_ena(&vsi->back->hw) || ice_vf_is_port_vlan_ena(vf)) + return; + + vlan_ops = &vsi->outer_vlan_ops; + + /* Rx VLAN filtering always disabled to allow software offloaded VLANs + * for VFs that only support VIRTCHNL_VF_OFFLOAD_VLAN and don't have a + * port VLAN configured + */ + vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering; + /* Don't fail when attempting to enable Rx VLAN filtering */ + vlan_ops->ena_rx_filtering = noop_vlan; + + /* Tx VLAN filtering always disabled to allow software offloaded VLANs + * for VFs that only support VIRTCHNL_VF_OFFLOAD_VLAN and don't have a + * port VLAN configured + */ + vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering; + /* Don't fail when attempting to enable Tx VLAN filtering */ + vlan_ops->ena_tx_filtering = noop_vlan; + + if (vlan_ops->dis_rx_filtering(vsi)) + dev_dbg(dev, "Failed to disable Rx VLAN filtering for old VF without VIRTCHNL_VF_OFFLOAD_VLAN_V2 support\n"); + if (vlan_ops->dis_tx_filtering(vsi)) + dev_dbg(dev, "Failed to disable Tx VLAN filtering for old VF without VIRTHCNL_VF_OFFLOAD_VLAN_V2 support\n"); + + /* All outer VLAN offloads must be disabled */ + vlan_ops->dis_stripping = ice_vsi_dis_outer_stripping; + vlan_ops->dis_insertion = ice_vsi_dis_outer_insertion; + + if (vlan_ops->dis_stripping(vsi)) + dev_dbg(dev, "Failed to disable outer VLAN stripping for old VF without VIRTCHNL_VF_OFFLOAD_VLAN_V2 support\n"); + + if (vlan_ops->dis_insertion(vsi)) + dev_dbg(dev, "Failed to disable outer VLAN insertion for old VF without VIRTCHNL_VF_OFFLOAD_VLAN_V2 support\n"); + + /* All inner VLAN offloads must be disabled */ + vlan_ops = &vsi->inner_vlan_ops; + + vlan_ops->dis_stripping = ice_vsi_dis_outer_stripping; + vlan_ops->dis_insertion = ice_vsi_dis_outer_insertion; + + if (vlan_ops->dis_stripping(vsi)) + dev_dbg(dev, "Failed to disable inner VLAN stripping for old VF without VIRTCHNL_VF_OFFLOAD_VLAN_V2 support\n"); + + if (vlan_ops->dis_insertion(vsi)) + dev_dbg(dev, "Failed to disable inner VLAN insertion for old VF without VIRTCHNL_VF_OFFLOAD_VLAN_V2 support\n"); +} + +/** + * ice_vf_vsi_cfg_svm_legacy_vlan_mode - Config VLAN mode for old VFs in SVM + * @vsi: VF's VSI being configured + * + * This should only be called when Single VLAN Mode (SVM) is enabled, there is + * not a port VLAN enabled on this VF, and the VF negotiates + * VIRTCHNL_VF_OFFLOAD_VLAN. + * + * All of the normal SVM VLAN ops are identical for this case. However, by + * default Rx VLAN filtering should be turned off by default in this case. + */ +void ice_vf_vsi_cfg_svm_legacy_vlan_mode(struct ice_vsi *vsi) +{ + struct ice_vf *vf = vsi->vf; + + if (WARN_ON(!vf)) + return; + + if (ice_is_dvm_ena(&vsi->back->hw) || ice_vf_is_port_vlan_ena(vf)) + return; + + if (vsi->inner_vlan_ops.dis_rx_filtering(vsi)) + dev_dbg(ice_pf_to_dev(vf->pf), "Failed to disable Rx VLAN filtering for old VF with VIRTCHNL_VF_OFFLOAD_VLAN support\n"); +} 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 new file mode 100644 index 000000000000..875a4e615f39 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#ifndef _ICE_VF_VSI_VLAN_OPS_H_ +#define _ICE_VF_VSI_VLAN_OPS_H_ + +#include "ice_vsi_vlan_ops.h" + +struct ice_vsi; + +void ice_vf_vsi_cfg_dvm_legacy_vlan_mode(struct ice_vsi *vsi); +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); +#else +static inline void ice_vf_vsi_init_vlan_ops(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 new file mode 100644 index 000000000000..2b4c791b6cba --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -0,0 +1,3826 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2022, Intel Corporation. */ + +#include "ice_virtchnl.h" +#include "ice_vf_lib_private.h" +#include "ice.h" +#include "ice_base.h" +#include "ice_lib.h" +#include "ice_fltr.h" +#include "ice_virtchnl_allowlist.h" +#include "ice_vf_vsi_vlan_ops.h" +#include "ice_vlan.h" +#include "ice_flex_pipe.h" +#include "ice_dcb_lib.h" + +#define FIELD_SELECTOR(proto_hdr_field) \ + BIT((proto_hdr_field) & PROTO_HDR_FIELD_MASK) + +struct ice_vc_hdr_match_type { + u32 vc_hdr; /* virtchnl headers (VIRTCHNL_PROTO_HDR_XXX) */ + u32 ice_hdr; /* ice headers (ICE_FLOW_SEG_HDR_XXX) */ +}; + +static const struct ice_vc_hdr_match_type ice_vc_hdr_list[] = { + {VIRTCHNL_PROTO_HDR_NONE, ICE_FLOW_SEG_HDR_NONE}, + {VIRTCHNL_PROTO_HDR_ETH, ICE_FLOW_SEG_HDR_ETH}, + {VIRTCHNL_PROTO_HDR_S_VLAN, ICE_FLOW_SEG_HDR_VLAN}, + {VIRTCHNL_PROTO_HDR_C_VLAN, ICE_FLOW_SEG_HDR_VLAN}, + {VIRTCHNL_PROTO_HDR_IPV4, ICE_FLOW_SEG_HDR_IPV4 | + ICE_FLOW_SEG_HDR_IPV_OTHER}, + {VIRTCHNL_PROTO_HDR_IPV6, ICE_FLOW_SEG_HDR_IPV6 | + ICE_FLOW_SEG_HDR_IPV_OTHER}, + {VIRTCHNL_PROTO_HDR_TCP, ICE_FLOW_SEG_HDR_TCP}, + {VIRTCHNL_PROTO_HDR_UDP, ICE_FLOW_SEG_HDR_UDP}, + {VIRTCHNL_PROTO_HDR_SCTP, ICE_FLOW_SEG_HDR_SCTP}, + {VIRTCHNL_PROTO_HDR_PPPOE, ICE_FLOW_SEG_HDR_PPPOE}, + {VIRTCHNL_PROTO_HDR_GTPU_IP, ICE_FLOW_SEG_HDR_GTPU_IP}, + {VIRTCHNL_PROTO_HDR_GTPU_EH, ICE_FLOW_SEG_HDR_GTPU_EH}, + {VIRTCHNL_PROTO_HDR_GTPU_EH_PDU_DWN, + ICE_FLOW_SEG_HDR_GTPU_DWN}, + {VIRTCHNL_PROTO_HDR_GTPU_EH_PDU_UP, + ICE_FLOW_SEG_HDR_GTPU_UP}, + {VIRTCHNL_PROTO_HDR_L2TPV3, ICE_FLOW_SEG_HDR_L2TPV3}, + {VIRTCHNL_PROTO_HDR_ESP, ICE_FLOW_SEG_HDR_ESP}, + {VIRTCHNL_PROTO_HDR_AH, ICE_FLOW_SEG_HDR_AH}, + {VIRTCHNL_PROTO_HDR_PFCP, ICE_FLOW_SEG_HDR_PFCP_SESSION}, +}; + +struct ice_vc_hash_field_match_type { + u32 vc_hdr; /* virtchnl headers + * (VIRTCHNL_PROTO_HDR_XXX) + */ + u32 vc_hash_field; /* virtchnl hash fields selector + * FIELD_SELECTOR((VIRTCHNL_PROTO_HDR_ETH_XXX)) + */ + u64 ice_hash_field; /* ice hash fields + * (BIT_ULL(ICE_FLOW_FIELD_IDX_XXX)) + */ +}; + +static const struct +ice_vc_hash_field_match_type ice_vc_hash_field_list[] = { + {VIRTCHNL_PROTO_HDR_ETH, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ETH_SRC), + BIT_ULL(ICE_FLOW_FIELD_IDX_ETH_SA)}, + {VIRTCHNL_PROTO_HDR_ETH, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ETH_DST), + BIT_ULL(ICE_FLOW_FIELD_IDX_ETH_DA)}, + {VIRTCHNL_PROTO_HDR_ETH, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ETH_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ETH_DST), + ICE_FLOW_HASH_ETH}, + {VIRTCHNL_PROTO_HDR_ETH, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ETH_ETHERTYPE), + BIT_ULL(ICE_FLOW_FIELD_IDX_ETH_TYPE)}, + {VIRTCHNL_PROTO_HDR_S_VLAN, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_S_VLAN_ID), + BIT_ULL(ICE_FLOW_FIELD_IDX_S_VLAN)}, + {VIRTCHNL_PROTO_HDR_C_VLAN, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_C_VLAN_ID), + BIT_ULL(ICE_FLOW_FIELD_IDX_C_VLAN)}, + {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA)}, + {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA)}, + {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST), + ICE_FLOW_HASH_IPV4}, + {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT), + ICE_FLOW_HASH_IPV4 | BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_SA)}, + {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_DA)}, + {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST), + ICE_FLOW_HASH_IPV6}, + {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_SA) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_DA) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT), + ICE_FLOW_HASH_IPV6 | BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)}, + {VIRTCHNL_PROTO_HDR_TCP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_SRC_PORT), + BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_SRC_PORT)}, + {VIRTCHNL_PROTO_HDR_TCP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_DST_PORT), + BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_DST_PORT)}, + {VIRTCHNL_PROTO_HDR_TCP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_SRC_PORT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_DST_PORT), + ICE_FLOW_HASH_TCP_PORT}, + {VIRTCHNL_PROTO_HDR_UDP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_SRC_PORT), + BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_SRC_PORT)}, + {VIRTCHNL_PROTO_HDR_UDP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_DST_PORT), + BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_DST_PORT)}, + {VIRTCHNL_PROTO_HDR_UDP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_SRC_PORT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_DST_PORT), + ICE_FLOW_HASH_UDP_PORT}, + {VIRTCHNL_PROTO_HDR_SCTP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_SRC_PORT), + BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT)}, + {VIRTCHNL_PROTO_HDR_SCTP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_DST_PORT), + BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_DST_PORT)}, + {VIRTCHNL_PROTO_HDR_SCTP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_SRC_PORT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_DST_PORT), + ICE_FLOW_HASH_SCTP_PORT}, + {VIRTCHNL_PROTO_HDR_PPPOE, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_PPPOE_SESS_ID), + BIT_ULL(ICE_FLOW_FIELD_IDX_PPPOE_SESS_ID)}, + {VIRTCHNL_PROTO_HDR_GTPU_IP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_GTPU_IP_TEID), + BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_IP_TEID)}, + {VIRTCHNL_PROTO_HDR_L2TPV3, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_L2TPV3_SESS_ID), + BIT_ULL(ICE_FLOW_FIELD_IDX_L2TPV3_SESS_ID)}, + {VIRTCHNL_PROTO_HDR_ESP, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ESP_SPI), + BIT_ULL(ICE_FLOW_FIELD_IDX_ESP_SPI)}, + {VIRTCHNL_PROTO_HDR_AH, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_AH_SPI), + BIT_ULL(ICE_FLOW_FIELD_IDX_AH_SPI)}, + {VIRTCHNL_PROTO_HDR_PFCP, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_PFCP_SEID), + BIT_ULL(ICE_FLOW_FIELD_IDX_PFCP_SEID)}, +}; + +/** + * ice_vc_vf_broadcast - Broadcast a message to all VFs on PF + * @pf: pointer to the PF structure + * @v_opcode: operation code + * @v_retval: return value + * @msg: pointer to the msg buffer + * @msglen: msg length + */ +static void +ice_vc_vf_broadcast(struct ice_pf *pf, enum virtchnl_ops v_opcode, + enum virtchnl_status_code v_retval, u8 *msg, u16 msglen) +{ + struct ice_hw *hw = &pf->hw; + struct ice_vf *vf; + unsigned int bkt; + + mutex_lock(&pf->vfs.table_lock); + ice_for_each_vf(pf, bkt, vf) { + /* Not all vfs are enabled so skip the ones that are not */ + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states) && + !test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) + continue; + + /* Ignore return value on purpose - a given VF may fail, but + * we need to keep going and send to all of them + */ + ice_aq_send_msg_to_vf(hw, vf->vf_id, v_opcode, v_retval, msg, + msglen, NULL); + } + mutex_unlock(&pf->vfs.table_lock); +} + +/** + * ice_set_pfe_link - Set the link speed/status of the virtchnl_pf_event + * @vf: pointer to the VF structure + * @pfe: pointer to the virtchnl_pf_event to set link speed/status for + * @ice_link_speed: link speed specified by ICE_AQ_LINK_SPEED_* + * @link_up: whether or not to set the link up/down + */ +static void +ice_set_pfe_link(struct ice_vf *vf, struct virtchnl_pf_event *pfe, + int ice_link_speed, bool link_up) +{ + if (vf->driver_caps & VIRTCHNL_VF_CAP_ADV_LINK_SPEED) { + pfe->event_data.link_event_adv.link_status = link_up; + /* Speed in Mbps */ + pfe->event_data.link_event_adv.link_speed = + ice_conv_link_speed_to_virtchnl(true, ice_link_speed); + } else { + pfe->event_data.link_event.link_status = link_up; + /* Legacy method for virtchnl link speeds */ + pfe->event_data.link_event.link_speed = + (enum virtchnl_link_speed) + ice_conv_link_speed_to_virtchnl(false, ice_link_speed); + } +} + +/** + * ice_vc_notify_vf_link_state - Inform a VF of link status + * @vf: pointer to the VF structure + * + * send a link status message to a single VF + */ +void ice_vc_notify_vf_link_state(struct ice_vf *vf) +{ + struct virtchnl_pf_event pfe = { 0 }; + struct ice_hw *hw = &vf->pf->hw; + + pfe.event = VIRTCHNL_EVENT_LINK_CHANGE; + pfe.severity = PF_EVENT_SEVERITY_INFO; + + if (ice_is_vf_link_up(vf)) + ice_set_pfe_link(vf, &pfe, + hw->port_info->phy.link_info.link_speed, true); + else + ice_set_pfe_link(vf, &pfe, ICE_AQ_LINK_SPEED_UNKNOWN, false); + + ice_aq_send_msg_to_vf(hw, vf->vf_id, VIRTCHNL_OP_EVENT, + VIRTCHNL_STATUS_SUCCESS, (u8 *)&pfe, + sizeof(pfe), NULL); +} + +/** + * ice_vc_notify_link_state - Inform all VFs on a PF of link status + * @pf: pointer to the PF structure + */ +void ice_vc_notify_link_state(struct ice_pf *pf) +{ + struct ice_vf *vf; + unsigned int bkt; + + mutex_lock(&pf->vfs.table_lock); + ice_for_each_vf(pf, bkt, vf) + ice_vc_notify_vf_link_state(vf); + mutex_unlock(&pf->vfs.table_lock); +} + +/** + * ice_vc_notify_reset - Send pending reset message to all VFs + * @pf: pointer to the PF structure + * + * indicate a pending reset to all VFs on a given PF + */ +void ice_vc_notify_reset(struct ice_pf *pf) +{ + struct virtchnl_pf_event pfe; + + if (!ice_has_vfs(pf)) + return; + + pfe.event = VIRTCHNL_EVENT_RESET_IMPENDING; + pfe.severity = PF_EVENT_SEVERITY_CERTAIN_DOOM; + ice_vc_vf_broadcast(pf, VIRTCHNL_OP_EVENT, VIRTCHNL_STATUS_SUCCESS, + (u8 *)&pfe, sizeof(struct virtchnl_pf_event)); +} + +/** + * ice_vc_send_msg_to_vf - Send message to VF + * @vf: pointer to the VF info + * @v_opcode: virtual channel opcode + * @v_retval: virtual channel return value + * @msg: pointer to the msg buffer + * @msglen: msg length + * + * send msg to VF + */ +int +ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode, + enum virtchnl_status_code v_retval, u8 *msg, u16 msglen) +{ + struct device *dev; + struct ice_pf *pf; + int aq_ret; + + pf = vf->pf; + dev = ice_pf_to_dev(pf); + + aq_ret = ice_aq_send_msg_to_vf(&pf->hw, vf->vf_id, v_opcode, v_retval, + msg, msglen, NULL); + if (aq_ret && pf->hw.mailboxq.sq_last_status != ICE_AQ_RC_ENOSYS) { + dev_info(dev, "Unable to send the message to VF %d ret %d aq_err %s\n", + vf->vf_id, aq_ret, + ice_aq_str(pf->hw.mailboxq.sq_last_status)); + return -EIO; + } + + return 0; +} + +/** + * ice_vc_get_ver_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to request the API version used by the PF + */ +static int ice_vc_get_ver_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_version_info info = { + VIRTCHNL_VERSION_MAJOR, VIRTCHNL_VERSION_MINOR + }; + + vf->vf_ver = *(struct virtchnl_version_info *)msg; + /* VFs running the 1.0 API expect to get 1.0 back or they will cry. */ + if (VF_IS_V10(&vf->vf_ver)) + info.minor = VIRTCHNL_VERSION_MINOR_NO_VF_CAPS; + + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_VERSION, + VIRTCHNL_STATUS_SUCCESS, (u8 *)&info, + sizeof(struct virtchnl_version_info)); +} + +/** + * ice_vc_get_max_frame_size - get max frame size allowed for VF + * @vf: VF used to determine max frame size + * + * Max frame size is determined based on the current port's max frame size and + * whether a port VLAN is configured on this VF. The VF is not aware whether + * it's in a port VLAN so the PF needs to account for this in max frame size + * checks and sending the max frame size to the VF. + */ +static u16 ice_vc_get_max_frame_size(struct ice_vf *vf) +{ + struct ice_port_info *pi = ice_vf_get_port_info(vf); + u16 max_frame_size; + + max_frame_size = pi->phy.link_info.max_frame_size; + + if (ice_vf_is_port_vlan_ena(vf)) + max_frame_size -= VLAN_HLEN; + + return max_frame_size; +} + +/** + * ice_vc_get_vlan_caps + * @hw: pointer to the hw + * @vf: pointer to the VF info + * @vsi: pointer to the VSI + * @driver_caps: current driver caps + * + * Return 0 if there is no VLAN caps supported, or VLAN caps value + */ +static u32 +ice_vc_get_vlan_caps(struct ice_hw *hw, struct ice_vf *vf, struct ice_vsi *vsi, + u32 driver_caps) +{ + if (ice_is_eswitch_mode_switchdev(vf->pf)) + /* In switchdev setting VLAN from VF isn't supported */ + return 0; + + if (driver_caps & VIRTCHNL_VF_OFFLOAD_VLAN_V2) { + /* VLAN offloads based on current device configuration */ + return VIRTCHNL_VF_OFFLOAD_VLAN_V2; + } else if (driver_caps & VIRTCHNL_VF_OFFLOAD_VLAN) { + /* allow VF to negotiate VIRTCHNL_VF_OFFLOAD explicitly for + * these two conditions, which amounts to guest VLAN filtering + * and offloads being based on the inner VLAN or the + * inner/single VLAN respectively and don't allow VF to + * negotiate VIRTCHNL_VF_OFFLOAD in any other cases + */ + if (ice_is_dvm_ena(hw) && ice_vf_is_port_vlan_ena(vf)) { + return VIRTCHNL_VF_OFFLOAD_VLAN; + } else if (!ice_is_dvm_ena(hw) && + !ice_vf_is_port_vlan_ena(vf)) { + /* configure backward compatible support for VFs that + * only support VIRTCHNL_VF_OFFLOAD_VLAN, the PF is + * configured in SVM, and no port VLAN is configured + */ + ice_vf_vsi_cfg_svm_legacy_vlan_mode(vsi); + return VIRTCHNL_VF_OFFLOAD_VLAN; + } else if (ice_is_dvm_ena(hw)) { + /* configure software offloaded VLAN support when DVM + * is enabled, but no port VLAN is enabled + */ + ice_vf_vsi_cfg_dvm_legacy_vlan_mode(vsi); + } + } + + return 0; +} + +/** + * ice_vc_get_vf_res_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to request its resources + */ +static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_vf_resource *vfres = NULL; + struct ice_hw *hw = &vf->pf->hw; + struct ice_vsi *vsi; + int len = 0; + int ret; + + if (ice_check_vf_init(vf)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + + len = sizeof(struct virtchnl_vf_resource); + + vfres = kzalloc(len, GFP_KERNEL); + if (!vfres) { + v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; + len = 0; + goto err; + } + if (VF_IS_V11(&vf->vf_ver)) + vf->driver_caps = *(u32 *)msg; + else + vf->driver_caps = VIRTCHNL_VF_OFFLOAD_L2 | + VIRTCHNL_VF_OFFLOAD_RSS_REG | + VIRTCHNL_VF_OFFLOAD_VLAN; + + vfres->vf_cap_flags = VIRTCHNL_VF_OFFLOAD_L2; + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + + vfres->vf_cap_flags |= ice_vc_get_vlan_caps(hw, vf, vsi, + vf->driver_caps); + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF) { + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PF; + } else { + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_AQ) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_AQ; + else + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_REG; + } + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_FDIR_PF) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_FDIR_PF; + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2; + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_ENCAP) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_ENCAP; + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM; + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RX_POLLING) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RX_POLLING; + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_WB_ON_ITR) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_WB_ON_ITR; + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_REQ_QUEUES) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_REQ_QUEUES; + + if (vf->driver_caps & VIRTCHNL_VF_CAP_ADV_LINK_SPEED) + vfres->vf_cap_flags |= VIRTCHNL_VF_CAP_ADV_LINK_SPEED; + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF; + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_USO) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_USO; + + 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->rss_key_size = ICE_VSIQF_HKEY_ARRAY_SIZE; + vfres->rss_lut_size = ICE_VSIQF_HLUT_ARRAY_SIZE; + vfres->max_mtu = ice_vc_get_max_frame_size(vf); + + vfres->vsi_res[0].vsi_id = vf->lan_vsi_num; + vfres->vsi_res[0].vsi_type = VIRTCHNL_VSI_SRIOV; + vfres->vsi_res[0].num_queue_pairs = vsi->num_txq; + ether_addr_copy(vfres->vsi_res[0].default_mac_addr, + vf->hw_lan_addr.addr); + + /* match guest capabilities */ + vf->driver_caps = vfres->vf_cap_flags; + + ice_vc_set_caps_allowlist(vf); + ice_vc_set_working_allowlist(vf); + + set_bit(ICE_VF_STATE_ACTIVE, vf->vf_states); + +err: + /* send the response back to the VF */ + ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_VF_RESOURCES, v_ret, + (u8 *)vfres, len); + + kfree(vfres); + return ret; +} + +/** + * ice_vc_reset_vf_msg + * @vf: pointer to the VF info + * + * called from the VF to reset itself, + * unlike other virtchnl messages, PF driver + * doesn't send the response back to the VF + */ +static void ice_vc_reset_vf_msg(struct ice_vf *vf) +{ + if (test_bit(ICE_VF_STATE_INIT, vf->vf_states)) + ice_reset_vf(vf, 0); +} + +/** + * ice_vc_isvalid_vsi_id + * @vf: pointer to the VF info + * @vsi_id: VF relative VSI ID + * + * check for the valid VSI ID + */ +bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id) +{ + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + + vsi = ice_find_vsi(pf, vsi_id); + + return (vsi && (vsi->vf == vf)); +} + +/** + * ice_vc_isvalid_q_id + * @vf: pointer to the VF info + * @vsi_id: VSI ID + * @qid: VSI relative queue ID + * + * check for the valid queue ID + */ +static bool ice_vc_isvalid_q_id(struct ice_vf *vf, u16 vsi_id, u8 qid) +{ + struct ice_vsi *vsi = ice_find_vsi(vf->pf, vsi_id); + /* allocated Tx and Rx queues should be always equal for VF VSI */ + return (vsi && (qid < vsi->alloc_txq)); +} + +/** + * ice_vc_isvalid_ring_len + * @ring_len: length of ring + * + * check for the valid ring count, should be multiple of ICE_REQ_DESC_MULTIPLE + * or zero + */ +static bool ice_vc_isvalid_ring_len(u16 ring_len) +{ + return ring_len == 0 || + (ring_len >= ICE_MIN_NUM_DESC && + ring_len <= ICE_MAX_NUM_DESC && + !(ring_len % ICE_REQ_DESC_MULTIPLE)); +} + +/** + * ice_vc_validate_pattern + * @vf: pointer to the VF info + * @proto: virtchnl protocol headers + * + * validate the pattern is supported or not. + * + * Return: true on success, false on error. + */ +bool +ice_vc_validate_pattern(struct ice_vf *vf, struct virtchnl_proto_hdrs *proto) +{ + bool is_ipv4 = false; + bool is_ipv6 = false; + bool is_udp = false; + u16 ptype = -1; + int i = 0; + + while (i < proto->count && + proto->proto_hdr[i].type != VIRTCHNL_PROTO_HDR_NONE) { + switch (proto->proto_hdr[i].type) { + case VIRTCHNL_PROTO_HDR_ETH: + ptype = ICE_PTYPE_MAC_PAY; + break; + case VIRTCHNL_PROTO_HDR_IPV4: + ptype = ICE_PTYPE_IPV4_PAY; + is_ipv4 = true; + break; + case VIRTCHNL_PROTO_HDR_IPV6: + ptype = ICE_PTYPE_IPV6_PAY; + is_ipv6 = true; + break; + case VIRTCHNL_PROTO_HDR_UDP: + if (is_ipv4) + ptype = ICE_PTYPE_IPV4_UDP_PAY; + else if (is_ipv6) + ptype = ICE_PTYPE_IPV6_UDP_PAY; + is_udp = true; + break; + case VIRTCHNL_PROTO_HDR_TCP: + if (is_ipv4) + ptype = ICE_PTYPE_IPV4_TCP_PAY; + else if (is_ipv6) + ptype = ICE_PTYPE_IPV6_TCP_PAY; + break; + case VIRTCHNL_PROTO_HDR_SCTP: + if (is_ipv4) + ptype = ICE_PTYPE_IPV4_SCTP_PAY; + else if (is_ipv6) + ptype = ICE_PTYPE_IPV6_SCTP_PAY; + break; + case VIRTCHNL_PROTO_HDR_GTPU_IP: + case VIRTCHNL_PROTO_HDR_GTPU_EH: + if (is_ipv4) + ptype = ICE_MAC_IPV4_GTPU; + else if (is_ipv6) + ptype = ICE_MAC_IPV6_GTPU; + goto out; + case VIRTCHNL_PROTO_HDR_L2TPV3: + if (is_ipv4) + ptype = ICE_MAC_IPV4_L2TPV3; + else if (is_ipv6) + ptype = ICE_MAC_IPV6_L2TPV3; + goto out; + case VIRTCHNL_PROTO_HDR_ESP: + if (is_ipv4) + ptype = is_udp ? ICE_MAC_IPV4_NAT_T_ESP : + ICE_MAC_IPV4_ESP; + else if (is_ipv6) + ptype = is_udp ? ICE_MAC_IPV6_NAT_T_ESP : + ICE_MAC_IPV6_ESP; + goto out; + case VIRTCHNL_PROTO_HDR_AH: + if (is_ipv4) + ptype = ICE_MAC_IPV4_AH; + else if (is_ipv6) + ptype = ICE_MAC_IPV6_AH; + goto out; + case VIRTCHNL_PROTO_HDR_PFCP: + if (is_ipv4) + ptype = ICE_MAC_IPV4_PFCP_SESSION; + else if (is_ipv6) + ptype = ICE_MAC_IPV6_PFCP_SESSION; + goto out; + default: + break; + } + i++; + } + +out: + return ice_hw_ptype_ena(&vf->pf->hw, ptype); +} + +/** + * ice_vc_parse_rss_cfg - parses hash fields and headers from + * a specific virtchnl RSS cfg + * @hw: pointer to the hardware + * @rss_cfg: pointer to the virtchnl RSS cfg + * @addl_hdrs: pointer to the protocol header fields (ICE_FLOW_SEG_HDR_*) + * to configure + * @hash_flds: pointer to the hash bit fields (ICE_FLOW_HASH_*) to configure + * + * Return true if all the protocol header and hash fields in the RSS cfg could + * be parsed, else return false + * + * This function parses the virtchnl RSS cfg to be the intended + * hash fields and the intended header for RSS configuration + */ +static bool +ice_vc_parse_rss_cfg(struct ice_hw *hw, struct virtchnl_rss_cfg *rss_cfg, + u32 *addl_hdrs, u64 *hash_flds) +{ + const struct ice_vc_hash_field_match_type *hf_list; + const struct ice_vc_hdr_match_type *hdr_list; + int i, hf_list_len, hdr_list_len; + + hf_list = ice_vc_hash_field_list; + hf_list_len = ARRAY_SIZE(ice_vc_hash_field_list); + hdr_list = ice_vc_hdr_list; + hdr_list_len = ARRAY_SIZE(ice_vc_hdr_list); + + for (i = 0; i < rss_cfg->proto_hdrs.count; i++) { + struct virtchnl_proto_hdr *proto_hdr = + &rss_cfg->proto_hdrs.proto_hdr[i]; + bool hdr_found = false; + int j; + + /* Find matched ice headers according to virtchnl headers. */ + for (j = 0; j < hdr_list_len; j++) { + struct ice_vc_hdr_match_type hdr_map = hdr_list[j]; + + if (proto_hdr->type == hdr_map.vc_hdr) { + *addl_hdrs |= hdr_map.ice_hdr; + hdr_found = true; + } + } + + if (!hdr_found) + return false; + + /* Find matched ice hash fields according to + * virtchnl hash fields. + */ + for (j = 0; j < hf_list_len; j++) { + struct ice_vc_hash_field_match_type hf_map = hf_list[j]; + + if (proto_hdr->type == hf_map.vc_hdr && + proto_hdr->field_selector == hf_map.vc_hash_field) { + *hash_flds |= hf_map.ice_hash_field; + break; + } + } + } + + return true; +} + +/** + * ice_vf_adv_rss_offload_ena - determine if capabilities support advanced + * RSS offloads + * @caps: VF driver negotiated capabilities + * + * Return true if VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability is set, + * else return false + */ +static bool ice_vf_adv_rss_offload_ena(u32 caps) +{ + return !!(caps & VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF); +} + +/** + * ice_vc_handle_rss_cfg + * @vf: pointer to the VF info + * @msg: pointer to the message buffer + * @add: add a RSS config if true, otherwise delete a RSS config + * + * This function adds/deletes a RSS config + */ +static int ice_vc_handle_rss_cfg(struct ice_vf *vf, u8 *msg, bool add) +{ + u32 v_opcode = add ? VIRTCHNL_OP_ADD_RSS_CFG : VIRTCHNL_OP_DEL_RSS_CFG; + struct virtchnl_rss_cfg *rss_cfg = (struct virtchnl_rss_cfg *)msg; + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_hw *hw = &vf->pf->hw; + struct ice_vsi *vsi; + + if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) { + dev_dbg(dev, "VF %d attempting to configure RSS, but RSS is not supported by the PF\n", + vf->vf_id); + v_ret = VIRTCHNL_STATUS_ERR_NOT_SUPPORTED; + goto error_param; + } + + if (!ice_vf_adv_rss_offload_ena(vf->driver_caps)) { + dev_dbg(dev, "VF %d attempting to configure RSS, but Advanced RSS offload is not supported\n", + vf->vf_id); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (rss_cfg->proto_hdrs.count > VIRTCHNL_MAX_NUM_PROTO_HDRS || + rss_cfg->rss_algorithm < VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC || + rss_cfg->rss_algorithm > VIRTCHNL_RSS_ALG_XOR_SYMMETRIC) { + dev_dbg(dev, "VF %d attempting to configure RSS, but RSS configuration is not valid\n", + vf->vf_id); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_validate_pattern(vf, &rss_cfg->proto_hdrs)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (rss_cfg->rss_algorithm == VIRTCHNL_RSS_ALG_R_ASYMMETRIC) { + struct ice_vsi_ctx *ctx; + u8 lut_type, hash_type; + int status; + + lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_VSI; + hash_type = add ? ICE_AQ_VSI_Q_OPT_RSS_XOR : + ICE_AQ_VSI_Q_OPT_RSS_TPLZ; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) { + v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; + goto error_param; + } + + ctx->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_M); + + /* Preserve existing queueing option setting */ + ctx->info.q_opt_rss |= (vsi->info.q_opt_rss & + ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_M); + ctx->info.q_opt_tc = vsi->info.q_opt_tc; + ctx->info.q_opt_flags = vsi->info.q_opt_rss; + + ctx->info.valid_sections = + cpu_to_le16(ICE_AQ_VSI_PROP_Q_OPT_VALID); + + status = ice_update_vsi(hw, vsi->idx, ctx, NULL); + if (status) { + dev_err(dev, "update VSI for RSS failed, err %d aq_err %s\n", + status, ice_aq_str(hw->adminq.sq_last_status)); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + } else { + vsi->info.q_opt_rss = ctx->info.q_opt_rss; + } + + kfree(ctx); + } else { + u32 addl_hdrs = ICE_FLOW_SEG_HDR_NONE; + u64 hash_flds = ICE_HASH_INVALID; + + if (!ice_vc_parse_rss_cfg(hw, rss_cfg, &addl_hdrs, + &hash_flds)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (add) { + if (ice_add_rss_cfg(hw, vsi->idx, hash_flds, + addl_hdrs)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + dev_err(dev, "ice_add_rss_cfg failed for vsi = %d, v_ret = %d\n", + vsi->vsi_num, v_ret); + } + } else { + int status; + + status = ice_rem_rss_cfg(hw, vsi->idx, hash_flds, + addl_hdrs); + /* We just ignore -ENOENT, because if two configurations + * share the same profile remove one of them actually + * removes both, since the profile is deleted. + */ + if (status && status != -ENOENT) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + dev_err(dev, "ice_rem_rss_cfg failed for VF ID:%d, error:%d\n", + vf->vf_id, status); + } + } + } + +error_param: + return ice_vc_send_msg_to_vf(vf, v_opcode, v_ret, NULL, 0); +} + +/** + * ice_vc_config_rss_key + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * Configure the VF's RSS key + */ +static int ice_vc_config_rss_key(struct ice_vf *vf, u8 *msg) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_rss_key *vrk = + (struct virtchnl_rss_key *)msg; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, vrk->vsi_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (vrk->key_len != ICE_VSIQF_HKEY_ARRAY_SIZE) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (ice_set_rss_key(vsi, vrk->key)) + v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR; +error_param: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_KEY, v_ret, + NULL, 0); +} + +/** + * ice_vc_config_rss_lut + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * Configure the VF's RSS LUT + */ +static int ice_vc_config_rss_lut(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_rss_lut *vrl = (struct virtchnl_rss_lut *)msg; + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, vrl->vsi_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (vrl->lut_entries != ICE_VSIQF_HLUT_ARRAY_SIZE) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (ice_set_rss_lut(vsi, vrl->lut, ICE_VSIQF_HLUT_ARRAY_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, + NULL, 0); +} + +/** + * ice_vc_cfg_promiscuous_mode_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to configure VF VSIs promiscuous mode + */ +static int ice_vc_cfg_promiscuous_mode_msg(struct ice_vf *vf, u8 *msg) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + bool rm_promisc, alluni = false, allmulti = false; + struct virtchnl_promisc_info *info = + (struct virtchnl_promisc_info *)msg; + struct ice_vsi_vlan_ops *vlan_ops; + int mcast_err = 0, ucast_err = 0; + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + u8 mcast_m, ucast_m; + struct device *dev; + int ret = 0; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, info->vsi_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + dev = ice_pf_to_dev(pf); + if (!ice_is_vf_trusted(vf)) { + dev_err(dev, "Unprivileged VF %d is attempting to configure promiscuous mode\n", + vf->vf_id); + /* Leave v_ret alone, lie to the VF on purpose. */ + goto error_param; + } + + if (info->flags & FLAG_VF_UNICAST_PROMISC) + alluni = true; + + if (info->flags & FLAG_VF_MULTICAST_PROMISC) + allmulti = true; + + rm_promisc = !allmulti && !alluni; + + vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); + if (rm_promisc) + ret = vlan_ops->ena_rx_filtering(vsi); + else + ret = vlan_ops->dis_rx_filtering(vsi); + if (ret) { + dev_err(dev, "Failed to configure VLAN pruning in promiscuous mode\n"); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + ice_vf_get_promisc_masks(vf, vsi, &ucast_m, &mcast_m); + + if (!test_bit(ICE_FLAG_VF_TRUE_PROMISC_ENA, pf->flags)) { + if (alluni) { + /* in this case we're turning on promiscuous mode */ + ret = ice_set_dflt_vsi(vsi); + } else { + /* in this case we're turning off promiscuous mode */ + if (ice_is_dflt_vsi_in_use(vsi->port_info)) + ret = ice_clear_dflt_vsi(vsi); + } + + /* in this case we're turning on/off only + * allmulticast + */ + if (allmulti) + mcast_err = ice_vf_set_vsi_promisc(vf, vsi, mcast_m); + else + mcast_err = ice_vf_clear_vsi_promisc(vf, vsi, mcast_m); + + if (ret) { + dev_err(dev, "Turning on/off promiscuous mode for VF %d failed, error: %d\n", + vf->vf_id, ret); + v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR; + goto error_param; + } + } else { + if (alluni) + ucast_err = ice_vf_set_vsi_promisc(vf, vsi, ucast_m); + else + ucast_err = ice_vf_clear_vsi_promisc(vf, vsi, ucast_m); + + if (allmulti) + mcast_err = ice_vf_set_vsi_promisc(vf, vsi, mcast_m); + else + mcast_err = ice_vf_clear_vsi_promisc(vf, vsi, mcast_m); + + if (ucast_err || mcast_err) + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + } + + if (!mcast_err) { + if (allmulti && + !test_and_set_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states)) + dev_info(dev, "VF %u successfully set multicast promiscuous mode\n", + vf->vf_id); + else if (!allmulti && + test_and_clear_bit(ICE_VF_STATE_MC_PROMISC, + vf->vf_states)) + dev_info(dev, "VF %u successfully unset multicast promiscuous mode\n", + vf->vf_id); + } else { + dev_err(dev, "Error while modifying multicast promiscuous mode for VF %u, error: %d\n", + vf->vf_id, mcast_err); + } + + if (!ucast_err) { + if (alluni && + !test_and_set_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states)) + dev_info(dev, "VF %u successfully set unicast promiscuous mode\n", + vf->vf_id); + else if (!alluni && + test_and_clear_bit(ICE_VF_STATE_UC_PROMISC, + vf->vf_states)) + dev_info(dev, "VF %u successfully unset unicast promiscuous mode\n", + vf->vf_id); + } else { + dev_err(dev, "Error while modifying unicast promiscuous mode for VF %u, error: %d\n", + vf->vf_id, ucast_err); + } + +error_param: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE, + v_ret, NULL, 0); +} + +/** + * ice_vc_get_stats_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to get VSI stats + */ +static int ice_vc_get_stats_msg(struct ice_vf *vf, u8 *msg) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_queue_select *vqs = + (struct virtchnl_queue_select *)msg; + struct ice_eth_stats stats = { 0 }; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, vqs->vsi_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + ice_update_eth_stats(vsi); + + stats = vsi->eth_stats; + +error_param: + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_STATS, v_ret, + (u8 *)&stats, sizeof(stats)); +} + +/** + * ice_vc_validate_vqs_bitmaps - validate Rx/Tx queue bitmaps from VIRTCHNL + * @vqs: virtchnl_queue_select structure containing bitmaps to validate + * + * Return true on successful validation, else false + */ +static bool ice_vc_validate_vqs_bitmaps(struct virtchnl_queue_select *vqs) +{ + if ((!vqs->rx_queues && !vqs->tx_queues) || + vqs->rx_queues >= BIT(ICE_MAX_RSS_QS_PER_VF) || + vqs->tx_queues >= BIT(ICE_MAX_RSS_QS_PER_VF)) + return false; + + return true; +} + +/** + * ice_vf_ena_txq_interrupt - enable Tx queue interrupt via QINT_TQCTL + * @vsi: VSI of the VF to configure + * @q_idx: VF queue index used to determine the queue in the PF's space + */ +static void ice_vf_ena_txq_interrupt(struct ice_vsi *vsi, u32 q_idx) +{ + struct ice_hw *hw = &vsi->back->hw; + u32 pfq = vsi->txq_map[q_idx]; + u32 reg; + + reg = rd32(hw, QINT_TQCTL(pfq)); + + /* MSI-X index 0 in the VF's space is always for the OICR, which means + * this is most likely a poll mode VF driver, so don't enable an + * interrupt that was never configured via VIRTCHNL_OP_CONFIG_IRQ_MAP + */ + if (!(reg & QINT_TQCTL_MSIX_INDX_M)) + return; + + wr32(hw, QINT_TQCTL(pfq), reg | QINT_TQCTL_CAUSE_ENA_M); +} + +/** + * ice_vf_ena_rxq_interrupt - enable Tx queue interrupt via QINT_RQCTL + * @vsi: VSI of the VF to configure + * @q_idx: VF queue index used to determine the queue in the PF's space + */ +static void ice_vf_ena_rxq_interrupt(struct ice_vsi *vsi, u32 q_idx) +{ + struct ice_hw *hw = &vsi->back->hw; + u32 pfq = vsi->rxq_map[q_idx]; + u32 reg; + + reg = rd32(hw, QINT_RQCTL(pfq)); + + /* MSI-X index 0 in the VF's space is always for the OICR, which means + * this is most likely a poll mode VF driver, so don't enable an + * interrupt that was never configured via VIRTCHNL_OP_CONFIG_IRQ_MAP + */ + if (!(reg & QINT_RQCTL_MSIX_INDX_M)) + return; + + wr32(hw, QINT_RQCTL(pfq), reg | QINT_RQCTL_CAUSE_ENA_M); +} + +/** + * ice_vc_ena_qs_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to enable all or specific queue(s) + */ +static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_queue_select *vqs = + (struct virtchnl_queue_select *)msg; + struct ice_vsi *vsi; + unsigned long q_map; + u16 vf_q_id; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, vqs->vsi_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_validate_vqs_bitmaps(vqs)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + /* Enable only Rx rings, Tx rings were enabled by the FW when the + * Tx queue group list was configured and the context bits were + * programmed using ice_vsi_cfg_txqs + */ + q_map = vqs->rx_queues; + for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { + if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + /* Skip queue if enabled */ + if (test_bit(vf_q_id, vf->rxq_ena)) + continue; + + if (ice_vsi_ctrl_one_rx_ring(vsi, true, vf_q_id, true)) { + dev_err(ice_pf_to_dev(vsi->back), "Failed to enable Rx ring %d on VSI %d\n", + vf_q_id, vsi->vsi_num); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + ice_vf_ena_rxq_interrupt(vsi, vf_q_id); + set_bit(vf_q_id, vf->rxq_ena); + } + + q_map = vqs->tx_queues; + for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { + if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + /* Skip queue if enabled */ + if (test_bit(vf_q_id, vf->txq_ena)) + continue; + + ice_vf_ena_txq_interrupt(vsi, vf_q_id); + set_bit(vf_q_id, vf->txq_ena); + } + + /* Set flag to indicate that queues are enabled */ + if (v_ret == VIRTCHNL_STATUS_SUCCESS) + set_bit(ICE_VF_STATE_QS_ENA, vf->vf_states); + +error_param: + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ENABLE_QUEUES, v_ret, + NULL, 0); +} + +/** + * ice_vf_vsi_dis_single_txq - disable a single Tx queue + * @vf: VF to disable queue for + * @vsi: VSI for the VF + * @q_id: VF relative (0-based) queue ID + * + * Attempt to disable the Tx queue passed in. If the Tx queue was successfully + * disabled then clear q_id bit in the enabled queues bitmap and return + * success. Otherwise return error. + */ +static int +ice_vf_vsi_dis_single_txq(struct ice_vf *vf, struct ice_vsi *vsi, u16 q_id) +{ + struct ice_txq_meta txq_meta = { 0 }; + struct ice_tx_ring *ring; + int err; + + if (!test_bit(q_id, vf->txq_ena)) + dev_dbg(ice_pf_to_dev(vsi->back), "Queue %u on VSI %u is not enabled, but stopping it anyway\n", + q_id, vsi->vsi_num); + + ring = vsi->tx_rings[q_id]; + if (!ring) + return -EINVAL; + + ice_fill_txq_meta(vsi, ring, &txq_meta); + + err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, vf->vf_id, ring, &txq_meta); + if (err) { + dev_err(ice_pf_to_dev(vsi->back), "Failed to stop Tx ring %d on VSI %d\n", + q_id, vsi->vsi_num); + return err; + } + + /* Clear enabled queues flag */ + clear_bit(q_id, vf->txq_ena); + + return 0; +} + +/** + * ice_vc_dis_qs_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to disable all or specific queue(s) + */ +static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_queue_select *vqs = + (struct virtchnl_queue_select *)msg; + struct ice_vsi *vsi; + unsigned long q_map; + u16 vf_q_id; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) && + !test_bit(ICE_VF_STATE_QS_ENA, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, vqs->vsi_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_validate_vqs_bitmaps(vqs)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (vqs->tx_queues) { + q_map = vqs->tx_queues; + + for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { + if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (ice_vf_vsi_dis_single_txq(vf, vsi, vf_q_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + } + } + + q_map = vqs->rx_queues; + /* speed up Rx queue disable by batching them if possible */ + if (q_map && + bitmap_equal(&q_map, vf->rxq_ena, ICE_MAX_RSS_QS_PER_VF)) { + if (ice_vsi_stop_all_rx_rings(vsi)) { + dev_err(ice_pf_to_dev(vsi->back), "Failed to stop all Rx rings on VSI %d\n", + vsi->vsi_num); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + bitmap_zero(vf->rxq_ena, ICE_MAX_RSS_QS_PER_VF); + } else if (q_map) { + for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { + if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + /* Skip queue if not enabled */ + if (!test_bit(vf_q_id, vf->rxq_ena)) + continue; + + if (ice_vsi_ctrl_one_rx_ring(vsi, false, vf_q_id, + true)) { + dev_err(ice_pf_to_dev(vsi->back), "Failed to stop Rx ring %d on VSI %d\n", + vf_q_id, vsi->vsi_num); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + /* Clear enabled queues flag */ + clear_bit(vf_q_id, vf->rxq_ena); + } + } + + /* Clear enabled queues flag */ + if (v_ret == VIRTCHNL_STATUS_SUCCESS && ice_vf_has_no_qs_ena(vf)) + clear_bit(ICE_VF_STATE_QS_ENA, vf->vf_states); + +error_param: + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DISABLE_QUEUES, v_ret, + NULL, 0); +} + +/** + * ice_cfg_interrupt + * @vf: pointer to the VF info + * @vsi: the VSI being configured + * @vector_id: vector ID + * @map: vector map for mapping vectors to queues + * @q_vector: structure for interrupt vector + * configure the IRQ to queue map + */ +static int +ice_cfg_interrupt(struct ice_vf *vf, struct ice_vsi *vsi, u16 vector_id, + struct virtchnl_vector_map *map, + struct ice_q_vector *q_vector) +{ + u16 vsi_q_id, vsi_q_id_idx; + unsigned long qmap; + + q_vector->num_ring_rx = 0; + q_vector->num_ring_tx = 0; + + qmap = map->rxq_map; + for_each_set_bit(vsi_q_id_idx, &qmap, ICE_MAX_RSS_QS_PER_VF) { + vsi_q_id = vsi_q_id_idx; + + if (!ice_vc_isvalid_q_id(vf, vsi->vsi_num, vsi_q_id)) + return VIRTCHNL_STATUS_ERR_PARAM; + + q_vector->num_ring_rx++; + q_vector->rx.itr_idx = map->rxitr_idx; + vsi->rx_rings[vsi_q_id]->q_vector = q_vector; + ice_cfg_rxq_interrupt(vsi, vsi_q_id, vector_id, + q_vector->rx.itr_idx); + } + + qmap = map->txq_map; + for_each_set_bit(vsi_q_id_idx, &qmap, ICE_MAX_RSS_QS_PER_VF) { + vsi_q_id = vsi_q_id_idx; + + if (!ice_vc_isvalid_q_id(vf, vsi->vsi_num, vsi_q_id)) + return VIRTCHNL_STATUS_ERR_PARAM; + + q_vector->num_ring_tx++; + q_vector->tx.itr_idx = map->txitr_idx; + vsi->tx_rings[vsi_q_id]->q_vector = q_vector; + ice_cfg_txq_interrupt(vsi, vsi_q_id, vector_id, + q_vector->tx.itr_idx); + } + + return VIRTCHNL_STATUS_SUCCESS; +} + +/** + * ice_vc_cfg_irq_map_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to configure the IRQ to queue map + */ +static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + 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; + + irqmap_info = (struct virtchnl_irq_map_info *)msg; + num_q_vectors_mapped = irqmap_info->num_vectors; + + /* Check to make sure number of VF vectors mapped is not greater than + * number of VF vectors originally allocated, and check that + * 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 || + !num_q_vectors_mapped) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + for (i = 0; i < num_q_vectors_mapped; i++) { + struct ice_q_vector *q_vector; + + map = &irqmap_info->vecmap[i]; + + vector_id = map->vector_id; + vsi_id = map->vsi_id; + /* 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) || + !ice_vc_isvalid_vsi_id(vf, vsi_id) || + (!vector_id && (map->rxq_map || map->txq_map))) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + /* No need to map VF miscellaneous or rogue vector */ + if (!vector_id) + continue; + + /* Subtract non queue vector from vector_id passed by VF + * to get actual number of VSI queue vector array index + */ + q_vector = vsi->q_vectors[vector_id - ICE_NONQ_VECS_VF]; + if (!q_vector) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + /* lookout for the invalid queue index */ + v_ret = (enum virtchnl_status_code) + ice_cfg_interrupt(vf, vsi, vector_id, map, q_vector); + if (v_ret) + goto error_param; + } + +error_param: + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_IRQ_MAP, v_ret, + NULL, 0); +} + +/** + * ice_vc_cfg_qs_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to configure the Rx/Tx queues + */ +static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_vsi_queue_config_info *qci = + (struct virtchnl_vsi_queue_config_info *)msg; + struct virtchnl_queue_pair_info *qpi; + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + int i = -1, q_idx; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) + goto error_param; + + if (!ice_vc_isvalid_vsi_id(vf, qci->vsi_id)) + goto error_param; + + vsi = ice_get_vf_vsi(vf); + if (!vsi) + goto error_param; + + if (qci->num_queue_pairs > ICE_MAX_RSS_QS_PER_VF || + qci->num_queue_pairs > min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)) { + dev_err(ice_pf_to_dev(pf), "VF-%d requesting more than supported number of queues: %d\n", + vf->vf_id, min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)); + goto error_param; + } + + for (i = 0; i < qci->num_queue_pairs; i++) { + qpi = &qci->qpair[i]; + if (qpi->txq.vsi_id != qci->vsi_id || + qpi->rxq.vsi_id != qci->vsi_id || + qpi->rxq.queue_id != qpi->txq.queue_id || + qpi->txq.headwb_enabled || + !ice_vc_isvalid_ring_len(qpi->txq.ring_len) || + !ice_vc_isvalid_ring_len(qpi->rxq.ring_len) || + !ice_vc_isvalid_q_id(vf, qci->vsi_id, qpi->txq.queue_id)) { + goto error_param; + } + + q_idx = qpi->rxq.queue_id; + + /* make sure selected "q_idx" is in valid range of queues + * for selected "vsi" + */ + if (q_idx >= vsi->alloc_txq || q_idx >= vsi->alloc_rxq) { + goto error_param; + } + + /* copy Tx queue info from VF into VSI */ + if (qpi->txq.ring_len > 0) { + vsi->tx_rings[i]->dma = qpi->txq.dma_ring_addr; + vsi->tx_rings[i]->count = qpi->txq.ring_len; + + /* Disable any existing queue first */ + if (ice_vf_vsi_dis_single_txq(vf, vsi, q_idx)) + goto error_param; + + /* Configure a queue with the requested settings */ + if (ice_vsi_cfg_single_txq(vsi, vsi->tx_rings, q_idx)) { + dev_warn(ice_pf_to_dev(pf), "VF-%d failed to configure TX queue %d\n", + vf->vf_id, i); + goto error_param; + } + } + + /* copy Rx queue info from VF into VSI */ + if (qpi->rxq.ring_len > 0) { + u16 max_frame_size = ice_vc_get_max_frame_size(vf); + + vsi->rx_rings[i]->dma = qpi->rxq.dma_ring_addr; + vsi->rx_rings[i]->count = qpi->rxq.ring_len; + + if (qpi->rxq.databuffer_size != 0 && + (qpi->rxq.databuffer_size > ((16 * 1024) - 128) || + qpi->rxq.databuffer_size < 1024)) + goto error_param; + vsi->rx_buf_len = qpi->rxq.databuffer_size; + vsi->rx_rings[i]->rx_buf_len = vsi->rx_buf_len; + if (qpi->rxq.max_pkt_size > max_frame_size || + qpi->rxq.max_pkt_size < 64) + goto error_param; + + vsi->max_frame = qpi->rxq.max_pkt_size; + /* add space for the port VLAN since the VF driver is + * not expected to account for it in the MTU + * calculation + */ + if (ice_vf_is_port_vlan_ena(vf)) + vsi->max_frame += VLAN_HLEN; + + if (ice_vsi_cfg_single_rxq(vsi, q_idx)) { + dev_warn(ice_pf_to_dev(pf), "VF-%d failed to configure RX queue %d\n", + vf->vf_id, i); + goto error_param; + } + } + } + + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_VSI_QUEUES, + VIRTCHNL_STATUS_SUCCESS, NULL, 0); +error_param: + /* disable whatever we can */ + for (; i >= 0; i--) { + if (ice_vsi_ctrl_one_rx_ring(vsi, false, i, true)) + dev_err(ice_pf_to_dev(pf), "VF-%d could not disable RX queue %d\n", + vf->vf_id, i); + if (ice_vf_vsi_dis_single_txq(vf, vsi, i)) + dev_err(ice_pf_to_dev(pf), "VF-%d could not disable TX queue %d\n", + vf->vf_id, i); + } + + /* 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); +} + +/** + * ice_can_vf_change_mac + * @vf: pointer to the VF info + * + * Return true if the VF is allowed to change its MAC filters, false otherwise + */ +static bool ice_can_vf_change_mac(struct ice_vf *vf) +{ + /* If the VF MAC address has been set administratively (via the + * ndo_set_vf_mac command), then deny permission to the VF to + * add/delete unicast MAC addresses, unless the VF is trusted + */ + if (vf->pf_set_mac && !ice_is_vf_trusted(vf)) + return false; + + return true; +} + +/** + * ice_vc_ether_addr_type - get type of virtchnl_ether_addr + * @vc_ether_addr: used to extract the type + */ +static u8 +ice_vc_ether_addr_type(struct virtchnl_ether_addr *vc_ether_addr) +{ + return (vc_ether_addr->type & VIRTCHNL_ETHER_ADDR_TYPE_MASK); +} + +/** + * ice_is_vc_addr_legacy - check if the MAC address is from an older VF + * @vc_ether_addr: VIRTCHNL structure that contains MAC and type + */ +static bool +ice_is_vc_addr_legacy(struct virtchnl_ether_addr *vc_ether_addr) +{ + u8 type = ice_vc_ether_addr_type(vc_ether_addr); + + return (type == VIRTCHNL_ETHER_ADDR_LEGACY); +} + +/** + * ice_is_vc_addr_primary - check if the MAC address is the VF's primary MAC + * @vc_ether_addr: VIRTCHNL structure that contains MAC and type + * + * This function should only be called when the MAC address in + * virtchnl_ether_addr is a valid unicast MAC + */ +static bool +ice_is_vc_addr_primary(struct virtchnl_ether_addr __maybe_unused *vc_ether_addr) +{ + u8 type = ice_vc_ether_addr_type(vc_ether_addr); + + return (type == VIRTCHNL_ETHER_ADDR_PRIMARY); +} + +/** + * ice_vfhw_mac_add - update the VF's cached hardware MAC if allowed + * @vf: VF to update + * @vc_ether_addr: structure from VIRTCHNL with MAC to add + */ +static void +ice_vfhw_mac_add(struct ice_vf *vf, struct virtchnl_ether_addr *vc_ether_addr) +{ + u8 *mac_addr = vc_ether_addr->addr; + + if (!is_valid_ether_addr(mac_addr)) + return; + + /* only allow legacy VF drivers to set the device and hardware MAC if it + * is zero and allow new VF drivers to set the hardware MAC if the type + * was correctly specified over VIRTCHNL + */ + if ((ice_is_vc_addr_legacy(vc_ether_addr) && + is_zero_ether_addr(vf->hw_lan_addr.addr)) || + ice_is_vc_addr_primary(vc_ether_addr)) { + ether_addr_copy(vf->dev_lan_addr.addr, mac_addr); + ether_addr_copy(vf->hw_lan_addr.addr, mac_addr); + } + + /* hardware and device MACs are already set, but its possible that the + * VF driver sent the VIRTCHNL_OP_ADD_ETH_ADDR message before the + * VIRTCHNL_OP_DEL_ETH_ADDR when trying to update its MAC, so save it + * away for the legacy VF driver case as it will be updated in the + * delete flow for this case + */ + if (ice_is_vc_addr_legacy(vc_ether_addr)) { + ether_addr_copy(vf->legacy_last_added_umac.addr, + mac_addr); + vf->legacy_last_added_umac.time_modified = jiffies; + } +} + +/** + * ice_vc_add_mac_addr - attempt to add the MAC address passed in + * @vf: pointer to the VF info + * @vsi: pointer to the VF's VSI + * @vc_ether_addr: VIRTCHNL MAC address structure used to add MAC + */ +static int +ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, + struct virtchnl_ether_addr *vc_ether_addr) +{ + struct device *dev = ice_pf_to_dev(vf->pf); + u8 *mac_addr = vc_ether_addr->addr; + int ret; + + /* device MAC already added */ + if (ether_addr_equal(mac_addr, vf->dev_lan_addr.addr)) + return 0; + + if (is_unicast_ether_addr(mac_addr) && !ice_can_vf_change_mac(vf)) { + dev_err(dev, "VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n"); + return -EPERM; + } + + ret = ice_fltr_add_mac(vsi, mac_addr, ICE_FWD_TO_VSI); + if (ret == -EEXIST) { + dev_dbg(dev, "MAC %pM already exists for VF %d\n", mac_addr, + vf->vf_id); + /* don't return since we might need to update + * the primary MAC in ice_vfhw_mac_add() below + */ + } else if (ret) { + dev_err(dev, "Failed to add MAC %pM for VF %d\n, error %d\n", + mac_addr, vf->vf_id, ret); + return ret; + } else { + vf->num_mac++; + } + + ice_vfhw_mac_add(vf, vc_ether_addr); + + return ret; +} + +/** + * ice_is_legacy_umac_expired - check if last added legacy unicast MAC expired + * @last_added_umac: structure used to check expiration + */ +static bool ice_is_legacy_umac_expired(struct ice_time_mac *last_added_umac) +{ +#define ICE_LEGACY_VF_MAC_CHANGE_EXPIRE_TIME msecs_to_jiffies(3000) + return time_is_before_jiffies(last_added_umac->time_modified + + ICE_LEGACY_VF_MAC_CHANGE_EXPIRE_TIME); +} + +/** + * ice_update_legacy_cached_mac - update cached hardware MAC for legacy VF + * @vf: VF to update + * @vc_ether_addr: structure from VIRTCHNL with MAC to check + * + * only update cached hardware MAC for legacy VF drivers on delete + * because we cannot guarantee order/type of MAC from the VF driver + */ +static void +ice_update_legacy_cached_mac(struct ice_vf *vf, + struct virtchnl_ether_addr *vc_ether_addr) +{ + if (!ice_is_vc_addr_legacy(vc_ether_addr) || + ice_is_legacy_umac_expired(&vf->legacy_last_added_umac)) + return; + + ether_addr_copy(vf->dev_lan_addr.addr, vf->legacy_last_added_umac.addr); + ether_addr_copy(vf->hw_lan_addr.addr, vf->legacy_last_added_umac.addr); +} + +/** + * ice_vfhw_mac_del - update the VF's cached hardware MAC if allowed + * @vf: VF to update + * @vc_ether_addr: structure from VIRTCHNL with MAC to delete + */ +static void +ice_vfhw_mac_del(struct ice_vf *vf, struct virtchnl_ether_addr *vc_ether_addr) +{ + u8 *mac_addr = vc_ether_addr->addr; + + if (!is_valid_ether_addr(mac_addr) || + !ether_addr_equal(vf->dev_lan_addr.addr, mac_addr)) + return; + + /* allow the device MAC to be repopulated in the add flow and don't + * clear the hardware MAC (i.e. hw_lan_addr.addr) here as that is meant + * to be persistent on VM reboot and across driver unload/load, which + * won't work if we clear the hardware MAC here + */ + eth_zero_addr(vf->dev_lan_addr.addr); + + ice_update_legacy_cached_mac(vf, vc_ether_addr); +} + +/** + * ice_vc_del_mac_addr - attempt to delete the MAC address passed in + * @vf: pointer to the VF info + * @vsi: pointer to the VF's VSI + * @vc_ether_addr: VIRTCHNL MAC address structure used to delete MAC + */ +static int +ice_vc_del_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, + struct virtchnl_ether_addr *vc_ether_addr) +{ + struct device *dev = ice_pf_to_dev(vf->pf); + u8 *mac_addr = vc_ether_addr->addr; + int status; + + if (!ice_can_vf_change_mac(vf) && + ether_addr_equal(vf->dev_lan_addr.addr, mac_addr)) + return 0; + + status = ice_fltr_remove_mac(vsi, mac_addr, ICE_FWD_TO_VSI); + if (status == -ENOENT) { + dev_err(dev, "MAC %pM does not exist for VF %d\n", mac_addr, + vf->vf_id); + return -ENOENT; + } else if (status) { + dev_err(dev, "Failed to delete MAC %pM for VF %d, error %d\n", + mac_addr, vf->vf_id, status); + return -EIO; + } + + ice_vfhw_mac_del(vf, vc_ether_addr); + + vf->num_mac--; + + return 0; +} + +/** + * ice_vc_handle_mac_addr_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * @set: true if MAC filters are being set, false otherwise + * + * add guest MAC address filter + */ +static int +ice_vc_handle_mac_addr_msg(struct ice_vf *vf, u8 *msg, bool set) +{ + int (*ice_vc_cfg_mac) + (struct ice_vf *vf, struct ice_vsi *vsi, + struct virtchnl_ether_addr *virtchnl_ether_addr); + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_ether_addr_list *al = + (struct virtchnl_ether_addr_list *)msg; + struct ice_pf *pf = vf->pf; + enum virtchnl_ops vc_op; + struct ice_vsi *vsi; + int i; + + if (set) { + vc_op = VIRTCHNL_OP_ADD_ETH_ADDR; + ice_vc_cfg_mac = ice_vc_add_mac_addr; + } else { + vc_op = VIRTCHNL_OP_DEL_ETH_ADDR; + ice_vc_cfg_mac = ice_vc_del_mac_addr; + } + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) || + !ice_vc_isvalid_vsi_id(vf, al->vsi_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto handle_mac_exit; + } + + /* If this VF is not privileged, then we can't add more than a + * limited number of addresses. Check to make sure that the + * additions do not push us over the limit. + */ + if (set && !ice_is_vf_trusted(vf) && + (vf->num_mac + al->num_elements) > ICE_MAX_MACADDR_PER_VF) { + dev_err(ice_pf_to_dev(pf), "Can't add more MAC addresses, because VF-%d is not trusted, switch the VF to trusted mode in order to add more functionalities\n", + vf->vf_id); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto handle_mac_exit; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto handle_mac_exit; + } + + for (i = 0; i < al->num_elements; i++) { + u8 *mac_addr = al->list[i].addr; + int result; + + if (is_broadcast_ether_addr(mac_addr) || + is_zero_ether_addr(mac_addr)) + continue; + + result = ice_vc_cfg_mac(vf, vsi, &al->list[i]); + if (result == -EEXIST || result == -ENOENT) { + continue; + } else if (result) { + v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR; + goto handle_mac_exit; + } + } + +handle_mac_exit: + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, vc_op, v_ret, NULL, 0); +} + +/** + * ice_vc_add_mac_addr_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * add guest MAC address filter + */ +static int ice_vc_add_mac_addr_msg(struct ice_vf *vf, u8 *msg) +{ + return ice_vc_handle_mac_addr_msg(vf, msg, true); +} + +/** + * ice_vc_del_mac_addr_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * remove guest MAC address filter + */ +static int ice_vc_del_mac_addr_msg(struct ice_vf *vf, u8 *msg) +{ + return ice_vc_handle_mac_addr_msg(vf, msg, false); +} + +/** + * ice_vc_request_qs_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * VFs get a default number of queues but can use this message to request a + * different number. If the request is successful, PF will reset the VF and + * return 0. If unsuccessful, PF will send message informing VF of number of + * available queue pairs via virtchnl message response to VF. + */ +static int ice_vc_request_qs_msg(struct ice_vf *vf, u8 *msg) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_vf_res_request *vfres = + (struct virtchnl_vf_res_request *)msg; + u16 req_queues = vfres->num_queue_pairs; + struct ice_pf *pf = vf->pf; + u16 max_allowed_vf_queues; + u16 tx_rx_queue_left; + struct device *dev; + u16 cur_queues; + + dev = ice_pf_to_dev(pf); + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + cur_queues = vf->num_vf_qs; + tx_rx_queue_left = min_t(u16, ice_get_avail_txq_count(pf), + ice_get_avail_rxq_count(pf)); + max_allowed_vf_queues = tx_rx_queue_left + cur_queues; + if (!req_queues) { + dev_err(dev, "VF %d tried to request 0 queues. Ignoring.\n", + vf->vf_id); + } else if (req_queues > ICE_MAX_RSS_QS_PER_VF) { + dev_err(dev, "VF %d tried to request more than %d queues.\n", + vf->vf_id, ICE_MAX_RSS_QS_PER_VF); + vfres->num_queue_pairs = ICE_MAX_RSS_QS_PER_VF; + } else if (req_queues > cur_queues && + req_queues - cur_queues > tx_rx_queue_left) { + dev_warn(dev, "VF %d requested %u more queues, but only %u left.\n", + vf->vf_id, req_queues - cur_queues, tx_rx_queue_left); + vfres->num_queue_pairs = min_t(u16, max_allowed_vf_queues, + ICE_MAX_RSS_QS_PER_VF); + } else { + /* request is successful, then reset VF */ + vf->num_req_qs = req_queues; + ice_reset_vf(vf, ICE_VF_RESET_NOTIFY); + dev_info(dev, "VF %d granted request of %u queues.\n", + vf->vf_id, req_queues); + return 0; + } + +error_param: + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_REQUEST_QUEUES, + v_ret, (u8 *)vfres, sizeof(*vfres)); +} + +/** + * ice_vf_vlan_offload_ena - determine if capabilities support VLAN offloads + * @caps: VF driver negotiated capabilities + * + * Return true if VIRTCHNL_VF_OFFLOAD_VLAN capability is set, else return false + */ +static bool ice_vf_vlan_offload_ena(u32 caps) +{ + return !!(caps & VIRTCHNL_VF_OFFLOAD_VLAN); +} + +/** + * ice_is_vlan_promisc_allowed - check if VLAN promiscuous config is allowed + * @vf: VF used to determine if VLAN promiscuous config is allowed + */ +static bool ice_is_vlan_promisc_allowed(struct ice_vf *vf) +{ + if ((test_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states) || + test_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states)) && + test_bit(ICE_FLAG_VF_TRUE_PROMISC_ENA, vf->pf->flags)) + return true; + + return false; +} + +/** + * ice_vf_ena_vlan_promisc - Enable Tx/Rx VLAN promiscuous for the VLAN + * @vsi: VF's VSI used to enable VLAN promiscuous mode + * @vlan: VLAN used to enable VLAN promiscuous + * + * This function should only be called if VLAN promiscuous mode is allowed, + * which can be determined via ice_is_vlan_promisc_allowed(). + */ +static int ice_vf_ena_vlan_promisc(struct ice_vsi *vsi, struct ice_vlan *vlan) +{ + u8 promisc_m = ICE_PROMISC_VLAN_TX | ICE_PROMISC_VLAN_RX; + int status; + + status = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, promisc_m, + vlan->vid); + if (status && status != -EEXIST) + return status; + + return 0; +} + +/** + * ice_vf_dis_vlan_promisc - Disable Tx/Rx VLAN promiscuous for the VLAN + * @vsi: VF's VSI used to disable VLAN promiscuous mode for + * @vlan: VLAN used to disable VLAN promiscuous + * + * This function should only be called if VLAN promiscuous mode is allowed, + * which can be determined via ice_is_vlan_promisc_allowed(). + */ +static int ice_vf_dis_vlan_promisc(struct ice_vsi *vsi, struct ice_vlan *vlan) +{ + u8 promisc_m = ICE_PROMISC_VLAN_TX | ICE_PROMISC_VLAN_RX; + int status; + + status = ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, promisc_m, + vlan->vid); + if (status && status != -ENOENT) + return status; + + return 0; +} + +/** + * ice_vf_has_max_vlans - check if VF already has the max allowed VLAN filters + * @vf: VF to check against + * @vsi: VF's VSI + * + * If the VF is trusted then the VF is allowed to add as many VLANs as it + * wants to, so return false. + * + * When the VF is untrusted compare the number of non-zero VLANs + 1 to the max + * allowed VLANs for an untrusted VF. Return the result of this comparison. + */ +static bool ice_vf_has_max_vlans(struct ice_vf *vf, struct ice_vsi *vsi) +{ + if (ice_is_vf_trusted(vf)) + return false; + +#define ICE_VF_ADDED_VLAN_ZERO_FLTRS 1 + return ((ice_vsi_num_non_zero_vlans(vsi) + + ICE_VF_ADDED_VLAN_ZERO_FLTRS) >= ICE_MAX_VLAN_PER_VF); +} + +/** + * ice_vc_process_vlan_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * @add_v: Add VLAN if true, otherwise delete VLAN + * + * Process virtchnl op to add or remove programmed guest VLAN ID + */ +static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_vlan_filter_list *vfl = + (struct virtchnl_vlan_filter_list *)msg; + struct ice_pf *pf = vf->pf; + bool vlan_promisc = false; + struct ice_vsi *vsi; + struct device *dev; + int status = 0; + int i; + + dev = ice_pf_to_dev(pf); + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (!ice_vf_vlan_offload_ena(vf->driver_caps)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, vfl->vsi_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + for (i = 0; i < vfl->num_elements; i++) { + if (vfl->vlan_id[i] >= VLAN_N_VID) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + dev_err(dev, "invalid VF VLAN id %d\n", + vfl->vlan_id[i]); + goto error_param; + } + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (add_v && ice_vf_has_max_vlans(vf, vsi)) { + dev_info(dev, "VF-%d is not trusted, switch the VF to trusted mode, in order to add more VLAN addresses\n", + vf->vf_id); + /* There is no need to let VF know about being not trusted, + * so we can just return success message here + */ + goto error_param; + } + + /* in DVM a VF can add/delete inner VLAN filters when + * VIRTCHNL_VF_OFFLOAD_VLAN is negotiated, so only reject in SVM + */ + if (ice_vf_is_port_vlan_ena(vf) && !ice_is_dvm_ena(&pf->hw)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + /* in DVM VLAN promiscuous is based on the outer VLAN, which would be + * the port VLAN if VIRTCHNL_VF_OFFLOAD_VLAN was negotiated, so only + * allow vlan_promisc = true in SVM and if no port VLAN is configured + */ + vlan_promisc = ice_is_vlan_promisc_allowed(vf) && + !ice_is_dvm_ena(&pf->hw) && + !ice_vf_is_port_vlan_ena(vf); + + if (add_v) { + for (i = 0; i < vfl->num_elements; i++) { + u16 vid = vfl->vlan_id[i]; + struct ice_vlan vlan; + + if (ice_vf_has_max_vlans(vf, vsi)) { + dev_info(dev, "VF-%d is not trusted, switch the VF to trusted mode, in order to add more VLAN addresses\n", + vf->vf_id); + /* There is no need to let VF know about being + * not trusted, so we can just return success + * message here as well. + */ + goto error_param; + } + + /* we add VLAN 0 by default for each VF so we can enable + * Tx VLAN anti-spoof without triggering MDD events so + * we don't need to add it again here + */ + if (!vid) + continue; + + vlan = ICE_VLAN(ETH_P_8021Q, vid, 0); + status = vsi->inner_vlan_ops.add_vlan(vsi, &vlan); + if (status) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + /* Enable VLAN filtering on first non-zero VLAN */ + if (!vlan_promisc && vid && !ice_is_dvm_ena(&pf->hw)) { + if (vf->spoofchk) { + status = vsi->inner_vlan_ops.ena_tx_filtering(vsi); + if (status) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + dev_err(dev, "Enable VLAN anti-spoofing on VLAN ID: %d failed error-%d\n", + vid, status); + goto error_param; + } + } + if (vsi->inner_vlan_ops.ena_rx_filtering(vsi)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + dev_err(dev, "Enable VLAN pruning on VLAN ID: %d failed error-%d\n", + vid, status); + goto error_param; + } + } else if (vlan_promisc) { + status = ice_vf_ena_vlan_promisc(vsi, &vlan); + if (status) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + dev_err(dev, "Enable Unicast/multicast promiscuous mode on VLAN ID:%d failed error-%d\n", + vid, status); + } + } + } + } else { + /* In case of non_trusted VF, number of VLAN elements passed + * to PF for removal might be greater than number of VLANs + * filter programmed for that VF - So, use actual number of + * VLANS added earlier with add VLAN opcode. In order to avoid + * removing VLAN that doesn't exist, which result to sending + * erroneous failed message back to the VF + */ + int num_vf_vlan; + + num_vf_vlan = vsi->num_vlan; + for (i = 0; i < vfl->num_elements && i < num_vf_vlan; i++) { + u16 vid = vfl->vlan_id[i]; + struct ice_vlan vlan; + + /* we add VLAN 0 by default for each VF so we can enable + * Tx VLAN anti-spoof without triggering MDD events so + * we don't want a VIRTCHNL request to remove it + */ + if (!vid) + continue; + + vlan = ICE_VLAN(ETH_P_8021Q, vid, 0); + status = vsi->inner_vlan_ops.del_vlan(vsi, &vlan); + if (status) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + /* Disable VLAN filtering when only VLAN 0 is left */ + if (!ice_vsi_has_non_zero_vlans(vsi)) { + vsi->inner_vlan_ops.dis_tx_filtering(vsi); + vsi->inner_vlan_ops.dis_rx_filtering(vsi); + } + + if (vlan_promisc) + ice_vf_dis_vlan_promisc(vsi, &vlan); + } + } + +error_param: + /* send the response to the VF */ + if (add_v) + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ADD_VLAN, v_ret, + NULL, 0); + else + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DEL_VLAN, v_ret, + NULL, 0); +} + +/** + * ice_vc_add_vlan_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * Add and program guest VLAN ID + */ +static int ice_vc_add_vlan_msg(struct ice_vf *vf, u8 *msg) +{ + return ice_vc_process_vlan_msg(vf, msg, true); +} + +/** + * ice_vc_remove_vlan_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * remove programmed guest VLAN ID + */ +static int ice_vc_remove_vlan_msg(struct ice_vf *vf, u8 *msg) +{ + return ice_vc_process_vlan_msg(vf, msg, false); +} + +/** + * ice_vc_ena_vlan_stripping + * @vf: pointer to the VF info + * + * Enable VLAN header stripping for a given VF + */ +static int ice_vc_ena_vlan_stripping(struct ice_vf *vf) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (!ice_vf_vlan_offload_ena(vf->driver_caps)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (vsi->inner_vlan_ops.ena_stripping(vsi, ETH_P_8021Q)) + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + +error_param: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING, + v_ret, NULL, 0); +} + +/** + * ice_vc_dis_vlan_stripping + * @vf: pointer to the VF info + * + * Disable VLAN header stripping for a given VF + */ +static int ice_vc_dis_vlan_stripping(struct ice_vf *vf) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (!ice_vf_vlan_offload_ena(vf->driver_caps)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (vsi->inner_vlan_ops.dis_stripping(vsi)) + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + +error_param: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING, + v_ret, NULL, 0); +} + +/** + * ice_vf_init_vlan_stripping - enable/disable VLAN stripping on initialization + * @vf: VF to enable/disable VLAN stripping for on initialization + * + * Set the default for VLAN stripping based on whether a port VLAN is configured + * and the current VLAN mode of the device. + */ +static int ice_vf_init_vlan_stripping(struct ice_vf *vf) +{ + struct ice_vsi *vsi = ice_get_vf_vsi(vf); + + if (!vsi) + return -EINVAL; + + /* don't modify stripping if port VLAN is configured in SVM since the + * port VLAN is based on the inner/single VLAN in SVM + */ + 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); +} + +static u16 ice_vc_get_max_vlan_fltrs(struct ice_vf *vf) +{ + if (vf->trusted) + return VLAN_N_VID; + else + return ICE_MAX_VLAN_PER_VF; +} + +/** + * ice_vf_outer_vlan_not_allowed - check if outer VLAN can be used + * @vf: VF that being checked for + * + * When the device is in double VLAN mode, check whether or not the outer VLAN + * is allowed. + */ +static bool ice_vf_outer_vlan_not_allowed(struct ice_vf *vf) +{ + if (ice_vf_is_port_vlan_ena(vf)) + return true; + + return false; +} + +/** + * ice_vc_set_dvm_caps - set VLAN capabilities when the device is in DVM + * @vf: VF that capabilities are being set for + * @caps: VLAN capabilities to populate + * + * Determine VLAN capabilities support based on whether a port VLAN is + * configured. If a port VLAN is configured then the VF should use the inner + * filtering/offload capabilities since the port VLAN is using the outer VLAN + * capabilies. + */ +static void +ice_vc_set_dvm_caps(struct ice_vf *vf, struct virtchnl_vlan_caps *caps) +{ + struct virtchnl_vlan_supported_caps *supported_caps; + + if (ice_vf_outer_vlan_not_allowed(vf)) { + /* until support for inner VLAN filtering is added when a port + * VLAN is configured, only support software offloaded inner + * VLANs when a port VLAN is confgured in DVM + */ + supported_caps = &caps->filtering.filtering_support; + supported_caps->inner = VIRTCHNL_VLAN_UNSUPPORTED; + + supported_caps = &caps->offloads.stripping_support; + supported_caps->inner = VIRTCHNL_VLAN_ETHERTYPE_8100 | + VIRTCHNL_VLAN_TOGGLE | + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG1; + supported_caps->outer = VIRTCHNL_VLAN_UNSUPPORTED; + + supported_caps = &caps->offloads.insertion_support; + supported_caps->inner = VIRTCHNL_VLAN_ETHERTYPE_8100 | + VIRTCHNL_VLAN_TOGGLE | + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG1; + supported_caps->outer = VIRTCHNL_VLAN_UNSUPPORTED; + + caps->offloads.ethertype_init = VIRTCHNL_VLAN_ETHERTYPE_8100; + caps->offloads.ethertype_match = + VIRTCHNL_ETHERTYPE_STRIPPING_MATCHES_INSERTION; + } else { + supported_caps = &caps->filtering.filtering_support; + supported_caps->inner = VIRTCHNL_VLAN_UNSUPPORTED; + supported_caps->outer = VIRTCHNL_VLAN_ETHERTYPE_8100 | + VIRTCHNL_VLAN_ETHERTYPE_88A8 | + VIRTCHNL_VLAN_ETHERTYPE_9100 | + VIRTCHNL_VLAN_ETHERTYPE_AND; + caps->filtering.ethertype_init = VIRTCHNL_VLAN_ETHERTYPE_8100 | + VIRTCHNL_VLAN_ETHERTYPE_88A8 | + VIRTCHNL_VLAN_ETHERTYPE_9100; + + supported_caps = &caps->offloads.stripping_support; + supported_caps->inner = VIRTCHNL_VLAN_TOGGLE | + VIRTCHNL_VLAN_ETHERTYPE_8100 | + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG1; + supported_caps->outer = VIRTCHNL_VLAN_TOGGLE | + VIRTCHNL_VLAN_ETHERTYPE_8100 | + VIRTCHNL_VLAN_ETHERTYPE_88A8 | + VIRTCHNL_VLAN_ETHERTYPE_9100 | + VIRTCHNL_VLAN_ETHERTYPE_XOR | + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG2_2; + + supported_caps = &caps->offloads.insertion_support; + supported_caps->inner = VIRTCHNL_VLAN_TOGGLE | + VIRTCHNL_VLAN_ETHERTYPE_8100 | + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG1; + supported_caps->outer = VIRTCHNL_VLAN_TOGGLE | + VIRTCHNL_VLAN_ETHERTYPE_8100 | + VIRTCHNL_VLAN_ETHERTYPE_88A8 | + VIRTCHNL_VLAN_ETHERTYPE_9100 | + VIRTCHNL_VLAN_ETHERTYPE_XOR | + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG2; + + caps->offloads.ethertype_init = VIRTCHNL_VLAN_ETHERTYPE_8100; + + caps->offloads.ethertype_match = + VIRTCHNL_ETHERTYPE_STRIPPING_MATCHES_INSERTION; + } + + caps->filtering.max_filters = ice_vc_get_max_vlan_fltrs(vf); +} + +/** + * ice_vc_set_svm_caps - set VLAN capabilities when the device is in SVM + * @vf: VF that capabilities are being set for + * @caps: VLAN capabilities to populate + * + * Determine VLAN capabilities support based on whether a port VLAN is + * configured. If a port VLAN is configured then the VF does not have any VLAN + * filtering or offload capabilities since the port VLAN is using the inner VLAN + * capabilities in single VLAN mode (SVM). Otherwise allow the VF to use inner + * VLAN fitlering and offload capabilities. + */ +static void +ice_vc_set_svm_caps(struct ice_vf *vf, struct virtchnl_vlan_caps *caps) +{ + struct virtchnl_vlan_supported_caps *supported_caps; + + if (ice_vf_is_port_vlan_ena(vf)) { + supported_caps = &caps->filtering.filtering_support; + supported_caps->inner = VIRTCHNL_VLAN_UNSUPPORTED; + supported_caps->outer = VIRTCHNL_VLAN_UNSUPPORTED; + + supported_caps = &caps->offloads.stripping_support; + supported_caps->inner = VIRTCHNL_VLAN_UNSUPPORTED; + supported_caps->outer = VIRTCHNL_VLAN_UNSUPPORTED; + + supported_caps = &caps->offloads.insertion_support; + supported_caps->inner = VIRTCHNL_VLAN_UNSUPPORTED; + supported_caps->outer = VIRTCHNL_VLAN_UNSUPPORTED; + + caps->offloads.ethertype_init = VIRTCHNL_VLAN_UNSUPPORTED; + caps->offloads.ethertype_match = VIRTCHNL_VLAN_UNSUPPORTED; + caps->filtering.max_filters = 0; + } else { + supported_caps = &caps->filtering.filtering_support; + supported_caps->inner = VIRTCHNL_VLAN_ETHERTYPE_8100; + supported_caps->outer = VIRTCHNL_VLAN_UNSUPPORTED; + caps->filtering.ethertype_init = VIRTCHNL_VLAN_ETHERTYPE_8100; + + supported_caps = &caps->offloads.stripping_support; + supported_caps->inner = VIRTCHNL_VLAN_ETHERTYPE_8100 | + VIRTCHNL_VLAN_TOGGLE | + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG1; + supported_caps->outer = VIRTCHNL_VLAN_UNSUPPORTED; + + supported_caps = &caps->offloads.insertion_support; + supported_caps->inner = VIRTCHNL_VLAN_ETHERTYPE_8100 | + VIRTCHNL_VLAN_TOGGLE | + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG1; + supported_caps->outer = VIRTCHNL_VLAN_UNSUPPORTED; + + caps->offloads.ethertype_init = VIRTCHNL_VLAN_ETHERTYPE_8100; + caps->offloads.ethertype_match = + VIRTCHNL_ETHERTYPE_STRIPPING_MATCHES_INSERTION; + caps->filtering.max_filters = ice_vc_get_max_vlan_fltrs(vf); + } +} + +/** + * ice_vc_get_offload_vlan_v2_caps - determine VF's VLAN capabilities + * @vf: VF to determine VLAN capabilities for + * + * This will only be called if the VF and PF successfully negotiated + * VIRTCHNL_VF_OFFLOAD_VLAN_V2. + * + * Set VLAN capabilities based on the current VLAN mode and whether a port VLAN + * is configured or not. + */ +static int ice_vc_get_offload_vlan_v2_caps(struct ice_vf *vf) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_vlan_caps *caps = NULL; + int err, len = 0; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + caps = kzalloc(sizeof(*caps), GFP_KERNEL); + if (!caps) { + v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; + goto out; + } + len = sizeof(*caps); + + if (ice_is_dvm_ena(&vf->pf->hw)) + ice_vc_set_dvm_caps(vf, caps); + else + ice_vc_set_svm_caps(vf, caps); + + /* store negotiated caps to prevent invalid VF messages */ + memcpy(&vf->vlan_v2_caps, caps, sizeof(*caps)); + +out: + err = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS, + v_ret, (u8 *)caps, len); + kfree(caps); + return err; +} + +/** + * ice_vc_validate_vlan_tpid - validate VLAN TPID + * @filtering_caps: negotiated/supported VLAN filtering capabilities + * @tpid: VLAN TPID used for validation + * + * Convert the VLAN TPID to a VIRTCHNL_VLAN_ETHERTYPE_* and then compare against + * the negotiated/supported filtering caps to see if the VLAN TPID is valid. + */ +static bool ice_vc_validate_vlan_tpid(u16 filtering_caps, u16 tpid) +{ + enum virtchnl_vlan_support vlan_ethertype = VIRTCHNL_VLAN_UNSUPPORTED; + + switch (tpid) { + case ETH_P_8021Q: + vlan_ethertype = VIRTCHNL_VLAN_ETHERTYPE_8100; + break; + case ETH_P_8021AD: + vlan_ethertype = VIRTCHNL_VLAN_ETHERTYPE_88A8; + break; + case ETH_P_QINQ1: + vlan_ethertype = VIRTCHNL_VLAN_ETHERTYPE_9100; + break; + } + + if (!(filtering_caps & vlan_ethertype)) + return false; + + return true; +} + +/** + * ice_vc_is_valid_vlan - validate the virtchnl_vlan + * @vc_vlan: virtchnl_vlan to validate + * + * If the VLAN TCI and VLAN TPID are 0, then this filter is invalid, so return + * false. Otherwise return true. + */ +static bool ice_vc_is_valid_vlan(struct virtchnl_vlan *vc_vlan) +{ + if (!vc_vlan->tci || !vc_vlan->tpid) + return false; + + return true; +} + +/** + * ice_vc_validate_vlan_filter_list - validate the filter list from the VF + * @vfc: negotiated/supported VLAN filtering capabilities + * @vfl: VLAN filter list from VF to validate + * + * Validate all of the filters in the VLAN filter list from the VF. If any of + * the checks fail then return false. Otherwise return true. + */ +static bool +ice_vc_validate_vlan_filter_list(struct virtchnl_vlan_filtering_caps *vfc, + struct virtchnl_vlan_filter_list_v2 *vfl) +{ + u16 i; + + if (!vfl->num_elements) + return false; + + for (i = 0; i < vfl->num_elements; i++) { + struct virtchnl_vlan_supported_caps *filtering_support = + &vfc->filtering_support; + struct virtchnl_vlan_filter *vlan_fltr = &vfl->filters[i]; + struct virtchnl_vlan *outer = &vlan_fltr->outer; + struct virtchnl_vlan *inner = &vlan_fltr->inner; + + if ((ice_vc_is_valid_vlan(outer) && + filtering_support->outer == VIRTCHNL_VLAN_UNSUPPORTED) || + (ice_vc_is_valid_vlan(inner) && + filtering_support->inner == VIRTCHNL_VLAN_UNSUPPORTED)) + return false; + + if ((outer->tci_mask && + !(filtering_support->outer & VIRTCHNL_VLAN_FILTER_MASK)) || + (inner->tci_mask && + !(filtering_support->inner & VIRTCHNL_VLAN_FILTER_MASK))) + return false; + + if (((outer->tci & VLAN_PRIO_MASK) && + !(filtering_support->outer & VIRTCHNL_VLAN_PRIO)) || + ((inner->tci & VLAN_PRIO_MASK) && + !(filtering_support->inner & VIRTCHNL_VLAN_PRIO))) + return false; + + if ((ice_vc_is_valid_vlan(outer) && + !ice_vc_validate_vlan_tpid(filtering_support->outer, + outer->tpid)) || + (ice_vc_is_valid_vlan(inner) && + !ice_vc_validate_vlan_tpid(filtering_support->inner, + inner->tpid))) + return false; + } + + return true; +} + +/** + * ice_vc_to_vlan - transform from struct virtchnl_vlan to struct ice_vlan + * @vc_vlan: struct virtchnl_vlan to transform + */ +static struct ice_vlan ice_vc_to_vlan(struct virtchnl_vlan *vc_vlan) +{ + struct ice_vlan vlan = { 0 }; + + vlan.prio = (vc_vlan->tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; + vlan.vid = vc_vlan->tci & VLAN_VID_MASK; + vlan.tpid = vc_vlan->tpid; + + return vlan; +} + +/** + * ice_vc_vlan_action - action to perform on the virthcnl_vlan + * @vsi: VF's VSI used to perform the action + * @vlan_action: function to perform the action with (i.e. add/del) + * @vlan: VLAN filter to perform the action with + */ +static int +ice_vc_vlan_action(struct ice_vsi *vsi, + int (*vlan_action)(struct ice_vsi *, struct ice_vlan *), + struct ice_vlan *vlan) +{ + int err; + + err = vlan_action(vsi, vlan); + if (err) + return err; + + return 0; +} + +/** + * ice_vc_del_vlans - delete VLAN(s) from the virtchnl filter list + * @vf: VF used to delete the VLAN(s) + * @vsi: VF's VSI used to delete the VLAN(s) + * @vfl: virthchnl filter list used to delete the filters + */ +static int +ice_vc_del_vlans(struct ice_vf *vf, struct ice_vsi *vsi, + struct virtchnl_vlan_filter_list_v2 *vfl) +{ + bool vlan_promisc = ice_is_vlan_promisc_allowed(vf); + int err; + u16 i; + + for (i = 0; i < vfl->num_elements; i++) { + struct virtchnl_vlan_filter *vlan_fltr = &vfl->filters[i]; + struct virtchnl_vlan *vc_vlan; + + vc_vlan = &vlan_fltr->outer; + if (ice_vc_is_valid_vlan(vc_vlan)) { + struct ice_vlan vlan = ice_vc_to_vlan(vc_vlan); + + err = ice_vc_vlan_action(vsi, + vsi->outer_vlan_ops.del_vlan, + &vlan); + if (err) + return err; + + if (vlan_promisc) + ice_vf_dis_vlan_promisc(vsi, &vlan); + + /* Disable VLAN filtering when only VLAN 0 is left */ + if (!ice_vsi_has_non_zero_vlans(vsi) && ice_is_dvm_ena(&vsi->back->hw)) { + err = vsi->outer_vlan_ops.dis_tx_filtering(vsi); + if (err) + return err; + } + } + + vc_vlan = &vlan_fltr->inner; + if (ice_vc_is_valid_vlan(vc_vlan)) { + struct ice_vlan vlan = ice_vc_to_vlan(vc_vlan); + + err = ice_vc_vlan_action(vsi, + vsi->inner_vlan_ops.del_vlan, + &vlan); + if (err) + return err; + + /* no support for VLAN promiscuous on inner VLAN unless + * we are in Single VLAN Mode (SVM) + */ + if (!ice_is_dvm_ena(&vsi->back->hw)) { + if (vlan_promisc) + ice_vf_dis_vlan_promisc(vsi, &vlan); + + /* Disable VLAN filtering when only VLAN 0 is left */ + if (!ice_vsi_has_non_zero_vlans(vsi)) { + err = vsi->inner_vlan_ops.dis_tx_filtering(vsi); + if (err) + return err; + } + } + } + } + + return 0; +} + +/** + * ice_vc_remove_vlan_v2_msg - virtchnl handler for VIRTCHNL_OP_DEL_VLAN_V2 + * @vf: VF the message was received from + * @msg: message received from the VF + */ +static int ice_vc_remove_vlan_v2_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_vlan_filter_list_v2 *vfl = + (struct virtchnl_vlan_filter_list_v2 *)msg; + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct ice_vsi *vsi; + + if (!ice_vc_validate_vlan_filter_list(&vf->vlan_v2_caps.filtering, + vfl)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + if (!ice_vc_isvalid_vsi_id(vf, vfl->vport_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + if (ice_vc_del_vlans(vf, vsi, vfl)) + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + +out: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DEL_VLAN_V2, v_ret, NULL, + 0); +} + +/** + * ice_vc_add_vlans - add VLAN(s) from the virtchnl filter list + * @vf: VF used to add the VLAN(s) + * @vsi: VF's VSI used to add the VLAN(s) + * @vfl: virthchnl filter list used to add the filters + */ +static int +ice_vc_add_vlans(struct ice_vf *vf, struct ice_vsi *vsi, + struct virtchnl_vlan_filter_list_v2 *vfl) +{ + bool vlan_promisc = ice_is_vlan_promisc_allowed(vf); + int err; + u16 i; + + for (i = 0; i < vfl->num_elements; i++) { + struct virtchnl_vlan_filter *vlan_fltr = &vfl->filters[i]; + struct virtchnl_vlan *vc_vlan; + + vc_vlan = &vlan_fltr->outer; + if (ice_vc_is_valid_vlan(vc_vlan)) { + struct ice_vlan vlan = ice_vc_to_vlan(vc_vlan); + + err = ice_vc_vlan_action(vsi, + vsi->outer_vlan_ops.add_vlan, + &vlan); + if (err) + return err; + + if (vlan_promisc) { + err = ice_vf_ena_vlan_promisc(vsi, &vlan); + if (err) + return err; + } + + /* Enable VLAN filtering on first non-zero VLAN */ + if (vf->spoofchk && vlan.vid && ice_is_dvm_ena(&vsi->back->hw)) { + err = vsi->outer_vlan_ops.ena_tx_filtering(vsi); + if (err) + return err; + } + } + + vc_vlan = &vlan_fltr->inner; + if (ice_vc_is_valid_vlan(vc_vlan)) { + struct ice_vlan vlan = ice_vc_to_vlan(vc_vlan); + + err = ice_vc_vlan_action(vsi, + vsi->inner_vlan_ops.add_vlan, + &vlan); + if (err) + return err; + + /* no support for VLAN promiscuous on inner VLAN unless + * we are in Single VLAN Mode (SVM) + */ + if (!ice_is_dvm_ena(&vsi->back->hw)) { + if (vlan_promisc) { + err = ice_vf_ena_vlan_promisc(vsi, &vlan); + if (err) + return err; + } + + /* Enable VLAN filtering on first non-zero VLAN */ + if (vf->spoofchk && vlan.vid) { + err = vsi->inner_vlan_ops.ena_tx_filtering(vsi); + if (err) + return err; + } + } + } + } + + return 0; +} + +/** + * ice_vc_validate_add_vlan_filter_list - validate add filter list from the VF + * @vsi: VF VSI used to get number of existing VLAN filters + * @vfc: negotiated/supported VLAN filtering capabilities + * @vfl: VLAN filter list from VF to validate + * + * Validate all of the filters in the VLAN filter list from the VF during the + * VIRTCHNL_OP_ADD_VLAN_V2 opcode. If any of the checks fail then return false. + * Otherwise return true. + */ +static bool +ice_vc_validate_add_vlan_filter_list(struct ice_vsi *vsi, + struct virtchnl_vlan_filtering_caps *vfc, + struct virtchnl_vlan_filter_list_v2 *vfl) +{ + u16 num_requested_filters = ice_vsi_num_non_zero_vlans(vsi) + + vfl->num_elements; + + if (num_requested_filters > vfc->max_filters) + return false; + + return ice_vc_validate_vlan_filter_list(vfc, vfl); +} + +/** + * ice_vc_add_vlan_v2_msg - virtchnl handler for VIRTCHNL_OP_ADD_VLAN_V2 + * @vf: VF the message was received from + * @msg: message received from the VF + */ +static int ice_vc_add_vlan_v2_msg(struct ice_vf *vf, u8 *msg) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_vlan_filter_list_v2 *vfl = + (struct virtchnl_vlan_filter_list_v2 *)msg; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + if (!ice_vc_isvalid_vsi_id(vf, vfl->vport_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + if (!ice_vc_validate_add_vlan_filter_list(vsi, + &vf->vlan_v2_caps.filtering, + vfl)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + if (ice_vc_add_vlans(vf, vsi, vfl)) + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + +out: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ADD_VLAN_V2, v_ret, NULL, + 0); +} + +/** + * ice_vc_valid_vlan_setting - validate VLAN setting + * @negotiated_settings: negotiated VLAN settings during VF init + * @ethertype_setting: ethertype(s) requested for the VLAN setting + */ +static bool +ice_vc_valid_vlan_setting(u32 negotiated_settings, u32 ethertype_setting) +{ + if (ethertype_setting && !(negotiated_settings & ethertype_setting)) + return false; + + /* only allow a single VIRTCHNL_VLAN_ETHERTYPE if + * VIRTHCNL_VLAN_ETHERTYPE_AND is not negotiated/supported + */ + if (!(negotiated_settings & VIRTCHNL_VLAN_ETHERTYPE_AND) && + hweight32(ethertype_setting) > 1) + return false; + + /* ability to modify the VLAN setting was not negotiated */ + if (!(negotiated_settings & VIRTCHNL_VLAN_TOGGLE)) + return false; + + return true; +} + +/** + * ice_vc_valid_vlan_setting_msg - validate the VLAN setting message + * @caps: negotiated VLAN settings during VF init + * @msg: message to validate + * + * Used to validate any VLAN virtchnl message sent as a + * virtchnl_vlan_setting structure. Validates the message against the + * negotiated/supported caps during VF driver init. + */ +static bool +ice_vc_valid_vlan_setting_msg(struct virtchnl_vlan_supported_caps *caps, + struct virtchnl_vlan_setting *msg) +{ + if ((!msg->outer_ethertype_setting && + !msg->inner_ethertype_setting) || + (!caps->outer && !caps->inner)) + return false; + + if (msg->outer_ethertype_setting && + !ice_vc_valid_vlan_setting(caps->outer, + msg->outer_ethertype_setting)) + return false; + + if (msg->inner_ethertype_setting && + !ice_vc_valid_vlan_setting(caps->inner, + msg->inner_ethertype_setting)) + return false; + + return true; +} + +/** + * ice_vc_get_tpid - transform from VIRTCHNL_VLAN_ETHERTYPE_* to VLAN TPID + * @ethertype_setting: VIRTCHNL_VLAN_ETHERTYPE_* used to get VLAN TPID + * @tpid: VLAN TPID to populate + */ +static int ice_vc_get_tpid(u32 ethertype_setting, u16 *tpid) +{ + switch (ethertype_setting) { + case VIRTCHNL_VLAN_ETHERTYPE_8100: + *tpid = ETH_P_8021Q; + break; + case VIRTCHNL_VLAN_ETHERTYPE_88A8: + *tpid = ETH_P_8021AD; + break; + case VIRTCHNL_VLAN_ETHERTYPE_9100: + *tpid = ETH_P_QINQ1; + break; + default: + *tpid = 0; + return -EINVAL; + } + + return 0; +} + +/** + * ice_vc_ena_vlan_offload - enable VLAN offload based on the ethertype_setting + * @vsi: VF's VSI used to enable the VLAN offload + * @ena_offload: function used to enable the VLAN offload + * @ethertype_setting: VIRTCHNL_VLAN_ETHERTYPE_* to enable offloads for + */ +static int +ice_vc_ena_vlan_offload(struct ice_vsi *vsi, + int (*ena_offload)(struct ice_vsi *vsi, u16 tpid), + u32 ethertype_setting) +{ + u16 tpid; + int err; + + err = ice_vc_get_tpid(ethertype_setting, &tpid); + if (err) + return err; + + err = ena_offload(vsi, tpid); + if (err) + return err; + + return 0; +} + +#define ICE_L2TSEL_QRX_CONTEXT_REG_IDX 3 +#define ICE_L2TSEL_BIT_OFFSET 23 +enum ice_l2tsel { + ICE_L2TSEL_EXTRACT_FIRST_TAG_L2TAG2_2ND, + ICE_L2TSEL_EXTRACT_FIRST_TAG_L2TAG1, +}; + +/** + * ice_vsi_update_l2tsel - update l2tsel field for all Rx rings on this VSI + * @vsi: VSI used to update l2tsel on + * @l2tsel: l2tsel setting requested + * + * Use the l2tsel setting to update all of the Rx queue context bits for l2tsel. + * This will modify which descriptor field the first offloaded VLAN will be + * stripped into. + */ +static void ice_vsi_update_l2tsel(struct ice_vsi *vsi, enum ice_l2tsel l2tsel) +{ + struct ice_hw *hw = &vsi->back->hw; + u32 l2tsel_bit; + int i; + + if (l2tsel == ICE_L2TSEL_EXTRACT_FIRST_TAG_L2TAG2_2ND) + l2tsel_bit = 0; + else + l2tsel_bit = BIT(ICE_L2TSEL_BIT_OFFSET); + + for (i = 0; i < vsi->alloc_rxq; i++) { + u16 pfq = vsi->rxq_map[i]; + u32 qrx_context_offset; + u32 regval; + + qrx_context_offset = + QRX_CONTEXT(ICE_L2TSEL_QRX_CONTEXT_REG_IDX, pfq); + + regval = rd32(hw, qrx_context_offset); + regval &= ~BIT(ICE_L2TSEL_BIT_OFFSET); + regval |= l2tsel_bit; + wr32(hw, qrx_context_offset, regval); + } +} + +/** + * ice_vc_ena_vlan_stripping_v2_msg + * @vf: VF the message was received from + * @msg: message received from the VF + * + * virthcnl handler for VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2 + */ +static int ice_vc_ena_vlan_stripping_v2_msg(struct ice_vf *vf, u8 *msg) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_vlan_supported_caps *stripping_support; + struct virtchnl_vlan_setting *strip_msg = + (struct virtchnl_vlan_setting *)msg; + u32 ethertype_setting; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + if (!ice_vc_isvalid_vsi_id(vf, strip_msg->vport_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + stripping_support = &vf->vlan_v2_caps.offloads.stripping_support; + if (!ice_vc_valid_vlan_setting_msg(stripping_support, strip_msg)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + ethertype_setting = strip_msg->outer_ethertype_setting; + if (ethertype_setting) { + if (ice_vc_ena_vlan_offload(vsi, + vsi->outer_vlan_ops.ena_stripping, + ethertype_setting)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } else { + enum ice_l2tsel l2tsel = + ICE_L2TSEL_EXTRACT_FIRST_TAG_L2TAG2_2ND; + + /* PF tells the VF that the outer VLAN tag is always + * extracted to VIRTCHNL_VLAN_TAG_LOCATION_L2TAG2_2 and + * inner is always extracted to + * VIRTCHNL_VLAN_TAG_LOCATION_L2TAG1. This is needed to + * support outer stripping so the first tag always ends + * up in L2TAG2_2ND and the second/inner tag, if + * enabled, is extracted in L2TAG1. + */ + ice_vsi_update_l2tsel(vsi, l2tsel); + } + } + + ethertype_setting = strip_msg->inner_ethertype_setting; + if (ethertype_setting && + ice_vc_ena_vlan_offload(vsi, vsi->inner_vlan_ops.ena_stripping, + ethertype_setting)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + +out: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2, + v_ret, NULL, 0); +} + +/** + * ice_vc_dis_vlan_stripping_v2_msg + * @vf: VF the message was received from + * @msg: message received from the VF + * + * virthcnl handler for VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2 + */ +static int ice_vc_dis_vlan_stripping_v2_msg(struct ice_vf *vf, u8 *msg) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_vlan_supported_caps *stripping_support; + struct virtchnl_vlan_setting *strip_msg = + (struct virtchnl_vlan_setting *)msg; + u32 ethertype_setting; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + if (!ice_vc_isvalid_vsi_id(vf, strip_msg->vport_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + stripping_support = &vf->vlan_v2_caps.offloads.stripping_support; + if (!ice_vc_valid_vlan_setting_msg(stripping_support, strip_msg)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + ethertype_setting = strip_msg->outer_ethertype_setting; + if (ethertype_setting) { + if (vsi->outer_vlan_ops.dis_stripping(vsi)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } else { + enum ice_l2tsel l2tsel = + ICE_L2TSEL_EXTRACT_FIRST_TAG_L2TAG1; + + /* PF tells the VF that the outer VLAN tag is always + * extracted to VIRTCHNL_VLAN_TAG_LOCATION_L2TAG2_2 and + * inner is always extracted to + * VIRTCHNL_VLAN_TAG_LOCATION_L2TAG1. This is needed to + * support inner stripping while outer stripping is + * disabled so that the first and only tag is extracted + * in L2TAG1. + */ + ice_vsi_update_l2tsel(vsi, l2tsel); + } + } + + ethertype_setting = strip_msg->inner_ethertype_setting; + if (ethertype_setting && vsi->inner_vlan_ops.dis_stripping(vsi)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + +out: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2, + v_ret, NULL, 0); +} + +/** + * ice_vc_ena_vlan_insertion_v2_msg + * @vf: VF the message was received from + * @msg: message received from the VF + * + * virthcnl handler for VIRTCHNL_OP_ENABLE_VLAN_INSERTION_V2 + */ +static int ice_vc_ena_vlan_insertion_v2_msg(struct ice_vf *vf, u8 *msg) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_vlan_supported_caps *insertion_support; + struct virtchnl_vlan_setting *insertion_msg = + (struct virtchnl_vlan_setting *)msg; + u32 ethertype_setting; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + if (!ice_vc_isvalid_vsi_id(vf, insertion_msg->vport_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + insertion_support = &vf->vlan_v2_caps.offloads.insertion_support; + if (!ice_vc_valid_vlan_setting_msg(insertion_support, insertion_msg)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + ethertype_setting = insertion_msg->outer_ethertype_setting; + if (ethertype_setting && + ice_vc_ena_vlan_offload(vsi, vsi->outer_vlan_ops.ena_insertion, + ethertype_setting)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + ethertype_setting = insertion_msg->inner_ethertype_setting; + if (ethertype_setting && + ice_vc_ena_vlan_offload(vsi, vsi->inner_vlan_ops.ena_insertion, + ethertype_setting)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + +out: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ENABLE_VLAN_INSERTION_V2, + v_ret, NULL, 0); +} + +/** + * ice_vc_dis_vlan_insertion_v2_msg + * @vf: VF the message was received from + * @msg: message received from the VF + * + * virthcnl handler for VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2 + */ +static int ice_vc_dis_vlan_insertion_v2_msg(struct ice_vf *vf, u8 *msg) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_vlan_supported_caps *insertion_support; + struct virtchnl_vlan_setting *insertion_msg = + (struct virtchnl_vlan_setting *)msg; + u32 ethertype_setting; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + if (!ice_vc_isvalid_vsi_id(vf, insertion_msg->vport_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + insertion_support = &vf->vlan_v2_caps.offloads.insertion_support; + if (!ice_vc_valid_vlan_setting_msg(insertion_support, insertion_msg)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + ethertype_setting = insertion_msg->outer_ethertype_setting; + if (ethertype_setting && vsi->outer_vlan_ops.dis_insertion(vsi)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + ethertype_setting = insertion_msg->inner_ethertype_setting; + if (ethertype_setting && vsi->inner_vlan_ops.dis_insertion(vsi)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + +out: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2, + v_ret, NULL, 0); +} + +static const struct ice_virtchnl_ops ice_virtchnl_dflt_ops = { + .get_ver_msg = ice_vc_get_ver_msg, + .get_vf_res_msg = ice_vc_get_vf_res_msg, + .reset_vf = ice_vc_reset_vf_msg, + .add_mac_addr_msg = ice_vc_add_mac_addr_msg, + .del_mac_addr_msg = ice_vc_del_mac_addr_msg, + .cfg_qs_msg = ice_vc_cfg_qs_msg, + .ena_qs_msg = ice_vc_ena_qs_msg, + .dis_qs_msg = ice_vc_dis_qs_msg, + .request_qs_msg = ice_vc_request_qs_msg, + .cfg_irq_map_msg = ice_vc_cfg_irq_map_msg, + .config_rss_key = ice_vc_config_rss_key, + .config_rss_lut = ice_vc_config_rss_lut, + .get_stats_msg = ice_vc_get_stats_msg, + .cfg_promiscuous_mode_msg = ice_vc_cfg_promiscuous_mode_msg, + .add_vlan_msg = ice_vc_add_vlan_msg, + .remove_vlan_msg = ice_vc_remove_vlan_msg, + .ena_vlan_stripping = ice_vc_ena_vlan_stripping, + .dis_vlan_stripping = ice_vc_dis_vlan_stripping, + .handle_rss_cfg_msg = ice_vc_handle_rss_cfg, + .add_fdir_fltr_msg = ice_vc_add_fdir_fltr, + .del_fdir_fltr_msg = ice_vc_del_fdir_fltr, + .get_offload_vlan_v2_caps = ice_vc_get_offload_vlan_v2_caps, + .add_vlan_v2_msg = ice_vc_add_vlan_v2_msg, + .remove_vlan_v2_msg = ice_vc_remove_vlan_v2_msg, + .ena_vlan_stripping_v2_msg = ice_vc_ena_vlan_stripping_v2_msg, + .dis_vlan_stripping_v2_msg = ice_vc_dis_vlan_stripping_v2_msg, + .ena_vlan_insertion_v2_msg = ice_vc_ena_vlan_insertion_v2_msg, + .dis_vlan_insertion_v2_msg = ice_vc_dis_vlan_insertion_v2_msg, +}; + +/** + * ice_virtchnl_set_dflt_ops - Switch to default virtchnl ops + * @vf: the VF to switch ops + */ +void ice_virtchnl_set_dflt_ops(struct ice_vf *vf) +{ + vf->virtchnl_ops = &ice_virtchnl_dflt_ops; +} + +/** + * ice_vc_repr_add_mac + * @vf: pointer to VF + * @msg: virtchannel message + * + * When port representors are created, we do not add MAC rule + * to firmware, we store it so that PF could report same + * MAC as VF. + */ +static int ice_vc_repr_add_mac(struct ice_vf *vf, u8 *msg) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_ether_addr_list *al = + (struct virtchnl_ether_addr_list *)msg; + struct ice_vsi *vsi; + struct ice_pf *pf; + int i; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) || + !ice_vc_isvalid_vsi_id(vf, al->vsi_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto handle_mac_exit; + } + + pf = vf->pf; + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto handle_mac_exit; + } + + for (i = 0; i < al->num_elements; i++) { + u8 *mac_addr = al->list[i].addr; + int result; + + if (!is_unicast_ether_addr(mac_addr) || + ether_addr_equal(mac_addr, vf->hw_lan_addr.addr)) + continue; + + if (vf->pf_set_mac) { + dev_err(ice_pf_to_dev(pf), "VF attempting to override administratively set MAC address\n"); + v_ret = VIRTCHNL_STATUS_ERR_NOT_SUPPORTED; + goto handle_mac_exit; + } + + result = ice_eswitch_add_vf_mac_rule(pf, vf, mac_addr); + if (result) { + dev_err(ice_pf_to_dev(pf), "Failed to add MAC %pM for VF %d\n, error %d\n", + mac_addr, vf->vf_id, result); + goto handle_mac_exit; + } + + ice_vfhw_mac_add(vf, &al->list[i]); + vf->num_mac++; + break; + } + +handle_mac_exit: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ADD_ETH_ADDR, + v_ret, NULL, 0); +} + +/** + * ice_vc_repr_del_mac - response with success for deleting MAC + * @vf: pointer to VF + * @msg: virtchannel message + * + * Respond with success to not break normal VF flow. + * For legacy VF driver try to update cached MAC address. + */ +static int +ice_vc_repr_del_mac(struct ice_vf __always_unused *vf, u8 __always_unused *msg) +{ + struct virtchnl_ether_addr_list *al = + (struct virtchnl_ether_addr_list *)msg; + + ice_update_legacy_cached_mac(vf, &al->list[0]); + + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DEL_ETH_ADDR, + VIRTCHNL_STATUS_SUCCESS, NULL, 0); +} + +static int +ice_vc_repr_cfg_promiscuous_mode(struct ice_vf *vf, u8 __always_unused *msg) +{ + dev_dbg(ice_pf_to_dev(vf->pf), + "Can't config promiscuous mode in switchdev mode for VF %d\n", + vf->vf_id); + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE, + VIRTCHNL_STATUS_ERR_NOT_SUPPORTED, + NULL, 0); +} + +static const struct ice_virtchnl_ops ice_virtchnl_repr_ops = { + .get_ver_msg = ice_vc_get_ver_msg, + .get_vf_res_msg = ice_vc_get_vf_res_msg, + .reset_vf = ice_vc_reset_vf_msg, + .add_mac_addr_msg = ice_vc_repr_add_mac, + .del_mac_addr_msg = ice_vc_repr_del_mac, + .cfg_qs_msg = ice_vc_cfg_qs_msg, + .ena_qs_msg = ice_vc_ena_qs_msg, + .dis_qs_msg = ice_vc_dis_qs_msg, + .request_qs_msg = ice_vc_request_qs_msg, + .cfg_irq_map_msg = ice_vc_cfg_irq_map_msg, + .config_rss_key = ice_vc_config_rss_key, + .config_rss_lut = ice_vc_config_rss_lut, + .get_stats_msg = ice_vc_get_stats_msg, + .cfg_promiscuous_mode_msg = ice_vc_repr_cfg_promiscuous_mode, + .add_vlan_msg = ice_vc_add_vlan_msg, + .remove_vlan_msg = ice_vc_remove_vlan_msg, + .ena_vlan_stripping = ice_vc_ena_vlan_stripping, + .dis_vlan_stripping = ice_vc_dis_vlan_stripping, + .handle_rss_cfg_msg = ice_vc_handle_rss_cfg, + .add_fdir_fltr_msg = ice_vc_add_fdir_fltr, + .del_fdir_fltr_msg = ice_vc_del_fdir_fltr, + .get_offload_vlan_v2_caps = ice_vc_get_offload_vlan_v2_caps, + .add_vlan_v2_msg = ice_vc_add_vlan_v2_msg, + .remove_vlan_v2_msg = ice_vc_remove_vlan_v2_msg, + .ena_vlan_stripping_v2_msg = ice_vc_ena_vlan_stripping_v2_msg, + .dis_vlan_stripping_v2_msg = ice_vc_dis_vlan_stripping_v2_msg, + .ena_vlan_insertion_v2_msg = ice_vc_ena_vlan_insertion_v2_msg, + .dis_vlan_insertion_v2_msg = ice_vc_dis_vlan_insertion_v2_msg, +}; + +/** + * ice_virtchnl_set_repr_ops - Switch to representor virtchnl ops + * @vf: the VF to switch ops + */ +void ice_virtchnl_set_repr_ops(struct ice_vf *vf) +{ + vf->virtchnl_ops = &ice_virtchnl_repr_ops; +} + +/** + * ice_vc_process_vf_msg - Process request from VF + * @pf: pointer to the PF structure + * @event: pointer to the AQ event + * + * called from the common asq/arq handler to + * process request from VF + */ +void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) +{ + u32 v_opcode = le32_to_cpu(event->desc.cookie_high); + s16 vf_id = le16_to_cpu(event->desc.retval); + const struct ice_virtchnl_ops *ops; + u16 msglen = event->msg_len; + u8 *msg = event->msg_buf; + struct ice_vf *vf = NULL; + struct device *dev; + int err = 0; + + dev = ice_pf_to_dev(pf); + + vf = ice_get_vf_by_id(pf, vf_id); + if (!vf) { + dev_err(dev, "Unable to locate VF for message from VF ID %d, opcode %d, len %d\n", + vf_id, v_opcode, msglen); + return; + } + + mutex_lock(&vf->cfg_lock); + + /* Check if VF is disabled. */ + if (test_bit(ICE_VF_STATE_DIS, vf->vf_states)) { + err = -EPERM; + goto error_handler; + } + + ops = vf->virtchnl_ops; + + /* Perform basic checks on the msg */ + err = virtchnl_vc_validate_vf_msg(&vf->vf_ver, v_opcode, msg, msglen); + if (err) { + if (err == VIRTCHNL_STATUS_ERR_PARAM) + err = -EPERM; + else + err = -EINVAL; + } + +error_handler: + if (err) { + ice_vc_send_msg_to_vf(vf, v_opcode, VIRTCHNL_STATUS_ERR_PARAM, + NULL, 0); + dev_err(dev, "Invalid message from VF %d, opcode %d, len %d, error %d\n", + vf_id, v_opcode, msglen, err); + goto finish; + } + + if (!ice_vc_is_opcode_allowed(vf, v_opcode)) { + ice_vc_send_msg_to_vf(vf, v_opcode, + VIRTCHNL_STATUS_ERR_NOT_SUPPORTED, NULL, + 0); + goto finish; + } + + switch (v_opcode) { + case VIRTCHNL_OP_VERSION: + err = ops->get_ver_msg(vf, msg); + break; + case VIRTCHNL_OP_GET_VF_RESOURCES: + err = ops->get_vf_res_msg(vf, msg); + if (ice_vf_init_vlan_stripping(vf)) + dev_dbg(dev, "Failed to initialize VLAN stripping for VF %d\n", + vf->vf_id); + ice_vc_notify_vf_link_state(vf); + break; + case VIRTCHNL_OP_RESET_VF: + ops->reset_vf(vf); + break; + case VIRTCHNL_OP_ADD_ETH_ADDR: + err = ops->add_mac_addr_msg(vf, msg); + break; + case VIRTCHNL_OP_DEL_ETH_ADDR: + err = ops->del_mac_addr_msg(vf, msg); + break; + case VIRTCHNL_OP_CONFIG_VSI_QUEUES: + err = ops->cfg_qs_msg(vf, msg); + break; + case VIRTCHNL_OP_ENABLE_QUEUES: + err = ops->ena_qs_msg(vf, msg); + ice_vc_notify_vf_link_state(vf); + break; + case VIRTCHNL_OP_DISABLE_QUEUES: + err = ops->dis_qs_msg(vf, msg); + break; + case VIRTCHNL_OP_REQUEST_QUEUES: + err = ops->request_qs_msg(vf, msg); + break; + case VIRTCHNL_OP_CONFIG_IRQ_MAP: + err = ops->cfg_irq_map_msg(vf, msg); + break; + case VIRTCHNL_OP_CONFIG_RSS_KEY: + err = ops->config_rss_key(vf, msg); + break; + case VIRTCHNL_OP_CONFIG_RSS_LUT: + err = ops->config_rss_lut(vf, msg); + break; + case VIRTCHNL_OP_GET_STATS: + err = ops->get_stats_msg(vf, msg); + break; + case VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE: + err = ops->cfg_promiscuous_mode_msg(vf, msg); + break; + case VIRTCHNL_OP_ADD_VLAN: + err = ops->add_vlan_msg(vf, msg); + break; + case VIRTCHNL_OP_DEL_VLAN: + err = ops->remove_vlan_msg(vf, msg); + break; + case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING: + err = ops->ena_vlan_stripping(vf); + break; + case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING: + err = ops->dis_vlan_stripping(vf); + break; + case VIRTCHNL_OP_ADD_FDIR_FILTER: + err = ops->add_fdir_fltr_msg(vf, msg); + break; + case VIRTCHNL_OP_DEL_FDIR_FILTER: + err = ops->del_fdir_fltr_msg(vf, msg); + break; + case VIRTCHNL_OP_ADD_RSS_CFG: + err = ops->handle_rss_cfg_msg(vf, msg, true); + break; + case VIRTCHNL_OP_DEL_RSS_CFG: + err = ops->handle_rss_cfg_msg(vf, msg, false); + break; + case VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS: + err = ops->get_offload_vlan_v2_caps(vf); + break; + case VIRTCHNL_OP_ADD_VLAN_V2: + err = ops->add_vlan_v2_msg(vf, msg); + break; + case VIRTCHNL_OP_DEL_VLAN_V2: + err = ops->remove_vlan_v2_msg(vf, msg); + break; + case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2: + err = ops->ena_vlan_stripping_v2_msg(vf, msg); + break; + case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2: + err = ops->dis_vlan_stripping_v2_msg(vf, msg); + break; + case VIRTCHNL_OP_ENABLE_VLAN_INSERTION_V2: + err = ops->ena_vlan_insertion_v2_msg(vf, msg); + break; + case VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2: + err = ops->dis_vlan_insertion_v2_msg(vf, msg); + break; + case VIRTCHNL_OP_UNKNOWN: + default: + dev_err(dev, "Unsupported opcode %d from VF %d\n", v_opcode, + vf_id); + err = ice_vc_send_msg_to_vf(vf, v_opcode, + VIRTCHNL_STATUS_ERR_NOT_SUPPORTED, + NULL, 0); + break; + } + if (err) { + /* Helper function cares less about error return values here + * as it is busy with pending work. + */ + dev_info(dev, "PF failed to honor VF %d, opcode %d, error %d\n", + vf_id, v_opcode, err); + } + +finish: + mutex_unlock(&vf->cfg_lock); + ice_put_vf(vf); +} diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.h b/drivers/net/ethernet/intel/ice/ice_virtchnl.h new file mode 100644 index 000000000000..b5a3fd8adbb4 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2022, Intel Corporation. */ + +#ifndef _ICE_VIRTCHNL_H_ +#define _ICE_VIRTCHNL_H_ + +#include <linux/types.h> +#include <linux/bitops.h> +#include <linux/if_ether.h> +#include <linux/avf/virtchnl.h> +#include "ice_vf_lib.h" + +/* Restrict number of MAC Addr and VLAN that non-trusted VF can programmed */ +#define ICE_MAX_VLAN_PER_VF 8 + +/* MAC filters: 1 is reserved for the VF's default/perm_addr/LAA MAC, 1 for + * broadcast, and 16 for additional unicast/multicast filters + */ +#define ICE_MAX_MACADDR_PER_VF 18 + +struct ice_virtchnl_ops { + int (*get_ver_msg)(struct ice_vf *vf, u8 *msg); + int (*get_vf_res_msg)(struct ice_vf *vf, u8 *msg); + void (*reset_vf)(struct ice_vf *vf); + int (*add_mac_addr_msg)(struct ice_vf *vf, u8 *msg); + int (*del_mac_addr_msg)(struct ice_vf *vf, u8 *msg); + int (*cfg_qs_msg)(struct ice_vf *vf, u8 *msg); + int (*ena_qs_msg)(struct ice_vf *vf, u8 *msg); + int (*dis_qs_msg)(struct ice_vf *vf, u8 *msg); + int (*request_qs_msg)(struct ice_vf *vf, u8 *msg); + int (*cfg_irq_map_msg)(struct ice_vf *vf, u8 *msg); + int (*config_rss_key)(struct ice_vf *vf, u8 *msg); + int (*config_rss_lut)(struct ice_vf *vf, u8 *msg); + int (*get_stats_msg)(struct ice_vf *vf, u8 *msg); + int (*cfg_promiscuous_mode_msg)(struct ice_vf *vf, u8 *msg); + int (*add_vlan_msg)(struct ice_vf *vf, u8 *msg); + int (*remove_vlan_msg)(struct ice_vf *vf, u8 *msg); + int (*ena_vlan_stripping)(struct ice_vf *vf); + int (*dis_vlan_stripping)(struct ice_vf *vf); + int (*handle_rss_cfg_msg)(struct ice_vf *vf, u8 *msg, bool add); + int (*add_fdir_fltr_msg)(struct ice_vf *vf, u8 *msg); + int (*del_fdir_fltr_msg)(struct ice_vf *vf, u8 *msg); + int (*get_offload_vlan_v2_caps)(struct ice_vf *vf); + int (*add_vlan_v2_msg)(struct ice_vf *vf, u8 *msg); + int (*remove_vlan_v2_msg)(struct ice_vf *vf, u8 *msg); + int (*ena_vlan_stripping_v2_msg)(struct ice_vf *vf, u8 *msg); + int (*dis_vlan_stripping_v2_msg)(struct ice_vf *vf, u8 *msg); + int (*ena_vlan_insertion_v2_msg)(struct ice_vf *vf, u8 *msg); + int (*dis_vlan_insertion_v2_msg)(struct ice_vf *vf, u8 *msg); +}; + +#ifdef CONFIG_PCI_IOV +void ice_virtchnl_set_dflt_ops(struct ice_vf *vf); +void ice_virtchnl_set_repr_ops(struct ice_vf *vf); +void ice_vc_notify_vf_link_state(struct ice_vf *vf); +void ice_vc_notify_link_state(struct ice_pf *pf); +void ice_vc_notify_reset(struct ice_pf *pf); +int +ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode, + enum virtchnl_status_code v_retval, u8 *msg, u16 msglen); +bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id); +#else /* CONFIG_PCI_IOV */ +static inline void ice_virtchnl_set_dflt_ops(struct ice_vf *vf) { } +static inline void ice_virtchnl_set_repr_ops(struct ice_vf *vf) { } +static inline void ice_vc_notify_vf_link_state(struct ice_vf *vf) { } +static inline void ice_vc_notify_link_state(struct ice_pf *pf) { } +static inline void ice_vc_notify_reset(struct ice_pf *pf) { } + +static inline int +ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode, + enum virtchnl_status_code v_retval, u8 *msg, u16 msglen) +{ + return -EOPNOTSUPP; +} + +static inline bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id) +{ + return false; +} +#endif /* !CONFIG_PCI_IOV */ + +#endif /* _ICE_VIRTCHNL_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c index 9feebe5f556c..5a82216e7d03 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c @@ -55,6 +55,15 @@ static const u32 vlan_allowlist_opcodes[] = { VIRTCHNL_OP_ENABLE_VLAN_STRIPPING, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING, }; +/* VIRTCHNL_VF_OFFLOAD_VLAN_V2 */ +static const u32 vlan_v2_allowlist_opcodes[] = { + VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS, VIRTCHNL_OP_ADD_VLAN_V2, + VIRTCHNL_OP_DEL_VLAN_V2, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2, + VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2, + VIRTCHNL_OP_ENABLE_VLAN_INSERTION_V2, + VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2, +}; + /* VIRTCHNL_VF_OFFLOAD_RSS_PF */ static const u32 rss_pf_allowlist_opcodes[] = { VIRTCHNL_OP_CONFIG_RSS_KEY, VIRTCHNL_OP_CONFIG_RSS_LUT, @@ -89,6 +98,7 @@ static const struct allowlist_opcode_info allowlist_opcodes[] = { ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_RSS_PF, rss_pf_allowlist_opcodes), ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF, adv_rss_pf_allowlist_opcodes), ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_FDIR_PF, fdir_pf_allowlist_opcodes), + ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_VLAN_V2, vlan_v2_allowlist_opcodes), }; /** diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c index d64df81d4893..c6a58343d81d 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c @@ -5,6 +5,7 @@ #include "ice_base.h" #include "ice_lib.h" #include "ice_flow.h" +#include "ice_vf_lib_private.h" #define to_fltr_conf_from_desc(p) \ container_of(p, struct virtchnl_fdir_fltr_conf, input) @@ -1288,15 +1289,16 @@ ice_vc_fdir_irq_handler(struct ice_vsi *ctrl_vsi, union ice_32b_rx_flex_desc *rx_desc) { struct ice_pf *pf = ctrl_vsi->back; + struct ice_vf *vf = ctrl_vsi->vf; struct ice_vf_fdir_ctx *ctx_done; struct ice_vf_fdir_ctx *ctx_irq; struct ice_vf_fdir *fdir; unsigned long flags; struct device *dev; - struct ice_vf *vf; int ret; - vf = &pf->vf[ctrl_vsi->vf_id]; + if (WARN_ON(!vf)) + return; fdir = &vf->fdir; ctx_done = &fdir->ctx_done; @@ -1342,12 +1344,17 @@ static void ice_vf_fdir_dump_info(struct ice_vf *vf) pf = vf->pf; hw = &pf->hw; dev = ice_pf_to_dev(pf); - vf_vsi = pf->vsi[vf->lan_vsi_idx]; + vf_vsi = ice_get_vf_vsi(vf); + if (!vf_vsi) { + dev_dbg(dev, "VF %d: invalid VSI pointer\n", vf->vf_id); + return; + } + vsi_num = ice_get_hw_vsi_num(hw, vf_vsi->idx); 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", + 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, @@ -1571,15 +1578,16 @@ err_exit: */ void ice_flush_fdir_ctx(struct ice_pf *pf) { - int i; + struct ice_vf *vf; + unsigned int bkt; if (!test_and_clear_bit(ICE_FD_VF_FLUSH_CTX, pf->state)) return; - ice_for_each_vf(pf, i) { + mutex_lock(&pf->vfs.table_lock); + ice_for_each_vf(pf, bkt, vf) { struct device *dev = ice_pf_to_dev(pf); enum virtchnl_fdir_prgm_status status; - struct ice_vf *vf = &pf->vf[i]; struct ice_vf_fdir_ctx *ctx; unsigned long flags; int ret; @@ -1633,6 +1641,7 @@ err_exit: ctx->flags &= ~ICE_VF_FDIR_CTX_VALID; spin_unlock_irqrestore(&vf->fdir.ctx_lock, flags); } + mutex_unlock(&pf->vfs.table_lock); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.h index f4e629f4c09b..c5bcc8d7481c 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.h @@ -6,6 +6,7 @@ struct ice_vf; struct ice_pf; +struct ice_vsi; enum ice_fdir_ctx_stat { ICE_FDIR_CTX_READY, diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c deleted file mode 100644 index 39b80124d282..000000000000 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ /dev/null @@ -1,5317 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Copyright (c) 2018, Intel Corporation. */ - -#include "ice.h" -#include "ice_base.h" -#include "ice_lib.h" -#include "ice_fltr.h" -#include "ice_dcb_lib.h" -#include "ice_flow.h" -#include "ice_eswitch.h" -#include "ice_virtchnl_allowlist.h" -#include "ice_flex_pipe.h" - -#define FIELD_SELECTOR(proto_hdr_field) \ - BIT((proto_hdr_field) & PROTO_HDR_FIELD_MASK) - -struct ice_vc_hdr_match_type { - u32 vc_hdr; /* virtchnl headers (VIRTCHNL_PROTO_HDR_XXX) */ - u32 ice_hdr; /* ice headers (ICE_FLOW_SEG_HDR_XXX) */ -}; - -static const struct ice_vc_hdr_match_type ice_vc_hdr_list[] = { - {VIRTCHNL_PROTO_HDR_NONE, ICE_FLOW_SEG_HDR_NONE}, - {VIRTCHNL_PROTO_HDR_ETH, ICE_FLOW_SEG_HDR_ETH}, - {VIRTCHNL_PROTO_HDR_S_VLAN, ICE_FLOW_SEG_HDR_VLAN}, - {VIRTCHNL_PROTO_HDR_C_VLAN, ICE_FLOW_SEG_HDR_VLAN}, - {VIRTCHNL_PROTO_HDR_IPV4, ICE_FLOW_SEG_HDR_IPV4 | - ICE_FLOW_SEG_HDR_IPV_OTHER}, - {VIRTCHNL_PROTO_HDR_IPV6, ICE_FLOW_SEG_HDR_IPV6 | - ICE_FLOW_SEG_HDR_IPV_OTHER}, - {VIRTCHNL_PROTO_HDR_TCP, ICE_FLOW_SEG_HDR_TCP}, - {VIRTCHNL_PROTO_HDR_UDP, ICE_FLOW_SEG_HDR_UDP}, - {VIRTCHNL_PROTO_HDR_SCTP, ICE_FLOW_SEG_HDR_SCTP}, - {VIRTCHNL_PROTO_HDR_PPPOE, ICE_FLOW_SEG_HDR_PPPOE}, - {VIRTCHNL_PROTO_HDR_GTPU_IP, ICE_FLOW_SEG_HDR_GTPU_IP}, - {VIRTCHNL_PROTO_HDR_GTPU_EH, ICE_FLOW_SEG_HDR_GTPU_EH}, - {VIRTCHNL_PROTO_HDR_GTPU_EH_PDU_DWN, - ICE_FLOW_SEG_HDR_GTPU_DWN}, - {VIRTCHNL_PROTO_HDR_GTPU_EH_PDU_UP, - ICE_FLOW_SEG_HDR_GTPU_UP}, - {VIRTCHNL_PROTO_HDR_L2TPV3, ICE_FLOW_SEG_HDR_L2TPV3}, - {VIRTCHNL_PROTO_HDR_ESP, ICE_FLOW_SEG_HDR_ESP}, - {VIRTCHNL_PROTO_HDR_AH, ICE_FLOW_SEG_HDR_AH}, - {VIRTCHNL_PROTO_HDR_PFCP, ICE_FLOW_SEG_HDR_PFCP_SESSION}, -}; - -struct ice_vc_hash_field_match_type { - u32 vc_hdr; /* virtchnl headers - * (VIRTCHNL_PROTO_HDR_XXX) - */ - u32 vc_hash_field; /* virtchnl hash fields selector - * FIELD_SELECTOR((VIRTCHNL_PROTO_HDR_ETH_XXX)) - */ - u64 ice_hash_field; /* ice hash fields - * (BIT_ULL(ICE_FLOW_FIELD_IDX_XXX)) - */ -}; - -static const struct -ice_vc_hash_field_match_type ice_vc_hash_field_list[] = { - {VIRTCHNL_PROTO_HDR_ETH, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ETH_SRC), - BIT_ULL(ICE_FLOW_FIELD_IDX_ETH_SA)}, - {VIRTCHNL_PROTO_HDR_ETH, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ETH_DST), - BIT_ULL(ICE_FLOW_FIELD_IDX_ETH_DA)}, - {VIRTCHNL_PROTO_HDR_ETH, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ETH_SRC) | - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ETH_DST), - ICE_FLOW_HASH_ETH}, - {VIRTCHNL_PROTO_HDR_ETH, - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ETH_ETHERTYPE), - BIT_ULL(ICE_FLOW_FIELD_IDX_ETH_TYPE)}, - {VIRTCHNL_PROTO_HDR_S_VLAN, - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_S_VLAN_ID), - BIT_ULL(ICE_FLOW_FIELD_IDX_S_VLAN)}, - {VIRTCHNL_PROTO_HDR_C_VLAN, - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_C_VLAN_ID), - BIT_ULL(ICE_FLOW_FIELD_IDX_C_VLAN)}, - {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC), - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA)}, - {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST), - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA)}, - {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) | - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST), - ICE_FLOW_HASH_IPV4}, - {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) | - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT), - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA) | - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)}, - {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) | - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT), - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA) | - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)}, - {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) | - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) | - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT), - ICE_FLOW_HASH_IPV4 | BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)}, - {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT), - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)}, - {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC), - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_SA)}, - {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST), - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_DA)}, - {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC) | - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST), - ICE_FLOW_HASH_IPV6}, - {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC) | - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT), - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_SA) | - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)}, - {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST) | - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT), - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_DA) | - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)}, - {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC) | - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST) | - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT), - ICE_FLOW_HASH_IPV6 | BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)}, - {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT), - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)}, - {VIRTCHNL_PROTO_HDR_TCP, - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_SRC_PORT), - BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_SRC_PORT)}, - {VIRTCHNL_PROTO_HDR_TCP, - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_DST_PORT), - BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_DST_PORT)}, - {VIRTCHNL_PROTO_HDR_TCP, - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_SRC_PORT) | - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_DST_PORT), - ICE_FLOW_HASH_TCP_PORT}, - {VIRTCHNL_PROTO_HDR_UDP, - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_SRC_PORT), - BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_SRC_PORT)}, - {VIRTCHNL_PROTO_HDR_UDP, - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_DST_PORT), - BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_DST_PORT)}, - {VIRTCHNL_PROTO_HDR_UDP, - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_SRC_PORT) | - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_DST_PORT), - ICE_FLOW_HASH_UDP_PORT}, - {VIRTCHNL_PROTO_HDR_SCTP, - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_SRC_PORT), - BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT)}, - {VIRTCHNL_PROTO_HDR_SCTP, - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_DST_PORT), - BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_DST_PORT)}, - {VIRTCHNL_PROTO_HDR_SCTP, - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_SRC_PORT) | - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_DST_PORT), - ICE_FLOW_HASH_SCTP_PORT}, - {VIRTCHNL_PROTO_HDR_PPPOE, - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_PPPOE_SESS_ID), - BIT_ULL(ICE_FLOW_FIELD_IDX_PPPOE_SESS_ID)}, - {VIRTCHNL_PROTO_HDR_GTPU_IP, - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_GTPU_IP_TEID), - BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_IP_TEID)}, - {VIRTCHNL_PROTO_HDR_L2TPV3, - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_L2TPV3_SESS_ID), - BIT_ULL(ICE_FLOW_FIELD_IDX_L2TPV3_SESS_ID)}, - {VIRTCHNL_PROTO_HDR_ESP, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ESP_SPI), - BIT_ULL(ICE_FLOW_FIELD_IDX_ESP_SPI)}, - {VIRTCHNL_PROTO_HDR_AH, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_AH_SPI), - BIT_ULL(ICE_FLOW_FIELD_IDX_AH_SPI)}, - {VIRTCHNL_PROTO_HDR_PFCP, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_PFCP_SEID), - BIT_ULL(ICE_FLOW_FIELD_IDX_PFCP_SEID)}, -}; - -/** - * ice_get_vf_vsi - get VF's VSI based on the stored index - * @vf: VF used to get VSI - */ -struct ice_vsi *ice_get_vf_vsi(struct ice_vf *vf) -{ - return vf->pf->vsi[vf->lan_vsi_idx]; -} - -/** - * ice_validate_vf_id - helper to check if VF ID is valid - * @pf: pointer to the PF structure - * @vf_id: the ID of the VF to check - */ -static int ice_validate_vf_id(struct ice_pf *pf, u16 vf_id) -{ - /* vf_id range is only valid for 0-255, and should always be unsigned */ - if (vf_id >= pf->num_alloc_vfs) { - dev_err(ice_pf_to_dev(pf), "Invalid VF ID: %u\n", vf_id); - return -EINVAL; - } - return 0; -} - -/** - * ice_check_vf_init - helper to check if VF init complete - * @pf: pointer to the PF structure - * @vf: the pointer to the VF to check - */ -static int ice_check_vf_init(struct ice_pf *pf, struct ice_vf *vf) -{ - if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { - dev_err(ice_pf_to_dev(pf), "VF ID: %u in reset. Try again.\n", - vf->vf_id); - return -EBUSY; - } - return 0; -} - -/** - * ice_vc_vf_broadcast - Broadcast a message to all VFs on PF - * @pf: pointer to the PF structure - * @v_opcode: operation code - * @v_retval: return value - * @msg: pointer to the msg buffer - * @msglen: msg length - */ -static void -ice_vc_vf_broadcast(struct ice_pf *pf, enum virtchnl_ops v_opcode, - enum virtchnl_status_code v_retval, u8 *msg, u16 msglen) -{ - struct ice_hw *hw = &pf->hw; - unsigned int i; - - ice_for_each_vf(pf, i) { - struct ice_vf *vf = &pf->vf[i]; - - /* Not all vfs are enabled so skip the ones that are not */ - if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states) && - !test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) - continue; - - /* Ignore return value on purpose - a given VF may fail, but - * we need to keep going and send to all of them - */ - ice_aq_send_msg_to_vf(hw, vf->vf_id, v_opcode, v_retval, msg, - msglen, NULL); - } -} - -/** - * ice_set_pfe_link - Set the link speed/status of the virtchnl_pf_event - * @vf: pointer to the VF structure - * @pfe: pointer to the virtchnl_pf_event to set link speed/status for - * @ice_link_speed: link speed specified by ICE_AQ_LINK_SPEED_* - * @link_up: whether or not to set the link up/down - */ -static void -ice_set_pfe_link(struct ice_vf *vf, struct virtchnl_pf_event *pfe, - int ice_link_speed, bool link_up) -{ - if (vf->driver_caps & VIRTCHNL_VF_CAP_ADV_LINK_SPEED) { - pfe->event_data.link_event_adv.link_status = link_up; - /* Speed in Mbps */ - pfe->event_data.link_event_adv.link_speed = - ice_conv_link_speed_to_virtchnl(true, ice_link_speed); - } else { - pfe->event_data.link_event.link_status = link_up; - /* Legacy method for virtchnl link speeds */ - pfe->event_data.link_event.link_speed = - (enum virtchnl_link_speed) - ice_conv_link_speed_to_virtchnl(false, ice_link_speed); - } -} - -/** - * ice_vf_has_no_qs_ena - check if the VF has any Rx or Tx queues enabled - * @vf: the VF to check - * - * Returns true if the VF has no Rx and no Tx queues enabled and returns false - * otherwise - */ -static bool ice_vf_has_no_qs_ena(struct ice_vf *vf) -{ - return (!bitmap_weight(vf->rxq_ena, ICE_MAX_RSS_QS_PER_VF) && - !bitmap_weight(vf->txq_ena, ICE_MAX_RSS_QS_PER_VF)); -} - -/** - * ice_is_vf_link_up - check if the VF's link is up - * @vf: VF to check if link is up - */ -static bool ice_is_vf_link_up(struct ice_vf *vf) -{ - struct ice_pf *pf = vf->pf; - - if (ice_check_vf_init(pf, vf)) - return false; - - if (ice_vf_has_no_qs_ena(vf)) - return false; - else if (vf->link_forced) - return vf->link_up; - else - return pf->hw.port_info->phy.link_info.link_info & - ICE_AQ_LINK_UP; -} - -/** - * ice_vc_notify_vf_link_state - Inform a VF of link status - * @vf: pointer to the VF structure - * - * send a link status message to a single VF - */ -void ice_vc_notify_vf_link_state(struct ice_vf *vf) -{ - struct virtchnl_pf_event pfe = { 0 }; - struct ice_hw *hw = &vf->pf->hw; - - pfe.event = VIRTCHNL_EVENT_LINK_CHANGE; - pfe.severity = PF_EVENT_SEVERITY_INFO; - - if (ice_is_vf_link_up(vf)) - ice_set_pfe_link(vf, &pfe, - hw->port_info->phy.link_info.link_speed, true); - else - ice_set_pfe_link(vf, &pfe, ICE_AQ_LINK_SPEED_UNKNOWN, false); - - ice_aq_send_msg_to_vf(hw, vf->vf_id, VIRTCHNL_OP_EVENT, - VIRTCHNL_STATUS_SUCCESS, (u8 *)&pfe, - sizeof(pfe), NULL); -} - -/** - * ice_vf_invalidate_vsi - invalidate vsi_idx/vsi_num to remove VSI access - * @vf: VF to remove access to VSI for - */ -static void ice_vf_invalidate_vsi(struct ice_vf *vf) -{ - vf->lan_vsi_idx = ICE_NO_VSI; - vf->lan_vsi_num = ICE_NO_VSI; -} - -/** - * ice_vf_vsi_release - invalidate the VF's VSI after freeing it - * @vf: invalidate this VF's VSI after freeing it - */ -static void ice_vf_vsi_release(struct ice_vf *vf) -{ - ice_vsi_release(ice_get_vf_vsi(vf)); - ice_vf_invalidate_vsi(vf); -} - -/** - * ice_vf_ctrl_invalidate_vsi - invalidate ctrl_vsi_idx to remove VSI access - * @vf: VF that control VSI is being invalidated on - */ -static void ice_vf_ctrl_invalidate_vsi(struct ice_vf *vf) -{ - vf->ctrl_vsi_idx = ICE_NO_VSI; -} - -/** - * ice_vf_ctrl_vsi_release - invalidate the VF's control VSI after freeing it - * @vf: VF that control VSI is being released on - */ -static void ice_vf_ctrl_vsi_release(struct ice_vf *vf) -{ - ice_vsi_release(vf->pf->vsi[vf->ctrl_vsi_idx]); - ice_vf_ctrl_invalidate_vsi(vf); -} - -/** - * ice_free_vf_res - Free a VF's resources - * @vf: pointer to the VF info - */ -static void ice_free_vf_res(struct ice_vf *vf) -{ - struct ice_pf *pf = vf->pf; - int i, last_vector_idx; - - /* First, disable VF's configuration API to prevent OS from - * accessing the VF's VSI after it's freed or invalidated. - */ - clear_bit(ICE_VF_STATE_INIT, vf->vf_states); - ice_vf_fdir_exit(vf); - /* free VF control VSI */ - if (vf->ctrl_vsi_idx != ICE_NO_VSI) - ice_vf_ctrl_vsi_release(vf); - - /* free VSI and disconnect it from the parent uplink */ - if (vf->lan_vsi_idx != ICE_NO_VSI) { - ice_vf_vsi_release(vf); - vf->num_mac = 0; - } - - last_vector_idx = vf->first_vector_idx + pf->num_msix_per_vf - 1; - - /* clear VF MDD event information */ - memset(&vf->mdd_tx_events, 0, sizeof(vf->mdd_tx_events)); - memset(&vf->mdd_rx_events, 0, sizeof(vf->mdd_rx_events)); - - /* Disable interrupts so that VF starts in a known state */ - for (i = vf->first_vector_idx; i <= last_vector_idx; i++) { - wr32(&pf->hw, GLINT_DYN_CTL(i), GLINT_DYN_CTL_CLEARPBA_M); - ice_flush(&pf->hw); - } - /* reset some of the state variables keeping track of the resources */ - clear_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states); - clear_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states); -} - -/** - * ice_dis_vf_mappings - * @vf: pointer to the VF structure - */ -static void ice_dis_vf_mappings(struct ice_vf *vf) -{ - struct ice_pf *pf = vf->pf; - struct ice_vsi *vsi; - struct device *dev; - int first, last, v; - struct ice_hw *hw; - - hw = &pf->hw; - vsi = ice_get_vf_vsi(vf); - - dev = ice_pf_to_dev(pf); - wr32(hw, VPINT_ALLOC(vf->vf_id), 0); - wr32(hw, VPINT_ALLOC_PCI(vf->vf_id), 0); - - first = vf->first_vector_idx; - last = first + pf->num_msix_per_vf - 1; - for (v = first; v <= last; v++) { - u32 reg; - - reg = (((1 << GLINT_VECT2FUNC_IS_PF_S) & - GLINT_VECT2FUNC_IS_PF_M) | - ((hw->pf_id << GLINT_VECT2FUNC_PF_NUM_S) & - GLINT_VECT2FUNC_PF_NUM_M)); - wr32(hw, GLINT_VECT2FUNC(v), reg); - } - - if (vsi->tx_mapping_mode == ICE_VSI_MAP_CONTIG) - wr32(hw, VPLAN_TX_QBASE(vf->vf_id), 0); - else - dev_err(dev, "Scattered mode for VF Tx queues is not yet implemented\n"); - - if (vsi->rx_mapping_mode == ICE_VSI_MAP_CONTIG) - wr32(hw, VPLAN_RX_QBASE(vf->vf_id), 0); - else - dev_err(dev, "Scattered mode for VF Rx queues is not yet implemented\n"); -} - -/** - * ice_sriov_free_msix_res - Reset/free any used MSIX resources - * @pf: pointer to the PF structure - * - * Since no MSIX entries are taken from the pf->irq_tracker then just clear - * the pf->sriov_base_vector. - * - * Returns 0 on success, and -EINVAL on error. - */ -static int ice_sriov_free_msix_res(struct ice_pf *pf) -{ - struct ice_res_tracker *res; - - if (!pf) - return -EINVAL; - - res = pf->irq_tracker; - if (!res) - return -EINVAL; - - /* give back irq_tracker resources used */ - WARN_ON(pf->sriov_base_vector < res->num_entries); - - pf->sriov_base_vector = 0; - - return 0; -} - -/** - * ice_set_vf_state_qs_dis - Set VF queues state to disabled - * @vf: pointer to the VF structure - */ -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_dis_vf_qs - Disable the VF queues - * @vf: pointer to the VF structure - */ -static void ice_dis_vf_qs(struct ice_vf *vf) -{ - struct ice_vsi *vsi = ice_get_vf_vsi(vf); - - ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, vf->vf_id); - ice_vsi_stop_all_rx_rings(vsi); - ice_set_vf_state_qs_dis(vf); -} - -/** - * ice_free_vfs - Free all VFs - * @pf: pointer to the PF structure - */ -void ice_free_vfs(struct ice_pf *pf) -{ - struct device *dev = ice_pf_to_dev(pf); - struct ice_hw *hw = &pf->hw; - unsigned int tmp, i; - - set_bit(ICE_VF_DEINIT_IN_PROGRESS, pf->state); - - if (!pf->vf) - return; - - ice_eswitch_release(pf); - - while (test_and_set_bit(ICE_VF_DIS, pf->state)) - usleep_range(1000, 2000); - - /* Disable IOV before freeing resources. This lets any VF drivers - * running in the host get themselves cleaned up before we yank - * the carpet out from underneath their feet. - */ - if (!pci_vfs_assigned(pf->pdev)) - pci_disable_sriov(pf->pdev); - else - dev_warn(dev, "VFs are assigned - not disabling SR-IOV\n"); - - /* Avoid wait time by stopping all VFs at the same time */ - ice_for_each_vf(pf, i) - ice_dis_vf_qs(&pf->vf[i]); - - tmp = pf->num_alloc_vfs; - pf->num_qps_per_vf = 0; - pf->num_alloc_vfs = 0; - for (i = 0; i < tmp; i++) { - if (test_bit(ICE_VF_STATE_INIT, pf->vf[i].vf_states)) { - /* disable VF qp mappings and set VF disable state */ - ice_dis_vf_mappings(&pf->vf[i]); - set_bit(ICE_VF_STATE_DIS, pf->vf[i].vf_states); - ice_free_vf_res(&pf->vf[i]); - } - - mutex_destroy(&pf->vf[i].cfg_lock); - } - - if (ice_sriov_free_msix_res(pf)) - dev_err(dev, "Failed to free MSIX resources used by SR-IOV\n"); - - devm_kfree(dev, pf->vf); - pf->vf = NULL; - - /* This check is for when the driver is unloaded while VFs are - * assigned. Setting the number of VFs to 0 through sysfs is caught - * before this function ever gets called. - */ - if (!pci_vfs_assigned(pf->pdev)) { - unsigned int vf_id; - - /* Acknowledge VFLR for all VFs. Without this, VFs will fail to - * work correctly when SR-IOV gets re-enabled. - */ - for (vf_id = 0; vf_id < tmp; vf_id++) { - u32 reg_idx, bit_idx; - - reg_idx = (hw->func_caps.vf_base_id + vf_id) / 32; - bit_idx = (hw->func_caps.vf_base_id + vf_id) % 32; - wr32(hw, GLGEN_VFLRSTAT(reg_idx), BIT(bit_idx)); - } - } - - /* clear malicious info if the VFs are getting released */ - for (i = 0; i < tmp; i++) - if (ice_mbx_clear_malvf(&hw->mbx_snapshot, pf->malvfs, - ICE_MAX_VF_COUNT, i)) - dev_dbg(dev, "failed to clear malicious VF state for VF %u\n", - i); - - clear_bit(ICE_VF_DIS, pf->state); - clear_bit(ICE_VF_DEINIT_IN_PROGRESS, pf->state); - clear_bit(ICE_FLAG_SRIOV_ENA, pf->flags); -} - -/** - * ice_trigger_vf_reset - Reset a VF on HW - * @vf: pointer to the VF structure - * @is_vflr: true if VFLR was issued, false if not - * @is_pfr: true if the reset was triggered due to a previous PFR - * - * Trigger hardware to start a reset for a particular VF. Expects the caller - * to wait the proper amount of time to allow hardware to reset the VF before - * it cleans up and restores VF functionality. - */ -static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr, bool is_pfr) -{ - struct ice_pf *pf = vf->pf; - u32 reg, reg_idx, bit_idx; - unsigned int vf_abs_id, i; - struct device *dev; - struct ice_hw *hw; - - dev = ice_pf_to_dev(pf); - hw = &pf->hw; - vf_abs_id = vf->vf_id + hw->func_caps.vf_base_id; - - /* Inform VF that it is no longer active, as a warning */ - clear_bit(ICE_VF_STATE_ACTIVE, vf->vf_states); - - /* Disable VF's configuration API during reset. The flag is re-enabled - * when it's safe again to access VF's VSI. - */ - clear_bit(ICE_VF_STATE_INIT, vf->vf_states); - - /* VF_MBX_ARQLEN and VF_MBX_ATQLEN are cleared by PFR, so the driver - * needs to clear them in the case of VFR/VFLR. If this is done for - * PFR, it can mess up VF resets because the VF driver may already - * have started cleanup by the time we get here. - */ - if (!is_pfr) { - wr32(hw, VF_MBX_ARQLEN(vf->vf_id), 0); - wr32(hw, VF_MBX_ATQLEN(vf->vf_id), 0); - } - - /* In the case of a VFLR, the HW has already reset the VF and we - * just need to clean up, so don't hit the VFRTRIG register. - */ - if (!is_vflr) { - /* reset VF using VPGEN_VFRTRIG reg */ - reg = rd32(hw, VPGEN_VFRTRIG(vf->vf_id)); - reg |= VPGEN_VFRTRIG_VFSWR_M; - wr32(hw, VPGEN_VFRTRIG(vf->vf_id), reg); - } - /* clear the VFLR bit in GLGEN_VFLRSTAT */ - reg_idx = (vf_abs_id) / 32; - bit_idx = (vf_abs_id) % 32; - wr32(hw, GLGEN_VFLRSTAT(reg_idx), BIT(bit_idx)); - ice_flush(hw); - - wr32(hw, PF_PCI_CIAA, - VF_DEVICE_STATUS | (vf_abs_id << PF_PCI_CIAA_VF_NUM_S)); - for (i = 0; i < ICE_PCI_CIAD_WAIT_COUNT; i++) { - reg = rd32(hw, PF_PCI_CIAD); - /* no transactions pending so stop polling */ - if ((reg & VF_TRANS_PENDING_M) == 0) - break; - - dev_err(dev, "VF %u PCI transactions stuck\n", vf->vf_id); - udelay(ICE_PCI_CIAD_WAIT_DELAY_US); - } -} - -/** - * ice_vsi_manage_pvid - Enable or disable port VLAN for VSI - * @vsi: the VSI to update - * @pvid_info: VLAN ID and QoS used to set the PVID VSI context field - * @enable: true for enable PVID false for disable - */ -static int ice_vsi_manage_pvid(struct ice_vsi *vsi, u16 pvid_info, bool enable) -{ - 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; - - ctxt->info = vsi->info; - info = &ctxt->info; - if (enable) { - info->vlan_flags = ICE_AQ_VSI_VLAN_MODE_UNTAGGED | - ICE_AQ_VSI_PVLAN_INSERT_PVID | - ICE_AQ_VSI_VLAN_EMOD_STR; - info->sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; - } else { - info->vlan_flags = ICE_AQ_VSI_VLAN_EMOD_NOTHING | - ICE_AQ_VSI_VLAN_MODE_ALL; - info->sw_flags2 &= ~ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; - } - - info->pvid = cpu_to_le16(pvid_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_info(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)); - goto out; - } - - vsi->info.vlan_flags = info->vlan_flags; - vsi->info.sw_flags2 = info->sw_flags2; - vsi->info.pvid = info->pvid; -out: - kfree(ctxt); - return ret; -} - -/** - * ice_vf_get_port_info - Get the VF's port info structure - * @vf: VF used to get the port info structure for - */ -static struct ice_port_info *ice_vf_get_port_info(struct ice_vf *vf) -{ - return vf->pf->hw.port_info; -} - -/** - * ice_vf_vsi_setup - Set up a VF VSI - * @vf: VF to setup VSI for - * - * Returns pointer to the successfully allocated VSI struct on success, - * otherwise returns NULL on failure. - */ -static struct ice_vsi *ice_vf_vsi_setup(struct ice_vf *vf) -{ - struct ice_port_info *pi = ice_vf_get_port_info(vf); - struct ice_pf *pf = vf->pf; - struct ice_vsi *vsi; - - vsi = ice_vsi_setup(pf, pi, ICE_VSI_VF, vf->vf_id, NULL); - - if (!vsi) { - dev_err(ice_pf_to_dev(pf), "Failed to create VF VSI\n"); - ice_vf_invalidate_vsi(vf); - return NULL; - } - - vf->lan_vsi_idx = vsi->idx; - vf->lan_vsi_num = vsi->vsi_num; - - return vsi; -} - -/** - * ice_vf_ctrl_vsi_setup - Set up a VF control VSI - * @vf: VF to setup control VSI for - * - * Returns pointer to the successfully allocated VSI struct on success, - * otherwise returns NULL on failure. - */ -struct ice_vsi *ice_vf_ctrl_vsi_setup(struct ice_vf *vf) -{ - struct ice_port_info *pi = ice_vf_get_port_info(vf); - struct ice_pf *pf = vf->pf; - struct ice_vsi *vsi; - - vsi = ice_vsi_setup(pf, pi, ICE_VSI_CTRL, vf->vf_id, NULL); - if (!vsi) { - dev_err(ice_pf_to_dev(pf), "Failed to create VF control VSI\n"); - ice_vf_ctrl_invalidate_vsi(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->num_msix_per_vf; -} - -/** - * 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 (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_host_vlan_cfg - add VLAN 0 filter or rebuild the Port VLAN - * @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 either a VLAN 0 or port VLAN based filter after reset. - */ -static int ice_vf_rebuild_host_vlan_cfg(struct ice_vf *vf) -{ - struct device *dev = ice_pf_to_dev(vf->pf); - struct ice_vsi *vsi = ice_get_vf_vsi(vf); - u16 vlan_id = 0; - int err; - - if (vf->port_vlan_info) { - err = ice_vsi_manage_pvid(vsi, vf->port_vlan_info, true); - 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; - } - - vlan_id = vf->port_vlan_info & VLAN_VID_MASK; - } - - /* vlan_id will either be 0 or the port VLAN number */ - err = ice_vsi_add_vlan(vsi, vlan_id, ICE_FWD_TO_VSI); - if (err) { - dev_err(dev, "failed to add %s VLAN %u filter for VF %u, error %d\n", - vf->port_vlan_info ? "port" : "", vlan_id, vf->vf_id, - err); - return err; - } - - return 0; -} - -/** - * 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 (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.addr)) { - status = ice_fltr_add_mac(vsi, vf->hw_lan_addr.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.addr[0], vf->vf_id, - status); - return status; - } - vf->num_mac++; - - ether_addr_copy(vf->dev_lan_addr.addr, vf->hw_lan_addr.addr); - } - - 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) -{ - 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_ena_vf_msix_mappings - enable VF MSIX mappings in hardware - * @vf: VF to enable MSIX mappings for - * - * Some of the registers need to be indexed/configured using hardware global - * device values and other registers need 0-based values, which represent PF - * based values. - */ -static void ice_ena_vf_msix_mappings(struct ice_vf *vf) -{ - int device_based_first_msix, device_based_last_msix; - int pf_based_first_msix, pf_based_last_msix, v; - struct ice_pf *pf = vf->pf; - int device_based_vf_id; - struct ice_hw *hw; - u32 reg; - - hw = &pf->hw; - pf_based_first_msix = vf->first_vector_idx; - pf_based_last_msix = (pf_based_first_msix + pf->num_msix_per_vf) - 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->num_msix_per_vf) - 1; - device_based_vf_id = vf->vf_id + hw->func_caps.vf_base_id; - - reg = (((device_based_first_msix << VPINT_ALLOC_FIRST_S) & - VPINT_ALLOC_FIRST_M) | - ((device_based_last_msix << VPINT_ALLOC_LAST_S) & - VPINT_ALLOC_LAST_M) | VPINT_ALLOC_VALID_M); - wr32(hw, VPINT_ALLOC(vf->vf_id), reg); - - reg = (((device_based_first_msix << VPINT_ALLOC_PCI_FIRST_S) - & VPINT_ALLOC_PCI_FIRST_M) | - ((device_based_last_msix << VPINT_ALLOC_PCI_LAST_S) & - VPINT_ALLOC_PCI_LAST_M) | VPINT_ALLOC_PCI_VALID_M); - wr32(hw, VPINT_ALLOC_PCI(vf->vf_id), reg); - - /* map the interrupts to its functions */ - for (v = pf_based_first_msix; v <= pf_based_last_msix; v++) { - reg = (((device_based_vf_id << GLINT_VECT2FUNC_VF_NUM_S) & - GLINT_VECT2FUNC_VF_NUM_M) | - ((hw->pf_id << GLINT_VECT2FUNC_PF_NUM_S) & - GLINT_VECT2FUNC_PF_NUM_M)); - wr32(hw, GLINT_VECT2FUNC(v), reg); - } - - /* Map mailbox interrupt to VF MSI-X vector 0 */ - wr32(hw, VPINT_MBX_CTL(device_based_vf_id), VPINT_MBX_CTL_CAUSE_ENA_M); -} - -/** - * ice_ena_vf_q_mappings - enable Rx/Tx queue mappings for a VF - * @vf: VF to enable the mappings for - * @max_txq: max Tx queues allowed on the VF's VSI - * @max_rxq: max Rx queues allowed on the VF's VSI - */ -static void ice_ena_vf_q_mappings(struct ice_vf *vf, u16 max_txq, u16 max_rxq) -{ - struct device *dev = ice_pf_to_dev(vf->pf); - struct ice_vsi *vsi = ice_get_vf_vsi(vf); - struct ice_hw *hw = &vf->pf->hw; - u32 reg; - - /* set regardless of mapping mode */ - wr32(hw, VPLAN_TXQ_MAPENA(vf->vf_id), VPLAN_TXQ_MAPENA_TX_ENA_M); - - /* VF Tx queues allocation */ - if (vsi->tx_mapping_mode == ICE_VSI_MAP_CONTIG) { - /* set the VF PF Tx queue range - * VFNUMQ value should be set to (number of queues - 1). A value - * of 0 means 1 queue and a value of 255 means 256 queues - */ - reg = (((vsi->txq_map[0] << VPLAN_TX_QBASE_VFFIRSTQ_S) & - VPLAN_TX_QBASE_VFFIRSTQ_M) | - (((max_txq - 1) << VPLAN_TX_QBASE_VFNUMQ_S) & - VPLAN_TX_QBASE_VFNUMQ_M)); - wr32(hw, VPLAN_TX_QBASE(vf->vf_id), reg); - } else { - dev_err(dev, "Scattered mode for VF Tx queues is not yet implemented\n"); - } - - /* set regardless of mapping mode */ - wr32(hw, VPLAN_RXQ_MAPENA(vf->vf_id), VPLAN_RXQ_MAPENA_RX_ENA_M); - - /* VF Rx queues allocation */ - if (vsi->rx_mapping_mode == ICE_VSI_MAP_CONTIG) { - /* set the VF PF Rx queue range - * VFNUMQ value should be set to (number of queues - 1). A value - * of 0 means 1 queue and a value of 255 means 256 queues - */ - reg = (((vsi->rxq_map[0] << VPLAN_RX_QBASE_VFFIRSTQ_S) & - VPLAN_RX_QBASE_VFFIRSTQ_M) | - (((max_rxq - 1) << VPLAN_RX_QBASE_VFNUMQ_S) & - VPLAN_RX_QBASE_VFNUMQ_M)); - wr32(hw, VPLAN_RX_QBASE(vf->vf_id), reg); - } else { - dev_err(dev, "Scattered mode for VF Rx queues is not yet implemented\n"); - } -} - -/** - * ice_ena_vf_mappings - enable VF MSIX and queue mapping - * @vf: pointer to the VF structure - */ -static void ice_ena_vf_mappings(struct ice_vf *vf) -{ - struct ice_vsi *vsi = ice_get_vf_vsi(vf); - - ice_ena_vf_msix_mappings(vf); - ice_ena_vf_q_mappings(vf, vsi->alloc_txq, vsi->alloc_rxq); -} - -/** - * ice_determine_res - * @pf: pointer to the PF structure - * @avail_res: available resources in the PF structure - * @max_res: maximum resources that can be given per VF - * @min_res: minimum resources that can be given per VF - * - * Returns non-zero value if resources (queues/vectors) are available or - * returns zero if PF cannot accommodate for all num_alloc_vfs. - */ -static int -ice_determine_res(struct ice_pf *pf, u16 avail_res, u16 max_res, u16 min_res) -{ - bool checked_min_res = false; - int res; - - /* start by checking if PF can assign max number of resources for - * all num_alloc_vfs. - * if yes, return number per VF - * If no, divide by 2 and roundup, check again - * repeat the loop till we reach a point where even minimum resources - * are not available, in that case return 0 - */ - res = max_res; - while ((res >= min_res) && !checked_min_res) { - int num_all_res; - - num_all_res = pf->num_alloc_vfs * res; - if (num_all_res <= avail_res) - return res; - - if (res == min_res) - checked_min_res = true; - - res = DIV_ROUND_UP(res, 2); - } - return 0; -} - -/** - * ice_calc_vf_reg_idx - Calculate the VF's register index in the PF space - * @vf: VF to calculate the register index for - * @q_vector: a q_vector associated to the 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->num_msix_per_vf * vf->vf_id + - q_vector->v_idx + 1; -} - -/** - * ice_get_max_valid_res_idx - Get the max valid resource index - * @res: pointer to the resource to find the max valid index for - * - * Start from the end of the ice_res_tracker and return right when we find the - * first res->list entry with the ICE_RES_VALID_BIT set. This function is only - * valid for SR-IOV because it is the only consumer that manipulates the - * res->end and this is always called when res->end is set to res->num_entries. - */ -static int ice_get_max_valid_res_idx(struct ice_res_tracker *res) -{ - int i; - - if (!res) - return -EINVAL; - - for (i = res->num_entries - 1; i >= 0; i--) - if (res->list[i] & ICE_RES_VALID_BIT) - return i; - - return 0; -} - -/** - * ice_sriov_set_msix_res - Set any used MSIX resources - * @pf: pointer to PF structure - * @num_msix_needed: number of MSIX vectors needed for all SR-IOV VFs - * - * This function allows SR-IOV resources to be taken from the end of the PF's - * allowed HW MSIX vectors so that the irq_tracker will not be affected. We - * just set the pf->sriov_base_vector and return success. - * - * If there are not enough resources available, return an error. This should - * always be caught by ice_set_per_vf_res(). - * - * Return 0 on success, and -EINVAL when there are not enough MSIX vectors - * in the PF's space available for SR-IOV. - */ -static int ice_sriov_set_msix_res(struct ice_pf *pf, u16 num_msix_needed) -{ - u16 total_vectors = pf->hw.func_caps.common_cap.num_msix_vectors; - int vectors_used = pf->irq_tracker->num_entries; - int sriov_base_vector; - - sriov_base_vector = total_vectors - num_msix_needed; - - /* make sure we only grab irq_tracker entries from the list end and - * that we have enough available MSIX vectors - */ - if (sriov_base_vector < vectors_used) - return -EINVAL; - - pf->sriov_base_vector = sriov_base_vector; - - return 0; -} - -/** - * ice_set_per_vf_res - check if vectors and queues are available - * @pf: pointer to the PF structure - * - * First, determine HW interrupts from common pool. If we allocate fewer VFs, we - * get more vectors and can enable more queues per VF. Note that this does not - * grab any vectors from the SW pool already allocated. Also note, that all - * vector counts include one for each VF's miscellaneous interrupt vector - * (i.e. OICR). - * - * Minimum VFs - 2 vectors, 1 queue pair - * Small VFs - 5 vectors, 4 queue pairs - * Medium VFs - 17 vectors, 16 queue pairs - * - * Second, determine number of queue pairs per VF by starting with a pre-defined - * maximum each VF supports. If this is not possible, then we adjust based on - * queue pairs available on the device. - * - * Lastly, set queue and MSI-X VF variables tracked by the PF so it can be used - * by each VF during VF initialization and reset. - */ -static int ice_set_per_vf_res(struct ice_pf *pf) -{ - int max_valid_res_idx = ice_get_max_valid_res_idx(pf->irq_tracker); - int msix_avail_per_vf, msix_avail_for_sriov; - struct device *dev = ice_pf_to_dev(pf); - u16 num_msix_per_vf, num_txq, num_rxq; - - if (!pf->num_alloc_vfs || max_valid_res_idx < 0) - return -EINVAL; - - /* determine MSI-X resources per VF */ - msix_avail_for_sriov = pf->hw.func_caps.common_cap.num_msix_vectors - - pf->irq_tracker->num_entries; - msix_avail_per_vf = msix_avail_for_sriov / pf->num_alloc_vfs; - if (msix_avail_per_vf >= ICE_NUM_VF_MSIX_MED) { - num_msix_per_vf = ICE_NUM_VF_MSIX_MED; - } else if (msix_avail_per_vf >= ICE_NUM_VF_MSIX_SMALL) { - num_msix_per_vf = ICE_NUM_VF_MSIX_SMALL; - } else if (msix_avail_per_vf >= ICE_NUM_VF_MSIX_MULTIQ_MIN) { - num_msix_per_vf = ICE_NUM_VF_MSIX_MULTIQ_MIN; - } else if (msix_avail_per_vf >= ICE_MIN_INTR_PER_VF) { - num_msix_per_vf = ICE_MIN_INTR_PER_VF; - } else { - dev_err(dev, "Only %d MSI-X interrupts available for SR-IOV. Not enough to support minimum of %d MSI-X interrupts per VF for %d VFs\n", - msix_avail_for_sriov, ICE_MIN_INTR_PER_VF, - pf->num_alloc_vfs); - return -EIO; - } - - /* determine queue resources per VF */ - num_txq = ice_determine_res(pf, ice_get_avail_txq_count(pf), - min_t(u16, - num_msix_per_vf - ICE_NONQ_VECS_VF, - ICE_MAX_RSS_QS_PER_VF), - ICE_MIN_QS_PER_VF); - - num_rxq = ice_determine_res(pf, ice_get_avail_rxq_count(pf), - min_t(u16, - num_msix_per_vf - ICE_NONQ_VECS_VF, - ICE_MAX_RSS_QS_PER_VF), - ICE_MIN_QS_PER_VF); - - if (!num_txq || !num_rxq) { - dev_err(dev, "Not enough queues to support minimum of %d queue pairs per VF for %d VFs\n", - ICE_MIN_QS_PER_VF, pf->num_alloc_vfs); - return -EIO; - } - - if (ice_sriov_set_msix_res(pf, num_msix_per_vf * pf->num_alloc_vfs)) { - dev_err(dev, "Unable to set MSI-X resources for %d VFs\n", - pf->num_alloc_vfs); - return -EINVAL; - } - - /* only allow equal Tx/Rx queue count (i.e. queue pairs) */ - pf->num_qps_per_vf = min_t(int, num_txq, num_rxq); - pf->num_msix_per_vf = num_msix_per_vf; - dev_info(dev, "Enabling %d VFs with %d vectors and %d queues per VF\n", - pf->num_alloc_vfs, pf->num_msix_per_vf, pf->num_qps_per_vf); - - return 0; -} - -/** - * ice_clear_vf_reset_trigger - enable VF to access hardware - * @vf: VF to enabled hardware access for - */ -static void ice_clear_vf_reset_trigger(struct ice_vf *vf) -{ - struct ice_hw *hw = &vf->pf->hw; - u32 reg; - - reg = rd32(hw, VPGEN_VFRTRIG(vf->vf_id)); - reg &= ~VPGEN_VFRTRIG_VFSWR_M; - wr32(hw, VPGEN_VFRTRIG(vf->vf_id), reg); - ice_flush(hw); -} - -static int -ice_vf_set_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m) -{ - struct ice_hw *hw = &vsi->back->hw; - int status; - - if (vf->port_vlan_info) - status = ice_fltr_set_vsi_promisc(hw, vsi->idx, promisc_m, - vf->port_vlan_info & VLAN_VID_MASK); - else if (vsi->num_vlan > 1) - status = ice_fltr_set_vlan_vsi_promisc(hw, vsi, promisc_m); - else - status = ice_fltr_set_vsi_promisc(hw, vsi->idx, promisc_m, 0); - - if (status && status != -EEXIST) { - dev_err(ice_pf_to_dev(vsi->back), "enable Tx/Rx filter promiscuous mode on VF-%u failed, error: %d\n", - vf->vf_id, status); - return status; - } - - return 0; -} - -static int -ice_vf_clear_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m) -{ - struct ice_hw *hw = &vsi->back->hw; - int status; - - if (vf->port_vlan_info) - status = ice_fltr_clear_vsi_promisc(hw, vsi->idx, promisc_m, - vf->port_vlan_info & VLAN_VID_MASK); - else if (vsi->num_vlan > 1) - status = ice_fltr_clear_vlan_vsi_promisc(hw, vsi, promisc_m); - else - status = ice_fltr_clear_vsi_promisc(hw, vsi->idx, promisc_m, 0); - - if (status && status != -ENOENT) { - dev_err(ice_pf_to_dev(vsi->back), "disable Tx/Rx filter promiscuous mode on VF-%u failed, error: %d\n", - vf->vf_id, status); - return status; - } - - return 0; -} - -static void ice_vf_clear_counters(struct ice_vf *vf) -{ - struct ice_vsi *vsi = ice_get_vf_vsi(vf); - - vf->num_mac = 0; - vsi->num_vlan = 0; - memset(&vf->mdd_tx_events, 0, sizeof(vf->mdd_tx_events)); - memset(&vf->mdd_rx_events, 0, sizeof(vf->mdd_rx_events)); -} - -/** - * ice_vf_pre_vsi_rebuild - tasks to be done prior to VSI rebuild - * @vf: VF to perform pre VSI rebuild tasks - * - * These tasks are items that don't need to be amortized since they are most - * likely called in a for loop with all VF(s) in the reset_all_vfs() case. - */ -static void ice_vf_pre_vsi_rebuild(struct ice_vf *vf) -{ - ice_vf_clear_counters(vf); - ice_clear_vf_reset_trigger(vf); -} - -/** - * 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); - - 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)) - 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); - - /* rebuild aggregator node config for main VF VSI */ - ice_vf_rebuild_aggregator_node_cfg(vsi); -} - -/** - * ice_vf_rebuild_vsi_with_release - release and setup the VF's VSI - * @vf: VF to release and setup the VSI for - * - * This is only called when a single VF is being reset (i.e. VFR, VFLR, host VF - * configuration change, etc.). - */ -static int ice_vf_rebuild_vsi_with_release(struct ice_vf *vf) -{ - ice_vf_vsi_release(vf); - if (!ice_vf_vsi_setup(vf)) - return -ENOMEM; - - return 0; -} - -/** - * ice_vf_rebuild_vsi - rebuild the VF's VSI - * @vf: VF to rebuild the VSI for - * - * This is only called when all VF(s) are being reset (i.e. PCIe Reset on the - * host, PFR, CORER, etc.). - */ -static int ice_vf_rebuild_vsi(struct ice_vf *vf) -{ - struct ice_vsi *vsi = ice_get_vf_vsi(vf); - struct ice_pf *pf = vf->pf; - - if (ice_vsi_rebuild(vsi, true)) { - dev_err(ice_pf_to_dev(pf), "failed to rebuild VF %d VSI\n", - vf->vf_id); - return -EIO; - } - /* vsi->idx will remain the same in this case so don't update - * vf->lan_vsi_idx - */ - vsi->vsi_num = ice_get_hw_vsi_num(&pf->hw, vsi->idx); - vf->lan_vsi_num = vsi->vsi_num; - - return 0; -} - -/** - * 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); -} - -/** - * ice_vf_post_vsi_rebuild - tasks to do after the VF's VSI have been rebuilt - * @vf: VF to perform tasks on - */ -static void ice_vf_post_vsi_rebuild(struct ice_vf *vf) -{ - struct ice_pf *pf = vf->pf; - struct ice_hw *hw; - - hw = &pf->hw; - - ice_vf_rebuild_host_cfg(vf); - - ice_vf_set_initialized(vf); - ice_ena_vf_mappings(vf); - wr32(hw, VFGEN_RSTAT(vf->vf_id), VIRTCHNL_VFR_VFACTIVE); -} - -/** - * ice_reset_all_vfs - reset all allocated VFs in one go - * @pf: pointer to the PF structure - * @is_vflr: true if VFLR was issued, false if not - * - * First, tell the hardware to reset each VF, then do all the waiting in one - * chunk, and finally finish restoring each VF after the wait. This is useful - * during PF routines which need to reset all VFs, as otherwise it must perform - * these resets in a serialized fashion. - * - * Returns true if any VFs were reset, and false otherwise. - */ -bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr) -{ - struct device *dev = ice_pf_to_dev(pf); - struct ice_hw *hw = &pf->hw; - struct ice_vf *vf; - int v, i; - - /* If we don't have any VFs, then there is nothing to reset */ - if (!pf->num_alloc_vfs) - return false; - - /* clear all malicious info if the VFs are getting reset */ - ice_for_each_vf(pf, i) - if (ice_mbx_clear_malvf(&hw->mbx_snapshot, pf->malvfs, ICE_MAX_VF_COUNT, i)) - dev_dbg(dev, "failed to clear malicious VF state for VF %u\n", i); - - /* If VFs have been disabled, there is no need to reset */ - if (test_and_set_bit(ICE_VF_DIS, pf->state)) - return false; - - /* Begin reset on all VFs at once */ - ice_for_each_vf(pf, v) - ice_trigger_vf_reset(&pf->vf[v], is_vflr, true); - - /* HW requires some time to make sure it can flush the FIFO for a VF - * when it resets it. Poll the VPGEN_VFRSTAT register for each VF in - * sequence to make sure that it has completed. We'll keep track of - * the VFs using a simple iterator that increments once that VF has - * finished resetting. - */ - for (i = 0, v = 0; i < 10 && v < pf->num_alloc_vfs; i++) { - /* Check each VF in sequence */ - while (v < pf->num_alloc_vfs) { - u32 reg; - - vf = &pf->vf[v]; - reg = rd32(hw, VPGEN_VFRSTAT(vf->vf_id)); - if (!(reg & VPGEN_VFRSTAT_VFRD_M)) { - /* only delay if the check failed */ - usleep_range(10, 20); - break; - } - - /* If the current VF has finished resetting, move on - * to the next VF in sequence. - */ - v++; - } - } - - /* Display a warning if at least one VF didn't manage to reset in - * time, but continue on with the operation. - */ - if (v < pf->num_alloc_vfs) - dev_warn(dev, "VF reset check timeout\n"); - - /* free VF resources to begin resetting the VSI state */ - ice_for_each_vf(pf, v) { - vf = &pf->vf[v]; - - vf->driver_caps = 0; - ice_vc_set_default_allowlist(vf); - - ice_vf_fdir_exit(vf); - ice_vf_fdir_init(vf); - /* clean VF control VSI when resetting VFs since it should be - * setup only when VF creates its first FDIR rule. - */ - if (vf->ctrl_vsi_idx != ICE_NO_VSI) - ice_vf_ctrl_invalidate_vsi(vf); - - ice_vf_pre_vsi_rebuild(vf); - ice_vf_rebuild_vsi(vf); - ice_vf_post_vsi_rebuild(vf); - } - - if (ice_is_eswitch_mode_switchdev(pf)) - if (ice_eswitch_rebuild(pf)) - dev_warn(dev, "eswitch rebuild failed\n"); - - ice_flush(hw); - clear_bit(ICE_VF_DIS, pf->state); - - return true; -} - -/** - * ice_is_vf_disabled - * @vf: pointer to the VF info - * - * Returns true if the PF or VF is disabled, false otherwise. - */ -bool ice_is_vf_disabled(struct ice_vf *vf) -{ - struct ice_pf *pf = vf->pf; - - /* If the PF has been disabled, there is no need resetting VF until - * PF is active again. Similarly, if the VF has been disabled, this - * means something else is resetting the VF, so we shouldn't continue. - * Otherwise, set disable VF state bit for actual reset, and continue. - */ - return (test_bit(ICE_VF_DIS, pf->state) || - test_bit(ICE_VF_STATE_DIS, vf->vf_states)); -} - -/** - * ice_reset_vf - Reset a particular VF - * @vf: pointer to the VF structure - * @is_vflr: true if VFLR was issued, false if not - * - * Returns true if the VF is currently in reset, resets successfully, or resets - * are disabled and false otherwise. - */ -bool ice_reset_vf(struct ice_vf *vf, bool is_vflr) -{ - struct ice_pf *pf = vf->pf; - struct ice_vsi *vsi; - struct device *dev; - struct ice_hw *hw; - bool rsd = false; - u8 promisc_m; - u32 reg; - int i; - - dev = ice_pf_to_dev(pf); - - if (test_bit(ICE_VF_RESETS_DISABLED, pf->state)) { - dev_dbg(dev, "Trying to reset VF %d, but all VF resets are disabled\n", - vf->vf_id); - return true; - } - - if (ice_is_vf_disabled(vf)) { - dev_dbg(dev, "VF is already disabled, there is no need for resetting it, telling VM, all is fine %d\n", - vf->vf_id); - return true; - } - - /* Set VF disable bit state here, before triggering reset */ - set_bit(ICE_VF_STATE_DIS, vf->vf_states); - ice_trigger_vf_reset(vf, is_vflr, false); - - vsi = ice_get_vf_vsi(vf); - - ice_dis_vf_qs(vf); - - /* Call Disable LAN Tx queue AQ whether or not queues are - * enabled. This is needed for successful completion of VFR. - */ - ice_dis_vsi_txq(vsi->port_info, vsi->idx, 0, 0, NULL, NULL, - NULL, ICE_VF_RESET, vf->vf_id, NULL); - - hw = &pf->hw; - /* poll VPGEN_VFRSTAT reg to make sure - * that reset is complete - */ - for (i = 0; i < 10; i++) { - /* VF reset requires driver to first reset the VF and then - * poll the status register to make sure that the reset - * completed successfully. - */ - reg = rd32(hw, VPGEN_VFRSTAT(vf->vf_id)); - if (reg & VPGEN_VFRSTAT_VFRD_M) { - rsd = true; - break; - } - - /* only sleep if the reset is not done */ - usleep_range(10, 20); - } - - vf->driver_caps = 0; - ice_vc_set_default_allowlist(vf); - - /* Display a warning if VF didn't manage to reset in time, but need to - * continue on with the operation. - */ - if (!rsd) - dev_warn(dev, "VF reset check timeout on VF %d\n", vf->vf_id); - - /* disable promiscuous modes in case they were enabled - * ignore any error if disabling process failed - */ - if (test_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states) || - test_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states)) { - if (vf->port_vlan_info || vsi->num_vlan) - promisc_m = ICE_UCAST_VLAN_PROMISC_BITS; - else - promisc_m = ICE_UCAST_PROMISC_BITS; - - if (ice_vf_clear_vsi_promisc(vf, vsi, promisc_m)) - dev_err(dev, "disabling promiscuous mode failed\n"); - } - - ice_eswitch_del_vf_mac_rule(vf); - - ice_vf_fdir_exit(vf); - ice_vf_fdir_init(vf); - /* clean VF control VSI when resetting VF since it should be setup - * only when VF creates its first FDIR rule. - */ - if (vf->ctrl_vsi_idx != ICE_NO_VSI) - ice_vf_ctrl_vsi_release(vf); - - ice_vf_pre_vsi_rebuild(vf); - - if (ice_vf_rebuild_vsi_with_release(vf)) { - dev_err(dev, "Failed to release and setup the VF%u's VSI\n", vf->vf_id); - return false; - } - - ice_vf_post_vsi_rebuild(vf); - vsi = ice_get_vf_vsi(vf); - ice_eswitch_update_repr(vsi); - ice_eswitch_replay_vf_mac_rule(vf); - - /* if the VF has been reset allow it to come up again */ - if (ice_mbx_clear_malvf(&hw->mbx_snapshot, pf->malvfs, ICE_MAX_VF_COUNT, vf->vf_id)) - dev_dbg(dev, "failed to clear malicious VF state for VF %u\n", i); - - return true; -} - -/** - * ice_vc_notify_link_state - Inform all VFs on a PF of link status - * @pf: pointer to the PF structure - */ -void ice_vc_notify_link_state(struct ice_pf *pf) -{ - int i; - - ice_for_each_vf(pf, i) - ice_vc_notify_vf_link_state(&pf->vf[i]); -} - -/** - * ice_vc_notify_reset - Send pending reset message to all VFs - * @pf: pointer to the PF structure - * - * indicate a pending reset to all VFs on a given PF - */ -void ice_vc_notify_reset(struct ice_pf *pf) -{ - struct virtchnl_pf_event pfe; - - if (!pf->num_alloc_vfs) - return; - - pfe.event = VIRTCHNL_EVENT_RESET_IMPENDING; - pfe.severity = PF_EVENT_SEVERITY_CERTAIN_DOOM; - ice_vc_vf_broadcast(pf, VIRTCHNL_OP_EVENT, VIRTCHNL_STATUS_SUCCESS, - (u8 *)&pfe, sizeof(struct virtchnl_pf_event)); -} - -/** - * ice_vc_notify_vf_reset - Notify VF of a reset event - * @vf: pointer to the VF structure - */ -static void ice_vc_notify_vf_reset(struct ice_vf *vf) -{ - struct virtchnl_pf_event pfe; - struct ice_pf *pf; - - if (!vf) - return; - - pf = vf->pf; - if (ice_validate_vf_id(pf, vf->vf_id)) - return; - - /* Bail out if VF is in disabled state, neither initialized, nor active - * state - otherwise proceed with notifications - */ - if ((!test_bit(ICE_VF_STATE_INIT, vf->vf_states) && - !test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) || - test_bit(ICE_VF_STATE_DIS, vf->vf_states)) - return; - - pfe.event = VIRTCHNL_EVENT_RESET_IMPENDING; - pfe.severity = PF_EVENT_SEVERITY_CERTAIN_DOOM; - ice_aq_send_msg_to_vf(&pf->hw, vf->vf_id, VIRTCHNL_OP_EVENT, - VIRTCHNL_STATUS_SUCCESS, (u8 *)&pfe, sizeof(pfe), - NULL); -} - -/** - * ice_init_vf_vsi_res - initialize/setup VF VSI resources - * @vf: VF to initialize/setup the VSI for - * - * This function creates a VSI for the VF, adds a VLAN 0 filter, and sets up the - * VF VSI's broadcast filter and is only used during initial VF creation. - */ -static int ice_init_vf_vsi_res(struct ice_vf *vf) -{ - struct ice_pf *pf = vf->pf; - u8 broadcast[ETH_ALEN]; - struct ice_vsi *vsi; - struct device *dev; - int err; - - vf->first_vector_idx = ice_calc_vf_first_vector_idx(pf, vf); - - dev = ice_pf_to_dev(pf); - vsi = ice_vf_vsi_setup(vf); - if (!vsi) - return -ENOMEM; - - err = ice_vsi_add_vlan(vsi, 0, ICE_FWD_TO_VSI); - if (err) { - dev_warn(dev, "Failed to add VLAN 0 filter for VF %d\n", - vf->vf_id); - goto release_vsi; - } - - eth_broadcast_addr(broadcast); - err = ice_fltr_add_mac(vsi, broadcast, ICE_FWD_TO_VSI); - if (err) { - dev_err(dev, "Failed to add broadcast MAC filter for VF %d, error %d\n", - vf->vf_id, err); - goto release_vsi; - } - - vf->num_mac = 1; - - return 0; - -release_vsi: - ice_vf_vsi_release(vf); - return err; -} - -/** - * ice_start_vfs - start VFs so they are ready to be used by SR-IOV - * @pf: PF the VFs are associated with - */ -static int ice_start_vfs(struct ice_pf *pf) -{ - struct ice_hw *hw = &pf->hw; - int retval, i; - - ice_for_each_vf(pf, i) { - struct ice_vf *vf = &pf->vf[i]; - - ice_clear_vf_reset_trigger(vf); - - retval = ice_init_vf_vsi_res(vf); - if (retval) { - dev_err(ice_pf_to_dev(pf), "Failed to initialize VSI resources for VF %d, error %d\n", - vf->vf_id, retval); - goto teardown; - } - - set_bit(ICE_VF_STATE_INIT, vf->vf_states); - ice_ena_vf_mappings(vf); - wr32(hw, VFGEN_RSTAT(vf->vf_id), VIRTCHNL_VFR_VFACTIVE); - } - - ice_flush(hw); - return 0; - -teardown: - for (i = i - 1; i >= 0; i--) { - struct ice_vf *vf = &pf->vf[i]; - - ice_dis_vf_mappings(vf); - ice_vf_vsi_release(vf); - } - - return retval; -} - -/** - * ice_set_dflt_settings_vfs - set VF defaults during initialization/creation - * @pf: PF holding reference to all VFs for default configuration - */ -static void ice_set_dflt_settings_vfs(struct ice_pf *pf) -{ - int i; - - ice_for_each_vf(pf, i) { - struct ice_vf *vf = &pf->vf[i]; - - vf->pf = pf; - vf->vf_id = i; - vf->vf_sw_id = pf->first_sw; - /* assign default capabilities */ - set_bit(ICE_VIRTCHNL_VF_CAP_L2, &vf->vf_caps); - vf->spoofchk = true; - vf->num_vf_qs = pf->num_qps_per_vf; - ice_vc_set_default_allowlist(vf); - - /* ctrl_vsi_idx will be set to a valid value only when VF - * creates its first fdir rule. - */ - ice_vf_ctrl_invalidate_vsi(vf); - ice_vf_fdir_init(vf); - - ice_vc_set_dflt_vf_ops(&vf->vc_ops); - - mutex_init(&vf->cfg_lock); - } -} - -/** - * ice_alloc_vfs - allocate num_vfs in the PF structure - * @pf: PF to store the allocated VFs in - * @num_vfs: number of VFs to allocate - */ -static int ice_alloc_vfs(struct ice_pf *pf, int num_vfs) -{ - struct ice_vf *vfs; - - vfs = devm_kcalloc(ice_pf_to_dev(pf), num_vfs, sizeof(*vfs), - GFP_KERNEL); - if (!vfs) - return -ENOMEM; - - pf->vf = vfs; - pf->num_alloc_vfs = num_vfs; - - return 0; -} - -/** - * ice_ena_vfs - enable VFs so they are ready to be used - * @pf: pointer to the PF structure - * @num_vfs: number of VFs to enable - */ -static int ice_ena_vfs(struct ice_pf *pf, u16 num_vfs) -{ - struct device *dev = ice_pf_to_dev(pf); - struct ice_hw *hw = &pf->hw; - int ret; - - /* Disable global interrupt 0 so we don't try to handle the VFLR. */ - wr32(hw, GLINT_DYN_CTL(pf->oicr_idx), - ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S); - set_bit(ICE_OICR_INTR_DIS, pf->state); - ice_flush(hw); - - ret = pci_enable_sriov(pf->pdev, num_vfs); - if (ret) { - pf->num_alloc_vfs = 0; - goto err_unroll_intr; - } - - ret = ice_alloc_vfs(pf, num_vfs); - if (ret) - goto err_pci_disable_sriov; - - if (ice_set_per_vf_res(pf)) { - dev_err(dev, "Not enough resources for %d VFs, try with fewer number of VFs\n", - num_vfs); - ret = -ENOSPC; - goto err_unroll_sriov; - } - - ice_set_dflt_settings_vfs(pf); - - if (ice_start_vfs(pf)) { - dev_err(dev, "Failed to start VF(s)\n"); - ret = -EAGAIN; - goto err_unroll_sriov; - } - - clear_bit(ICE_VF_DIS, pf->state); - - ret = ice_eswitch_configure(pf); - if (ret) - goto err_unroll_sriov; - - /* rearm global interrupts */ - if (test_and_clear_bit(ICE_OICR_INTR_DIS, pf->state)) - ice_irq_dynamic_ena(hw, NULL, NULL); - - return 0; - -err_unroll_sriov: - devm_kfree(dev, pf->vf); - pf->vf = NULL; - pf->num_alloc_vfs = 0; -err_pci_disable_sriov: - pci_disable_sriov(pf->pdev); -err_unroll_intr: - /* rearm interrupts here */ - ice_irq_dynamic_ena(hw, NULL, NULL); - clear_bit(ICE_OICR_INTR_DIS, pf->state); - return ret; -} - -/** - * ice_pci_sriov_ena - Enable or change number of VFs - * @pf: pointer to the PF structure - * @num_vfs: number of VFs to allocate - * - * Returns 0 on success and negative on failure - */ -static int ice_pci_sriov_ena(struct ice_pf *pf, int num_vfs) -{ - int pre_existing_vfs = pci_num_vf(pf->pdev); - struct device *dev = ice_pf_to_dev(pf); - int err; - - if (pre_existing_vfs && pre_existing_vfs != num_vfs) - ice_free_vfs(pf); - else if (pre_existing_vfs && pre_existing_vfs == num_vfs) - return 0; - - if (num_vfs > pf->num_vfs_supported) { - dev_err(dev, "Can't enable %d VFs, max VFs supported is %d\n", - num_vfs, pf->num_vfs_supported); - return -EOPNOTSUPP; - } - - dev_info(dev, "Enabling %d VFs\n", num_vfs); - err = ice_ena_vfs(pf, num_vfs); - if (err) { - dev_err(dev, "Failed to enable SR-IOV: %d\n", err); - return err; - } - - set_bit(ICE_FLAG_SRIOV_ENA, pf->flags); - return 0; -} - -/** - * ice_check_sriov_allowed - check if SR-IOV is allowed based on various checks - * @pf: PF to enabled SR-IOV on - */ -static int ice_check_sriov_allowed(struct ice_pf *pf) -{ - struct device *dev = ice_pf_to_dev(pf); - - if (!test_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags)) { - dev_err(dev, "This device is not capable of SR-IOV\n"); - return -EOPNOTSUPP; - } - - if (ice_is_safe_mode(pf)) { - dev_err(dev, "SR-IOV cannot be configured - Device is in Safe Mode\n"); - return -EOPNOTSUPP; - } - - if (!ice_pf_state_is_nominal(pf)) { - dev_err(dev, "Cannot enable SR-IOV, device not ready\n"); - return -EBUSY; - } - - return 0; -} - -/** - * 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 - * - * This function is called when the user updates the number of VFs in sysfs. On - * success return whatever num_vfs was set to by the caller. Return negative on - * failure. - */ -int ice_sriov_configure(struct pci_dev *pdev, int num_vfs) -{ - struct ice_pf *pf = pci_get_drvdata(pdev); - struct device *dev = ice_pf_to_dev(pf); - int err; - - err = ice_check_sriov_allowed(pf); - if (err) - return err; - - if (!num_vfs) { - if (!pci_vfs_assigned(pdev)) { - ice_mbx_deinit_snapshot(&pf->hw); - ice_free_vfs(pf); - if (pf->lag) - ice_enable_lag(pf->lag); - return 0; - } - - dev_err(dev, "can't free VFs because some are assigned to VMs.\n"); - return -EBUSY; - } - - err = ice_mbx_init_snapshot(&pf->hw, num_vfs); - if (err) - return err; - - err = ice_pci_sriov_ena(pf, num_vfs); - if (err) { - ice_mbx_deinit_snapshot(&pf->hw); - return err; - } - - if (pf->lag) - ice_disable_lag(pf->lag); - return num_vfs; -} - -/** - * ice_process_vflr_event - Free VF resources via IRQ calls - * @pf: pointer to the PF structure - * - * called from the VFLR IRQ handler to - * free up VF resources and state variables - */ -void ice_process_vflr_event(struct ice_pf *pf) -{ - struct ice_hw *hw = &pf->hw; - unsigned int vf_id; - u32 reg; - - if (!test_and_clear_bit(ICE_VFLR_EVENT_PENDING, pf->state) || - !pf->num_alloc_vfs) - return; - - ice_for_each_vf(pf, vf_id) { - struct ice_vf *vf = &pf->vf[vf_id]; - u32 reg_idx, bit_idx; - - reg_idx = (hw->func_caps.vf_base_id + vf_id) / 32; - bit_idx = (hw->func_caps.vf_base_id + vf_id) % 32; - /* read GLGEN_VFLRSTAT register to find out the flr VFs */ - reg = rd32(hw, GLGEN_VFLRSTAT(reg_idx)); - if (reg & BIT(bit_idx)) - /* GLGEN_VFLRSTAT bit will be cleared in ice_reset_vf */ - ice_reset_vf(vf, true); - } -} - -/** - * ice_vc_reset_vf - Perform software reset on the VF after informing the AVF - * @vf: pointer to the VF info - */ -static void ice_vc_reset_vf(struct ice_vf *vf) -{ - ice_vc_notify_vf_reset(vf); - ice_reset_vf(vf, false); -} - -/** - * ice_get_vf_from_pfq - get the VF who owns the PF space queue passed in - * @pf: PF used to index all VFs - * @pfq: queue index relative to the PF's function space - * - * If no VF is found who owns the pfq then return NULL, otherwise return a - * pointer to the VF who owns the pfq - */ -static struct ice_vf *ice_get_vf_from_pfq(struct ice_pf *pf, u16 pfq) -{ - unsigned int vf_id; - - ice_for_each_vf(pf, vf_id) { - struct ice_vf *vf = &pf->vf[vf_id]; - struct ice_vsi *vsi; - u16 rxq_idx; - - vsi = ice_get_vf_vsi(vf); - - ice_for_each_rxq(vsi, rxq_idx) - if (vsi->rxq_map[rxq_idx] == pfq) - return vf; - } - - return NULL; -} - -/** - * ice_globalq_to_pfq - convert from global queue index to PF space queue index - * @pf: PF used for conversion - * @globalq: global queue index used to convert to PF space queue index - */ -static u32 ice_globalq_to_pfq(struct ice_pf *pf, u32 globalq) -{ - return globalq - pf->hw.func_caps.common_cap.rxq_first_id; -} - -/** - * ice_vf_lan_overflow_event - handle LAN overflow event for a VF - * @pf: PF that the LAN overflow event happened on - * @event: structure holding the event information for the LAN overflow event - * - * Determine if the LAN overflow event was caused by a VF queue. If it was not - * caused by a VF, do nothing. If a VF caused this LAN overflow event trigger a - * reset on the offending VF. - */ -void -ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event) -{ - u32 gldcb_rtctq, queue; - struct ice_vf *vf; - - gldcb_rtctq = le32_to_cpu(event->desc.params.lan_overflow.prtdcb_ruptq); - dev_dbg(ice_pf_to_dev(pf), "GLDCB_RTCTQ: 0x%08x\n", gldcb_rtctq); - - /* event returns device global Rx queue number */ - queue = (gldcb_rtctq & GLDCB_RTCTQ_RXQNUM_M) >> - GLDCB_RTCTQ_RXQNUM_S; - - vf = ice_get_vf_from_pfq(pf, ice_globalq_to_pfq(pf, queue)); - if (!vf) - return; - - ice_vc_reset_vf(vf); -} - -/** - * ice_vc_send_msg_to_vf - Send message to VF - * @vf: pointer to the VF info - * @v_opcode: virtual channel opcode - * @v_retval: virtual channel return value - * @msg: pointer to the msg buffer - * @msglen: msg length - * - * send msg to VF - */ -int -ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode, - enum virtchnl_status_code v_retval, u8 *msg, u16 msglen) -{ - struct device *dev; - struct ice_pf *pf; - int aq_ret; - - if (!vf) - return -EINVAL; - - pf = vf->pf; - if (ice_validate_vf_id(pf, vf->vf_id)) - return -EINVAL; - - dev = ice_pf_to_dev(pf); - - /* single place to detect unsuccessful return values */ - if (v_retval) { - vf->num_inval_msgs++; - dev_info(dev, "VF %d failed opcode %d, retval: %d\n", vf->vf_id, - v_opcode, v_retval); - if (vf->num_inval_msgs > ICE_DFLT_NUM_INVAL_MSGS_ALLOWED) { - dev_err(dev, "Number of invalid messages exceeded for VF %d\n", - vf->vf_id); - dev_err(dev, "Use PF Control I/F to enable the VF\n"); - set_bit(ICE_VF_STATE_DIS, vf->vf_states); - return -EIO; - } - } else { - vf->num_valid_msgs++; - /* reset the invalid counter, if a valid message is received. */ - vf->num_inval_msgs = 0; - } - - aq_ret = ice_aq_send_msg_to_vf(&pf->hw, vf->vf_id, v_opcode, v_retval, - msg, msglen, NULL); - if (aq_ret && pf->hw.mailboxq.sq_last_status != ICE_AQ_RC_ENOSYS) { - dev_info(dev, "Unable to send the message to VF %d ret %d aq_err %s\n", - vf->vf_id, aq_ret, - ice_aq_str(pf->hw.mailboxq.sq_last_status)); - return -EIO; - } - - return 0; -} - -/** - * ice_vc_get_ver_msg - * @vf: pointer to the VF info - * @msg: pointer to the msg buffer - * - * called from the VF to request the API version used by the PF - */ -static int ice_vc_get_ver_msg(struct ice_vf *vf, u8 *msg) -{ - struct virtchnl_version_info info = { - VIRTCHNL_VERSION_MAJOR, VIRTCHNL_VERSION_MINOR - }; - - vf->vf_ver = *(struct virtchnl_version_info *)msg; - /* VFs running the 1.0 API expect to get 1.0 back or they will cry. */ - if (VF_IS_V10(&vf->vf_ver)) - info.minor = VIRTCHNL_VERSION_MINOR_NO_VF_CAPS; - - return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_VERSION, - VIRTCHNL_STATUS_SUCCESS, (u8 *)&info, - sizeof(struct virtchnl_version_info)); -} - -/** - * ice_vc_get_max_frame_size - get max frame size allowed for VF - * @vf: VF used to determine max frame size - * - * Max frame size is determined based on the current port's max frame size and - * whether a port VLAN is configured on this VF. The VF is not aware whether - * it's in a port VLAN so the PF needs to account for this in max frame size - * checks and sending the max frame size to the VF. - */ -static u16 ice_vc_get_max_frame_size(struct ice_vf *vf) -{ - struct ice_port_info *pi = ice_vf_get_port_info(vf); - u16 max_frame_size; - - max_frame_size = pi->phy.link_info.max_frame_size; - - if (vf->port_vlan_info) - max_frame_size -= VLAN_HLEN; - - return max_frame_size; -} - -/** - * ice_vc_get_vf_res_msg - * @vf: pointer to the VF info - * @msg: pointer to the msg buffer - * - * called from the VF to request its resources - */ -static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) -{ - enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; - struct virtchnl_vf_resource *vfres = NULL; - struct ice_pf *pf = vf->pf; - struct ice_vsi *vsi; - int len = 0; - int ret; - - if (ice_check_vf_init(pf, vf)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto err; - } - - len = sizeof(struct virtchnl_vf_resource); - - vfres = kzalloc(len, GFP_KERNEL); - if (!vfres) { - v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; - len = 0; - goto err; - } - if (VF_IS_V11(&vf->vf_ver)) - vf->driver_caps = *(u32 *)msg; - else - vf->driver_caps = VIRTCHNL_VF_OFFLOAD_L2 | - VIRTCHNL_VF_OFFLOAD_RSS_REG | - VIRTCHNL_VF_OFFLOAD_VLAN; - - vfres->vf_cap_flags = VIRTCHNL_VF_OFFLOAD_L2; - vsi = ice_get_vf_vsi(vf); - if (!vsi) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto err; - } - - if (!vsi->info.pvid) - vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_VLAN; - - if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF) { - vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PF; - } else { - if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_AQ) - vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_AQ; - else - vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_REG; - } - - if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_FDIR_PF) - vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_FDIR_PF; - - if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2) - vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2; - - if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_ENCAP) - vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_ENCAP; - - if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM) - vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM; - - if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RX_POLLING) - vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RX_POLLING; - - if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_WB_ON_ITR) - vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_WB_ON_ITR; - - if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_REQ_QUEUES) - vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_REQ_QUEUES; - - if (vf->driver_caps & VIRTCHNL_VF_CAP_ADV_LINK_SPEED) - vfres->vf_cap_flags |= VIRTCHNL_VF_CAP_ADV_LINK_SPEED; - - if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF) - vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF; - - if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_USO) - vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_USO; - - vfres->num_vsis = 1; - /* Tx and Rx queue are equal for VF */ - vfres->num_queue_pairs = vsi->num_txq; - vfres->max_vectors = pf->num_msix_per_vf; - vfres->rss_key_size = ICE_VSIQF_HKEY_ARRAY_SIZE; - vfres->rss_lut_size = ICE_VSIQF_HLUT_ARRAY_SIZE; - vfres->max_mtu = ice_vc_get_max_frame_size(vf); - - vfres->vsi_res[0].vsi_id = vf->lan_vsi_num; - vfres->vsi_res[0].vsi_type = VIRTCHNL_VSI_SRIOV; - vfres->vsi_res[0].num_queue_pairs = vsi->num_txq; - ether_addr_copy(vfres->vsi_res[0].default_mac_addr, - vf->hw_lan_addr.addr); - - /* match guest capabilities */ - vf->driver_caps = vfres->vf_cap_flags; - - ice_vc_set_caps_allowlist(vf); - ice_vc_set_working_allowlist(vf); - - set_bit(ICE_VF_STATE_ACTIVE, vf->vf_states); - -err: - /* send the response back to the VF */ - ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_VF_RESOURCES, v_ret, - (u8 *)vfres, len); - - kfree(vfres); - return ret; -} - -/** - * ice_vc_reset_vf_msg - * @vf: pointer to the VF info - * - * called from the VF to reset itself, - * unlike other virtchnl messages, PF driver - * doesn't send the response back to the VF - */ -static void ice_vc_reset_vf_msg(struct ice_vf *vf) -{ - if (test_bit(ICE_VF_STATE_INIT, vf->vf_states)) - ice_reset_vf(vf, false); -} - -/** - * ice_find_vsi_from_id - * @pf: the PF structure to search for the VSI - * @id: ID of the VSI it is searching for - * - * searches for the VSI with the given ID - */ -static struct ice_vsi *ice_find_vsi_from_id(struct ice_pf *pf, u16 id) -{ - int i; - - ice_for_each_vsi(pf, i) - if (pf->vsi[i] && pf->vsi[i]->vsi_num == id) - return pf->vsi[i]; - - return NULL; -} - -/** - * ice_vc_isvalid_vsi_id - * @vf: pointer to the VF info - * @vsi_id: VF relative VSI ID - * - * check for the valid VSI ID - */ -bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id) -{ - struct ice_pf *pf = vf->pf; - struct ice_vsi *vsi; - - vsi = ice_find_vsi_from_id(pf, vsi_id); - - return (vsi && (vsi->vf_id == vf->vf_id)); -} - -/** - * ice_vc_isvalid_q_id - * @vf: pointer to the VF info - * @vsi_id: VSI ID - * @qid: VSI relative queue ID - * - * check for the valid queue ID - */ -static bool ice_vc_isvalid_q_id(struct ice_vf *vf, u16 vsi_id, u8 qid) -{ - struct ice_vsi *vsi = ice_find_vsi_from_id(vf->pf, vsi_id); - /* allocated Tx and Rx queues should be always equal for VF VSI */ - return (vsi && (qid < vsi->alloc_txq)); -} - -/** - * ice_vc_isvalid_ring_len - * @ring_len: length of ring - * - * check for the valid ring count, should be multiple of ICE_REQ_DESC_MULTIPLE - * or zero - */ -static bool ice_vc_isvalid_ring_len(u16 ring_len) -{ - return ring_len == 0 || - (ring_len >= ICE_MIN_NUM_DESC && - ring_len <= ICE_MAX_NUM_DESC && - !(ring_len % ICE_REQ_DESC_MULTIPLE)); -} - -/** - * ice_vc_validate_pattern - * @vf: pointer to the VF info - * @proto: virtchnl protocol headers - * - * validate the pattern is supported or not. - * - * Return: true on success, false on error. - */ -bool -ice_vc_validate_pattern(struct ice_vf *vf, struct virtchnl_proto_hdrs *proto) -{ - bool is_ipv4 = false; - bool is_ipv6 = false; - bool is_udp = false; - u16 ptype = -1; - int i = 0; - - while (i < proto->count && - proto->proto_hdr[i].type != VIRTCHNL_PROTO_HDR_NONE) { - switch (proto->proto_hdr[i].type) { - case VIRTCHNL_PROTO_HDR_ETH: - ptype = ICE_PTYPE_MAC_PAY; - break; - case VIRTCHNL_PROTO_HDR_IPV4: - ptype = ICE_PTYPE_IPV4_PAY; - is_ipv4 = true; - break; - case VIRTCHNL_PROTO_HDR_IPV6: - ptype = ICE_PTYPE_IPV6_PAY; - is_ipv6 = true; - break; - case VIRTCHNL_PROTO_HDR_UDP: - if (is_ipv4) - ptype = ICE_PTYPE_IPV4_UDP_PAY; - else if (is_ipv6) - ptype = ICE_PTYPE_IPV6_UDP_PAY; - is_udp = true; - break; - case VIRTCHNL_PROTO_HDR_TCP: - if (is_ipv4) - ptype = ICE_PTYPE_IPV4_TCP_PAY; - else if (is_ipv6) - ptype = ICE_PTYPE_IPV6_TCP_PAY; - break; - case VIRTCHNL_PROTO_HDR_SCTP: - if (is_ipv4) - ptype = ICE_PTYPE_IPV4_SCTP_PAY; - else if (is_ipv6) - ptype = ICE_PTYPE_IPV6_SCTP_PAY; - break; - case VIRTCHNL_PROTO_HDR_GTPU_IP: - case VIRTCHNL_PROTO_HDR_GTPU_EH: - if (is_ipv4) - ptype = ICE_MAC_IPV4_GTPU; - else if (is_ipv6) - ptype = ICE_MAC_IPV6_GTPU; - goto out; - case VIRTCHNL_PROTO_HDR_L2TPV3: - if (is_ipv4) - ptype = ICE_MAC_IPV4_L2TPV3; - else if (is_ipv6) - ptype = ICE_MAC_IPV6_L2TPV3; - goto out; - case VIRTCHNL_PROTO_HDR_ESP: - if (is_ipv4) - ptype = is_udp ? ICE_MAC_IPV4_NAT_T_ESP : - ICE_MAC_IPV4_ESP; - else if (is_ipv6) - ptype = is_udp ? ICE_MAC_IPV6_NAT_T_ESP : - ICE_MAC_IPV6_ESP; - goto out; - case VIRTCHNL_PROTO_HDR_AH: - if (is_ipv4) - ptype = ICE_MAC_IPV4_AH; - else if (is_ipv6) - ptype = ICE_MAC_IPV6_AH; - goto out; - case VIRTCHNL_PROTO_HDR_PFCP: - if (is_ipv4) - ptype = ICE_MAC_IPV4_PFCP_SESSION; - else if (is_ipv6) - ptype = ICE_MAC_IPV6_PFCP_SESSION; - goto out; - default: - break; - } - i++; - } - -out: - return ice_hw_ptype_ena(&vf->pf->hw, ptype); -} - -/** - * ice_vc_parse_rss_cfg - parses hash fields and headers from - * a specific virtchnl RSS cfg - * @hw: pointer to the hardware - * @rss_cfg: pointer to the virtchnl RSS cfg - * @addl_hdrs: pointer to the protocol header fields (ICE_FLOW_SEG_HDR_*) - * to configure - * @hash_flds: pointer to the hash bit fields (ICE_FLOW_HASH_*) to configure - * - * Return true if all the protocol header and hash fields in the RSS cfg could - * be parsed, else return false - * - * This function parses the virtchnl RSS cfg to be the intended - * hash fields and the intended header for RSS configuration - */ -static bool -ice_vc_parse_rss_cfg(struct ice_hw *hw, struct virtchnl_rss_cfg *rss_cfg, - u32 *addl_hdrs, u64 *hash_flds) -{ - const struct ice_vc_hash_field_match_type *hf_list; - const struct ice_vc_hdr_match_type *hdr_list; - int i, hf_list_len, hdr_list_len; - - hf_list = ice_vc_hash_field_list; - hf_list_len = ARRAY_SIZE(ice_vc_hash_field_list); - hdr_list = ice_vc_hdr_list; - hdr_list_len = ARRAY_SIZE(ice_vc_hdr_list); - - for (i = 0; i < rss_cfg->proto_hdrs.count; i++) { - struct virtchnl_proto_hdr *proto_hdr = - &rss_cfg->proto_hdrs.proto_hdr[i]; - bool hdr_found = false; - int j; - - /* Find matched ice headers according to virtchnl headers. */ - for (j = 0; j < hdr_list_len; j++) { - struct ice_vc_hdr_match_type hdr_map = hdr_list[j]; - - if (proto_hdr->type == hdr_map.vc_hdr) { - *addl_hdrs |= hdr_map.ice_hdr; - hdr_found = true; - } - } - - if (!hdr_found) - return false; - - /* Find matched ice hash fields according to - * virtchnl hash fields. - */ - for (j = 0; j < hf_list_len; j++) { - struct ice_vc_hash_field_match_type hf_map = hf_list[j]; - - if (proto_hdr->type == hf_map.vc_hdr && - proto_hdr->field_selector == hf_map.vc_hash_field) { - *hash_flds |= hf_map.ice_hash_field; - break; - } - } - } - - return true; -} - -/** - * ice_vf_adv_rss_offload_ena - determine if capabilities support advanced - * RSS offloads - * @caps: VF driver negotiated capabilities - * - * Return true if VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability is set, - * else return false - */ -static bool ice_vf_adv_rss_offload_ena(u32 caps) -{ - return !!(caps & VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF); -} - -/** - * ice_vc_handle_rss_cfg - * @vf: pointer to the VF info - * @msg: pointer to the message buffer - * @add: add a RSS config if true, otherwise delete a RSS config - * - * This function adds/deletes a RSS config - */ -static int ice_vc_handle_rss_cfg(struct ice_vf *vf, u8 *msg, bool add) -{ - u32 v_opcode = add ? VIRTCHNL_OP_ADD_RSS_CFG : VIRTCHNL_OP_DEL_RSS_CFG; - struct virtchnl_rss_cfg *rss_cfg = (struct virtchnl_rss_cfg *)msg; - enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; - struct device *dev = ice_pf_to_dev(vf->pf); - struct ice_hw *hw = &vf->pf->hw; - struct ice_vsi *vsi; - - if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) { - dev_dbg(dev, "VF %d attempting to configure RSS, but RSS is not supported by the PF\n", - vf->vf_id); - v_ret = VIRTCHNL_STATUS_ERR_NOT_SUPPORTED; - goto error_param; - } - - if (!ice_vf_adv_rss_offload_ena(vf->driver_caps)) { - dev_dbg(dev, "VF %d attempting to configure RSS, but Advanced RSS offload is not supported\n", - vf->vf_id); - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (rss_cfg->proto_hdrs.count > VIRTCHNL_MAX_NUM_PROTO_HDRS || - rss_cfg->rss_algorithm < VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC || - rss_cfg->rss_algorithm > VIRTCHNL_RSS_ALG_XOR_SYMMETRIC) { - dev_dbg(dev, "VF %d attempting to configure RSS, but RSS configuration is not valid\n", - vf->vf_id); - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - vsi = ice_get_vf_vsi(vf); - if (!vsi) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (!ice_vc_validate_pattern(vf, &rss_cfg->proto_hdrs)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (rss_cfg->rss_algorithm == VIRTCHNL_RSS_ALG_R_ASYMMETRIC) { - struct ice_vsi_ctx *ctx; - u8 lut_type, hash_type; - int status; - - lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_VSI; - hash_type = add ? ICE_AQ_VSI_Q_OPT_RSS_XOR : - ICE_AQ_VSI_Q_OPT_RSS_TPLZ; - - ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); - if (!ctx) { - v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; - goto error_param; - } - - ctx->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_M); - - /* Preserve existing queueing option setting */ - ctx->info.q_opt_rss |= (vsi->info.q_opt_rss & - ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_M); - ctx->info.q_opt_tc = vsi->info.q_opt_tc; - ctx->info.q_opt_flags = vsi->info.q_opt_rss; - - ctx->info.valid_sections = - cpu_to_le16(ICE_AQ_VSI_PROP_Q_OPT_VALID); - - status = ice_update_vsi(hw, vsi->idx, ctx, NULL); - if (status) { - dev_err(dev, "update VSI for RSS failed, err %d aq_err %s\n", - status, ice_aq_str(hw->adminq.sq_last_status)); - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - } else { - vsi->info.q_opt_rss = ctx->info.q_opt_rss; - } - - kfree(ctx); - } else { - u32 addl_hdrs = ICE_FLOW_SEG_HDR_NONE; - u64 hash_flds = ICE_HASH_INVALID; - - if (!ice_vc_parse_rss_cfg(hw, rss_cfg, &addl_hdrs, - &hash_flds)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (add) { - if (ice_add_rss_cfg(hw, vsi->idx, hash_flds, - addl_hdrs)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - dev_err(dev, "ice_add_rss_cfg failed for vsi = %d, v_ret = %d\n", - vsi->vsi_num, v_ret); - } - } else { - int status; - - status = ice_rem_rss_cfg(hw, vsi->idx, hash_flds, - addl_hdrs); - /* We just ignore -ENOENT, because if two configurations - * share the same profile remove one of them actually - * removes both, since the profile is deleted. - */ - if (status && status != -ENOENT) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - dev_err(dev, "ice_rem_rss_cfg failed for VF ID:%d, error:%d\n", - vf->vf_id, status); - } - } - } - -error_param: - return ice_vc_send_msg_to_vf(vf, v_opcode, v_ret, NULL, 0); -} - -/** - * ice_vc_config_rss_key - * @vf: pointer to the VF info - * @msg: pointer to the msg buffer - * - * Configure the VF's RSS key - */ -static int ice_vc_config_rss_key(struct ice_vf *vf, u8 *msg) -{ - enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; - struct virtchnl_rss_key *vrk = - (struct virtchnl_rss_key *)msg; - struct ice_vsi *vsi; - - if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (!ice_vc_isvalid_vsi_id(vf, vrk->vsi_id)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (vrk->key_len != ICE_VSIQF_HKEY_ARRAY_SIZE) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - vsi = ice_get_vf_vsi(vf); - if (!vsi) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (ice_set_rss_key(vsi, vrk->key)) - v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR; -error_param: - return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_KEY, v_ret, - NULL, 0); -} - -/** - * ice_vc_config_rss_lut - * @vf: pointer to the VF info - * @msg: pointer to the msg buffer - * - * Configure the VF's RSS LUT - */ -static int ice_vc_config_rss_lut(struct ice_vf *vf, u8 *msg) -{ - struct virtchnl_rss_lut *vrl = (struct virtchnl_rss_lut *)msg; - enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; - struct ice_vsi *vsi; - - if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (!ice_vc_isvalid_vsi_id(vf, vrl->vsi_id)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (vrl->lut_entries != ICE_VSIQF_HLUT_ARRAY_SIZE) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - vsi = ice_get_vf_vsi(vf); - if (!vsi) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (ice_set_rss_lut(vsi, vrl->lut, ICE_VSIQF_HLUT_ARRAY_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, - NULL, 0); -} - -/** - * ice_wait_on_vf_reset - poll to make sure a given VF is ready after reset - * @vf: The VF being resseting - * - * The max poll time is about ~800ms, which is about the maximum time it takes - * for a VF to be reset and/or a VF driver to be removed. - */ -static void ice_wait_on_vf_reset(struct ice_vf *vf) -{ - int i; - - for (i = 0; i < ICE_MAX_VF_RESET_TRIES; i++) { - if (test_bit(ICE_VF_STATE_INIT, vf->vf_states)) - break; - msleep(ICE_MAX_VF_RESET_SLEEP_MS); - } -} - -/** - * ice_check_vf_ready_for_cfg - check if VF is ready to be configured/queried - * @vf: VF to check if it's ready to be configured/queried - * - * The purpose of this function is to make sure the VF is not in reset, not - * disabled, and initialized so it can be configured and/or queried by a host - * administrator. - */ -int ice_check_vf_ready_for_cfg(struct ice_vf *vf) -{ - struct ice_pf *pf; - - ice_wait_on_vf_reset(vf); - - if (ice_is_vf_disabled(vf)) - return -EINVAL; - - pf = vf->pf; - if (ice_check_vf_init(pf, vf)) - return -EBUSY; - - return 0; -} - -/** - * ice_set_vf_spoofchk - * @netdev: network interface device structure - * @vf_id: VF identifier - * @ena: flag to enable or disable feature - * - * Enable or disable VF spoof checking - */ -int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena) -{ - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_pf *pf = np->vsi->back; - struct ice_vsi_ctx *ctx; - struct ice_vsi *vf_vsi; - struct device *dev; - struct ice_vf *vf; - int ret; - - dev = ice_pf_to_dev(pf); - if (ice_validate_vf_id(pf, vf_id)) - return -EINVAL; - - vf = &pf->vf[vf_id]; - ret = ice_check_vf_ready_for_cfg(vf); - if (ret) - return ret; - - vf_vsi = ice_get_vf_vsi(vf); - if (!vf_vsi) { - netdev_err(netdev, "VSI %d for VF %d is null\n", - vf->lan_vsi_idx, vf->vf_id); - return -EINVAL; - } - - if (vf_vsi->type != ICE_VSI_VF) { - netdev_err(netdev, "Type %d of VSI %d for VF %d is no ICE_VSI_VF\n", - vf_vsi->type, vf_vsi->vsi_num, vf->vf_id); - return -ENODEV; - } - - if (ena == vf->spoofchk) { - dev_dbg(dev, "VF spoofchk already %s\n", ena ? "ON" : "OFF"); - return 0; - } - - ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); - if (!ctx) - return -ENOMEM; - - ctx->info.sec_flags = vf_vsi->info.sec_flags; - ctx->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID); - if (ena) { - ctx->info.sec_flags |= - ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF | - (ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA << - ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S); - } else { - ctx->info.sec_flags &= - ~(ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF | - (ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA << - ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S)); - } - - ret = ice_update_vsi(&pf->hw, vf_vsi->idx, ctx, NULL); - if (ret) { - dev_err(dev, "Failed to %sable spoofchk on VF %d VSI %d\n error %d\n", - ena ? "en" : "dis", vf->vf_id, vf_vsi->vsi_num, ret); - goto out; - } - - /* only update spoofchk state and VSI context on success */ - vf_vsi->info.sec_flags = ctx->info.sec_flags; - vf->spoofchk = ena; - -out: - kfree(ctx); - return ret; -} - -/** - * ice_is_any_vf_in_promisc - check if any VF(s) are in promiscuous mode - * @pf: PF structure for accessing VF(s) - * - * Return false if no VF(s) are in unicast and/or multicast promiscuous mode, - * else return true - */ -bool ice_is_any_vf_in_promisc(struct ice_pf *pf) -{ - int vf_idx; - - ice_for_each_vf(pf, vf_idx) { - struct ice_vf *vf = &pf->vf[vf_idx]; - - /* found a VF that has promiscuous mode configured */ - if (test_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states) || - test_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states)) - return true; - } - - return false; -} - -/** - * ice_vc_cfg_promiscuous_mode_msg - * @vf: pointer to the VF info - * @msg: pointer to the msg buffer - * - * called from the VF to configure VF VSIs promiscuous mode - */ -static int ice_vc_cfg_promiscuous_mode_msg(struct ice_vf *vf, u8 *msg) -{ - enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; - bool rm_promisc, alluni = false, allmulti = false; - struct virtchnl_promisc_info *info = - (struct virtchnl_promisc_info *)msg; - int mcast_err = 0, ucast_err = 0; - struct ice_pf *pf = vf->pf; - struct ice_vsi *vsi; - struct device *dev; - int ret = 0; - - if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (!ice_vc_isvalid_vsi_id(vf, info->vsi_id)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - vsi = ice_get_vf_vsi(vf); - if (!vsi) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - dev = ice_pf_to_dev(pf); - if (!test_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps)) { - dev_err(dev, "Unprivileged VF %d is attempting to configure promiscuous mode\n", - vf->vf_id); - /* Leave v_ret alone, lie to the VF on purpose. */ - goto error_param; - } - - if (info->flags & FLAG_VF_UNICAST_PROMISC) - alluni = true; - - if (info->flags & FLAG_VF_MULTICAST_PROMISC) - allmulti = true; - - rm_promisc = !allmulti && !alluni; - - if (vsi->num_vlan || vf->port_vlan_info) { - if (rm_promisc) - ret = ice_cfg_vlan_pruning(vsi, true); - else - ret = ice_cfg_vlan_pruning(vsi, false); - if (ret) { - dev_err(dev, "Failed to configure VLAN pruning in promiscuous mode\n"); - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - } - - if (!test_bit(ICE_FLAG_VF_TRUE_PROMISC_ENA, pf->flags)) { - bool set_dflt_vsi = alluni || allmulti; - - if (set_dflt_vsi && !ice_is_dflt_vsi_in_use(pf->first_sw)) - /* only attempt to set the default forwarding VSI if - * it's not currently set - */ - ret = ice_set_dflt_vsi(pf->first_sw, vsi); - else if (!set_dflt_vsi && - ice_is_vsi_dflt_vsi(pf->first_sw, vsi)) - /* only attempt to free the default forwarding VSI if we - * are the owner - */ - ret = ice_clear_dflt_vsi(pf->first_sw); - - if (ret) { - dev_err(dev, "%sable VF %d as the default VSI failed, error %d\n", - set_dflt_vsi ? "en" : "dis", vf->vf_id, ret); - v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR; - goto error_param; - } - } else { - u8 mcast_m, ucast_m; - - if (vf->port_vlan_info || vsi->num_vlan > 1) { - mcast_m = ICE_MCAST_VLAN_PROMISC_BITS; - ucast_m = ICE_UCAST_VLAN_PROMISC_BITS; - } else { - mcast_m = ICE_MCAST_PROMISC_BITS; - ucast_m = ICE_UCAST_PROMISC_BITS; - } - - if (alluni) - ucast_err = ice_vf_set_vsi_promisc(vf, vsi, ucast_m); - else - ucast_err = ice_vf_clear_vsi_promisc(vf, vsi, ucast_m); - - if (allmulti) - mcast_err = ice_vf_set_vsi_promisc(vf, vsi, mcast_m); - else - mcast_err = ice_vf_clear_vsi_promisc(vf, vsi, mcast_m); - - if (ucast_err || mcast_err) - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - } - - if (!mcast_err) { - if (allmulti && - !test_and_set_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states)) - dev_info(dev, "VF %u successfully set multicast promiscuous mode\n", - vf->vf_id); - else if (!allmulti && test_and_clear_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states)) - dev_info(dev, "VF %u successfully unset multicast promiscuous mode\n", - vf->vf_id); - } - - if (!ucast_err) { - if (alluni && !test_and_set_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states)) - dev_info(dev, "VF %u successfully set unicast promiscuous mode\n", - vf->vf_id); - else if (!alluni && test_and_clear_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states)) - dev_info(dev, "VF %u successfully unset unicast promiscuous mode\n", - vf->vf_id); - } - -error_param: - return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE, - v_ret, NULL, 0); -} - -/** - * ice_vc_get_stats_msg - * @vf: pointer to the VF info - * @msg: pointer to the msg buffer - * - * called from the VF to get VSI stats - */ -static int ice_vc_get_stats_msg(struct ice_vf *vf, u8 *msg) -{ - enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; - struct virtchnl_queue_select *vqs = - (struct virtchnl_queue_select *)msg; - struct ice_eth_stats stats = { 0 }; - struct ice_vsi *vsi; - - if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (!ice_vc_isvalid_vsi_id(vf, vqs->vsi_id)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - vsi = ice_get_vf_vsi(vf); - if (!vsi) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - ice_update_eth_stats(vsi); - - stats = vsi->eth_stats; - -error_param: - /* send the response to the VF */ - return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_STATS, v_ret, - (u8 *)&stats, sizeof(stats)); -} - -/** - * ice_vc_validate_vqs_bitmaps - validate Rx/Tx queue bitmaps from VIRTCHNL - * @vqs: virtchnl_queue_select structure containing bitmaps to validate - * - * Return true on successful validation, else false - */ -static bool ice_vc_validate_vqs_bitmaps(struct virtchnl_queue_select *vqs) -{ - if ((!vqs->rx_queues && !vqs->tx_queues) || - vqs->rx_queues >= BIT(ICE_MAX_RSS_QS_PER_VF) || - vqs->tx_queues >= BIT(ICE_MAX_RSS_QS_PER_VF)) - return false; - - return true; -} - -/** - * ice_vf_ena_txq_interrupt - enable Tx queue interrupt via QINT_TQCTL - * @vsi: VSI of the VF to configure - * @q_idx: VF queue index used to determine the queue in the PF's space - */ -static void ice_vf_ena_txq_interrupt(struct ice_vsi *vsi, u32 q_idx) -{ - struct ice_hw *hw = &vsi->back->hw; - u32 pfq = vsi->txq_map[q_idx]; - u32 reg; - - reg = rd32(hw, QINT_TQCTL(pfq)); - - /* MSI-X index 0 in the VF's space is always for the OICR, which means - * this is most likely a poll mode VF driver, so don't enable an - * interrupt that was never configured via VIRTCHNL_OP_CONFIG_IRQ_MAP - */ - if (!(reg & QINT_TQCTL_MSIX_INDX_M)) - return; - - wr32(hw, QINT_TQCTL(pfq), reg | QINT_TQCTL_CAUSE_ENA_M); -} - -/** - * ice_vf_ena_rxq_interrupt - enable Tx queue interrupt via QINT_RQCTL - * @vsi: VSI of the VF to configure - * @q_idx: VF queue index used to determine the queue in the PF's space - */ -static void ice_vf_ena_rxq_interrupt(struct ice_vsi *vsi, u32 q_idx) -{ - struct ice_hw *hw = &vsi->back->hw; - u32 pfq = vsi->rxq_map[q_idx]; - u32 reg; - - reg = rd32(hw, QINT_RQCTL(pfq)); - - /* MSI-X index 0 in the VF's space is always for the OICR, which means - * this is most likely a poll mode VF driver, so don't enable an - * interrupt that was never configured via VIRTCHNL_OP_CONFIG_IRQ_MAP - */ - if (!(reg & QINT_RQCTL_MSIX_INDX_M)) - return; - - wr32(hw, QINT_RQCTL(pfq), reg | QINT_RQCTL_CAUSE_ENA_M); -} - -/** - * ice_vc_ena_qs_msg - * @vf: pointer to the VF info - * @msg: pointer to the msg buffer - * - * called from the VF to enable all or specific queue(s) - */ -static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg) -{ - enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; - struct virtchnl_queue_select *vqs = - (struct virtchnl_queue_select *)msg; - struct ice_vsi *vsi; - unsigned long q_map; - u16 vf_q_id; - - if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (!ice_vc_isvalid_vsi_id(vf, vqs->vsi_id)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (!ice_vc_validate_vqs_bitmaps(vqs)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - vsi = ice_get_vf_vsi(vf); - if (!vsi) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - /* Enable only Rx rings, Tx rings were enabled by the FW when the - * Tx queue group list was configured and the context bits were - * programmed using ice_vsi_cfg_txqs - */ - q_map = vqs->rx_queues; - for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { - if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - /* Skip queue if enabled */ - if (test_bit(vf_q_id, vf->rxq_ena)) - continue; - - if (ice_vsi_ctrl_one_rx_ring(vsi, true, vf_q_id, true)) { - dev_err(ice_pf_to_dev(vsi->back), "Failed to enable Rx ring %d on VSI %d\n", - vf_q_id, vsi->vsi_num); - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - ice_vf_ena_rxq_interrupt(vsi, vf_q_id); - set_bit(vf_q_id, vf->rxq_ena); - } - - q_map = vqs->tx_queues; - for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { - if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - /* Skip queue if enabled */ - if (test_bit(vf_q_id, vf->txq_ena)) - continue; - - ice_vf_ena_txq_interrupt(vsi, vf_q_id); - set_bit(vf_q_id, vf->txq_ena); - } - - /* Set flag to indicate that queues are enabled */ - if (v_ret == VIRTCHNL_STATUS_SUCCESS) - set_bit(ICE_VF_STATE_QS_ENA, vf->vf_states); - -error_param: - /* send the response to the VF */ - return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ENABLE_QUEUES, v_ret, - NULL, 0); -} - -/** - * ice_vc_dis_qs_msg - * @vf: pointer to the VF info - * @msg: pointer to the msg buffer - * - * called from the VF to disable all or specific - * queue(s) - */ -static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) -{ - enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; - struct virtchnl_queue_select *vqs = - (struct virtchnl_queue_select *)msg; - struct ice_vsi *vsi; - unsigned long q_map; - u16 vf_q_id; - - if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) && - !test_bit(ICE_VF_STATE_QS_ENA, vf->vf_states)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (!ice_vc_isvalid_vsi_id(vf, vqs->vsi_id)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (!ice_vc_validate_vqs_bitmaps(vqs)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - vsi = ice_get_vf_vsi(vf); - if (!vsi) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (vqs->tx_queues) { - q_map = vqs->tx_queues; - - for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { - struct ice_tx_ring *ring = vsi->tx_rings[vf_q_id]; - struct ice_txq_meta txq_meta = { 0 }; - - if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - /* Skip queue if not enabled */ - if (!test_bit(vf_q_id, vf->txq_ena)) - continue; - - ice_fill_txq_meta(vsi, ring, &txq_meta); - - if (ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, vf->vf_id, - ring, &txq_meta)) { - dev_err(ice_pf_to_dev(vsi->back), "Failed to stop Tx ring %d on VSI %d\n", - vf_q_id, vsi->vsi_num); - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - /* Clear enabled queues flag */ - clear_bit(vf_q_id, vf->txq_ena); - } - } - - q_map = vqs->rx_queues; - /* speed up Rx queue disable by batching them if possible */ - if (q_map && - bitmap_equal(&q_map, vf->rxq_ena, ICE_MAX_RSS_QS_PER_VF)) { - if (ice_vsi_stop_all_rx_rings(vsi)) { - dev_err(ice_pf_to_dev(vsi->back), "Failed to stop all Rx rings on VSI %d\n", - vsi->vsi_num); - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - bitmap_zero(vf->rxq_ena, ICE_MAX_RSS_QS_PER_VF); - } else if (q_map) { - for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { - if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - /* Skip queue if not enabled */ - if (!test_bit(vf_q_id, vf->rxq_ena)) - continue; - - if (ice_vsi_ctrl_one_rx_ring(vsi, false, vf_q_id, - true)) { - dev_err(ice_pf_to_dev(vsi->back), "Failed to stop Rx ring %d on VSI %d\n", - vf_q_id, vsi->vsi_num); - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - /* Clear enabled queues flag */ - clear_bit(vf_q_id, vf->rxq_ena); - } - } - - /* Clear enabled queues flag */ - if (v_ret == VIRTCHNL_STATUS_SUCCESS && ice_vf_has_no_qs_ena(vf)) - clear_bit(ICE_VF_STATE_QS_ENA, vf->vf_states); - -error_param: - /* send the response to the VF */ - return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DISABLE_QUEUES, v_ret, - NULL, 0); -} - -/** - * ice_cfg_interrupt - * @vf: pointer to the VF info - * @vsi: the VSI being configured - * @vector_id: vector ID - * @map: vector map for mapping vectors to queues - * @q_vector: structure for interrupt vector - * configure the IRQ to queue map - */ -static int -ice_cfg_interrupt(struct ice_vf *vf, struct ice_vsi *vsi, u16 vector_id, - struct virtchnl_vector_map *map, - struct ice_q_vector *q_vector) -{ - u16 vsi_q_id, vsi_q_id_idx; - unsigned long qmap; - - q_vector->num_ring_rx = 0; - q_vector->num_ring_tx = 0; - - qmap = map->rxq_map; - for_each_set_bit(vsi_q_id_idx, &qmap, ICE_MAX_RSS_QS_PER_VF) { - vsi_q_id = vsi_q_id_idx; - - if (!ice_vc_isvalid_q_id(vf, vsi->vsi_num, vsi_q_id)) - return VIRTCHNL_STATUS_ERR_PARAM; - - q_vector->num_ring_rx++; - q_vector->rx.itr_idx = map->rxitr_idx; - vsi->rx_rings[vsi_q_id]->q_vector = q_vector; - ice_cfg_rxq_interrupt(vsi, vsi_q_id, vector_id, - q_vector->rx.itr_idx); - } - - qmap = map->txq_map; - for_each_set_bit(vsi_q_id_idx, &qmap, ICE_MAX_RSS_QS_PER_VF) { - vsi_q_id = vsi_q_id_idx; - - if (!ice_vc_isvalid_q_id(vf, vsi->vsi_num, vsi_q_id)) - return VIRTCHNL_STATUS_ERR_PARAM; - - q_vector->num_ring_tx++; - q_vector->tx.itr_idx = map->txitr_idx; - vsi->tx_rings[vsi_q_id]->q_vector = q_vector; - ice_cfg_txq_interrupt(vsi, vsi_q_id, vector_id, - q_vector->tx.itr_idx); - } - - return VIRTCHNL_STATUS_SUCCESS; -} - -/** - * ice_vc_cfg_irq_map_msg - * @vf: pointer to the VF info - * @msg: pointer to the msg buffer - * - * called from the VF to configure the IRQ to queue map - */ -static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg) -{ - enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; - 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; - - irqmap_info = (struct virtchnl_irq_map_info *)msg; - num_q_vectors_mapped = irqmap_info->num_vectors; - - /* Check to make sure number of VF vectors mapped is not greater than - * number of VF vectors originally allocated, and check that - * there is actually at least a single VF queue vector mapped - */ - if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) || - pf->num_msix_per_vf < num_q_vectors_mapped || - !num_q_vectors_mapped) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - vsi = ice_get_vf_vsi(vf); - if (!vsi) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - for (i = 0; i < num_q_vectors_mapped; i++) { - struct ice_q_vector *q_vector; - - map = &irqmap_info->vecmap[i]; - - vector_id = map->vector_id; - vsi_id = map->vsi_id; - /* 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->num_msix_per_vf) || - !ice_vc_isvalid_vsi_id(vf, vsi_id) || - (!vector_id && (map->rxq_map || map->txq_map))) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - /* No need to map VF miscellaneous or rogue vector */ - if (!vector_id) - continue; - - /* Subtract non queue vector from vector_id passed by VF - * to get actual number of VSI queue vector array index - */ - q_vector = vsi->q_vectors[vector_id - ICE_NONQ_VECS_VF]; - if (!q_vector) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - /* lookout for the invalid queue index */ - v_ret = (enum virtchnl_status_code) - ice_cfg_interrupt(vf, vsi, vector_id, map, q_vector); - if (v_ret) - goto error_param; - } - -error_param: - /* send the response to the VF */ - return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_IRQ_MAP, v_ret, - NULL, 0); -} - -/** - * ice_vc_cfg_qs_msg - * @vf: pointer to the VF info - * @msg: pointer to the msg buffer - * - * called from the VF to configure the Rx/Tx queues - */ -static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) -{ - enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; - struct virtchnl_vsi_queue_config_info *qci = - (struct virtchnl_vsi_queue_config_info *)msg; - struct virtchnl_queue_pair_info *qpi; - struct ice_pf *pf = vf->pf; - struct ice_vsi *vsi; - int i, q_idx; - - if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (!ice_vc_isvalid_vsi_id(vf, qci->vsi_id)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - vsi = ice_get_vf_vsi(vf); - if (!vsi) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (qci->num_queue_pairs > ICE_MAX_RSS_QS_PER_VF || - qci->num_queue_pairs > min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)) { - dev_err(ice_pf_to_dev(pf), "VF-%d requesting more than supported number of queues: %d\n", - vf->vf_id, min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)); - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - for (i = 0; i < qci->num_queue_pairs; i++) { - qpi = &qci->qpair[i]; - if (qpi->txq.vsi_id != qci->vsi_id || - qpi->rxq.vsi_id != qci->vsi_id || - qpi->rxq.queue_id != qpi->txq.queue_id || - qpi->txq.headwb_enabled || - !ice_vc_isvalid_ring_len(qpi->txq.ring_len) || - !ice_vc_isvalid_ring_len(qpi->rxq.ring_len) || - !ice_vc_isvalid_q_id(vf, qci->vsi_id, qpi->txq.queue_id)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - q_idx = qpi->rxq.queue_id; - - /* make sure selected "q_idx" is in valid range of queues - * for selected "vsi" - */ - if (q_idx >= vsi->alloc_txq || q_idx >= vsi->alloc_rxq) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - /* copy Tx queue info from VF into VSI */ - if (qpi->txq.ring_len > 0) { - vsi->tx_rings[i]->dma = qpi->txq.dma_ring_addr; - vsi->tx_rings[i]->count = qpi->txq.ring_len; - if (ice_vsi_cfg_single_txq(vsi, vsi->tx_rings, q_idx)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - } - - /* copy Rx queue info from VF into VSI */ - if (qpi->rxq.ring_len > 0) { - u16 max_frame_size = ice_vc_get_max_frame_size(vf); - - vsi->rx_rings[i]->dma = qpi->rxq.dma_ring_addr; - vsi->rx_rings[i]->count = qpi->rxq.ring_len; - - if (qpi->rxq.databuffer_size != 0 && - (qpi->rxq.databuffer_size > ((16 * 1024) - 128) || - qpi->rxq.databuffer_size < 1024)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - vsi->rx_buf_len = qpi->rxq.databuffer_size; - vsi->rx_rings[i]->rx_buf_len = vsi->rx_buf_len; - if (qpi->rxq.max_pkt_size > max_frame_size || - qpi->rxq.max_pkt_size < 64) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - vsi->max_frame = qpi->rxq.max_pkt_size; - /* add space for the port VLAN since the VF driver is not - * expected to account for it in the MTU calculation - */ - if (vf->port_vlan_info) - vsi->max_frame += VLAN_HLEN; - - if (ice_vsi_cfg_single_rxq(vsi, q_idx)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - } - } - -error_param: - /* send the response to the VF */ - return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_VSI_QUEUES, v_ret, - NULL, 0); -} - -/** - * ice_is_vf_trusted - * @vf: pointer to the VF info - */ -static bool ice_is_vf_trusted(struct ice_vf *vf) -{ - return test_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps); -} - -/** - * ice_can_vf_change_mac - * @vf: pointer to the VF info - * - * Return true if the VF is allowed to change its MAC filters, false otherwise - */ -static bool ice_can_vf_change_mac(struct ice_vf *vf) -{ - /* If the VF MAC address has been set administratively (via the - * ndo_set_vf_mac command), then deny permission to the VF to - * add/delete unicast MAC addresses, unless the VF is trusted - */ - if (vf->pf_set_mac && !ice_is_vf_trusted(vf)) - return false; - - return true; -} - -/** - * ice_vc_ether_addr_type - get type of virtchnl_ether_addr - * @vc_ether_addr: used to extract the type - */ -static u8 -ice_vc_ether_addr_type(struct virtchnl_ether_addr *vc_ether_addr) -{ - return (vc_ether_addr->type & VIRTCHNL_ETHER_ADDR_TYPE_MASK); -} - -/** - * ice_is_vc_addr_legacy - check if the MAC address is from an older VF - * @vc_ether_addr: VIRTCHNL structure that contains MAC and type - */ -static bool -ice_is_vc_addr_legacy(struct virtchnl_ether_addr *vc_ether_addr) -{ - u8 type = ice_vc_ether_addr_type(vc_ether_addr); - - return (type == VIRTCHNL_ETHER_ADDR_LEGACY); -} - -/** - * ice_is_vc_addr_primary - check if the MAC address is the VF's primary MAC - * @vc_ether_addr: VIRTCHNL structure that contains MAC and type - * - * This function should only be called when the MAC address in - * virtchnl_ether_addr is a valid unicast MAC - */ -static bool -ice_is_vc_addr_primary(struct virtchnl_ether_addr __maybe_unused *vc_ether_addr) -{ - u8 type = ice_vc_ether_addr_type(vc_ether_addr); - - return (type == VIRTCHNL_ETHER_ADDR_PRIMARY); -} - -/** - * ice_vfhw_mac_add - update the VF's cached hardware MAC if allowed - * @vf: VF to update - * @vc_ether_addr: structure from VIRTCHNL with MAC to add - */ -static void -ice_vfhw_mac_add(struct ice_vf *vf, struct virtchnl_ether_addr *vc_ether_addr) -{ - u8 *mac_addr = vc_ether_addr->addr; - - if (!is_valid_ether_addr(mac_addr)) - return; - - /* only allow legacy VF drivers to set the device and hardware MAC if it - * is zero and allow new VF drivers to set the hardware MAC if the type - * was correctly specified over VIRTCHNL - */ - if ((ice_is_vc_addr_legacy(vc_ether_addr) && - is_zero_ether_addr(vf->hw_lan_addr.addr)) || - ice_is_vc_addr_primary(vc_ether_addr)) { - ether_addr_copy(vf->dev_lan_addr.addr, mac_addr); - ether_addr_copy(vf->hw_lan_addr.addr, mac_addr); - } - - /* hardware and device MACs are already set, but its possible that the - * VF driver sent the VIRTCHNL_OP_ADD_ETH_ADDR message before the - * VIRTCHNL_OP_DEL_ETH_ADDR when trying to update its MAC, so save it - * away for the legacy VF driver case as it will be updated in the - * delete flow for this case - */ - if (ice_is_vc_addr_legacy(vc_ether_addr)) { - ether_addr_copy(vf->legacy_last_added_umac.addr, - mac_addr); - vf->legacy_last_added_umac.time_modified = jiffies; - } -} - -/** - * ice_vc_add_mac_addr - attempt to add the MAC address passed in - * @vf: pointer to the VF info - * @vsi: pointer to the VF's VSI - * @vc_ether_addr: VIRTCHNL MAC address structure used to add MAC - */ -static int -ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, - struct virtchnl_ether_addr *vc_ether_addr) -{ - struct device *dev = ice_pf_to_dev(vf->pf); - u8 *mac_addr = vc_ether_addr->addr; - int ret; - - /* device MAC already added */ - if (ether_addr_equal(mac_addr, vf->dev_lan_addr.addr)) - return 0; - - if (is_unicast_ether_addr(mac_addr) && !ice_can_vf_change_mac(vf)) { - dev_err(dev, "VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n"); - return -EPERM; - } - - ret = ice_fltr_add_mac(vsi, mac_addr, ICE_FWD_TO_VSI); - if (ret == -EEXIST) { - dev_dbg(dev, "MAC %pM already exists for VF %d\n", mac_addr, - vf->vf_id); - /* don't return since we might need to update - * the primary MAC in ice_vfhw_mac_add() below - */ - } else if (ret) { - dev_err(dev, "Failed to add MAC %pM for VF %d\n, error %d\n", - mac_addr, vf->vf_id, ret); - return ret; - } else { - vf->num_mac++; - } - - ice_vfhw_mac_add(vf, vc_ether_addr); - - return ret; -} - -/** - * ice_is_legacy_umac_expired - check if last added legacy unicast MAC expired - * @last_added_umac: structure used to check expiration - */ -static bool ice_is_legacy_umac_expired(struct ice_time_mac *last_added_umac) -{ -#define ICE_LEGACY_VF_MAC_CHANGE_EXPIRE_TIME msecs_to_jiffies(3000) - return time_is_before_jiffies(last_added_umac->time_modified + - ICE_LEGACY_VF_MAC_CHANGE_EXPIRE_TIME); -} - -/** - * ice_update_legacy_cached_mac - update cached hardware MAC for legacy VF - * @vf: VF to update - * @vc_ether_addr: structure from VIRTCHNL with MAC to check - * - * only update cached hardware MAC for legacy VF drivers on delete - * because we cannot guarantee order/type of MAC from the VF driver - */ -static void -ice_update_legacy_cached_mac(struct ice_vf *vf, - struct virtchnl_ether_addr *vc_ether_addr) -{ - if (!ice_is_vc_addr_legacy(vc_ether_addr) || - ice_is_legacy_umac_expired(&vf->legacy_last_added_umac)) - return; - - ether_addr_copy(vf->dev_lan_addr.addr, vf->legacy_last_added_umac.addr); - ether_addr_copy(vf->hw_lan_addr.addr, vf->legacy_last_added_umac.addr); -} - -/** - * ice_vfhw_mac_del - update the VF's cached hardware MAC if allowed - * @vf: VF to update - * @vc_ether_addr: structure from VIRTCHNL with MAC to delete - */ -static void -ice_vfhw_mac_del(struct ice_vf *vf, struct virtchnl_ether_addr *vc_ether_addr) -{ - u8 *mac_addr = vc_ether_addr->addr; - - if (!is_valid_ether_addr(mac_addr) || - !ether_addr_equal(vf->dev_lan_addr.addr, mac_addr)) - return; - - /* allow the device MAC to be repopulated in the add flow and don't - * clear the hardware MAC (i.e. hw_lan_addr.addr) here as that is meant - * to be persistent on VM reboot and across driver unload/load, which - * won't work if we clear the hardware MAC here - */ - eth_zero_addr(vf->dev_lan_addr.addr); - - ice_update_legacy_cached_mac(vf, vc_ether_addr); -} - -/** - * ice_vc_del_mac_addr - attempt to delete the MAC address passed in - * @vf: pointer to the VF info - * @vsi: pointer to the VF's VSI - * @vc_ether_addr: VIRTCHNL MAC address structure used to delete MAC - */ -static int -ice_vc_del_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, - struct virtchnl_ether_addr *vc_ether_addr) -{ - struct device *dev = ice_pf_to_dev(vf->pf); - u8 *mac_addr = vc_ether_addr->addr; - int status; - - if (!ice_can_vf_change_mac(vf) && - ether_addr_equal(vf->dev_lan_addr.addr, mac_addr)) - return 0; - - status = ice_fltr_remove_mac(vsi, mac_addr, ICE_FWD_TO_VSI); - if (status == -ENOENT) { - dev_err(dev, "MAC %pM does not exist for VF %d\n", mac_addr, - vf->vf_id); - return -ENOENT; - } else if (status) { - dev_err(dev, "Failed to delete MAC %pM for VF %d, error %d\n", - mac_addr, vf->vf_id, status); - return -EIO; - } - - ice_vfhw_mac_del(vf, vc_ether_addr); - - vf->num_mac--; - - return 0; -} - -/** - * ice_vc_handle_mac_addr_msg - * @vf: pointer to the VF info - * @msg: pointer to the msg buffer - * @set: true if MAC filters are being set, false otherwise - * - * add guest MAC address filter - */ -static int -ice_vc_handle_mac_addr_msg(struct ice_vf *vf, u8 *msg, bool set) -{ - int (*ice_vc_cfg_mac) - (struct ice_vf *vf, struct ice_vsi *vsi, - struct virtchnl_ether_addr *virtchnl_ether_addr); - enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; - struct virtchnl_ether_addr_list *al = - (struct virtchnl_ether_addr_list *)msg; - struct ice_pf *pf = vf->pf; - enum virtchnl_ops vc_op; - struct ice_vsi *vsi; - int i; - - if (set) { - vc_op = VIRTCHNL_OP_ADD_ETH_ADDR; - ice_vc_cfg_mac = ice_vc_add_mac_addr; - } else { - vc_op = VIRTCHNL_OP_DEL_ETH_ADDR; - ice_vc_cfg_mac = ice_vc_del_mac_addr; - } - - if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) || - !ice_vc_isvalid_vsi_id(vf, al->vsi_id)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto handle_mac_exit; - } - - /* If this VF is not privileged, then we can't add more than a - * limited number of addresses. Check to make sure that the - * additions do not push us over the limit. - */ - if (set && !ice_is_vf_trusted(vf) && - (vf->num_mac + al->num_elements) > ICE_MAX_MACADDR_PER_VF) { - dev_err(ice_pf_to_dev(pf), "Can't add more MAC addresses, because VF-%d is not trusted, switch the VF to trusted mode in order to add more functionalities\n", - vf->vf_id); - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto handle_mac_exit; - } - - vsi = ice_get_vf_vsi(vf); - if (!vsi) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto handle_mac_exit; - } - - for (i = 0; i < al->num_elements; i++) { - u8 *mac_addr = al->list[i].addr; - int result; - - if (is_broadcast_ether_addr(mac_addr) || - is_zero_ether_addr(mac_addr)) - continue; - - result = ice_vc_cfg_mac(vf, vsi, &al->list[i]); - if (result == -EEXIST || result == -ENOENT) { - continue; - } else if (result) { - v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR; - goto handle_mac_exit; - } - } - -handle_mac_exit: - /* send the response to the VF */ - return ice_vc_send_msg_to_vf(vf, vc_op, v_ret, NULL, 0); -} - -/** - * ice_vc_add_mac_addr_msg - * @vf: pointer to the VF info - * @msg: pointer to the msg buffer - * - * add guest MAC address filter - */ -static int ice_vc_add_mac_addr_msg(struct ice_vf *vf, u8 *msg) -{ - return ice_vc_handle_mac_addr_msg(vf, msg, true); -} - -/** - * ice_vc_del_mac_addr_msg - * @vf: pointer to the VF info - * @msg: pointer to the msg buffer - * - * remove guest MAC address filter - */ -static int ice_vc_del_mac_addr_msg(struct ice_vf *vf, u8 *msg) -{ - return ice_vc_handle_mac_addr_msg(vf, msg, false); -} - -/** - * ice_vc_request_qs_msg - * @vf: pointer to the VF info - * @msg: pointer to the msg buffer - * - * VFs get a default number of queues but can use this message to request a - * different number. If the request is successful, PF will reset the VF and - * return 0. If unsuccessful, PF will send message informing VF of number of - * available queue pairs via virtchnl message response to VF. - */ -static int ice_vc_request_qs_msg(struct ice_vf *vf, u8 *msg) -{ - enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; - struct virtchnl_vf_res_request *vfres = - (struct virtchnl_vf_res_request *)msg; - u16 req_queues = vfres->num_queue_pairs; - struct ice_pf *pf = vf->pf; - u16 max_allowed_vf_queues; - u16 tx_rx_queue_left; - struct device *dev; - u16 cur_queues; - - dev = ice_pf_to_dev(pf); - if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - cur_queues = vf->num_vf_qs; - tx_rx_queue_left = min_t(u16, ice_get_avail_txq_count(pf), - ice_get_avail_rxq_count(pf)); - max_allowed_vf_queues = tx_rx_queue_left + cur_queues; - if (!req_queues) { - dev_err(dev, "VF %d tried to request 0 queues. Ignoring.\n", - vf->vf_id); - } else if (req_queues > ICE_MAX_RSS_QS_PER_VF) { - dev_err(dev, "VF %d tried to request more than %d queues.\n", - vf->vf_id, ICE_MAX_RSS_QS_PER_VF); - vfres->num_queue_pairs = ICE_MAX_RSS_QS_PER_VF; - } else if (req_queues > cur_queues && - req_queues - cur_queues > tx_rx_queue_left) { - dev_warn(dev, "VF %d requested %u more queues, but only %u left.\n", - vf->vf_id, req_queues - cur_queues, tx_rx_queue_left); - vfres->num_queue_pairs = min_t(u16, max_allowed_vf_queues, - ICE_MAX_RSS_QS_PER_VF); - } else { - /* request is successful, then reset VF */ - vf->num_req_qs = req_queues; - ice_vc_reset_vf(vf); - dev_info(dev, "VF %d granted request of %u queues.\n", - vf->vf_id, req_queues); - return 0; - } - -error_param: - /* send the response to the VF */ - return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_REQUEST_QUEUES, - v_ret, (u8 *)vfres, sizeof(*vfres)); -} - -/** - * ice_set_vf_port_vlan - * @netdev: network interface device structure - * @vf_id: VF identifier - * @vlan_id: VLAN ID being set - * @qos: priority setting - * @vlan_proto: VLAN protocol - * - * program VF Port VLAN ID and/or QoS - */ -int -ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, - __be16 vlan_proto) -{ - struct ice_pf *pf = ice_netdev_to_pf(netdev); - struct device *dev; - struct ice_vf *vf; - u16 vlanprio; - int ret; - - dev = ice_pf_to_dev(pf); - if (ice_validate_vf_id(pf, vf_id)) - return -EINVAL; - - if (vlan_id >= VLAN_N_VID || qos > 7) { - dev_err(dev, "Invalid Port VLAN parameters for VF %d, ID %d, QoS %d\n", - vf_id, vlan_id, qos); - return -EINVAL; - } - - if (vlan_proto != htons(ETH_P_8021Q)) { - dev_err(dev, "VF VLAN protocol is not supported\n"); - return -EPROTONOSUPPORT; - } - - vf = &pf->vf[vf_id]; - ret = ice_check_vf_ready_for_cfg(vf); - if (ret) - return ret; - - vlanprio = vlan_id | (qos << VLAN_PRIO_SHIFT); - - if (vf->port_vlan_info == vlanprio) { - /* duplicate request, so just return success */ - dev_dbg(dev, "Duplicate pvid %d request\n", vlanprio); - return 0; - } - - mutex_lock(&vf->cfg_lock); - - vf->port_vlan_info = vlanprio; - - if (vf->port_vlan_info) - dev_info(dev, "Setting VLAN %d, QoS 0x%x on VF %d\n", - vlan_id, qos, vf_id); - else - dev_info(dev, "Clearing port VLAN on VF %d\n", vf_id); - - ice_vc_reset_vf(vf); - mutex_unlock(&vf->cfg_lock); - - return 0; -} - -/** - * ice_vf_vlan_offload_ena - determine if capabilities support VLAN offloads - * @caps: VF driver negotiated capabilities - * - * Return true if VIRTCHNL_VF_OFFLOAD_VLAN capability is set, else return false - */ -static bool ice_vf_vlan_offload_ena(u32 caps) -{ - return !!(caps & VIRTCHNL_VF_OFFLOAD_VLAN); -} - -/** - * ice_vc_process_vlan_msg - * @vf: pointer to the VF info - * @msg: pointer to the msg buffer - * @add_v: Add VLAN if true, otherwise delete VLAN - * - * Process virtchnl op to add or remove programmed guest VLAN ID - */ -static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) -{ - enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; - struct virtchnl_vlan_filter_list *vfl = - (struct virtchnl_vlan_filter_list *)msg; - struct ice_pf *pf = vf->pf; - bool vlan_promisc = false; - struct ice_vsi *vsi; - struct device *dev; - struct ice_hw *hw; - int status = 0; - u8 promisc_m; - int i; - - dev = ice_pf_to_dev(pf); - if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (!ice_vf_vlan_offload_ena(vf->driver_caps)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (!ice_vc_isvalid_vsi_id(vf, vfl->vsi_id)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - for (i = 0; i < vfl->num_elements; i++) { - if (vfl->vlan_id[i] >= VLAN_N_VID) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - dev_err(dev, "invalid VF VLAN id %d\n", - vfl->vlan_id[i]); - goto error_param; - } - } - - hw = &pf->hw; - vsi = ice_get_vf_vsi(vf); - if (!vsi) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (add_v && !ice_is_vf_trusted(vf) && - vsi->num_vlan >= ICE_MAX_VLAN_PER_VF) { - dev_info(dev, "VF-%d is not trusted, switch the VF to trusted mode, in order to add more VLAN addresses\n", - vf->vf_id); - /* There is no need to let VF know about being not trusted, - * so we can just return success message here - */ - goto error_param; - } - - if (vsi->info.pvid) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if ((test_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states) || - test_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states)) && - test_bit(ICE_FLAG_VF_TRUE_PROMISC_ENA, pf->flags)) - vlan_promisc = true; - - if (add_v) { - for (i = 0; i < vfl->num_elements; i++) { - u16 vid = vfl->vlan_id[i]; - - if (!ice_is_vf_trusted(vf) && - vsi->num_vlan >= ICE_MAX_VLAN_PER_VF) { - dev_info(dev, "VF-%d is not trusted, switch the VF to trusted mode, in order to add more VLAN addresses\n", - vf->vf_id); - /* There is no need to let VF know about being - * not trusted, so we can just return success - * message here as well. - */ - goto error_param; - } - - /* we add VLAN 0 by default for each VF so we can enable - * Tx VLAN anti-spoof without triggering MDD events so - * we don't need to add it again here - */ - if (!vid) - continue; - - status = ice_vsi_add_vlan(vsi, vid, ICE_FWD_TO_VSI); - if (status) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - /* Enable VLAN pruning when non-zero VLAN is added */ - if (!vlan_promisc && vid && - !ice_vsi_is_vlan_pruning_ena(vsi)) { - status = ice_cfg_vlan_pruning(vsi, true); - if (status) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - dev_err(dev, "Enable VLAN pruning on VLAN ID: %d failed error-%d\n", - vid, status); - goto error_param; - } - } else if (vlan_promisc) { - /* Enable Ucast/Mcast VLAN promiscuous mode */ - promisc_m = ICE_PROMISC_VLAN_TX | - ICE_PROMISC_VLAN_RX; - - status = ice_set_vsi_promisc(hw, vsi->idx, - promisc_m, vid); - if (status) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - dev_err(dev, "Enable Unicast/multicast promiscuous mode on VLAN ID:%d failed error-%d\n", - vid, status); - } - } - } - } else { - /* In case of non_trusted VF, number of VLAN elements passed - * to PF for removal might be greater than number of VLANs - * filter programmed for that VF - So, use actual number of - * VLANS added earlier with add VLAN opcode. In order to avoid - * removing VLAN that doesn't exist, which result to sending - * erroneous failed message back to the VF - */ - int num_vf_vlan; - - num_vf_vlan = vsi->num_vlan; - for (i = 0; i < vfl->num_elements && i < num_vf_vlan; i++) { - u16 vid = vfl->vlan_id[i]; - - /* we add VLAN 0 by default for each VF so we can enable - * Tx VLAN anti-spoof without triggering MDD events so - * we don't want a VIRTCHNL request to remove it - */ - if (!vid) - continue; - - /* Make sure ice_vsi_kill_vlan is successful before - * updating VLAN information - */ - status = ice_vsi_kill_vlan(vsi, vid); - if (status) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - /* Disable VLAN pruning when only VLAN 0 is left */ - if (vsi->num_vlan == 1 && - ice_vsi_is_vlan_pruning_ena(vsi)) - ice_cfg_vlan_pruning(vsi, false); - - /* Disable Unicast/Multicast VLAN promiscuous mode */ - if (vlan_promisc) { - promisc_m = ICE_PROMISC_VLAN_TX | - ICE_PROMISC_VLAN_RX; - - ice_clear_vsi_promisc(hw, vsi->idx, - promisc_m, vid); - } - } - } - -error_param: - /* send the response to the VF */ - if (add_v) - return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ADD_VLAN, v_ret, - NULL, 0); - else - return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DEL_VLAN, v_ret, - NULL, 0); -} - -/** - * ice_vc_add_vlan_msg - * @vf: pointer to the VF info - * @msg: pointer to the msg buffer - * - * Add and program guest VLAN ID - */ -static int ice_vc_add_vlan_msg(struct ice_vf *vf, u8 *msg) -{ - return ice_vc_process_vlan_msg(vf, msg, true); -} - -/** - * ice_vc_remove_vlan_msg - * @vf: pointer to the VF info - * @msg: pointer to the msg buffer - * - * remove programmed guest VLAN ID - */ -static int ice_vc_remove_vlan_msg(struct ice_vf *vf, u8 *msg) -{ - return ice_vc_process_vlan_msg(vf, msg, false); -} - -/** - * ice_vc_ena_vlan_stripping - * @vf: pointer to the VF info - * - * Enable VLAN header stripping for a given VF - */ -static int ice_vc_ena_vlan_stripping(struct ice_vf *vf) -{ - enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; - struct ice_vsi *vsi; - - if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (!ice_vf_vlan_offload_ena(vf->driver_caps)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - vsi = ice_get_vf_vsi(vf); - if (ice_vsi_manage_vlan_stripping(vsi, true)) - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - -error_param: - return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING, - v_ret, NULL, 0); -} - -/** - * ice_vc_dis_vlan_stripping - * @vf: pointer to the VF info - * - * Disable VLAN header stripping for a given VF - */ -static int ice_vc_dis_vlan_stripping(struct ice_vf *vf) -{ - enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; - struct ice_vsi *vsi; - - if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (!ice_vf_vlan_offload_ena(vf->driver_caps)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - vsi = ice_get_vf_vsi(vf); - if (!vsi) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (ice_vsi_manage_vlan_stripping(vsi, false)) - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - -error_param: - return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING, - v_ret, NULL, 0); -} - -/** - * ice_vf_init_vlan_stripping - enable/disable VLAN stripping on initialization - * @vf: VF to enable/disable VLAN stripping for on initialization - * - * If the VIRTCHNL_VF_OFFLOAD_VLAN flag is set enable VLAN stripping, else if - * the flag is cleared then we want to disable stripping. For example, the flag - * will be cleared when port VLANs are configured by the administrator before - * passing the VF to the guest or if the AVF driver doesn't support VLAN - * offloads. - */ -static int ice_vf_init_vlan_stripping(struct ice_vf *vf) -{ - struct ice_vsi *vsi = ice_get_vf_vsi(vf); - - if (!vsi) - return -EINVAL; - - /* don't modify stripping if port VLAN is configured */ - if (vsi->info.pvid) - return 0; - - if (ice_vf_vlan_offload_ena(vf->driver_caps)) - return ice_vsi_manage_vlan_stripping(vsi, true); - else - return ice_vsi_manage_vlan_stripping(vsi, false); -} - -static struct ice_vc_vf_ops ice_vc_vf_dflt_ops = { - .get_ver_msg = ice_vc_get_ver_msg, - .get_vf_res_msg = ice_vc_get_vf_res_msg, - .reset_vf = ice_vc_reset_vf_msg, - .add_mac_addr_msg = ice_vc_add_mac_addr_msg, - .del_mac_addr_msg = ice_vc_del_mac_addr_msg, - .cfg_qs_msg = ice_vc_cfg_qs_msg, - .ena_qs_msg = ice_vc_ena_qs_msg, - .dis_qs_msg = ice_vc_dis_qs_msg, - .request_qs_msg = ice_vc_request_qs_msg, - .cfg_irq_map_msg = ice_vc_cfg_irq_map_msg, - .config_rss_key = ice_vc_config_rss_key, - .config_rss_lut = ice_vc_config_rss_lut, - .get_stats_msg = ice_vc_get_stats_msg, - .cfg_promiscuous_mode_msg = ice_vc_cfg_promiscuous_mode_msg, - .add_vlan_msg = ice_vc_add_vlan_msg, - .remove_vlan_msg = ice_vc_remove_vlan_msg, - .ena_vlan_stripping = ice_vc_ena_vlan_stripping, - .dis_vlan_stripping = ice_vc_dis_vlan_stripping, - .handle_rss_cfg_msg = ice_vc_handle_rss_cfg, - .add_fdir_fltr_msg = ice_vc_add_fdir_fltr, - .del_fdir_fltr_msg = ice_vc_del_fdir_fltr, -}; - -void ice_vc_set_dflt_vf_ops(struct ice_vc_vf_ops *ops) -{ - *ops = ice_vc_vf_dflt_ops; -} - -/** - * ice_vc_repr_add_mac - * @vf: pointer to VF - * @msg: virtchannel message - * - * When port representors are created, we do not add MAC rule - * to firmware, we store it so that PF could report same - * MAC as VF. - */ -static int ice_vc_repr_add_mac(struct ice_vf *vf, u8 *msg) -{ - enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; - struct virtchnl_ether_addr_list *al = - (struct virtchnl_ether_addr_list *)msg; - struct ice_vsi *vsi; - struct ice_pf *pf; - int i; - - if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) || - !ice_vc_isvalid_vsi_id(vf, al->vsi_id)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto handle_mac_exit; - } - - pf = vf->pf; - - vsi = ice_get_vf_vsi(vf); - if (!vsi) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto handle_mac_exit; - } - - for (i = 0; i < al->num_elements; i++) { - u8 *mac_addr = al->list[i].addr; - int result; - - if (!is_unicast_ether_addr(mac_addr) || - ether_addr_equal(mac_addr, vf->hw_lan_addr.addr)) - continue; - - if (vf->pf_set_mac) { - dev_err(ice_pf_to_dev(pf), "VF attempting to override administratively set MAC address\n"); - v_ret = VIRTCHNL_STATUS_ERR_NOT_SUPPORTED; - goto handle_mac_exit; - } - - result = ice_eswitch_add_vf_mac_rule(pf, vf, mac_addr); - if (result) { - dev_err(ice_pf_to_dev(pf), "Failed to add MAC %pM for VF %d\n, error %d\n", - mac_addr, vf->vf_id, result); - goto handle_mac_exit; - } - - ice_vfhw_mac_add(vf, &al->list[i]); - vf->num_mac++; - break; - } - -handle_mac_exit: - return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ADD_ETH_ADDR, - v_ret, NULL, 0); -} - -/** - * ice_vc_repr_del_mac - response with success for deleting MAC - * @vf: pointer to VF - * @msg: virtchannel message - * - * Respond with success to not break normal VF flow. - * For legacy VF driver try to update cached MAC address. - */ -static int -ice_vc_repr_del_mac(struct ice_vf __always_unused *vf, u8 __always_unused *msg) -{ - struct virtchnl_ether_addr_list *al = - (struct virtchnl_ether_addr_list *)msg; - - ice_update_legacy_cached_mac(vf, &al->list[0]); - - return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DEL_ETH_ADDR, - VIRTCHNL_STATUS_SUCCESS, NULL, 0); -} - -static int ice_vc_repr_add_vlan(struct ice_vf *vf, u8 __always_unused *msg) -{ - dev_dbg(ice_pf_to_dev(vf->pf), - "Can't add VLAN in switchdev mode for VF %d\n", vf->vf_id); - return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ADD_VLAN, - VIRTCHNL_STATUS_SUCCESS, NULL, 0); -} - -static int ice_vc_repr_del_vlan(struct ice_vf *vf, u8 __always_unused *msg) -{ - dev_dbg(ice_pf_to_dev(vf->pf), - "Can't delete VLAN in switchdev mode for VF %d\n", vf->vf_id); - return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DEL_VLAN, - VIRTCHNL_STATUS_SUCCESS, NULL, 0); -} - -static int ice_vc_repr_ena_vlan_stripping(struct ice_vf *vf) -{ - dev_dbg(ice_pf_to_dev(vf->pf), - "Can't enable VLAN stripping in switchdev mode for VF %d\n", - vf->vf_id); - return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING, - VIRTCHNL_STATUS_ERR_NOT_SUPPORTED, - NULL, 0); -} - -static int ice_vc_repr_dis_vlan_stripping(struct ice_vf *vf) -{ - dev_dbg(ice_pf_to_dev(vf->pf), - "Can't disable VLAN stripping in switchdev mode for VF %d\n", - vf->vf_id); - return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING, - VIRTCHNL_STATUS_ERR_NOT_SUPPORTED, - NULL, 0); -} - -static int -ice_vc_repr_cfg_promiscuous_mode(struct ice_vf *vf, u8 __always_unused *msg) -{ - dev_dbg(ice_pf_to_dev(vf->pf), - "Can't config promiscuous mode in switchdev mode for VF %d\n", - vf->vf_id); - return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE, - VIRTCHNL_STATUS_ERR_NOT_SUPPORTED, - NULL, 0); -} - -void ice_vc_change_ops_to_repr(struct ice_vc_vf_ops *ops) -{ - ops->add_mac_addr_msg = ice_vc_repr_add_mac; - ops->del_mac_addr_msg = ice_vc_repr_del_mac; - ops->add_vlan_msg = ice_vc_repr_add_vlan; - ops->remove_vlan_msg = ice_vc_repr_del_vlan; - ops->ena_vlan_stripping = ice_vc_repr_ena_vlan_stripping; - ops->dis_vlan_stripping = ice_vc_repr_dis_vlan_stripping; - ops->cfg_promiscuous_mode_msg = ice_vc_repr_cfg_promiscuous_mode; -} - -/** - * ice_vc_process_vf_msg - Process request from VF - * @pf: pointer to the PF structure - * @event: pointer to the AQ event - * - * called from the common asq/arq handler to - * process request from VF - */ -void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) -{ - u32 v_opcode = le32_to_cpu(event->desc.cookie_high); - s16 vf_id = le16_to_cpu(event->desc.retval); - u16 msglen = event->msg_len; - struct ice_vc_vf_ops *ops; - u8 *msg = event->msg_buf; - struct ice_vf *vf = NULL; - struct device *dev; - int err = 0; - - /* if de-init is underway, don't process messages from VF */ - if (test_bit(ICE_VF_DEINIT_IN_PROGRESS, pf->state)) - return; - - dev = ice_pf_to_dev(pf); - if (ice_validate_vf_id(pf, vf_id)) { - err = -EINVAL; - goto error_handler; - } - - vf = &pf->vf[vf_id]; - - /* Check if VF is disabled. */ - if (test_bit(ICE_VF_STATE_DIS, vf->vf_states)) { - err = -EPERM; - goto error_handler; - } - - ops = &vf->vc_ops; - - /* Perform basic checks on the msg */ - err = virtchnl_vc_validate_vf_msg(&vf->vf_ver, v_opcode, msg, msglen); - if (err) { - if (err == VIRTCHNL_STATUS_ERR_PARAM) - err = -EPERM; - else - err = -EINVAL; - } - - if (!ice_vc_is_opcode_allowed(vf, v_opcode)) { - ice_vc_send_msg_to_vf(vf, v_opcode, - VIRTCHNL_STATUS_ERR_NOT_SUPPORTED, NULL, - 0); - return; - } - -error_handler: - if (err) { - ice_vc_send_msg_to_vf(vf, v_opcode, VIRTCHNL_STATUS_ERR_PARAM, - NULL, 0); - dev_err(dev, "Invalid message from VF %d, opcode %d, len %d, error %d\n", - vf_id, v_opcode, msglen, err); - return; - } - - /* VF is being configured in another context that triggers a VFR, so no - * need to process this message - */ - if (!mutex_trylock(&vf->cfg_lock)) { - dev_info(dev, "VF %u is being configured in another context that will trigger a VFR, so there is no need to handle this message\n", - vf->vf_id); - return; - } - - switch (v_opcode) { - case VIRTCHNL_OP_VERSION: - err = ops->get_ver_msg(vf, msg); - break; - case VIRTCHNL_OP_GET_VF_RESOURCES: - err = ops->get_vf_res_msg(vf, msg); - if (ice_vf_init_vlan_stripping(vf)) - dev_err(dev, "Failed to initialize VLAN stripping for VF %d\n", - vf->vf_id); - ice_vc_notify_vf_link_state(vf); - break; - case VIRTCHNL_OP_RESET_VF: - ops->reset_vf(vf); - break; - case VIRTCHNL_OP_ADD_ETH_ADDR: - err = ops->add_mac_addr_msg(vf, msg); - break; - case VIRTCHNL_OP_DEL_ETH_ADDR: - err = ops->del_mac_addr_msg(vf, msg); - break; - case VIRTCHNL_OP_CONFIG_VSI_QUEUES: - err = ops->cfg_qs_msg(vf, msg); - break; - case VIRTCHNL_OP_ENABLE_QUEUES: - err = ops->ena_qs_msg(vf, msg); - ice_vc_notify_vf_link_state(vf); - break; - case VIRTCHNL_OP_DISABLE_QUEUES: - err = ops->dis_qs_msg(vf, msg); - break; - case VIRTCHNL_OP_REQUEST_QUEUES: - err = ops->request_qs_msg(vf, msg); - break; - case VIRTCHNL_OP_CONFIG_IRQ_MAP: - err = ops->cfg_irq_map_msg(vf, msg); - break; - case VIRTCHNL_OP_CONFIG_RSS_KEY: - err = ops->config_rss_key(vf, msg); - break; - case VIRTCHNL_OP_CONFIG_RSS_LUT: - err = ops->config_rss_lut(vf, msg); - break; - case VIRTCHNL_OP_GET_STATS: - err = ops->get_stats_msg(vf, msg); - break; - case VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE: - err = ops->cfg_promiscuous_mode_msg(vf, msg); - break; - case VIRTCHNL_OP_ADD_VLAN: - err = ops->add_vlan_msg(vf, msg); - break; - case VIRTCHNL_OP_DEL_VLAN: - err = ops->remove_vlan_msg(vf, msg); - break; - case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING: - err = ops->ena_vlan_stripping(vf); - break; - case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING: - err = ops->dis_vlan_stripping(vf); - break; - case VIRTCHNL_OP_ADD_FDIR_FILTER: - err = ops->add_fdir_fltr_msg(vf, msg); - break; - case VIRTCHNL_OP_DEL_FDIR_FILTER: - err = ops->del_fdir_fltr_msg(vf, msg); - break; - case VIRTCHNL_OP_ADD_RSS_CFG: - err = ops->handle_rss_cfg_msg(vf, msg, true); - break; - case VIRTCHNL_OP_DEL_RSS_CFG: - err = ops->handle_rss_cfg_msg(vf, msg, false); - break; - case VIRTCHNL_OP_UNKNOWN: - default: - dev_err(dev, "Unsupported opcode %d from VF %d\n", v_opcode, - vf_id); - err = ice_vc_send_msg_to_vf(vf, v_opcode, - VIRTCHNL_STATUS_ERR_NOT_SUPPORTED, - NULL, 0); - break; - } - if (err) { - /* Helper function cares less about error return values here - * as it is busy with pending work. - */ - dev_info(dev, "PF failed to honor VF %d, opcode %d, error %d\n", - vf_id, v_opcode, err); - } - - mutex_unlock(&vf->cfg_lock); -} - -/** - * ice_get_vf_cfg - * @netdev: network interface device structure - * @vf_id: VF identifier - * @ivi: VF configuration structure - * - * return VF configuration - */ -int -ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi) -{ - struct ice_pf *pf = ice_netdev_to_pf(netdev); - struct ice_vf *vf; - - if (ice_validate_vf_id(pf, vf_id)) - return -EINVAL; - - vf = &pf->vf[vf_id]; - - if (ice_check_vf_init(pf, vf)) - return -EBUSY; - - ivi->vf = vf_id; - ether_addr_copy(ivi->mac, vf->hw_lan_addr.addr); - - /* VF configuration for VLAN and applicable QoS */ - ivi->vlan = vf->port_vlan_info & VLAN_VID_MASK; - ivi->qos = (vf->port_vlan_info & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; - - ivi->trusted = vf->trusted; - ivi->spoofchk = vf->spoofchk; - if (!vf->link_forced) - ivi->linkstate = IFLA_VF_LINK_STATE_AUTO; - else if (vf->link_up) - ivi->linkstate = IFLA_VF_LINK_STATE_ENABLE; - else - ivi->linkstate = IFLA_VF_LINK_STATE_DISABLE; - ivi->max_tx_rate = vf->max_tx_rate; - ivi->min_tx_rate = vf->min_tx_rate; - return 0; -} - -/** - * ice_unicast_mac_exists - check if the unicast MAC exists on the PF's switch - * @pf: PF used to reference the switch's rules - * @umac: unicast MAC to compare against existing switch rules - * - * Return true on the first/any match, else return false - */ -static bool ice_unicast_mac_exists(struct ice_pf *pf, u8 *umac) -{ - struct ice_sw_recipe *mac_recipe_list = - &pf->hw.switch_info->recp_list[ICE_SW_LKUP_MAC]; - struct ice_fltr_mgmt_list_entry *list_itr; - struct list_head *rule_head; - struct mutex *rule_lock; /* protect MAC filter list access */ - - rule_head = &mac_recipe_list->filt_rules; - rule_lock = &mac_recipe_list->filt_rule_lock; - - mutex_lock(rule_lock); - list_for_each_entry(list_itr, rule_head, list_entry) { - u8 *existing_mac = &list_itr->fltr_info.l_data.mac.mac_addr[0]; - - if (ether_addr_equal(existing_mac, umac)) { - mutex_unlock(rule_lock); - return true; - } - } - - mutex_unlock(rule_lock); - - return false; -} - -/** - * ice_set_vf_mac - * @netdev: network interface device structure - * @vf_id: VF identifier - * @mac: MAC address - * - * program VF MAC address - */ -int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) -{ - struct ice_pf *pf = ice_netdev_to_pf(netdev); - struct ice_vf *vf; - int ret; - - if (ice_validate_vf_id(pf, vf_id)) - return -EINVAL; - - if (is_multicast_ether_addr(mac)) { - netdev_err(netdev, "%pM not a valid unicast address\n", mac); - return -EINVAL; - } - - vf = &pf->vf[vf_id]; - /* nothing left to do, unicast MAC already set */ - if (ether_addr_equal(vf->dev_lan_addr.addr, mac) && - ether_addr_equal(vf->hw_lan_addr.addr, mac)) - return 0; - - ret = ice_check_vf_ready_for_cfg(vf); - if (ret) - return ret; - - if (ice_unicast_mac_exists(pf, mac)) { - netdev_err(netdev, "Unicast MAC %pM already exists on this PF. Preventing setting VF %u unicast MAC address to %pM\n", - mac, vf_id, mac); - return -EINVAL; - } - - mutex_lock(&vf->cfg_lock); - - /* VF is notified of its new MAC via the PF's response to the - * VIRTCHNL_OP_GET_VF_RESOURCES message after the VF has been reset - */ - ether_addr_copy(vf->dev_lan_addr.addr, mac); - ether_addr_copy(vf->hw_lan_addr.addr, mac); - if (is_zero_ether_addr(mac)) { - /* VF will send VIRTCHNL_OP_ADD_ETH_ADDR message with its MAC */ - vf->pf_set_mac = false; - netdev_info(netdev, "Removing MAC on VF %d. VF driver will be reinitialized\n", - vf->vf_id); - } else { - /* PF will add MAC rule for the VF */ - vf->pf_set_mac = true; - netdev_info(netdev, "Setting MAC %pM on VF %d. VF driver will be reinitialized\n", - mac, vf_id); - } - - ice_vc_reset_vf(vf); - mutex_unlock(&vf->cfg_lock); - return 0; -} - -/** - * ice_set_vf_trust - * @netdev: network interface device structure - * @vf_id: VF identifier - * @trusted: Boolean value to enable/disable trusted VF - * - * Enable or disable a given VF as trusted - */ -int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted) -{ - struct ice_pf *pf = ice_netdev_to_pf(netdev); - struct ice_vf *vf; - int ret; - - if (ice_is_eswitch_mode_switchdev(pf)) { - dev_info(ice_pf_to_dev(pf), "Trusted VF is forbidden in switchdev mode\n"); - return -EOPNOTSUPP; - } - - if (ice_validate_vf_id(pf, vf_id)) - return -EINVAL; - - vf = &pf->vf[vf_id]; - ret = ice_check_vf_ready_for_cfg(vf); - if (ret) - return ret; - - /* Check if already trusted */ - if (trusted == vf->trusted) - return 0; - - mutex_lock(&vf->cfg_lock); - - vf->trusted = trusted; - ice_vc_reset_vf(vf); - dev_info(ice_pf_to_dev(pf), "VF %u is now %strusted\n", - vf_id, trusted ? "" : "un"); - - mutex_unlock(&vf->cfg_lock); - - return 0; -} - -/** - * ice_set_vf_link_state - * @netdev: network interface device structure - * @vf_id: VF identifier - * @link_state: required link state - * - * Set VF's link state, irrespective of physical link state status - */ -int ice_set_vf_link_state(struct net_device *netdev, int vf_id, int link_state) -{ - struct ice_pf *pf = ice_netdev_to_pf(netdev); - struct ice_vf *vf; - int ret; - - if (ice_validate_vf_id(pf, vf_id)) - return -EINVAL; - - vf = &pf->vf[vf_id]; - ret = ice_check_vf_ready_for_cfg(vf); - if (ret) - return ret; - - switch (link_state) { - case IFLA_VF_LINK_STATE_AUTO: - vf->link_forced = false; - break; - case IFLA_VF_LINK_STATE_ENABLE: - vf->link_forced = true; - vf->link_up = true; - break; - case IFLA_VF_LINK_STATE_DISABLE: - vf->link_forced = true; - vf->link_up = false; - break; - default: - return -EINVAL; - } - - ice_vc_notify_vf_link_state(vf); - - return 0; -} - -/** - * ice_calc_all_vfs_min_tx_rate - calculate cumulative min Tx rate on all VFs - * @pf: PF associated with VFs - */ -static int ice_calc_all_vfs_min_tx_rate(struct ice_pf *pf) -{ - int rate = 0, i; - - ice_for_each_vf(pf, i) - rate += pf->vf[i].min_tx_rate; - - return rate; -} - -/** - * ice_min_tx_rate_oversubscribed - check if min Tx rate causes oversubscription - * @vf: VF trying to configure min_tx_rate - * @min_tx_rate: min Tx rate in Mbps - * - * Check if the min_tx_rate being passed in will cause oversubscription of total - * min_tx_rate based on the current link speed and all other VFs configured - * min_tx_rate - * - * Return true if the passed min_tx_rate would cause oversubscription, else - * return false - */ -static bool -ice_min_tx_rate_oversubscribed(struct ice_vf *vf, int min_tx_rate) -{ - int link_speed_mbps = ice_get_link_speed_mbps(ice_get_vf_vsi(vf)); - int all_vfs_min_tx_rate = ice_calc_all_vfs_min_tx_rate(vf->pf); - - /* this VF's previous rate is being overwritten */ - all_vfs_min_tx_rate -= vf->min_tx_rate; - - if (all_vfs_min_tx_rate + min_tx_rate > link_speed_mbps) { - dev_err(ice_pf_to_dev(vf->pf), "min_tx_rate of %d Mbps on VF %u would cause oversubscription of %d Mbps based on the current link speed %d Mbps\n", - min_tx_rate, vf->vf_id, - all_vfs_min_tx_rate + min_tx_rate - link_speed_mbps, - link_speed_mbps); - return true; - } - - return false; -} - -/** - * ice_set_vf_bw - set min/max VF bandwidth - * @netdev: network interface device structure - * @vf_id: VF identifier - * @min_tx_rate: Minimum Tx rate in Mbps - * @max_tx_rate: Maximum Tx rate in Mbps - */ -int -ice_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, - int max_tx_rate) -{ - struct ice_pf *pf = ice_netdev_to_pf(netdev); - struct ice_vsi *vsi; - struct device *dev; - struct ice_vf *vf; - int ret; - - dev = ice_pf_to_dev(pf); - if (ice_validate_vf_id(pf, vf_id)) - return -EINVAL; - - vf = &pf->vf[vf_id]; - ret = ice_check_vf_ready_for_cfg(vf); - if (ret) - return ret; - - vsi = ice_get_vf_vsi(vf); - - /* when max_tx_rate is zero that means no max Tx rate limiting, so only - * check if max_tx_rate is non-zero - */ - if (max_tx_rate && min_tx_rate > max_tx_rate) { - dev_err(dev, "Cannot set min Tx rate %d Mbps greater than max Tx rate %d Mbps\n", - min_tx_rate, max_tx_rate); - return -EINVAL; - } - - if (min_tx_rate && ice_is_dcb_active(pf)) { - dev_err(dev, "DCB on PF is currently enabled. VF min Tx rate limiting not allowed on this PF.\n"); - return -EOPNOTSUPP; - } - - if (ice_min_tx_rate_oversubscribed(vf, min_tx_rate)) - return -EINVAL; - - if (vf->min_tx_rate != (unsigned int)min_tx_rate) { - ret = ice_set_min_bw_limit(vsi, (u64)min_tx_rate * 1000); - if (ret) { - dev_err(dev, "Unable to set min-tx-rate for VF %d\n", - vf->vf_id); - return ret; - } - - vf->min_tx_rate = min_tx_rate; - } - - if (vf->max_tx_rate != (unsigned int)max_tx_rate) { - ret = ice_set_max_bw_limit(vsi, (u64)max_tx_rate * 1000); - if (ret) { - dev_err(dev, "Unable to set max-tx-rate for VF %d\n", - vf->vf_id); - return ret; - } - - vf->max_tx_rate = max_tx_rate; - } - - return 0; -} - -/** - * ice_get_vf_stats - populate some stats for the VF - * @netdev: the netdev of the PF - * @vf_id: the host OS identifier (0-255) - * @vf_stats: pointer to the OS memory to be initialized - */ -int ice_get_vf_stats(struct net_device *netdev, int vf_id, - struct ifla_vf_stats *vf_stats) -{ - struct ice_pf *pf = ice_netdev_to_pf(netdev); - struct ice_eth_stats *stats; - struct ice_vsi *vsi; - struct ice_vf *vf; - int ret; - - if (ice_validate_vf_id(pf, vf_id)) - return -EINVAL; - - vf = &pf->vf[vf_id]; - ret = ice_check_vf_ready_for_cfg(vf); - if (ret) - return ret; - - vsi = ice_get_vf_vsi(vf); - if (!vsi) - return -EINVAL; - - ice_update_eth_stats(vsi); - stats = &vsi->eth_stats; - - memset(vf_stats, 0, sizeof(*vf_stats)); - - vf_stats->rx_packets = stats->rx_unicast + stats->rx_broadcast + - stats->rx_multicast; - vf_stats->tx_packets = stats->tx_unicast + stats->tx_broadcast + - stats->tx_multicast; - vf_stats->rx_bytes = stats->rx_bytes; - vf_stats->tx_bytes = stats->tx_bytes; - vf_stats->broadcast = stats->rx_broadcast; - vf_stats->multicast = stats->rx_multicast; - vf_stats->rx_dropped = stats->rx_discards; - vf_stats->tx_dropped = stats->tx_discards; - - return 0; -} - -/** - * ice_print_vf_rx_mdd_event - print VF Rx malicious driver detect event - * @vf: pointer to the VF structure - */ -void ice_print_vf_rx_mdd_event(struct ice_vf *vf) -{ - struct ice_pf *pf = vf->pf; - struct device *dev; - - dev = ice_pf_to_dev(pf); - - dev_info(dev, "%d Rx Malicious Driver Detection events detected on PF %d VF %d MAC %pM. mdd-auto-reset-vfs=%s\n", - vf->mdd_rx_events.count, pf->hw.pf_id, vf->vf_id, - vf->dev_lan_addr.addr, - test_bit(ICE_FLAG_MDD_AUTO_RESET_VF, pf->flags) - ? "on" : "off"); -} - -/** - * ice_print_vfs_mdd_events - print VFs malicious driver detect event - * @pf: pointer to the PF structure - * - * Called from ice_handle_mdd_event to rate limit and print VFs MDD events. - */ -void ice_print_vfs_mdd_events(struct ice_pf *pf) -{ - struct device *dev = ice_pf_to_dev(pf); - struct ice_hw *hw = &pf->hw; - int i; - - /* check that there are pending MDD events to print */ - if (!test_and_clear_bit(ICE_MDD_VF_PRINT_PENDING, pf->state)) - return; - - /* VF MDD event logs are rate limited to one second intervals */ - if (time_is_after_jiffies(pf->last_printed_mdd_jiffies + HZ * 1)) - return; - - pf->last_printed_mdd_jiffies = jiffies; - - ice_for_each_vf(pf, i) { - struct ice_vf *vf = &pf->vf[i]; - - /* only print Rx MDD event message if there are new events */ - if (vf->mdd_rx_events.count != vf->mdd_rx_events.last_printed) { - vf->mdd_rx_events.last_printed = - vf->mdd_rx_events.count; - ice_print_vf_rx_mdd_event(vf); - } - - /* only print Tx MDD event message if there are new events */ - if (vf->mdd_tx_events.count != vf->mdd_tx_events.last_printed) { - vf->mdd_tx_events.last_printed = - vf->mdd_tx_events.count; - - dev_info(dev, "%d Tx Malicious Driver Detection events detected on PF %d VF %d MAC %pM.\n", - vf->mdd_tx_events.count, hw->pf_id, i, - vf->dev_lan_addr.addr); - } - } -} - -/** - * ice_restore_all_vfs_msi_state - restore VF MSI state after PF FLR - * @pdev: pointer to a pci_dev 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) -{ - u16 vf_id; - int pos; - - if (!pci_num_vf(pdev)) - return; - - 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_is_malicious_vf - helper function to detect a malicious VF - * @pf: ptr to struct ice_pf - * @event: pointer to the AQ event - * @num_msg_proc: the number of messages processed so far - * @num_msg_pending: the number of messages peinding in admin queue - */ -bool -ice_is_malicious_vf(struct ice_pf *pf, struct ice_rq_event_info *event, - u16 num_msg_proc, u16 num_msg_pending) -{ - s16 vf_id = le16_to_cpu(event->desc.retval); - struct device *dev = ice_pf_to_dev(pf); - struct ice_mbx_data mbxdata; - bool malvf = false; - struct ice_vf *vf; - int status; - - if (ice_validate_vf_id(pf, vf_id)) - return false; - - vf = &pf->vf[vf_id]; - /* Check if VF is disabled. */ - if (test_bit(ICE_VF_STATE_DIS, vf->vf_states)) - return false; - - mbxdata.num_msg_proc = num_msg_proc; - mbxdata.num_pending_arq = num_msg_pending; - mbxdata.max_num_msgs_mbx = pf->hw.mailboxq.num_rq_entries; -#define ICE_MBX_OVERFLOW_WATERMARK 64 - mbxdata.async_watermark_val = ICE_MBX_OVERFLOW_WATERMARK; - - /* check to see if we have a malicious VF */ - status = ice_mbx_vf_state_handler(&pf->hw, &mbxdata, vf_id, &malvf); - if (status) - return false; - - if (malvf) { - bool report_vf = false; - - /* if the VF is malicious and we haven't let the user - * know about it, then let them know now - */ - status = ice_mbx_report_malvf(&pf->hw, pf->malvfs, - ICE_MAX_VF_COUNT, vf_id, - &report_vf); - if (status) - dev_dbg(dev, "Error reporting malicious VF\n"); - - if (report_vf) { - struct ice_vsi *pf_vsi = ice_get_main_vsi(pf); - - if (pf_vsi) - dev_warn(dev, "VF MAC %pM on PF MAC %pM is generating asynchronous messages and may be overflowing the PF message queue. Please see the Adapter User Guide for more information\n", - &vf->dev_lan_addr.addr[0], - pf_vsi->netdev->dev_addr); - } - - return true; - } - - /* if there was an error in detection or the VF is not malicious then - * return false - */ - return false; -} diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h deleted file mode 100644 index 752487a1bdd6..000000000000 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h +++ /dev/null @@ -1,346 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (c) 2018, Intel Corporation. */ - -#ifndef _ICE_VIRTCHNL_PF_H_ -#define _ICE_VIRTCHNL_PF_H_ -#include "ice.h" -#include "ice_virtchnl_fdir.h" - -/* Restrict number of MAC Addr and VLAN that non-trusted VF can programmed */ -#define ICE_MAX_VLAN_PER_VF 8 -/* MAC filters: 1 is reserved for the VF's default/perm_addr/LAA MAC, 1 for - * broadcast, and 16 for additional unicast/multicast filters - */ -#define ICE_MAX_MACADDR_PER_VF 18 - -/* Malicious Driver Detection */ -#define ICE_DFLT_NUM_INVAL_MSGS_ALLOWED 10 -#define ICE_MDD_EVENTS_THRESHOLD 30 - -/* Static VF transaction/status register def */ -#define VF_DEVICE_STATUS 0xAA -#define VF_TRANS_PENDING_M 0x20 - -/* wait defines for polling PF_PCI_CIAD register status */ -#define ICE_PCI_CIAD_WAIT_COUNT 100 -#define ICE_PCI_CIAD_WAIT_DELAY_US 1 - -/* VF resource constraints */ -#define ICE_MAX_VF_COUNT 256 -#define ICE_MIN_QS_PER_VF 1 -#define ICE_NONQ_VECS_VF 1 -#define ICE_MAX_SCATTER_QS_PER_VF 16 -#define ICE_MAX_RSS_QS_PER_VF 16 -#define ICE_NUM_VF_MSIX_MED 17 -#define ICE_NUM_VF_MSIX_SMALL 5 -#define ICE_NUM_VF_MSIX_MULTIQ_MIN 3 -#define ICE_MIN_INTR_PER_VF (ICE_MIN_QS_PER_VF + 1) -#define ICE_MAX_VF_RESET_TRIES 40 -#define ICE_MAX_VF_RESET_SLEEP_MS 20 - -#define ice_for_each_vf(pf, i) \ - for ((i) = 0; (i) < (pf)->num_alloc_vfs; (i)++) - -/* Specific VF states */ -enum ice_vf_states { - ICE_VF_STATE_INIT = 0, /* PF is initializing VF */ - ICE_VF_STATE_ACTIVE, /* VF resources are allocated for use */ - ICE_VF_STATE_QS_ENA, /* VF queue(s) enabled */ - ICE_VF_STATE_DIS, - ICE_VF_STATE_MC_PROMISC, - ICE_VF_STATE_UC_PROMISC, - ICE_VF_STATES_NBITS -}; - -/* VF capabilities */ -enum ice_virtchnl_cap { - ICE_VIRTCHNL_VF_CAP_L2 = 0, - ICE_VIRTCHNL_VF_CAP_PRIVILEGE, -}; - -struct ice_time_mac { - unsigned long time_modified; - u8 addr[ETH_ALEN]; -}; - -/* VF MDD events print structure */ -struct ice_mdd_vf_events { - u16 count; /* total count of Rx|Tx events */ - /* count number of the last printed event */ - u16 last_printed; -}; - -struct ice_vf; - -struct ice_vc_vf_ops { - int (*get_ver_msg)(struct ice_vf *vf, u8 *msg); - int (*get_vf_res_msg)(struct ice_vf *vf, u8 *msg); - void (*reset_vf)(struct ice_vf *vf); - int (*add_mac_addr_msg)(struct ice_vf *vf, u8 *msg); - int (*del_mac_addr_msg)(struct ice_vf *vf, u8 *msg); - int (*cfg_qs_msg)(struct ice_vf *vf, u8 *msg); - int (*ena_qs_msg)(struct ice_vf *vf, u8 *msg); - int (*dis_qs_msg)(struct ice_vf *vf, u8 *msg); - int (*request_qs_msg)(struct ice_vf *vf, u8 *msg); - int (*cfg_irq_map_msg)(struct ice_vf *vf, u8 *msg); - int (*config_rss_key)(struct ice_vf *vf, u8 *msg); - int (*config_rss_lut)(struct ice_vf *vf, u8 *msg); - int (*get_stats_msg)(struct ice_vf *vf, u8 *msg); - int (*cfg_promiscuous_mode_msg)(struct ice_vf *vf, u8 *msg); - int (*add_vlan_msg)(struct ice_vf *vf, u8 *msg); - int (*remove_vlan_msg)(struct ice_vf *vf, u8 *msg); - int (*ena_vlan_stripping)(struct ice_vf *vf); - int (*dis_vlan_stripping)(struct ice_vf *vf); - int (*handle_rss_cfg_msg)(struct ice_vf *vf, u8 *msg, bool add); - int (*add_fdir_fltr_msg)(struct ice_vf *vf, u8 *msg); - int (*del_fdir_fltr_msg)(struct ice_vf *vf, u8 *msg); -}; - -/* VF information structure */ -struct ice_vf { - struct ice_pf *pf; - - /* Used during virtchnl message handling and NDO ops against the VF - * that will trigger a VFR - */ - struct mutex cfg_lock; - - u16 vf_id; /* VF ID in the PF space */ - u16 lan_vsi_idx; /* index into PF struct */ - u16 ctrl_vsi_idx; - struct ice_vf_fdir fdir; - /* first vector index of this VF in the PF space */ - int first_vector_idx; - struct ice_sw *vf_sw_id; /* switch ID the VF VSIs connect to */ - struct virtchnl_version_info vf_ver; - u32 driver_caps; /* reported by VF driver */ - struct virtchnl_ether_addr dev_lan_addr; - struct virtchnl_ether_addr hw_lan_addr; - struct ice_time_mac legacy_last_added_umac; - DECLARE_BITMAP(txq_ena, ICE_MAX_RSS_QS_PER_VF); - DECLARE_BITMAP(rxq_ena, ICE_MAX_RSS_QS_PER_VF); - u16 port_vlan_info; /* Port VLAN ID and QoS */ - u8 pf_set_mac:1; /* VF MAC address set by VMM admin */ - u8 trusted:1; - u8 spoofchk:1; - u8 link_forced:1; - u8 link_up:1; /* only valid if VF link is forced */ - /* VSI indices - actual VSI pointers are maintained in the PF structure - * When assigned, these will be non-zero, because VSI 0 is always - * the main LAN VSI for the PF. - */ - u16 lan_vsi_num; /* ID as used by firmware */ - unsigned int min_tx_rate; /* Minimum Tx bandwidth limit in Mbps */ - unsigned int max_tx_rate; /* Maximum Tx bandwidth limit in Mbps */ - DECLARE_BITMAP(vf_states, ICE_VF_STATES_NBITS); /* VF runtime states */ - - u64 num_inval_msgs; /* number of continuous invalid msgs */ - u64 num_valid_msgs; /* number of valid msgs detected */ - unsigned long vf_caps; /* VF's adv. capabilities */ - u8 num_req_qs; /* num of queue pairs requested by VF */ - u16 num_mac; - u16 num_vf_qs; /* num of queue configured per VF */ - struct ice_mdd_vf_events mdd_rx_events; - struct ice_mdd_vf_events mdd_tx_events; - DECLARE_BITMAP(opcodes_allowlist, VIRTCHNL_OP_MAX); - - struct ice_repr *repr; - - struct ice_vc_vf_ops vc_ops; - - /* devlink port data */ - struct devlink_port devlink_port; -}; - -#ifdef CONFIG_PCI_IOV -struct ice_vsi *ice_get_vf_vsi(struct ice_vf *vf); -void ice_process_vflr_event(struct ice_pf *pf); -int ice_sriov_configure(struct pci_dev *pdev, int num_vfs); -int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac); -int -ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi); - -void ice_free_vfs(struct ice_pf *pf); -void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event); -void ice_vc_notify_link_state(struct ice_pf *pf); -void ice_vc_notify_reset(struct ice_pf *pf); -void ice_vc_notify_vf_link_state(struct ice_vf *vf); -void ice_vc_change_ops_to_repr(struct ice_vc_vf_ops *ops); -void ice_vc_set_dflt_vf_ops(struct ice_vc_vf_ops *ops); -bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr); -bool ice_reset_vf(struct ice_vf *vf, bool is_vflr); -void ice_restore_all_vfs_msi_state(struct pci_dev *pdev); -bool -ice_is_malicious_vf(struct ice_pf *pf, struct ice_rq_event_info *event, - u16 num_msg_proc, u16 num_msg_pending); - -int -ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, - __be16 vlan_proto); - -int -ice_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, - int max_tx_rate); - -int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted); - -int ice_set_vf_link_state(struct net_device *netdev, int vf_id, int link_state); - -int ice_check_vf_ready_for_cfg(struct ice_vf *vf); - -bool ice_is_vf_disabled(struct ice_vf *vf); - -int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena); - -int ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector); - -void ice_set_vf_state_qs_dis(struct ice_vf *vf); -int -ice_get_vf_stats(struct net_device *netdev, int vf_id, - struct ifla_vf_stats *vf_stats); -bool ice_is_any_vf_in_promisc(struct ice_pf *pf); -void -ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event); -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); -struct ice_vsi *ice_vf_ctrl_vsi_setup(struct ice_vf *vf); -int -ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode, - enum virtchnl_status_code v_retval, u8 *msg, u16 msglen); -bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id); -#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) { } -static inline -void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) { } -static inline void ice_vc_notify_link_state(struct ice_pf *pf) { } -static inline void ice_vc_notify_reset(struct ice_pf *pf) { } -static inline void ice_vc_notify_vf_link_state(struct ice_vf *vf) { } -static inline void ice_vc_change_ops_to_repr(struct ice_vc_vf_ops *ops) { } -static inline void ice_vc_set_dflt_vf_ops(struct ice_vc_vf_ops *ops) { } -static inline void ice_set_vf_state_qs_dis(struct ice_vf *vf) { } -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 int ice_check_vf_ready_for_cfg(struct ice_vf *vf) -{ - return -EOPNOTSUPP; -} - -static inline bool ice_is_vf_disabled(struct ice_vf *vf) -{ - return true; -} - -static inline struct ice_vsi *ice_get_vf_vsi(struct ice_vf *vf) -{ - return NULL; -} - -static inline bool -ice_is_malicious_vf(struct ice_pf __always_unused *pf, - struct ice_rq_event_info __always_unused *event, - u16 __always_unused num_msg_proc, - u16 __always_unused num_msg_pending) -{ - return false; -} - -static inline bool -ice_reset_all_vfs(struct ice_pf __always_unused *pf, - bool __always_unused is_vflr) -{ - return true; -} - -static inline bool -ice_reset_vf(struct ice_vf __always_unused *vf, bool __always_unused is_vflr) -{ - return true; -} - -static inline int -ice_sriov_configure(struct pci_dev __always_unused *pdev, - int __always_unused num_vfs) -{ - return -EOPNOTSUPP; -} - -static inline int -ice_set_vf_mac(struct net_device __always_unused *netdev, - int __always_unused vf_id, u8 __always_unused *mac) -{ - return -EOPNOTSUPP; -} - -static inline int -ice_get_vf_cfg(struct net_device __always_unused *netdev, - int __always_unused vf_id, - struct ifla_vf_info __always_unused *ivi) -{ - return -EOPNOTSUPP; -} - -static inline int -ice_set_vf_trust(struct net_device __always_unused *netdev, - int __always_unused vf_id, bool __always_unused trusted) -{ - return -EOPNOTSUPP; -} - -static inline int -ice_set_vf_port_vlan(struct net_device __always_unused *netdev, - int __always_unused vf_id, u16 __always_unused vid, - u8 __always_unused qos, __be16 __always_unused v_proto) -{ - return -EOPNOTSUPP; -} - -static inline int -ice_set_vf_spoofchk(struct net_device __always_unused *netdev, - int __always_unused vf_id, bool __always_unused ena) -{ - return -EOPNOTSUPP; -} - -static inline int -ice_set_vf_link_state(struct net_device __always_unused *netdev, - int __always_unused vf_id, int __always_unused link_state) -{ - return -EOPNOTSUPP; -} - -static inline int -ice_set_vf_bw(struct net_device __always_unused *netdev, - int __always_unused vf_id, int __always_unused min_tx_rate, - int __always_unused max_tx_rate) -{ - return -EOPNOTSUPP; -} - -static inline int -ice_calc_vf_reg_idx(struct ice_vf __always_unused *vf, - struct ice_q_vector __always_unused *q_vector) -{ - return 0; -} - -static inline int -ice_get_vf_stats(struct net_device __always_unused *netdev, - int __always_unused vf_id, - struct ifla_vf_stats __always_unused *vf_stats) -{ - return -EOPNOTSUPP; -} - -static inline bool ice_is_any_vf_in_promisc(struct ice_pf __always_unused *pf) -{ - return false; -} -#endif /* CONFIG_PCI_IOV */ -#endif /* _ICE_VIRTCHNL_PF_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_vlan.h b/drivers/net/ethernet/intel/ice/ice_vlan.h new file mode 100644 index 000000000000..bc4550a03173 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_vlan.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#ifndef _ICE_VLAN_H_ +#define _ICE_VLAN_H_ + +#include <linux/types.h> +#include "ice_type.h" + +struct ice_vlan { + u16 tpid; + u16 vid; + u8 prio; +}; + +#define ICE_VLAN(tpid, vid, prio) ((struct ice_vlan){ tpid, vid, prio }) + +#endif /* _ICE_VLAN_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_vlan_mode.c b/drivers/net/ethernet/intel/ice/ice_vlan_mode.c new file mode 100644 index 000000000000..bcda2e004807 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_vlan_mode.c @@ -0,0 +1,438 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#include "ice_common.h" + +/** + * ice_pkg_get_supported_vlan_mode - determine if DDP supports Double VLAN mode + * @hw: pointer to the HW struct + * @dvm: output variable to determine if DDP supports DVM(true) or SVM(false) + */ +static int +ice_pkg_get_supported_vlan_mode(struct ice_hw *hw, bool *dvm) +{ + u16 meta_init_size = sizeof(struct ice_meta_init_section); + struct ice_meta_init_section *sect; + struct ice_buf_build *bld; + int status; + + /* if anything fails, we assume there is no DVM support */ + *dvm = false; + + bld = ice_pkg_buf_alloc_single_section(hw, + ICE_SID_RXPARSER_METADATA_INIT, + meta_init_size, (void **)§); + if (!bld) + return -ENOMEM; + + /* only need to read a single section */ + sect->count = cpu_to_le16(1); + sect->offset = cpu_to_le16(ICE_META_VLAN_MODE_ENTRY); + + status = ice_aq_upload_section(hw, + (struct ice_buf_hdr *)ice_pkg_buf(bld), + ICE_PKG_BUF_SIZE, NULL); + if (!status) { + DECLARE_BITMAP(entry, ICE_META_INIT_BITS); + u32 arr[ICE_META_INIT_DW_CNT]; + u16 i; + + /* convert to host bitmap format */ + for (i = 0; i < ICE_META_INIT_DW_CNT; i++) + arr[i] = le32_to_cpu(sect->entry.bm[i]); + + bitmap_from_arr32(entry, arr, (u16)ICE_META_INIT_BITS); + + /* check if DVM is supported */ + *dvm = test_bit(ICE_META_VLAN_MODE_BIT, entry); + } + + ice_pkg_buf_free(hw, bld); + + return status; +} + +/** + * ice_aq_get_vlan_mode - get the VLAN mode of the device + * @hw: pointer to the HW structure + * @get_params: structure FW fills in based on the current VLAN mode config + * + * Get VLAN Mode Parameters (0x020D) + */ +static int +ice_aq_get_vlan_mode(struct ice_hw *hw, + struct ice_aqc_get_vlan_mode *get_params) +{ + struct ice_aq_desc desc; + + if (!get_params) + return -EINVAL; + + ice_fill_dflt_direct_cmd_desc(&desc, + ice_aqc_opc_get_vlan_mode_parameters); + + return ice_aq_send_cmd(hw, &desc, get_params, sizeof(*get_params), + NULL); +} + +/** + * ice_aq_is_dvm_ena - query FW to check if double VLAN mode is enabled + * @hw: pointer to the HW structure + * + * Returns true if the hardware/firmware is configured in double VLAN mode, + * else return false signaling that the hardware/firmware is configured in + * single VLAN mode. + * + * Also, return false if this call fails for any reason (i.e. firmware doesn't + * support this AQ call). + */ +static bool ice_aq_is_dvm_ena(struct ice_hw *hw) +{ + struct ice_aqc_get_vlan_mode get_params = { 0 }; + int status; + + status = ice_aq_get_vlan_mode(hw, &get_params); + if (status) { + ice_debug(hw, ICE_DBG_AQ, "Failed to get VLAN mode, status %d\n", + status); + return false; + } + + return (get_params.vlan_mode & ICE_AQ_VLAN_MODE_DVM_ENA); +} + +/** + * ice_is_dvm_ena - check if double VLAN mode is enabled + * @hw: pointer to the HW structure + * + * The device is configured in single or double VLAN mode on initialization and + * this cannot be dynamically changed during runtime. Based on this there is no + * need to make an AQ call every time the driver needs to know the VLAN mode. + * Instead, use the cached VLAN mode. + */ +bool ice_is_dvm_ena(struct ice_hw *hw) +{ + return hw->dvm_ena; +} + +/** + * ice_cache_vlan_mode - cache VLAN mode after DDP is downloaded + * @hw: pointer to the HW structure + * + * This is only called after downloading the DDP and after the global + * configuration lock has been released because all ports on a device need to + * cache the VLAN mode. + */ +static void ice_cache_vlan_mode(struct ice_hw *hw) +{ + hw->dvm_ena = ice_aq_is_dvm_ena(hw) ? true : false; +} + +/** + * ice_pkg_supports_dvm - find out if DDP supports DVM + * @hw: pointer to the HW structure + */ +static bool ice_pkg_supports_dvm(struct ice_hw *hw) +{ + bool pkg_supports_dvm; + int status; + + status = ice_pkg_get_supported_vlan_mode(hw, &pkg_supports_dvm); + if (status) { + ice_debug(hw, ICE_DBG_PKG, "Failed to get supported VLAN mode, status %d\n", + status); + return false; + } + + return pkg_supports_dvm; +} + +/** + * ice_fw_supports_dvm - find out if FW supports DVM + * @hw: pointer to the HW structure + */ +static bool ice_fw_supports_dvm(struct ice_hw *hw) +{ + struct ice_aqc_get_vlan_mode get_vlan_mode = { 0 }; + int status; + + /* If firmware returns success, then it supports DVM, else it only + * supports SVM + */ + status = ice_aq_get_vlan_mode(hw, &get_vlan_mode); + if (status) { + ice_debug(hw, ICE_DBG_NVM, "Failed to get VLAN mode, status %d\n", + status); + return false; + } + + return true; +} + +/** + * ice_is_dvm_supported - check if Double VLAN Mode is supported + * @hw: pointer to the hardware structure + * + * Returns true if Double VLAN Mode (DVM) is supported and false if only Single + * VLAN Mode (SVM) is supported. In order for DVM to be supported the DDP and + * firmware must support it, otherwise only SVM is supported. This function + * should only be called while the global config lock is held and after the + * package has been successfully downloaded. + */ +static bool ice_is_dvm_supported(struct ice_hw *hw) +{ + if (!ice_pkg_supports_dvm(hw)) { + ice_debug(hw, ICE_DBG_PKG, "DDP doesn't support DVM\n"); + return false; + } + + if (!ice_fw_supports_dvm(hw)) { + ice_debug(hw, ICE_DBG_PKG, "FW doesn't support DVM\n"); + return false; + } + + return true; +} + +#define ICE_EXTERNAL_VLAN_ID_FV_IDX 11 +#define ICE_SW_LKUP_VLAN_LOC_LKUP_IDX 1 +#define ICE_SW_LKUP_VLAN_PKT_FLAGS_LKUP_IDX 2 +#define ICE_SW_LKUP_PROMISC_VLAN_LOC_LKUP_IDX 2 +#define ICE_PKT_FLAGS_0_TO_15_FV_IDX 1 +static struct ice_update_recipe_lkup_idx_params ice_dvm_dflt_recipes[] = { + { + /* Update recipe ICE_SW_LKUP_VLAN to filter based on the + * outer/single VLAN in DVM + */ + .rid = ICE_SW_LKUP_VLAN, + .fv_idx = ICE_EXTERNAL_VLAN_ID_FV_IDX, + .ignore_valid = true, + .mask = 0, + .mask_valid = false, /* use pre-existing mask */ + .lkup_idx = ICE_SW_LKUP_VLAN_LOC_LKUP_IDX, + }, + { + /* Update recipe ICE_SW_LKUP_VLAN to filter based on the VLAN + * packet flags to support VLAN filtering on multiple VLAN + * ethertypes (i.e. 0x8100 and 0x88a8) in DVM + */ + .rid = ICE_SW_LKUP_VLAN, + .fv_idx = ICE_PKT_FLAGS_0_TO_15_FV_IDX, + .ignore_valid = false, + .mask = ICE_PKT_FLAGS_0_TO_15_VLAN_FLAGS_MASK, + .mask_valid = true, + .lkup_idx = ICE_SW_LKUP_VLAN_PKT_FLAGS_LKUP_IDX, + }, + { + /* Update recipe ICE_SW_LKUP_PROMISC_VLAN to filter based on the + * outer/single VLAN in DVM + */ + .rid = ICE_SW_LKUP_PROMISC_VLAN, + .fv_idx = ICE_EXTERNAL_VLAN_ID_FV_IDX, + .ignore_valid = true, + .mask = 0, + .mask_valid = false, /* use pre-existing mask */ + .lkup_idx = ICE_SW_LKUP_PROMISC_VLAN_LOC_LKUP_IDX, + }, +}; + +/** + * ice_dvm_update_dflt_recipes - update default switch recipes in DVM + * @hw: hardware structure used to update the recipes + */ +static int ice_dvm_update_dflt_recipes(struct ice_hw *hw) +{ + unsigned long i; + + for (i = 0; i < ARRAY_SIZE(ice_dvm_dflt_recipes); i++) { + struct ice_update_recipe_lkup_idx_params *params; + int status; + + params = &ice_dvm_dflt_recipes[i]; + + status = ice_update_recipe_lkup_idx(hw, params); + if (status) { + ice_debug(hw, ICE_DBG_INIT, "Failed to update RID %d lkup_idx %d fv_idx %d mask_valid %s mask 0x%04x\n", + params->rid, params->lkup_idx, params->fv_idx, + params->mask_valid ? "true" : "false", + params->mask); + return status; + } + } + + return 0; +} + +/** + * ice_aq_set_vlan_mode - set the VLAN mode of the device + * @hw: pointer to the HW structure + * @set_params: requested VLAN mode configuration + * + * Set VLAN Mode Parameters (0x020C) + */ +static int +ice_aq_set_vlan_mode(struct ice_hw *hw, + struct ice_aqc_set_vlan_mode *set_params) +{ + u8 rdma_packet, mng_vlan_prot_id; + struct ice_aq_desc desc; + + if (!set_params) + return -EINVAL; + + if (set_params->l2tag_prio_tagging > ICE_AQ_VLAN_PRIO_TAG_MAX) + return -EINVAL; + + rdma_packet = set_params->rdma_packet; + if (rdma_packet != ICE_AQ_SVM_VLAN_RDMA_PKT_FLAG_SETTING && + rdma_packet != ICE_AQ_DVM_VLAN_RDMA_PKT_FLAG_SETTING) + return -EINVAL; + + mng_vlan_prot_id = set_params->mng_vlan_prot_id; + if (mng_vlan_prot_id != ICE_AQ_VLAN_MNG_PROTOCOL_ID_OUTER && + mng_vlan_prot_id != ICE_AQ_VLAN_MNG_PROTOCOL_ID_INNER) + return -EINVAL; + + ice_fill_dflt_direct_cmd_desc(&desc, + ice_aqc_opc_set_vlan_mode_parameters); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + return ice_aq_send_cmd(hw, &desc, set_params, sizeof(*set_params), + NULL); +} + +/** + * ice_set_dvm - sets up software and hardware for double VLAN mode + * @hw: pointer to the hardware structure + */ +static int ice_set_dvm(struct ice_hw *hw) +{ + struct ice_aqc_set_vlan_mode params = { 0 }; + int status; + + params.l2tag_prio_tagging = ICE_AQ_VLAN_PRIO_TAG_OUTER_CTAG; + params.rdma_packet = ICE_AQ_DVM_VLAN_RDMA_PKT_FLAG_SETTING; + params.mng_vlan_prot_id = ICE_AQ_VLAN_MNG_PROTOCOL_ID_OUTER; + + status = ice_aq_set_vlan_mode(hw, ¶ms); + if (status) { + ice_debug(hw, ICE_DBG_INIT, "Failed to set double VLAN mode parameters, status %d\n", + status); + return status; + } + + status = ice_dvm_update_dflt_recipes(hw); + if (status) { + ice_debug(hw, ICE_DBG_INIT, "Failed to update default recipes for double VLAN mode, status %d\n", + status); + return status; + } + + status = ice_aq_set_port_params(hw->port_info, true, NULL); + if (status) { + ice_debug(hw, ICE_DBG_INIT, "Failed to set port in double VLAN mode, status %d\n", + status); + return status; + } + + status = ice_set_dvm_boost_entries(hw); + if (status) { + ice_debug(hw, ICE_DBG_INIT, "Failed to set boost TCAM entries for double VLAN mode, status %d\n", + status); + return status; + } + + return 0; +} + +/** + * ice_set_svm - set single VLAN mode + * @hw: pointer to the HW structure + */ +static int ice_set_svm(struct ice_hw *hw) +{ + struct ice_aqc_set_vlan_mode *set_params; + int status; + + status = ice_aq_set_port_params(hw->port_info, false, NULL); + if (status) { + ice_debug(hw, ICE_DBG_INIT, "Failed to set port parameters for single VLAN mode\n"); + return status; + } + + set_params = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*set_params), + GFP_KERNEL); + if (!set_params) + return -ENOMEM; + + /* default configuration for SVM configurations */ + set_params->l2tag_prio_tagging = ICE_AQ_VLAN_PRIO_TAG_INNER_CTAG; + set_params->rdma_packet = ICE_AQ_SVM_VLAN_RDMA_PKT_FLAG_SETTING; + set_params->mng_vlan_prot_id = ICE_AQ_VLAN_MNG_PROTOCOL_ID_INNER; + + status = ice_aq_set_vlan_mode(hw, set_params); + if (status) + ice_debug(hw, ICE_DBG_INIT, "Failed to configure port in single VLAN mode\n"); + + devm_kfree(ice_hw_to_dev(hw), set_params); + return status; +} + +/** + * ice_set_vlan_mode + * @hw: pointer to the HW structure + */ +int ice_set_vlan_mode(struct ice_hw *hw) +{ + if (!ice_is_dvm_supported(hw)) + return 0; + + if (!ice_set_dvm(hw)) + return 0; + + return ice_set_svm(hw); +} + +/** + * ice_print_dvm_not_supported - print if DDP and/or FW doesn't support DVM + * @hw: pointer to the HW structure + * + * The purpose of this function is to print that QinQ is not supported due to + * incompatibilty from the DDP and/or FW. This will give a hint to the user to + * update one and/or both components if they expect QinQ functionality. + */ +static void ice_print_dvm_not_supported(struct ice_hw *hw) +{ + bool pkg_supports_dvm = ice_pkg_supports_dvm(hw); + bool fw_supports_dvm = ice_fw_supports_dvm(hw); + + if (!fw_supports_dvm && !pkg_supports_dvm) + dev_info(ice_hw_to_dev(hw), "QinQ functionality cannot be enabled on this device. Update your DDP package and NVM to versions that support QinQ.\n"); + else if (!pkg_supports_dvm) + dev_info(ice_hw_to_dev(hw), "QinQ functionality cannot be enabled on this device. Update your DDP package to a version that supports QinQ.\n"); + else if (!fw_supports_dvm) + dev_info(ice_hw_to_dev(hw), "QinQ functionality cannot be enabled on this device. Update your NVM to a version that supports QinQ.\n"); +} + +/** + * ice_post_pkg_dwnld_vlan_mode_cfg - configure VLAN mode after DDP download + * @hw: pointer to the HW structure + * + * This function is meant to configure any VLAN mode specific functionality + * after the global configuration lock has been released and the DDP has been + * downloaded. + * + * Since only one PF downloads the DDP and configures the VLAN mode there needs + * to be a way to configure the other PFs after the DDP has been downloaded and + * the global configuration lock has been released. All such code should go in + * this function. + */ +void ice_post_pkg_dwnld_vlan_mode_cfg(struct ice_hw *hw) +{ + ice_cache_vlan_mode(hw); + + if (ice_is_dvm_ena(hw)) + ice_change_proto_id_to_dvm(); + else + ice_print_dvm_not_supported(hw); +} diff --git a/drivers/net/ethernet/intel/ice/ice_vlan_mode.h b/drivers/net/ethernet/intel/ice/ice_vlan_mode.h new file mode 100644 index 000000000000..a0fb743d08e2 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_vlan_mode.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#ifndef _ICE_VLAN_MODE_H_ +#define _ICE_VLAN_MODE_H_ + +struct ice_hw; + +bool ice_is_dvm_ena(struct ice_hw *hw); +int ice_set_vlan_mode(struct ice_hw *hw); +void ice_post_pkg_dwnld_vlan_mode_cfg(struct ice_hw *hw); + +#endif /* _ICE_VLAN_MODE_H */ diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c new file mode 100644 index 000000000000..5b4a0abb4607 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c @@ -0,0 +1,707 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#include "ice_vsi_vlan_lib.h" +#include "ice_lib.h" +#include "ice_fltr.h" +#include "ice.h" + +static void print_invalid_tpid(struct ice_vsi *vsi, u16 tpid) +{ + dev_err(ice_pf_to_dev(vsi->back), "%s %d specified invalid VLAN tpid 0x%04x\n", + ice_vsi_type_str(vsi->type), vsi->idx, tpid); +} + +/** + * validate_vlan - check if the ice_vlan passed in is valid + * @vsi: VSI used for printing error message + * @vlan: ice_vlan structure to validate + * + * Return true if the VLAN TPID is valid or if the VLAN TPID is 0 and the VLAN + * VID is 0, which allows for non-zero VLAN filters with the specified VLAN TPID + * and untagged VLAN 0 filters to be added to the prune list respectively. + */ +static bool validate_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) +{ + if (vlan->tpid != ETH_P_8021Q && vlan->tpid != ETH_P_8021AD && + vlan->tpid != ETH_P_QINQ1 && (vlan->tpid || vlan->vid)) { + print_invalid_tpid(vsi, vlan->tpid); + return false; + } + + return true; +} + +/** + * ice_vsi_add_vlan - default add VLAN implementation for all VSI types + * @vsi: VSI being configured + * @vlan: VLAN filter to add + */ +int ice_vsi_add_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) +{ + int err; + + if (!validate_vlan(vsi, vlan)) + return -EINVAL; + + err = ice_fltr_add_vlan(vsi, vlan); + if (err && err != -EEXIST) { + dev_err(ice_pf_to_dev(vsi->back), "Failure Adding VLAN %d on VSI %i, status %d\n", + vlan->vid, vsi->vsi_num, err); + return err; + } + + vsi->num_vlan++; + return 0; +} + +/** + * ice_vsi_del_vlan - default del VLAN implementation for all VSI types + * @vsi: VSI being configured + * @vlan: VLAN filter to delete + */ +int ice_vsi_del_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) +{ + struct ice_pf *pf = vsi->back; + struct device *dev; + int err; + + if (!validate_vlan(vsi, vlan)) + return -EINVAL; + + dev = ice_pf_to_dev(pf); + + err = ice_fltr_remove_vlan(vsi, vlan); + if (!err) + vsi->num_vlan--; + else if (err == -ENOENT || err == -EBUSY) + err = 0; + else + dev_err(dev, "Error removing VLAN %d on VSI %i error: %d\n", + vlan->vid, vsi->vsi_num, err); + + return err; +} + +/** + * ice_vsi_manage_vlan_insertion - Manage VLAN insertion for the VSI for Tx + * @vsi: the VSI being changed + */ +static int ice_vsi_manage_vlan_insertion(struct ice_vsi *vsi) +{ + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx *ctxt; + int err; + + ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + /* Here we are configuring the VSI to let the driver add VLAN tags by + * setting inner_vlan_flags to ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL. The actual VLAN tag + * insertion happens in the Tx hot path, in ice_tx_map. + */ + ctxt->info.inner_vlan_flags = ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL; + + /* Preserve existing VLAN strip setting */ + ctxt->info.inner_vlan_flags |= (vsi->info.inner_vlan_flags & + ICE_AQ_VSI_INNER_VLAN_EMODE_M); + + ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID); + + err = ice_update_vsi(hw, vsi->idx, ctxt, NULL); + if (err) { + dev_err(ice_pf_to_dev(vsi->back), "update VSI for VLAN insert failed, err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); + goto out; + } + + vsi->info.inner_vlan_flags = ctxt->info.inner_vlan_flags; +out: + kfree(ctxt); + return err; +} + +/** + * ice_vsi_manage_vlan_stripping - Manage VLAN stripping for the VSI for Rx + * @vsi: the VSI being changed + * @ena: boolean value indicating if this is a enable or disable request + */ +static int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena) +{ + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx *ctxt; + int err; + + /* do not allow modifying VLAN stripping when a port VLAN is configured + * on this VSI + */ + if (vsi->info.port_based_inner_vlan) + return 0; + + ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + /* Here we are configuring what the VSI should do with the VLAN tag in + * the Rx packet. We can either leave the tag in the packet or put it in + * the Rx descriptor. + */ + if (ena) + /* Strip VLAN tag from Rx packet and put it in the desc */ + ctxt->info.inner_vlan_flags = ICE_AQ_VSI_INNER_VLAN_EMODE_STR_BOTH; + else + /* Disable stripping. Leave tag in packet */ + ctxt->info.inner_vlan_flags = ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING; + + /* Allow all packets untagged/tagged */ + ctxt->info.inner_vlan_flags |= ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL; + + ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID); + + err = ice_update_vsi(hw, vsi->idx, ctxt, NULL); + if (err) { + dev_err(ice_pf_to_dev(vsi->back), "update VSI for VLAN strip failed, ena = %d err %d aq_err %s\n", + ena, err, ice_aq_str(hw->adminq.sq_last_status)); + goto out; + } + + vsi->info.inner_vlan_flags = ctxt->info.inner_vlan_flags; +out: + kfree(ctxt); + return err; +} + +int ice_vsi_ena_inner_stripping(struct ice_vsi *vsi, const u16 tpid) +{ + if (tpid != ETH_P_8021Q) { + print_invalid_tpid(vsi, tpid); + return -EINVAL; + } + + return ice_vsi_manage_vlan_stripping(vsi, true); +} + +int ice_vsi_dis_inner_stripping(struct ice_vsi *vsi) +{ + return ice_vsi_manage_vlan_stripping(vsi, false); +} + +int ice_vsi_ena_inner_insertion(struct ice_vsi *vsi, const u16 tpid) +{ + if (tpid != ETH_P_8021Q) { + print_invalid_tpid(vsi, tpid); + return -EINVAL; + } + + return ice_vsi_manage_vlan_insertion(vsi); +} + +int ice_vsi_dis_inner_insertion(struct ice_vsi *vsi) +{ + return ice_vsi_manage_vlan_insertion(vsi); +} + +/** + * __ice_vsi_set_inner_port_vlan - set port VLAN VSI context settings to enable a port VLAN + * @vsi: the VSI to update + * @pvid_info: VLAN ID and QoS used to set the PVID VSI context field + */ +static int __ice_vsi_set_inner_port_vlan(struct ice_vsi *vsi, u16 pvid_info) +{ + 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; + + ctxt->info = vsi->info; + info = &ctxt->info; + info->inner_vlan_flags = ICE_AQ_VSI_INNER_VLAN_TX_MODE_ACCEPTUNTAGGED | + ICE_AQ_VSI_INNER_VLAN_INSERT_PVID | + ICE_AQ_VSI_INNER_VLAN_EMODE_STR; + info->sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; + + info->port_based_inner_vlan = cpu_to_le16(pvid_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_info(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)); + goto out; + } + + vsi->info.inner_vlan_flags = info->inner_vlan_flags; + vsi->info.sw_flags2 = info->sw_flags2; + vsi->info.port_based_inner_vlan = info->port_based_inner_vlan; +out: + kfree(ctxt); + return ret; +} + +int ice_vsi_set_inner_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) +{ + u16 port_vlan_info; + + if (vlan->tpid != ETH_P_8021Q) + return -EINVAL; + + if (vlan->prio > 7) + return -EINVAL; + + port_vlan_info = vlan->vid | (vlan->prio << VLAN_PRIO_SHIFT); + + return __ice_vsi_set_inner_port_vlan(vsi, port_vlan_info); +} + +/** + * ice_cfg_vlan_pruning - enable or disable VLAN pruning on the VSI + * @vsi: VSI to enable or disable VLAN pruning on + * @ena: set to true to enable VLAN pruning and false to disable it + * + * returns 0 if VSI is updated, negative otherwise + */ +static int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena) +{ + struct ice_vsi_ctx *ctxt; + struct ice_pf *pf; + int status; + + if (!vsi) + return -EINVAL; + + /* Don't enable VLAN pruning if the netdev is currently in promiscuous + * mode. VLAN pruning will be enabled when the interface exits + * promiscuous mode if any VLAN filters are active. + */ + if (vsi->netdev && vsi->netdev->flags & IFF_PROMISC && ena) + return 0; + + pf = vsi->back; + ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + ctxt->info = vsi->info; + + if (ena) + ctxt->info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; + else + ctxt->info.sw_flags2 &= ~ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; + + ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SW_VALID); + + status = ice_update_vsi(&pf->hw, vsi->idx, ctxt, NULL); + if (status) { + netdev_err(vsi->netdev, "%sabling VLAN pruning on VSI handle: %d, VSI HW ID: %d failed, err = %d, aq_err = %s\n", + ena ? "En" : "Dis", vsi->idx, vsi->vsi_num, status, + ice_aq_str(pf->hw.adminq.sq_last_status)); + goto err_out; + } + + vsi->info.sw_flags2 = ctxt->info.sw_flags2; + + kfree(ctxt); + return 0; + +err_out: + kfree(ctxt); + return status; +} + +int ice_vsi_ena_rx_vlan_filtering(struct ice_vsi *vsi) +{ + return ice_cfg_vlan_pruning(vsi, true); +} + +int ice_vsi_dis_rx_vlan_filtering(struct ice_vsi *vsi) +{ + return ice_cfg_vlan_pruning(vsi, false); +} + +static int ice_cfg_vlan_antispoof(struct ice_vsi *vsi, bool enable) +{ + struct ice_vsi_ctx *ctx; + int err; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->info.sec_flags = vsi->info.sec_flags; + ctx->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID); + + if (enable) + ctx->info.sec_flags |= ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA << + ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S; + else + ctx->info.sec_flags &= ~(ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA << + ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S); + + err = ice_update_vsi(&vsi->back->hw, vsi->idx, ctx, NULL); + if (err) + dev_err(ice_pf_to_dev(vsi->back), "Failed to configure Tx VLAN anti-spoof %s for VSI %d, error %d\n", + enable ? "ON" : "OFF", vsi->vsi_num, err); + else + vsi->info.sec_flags = ctx->info.sec_flags; + + kfree(ctx); + + return err; +} + +int ice_vsi_ena_tx_vlan_filtering(struct ice_vsi *vsi) +{ + return ice_cfg_vlan_antispoof(vsi, true); +} + +int ice_vsi_dis_tx_vlan_filtering(struct ice_vsi *vsi) +{ + return ice_cfg_vlan_antispoof(vsi, false); +} + +/** + * tpid_to_vsi_outer_vlan_type - convert from TPID to VSI context based tag_type + * @tpid: tpid used to translate into VSI context based tag_type + * @tag_type: output variable to hold the VSI context based tag type + */ +static int tpid_to_vsi_outer_vlan_type(u16 tpid, u8 *tag_type) +{ + switch (tpid) { + case ETH_P_8021Q: + *tag_type = ICE_AQ_VSI_OUTER_TAG_VLAN_8100; + break; + case ETH_P_8021AD: + *tag_type = ICE_AQ_VSI_OUTER_TAG_STAG; + break; + case ETH_P_QINQ1: + *tag_type = ICE_AQ_VSI_OUTER_TAG_VLAN_9100; + break; + default: + *tag_type = 0; + return -EINVAL; + } + + return 0; +} + +/** + * ice_vsi_ena_outer_stripping - enable outer VLAN stripping + * @vsi: VSI to configure + * @tpid: TPID to enable outer VLAN stripping for + * + * Enable outer VLAN stripping via VSI context. This function should only be + * 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. + * + * Since the VSI context only supports a single TPID for insertion and + * stripping, setting the TPID for stripping will affect the TPID for insertion. + * Callers need to be aware of this limitation. + * + * Only modify outer VLAN stripping settings and the VLAN TPID. Outer VLAN + * insertion settings are unmodified. + * + * This enables hardware to strip a VLAN tag with the specified TPID to be + * stripped from the packet and placed in the receive descriptor. + */ +int ice_vsi_ena_outer_stripping(struct ice_vsi *vsi, u16 tpid) +{ + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx *ctxt; + u8 tag_type; + int err; + + /* do not allow modifying VLAN stripping when a port VLAN is configured + * on this VSI + */ + if (vsi->info.port_based_outer_vlan) + return 0; + + if (tpid_to_vsi_outer_vlan_type(tpid, &tag_type)) + return -EINVAL; + + ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + ctxt->info.valid_sections = + cpu_to_le16(ICE_AQ_VSI_PROP_OUTER_TAG_VALID); + /* clear current outer VLAN strip settings */ + ctxt->info.outer_vlan_flags = vsi->info.outer_vlan_flags & + ~(ICE_AQ_VSI_OUTER_VLAN_EMODE_M | ICE_AQ_VSI_OUTER_TAG_TYPE_M); + ctxt->info.outer_vlan_flags |= + ((ICE_AQ_VSI_OUTER_VLAN_EMODE_SHOW_BOTH << + ICE_AQ_VSI_OUTER_VLAN_EMODE_S) | + ((tag_type << ICE_AQ_VSI_OUTER_TAG_TYPE_S) & + ICE_AQ_VSI_OUTER_TAG_TYPE_M)); + + err = ice_update_vsi(hw, vsi->idx, ctxt, NULL); + if (err) + dev_err(ice_pf_to_dev(vsi->back), "update VSI for enabling outer VLAN stripping failed, err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); + else + vsi->info.outer_vlan_flags = ctxt->info.outer_vlan_flags; + + kfree(ctxt); + return err; +} + +/** + * ice_vsi_dis_outer_stripping - disable outer VLAN stripping + * @vsi: VSI to configure + * + * Disable outer VLAN stripping via VSI context. This function should only be + * 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. + * + * Only modify the outer VLAN stripping settings. The VLAN TPID and outer VLAN + * insertion settings are unmodified. + * + * This tells the hardware to not strip any VLAN tagged packets, thus leaving + * them in the packet. This enables software offloaded VLAN stripping and + * disables hardware offloaded VLAN stripping. + */ +int ice_vsi_dis_outer_stripping(struct ice_vsi *vsi) +{ + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx *ctxt; + int err; + + if (vsi->info.port_based_outer_vlan) + return 0; + + ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + ctxt->info.valid_sections = + cpu_to_le16(ICE_AQ_VSI_PROP_OUTER_TAG_VALID); + /* clear current outer VLAN strip settings */ + ctxt->info.outer_vlan_flags = vsi->info.outer_vlan_flags & + ~ICE_AQ_VSI_OUTER_VLAN_EMODE_M; + ctxt->info.outer_vlan_flags |= ICE_AQ_VSI_OUTER_VLAN_EMODE_NOTHING << + ICE_AQ_VSI_OUTER_VLAN_EMODE_S; + + err = ice_update_vsi(hw, vsi->idx, ctxt, NULL); + if (err) + dev_err(ice_pf_to_dev(vsi->back), "update VSI for disabling outer VLAN stripping failed, err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); + else + vsi->info.outer_vlan_flags = ctxt->info.outer_vlan_flags; + + kfree(ctxt); + return err; +} + +/** + * ice_vsi_ena_outer_insertion - enable outer VLAN insertion + * @vsi: VSI to configure + * @tpid: TPID to enable outer VLAN insertion for + * + * Enable outer VLAN insertion via VSI context. This function should only be + * 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. + * + * Since the VSI context only supports a single TPID for insertion and + * stripping, setting the TPID for insertion will affect the TPID for stripping. + * Callers need to be aware of this limitation. + * + * Only modify outer VLAN insertion settings and the VLAN TPID. Outer VLAN + * stripping settings are unmodified. + * + * This allows a VLAN tag with the specified TPID to be inserted in the transmit + * descriptor. + */ +int ice_vsi_ena_outer_insertion(struct ice_vsi *vsi, u16 tpid) +{ + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx *ctxt; + u8 tag_type; + int err; + + if (vsi->info.port_based_outer_vlan) + return 0; + + if (tpid_to_vsi_outer_vlan_type(tpid, &tag_type)) + return -EINVAL; + + ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + ctxt->info.valid_sections = + cpu_to_le16(ICE_AQ_VSI_PROP_OUTER_TAG_VALID); + /* clear current outer VLAN insertion settings */ + ctxt->info.outer_vlan_flags = vsi->info.outer_vlan_flags & + ~(ICE_AQ_VSI_OUTER_VLAN_PORT_BASED_INSERT | + ICE_AQ_VSI_OUTER_VLAN_BLOCK_TX_DESC | + ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M | + ICE_AQ_VSI_OUTER_TAG_TYPE_M); + ctxt->info.outer_vlan_flags |= + ((ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL << + ICE_AQ_VSI_OUTER_VLAN_TX_MODE_S) & + ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M) | + ((tag_type << ICE_AQ_VSI_OUTER_TAG_TYPE_S) & + ICE_AQ_VSI_OUTER_TAG_TYPE_M); + + err = ice_update_vsi(hw, vsi->idx, ctxt, NULL); + if (err) + dev_err(ice_pf_to_dev(vsi->back), "update VSI for enabling outer VLAN insertion failed, err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); + else + vsi->info.outer_vlan_flags = ctxt->info.outer_vlan_flags; + + kfree(ctxt); + return err; +} + +/** + * ice_vsi_dis_outer_insertion - disable outer VLAN insertion + * @vsi: VSI to configure + * + * Disable outer VLAN insertion via VSI context. This function should only be + * 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. + * + * Only modify the outer VLAN insertion settings. The VLAN TPID and outer VLAN + * settings are unmodified. + * + * This tells the hardware to not allow any VLAN tagged packets in the transmit + * descriptor. This enables software offloaded VLAN insertion and disables + * hardware offloaded VLAN insertion. + */ +int ice_vsi_dis_outer_insertion(struct ice_vsi *vsi) +{ + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx *ctxt; + int err; + + if (vsi->info.port_based_outer_vlan) + return 0; + + ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + ctxt->info.valid_sections = + cpu_to_le16(ICE_AQ_VSI_PROP_OUTER_TAG_VALID); + /* clear current outer VLAN insertion settings */ + ctxt->info.outer_vlan_flags = vsi->info.outer_vlan_flags & + ~(ICE_AQ_VSI_OUTER_VLAN_PORT_BASED_INSERT | + ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M); + ctxt->info.outer_vlan_flags |= + ICE_AQ_VSI_OUTER_VLAN_BLOCK_TX_DESC | + ((ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL << + ICE_AQ_VSI_OUTER_VLAN_TX_MODE_S) & + ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M); + + err = ice_update_vsi(hw, vsi->idx, ctxt, NULL); + if (err) + dev_err(ice_pf_to_dev(vsi->back), "update VSI for disabling outer VLAN insertion failed, err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); + else + vsi->info.outer_vlan_flags = ctxt->info.outer_vlan_flags; + + kfree(ctxt); + return err; +} + +/** + * __ice_vsi_set_outer_port_vlan - set the outer port VLAN and related settings + * @vsi: VSI to configure + * @vlan_info: packed u16 that contains the VLAN prio and ID + * @tpid: TPID of the port VLAN + * + * Set the port VLAN prio, ID, and TPID. + * + * Enable VLAN pruning so the VSI doesn't receive any traffic that doesn't match + * a VLAN prune rule. The caller should take care to add a VLAN prune rule that + * matches the port VLAN ID and TPID. + * + * Tell hardware to strip outer VLAN tagged packets on receive and don't put + * them in the receive descriptor. VSI(s) in port VLANs should not be aware of + * the port VLAN ID or TPID they are assigned to. + * + * Tell hardware to prevent outer VLAN tag insertion on transmit and only allow + * untagged outer packets from the transmit descriptor. + * + * Also, tell the hardware to insert the port VLAN on transmit. + */ +static int +__ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, u16 vlan_info, u16 tpid) +{ + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx *ctxt; + u8 tag_type; + int err; + + if (tpid_to_vsi_outer_vlan_type(tpid, &tag_type)) + return -EINVAL; + + ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + ctxt->info = vsi->info; + + ctxt->info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; + + ctxt->info.port_based_outer_vlan = cpu_to_le16(vlan_info); + ctxt->info.outer_vlan_flags = + (ICE_AQ_VSI_OUTER_VLAN_EMODE_SHOW << + ICE_AQ_VSI_OUTER_VLAN_EMODE_S) | + ((tag_type << ICE_AQ_VSI_OUTER_TAG_TYPE_S) & + ICE_AQ_VSI_OUTER_TAG_TYPE_M) | + ICE_AQ_VSI_OUTER_VLAN_BLOCK_TX_DESC | + (ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ACCEPTUNTAGGED << + ICE_AQ_VSI_OUTER_VLAN_TX_MODE_S) | + ICE_AQ_VSI_OUTER_VLAN_PORT_BASED_INSERT; + + 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 setting outer port based VLAN failed, err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); + } else { + vsi->info.port_based_outer_vlan = ctxt->info.port_based_outer_vlan; + vsi->info.outer_vlan_flags = ctxt->info.outer_vlan_flags; + vsi->info.sw_flags2 = ctxt->info.sw_flags2; + } + + kfree(ctxt); + return err; +} + +/** + * ice_vsi_set_outer_port_vlan - public version of __ice_vsi_set_outer_port_vlan + * @vsi: VSI to configure + * @vlan: ice_vlan structure used to set the port VLAN + * + * Set the outer port VLAN via VSI context. This function should only be + * 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) +{ + u16 port_vlan_info; + + if (vlan->prio > (VLAN_PRIO_MASK >> VLAN_PRIO_SHIFT)) + return -EINVAL; + + port_vlan_info = vlan->vid | (vlan->prio << VLAN_PRIO_SHIFT); + + return __ice_vsi_set_outer_port_vlan(vsi, port_vlan_info, vlan->tpid); +} diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h new file mode 100644 index 000000000000..f459909490ec --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#ifndef _ICE_VSI_VLAN_LIB_H_ +#define _ICE_VSI_VLAN_LIB_H_ + +#include <linux/types.h> +#include "ice_vlan.h" + +struct ice_vsi; + +int ice_vsi_add_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan); +int ice_vsi_del_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan); + +int ice_vsi_ena_inner_stripping(struct ice_vsi *vsi, u16 tpid); +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_ena_rx_vlan_filtering(struct ice_vsi *vsi); +int ice_vsi_dis_rx_vlan_filtering(struct ice_vsi *vsi); +int ice_vsi_ena_tx_vlan_filtering(struct ice_vsi *vsi); +int ice_vsi_dis_tx_vlan_filtering(struct ice_vsi *vsi); + +int ice_vsi_ena_outer_stripping(struct ice_vsi *vsi, u16 tpid); +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); + +#endif /* _ICE_VSI_VLAN_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.c new file mode 100644 index 000000000000..4a6c850d83ac --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.c @@ -0,0 +1,103 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#include "ice_pf_vsi_vlan_ops.h" +#include "ice_vf_vsi_vlan_ops.h" +#include "ice_lib.h" +#include "ice.h" + +static int +op_unsupported_vlan_arg(struct ice_vsi * __always_unused vsi, + struct ice_vlan * __always_unused vlan) +{ + return -EOPNOTSUPP; +} + +static int +op_unsupported_tpid_arg(struct ice_vsi *__always_unused vsi, + u16 __always_unused tpid) +{ + return -EOPNOTSUPP; +} + +static int op_unsupported(struct ice_vsi *__always_unused vsi) +{ + return -EOPNOTSUPP; +} + +/* If any new ops are added to the VSI VLAN ops interface then an unsupported + * implementation should be set here. + */ +static struct ice_vsi_vlan_ops ops_unsupported = { + .add_vlan = op_unsupported_vlan_arg, + .del_vlan = op_unsupported_vlan_arg, + .ena_stripping = op_unsupported_tpid_arg, + .dis_stripping = op_unsupported, + .ena_insertion = op_unsupported_tpid_arg, + .dis_insertion = op_unsupported, + .ena_rx_filtering = op_unsupported, + .dis_rx_filtering = op_unsupported, + .ena_tx_filtering = op_unsupported, + .dis_tx_filtering = op_unsupported, + .set_port_vlan = op_unsupported_vlan_arg, +}; + +/** + * ice_vsi_init_unsupported_vlan_ops - init all VSI VLAN ops to unsupported + * @vsi: VSI to initialize VSI VLAN ops to unsupported for + * + * By default all inner and outer VSI VLAN ops return -EOPNOTSUPP. This was done + * as oppsed to leaving the ops null to prevent unexpected crashes. Instead if + * an unsupported VSI VLAN op is called it will just return -EOPNOTSUPP. + * + */ +static void ice_vsi_init_unsupported_vlan_ops(struct ice_vsi *vsi) +{ + vsi->outer_vlan_ops = ops_unsupported; + vsi->inner_vlan_ops = ops_unsupported; +} + +/** + * ice_vsi_init_vlan_ops - initialize type specific VSI VLAN ops + * @vsi: VSI to initialize ops for + * + * If any VSI types are added and/or require different ops than the PF or VF VSI + * then they will have to add a case here to handle that. Also, VSI type + * specific files should be added in the same manner that was done for PF VSI. + */ +void ice_vsi_init_vlan_ops(struct ice_vsi *vsi) +{ + /* Initialize all VSI types to have unsupported VSI VLAN ops */ + ice_vsi_init_unsupported_vlan_ops(vsi); + + switch (vsi->type) { + case ICE_VSI_PF: + case ICE_VSI_SWITCHDEV_CTRL: + ice_pf_vsi_init_vlan_ops(vsi); + break; + case ICE_VSI_VF: + ice_vf_vsi_init_vlan_ops(vsi); + break; + default: + dev_dbg(ice_pf_to_dev(vsi->back), "%s does not support VLAN operations\n", + ice_vsi_type_str(vsi->type)); + break; + } +} + +/** + * ice_get_compat_vsi_vlan_ops - Get VSI VLAN ops based on VLAN mode + * @vsi: VSI used to get the VSI VLAN ops + * + * This function is meant to be used when the caller doesn't know which VLAN ops + * to use (i.e. inner or outer). This allows backward compatibility for VLANs + * since most of the Outer VSI VLAN functins are not supported when + * the device is configured in Single VLAN Mode (SVM). + */ +struct ice_vsi_vlan_ops *ice_get_compat_vsi_vlan_ops(struct ice_vsi *vsi) +{ + if (ice_is_dvm_ena(&vsi->back->hw)) + return &vsi->outer_vlan_ops; + else + return &vsi->inner_vlan_ops; +} diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.h b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.h new file mode 100644 index 000000000000..5b47568f6256 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#ifndef _ICE_VSI_VLAN_OPS_H_ +#define _ICE_VSI_VLAN_OPS_H_ + +#include "ice_type.h" +#include "ice_vsi_vlan_lib.h" + +struct ice_vsi; + +struct ice_vsi_vlan_ops { + int (*add_vlan)(struct ice_vsi *vsi, struct ice_vlan *vlan); + int (*del_vlan)(struct ice_vsi *vsi, struct ice_vlan *vlan); + int (*ena_stripping)(struct ice_vsi *vsi, const u16 tpid); + int (*dis_stripping)(struct ice_vsi *vsi); + int (*ena_insertion)(struct ice_vsi *vsi, const u16 tpid); + int (*dis_insertion)(struct ice_vsi *vsi); + int (*ena_rx_filtering)(struct ice_vsi *vsi); + int (*dis_rx_filtering)(struct ice_vsi *vsi); + 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); +}; + +void ice_vsi_init_vlan_ops(struct ice_vsi *vsi); +struct ice_vsi_vlan_ops *ice_get_compat_vsi_vlan_ops(struct ice_vsi *vsi); + +#endif /* _ICE_VSI_VLAN_OPS_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 2388837d6d6c..056c904b83cc 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -41,8 +41,10 @@ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx) static void ice_qp_clean_rings(struct ice_vsi *vsi, u16 q_idx) { ice_clean_tx_ring(vsi->tx_rings[q_idx]); - if (ice_is_xdp_ena_vsi(vsi)) + if (ice_is_xdp_ena_vsi(vsi)) { + synchronize_rcu(); ice_clean_tx_ring(vsi->xdp_rings[q_idx]); + } ice_clean_rx_ring(vsi->rx_rings[q_idx]); } @@ -190,6 +192,7 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) err = ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, true); if (err) return err; + ice_clean_rx_ring(rx_ring); ice_qvec_toggle_napi(vsi, q_vector, false); ice_qp_clean_rings(vsi, q_idx); @@ -241,7 +244,7 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) if (err) goto free_buf; ice_set_ring_xdp(xdp_ring); - xdp_ring->xsk_pool = ice_tx_xsk_pool(xdp_ring); + ice_tx_xsk_pool(vsi, q_idx); } err = ice_vsi_cfg_rxq(rx_ring); @@ -315,6 +318,62 @@ ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) } /** + * ice_realloc_rx_xdp_bufs - reallocate for either XSK or normal buffer + * @rx_ring: Rx ring + * @pool_present: is pool for XSK present + * + * Try allocating memory and return ENOMEM, if failed to allocate. + * If allocation was successful, substitute buffer with allocated one. + * Returns 0 on success, negative on failure + */ +static int +ice_realloc_rx_xdp_bufs(struct ice_rx_ring *rx_ring, bool pool_present) +{ + size_t elem_size = pool_present ? sizeof(*rx_ring->xdp_buf) : + sizeof(*rx_ring->rx_buf); + void *sw_ring = kcalloc(rx_ring->count, elem_size, GFP_KERNEL); + + if (!sw_ring) + return -ENOMEM; + + if (pool_present) { + kfree(rx_ring->rx_buf); + rx_ring->rx_buf = NULL; + rx_ring->xdp_buf = sw_ring; + } else { + kfree(rx_ring->xdp_buf); + rx_ring->xdp_buf = NULL; + rx_ring->rx_buf = sw_ring; + } + + return 0; +} + +/** + * ice_realloc_zc_buf - reallocate XDP ZC queue pairs + * @vsi: Current VSI + * @zc: is zero copy set + * + * Reallocate buffer for rx_rings that might be used by XSK. + * XDP requires more memory, than rx_buf provides. + * Returns 0 on success, negative on failure + */ +int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc) +{ + struct ice_rx_ring *rx_ring; + unsigned long q; + + for_each_set_bit(q, vsi->af_xdp_zc_qps, + max_t(int, vsi->alloc_txq, vsi->alloc_rxq)) { + rx_ring = vsi->rx_rings[q]; + if (ice_realloc_rx_xdp_bufs(rx_ring, zc)) + return -ENOMEM; + } + + return 0; +} + +/** * ice_xsk_pool_setup - enable/disable a buffer pool region depending on its state * @vsi: Current VSI * @pool: buffer pool to enable/associate to a ring, NULL to disable @@ -327,14 +386,26 @@ int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) bool if_running, pool_present = !!pool; int ret = 0, pool_failure = 0; + if (qid >= vsi->num_rxq || qid >= vsi->num_txq) { + netdev_err(vsi->netdev, "Please use queue id in scope of combined queues count\n"); + pool_failure = -EINVAL; + goto failure; + } + if_running = netif_running(vsi->netdev) && ice_is_xdp_ena_vsi(vsi); if (if_running) { + struct ice_rx_ring *rx_ring = vsi->rx_rings[qid]; + ret = ice_qp_dis(vsi, qid); if (ret) { netdev_err(vsi->netdev, "ice_qp_dis error = %d\n", ret); goto xsk_pool_if_up; } + + ret = ice_realloc_rx_xdp_bufs(rx_ring, pool_present); + if (ret) + goto xsk_pool_if_up; } pool_failure = pool_present ? ice_xsk_pool_enable(vsi, pool, qid) : @@ -344,11 +415,12 @@ xsk_pool_if_up: if (if_running) { ret = ice_qp_ena(vsi, qid); if (!ret && pool_present) - napi_schedule(&vsi->xdp_rings[qid]->q_vector->napi); + napi_schedule(&vsi->rx_rings[qid]->xdp_ring->q_vector->napi); else if (ret) netdev_err(vsi->netdev, "ice_qp_ena error = %d\n", ret); } +failure: if (pool_failure) { netdev_err(vsi->netdev, "Could not %sable buffer pool, error = %d\n", pool_present ? "en" : "dis", pool_failure); @@ -359,33 +431,28 @@ xsk_pool_if_up: } /** - * ice_alloc_rx_bufs_zc - allocate a number of Rx buffers - * @rx_ring: Rx ring + * ice_fill_rx_descs - pick buffers from XSK buffer pool and use it + * @pool: XSK Buffer pool to pull the buffers from + * @xdp: SW ring of xdp_buff that will hold the buffers + * @rx_desc: Pointer to Rx descriptors that will be filled * @count: The number of buffers to allocate * * This function allocates a number of Rx buffers from the fill ring * or the internal recycle mechanism and places them on the Rx ring. * - * Returns true if all allocations were successful, false if any fail. + * Note that ring wrap should be handled by caller of this function. + * + * Returns the amount of allocated Rx descriptors */ -bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) +static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp, + union ice_32b_rx_flex_desc *rx_desc, u16 count) { - union ice_32b_rx_flex_desc *rx_desc; - u16 ntu = rx_ring->next_to_use; - struct xdp_buff **xdp; - u32 nb_buffs, i; dma_addr_t dma; + u16 buffs; + int i; - rx_desc = ICE_RX_DESC(rx_ring, ntu); - xdp = ice_xdp_buf(rx_ring, ntu); - - nb_buffs = min_t(u16, count, rx_ring->count - ntu); - nb_buffs = xsk_buff_alloc_batch(rx_ring->xsk_pool, xdp, nb_buffs); - if (!nb_buffs) - return false; - - i = nb_buffs; - while (i--) { + buffs = xsk_buff_alloc_batch(pool, xdp, count); + for (i = 0; i < buffs; i++) { dma = xsk_buff_xdp_get_dma(*xdp); rx_desc->read.pkt_addr = cpu_to_le64(dma); rx_desc->wb.status_error0 = 0; @@ -394,13 +461,81 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) xdp++; } + return buffs; +} + +/** + * __ice_alloc_rx_bufs_zc - allocate a number of Rx buffers + * @rx_ring: Rx ring + * @count: The number of buffers to allocate + * + * Place the @count of descriptors onto Rx ring. Handle the ring wrap + * for case where space from next_to_use up to the end of ring is less + * than @count. Finally do a tail bump. + * + * Returns true if all allocations were successful, false if any fail. + */ +static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) +{ + u32 nb_buffs_extra = 0, nb_buffs = 0; + union ice_32b_rx_flex_desc *rx_desc; + u16 ntu = rx_ring->next_to_use; + u16 total_count = count; + struct xdp_buff **xdp; + + rx_desc = ICE_RX_DESC(rx_ring, ntu); + xdp = ice_xdp_buf(rx_ring, ntu); + + if (ntu + count >= rx_ring->count) { + nb_buffs_extra = ice_fill_rx_descs(rx_ring->xsk_pool, xdp, + rx_desc, + rx_ring->count - ntu); + if (nb_buffs_extra != rx_ring->count - ntu) { + ntu += nb_buffs_extra; + goto exit; + } + rx_desc = ICE_RX_DESC(rx_ring, 0); + xdp = ice_xdp_buf(rx_ring, 0); + ntu = 0; + count -= nb_buffs_extra; + ice_release_rx_desc(rx_ring, 0); + } + + nb_buffs = ice_fill_rx_descs(rx_ring->xsk_pool, xdp, rx_desc, count); + ntu += nb_buffs; if (ntu == rx_ring->count) ntu = 0; - ice_release_rx_desc(rx_ring, ntu); +exit: + if (rx_ring->next_to_use != ntu) + ice_release_rx_desc(rx_ring, ntu); - return count == nb_buffs; + return total_count == (nb_buffs_extra + nb_buffs); +} + +/** + * ice_alloc_rx_bufs_zc - allocate a number of Rx buffers + * @rx_ring: Rx ring + * @count: The number of buffers to allocate + * + * Wrapper for internal allocation routine; figure out how many tail + * bumps should take place based on the given threshold + * + * Returns true if all calls to internal alloc routine succeeded + */ +bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) +{ + u16 rx_thresh = ICE_RING_QUARTER(rx_ring); + u16 leftover, i, tail_bumps; + + tail_bumps = count / rx_thresh; + leftover = count - (tail_bumps * rx_thresh); + + for (i = 0; i < tail_bumps; i++) + if (!__ice_alloc_rx_bufs_zc(rx_ring, rx_thresh)) + return false; + return __ice_alloc_rx_bufs_zc(rx_ring, leftover); } /** @@ -428,20 +563,24 @@ static void ice_bump_ntc(struct ice_rx_ring *rx_ring) static struct sk_buff * ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) { - unsigned int datasize_hard = xdp->data_end - xdp->data_hard_start; + unsigned int totalsize = xdp->data_end - xdp->data_meta; unsigned int metasize = xdp->data - xdp->data_meta; - unsigned int datasize = xdp->data_end - xdp->data; struct sk_buff *skb; - skb = __napi_alloc_skb(&rx_ring->q_vector->napi, datasize_hard, + net_prefetch(xdp->data_meta); + + skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize, GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL; - skb_reserve(skb, xdp->data - xdp->data_hard_start); - memcpy(__skb_put(skb, datasize), xdp->data, datasize); - if (metasize) + memcpy(__skb_put(skb, totalsize), xdp->data_meta, + ALIGN(totalsize, sizeof(long))); + + if (metasize) { skb_metadata_set(skb, metasize); + __skb_pull(skb, metasize); + } xsk_buff_free(xdp); return skb; @@ -467,9 +606,13 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, if (likely(act == XDP_REDIRECT)) { err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); - if (err) - goto out_failure; - return ICE_XDP_REDIR; + if (!err) + return ICE_XDP_REDIR; + if (xsk_uses_need_wakeup(rx_ring->xsk_pool) && err == -ENOBUFS) + result = ICE_XDP_EXIT; + else + result = ICE_XDP_CONSUMED; + goto out_failure; } switch (act) { @@ -480,15 +623,16 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, if (result == ICE_XDP_CONSUMED) goto out_failure; break; + case XDP_DROP: + result = ICE_XDP_CONSUMED; + break; default: bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, act); fallthrough; case XDP_ABORTED: + result = ICE_XDP_CONSUMED; out_failure: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); - fallthrough; - case XDP_DROP: - result = ICE_XDP_CONSUMED; break; } @@ -509,6 +653,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) unsigned int xdp_xmit = 0; struct bpf_prog *xdp_prog; bool failure = false; + int entries_to_alloc; /* ZC patch is enabled only when XDP program is set, * so here it can not be NULL @@ -528,7 +673,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) rx_desc = ICE_RX_DESC(rx_ring, rx_ring->next_to_clean); stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_DD_S); - if (!ice_test_staterr(rx_desc, stat_err_bits)) + if (!ice_test_staterr(rx_desc->wb.status_error0, stat_err_bits)) break; /* This memory barrier is needed to keep us from reading @@ -537,6 +682,9 @@ 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)) + break; + xdp = *ice_xdp_buf(rx_ring, rx_ring->next_to_clean); size = le16_to_cpu(rx_desc->wb.pkt_len) & @@ -553,18 +701,23 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) xsk_buff_dma_sync_for_cpu(xdp, rx_ring->xsk_pool); xdp_res = ice_run_xdp_zc(rx_ring, xdp, xdp_prog, xdp_ring); - if (xdp_res) { - if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR)) - xdp_xmit |= xdp_res; - else - xsk_buff_free(xdp); + if (likely(xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))) { + xdp_xmit |= xdp_res; + } else if (xdp_res == ICE_XDP_EXIT) { + failure = true; + break; + } else if (xdp_res == ICE_XDP_CONSUMED) { + xsk_buff_free(xdp); + } else if (xdp_res == ICE_XDP_PASS) { + goto construct_skb; + } - total_rx_bytes += size; - total_rx_packets++; + total_rx_bytes += size; + total_rx_packets++; + + ice_bump_ntc(rx_ring); + continue; - ice_bump_ntc(rx_ring); - continue; - } construct_skb: /* XDP_PASS path */ skb = ice_construct_skb_zc(rx_ring, xdp); @@ -583,9 +736,7 @@ construct_skb: total_rx_bytes += skb->len; total_rx_packets++; - stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_L2TAG1P_S); - if (ice_test_staterr(rx_desc, stat_err_bits)) - vlan_tag = le16_to_cpu(rx_desc->wb.l2tag1); + vlan_tag = ice_get_vlan_tag_from_rx_desc(rx_desc); rx_ptype = le16_to_cpu(rx_desc->wb.ptype_flex_flags0) & ICE_RX_FLEX_DESC_PTYPE_M; @@ -594,7 +745,9 @@ construct_skb: ice_receive_skb(rx_ring, skb, vlan_tag); } - failure = !ice_alloc_rx_bufs_zc(rx_ring, ICE_DESC_UNUSED(rx_ring)); + entries_to_alloc = ICE_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); ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes); @@ -612,58 +765,6 @@ construct_skb: } /** - * ice_xmit_zc - Completes AF_XDP entries, and cleans XDP entries - * @xdp_ring: XDP Tx ring - * @budget: max number of frames to xmit - * - * Returns true if cleanup/transmission is done. - */ -static bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, int budget) -{ - struct ice_tx_desc *tx_desc = NULL; - bool work_done = true; - struct xdp_desc desc; - dma_addr_t dma; - - while (likely(budget-- > 0)) { - struct ice_tx_buf *tx_buf; - - if (unlikely(!ICE_DESC_UNUSED(xdp_ring))) { - xdp_ring->tx_stats.tx_busy++; - work_done = false; - break; - } - - tx_buf = &xdp_ring->tx_buf[xdp_ring->next_to_use]; - - if (!xsk_tx_peek_desc(xdp_ring->xsk_pool, &desc)) - break; - - dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc.addr); - xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, - desc.len); - - tx_buf->bytecount = desc.len; - - 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_TXD_LAST_DESC_CMD, 0, desc.len, 0); - - xdp_ring->next_to_use++; - if (xdp_ring->next_to_use == xdp_ring->count) - xdp_ring->next_to_use = 0; - } - - if (tx_desc) { - ice_xdp_ring_update_tail(xdp_ring); - xsk_tx_release(xdp_ring->xsk_pool); - } - - return budget > 0 && work_done; -} - -/** * ice_clean_xdp_tx_buf - Free and unmap XDP Tx buffer * @xdp_ring: XDP Tx ring * @tx_buf: Tx buffer to clean @@ -672,38 +773,45 @@ static void ice_clean_xdp_tx_buf(struct ice_tx_ring *xdp_ring, struct ice_tx_buf *tx_buf) { xdp_return_frame((struct xdp_frame *)tx_buf->raw_buf); + xdp_ring->xdp_tx_active--; dma_unmap_single(xdp_ring->dev, dma_unmap_addr(tx_buf, dma), dma_unmap_len(tx_buf, len), DMA_TO_DEVICE); dma_unmap_len_set(tx_buf, len, 0); } /** - * ice_clean_tx_irq_zc - Completes AF_XDP entries, and cleans XDP entries + * ice_clean_xdp_irq_zc - produce AF_XDP descriptors to CQ * @xdp_ring: XDP Tx ring - * @budget: NAPI budget - * - * Returns true if cleanup/tranmission is done. */ -bool ice_clean_tx_irq_zc(struct ice_tx_ring *xdp_ring, int budget) +static void ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring) { - int total_packets = 0, total_bytes = 0; - s16 ntc = xdp_ring->next_to_clean; + u16 ntc = xdp_ring->next_to_clean; struct ice_tx_desc *tx_desc; + u16 cnt = xdp_ring->count; struct ice_tx_buf *tx_buf; - u32 xsk_frames = 0; - bool xmit_done; + u16 xsk_frames = 0; + u16 last_rs; + int i; - tx_desc = ICE_TX_DESC(xdp_ring, ntc); - tx_buf = &xdp_ring->tx_buf[ntc]; - ntc -= xdp_ring->count; + last_rs = xdp_ring->next_to_use ? xdp_ring->next_to_use - 1 : cnt - 1; + tx_desc = ICE_TX_DESC(xdp_ring, last_rs); + if ((tx_desc->cmd_type_offset_bsz & + cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE))) { + if (last_rs >= ntc) + xsk_frames = last_rs - ntc + 1; + else + xsk_frames = last_rs + cnt - ntc + 1; + } - do { - if (!(tx_desc->cmd_type_offset_bsz & - cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE))) - break; + if (!xsk_frames) + return; + + if (likely(!xdp_ring->xdp_tx_active)) + goto skip; - total_bytes += tx_buf->bytecount; - total_packets++; + ntc = xdp_ring->next_to_clean; + for (i = 0; i < xsk_frames; i++) { + tx_buf = &xdp_ring->tx_buf[ntc]; if (tx_buf->raw_buf) { ice_clean_xdp_tx_buf(xdp_ring, tx_buf); @@ -712,34 +820,145 @@ bool ice_clean_tx_irq_zc(struct ice_tx_ring *xdp_ring, int budget) xsk_frames++; } - tx_desc->cmd_type_offset_bsz = 0; - tx_buf++; - tx_desc++; ntc++; + if (ntc >= xdp_ring->count) + ntc = 0; + } +skip: + tx_desc->cmd_type_offset_bsz = 0; + xdp_ring->next_to_clean += xsk_frames; + if (xdp_ring->next_to_clean >= cnt) + xdp_ring->next_to_clean -= cnt; + if (xsk_frames) + xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames); +} - if (unlikely(!ntc)) { - ntc -= xdp_ring->count; - tx_buf = xdp_ring->tx_buf; - tx_desc = ICE_TX_DESC(xdp_ring, 0); - } +/** + * ice_xmit_pkt - produce a single HW Tx descriptor out of AF_XDP descriptor + * @xdp_ring: XDP ring to produce the HW Tx descriptor on + * @desc: AF_XDP descriptor to pull the DMA address and length from + * @total_bytes: bytes accumulator that will be used for stats update + */ +static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc, + unsigned int *total_bytes) +{ + struct ice_tx_desc *tx_desc; + dma_addr_t dma; - prefetch(tx_desc); + dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc->addr); + xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, desc->len); - } while (likely(--budget)); + 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, + 0, desc->len, 0); - ntc += xdp_ring->count; - xdp_ring->next_to_clean = ntc; + *total_bytes += desc->len; +} - if (xsk_frames) - xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames); +/** + * ice_xmit_pkt_batch - produce a batch of HW Tx descriptors out of AF_XDP descriptors + * @xdp_ring: XDP ring to produce the HW Tx descriptors on + * @descs: AF_XDP descriptors to pull the DMA addresses and lengths from + * @total_bytes: bytes accumulator that will be used for stats update + */ +static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs, + unsigned int *total_bytes) +{ + u16 ntu = xdp_ring->next_to_use; + struct ice_tx_desc *tx_desc; + u32 i; + + loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) { + dma_addr_t dma; + + dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, descs[i].addr); + xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, descs[i].len); + + 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, descs[i].len, 0); + + *total_bytes += descs[i].len; + } + + xdp_ring->next_to_use = ntu; +} + +/** + * ice_fill_tx_hw_ring - produce the number of Tx descriptors onto ring + * @xdp_ring: XDP ring to produce the HW Tx descriptors on + * @descs: AF_XDP descriptors to pull the DMA addresses and lengths from + * @nb_pkts: count of packets to be send + * @total_bytes: bytes accumulator that will be used for stats update + */ +static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs, + u32 nb_pkts, unsigned int *total_bytes) +{ + u32 batched, leftover, i; + + batched = ALIGN_DOWN(nb_pkts, PKTS_PER_BATCH); + leftover = nb_pkts & (PKTS_PER_BATCH - 1); + for (i = 0; i < batched; i += PKTS_PER_BATCH) + ice_xmit_pkt_batch(xdp_ring, &descs[i], total_bytes); + for (; i < batched + leftover; i++) + ice_xmit_pkt(xdp_ring, &descs[i], total_bytes); +} + +/** + * ice_set_rs_bit - set RS bit on last produced descriptor (one behind current NTU) + * @xdp_ring: XDP ring to produce the HW Tx descriptors on + */ +static void ice_set_rs_bit(struct ice_tx_ring *xdp_ring) +{ + u16 ntu = xdp_ring->next_to_use ? xdp_ring->next_to_use - 1 : xdp_ring->count - 1; + struct ice_tx_desc *tx_desc; + + tx_desc = ICE_TX_DESC(xdp_ring, ntu); + tx_desc->cmd_type_offset_bsz |= + cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S); +} + +/** + * ice_xmit_zc - take entries from XSK Tx ring and place them onto HW Tx ring + * @xdp_ring: XDP ring to produce the HW Tx descriptors on + * + * Returns true if there is no more work that needs to be done, false otherwise + */ +bool ice_xmit_zc(struct ice_tx_ring *xdp_ring) +{ + struct xdp_desc *descs = xdp_ring->xsk_pool->tx_descs; + u32 nb_pkts, nb_processed = 0; + unsigned int total_bytes = 0; + int budget; + + ice_clean_xdp_irq_zc(xdp_ring); + + budget = ICE_DESC_UNUSED(xdp_ring); + budget = min_t(u16, budget, ICE_RING_QUARTER(xdp_ring)); + + nb_pkts = xsk_tx_peek_release_desc_batch(xdp_ring->xsk_pool, budget); + if (!nb_pkts) + return true; + + if (xdp_ring->next_to_use + nb_pkts >= xdp_ring->count) { + nb_processed = xdp_ring->count - xdp_ring->next_to_use; + ice_fill_tx_hw_ring(xdp_ring, descs, nb_processed, &total_bytes); + xdp_ring->next_to_use = 0; + } + + ice_fill_tx_hw_ring(xdp_ring, &descs[nb_processed], nb_pkts - nb_processed, + &total_bytes); + + ice_set_rs_bit(xdp_ring); + ice_xdp_ring_update_tail(xdp_ring); + ice_update_tx_ring_stats(xdp_ring, nb_pkts, total_bytes); if (xsk_uses_need_wakeup(xdp_ring->xsk_pool)) xsk_set_tx_need_wakeup(xdp_ring->xsk_pool); - ice_update_tx_ring_stats(xdp_ring, total_packets, total_bytes); - xmit_done = ice_xmit_zc(xdp_ring, ICE_DFLT_IRQ_WORK); - - return budget > 0 && xmit_done; + return nb_pkts < budget; } /** @@ -759,19 +978,19 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, struct ice_vsi *vsi = np->vsi; struct ice_tx_ring *ring; - if (test_bit(ICE_DOWN, vsi->state)) + if (test_bit(ICE_VSI_DOWN, vsi->state)) return -ENETDOWN; if (!ice_is_xdp_ena_vsi(vsi)) - return -ENXIO; + return -EINVAL; - if (queue_id >= vsi->num_txq) - return -ENXIO; + if (queue_id >= vsi->num_txq || queue_id >= vsi->num_rxq) + return -EINVAL; - if (!vsi->xdp_rings[queue_id]->xsk_pool) - return -ENXIO; + ring = vsi->rx_rings[queue_id]->xdp_ring; - ring = vsi->xdp_rings[queue_id]; + if (!ring->xsk_pool) + return -EINVAL; /* The idea here is that if NAPI is running, mark a miss, so * it will run again. If not, trigger an interrupt and @@ -810,14 +1029,16 @@ bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi) */ void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring) { - u16 count_mask = rx_ring->count - 1; u16 ntc = rx_ring->next_to_clean; u16 ntu = rx_ring->next_to_use; - for ( ; ntc != ntu; ntc = (ntc + 1) & count_mask) { + while (ntc != ntu) { struct xdp_buff *xdp = *ice_xdp_buf(rx_ring, ntc); xsk_buff_free(xdp); + ntc++; + if (ntc >= rx_ring->count) + ntc = 0; } } diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h index 4c7bd8e9dfc4..6fa181f080ef 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.h +++ b/drivers/net/ethernet/intel/ice/ice_xsk.h @@ -4,7 +4,16 @@ #ifndef _ICE_XSK_H_ #define _ICE_XSK_H_ #include "ice_txrx.h" -#include "ice.h" + +#define PKTS_PER_BATCH 8 + +#ifdef __clang__ +#define loop_unrolled_for _Pragma("clang loop unroll_count(8)") for +#elif __GNUC__ >= 8 +#define loop_unrolled_for _Pragma("GCC unroll 8") for +#else +#define loop_unrolled_for for +#endif struct ice_vsi; @@ -12,13 +21,19 @@ struct ice_vsi; int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid); int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget); -bool ice_clean_tx_irq_zc(struct ice_tx_ring *xdp_ring, int budget); int ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, u32 flags); bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count); bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi); void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring); void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring); +bool ice_xmit_zc(struct ice_tx_ring *xdp_ring); +int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc); #else +static inline bool ice_xmit_zc(struct ice_tx_ring __always_unused *xdp_ring) +{ + return false; +} + static inline int ice_xsk_pool_setup(struct ice_vsi __always_unused *vsi, struct xsk_buff_pool __always_unused *pool, @@ -35,13 +50,6 @@ ice_clean_rx_irq_zc(struct ice_rx_ring __always_unused *rx_ring, } static inline bool -ice_clean_tx_irq_zc(struct ice_tx_ring __always_unused *xdp_ring, - int __always_unused budget) -{ - return false; -} - -static inline bool ice_alloc_rx_bufs_zc(struct ice_rx_ring __always_unused *rx_ring, u16 __always_unused count) { @@ -62,5 +70,12 @@ ice_xsk_wakeup(struct net_device __always_unused *netdev, static inline void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring) { } static inline void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring) { } + +static inline int +ice_realloc_zc_buf(struct ice_vsi __always_unused *vsi, + bool __always_unused zc) +{ + return 0; +} #endif /* CONFIG_XDP_SOCKETS */ #endif /* !_ICE_XSK_H_ */ |