diff options
Diffstat (limited to 'drivers/net/ethernet/intel')
31 files changed, 676 insertions, 1139 deletions
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index a563a94e2780..7c6ee1e604aa 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -296,6 +296,7 @@ config ICE depends on GNSS || GNSS = n select AUXILIARY_BUS select DIMLIB + select LIBETH_XDP select LIBIE select LIBIE_ADMINQ select LIBIE_FWLOG diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index 018e61aea787..aa08f397988e 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -461,6 +461,7 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca); #define FLAG2_CHECK_RX_HWTSTAMP BIT(13) #define FLAG2_CHECK_SYSTIM_OVERFLOW BIT(14) #define FLAG2_ENABLE_S0IX_FLOWS BIT(15) +#define FLAG2_DISABLE_K1 BIT(16) #define E1000_RX_DESC_PS(R, i) \ (&(((union e1000_rx_desc_packet_split *)((R).desc))[i])) diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index 8e40bb50a01e..cee57a2149ab 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -26,6 +26,8 @@ struct e1000_stats { static const char e1000e_priv_flags_strings[][ETH_GSTRING_LEN] = { #define E1000E_PRIV_FLAGS_S0IX_ENABLED BIT(0) "s0ix-enabled", +#define E1000E_PRIV_FLAGS_DISABLE_K1 BIT(1) + "disable-k1", }; #define E1000E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(e1000e_priv_flags_strings) @@ -2301,26 +2303,59 @@ static u32 e1000e_get_priv_flags(struct net_device *netdev) if (adapter->flags2 & FLAG2_ENABLE_S0IX_FLOWS) priv_flags |= E1000E_PRIV_FLAGS_S0IX_ENABLED; + if (adapter->flags2 & FLAG2_DISABLE_K1) + priv_flags |= E1000E_PRIV_FLAGS_DISABLE_K1; + return priv_flags; } static int e1000e_set_priv_flags(struct net_device *netdev, u32 priv_flags) { struct e1000_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; unsigned int flags2 = adapter->flags2; + unsigned int changed; - flags2 &= ~FLAG2_ENABLE_S0IX_FLOWS; - if (priv_flags & E1000E_PRIV_FLAGS_S0IX_ENABLED) { - struct e1000_hw *hw = &adapter->hw; + flags2 &= ~(FLAG2_ENABLE_S0IX_FLOWS | FLAG2_DISABLE_K1); - if (hw->mac.type < e1000_pch_cnp) + if (priv_flags & E1000E_PRIV_FLAGS_S0IX_ENABLED) { + if (hw->mac.type < e1000_pch_cnp) { + e_err("S0ix is not supported on this device\n"); return -EINVAL; + } + flags2 |= FLAG2_ENABLE_S0IX_FLOWS; } - if (flags2 != adapter->flags2) + if (priv_flags & E1000E_PRIV_FLAGS_DISABLE_K1) { + if (hw->mac.type < e1000_ich8lan) { + e_err("Disabling K1 is not supported on this device\n"); + return -EINVAL; + } + + flags2 |= FLAG2_DISABLE_K1; + } + + changed = adapter->flags2 ^ flags2; + if (changed) adapter->flags2 = flags2; + if (changed & FLAG2_DISABLE_K1) { + /* reset the hardware to apply the changes */ + while (test_and_set_bit(__E1000_RESETTING, + &adapter->state)) + usleep_range(1000, 2000); + + if (netif_running(adapter->netdev)) { + e1000e_down(adapter, true); + e1000e_up(adapter); + } else { + e1000e_reset(adapter); + } + + clear_bit(__E1000_RESETTING, &adapter->state); + } + return 0; } diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index df4e7d781cb1..0ff8688ac3b8 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -286,21 +286,26 @@ static void e1000_toggle_lanphypc_pch_lpt(struct e1000_hw *hw) } /** - * e1000_reconfigure_k1_exit_timeout - reconfigure K1 exit timeout to - * align to MTP and later platform requirements. + * e1000_reconfigure_k1_params - reconfigure Kumeran K1 parameters. * @hw: pointer to the HW structure * + * By default K1 is enabled after MAC reset, so this function only + * disables it. + * * Context: PHY semaphore must be held by caller. * Return: 0 on success, negative on failure */ -static s32 e1000_reconfigure_k1_exit_timeout(struct e1000_hw *hw) +static s32 e1000_reconfigure_k1_params(struct e1000_hw *hw) { u16 phy_timeout; u32 fextnvm12; s32 ret_val; - if (hw->mac.type < e1000_pch_mtp) + if (hw->mac.type < e1000_pch_mtp) { + if (hw->adapter->flags2 & FLAG2_DISABLE_K1) + return e1000_configure_k1_ich8lan(hw, false); return 0; + } /* Change Kumeran K1 power down state from P0s to P1 */ fextnvm12 = er32(FEXTNVM12); @@ -310,6 +315,8 @@ static s32 e1000_reconfigure_k1_exit_timeout(struct e1000_hw *hw) /* Wait for the interface the settle */ usleep_range(1000, 1100); + if (hw->adapter->flags2 & FLAG2_DISABLE_K1) + return e1000_configure_k1_ich8lan(hw, false); /* Change K1 exit timeout */ ret_val = e1e_rphy_locked(hw, I217_PHY_TIMEOUTS_REG, @@ -373,8 +380,8 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) /* At this point the PHY might be inaccessible so don't * propagate the failure */ - if (e1000_reconfigure_k1_exit_timeout(hw)) - e_dbg("Failed to reconfigure K1 exit timeout\n"); + if (e1000_reconfigure_k1_params(hw)) + e_dbg("Failed to reconfigure K1 parameters\n"); fallthrough; case e1000_pch_lpt: @@ -473,10 +480,10 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) if (hw->mac.type >= e1000_pch_mtp) { ret_val = hw->phy.ops.acquire(hw); if (ret_val) { - e_err("Failed to reconfigure K1 exit timeout\n"); + e_err("Failed to reconfigure K1 parameters\n"); goto out; } - ret_val = e1000_reconfigure_k1_exit_timeout(hw); + ret_val = e1000_reconfigure_k1_params(hw); hw->phy.ops.release(hw); } } @@ -4948,17 +4955,15 @@ static s32 e1000_init_hw_ich8lan(struct e1000_hw *hw) u16 i; e1000_initialize_hw_bits_ich8lan(hw); - if (hw->mac.type >= e1000_pch_mtp) { - ret_val = hw->phy.ops.acquire(hw); - if (ret_val) - return ret_val; + ret_val = hw->phy.ops.acquire(hw); + if (ret_val) + return ret_val; - ret_val = e1000_reconfigure_k1_exit_timeout(hw); - hw->phy.ops.release(hw); - if (ret_val) { - e_dbg("Error failed to reconfigure K1 exit timeout\n"); - return ret_val; - } + ret_val = e1000_reconfigure_k1_params(hw); + hw->phy.ops.release(hw); + if (ret_val) { + e_dbg("Error failed to reconfigure K1 parameters\n"); + return ret_val; } /* Initialize identification LED */ diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 201322dac233..116f3c92b5bc 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -7675,6 +7675,9 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* init PTP hardware clock */ e1000e_ptp_init(adapter); + if (hw->mac.type >= e1000_pch_mtp) + adapter->flags2 |= FLAG2_DISABLE_K1; + /* reset the hardware with the new settings */ e1000e_reset(adapter); diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 081a4526a2f0..0fe0d52c796b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -4788,6 +4788,7 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link) unsigned long q_map; struct i40e_vf *vf; int abs_vf_id; + int old_link; int ret = 0; int tmp; @@ -4806,6 +4807,17 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link) vf = &pf->vf[vf_id]; abs_vf_id = vf->vf_id + hw->func_caps.vf_base_id; + /* skip VF link state change if requested state is already set */ + if (!vf->link_forced) + old_link = IFLA_VF_LINK_STATE_AUTO; + else if (vf->link_up) + old_link = IFLA_VF_LINK_STATE_ENABLE; + else + old_link = IFLA_VF_LINK_STATE_DISABLE; + + if (link == old_link) + goto error_out; + pfe.event = VIRTCHNL_EVENT_LINK_CHANGE; pfe.severity = PF_EVENT_SEVERITY_INFO; diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c index fb2de521731a..938914abbe06 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c @@ -459,6 +459,7 @@ static void ice_devlink_reinit_down(struct ice_pf *pf) rtnl_lock(); ice_vsi_decfg(ice_get_main_vsi(pf)); rtnl_unlock(); + ice_deinit_pf(pf); ice_deinit_dev(pf); } @@ -1231,11 +1232,13 @@ static void ice_set_min_max_msix(struct ice_pf *pf) static int ice_devlink_reinit_up(struct ice_pf *pf) { struct ice_vsi *vsi = ice_get_main_vsi(pf); + struct device *dev = ice_pf_to_dev(pf); + bool need_dev_deinit = false; int err; err = ice_init_hw(&pf->hw); if (err) { - dev_err(ice_pf_to_dev(pf), "ice_init_hw failed: %d\n", err); + dev_err(dev, "ice_init_hw failed: %d\n", err); return err; } @@ -1246,13 +1249,19 @@ static int ice_devlink_reinit_up(struct ice_pf *pf) if (err) goto unroll_hw_init; + err = ice_init_pf(pf); + if (err) { + dev_err(dev, "ice_init_pf failed: %d\n", err); + goto unroll_dev_init; + } + vsi->flags = ICE_VSI_FLAG_INIT; rtnl_lock(); err = ice_vsi_cfg(vsi); rtnl_unlock(); if (err) - goto err_vsi_cfg; + goto unroll_pf_init; /* No need to take devl_lock, it's already taken by devlink API */ err = ice_load(pf); @@ -1265,10 +1274,14 @@ err_load: rtnl_lock(); ice_vsi_decfg(vsi); rtnl_unlock(); -err_vsi_cfg: - ice_deinit_dev(pf); +unroll_pf_init: + ice_deinit_pf(pf); +unroll_dev_init: + need_dev_deinit = true; unroll_hw_init: ice_deinit_hw(&pf->hw); + if (need_dev_deinit) + ice_deinit_dev(pf); return err; } diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 22b8323ff0d0..147aaee192a7 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -351,6 +351,7 @@ struct ice_vsi { u16 num_q_vectors; /* tell if only dynamic irq allocation is allowed */ bool irq_dyn_alloc; + bool hsplit:1; u16 vsi_num; /* HW (absolute) index of this VSI */ u16 idx; /* software index in pf->vsi[] */ @@ -374,6 +375,8 @@ struct ice_vsi { spinlock_t arfs_lock; /* protects aRFS hash table and filter state */ atomic_t *arfs_last_fltr_id; + u16 max_frame; + struct ice_aqc_vsi_props info; /* VSI properties */ struct ice_vsi_vlan_info vlan_info; /* vlan config to be restored */ @@ -509,7 +512,6 @@ enum ice_pf_flags { ICE_FLAG_MOD_POWER_UNSUPPORTED, ICE_FLAG_PHY_FW_LOAD_FAILED, ICE_FLAG_ETHTOOL_CTXT, /* set when ethtool holds RTNL lock */ - ICE_FLAG_LEGACY_RX, ICE_FLAG_VF_TRUE_PROMISC_ENA, ICE_FLAG_MDD_AUTO_RESET_VF, ICE_FLAG_VF_VLAN_PRUNING, @@ -1029,11 +1031,15 @@ int ice_open(struct net_device *netdev); int ice_open_internal(struct net_device *netdev); int ice_stop(struct net_device *netdev); void ice_service_task_schedule(struct ice_pf *pf); +void ice_start_service_task(struct ice_pf *pf); int ice_load(struct ice_pf *pf); void ice_unload(struct ice_pf *pf); void ice_adv_lnk_speed_maps_init(void); +void ice_init_dev_hw(struct ice_pf *pf); int ice_init_dev(struct ice_pf *pf); void ice_deinit_dev(struct ice_pf *pf); +int ice_init_pf(struct ice_pf *pf); +void ice_deinit_pf(struct ice_pf *pf); int ice_change_mtu(struct net_device *netdev, int new_mtu); void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue); int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp); diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 2d35a278c555..eadb1e3d12b3 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -2,6 +2,7 @@ /* Copyright (c) 2019, Intel Corporation. */ #include <net/xdp_sock_drv.h> +#include <linux/net/intel/libie/rx.h> #include "ice_base.h" #include "ice_lib.h" #include "ice_dcb_lib.h" @@ -462,19 +463,6 @@ u16 ice_calc_ts_ring_count(struct ice_tx_ring *tx_ring) } /** - * ice_rx_offset - Return expected offset into page to access data - * @rx_ring: Ring we are requesting offset of - * - * Returns the offset value for ring into the data buffer. - */ -static unsigned int ice_rx_offset(struct ice_rx_ring *rx_ring) -{ - if (ice_ring_uses_build_skb(rx_ring)) - return ICE_SKB_PAD; - return 0; -} - -/** * ice_setup_rx_ctx - Configure a receive ring context * @ring: The Rx ring to configure * @@ -536,8 +524,29 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) else rlan_ctx.l2tsel = 1; - rlan_ctx.dtype = ICE_RX_DTYPE_NO_SPLIT; - rlan_ctx.hsplit_0 = ICE_RLAN_RX_HSPLIT_0_NO_SPLIT; + if (ring->hdr_pp) { + rlan_ctx.hbuf = ring->rx_hdr_len >> ICE_RLAN_CTX_HBUF_S; + rlan_ctx.dtype = ICE_RX_DTYPE_HEADER_SPLIT; + + /* + * If the frame is TCP/UDP/SCTP, it will be split by the + * payload. + * If not, but it's an IPv4/IPv6 frame, it will be split by + * the IP header. + * If not IP, it will be split by the Ethernet header. + * + * In any case, the header buffer will never be left empty. + */ + rlan_ctx.hsplit_0 = ICE_RLAN_RX_HSPLIT_0_SPLIT_L2 | + ICE_RLAN_RX_HSPLIT_0_SPLIT_IP | + ICE_RLAN_RX_HSPLIT_0_SPLIT_TCP_UDP | + ICE_RLAN_RX_HSPLIT_0_SPLIT_SCTP; + } else { + rlan_ctx.hbuf = 0; + rlan_ctx.dtype = ICE_RX_DTYPE_NO_SPLIT; + rlan_ctx.hsplit_0 = ICE_RLAN_RX_HSPLIT_0_NO_SPLIT; + } + rlan_ctx.hsplit_1 = ICE_RLAN_RX_HSPLIT_1_NO_SPLIT; /* This controls whether VLAN is stripped from inner headers @@ -549,7 +558,7 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) /* Max packet size for this queue - must not be set to a larger value * than 5 x DBUF */ - rlan_ctx.rxmax = min_t(u32, ring->max_frame, + rlan_ctx.rxmax = min_t(u32, vsi->max_frame, ICE_MAX_CHAINED_RX_BUFS * ring->rx_buf_len); /* Rx queue threshold in units of 64 */ @@ -586,14 +595,6 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) if (vsi->type == ICE_VSI_VF) return 0; - /* configure Rx buffer alignment */ - if (!vsi->netdev || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags)) - ice_clear_ring_build_skb_ena(ring); - else - ice_set_ring_build_skb_ena(ring); - - ring->rx_offset = ice_rx_offset(ring); - /* init queue specific tail register */ ring->tail = hw->hw_addr + QRX_TAIL(pf_q); writel(0, ring->tail); @@ -601,36 +602,51 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) return 0; } -static void ice_xsk_pool_fill_cb(struct ice_rx_ring *ring) +static int ice_rxq_pp_create(struct ice_rx_ring *rq) { - void *ctx_ptr = &ring->pkt_ctx; - struct xsk_cb_desc desc = {}; - - XSK_CHECK_PRIV_TYPE(struct ice_xdp_buff); - desc.src = &ctx_ptr; - desc.off = offsetof(struct ice_xdp_buff, pkt_ctx) - - sizeof(struct xdp_buff); - desc.bytes = sizeof(ctx_ptr); - xsk_pool_fill_cb(ring->xsk_pool, &desc); -} + struct libeth_fq fq = { + .count = rq->count, + .nid = NUMA_NO_NODE, + .hsplit = rq->vsi->hsplit, + .xdp = ice_is_xdp_ena_vsi(rq->vsi), + .buf_len = LIBIE_MAX_RX_BUF_LEN, + }; + int err; -/** - * ice_get_frame_sz - calculate xdp_buff::frame_sz - * @rx_ring: the ring being configured - * - * Return frame size based on underlying PAGE_SIZE - */ -static unsigned int ice_get_frame_sz(struct ice_rx_ring *rx_ring) -{ - unsigned int frame_sz; + err = libeth_rx_fq_create(&fq, &rq->q_vector->napi); + if (err) + return err; + + rq->pp = fq.pp; + rq->rx_fqes = fq.fqes; + rq->truesize = fq.truesize; + rq->rx_buf_len = fq.buf_len; -#if (PAGE_SIZE >= 8192) - frame_sz = rx_ring->rx_buf_len; -#else - frame_sz = ice_rx_pg_size(rx_ring) / 2; -#endif + if (!fq.hsplit) + return 0; + + fq = (struct libeth_fq){ + .count = rq->count, + .type = LIBETH_FQE_HDR, + .nid = NUMA_NO_NODE, + .xdp = ice_is_xdp_ena_vsi(rq->vsi), + }; - return frame_sz; + err = libeth_rx_fq_create(&fq, &rq->q_vector->napi); + if (err) + goto destroy; + + rq->hdr_pp = fq.pp; + rq->hdr_fqes = fq.fqes; + rq->hdr_truesize = fq.truesize; + rq->rx_hdr_len = fq.buf_len; + + return 0; + +destroy: + ice_rxq_pp_destroy(rq); + + return err; } /** @@ -642,7 +658,8 @@ static unsigned int ice_get_frame_sz(struct ice_rx_ring *rx_ring) static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) { struct device *dev = ice_pf_to_dev(ring->vsi->back); - u32 num_bufs = ICE_RX_DESC_UNUSED(ring); + u32 num_bufs = ICE_DESC_UNUSED(ring); + u32 rx_buf_len; int err; if (ring->vsi->type == ICE_VSI_PF || ring->vsi->type == ICE_VSI_SF) { @@ -656,15 +673,19 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) } ice_rx_xsk_pool(ring); + err = ice_realloc_rx_xdp_bufs(ring, ring->xsk_pool); + if (err) + return err; + if (ring->xsk_pool) { xdp_rxq_info_unreg(&ring->xdp_rxq); - ring->rx_buf_len = + rx_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool); err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, ring->q_index, ring->q_vector->napi.napi_id, - ring->rx_buf_len); + rx_buf_len); if (err) return err; err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, @@ -673,36 +694,33 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) if (err) return err; xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq); - ice_xsk_pool_fill_cb(ring); dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n", ring->q_index); } else { + err = ice_rxq_pp_create(ring); + if (err) + return err; + if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) { err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, ring->q_index, ring->q_vector->napi.napi_id, ring->rx_buf_len); if (err) - return err; + goto err_destroy_fq; } - - err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, - MEM_TYPE_PAGE_SHARED, - NULL); - if (err) - return err; + xdp_rxq_info_attach_page_pool(&ring->xdp_rxq, + ring->pp); } } - xdp_init_buff(&ring->xdp, ice_get_frame_sz(ring), &ring->xdp_rxq); ring->xdp.data = NULL; - ring->xdp_ext.pkt_ctx = &ring->pkt_ctx; err = ice_setup_rx_ctx(ring); if (err) { dev_err(dev, "ice_setup_rx_ctx failed for RxQ %d, err %d\n", ring->q_index, err); - return err; + goto err_destroy_fq; } if (ring->xsk_pool) { @@ -730,9 +748,17 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) if (ring->vsi->type == ICE_VSI_CTRL) ice_init_ctrl_rx_descs(ring, num_bufs); else - ice_alloc_rx_bufs(ring, num_bufs); + err = ice_alloc_rx_bufs(ring, num_bufs); + + if (err) + goto err_destroy_fq; return 0; + +err_destroy_fq: + ice_rxq_pp_destroy(ring); + + return err; } int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx) @@ -753,18 +779,10 @@ int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx) */ static void ice_vsi_cfg_frame_size(struct ice_vsi *vsi, struct ice_rx_ring *ring) { - if (!vsi->netdev || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags)) { - ring->max_frame = ICE_MAX_FRAME_LEGACY_RX; - ring->rx_buf_len = ICE_RXBUF_1664; -#if (PAGE_SIZE < 8192) - } else if (!ICE_2K_TOO_SMALL_WITH_PADDING && - (vsi->netdev->mtu <= ETH_DATA_LEN)) { - ring->max_frame = ICE_RXBUF_1536 - NET_IP_ALIGN; - ring->rx_buf_len = ICE_RXBUF_1536 - NET_IP_ALIGN; -#endif + if (!vsi->netdev) { + vsi->max_frame = ICE_MAX_FRAME_LEGACY_RX; } else { - ring->max_frame = ICE_AQ_SET_MAC_FRAME_SIZE_MAX; - ring->rx_buf_len = ICE_RXBUF_3072; + vsi->max_frame = ICE_AQ_SET_MAC_FRAME_SIZE_MAX; } } diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 2532b6f82e97..046bc9c65c51 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -1161,6 +1161,9 @@ int ice_init_hw(struct ice_hw *hw) status = ice_init_hw_tbls(hw); if (status) goto err_unroll_fltr_mgmt_struct; + + ice_init_dev_hw(hw->back); + mutex_init(&hw->tnl_lock); ice_init_chk_recipe_reuse_support(hw); @@ -3389,6 +3392,7 @@ bool ice_is_100m_speed_supported(struct ice_hw *hw) case ICE_DEV_ID_E822L_SGMII: case ICE_DEV_ID_E823L_1GBE: case ICE_DEV_ID_E823C_SGMII: + case ICE_DEV_ID_E825C_SGMII: return true; default: return false; diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index dc131779d426..a1d9abee97e5 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -10,6 +10,7 @@ #include "ice_lib.h" #include "ice_dcb_lib.h" #include <net/dcbnl.h> +#include <net/libeth/rx.h> struct ice_stats { char stat_string[ETH_GSTRING_LEN]; @@ -340,7 +341,6 @@ static const struct ice_priv_flag ice_gstrings_priv_flags[] = { ICE_FLAG_VF_TRUE_PROMISC_ENA), ICE_PRIV_FLAG("mdd-auto-reset-vf", ICE_FLAG_MDD_AUTO_RESET_VF), ICE_PRIV_FLAG("vf-vlan-pruning", ICE_FLAG_VF_VLAN_PRUNING), - ICE_PRIV_FLAG("legacy-rx", ICE_FLAG_LEGACY_RX), }; #define ICE_PRIV_FLAG_ARRAY_SIZE ARRAY_SIZE(ice_gstrings_priv_flags) @@ -794,8 +794,7 @@ static int ice_get_extended_regs(struct net_device *netdev, void *p) static void ice_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); struct ice_hw *hw = &pf->hw; u32 *regs_buf = (u32 *)p; unsigned int i; @@ -810,8 +809,7 @@ ice_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p) static u32 ice_get_msglevel(struct net_device *netdev) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); #ifndef CONFIG_DYNAMIC_DEBUG if (pf->hw.debug_mask) @@ -824,8 +822,7 @@ static u32 ice_get_msglevel(struct net_device *netdev) static void ice_set_msglevel(struct net_device *netdev, u32 data) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); #ifndef CONFIG_DYNAMIC_DEBUG if (ICE_DBG_USER & data) @@ -840,16 +837,14 @@ static void ice_set_msglevel(struct net_device *netdev, u32 data) static void ice_get_link_ext_stats(struct net_device *netdev, struct ethtool_link_ext_stats *stats) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); stats->link_down_events = pf->link_down_events; } static int ice_get_eeprom_len(struct net_device *netdev) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); return (int)pf->hw.flash.flash_size; } @@ -858,9 +853,7 @@ static int ice_get_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom, u8 *bytes) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_vsi *vsi = np->vsi; - struct ice_pf *pf = vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); struct ice_hw *hw = &pf->hw; struct device *dev; int ret; @@ -959,8 +952,7 @@ static u64 ice_link_test(struct net_device *netdev) */ static u64 ice_eeprom_test(struct net_device *netdev) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); netdev_info(netdev, "EEPROM test\n"); return !!(ice_nvm_validate_checksum(&pf->hw)); @@ -1239,8 +1231,9 @@ static int ice_diag_send(struct ice_tx_ring *tx_ring, u8 *data, u16 size) */ static int ice_lbtest_receive_frames(struct ice_rx_ring *rx_ring) { - struct ice_rx_buf *rx_buf; + struct libeth_fqe *rx_buf; int valid_frames, i; + struct page *page; u8 *received_buf; valid_frames = 0; @@ -1255,8 +1248,10 @@ static int ice_lbtest_receive_frames(struct ice_rx_ring *rx_ring) cpu_to_le16(BIT(ICE_RX_FLEX_DESC_STATUS0_EOF_S))))) continue; - rx_buf = &rx_ring->rx_buf[i]; - received_buf = page_address(rx_buf->page) + rx_buf->page_offset; + rx_buf = &rx_ring->rx_fqes[i]; + page = __netmem_to_page(rx_buf->netmem); + received_buf = page_address(page) + rx_buf->offset + + page->pp->p.offset; if (ice_lbtest_check_frame(received_buf)) valid_frames++; @@ -1274,9 +1269,8 @@ static int ice_lbtest_receive_frames(struct ice_rx_ring *rx_ring) */ static u64 ice_loopback_test(struct net_device *netdev) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_vsi *orig_vsi = np->vsi, *test_vsi; - struct ice_pf *pf = orig_vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); + struct ice_vsi *test_vsi; u8 *tx_frame __free(kfree) = NULL; u8 broadcast[ETH_ALEN], ret = 0; int num_frames, valid_frames; @@ -1365,8 +1359,7 @@ lbtest_vsi_close: */ static u64 ice_intr_test(struct net_device *netdev) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); u16 swic_old = pf->sw_int_count; netdev_info(netdev, "interrupt test\n"); @@ -1394,9 +1387,8 @@ static void ice_self_test(struct net_device *netdev, struct ethtool_test *eth_test, u64 *data) { - struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_pf *pf = ice_netdev_to_pf(netdev); bool if_running = netif_running(netdev); - struct ice_pf *pf = np->vsi->back; struct device *dev; dev = ice_pf_to_dev(pf); @@ -1720,9 +1712,7 @@ static int ice_nway_reset(struct net_device *netdev) */ static u32 ice_get_priv_flags(struct net_device *netdev) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_vsi *vsi = np->vsi; - struct ice_pf *pf = vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); u32 i, ret_flags = 0; for (i = 0; i < ICE_PRIV_FLAG_ARRAY_SIZE; i++) { @@ -1869,10 +1859,6 @@ static int ice_set_priv_flags(struct net_device *netdev, u32 flags) ice_nway_reset(netdev); } } - if (test_bit(ICE_FLAG_LEGACY_RX, change_flags)) { - /* down and up VSI so that changes of Rx cfg are reflected. */ - ice_down_up(vsi); - } /* don't allow modification of this flag when a single VF is in * promiscuous mode because it's not supported */ @@ -3165,6 +3151,10 @@ ice_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, ring->rx_jumbo_max_pending = 0; ring->rx_mini_pending = 0; ring->rx_jumbo_pending = 0; + + kernel_ring->tcp_data_split = vsi->hsplit ? + ETHTOOL_TCP_DATA_SPLIT_ENABLED : + ETHTOOL_TCP_DATA_SPLIT_DISABLED; } static int @@ -3181,6 +3171,7 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, int i, timeout = 50, err = 0; struct ice_hw *hw = &pf->hw; u16 new_rx_cnt, new_tx_cnt; + bool hsplit; if (ring->tx_pending > ICE_MAX_NUM_DESC_BY_MAC(hw) || ring->tx_pending < ICE_MIN_NUM_DESC || @@ -3206,9 +3197,12 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, netdev_info(netdev, "Requested Rx descriptor count rounded up to %d\n", new_rx_cnt); + hsplit = kernel_ring->tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_ENABLED; + /* if nothing to do return success */ if (new_tx_cnt == vsi->tx_rings[0]->count && - new_rx_cnt == vsi->rx_rings[0]->count) { + new_rx_cnt == vsi->rx_rings[0]->count && + hsplit == vsi->hsplit) { netdev_dbg(netdev, "Nothing to change, descriptor count is same as requested\n"); return 0; } @@ -3238,6 +3232,8 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, vsi->xdp_rings[i]->count = new_tx_cnt; vsi->num_tx_desc = (u16)new_tx_cnt; vsi->num_rx_desc = (u16)new_rx_cnt; + vsi->hsplit = hsplit; + netdev_dbg(netdev, "Link is down, descriptor count change happens when link is brought up\n"); goto done; } @@ -3321,7 +3317,8 @@ process_rx: rx_rings[i].count = new_rx_cnt; rx_rings[i].cached_phctime = pf->ptp.cached_phc_time; rx_rings[i].desc = NULL; - rx_rings[i].rx_buf = NULL; + rx_rings[i].xdp_buf = NULL; + /* this is to allow wr32 to have something to write to * during early allocation of Rx buffers */ @@ -3330,10 +3327,6 @@ process_rx: err = ice_setup_rx_ring(&rx_rings[i]); if (err) goto rx_unwind; - - /* allocate Rx buffers */ - err = ice_alloc_rx_bufs(&rx_rings[i], - ICE_RX_DESC_UNUSED(&rx_rings[i])); rx_unwind: if (err) { while (i) { @@ -3347,6 +3340,8 @@ rx_unwind: } process_link: + vsi->hsplit = hsplit; + /* Bring interface down, copy in the new ring info, then restore the * interface. if VSI is up, bring it down and then back up */ @@ -4417,9 +4412,7 @@ static int ice_get_module_info(struct net_device *netdev, struct ethtool_modinfo *modinfo) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_vsi *vsi = np->vsi; - struct ice_pf *pf = vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); struct ice_hw *hw = &pf->hw; u8 sff8472_comp = 0; u8 sff8472_swap = 0; @@ -4491,12 +4484,10 @@ static int ice_get_module_eeprom(struct net_device *netdev, struct ethtool_eeprom *ee, u8 *data) { - struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_pf *pf = ice_netdev_to_pf(netdev); #define SFF_READ_BLOCK_SIZE 8 u8 value[SFF_READ_BLOCK_SIZE] = { 0 }; u8 addr = ICE_I2C_EEPROM_DEV_ADDR; - struct ice_vsi *vsi = np->vsi; - struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; bool is_sfp = false; unsigned int i, j; @@ -4661,6 +4652,98 @@ static void ice_get_fec_stats(struct net_device *netdev, pi->lport, err); } +static void ice_get_eth_mac_stats(struct net_device *netdev, + struct ethtool_eth_mac_stats *mac_stats) +{ + struct ice_pf *pf = ice_netdev_to_pf(netdev); + struct ice_hw_port_stats *ps = &pf->stats; + + mac_stats->FramesTransmittedOK = ps->eth.tx_unicast + + ps->eth.tx_multicast + + ps->eth.tx_broadcast; + mac_stats->FramesReceivedOK = ps->eth.rx_unicast + + ps->eth.rx_multicast + + ps->eth.rx_broadcast; + mac_stats->FrameCheckSequenceErrors = ps->crc_errors; + mac_stats->OctetsTransmittedOK = ps->eth.tx_bytes; + mac_stats->OctetsReceivedOK = ps->eth.rx_bytes; + mac_stats->MulticastFramesXmittedOK = ps->eth.tx_multicast; + mac_stats->BroadcastFramesXmittedOK = ps->eth.tx_broadcast; + mac_stats->MulticastFramesReceivedOK = ps->eth.rx_multicast; + mac_stats->BroadcastFramesReceivedOK = ps->eth.rx_broadcast; + mac_stats->InRangeLengthErrors = ps->rx_len_errors; + mac_stats->FrameTooLongErrors = ps->rx_oversize; +} + +static void ice_get_pause_stats(struct net_device *netdev, + struct ethtool_pause_stats *pause_stats) +{ + struct ice_pf *pf = ice_netdev_to_pf(netdev); + struct ice_hw_port_stats *ps = &pf->stats; + + pause_stats->tx_pause_frames = ps->link_xon_tx + ps->link_xoff_tx; + pause_stats->rx_pause_frames = ps->link_xon_rx + ps->link_xoff_rx; +} + +static const struct ethtool_rmon_hist_range ice_rmon_ranges[] = { + { 0, 64 }, + { 65, 127 }, + { 128, 255 }, + { 256, 511 }, + { 512, 1023 }, + { 1024, 1522 }, + { 1523, 9522 }, + {} +}; + +static void ice_get_rmon_stats(struct net_device *netdev, + struct ethtool_rmon_stats *rmon, + const struct ethtool_rmon_hist_range **ranges) +{ + struct ice_pf *pf = ice_netdev_to_pf(netdev); + struct ice_hw_port_stats *ps = &pf->stats; + + rmon->undersize_pkts = ps->rx_undersize; + rmon->oversize_pkts = ps->rx_oversize; + rmon->fragments = ps->rx_fragments; + rmon->jabbers = ps->rx_jabber; + + rmon->hist[0] = ps->rx_size_64; + rmon->hist[1] = ps->rx_size_127; + rmon->hist[2] = ps->rx_size_255; + rmon->hist[3] = ps->rx_size_511; + rmon->hist[4] = ps->rx_size_1023; + rmon->hist[5] = ps->rx_size_1522; + rmon->hist[6] = ps->rx_size_big; + + rmon->hist_tx[0] = ps->tx_size_64; + rmon->hist_tx[1] = ps->tx_size_127; + rmon->hist_tx[2] = ps->tx_size_255; + rmon->hist_tx[3] = ps->tx_size_511; + rmon->hist_tx[4] = ps->tx_size_1023; + rmon->hist_tx[5] = ps->tx_size_1522; + rmon->hist_tx[6] = ps->tx_size_big; + + *ranges = ice_rmon_ranges; +} + +/* ice_get_ts_stats - provide timestamping stats + * @netdev: the netdevice pointer from ethtool + * @ts_stats: the ethtool data structure to fill in + */ +static void ice_get_ts_stats(struct net_device *netdev, + struct ethtool_ts_stats *ts_stats) +{ + struct ice_pf *pf = ice_netdev_to_pf(netdev); + struct ice_ptp *ptp = &pf->ptp; + + ts_stats->pkts = ptp->tx_hwtstamp_good; + ts_stats->err = ptp->tx_hwtstamp_skipped + + ptp->tx_hwtstamp_flushed + + ptp->tx_hwtstamp_discarded; + ts_stats->lost = ptp->tx_hwtstamp_timeouts; +} + #define ICE_ETHTOOL_PFR (ETH_RESET_IRQ | ETH_RESET_DMA | \ ETH_RESET_FILTER | ETH_RESET_OFFLOAD) @@ -4682,8 +4765,7 @@ static void ice_get_fec_stats(struct net_device *netdev, */ static int ice_ethtool_reset(struct net_device *dev, u32 *flags) { - struct ice_netdev_priv *np = netdev_priv(dev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(dev); enum ice_reset_req reset; switch (*flags) { @@ -4741,9 +4823,14 @@ static const struct ethtool_ops ice_ethtool_ops = { ETHTOOL_COALESCE_USE_ADAPTIVE | ETHTOOL_COALESCE_RX_USECS_HIGH, .supported_input_xfrm = RXH_XFRM_SYM_XOR, + .supported_ring_params = ETHTOOL_RING_USE_TCP_DATA_SPLIT, .get_link_ksettings = ice_get_link_ksettings, .set_link_ksettings = ice_set_link_ksettings, .get_fec_stats = ice_get_fec_stats, + .get_eth_mac_stats = ice_get_eth_mac_stats, + .get_pause_stats = ice_get_pause_stats, + .get_rmon_stats = ice_get_rmon_stats, + .get_ts_stats = ice_get_ts_stats, .get_drvinfo = ice_get_drvinfo, .get_regs_len = ice_get_regs_len, .get_regs = ice_get_regs, diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c index 013c93b6605e..c8cb492fddf4 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c @@ -574,9 +574,7 @@ ice_destroy_tunnel_end: int ice_udp_tunnel_set_port(struct net_device *netdev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_vsi *vsi = np->vsi; - struct ice_pf *pf = vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); enum ice_tunnel_type tnl_type; int status; u16 index; @@ -598,9 +596,7 @@ int ice_udp_tunnel_set_port(struct net_device *netdev, unsigned int table, int ice_udp_tunnel_unset_port(struct net_device *netdev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_vsi *vsi = np->vsi; - struct ice_pf *pf = vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); enum ice_tunnel_type tnl_type; int status; diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c index aebf8e08a297..d2576d606e10 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.c +++ b/drivers/net/ethernet/intel/ice/ice_lag.c @@ -2177,8 +2177,7 @@ static void ice_lag_chk_disabled_bond(struct ice_lag *lag, void *ptr) */ static void ice_lag_disable_sriov_bond(struct ice_lag *lag) { - struct ice_netdev_priv *np = netdev_priv(lag->netdev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(lag->netdev); ice_clear_feature_support(pf, ICE_F_SRIOV_LAG); ice_clear_feature_support(pf, ICE_F_SRIOV_AA_LAG); diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h index 10c312d49e05..185672c7e17d 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -342,6 +342,9 @@ enum ice_flg64_bits { /* for ice_32byte_rx_flex_desc.pkt_length member */ #define ICE_RX_FLX_DESC_PKT_LEN_M (0x3FFF) /* 14-bits */ +/* ice_32byte_rx_flex_desc::hdr_len_sph_flex_flags1 */ +#define ICE_RX_FLEX_DESC_HDR_LEN_M GENMASK(10, 0) + enum ice_rx_flex_desc_status_error_0_bits { /* Note: These are predefined bit offsets */ ICE_RX_FLEX_DESC_STATUS0_DD_S = 0, diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 4479c824561e..15621707fbf8 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -1427,7 +1427,6 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) ring->reg_idx = vsi->rxq_map[i]; ring->vsi = vsi; ring->netdev = vsi->netdev; - ring->dev = dev; ring->count = vsi->num_rx_desc; ring->cached_phctime = pf->ptp.cached_phc_time; @@ -2769,7 +2768,6 @@ void ice_dis_vsi(struct ice_vsi *vsi, bool locked) * @vsi: VSI pointer * * Associate queue[s] with napi for all vectors. - * The caller must hold rtnl_lock. */ void ice_vsi_set_napi_queues(struct ice_vsi *vsi) { @@ -2779,6 +2777,7 @@ void ice_vsi_set_napi_queues(struct ice_vsi *vsi) if (!netdev) return; + ASSERT_RTNL(); ice_for_each_rxq(vsi, q_idx) netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_RX, &vsi->rx_rings[q_idx]->q_vector->napi); @@ -2799,7 +2798,6 @@ void ice_vsi_set_napi_queues(struct ice_vsi *vsi) * @vsi: VSI pointer * * Clear the association between all VSI queues queue[s] and napi. - * The caller must hold rtnl_lock. */ void ice_vsi_clear_napi_queues(struct ice_vsi *vsi) { @@ -2809,6 +2807,7 @@ void ice_vsi_clear_napi_queues(struct ice_vsi *vsi) if (!netdev) return; + ASSERT_RTNL(); /* Clear the NAPI's interrupt number */ ice_for_each_q_vector(vsi, v_idx) { struct ice_q_vector *q_vector = vsi->q_vectors[v_idx]; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 86f5859e88ef..2533876f1a2f 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -37,6 +37,8 @@ static const char ice_copyright[] = "Copyright (c) 2018, Intel Corporation."; #define ICE_DDP_PKG_FILE ICE_DDP_PKG_PATH "ice.pkg" MODULE_DESCRIPTION(DRV_SUMMARY); +MODULE_IMPORT_NS("LIBETH"); +MODULE_IMPORT_NS("LIBETH_XDP"); MODULE_IMPORT_NS("LIBIE"); MODULE_IMPORT_NS("LIBIE_ADMINQ"); MODULE_IMPORT_NS("LIBIE_FWLOG"); @@ -2957,10 +2959,7 @@ int ice_vsi_determine_xdp_res(struct ice_vsi *vsi) */ static int ice_max_xdp_frame_size(struct ice_vsi *vsi) { - if (test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags)) - return ICE_RXBUF_1664; - else - return ICE_RXBUF_3072; + return ICE_RXBUF_3072; } /** @@ -3018,19 +3017,11 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, } } xdp_features_set_redirect_target(vsi->netdev, true); - /* reallocate Rx queues that are used for zero-copy */ - xdp_ring_err = ice_realloc_zc_buf(vsi, true); - if (xdp_ring_err) - NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Rx resources failed"); } else if (ice_is_xdp_ena_vsi(vsi) && !prog) { xdp_features_clear_redirect_target(vsi->netdev); xdp_ring_err = ice_destroy_xdp_rings(vsi, ICE_XDP_CFG_FULL); if (xdp_ring_err) NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Tx resources failed"); - /* reallocate Rx queues that were used for zero-copy */ - xdp_ring_err = ice_realloc_zc_buf(vsi, false); - if (xdp_ring_err) - NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Rx resources failed"); } resume_if: @@ -3949,9 +3940,10 @@ u16 ice_get_avail_rxq_count(struct ice_pf *pf) * ice_deinit_pf - Unrolls initialziations done by ice_init_pf * @pf: board private structure to initialize */ -static void ice_deinit_pf(struct ice_pf *pf) +void ice_deinit_pf(struct ice_pf *pf) { - ice_service_task_stop(pf); + /* note that we unroll also on ice_init_pf() failure here */ + mutex_destroy(&pf->lag_mutex); mutex_destroy(&pf->adev_mutex); mutex_destroy(&pf->sw_mutex); @@ -3977,6 +3969,9 @@ static void ice_deinit_pf(struct ice_pf *pf) if (pf->ptp.clock) ptp_clock_unregister(pf->ptp.clock); + if (!xa_empty(&pf->irq_tracker.entries)) + ice_free_irq_msix_misc(pf); + xa_destroy(&pf->dyn_ports); xa_destroy(&pf->sf_nums); } @@ -4030,13 +4025,25 @@ static void ice_set_pf_caps(struct ice_pf *pf) pf->max_pf_rxqs = func_caps->common_cap.num_rxq; } +void ice_start_service_task(struct ice_pf *pf) +{ + timer_setup(&pf->serv_tmr, ice_service_timer, 0); + pf->serv_tmr_period = HZ; + INIT_WORK(&pf->serv_task, ice_service_task); + clear_bit(ICE_SERVICE_SCHED, pf->state); +} + /** * ice_init_pf - Initialize general software structures (struct ice_pf) * @pf: board private structure to initialize + * Return: 0 on success, negative errno otherwise. */ -static int ice_init_pf(struct ice_pf *pf) +int ice_init_pf(struct ice_pf *pf) { - ice_set_pf_caps(pf); + struct udp_tunnel_nic_info *udp_tunnel_nic = &pf->hw.udp_tunnel_nic; + struct device *dev = ice_pf_to_dev(pf); + struct ice_hw *hw = &pf->hw; + int err = -ENOMEM; mutex_init(&pf->sw_mutex); mutex_init(&pf->tc_mutex); @@ -4049,32 +4056,7 @@ static int ice_init_pf(struct ice_pf *pf) init_waitqueue_head(&pf->reset_wait_queue); - /* setup service timer and periodic service task */ - timer_setup(&pf->serv_tmr, ice_service_timer, 0); - pf->serv_tmr_period = HZ; - INIT_WORK(&pf->serv_task, ice_service_task); - clear_bit(ICE_SERVICE_SCHED, pf->state); - mutex_init(&pf->avail_q_mutex); - pf->avail_txqs = bitmap_zalloc(pf->max_pf_txqs, GFP_KERNEL); - if (!pf->avail_txqs) - return -ENOMEM; - - pf->avail_rxqs = bitmap_zalloc(pf->max_pf_rxqs, GFP_KERNEL); - if (!pf->avail_rxqs) { - bitmap_free(pf->avail_txqs); - pf->avail_txqs = NULL; - return -ENOMEM; - } - - pf->txtime_txqs = bitmap_zalloc(pf->max_pf_txqs, GFP_KERNEL); - if (!pf->txtime_txqs) { - bitmap_free(pf->avail_txqs); - pf->avail_txqs = NULL; - bitmap_free(pf->avail_rxqs); - pf->avail_rxqs = NULL; - return -ENOMEM; - } mutex_init(&pf->vfs.table_lock); hash_init(pf->vfs.table); @@ -4087,7 +4069,36 @@ static int ice_init_pf(struct ice_pf *pf) xa_init(&pf->dyn_ports); xa_init(&pf->sf_nums); + pf->avail_txqs = bitmap_zalloc(pf->max_pf_txqs, GFP_KERNEL); + pf->avail_rxqs = bitmap_zalloc(pf->max_pf_rxqs, GFP_KERNEL); + pf->txtime_txqs = bitmap_zalloc(pf->max_pf_txqs, GFP_KERNEL); + if (!pf->avail_txqs || !pf->avail_rxqs || !pf->txtime_txqs) + goto undo_init; + + udp_tunnel_nic->set_port = ice_udp_tunnel_set_port; + udp_tunnel_nic->unset_port = ice_udp_tunnel_unset_port; + udp_tunnel_nic->shared = &hw->udp_tunnel_shared; + udp_tunnel_nic->tables[0].n_entries = hw->tnl.valid_count[TNL_VXLAN]; + udp_tunnel_nic->tables[0].tunnel_types = UDP_TUNNEL_TYPE_VXLAN; + udp_tunnel_nic->tables[1].n_entries = hw->tnl.valid_count[TNL_GENEVE]; + udp_tunnel_nic->tables[1].tunnel_types = UDP_TUNNEL_TYPE_GENEVE; + + /* In case of MSIX we are going to setup the misc vector right here + * to handle admin queue events etc. In case of legacy and MSI + * the misc functionality and queue processing is combined in + * the same vector and that gets setup at open. + */ + err = ice_req_irq_msix_misc(pf); + if (err) { + dev_err(dev, "setup of misc vector failed: %d\n", err); + goto undo_init; + } + return 0; +undo_init: + /* deinit handles half-initialized pf just fine */ + ice_deinit_pf(pf); + return err; } /** @@ -4722,9 +4733,8 @@ static void ice_decfg_netdev(struct ice_vsi *vsi) vsi->netdev = NULL; } -int ice_init_dev(struct ice_pf *pf) +void ice_init_dev_hw(struct ice_pf *pf) { - struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; int err; @@ -4744,61 +4754,28 @@ int ice_init_dev(struct ice_pf *pf) */ ice_set_safe_mode_caps(hw); } +} - err = ice_init_pf(pf); - if (err) { - dev_err(dev, "ice_init_pf failed: %d\n", err); - return err; - } - - pf->hw.udp_tunnel_nic.set_port = ice_udp_tunnel_set_port; - pf->hw.udp_tunnel_nic.unset_port = ice_udp_tunnel_unset_port; - pf->hw.udp_tunnel_nic.shared = &pf->hw.udp_tunnel_shared; - if (pf->hw.tnl.valid_count[TNL_VXLAN]) { - pf->hw.udp_tunnel_nic.tables[0].n_entries = - pf->hw.tnl.valid_count[TNL_VXLAN]; - pf->hw.udp_tunnel_nic.tables[0].tunnel_types = - UDP_TUNNEL_TYPE_VXLAN; - } - if (pf->hw.tnl.valid_count[TNL_GENEVE]) { - pf->hw.udp_tunnel_nic.tables[1].n_entries = - pf->hw.tnl.valid_count[TNL_GENEVE]; - pf->hw.udp_tunnel_nic.tables[1].tunnel_types = - UDP_TUNNEL_TYPE_GENEVE; - } +int ice_init_dev(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + int err; + ice_set_pf_caps(pf); err = ice_init_interrupt_scheme(pf); if (err) { dev_err(dev, "ice_init_interrupt_scheme failed: %d\n", err); - err = -EIO; - goto unroll_pf_init; + return -EIO; } - /* In case of MSIX we are going to setup the misc vector right here - * to handle admin queue events etc. In case of legacy and MSI - * the misc functionality and queue processing is combined in - * the same vector and that gets setup at open. - */ - err = ice_req_irq_msix_misc(pf); - if (err) { - dev_err(dev, "setup of misc vector failed: %d\n", err); - goto unroll_irq_scheme_init; - } + ice_start_service_task(pf); return 0; - -unroll_irq_scheme_init: - ice_clear_interrupt_scheme(pf); -unroll_pf_init: - ice_deinit_pf(pf); - return err; } void ice_deinit_dev(struct ice_pf *pf) { - ice_free_irq_msix_misc(pf); - ice_deinit_pf(pf); - ice_deinit_hw(&pf->hw); + ice_service_task_stop(pf); /* Service task is already stopped, so call reset directly. */ ice_reset(&pf->hw, ICE_RESET_PFR); @@ -5038,21 +5015,24 @@ static void ice_deinit_devlink(struct ice_pf *pf) static int ice_init(struct ice_pf *pf) { + struct device *dev = ice_pf_to_dev(pf); int err; - err = ice_init_dev(pf); - if (err) + err = ice_init_pf(pf); + if (err) { + dev_err(dev, "ice_init_pf failed: %d\n", err); return err; + } if (pf->hw.mac_type == ICE_MAC_E830) { err = pci_enable_ptm(pf->pdev, NULL); if (err) - dev_dbg(ice_pf_to_dev(pf), "PCIe PTM not supported by PCIe bus/controller\n"); + dev_dbg(dev, "PCIe PTM not supported by PCIe bus/controller\n"); } err = ice_alloc_vsis(pf); if (err) - goto err_alloc_vsis; + goto unroll_pf_init; err = ice_init_pf_sw(pf); if (err) @@ -5089,8 +5069,8 @@ err_init_link: ice_deinit_pf_sw(pf); err_init_pf_sw: ice_dealloc_vsis(pf); -err_alloc_vsis: - ice_deinit_dev(pf); +unroll_pf_init: + ice_deinit_pf(pf); return err; } @@ -5101,7 +5081,7 @@ static void ice_deinit(struct ice_pf *pf) ice_deinit_pf_sw(pf); ice_dealloc_vsis(pf); - ice_deinit_dev(pf); + ice_deinit_pf(pf); } /** @@ -5235,6 +5215,7 @@ static int ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) { struct device *dev = &pdev->dev; + bool need_dev_deinit = false; struct ice_adapter *adapter; struct ice_pf *pf; struct ice_hw *hw; @@ -5331,10 +5312,14 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) } pf->adapter = adapter; - err = ice_init(pf); + err = ice_init_dev(pf); if (err) goto unroll_adapter; + err = ice_init(pf); + if (err) + goto unroll_dev_init; + devl_lock(priv_to_devlink(pf)); err = ice_load(pf); if (err) @@ -5352,10 +5337,14 @@ unroll_load: unroll_init: devl_unlock(priv_to_devlink(pf)); ice_deinit(pf); +unroll_dev_init: + need_dev_deinit = true; unroll_adapter: ice_adapter_put(pdev); unroll_hw_init: ice_deinit_hw(hw); + if (need_dev_deinit) + ice_deinit_dev(pf); return err; } @@ -5450,10 +5439,6 @@ static void ice_remove(struct pci_dev *pdev) ice_hwmon_exit(pf); - ice_service_task_stop(pf); - ice_aq_cancel_waiting_tasks(pf); - set_bit(ICE_DOWN, pf->state); - if (!ice_is_safe_mode(pf)) ice_remove_arfs(pf); @@ -5471,6 +5456,11 @@ static void ice_remove(struct pci_dev *pdev) ice_set_wake(pf); ice_adapter_put(pdev); + ice_deinit_hw(&pf->hw); + + ice_deinit_dev(pf); + ice_aq_cancel_waiting_tasks(pf); + set_bit(ICE_DOWN, pf->state); } /** @@ -7138,6 +7128,9 @@ void ice_update_pf_stats(struct ice_pf *pf) &prev_ps->mac_remote_faults, &cur_ps->mac_remote_faults); + ice_stat_update32(hw, GLPRT_RLEC(port), pf->stat_prev_loaded, + &prev_ps->rx_len_errors, &cur_ps->rx_len_errors); + ice_stat_update32(hw, GLPRT_RUC(port), pf->stat_prev_loaded, &prev_ps->rx_undersize, &cur_ps->rx_undersize); @@ -7862,12 +7855,6 @@ int ice_change_mtu(struct net_device *netdev, int new_mtu) frame_size - ICE_ETH_PKT_HDR_PAD); return -EINVAL; } - } else if (test_bit(ICE_FLAG_LEGACY_RX, pf->flags)) { - if (new_mtu + ICE_ETH_PKT_HDR_PAD > ICE_MAX_FRAME_LEGACY_RX) { - netdev_err(netdev, "Too big MTU for legacy-rx; Max is %d\n", - ICE_MAX_FRAME_LEGACY_RX - ICE_ETH_PKT_HDR_PAD); - return -EINVAL; - } } /* if a reset is in progress, wait for some time for it to complete */ @@ -8071,9 +8058,7 @@ static int ice_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u32 filter_mask, int nlflags) { - struct ice_netdev_priv *np = netdev_priv(dev); - struct ice_vsi *vsi = np->vsi; - struct ice_pf *pf = vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(dev); u16 bmode; bmode = pf->first_sw->bridge_mode; @@ -8143,8 +8128,7 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 __always_unused flags, struct netlink_ext_ack __always_unused *extack) { - struct ice_netdev_priv *np = netdev_priv(dev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(dev); struct nlattr *attr, *br_spec; struct ice_hw *hw = &pf->hw; struct ice_sw *pf_sw; @@ -9578,8 +9562,7 @@ ice_indr_setup_tc_cb(struct net_device *netdev, struct Qdisc *sch, */ int ice_open(struct net_device *netdev) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); if (ice_is_reset_in_progress(pf->state)) { netdev_err(netdev, "can't open net device while reset is in progress"); diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index fb0f6365a6d6..985b3e79b312 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -500,6 +500,9 @@ void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx) if (tstamp) { shhwtstamps.hwtstamp = ns_to_ktime(tstamp); ice_trace(tx_tstamp_complete, skb, idx); + + /* Count the number of Tx timestamps that succeeded */ + pf->ptp.tx_hwtstamp_good++; } skb_tstamp_tx(skb, &shhwtstamps); @@ -558,6 +561,7 @@ static void ice_ptp_process_tx_tstamp(struct ice_ptp_tx *tx) { struct ice_ptp_port *ptp_port; unsigned long flags; + u32 tstamp_good = 0; struct ice_pf *pf; struct ice_hw *hw; u64 tstamp_ready; @@ -658,11 +662,16 @@ skip_ts_read: if (tstamp) { shhwtstamps.hwtstamp = ns_to_ktime(tstamp); ice_trace(tx_tstamp_complete, skb, idx); + + /* Count the number of Tx timestamps that succeeded */ + tstamp_good++; } skb_tstamp_tx(skb, &shhwtstamps); dev_kfree_skb_any(skb); } + + pf->ptp.tx_hwtstamp_good += tstamp_good; } /** @@ -2206,8 +2215,7 @@ static int ice_ptp_getcrosststamp(struct ptp_clock_info *info, int ice_ptp_hwtstamp_get(struct net_device *netdev, struct kernel_hwtstamp_config *config) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); if (pf->ptp.state != ICE_PTP_READY) return -EIO; @@ -2278,8 +2286,7 @@ int ice_ptp_hwtstamp_set(struct net_device *netdev, struct kernel_hwtstamp_config *config, struct netlink_ext_ack *extack) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); int err; if (pf->ptp.state != ICE_PTP_READY) diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h index 137f2070a2d9..27016aac4f1e 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp.h @@ -237,6 +237,7 @@ struct ice_ptp_pin_desc { * @clock: pointer to registered PTP clock device * @tstamp_config: hardware timestamping configuration * @reset_time: kernel time after clock stop on reset + * @tx_hwtstamp_good: number of completed Tx timestamp requests * @tx_hwtstamp_skipped: number of Tx time stamp requests skipped * @tx_hwtstamp_timeouts: number of Tx skbs discarded with no time stamp * @tx_hwtstamp_flushed: number of Tx skbs flushed due to interface closed @@ -261,6 +262,7 @@ struct ice_ptp { struct ptp_clock *clock; struct kernel_hwtstamp_config tstamp_config; u64 reset_time; + u64 tx_hwtstamp_good; u32 tx_hwtstamp_skipped; u32 tx_hwtstamp_timeouts; u32 tx_hwtstamp_flushed; diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index 843e82fd3bf9..6b1126ddb561 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -1190,8 +1190,7 @@ ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event) */ int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); struct ice_vsi *vf_vsi; struct device *dev; struct ice_vf *vf; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 73f08d02f9c7..ad76768a4232 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -7,6 +7,8 @@ #include <linux/netdevice.h> #include <linux/prefetch.h> #include <linux/bpf_trace.h> +#include <linux/net/intel/libie/rx.h> +#include <net/libeth/xdp.h> #include <net/dsfield.h> #include <net/mpls.h> #include <net/xdp.h> @@ -111,7 +113,7 @@ ice_prgm_fdir_fltr(struct ice_vsi *vsi, struct ice_fltr_desc *fdir_desc, static void ice_unmap_and_free_tx_buf(struct ice_tx_ring *ring, struct ice_tx_buf *tx_buf) { - if (dma_unmap_len(tx_buf, len)) + if (tx_buf->type != ICE_TX_BUF_XDP_TX && dma_unmap_len(tx_buf, len)) dma_unmap_page(ring->dev, dma_unmap_addr(tx_buf, dma), dma_unmap_len(tx_buf, len), @@ -125,7 +127,7 @@ ice_unmap_and_free_tx_buf(struct ice_tx_ring *ring, struct ice_tx_buf *tx_buf) dev_kfree_skb_any(tx_buf->skb); break; case ICE_TX_BUF_XDP_TX: - page_frag_free(tx_buf->raw_buf); + libeth_xdp_return_va(tx_buf->raw_buf, false); break; case ICE_TX_BUF_XDP_XMIT: xdp_return_frame(tx_buf->xdpf); @@ -506,61 +508,67 @@ err: return -ENOMEM; } +void ice_rxq_pp_destroy(struct ice_rx_ring *rq) +{ + struct libeth_fq fq = { + .fqes = rq->rx_fqes, + .pp = rq->pp, + }; + + libeth_rx_fq_destroy(&fq); + rq->rx_fqes = NULL; + rq->pp = NULL; + + if (!rq->hdr_pp) + return; + + fq.fqes = rq->hdr_fqes; + fq.pp = rq->hdr_pp; + + libeth_rx_fq_destroy(&fq); + rq->hdr_fqes = NULL; + rq->hdr_pp = NULL; +} + /** * ice_clean_rx_ring - Free Rx buffers * @rx_ring: ring to be cleaned */ void ice_clean_rx_ring(struct ice_rx_ring *rx_ring) { - struct xdp_buff *xdp = &rx_ring->xdp; - struct device *dev = rx_ring->dev; u32 size; - u16 i; - - /* ring already cleared, nothing to do */ - if (!rx_ring->rx_buf) - return; if (rx_ring->xsk_pool) { ice_xsk_clean_rx_ring(rx_ring); goto rx_skip_free; } - if (xdp->data) { - xdp_return_buff(xdp); - xdp->data = NULL; - } + /* ring already cleared, nothing to do */ + if (!rx_ring->rx_fqes) + return; + + libeth_xdp_return_stash(&rx_ring->xdp); /* Free all the Rx ring sk_buffs */ - for (i = 0; i < rx_ring->count; i++) { - struct ice_rx_buf *rx_buf = &rx_ring->rx_buf[i]; + for (u32 i = rx_ring->next_to_clean; i != rx_ring->next_to_use; ) { + libeth_rx_recycle_slow(rx_ring->rx_fqes[i].netmem); - if (!rx_buf->page) - continue; + if (rx_ring->hdr_pp) + libeth_rx_recycle_slow(rx_ring->hdr_fqes[i].netmem); - /* Invalidate cache lines that may have been written to by - * device so that we avoid corrupting memory. - */ - dma_sync_single_range_for_cpu(dev, rx_buf->dma, - rx_buf->page_offset, - rx_ring->rx_buf_len, - DMA_FROM_DEVICE); - - /* free resources associated with mapping */ - dma_unmap_page_attrs(dev, rx_buf->dma, ice_rx_pg_size(rx_ring), - DMA_FROM_DEVICE, ICE_RX_DMA_ATTR); - __page_frag_cache_drain(rx_buf->page, rx_buf->pagecnt_bias); - - rx_buf->page = NULL; - rx_buf->page_offset = 0; + if (unlikely(++i == rx_ring->count)) + i = 0; } -rx_skip_free: - if (rx_ring->xsk_pool) - memset(rx_ring->xdp_buf, 0, array_size(rx_ring->count, sizeof(*rx_ring->xdp_buf))); - else - memset(rx_ring->rx_buf, 0, array_size(rx_ring->count, sizeof(*rx_ring->rx_buf))); + if (rx_ring->vsi->type == ICE_VSI_PF && + xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) { + xdp_rxq_info_detach_mem_model(&rx_ring->xdp_rxq); + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); + } + ice_rxq_pp_destroy(rx_ring); + +rx_skip_free: /* Zero out the descriptor ring */ size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc), PAGE_SIZE); @@ -568,7 +576,6 @@ rx_skip_free: rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; - rx_ring->first_desc = 0; rx_ring->next_to_use = 0; } @@ -580,26 +587,20 @@ rx_skip_free: */ void ice_free_rx_ring(struct ice_rx_ring *rx_ring) { + struct device *dev = ice_pf_to_dev(rx_ring->vsi->back); u32 size; ice_clean_rx_ring(rx_ring); - if (rx_ring->vsi->type == ICE_VSI_PF) - if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) - xdp_rxq_info_unreg(&rx_ring->xdp_rxq); WRITE_ONCE(rx_ring->xdp_prog, NULL); if (rx_ring->xsk_pool) { kfree(rx_ring->xdp_buf); rx_ring->xdp_buf = NULL; - } else { - kfree(rx_ring->rx_buf); - rx_ring->rx_buf = NULL; } if (rx_ring->desc) { size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc), PAGE_SIZE); - dmam_free_coherent(rx_ring->dev, size, - rx_ring->desc, rx_ring->dma); + dmam_free_coherent(dev, size, rx_ring->desc, rx_ring->dma); rx_ring->desc = NULL; } } @@ -612,19 +613,9 @@ void ice_free_rx_ring(struct ice_rx_ring *rx_ring) */ int ice_setup_rx_ring(struct ice_rx_ring *rx_ring) { - struct device *dev = rx_ring->dev; + struct device *dev = ice_pf_to_dev(rx_ring->vsi->back); u32 size; - if (!dev) - return -ENOMEM; - - /* warn if we are about to overwrite the pointer */ - WARN_ON(rx_ring->rx_buf); - rx_ring->rx_buf = - kcalloc(rx_ring->count, sizeof(*rx_ring->rx_buf), GFP_KERNEL); - if (!rx_ring->rx_buf) - return -ENOMEM; - /* round up to nearest page */ size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc), PAGE_SIZE); @@ -633,22 +624,16 @@ int ice_setup_rx_ring(struct ice_rx_ring *rx_ring) if (!rx_ring->desc) { dev_err(dev, "Unable to allocate memory for the Rx descriptor ring, size=%d\n", size); - goto err; + return -ENOMEM; } rx_ring->next_to_use = 0; rx_ring->next_to_clean = 0; - rx_ring->first_desc = 0; if (ice_is_xdp_ena_vsi(rx_ring->vsi)) WRITE_ONCE(rx_ring->xdp_prog, rx_ring->vsi->xdp_prog); return 0; - -err: - kfree(rx_ring->rx_buf); - rx_ring->rx_buf = NULL; - return -ENOMEM; } /** @@ -662,7 +647,7 @@ err: * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR} */ static u32 -ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, +ice_run_xdp(struct ice_rx_ring *rx_ring, struct libeth_xdp_buff *xdp, struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring, union ice_32b_rx_flex_desc *eop_desc) { @@ -672,23 +657,23 @@ ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, if (!xdp_prog) goto exit; - ice_xdp_meta_set_desc(xdp, eop_desc); + xdp->desc = eop_desc; - act = bpf_prog_run_xdp(xdp_prog, xdp); + act = bpf_prog_run_xdp(xdp_prog, &xdp->base); switch (act) { case XDP_PASS: break; case XDP_TX: if (static_branch_unlikely(&ice_xdp_locking_key)) spin_lock(&xdp_ring->tx_lock); - ret = __ice_xmit_xdp_ring(xdp, xdp_ring, false); + ret = __ice_xmit_xdp_ring(&xdp->base, xdp_ring, false); if (static_branch_unlikely(&ice_xdp_locking_key)) spin_unlock(&xdp_ring->tx_lock); if (ret == ICE_XDP_CONSUMED) goto out_failure; break; case XDP_REDIRECT: - if (xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog)) + if (xdp_do_redirect(rx_ring->netdev, &xdp->base, xdp_prog)) goto out_failure; ret = ICE_XDP_REDIR; break; @@ -700,8 +685,10 @@ out_failure: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); fallthrough; case XDP_DROP: + libeth_xdp_return_buff(xdp); ret = ICE_XDP_CONSUMED; } + exit: return ret; } @@ -790,53 +777,6 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, } /** - * ice_alloc_mapped_page - recycle or make a new page - * @rx_ring: ring to use - * @bi: rx_buf struct to modify - * - * Returns true if the page was successfully allocated or - * reused. - */ -static bool -ice_alloc_mapped_page(struct ice_rx_ring *rx_ring, struct ice_rx_buf *bi) -{ - struct page *page = bi->page; - dma_addr_t dma; - - /* since we are recycling buffers we should seldom need to alloc */ - if (likely(page)) - return true; - - /* alloc new page for storage */ - page = dev_alloc_pages(ice_rx_pg_order(rx_ring)); - if (unlikely(!page)) { - rx_ring->ring_stats->rx_stats.alloc_page_failed++; - return false; - } - - /* map page for use */ - dma = dma_map_page_attrs(rx_ring->dev, page, 0, ice_rx_pg_size(rx_ring), - DMA_FROM_DEVICE, ICE_RX_DMA_ATTR); - - /* if mapping failed free memory back to system since - * there isn't much point in holding memory we can't use - */ - if (dma_mapping_error(rx_ring->dev, dma)) { - __free_pages(page, ice_rx_pg_order(rx_ring)); - rx_ring->ring_stats->rx_stats.alloc_page_failed++; - return false; - } - - bi->dma = dma; - bi->page = page; - bi->page_offset = rx_ring->rx_offset; - page_ref_add(page, USHRT_MAX - 1); - bi->pagecnt_bias = USHRT_MAX; - - return true; -} - -/** * ice_init_ctrl_rx_descs - Initialize Rx descriptors for control vsi. * @rx_ring: ring to init descriptors on * @count: number of descriptors to initialize @@ -882,9 +822,20 @@ void ice_init_ctrl_rx_descs(struct ice_rx_ring *rx_ring, u32 count) */ bool ice_alloc_rx_bufs(struct ice_rx_ring *rx_ring, unsigned int cleaned_count) { + const struct libeth_fq_fp hdr_fq = { + .pp = rx_ring->hdr_pp, + .fqes = rx_ring->hdr_fqes, + .truesize = rx_ring->hdr_truesize, + .count = rx_ring->count, + }; + const struct libeth_fq_fp fq = { + .pp = rx_ring->pp, + .fqes = rx_ring->rx_fqes, + .truesize = rx_ring->truesize, + .count = rx_ring->count, + }; union ice_32b_rx_flex_desc *rx_desc; u16 ntu = rx_ring->next_to_use; - struct ice_rx_buf *bi; /* do nothing if no valid netdev defined */ if (!rx_ring->netdev || !cleaned_count) @@ -892,30 +843,39 @@ bool ice_alloc_rx_bufs(struct ice_rx_ring *rx_ring, unsigned int cleaned_count) /* get the Rx descriptor and buffer based on next_to_use */ rx_desc = ICE_RX_DESC(rx_ring, ntu); - bi = &rx_ring->rx_buf[ntu]; do { - /* if we fail here, we have work remaining */ - if (!ice_alloc_mapped_page(rx_ring, bi)) - break; + dma_addr_t addr; - /* sync the buffer for use by the device */ - dma_sync_single_range_for_device(rx_ring->dev, bi->dma, - bi->page_offset, - rx_ring->rx_buf_len, - DMA_FROM_DEVICE); + addr = libeth_rx_alloc(&fq, ntu); + if (addr == DMA_MAPPING_ERROR) { + rx_ring->ring_stats->rx_stats.alloc_page_failed++; + break; + } /* Refresh the desc even if buffer_addrs didn't change * because each write-back erases this info. */ - rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset); + rx_desc->read.pkt_addr = cpu_to_le64(addr); + + if (!hdr_fq.pp) + goto next; + + addr = libeth_rx_alloc(&hdr_fq, ntu); + if (addr == DMA_MAPPING_ERROR) { + rx_ring->ring_stats->rx_stats.alloc_page_failed++; + + libeth_rx_recycle_slow(fq.fqes[ntu].netmem); + break; + } + + rx_desc->read.hdr_addr = cpu_to_le64(addr); +next: rx_desc++; - bi++; ntu++; if (unlikely(ntu == rx_ring->count)) { rx_desc = ICE_RX_DESC(rx_ring, 0); - bi = rx_ring->rx_buf; ntu = 0; } @@ -932,402 +892,6 @@ bool ice_alloc_rx_bufs(struct ice_rx_ring *rx_ring, unsigned int cleaned_count) } /** - * ice_rx_buf_adjust_pg_offset - Prepare Rx buffer for reuse - * @rx_buf: Rx buffer to adjust - * @size: Size of adjustment - * - * Update the offset within page so that Rx buf will be ready to be reused. - * For systems with PAGE_SIZE < 8192 this function will flip the page offset - * so the second half of page assigned to Rx buffer will be used, otherwise - * the offset is moved by "size" bytes - */ -static void -ice_rx_buf_adjust_pg_offset(struct ice_rx_buf *rx_buf, unsigned int size) -{ -#if (PAGE_SIZE < 8192) - /* flip page offset to other buffer */ - rx_buf->page_offset ^= size; -#else - /* move offset up to the next cache line */ - rx_buf->page_offset += size; -#endif -} - -/** - * ice_can_reuse_rx_page - Determine if page can be reused for another Rx - * @rx_buf: buffer containing the page - * - * If page is reusable, we have a green light for calling ice_reuse_rx_page, - * which will assign the current buffer to the buffer that next_to_alloc is - * pointing to; otherwise, the DMA mapping needs to be destroyed and - * page freed - */ -static bool -ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf) -{ - unsigned int pagecnt_bias = rx_buf->pagecnt_bias; - struct page *page = rx_buf->page; - - /* avoid re-using remote and pfmemalloc pages */ - if (!dev_page_is_reusable(page)) - return false; - - /* if we are only owner of page we can reuse it */ - if (unlikely(rx_buf->pgcnt - pagecnt_bias > 1)) - return false; -#if (PAGE_SIZE >= 8192) -#define ICE_LAST_OFFSET \ - (SKB_WITH_OVERHEAD(PAGE_SIZE) - ICE_RXBUF_3072) - if (rx_buf->page_offset > ICE_LAST_OFFSET) - return false; -#endif /* PAGE_SIZE >= 8192) */ - - /* If we have drained the page fragment pool we need to update - * the pagecnt_bias and page count so that we fully restock the - * number of references the driver holds. - */ - if (unlikely(pagecnt_bias == 1)) { - page_ref_add(page, USHRT_MAX - 1); - rx_buf->pagecnt_bias = USHRT_MAX; - } - - return true; -} - -/** - * ice_add_xdp_frag - Add contents of Rx buffer to xdp buf as a frag - * @rx_ring: Rx descriptor ring to transact packets on - * @xdp: xdp buff to place the data into - * @rx_buf: buffer containing page to add - * @size: packet length from rx_desc - * - * This function will add the data contained in rx_buf->page to the xdp buf. - * It will just attach the page as a frag. - */ -static int -ice_add_xdp_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, - struct ice_rx_buf *rx_buf, const unsigned int size) -{ - struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); - - if (!size) - return 0; - - if (!xdp_buff_has_frags(xdp)) { - sinfo->nr_frags = 0; - sinfo->xdp_frags_size = 0; - xdp_buff_set_frags_flag(xdp); - } - - if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) - return -ENOMEM; - - __skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, rx_buf->page, - rx_buf->page_offset, size); - sinfo->xdp_frags_size += size; - - if (page_is_pfmemalloc(rx_buf->page)) - xdp_buff_set_frag_pfmemalloc(xdp); - - return 0; -} - -/** - * ice_reuse_rx_page - page flip buffer and store it back on the ring - * @rx_ring: Rx descriptor ring to store buffers on - * @old_buf: donor buffer to have page reused - * - * Synchronizes page for reuse by the adapter - */ -static void -ice_reuse_rx_page(struct ice_rx_ring *rx_ring, struct ice_rx_buf *old_buf) -{ - u16 nta = rx_ring->next_to_alloc; - struct ice_rx_buf *new_buf; - - new_buf = &rx_ring->rx_buf[nta]; - - /* update, and store next to alloc */ - nta++; - rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; - - /* Transfer page from old buffer to new buffer. - * Move each member individually to avoid possible store - * forwarding stalls and unnecessary copy of skb. - */ - new_buf->dma = old_buf->dma; - new_buf->page = old_buf->page; - new_buf->page_offset = old_buf->page_offset; - new_buf->pagecnt_bias = old_buf->pagecnt_bias; -} - -/** - * ice_get_rx_buf - Fetch Rx buffer and synchronize data for use - * @rx_ring: Rx descriptor ring to transact packets on - * @size: size of buffer to add to skb - * @ntc: index of next to clean element - * - * This function will pull an Rx buffer from the ring and synchronize it - * for use by the CPU. - */ -static struct ice_rx_buf * -ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size, - const unsigned int ntc) -{ - struct ice_rx_buf *rx_buf; - - rx_buf = &rx_ring->rx_buf[ntc]; - prefetchw(rx_buf->page); - - if (!size) - return rx_buf; - /* we are reusing so sync this buffer for CPU use */ - dma_sync_single_range_for_cpu(rx_ring->dev, rx_buf->dma, - rx_buf->page_offset, size, - DMA_FROM_DEVICE); - - /* We have pulled a buffer for use, so decrement pagecnt_bias */ - rx_buf->pagecnt_bias--; - - return rx_buf; -} - -/** - * ice_get_pgcnts - grab page_count() for gathered fragments - * @rx_ring: Rx descriptor ring to store the page counts on - * @ntc: the next to clean element (not included in this frame!) - * - * This function is intended to be called right before running XDP - * program so that the page recycling mechanism will be able to take - * a correct decision regarding underlying pages; this is done in such - * way as XDP program can change the refcount of page - */ -static void ice_get_pgcnts(struct ice_rx_ring *rx_ring, unsigned int ntc) -{ - u32 idx = rx_ring->first_desc; - struct ice_rx_buf *rx_buf; - u32 cnt = rx_ring->count; - - while (idx != ntc) { - rx_buf = &rx_ring->rx_buf[idx]; - rx_buf->pgcnt = page_count(rx_buf->page); - - if (++idx == cnt) - idx = 0; - } -} - -/** - * ice_build_skb - Build skb around an existing buffer - * @rx_ring: Rx descriptor ring to transact packets on - * @xdp: xdp_buff pointing to the data - * - * This function builds an skb around an existing XDP buffer, taking care - * to set up the skb correctly and avoid any memcpy overhead. Driver has - * already combined frags (if any) to skb_shared_info. - */ -static struct sk_buff * -ice_build_skb(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) -{ - u8 metasize = xdp->data - xdp->data_meta; - struct skb_shared_info *sinfo = NULL; - unsigned int nr_frags; - struct sk_buff *skb; - - if (unlikely(xdp_buff_has_frags(xdp))) { - sinfo = xdp_get_shared_info_from_buff(xdp); - nr_frags = sinfo->nr_frags; - } - - /* Prefetch first cache line of first page. If xdp->data_meta - * is unused, this points exactly as xdp->data, otherwise we - * likely have a consumer accessing first few bytes of meta - * data, and then actual data. - */ - net_prefetch(xdp->data_meta); - /* build an skb around the page buffer */ - skb = napi_build_skb(xdp->data_hard_start, xdp->frame_sz); - if (unlikely(!skb)) - return NULL; - - /* must to record Rx queue, otherwise OS features such as - * symmetric queue won't work - */ - skb_record_rx_queue(skb, rx_ring->q_index); - - /* update pointers within the skb to store the data */ - skb_reserve(skb, xdp->data - xdp->data_hard_start); - __skb_put(skb, xdp->data_end - xdp->data); - if (metasize) - skb_metadata_set(skb, metasize); - - if (unlikely(xdp_buff_has_frags(xdp))) - xdp_update_skb_frags_info(skb, nr_frags, sinfo->xdp_frags_size, - nr_frags * xdp->frame_sz, - xdp_buff_get_skb_flags(xdp)); - - return skb; -} - -/** - * ice_construct_skb - Allocate skb and populate it - * @rx_ring: Rx descriptor ring to transact packets on - * @xdp: xdp_buff pointing to the data - * - * This function allocates an skb. It then populates it with the page - * data from the current receive descriptor, taking care to set up the - * skb correctly. - */ -static struct sk_buff * -ice_construct_skb(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) -{ - unsigned int size = xdp->data_end - xdp->data; - struct skb_shared_info *sinfo = NULL; - struct ice_rx_buf *rx_buf; - unsigned int nr_frags = 0; - unsigned int headlen; - struct sk_buff *skb; - - /* prefetch first cache line of first page */ - net_prefetch(xdp->data); - - if (unlikely(xdp_buff_has_frags(xdp))) { - sinfo = xdp_get_shared_info_from_buff(xdp); - nr_frags = sinfo->nr_frags; - } - - /* allocate a skb to store the frags */ - skb = napi_alloc_skb(&rx_ring->q_vector->napi, ICE_RX_HDR_SIZE); - if (unlikely(!skb)) - return NULL; - - rx_buf = &rx_ring->rx_buf[rx_ring->first_desc]; - skb_record_rx_queue(skb, rx_ring->q_index); - /* Determine available headroom for copy */ - headlen = size; - if (headlen > ICE_RX_HDR_SIZE) - headlen = eth_get_headlen(skb->dev, xdp->data, ICE_RX_HDR_SIZE); - - /* align pull length to size of long to optimize memcpy performance */ - memcpy(__skb_put(skb, headlen), xdp->data, ALIGN(headlen, - sizeof(long))); - - /* if we exhaust the linear part then add what is left as a frag */ - size -= headlen; - if (size) { - /* besides adding here a partial frag, we are going to add - * frags from xdp_buff, make sure there is enough space for - * them - */ - if (unlikely(nr_frags >= MAX_SKB_FRAGS - 1)) { - dev_kfree_skb(skb); - return NULL; - } - skb_add_rx_frag(skb, 0, rx_buf->page, - rx_buf->page_offset + headlen, size, - xdp->frame_sz); - } else { - /* buffer is unused, restore biased page count in Rx buffer; - * data was copied onto skb's linear part so there's no - * need for adjusting page offset and we can reuse this buffer - * as-is - */ - rx_buf->pagecnt_bias++; - } - - if (unlikely(xdp_buff_has_frags(xdp))) { - struct skb_shared_info *skinfo = skb_shinfo(skb); - - memcpy(&skinfo->frags[skinfo->nr_frags], &sinfo->frags[0], - sizeof(skb_frag_t) * nr_frags); - - xdp_update_skb_frags_info(skb, skinfo->nr_frags + nr_frags, - sinfo->xdp_frags_size, - nr_frags * xdp->frame_sz, - xdp_buff_get_skb_flags(xdp)); - } - - return skb; -} - -/** - * ice_put_rx_buf - Clean up used buffer and either recycle or free - * @rx_ring: Rx descriptor ring to transact packets on - * @rx_buf: Rx buffer to pull data from - * - * This function will clean up the contents of the rx_buf. It will either - * recycle the buffer or unmap it and free the associated resources. - */ -static void -ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf) -{ - if (!rx_buf) - return; - - if (ice_can_reuse_rx_page(rx_buf)) { - /* hand second half of page back to the ring */ - ice_reuse_rx_page(rx_ring, rx_buf); - } else { - /* we are not reusing the buffer so unmap it */ - dma_unmap_page_attrs(rx_ring->dev, rx_buf->dma, - ice_rx_pg_size(rx_ring), DMA_FROM_DEVICE, - ICE_RX_DMA_ATTR); - __page_frag_cache_drain(rx_buf->page, rx_buf->pagecnt_bias); - } - - /* clear contents of buffer_info */ - rx_buf->page = NULL; -} - -/** - * ice_put_rx_mbuf - ice_put_rx_buf() caller, for all buffers in frame - * @rx_ring: Rx ring with all the auxiliary data - * @xdp: XDP buffer carrying linear + frags part - * @ntc: the next to clean element (not included in this frame!) - * @verdict: return code from XDP program execution - * - * Called after XDP program is completed, or on error with verdict set to - * ICE_XDP_CONSUMED. - * - * Walk through buffers from first_desc to the end of the frame, releasing - * buffers and satisfying internal page recycle mechanism. The action depends - * on verdict from XDP program. - */ -static void ice_put_rx_mbuf(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, - u32 ntc, u32 verdict) -{ - u32 idx = rx_ring->first_desc; - u32 cnt = rx_ring->count; - struct ice_rx_buf *buf; - u32 xdp_frags = 0; - int i = 0; - - if (unlikely(xdp_buff_has_frags(xdp))) - xdp_frags = xdp_get_shared_info_from_buff(xdp)->nr_frags; - - while (idx != ntc) { - buf = &rx_ring->rx_buf[idx]; - if (++idx == cnt) - idx = 0; - - /* An XDP program could release fragments from the end of the - * buffer. For these, we need to keep the pagecnt_bias as-is. - * To do this, only adjust pagecnt_bias for fragments up to - * the total remaining after the XDP program has run. - */ - if (verdict != ICE_XDP_CONSUMED) - ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); - else if (i++ <= xdp_frags) - buf->pagecnt_bias++; - - ice_put_rx_buf(rx_ring, buf); - } - - xdp->data = NULL; - rx_ring->first_desc = ntc; -} - -/** * ice_clean_ctrl_rx_irq - Clean descriptors from flow director Rx ring * @rx_ring: Rx descriptor ring for ctrl_vsi to transact packets on * @@ -1361,9 +925,8 @@ void ice_clean_ctrl_rx_irq(struct ice_rx_ring *rx_ring) total_rx_pkts++; } - rx_ring->first_desc = ntc; rx_ring->next_to_clean = ntc; - ice_init_ctrl_rx_descs(rx_ring, ICE_RX_DESC_UNUSED(rx_ring)); + ice_init_ctrl_rx_descs(rx_ring, ICE_DESC_UNUSED(rx_ring)); } /** @@ -1381,16 +944,17 @@ void ice_clean_ctrl_rx_irq(struct ice_rx_ring *rx_ring) static int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) { unsigned int total_rx_bytes = 0, total_rx_pkts = 0; - unsigned int offset = rx_ring->rx_offset; - struct xdp_buff *xdp = &rx_ring->xdp; struct ice_tx_ring *xdp_ring = NULL; struct bpf_prog *xdp_prog = NULL; u32 ntc = rx_ring->next_to_clean; + LIBETH_XDP_ONSTACK_BUFF(xdp); u32 cached_ntu, xdp_verdict; u32 cnt = rx_ring->count; u32 xdp_xmit = 0; bool failure; + libeth_xdp_init_buff(xdp, &rx_ring->xdp, &rx_ring->xdp_rxq); + xdp_prog = READ_ONCE(rx_ring->xdp_prog); if (xdp_prog) { xdp_ring = rx_ring->xdp_ring; @@ -1400,19 +964,21 @@ static int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) /* start the loop to process Rx packets bounded by 'budget' */ while (likely(total_rx_pkts < (unsigned int)budget)) { union ice_32b_rx_flex_desc *rx_desc; - struct ice_rx_buf *rx_buf; + struct libeth_fqe *rx_buf; struct sk_buff *skb; unsigned int size; u16 stat_err_bits; u16 vlan_tci; + bool rxe; /* get the Rx desc from Rx ring based on 'next_to_clean' */ rx_desc = ICE_RX_DESC(rx_ring, ntc); - /* status_error_len will always be zero for unused descriptors - * because it's cleared in cleanup, and overlaps with hdr_addr - * which is always zero because packet split isn't used, if the - * hardware wrote DD then it will be non-zero + /* + * The DD bit will always be zero for unused descriptors + * because it's cleared in cleanup or when setting the DMA + * address of the header buffer, which never uses the DD bit. + * If the hardware wrote the descriptor, it will be non-zero. */ stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_DD_S); if (!ice_test_staterr(rx_desc->wb.status_error0, stat_err_bits)) @@ -1426,71 +992,65 @@ static int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) ice_trace(clean_rx_irq, rx_ring, rx_desc); + stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_HBO_S) | + BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S); + rxe = ice_test_staterr(rx_desc->wb.status_error0, + stat_err_bits); + + if (!rx_ring->hdr_pp) + goto payload; + + size = le16_get_bits(rx_desc->wb.hdr_len_sph_flex_flags1, + ICE_RX_FLEX_DESC_HDR_LEN_M); + if (unlikely(rxe)) + size = 0; + + rx_buf = &rx_ring->hdr_fqes[ntc]; + libeth_xdp_process_buff(xdp, rx_buf, size); + rx_buf->netmem = 0; + +payload: size = le16_to_cpu(rx_desc->wb.pkt_len) & ICE_RX_FLX_DESC_PKT_LEN_M; + if (unlikely(rxe)) + size = 0; /* retrieve a buffer from the ring */ - rx_buf = ice_get_rx_buf(rx_ring, size, ntc); + rx_buf = &rx_ring->rx_fqes[ntc]; + libeth_xdp_process_buff(xdp, rx_buf, size); - /* Increment ntc before calls to ice_put_rx_mbuf() */ if (++ntc == cnt) ntc = 0; - if (!xdp->data) { - void *hard_start; - - hard_start = page_address(rx_buf->page) + rx_buf->page_offset - - offset; - xdp_prepare_buff(xdp, hard_start, offset, size, !!offset); - xdp_buff_clear_frags_flag(xdp); - } else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) { - ice_put_rx_mbuf(rx_ring, xdp, ntc, ICE_XDP_CONSUMED); - break; - } - /* skip if it is NOP desc */ - if (ice_is_non_eop(rx_ring, rx_desc)) + if (ice_is_non_eop(rx_ring, rx_desc) || unlikely(!xdp->data)) continue; - ice_get_pgcnts(rx_ring, ntc); xdp_verdict = ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_desc); if (xdp_verdict == ICE_XDP_PASS) goto construct_skb; - total_rx_bytes += xdp_get_buff_len(xdp); - total_rx_pkts++; - ice_put_rx_mbuf(rx_ring, xdp, ntc, xdp_verdict); - xdp_xmit |= xdp_verdict & (ICE_XDP_TX | ICE_XDP_REDIR); + if (xdp_verdict & (ICE_XDP_TX | ICE_XDP_REDIR)) + xdp_xmit |= xdp_verdict; + total_rx_bytes += xdp_get_buff_len(&xdp->base); + total_rx_pkts++; + xdp->data = NULL; continue; + construct_skb: - if (likely(ice_ring_uses_build_skb(rx_ring))) - skb = ice_build_skb(rx_ring, xdp); - else - skb = ice_construct_skb(rx_ring, xdp); + skb = xdp_build_skb_from_buff(&xdp->base); + xdp->data = NULL; + /* exit if we failed to retrieve a buffer */ if (!skb) { + libeth_xdp_return_buff_slow(xdp); rx_ring->ring_stats->rx_stats.alloc_buf_failed++; - xdp_verdict = ICE_XDP_CONSUMED; - } - ice_put_rx_mbuf(rx_ring, xdp, ntc, xdp_verdict); - - if (!skb) - break; - - stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S); - if (unlikely(ice_test_staterr(rx_desc->wb.status_error0, - stat_err_bits))) { - dev_kfree_skb_any(skb); continue; } vlan_tci = ice_get_vlan_tci(rx_desc); - /* pad the skb if needed, to make a valid ethernet frame */ - if (eth_skb_pad(skb)) - continue; - /* probably a little skewed due to removing CRC */ total_rx_bytes += skb->len; @@ -1507,11 +1067,13 @@ construct_skb: rx_ring->next_to_clean = ntc; /* return up to cleaned_count buffers to hardware */ - failure = ice_alloc_rx_bufs(rx_ring, ICE_RX_DESC_UNUSED(rx_ring)); + failure = ice_alloc_rx_bufs(rx_ring, ICE_DESC_UNUSED(rx_ring)); if (xdp_xmit) ice_finalize_xdp_rx(xdp_ring, xdp_xmit, cached_ntu); + libeth_xdp_save_buff(&rx_ring->xdp, xdp); + if (rx_ring->ring_stats) ice_update_rx_ring_stats(rx_ring, total_rx_pkts, total_rx_bytes); diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index 841a07bfba54..e440c55d9e9f 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -4,6 +4,8 @@ #ifndef _ICE_TXRX_H_ #define _ICE_TXRX_H_ +#include <net/libeth/types.h> + #include "ice_type.h" #define ICE_DFLT_IRQ_WORK 256 @@ -27,72 +29,6 @@ #define ICE_MAX_TXQ_PER_TXQG 128 -/* Attempt to maximize the headroom available for incoming frames. We use a 2K - * buffer for MTUs <= 1500 and need 1536/1534 to store the data for the frame. - * This leaves us with 512 bytes of room. From that we need to deduct the - * space needed for the shared info and the padding needed to IP align the - * frame. - * - * Note: For cache line sizes 256 or larger this value is going to end - * up negative. In these cases we should fall back to the legacy - * receive path. - */ -#if (PAGE_SIZE < 8192) -#define ICE_2K_TOO_SMALL_WITH_PADDING \ - ((unsigned int)(NET_SKB_PAD + ICE_RXBUF_1536) > \ - SKB_WITH_OVERHEAD(ICE_RXBUF_2048)) - -/** - * ice_compute_pad - compute the padding - * @rx_buf_len: buffer length - * - * Figure out the size of half page based on given buffer length and - * then subtract the skb_shared_info followed by subtraction of the - * actual buffer length; this in turn results in the actual space that - * is left for padding usage - */ -static inline int ice_compute_pad(int rx_buf_len) -{ - int half_page_size; - - half_page_size = ALIGN(rx_buf_len, PAGE_SIZE / 2); - return SKB_WITH_OVERHEAD(half_page_size) - rx_buf_len; -} - -/** - * ice_skb_pad - determine the padding that we can supply - * - * Figure out the right Rx buffer size and based on that calculate the - * padding - */ -static inline int ice_skb_pad(void) -{ - int rx_buf_len; - - /* If a 2K buffer cannot handle a standard Ethernet frame then - * optimize padding for a 3K buffer instead of a 1.5K buffer. - * - * For a 3K buffer we need to add enough padding to allow for - * tailroom due to NET_IP_ALIGN possibly shifting us out of - * cache-line alignment. - */ - if (ICE_2K_TOO_SMALL_WITH_PADDING) - rx_buf_len = ICE_RXBUF_3072 + SKB_DATA_ALIGN(NET_IP_ALIGN); - else - rx_buf_len = ICE_RXBUF_1536; - - /* if needed make room for NET_IP_ALIGN */ - rx_buf_len -= NET_IP_ALIGN; - - return ice_compute_pad(rx_buf_len); -} - -#define ICE_SKB_PAD ice_skb_pad() -#else -#define ICE_2K_TOO_SMALL_WITH_PADDING false -#define ICE_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) -#endif - /* We are assuming that the cache line is always 64 Bytes here for ice. * In order to make sure that is a correct assumption there is a check in probe * to print a warning if the read from GLPCI_CNF2 tells us that the cache line @@ -112,10 +48,6 @@ static inline int ice_skb_pad(void) (u16)((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \ (R)->next_to_clean - (R)->next_to_use - 1) -#define ICE_RX_DESC_UNUSED(R) \ - ((((R)->first_desc > (R)->next_to_use) ? 0 : (R)->count) + \ - (R)->first_desc - (R)->next_to_use - 1) - #define ICE_RING_QUARTER(R) ((R)->count >> 2) #define ICE_TX_FLAGS_TSO BIT(0) @@ -197,14 +129,6 @@ struct ice_tx_offload_params { u8 header_len; }; -struct ice_rx_buf { - dma_addr_t dma; - struct page *page; - unsigned int page_offset; - unsigned int pgcnt; - unsigned int pagecnt_bias; -}; - struct ice_q_stats { u64 pkts; u64 bytes; @@ -262,15 +186,6 @@ struct ice_pkt_ctx { __be16 vlan_proto; }; -struct ice_xdp_buff { - struct xdp_buff xdp_buff; - const union ice_32b_rx_flex_desc *eop_desc; - const struct ice_pkt_ctx *pkt_ctx; -}; - -/* Required for compatibility with xdp_buffs from xsk_pool */ -static_assert(offsetof(struct ice_xdp_buff, xdp_buff) == 0); - /* indices into GLINT_ITR registers */ #define ICE_RX_ITR ICE_IDX_ITR0 #define ICE_TX_ITR ICE_IDX_ITR1 @@ -323,7 +238,7 @@ struct ice_tstamp_ring { struct ice_rx_ring { /* CL1 - 1st cacheline starts here */ void *desc; /* Descriptor ring memory */ - struct device *dev; /* Used for DMA mapping */ + struct page_pool *pp; struct net_device *netdev; /* netdev ring maps to */ struct ice_vsi *vsi; /* Backreference to associated VSI */ struct ice_q_vector *q_vector; /* Backreference to associated vector */ @@ -335,14 +250,19 @@ struct ice_rx_ring { u16 next_to_alloc; union { - struct ice_rx_buf *rx_buf; + struct libeth_fqe *rx_fqes; struct xdp_buff **xdp_buf; }; + /* CL2 - 2nd cacheline starts here */ + struct libeth_fqe *hdr_fqes; + struct page_pool *hdr_pp; + union { - struct ice_xdp_buff xdp_ext; - struct xdp_buff xdp; + struct libeth_xdp_buff_stash xdp; + struct libeth_xdp_buff *xsk; }; + /* CL3 - 3rd cacheline starts here */ union { struct ice_pkt_ctx pkt_ctx; @@ -352,12 +272,13 @@ struct ice_rx_ring { }; }; struct bpf_prog *xdp_prog; - u16 rx_offset; /* used in interrupt processing */ u16 next_to_use; u16 next_to_clean; - u16 first_desc; + + u32 hdr_truesize; + u32 truesize; /* stats structs */ struct ice_ring_stats *ring_stats; @@ -368,12 +289,11 @@ struct ice_rx_ring { struct ice_tx_ring *xdp_ring; struct ice_rx_ring *next; /* pointer to next ring in q_vector */ struct xsk_buff_pool *xsk_pool; - u16 max_frame; + u16 rx_hdr_len; u16 rx_buf_len; dma_addr_t dma; /* physical address of ring */ u8 dcb_tc; /* Traffic class of ring */ u8 ptp_rx; -#define ICE_RX_FLAGS_RING_BUILD_SKB BIT(1) #define ICE_RX_FLAGS_CRC_STRIP_DIS BIT(2) #define ICE_RX_FLAGS_MULTIDEV BIT(3) #define ICE_RX_FLAGS_RING_GCS BIT(4) @@ -422,21 +342,6 @@ struct ice_tx_ring { u16 quanta_prof_id; } ____cacheline_internodealigned_in_smp; -static inline bool ice_ring_uses_build_skb(struct ice_rx_ring *ring) -{ - return !!(ring->flags & ICE_RX_FLAGS_RING_BUILD_SKB); -} - -static inline void ice_set_ring_build_skb_ena(struct ice_rx_ring *ring) -{ - ring->flags |= ICE_RX_FLAGS_RING_BUILD_SKB; -} - -static inline void ice_clear_ring_build_skb_ena(struct ice_rx_ring *ring) -{ - ring->flags &= ~ICE_RX_FLAGS_RING_BUILD_SKB; -} - static inline bool ice_ring_ch_enabled(struct ice_tx_ring *ring) { return !!ring->ch; @@ -491,18 +396,13 @@ struct ice_coalesce_stored { static inline unsigned int ice_rx_pg_order(struct ice_rx_ring *ring) { -#if (PAGE_SIZE < 8192) - if (ring->rx_buf_len > (PAGE_SIZE / 2)) - return 1; -#endif return 0; } -#define ice_rx_pg_size(_ring) (PAGE_SIZE << ice_rx_pg_order(_ring)) - union ice_32b_rx_flex_desc; void ice_init_ctrl_rx_descs(struct ice_rx_ring *rx_ring, u32 num_descs); +void ice_rxq_pp_destroy(struct ice_rx_ring *rq); bool ice_alloc_rx_bufs(struct ice_rx_ring *rxr, unsigned int cleaned_count); netdev_tx_t ice_start_xmit(struct sk_buff *skb, struct net_device *netdev); u16 diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c index 45cfaabc41cb..956da38d63b0 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c @@ -3,6 +3,7 @@ #include <linux/filter.h> #include <linux/net/intel/libie/rx.h> +#include <net/libeth/xdp.h> #include "ice_txrx_lib.h" #include "ice_eswitch.h" @@ -230,9 +231,12 @@ ice_process_skb_fields(struct ice_rx_ring *rx_ring, if (ice_is_port_repr_netdev(netdev)) ice_repr_inc_rx_stats(netdev, skb->len); + + /* __skb_push() is needed because xdp_build_skb_from_buff() + * calls eth_type_trans() + */ + __skb_push(skb, ETH_HLEN); skb->protocol = eth_type_trans(skb, netdev); - } else { - skb->protocol = eth_type_trans(skb, rx_ring->netdev); } ice_rx_csum(rx_ring, skb, rx_desc, ptype); @@ -270,19 +274,18 @@ static void ice_clean_xdp_tx_buf(struct device *dev, struct ice_tx_buf *tx_buf, struct xdp_frame_bulk *bq) { - dma_unmap_single(dev, dma_unmap_addr(tx_buf, dma), - dma_unmap_len(tx_buf, len), DMA_TO_DEVICE); - dma_unmap_len_set(tx_buf, len, 0); - switch (tx_buf->type) { case ICE_TX_BUF_XDP_TX: - page_frag_free(tx_buf->raw_buf); + libeth_xdp_return_va(tx_buf->raw_buf, true); break; case ICE_TX_BUF_XDP_XMIT: + dma_unmap_single(dev, dma_unmap_addr(tx_buf, dma), + dma_unmap_len(tx_buf, len), DMA_TO_DEVICE); xdp_return_frame_bulk(tx_buf->xdpf, bq); break; } + dma_unmap_len_set(tx_buf, len, 0); tx_buf->type = ICE_TX_BUF_EMPTY; } @@ -377,9 +380,11 @@ int __ice_xmit_xdp_ring(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring, struct ice_tx_buf *tx_buf; u32 cnt = xdp_ring->count; void *data = xdp->data; + struct page *page; u32 nr_frags = 0; u32 free_space; u32 frag = 0; + u32 offset; free_space = ICE_DESC_UNUSED(xdp_ring); if (free_space < ICE_RING_QUARTER(xdp_ring)) @@ -399,24 +404,28 @@ int __ice_xmit_xdp_ring(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring, tx_head = &xdp_ring->tx_buf[ntu]; tx_buf = tx_head; + page = virt_to_page(data); + offset = offset_in_page(xdp->data); + for (;;) { dma_addr_t dma; - dma = dma_map_single(dev, data, size, DMA_TO_DEVICE); - if (dma_mapping_error(dev, dma)) - goto dma_unmap; - - /* record length, and DMA address */ - dma_unmap_len_set(tx_buf, len, size); - dma_unmap_addr_set(tx_buf, dma, dma); - if (frame) { + dma = dma_map_single(dev, data, size, DMA_TO_DEVICE); + if (dma_mapping_error(dev, dma)) + goto dma_unmap; tx_buf->type = ICE_TX_BUF_FRAG; } else { + dma = page_pool_get_dma_addr(page) + offset; + dma_sync_single_for_device(dev, dma, size, DMA_BIDIRECTIONAL); tx_buf->type = ICE_TX_BUF_XDP_TX; tx_buf->raw_buf = data; } + /* record length, and DMA address */ + dma_unmap_len_set(tx_buf, len, size); + dma_unmap_addr_set(tx_buf, dma, dma); + tx_desc->buf_addr = cpu_to_le64(dma); tx_desc->cmd_type_offset_bsz = ice_build_ctob(0, 0, size, 0); @@ -430,6 +439,8 @@ int __ice_xmit_xdp_ring(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring, tx_desc = ICE_TX_DESC(xdp_ring, ntu); tx_buf = &xdp_ring->tx_buf[ntu]; + page = skb_frag_page(&sinfo->frags[frag]); + offset = skb_frag_off(&sinfo->frags[frag]); data = skb_frag_address(&sinfo->frags[frag]); size = skb_frag_size(&sinfo->frags[frag]); frag++; @@ -514,10 +525,13 @@ void ice_finalize_xdp_rx(struct ice_tx_ring *xdp_ring, unsigned int xdp_res, */ static int ice_xdp_rx_hw_ts(const struct xdp_md *ctx, u64 *ts_ns) { - const struct ice_xdp_buff *xdp_ext = (void *)ctx; + const struct libeth_xdp_buff *xdp_ext = (void *)ctx; + struct ice_rx_ring *rx_ring; - *ts_ns = ice_ptp_get_rx_hwts(xdp_ext->eop_desc, - xdp_ext->pkt_ctx); + rx_ring = libeth_xdp_buff_to_rq(xdp_ext, typeof(*rx_ring), xdp_rxq); + + *ts_ns = ice_ptp_get_rx_hwts(xdp_ext->desc, + &rx_ring->pkt_ctx); if (!*ts_ns) return -ENODATA; @@ -545,10 +559,10 @@ ice_xdp_rx_hash_type(const union ice_32b_rx_flex_desc *eop_desc) static int ice_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash, enum xdp_rss_hash_type *rss_type) { - const struct ice_xdp_buff *xdp_ext = (void *)ctx; + const struct libeth_xdp_buff *xdp_ext = (void *)ctx; - *hash = ice_get_rx_hash(xdp_ext->eop_desc); - *rss_type = ice_xdp_rx_hash_type(xdp_ext->eop_desc); + *hash = ice_get_rx_hash(xdp_ext->desc); + *rss_type = ice_xdp_rx_hash_type(xdp_ext->desc); if (!likely(*hash)) return -ENODATA; @@ -567,13 +581,16 @@ static int ice_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash, static int ice_xdp_rx_vlan_tag(const struct xdp_md *ctx, __be16 *vlan_proto, u16 *vlan_tci) { - const struct ice_xdp_buff *xdp_ext = (void *)ctx; + const struct libeth_xdp_buff *xdp_ext = (void *)ctx; + struct ice_rx_ring *rx_ring; + + rx_ring = libeth_xdp_buff_to_rq(xdp_ext, typeof(*rx_ring), xdp_rxq); - *vlan_proto = xdp_ext->pkt_ctx->vlan_proto; + *vlan_proto = rx_ring->pkt_ctx.vlan_proto; if (!*vlan_proto) return -ENODATA; - *vlan_tci = ice_get_vlan_tci(xdp_ext->eop_desc); + *vlan_tci = ice_get_vlan_tci(xdp_ext->desc); if (!*vlan_tci) return -ENODATA; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h index 99717730f21a..6a3f10f7a53f 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h @@ -135,13 +135,4 @@ ice_process_skb_fields(struct ice_rx_ring *rx_ring, void ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tci); -static inline void -ice_xdp_meta_set_desc(struct xdp_buff *xdp, - union ice_32b_rx_flex_desc *eop_desc) -{ - struct ice_xdp_buff *xdp_ext = container_of(xdp, struct ice_xdp_buff, - xdp_buff); - - xdp_ext->eop_desc = eop_desc; -} #endif /* !_ICE_TXRX_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index b0a1b67071c5..6a2ec8389a8f 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -1063,6 +1063,7 @@ struct ice_hw_port_stats { u64 error_bytes; /* errbc */ u64 mac_local_faults; /* mlfc */ u64 mac_remote_faults; /* mrfc */ + u64 rx_len_errors; /* rlec */ u64 link_xon_rx; /* lxonrxc */ u64 link_xoff_rx; /* lxoffrxc */ u64 link_xon_tx; /* lxontxc */ diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 575fd48f485f..989ff1fd9110 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -3,6 +3,7 @@ #include <linux/bpf_trace.h> #include <linux/unroll.h> +#include <net/libeth/xdp.h> #include <net/xdp_sock_drv.h> #include <net/xdp.h> #include "ice.h" @@ -169,50 +170,18 @@ ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) * If allocation was successful, substitute buffer with allocated one. * Returns 0 on success, negative on failure */ -static int +int ice_realloc_rx_xdp_bufs(struct ice_rx_ring *rx_ring, bool pool_present) { - size_t elem_size = pool_present ? sizeof(*rx_ring->xdp_buf) : - sizeof(*rx_ring->rx_buf); - void *sw_ring = kcalloc(rx_ring->count, elem_size, GFP_KERNEL); - - if (!sw_ring) - return -ENOMEM; - if (pool_present) { - kfree(rx_ring->rx_buf); - rx_ring->rx_buf = NULL; - rx_ring->xdp_buf = sw_ring; + rx_ring->xdp_buf = kcalloc(rx_ring->count, + sizeof(*rx_ring->xdp_buf), + GFP_KERNEL); + if (!rx_ring->xdp_buf) + return -ENOMEM; } else { kfree(rx_ring->xdp_buf); rx_ring->xdp_buf = NULL; - rx_ring->rx_buf = sw_ring; - } - - return 0; -} - -/** - * ice_realloc_zc_buf - reallocate XDP ZC queue pairs - * @vsi: Current VSI - * @zc: is zero copy set - * - * Reallocate buffer for rx_rings that might be used by XSK. - * XDP requires more memory, than rx_buf provides. - * Returns 0 on success, negative on failure - */ -int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc) -{ - struct ice_rx_ring *rx_ring; - uint i; - - ice_for_each_rxq(vsi, i) { - rx_ring = vsi->rx_rings[i]; - if (!rx_ring->xsk_pool) - continue; - - if (ice_realloc_rx_xdp_bufs(rx_ring, zc)) - return -ENOMEM; } return 0; @@ -228,6 +197,7 @@ int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc) */ int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) { + struct ice_rx_ring *rx_ring = vsi->rx_rings[qid]; bool if_running, pool_present = !!pool; int ret = 0, pool_failure = 0; @@ -241,8 +211,6 @@ int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) ice_is_xdp_ena_vsi(vsi); if (if_running) { - struct ice_rx_ring *rx_ring = vsi->rx_rings[qid]; - ret = ice_qp_dis(vsi, qid); if (ret) { netdev_err(vsi->netdev, "ice_qp_dis error = %d\n", ret); @@ -303,11 +271,6 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp, rx_desc->read.pkt_addr = cpu_to_le64(dma); rx_desc->wb.status_error0 = 0; - /* Put private info that changes on a per-packet basis - * into xdp_buff_xsk->cb. - */ - ice_xdp_meta_set_desc(*xdp, rx_desc); - rx_desc++; xdp++; } @@ -393,69 +356,6 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, } /** - * ice_construct_skb_zc - Create an sk_buff from zero-copy buffer - * @rx_ring: Rx ring - * @xdp: Pointer to XDP buffer - * - * This function allocates a new skb from a zero-copy Rx buffer. - * - * Returns the skb on success, NULL on failure. - */ -static struct sk_buff * -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); - if (unlikely(!skb)) - return NULL; - - memcpy(__skb_put(skb, totalsize), xdp->data_meta, - ALIGN(totalsize, sizeof(long))); - - if (metasize) { - skb_metadata_set(skb, metasize); - __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; -} - -/** * ice_clean_xdp_irq_zc - produce AF_XDP descriptors to CQ * @xdp_ring: XDP Tx ring * @xsk_pool: AF_XDP buffer pool pointer @@ -669,10 +569,10 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, struct xsk_buff_pool *xsk_pool, int budget) { + struct xdp_buff *first = (struct xdp_buff *)rx_ring->xsk; unsigned int total_rx_bytes = 0, total_rx_packets = 0; 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; @@ -686,9 +586,6 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, 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; @@ -724,15 +621,17 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, first = xdp; } else if (likely(size) && !xsk_buff_add_frag(first, xdp)) { xsk_buff_free(first); - break; + first = NULL; } if (++ntc == cnt) ntc = 0; - if (ice_is_non_eop(rx_ring, rx_desc)) + if (ice_is_non_eop(rx_ring, rx_desc) || unlikely(!first)) continue; + ((struct libeth_xdp_buff *)first)->desc = rx_desc; + xdp_res = ice_run_xdp_zc(rx_ring, first, xdp_prog, xdp_ring, xsk_pool); if (likely(xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))) { @@ -740,7 +639,6 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, } 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(first); @@ -752,24 +650,20 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, total_rx_packets++; first = NULL; - rx_ring->first_desc = ntc; continue; construct_skb: /* XDP_PASS path */ - skb = ice_construct_skb_zc(rx_ring, first); + skb = xdp_build_skb_from_zc(first); if (!skb) { + xsk_buff_free(first); + first = NULL; + rx_ring->ring_stats->rx_stats.alloc_buf_failed++; - break; + continue; } first = NULL; - rx_ring->first_desc = ntc; - - if (eth_skb_pad(skb)) { - skb = NULL; - continue; - } total_rx_bytes += skb->len; total_rx_packets++; @@ -781,7 +675,9 @@ construct_skb: } rx_ring->next_to_clean = ntc; - entries_to_alloc = ICE_RX_DESC_UNUSED(rx_ring); + rx_ring->xsk = (struct libeth_xdp_buff *)first; + + entries_to_alloc = ICE_DESC_UNUSED(rx_ring); if (entries_to_alloc > ICE_RING_QUARTER(rx_ring)) failure |= !ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, entries_to_alloc); diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h index 600cbeeaa203..5275fcedc9e1 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.h +++ b/drivers/net/ethernet/intel/ice/ice_xsk.h @@ -22,7 +22,7 @@ bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi); void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring); void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring); bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, struct xsk_buff_pool *xsk_pool); -int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc); +int ice_realloc_rx_xdp_bufs(struct ice_rx_ring *rx_ring, bool pool_present); void ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector, u16 qid); void ice_qvec_toggle_napi(struct ice_vsi *vsi, struct ice_q_vector *q_vector, @@ -77,8 +77,8 @@ static inline void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring) { } static inline void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring) { } static inline int -ice_realloc_zc_buf(struct ice_vsi __always_unused *vsi, - bool __always_unused zc) +ice_realloc_rx_xdp_bufs(struct ice_rx_ring *rx_ring, + bool __always_unused pool_present) { return 0; } diff --git a/drivers/net/ethernet/intel/ice/virt/queues.c b/drivers/net/ethernet/intel/ice/virt/queues.c index 370f6ec2a374..7928f4e8e788 100644 --- a/drivers/net/ethernet/intel/ice/virt/queues.c +++ b/drivers/net/ethernet/intel/ice/virt/queues.c @@ -842,18 +842,17 @@ int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) (qpi->rxq.databuffer_size > ((16 * 1024) - 128) || qpi->rxq.databuffer_size < 1024)) goto error_param; - ring->rx_buf_len = qpi->rxq.databuffer_size; if (qpi->rxq.max_pkt_size > max_frame_size || qpi->rxq.max_pkt_size < 64) goto error_param; - ring->max_frame = qpi->rxq.max_pkt_size; + vsi->max_frame = qpi->rxq.max_pkt_size; /* add space for the port VLAN since the VF driver is * not expected to account for it in the MTU * calculation */ if (ice_vf_is_port_vlan_ena(vf)) - ring->max_frame += VLAN_HLEN; + vsi->max_frame += VLAN_HLEN; if (ice_vsi_cfg_single_rxq(vsi, q_idx)) { dev_warn(ice_pf_to_dev(pf), "VF-%d failed to configure RX queue %d\n", diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h index ca4da0c89979..50fa7be0c00d 100644 --- a/drivers/net/ethernet/intel/idpf/idpf.h +++ b/drivers/net/ethernet/intel/idpf/idpf.h @@ -735,12 +735,10 @@ static inline bool idpf_is_rdma_cap_ena(struct idpf_adapter *adapter) #define IDPF_CAP_RSS (\ VIRTCHNL2_FLOW_IPV4_TCP |\ - VIRTCHNL2_FLOW_IPV4_TCP |\ VIRTCHNL2_FLOW_IPV4_UDP |\ VIRTCHNL2_FLOW_IPV4_SCTP |\ VIRTCHNL2_FLOW_IPV4_OTHER |\ VIRTCHNL2_FLOW_IPV6_TCP |\ - VIRTCHNL2_FLOW_IPV6_TCP |\ VIRTCHNL2_FLOW_IPV6_UDP |\ VIRTCHNL2_FLOW_IPV6_SCTP |\ VIRTCHNL2_FLOW_IPV6_OTHER) diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 61dfcd8cb370..ac57212ab02b 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -1235,7 +1235,7 @@ static int igbvf_vlan_rx_add_vid(struct net_device *netdev, spin_lock_bh(&hw->mbx_lock); if (hw->mac.ops.set_vfta(hw, vid, true)) { - dev_warn(&adapter->pdev->dev, "Vlan id %d\n is not added", vid); + dev_warn(&adapter->pdev->dev, "Vlan id %d is not added\n", vid); spin_unlock_bh(&hw->mbx_lock); return -EINVAL; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c index d5b1b974b4a3..3069b583fd81 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c @@ -198,7 +198,7 @@ static int prot_autoc_read_82599(struct ixgbe_hw *hw, bool *locked, * @hw: pointer to hardware structure * @autoc: value to write to AUTOC * @locked: bool to indicate whether the SW/FW lock was already taken by - * previous proc_autoc_read_82599. + * previous prot_autoc_read_82599. * * This part (82599) may need to hold a the SW/FW lock around all writes to * AUTOC. Likewise after a write we need to do a pipeline reset. @@ -1622,7 +1622,7 @@ int ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw, break; } - /* store source and destination IP masks (big-enian) */ + /* store source and destination IP masks (big-endian) */ IXGBE_WRITE_REG_BE32(hw, IXGBE_FDIRSIP4M, ~input_mask->formatted.src_ip[0]); IXGBE_WRITE_REG_BE32(hw, IXGBE_FDIRDIP4M, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c index 170a29d162c6..a1d04914fbbc 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -318,7 +318,7 @@ static int ixgbe_xdp_queues(struct ixgbe_adapter *adapter) * ixgbe_set_dcb_sriov_queues: Allocate queues for SR-IOV devices w/ DCB * @adapter: board private structure to initialize * - * When SR-IOV (Single Root IO Virtualiztion) is enabled, allocate queues + * When SR-IOV (Single Root IO Virtualization) is enabled, allocate queues * and VM pools where appropriate. Also assign queues based on DCB * priorities and map accordingly.. * @@ -492,7 +492,7 @@ static bool ixgbe_set_dcb_queues(struct ixgbe_adapter *adapter) * ixgbe_set_sriov_queues - Allocate queues for SR-IOV devices * @adapter: board private structure to initialize * - * When SR-IOV (Single Root IO Virtualiztion) is enabled, allocate queues + * When SR-IOV (Single Root IO Virtualization) is enabled, allocate queues * and VM pools where appropriate. If RSS is available, then also try and * enable RSS and map accordingly. * |