diff options
Diffstat (limited to 'drivers/net/ethernet/intel')
27 files changed, 2187 insertions, 308 deletions
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 29ad1797adce..982ae70c51e8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -3585,11 +3585,6 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) if (ring->xsk_pool) { ring->rx_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool); - /* For AF_XDP ZC, we disallow packets to span on - * multiple buffers, thus letting us skip that - * handling in the fast-path. - */ - chain_len = 1; ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_XSK_BUFF_POOL, NULL); @@ -13822,6 +13817,7 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) NETDEV_XDP_ACT_REDIRECT | NETDEV_XDP_ACT_XSK_ZEROCOPY | NETDEV_XDP_ACT_RX_SG; + netdev->xdp_zc_max_segs = I40E_MAX_BUFFER_TXD; } else { /* Relate the VSI_VMDQ name to the VSI_MAIN name. Note that we * are still limited by IFNAMSIZ, but we're adding 'v%d\0' to diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 8b8bf4880faa..0b3a27f118fb 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2284,8 +2284,8 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, * If the buffer is an EOP buffer, this function exits returning false, * otherwise return true indicating that this is in fact a non-EOP buffer. */ -static bool i40e_is_non_eop(struct i40e_ring *rx_ring, - union i40e_rx_desc *rx_desc) +bool i40e_is_non_eop(struct i40e_ring *rx_ring, + union i40e_rx_desc *rx_desc) { /* if we are the last buffer then there is nothing else to do */ #define I40E_RXD_EOF BIT(I40E_RX_DESC_STATUS_EOF_SHIFT) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 8c3d24012c54..900b0d9ede9f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -473,6 +473,8 @@ int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size); bool __i40e_chk_linearize(struct sk_buff *skb); int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags); +bool i40e_is_non_eop(struct i40e_ring *rx_ring, + union i40e_rx_desc *rx_desc); /** * i40e_get_head - Retrieve head from head writeback diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index be59ba3774e1..398fb4854cbe 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -4305,6 +4305,38 @@ err_out: } /** + * i40e_check_vf_init_timeout + * @vf: the virtual function + * + * Check that the VF's initialization was successfully done and if not + * wait up to 300ms for its finish. + * + * Returns true when VF is initialized, false on timeout + **/ +static bool i40e_check_vf_init_timeout(struct i40e_vf *vf) +{ + int i; + + /* When the VF is resetting wait until it is done. + * It can take up to 200 milliseconds, but wait for + * up to 300 milliseconds to be safe. + */ + for (i = 0; i < 15; i++) { + if (test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) + return true; + msleep(20); + } + + if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) { + dev_err(&vf->pf->pdev->dev, + "VF %d still in reset. Try again.\n", vf->vf_id); + return false; + } + + return true; +} + +/** * i40e_ndo_set_vf_mac * @netdev: network interface device structure * @vf_id: VF identifier @@ -4322,7 +4354,6 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) int ret = 0; struct hlist_node *h; int bkt; - u8 i; if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) { dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n"); @@ -4335,21 +4366,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) goto error_param; vf = &pf->vf[vf_id]; - - /* When the VF is resetting wait until it is done. - * It can take up to 200 milliseconds, - * but wait for up to 300 milliseconds to be safe. - * Acquire the VSI pointer only after the VF has been - * properly initialized. - */ - for (i = 0; i < 15; i++) { - if (test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) - break; - msleep(20); - } - if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) { - dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n", - vf_id); + if (!i40e_check_vf_init_timeout(vf)) { ret = -EAGAIN; goto error_param; } @@ -4451,13 +4468,11 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, } vf = &pf->vf[vf_id]; - vsi = pf->vsi[vf->lan_vsi_idx]; - if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) { - dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n", - vf_id); + if (!i40e_check_vf_init_timeout(vf)) { ret = -EAGAIN; goto error_pvid; } + vsi = pf->vsi[vf->lan_vsi_idx]; if (le16_to_cpu(vsi->info.pvid) == vlanprio) /* duplicate request, so just return success */ @@ -4601,13 +4616,11 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, } vf = &pf->vf[vf_id]; - vsi = pf->vsi[vf->lan_vsi_idx]; - if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) { - dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n", - vf_id); + if (!i40e_check_vf_init_timeout(vf)) { ret = -EAGAIN; goto error; } + vsi = pf->vsi[vf->lan_vsi_idx]; ret = i40e_set_bw_limit(vsi, vsi->seid, max_tx_rate); if (ret) @@ -4774,9 +4787,7 @@ int i40e_ndo_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool enable) } vf = &(pf->vf[vf_id]); - if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) { - dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n", - vf_id); + if (!i40e_check_vf_init_timeout(vf)) { ret = -EAGAIN; goto out; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 05ec1181471e..37f41c8a682f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -294,8 +294,14 @@ static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring, { unsigned int totalsize = xdp->data_end - xdp->data_meta; unsigned int metasize = xdp->data - xdp->data_meta; + struct skb_shared_info *sinfo = NULL; struct sk_buff *skb; + u32 nr_frags = 0; + if (unlikely(xdp_buff_has_frags(xdp))) { + sinfo = xdp_get_shared_info_from_buff(xdp); + nr_frags = sinfo->nr_frags; + } net_prefetch(xdp->data_meta); /* allocate a skb to store the frags */ @@ -312,6 +318,28 @@ static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring, __skb_pull(skb, metasize); } + if (likely(!xdp_buff_has_frags(xdp))) + goto out; + + for (int i = 0; i < nr_frags; i++) { + struct skb_shared_info *skinfo = skb_shinfo(skb); + skb_frag_t *frag = &sinfo->frags[i]; + struct page *page; + void *addr; + + page = dev_alloc_page(); + if (!page) { + dev_kfree_skb(skb); + return NULL; + } + addr = page_to_virt(page); + + memcpy(addr, skb_frag_page(frag), skb_frag_size(frag)); + + __skb_fill_page_desc_noacc(skinfo, skinfo->nr_frags++, + addr, 0, skb_frag_size(frag)); + } + out: xsk_buff_free(xdp); return skb; @@ -322,14 +350,13 @@ static void i40e_handle_xdp_result_zc(struct i40e_ring *rx_ring, union i40e_rx_desc *rx_desc, unsigned int *rx_packets, unsigned int *rx_bytes, - unsigned int size, unsigned int xdp_res, bool *failure) { struct sk_buff *skb; *rx_packets = 1; - *rx_bytes = size; + *rx_bytes = xdp_get_buff_len(xdp_buff); if (likely(xdp_res == I40E_XDP_REDIR) || xdp_res == I40E_XDP_TX) return; @@ -363,7 +390,6 @@ static void i40e_handle_xdp_result_zc(struct i40e_ring *rx_ring, return; } - *rx_bytes = skb->len; i40e_process_skb_fields(rx_ring, rx_desc, skb); napi_gro_receive(&rx_ring->q_vector->napi, skb); return; @@ -374,6 +400,31 @@ static void i40e_handle_xdp_result_zc(struct i40e_ring *rx_ring, WARN_ON_ONCE(1); } +static int +i40e_add_xsk_frag(struct i40e_ring *rx_ring, struct xdp_buff *first, + struct xdp_buff *xdp, const unsigned int size) +{ + struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(first); + + if (!xdp_buff_has_frags(first)) { + sinfo->nr_frags = 0; + sinfo->xdp_frags_size = 0; + xdp_buff_set_frags_flag(first); + } + + if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) { + xsk_buff_free(first); + return -ENOMEM; + } + + __skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, + virt_to_page(xdp->data_hard_start), 0, size); + sinfo->xdp_frags_size += size; + xsk_buff_add_frag(xdp); + + return 0; +} + /** * i40e_clean_rx_irq_zc - Consumes Rx packets from the hardware ring * @rx_ring: Rx ring @@ -384,13 +435,18 @@ static void i40e_handle_xdp_result_zc(struct i40e_ring *rx_ring, int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) { unsigned int total_rx_bytes = 0, total_rx_packets = 0; + u16 next_to_process = rx_ring->next_to_process; u16 next_to_clean = rx_ring->next_to_clean; u16 count_mask = rx_ring->count - 1; unsigned int xdp_res, xdp_xmit = 0; + struct xdp_buff *first = NULL; struct bpf_prog *xdp_prog; bool failure = false; u16 cleaned_count; + if (next_to_process != next_to_clean) + first = *i40e_rx_bi(rx_ring, next_to_clean); + /* NB! xdp_prog will always be !NULL, due to the fact that * this path is enabled by setting an XDP program. */ @@ -404,7 +460,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) unsigned int size; u64 qword; - rx_desc = I40E_RX_DESC(rx_ring, next_to_clean); + rx_desc = I40E_RX_DESC(rx_ring, next_to_process); qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); /* This memory barrier is needed to keep us from reading @@ -417,9 +473,9 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) i40e_clean_programming_status(rx_ring, rx_desc->raw.qword[0], qword); - bi = *i40e_rx_bi(rx_ring, next_to_clean); + bi = *i40e_rx_bi(rx_ring, next_to_process); xsk_buff_free(bi); - next_to_clean = (next_to_clean + 1) & count_mask; + next_to_process = (next_to_process + 1) & count_mask; continue; } @@ -428,22 +484,35 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) if (!size) break; - bi = *i40e_rx_bi(rx_ring, next_to_clean); + bi = *i40e_rx_bi(rx_ring, next_to_process); xsk_buff_set_size(bi, size); xsk_buff_dma_sync_for_cpu(bi, rx_ring->xsk_pool); - xdp_res = i40e_run_xdp_zc(rx_ring, bi, xdp_prog); - i40e_handle_xdp_result_zc(rx_ring, bi, rx_desc, &rx_packets, - &rx_bytes, size, xdp_res, &failure); + if (!first) + first = bi; + else if (i40e_add_xsk_frag(rx_ring, first, bi, size)) + break; + + next_to_process = (next_to_process + 1) & count_mask; + + if (i40e_is_non_eop(rx_ring, rx_desc)) + continue; + + xdp_res = i40e_run_xdp_zc(rx_ring, first, xdp_prog); + i40e_handle_xdp_result_zc(rx_ring, first, rx_desc, &rx_packets, + &rx_bytes, xdp_res, &failure); + first->flags = 0; + next_to_clean = next_to_process; if (failure) break; total_rx_packets += rx_packets; total_rx_bytes += rx_bytes; xdp_xmit |= xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR); - next_to_clean = (next_to_clean + 1) & count_mask; + first = NULL; } rx_ring->next_to_clean = next_to_clean; + rx_ring->next_to_process = next_to_process; cleaned_count = (next_to_clean - rx_ring->next_to_use - 1) & count_mask; if (cleaned_count >= I40E_RX_BUFFER_WRITE) @@ -466,6 +535,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) static void i40e_xmit_pkt(struct i40e_ring *xdp_ring, struct xdp_desc *desc, unsigned int *total_bytes) { + u32 cmd = I40E_TX_DESC_CMD_ICRC | xsk_is_eop_desc(desc); struct i40e_tx_desc *tx_desc; dma_addr_t dma; @@ -474,8 +544,7 @@ static void i40e_xmit_pkt(struct i40e_ring *xdp_ring, struct xdp_desc *desc, tx_desc = I40E_TX_DESC(xdp_ring, xdp_ring->next_to_use++); tx_desc->buffer_addr = cpu_to_le64(dma); - tx_desc->cmd_type_offset_bsz = build_ctob(I40E_TX_DESC_CMD_ICRC | I40E_TX_DESC_CMD_EOP, - 0, desc->len, 0); + tx_desc->cmd_type_offset_bsz = build_ctob(cmd, 0, desc->len, 0); *total_bytes += desc->len; } @@ -489,14 +558,14 @@ static void i40e_xmit_pkt_batch(struct i40e_ring *xdp_ring, struct xdp_desc *des u32 i; loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) { + u32 cmd = I40E_TX_DESC_CMD_ICRC | xsk_is_eop_desc(&desc[i]); + dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc[i].addr); xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, desc[i].len); tx_desc = I40E_TX_DESC(xdp_ring, ntu++); tx_desc->buffer_addr = cpu_to_le64(dma); - tx_desc->cmd_type_offset_bsz = build_ctob(I40E_TX_DESC_CMD_ICRC | - I40E_TX_DESC_CMD_EOP, - 0, desc[i].len, 0); + tx_desc->cmd_type_offset_bsz = build_ctob(cmd, 0, desc[i].len, 0); *total_bytes += desc[i].len; } diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile index 817977e3039d..960277d78e09 100644 --- a/drivers/net/ethernet/intel/ice/Makefile +++ b/drivers/net/ethernet/intel/ice/Makefile @@ -47,5 +47,5 @@ ice-$(CONFIG_PTP_1588_CLOCK) += ice_ptp.o ice_ptp_hw.o ice-$(CONFIG_DCB) += ice_dcb.o ice_dcb_nl.o ice_dcb_lib.o ice-$(CONFIG_RFS_ACCEL) += ice_arfs.o ice-$(CONFIG_XDP_SOCKETS) += ice_xsk.o -ice-$(CONFIG_ICE_SWITCHDEV) += ice_eswitch.o +ice-$(CONFIG_ICE_SWITCHDEV) += ice_eswitch.o ice_eswitch_br.o ice-$(CONFIG_GNSS) += ice_gnss.o diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 4ba3d99439a0..9109006336f0 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -370,6 +370,7 @@ struct ice_vsi { u16 rx_buf_len; struct ice_aqc_vsi_props info; /* VSI properties */ + struct ice_vsi_vlan_info vlan_info; /* vlan config to be restored */ /* VSI stats */ struct rtnl_link_stats64 net_stats; @@ -517,6 +518,7 @@ enum ice_misc_thread_tasks { struct ice_switchdev_info { struct ice_vsi *control_vsi; struct ice_vsi *uplink_vsi; + struct ice_esw_br_offloads *br_offloads; bool is_running; }; @@ -626,6 +628,7 @@ struct ice_pf { struct ice_lag *lag; /* Link Aggregation information */ struct ice_switchdev_info switchdev; + struct ice_esw_br_port *br_port; #define ICE_INVALID_AGG_NODE_ID 0 #define ICE_PF_AGG_NODE_ID_START 1 @@ -853,7 +856,7 @@ static inline bool ice_is_adq_active(struct ice_pf *pf) return false; } -bool netif_is_ice(struct net_device *dev); +bool netif_is_ice(const struct net_device *dev); int ice_vsi_setup_tx_rings(struct ice_vsi *vsi); int ice_vsi_setup_rx_rings(struct ice_vsi *vsi); int ice_vsi_open_ctrl(struct ice_vsi *vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index b678bdf96f3a..9ab9fb558b5e 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -408,7 +408,6 @@ static unsigned int ice_rx_offset(struct ice_rx_ring *rx_ring) */ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) { - int chain_len = ICE_MAX_CHAINED_RX_BUFS; struct ice_vsi *vsi = ring->vsi; u32 rxdid = ICE_RXDID_FLEX_NIC; struct ice_rlan_ctx rlan_ctx; @@ -472,17 +471,11 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) */ rlan_ctx.showiv = 0; - /* For AF_XDP ZC, we disallow packets to span on - * multiple buffers, thus letting us skip that - * handling in the fast-path. - */ - if (ring->xsk_pool) - chain_len = 1; /* Max packet size for this queue - must not be set to a larger value * than 5 x DBUF */ rlan_ctx.rxmax = min_t(u32, vsi->max_frame, - chain_len * ring->rx_buf_len); + ICE_MAX_CHAINED_RX_BUFS * ring->rx_buf_len); /* Rx queue threshold in units of 64 */ rlan_ctx.lrxqthresh = 1; diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index ad0a007b7398..9a53a5e5d73e 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -4,6 +4,7 @@ #include "ice.h" #include "ice_lib.h" #include "ice_eswitch.h" +#include "ice_eswitch_br.h" #include "ice_fltr.h" #include "ice_repr.h" #include "ice_devlink.h" @@ -103,17 +104,28 @@ static int ice_eswitch_setup_env(struct ice_pf *pf) rule_added = true; } + vlan_ops = ice_get_compat_vsi_vlan_ops(uplink_vsi); + if (vlan_ops->dis_rx_filtering(uplink_vsi)) + goto err_dis_rx; + if (ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_set_allow_override)) goto err_override_uplink; if (ice_vsi_update_security(ctrl_vsi, ice_vsi_ctx_set_allow_override)) goto err_override_control; + if (ice_vsi_update_local_lb(uplink_vsi, true)) + goto err_override_local_lb; + return 0; +err_override_local_lb: + ice_vsi_update_security(ctrl_vsi, ice_vsi_ctx_clear_allow_override); err_override_control: ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override); err_override_uplink: + vlan_ops->ena_rx_filtering(uplink_vsi); +err_dis_rx: if (rule_added) ice_clear_dflt_vsi(uplink_vsi); err_def_rx: @@ -306,6 +318,9 @@ void ice_eswitch_update_repr(struct ice_vsi *vsi) repr->src_vsi = vsi; repr->dst->u.port_info.port_id = vsi->vsi_num; + if (repr->br_port) + repr->br_port->vsi = vsi; + ret = ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof); if (ret) { ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr, ICE_FWD_TO_VSI); @@ -331,6 +346,9 @@ ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev) np = netdev_priv(netdev); vsi = np->vsi; + if (!vsi || !ice_is_switchdev_running(vsi->back)) + return NETDEV_TX_BUSY; + if (ice_is_reset_in_progress(vsi->back->state) || test_bit(ICE_VF_DIS, vsi->back->state)) return NETDEV_TX_BUSY; @@ -378,9 +396,14 @@ static void ice_eswitch_release_env(struct ice_pf *pf) { struct ice_vsi *uplink_vsi = pf->switchdev.uplink_vsi; struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi; + struct ice_vsi_vlan_ops *vlan_ops; + + vlan_ops = ice_get_compat_vsi_vlan_ops(uplink_vsi); + ice_vsi_update_local_lb(uplink_vsi, false); ice_vsi_update_security(ctrl_vsi, ice_vsi_ctx_clear_allow_override); ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override); + vlan_ops->ena_rx_filtering(uplink_vsi); ice_clear_dflt_vsi(uplink_vsi); ice_fltr_add_mac_and_broadcast(uplink_vsi, uplink_vsi->port_info->mac.perm_addr, @@ -455,16 +478,24 @@ static void ice_eswitch_napi_disable(struct ice_pf *pf) */ static int ice_eswitch_enable_switchdev(struct ice_pf *pf) { - struct ice_vsi *ctrl_vsi; + struct ice_vsi *ctrl_vsi, *uplink_vsi; + + uplink_vsi = ice_get_main_vsi(pf); + if (!uplink_vsi) + return -ENODEV; + + if (netif_is_any_bridge_port(uplink_vsi->netdev)) { + dev_err(ice_pf_to_dev(pf), + "Uplink port cannot be a bridge port\n"); + return -EINVAL; + } pf->switchdev.control_vsi = ice_eswitch_vsi_setup(pf, pf->hw.port_info); if (!pf->switchdev.control_vsi) return -ENODEV; ctrl_vsi = pf->switchdev.control_vsi; - pf->switchdev.uplink_vsi = ice_get_main_vsi(pf); - if (!pf->switchdev.uplink_vsi) - goto err_vsi; + pf->switchdev.uplink_vsi = uplink_vsi; if (ice_eswitch_setup_env(pf)) goto err_vsi; @@ -480,10 +511,15 @@ static int ice_eswitch_enable_switchdev(struct ice_pf *pf) if (ice_vsi_open(ctrl_vsi)) goto err_setup_reprs; + if (ice_eswitch_br_offloads_init(pf)) + goto err_br_offloads; + ice_eswitch_napi_enable(pf); return 0; +err_br_offloads: + ice_vsi_close(ctrl_vsi); err_setup_reprs: ice_repr_rem_from_all_vfs(pf); err_repr_add: @@ -502,8 +538,8 @@ static void ice_eswitch_disable_switchdev(struct ice_pf *pf) struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi; ice_eswitch_napi_disable(pf); + ice_eswitch_br_offloads_deinit(pf); ice_eswitch_release_env(pf); - ice_rem_adv_rule_for_vsi(&pf->hw, ctrl_vsi->idx); ice_eswitch_release_reprs(pf, ctrl_vsi); ice_vsi_release(ctrl_vsi); ice_repr_rem_from_all_vfs(pf); diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c new file mode 100644 index 000000000000..cc7357ed6e5f --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c @@ -0,0 +1,1309 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023, Intel Corporation. */ + +#include "ice.h" +#include "ice_eswitch_br.h" +#include "ice_repr.h" +#include "ice_switch.h" +#include "ice_vlan.h" +#include "ice_vf_vsi_vlan_ops.h" +#include "ice_trace.h" + +#define ICE_ESW_BRIDGE_UPDATE_INTERVAL msecs_to_jiffies(1000) + +static const struct rhashtable_params ice_fdb_ht_params = { + .key_offset = offsetof(struct ice_esw_br_fdb_entry, data), + .key_len = sizeof(struct ice_esw_br_fdb_data), + .head_offset = offsetof(struct ice_esw_br_fdb_entry, ht_node), + .automatic_shrinking = true, +}; + +static bool ice_eswitch_br_is_dev_valid(const struct net_device *dev) +{ + /* Accept only PF netdev and PRs */ + return ice_is_port_repr_netdev(dev) || netif_is_ice(dev); +} + +static struct ice_esw_br_port * +ice_eswitch_br_netdev_to_port(struct net_device *dev) +{ + if (ice_is_port_repr_netdev(dev)) { + struct ice_repr *repr = ice_netdev_to_repr(dev); + + return repr->br_port; + } else if (netif_is_ice(dev)) { + struct ice_pf *pf = ice_netdev_to_pf(dev); + + return pf->br_port; + } + + return NULL; +} + +static void +ice_eswitch_br_ingress_rule_setup(struct ice_adv_rule_info *rule_info, + u8 pf_id, u16 vf_vsi_idx) +{ + rule_info->sw_act.vsi_handle = vf_vsi_idx; + rule_info->sw_act.flag |= ICE_FLTR_RX; + rule_info->sw_act.src = pf_id; + rule_info->priority = 5; +} + +static void +ice_eswitch_br_egress_rule_setup(struct ice_adv_rule_info *rule_info, + u16 pf_vsi_idx) +{ + rule_info->sw_act.vsi_handle = pf_vsi_idx; + rule_info->sw_act.flag |= ICE_FLTR_TX; + rule_info->flags_info.act = ICE_SINGLE_ACT_LAN_ENABLE; + rule_info->flags_info.act_valid = true; + rule_info->priority = 5; +} + +static int +ice_eswitch_br_rule_delete(struct ice_hw *hw, struct ice_rule_query_data *rule) +{ + int err; + + if (!rule) + return -EINVAL; + + err = ice_rem_adv_rule_by_id(hw, rule); + kfree(rule); + + return err; +} + +static u16 +ice_eswitch_br_get_lkups_cnt(u16 vid) +{ + return ice_eswitch_br_is_vid_valid(vid) ? 2 : 1; +} + +static void +ice_eswitch_br_add_vlan_lkup(struct ice_adv_lkup_elem *list, u16 vid) +{ + if (ice_eswitch_br_is_vid_valid(vid)) { + list[1].type = ICE_VLAN_OFOS; + list[1].h_u.vlan_hdr.vlan = cpu_to_be16(vid & VLAN_VID_MASK); + list[1].m_u.vlan_hdr.vlan = cpu_to_be16(0xFFFF); + } +} + +static struct ice_rule_query_data * +ice_eswitch_br_fwd_rule_create(struct ice_hw *hw, int vsi_idx, int port_type, + const unsigned char *mac, u16 vid) +{ + struct ice_adv_rule_info rule_info = { 0 }; + struct ice_rule_query_data *rule; + struct ice_adv_lkup_elem *list; + u16 lkups_cnt; + int err; + + lkups_cnt = ice_eswitch_br_get_lkups_cnt(vid); + + rule = kzalloc(sizeof(*rule), GFP_KERNEL); + if (!rule) + return ERR_PTR(-ENOMEM); + + list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC); + if (!list) { + err = -ENOMEM; + goto err_list_alloc; + } + + switch (port_type) { + case ICE_ESWITCH_BR_UPLINK_PORT: + ice_eswitch_br_egress_rule_setup(&rule_info, vsi_idx); + break; + case ICE_ESWITCH_BR_VF_REPR_PORT: + ice_eswitch_br_ingress_rule_setup(&rule_info, hw->pf_id, + vsi_idx); + break; + default: + err = -EINVAL; + goto err_add_rule; + } + + list[0].type = ICE_MAC_OFOS; + ether_addr_copy(list[0].h_u.eth_hdr.dst_addr, mac); + eth_broadcast_addr(list[0].m_u.eth_hdr.dst_addr); + + ice_eswitch_br_add_vlan_lkup(list, vid); + + rule_info.need_pass_l2 = true; + + rule_info.sw_act.fltr_act = ICE_FWD_TO_VSI; + + err = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, rule); + if (err) + goto err_add_rule; + + kfree(list); + + return rule; + +err_add_rule: + kfree(list); +err_list_alloc: + kfree(rule); + + return ERR_PTR(err); +} + +static struct ice_rule_query_data * +ice_eswitch_br_guard_rule_create(struct ice_hw *hw, u16 vsi_idx, + const unsigned char *mac, u16 vid) +{ + struct ice_adv_rule_info rule_info = { 0 }; + struct ice_rule_query_data *rule; + struct ice_adv_lkup_elem *list; + int err = -ENOMEM; + u16 lkups_cnt; + + lkups_cnt = ice_eswitch_br_get_lkups_cnt(vid); + + rule = kzalloc(sizeof(*rule), GFP_KERNEL); + if (!rule) + goto err_exit; + + list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC); + if (!list) + goto err_list_alloc; + + list[0].type = ICE_MAC_OFOS; + ether_addr_copy(list[0].h_u.eth_hdr.src_addr, mac); + eth_broadcast_addr(list[0].m_u.eth_hdr.src_addr); + + ice_eswitch_br_add_vlan_lkup(list, vid); + + rule_info.allow_pass_l2 = true; + rule_info.sw_act.vsi_handle = vsi_idx; + rule_info.sw_act.fltr_act = ICE_NOP; + rule_info.priority = 5; + + err = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, rule); + if (err) + goto err_add_rule; + + kfree(list); + + return rule; + +err_add_rule: + kfree(list); +err_list_alloc: + kfree(rule); +err_exit: + return ERR_PTR(err); +} + +static struct ice_esw_br_flow * +ice_eswitch_br_flow_create(struct device *dev, struct ice_hw *hw, int vsi_idx, + int port_type, const unsigned char *mac, u16 vid) +{ + struct ice_rule_query_data *fwd_rule, *guard_rule; + struct ice_esw_br_flow *flow; + int err; + + flow = kzalloc(sizeof(*flow), GFP_KERNEL); + if (!flow) + return ERR_PTR(-ENOMEM); + + fwd_rule = ice_eswitch_br_fwd_rule_create(hw, vsi_idx, port_type, mac, + vid); + err = PTR_ERR_OR_ZERO(fwd_rule); + if (err) { + dev_err(dev, "Failed to create eswitch bridge %sgress forward rule, err: %d\n", + port_type == ICE_ESWITCH_BR_UPLINK_PORT ? "e" : "in", + err); + goto err_fwd_rule; + } + + guard_rule = ice_eswitch_br_guard_rule_create(hw, vsi_idx, mac, vid); + err = PTR_ERR_OR_ZERO(guard_rule); + if (err) { + dev_err(dev, "Failed to create eswitch bridge %sgress guard rule, err: %d\n", + port_type == ICE_ESWITCH_BR_UPLINK_PORT ? "e" : "in", + err); + goto err_guard_rule; + } + + flow->fwd_rule = fwd_rule; + flow->guard_rule = guard_rule; + + return flow; + +err_guard_rule: + ice_eswitch_br_rule_delete(hw, fwd_rule); +err_fwd_rule: + kfree(flow); + + return ERR_PTR(err); +} + +static struct ice_esw_br_fdb_entry * +ice_eswitch_br_fdb_find(struct ice_esw_br *bridge, const unsigned char *mac, + u16 vid) +{ + struct ice_esw_br_fdb_data data = { + .vid = vid, + }; + + ether_addr_copy(data.addr, mac); + return rhashtable_lookup_fast(&bridge->fdb_ht, &data, + ice_fdb_ht_params); +} + +static void +ice_eswitch_br_flow_delete(struct ice_pf *pf, struct ice_esw_br_flow *flow) +{ + struct device *dev = ice_pf_to_dev(pf); + int err; + + err = ice_eswitch_br_rule_delete(&pf->hw, flow->fwd_rule); + if (err) + dev_err(dev, "Failed to delete FDB forward rule, err: %d\n", + err); + + err = ice_eswitch_br_rule_delete(&pf->hw, flow->guard_rule); + if (err) + dev_err(dev, "Failed to delete FDB guard rule, err: %d\n", + err); + + kfree(flow); +} + +static struct ice_esw_br_vlan * +ice_esw_br_port_vlan_lookup(struct ice_esw_br *bridge, u16 vsi_idx, u16 vid) +{ + struct ice_pf *pf = bridge->br_offloads->pf; + struct device *dev = ice_pf_to_dev(pf); + struct ice_esw_br_port *port; + struct ice_esw_br_vlan *vlan; + + port = xa_load(&bridge->ports, vsi_idx); + if (!port) { + dev_info(dev, "Bridge port lookup failed (vsi=%u)\n", vsi_idx); + return ERR_PTR(-EINVAL); + } + + vlan = xa_load(&port->vlans, vid); + if (!vlan) { + dev_info(dev, "Bridge port vlan metadata lookup failed (vsi=%u)\n", + vsi_idx); + return ERR_PTR(-EINVAL); + } + + return vlan; +} + +static void +ice_eswitch_br_fdb_entry_delete(struct ice_esw_br *bridge, + struct ice_esw_br_fdb_entry *fdb_entry) +{ + struct ice_pf *pf = bridge->br_offloads->pf; + + rhashtable_remove_fast(&bridge->fdb_ht, &fdb_entry->ht_node, + ice_fdb_ht_params); + list_del(&fdb_entry->list); + + ice_eswitch_br_flow_delete(pf, fdb_entry->flow); + + kfree(fdb_entry); +} + +static void +ice_eswitch_br_fdb_offload_notify(struct net_device *dev, + const unsigned char *mac, u16 vid, + unsigned long val) +{ + struct switchdev_notifier_fdb_info fdb_info = { + .addr = mac, + .vid = vid, + .offloaded = true, + }; + + call_switchdev_notifiers(val, dev, &fdb_info.info, NULL); +} + +static void +ice_eswitch_br_fdb_entry_notify_and_cleanup(struct ice_esw_br *bridge, + struct ice_esw_br_fdb_entry *entry) +{ + if (!(entry->flags & ICE_ESWITCH_BR_FDB_ADDED_BY_USER)) + ice_eswitch_br_fdb_offload_notify(entry->dev, entry->data.addr, + entry->data.vid, + SWITCHDEV_FDB_DEL_TO_BRIDGE); + ice_eswitch_br_fdb_entry_delete(bridge, entry); +} + +static void +ice_eswitch_br_fdb_entry_find_and_delete(struct ice_esw_br *bridge, + const unsigned char *mac, u16 vid) +{ + struct ice_pf *pf = bridge->br_offloads->pf; + struct ice_esw_br_fdb_entry *fdb_entry; + struct device *dev = ice_pf_to_dev(pf); + + fdb_entry = ice_eswitch_br_fdb_find(bridge, mac, vid); + if (!fdb_entry) { + dev_err(dev, "FDB entry with mac: %pM and vid: %u not found\n", + mac, vid); + return; + } + + trace_ice_eswitch_br_fdb_entry_find_and_delete(fdb_entry); + ice_eswitch_br_fdb_entry_notify_and_cleanup(bridge, fdb_entry); +} + +static void +ice_eswitch_br_fdb_entry_create(struct net_device *netdev, + struct ice_esw_br_port *br_port, + bool added_by_user, + const unsigned char *mac, u16 vid) +{ + struct ice_esw_br *bridge = br_port->bridge; + struct ice_pf *pf = bridge->br_offloads->pf; + struct device *dev = ice_pf_to_dev(pf); + struct ice_esw_br_fdb_entry *fdb_entry; + struct ice_esw_br_flow *flow; + struct ice_esw_br_vlan *vlan; + struct ice_hw *hw = &pf->hw; + unsigned long event; + int err; + + /* untagged filtering is not yet supported */ + if (!(bridge->flags & ICE_ESWITCH_BR_VLAN_FILTERING) && vid) + return; + + if ((bridge->flags & ICE_ESWITCH_BR_VLAN_FILTERING)) { + vlan = ice_esw_br_port_vlan_lookup(bridge, br_port->vsi_idx, + vid); + if (IS_ERR(vlan)) { + dev_err(dev, "Failed to find vlan lookup, err: %ld\n", + PTR_ERR(vlan)); + return; + } + } + + fdb_entry = ice_eswitch_br_fdb_find(bridge, mac, vid); + if (fdb_entry) + ice_eswitch_br_fdb_entry_notify_and_cleanup(bridge, fdb_entry); + + fdb_entry = kzalloc(sizeof(*fdb_entry), GFP_KERNEL); + if (!fdb_entry) { + err = -ENOMEM; + goto err_exit; + } + + flow = ice_eswitch_br_flow_create(dev, hw, br_port->vsi_idx, + br_port->type, mac, vid); + if (IS_ERR(flow)) { + err = PTR_ERR(flow); + goto err_add_flow; + } + + ether_addr_copy(fdb_entry->data.addr, mac); + fdb_entry->data.vid = vid; + fdb_entry->br_port = br_port; + fdb_entry->flow = flow; + fdb_entry->dev = netdev; + fdb_entry->last_use = jiffies; + event = SWITCHDEV_FDB_ADD_TO_BRIDGE; + + if (added_by_user) { + fdb_entry->flags |= ICE_ESWITCH_BR_FDB_ADDED_BY_USER; + event = SWITCHDEV_FDB_OFFLOADED; + } + + err = rhashtable_insert_fast(&bridge->fdb_ht, &fdb_entry->ht_node, + ice_fdb_ht_params); + if (err) + goto err_fdb_insert; + + list_add(&fdb_entry->list, &bridge->fdb_list); + trace_ice_eswitch_br_fdb_entry_create(fdb_entry); + + ice_eswitch_br_fdb_offload_notify(netdev, mac, vid, event); + + return; + +err_fdb_insert: + ice_eswitch_br_flow_delete(pf, flow); +err_add_flow: + kfree(fdb_entry); +err_exit: + dev_err(dev, "Failed to create fdb entry, err: %d\n", err); +} + +static void +ice_eswitch_br_fdb_work_dealloc(struct ice_esw_br_fdb_work *fdb_work) +{ + kfree(fdb_work->fdb_info.addr); + kfree(fdb_work); +} + +static void +ice_eswitch_br_fdb_event_work(struct work_struct *work) +{ + struct ice_esw_br_fdb_work *fdb_work = ice_work_to_fdb_work(work); + bool added_by_user = fdb_work->fdb_info.added_by_user; + const unsigned char *mac = fdb_work->fdb_info.addr; + u16 vid = fdb_work->fdb_info.vid; + struct ice_esw_br_port *br_port; + + rtnl_lock(); + + br_port = ice_eswitch_br_netdev_to_port(fdb_work->dev); + if (!br_port) + goto err_exit; + + switch (fdb_work->event) { + case SWITCHDEV_FDB_ADD_TO_DEVICE: + ice_eswitch_br_fdb_entry_create(fdb_work->dev, br_port, + added_by_user, mac, vid); + break; + case SWITCHDEV_FDB_DEL_TO_DEVICE: + ice_eswitch_br_fdb_entry_find_and_delete(br_port->bridge, + mac, vid); + break; + default: + goto err_exit; + } + +err_exit: + rtnl_unlock(); + dev_put(fdb_work->dev); + ice_eswitch_br_fdb_work_dealloc(fdb_work); +} + +static struct ice_esw_br_fdb_work * +ice_eswitch_br_fdb_work_alloc(struct switchdev_notifier_fdb_info *fdb_info, + struct net_device *dev, + unsigned long event) +{ + struct ice_esw_br_fdb_work *work; + unsigned char *mac; + + work = kzalloc(sizeof(*work), GFP_ATOMIC); + if (!work) + return ERR_PTR(-ENOMEM); + + INIT_WORK(&work->work, ice_eswitch_br_fdb_event_work); + memcpy(&work->fdb_info, fdb_info, sizeof(work->fdb_info)); + + mac = kzalloc(ETH_ALEN, GFP_ATOMIC); + if (!mac) { + kfree(work); + return ERR_PTR(-ENOMEM); + } + + ether_addr_copy(mac, fdb_info->addr); + work->fdb_info.addr = mac; + work->event = event; + work->dev = dev; + + return work; +} + +static int +ice_eswitch_br_switchdev_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct net_device *dev = switchdev_notifier_info_to_dev(ptr); + struct switchdev_notifier_fdb_info *fdb_info; + struct switchdev_notifier_info *info = ptr; + struct ice_esw_br_offloads *br_offloads; + struct ice_esw_br_fdb_work *work; + struct netlink_ext_ack *extack; + struct net_device *upper; + + br_offloads = ice_nb_to_br_offloads(nb, switchdev_nb); + extack = switchdev_notifier_info_to_extack(ptr); + + upper = netdev_master_upper_dev_get_rcu(dev); + if (!upper) + return NOTIFY_DONE; + + if (!netif_is_bridge_master(upper)) + return NOTIFY_DONE; + + if (!ice_eswitch_br_is_dev_valid(dev)) + return NOTIFY_DONE; + + if (!ice_eswitch_br_netdev_to_port(dev)) + return NOTIFY_DONE; + + switch (event) { + case SWITCHDEV_FDB_ADD_TO_DEVICE: + case SWITCHDEV_FDB_DEL_TO_DEVICE: + fdb_info = container_of(info, typeof(*fdb_info), info); + + work = ice_eswitch_br_fdb_work_alloc(fdb_info, dev, event); + if (IS_ERR(work)) { + NL_SET_ERR_MSG_MOD(extack, "Failed to init switchdev fdb work"); + return notifier_from_errno(PTR_ERR(work)); + } + dev_hold(dev); + + queue_work(br_offloads->wq, &work->work); + break; + default: + break; + } + return NOTIFY_DONE; +} + +static void ice_eswitch_br_fdb_flush(struct ice_esw_br *bridge) +{ + struct ice_esw_br_fdb_entry *entry, *tmp; + + list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list) + ice_eswitch_br_fdb_entry_notify_and_cleanup(bridge, entry); +} + +static void +ice_eswitch_br_vlan_filtering_set(struct ice_esw_br *bridge, bool enable) +{ + if (enable == !!(bridge->flags & ICE_ESWITCH_BR_VLAN_FILTERING)) + return; + + ice_eswitch_br_fdb_flush(bridge); + if (enable) + bridge->flags |= ICE_ESWITCH_BR_VLAN_FILTERING; + else + bridge->flags &= ~ICE_ESWITCH_BR_VLAN_FILTERING; +} + +static void +ice_eswitch_br_clear_pvid(struct ice_esw_br_port *port) +{ + struct ice_vlan port_vlan = ICE_VLAN(ETH_P_8021Q, port->pvid, 0); + struct ice_vsi_vlan_ops *vlan_ops; + + vlan_ops = ice_get_compat_vsi_vlan_ops(port->vsi); + + vlan_ops->del_vlan(port->vsi, &port_vlan); + vlan_ops->clear_port_vlan(port->vsi); + + ice_vf_vsi_disable_port_vlan(port->vsi); + + port->pvid = 0; +} + +static void +ice_eswitch_br_vlan_cleanup(struct ice_esw_br_port *port, + struct ice_esw_br_vlan *vlan) +{ + struct ice_esw_br_fdb_entry *fdb_entry, *tmp; + struct ice_esw_br *bridge = port->bridge; + + trace_ice_eswitch_br_vlan_cleanup(vlan); + + list_for_each_entry_safe(fdb_entry, tmp, &bridge->fdb_list, list) { + if (vlan->vid == fdb_entry->data.vid) + ice_eswitch_br_fdb_entry_delete(bridge, fdb_entry); + } + + xa_erase(&port->vlans, vlan->vid); + if (port->pvid == vlan->vid) + ice_eswitch_br_clear_pvid(port); + kfree(vlan); +} + +static void ice_eswitch_br_port_vlans_flush(struct ice_esw_br_port *port) +{ + struct ice_esw_br_vlan *vlan; + unsigned long index; + + xa_for_each(&port->vlans, index, vlan) + ice_eswitch_br_vlan_cleanup(port, vlan); +} + +static int +ice_eswitch_br_set_pvid(struct ice_esw_br_port *port, + struct ice_esw_br_vlan *vlan) +{ + struct ice_vlan port_vlan = ICE_VLAN(ETH_P_8021Q, vlan->vid, 0); + struct device *dev = ice_pf_to_dev(port->vsi->back); + struct ice_vsi_vlan_ops *vlan_ops; + int err; + + if (port->pvid == vlan->vid || vlan->vid == 1) + return 0; + + /* Setting port vlan on uplink isn't supported by hw */ + if (port->type == ICE_ESWITCH_BR_UPLINK_PORT) + return -EOPNOTSUPP; + + if (port->pvid) { + dev_info(dev, + "Port VLAN (vsi=%u, vid=%u) already exists on the port, remove it before adding new one\n", + port->vsi_idx, port->pvid); + return -EEXIST; + } + + ice_vf_vsi_enable_port_vlan(port->vsi); + + vlan_ops = ice_get_compat_vsi_vlan_ops(port->vsi); + err = vlan_ops->set_port_vlan(port->vsi, &port_vlan); + if (err) + return err; + + err = vlan_ops->add_vlan(port->vsi, &port_vlan); + if (err) + return err; + + ice_eswitch_br_port_vlans_flush(port); + port->pvid = vlan->vid; + + return 0; +} + +static struct ice_esw_br_vlan * +ice_eswitch_br_vlan_create(u16 vid, u16 flags, struct ice_esw_br_port *port) +{ + struct device *dev = ice_pf_to_dev(port->vsi->back); + struct ice_esw_br_vlan *vlan; + int err; + + vlan = kzalloc(sizeof(*vlan), GFP_KERNEL); + if (!vlan) + return ERR_PTR(-ENOMEM); + + vlan->vid = vid; + vlan->flags = flags; + if ((flags & BRIDGE_VLAN_INFO_PVID) && + (flags & BRIDGE_VLAN_INFO_UNTAGGED)) { + err = ice_eswitch_br_set_pvid(port, vlan); + if (err) + goto err_set_pvid; + } else if ((flags & BRIDGE_VLAN_INFO_PVID) || + (flags & BRIDGE_VLAN_INFO_UNTAGGED)) { + dev_info(dev, "VLAN push and pop are supported only simultaneously\n"); + err = -EOPNOTSUPP; + goto err_set_pvid; + } + + err = xa_insert(&port->vlans, vlan->vid, vlan, GFP_KERNEL); + if (err) + goto err_insert; + + trace_ice_eswitch_br_vlan_create(vlan); + + return vlan; + +err_insert: + if (port->pvid) + ice_eswitch_br_clear_pvid(port); +err_set_pvid: + kfree(vlan); + return ERR_PTR(err); +} + +static int +ice_eswitch_br_port_vlan_add(struct ice_esw_br *bridge, u16 vsi_idx, u16 vid, + u16 flags, struct netlink_ext_ack *extack) +{ + struct ice_esw_br_port *port; + struct ice_esw_br_vlan *vlan; + + port = xa_load(&bridge->ports, vsi_idx); + if (!port) + return -EINVAL; + + if (port->pvid) { + dev_info(ice_pf_to_dev(port->vsi->back), + "Port VLAN (vsi=%u, vid=%d) exists on the port, remove it to add trunk VLANs\n", + port->vsi_idx, port->pvid); + return -EEXIST; + } + + vlan = xa_load(&port->vlans, vid); + if (vlan) { + if (vlan->flags == flags) + return 0; + + ice_eswitch_br_vlan_cleanup(port, vlan); + } + + vlan = ice_eswitch_br_vlan_create(vid, flags, port); + if (IS_ERR(vlan)) { + NL_SET_ERR_MSG_FMT_MOD(extack, "Failed to create VLAN entry, vid: %u, vsi: %u", + vid, vsi_idx); + return PTR_ERR(vlan); + } + + return 0; +} + +static void +ice_eswitch_br_port_vlan_del(struct ice_esw_br *bridge, u16 vsi_idx, u16 vid) +{ + struct ice_esw_br_port *port; + struct ice_esw_br_vlan *vlan; + + port = xa_load(&bridge->ports, vsi_idx); + if (!port) + return; + + vlan = xa_load(&port->vlans, vid); + if (!vlan) + return; + + ice_eswitch_br_vlan_cleanup(port, vlan); +} + +static int +ice_eswitch_br_port_obj_add(struct net_device *netdev, const void *ctx, + const struct switchdev_obj *obj, + struct netlink_ext_ack *extack) +{ + struct ice_esw_br_port *br_port = ice_eswitch_br_netdev_to_port(netdev); + struct switchdev_obj_port_vlan *vlan; + int err; + + if (!br_port) + return -EINVAL; + + switch (obj->id) { + case SWITCHDEV_OBJ_ID_PORT_VLAN: + vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); + err = ice_eswitch_br_port_vlan_add(br_port->bridge, + br_port->vsi_idx, vlan->vid, + vlan->flags, extack); + return err; + default: + return -EOPNOTSUPP; + } +} + +static int +ice_eswitch_br_port_obj_del(struct net_device *netdev, const void *ctx, + const struct switchdev_obj *obj) +{ + struct ice_esw_br_port *br_port = ice_eswitch_br_netdev_to_port(netdev); + struct switchdev_obj_port_vlan *vlan; + + if (!br_port) + return -EINVAL; + + switch (obj->id) { + case SWITCHDEV_OBJ_ID_PORT_VLAN: + vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); + ice_eswitch_br_port_vlan_del(br_port->bridge, br_port->vsi_idx, + vlan->vid); + return 0; + default: + return -EOPNOTSUPP; + } +} + +static int +ice_eswitch_br_port_obj_attr_set(struct net_device *netdev, const void *ctx, + const struct switchdev_attr *attr, + struct netlink_ext_ack *extack) +{ + struct ice_esw_br_port *br_port = ice_eswitch_br_netdev_to_port(netdev); + + if (!br_port) + return -EINVAL; + + switch (attr->id) { + case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING: + ice_eswitch_br_vlan_filtering_set(br_port->bridge, + attr->u.vlan_filtering); + return 0; + case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME: + br_port->bridge->ageing_time = + clock_t_to_jiffies(attr->u.ageing_time); + return 0; + default: + return -EOPNOTSUPP; + } +} + +static int +ice_eswitch_br_event_blocking(struct notifier_block *nb, unsigned long event, + void *ptr) +{ + struct net_device *dev = switchdev_notifier_info_to_dev(ptr); + int err; + + switch (event) { + case SWITCHDEV_PORT_OBJ_ADD: + err = switchdev_handle_port_obj_add(dev, ptr, + ice_eswitch_br_is_dev_valid, + ice_eswitch_br_port_obj_add); + break; + case SWITCHDEV_PORT_OBJ_DEL: + err = switchdev_handle_port_obj_del(dev, ptr, + ice_eswitch_br_is_dev_valid, + ice_eswitch_br_port_obj_del); + break; + case SWITCHDEV_PORT_ATTR_SET: + err = switchdev_handle_port_attr_set(dev, ptr, + ice_eswitch_br_is_dev_valid, + ice_eswitch_br_port_obj_attr_set); + break; + default: + err = 0; + } + + return notifier_from_errno(err); +} + +static void +ice_eswitch_br_port_deinit(struct ice_esw_br *bridge, + struct ice_esw_br_port *br_port) +{ + struct ice_esw_br_fdb_entry *fdb_entry, *tmp; + struct ice_vsi *vsi = br_port->vsi; + + list_for_each_entry_safe(fdb_entry, tmp, &bridge->fdb_list, list) { + if (br_port == fdb_entry->br_port) + ice_eswitch_br_fdb_entry_delete(bridge, fdb_entry); + } + + if (br_port->type == ICE_ESWITCH_BR_UPLINK_PORT && vsi->back) + vsi->back->br_port = NULL; + else if (vsi->vf && vsi->vf->repr) + vsi->vf->repr->br_port = NULL; + + xa_erase(&bridge->ports, br_port->vsi_idx); + ice_eswitch_br_port_vlans_flush(br_port); + kfree(br_port); +} + +static struct ice_esw_br_port * +ice_eswitch_br_port_init(struct ice_esw_br *bridge) +{ + struct ice_esw_br_port *br_port; + + br_port = kzalloc(sizeof(*br_port), GFP_KERNEL); + if (!br_port) + return ERR_PTR(-ENOMEM); + + xa_init(&br_port->vlans); + + br_port->bridge = bridge; + + return br_port; +} + +static int +ice_eswitch_br_vf_repr_port_init(struct ice_esw_br *bridge, + struct ice_repr *repr) +{ + struct ice_esw_br_port *br_port; + int err; + + br_port = ice_eswitch_br_port_init(bridge); + if (IS_ERR(br_port)) + return PTR_ERR(br_port); + + br_port->vsi = repr->src_vsi; + br_port->vsi_idx = br_port->vsi->idx; + br_port->type = ICE_ESWITCH_BR_VF_REPR_PORT; + repr->br_port = br_port; + + err = xa_insert(&bridge->ports, br_port->vsi_idx, br_port, GFP_KERNEL); + if (err) { + ice_eswitch_br_port_deinit(bridge, br_port); + return err; + } + + return 0; +} + +static int +ice_eswitch_br_uplink_port_init(struct ice_esw_br *bridge, struct ice_pf *pf) +{ + struct ice_vsi *vsi = pf->switchdev.uplink_vsi; + struct ice_esw_br_port *br_port; + int err; + + br_port = ice_eswitch_br_port_init(bridge); + if (IS_ERR(br_port)) + return PTR_ERR(br_port); + + br_port->vsi = vsi; + br_port->vsi_idx = br_port->vsi->idx; + br_port->type = ICE_ESWITCH_BR_UPLINK_PORT; + pf->br_port = br_port; + + err = xa_insert(&bridge->ports, br_port->vsi_idx, br_port, GFP_KERNEL); + if (err) { + ice_eswitch_br_port_deinit(bridge, br_port); + return err; + } + + return 0; +} + +static void +ice_eswitch_br_ports_flush(struct ice_esw_br *bridge) +{ + struct ice_esw_br_port *port; + unsigned long i; + + xa_for_each(&bridge->ports, i, port) + ice_eswitch_br_port_deinit(bridge, port); +} + +static void +ice_eswitch_br_deinit(struct ice_esw_br_offloads *br_offloads, + struct ice_esw_br *bridge) +{ + if (!bridge) + return; + + /* Cleanup all the ports that were added asynchronously + * through NETDEV_CHANGEUPPER event. + */ + ice_eswitch_br_ports_flush(bridge); + WARN_ON(!xa_empty(&bridge->ports)); + xa_destroy(&bridge->ports); + rhashtable_destroy(&bridge->fdb_ht); + + br_offloads->bridge = NULL; + kfree(bridge); +} + +static struct ice_esw_br * +ice_eswitch_br_init(struct ice_esw_br_offloads *br_offloads, int ifindex) +{ + struct ice_esw_br *bridge; + int err; + + bridge = kzalloc(sizeof(*bridge), GFP_KERNEL); + if (!bridge) + return ERR_PTR(-ENOMEM); + + err = rhashtable_init(&bridge->fdb_ht, &ice_fdb_ht_params); + if (err) { + kfree(bridge); + return ERR_PTR(err); + } + + INIT_LIST_HEAD(&bridge->fdb_list); + bridge->br_offloads = br_offloads; + bridge->ifindex = ifindex; + bridge->ageing_time = clock_t_to_jiffies(BR_DEFAULT_AGEING_TIME); + xa_init(&bridge->ports); + br_offloads->bridge = bridge; + + return bridge; +} + +static struct ice_esw_br * +ice_eswitch_br_get(struct ice_esw_br_offloads *br_offloads, int ifindex, + struct netlink_ext_ack *extack) +{ + struct ice_esw_br *bridge = br_offloads->bridge; + + if (bridge) { + if (bridge->ifindex != ifindex) { + NL_SET_ERR_MSG_MOD(extack, + "Only one bridge is supported per eswitch"); + return ERR_PTR(-EOPNOTSUPP); + } + return bridge; + } + + /* Create the bridge if it doesn't exist yet */ + bridge = ice_eswitch_br_init(br_offloads, ifindex); + if (IS_ERR(bridge)) + NL_SET_ERR_MSG_MOD(extack, "Failed to init the bridge"); + + return bridge; +} + +static void +ice_eswitch_br_verify_deinit(struct ice_esw_br_offloads *br_offloads, + struct ice_esw_br *bridge) +{ + /* Remove the bridge if it exists and there are no ports left */ + if (!bridge || !xa_empty(&bridge->ports)) + return; + + ice_eswitch_br_deinit(br_offloads, bridge); +} + +static int +ice_eswitch_br_port_unlink(struct ice_esw_br_offloads *br_offloads, + struct net_device *dev, int ifindex, + struct netlink_ext_ack *extack) +{ + struct ice_esw_br_port *br_port = ice_eswitch_br_netdev_to_port(dev); + struct ice_esw_br *bridge; + + if (!br_port) { + NL_SET_ERR_MSG_MOD(extack, + "Port representor is not attached to any bridge"); + return -EINVAL; + } + + if (br_port->bridge->ifindex != ifindex) { + NL_SET_ERR_MSG_MOD(extack, + "Port representor is attached to another bridge"); + return -EINVAL; + } + + bridge = br_port->bridge; + + trace_ice_eswitch_br_port_unlink(br_port); + ice_eswitch_br_port_deinit(br_port->bridge, br_port); + ice_eswitch_br_verify_deinit(br_offloads, bridge); + + return 0; +} + +static int +ice_eswitch_br_port_link(struct ice_esw_br_offloads *br_offloads, + struct net_device *dev, int ifindex, + struct netlink_ext_ack *extack) +{ + struct ice_esw_br *bridge; + int err; + + if (ice_eswitch_br_netdev_to_port(dev)) { + NL_SET_ERR_MSG_MOD(extack, + "Port is already attached to the bridge"); + return -EINVAL; + } + + bridge = ice_eswitch_br_get(br_offloads, ifindex, extack); + if (IS_ERR(bridge)) + return PTR_ERR(bridge); + + if (ice_is_port_repr_netdev(dev)) { + struct ice_repr *repr = ice_netdev_to_repr(dev); + + err = ice_eswitch_br_vf_repr_port_init(bridge, repr); + trace_ice_eswitch_br_port_link(repr->br_port); + } else { + struct ice_pf *pf = ice_netdev_to_pf(dev); + + err = ice_eswitch_br_uplink_port_init(bridge, pf); + trace_ice_eswitch_br_port_link(pf->br_port); + } + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to init bridge port"); + goto err_port_init; + } + + return 0; + +err_port_init: + ice_eswitch_br_verify_deinit(br_offloads, bridge); + return err; +} + +static int +ice_eswitch_br_port_changeupper(struct notifier_block *nb, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_changeupper_info *info = ptr; + struct ice_esw_br_offloads *br_offloads; + struct netlink_ext_ack *extack; + struct net_device *upper; + + br_offloads = ice_nb_to_br_offloads(nb, netdev_nb); + + if (!ice_eswitch_br_is_dev_valid(dev)) + return 0; + + upper = info->upper_dev; + if (!netif_is_bridge_master(upper)) + return 0; + + extack = netdev_notifier_info_to_extack(&info->info); + + if (info->linking) + return ice_eswitch_br_port_link(br_offloads, dev, + upper->ifindex, extack); + else + return ice_eswitch_br_port_unlink(br_offloads, dev, + upper->ifindex, extack); +} + +static int +ice_eswitch_br_port_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + int err = 0; + + switch (event) { + case NETDEV_CHANGEUPPER: + err = ice_eswitch_br_port_changeupper(nb, ptr); + break; + } + + return notifier_from_errno(err); +} + +static void +ice_eswitch_br_offloads_dealloc(struct ice_pf *pf) +{ + struct ice_esw_br_offloads *br_offloads = pf->switchdev.br_offloads; + + ASSERT_RTNL(); + + if (!br_offloads) + return; + + ice_eswitch_br_deinit(br_offloads, br_offloads->bridge); + + pf->switchdev.br_offloads = NULL; + kfree(br_offloads); +} + +static struct ice_esw_br_offloads * +ice_eswitch_br_offloads_alloc(struct ice_pf *pf) +{ + struct ice_esw_br_offloads *br_offloads; + + ASSERT_RTNL(); + + if (pf->switchdev.br_offloads) + return ERR_PTR(-EEXIST); + + br_offloads = kzalloc(sizeof(*br_offloads), GFP_KERNEL); + if (!br_offloads) + return ERR_PTR(-ENOMEM); + + pf->switchdev.br_offloads = br_offloads; + br_offloads->pf = pf; + + return br_offloads; +} + +void +ice_eswitch_br_offloads_deinit(struct ice_pf *pf) +{ + struct ice_esw_br_offloads *br_offloads; + + br_offloads = pf->switchdev.br_offloads; + if (!br_offloads) + return; + + cancel_delayed_work_sync(&br_offloads->update_work); + unregister_netdevice_notifier(&br_offloads->netdev_nb); + unregister_switchdev_blocking_notifier(&br_offloads->switchdev_blk); + unregister_switchdev_notifier(&br_offloads->switchdev_nb); + destroy_workqueue(br_offloads->wq); + /* Although notifier block is unregistered just before, + * so we don't get any new events, some events might be + * already in progress. Hold the rtnl lock and wait for + * them to finished. + */ + rtnl_lock(); + ice_eswitch_br_offloads_dealloc(pf); + rtnl_unlock(); +} + +static void ice_eswitch_br_update(struct ice_esw_br_offloads *br_offloads) +{ + struct ice_esw_br *bridge = br_offloads->bridge; + struct ice_esw_br_fdb_entry *entry, *tmp; + + if (!bridge) + return; + + rtnl_lock(); + list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list) { + if (entry->flags & ICE_ESWITCH_BR_FDB_ADDED_BY_USER) + continue; + + if (time_is_after_eq_jiffies(entry->last_use + + bridge->ageing_time)) + continue; + + ice_eswitch_br_fdb_entry_notify_and_cleanup(bridge, entry); + } + rtnl_unlock(); +} + +static void ice_eswitch_br_update_work(struct work_struct *work) +{ + struct ice_esw_br_offloads *br_offloads; + + br_offloads = ice_work_to_br_offloads(work); + + ice_eswitch_br_update(br_offloads); + + queue_delayed_work(br_offloads->wq, &br_offloads->update_work, + ICE_ESW_BRIDGE_UPDATE_INTERVAL); +} + +int +ice_eswitch_br_offloads_init(struct ice_pf *pf) +{ + struct ice_esw_br_offloads *br_offloads; + struct device *dev = ice_pf_to_dev(pf); + int err; + + rtnl_lock(); + br_offloads = ice_eswitch_br_offloads_alloc(pf); + rtnl_unlock(); + if (IS_ERR(br_offloads)) { + dev_err(dev, "Failed to init eswitch bridge\n"); + return PTR_ERR(br_offloads); + } + + br_offloads->wq = alloc_ordered_workqueue("ice_bridge_wq", 0); + if (!br_offloads->wq) { + err = -ENOMEM; + dev_err(dev, "Failed to allocate bridge workqueue\n"); + goto err_alloc_wq; + } + + br_offloads->switchdev_nb.notifier_call = + ice_eswitch_br_switchdev_event; + err = register_switchdev_notifier(&br_offloads->switchdev_nb); + if (err) { + dev_err(dev, + "Failed to register switchdev notifier\n"); + goto err_reg_switchdev_nb; + } + + br_offloads->switchdev_blk.notifier_call = + ice_eswitch_br_event_blocking; + err = register_switchdev_blocking_notifier(&br_offloads->switchdev_blk); + if (err) { + dev_err(dev, + "Failed to register bridge blocking switchdev notifier\n"); + goto err_reg_switchdev_blk; + } + + br_offloads->netdev_nb.notifier_call = ice_eswitch_br_port_event; + err = register_netdevice_notifier(&br_offloads->netdev_nb); + if (err) { + dev_err(dev, + "Failed to register bridge port event notifier\n"); + goto err_reg_netdev_nb; + } + + INIT_DELAYED_WORK(&br_offloads->update_work, + ice_eswitch_br_update_work); + queue_delayed_work(br_offloads->wq, &br_offloads->update_work, + ICE_ESW_BRIDGE_UPDATE_INTERVAL); + + return 0; + +err_reg_netdev_nb: + unregister_switchdev_blocking_notifier(&br_offloads->switchdev_blk); +err_reg_switchdev_blk: + unregister_switchdev_notifier(&br_offloads->switchdev_nb); +err_reg_switchdev_nb: + destroy_workqueue(br_offloads->wq); +err_alloc_wq: + rtnl_lock(); + ice_eswitch_br_offloads_dealloc(pf); + rtnl_unlock(); + + return err; +} diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.h b/drivers/net/ethernet/intel/ice/ice_eswitch_br.h new file mode 100644 index 000000000000..85a8fadb2928 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.h @@ -0,0 +1,120 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2023, Intel Corporation. */ + +#ifndef _ICE_ESWITCH_BR_H_ +#define _ICE_ESWITCH_BR_H_ + +#include <linux/rhashtable.h> +#include <linux/workqueue.h> + +struct ice_esw_br_fdb_data { + unsigned char addr[ETH_ALEN]; + u16 vid; +}; + +struct ice_esw_br_flow { + struct ice_rule_query_data *fwd_rule; + struct ice_rule_query_data *guard_rule; +}; + +enum { + ICE_ESWITCH_BR_FDB_ADDED_BY_USER = BIT(0), +}; + +struct ice_esw_br_fdb_entry { + struct ice_esw_br_fdb_data data; + struct rhash_head ht_node; + struct list_head list; + + int flags; + + struct net_device *dev; + struct ice_esw_br_port *br_port; + struct ice_esw_br_flow *flow; + + unsigned long last_use; +}; + +enum ice_esw_br_port_type { + ICE_ESWITCH_BR_UPLINK_PORT = 0, + ICE_ESWITCH_BR_VF_REPR_PORT = 1, +}; + +struct ice_esw_br_port { + struct ice_esw_br *bridge; + struct ice_vsi *vsi; + enum ice_esw_br_port_type type; + u16 vsi_idx; + u16 pvid; + struct xarray vlans; +}; + +enum { + ICE_ESWITCH_BR_VLAN_FILTERING = BIT(0), +}; + +struct ice_esw_br { + struct ice_esw_br_offloads *br_offloads; + struct xarray ports; + + struct rhashtable fdb_ht; + struct list_head fdb_list; + + int ifindex; + u32 flags; + unsigned long ageing_time; +}; + +struct ice_esw_br_offloads { + struct ice_pf *pf; + struct ice_esw_br *bridge; + struct notifier_block netdev_nb; + struct notifier_block switchdev_blk; + struct notifier_block switchdev_nb; + + struct workqueue_struct *wq; + struct delayed_work update_work; +}; + +struct ice_esw_br_fdb_work { + struct work_struct work; + struct switchdev_notifier_fdb_info fdb_info; + struct net_device *dev; + unsigned long event; +}; + +struct ice_esw_br_vlan { + u16 vid; + u16 flags; +}; + +#define ice_nb_to_br_offloads(nb, nb_name) \ + container_of(nb, \ + struct ice_esw_br_offloads, \ + nb_name) + +#define ice_work_to_br_offloads(w) \ + container_of(w, \ + struct ice_esw_br_offloads, \ + update_work.work) + +#define ice_work_to_fdb_work(w) \ + container_of(w, \ + struct ice_esw_br_fdb_work, \ + work) + +static inline bool ice_eswitch_br_is_vid_valid(u16 vid) +{ + /* In trunk VLAN mode, for untagged traffic the bridge sends requests + * to offload VLAN 1 with pvid and untagged flags set. Since these + * flags are not supported, add a MAC filter instead. + */ + return vid > 1; +} + +void +ice_eswitch_br_offloads_deinit(struct ice_pf *pf); +int +ice_eswitch_br_offloads_init(struct ice_pf *pf); + +#endif /* _ICE_ESWITCH_BR_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 0054d7e64ec3..a43c23c80565 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -4076,3 +4076,28 @@ void ice_vsi_ctx_clear_allow_override(struct ice_vsi_ctx *ctx) { ctx->info.sec_flags &= ~ICE_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD; } + +/** + * ice_vsi_update_local_lb - update sw block in VSI with local loopback bit + * @vsi: pointer to VSI structure + * @set: set or unset the bit + */ +int +ice_vsi_update_local_lb(struct ice_vsi *vsi, bool set) +{ + struct ice_vsi_ctx ctx = { + .info = vsi->info, + }; + + ctx.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SW_VALID); + if (set) + ctx.info.sw_flags |= ICE_AQ_VSI_SW_FLAG_LOCAL_LB; + else + ctx.info.sw_flags &= ~ICE_AQ_VSI_SW_FLAG_LOCAL_LB; + + if (ice_update_vsi(&vsi->back->hw, vsi->idx, &ctx, NULL)) + return -ENODEV; + + vsi->info = ctx.info; + return 0; +} diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index e985766e6bb5..1628385a9672 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -157,6 +157,7 @@ void ice_vsi_ctx_clear_antispoof(struct ice_vsi_ctx *ctx); void ice_vsi_ctx_set_allow_override(struct ice_vsi_ctx *ctx); void ice_vsi_ctx_clear_allow_override(struct ice_vsi_ctx *ctx); +int ice_vsi_update_local_lb(struct ice_vsi *vsi, bool set); int ice_vsi_add_vlan_zero(struct ice_vsi *vsi); int ice_vsi_del_vlan_zero(struct ice_vsi *vsi); bool ice_vsi_has_non_zero_vlans(struct ice_vsi *vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index f02d44455772..9b36cce306b8 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -80,7 +80,7 @@ ice_indr_setup_tc_cb(struct net_device *netdev, struct Qdisc *sch, void *data, void (*cleanup)(struct flow_block_cb *block_cb)); -bool netif_is_ice(struct net_device *dev) +bool netif_is_ice(const struct net_device *dev) { return dev && (dev->netdev_ops == &ice_netdev_ops); } @@ -3392,6 +3392,7 @@ static void ice_set_ops(struct ice_vsi *vsi) netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | NETDEV_XDP_ACT_XSK_ZEROCOPY | NETDEV_XDP_ACT_RX_SG; + netdev->xdp_zc_max_segs = ICE_MAX_BUF_TXD; } /** @@ -5703,7 +5704,7 @@ static void ice_set_rx_mode(struct net_device *netdev) struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; - if (!vsi) + if (!vsi || ice_is_switchdev_running(vsi->back)) return; /* Set the flags to synchronize filters @@ -6255,7 +6256,7 @@ static void ice_tx_dim_work(struct work_struct *work) u16 itr; dim = container_of(work, struct dim, work); - rc = (struct ice_ring_container *)dim->priv; + rc = dim->priv; WARN_ON(dim->profile_ix >= ARRAY_SIZE(tx_profile)); @@ -6275,7 +6276,7 @@ static void ice_rx_dim_work(struct work_struct *work) u16 itr; dim = container_of(work, struct dim, work); - rc = (struct ice_ring_container *)dim->priv; + rc = dim->priv; WARN_ON(dim->profile_ix >= ARRAY_SIZE(rx_profile)); diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c index e30e12321abd..c686ac0935eb 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.c +++ b/drivers/net/ethernet/intel/ice/ice_repr.c @@ -254,7 +254,7 @@ static const struct net_device_ops ice_repr_netdev_ops = { * ice_is_port_repr_netdev - Check if a given netdevice is a port representor netdev * @netdev: pointer to netdev */ -bool ice_is_port_repr_netdev(struct net_device *netdev) +bool ice_is_port_repr_netdev(const struct net_device *netdev) { return netdev && (netdev->netdev_ops == &ice_repr_netdev_ops); } diff --git a/drivers/net/ethernet/intel/ice/ice_repr.h b/drivers/net/ethernet/intel/ice/ice_repr.h index 9c2a6f496b3b..e1ee2d2c1d2d 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.h +++ b/drivers/net/ethernet/intel/ice/ice_repr.h @@ -12,6 +12,7 @@ struct ice_repr { struct ice_q_vector *q_vector; struct net_device *netdev; struct metadata_dst *dst; + struct ice_esw_br_port *br_port; #ifdef CONFIG_ICE_SWITCHDEV /* info about slow path rule */ struct ice_rule_query_data sp_rule; @@ -27,5 +28,5 @@ void ice_repr_stop_tx_queues(struct ice_repr *repr); void ice_repr_set_traffic_vsi(struct ice_repr *repr, struct ice_vsi *vsi); struct ice_repr *ice_netdev_to_repr(struct net_device *netdev); -bool ice_is_port_repr_netdev(struct net_device *netdev); +bool ice_is_port_repr_netdev(const struct net_device *netdev); #endif diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 6db4ca7978cb..813fef5fd748 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -2272,6 +2272,10 @@ ice_get_recp_frm_fw(struct ice_hw *hw, struct ice_sw_recipe *recps, u8 rid, /* Propagate some data to the recipe database */ recps[idx].is_root = !!is_root; recps[idx].priority = root_bufs.content.act_ctrl_fwd_priority; + recps[idx].need_pass_l2 = root_bufs.content.act_ctrl & + ICE_AQ_RECIPE_ACT_NEED_PASS_L2; + recps[idx].allow_pass_l2 = root_bufs.content.act_ctrl & + ICE_AQ_RECIPE_ACT_ALLOW_PASS_L2; bitmap_zero(recps[idx].res_idxs, ICE_MAX_FV_WORDS); if (root_bufs.content.result_indx & ICE_AQ_RECIPE_RESULT_EN) { recps[idx].chain_idx = root_bufs.content.result_indx & @@ -4613,13 +4617,13 @@ static struct ice_protocol_entry ice_prot_id_tbl[ICE_PROTOCOL_LAST] = { * ice_find_recp - find a recipe * @hw: pointer to the hardware structure * @lkup_exts: extension sequence to match - * @tun_type: type of recipe tunnel + * @rinfo: information regarding the rule e.g. priority and action info * * Returns index of matching recipe, or ICE_MAX_NUM_RECIPES if not found. */ static u16 ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts, - enum ice_sw_tunnel_type tun_type) + const struct ice_adv_rule_info *rinfo) { bool refresh_required = true; struct ice_sw_recipe *recp; @@ -4680,9 +4684,12 @@ ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts, } /* If for "i"th recipe the found was never set to false * then it means we found our match - * Also tun type of recipe needs to be checked + * Also tun type and *_pass_l2 of recipe needs to be + * checked */ - if (found && recp[i].tun_type == tun_type) + if (found && recp[i].tun_type == rinfo->tun_type && + recp[i].need_pass_l2 == rinfo->need_pass_l2 && + recp[i].allow_pass_l2 == rinfo->allow_pass_l2) return i; /* Return the recipe ID */ } } @@ -4952,6 +4959,7 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, unsigned long *profiles) { DECLARE_BITMAP(result_idx_bm, ICE_MAX_FV_WORDS); + struct ice_aqc_recipe_content *content; struct ice_aqc_recipe_data_elem *tmp; struct ice_aqc_recipe_data_elem *buf; struct ice_recp_grp_entry *entry; @@ -5012,6 +5020,8 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, if (status) goto err_unroll; + content = &buf[recps].content; + /* Clear the result index of the located recipe, as this will be * updated, if needed, later in the recipe creation process. */ @@ -5022,26 +5032,24 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, /* if the recipe is a non-root recipe RID should be programmed * as 0 for the rules to be applied correctly. */ - buf[recps].content.rid = 0; - memset(&buf[recps].content.lkup_indx, 0, - sizeof(buf[recps].content.lkup_indx)); + content->rid = 0; + memset(&content->lkup_indx, 0, + sizeof(content->lkup_indx)); /* All recipes use look-up index 0 to match switch ID. */ - buf[recps].content.lkup_indx[0] = ICE_AQ_SW_ID_LKUP_IDX; - buf[recps].content.mask[0] = - cpu_to_le16(ICE_AQ_SW_ID_LKUP_MASK); + content->lkup_indx[0] = ICE_AQ_SW_ID_LKUP_IDX; + content->mask[0] = cpu_to_le16(ICE_AQ_SW_ID_LKUP_MASK); /* Setup lkup_indx 1..4 to INVALID/ignore and set the mask * to be 0 */ for (i = 1; i <= ICE_NUM_WORDS_RECIPE; i++) { - buf[recps].content.lkup_indx[i] = 0x80; - buf[recps].content.mask[i] = 0; + content->lkup_indx[i] = 0x80; + content->mask[i] = 0; } for (i = 0; i < entry->r_group.n_val_pairs; i++) { - buf[recps].content.lkup_indx[i + 1] = entry->fv_idx[i]; - buf[recps].content.mask[i + 1] = - cpu_to_le16(entry->fv_mask[i]); + content->lkup_indx[i + 1] = entry->fv_idx[i]; + content->mask[i + 1] = cpu_to_le16(entry->fv_mask[i]); } if (rm->n_grp_count > 1) { @@ -5055,7 +5063,7 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, } entry->chain_idx = chain_idx; - buf[recps].content.result_indx = + content->result_indx = ICE_AQ_RECIPE_RESULT_EN | ((chain_idx << ICE_AQ_RECIPE_RESULT_DATA_S) & ICE_AQ_RECIPE_RESULT_DATA_M); @@ -5069,7 +5077,13 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, ICE_MAX_NUM_RECIPES); set_bit(buf[recps].recipe_indx, (unsigned long *)buf[recps].recipe_bitmap); - buf[recps].content.act_ctrl_fwd_priority = rm->priority; + content->act_ctrl_fwd_priority = rm->priority; + + if (rm->need_pass_l2) + content->act_ctrl |= ICE_AQ_RECIPE_ACT_NEED_PASS_L2; + + if (rm->allow_pass_l2) + content->act_ctrl |= ICE_AQ_RECIPE_ACT_ALLOW_PASS_L2; recps++; } @@ -5107,9 +5121,11 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, if (status) goto err_unroll; + content = &buf[recps].content; + buf[recps].recipe_indx = (u8)rid; - buf[recps].content.rid = (u8)rid; - buf[recps].content.rid |= ICE_AQ_RECIPE_ID_IS_ROOT; + content->rid = (u8)rid; + content->rid |= ICE_AQ_RECIPE_ID_IS_ROOT; /* the new entry created should also be part of rg_list to * make sure we have complete recipe */ @@ -5121,16 +5137,13 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, goto err_unroll; } last_chain_entry->rid = rid; - memset(&buf[recps].content.lkup_indx, 0, - sizeof(buf[recps].content.lkup_indx)); + memset(&content->lkup_indx, 0, sizeof(content->lkup_indx)); /* All recipes use look-up index 0 to match switch ID. */ - buf[recps].content.lkup_indx[0] = ICE_AQ_SW_ID_LKUP_IDX; - buf[recps].content.mask[0] = - cpu_to_le16(ICE_AQ_SW_ID_LKUP_MASK); + content->lkup_indx[0] = ICE_AQ_SW_ID_LKUP_IDX; + content->mask[0] = cpu_to_le16(ICE_AQ_SW_ID_LKUP_MASK); for (i = 1; i <= ICE_NUM_WORDS_RECIPE; i++) { - buf[recps].content.lkup_indx[i] = - ICE_AQ_RECIPE_LKUP_IGNORE; - buf[recps].content.mask[i] = 0; + content->lkup_indx[i] = ICE_AQ_RECIPE_LKUP_IGNORE; + content->mask[i] = 0; } i = 1; @@ -5142,8 +5155,8 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, last_chain_entry->chain_idx = ICE_INVAL_CHAIN_IND; list_for_each_entry(entry, &rm->rg_list, l_entry) { last_chain_entry->fv_idx[i] = entry->chain_idx; - buf[recps].content.lkup_indx[i] = entry->chain_idx; - buf[recps].content.mask[i++] = cpu_to_le16(0xFFFF); + content->lkup_indx[i] = entry->chain_idx; + content->mask[i++] = cpu_to_le16(0xFFFF); set_bit(entry->rid, rm->r_bitmap); } list_add(&last_chain_entry->l_entry, &rm->rg_list); @@ -5155,7 +5168,7 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, status = -EINVAL; goto err_unroll; } - buf[recps].content.act_ctrl_fwd_priority = rm->priority; + content->act_ctrl_fwd_priority = rm->priority; recps++; rm->root_rid = (u8)rid; @@ -5220,6 +5233,8 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, recp->priority = buf[buf_idx].content.act_ctrl_fwd_priority; recp->n_grp_count = rm->n_grp_count; recp->tun_type = rm->tun_type; + recp->need_pass_l2 = rm->need_pass_l2; + recp->allow_pass_l2 = rm->allow_pass_l2; recp->recp_created = true; } rm->root_buf = buf; @@ -5388,6 +5403,9 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, /* set the recipe priority if specified */ rm->priority = (u8)rinfo->priority; + rm->need_pass_l2 = rinfo->need_pass_l2; + rm->allow_pass_l2 = rinfo->allow_pass_l2; + /* Find offsets from the field vector. Pick the first one for all the * recipes. */ @@ -5403,7 +5421,7 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, } /* Look for a recipe which matches our requested fv / mask list */ - *rid = ice_find_recp(hw, lkup_exts, rinfo->tun_type); + *rid = ice_find_recp(hw, lkup_exts, rinfo); if (*rid < ICE_MAX_NUM_RECIPES) /* Success if found a recipe that match the existing criteria */ goto err_unroll; @@ -5839,7 +5857,9 @@ static bool ice_rules_equal(const struct ice_adv_rule_info *first, return first->sw_act.flag == second->sw_act.flag && first->tun_type == second->tun_type && first->vlan_type == second->vlan_type && - first->src_vsi == second->src_vsi; + first->src_vsi == second->src_vsi && + first->need_pass_l2 == second->need_pass_l2 && + first->allow_pass_l2 == second->allow_pass_l2; } /** @@ -6078,7 +6098,8 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, if (!(rinfo->sw_act.fltr_act == ICE_FWD_TO_VSI || rinfo->sw_act.fltr_act == ICE_FWD_TO_Q || rinfo->sw_act.fltr_act == ICE_FWD_TO_QGRP || - rinfo->sw_act.fltr_act == ICE_DROP_PACKET)) { + rinfo->sw_act.fltr_act == ICE_DROP_PACKET || + rinfo->sw_act.fltr_act == ICE_NOP)) { status = -EIO; goto free_pkt_profile; } @@ -6089,7 +6110,8 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, goto free_pkt_profile; } - if (rinfo->sw_act.fltr_act == ICE_FWD_TO_VSI) + if (rinfo->sw_act.fltr_act == ICE_FWD_TO_VSI || + rinfo->sw_act.fltr_act == ICE_NOP) rinfo->sw_act.fwd_id.hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); @@ -6159,6 +6181,11 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_DROP | ICE_SINGLE_ACT_VALID_BIT; break; + case ICE_NOP: + act |= FIELD_PREP(ICE_SINGLE_ACT_VSI_ID_M, + rinfo->sw_act.fwd_id.hw_vsi_id); + act &= ~ICE_SINGLE_ACT_VALID_BIT; + break; default: status = -EIO; goto err_ice_add_adv_rule; @@ -6439,7 +6466,7 @@ ice_rem_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, return -EIO; } - rid = ice_find_recp(hw, &lkup_exts, rinfo->tun_type); + rid = ice_find_recp(hw, &lkup_exts, rinfo); /* If did not find a recipe that match the existing criteria */ if (rid == ICE_MAX_NUM_RECIPES) return -EINVAL; @@ -6533,59 +6560,6 @@ ice_rem_adv_rule_by_id(struct ice_hw *hw, } /** - * ice_rem_adv_rule_for_vsi - removes existing advanced switch rules for a - * given VSI handle - * @hw: pointer to the hardware structure - * @vsi_handle: VSI handle for which we are supposed to remove all the rules. - * - * This function is used to remove all the rules for a given VSI and as soon - * as removing a rule fails, it will return immediately with the error code, - * else it will return success. - */ -int ice_rem_adv_rule_for_vsi(struct ice_hw *hw, u16 vsi_handle) -{ - struct ice_adv_fltr_mgmt_list_entry *list_itr, *tmp_entry; - struct ice_vsi_list_map_info *map_info; - struct ice_adv_rule_info rinfo; - struct list_head *list_head; - struct ice_switch_info *sw; - int status; - u8 rid; - - sw = hw->switch_info; - for (rid = 0; rid < ICE_MAX_NUM_RECIPES; rid++) { - if (!sw->recp_list[rid].recp_created) - continue; - if (!sw->recp_list[rid].adv_rule) - continue; - - list_head = &sw->recp_list[rid].filt_rules; - list_for_each_entry_safe(list_itr, tmp_entry, list_head, - list_entry) { - rinfo = list_itr->rule_info; - - if (rinfo.sw_act.fltr_act == ICE_FWD_TO_VSI_LIST) { - map_info = list_itr->vsi_list_info; - if (!map_info) - continue; - - if (!test_bit(vsi_handle, map_info->vsi_map)) - continue; - } else if (rinfo.sw_act.vsi_handle != vsi_handle) { - continue; - } - - rinfo.sw_act.vsi_handle = vsi_handle; - status = ice_rem_adv_rule(hw, list_itr->lkups, - list_itr->lkups_cnt, &rinfo); - if (status) - return status; - } - } - return 0; -} - -/** * ice_replay_vsi_adv_rule - Replay advanced rule for requested VSI * @hw: pointer to the hardware structure * @vsi_handle: driver VSI handle diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h index c84b56fe84a5..10f5a0ae199e 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.h +++ b/drivers/net/ethernet/intel/ice/ice_switch.h @@ -191,6 +191,8 @@ struct ice_adv_rule_info { u16 vlan_type; u16 fltr_rule_id; u32 priority; + u16 need_pass_l2:1; + u16 allow_pass_l2:1; u16 src_vsi; struct ice_sw_act_ctrl sw_act; struct ice_adv_rule_flags_info flags_info; @@ -254,6 +256,9 @@ struct ice_sw_recipe { */ u8 priority; + u8 need_pass_l2:1; + u8 allow_pass_l2:1; + struct list_head rg_list; /* AQ buffer associated with this recipe */ @@ -379,7 +384,6 @@ int ice_set_vlan_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, bool rm_vlan_promisc); -int ice_rem_adv_rule_for_vsi(struct ice_hw *hw, u16 vsi_handle); int ice_rem_adv_rule_by_id(struct ice_hw *hw, struct ice_rule_query_data *remove_entry); diff --git a/drivers/net/ethernet/intel/ice/ice_trace.h b/drivers/net/ethernet/intel/ice/ice_trace.h index ae98d5a8ff60..b2f5c9fe0149 100644 --- a/drivers/net/ethernet/intel/ice/ice_trace.h +++ b/drivers/net/ethernet/intel/ice/ice_trace.h @@ -21,6 +21,7 @@ #define _ICE_TRACE_H_ #include <linux/tracepoint.h> +#include "ice_eswitch_br.h" /* ice_trace() macro enables shared code to refer to trace points * like: @@ -240,6 +241,95 @@ DEFINE_TX_TSTAMP_OP_EVENT(ice_tx_tstamp_fw_req); DEFINE_TX_TSTAMP_OP_EVENT(ice_tx_tstamp_fw_done); DEFINE_TX_TSTAMP_OP_EVENT(ice_tx_tstamp_complete); +DECLARE_EVENT_CLASS(ice_esw_br_fdb_template, + TP_PROTO(struct ice_esw_br_fdb_entry *fdb), + TP_ARGS(fdb), + TP_STRUCT__entry(__array(char, dev_name, IFNAMSIZ) + __array(unsigned char, addr, ETH_ALEN) + __field(u16, vid) + __field(int, flags)), + TP_fast_assign(strscpy(__entry->dev_name, + netdev_name(fdb->dev), + IFNAMSIZ); + memcpy(__entry->addr, fdb->data.addr, ETH_ALEN); + __entry->vid = fdb->data.vid; + __entry->flags = fdb->flags;), + TP_printk("net_device=%s addr=%pM vid=%u flags=%x", + __entry->dev_name, + __entry->addr, + __entry->vid, + __entry->flags) +); + +DEFINE_EVENT(ice_esw_br_fdb_template, + ice_eswitch_br_fdb_entry_create, + TP_PROTO(struct ice_esw_br_fdb_entry *fdb), + TP_ARGS(fdb) +); + +DEFINE_EVENT(ice_esw_br_fdb_template, + ice_eswitch_br_fdb_entry_find_and_delete, + TP_PROTO(struct ice_esw_br_fdb_entry *fdb), + TP_ARGS(fdb) +); + +DECLARE_EVENT_CLASS(ice_esw_br_vlan_template, + TP_PROTO(struct ice_esw_br_vlan *vlan), + TP_ARGS(vlan), + TP_STRUCT__entry(__field(u16, vid) + __field(u16, flags)), + TP_fast_assign(__entry->vid = vlan->vid; + __entry->flags = vlan->flags;), + TP_printk("vid=%u flags=%x", + __entry->vid, + __entry->flags) +); + +DEFINE_EVENT(ice_esw_br_vlan_template, + ice_eswitch_br_vlan_create, + TP_PROTO(struct ice_esw_br_vlan *vlan), + TP_ARGS(vlan) +); + +DEFINE_EVENT(ice_esw_br_vlan_template, + ice_eswitch_br_vlan_cleanup, + TP_PROTO(struct ice_esw_br_vlan *vlan), + TP_ARGS(vlan) +); + +#define ICE_ESW_BR_PORT_NAME_L 16 + +DECLARE_EVENT_CLASS(ice_esw_br_port_template, + TP_PROTO(struct ice_esw_br_port *port), + TP_ARGS(port), + TP_STRUCT__entry(__field(u16, vport_num) + __array(char, port_type, ICE_ESW_BR_PORT_NAME_L)), + TP_fast_assign(__entry->vport_num = port->vsi_idx; + if (port->type == ICE_ESWITCH_BR_UPLINK_PORT) + strscpy(__entry->port_type, + "Uplink", + ICE_ESW_BR_PORT_NAME_L); + else + strscpy(__entry->port_type, + "VF Representor", + ICE_ESW_BR_PORT_NAME_L);), + TP_printk("vport_num=%u port type=%s", + __entry->vport_num, + __entry->port_type) +); + +DEFINE_EVENT(ice_esw_br_port_template, + ice_eswitch_br_port_link, + TP_PROTO(struct ice_esw_br_port *port), + TP_ARGS(port) +); + +DEFINE_EVENT(ice_esw_br_port_template, + ice_eswitch_br_port_unlink, + TP_PROTO(struct ice_esw_br_port *port), + TP_ARGS(port) +); + /* End tracepoints */ #endif /* _ICE_TRACE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index a09556e57803..df9171a1a34f 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -1033,6 +1033,7 @@ enum ice_sw_fwd_act_type { ICE_FWD_TO_Q, ICE_FWD_TO_QGRP, ICE_DROP_PACKET, + ICE_NOP, ICE_INVAL_ACT }; diff --git a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c index b1ffb81893d4..d7b10dc67f03 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c @@ -21,6 +21,99 @@ noop_vlan(struct ice_vsi __always_unused *vsi) return 0; } +static void ice_port_vlan_on(struct ice_vsi *vsi) +{ + struct ice_vsi_vlan_ops *vlan_ops; + struct ice_pf *pf = vsi->back; + + if (ice_is_dvm_ena(&pf->hw)) { + vlan_ops = &vsi->outer_vlan_ops; + + /* setup outer VLAN ops */ + vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan; + vlan_ops->clear_port_vlan = ice_vsi_clear_outer_port_vlan; + vlan_ops->clear_port_vlan = ice_vsi_clear_outer_port_vlan; + + /* setup inner VLAN ops */ + vlan_ops = &vsi->inner_vlan_ops; + vlan_ops->add_vlan = noop_vlan_arg; + vlan_ops->del_vlan = noop_vlan_arg; + vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping; + vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping; + vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; + vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; + } else { + vlan_ops = &vsi->inner_vlan_ops; + + vlan_ops->set_port_vlan = ice_vsi_set_inner_port_vlan; + vlan_ops->clear_port_vlan = ice_vsi_clear_inner_port_vlan; + vlan_ops->clear_port_vlan = ice_vsi_clear_inner_port_vlan; + } + vlan_ops->ena_rx_filtering = ice_vsi_ena_rx_vlan_filtering; +} + +static void ice_port_vlan_off(struct ice_vsi *vsi) +{ + struct ice_vsi_vlan_ops *vlan_ops; + struct ice_pf *pf = vsi->back; + + /* setup inner VLAN ops */ + vlan_ops = &vsi->inner_vlan_ops; + + vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping; + vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping; + vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; + vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; + + if (ice_is_dvm_ena(&pf->hw)) { + vlan_ops = &vsi->outer_vlan_ops; + + vlan_ops->del_vlan = ice_vsi_del_vlan; + vlan_ops->ena_stripping = ice_vsi_ena_outer_stripping; + vlan_ops->dis_stripping = ice_vsi_dis_outer_stripping; + vlan_ops->ena_insertion = ice_vsi_ena_outer_insertion; + vlan_ops->dis_insertion = ice_vsi_dis_outer_insertion; + } else { + vlan_ops->del_vlan = ice_vsi_del_vlan; + } + + if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags)) + vlan_ops->ena_rx_filtering = noop_vlan; + else + vlan_ops->ena_rx_filtering = + ice_vsi_ena_rx_vlan_filtering; +} + +/** + * ice_vf_vsi_enable_port_vlan - Set VSI VLAN ops to support port VLAN + * @vsi: VF's VSI being configured + * + * The function won't create port VLAN, it only allows to create port VLAN + * using VLAN ops on the VF VSI. + */ +void ice_vf_vsi_enable_port_vlan(struct ice_vsi *vsi) +{ + if (WARN_ON_ONCE(!vsi->vf)) + return; + + ice_port_vlan_on(vsi); +} + +/** + * ice_vf_vsi_disable_port_vlan - Clear VSI support for creating port VLAN + * @vsi: VF's VSI being configured + * + * The function should be called after removing port VLAN on VSI + * (using VLAN ops) + */ +void ice_vf_vsi_disable_port_vlan(struct ice_vsi *vsi) +{ + if (WARN_ON_ONCE(!vsi->vf)) + return; + + ice_port_vlan_off(vsi); +} + /** * ice_vf_vsi_init_vlan_ops - Initialize default VSI VLAN ops for VF VSI * @vsi: VF's VSI being configured @@ -39,91 +132,18 @@ void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi) if (WARN_ON(!vf)) return; - if (ice_is_dvm_ena(&pf->hw)) { - vlan_ops = &vsi->outer_vlan_ops; + if (ice_vf_is_port_vlan_ena(vf)) + ice_port_vlan_on(vsi); + else + ice_port_vlan_off(vsi); - /* outer VLAN ops regardless of port VLAN config */ - vlan_ops->add_vlan = ice_vsi_add_vlan; - vlan_ops->ena_tx_filtering = ice_vsi_ena_tx_vlan_filtering; - vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering; - - if (ice_vf_is_port_vlan_ena(vf)) { - /* setup outer VLAN ops */ - vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan; - /* all Rx traffic should be in the domain of the - * assigned port VLAN, so prevent disabling Rx VLAN - * filtering - */ - vlan_ops->dis_rx_filtering = noop_vlan; - vlan_ops->ena_rx_filtering = - ice_vsi_ena_rx_vlan_filtering; - - /* setup inner VLAN ops */ - vlan_ops = &vsi->inner_vlan_ops; - vlan_ops->add_vlan = noop_vlan_arg; - vlan_ops->del_vlan = noop_vlan_arg; - vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping; - vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping; - vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; - vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; - } else { - vlan_ops->dis_rx_filtering = - ice_vsi_dis_rx_vlan_filtering; - - if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags)) - vlan_ops->ena_rx_filtering = noop_vlan; - else - vlan_ops->ena_rx_filtering = - ice_vsi_ena_rx_vlan_filtering; - - vlan_ops->del_vlan = ice_vsi_del_vlan; - vlan_ops->ena_stripping = ice_vsi_ena_outer_stripping; - vlan_ops->dis_stripping = ice_vsi_dis_outer_stripping; - vlan_ops->ena_insertion = ice_vsi_ena_outer_insertion; - vlan_ops->dis_insertion = ice_vsi_dis_outer_insertion; - - /* setup inner VLAN ops */ - vlan_ops = &vsi->inner_vlan_ops; - - vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping; - vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping; - vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; - vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; - } - } else { - vlan_ops = &vsi->inner_vlan_ops; + vlan_ops = ice_is_dvm_ena(&pf->hw) ? + &vsi->outer_vlan_ops : &vsi->inner_vlan_ops; - /* inner VLAN ops regardless of port VLAN config */ - vlan_ops->add_vlan = ice_vsi_add_vlan; - vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering; - vlan_ops->ena_tx_filtering = ice_vsi_ena_tx_vlan_filtering; - vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering; - - if (ice_vf_is_port_vlan_ena(vf)) { - vlan_ops->set_port_vlan = ice_vsi_set_inner_port_vlan; - vlan_ops->ena_rx_filtering = - ice_vsi_ena_rx_vlan_filtering; - /* all Rx traffic should be in the domain of the - * assigned port VLAN, so prevent disabling Rx VLAN - * filtering - */ - vlan_ops->dis_rx_filtering = noop_vlan; - } else { - vlan_ops->dis_rx_filtering = - ice_vsi_dis_rx_vlan_filtering; - if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags)) - vlan_ops->ena_rx_filtering = noop_vlan; - else - vlan_ops->ena_rx_filtering = - ice_vsi_ena_rx_vlan_filtering; - - vlan_ops->del_vlan = ice_vsi_del_vlan; - vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping; - vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping; - vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; - vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; - } - } + vlan_ops->add_vlan = ice_vsi_add_vlan; + vlan_ops->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; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.h b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.h index 875a4e615f39..df8aa09df3e3 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.h @@ -13,7 +13,11 @@ void ice_vf_vsi_cfg_svm_legacy_vlan_mode(struct ice_vsi *vsi); #ifdef CONFIG_PCI_IOV void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi); +void ice_vf_vsi_enable_port_vlan(struct ice_vsi *vsi); +void ice_vf_vsi_disable_port_vlan(struct ice_vsi *vsi); #else static inline void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi) { } +static inline void ice_vf_vsi_enable_port_vlan(struct ice_vsi *vsi) { } +static inline void ice_vf_vsi_disable_port_vlan(struct ice_vsi *vsi) { } #endif /* CONFIG_PCI_IOV */ #endif /* _ICE_PF_VSI_VLAN_OPS_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c index 5b4a0abb4607..76266e709a39 100644 --- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c @@ -202,6 +202,24 @@ int ice_vsi_dis_inner_insertion(struct ice_vsi *vsi) return ice_vsi_manage_vlan_insertion(vsi); } +static void +ice_save_vlan_info(struct ice_aqc_vsi_props *info, + struct ice_vsi_vlan_info *vlan) +{ + vlan->sw_flags2 = info->sw_flags2; + vlan->inner_vlan_flags = info->inner_vlan_flags; + vlan->outer_vlan_flags = info->outer_vlan_flags; +} + +static void +ice_restore_vlan_info(struct ice_aqc_vsi_props *info, + struct ice_vsi_vlan_info *vlan) +{ + info->sw_flags2 = vlan->sw_flags2; + info->inner_vlan_flags = vlan->inner_vlan_flags; + info->outer_vlan_flags = vlan->outer_vlan_flags; +} + /** * __ice_vsi_set_inner_port_vlan - set port VLAN VSI context settings to enable a port VLAN * @vsi: the VSI to update @@ -218,6 +236,7 @@ static int __ice_vsi_set_inner_port_vlan(struct ice_vsi *vsi, u16 pvid_info) if (!ctxt) return -ENOMEM; + ice_save_vlan_info(&vsi->info, &vsi->vlan_info); ctxt->info = vsi->info; info = &ctxt->info; info->inner_vlan_flags = ICE_AQ_VSI_INNER_VLAN_TX_MODE_ACCEPTUNTAGGED | @@ -259,6 +278,33 @@ int ice_vsi_set_inner_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) return __ice_vsi_set_inner_port_vlan(vsi, port_vlan_info); } +int ice_vsi_clear_inner_port_vlan(struct ice_vsi *vsi) +{ + struct ice_hw *hw = &vsi->back->hw; + struct ice_aqc_vsi_props *info; + struct ice_vsi_ctx *ctxt; + int ret; + + ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + ice_restore_vlan_info(&vsi->info, &vsi->vlan_info); + vsi->info.port_based_inner_vlan = 0; + ctxt->info = vsi->info; + info = &ctxt->info; + info->valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID | + ICE_AQ_VSI_PROP_SW_VALID); + + ret = ice_update_vsi(hw, vsi->idx, ctxt, NULL); + if (ret) + dev_err(ice_hw_to_dev(hw), "update VSI for port VLAN failed, err %d aq_err %s\n", + ret, ice_aq_str(hw->adminq.sq_last_status)); + + kfree(ctxt); + return ret; +} + /** * ice_cfg_vlan_pruning - enable or disable VLAN pruning on the VSI * @vsi: VSI to enable or disable VLAN pruning on @@ -647,6 +693,7 @@ __ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, u16 vlan_info, u16 tpid) if (!ctxt) return -ENOMEM; + ice_save_vlan_info(&vsi->info, &vsi->vlan_info); ctxt->info = vsi->info; ctxt->info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; @@ -689,9 +736,6 @@ __ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, u16 vlan_info, u16 tpid) * used if DVM is supported. Also, this function should never be called directly * as it should be part of ice_vsi_vlan_ops if it's needed. * - * This function does not support clearing the port VLAN as there is currently - * no use case for this. - * * Use the ice_vlan structure passed in to set this VSI in a port VLAN. */ int ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) @@ -705,3 +749,37 @@ int ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) return __ice_vsi_set_outer_port_vlan(vsi, port_vlan_info, vlan->tpid); } + +/** + * ice_vsi_clear_outer_port_vlan - clear outer port vlan + * @vsi: VSI to configure + * + * The function is restoring previously set vlan config (saved in + * vsi->vlan_info). Setting happens in port vlan configuration. + */ +int ice_vsi_clear_outer_port_vlan(struct ice_vsi *vsi) +{ + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx *ctxt; + int err; + + ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + ice_restore_vlan_info(&vsi->info, &vsi->vlan_info); + vsi->info.port_based_outer_vlan = 0; + ctxt->info = vsi->info; + + ctxt->info.valid_sections = + cpu_to_le16(ICE_AQ_VSI_PROP_OUTER_TAG_VALID | + ICE_AQ_VSI_PROP_SW_VALID); + + err = ice_update_vsi(hw, vsi->idx, ctxt, NULL); + if (err) + dev_err(ice_pf_to_dev(vsi->back), "update VSI for clearing outer port based VLAN failed, err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); + + kfree(ctxt); + return err; +} diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h index f459909490ec..f0d84d11bd5b 100644 --- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h @@ -7,6 +7,12 @@ #include <linux/types.h> #include "ice_vlan.h" +struct ice_vsi_vlan_info { + u8 sw_flags2; + u8 inner_vlan_flags; + u8 outer_vlan_flags; +}; + struct ice_vsi; int ice_vsi_add_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan); @@ -17,6 +23,7 @@ int ice_vsi_dis_inner_stripping(struct ice_vsi *vsi); int ice_vsi_ena_inner_insertion(struct ice_vsi *vsi, u16 tpid); int ice_vsi_dis_inner_insertion(struct ice_vsi *vsi); int ice_vsi_set_inner_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan); +int ice_vsi_clear_inner_port_vlan(struct ice_vsi *vsi); int ice_vsi_ena_rx_vlan_filtering(struct ice_vsi *vsi); int ice_vsi_dis_rx_vlan_filtering(struct ice_vsi *vsi); @@ -28,5 +35,6 @@ int ice_vsi_dis_outer_stripping(struct ice_vsi *vsi); int ice_vsi_ena_outer_insertion(struct ice_vsi *vsi, u16 tpid); int ice_vsi_dis_outer_insertion(struct ice_vsi *vsi); int ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan); +int ice_vsi_clear_outer_port_vlan(struct ice_vsi *vsi); #endif /* _ICE_VSI_VLAN_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.h b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.h index 5b47568f6256..b2d2330dedcb 100644 --- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.h +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.h @@ -21,6 +21,7 @@ struct ice_vsi_vlan_ops { int (*ena_tx_filtering)(struct ice_vsi *vsi); int (*dis_tx_filtering)(struct ice_vsi *vsi); int (*set_port_vlan)(struct ice_vsi *vsi, struct ice_vlan *vlan); + int (*clear_port_vlan)(struct ice_vsi *vsi); }; void ice_vsi_init_vlan_ops(struct ice_vsi *vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index a7fe2b4ce655..2a3f0834e139 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -546,19 +546,6 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) } /** - * ice_bump_ntc - Bump the next_to_clean counter of an Rx ring - * @rx_ring: Rx ring - */ -static void ice_bump_ntc(struct ice_rx_ring *rx_ring) -{ - int ntc = rx_ring->next_to_clean + 1; - - ntc = (ntc < rx_ring->count) ? ntc : 0; - rx_ring->next_to_clean = ntc; - prefetch(ICE_RX_DESC(rx_ring, ntc)); -} - -/** * ice_construct_skb_zc - Create an sk_buff from zero-copy buffer * @rx_ring: Rx ring * @xdp: Pointer to XDP buffer @@ -572,8 +559,14 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) { unsigned int totalsize = xdp->data_end - xdp->data_meta; unsigned int metasize = xdp->data - xdp->data_meta; + struct skb_shared_info *sinfo = NULL; struct sk_buff *skb; + u32 nr_frags = 0; + if (unlikely(xdp_buff_has_frags(xdp))) { + sinfo = xdp_get_shared_info_from_buff(xdp); + nr_frags = sinfo->nr_frags; + } net_prefetch(xdp->data_meta); skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize, @@ -589,6 +582,29 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) __skb_pull(skb, metasize); } + if (likely(!xdp_buff_has_frags(xdp))) + goto out; + + for (int i = 0; i < nr_frags; i++) { + struct skb_shared_info *skinfo = skb_shinfo(skb); + skb_frag_t *frag = &sinfo->frags[i]; + struct page *page; + void *addr; + + page = dev_alloc_page(); + if (!page) { + dev_kfree_skb(skb); + return NULL; + } + addr = page_to_virt(page); + + memcpy(addr, skb_frag_page(frag), skb_frag_size(frag)); + + __skb_fill_page_desc_noacc(skinfo, skinfo->nr_frags++, + addr, 0, skb_frag_size(frag)); + } + +out: xsk_buff_free(xdp); return skb; } @@ -597,7 +613,7 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) * ice_clean_xdp_irq_zc - produce AF_XDP descriptors to CQ * @xdp_ring: XDP Tx ring */ -static void ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring) +static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring) { u16 ntc = xdp_ring->next_to_clean; struct ice_tx_desc *tx_desc; @@ -619,7 +635,7 @@ static void ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring) } if (!completed_frames) - return; + return 0; if (likely(!xdp_ring->xdp_tx_active)) { xsk_frames = completed_frames; @@ -649,6 +665,8 @@ skip: xdp_ring->next_to_clean -= cnt; if (xsk_frames) xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames); + + return completed_frames; } /** @@ -666,37 +684,72 @@ skip: static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring) { + struct skb_shared_info *sinfo = NULL; u32 size = xdp->data_end - xdp->data; u32 ntu = xdp_ring->next_to_use; struct ice_tx_desc *tx_desc; struct ice_tx_buf *tx_buf; - dma_addr_t dma; - - if (ICE_DESC_UNUSED(xdp_ring) < ICE_RING_QUARTER(xdp_ring)) { - ice_clean_xdp_irq_zc(xdp_ring); - if (!ICE_DESC_UNUSED(xdp_ring)) { - xdp_ring->ring_stats->tx_stats.tx_busy++; - return ICE_XDP_CONSUMED; - } + struct xdp_buff *head; + u32 nr_frags = 0; + u32 free_space; + u32 frag = 0; + + free_space = ICE_DESC_UNUSED(xdp_ring); + if (free_space < ICE_RING_QUARTER(xdp_ring)) + free_space += ice_clean_xdp_irq_zc(xdp_ring); + + if (unlikely(!free_space)) + goto busy; + + if (unlikely(xdp_buff_has_frags(xdp))) { + sinfo = xdp_get_shared_info_from_buff(xdp); + nr_frags = sinfo->nr_frags; + if (free_space < nr_frags + 1) + goto busy; } - dma = xsk_buff_xdp_get_dma(xdp); - xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, size); - - tx_buf = &xdp_ring->tx_buf[ntu]; - tx_buf->xdp = xdp; - tx_buf->type = ICE_TX_BUF_XSK_TX; tx_desc = ICE_TX_DESC(xdp_ring, ntu); - tx_desc->buf_addr = cpu_to_le64(dma); - tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP, - 0, size, 0); - xdp_ring->xdp_tx_active++; + tx_buf = &xdp_ring->tx_buf[ntu]; + head = xdp; + + for (;;) { + dma_addr_t dma; + + dma = xsk_buff_xdp_get_dma(xdp); + xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, size); + + tx_buf->xdp = xdp; + tx_buf->type = ICE_TX_BUF_XSK_TX; + tx_desc->buf_addr = cpu_to_le64(dma); + tx_desc->cmd_type_offset_bsz = ice_build_ctob(0, 0, size, 0); + /* account for each xdp_buff from xsk_buff_pool */ + xdp_ring->xdp_tx_active++; + + if (++ntu == xdp_ring->count) + ntu = 0; + + if (frag == nr_frags) + break; + + tx_desc = ICE_TX_DESC(xdp_ring, ntu); + tx_buf = &xdp_ring->tx_buf[ntu]; + + xdp = xsk_buff_get_frag(head); + size = skb_frag_size(&sinfo->frags[frag]); + frag++; + } - if (++ntu == xdp_ring->count) - ntu = 0; xdp_ring->next_to_use = ntu; + /* update last descriptor from a frame with EOP */ + tx_desc->cmd_type_offset_bsz |= + cpu_to_le64(ICE_TX_DESC_CMD_EOP << ICE_TXD_QW1_CMD_S); return ICE_XDP_TX; + +busy: + xdp_ring->ring_stats->tx_stats.tx_busy++; + + return ICE_XDP_CONSUMED; } /** @@ -752,6 +805,34 @@ out_failure: return result; } +static int +ice_add_xsk_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *first, + struct xdp_buff *xdp, const unsigned int size) +{ + struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(first); + + if (!size) + return 0; + + if (!xdp_buff_has_frags(first)) { + sinfo->nr_frags = 0; + sinfo->xdp_frags_size = 0; + xdp_buff_set_frags_flag(first); + } + + if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) { + xsk_buff_free(first); + return -ENOMEM; + } + + __skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, + virt_to_page(xdp->data_hard_start), 0, size); + sinfo->xdp_frags_size += size; + xsk_buff_add_frag(xdp); + + return 0; +} + /** * ice_clean_rx_irq_zc - consumes packets from the hardware ring * @rx_ring: AF_XDP Rx ring @@ -762,9 +843,14 @@ out_failure: int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) { unsigned int total_rx_bytes = 0, total_rx_packets = 0; + struct xsk_buff_pool *xsk_pool = rx_ring->xsk_pool; + u32 ntc = rx_ring->next_to_clean; + u32 ntu = rx_ring->next_to_use; + struct xdp_buff *first = NULL; struct ice_tx_ring *xdp_ring; unsigned int xdp_xmit = 0; struct bpf_prog *xdp_prog; + u32 cnt = rx_ring->count; bool failure = false; int entries_to_alloc; @@ -774,6 +860,9 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) xdp_prog = READ_ONCE(rx_ring->xdp_prog); xdp_ring = rx_ring->xdp_ring; + if (ntc != rx_ring->first_desc) + first = *ice_xdp_buf(rx_ring, rx_ring->first_desc); + while (likely(total_rx_packets < (unsigned int)budget)) { union ice_32b_rx_flex_desc *rx_desc; unsigned int size, xdp_res = 0; @@ -783,7 +872,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) u16 vlan_tag = 0; u16 rx_ptype; - rx_desc = ICE_RX_DESC(rx_ring, rx_ring->next_to_clean); + rx_desc = ICE_RX_DESC(rx_ring, ntc); stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_DD_S); if (!ice_test_staterr(rx_desc->wb.status_error0, stat_err_bits)) @@ -795,51 +884,61 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) */ dma_rmb(); - if (unlikely(rx_ring->next_to_clean == rx_ring->next_to_use)) + if (unlikely(ntc == ntu)) break; - xdp = *ice_xdp_buf(rx_ring, rx_ring->next_to_clean); + xdp = *ice_xdp_buf(rx_ring, ntc); size = le16_to_cpu(rx_desc->wb.pkt_len) & ICE_RX_FLX_DESC_PKT_LEN_M; - if (!size) { - xdp->data = NULL; - xdp->data_end = NULL; - xdp->data_hard_start = NULL; - xdp->data_meta = NULL; - goto construct_skb; - } xsk_buff_set_size(xdp, size); - xsk_buff_dma_sync_for_cpu(xdp, rx_ring->xsk_pool); + xsk_buff_dma_sync_for_cpu(xdp, xsk_pool); + + if (!first) { + first = xdp; + xdp_buff_clear_frags_flag(first); + } else if (ice_add_xsk_frag(rx_ring, first, xdp, size)) { + break; + } + + if (++ntc == cnt) + ntc = 0; - xdp_res = ice_run_xdp_zc(rx_ring, xdp, xdp_prog, xdp_ring); + if (ice_is_non_eop(rx_ring, rx_desc)) + continue; + + xdp_res = ice_run_xdp_zc(rx_ring, first, xdp_prog, xdp_ring); if (likely(xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))) { xdp_xmit |= xdp_res; } else if (xdp_res == ICE_XDP_EXIT) { failure = true; + first = NULL; + rx_ring->first_desc = ntc; break; } else if (xdp_res == ICE_XDP_CONSUMED) { - xsk_buff_free(xdp); + xsk_buff_free(first); } else if (xdp_res == ICE_XDP_PASS) { goto construct_skb; } - total_rx_bytes += size; + total_rx_bytes += xdp_get_buff_len(first); total_rx_packets++; - ice_bump_ntc(rx_ring); + first = NULL; + rx_ring->first_desc = ntc; continue; construct_skb: /* XDP_PASS path */ - skb = ice_construct_skb_zc(rx_ring, xdp); + skb = ice_construct_skb_zc(rx_ring, first); if (!skb) { rx_ring->ring_stats->rx_stats.alloc_buf_failed++; break; } - ice_bump_ntc(rx_ring); + first = NULL; + rx_ring->first_desc = ntc; if (eth_skb_pad(skb)) { skb = NULL; @@ -858,18 +957,22 @@ construct_skb: ice_receive_skb(rx_ring, skb, vlan_tag); } - entries_to_alloc = ICE_DESC_UNUSED(rx_ring); + rx_ring->next_to_clean = ntc; + entries_to_alloc = ICE_RX_DESC_UNUSED(rx_ring); if (entries_to_alloc > ICE_RING_QUARTER(rx_ring)) failure |= !ice_alloc_rx_bufs_zc(rx_ring, entries_to_alloc); ice_finalize_xdp_rx(xdp_ring, xdp_xmit, 0); ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes); - if (xsk_uses_need_wakeup(rx_ring->xsk_pool)) { - if (failure || rx_ring->next_to_clean == rx_ring->next_to_use) - xsk_set_rx_need_wakeup(rx_ring->xsk_pool); + if (xsk_uses_need_wakeup(xsk_pool)) { + /* ntu could have changed when allocating entries above, so + * use rx_ring value instead of stack based one + */ + if (failure || ntc == rx_ring->next_to_use) + xsk_set_rx_need_wakeup(xsk_pool); else - xsk_clear_rx_need_wakeup(rx_ring->xsk_pool); + xsk_clear_rx_need_wakeup(xsk_pool); return (int)total_rx_packets; } @@ -894,7 +997,7 @@ static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc, tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_to_use++); tx_desc->buf_addr = cpu_to_le64(dma); - tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP, + tx_desc->cmd_type_offset_bsz = ice_build_ctob(xsk_is_eop_desc(desc), 0, desc->len, 0); *total_bytes += desc->len; @@ -921,7 +1024,7 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de tx_desc = ICE_TX_DESC(xdp_ring, ntu++); tx_desc->buf_addr = cpu_to_le64(dma); - tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP, + tx_desc->cmd_type_offset_bsz = ice_build_ctob(xsk_is_eop_desc(&descs[i]), 0, descs[i].len, 0); *total_bytes += descs[i].len; diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index bdeb36790d77..2a10254edbbd 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -6143,6 +6143,26 @@ static int igc_tsn_clear_schedule(struct igc_adapter *adapter) return 0; } +static void igc_taprio_stats(struct net_device *dev, + struct tc_taprio_qopt_stats *stats) +{ + /* When Strict_End is enabled, the tx_overruns counter + * will always be zero. + */ + stats->tx_overruns = 0; +} + +static void igc_taprio_queue_stats(struct net_device *dev, + struct tc_taprio_qopt_queue_stats *queue_stats) +{ + struct tc_taprio_qopt_stats *stats = &queue_stats->stats; + + /* When Strict_End is enabled, the tx_overruns counter + * will always be zero. + */ + stats->tx_overruns = 0; +} + static int igc_save_qbv_schedule(struct igc_adapter *adapter, struct tc_taprio_qopt_offload *qopt) { @@ -6153,11 +6173,20 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, size_t n; int i; - if (qopt->cmd == TAPRIO_CMD_DESTROY) + switch (qopt->cmd) { + case TAPRIO_CMD_REPLACE: + break; + case TAPRIO_CMD_DESTROY: return igc_tsn_clear_schedule(adapter); - - if (qopt->cmd != TAPRIO_CMD_REPLACE) + case TAPRIO_CMD_STATS: + igc_taprio_stats(adapter->netdev, &qopt->stats); + return 0; + case TAPRIO_CMD_QUEUE_STATS: + igc_taprio_queue_stats(adapter->netdev, &qopt->queue_stats); + return 0; + default: return -EOPNOTSUPP; + } if (qopt->base_time < 0) return -ERANGE; |