diff options
Diffstat (limited to 'drivers/net/ethernet/intel/ice/ice_lib.c')
| -rw-r--r-- | drivers/net/ethernet/intel/ice/ice_lib.c | 2123 |
1 files changed, 841 insertions, 1282 deletions
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index a596e07b3ce9..15621707fbf8 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -7,7 +7,7 @@ #include "ice_lib.h" #include "ice_fltr.h" #include "ice_dcb_lib.h" -#include "ice_devlink.h" +#include "ice_type.h" #include "ice_vsi_vlan_ops.h" /** @@ -21,14 +21,14 @@ const char *ice_vsi_type_str(enum ice_vsi_type vsi_type) return "ICE_VSI_PF"; case ICE_VSI_VF: return "ICE_VSI_VF"; + case ICE_VSI_SF: + return "ICE_VSI_SF"; case ICE_VSI_CTRL: return "ICE_VSI_CTRL"; case ICE_VSI_CHNL: return "ICE_VSI_CHNL"; case ICE_VSI_LB: return "ICE_VSI_LB"; - case ICE_VSI_SWITCHDEV_CTRL: - return "ICE_VSI_SWITCHDEV_CTRL"; default: return "unknown"; } @@ -117,14 +117,8 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi) if (!vsi->q_vectors) goto err_vectors; - vsi->af_xdp_zc_qps = bitmap_zalloc(max_t(int, vsi->alloc_txq, vsi->alloc_rxq), GFP_KERNEL); - if (!vsi->af_xdp_zc_qps) - goto err_zc_qps; - return 0; -err_zc_qps: - devm_kfree(dev, vsi->q_vectors); err_vectors: devm_kfree(dev, vsi->rxq_map); err_rxq_map: @@ -144,7 +138,7 @@ static void ice_vsi_set_num_desc(struct ice_vsi *vsi) { switch (vsi->type) { case ICE_VSI_PF: - case ICE_VSI_SWITCHDEV_CTRL: + case ICE_VSI_SF: case ICE_VSI_CTRL: case ICE_VSI_LB: /* a user could change the values of num_[tr]x_desc using @@ -163,17 +157,27 @@ static void ice_vsi_set_num_desc(struct ice_vsi *vsi) } } +static u16 ice_get_rxq_count(struct ice_pf *pf) +{ + return min(ice_get_avail_rxq_count(pf), num_online_cpus()); +} + +static u16 ice_get_txq_count(struct ice_pf *pf) +{ + return min(ice_get_avail_txq_count(pf), num_online_cpus()); +} + /** * ice_vsi_set_num_qs - Set number of queues, descriptors and vectors for a VSI * @vsi: the VSI being configured - * @vf: the VF associated with this VSI, if any * * Return 0 on success and a negative value on error */ -static void ice_vsi_set_num_qs(struct ice_vsi *vsi, struct ice_vf *vf) +static void ice_vsi_set_num_qs(struct ice_vsi *vsi) { enum ice_vsi_type vsi_type = vsi->type; struct ice_pf *pf = vsi->back; + struct ice_vf *vf = vsi->vf; if (WARN_ON(vsi_type == ICE_VSI_VF && !vf)) return; @@ -184,9 +188,7 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi, struct ice_vf *vf) vsi->alloc_txq = vsi->req_txq; vsi->num_txq = vsi->req_txq; } else { - vsi->alloc_txq = min3(pf->num_lan_msix, - ice_get_avail_txq_count(pf), - (u16)num_online_cpus()); + vsi->alloc_txq = ice_get_txq_count(pf); } pf->num_lan_tx = vsi->alloc_txq; @@ -199,25 +201,19 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi, struct ice_vf *vf) vsi->alloc_rxq = vsi->req_rxq; vsi->num_rxq = vsi->req_rxq; } else { - vsi->alloc_rxq = min3(pf->num_lan_msix, - ice_get_avail_rxq_count(pf), - (u16)num_online_cpus()); + vsi->alloc_rxq = ice_get_rxq_count(pf); } } pf->num_lan_rx = vsi->alloc_rxq; - vsi->num_q_vectors = min_t(int, pf->num_lan_msix, - max_t(int, vsi->alloc_rxq, - vsi->alloc_txq)); + vsi->num_q_vectors = max(vsi->alloc_rxq, vsi->alloc_txq); break; - case ICE_VSI_SWITCHDEV_CTRL: - /* The number of queues for ctrl VSI is equal to number of VFs. - * Each ring is associated to the corresponding VF_PR netdev. - */ - vsi->alloc_txq = ice_get_num_vfs(pf); - vsi->alloc_rxq = vsi->alloc_txq; + case ICE_VSI_SF: + vsi->alloc_txq = 1; + vsi->alloc_rxq = 1; vsi->num_q_vectors = 1; + vsi->irq_dyn_alloc = true; break; case ICE_VSI_VF: if (vf->num_req_qs) @@ -229,7 +225,7 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi, struct ice_vf *vf) * of queues vectors, subtract 1 (ICE_NONQ_VECS_VF) from the * original vector count */ - vsi->num_q_vectors = pf->vfs.num_msix_per - ICE_NONQ_VECS_VF; + vsi->num_q_vectors = vf->num_msix - ICE_NONQ_VECS_VF; break; case ICE_VSI_CTRL: vsi->alloc_txq = 1; @@ -282,15 +278,16 @@ static int ice_get_free_slot(void *array, int size, int curr) } /** - * ice_vsi_delete - delete a VSI from the switch + * ice_vsi_delete_from_hw - delete a VSI from the switch * @vsi: pointer to VSI being removed */ -void ice_vsi_delete(struct ice_vsi *vsi) +static void ice_vsi_delete_from_hw(struct ice_vsi *vsi) { struct ice_pf *pf = vsi->back; struct ice_vsi_ctx *ctxt; int status; + ice_fltr_remove_all(vsi); ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); if (!ctxt) return; @@ -320,75 +317,159 @@ static void ice_vsi_free_arrays(struct ice_vsi *vsi) dev = ice_pf_to_dev(pf); - if (vsi->af_xdp_zc_qps) { - bitmap_free(vsi->af_xdp_zc_qps); - vsi->af_xdp_zc_qps = NULL; - } /* free the ring and vector containers */ - if (vsi->q_vectors) { - devm_kfree(dev, vsi->q_vectors); - vsi->q_vectors = NULL; - } - if (vsi->tx_rings) { - devm_kfree(dev, vsi->tx_rings); - vsi->tx_rings = NULL; + devm_kfree(dev, vsi->q_vectors); + vsi->q_vectors = NULL; + devm_kfree(dev, vsi->tx_rings); + vsi->tx_rings = NULL; + devm_kfree(dev, vsi->rx_rings); + vsi->rx_rings = NULL; + devm_kfree(dev, vsi->txq_map); + vsi->txq_map = NULL; + devm_kfree(dev, vsi->rxq_map); + vsi->rxq_map = NULL; +} + +/** + * ice_vsi_free_stats - Free the ring statistics structures + * @vsi: VSI pointer + */ +static void ice_vsi_free_stats(struct ice_vsi *vsi) +{ + struct ice_vsi_stats *vsi_stat; + struct ice_pf *pf = vsi->back; + int i; + + if (vsi->type == ICE_VSI_CHNL) + return; + if (!pf->vsi_stats) + return; + + vsi_stat = pf->vsi_stats[vsi->idx]; + if (!vsi_stat) + return; + + ice_for_each_alloc_txq(vsi, i) { + if (vsi_stat->tx_ring_stats[i]) { + kfree_rcu(vsi_stat->tx_ring_stats[i], rcu); + WRITE_ONCE(vsi_stat->tx_ring_stats[i], NULL); + } } - if (vsi->rx_rings) { - devm_kfree(dev, vsi->rx_rings); - vsi->rx_rings = NULL; + + ice_for_each_alloc_rxq(vsi, i) { + if (vsi_stat->rx_ring_stats[i]) { + kfree_rcu(vsi_stat->rx_ring_stats[i], rcu); + WRITE_ONCE(vsi_stat->rx_ring_stats[i], NULL); + } } - if (vsi->txq_map) { - devm_kfree(dev, vsi->txq_map); - vsi->txq_map = NULL; + + kfree(vsi_stat->tx_ring_stats); + kfree(vsi_stat->rx_ring_stats); + kfree(vsi_stat); + pf->vsi_stats[vsi->idx] = NULL; +} + +/** + * ice_vsi_alloc_ring_stats - Allocates Tx and Rx ring stats for the VSI + * @vsi: VSI which is having stats allocated + */ +static int ice_vsi_alloc_ring_stats(struct ice_vsi *vsi) +{ + struct ice_ring_stats **tx_ring_stats; + struct ice_ring_stats **rx_ring_stats; + struct ice_vsi_stats *vsi_stats; + struct ice_pf *pf = vsi->back; + u16 i; + + vsi_stats = pf->vsi_stats[vsi->idx]; + tx_ring_stats = vsi_stats->tx_ring_stats; + rx_ring_stats = vsi_stats->rx_ring_stats; + + /* Allocate Tx ring stats */ + ice_for_each_alloc_txq(vsi, i) { + struct ice_ring_stats *ring_stats; + struct ice_tx_ring *ring; + + ring = vsi->tx_rings[i]; + ring_stats = tx_ring_stats[i]; + + if (!ring_stats) { + ring_stats = kzalloc(sizeof(*ring_stats), GFP_KERNEL); + if (!ring_stats) + goto err_out; + + WRITE_ONCE(tx_ring_stats[i], ring_stats); + } + + ring->ring_stats = ring_stats; } - if (vsi->rxq_map) { - devm_kfree(dev, vsi->rxq_map); - vsi->rxq_map = NULL; + + /* Allocate Rx ring stats */ + ice_for_each_alloc_rxq(vsi, i) { + struct ice_ring_stats *ring_stats; + struct ice_rx_ring *ring; + + ring = vsi->rx_rings[i]; + ring_stats = rx_ring_stats[i]; + + if (!ring_stats) { + ring_stats = kzalloc(sizeof(*ring_stats), GFP_KERNEL); + if (!ring_stats) + goto err_out; + + WRITE_ONCE(rx_ring_stats[i], ring_stats); + } + + ring->ring_stats = ring_stats; } + + return 0; + +err_out: + ice_vsi_free_stats(vsi); + return -ENOMEM; } /** - * ice_vsi_clear - clean up and deallocate the provided VSI + * ice_vsi_free - clean up and deallocate the provided VSI * @vsi: pointer to VSI being cleared * * This deallocates the VSI's queue resources, removes it from the PF's * VSI array if necessary, and deallocates the VSI - * - * Returns 0 on success, negative on failure */ -int ice_vsi_clear(struct ice_vsi *vsi) +void ice_vsi_free(struct ice_vsi *vsi) { struct ice_pf *pf = NULL; struct device *dev; - if (!vsi) - return 0; - - if (!vsi->back) - return -EINVAL; + if (!vsi || !vsi->back) + return; pf = vsi->back; dev = ice_pf_to_dev(pf); if (!pf->vsi[vsi->idx] || pf->vsi[vsi->idx] != vsi) { dev_dbg(dev, "vsi does not exist at pf->vsi[%d]\n", vsi->idx); - return -EINVAL; + return; } mutex_lock(&pf->sw_mutex); /* updates the PF for this cleared VSI */ pf->vsi[vsi->idx] = NULL; - if (vsi->idx < pf->next_vsi && vsi->type != ICE_VSI_CTRL) - pf->next_vsi = vsi->idx; - if (vsi->idx < pf->next_vsi && vsi->type == ICE_VSI_CTRL && vsi->vf) - pf->next_vsi = vsi->idx; + pf->next_vsi = vsi->idx; + ice_vsi_free_stats(vsi); ice_vsi_free_arrays(vsi); + mutex_destroy(&vsi->xdp_state_lock); mutex_unlock(&pf->sw_mutex); devm_kfree(dev, vsi); +} - return 0; +void ice_vsi_delete(struct ice_vsi *vsi) +{ + ice_vsi_delete_from_hw(vsi); + ice_vsi_free(vsi); } /** @@ -403,8 +484,7 @@ static irqreturn_t ice_msix_clean_ctrl_vsi(int __always_unused irq, void *data) if (!q_vector->tx.tx_ring) return IRQ_HANDLED; -#define FDIR_RX_DESC_CLEAN_BUDGET 64 - ice_clean_rx_irq(q_vector->rx.rx_ring, FDIR_RX_DESC_CLEAN_BUDGET); + ice_clean_ctrl_rx_irq(q_vector->rx.rx_ring); ice_clean_ctrl_tx_irq(q_vector->tx.tx_ring); return IRQ_HANDLED; @@ -429,24 +509,6 @@ static irqreturn_t ice_msix_clean_rings(int __always_unused irq, void *data) return IRQ_HANDLED; } -static irqreturn_t ice_eswitch_msix_clean_rings(int __always_unused irq, void *data) -{ - struct ice_q_vector *q_vector = (struct ice_q_vector *)data; - struct ice_pf *pf = q_vector->vsi->back; - struct ice_vf *vf; - unsigned int bkt; - - if (!q_vector->tx.tx_ring && !q_vector->rx.rx_ring) - return IRQ_HANDLED; - - rcu_read_lock(); - ice_for_each_vf_rcu(pf, bkt, vf) - napi_schedule(&vf->repr->q_vector->napi); - rcu_read_unlock(); - - return IRQ_HANDLED; -} - /** * ice_vsi_alloc_stat_arrays - Allocate statistics arrays * @vsi: VSI pointer @@ -461,6 +523,10 @@ static int ice_vsi_alloc_stat_arrays(struct ice_vsi *vsi) if (!pf->vsi_stats) return -ENOENT; + if (pf->vsi_stats[vsi->idx]) + /* realloc will happen in rebuild path */ + return 0; + vsi_stat = kzalloc(sizeof(*vsi_stat), GFP_KERNEL); if (!vsi_stat) return -ENOMEM; @@ -491,128 +557,94 @@ err_alloc_tx: } /** - * ice_vsi_alloc - Allocates the next available struct VSI in the PF - * @pf: board private structure - * @vsi_type: type of VSI + * ice_vsi_alloc_def - set default values for already allocated VSI + * @vsi: ptr to VSI * @ch: ptr to channel - * @vf: VF for ICE_VSI_VF and ICE_VSI_CTRL - * - * The VF pointer is used for ICE_VSI_VF and ICE_VSI_CTRL. For ICE_VSI_CTRL, - * it may be NULL in the case there is no association with a VF. For - * ICE_VSI_VF the VF pointer *must not* be NULL. - * - * returns a pointer to a VSI on success, NULL on failure. */ -static struct ice_vsi * -ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type vsi_type, - struct ice_channel *ch, struct ice_vf *vf) +static int +ice_vsi_alloc_def(struct ice_vsi *vsi, struct ice_channel *ch) { - struct device *dev = ice_pf_to_dev(pf); - struct ice_vsi *vsi = NULL; - - if (WARN_ON(vsi_type == ICE_VSI_VF && !vf)) - return NULL; - - /* Need to protect the allocation of the VSIs at the PF level */ - mutex_lock(&pf->sw_mutex); - - /* If we have already allocated our maximum number of VSIs, - * pf->next_vsi will be ICE_NO_VSI. If not, pf->next_vsi index - * is available to be populated - */ - if (pf->next_vsi == ICE_NO_VSI) { - dev_dbg(dev, "out of VSI slots!\n"); - goto unlock_pf; + if (vsi->type != ICE_VSI_CHNL) { + ice_vsi_set_num_qs(vsi); + if (ice_vsi_alloc_arrays(vsi)) + return -ENOMEM; } - vsi = devm_kzalloc(dev, sizeof(*vsi), GFP_KERNEL); - if (!vsi) - goto unlock_pf; - - vsi->type = vsi_type; - vsi->back = pf; - set_bit(ICE_VSI_DOWN, vsi->state); - - if (vsi_type == ICE_VSI_VF) - ice_vsi_set_num_qs(vsi, vf); - else if (vsi_type != ICE_VSI_CHNL) - ice_vsi_set_num_qs(vsi, NULL); + vsi->irq_dyn_alloc = pci_msix_can_alloc_dyn(vsi->back->pdev); switch (vsi->type) { - case ICE_VSI_SWITCHDEV_CTRL: - if (ice_vsi_alloc_arrays(vsi)) - goto err_rings; - - /* Setup eswitch MSIX irq handler for VSI */ - vsi->irq_handler = ice_eswitch_msix_clean_rings; - break; case ICE_VSI_PF: - if (ice_vsi_alloc_arrays(vsi)) - goto err_rings; - + case ICE_VSI_SF: /* Setup default MSIX irq handler for VSI */ vsi->irq_handler = ice_msix_clean_rings; break; case ICE_VSI_CTRL: - if (ice_vsi_alloc_arrays(vsi)) - goto err_rings; - /* Setup ctrl VSI MSIX irq handler */ vsi->irq_handler = ice_msix_clean_ctrl_vsi; - - /* For the PF control VSI this is NULL, for the VF control VSI - * this will be the first VF to allocate it. - */ - vsi->vf = vf; - break; - case ICE_VSI_VF: - if (ice_vsi_alloc_arrays(vsi)) - goto err_rings; - vsi->vf = vf; break; case ICE_VSI_CHNL: if (!ch) - goto err_rings; + return -EINVAL; + vsi->num_rxq = ch->num_rxq; vsi->num_txq = ch->num_txq; vsi->next_base_q = ch->base_q; break; + case ICE_VSI_VF: case ICE_VSI_LB: - if (ice_vsi_alloc_arrays(vsi)) - goto err_rings; break; default: - dev_warn(dev, "Unknown VSI type %d\n", vsi->type); - goto unlock_pf; + ice_vsi_free_arrays(vsi); + return -EINVAL; } - if (vsi->type == ICE_VSI_CTRL && !vf) { - /* Use the last VSI slot as the index for PF control VSI */ - vsi->idx = pf->num_alloc_vsi - 1; - pf->ctrl_vsi_idx = vsi->idx; - pf->vsi[vsi->idx] = vsi; - } else { - /* fill slot and make note of the index */ - vsi->idx = pf->next_vsi; - pf->vsi[pf->next_vsi] = vsi; + return 0; +} + +/** + * ice_vsi_alloc - Allocates the next available struct VSI in the PF + * @pf: board private structure + * + * Reserves a VSI index from the PF and allocates an empty VSI structure + * without a type. The VSI structure must later be initialized by calling + * ice_vsi_cfg(). + * + * returns a pointer to a VSI on success, NULL on failure. + */ +struct ice_vsi *ice_vsi_alloc(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + struct ice_vsi *vsi = NULL; - /* prepare pf->next_vsi for next use */ - pf->next_vsi = ice_get_free_slot(pf->vsi, pf->num_alloc_vsi, - pf->next_vsi); + /* Need to protect the allocation of the VSIs at the PF level */ + mutex_lock(&pf->sw_mutex); + + /* If we have already allocated our maximum number of VSIs, + * pf->next_vsi will be ICE_NO_VSI. If not, pf->next_vsi index + * is available to be populated + */ + if (pf->next_vsi == ICE_NO_VSI) { + dev_dbg(dev, "out of VSI slots!\n"); + goto unlock_pf; } - if (vsi->type == ICE_VSI_CTRL && vf) - vf->ctrl_vsi_idx = vsi->idx; + vsi = devm_kzalloc(dev, sizeof(*vsi), GFP_KERNEL); + if (!vsi) + goto unlock_pf; - /* allocate memory for Tx/Rx ring stat pointers */ - if (ice_vsi_alloc_stat_arrays(vsi)) - goto err_rings; + vsi->back = pf; + set_bit(ICE_VSI_DOWN, vsi->state); - goto unlock_pf; + /* fill slot and make note of the index */ + vsi->idx = pf->next_vsi; + pf->vsi[pf->next_vsi] = vsi; + + /* prepare pf->next_vsi for next use */ + pf->next_vsi = ice_get_free_slot(pf->vsi, pf->num_alloc_vsi, + pf->next_vsi); + + mutex_init(&vsi->xdp_state_lock); -err_rings: - devm_kfree(dev, vsi); - vsi = NULL; unlock_pf: mutex_unlock(&pf->sw_mutex); return vsi; @@ -800,7 +832,13 @@ bool ice_is_safe_mode(struct ice_pf *pf) */ bool ice_is_rdma_ena(struct ice_pf *pf) { - return test_bit(ICE_FLAG_RDMA_ENA, pf->flags); + union devlink_param_value value; + int err; + + err = devl_param_driverinit_value_get(priv_to_devlink(pf), + DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA, + &value); + return err ? test_bit(ICE_FLAG_RDMA_ENA, pf->flags) : value.vbool; } /** @@ -835,10 +873,8 @@ static void ice_rss_clean(struct ice_vsi *vsi) dev = ice_pf_to_dev(pf); - if (vsi->rss_hkey_user) - devm_kfree(dev, vsi->rss_hkey_user); - if (vsi->rss_lut_user) - devm_kfree(dev, vsi->rss_lut_user); + devm_kfree(dev, vsi->rss_hkey_user); + devm_kfree(dev, vsi->rss_lut_user); ice_vsi_clean_rss_flow_fld(vsi); /* remove RSS replay list */ @@ -854,6 +890,7 @@ static void ice_vsi_set_rss_params(struct ice_vsi *vsi) { struct ice_hw_common_caps *cap; struct ice_pf *pf = vsi->back; + u16 max_rss_size; if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) { vsi->rss_size = 1; @@ -861,32 +898,31 @@ static void ice_vsi_set_rss_params(struct ice_vsi *vsi) } cap = &pf->hw.func_caps.common_cap; + max_rss_size = BIT(cap->rss_table_entry_width); switch (vsi->type) { case ICE_VSI_CHNL: case ICE_VSI_PF: /* PF VSI will inherit RSS instance of PF */ vsi->rss_table_size = (u16)cap->rss_table_size; if (vsi->type == ICE_VSI_CHNL) - vsi->rss_size = min_t(u16, vsi->num_rxq, - BIT(cap->rss_table_entry_width)); + vsi->rss_size = min_t(u16, vsi->num_rxq, max_rss_size); else vsi->rss_size = min_t(u16, num_online_cpus(), - BIT(cap->rss_table_entry_width)); - vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF; + max_rss_size); + vsi->rss_lut_type = ICE_LUT_PF; break; - case ICE_VSI_SWITCHDEV_CTRL: - vsi->rss_table_size = ICE_VSIQF_HLUT_ARRAY_SIZE; - vsi->rss_size = min_t(u16, num_online_cpus(), - BIT(cap->rss_table_entry_width)); - vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_VSI; + case ICE_VSI_SF: + vsi->rss_table_size = ICE_LUT_VSI_SIZE; + vsi->rss_size = min_t(u16, num_online_cpus(), max_rss_size); + vsi->rss_lut_type = ICE_LUT_VSI; break; case ICE_VSI_VF: /* VF VSI will get a small RSS table. * For VSI_LUT, LUT size should be set to 64 bytes. */ - vsi->rss_table_size = ICE_VSIQF_HLUT_ARRAY_SIZE; + vsi->rss_table_size = ICE_LUT_VSI_SIZE; vsi->rss_size = ICE_MAX_RSS_QS_PER_VF; - vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_VSI; + vsi->rss_lut_type = ICE_LUT_VSI; break; case ICE_VSI_LB: break; @@ -916,9 +952,8 @@ static void ice_set_dflt_vsi_ctx(struct ice_hw *hw, struct ice_vsi_ctx *ctxt) /* Traffic from VSI can be sent to LAN */ ctxt->info.sw_flags2 = ICE_AQ_VSI_SW_FLAG_LAN_ENA; /* allow all untagged/tagged packets by default on Tx */ - ctxt->info.inner_vlan_flags = ((ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL & - ICE_AQ_VSI_INNER_VLAN_TX_MODE_M) >> - ICE_AQ_VSI_INNER_VLAN_TX_MODE_S); + ctxt->info.inner_vlan_flags = FIELD_PREP(ICE_AQ_VSI_INNER_VLAN_TX_MODE_M, + ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL); /* SVM - by default bits 3 and 4 in inner_vlan_flags are 0's which * results in legacy behavior (show VLAN, DEI, and UP) in descriptor. * @@ -926,15 +961,14 @@ static void ice_set_dflt_vsi_ctx(struct ice_hw *hw, struct ice_vsi_ctx *ctxt) */ if (ice_is_dvm_ena(hw)) { ctxt->info.inner_vlan_flags |= - ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING; + FIELD_PREP(ICE_AQ_VSI_INNER_VLAN_EMODE_M, + ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING); ctxt->info.outer_vlan_flags = - (ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL << - ICE_AQ_VSI_OUTER_VLAN_TX_MODE_S) & - ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M; + FIELD_PREP(ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M, + ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL); ctxt->info.outer_vlan_flags |= - (ICE_AQ_VSI_OUTER_TAG_VLAN_8100 << - ICE_AQ_VSI_OUTER_TAG_TYPE_S) & - ICE_AQ_VSI_OUTER_TAG_TYPE_M; + FIELD_PREP(ICE_AQ_VSI_OUTER_TAG_TYPE_M, + ICE_AQ_VSI_OUTER_TAG_VLAN_8100); ctxt->info.outer_vlan_flags |= FIELD_PREP(ICE_AQ_VSI_OUTER_VLAN_EMODE_M, ICE_AQ_VSI_OUTER_VLAN_EMODE_NOTHING); @@ -1013,10 +1047,8 @@ static int ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) vsi->tc_cfg.tc_info[i].qcount_tx = num_txq_per_tc; vsi->tc_cfg.tc_info[i].netdev_tc = netdev_tc++; - qmap = ((offset << ICE_AQ_VSI_TC_Q_OFFSET_S) & - ICE_AQ_VSI_TC_Q_OFFSET_M) | - ((pow << ICE_AQ_VSI_TC_Q_NUM_S) & - ICE_AQ_VSI_TC_Q_NUM_M); + qmap = FIELD_PREP(ICE_AQ_VSI_TC_Q_OFFSET_M, offset); + qmap |= FIELD_PREP(ICE_AQ_VSI_TC_Q_NUM_M, pow); offset += num_rxq_per_tc; tx_count += num_txq_per_tc; ctxt->info.tc_mapping[i] = cpu_to_le16(qmap); @@ -1099,18 +1131,14 @@ static void ice_set_fd_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi) ctxt->info.max_fd_fltr_shared = cpu_to_le16(vsi->num_bfltr); /* default queue index within the VSI of the default FD */ - val = ((dflt_q << ICE_AQ_VSI_FD_DEF_Q_S) & - ICE_AQ_VSI_FD_DEF_Q_M); + val = FIELD_PREP(ICE_AQ_VSI_FD_DEF_Q_M, dflt_q); /* target queue or queue group to the FD filter */ - val |= ((dflt_q_group << ICE_AQ_VSI_FD_DEF_GRP_S) & - ICE_AQ_VSI_FD_DEF_GRP_M); + val |= FIELD_PREP(ICE_AQ_VSI_FD_DEF_GRP_M, dflt_q_group); ctxt->info.fd_def_q = cpu_to_le16(val); /* queue index on which FD filter completion is reported */ - val = ((report_q << ICE_AQ_VSI_FD_REPORT_Q_S) & - ICE_AQ_VSI_FD_REPORT_Q_M); + val = FIELD_PREP(ICE_AQ_VSI_FD_REPORT_Q_M, report_q); /* priority of the default qindex action */ - val |= ((dflt_q_prio << ICE_AQ_VSI_FD_DEF_PRIORITY_S) & - ICE_AQ_VSI_FD_DEF_PRIORITY_M); + val |= FIELD_PREP(ICE_AQ_VSI_FD_DEF_PRIORITY_M, dflt_q_prio); ctxt->info.fd_report_opt = cpu_to_le16(val); } @@ -1133,12 +1161,11 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi) case ICE_VSI_PF: /* PF VSI will inherit RSS instance of PF */ lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_PF; - hash_type = ICE_AQ_VSI_Q_OPT_RSS_TPLZ; break; case ICE_VSI_VF: + case ICE_VSI_SF: /* VF VSI will gets a small RSS table which is a VSI LUT type */ lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_VSI; - hash_type = ICE_AQ_VSI_Q_OPT_RSS_TPLZ; break; default: dev_dbg(dev, "Unsupported VSI type %s\n", @@ -1146,27 +1173,26 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi) return; } - ctxt->info.q_opt_rss = ((lut_type << ICE_AQ_VSI_Q_OPT_RSS_LUT_S) & - ICE_AQ_VSI_Q_OPT_RSS_LUT_M) | - ((hash_type << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) & - ICE_AQ_VSI_Q_OPT_RSS_HASH_M); + hash_type = ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ; + vsi->rss_hfunc = hash_type; + + ctxt->info.q_opt_rss = + FIELD_PREP(ICE_AQ_VSI_Q_OPT_RSS_LUT_M, lut_type) | + FIELD_PREP(ICE_AQ_VSI_Q_OPT_RSS_HASH_M, hash_type); } static void ice_chnl_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) { - struct ice_pf *pf = vsi->back; u16 qcount, qmap; u8 offset = 0; int pow; - qcount = min_t(int, vsi->num_rxq, pf->num_lan_msix); + qcount = vsi->num_rxq; pow = order_base_2(qcount); - qmap = ((offset << ICE_AQ_VSI_TC_Q_OFFSET_S) & - ICE_AQ_VSI_TC_Q_OFFSET_M) | - ((pow << ICE_AQ_VSI_TC_Q_NUM_S) & - ICE_AQ_VSI_TC_Q_NUM_M); + qmap = FIELD_PREP(ICE_AQ_VSI_TC_Q_OFFSET_M, offset); + qmap |= FIELD_PREP(ICE_AQ_VSI_TC_Q_NUM_M, pow); ctxt->info.tc_mapping[0] = cpu_to_le16(qmap); ctxt->info.mapping_flags |= cpu_to_le16(ICE_AQ_VSI_Q_MAP_CONTIG); @@ -1175,14 +1201,28 @@ ice_chnl_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) } /** + * ice_vsi_is_vlan_pruning_ena - check if VLAN pruning is enabled or not + * @vsi: VSI to check whether or not VLAN pruning is enabled. + * + * returns true if Rx VLAN pruning is enabled and false otherwise. + */ +static bool ice_vsi_is_vlan_pruning_ena(struct ice_vsi *vsi) +{ + return vsi->info.sw_flags2 & ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; +} + +/** * ice_vsi_init - Create and initialize a VSI * @vsi: the VSI being configured - * @init_vsi: is this call creating a VSI + * @vsi_flags: VSI configuration flags + * + * Set ICE_FLAG_VSI_INIT to initialize a new VSI context, clear it to + * reconfigure an existing context. * * This initializes a VSI context depending on the VSI type to be added and * passes it down to the add_vsi aq command to create a new VSI. */ -static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi) +static int ice_vsi_init(struct ice_vsi *vsi, u32 vsi_flags) { struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; @@ -1201,7 +1241,7 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi) case ICE_VSI_PF: ctxt->flags = ICE_AQ_VSI_TYPE_PF; break; - case ICE_VSI_SWITCHDEV_CTRL: + case ICE_VSI_SF: case ICE_VSI_CHNL: ctxt->flags = ICE_AQ_VSI_TYPE_VMDQ2; break; @@ -1244,7 +1284,7 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi) /* if updating VSI context, make sure to set valid_section: * to indicate which section of VSI context being updated */ - if (!init_vsi) + if (!(vsi_flags & ICE_VSI_FLAG_INIT)) ctxt->info.valid_sections |= cpu_to_le16(ICE_AQ_VSI_PROP_Q_OPT_VALID); } @@ -1257,7 +1297,8 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi) if (ret) goto out; - if (!init_vsi) /* means VSI being updated */ + if (!(vsi_flags & ICE_VSI_FLAG_INIT)) + /* means VSI being updated */ /* must to indicate which section of VSI context are * being modified */ @@ -1272,7 +1313,7 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi) cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID); } - if (init_vsi) { + if (vsi_flags & ICE_VSI_FLAG_INIT) { ret = ice_add_vsi(hw, vsi->idx, ctxt, NULL); if (ret) { dev_err(dev, "Add VSI failed, err %d\n", ret); @@ -1300,190 +1341,6 @@ out: } /** - * ice_free_res - free a block of resources - * @res: pointer to the resource - * @index: starting index previously returned by ice_get_res - * @id: identifier to track owner - * - * Returns number of resources freed - */ -int ice_free_res(struct ice_res_tracker *res, u16 index, u16 id) -{ - int count = 0; - int i; - - if (!res || index >= res->end) - return -EINVAL; - - id |= ICE_RES_VALID_BIT; - for (i = index; i < res->end && res->list[i] == id; i++) { - res->list[i] = 0; - count++; - } - - return count; -} - -/** - * ice_search_res - Search the tracker for a block of resources - * @res: pointer to the resource - * @needed: size of the block needed - * @id: identifier to track owner - * - * Returns the base item index of the block, or -ENOMEM for error - */ -static int ice_search_res(struct ice_res_tracker *res, u16 needed, u16 id) -{ - u16 start = 0, end = 0; - - if (needed > res->end) - return -ENOMEM; - - id |= ICE_RES_VALID_BIT; - - do { - /* skip already allocated entries */ - if (res->list[end++] & ICE_RES_VALID_BIT) { - start = end; - if ((start + needed) > res->end) - break; - } - - if (end == (start + needed)) { - int i = start; - - /* there was enough, so assign it to the requestor */ - while (i != end) - res->list[i++] = id; - - return start; - } - } while (end < res->end); - - return -ENOMEM; -} - -/** - * ice_get_free_res_count - Get free count from a resource tracker - * @res: Resource tracker instance - */ -static u16 ice_get_free_res_count(struct ice_res_tracker *res) -{ - u16 i, count = 0; - - for (i = 0; i < res->end; i++) - if (!(res->list[i] & ICE_RES_VALID_BIT)) - count++; - - return count; -} - -/** - * ice_get_res - get a block of resources - * @pf: board private structure - * @res: pointer to the resource - * @needed: size of the block needed - * @id: identifier to track owner - * - * Returns the base item index of the block, or negative for error - */ -int -ice_get_res(struct ice_pf *pf, struct ice_res_tracker *res, u16 needed, u16 id) -{ - if (!res || !pf) - return -EINVAL; - - if (!needed || needed > res->num_entries || id >= ICE_RES_VALID_BIT) { - dev_err(ice_pf_to_dev(pf), "param err: needed=%d, num_entries = %d id=0x%04x\n", - needed, res->num_entries, id); - return -EINVAL; - } - - return ice_search_res(res, needed, id); -} - -/** - * ice_get_vf_ctrl_res - Get VF control VSI resource - * @pf: pointer to the PF structure - * @vsi: the VSI to allocate a resource for - * - * Look up whether another VF has already allocated the control VSI resource. - * If so, re-use this resource so that we share it among all VFs. - * - * Otherwise, allocate the resource and return it. - */ -static int ice_get_vf_ctrl_res(struct ice_pf *pf, struct ice_vsi *vsi) -{ - struct ice_vf *vf; - unsigned int bkt; - int base; - - rcu_read_lock(); - ice_for_each_vf_rcu(pf, bkt, vf) { - if (vf != vsi->vf && vf->ctrl_vsi_idx != ICE_NO_VSI) { - base = pf->vsi[vf->ctrl_vsi_idx]->base_vector; - rcu_read_unlock(); - return base; - } - } - rcu_read_unlock(); - - return ice_get_res(pf, pf->irq_tracker, vsi->num_q_vectors, - ICE_RES_VF_CTRL_VEC_ID); -} - -/** - * ice_vsi_setup_vector_base - Set up the base vector for the given VSI - * @vsi: ptr to the VSI - * - * This should only be called after ice_vsi_alloc() which allocates the - * corresponding SW VSI structure and initializes num_queue_pairs for the - * newly allocated VSI. - * - * Returns 0 on success or negative on failure - */ -static int ice_vsi_setup_vector_base(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - struct device *dev; - u16 num_q_vectors; - int base; - - dev = ice_pf_to_dev(pf); - /* SRIOV doesn't grab irq_tracker entries for each VSI */ - if (vsi->type == ICE_VSI_VF) - return 0; - if (vsi->type == ICE_VSI_CHNL) - return 0; - - if (vsi->base_vector) { - dev_dbg(dev, "VSI %d has non-zero base vector %d\n", - vsi->vsi_num, vsi->base_vector); - return -EEXIST; - } - - num_q_vectors = vsi->num_q_vectors; - /* reserve slots from OS requested IRQs */ - if (vsi->type == ICE_VSI_CTRL && vsi->vf) { - base = ice_get_vf_ctrl_res(pf, vsi); - } else { - base = ice_get_res(pf, pf->irq_tracker, num_q_vectors, - vsi->idx); - } - - if (base < 0) { - dev_err(dev, "%d MSI-X interrupts available. %s %d failed to get %d MSI-X vectors\n", - ice_get_free_res_count(pf->irq_tracker), - ice_vsi_type_str(vsi->type), vsi->idx, num_q_vectors); - return -ENOENT; - } - vsi->base_vector = (u16)base; - pf->num_avail_sw_msix -= num_q_vectors; - - return 0; -} - -/** * ice_vsi_clear_rings - Deallocates the Tx and Rx rings for VSI * @vsi: the VSI having rings deallocated */ @@ -1570,116 +1427,19 @@ 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; - WRITE_ONCE(vsi->rx_rings[i], ring); - } - - return 0; - -err_out: - ice_vsi_clear_rings(vsi); - return -ENOMEM; -} - -/** - * ice_vsi_free_stats - Free the ring statistics structures - * @vsi: VSI pointer - */ -static void ice_vsi_free_stats(struct ice_vsi *vsi) -{ - struct ice_vsi_stats *vsi_stat; - struct ice_pf *pf = vsi->back; - int i; - - if (vsi->type == ICE_VSI_CHNL) - return; - if (!pf->vsi_stats) - return; - - vsi_stat = pf->vsi_stats[vsi->idx]; - if (!vsi_stat) - return; - - ice_for_each_alloc_txq(vsi, i) { - if (vsi_stat->tx_ring_stats[i]) { - kfree_rcu(vsi_stat->tx_ring_stats[i], rcu); - WRITE_ONCE(vsi_stat->tx_ring_stats[i], NULL); - } - } - ice_for_each_alloc_rxq(vsi, i) { - if (vsi_stat->rx_ring_stats[i]) { - kfree_rcu(vsi_stat->rx_ring_stats[i], rcu); - WRITE_ONCE(vsi_stat->rx_ring_stats[i], NULL); - } - } + if (ice_is_feature_supported(pf, ICE_F_GCS)) + ring->flags |= ICE_RX_FLAGS_RING_GCS; - kfree(vsi_stat->tx_ring_stats); - kfree(vsi_stat->rx_ring_stats); - kfree(vsi_stat); - pf->vsi_stats[vsi->idx] = NULL; -} - -/** - * ice_vsi_alloc_ring_stats - Allocates Tx and Rx ring stats for the VSI - * @vsi: VSI which is having stats allocated - */ -static int ice_vsi_alloc_ring_stats(struct ice_vsi *vsi) -{ - struct ice_ring_stats **tx_ring_stats; - struct ice_ring_stats **rx_ring_stats; - struct ice_vsi_stats *vsi_stats; - struct ice_pf *pf = vsi->back; - u16 i; - - vsi_stats = pf->vsi_stats[vsi->idx]; - tx_ring_stats = vsi_stats->tx_ring_stats; - rx_ring_stats = vsi_stats->rx_ring_stats; - - /* Allocate Tx ring stats */ - ice_for_each_alloc_txq(vsi, i) { - struct ice_ring_stats *ring_stats; - struct ice_tx_ring *ring; - - ring = vsi->tx_rings[i]; - ring_stats = tx_ring_stats[i]; - - if (!ring_stats) { - ring_stats = kzalloc(sizeof(*ring_stats), GFP_KERNEL); - if (!ring_stats) - goto err_out; - - WRITE_ONCE(tx_ring_stats[i], ring_stats); - } - - ring->ring_stats = ring_stats; - } - - /* Allocate Rx ring stats */ - ice_for_each_alloc_rxq(vsi, i) { - struct ice_ring_stats *ring_stats; - struct ice_rx_ring *ring; - - ring = vsi->rx_rings[i]; - ring_stats = rx_ring_stats[i]; - - if (!ring_stats) { - ring_stats = kzalloc(sizeof(*ring_stats), GFP_KERNEL); - if (!ring_stats) - goto err_out; - - WRITE_ONCE(rx_ring_stats[i], ring_stats); - } - - ring->ring_stats = ring_stats; + WRITE_ONCE(vsi->rx_rings[i], ring); } return 0; err_out: - ice_vsi_free_stats(vsi); + ice_vsi_clear_rings(vsi); return -ENOMEM; } @@ -1817,12 +1577,81 @@ static void ice_vsi_set_vf_rss_flow_fld(struct ice_vsi *vsi) return; } - status = ice_add_avf_rss_cfg(&pf->hw, vsi->idx, ICE_DEFAULT_RSS_HENA); + status = ice_add_avf_rss_cfg(&pf->hw, vsi, ICE_DEFAULT_RSS_HASHCFG); if (status) dev_dbg(dev, "ice_add_avf_rss_cfg failed for vsi = %d, error = %d\n", vsi->vsi_num, status); } +static const struct ice_rss_hash_cfg default_rss_cfgs[] = { + /* configure RSS for IPv4 with input set IP src/dst */ + {ICE_FLOW_SEG_HDR_IPV4, ICE_FLOW_HASH_IPV4, ICE_RSS_ANY_HEADERS, false}, + /* configure RSS for IPv6 with input set IPv6 src/dst */ + {ICE_FLOW_SEG_HDR_IPV6, ICE_FLOW_HASH_IPV6, ICE_RSS_ANY_HEADERS, false}, + /* configure RSS for tcp4 with input set IP src/dst, TCP src/dst */ + {ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV4, + ICE_HASH_TCP_IPV4, ICE_RSS_ANY_HEADERS, false}, + /* configure RSS for udp4 with input set IP src/dst, UDP src/dst */ + {ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_IPV4, + ICE_HASH_UDP_IPV4, ICE_RSS_ANY_HEADERS, false}, + /* configure RSS for sctp4 with input set IP src/dst - only support + * RSS on SCTPv4 on outer headers (non-tunneled) + */ + {ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV4, + ICE_HASH_SCTP_IPV4, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpc4 with input set IPv4 src/dst */ + {ICE_FLOW_SEG_HDR_GTPC | ICE_FLOW_SEG_HDR_IPV4, + ICE_FLOW_HASH_IPV4, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpc4t with input set IPv4 src/dst */ + {ICE_FLOW_SEG_HDR_GTPC_TEID | ICE_FLOW_SEG_HDR_IPV4, + ICE_FLOW_HASH_GTP_C_IPV4_TEID, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpu4 with input set IPv4 src/dst */ + {ICE_FLOW_SEG_HDR_GTPU_IP | ICE_FLOW_SEG_HDR_IPV4, + ICE_FLOW_HASH_GTP_U_IPV4_TEID, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpu4e with input set IPv4 src/dst */ + {ICE_FLOW_SEG_HDR_GTPU_EH | ICE_FLOW_SEG_HDR_IPV4, + ICE_FLOW_HASH_GTP_U_IPV4_EH, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpu4u with input set IPv4 src/dst */ + { ICE_FLOW_SEG_HDR_GTPU_UP | ICE_FLOW_SEG_HDR_IPV4, + ICE_FLOW_HASH_GTP_U_IPV4_UP, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpu4d with input set IPv4 src/dst */ + {ICE_FLOW_SEG_HDR_GTPU_DWN | ICE_FLOW_SEG_HDR_IPV4, + ICE_FLOW_HASH_GTP_U_IPV4_DWN, ICE_RSS_OUTER_HEADERS, false}, + + /* configure RSS for tcp6 with input set IPv6 src/dst, TCP src/dst */ + {ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV6, + ICE_HASH_TCP_IPV6, ICE_RSS_ANY_HEADERS, false}, + /* configure RSS for udp6 with input set IPv6 src/dst, UDP src/dst */ + {ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_IPV6, + ICE_HASH_UDP_IPV6, ICE_RSS_ANY_HEADERS, false}, + /* configure RSS for sctp6 with input set IPv6 src/dst - only support + * RSS on SCTPv6 on outer headers (non-tunneled) + */ + {ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV6, + ICE_HASH_SCTP_IPV6, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for IPSEC ESP SPI with input set MAC_IPV4_SPI */ + {ICE_FLOW_SEG_HDR_ESP, + ICE_FLOW_HASH_ESP_SPI, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpc6 with input set IPv6 src/dst */ + {ICE_FLOW_SEG_HDR_GTPC | ICE_FLOW_SEG_HDR_IPV6, + ICE_FLOW_HASH_IPV6, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpc6t with input set IPv6 src/dst */ + {ICE_FLOW_SEG_HDR_GTPC_TEID | ICE_FLOW_SEG_HDR_IPV6, + ICE_FLOW_HASH_GTP_C_IPV6_TEID, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpu6 with input set IPv6 src/dst */ + {ICE_FLOW_SEG_HDR_GTPU_IP | ICE_FLOW_SEG_HDR_IPV6, + ICE_FLOW_HASH_GTP_U_IPV6_TEID, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpu6e with input set IPv6 src/dst */ + {ICE_FLOW_SEG_HDR_GTPU_EH | ICE_FLOW_SEG_HDR_IPV6, + ICE_FLOW_HASH_GTP_U_IPV6_EH, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpu6u with input set IPv6 src/dst */ + { ICE_FLOW_SEG_HDR_GTPU_UP | ICE_FLOW_SEG_HDR_IPV6, + ICE_FLOW_HASH_GTP_U_IPV6_UP, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpu6d with input set IPv6 src/dst */ + {ICE_FLOW_SEG_HDR_GTPU_DWN | ICE_FLOW_SEG_HDR_IPV6, + ICE_FLOW_HASH_GTP_U_IPV6_DWN, ICE_RSS_OUTER_HEADERS, false}, +}; + /** * ice_vsi_set_rss_flow_fld - Sets RSS input set for different flows * @vsi: VSI to be configured @@ -1836,11 +1665,12 @@ static void ice_vsi_set_vf_rss_flow_fld(struct ice_vsi *vsi) */ static void ice_vsi_set_rss_flow_fld(struct ice_vsi *vsi) { - u16 vsi_handle = vsi->idx, vsi_num = vsi->vsi_num; + u16 vsi_num = vsi->vsi_num; struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; struct device *dev; int status; + u32 i; dev = ice_pf_to_dev(pf); if (ice_is_safe_mode(pf)) { @@ -1848,67 +1678,15 @@ static void ice_vsi_set_rss_flow_fld(struct ice_vsi *vsi) vsi_num); return; } - /* configure RSS for IPv4 with input set IP src/dst */ - status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV4, - ICE_FLOW_SEG_HDR_IPV4); - if (status) - dev_dbg(dev, "ice_add_rss_cfg failed for ipv4 flow, vsi = %d, error = %d\n", - vsi_num, status); - - /* configure RSS for IPv6 with input set IPv6 src/dst */ - status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV6, - ICE_FLOW_SEG_HDR_IPV6); - if (status) - dev_dbg(dev, "ice_add_rss_cfg failed for ipv6 flow, vsi = %d, error = %d\n", - vsi_num, status); - - /* configure RSS for tcp4 with input set IP src/dst, TCP src/dst */ - status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_TCP_IPV4, - ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV4); - if (status) - dev_dbg(dev, "ice_add_rss_cfg failed for tcp4 flow, vsi = %d, error = %d\n", - vsi_num, status); - - /* configure RSS for udp4 with input set IP src/dst, UDP src/dst */ - status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_UDP_IPV4, - ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_IPV4); - if (status) - dev_dbg(dev, "ice_add_rss_cfg failed for udp4 flow, vsi = %d, error = %d\n", - vsi_num, status); - - /* configure RSS for sctp4 with input set IP src/dst */ - status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV4, - ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV4); - if (status) - dev_dbg(dev, "ice_add_rss_cfg failed for sctp4 flow, vsi = %d, error = %d\n", - vsi_num, status); - - /* configure RSS for tcp6 with input set IPv6 src/dst, TCP src/dst */ - status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_TCP_IPV6, - ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV6); - if (status) - dev_dbg(dev, "ice_add_rss_cfg failed for tcp6 flow, vsi = %d, error = %d\n", - vsi_num, status); - - /* configure RSS for udp6 with input set IPv6 src/dst, UDP src/dst */ - status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_UDP_IPV6, - ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_IPV6); - if (status) - dev_dbg(dev, "ice_add_rss_cfg failed for udp6 flow, vsi = %d, error = %d\n", - vsi_num, status); - - /* configure RSS for sctp6 with input set IPv6 src/dst */ - status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV6, - ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV6); - if (status) - dev_dbg(dev, "ice_add_rss_cfg failed for sctp6 flow, vsi = %d, error = %d\n", - vsi_num, status); + for (i = 0; i < ARRAY_SIZE(default_rss_cfgs); i++) { + const struct ice_rss_hash_cfg *cfg = &default_rss_cfgs[i]; - status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_ESP_SPI, - ICE_FLOW_SEG_HDR_ESP); - if (status) - dev_dbg(dev, "ice_add_rss_cfg failed for esp/spi flow, vsi = %d, error = %d\n", - vsi_num, status); + status = ice_add_rss_cfg(hw, vsi, cfg); + if (status) + dev_dbg(dev, "ice_add_rss_cfg failed, addl_hdrs = %x, hash_flds = %llx, hdr_type = %d, symm = %d\n", + cfg->addl_hdrs, cfg->hash_flds, + cfg->hdr_type, cfg->symm); + } } /** @@ -1935,6 +1713,12 @@ bool ice_pf_state_is_nominal(struct ice_pf *pf) return true; } +#define ICE_FW_MODE_REC_M BIT(1) +bool ice_is_recovery_mode(struct ice_hw *hw) +{ + return rd32(hw, GL_MNG_FWSM) & ICE_FW_MODE_REC_M; +} + /** * ice_update_eth_stats - Update VSI-specific ethernet statistics counters * @vsi: the VSI to be updated @@ -1986,31 +1770,6 @@ void ice_update_eth_stats(struct ice_vsi *vsi) } /** - * ice_vsi_cfg_frame_size - setup max frame size and Rx buffer length - * @vsi: VSI - */ -void ice_vsi_cfg_frame_size(struct ice_vsi *vsi) -{ - if (!vsi->netdev || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags)) { - vsi->max_frame = ICE_AQ_SET_MAC_FRAME_SIZE_MAX; - vsi->rx_buf_len = ICE_RXBUF_2048; -#if (PAGE_SIZE < 8192) - } else if (!ICE_2K_TOO_SMALL_WITH_PADDING && - (vsi->netdev->mtu <= ETH_DATA_LEN)) { - vsi->max_frame = ICE_RXBUF_1536 - NET_IP_ALIGN; - vsi->rx_buf_len = ICE_RXBUF_1536 - NET_IP_ALIGN; -#endif - } else { - vsi->max_frame = ICE_AQ_SET_MAC_FRAME_SIZE_MAX; -#if (PAGE_SIZE < 8192) - vsi->rx_buf_len = ICE_RXBUF_3072; -#else - vsi->rx_buf_len = ICE_RXBUF_2048; -#endif - } -} - -/** * ice_write_qrxflxp_cntxt - write/configure QRXFLXP_CNTXT register * @hw: HW pointer * @pf_q: index of the Rx queue in the PF's queue space @@ -2018,9 +1777,8 @@ void ice_vsi_cfg_frame_size(struct ice_vsi *vsi) * @prio: priority for the RXDID for this queue * @ena_ts: true to enable timestamp and false to disable timestamp */ -void -ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio, - bool ena_ts) +void ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio, + bool ena_ts) { int regval = rd32(hw, QRXFLXP_CNTXT(pf_q)); @@ -2029,11 +1787,8 @@ ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio, QRXFLXP_CNTXT_RXDID_PRIO_M | QRXFLXP_CNTXT_TS_M); - regval |= (rxdid << QRXFLXP_CNTXT_RXDID_IDX_S) & - QRXFLXP_CNTXT_RXDID_IDX_M; - - regval |= (prio << QRXFLXP_CNTXT_RXDID_PRIO_S) & - QRXFLXP_CNTXT_RXDID_PRIO_M; + regval |= FIELD_PREP(QRXFLXP_CNTXT_RXDID_IDX_M, rxdid); + regval |= FIELD_PREP(QRXFLXP_CNTXT_RXDID_PRIO_M, prio); if (ena_ts) /* Enable TimeSync on this queue */ @@ -2042,127 +1797,6 @@ ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio, wr32(hw, QRXFLXP_CNTXT(pf_q), regval); } -int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx) -{ - if (q_idx >= vsi->num_rxq) - return -EINVAL; - - return ice_vsi_cfg_rxq(vsi->rx_rings[q_idx]); -} - -int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_tx_ring **tx_rings, u16 q_idx) -{ - struct ice_aqc_add_tx_qgrp *qg_buf; - int err; - - if (q_idx >= vsi->alloc_txq || !tx_rings || !tx_rings[q_idx]) - return -EINVAL; - - qg_buf = kzalloc(struct_size(qg_buf, txqs, 1), GFP_KERNEL); - if (!qg_buf) - return -ENOMEM; - - qg_buf->num_txqs = 1; - - err = ice_vsi_cfg_txq(vsi, tx_rings[q_idx], qg_buf); - kfree(qg_buf); - return err; -} - -/** - * ice_vsi_cfg_rxqs - Configure the VSI for Rx - * @vsi: the VSI being configured - * - * Return 0 on success and a negative value on error - * Configure the Rx VSI for operation. - */ -int ice_vsi_cfg_rxqs(struct ice_vsi *vsi) -{ - u16 i; - - if (vsi->type == ICE_VSI_VF) - goto setup_rings; - - ice_vsi_cfg_frame_size(vsi); -setup_rings: - /* set up individual rings */ - ice_for_each_rxq(vsi, i) { - int err = ice_vsi_cfg_rxq(vsi->rx_rings[i]); - - if (err) - return err; - } - - return 0; -} - -/** - * ice_vsi_cfg_txqs - Configure the VSI for Tx - * @vsi: the VSI being configured - * @rings: Tx ring array to be configured - * @count: number of Tx ring array elements - * - * Return 0 on success and a negative value on error - * Configure the Tx VSI for operation. - */ -static int -ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_tx_ring **rings, u16 count) -{ - struct ice_aqc_add_tx_qgrp *qg_buf; - u16 q_idx = 0; - int err = 0; - - qg_buf = kzalloc(struct_size(qg_buf, txqs, 1), GFP_KERNEL); - if (!qg_buf) - return -ENOMEM; - - qg_buf->num_txqs = 1; - - for (q_idx = 0; q_idx < count; q_idx++) { - err = ice_vsi_cfg_txq(vsi, rings[q_idx], qg_buf); - if (err) - goto err_cfg_txqs; - } - -err_cfg_txqs: - kfree(qg_buf); - return err; -} - -/** - * ice_vsi_cfg_lan_txqs - Configure the VSI for Tx - * @vsi: the VSI being configured - * - * Return 0 on success and a negative value on error - * Configure the Tx VSI for operation. - */ -int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi) -{ - return ice_vsi_cfg_txqs(vsi, vsi->tx_rings, vsi->num_txq); -} - -/** - * ice_vsi_cfg_xdp_txqs - Configure Tx queues dedicated for XDP in given VSI - * @vsi: the VSI being configured - * - * Return 0 on success and a negative value on error - * Configure the Tx queues dedicated for XDP in given VSI for operation. - */ -int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi) -{ - int ret; - int i; - - ret = ice_vsi_cfg_txqs(vsi, vsi->xdp_rings, vsi->num_xdp_txq); - if (ret) - return ret; - - ice_for_each_rxq(vsi, i) - ice_tx_xsk_pool(vsi, i); - - return ret; -} - /** * ice_intrl_usec_to_reg - convert interrupt rate limit to register value * @intrl: interrupt rate limit in usecs @@ -2416,20 +2050,6 @@ bool ice_vsi_is_rx_queue_active(struct ice_vsi *vsi) return false; } -/** - * ice_vsi_is_vlan_pruning_ena - check if VLAN pruning is enabled or not - * @vsi: VSI to check whether or not VLAN pruning is enabled. - * - * returns true if Rx VLAN pruning is enabled and false otherwise. - */ -bool ice_vsi_is_vlan_pruning_ena(struct ice_vsi *vsi) -{ - if (!vsi) - return false; - - return (vsi->info.sw_flags2 & ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA); -} - static void ice_vsi_set_tc_cfg(struct ice_vsi *vsi) { if (!test_bit(ICE_FLAG_DCB_ENA, vsi->back->flags)) { @@ -2443,56 +2063,15 @@ static void ice_vsi_set_tc_cfg(struct ice_vsi *vsi) } /** - * ice_vsi_set_q_vectors_reg_idx - set the HW register index for all q_vectors - * @vsi: VSI to set the q_vectors register index on - */ -static int -ice_vsi_set_q_vectors_reg_idx(struct ice_vsi *vsi) -{ - u16 i; - - if (!vsi || !vsi->q_vectors) - return -EINVAL; - - ice_for_each_q_vector(vsi, i) { - struct ice_q_vector *q_vector = vsi->q_vectors[i]; - - if (!q_vector) { - dev_err(ice_pf_to_dev(vsi->back), "Failed to set reg_idx on q_vector %d VSI %d\n", - i, vsi->vsi_num); - goto clear_reg_idx; - } - - if (vsi->type == ICE_VSI_VF) { - struct ice_vf *vf = vsi->vf; - - q_vector->reg_idx = ice_calc_vf_reg_idx(vf, q_vector); - } else { - q_vector->reg_idx = - q_vector->v_idx + vsi->base_vector; - } - } - - return 0; - -clear_reg_idx: - ice_for_each_q_vector(vsi, i) { - struct ice_q_vector *q_vector = vsi->q_vectors[i]; - - if (q_vector) - q_vector->reg_idx = 0; - } - - return -EINVAL; -} - -/** - * ice_cfg_sw_lldp - Config switch rules for LLDP packet handling + * ice_vsi_cfg_sw_lldp - Config switch rules for LLDP packet handling * @vsi: the VSI being configured * @tx: bool to determine Tx or Rx rule * @create: bool to determine create or remove Rule + * + * Adding an ethtype Tx rule to the uplink VSI results in it being applied + * to the whole port, so LLDP transmission for VFs will be blocked too. */ -void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create) +void ice_vsi_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create) { int (*eth_fltr)(struct ice_vsi *v, u16 type, u16 flag, enum ice_sw_fwd_act_type act); @@ -2507,19 +2086,59 @@ void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create) status = eth_fltr(vsi, ETH_P_LLDP, ICE_FLTR_TX, ICE_DROP_PACKET); } else { - if (ice_fw_supports_lldp_fltr_ctrl(&pf->hw)) { - status = ice_lldp_fltr_add_remove(&pf->hw, vsi->vsi_num, - create); - } else { + if (!test_bit(ICE_FLAG_LLDP_AQ_FLTR, pf->flags)) { status = eth_fltr(vsi, ETH_P_LLDP, ICE_FLTR_RX, ICE_FWD_TO_VSI); + if (!status || !create) + goto report; + + dev_info(dev, + "Failed to add generic LLDP Rx filter on VSI %i error: %d, falling back to specialized AQ control\n", + vsi->vsi_num, status); } + + status = ice_lldp_fltr_add_remove(&pf->hw, vsi, create); + if (!status) + set_bit(ICE_FLAG_LLDP_AQ_FLTR, pf->flags); + } +report: if (status) - dev_dbg(dev, "Fail %s %s LLDP rule on VSI %i error: %d\n", - create ? "adding" : "removing", tx ? "TX" : "RX", - vsi->vsi_num, status); + dev_warn(dev, "Failed to %s %s LLDP rule on VSI %i error: %d\n", + create ? "add" : "remove", tx ? "Tx" : "Rx", + vsi->vsi_num, status); +} + +/** + * ice_cfg_sw_rx_lldp - Enable/disable software handling of LLDP + * @pf: the PF being configured + * @enable: enable or disable + * + * Configure switch rules to enable/disable LLDP handling by software + * across PF. + */ +void ice_cfg_sw_rx_lldp(struct ice_pf *pf, bool enable) +{ + struct ice_vsi *vsi; + struct ice_vf *vf; + unsigned int bkt; + + vsi = ice_get_main_vsi(pf); + ice_vsi_cfg_sw_lldp(vsi, false, enable); + + if (!test_bit(ICE_FLAG_SRIOV_ENA, pf->flags)) + return; + + ice_for_each_vf(pf, bkt, vf) { + vsi = ice_get_vf_vsi(vf); + + if (WARN_ON(!vsi)) + continue; + + if (ice_vf_is_lldp_ena(vf)) + ice_vsi_cfg_sw_lldp(vsi, false, enable); + } } /** @@ -2555,7 +2174,7 @@ static void ice_set_agg_vsi(struct ice_vsi *vsi) case ICE_VSI_CHNL: case ICE_VSI_LB: case ICE_VSI_PF: - case ICE_VSI_SWITCHDEV_CTRL: + case ICE_VSI_SF: max_agg_nodes = ICE_MAX_PF_AGG_NODES; agg_node_id_start = ICE_PF_AGG_NODE_ID_START; agg_node_iter = &pf->pf_agg_node[0]; @@ -2644,55 +2263,70 @@ static void ice_set_agg_vsi(struct ice_vsi *vsi) vsi->agg_node->num_vsis); } -/** - * ice_vsi_setup - Set up a VSI by a given type - * @pf: board private structure - * @pi: pointer to the port_info instance - * @vsi_type: VSI type - * @vf: pointer to VF to which this VSI connects. This field is used primarily - * for the ICE_VSI_VF type. Other VSI types should pass NULL. - * @ch: ptr to channel - * - * This allocates the sw VSI structure and its queue resources. - * - * Returns pointer to the successfully allocated and configured VSI sw struct on - * success, NULL on failure. - */ -struct ice_vsi * -ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, - enum ice_vsi_type vsi_type, struct ice_vf *vf, - struct ice_channel *ch) +static int ice_vsi_cfg_tc_lan(struct ice_pf *pf, struct ice_vsi *vsi) { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; struct device *dev = ice_pf_to_dev(pf); - struct ice_vsi *vsi; int ret, i; - if (vsi_type == ICE_VSI_CHNL) - vsi = ice_vsi_alloc(pf, vsi_type, ch, NULL); - else if (vsi_type == ICE_VSI_VF || vsi_type == ICE_VSI_CTRL) - vsi = ice_vsi_alloc(pf, vsi_type, NULL, vf); - else - vsi = ice_vsi_alloc(pf, vsi_type, NULL, NULL); + /* configure VSI nodes based on number of queues and TC's */ + ice_for_each_traffic_class(i) { + if (!(vsi->tc_cfg.ena_tc & BIT(i))) + continue; - if (!vsi) { - dev_err(dev, "could not allocate VSI\n"); - return NULL; + if (vsi->type == ICE_VSI_CHNL) { + if (!vsi->alloc_txq && vsi->num_txq) + max_txqs[i] = vsi->num_txq; + else + max_txqs[i] = pf->num_lan_tx; + } else { + max_txqs[i] = vsi->alloc_txq; + } + + if (vsi->type == ICE_VSI_PF) + max_txqs[i] += vsi->num_xdp_txq; + } + + dev_dbg(dev, "vsi->tc_cfg.ena_tc = %d\n", vsi->tc_cfg.ena_tc); + ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc, + max_txqs); + if (ret) { + dev_err(dev, "VSI %d failed lan queue config, error %d\n", + vsi->vsi_num, ret); + return ret; } - vsi->port_info = pi; + return 0; +} + +/** + * ice_vsi_cfg_def - configure default VSI based on the type + * @vsi: pointer to VSI + */ +static int ice_vsi_cfg_def(struct ice_vsi *vsi) +{ + struct device *dev = ice_pf_to_dev(vsi->back); + struct ice_pf *pf = vsi->back; + int ret; + vsi->vsw = pf->first_sw; - if (vsi->type == ICE_VSI_PF) - vsi->ethtype = ETH_P_PAUSE; + + ret = ice_vsi_alloc_def(vsi, vsi->ch); + if (ret) + return ret; + + /* allocate memory for Tx/Rx ring stat pointers */ + ret = ice_vsi_alloc_stat_arrays(vsi); + if (ret) + goto unroll_vsi_alloc; ice_alloc_fd_res(vsi); - if (vsi_type != ICE_VSI_CHNL) { - if (ice_vsi_get_qs(vsi)) { - dev_err(dev, "Failed to allocate queues. vsi->idx = %d\n", - vsi->idx); - goto unroll_vsi_alloc; - } + ret = ice_vsi_get_qs(vsi); + if (ret) { + dev_err(dev, "Failed to allocate queues. vsi->idx = %d\n", + vsi->idx); + goto unroll_vsi_alloc_stat; } /* set RSS capabilities */ @@ -2702,7 +2336,7 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, ice_vsi_set_tc_cfg(vsi); /* create the VSI */ - ret = ice_vsi_init(vsi, true); + ret = ice_vsi_init(vsi, vsi->flags); if (ret) goto unroll_get_qs; @@ -2710,20 +2344,12 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, switch (vsi->type) { case ICE_VSI_CTRL: - case ICE_VSI_SWITCHDEV_CTRL: + case ICE_VSI_SF: case ICE_VSI_PF: ret = ice_vsi_alloc_q_vectors(vsi); if (ret) goto unroll_vsi_init; - ret = ice_vsi_setup_vector_base(vsi); - if (ret) - goto unroll_alloc_q_vector; - - ret = ice_vsi_set_q_vectors_reg_idx(vsi); - if (ret) - goto unroll_vector_base; - ret = ice_vsi_alloc_rings(vsi); if (ret) goto unroll_vector_base; @@ -2732,8 +2358,20 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, if (ret) goto unroll_vector_base; + if (ice_is_xdp_ena_vsi(vsi)) { + ret = ice_vsi_determine_xdp_res(vsi); + if (ret) + goto unroll_vector_base; + ret = ice_prepare_xdp_rings(vsi, vsi->xdp_prog, + ICE_XDP_CFG_PART); + if (ret) + goto unroll_vector_base; + } + ice_vsi_map_rings_to_vectors(vsi); + vsi->stat_offsets_loaded = false; + /* ICE_VSI_CTRL does not need RSS so skip RSS processing */ if (vsi->type != ICE_VSI_CTRL) /* Do not exit if configuring RSS had an issue, at @@ -2766,13 +2404,12 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, if (ret) goto unroll_alloc_q_vector; - ret = ice_vsi_set_q_vectors_reg_idx(vsi); - if (ret) - goto unroll_vector_base; - ret = ice_vsi_alloc_ring_stats(vsi); if (ret) goto unroll_vector_base; + + vsi->stat_offsets_loaded = false; + /* Do not exit if configuring RSS had an issue, at least * receive traffic on first queue. Hence no need to capture * return value @@ -2794,33 +2431,132 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, break; default: /* clean up the resources and exit */ + ret = -EINVAL; goto unroll_vsi_init; } - /* configure VSI nodes based on number of queues and TC's */ - ice_for_each_traffic_class(i) { - if (!(vsi->tc_cfg.ena_tc & BIT(i))) - continue; + return 0; - if (vsi->type == ICE_VSI_CHNL) { - if (!vsi->alloc_txq && vsi->num_txq) - max_txqs[i] = vsi->num_txq; - else - max_txqs[i] = pf->num_lan_tx; +unroll_vector_base: + /* reclaim SW interrupts back to the common pool */ +unroll_alloc_q_vector: + ice_vsi_free_q_vectors(vsi); +unroll_vsi_init: + ice_vsi_delete_from_hw(vsi); +unroll_get_qs: + ice_vsi_put_qs(vsi); +unroll_vsi_alloc_stat: + ice_vsi_free_stats(vsi); +unroll_vsi_alloc: + ice_vsi_free_arrays(vsi); + return ret; +} + +/** + * ice_vsi_cfg - configure a previously allocated VSI + * @vsi: pointer to VSI + */ +int ice_vsi_cfg(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + int ret; + + if (WARN_ON(vsi->type == ICE_VSI_VF && !vsi->vf)) + return -EINVAL; + + ret = ice_vsi_cfg_def(vsi); + if (ret) + return ret; + + ret = ice_vsi_cfg_tc_lan(vsi->back, vsi); + if (ret) + ice_vsi_decfg(vsi); + + if (vsi->type == ICE_VSI_CTRL) { + if (vsi->vf) { + WARN_ON(vsi->vf->ctrl_vsi_idx != ICE_NO_VSI); + vsi->vf->ctrl_vsi_idx = vsi->idx; } else { - max_txqs[i] = vsi->alloc_txq; + WARN_ON(pf->ctrl_vsi_idx != ICE_NO_VSI); + pf->ctrl_vsi_idx = vsi->idx; } } - dev_dbg(dev, "vsi->tc_cfg.ena_tc = %d\n", vsi->tc_cfg.ena_tc); - ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc, - max_txqs); - if (ret) { - dev_err(dev, "VSI %d failed lan queue config, error %d\n", - vsi->vsi_num, ret); - goto unroll_clear_rings; + return ret; +} + +/** + * ice_vsi_decfg - remove all VSI configuration + * @vsi: pointer to VSI + */ +void ice_vsi_decfg(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + int err; + + ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx); + err = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx); + if (err) + dev_err(ice_pf_to_dev(pf), "Failed to remove RDMA scheduler config for VSI %u, err %d\n", + vsi->vsi_num, err); + + if (vsi->xdp_rings) + /* return value check can be skipped here, it always returns + * 0 if reset is in progress + */ + ice_destroy_xdp_rings(vsi, ICE_XDP_CFG_PART); + + ice_vsi_clear_rings(vsi); + ice_vsi_free_q_vectors(vsi); + ice_vsi_put_qs(vsi); + ice_vsi_free_arrays(vsi); + + /* SR-IOV determines needed MSIX resources all at once instead of per + * VSI since when VFs are spawned we know how many VFs there are and how + * many interrupts each VF needs. SR-IOV MSIX resources are also + * cleared in the same manner. + */ + + if (vsi->type == ICE_VSI_VF && + vsi->agg_node && vsi->agg_node->valid) + vsi->agg_node->num_vsis--; +} + +/** + * ice_vsi_setup - Set up a VSI by a given type + * @pf: board private structure + * @params: parameters to use when creating the VSI + * + * This allocates the sw VSI structure and its queue resources. + * + * Returns pointer to the successfully allocated and configured VSI sw struct on + * success, NULL on failure. + */ +struct ice_vsi * +ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params) +{ + struct device *dev = ice_pf_to_dev(pf); + struct ice_vsi *vsi; + int ret; + + /* ice_vsi_setup can only initialize a new VSI, and we must have + * a port_info structure for it. + */ + if (WARN_ON(!(params->flags & ICE_VSI_FLAG_INIT)) || + WARN_ON(!params->port_info)) + return NULL; + + vsi = ice_vsi_alloc(pf); + if (!vsi) { + dev_err(dev, "could not allocate VSI\n"); + return NULL; } + vsi->params = *params; + ret = ice_vsi_cfg(vsi); + if (ret) + goto err_vsi_cfg; + /* Add switch rule to drop all Tx Flow Control Frames, of look up * type ETHERTYPE from VSIs, and restrict malicious VF from sending * out PAUSE or PFC frames. If enabled, FW can still send FC frames. @@ -2830,34 +2566,19 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, * be dropped so that VFs cannot send LLDP packets to reconfig DCB * settings in the HW. */ - if (!ice_is_safe_mode(pf)) - if (vsi->type == ICE_VSI_PF) { - ice_fltr_add_eth(vsi, ETH_P_PAUSE, ICE_FLTR_TX, - ICE_DROP_PACKET); - ice_cfg_sw_lldp(vsi, true, true); - } + if (!ice_is_safe_mode(pf) && vsi->type == ICE_VSI_PF) { + ice_fltr_add_eth(vsi, ETH_P_PAUSE, ICE_FLTR_TX, + ICE_DROP_PACKET); + ice_vsi_cfg_sw_lldp(vsi, true, true); + } if (!vsi->agg_node) ice_set_agg_vsi(vsi); + return vsi; -unroll_clear_rings: - ice_vsi_clear_rings(vsi); -unroll_vector_base: - /* reclaim SW interrupts back to the common pool */ - ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx); - pf->num_avail_sw_msix += vsi->num_q_vectors; -unroll_alloc_q_vector: - ice_vsi_free_q_vectors(vsi); -unroll_vsi_init: - ice_vsi_free_stats(vsi); - ice_vsi_delete(vsi); -unroll_get_qs: - ice_vsi_put_qs(vsi); -unroll_vsi_alloc: - if (vsi_type == ICE_VSI_VF) - ice_enable_lag(pf->lag); - ice_vsi_clear(vsi); +err_vsi_cfg: + ice_vsi_free(vsi); return NULL; } @@ -2881,7 +2602,7 @@ static void ice_vsi_release_msix(struct ice_vsi *vsi) for (q = 0; q < q_vector->num_ring_tx; q++) { ice_write_itr(&q_vector->tx, 0); wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), 0); - if (ice_is_xdp_ena_vsi(vsi)) { + if (vsi->xdp_rings) { u32 xdp_txq = txq + vsi->num_xdp_txq; wr32(hw, QINT_TQCTL(vsi->txq_map[xdp_txq]), 0); @@ -2906,7 +2627,6 @@ static void ice_vsi_release_msix(struct ice_vsi *vsi) void ice_vsi_free_irq(struct ice_vsi *vsi) { struct ice_pf *pf = vsi->back; - int base = vsi->base_vector; int i; if (!vsi->q_vectors || !vsi->irqs_ready) @@ -2917,13 +2637,11 @@ void ice_vsi_free_irq(struct ice_vsi *vsi) return; vsi->irqs_ready = false; - ice_free_cpu_rx_rmap(vsi); ice_for_each_q_vector(vsi, i) { - u16 vector = i + base; int irq_num; - irq_num = pf->msix_entries[vector].vector; + irq_num = vsi->q_vectors[i]->irq.virq; /* free only the irqs that were actually requested */ if (!vsi->q_vectors[i] || @@ -2931,12 +2649,6 @@ void ice_vsi_free_irq(struct ice_vsi *vsi) vsi->q_vectors[i]->num_ring_rx)) continue; - /* clear the affinity notifier in the IRQ descriptor */ - if (!IS_ENABLED(CONFIG_RFS_ACCEL)) - irq_set_affinity_notifier(irq_num, NULL); - - /* clear the affinity_mask in the IRQ descriptor */ - irq_set_affinity_hint(irq_num, NULL); synchronize_irq(irq_num); devm_free_irq(ice_pf_to_dev(pf), irq_num, vsi->q_vectors[i]); } @@ -2983,6 +2695,7 @@ void ice_vsi_close(struct ice_vsi *vsi) if (!test_and_set_bit(ICE_VSI_DOWN, vsi->state)) ice_down(vsi); + ice_vsi_clear_napi_queues(vsi); ice_vsi_free_irq(vsi); ice_vsi_free_tx_rings(vsi); ice_vsi_free_rx_rings(vsi); @@ -3002,7 +2715,8 @@ int ice_ena_vsi(struct ice_vsi *vsi, bool locked) clear_bit(ICE_VSI_NEEDS_RESTART, vsi->state); - if (vsi->netdev && vsi->type == ICE_VSI_PF) { + if (vsi->netdev && (vsi->type == ICE_VSI_PF || + vsi->type == ICE_VSI_SF)) { if (netif_running(vsi->netdev)) { if (!locked) rtnl_lock(); @@ -3026,129 +2740,108 @@ int ice_ena_vsi(struct ice_vsi *vsi, bool locked) */ void ice_dis_vsi(struct ice_vsi *vsi, bool locked) { - if (test_bit(ICE_VSI_DOWN, vsi->state)) - return; + bool already_down = test_bit(ICE_VSI_DOWN, vsi->state); set_bit(ICE_VSI_NEEDS_RESTART, vsi->state); - if (vsi->type == ICE_VSI_PF && vsi->netdev) { + if (vsi->netdev && (vsi->type == ICE_VSI_PF || + vsi->type == ICE_VSI_SF)) { if (netif_running(vsi->netdev)) { if (!locked) rtnl_lock(); - - ice_vsi_close(vsi); + already_down = test_bit(ICE_VSI_DOWN, vsi->state); + if (!already_down) + ice_vsi_close(vsi); if (!locked) rtnl_unlock(); - } else { + } else if (!already_down) { ice_vsi_close(vsi); } - } else if (vsi->type == ICE_VSI_CTRL || - vsi->type == ICE_VSI_SWITCHDEV_CTRL) { + } else if (vsi->type == ICE_VSI_CTRL && !already_down) { ice_vsi_close(vsi); } } /** - * ice_vsi_dis_irq - Mask off queue interrupt generation on the VSI - * @vsi: the VSI being un-configured + * ice_vsi_set_napi_queues - associate netdev queues with napi + * @vsi: VSI pointer + * + * Associate queue[s] with napi for all vectors. */ -void ice_vsi_dis_irq(struct ice_vsi *vsi) +void ice_vsi_set_napi_queues(struct ice_vsi *vsi) { - int base = vsi->base_vector; - struct ice_pf *pf = vsi->back; - struct ice_hw *hw = &pf->hw; - u32 val; - int i; + struct net_device *netdev = vsi->netdev; + int q_idx, v_idx; - /* disable interrupt causation from each queue */ - if (vsi->tx_rings) { - ice_for_each_txq(vsi, i) { - if (vsi->tx_rings[i]) { - u16 reg; + if (!netdev) + return; - reg = vsi->tx_rings[i]->reg_idx; - val = rd32(hw, QINT_TQCTL(reg)); - val &= ~QINT_TQCTL_CAUSE_ENA_M; - wr32(hw, QINT_TQCTL(reg), val); - } - } - } + 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); - if (vsi->rx_rings) { - ice_for_each_rxq(vsi, i) { - if (vsi->rx_rings[i]) { - u16 reg; + ice_for_each_txq(vsi, q_idx) + netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_TX, + &vsi->tx_rings[q_idx]->q_vector->napi); + /* Also set the interrupt number for the NAPI */ + ice_for_each_q_vector(vsi, v_idx) { + struct ice_q_vector *q_vector = vsi->q_vectors[v_idx]; - reg = vsi->rx_rings[i]->reg_idx; - val = rd32(hw, QINT_RQCTL(reg)); - val &= ~QINT_RQCTL_CAUSE_ENA_M; - wr32(hw, QINT_RQCTL(reg), val); - } - } + netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq); } - - /* disable each interrupt */ - ice_for_each_q_vector(vsi, i) { - if (!vsi->q_vectors[i]) - continue; - wr32(hw, GLINT_DYN_CTL(vsi->q_vectors[i]->reg_idx), 0); - } - - ice_flush(hw); - - /* don't call synchronize_irq() for VF's from the host */ - if (vsi->type == ICE_VSI_VF) - return; - - ice_for_each_q_vector(vsi, i) - synchronize_irq(pf->msix_entries[i + base].vector); } /** - * ice_napi_del - Remove NAPI handler for the VSI - * @vsi: VSI for which NAPI handler is to be removed + * ice_vsi_clear_napi_queues - dissociate netdev queues from napi + * @vsi: VSI pointer + * + * Clear the association between all VSI queues queue[s] and napi. */ -void ice_napi_del(struct ice_vsi *vsi) +void ice_vsi_clear_napi_queues(struct ice_vsi *vsi) { - int v_idx; + struct net_device *netdev = vsi->netdev; + int q_idx, v_idx; - if (!vsi->netdev) + if (!netdev) return; - ice_for_each_q_vector(vsi, v_idx) - netif_napi_del(&vsi->q_vectors[v_idx]->napi); + 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]; + + netif_napi_set_irq(&q_vector->napi, -1); + } + + ice_for_each_txq(vsi, q_idx) + netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_TX, NULL); + + ice_for_each_rxq(vsi, q_idx) + netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_RX, NULL); } /** - * ice_free_vf_ctrl_res - Free the VF control VSI resource - * @pf: pointer to PF structure - * @vsi: the VSI to free resources for + * ice_napi_add - register NAPI handler for the VSI + * @vsi: VSI for which NAPI handler is to be registered * - * Check if the VF control VSI resource is still in use. If no VF is using it - * any more, release the VSI resource. Otherwise, leave it to be cleaned up - * once no other VF uses it. + * This function is only called in the driver's load path. Registering the NAPI + * handler is done in ice_vsi_alloc_q_vector() for all other cases (i.e. resume, + * reset/rebuild, etc.) */ -static void ice_free_vf_ctrl_res(struct ice_pf *pf, struct ice_vsi *vsi) +void ice_napi_add(struct ice_vsi *vsi) { - struct ice_vf *vf; - unsigned int bkt; + int v_idx; - rcu_read_lock(); - ice_for_each_vf_rcu(pf, bkt, vf) { - if (vf != vsi->vf && vf->ctrl_vsi_idx != ICE_NO_VSI) { - rcu_read_unlock(); - return; - } - } - rcu_read_unlock(); + if (!vsi->netdev) + return; - /* No other VFs left that have control VSI. It is now safe to reclaim - * SW interrupts back to the common pool. - */ - ice_free_res(pf->irq_tracker, vsi->base_vector, - ICE_RES_VF_CTRL_VEC_ID); - pf->num_avail_sw_msix += vsi->num_q_vectors; + ice_for_each_q_vector(vsi, v_idx) + netif_napi_add_config(vsi->netdev, + &vsi->q_vectors[v_idx]->napi, + ice_napi_poll, + v_idx); } /** @@ -3160,94 +2853,33 @@ static void ice_free_vf_ctrl_res(struct ice_pf *pf, struct ice_vsi *vsi) int ice_vsi_release(struct ice_vsi *vsi) { struct ice_pf *pf; - int err; if (!vsi->back) return -ENODEV; pf = vsi->back; - /* do not unregister while driver is in the reset recovery pending - * state. Since reset/rebuild happens through PF service task workqueue, - * it's not a good idea to unregister netdev that is associated to the - * PF that is running the work queue items currently. This is done to - * avoid check_flush_dependency() warning on this wq - */ - if (vsi->netdev && !ice_is_reset_in_progress(pf->state) && - (test_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state))) { - unregister_netdev(vsi->netdev); - clear_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state); - } - if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) ice_rss_clean(vsi); - /* Disable VSI and free resources */ - if (vsi->type != ICE_VSI_LB) - ice_vsi_dis_irq(vsi); ice_vsi_close(vsi); - /* SR-IOV determines needed MSIX resources all at once instead of per - * VSI since when VFs are spawned we know how many VFs there are and how - * many interrupts each VF needs. SR-IOV MSIX resources are also - * cleared in the same manner. + /* The Rx rule will only exist to remove if the LLDP FW + * engine is currently stopped */ - if (vsi->type == ICE_VSI_CTRL && vsi->vf) { - ice_free_vf_ctrl_res(pf, vsi); - } else if (vsi->type != ICE_VSI_VF) { - /* reclaim SW interrupts back to the common pool */ - ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx); - pf->num_avail_sw_msix += vsi->num_q_vectors; - } + if (!ice_is_safe_mode(pf) && + !test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags) && + (vsi->type == ICE_VSI_PF || (vsi->type == ICE_VSI_VF && + ice_vf_is_lldp_ena(vsi->vf)))) + ice_vsi_cfg_sw_lldp(vsi, false, false); - if (!ice_is_safe_mode(pf)) { - if (vsi->type == ICE_VSI_PF) { - ice_fltr_remove_eth(vsi, ETH_P_PAUSE, ICE_FLTR_TX, - ICE_DROP_PACKET); - ice_cfg_sw_lldp(vsi, true, false); - /* The Rx rule will only exist to remove if the LLDP FW - * engine is currently stopped - */ - if (!test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags)) - ice_cfg_sw_lldp(vsi, false, false); - } - } - - if (ice_is_vsi_dflt_vsi(vsi)) - ice_clear_dflt_vsi(vsi); - ice_fltr_remove_all(vsi); - ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx); - err = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx); - if (err) - dev_err(ice_pf_to_dev(vsi->back), "Failed to remove RDMA scheduler config for VSI %u, err %d\n", - vsi->vsi_num, err); - ice_vsi_delete(vsi); - ice_vsi_free_q_vectors(vsi); - - if (vsi->netdev) { - if (test_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state)) { - unregister_netdev(vsi->netdev); - clear_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state); - } - if (test_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state)) { - free_netdev(vsi->netdev); - vsi->netdev = NULL; - clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); - } - } - - if (vsi->type == ICE_VSI_VF && - vsi->agg_node && vsi->agg_node->valid) - vsi->agg_node->num_vsis--; - ice_vsi_clear_rings(vsi); - ice_vsi_free_stats(vsi); - ice_vsi_put_qs(vsi); + ice_vsi_decfg(vsi); /* retain SW VSI data structure since it is needed to unregister and * free VSI netdev when PF is not in reset recovery pending state,\ * for ex: during rmmod. */ if (!ice_is_reset_in_progress(pf->state)) - ice_vsi_clear(vsi); + ice_vsi_delete(vsi); return 0; } @@ -3367,27 +2999,26 @@ ice_vsi_rebuild_set_coalesce(struct ice_vsi *vsi, } /** - * ice_vsi_realloc_stat_arrays - Frees unused stat structures + * ice_vsi_realloc_stat_arrays - Frees unused stat structures or alloc new ones * @vsi: VSI pointer - * @prev_txq: Number of Tx rings before ring reallocation - * @prev_rxq: Number of Rx rings before ring reallocation */ static int -ice_vsi_realloc_stat_arrays(struct ice_vsi *vsi, int prev_txq, int prev_rxq) +ice_vsi_realloc_stat_arrays(struct ice_vsi *vsi) { + u16 req_txq = vsi->req_txq ? vsi->req_txq : vsi->alloc_txq; + u16 req_rxq = vsi->req_rxq ? vsi->req_rxq : vsi->alloc_rxq; + struct ice_ring_stats **tx_ring_stats; + struct ice_ring_stats **rx_ring_stats; struct ice_vsi_stats *vsi_stat; struct ice_pf *pf = vsi->back; + u16 prev_txq = vsi->alloc_txq; + u16 prev_rxq = vsi->alloc_rxq; int i; - if (!prev_txq || !prev_rxq) - return 0; - if (vsi->type == ICE_VSI_CHNL) - return 0; - vsi_stat = pf->vsi_stats[vsi->idx]; - if (vsi->num_txq < prev_txq) { - for (i = vsi->num_txq; i < prev_txq; i++) { + if (req_txq < prev_txq) { + for (i = req_txq; i < prev_txq; i++) { if (vsi_stat->tx_ring_stats[i]) { kfree_rcu(vsi_stat->tx_ring_stats[i], rcu); WRITE_ONCE(vsi_stat->tx_ring_stats[i], NULL); @@ -3395,8 +3026,18 @@ ice_vsi_realloc_stat_arrays(struct ice_vsi *vsi, int prev_txq, int prev_rxq) } } - if (vsi->num_rxq < prev_rxq) { - for (i = vsi->num_rxq; i < prev_rxq; i++) { + tx_ring_stats = vsi_stat->tx_ring_stats; + vsi_stat->tx_ring_stats = + krealloc_array(vsi_stat->tx_ring_stats, req_txq, + sizeof(*vsi_stat->tx_ring_stats), + GFP_KERNEL | __GFP_ZERO); + if (!vsi_stat->tx_ring_stats) { + vsi_stat->tx_ring_stats = tx_ring_stats; + return -ENOMEM; + } + + if (req_rxq < prev_rxq) { + for (i = req_rxq; i < prev_rxq; i++) { if (vsi_stat->rx_ring_stats[i]) { kfree_rcu(vsi_stat->rx_ring_stats[i], rcu); WRITE_ONCE(vsi_stat->rx_ring_stats[i], NULL); @@ -3404,228 +3045,85 @@ ice_vsi_realloc_stat_arrays(struct ice_vsi *vsi, int prev_txq, int prev_rxq) } } + rx_ring_stats = vsi_stat->rx_ring_stats; + vsi_stat->rx_ring_stats = + krealloc_array(vsi_stat->rx_ring_stats, req_rxq, + sizeof(*vsi_stat->rx_ring_stats), + GFP_KERNEL | __GFP_ZERO); + if (!vsi_stat->rx_ring_stats) { + vsi_stat->rx_ring_stats = rx_ring_stats; + return -ENOMEM; + } + return 0; } /** * ice_vsi_rebuild - Rebuild VSI after reset * @vsi: VSI to be rebuild - * @init_vsi: is this an initialization or a reconfigure of the VSI + * @vsi_flags: flags used for VSI rebuild flow + * + * Set vsi_flags to ICE_VSI_FLAG_INIT to initialize a new VSI, or + * ICE_VSI_FLAG_NO_INIT to rebuild an existing VSI in hardware. * * Returns 0 on success and negative value on failure */ -int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) +int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags) { - u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; struct ice_coalesce_stored *coalesce; - int ret, i, prev_txq, prev_rxq; - int prev_num_q_vectors = 0; - enum ice_vsi_type vtype; + int prev_num_q_vectors; struct ice_pf *pf; + int ret; if (!vsi) return -EINVAL; + vsi->flags = vsi_flags; pf = vsi->back; - vtype = vsi->type; - if (WARN_ON(vtype == ICE_VSI_VF && !vsi->vf)) + if (WARN_ON(vsi->type == ICE_VSI_VF && !vsi->vf)) return -EINVAL; - ice_vsi_init_vlan_ops(vsi); + mutex_lock(&vsi->xdp_state_lock); - coalesce = kcalloc(vsi->num_q_vectors, - sizeof(struct ice_coalesce_stored), GFP_KERNEL); - if (!coalesce) - return -ENOMEM; - - prev_num_q_vectors = ice_vsi_rebuild_get_coalesce(vsi, coalesce); - - prev_txq = vsi->num_txq; - prev_rxq = vsi->num_rxq; - - ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx); - ret = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx); + ret = ice_vsi_realloc_stat_arrays(vsi); if (ret) - dev_err(ice_pf_to_dev(vsi->back), "Failed to remove RDMA scheduler config for VSI %u, err %d\n", - vsi->vsi_num, ret); - ice_vsi_free_q_vectors(vsi); - - /* SR-IOV determines needed MSIX resources all at once instead of per - * VSI since when VFs are spawned we know how many VFs there are and how - * many interrupts each VF needs. SR-IOV MSIX resources are also - * cleared in the same manner. - */ - if (vtype != ICE_VSI_VF) { - /* reclaim SW interrupts back to the common pool */ - ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx); - pf->num_avail_sw_msix += vsi->num_q_vectors; - vsi->base_vector = 0; - } + goto unlock; - if (ice_is_xdp_ena_vsi(vsi)) - /* return value check can be skipped here, it always returns - * 0 if reset is in progress - */ - ice_destroy_xdp_rings(vsi); - ice_vsi_put_qs(vsi); - ice_vsi_clear_rings(vsi); - ice_vsi_free_arrays(vsi); - if (vtype == ICE_VSI_VF) - ice_vsi_set_num_qs(vsi, vsi->vf); - else - ice_vsi_set_num_qs(vsi, NULL); - - ret = ice_vsi_alloc_arrays(vsi); - if (ret < 0) - goto err_vsi; - - ice_vsi_get_qs(vsi); - - ice_alloc_fd_res(vsi); - ice_vsi_set_tc_cfg(vsi); - - /* Initialize VSI struct elements and create VSI in FW */ - ret = ice_vsi_init(vsi, init_vsi); - if (ret < 0) - goto err_vsi; - - switch (vtype) { - case ICE_VSI_CTRL: - case ICE_VSI_SWITCHDEV_CTRL: - case ICE_VSI_PF: - ret = ice_vsi_alloc_q_vectors(vsi); - if (ret) - goto err_rings; - - ret = ice_vsi_setup_vector_base(vsi); - if (ret) - goto err_vectors; - - ret = ice_vsi_set_q_vectors_reg_idx(vsi); - if (ret) - goto err_vectors; - - ret = ice_vsi_alloc_rings(vsi); - if (ret) - goto err_vectors; - - ret = ice_vsi_alloc_ring_stats(vsi); - if (ret) - goto err_vectors; - - ice_vsi_map_rings_to_vectors(vsi); - - vsi->stat_offsets_loaded = false; - if (ice_is_xdp_ena_vsi(vsi)) { - ret = ice_vsi_determine_xdp_res(vsi); - if (ret) - goto err_vectors; - ret = ice_prepare_xdp_rings(vsi, vsi->xdp_prog); - if (ret) - goto err_vectors; - } - /* ICE_VSI_CTRL does not need RSS so skip RSS processing */ - if (vtype != ICE_VSI_CTRL) - /* Do not exit if configuring RSS had an issue, at - * least receive traffic on first queue. Hence no - * need to capture return value - */ - if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) - ice_vsi_cfg_rss_lut_key(vsi); - - /* disable or enable CRC stripping */ - if (vsi->netdev) - ice_vsi_cfg_crc_strip(vsi, !!(vsi->netdev->features & - NETIF_F_RXFCS)); - - break; - case ICE_VSI_VF: - ret = ice_vsi_alloc_q_vectors(vsi); - if (ret) - goto err_rings; - - ret = ice_vsi_set_q_vectors_reg_idx(vsi); - if (ret) - goto err_vectors; - - ret = ice_vsi_alloc_rings(vsi); - if (ret) - goto err_vectors; - - ret = ice_vsi_alloc_ring_stats(vsi); - if (ret) - goto err_vectors; - - vsi->stat_offsets_loaded = false; - break; - case ICE_VSI_CHNL: - if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) { - ice_vsi_cfg_rss_lut_key(vsi); - ice_vsi_set_rss_flow_fld(vsi); - } - break; - default: - break; - } - - /* configure VSI nodes based on number of queues and TC's */ - for (i = 0; i < vsi->tc_cfg.numtc; i++) { - /* configure VSI nodes based on number of queues and TC's. - * ADQ creates VSIs for each TC/Channel but doesn't - * allocate queues instead it reconfigures the PF queues - * as per the TC command. So max_txqs should point to the - * PF Tx queues. - */ - if (vtype == ICE_VSI_CHNL) - max_txqs[i] = pf->num_lan_tx; - else - max_txqs[i] = vsi->alloc_txq; + ice_vsi_decfg(vsi); + ret = ice_vsi_cfg_def(vsi); + if (ret) + goto unlock; - if (ice_is_xdp_ena_vsi(vsi)) - max_txqs[i] += vsi->num_xdp_txq; + coalesce = kcalloc(vsi->num_q_vectors, + sizeof(struct ice_coalesce_stored), GFP_KERNEL); + if (!coalesce) { + ret = -ENOMEM; + goto decfg; } - if (test_bit(ICE_FLAG_TC_MQPRIO, pf->flags)) - /* If MQPRIO is set, means channel code path, hence for main - * VSI's, use TC as 1 - */ - ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, 1, max_txqs); - else - ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, - vsi->tc_cfg.ena_tc, max_txqs); + prev_num_q_vectors = ice_vsi_rebuild_get_coalesce(vsi, coalesce); + ret = ice_vsi_cfg_tc_lan(pf, vsi); if (ret) { - dev_err(ice_pf_to_dev(pf), "VSI %d failed lan queue config, error %d\n", - vsi->vsi_num, ret); - if (init_vsi) { + if (vsi_flags & ICE_VSI_FLAG_INIT) { ret = -EIO; - goto err_vectors; - } else { - return ice_schedule_reset(pf, ICE_RESET_PFR); + goto free_coalesce; } - } - if (ice_vsi_realloc_stat_arrays(vsi, prev_txq, prev_rxq)) - goto err_vectors; + ret = ice_schedule_reset(pf, ICE_RESET_PFR); + goto free_coalesce; + } ice_vsi_rebuild_set_coalesce(vsi, coalesce, prev_num_q_vectors); - kfree(coalesce); - - return 0; + clear_bit(ICE_VSI_REBUILD_PENDING, vsi->state); -err_vectors: - ice_vsi_free_q_vectors(vsi); -err_rings: - if (vsi->netdev) { - vsi->current_netdev_flags = 0; - unregister_netdev(vsi->netdev); - free_netdev(vsi->netdev); - vsi->netdev = NULL; - } -err_vsi: - ice_vsi_clear(vsi); - set_bit(ICE_RESET_FAILED, pf->state); +free_coalesce: kfree(coalesce); +decfg: + if (ret) + ice_vsi_decfg(vsi); +unlock: + mutex_unlock(&vsi->xdp_state_lock); return ret; } @@ -3700,7 +3198,7 @@ void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc) if (!netdev) return; - /* CHNL VSI doesn't have it's own netdev, hence, no netdev_tc */ + /* CHNL VSI doesn't have its own netdev, hence, no netdev_tc */ if (vsi->type == ICE_VSI_CHNL) return; @@ -3768,9 +3266,8 @@ ice_vsi_setup_q_map_mqprio(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt, vsi->tc_cfg.ena_tc = ena_tc ? ena_tc : 1; pow = order_base_2(tc0_qcount); - qmap = ((tc0_offset << ICE_AQ_VSI_TC_Q_OFFSET_S) & - ICE_AQ_VSI_TC_Q_OFFSET_M) | - ((pow << ICE_AQ_VSI_TC_Q_NUM_S) & ICE_AQ_VSI_TC_Q_NUM_M); + qmap = FIELD_PREP(ICE_AQ_VSI_TC_Q_OFFSET_M, tc0_offset); + qmap |= FIELD_PREP(ICE_AQ_VSI_TC_Q_NUM_M, pow); ice_for_each_traffic_class(i) { if (!(vsi->tc_cfg.ena_tc & BIT(i))) { @@ -3860,7 +3357,7 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc) dev = ice_pf_to_dev(pf); if (vsi->tc_cfg.ena_tc == ena_tc && vsi->mqprio_qopt.mode != TC_MQPRIO_MODE_CHANNEL) - return ret; + return 0; ice_for_each_traffic_class(i) { /* build bitmap of enabled TCs */ @@ -4013,6 +3510,12 @@ int ice_set_dflt_vsi(struct ice_vsi *vsi) dev = ice_pf_to_dev(vsi->back); + if (ice_lag_is_switchdev_running(vsi->back)) { + dev_dbg(dev, "VSI %d passed is a part of LAG containing interfaces in switchdev mode, nothing to do\n", + vsi->vsi_num); + return 0; + } + /* the VSI passed in is already the default VSI */ if (ice_is_vsi_dflt_vsi(vsi)) { dev_dbg(dev, "VSI %d passed in is already the default forwarding VSI, nothing to do\n", @@ -4232,20 +3735,20 @@ int ice_set_link(struct ice_vsi *vsi, bool ena) status = ice_aq_set_link_restart_an(pi, ena, NULL); - /* if link is owned by manageability, FW will return ICE_AQ_RC_EMODE. + /* if link is owned by manageability, FW will return LIBIE_AQ_RC_EMODE. * this is not a fatal error, so print a warning message and return * a success code. Return an error if FW returns an error code other - * than ICE_AQ_RC_EMODE + * than LIBIE_AQ_RC_EMODE */ if (status == -EIO) { - if (hw->adminq.sq_last_status == ICE_AQ_RC_EMODE) + if (hw->adminq.sq_last_status == LIBIE_AQ_RC_EMODE) dev_dbg(dev, "can't set link to %s, err %d aq_err %s. not fatal, continuing\n", (ena ? "ON" : "OFF"), status, - ice_aq_str(hw->adminq.sq_last_status)); + libie_aq_str(hw->adminq.sq_last_status)); } else if (status) { dev_err(dev, "can't set link to %s, err %d aq_err %s\n", (ena ? "ON" : "OFF"), status, - ice_aq_str(hw->adminq.sq_last_status)); + libie_aq_str(hw->adminq.sq_last_status)); return status; } @@ -4390,7 +3893,7 @@ bool ice_is_feature_supported(struct ice_pf *pf, enum ice_feature f) * @pf: pointer to the struct ice_pf instance * @f: feature enum to set */ -static void ice_set_feature_support(struct ice_pf *pf, enum ice_feature f) +void ice_set_feature_support(struct ice_pf *pf, enum ice_feature f) { if (f < 0 || f >= ICE_F_MAX) return; @@ -4423,17 +3926,31 @@ void ice_init_feature_support(struct ice_pf *pf) case ICE_DEV_ID_E810C_BACKPLANE: case ICE_DEV_ID_E810C_QSFP: case ICE_DEV_ID_E810C_SFP: + case ICE_DEV_ID_E810_XXV_BACKPLANE: + case ICE_DEV_ID_E810_XXV_QSFP: + case ICE_DEV_ID_E810_XXV_SFP: ice_set_feature_support(pf, ICE_F_DSCP); - ice_set_feature_support(pf, ICE_F_PTP_EXTTS); - if (ice_is_e810t(&pf->hw)) { + if (ice_is_phy_rclk_in_netlist(&pf->hw)) + ice_set_feature_support(pf, ICE_F_PHY_RCLK); + /* If we don't own the timer - don't enable other caps */ + if (!ice_pf_src_tmr_owned(pf)) + break; + if (ice_is_cgu_in_netlist(&pf->hw)) + ice_set_feature_support(pf, ICE_F_CGU); + if (ice_is_clock_mux_in_netlist(&pf->hw)) ice_set_feature_support(pf, ICE_F_SMA_CTRL); - if (ice_gnss_is_gps_present(&pf->hw)) - ice_set_feature_support(pf, ICE_F_GNSS); - } + if (ice_gnss_is_module_present(&pf->hw)) + ice_set_feature_support(pf, ICE_F_GNSS); break; default: break; } + + if (pf->hw.mac_type == ICE_MAC_E830) { + ice_set_feature_support(pf, ICE_F_MBX_LIMIT); + ice_set_feature_support(pf, ICE_F_GCS); + ice_set_feature_support(pf, ICE_F_TXTIME); + } } /** @@ -4480,19 +3997,61 @@ void ice_vsi_ctx_clear_antispoof(struct ice_vsi_ctx *ctx) } /** - * ice_vsi_ctx_set_allow_override - allow destination override on VSI - * @ctx: pointer to VSI ctx structure + * ice_vsi_update_local_lb - update sw block in VSI with local loopback bit + * @vsi: pointer to VSI structure + * @set: set or unset the bit */ -void ice_vsi_ctx_set_allow_override(struct ice_vsi_ctx *ctx) +int +ice_vsi_update_local_lb(struct ice_vsi *vsi, bool set) { - ctx->info.sec_flags |= ICE_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD; + struct ice_vsi_ctx ctx = { + .info = vsi->info, + }; + + ctx.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SW_VALID); + if (set) + ctx.info.sw_flags |= ICE_AQ_VSI_SW_FLAG_LOCAL_LB; + else + ctx.info.sw_flags &= ~ICE_AQ_VSI_SW_FLAG_LOCAL_LB; + + if (ice_update_vsi(&vsi->back->hw, vsi->idx, &ctx, NULL)) + return -ENODEV; + + vsi->info = ctx.info; + return 0; } /** - * ice_vsi_ctx_clear_allow_override - turn off destination override on VSI - * @ctx: pointer to VSI ctx structure + * ice_vsi_update_l2tsel - update l2tsel field for all Rx rings on this VSI + * @vsi: VSI used to update l2tsel on + * @l2tsel: l2tsel setting requested + * + * Use the l2tsel setting to update all of the Rx queue context bits for l2tsel. + * This will modify which descriptor field the first offloaded VLAN will be + * stripped into. */ -void ice_vsi_ctx_clear_allow_override(struct ice_vsi_ctx *ctx) +void ice_vsi_update_l2tsel(struct ice_vsi *vsi, enum ice_l2tsel l2tsel) { - ctx->info.sec_flags &= ~ICE_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD; + struct ice_hw *hw = &vsi->back->hw; + u32 l2tsel_bit; + int i; + + if (l2tsel == ICE_L2TSEL_EXTRACT_FIRST_TAG_L2TAG2_2ND) + l2tsel_bit = 0; + else + l2tsel_bit = BIT(ICE_L2TSEL_BIT_OFFSET); + + for (i = 0; i < vsi->alloc_rxq; i++) { + u16 pfq = vsi->rxq_map[i]; + u32 qrx_context_offset; + u32 regval; + + qrx_context_offset = + QRX_CONTEXT(ICE_L2TSEL_QRX_CONTEXT_REG_IDX, pfq); + + regval = rd32(hw, qrx_context_offset); + regval &= ~BIT(ICE_L2TSEL_BIT_OFFSET); + regval |= l2tsel_bit; + wr32(hw, qrx_context_offset, regval); + } } |