diff options
Diffstat (limited to 'drivers/net/ethernet/intel/i40e')
| -rw-r--r-- | drivers/net/ethernet/intel/i40e/i40e.h | 10 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/i40e/i40e_debugfs.c | 52 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 89 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/i40e/i40e_main.c | 158 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/i40e/i40e_txrx.c | 421 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/i40e/i40e_txrx.h | 68 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/i40e/i40e_type.h | 2 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 1000 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h | 20 |
9 files changed, 1417 insertions, 403 deletions
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 46e9f4e0a02c..36d9401a6258 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -507,6 +507,7 @@ struct i40e_pf { #define I40E_HW_STOP_FW_LLDP BIT(16) #define I40E_HW_PORT_ID_VALID BIT(17) #define I40E_HW_RESTART_AUTONEG BIT(18) +#define I40E_HW_STOPPABLE_FW_LLDP BIT(19) u64 flags; #define I40E_FLAG_RX_CSUM_ENABLED BIT_ULL(0) @@ -824,6 +825,7 @@ struct i40e_q_vector { struct i40e_ring_container rx; struct i40e_ring_container tx; + u8 itr_countdown; /* when 0 should adjust adaptive ITR */ u8 num_ringpairs; /* total number of ring pairs in vector */ cpumask_t affinity_mask; @@ -832,8 +834,6 @@ struct i40e_q_vector { struct rcu_head rcu; /* to avoid race with update stats on free */ char name[I40E_INT_NAME_STR_LEN]; bool arm_wb_state; -#define ITR_COUNTDOWN_START 100 - u8 itr_countdown; /* when 0 should adjust ITR */ } ____cacheline_internodealigned_in_smp; /* lan device */ @@ -1109,4 +1109,10 @@ static inline bool i40e_enabled_xdp_vsi(struct i40e_vsi *vsi) int i40e_create_queue_channel(struct i40e_vsi *vsi, struct i40e_channel *ch); int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate); +int i40e_add_del_cloud_filter(struct i40e_vsi *vsi, + struct i40e_cloud_filter *filter, + bool add); +int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi, + struct i40e_cloud_filter *filter, + bool add); #endif /* _I40E_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 4c3b4243cf65..b829fd365693 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -155,8 +155,8 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) dev_info(&pf->pdev->dev, " vlan_features = 0x%08lx\n", (unsigned long int)nd->vlan_features); } - dev_info(&pf->pdev->dev, - " vlgrp: & = %p\n", vsi->active_vlans); + dev_info(&pf->pdev->dev, " active_vlans is %s\n", + vsi->active_vlans ? "<valid>" : "<null>"); dev_info(&pf->pdev->dev, " flags = 0x%08lx, netdev_registered = %i, current_netdev_flags = 0x%04x\n", vsi->flags, vsi->netdev_registered, vsi->current_netdev_flags); @@ -270,14 +270,6 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) continue; dev_info(&pf->pdev->dev, - " rx_rings[%i]: desc = %p\n", - i, rx_ring->desc); - dev_info(&pf->pdev->dev, - " rx_rings[%i]: dev = %p, netdev = %p, rx_bi = %p\n", - i, rx_ring->dev, - rx_ring->netdev, - rx_ring->rx_bi); - dev_info(&pf->pdev->dev, " rx_rings[%i]: state = %lu, queue_index = %d, reg_idx = %d\n", i, *rx_ring->state, rx_ring->queue_index, @@ -307,17 +299,12 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) rx_ring->rx_stats.realloc_count, rx_ring->rx_stats.page_reuse_count); dev_info(&pf->pdev->dev, - " rx_rings[%i]: size = %i, dma = 0x%08lx\n", - i, rx_ring->size, - (unsigned long int)rx_ring->dma); - dev_info(&pf->pdev->dev, - " rx_rings[%i]: vsi = %p, q_vector = %p\n", - i, rx_ring->vsi, - rx_ring->q_vector); + " rx_rings[%i]: size = %i\n", + i, rx_ring->size); dev_info(&pf->pdev->dev, - " rx_rings[%i]: rx_itr_setting = %d (%s)\n", - i, rx_ring->rx_itr_setting, - ITR_IS_DYNAMIC(rx_ring->rx_itr_setting) ? "dynamic" : "fixed"); + " rx_rings[%i]: itr_setting = %d (%s)\n", + i, rx_ring->itr_setting, + ITR_IS_DYNAMIC(rx_ring->itr_setting) ? "dynamic" : "fixed"); } for (i = 0; i < vsi->num_queue_pairs; i++) { struct i40e_ring *tx_ring = READ_ONCE(vsi->tx_rings[i]); @@ -326,14 +313,6 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) continue; dev_info(&pf->pdev->dev, - " tx_rings[%i]: desc = %p\n", - i, tx_ring->desc); - dev_info(&pf->pdev->dev, - " tx_rings[%i]: dev = %p, netdev = %p, tx_bi = %p\n", - i, tx_ring->dev, - tx_ring->netdev, - tx_ring->tx_bi); - dev_info(&pf->pdev->dev, " tx_rings[%i]: state = %lu, queue_index = %d, reg_idx = %d\n", i, *tx_ring->state, tx_ring->queue_index, @@ -355,20 +334,15 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) tx_ring->tx_stats.tx_busy, tx_ring->tx_stats.tx_done_old); dev_info(&pf->pdev->dev, - " tx_rings[%i]: size = %i, dma = 0x%08lx\n", - i, tx_ring->size, - (unsigned long int)tx_ring->dma); - dev_info(&pf->pdev->dev, - " tx_rings[%i]: vsi = %p, q_vector = %p\n", - i, tx_ring->vsi, - tx_ring->q_vector); + " tx_rings[%i]: size = %i\n", + i, tx_ring->size); dev_info(&pf->pdev->dev, " tx_rings[%i]: DCB tc = %d\n", i, tx_ring->dcb_tc); dev_info(&pf->pdev->dev, - " tx_rings[%i]: tx_itr_setting = %d (%s)\n", - i, tx_ring->tx_itr_setting, - ITR_IS_DYNAMIC(tx_ring->tx_itr_setting) ? "dynamic" : "fixed"); + " tx_rings[%i]: itr_setting = %d (%s)\n", + i, tx_ring->itr_setting, + ITR_IS_DYNAMIC(tx_ring->itr_setting) ? "dynamic" : "fixed"); } rcu_read_unlock(); dev_info(&pf->pdev->dev, @@ -466,8 +440,6 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) vsi->info.resp_reserved[6], vsi->info.resp_reserved[7], vsi->info.resp_reserved[8], vsi->info.resp_reserved[9], vsi->info.resp_reserved[10], vsi->info.resp_reserved[11]); - if (vsi->back) - dev_info(&pf->pdev->dev, " PF = %p\n", vsi->back); dev_info(&pf->pdev->dev, " idx = %d\n", vsi->idx); dev_info(&pf->pdev->dev, " tc_config: numtc = %d, enabled_tc = 0x%x\n", diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 2f5bee713fef..0dcbbda164c4 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -2244,14 +2244,14 @@ static int __i40e_get_coalesce(struct net_device *netdev, rx_ring = vsi->rx_rings[queue]; tx_ring = vsi->tx_rings[queue]; - if (ITR_IS_DYNAMIC(rx_ring->rx_itr_setting)) + if (ITR_IS_DYNAMIC(rx_ring->itr_setting)) ec->use_adaptive_rx_coalesce = 1; - if (ITR_IS_DYNAMIC(tx_ring->tx_itr_setting)) + if (ITR_IS_DYNAMIC(tx_ring->itr_setting)) ec->use_adaptive_tx_coalesce = 1; - ec->rx_coalesce_usecs = rx_ring->rx_itr_setting & ~I40E_ITR_DYNAMIC; - ec->tx_coalesce_usecs = tx_ring->tx_itr_setting & ~I40E_ITR_DYNAMIC; + ec->rx_coalesce_usecs = rx_ring->itr_setting & ~I40E_ITR_DYNAMIC; + ec->tx_coalesce_usecs = tx_ring->itr_setting & ~I40E_ITR_DYNAMIC; /* we use the _usecs_high to store/set the interrupt rate limit * that the hardware supports, that almost but not quite @@ -2311,34 +2311,35 @@ static void i40e_set_itr_per_queue(struct i40e_vsi *vsi, struct i40e_pf *pf = vsi->back; struct i40e_hw *hw = &pf->hw; struct i40e_q_vector *q_vector; - u16 vector, intrl; + u16 intrl; intrl = i40e_intrl_usec_to_reg(vsi->int_rate_limit); - rx_ring->rx_itr_setting = ec->rx_coalesce_usecs; - tx_ring->tx_itr_setting = ec->tx_coalesce_usecs; + rx_ring->itr_setting = ITR_REG_ALIGN(ec->rx_coalesce_usecs); + tx_ring->itr_setting = ITR_REG_ALIGN(ec->tx_coalesce_usecs); if (ec->use_adaptive_rx_coalesce) - rx_ring->rx_itr_setting |= I40E_ITR_DYNAMIC; + rx_ring->itr_setting |= I40E_ITR_DYNAMIC; else - rx_ring->rx_itr_setting &= ~I40E_ITR_DYNAMIC; + rx_ring->itr_setting &= ~I40E_ITR_DYNAMIC; if (ec->use_adaptive_tx_coalesce) - tx_ring->tx_itr_setting |= I40E_ITR_DYNAMIC; + tx_ring->itr_setting |= I40E_ITR_DYNAMIC; else - tx_ring->tx_itr_setting &= ~I40E_ITR_DYNAMIC; + tx_ring->itr_setting &= ~I40E_ITR_DYNAMIC; q_vector = rx_ring->q_vector; - q_vector->rx.itr = ITR_TO_REG(rx_ring->rx_itr_setting); - vector = vsi->base_vector + q_vector->v_idx; - wr32(hw, I40E_PFINT_ITRN(I40E_RX_ITR, vector - 1), q_vector->rx.itr); + q_vector->rx.target_itr = ITR_TO_REG(rx_ring->itr_setting); q_vector = tx_ring->q_vector; - q_vector->tx.itr = ITR_TO_REG(tx_ring->tx_itr_setting); - vector = vsi->base_vector + q_vector->v_idx; - wr32(hw, I40E_PFINT_ITRN(I40E_TX_ITR, vector - 1), q_vector->tx.itr); + q_vector->tx.target_itr = ITR_TO_REG(tx_ring->itr_setting); - wr32(hw, I40E_PFINT_RATEN(vector - 1), intrl); + /* The interrupt handler itself will take care of programming + * the Tx and Rx ITR values based on the values we have entered + * into the q_vector, no need to write the values now. + */ + + wr32(hw, I40E_PFINT_RATEN(q_vector->reg_idx), intrl); i40e_flush(hw); } @@ -2364,11 +2365,11 @@ static int __i40e_set_coalesce(struct net_device *netdev, vsi->work_limit = ec->tx_max_coalesced_frames_irq; if (queue < 0) { - cur_rx_itr = vsi->rx_rings[0]->rx_itr_setting; - cur_tx_itr = vsi->tx_rings[0]->tx_itr_setting; + cur_rx_itr = vsi->rx_rings[0]->itr_setting; + cur_tx_itr = vsi->tx_rings[0]->itr_setting; } else if (queue < vsi->num_queue_pairs) { - cur_rx_itr = vsi->rx_rings[queue]->rx_itr_setting; - cur_tx_itr = vsi->tx_rings[queue]->tx_itr_setting; + cur_rx_itr = vsi->rx_rings[queue]->itr_setting; + cur_tx_itr = vsi->tx_rings[queue]->itr_setting; } else { netif_info(pf, drv, netdev, "Invalid queue value, queue range is 0 - %d\n", vsi->num_queue_pairs - 1); @@ -2396,7 +2397,7 @@ static int __i40e_set_coalesce(struct net_device *netdev, return -EINVAL; } - if (ec->rx_coalesce_usecs > (I40E_MAX_ITR << 1)) { + if (ec->rx_coalesce_usecs > I40E_MAX_ITR) { netif_info(pf, drv, netdev, "Invalid value, rx-usecs range is 0-8160\n"); return -EINVAL; } @@ -2407,16 +2408,16 @@ static int __i40e_set_coalesce(struct net_device *netdev, return -EINVAL; } - if (ec->tx_coalesce_usecs > (I40E_MAX_ITR << 1)) { + if (ec->tx_coalesce_usecs > I40E_MAX_ITR) { netif_info(pf, drv, netdev, "Invalid value, tx-usecs range is 0-8160\n"); return -EINVAL; } if (ec->use_adaptive_rx_coalesce && !cur_rx_itr) - ec->rx_coalesce_usecs = I40E_MIN_ITR << 1; + ec->rx_coalesce_usecs = I40E_MIN_ITR; if (ec->use_adaptive_tx_coalesce && !cur_tx_itr) - ec->tx_coalesce_usecs = I40E_MIN_ITR << 1; + ec->tx_coalesce_usecs = I40E_MIN_ITR; intrl_reg = i40e_intrl_usec_to_reg(ec->rx_coalesce_usecs_high); vsi->int_rate_limit = INTRL_REG_TO_USEC(intrl_reg); @@ -4406,6 +4407,8 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) } flags_complete: + changed_flags = orig_flags ^ new_flags; + /* Before we finalize any flag changes, we need to perform some * checks to ensure that the changes are supported and safe. */ @@ -4415,21 +4418,17 @@ flags_complete: !(pf->hw_features & I40E_HW_ATR_EVICT_CAPABLE)) return -EOPNOTSUPP; - /* Disable FW LLDP not supported if NPAR active or if FW - * API version < 1.7 + /* If the driver detected FW LLDP was disabled on init, this flag could + * be set, however we do not support _changing_ the flag if NPAR is + * enabled or FW API version < 1.7. There are situations where older + * FW versions/NPAR enabled PFs could disable LLDP, however we _must_ + * not allow the user to enable/disable LLDP with this flag on + * unsupported FW versions. */ - if (new_flags & I40E_FLAG_DISABLE_FW_LLDP) { - if (pf->hw.func_caps.npar_enable) { - dev_warn(&pf->pdev->dev, - "Unable to stop FW LLDP if NPAR active\n"); - return -EOPNOTSUPP; - } - - if (pf->hw.aq.api_maj_ver < 1 || - (pf->hw.aq.api_maj_ver == 1 && - pf->hw.aq.api_min_ver < 7)) { + if (changed_flags & I40E_FLAG_DISABLE_FW_LLDP) { + if (!(pf->hw_features & I40E_HW_STOPPABLE_FW_LLDP)) { dev_warn(&pf->pdev->dev, - "FW ver does not support stopping FW LLDP\n"); + "Device does not support changing FW LLDP\n"); return -EOPNOTSUPP; } } @@ -4439,6 +4438,10 @@ flags_complete: * something else has modified the flags variable since we copied it * originally. We'll just punt with an error and log something in the * message buffer. + * + * This is the point of no return for this function. We need to have + * checked any discrepancies or misconfigurations and returned + * EOPNOTSUPP before updating pf->flags here. */ if (cmpxchg64(&pf->flags, orig_flags, new_flags) != orig_flags) { dev_warn(&pf->pdev->dev, @@ -4446,8 +4449,6 @@ flags_complete: return -EAGAIN; } - changed_flags = orig_flags ^ new_flags; - /* Process any additional changes needed as a result of flag changes. * The changed_flags value reflects the list of bits that were * changed in the code above. @@ -4479,6 +4480,12 @@ flags_complete: } } + if ((changed_flags & pf->flags & + I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED) && + (pf->flags & I40E_FLAG_MFP_ENABLED)) + dev_warn(&pf->pdev->dev, + "Turning on link-down-on-close flag may affect other partitions\n"); + if (changed_flags & I40E_FLAG_DISABLE_FW_LLDP) { if (pf->flags & I40E_FLAG_DISABLE_FW_LLDP) { struct i40e_dcbx_config *dcbcfg; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index e31adbc75f9c..f6d37456f3b7 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -69,12 +69,6 @@ static int i40e_reset(struct i40e_pf *pf); static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired); static void i40e_fdir_sb_setup(struct i40e_pf *pf); static int i40e_veb_get_bw_info(struct i40e_veb *veb); -static int i40e_add_del_cloud_filter(struct i40e_vsi *vsi, - struct i40e_cloud_filter *filter, - bool add); -static int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi, - struct i40e_cloud_filter *filter, - bool add); static int i40e_get_capabilities(struct i40e_pf *pf, enum i40e_admin_queue_opc list_type); @@ -215,8 +209,8 @@ static int i40e_get_lump(struct i40e_pf *pf, struct i40e_lump_tracking *pile, if (!pile || needed == 0 || id >= I40E_PILE_VALID_BIT) { dev_info(&pf->pdev->dev, - "param err: pile=%p needed=%d id=0x%04x\n", - pile, needed, id); + "param err: pile=%s needed=%d id=0x%04x\n", + pile ? "<valid>" : "<null>", needed, id); return -EINVAL; } @@ -1380,14 +1374,7 @@ struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi, ether_addr_copy(f->macaddr, macaddr); f->vlan = vlan; - /* If we're in overflow promisc mode, set the state directly - * to failed, so we don't bother to try sending the filter - * to the hardware. - */ - if (test_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state)) - f->state = I40E_FILTER_FAILED; - else - f->state = I40E_FILTER_NEW; + f->state = I40E_FILTER_NEW; INIT_HLIST_NODE(&f->hlist); key = i40e_addr_to_hkey(macaddr); @@ -2116,17 +2103,16 @@ void i40e_aqc_del_filters(struct i40e_vsi *vsi, const char *vsi_name, * @list: the list of filters to send to firmware * @add_head: Position in the add hlist * @num_add: the number of filters to add - * @promisc_change: set to true on exit if promiscuous mode was forced on * * Send a request to firmware via AdminQ to add a chunk of filters. Will set - * promisc_changed to true if the firmware has run out of space for more - * filters. + * __I40E_VSI_OVERFLOW_PROMISC bit in vsi->state if the firmware has run out of + * space for more filters. */ static void i40e_aqc_add_filters(struct i40e_vsi *vsi, const char *vsi_name, struct i40e_aqc_add_macvlan_element_data *list, struct i40e_new_mac_filter *add_head, - int num_add, bool *promisc_changed) + int num_add) { struct i40e_hw *hw = &vsi->back->hw; int aq_err, fcnt; @@ -2136,7 +2122,6 @@ void i40e_aqc_add_filters(struct i40e_vsi *vsi, const char *vsi_name, fcnt = i40e_update_filter_state(num_add, list, add_head); if (fcnt != num_add) { - *promisc_changed = true; set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); dev_warn(&vsi->back->pdev->dev, "Error %s adding RX filters on %s, promiscuous mode forced on\n", @@ -2177,11 +2162,13 @@ i40e_aqc_broadcast_filter(struct i40e_vsi *vsi, const char *vsi_name, NULL); } - if (aq_ret) + if (aq_ret) { + set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); dev_warn(&vsi->back->pdev->dev, - "Error %s setting broadcast promiscuous mode on %s\n", + "Error %s, forcing overflow promiscuous on %s\n", i40e_aq_str(hw, hw->aq.asq_last_status), vsi_name); + } return aq_ret; } @@ -2267,9 +2254,9 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) struct i40e_mac_filter *f; struct i40e_new_mac_filter *new, *add_head = NULL; struct i40e_hw *hw = &vsi->back->hw; + bool old_overflow, new_overflow; unsigned int failed_filters = 0; unsigned int vlan_filters = 0; - bool promisc_changed = false; char vsi_name[16] = "PF"; int filter_list_len = 0; i40e_status aq_ret = 0; @@ -2291,6 +2278,8 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) usleep_range(1000, 2000); pf = vsi->back; + old_overflow = test_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); + if (vsi->netdev) { changed_flags = vsi->current_netdev_flags ^ vsi->netdev->flags; vsi->current_netdev_flags = vsi->netdev->flags; @@ -2423,12 +2412,6 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) num_add = 0; hlist_for_each_entry_safe(new, h, &tmp_add_list, hlist) { - if (test_bit(__I40E_VSI_OVERFLOW_PROMISC, - vsi->state)) { - new->state = I40E_FILTER_FAILED; - continue; - } - /* handle broadcast filters by updating the broadcast * promiscuous flag instead of adding a MAC filter. */ @@ -2464,15 +2447,14 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) /* flush a full buffer */ if (num_add == filter_list_len) { i40e_aqc_add_filters(vsi, vsi_name, add_list, - add_head, num_add, - &promisc_changed); + add_head, num_add); memset(add_list, 0, list_size); num_add = 0; } } if (num_add) { i40e_aqc_add_filters(vsi, vsi_name, add_list, add_head, - num_add, &promisc_changed); + num_add); } /* Now move all of the filters from the temp add list back to * the VSI's list. @@ -2501,24 +2483,16 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) } spin_unlock_bh(&vsi->mac_filter_hash_lock); - /* If promiscuous mode has changed, we need to calculate a new - * threshold for when we are safe to exit - */ - if (promisc_changed) - vsi->promisc_threshold = (vsi->active_filters * 3) / 4; - /* Check if we are able to exit overflow promiscuous mode. We can * safely exit if we didn't just enter, we no longer have any failed * filters, and we have reduced filters below the threshold value. */ - if (test_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state) && - !promisc_changed && !failed_filters && - (vsi->active_filters < vsi->promisc_threshold)) { + if (old_overflow && !failed_filters && + vsi->active_filters < vsi->promisc_threshold) { dev_info(&pf->pdev->dev, "filter logjam cleared on %s, leaving overflow promiscuous mode\n", vsi_name); clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); - promisc_changed = true; vsi->promisc_threshold = 0; } @@ -2528,6 +2502,14 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) goto out; } + new_overflow = test_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); + + /* If we are entering overflow promiscuous, we need to calculate a new + * threshold for when we are safe to exit + */ + if (!old_overflow && new_overflow) + vsi->promisc_threshold = (vsi->active_filters * 3) / 4; + /* check for changes in promiscuous modes */ if (changed_flags & IFF_ALLMULTI) { bool cur_multipromisc; @@ -2548,12 +2530,11 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) } } - if ((changed_flags & IFF_PROMISC) || promisc_changed) { + if ((changed_flags & IFF_PROMISC) || old_overflow != new_overflow) { bool cur_promisc; cur_promisc = (!!(vsi->current_netdev_flags & IFF_PROMISC) || - test_bit(__I40E_VSI_OVERFLOW_PROMISC, - vsi->state)); + new_overflow); aq_ret = i40e_set_promiscuous(pf, cur_promisc); if (aq_ret) { retval = i40e_aq_rc_to_posix(aq_ret, @@ -3449,15 +3430,20 @@ static void i40e_vsi_configure_msix(struct i40e_vsi *vsi) for (i = 0; i < vsi->num_q_vectors; i++, vector++) { struct i40e_q_vector *q_vector = vsi->q_vectors[i]; - q_vector->itr_countdown = ITR_COUNTDOWN_START; - q_vector->rx.itr = ITR_TO_REG(vsi->rx_rings[i]->rx_itr_setting); - q_vector->rx.latency_range = I40E_LOW_LATENCY; + q_vector->rx.next_update = jiffies + 1; + q_vector->rx.target_itr = + ITR_TO_REG(vsi->rx_rings[i]->itr_setting); wr32(hw, I40E_PFINT_ITRN(I40E_RX_ITR, vector - 1), - q_vector->rx.itr); - q_vector->tx.itr = ITR_TO_REG(vsi->tx_rings[i]->tx_itr_setting); - q_vector->tx.latency_range = I40E_LOW_LATENCY; + q_vector->rx.target_itr); + q_vector->rx.current_itr = q_vector->rx.target_itr; + + q_vector->tx.next_update = jiffies + 1; + q_vector->tx.target_itr = + ITR_TO_REG(vsi->tx_rings[i]->itr_setting); wr32(hw, I40E_PFINT_ITRN(I40E_TX_ITR, vector - 1), - q_vector->tx.itr); + q_vector->tx.target_itr); + q_vector->tx.current_itr = q_vector->tx.target_itr; + wr32(hw, I40E_PFINT_RATEN(vector - 1), i40e_intrl_usec_to_reg(vsi->int_rate_limit)); @@ -3558,13 +3544,14 @@ static void i40e_configure_msi_and_legacy(struct i40e_vsi *vsi) u32 val; /* set the ITR configuration */ - q_vector->itr_countdown = ITR_COUNTDOWN_START; - q_vector->rx.itr = ITR_TO_REG(vsi->rx_rings[0]->rx_itr_setting); - q_vector->rx.latency_range = I40E_LOW_LATENCY; - wr32(hw, I40E_PFINT_ITR0(I40E_RX_ITR), q_vector->rx.itr); - q_vector->tx.itr = ITR_TO_REG(vsi->tx_rings[0]->tx_itr_setting); - q_vector->tx.latency_range = I40E_LOW_LATENCY; - wr32(hw, I40E_PFINT_ITR0(I40E_TX_ITR), q_vector->tx.itr); + q_vector->rx.next_update = jiffies + 1; + q_vector->rx.target_itr = ITR_TO_REG(vsi->rx_rings[0]->itr_setting); + wr32(hw, I40E_PFINT_ITR0(I40E_RX_ITR), q_vector->rx.target_itr); + q_vector->rx.current_itr = q_vector->rx.target_itr; + q_vector->tx.next_update = jiffies + 1; + q_vector->tx.target_itr = ITR_TO_REG(vsi->tx_rings[0]->itr_setting); + wr32(hw, I40E_PFINT_ITR0(I40E_TX_ITR), q_vector->tx.target_itr); + q_vector->tx.current_itr = q_vector->tx.target_itr; i40e_enable_misc_int_causes(pf); @@ -5375,7 +5362,7 @@ out: * @vsi: VSI to be configured * **/ -int i40e_get_link_speed(struct i40e_vsi *vsi) +static int i40e_get_link_speed(struct i40e_vsi *vsi) { struct i40e_pf *pf = vsi->back; @@ -6848,8 +6835,8 @@ i40e_set_cld_element(struct i40e_cloud_filter *filter, * Add or delete a cloud filter for a specific flow spec. * Returns 0 if the filter were successfully added. **/ -static int i40e_add_del_cloud_filter(struct i40e_vsi *vsi, - struct i40e_cloud_filter *filter, bool add) +int i40e_add_del_cloud_filter(struct i40e_vsi *vsi, + struct i40e_cloud_filter *filter, bool add) { struct i40e_aqc_cloud_filters_element_data cld_filter; struct i40e_pf *pf = vsi->back; @@ -6915,9 +6902,9 @@ static int i40e_add_del_cloud_filter(struct i40e_vsi *vsi, * Add or delete a cloud filter for a specific flow spec using big buffer. * Returns 0 if the filter were successfully added. **/ -static int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi, - struct i40e_cloud_filter *filter, - bool add) +int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi, + struct i40e_cloud_filter *filter, + bool add) { struct i40e_aqc_cloud_filters_element_bb cld_filter; struct i40e_pf *pf = vsi->back; @@ -9215,6 +9202,17 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) } i40e_get_oem_version(&pf->hw); + if (test_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state) && + ((hw->aq.fw_maj_ver == 4 && hw->aq.fw_min_ver <= 33) || + hw->aq.fw_maj_ver < 4) && hw->mac.type == I40E_MAC_XL710) { + /* The following delay is necessary for 4.33 firmware and older + * to recover after EMP reset. 200 ms should suffice but we + * put here 300 ms to be sure that FW is ready to operate + * after reset. + */ + mdelay(300); + } + /* re-verify the eeprom if we just had an EMP reset */ if (test_and_clear_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state)) i40e_verify_eeprom(pf); @@ -9937,18 +9935,17 @@ static int i40e_vsi_clear(struct i40e_vsi *vsi) mutex_lock(&pf->switch_mutex); if (!pf->vsi[vsi->idx]) { - dev_err(&pf->pdev->dev, "pf->vsi[%d] is NULL, just free vsi[%d](%p,type %d)\n", - vsi->idx, vsi->idx, vsi, vsi->type); + dev_err(&pf->pdev->dev, "pf->vsi[%d] is NULL, just free vsi[%d](type %d)\n", + vsi->idx, vsi->idx, vsi->type); goto unlock_vsi; } if (pf->vsi[vsi->idx] != vsi) { dev_err(&pf->pdev->dev, - "pf->vsi[%d](%p, type %d) != vsi[%d](%p,type %d): no free!\n", + "pf->vsi[%d](type %d) != vsi[%d](type %d): no free!\n", pf->vsi[vsi->idx]->idx, - pf->vsi[vsi->idx], pf->vsi[vsi->idx]->type, - vsi->idx, vsi, vsi->type); + vsi->idx, vsi->type); goto unlock_vsi; } @@ -10018,7 +10015,7 @@ static int i40e_alloc_rings(struct i40e_vsi *vsi) ring->dcb_tc = 0; if (vsi->back->hw_features & I40E_HW_WB_ON_ITR_CAPABLE) ring->flags = I40E_TXR_FLAGS_WB_ON_ITR; - ring->tx_itr_setting = pf->tx_itr_default; + ring->itr_setting = pf->tx_itr_default; vsi->tx_rings[i] = ring++; if (!i40e_enabled_xdp_vsi(vsi)) @@ -10036,7 +10033,7 @@ static int i40e_alloc_rings(struct i40e_vsi *vsi) if (vsi->back->hw_features & I40E_HW_WB_ON_ITR_CAPABLE) ring->flags = I40E_TXR_FLAGS_WB_ON_ITR; set_ring_xdp(ring); - ring->tx_itr_setting = pf->tx_itr_default; + ring->itr_setting = pf->tx_itr_default; vsi->xdp_rings[i] = ring++; setup_rx: @@ -10049,7 +10046,7 @@ setup_rx: ring->count = vsi->num_desc; ring->size = 0; ring->dcb_tc = 0; - ring->rx_itr_setting = pf->rx_itr_default; + ring->itr_setting = pf->rx_itr_default; vsi->rx_rings[i] = ring; } @@ -10328,9 +10325,6 @@ static int i40e_vsi_alloc_q_vector(struct i40e_vsi *vsi, int v_idx, int cpu) netif_napi_add(vsi->netdev, &q_vector->napi, i40e_napi_poll, NAPI_POLL_WEIGHT); - q_vector->rx.latency_range = I40E_LOW_LATENCY; - q_vector->tx.latency_range = I40E_LOW_LATENCY; - /* tie q_vector and vsi together */ vsi->q_vectors[v_idx] = q_vector; @@ -11089,6 +11083,16 @@ static int i40e_sw_init(struct i40e_pf *pf) /* IWARP needs one extra vector for CQP just like MISC.*/ pf->num_iwarp_msix = (int)num_online_cpus() + 1; } + /* Stopping the FW LLDP engine is only supported on the + * XL710 with a FW ver >= 1.7. Also, stopping FW LLDP + * engine is not supported if NPAR is functioning on this + * part + */ + if (pf->hw.mac.type == I40E_MAC_XL710 && + !pf->hw.func_caps.npar_enable && + (pf->hw.aq.api_maj_ver > 1 || + (pf->hw.aq.api_maj_ver == 1 && pf->hw.aq.api_min_ver > 6))) + pf->hw_features |= I40E_HW_STOPPABLE_FW_LLDP; #ifdef CONFIG_PCI_IOV if (pf->hw.func_caps.num_vfs && pf->hw.partition_id == 1) { diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index e554aa6cf070..1ec9b1d8023d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -995,99 +995,241 @@ void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) } } +static inline bool i40e_container_is_rx(struct i40e_q_vector *q_vector, + struct i40e_ring_container *rc) +{ + return &q_vector->rx == rc; +} + +static inline unsigned int i40e_itr_divisor(struct i40e_q_vector *q_vector) +{ + unsigned int divisor; + + switch (q_vector->vsi->back->hw.phy.link_info.link_speed) { + case I40E_LINK_SPEED_40GB: + divisor = I40E_ITR_ADAPTIVE_MIN_INC * 1024; + break; + case I40E_LINK_SPEED_25GB: + case I40E_LINK_SPEED_20GB: + divisor = I40E_ITR_ADAPTIVE_MIN_INC * 512; + break; + default: + case I40E_LINK_SPEED_10GB: + divisor = I40E_ITR_ADAPTIVE_MIN_INC * 256; + break; + case I40E_LINK_SPEED_1GB: + case I40E_LINK_SPEED_100MB: + divisor = I40E_ITR_ADAPTIVE_MIN_INC * 32; + break; + } + + return divisor; +} + /** - * i40e_set_new_dynamic_itr - Find new ITR level + * i40e_update_itr - update the dynamic ITR value based on statistics + * @q_vector: structure containing interrupt and ring information * @rc: structure containing ring performance data * - * Returns true if ITR changed, false if not - * - * Stores a new ITR value based on packets and byte counts during - * the last interrupt. The advantage of per interrupt computation - * is faster updates and more accurate ITR for the current traffic - * pattern. Constants in this function were computed based on - * theoretical maximum wire speed and thresholds were set based on - * testing data as well as attempting to minimize response time + * Stores a new ITR value based on packets and byte + * counts during the last interrupt. The advantage of per interrupt + * computation is faster updates and more accurate ITR for the current + * traffic pattern. Constants in this function were computed + * based on theoretical maximum wire speed and thresholds were set based + * on testing data as well as attempting to minimize response time * while increasing bulk throughput. **/ -static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) +static void i40e_update_itr(struct i40e_q_vector *q_vector, + struct i40e_ring_container *rc) { - enum i40e_latency_range new_latency_range = rc->latency_range; - u32 new_itr = rc->itr; - int bytes_per_usec; - unsigned int usecs, estimated_usecs; + unsigned int avg_wire_size, packets, bytes, itr; + unsigned long next_update = jiffies; - if (rc->total_packets == 0 || !rc->itr) - return false; + /* If we don't have any rings just leave ourselves set for maximum + * possible latency so we take ourselves out of the equation. + */ + if (!rc->ring || !ITR_IS_DYNAMIC(rc->ring->itr_setting)) + return; - usecs = (rc->itr << 1) * ITR_COUNTDOWN_START; - bytes_per_usec = rc->total_bytes / usecs; + /* For Rx we want to push the delay up and default to low latency. + * for Tx we want to pull the delay down and default to high latency. + */ + itr = i40e_container_is_rx(q_vector, rc) ? + I40E_ITR_ADAPTIVE_MIN_USECS | I40E_ITR_ADAPTIVE_LATENCY : + I40E_ITR_ADAPTIVE_MAX_USECS | I40E_ITR_ADAPTIVE_LATENCY; + + /* If we didn't update within up to 1 - 2 jiffies we can assume + * that either packets are coming in so slow there hasn't been + * any work, or that there is so much work that NAPI is dealing + * with interrupt moderation and we don't need to do anything. + */ + if (time_after(next_update, rc->next_update)) + goto clear_counts; + + /* If itr_countdown is set it means we programmed an ITR within + * the last 4 interrupt cycles. This has a side effect of us + * potentially firing an early interrupt. In order to work around + * this we need to throw out any data received for a few + * interrupts following the update. + */ + if (q_vector->itr_countdown) { + itr = rc->target_itr; + goto clear_counts; + } + + packets = rc->total_packets; + bytes = rc->total_bytes; - /* The calculations in this algorithm depend on interrupts actually - * firing at the ITR rate. This may not happen if the packet rate is - * really low, or if we've been napi polling. Check to make sure - * that's not the case before we continue. + if (i40e_container_is_rx(q_vector, rc)) { + /* If Rx there are 1 to 4 packets and bytes are less than + * 9000 assume insufficient data to use bulk rate limiting + * approach unless Tx is already in bulk rate limiting. We + * are likely latency driven. + */ + if (packets && packets < 4 && bytes < 9000 && + (q_vector->tx.target_itr & I40E_ITR_ADAPTIVE_LATENCY)) { + itr = I40E_ITR_ADAPTIVE_LATENCY; + goto adjust_by_size; + } + } else if (packets < 4) { + /* If we have Tx and Rx ITR maxed and Tx ITR is running in + * bulk mode and we are receiving 4 or fewer packets just + * reset the ITR_ADAPTIVE_LATENCY bit for latency mode so + * that the Rx can relax. + */ + if (rc->target_itr == I40E_ITR_ADAPTIVE_MAX_USECS && + (q_vector->rx.target_itr & I40E_ITR_MASK) == + I40E_ITR_ADAPTIVE_MAX_USECS) + goto clear_counts; + } else if (packets > 32) { + /* If we have processed over 32 packets in a single interrupt + * for Tx assume we need to switch over to "bulk" mode. + */ + rc->target_itr &= ~I40E_ITR_ADAPTIVE_LATENCY; + } + + /* We have no packets to actually measure against. This means + * either one of the other queues on this vector is active or + * we are a Tx queue doing TSO with too high of an interrupt rate. + * + * Between 4 and 56 we can assume that our current interrupt delay + * is only slightly too low. As such we should increase it by a small + * fixed amount. */ - estimated_usecs = jiffies_to_usecs(jiffies - rc->last_itr_update); - if (estimated_usecs > usecs) { - new_latency_range = I40E_LOW_LATENCY; - goto reset_latency; + if (packets < 56) { + itr = rc->target_itr + I40E_ITR_ADAPTIVE_MIN_INC; + if ((itr & I40E_ITR_MASK) > I40E_ITR_ADAPTIVE_MAX_USECS) { + itr &= I40E_ITR_ADAPTIVE_LATENCY; + itr += I40E_ITR_ADAPTIVE_MAX_USECS; + } + goto clear_counts; } - /* simple throttlerate management - * 0-10MB/s lowest (50000 ints/s) - * 10-20MB/s low (20000 ints/s) - * 20-1249MB/s bulk (18000 ints/s) + if (packets <= 256) { + itr = min(q_vector->tx.current_itr, q_vector->rx.current_itr); + itr &= I40E_ITR_MASK; + + /* Between 56 and 112 is our "goldilocks" zone where we are + * working out "just right". Just report that our current + * ITR is good for us. + */ + if (packets <= 112) + goto clear_counts; + + /* If packet count is 128 or greater we are likely looking + * at a slight overrun of the delay we want. Try halving + * our delay to see if that will cut the number of packets + * in half per interrupt. + */ + itr /= 2; + itr &= I40E_ITR_MASK; + if (itr < I40E_ITR_ADAPTIVE_MIN_USECS) + itr = I40E_ITR_ADAPTIVE_MIN_USECS; + + goto clear_counts; + } + + /* The paths below assume we are dealing with a bulk ITR since + * number of packets is greater than 256. We are just going to have + * to compute a value and try to bring the count under control, + * though for smaller packet sizes there isn't much we can do as + * NAPI polling will likely be kicking in sooner rather than later. + */ + itr = I40E_ITR_ADAPTIVE_BULK; + +adjust_by_size: + /* If packet counts are 256 or greater we can assume we have a gross + * overestimation of what the rate should be. Instead of trying to fine + * tune it just use the formula below to try and dial in an exact value + * give the current packet size of the frame. + */ + avg_wire_size = bytes / packets; + + /* The following is a crude approximation of: + * wmem_default / (size + overhead) = desired_pkts_per_int + * rate / bits_per_byte / (size + ethernet overhead) = pkt_rate + * (desired_pkt_rate / pkt_rate) * usecs_per_sec = ITR value * - * The math works out because the divisor is in 10^(-6) which - * turns the bytes/us input value into MB/s values, but - * make sure to use usecs, as the register values written - * are in 2 usec increments in the ITR registers, and make sure - * to use the smoothed values that the countdown timer gives us. + * Assuming wmem_default is 212992 and overhead is 640 bytes per + * packet, (256 skb, 64 headroom, 320 shared info), we can reduce the + * formula down to + * + * (170 * (size + 24)) / (size + 640) = ITR + * + * We first do some math on the packet size and then finally bitshift + * by 8 after rounding up. We also have to account for PCIe link speed + * difference as ITR scales based on this. */ - switch (new_latency_range) { - case I40E_LOWEST_LATENCY: - if (bytes_per_usec > 10) - new_latency_range = I40E_LOW_LATENCY; - break; - case I40E_LOW_LATENCY: - if (bytes_per_usec > 20) - new_latency_range = I40E_BULK_LATENCY; - else if (bytes_per_usec <= 10) - new_latency_range = I40E_LOWEST_LATENCY; - break; - case I40E_BULK_LATENCY: - default: - if (bytes_per_usec <= 20) - new_latency_range = I40E_LOW_LATENCY; - break; + if (avg_wire_size <= 60) { + /* Start at 250k ints/sec */ + avg_wire_size = 4096; + } else if (avg_wire_size <= 380) { + /* 250K ints/sec to 60K ints/sec */ + avg_wire_size *= 40; + avg_wire_size += 1696; + } else if (avg_wire_size <= 1084) { + /* 60K ints/sec to 36K ints/sec */ + avg_wire_size *= 15; + avg_wire_size += 11452; + } else if (avg_wire_size <= 1980) { + /* 36K ints/sec to 30K ints/sec */ + avg_wire_size *= 5; + avg_wire_size += 22420; + } else { + /* plateau at a limit of 30K ints/sec */ + avg_wire_size = 32256; } -reset_latency: - rc->latency_range = new_latency_range; + /* If we are in low latency mode halve our delay which doubles the + * rate to somewhere between 100K to 16K ints/sec + */ + if (itr & I40E_ITR_ADAPTIVE_LATENCY) + avg_wire_size /= 2; - switch (new_latency_range) { - case I40E_LOWEST_LATENCY: - new_itr = I40E_ITR_50K; - break; - case I40E_LOW_LATENCY: - new_itr = I40E_ITR_20K; - break; - case I40E_BULK_LATENCY: - new_itr = I40E_ITR_18K; - break; - default: - break; + /* Resultant value is 256 times larger than it needs to be. This + * gives us room to adjust the value as needed to either increase + * or decrease the value based on link speeds of 10G, 2.5G, 1G, etc. + * + * Use addition as we have already recorded the new latency flag + * for the ITR value. + */ + itr += DIV_ROUND_UP(avg_wire_size, i40e_itr_divisor(q_vector)) * + I40E_ITR_ADAPTIVE_MIN_INC; + + if ((itr & I40E_ITR_MASK) > I40E_ITR_ADAPTIVE_MAX_USECS) { + itr &= I40E_ITR_ADAPTIVE_LATENCY; + itr += I40E_ITR_ADAPTIVE_MAX_USECS; } +clear_counts: + /* write back value */ + rc->target_itr = itr; + + /* next update should occur within next jiffy */ + rc->next_update = next_update + 1; + rc->total_bytes = 0; rc->total_packets = 0; - rc->last_itr_update = jiffies; - - if (new_itr != rc->itr) { - rc->itr = new_itr; - return true; - } - return false; } /** @@ -1991,7 +2133,7 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, * @rx_buffer: rx buffer to pull data from * * This function will clean up the contents of the rx_buffer. It will - * either recycle the bufer or unmap it and free the associated resources. + * either recycle the buffer or unmap it and free the associated resources. */ static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, struct i40e_rx_buffer *rx_buffer) @@ -2274,29 +2416,45 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) return failure ? budget : (int)total_rx_packets; } -static u32 i40e_buildreg_itr(const int type, const u16 itr) +static inline u32 i40e_buildreg_itr(const int type, u16 itr) { u32 val; + /* We don't bother with setting the CLEARPBA bit as the data sheet + * points out doing so is "meaningless since it was already + * auto-cleared". The auto-clearing happens when the interrupt is + * asserted. + * + * Hardware errata 28 for also indicates that writing to a + * xxINT_DYN_CTLx CSR with INTENA_MSK (bit 31) set to 0 will clear + * an event in the PBA anyway so we need to rely on the automask + * to hold pending events for us until the interrupt is re-enabled + * + * The itr value is reported in microseconds, and the register + * value is recorded in 2 microsecond units. For this reason we + * only need to shift by the interval shift - 1 instead of the + * full value. + */ + itr &= I40E_ITR_MASK; + val = I40E_PFINT_DYN_CTLN_INTENA_MASK | - I40E_PFINT_DYN_CTLN_CLEARPBA_MASK | (type << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) | - (itr << I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT); + (itr << (I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT - 1)); return val; } /* a small macro to shorten up some long lines */ #define INTREG I40E_PFINT_DYN_CTLN -static inline int get_rx_itr(struct i40e_vsi *vsi, int idx) -{ - return vsi->rx_rings[idx]->rx_itr_setting; -} -static inline int get_tx_itr(struct i40e_vsi *vsi, int idx) -{ - return vsi->tx_rings[idx]->tx_itr_setting; -} +/* The act of updating the ITR will cause it to immediately trigger. In order + * to prevent this from throwing off adaptive update statistics we defer the + * update so that it can only happen so often. So after either Tx or Rx are + * updated we make the adaptive scheme wait until either the ITR completely + * expires via the next_update expiration or we have been through at least + * 3 interrupts. + */ +#define ITR_COUNTDOWN_START 3 /** * i40e_update_enable_itr - Update itr and re-enable MSIX interrupt @@ -2308,10 +2466,7 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) { struct i40e_hw *hw = &vsi->back->hw; - bool rx = false, tx = false; - u32 rxval, txval; - int idx = q_vector->v_idx; - int rx_itr_setting, tx_itr_setting; + u32 intval; /* If we don't have MSIX, then we only need to re-enable icr0 */ if (!(vsi->back->flags & I40E_FLAG_MSIX_ENABLED)) { @@ -2319,65 +2474,49 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, return; } - /* avoid dynamic calculation if in countdown mode OR if - * all dynamic is disabled - */ - rxval = txval = i40e_buildreg_itr(I40E_ITR_NONE, 0); - - rx_itr_setting = get_rx_itr(vsi, idx); - tx_itr_setting = get_tx_itr(vsi, idx); - - if (q_vector->itr_countdown > 0 || - (!ITR_IS_DYNAMIC(rx_itr_setting) && - !ITR_IS_DYNAMIC(tx_itr_setting))) { - goto enable_int; - } - - if (ITR_IS_DYNAMIC(rx_itr_setting)) { - rx = i40e_set_new_dynamic_itr(&q_vector->rx); - rxval = i40e_buildreg_itr(I40E_RX_ITR, q_vector->rx.itr); - } - - if (ITR_IS_DYNAMIC(tx_itr_setting)) { - tx = i40e_set_new_dynamic_itr(&q_vector->tx); - txval = i40e_buildreg_itr(I40E_TX_ITR, q_vector->tx.itr); - } + /* These will do nothing if dynamic updates are not enabled */ + i40e_update_itr(q_vector, &q_vector->tx); + i40e_update_itr(q_vector, &q_vector->rx); - if (rx || tx) { - /* get the higher of the two ITR adjustments and - * use the same value for both ITR registers - * when in adaptive mode (Rx and/or Tx) - */ - u16 itr = max(q_vector->tx.itr, q_vector->rx.itr); - - q_vector->tx.itr = q_vector->rx.itr = itr; - txval = i40e_buildreg_itr(I40E_TX_ITR, itr); - tx = true; - rxval = i40e_buildreg_itr(I40E_RX_ITR, itr); - rx = true; - } - - /* only need to enable the interrupt once, but need - * to possibly update both ITR values + /* This block of logic allows us to get away with only updating + * one ITR value with each interrupt. The idea is to perform a + * pseudo-lazy update with the following criteria. + * + * 1. Rx is given higher priority than Tx if both are in same state + * 2. If we must reduce an ITR that is given highest priority. + * 3. We then give priority to increasing ITR based on amount. */ - if (rx) { - /* set the INTENA_MSK_MASK so that this first write - * won't actually enable the interrupt, instead just - * updating the ITR (it's bit 31 PF and VF) + if (q_vector->rx.target_itr < q_vector->rx.current_itr) { + /* Rx ITR needs to be reduced, this is highest priority */ + intval = i40e_buildreg_itr(I40E_RX_ITR, + q_vector->rx.target_itr); + q_vector->rx.current_itr = q_vector->rx.target_itr; + q_vector->itr_countdown = ITR_COUNTDOWN_START; + } else if ((q_vector->tx.target_itr < q_vector->tx.current_itr) || + ((q_vector->rx.target_itr - q_vector->rx.current_itr) < + (q_vector->tx.target_itr - q_vector->tx.current_itr))) { + /* Tx ITR needs to be reduced, this is second priority + * Tx ITR needs to be increased more than Rx, fourth priority */ - rxval |= BIT(31); - /* don't check _DOWN because interrupt isn't being enabled */ - wr32(hw, INTREG(q_vector->reg_idx), rxval); + intval = i40e_buildreg_itr(I40E_TX_ITR, + q_vector->tx.target_itr); + q_vector->tx.current_itr = q_vector->tx.target_itr; + q_vector->itr_countdown = ITR_COUNTDOWN_START; + } else if (q_vector->rx.current_itr != q_vector->rx.target_itr) { + /* Rx ITR needs to be increased, third priority */ + intval = i40e_buildreg_itr(I40E_RX_ITR, + q_vector->rx.target_itr); + q_vector->rx.current_itr = q_vector->rx.target_itr; + q_vector->itr_countdown = ITR_COUNTDOWN_START; + } else { + /* No ITR update, lowest priority */ + intval = i40e_buildreg_itr(I40E_ITR_NONE, 0); + if (q_vector->itr_countdown) + q_vector->itr_countdown--; } -enable_int: if (!test_bit(__I40E_VSI_DOWN, vsi->state)) - wr32(hw, INTREG(q_vector->reg_idx), txval); - - if (q_vector->itr_countdown) - q_vector->itr_countdown--; - else - q_vector->itr_countdown = ITR_COUNTDOWN_START; + wr32(hw, INTREG(q_vector->reg_idx), intval); } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 701b708628b0..f75a8fe68fcf 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -30,32 +30,37 @@ #include <net/xdp.h> /* Interrupt Throttling and Rate Limiting Goodies */ - -#define I40E_MAX_ITR 0x0FF0 /* reg uses 2 usec resolution */ -#define I40E_MIN_ITR 0x0001 /* reg uses 2 usec resolution */ -#define I40E_ITR_100K 0x0005 -#define I40E_ITR_50K 0x000A -#define I40E_ITR_20K 0x0019 -#define I40E_ITR_18K 0x001B -#define I40E_ITR_8K 0x003E -#define I40E_ITR_4K 0x007A -#define I40E_MAX_INTRL 0x3B /* reg uses 4 usec resolution */ -#define I40E_ITR_RX_DEF (ITR_REG_TO_USEC(I40E_ITR_20K) | \ - I40E_ITR_DYNAMIC) -#define I40E_ITR_TX_DEF (ITR_REG_TO_USEC(I40E_ITR_20K) | \ - I40E_ITR_DYNAMIC) -#define I40E_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ -#define I40E_MIN_INT_RATE 250 /* ~= 1000000 / (I40E_MAX_ITR * 2) */ -#define I40E_MAX_INT_RATE 500000 /* == 1000000 / (I40E_MIN_ITR * 2) */ #define I40E_DEFAULT_IRQ_WORK 256 -#define ITR_TO_REG(setting) ((setting & ~I40E_ITR_DYNAMIC) >> 1) -#define ITR_IS_DYNAMIC(setting) (!!(setting & I40E_ITR_DYNAMIC)) -#define ITR_REG_TO_USEC(itr_reg) (itr_reg << 1) + +/* The datasheet for the X710 and XL710 indicate that the maximum value for + * the ITR is 8160usec which is then called out as 0xFF0 with a 2usec + * resolution. 8160 is 0x1FE0 when written out in hex. So instead of storing + * the register value which is divided by 2 lets use the actual values and + * avoid an excessive amount of translation. + */ +#define I40E_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ +#define I40E_ITR_MASK 0x1FFE /* mask for ITR register value */ +#define I40E_MIN_ITR 2 /* reg uses 2 usec resolution */ +#define I40E_ITR_100K 10 /* all values below must be even */ +#define I40E_ITR_50K 20 +#define I40E_ITR_20K 50 +#define I40E_ITR_18K 60 +#define I40E_ITR_8K 122 +#define I40E_MAX_ITR 8160 /* maximum value as per datasheet */ +#define ITR_TO_REG(setting) ((setting) & ~I40E_ITR_DYNAMIC) +#define ITR_REG_ALIGN(setting) __ALIGN_MASK(setting, ~I40E_ITR_MASK) +#define ITR_IS_DYNAMIC(setting) (!!((setting) & I40E_ITR_DYNAMIC)) + +#define I40E_ITR_RX_DEF (I40E_ITR_20K | I40E_ITR_DYNAMIC) +#define I40E_ITR_TX_DEF (I40E_ITR_20K | I40E_ITR_DYNAMIC) + /* 0x40 is the enable bit for interrupt rate limiting, and must be set if * the value of the rate limit is non-zero */ #define INTRL_ENA BIT(6) +#define I40E_MAX_INTRL 0x3B /* reg uses 4 usec resolution */ #define INTRL_REG_TO_USEC(intrl) ((intrl & ~INTRL_ENA) << 2) + /** * i40e_intrl_usec_to_reg - convert interrupt rate limit to register * @intrl: interrupt rate limit to convert @@ -382,8 +387,7 @@ struct i40e_ring { * these values always store the USER setting, and must be converted * before programming to a register. */ - u16 rx_itr_setting; - u16 tx_itr_setting; + u16 itr_setting; u16 count; /* Number of descriptors */ u16 reg_idx; /* HW register index of the ring */ @@ -459,21 +463,21 @@ static inline void set_ring_xdp(struct i40e_ring *ring) ring->flags |= I40E_TXR_FLAGS_XDP; } -enum i40e_latency_range { - I40E_LOWEST_LATENCY = 0, - I40E_LOW_LATENCY = 1, - I40E_BULK_LATENCY = 2, -}; +#define I40E_ITR_ADAPTIVE_MIN_INC 0x0002 +#define I40E_ITR_ADAPTIVE_MIN_USECS 0x0002 +#define I40E_ITR_ADAPTIVE_MAX_USECS 0x007e +#define I40E_ITR_ADAPTIVE_LATENCY 0x8000 +#define I40E_ITR_ADAPTIVE_BULK 0x0000 +#define ITR_IS_BULK(x) (!((x) & I40E_ITR_ADAPTIVE_LATENCY)) struct i40e_ring_container { - /* array of pointers to rings */ - struct i40e_ring *ring; + struct i40e_ring *ring; /* pointer to linked list of ring(s) */ + unsigned long next_update; /* jiffies value of next update */ unsigned int total_bytes; /* total bytes processed this int */ unsigned int total_packets; /* total packets processed this int */ - unsigned long last_itr_update; /* jiffies of last ITR update */ u16 count; - enum i40e_latency_range latency_range; - u16 itr; + u16 target_itr; /* target ITR setting for ring(s) */ + u16 current_itr; /* current ITR setting for ring(s) */ }; /* iterator for handling rings in ring container */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index cd294e6a8587..b0eed8c0b2f2 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -39,7 +39,7 @@ #define I40E_MASK(mask, shift) ((u32)(mask) << (shift)) #define I40E_MAX_VSI_QP 16 -#define I40E_MAX_VF_VSI 3 +#define I40E_MAX_VF_VSI 4 #define I40E_MAX_CHAINED_RX_BUFFERS 5 #define I40E_MAX_PF_UDP_OFFLOAD_PORTS 16 diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index e9309fb9084b..5cca083da93c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -258,6 +258,38 @@ static u16 i40e_vc_get_pf_queue_id(struct i40e_vf *vf, u16 vsi_id, } /** + * i40e_get_real_pf_qid + * @vf: pointer to the VF info + * @vsi_id: vsi id + * @queue_id: queue number + * + * wrapper function to get pf_queue_id handling ADq code as well + **/ +static u16 i40e_get_real_pf_qid(struct i40e_vf *vf, u16 vsi_id, u16 queue_id) +{ + int i; + + if (vf->adq_enabled) { + /* Although VF considers all the queues(can be 1 to 16) as its + * own but they may actually belong to different VSIs(up to 4). + * We need to find which queues belongs to which VSI. + */ + for (i = 0; i < vf->num_tc; i++) { + if (queue_id < vf->ch[i].num_qps) { + vsi_id = vf->ch[i].vsi_id; + break; + } + /* find right queue id which is relative to a + * given VSI. + */ + queue_id -= vf->ch[i].num_qps; + } + } + + return i40e_vc_get_pf_queue_id(vf, vsi_id, queue_id); +} + +/** * i40e_config_irq_link_list * @vf: pointer to the VF info * @vsi_id: id of VSI as given by the FW @@ -310,7 +342,7 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id, vsi_queue_id = next_q / I40E_VIRTCHNL_SUPPORTED_QTYPES; qtype = next_q % I40E_VIRTCHNL_SUPPORTED_QTYPES; - pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_id, vsi_queue_id); + pf_queue_id = i40e_get_real_pf_qid(vf, vsi_id, vsi_queue_id); reg = ((qtype << I40E_VPINT_LNKLSTN_FIRSTQ_TYPE_SHIFT) | pf_queue_id); wr32(hw, reg_idx, reg); @@ -333,8 +365,9 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id, if (next_q < size) { vsi_queue_id = next_q / I40E_VIRTCHNL_SUPPORTED_QTYPES; qtype = next_q % I40E_VIRTCHNL_SUPPORTED_QTYPES; - pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_id, - vsi_queue_id); + pf_queue_id = i40e_get_real_pf_qid(vf, + vsi_id, + vsi_queue_id); } else { pf_queue_id = I40E_QUEUE_END_OF_LIST; qtype = 0; @@ -669,18 +702,20 @@ error_param: /** * i40e_alloc_vsi_res * @vf: pointer to the VF info - * @type: type of VSI to allocate + * @idx: VSI index, applies only for ADq mode, zero otherwise * * alloc VF vsi context & resources **/ -static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type) +static int i40e_alloc_vsi_res(struct i40e_vf *vf, u8 idx) { struct i40e_mac_filter *f = NULL; struct i40e_pf *pf = vf->pf; struct i40e_vsi *vsi; + u64 max_tx_rate = 0; int ret = 0; - vsi = i40e_vsi_setup(pf, type, pf->vsi[pf->lan_vsi]->seid, vf->vf_id); + vsi = i40e_vsi_setup(pf, I40E_VSI_SRIOV, pf->vsi[pf->lan_vsi]->seid, + vf->vf_id); if (!vsi) { dev_err(&pf->pdev->dev, @@ -689,7 +724,8 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type) ret = -ENOENT; goto error_alloc_vsi_res; } - if (type == I40E_VSI_SRIOV) { + + if (!idx) { u64 hena = i40e_pf_get_default_rss_hena(pf); u8 broadcast[ETH_ALEN]; @@ -721,17 +757,29 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type) spin_unlock_bh(&vsi->mac_filter_hash_lock); wr32(&pf->hw, I40E_VFQF_HENA1(0, vf->vf_id), (u32)hena); wr32(&pf->hw, I40E_VFQF_HENA1(1, vf->vf_id), (u32)(hena >> 32)); + /* program mac filter only for VF VSI */ + ret = i40e_sync_vsi_filters(vsi); + if (ret) + dev_err(&pf->pdev->dev, "Unable to program ucast filters\n"); } - /* program mac filter */ - ret = i40e_sync_vsi_filters(vsi); - if (ret) - dev_err(&pf->pdev->dev, "Unable to program ucast filters\n"); + /* storing VSI index and id for ADq and don't apply the mac filter */ + if (vf->adq_enabled) { + vf->ch[idx].vsi_idx = vsi->idx; + vf->ch[idx].vsi_id = vsi->id; + } /* Set VF bandwidth if specified */ if (vf->tx_rate) { + max_tx_rate = vf->tx_rate; + } else if (vf->ch[idx].max_tx_rate) { + max_tx_rate = vf->ch[idx].max_tx_rate; + } + + if (max_tx_rate) { + max_tx_rate = div_u64(max_tx_rate, I40E_BW_CREDIT_DIVISOR); ret = i40e_aq_config_vsi_bw_limit(&pf->hw, vsi->seid, - vf->tx_rate / 50, 0, NULL); + max_tx_rate, 0, NULL); if (ret) dev_err(&pf->pdev->dev, "Unable to set tx rate, VF %d, error code %d.\n", vf->vf_id, ret); @@ -742,6 +790,92 @@ error_alloc_vsi_res: } /** + * i40e_map_pf_queues_to_vsi + * @vf: pointer to the VF info + * + * PF maps LQPs to a VF by programming VSILAN_QTABLE & VPLAN_QTABLE. This + * function takes care of first part VSILAN_QTABLE, mapping pf queues to VSI. + **/ +static void i40e_map_pf_queues_to_vsi(struct i40e_vf *vf) +{ + struct i40e_pf *pf = vf->pf; + struct i40e_hw *hw = &pf->hw; + u32 reg, num_tc = 1; /* VF has at least one traffic class */ + u16 vsi_id, qps; + int i, j; + + if (vf->adq_enabled) + num_tc = vf->num_tc; + + for (i = 0; i < num_tc; i++) { + if (vf->adq_enabled) { + qps = vf->ch[i].num_qps; + vsi_id = vf->ch[i].vsi_id; + } else { + qps = pf->vsi[vf->lan_vsi_idx]->alloc_queue_pairs; + vsi_id = vf->lan_vsi_id; + } + + for (j = 0; j < 7; j++) { + if (j * 2 >= qps) { + /* end of list */ + reg = 0x07FF07FF; + } else { + u16 qid = i40e_vc_get_pf_queue_id(vf, + vsi_id, + j * 2); + reg = qid; + qid = i40e_vc_get_pf_queue_id(vf, vsi_id, + (j * 2) + 1); + reg |= qid << 16; + } + i40e_write_rx_ctl(hw, + I40E_VSILAN_QTABLE(j, vsi_id), + reg); + } + } +} + +/** + * i40e_map_pf_to_vf_queues + * @vf: pointer to the VF info + * + * PF maps LQPs to a VF by programming VSILAN_QTABLE & VPLAN_QTABLE. This + * function takes care of the second part VPLAN_QTABLE & completes VF mappings. + **/ +static void i40e_map_pf_to_vf_queues(struct i40e_vf *vf) +{ + struct i40e_pf *pf = vf->pf; + struct i40e_hw *hw = &pf->hw; + u32 reg, total_qps = 0; + u32 qps, num_tc = 1; /* VF has at least one traffic class */ + u16 vsi_id, qid; + int i, j; + + if (vf->adq_enabled) + num_tc = vf->num_tc; + + for (i = 0; i < num_tc; i++) { + if (vf->adq_enabled) { + qps = vf->ch[i].num_qps; + vsi_id = vf->ch[i].vsi_id; + } else { + qps = pf->vsi[vf->lan_vsi_idx]->alloc_queue_pairs; + vsi_id = vf->lan_vsi_id; + } + + for (j = 0; j < qps; j++) { + qid = i40e_vc_get_pf_queue_id(vf, vsi_id, j); + + reg = (qid & I40E_VPLAN_QTABLE_QINDEX_MASK); + wr32(hw, I40E_VPLAN_QTABLE(total_qps, vf->vf_id), + reg); + total_qps++; + } + } +} + +/** * i40e_enable_vf_mappings * @vf: pointer to the VF info * @@ -751,8 +885,7 @@ static void i40e_enable_vf_mappings(struct i40e_vf *vf) { struct i40e_pf *pf = vf->pf; struct i40e_hw *hw = &pf->hw; - u32 reg, total_queue_pairs = 0; - int j; + u32 reg; /* Tell the hardware we're using noncontiguous mapping. HW requires * that VF queues be mapped using this method, even when they are @@ -765,30 +898,8 @@ static void i40e_enable_vf_mappings(struct i40e_vf *vf) reg = I40E_VPLAN_MAPENA_TXRX_ENA_MASK; wr32(hw, I40E_VPLAN_MAPENA(vf->vf_id), reg); - /* map PF queues to VF queues */ - for (j = 0; j < pf->vsi[vf->lan_vsi_idx]->alloc_queue_pairs; j++) { - u16 qid = i40e_vc_get_pf_queue_id(vf, vf->lan_vsi_id, j); - - reg = (qid & I40E_VPLAN_QTABLE_QINDEX_MASK); - wr32(hw, I40E_VPLAN_QTABLE(total_queue_pairs, vf->vf_id), reg); - total_queue_pairs++; - } - - /* map PF queues to VSI */ - for (j = 0; j < 7; j++) { - if (j * 2 >= pf->vsi[vf->lan_vsi_idx]->alloc_queue_pairs) { - reg = 0x07FF07FF; /* unused */ - } else { - u16 qid = i40e_vc_get_pf_queue_id(vf, vf->lan_vsi_id, - j * 2); - reg = qid; - qid = i40e_vc_get_pf_queue_id(vf, vf->lan_vsi_id, - (j * 2) + 1); - reg |= qid << 16; - } - i40e_write_rx_ctl(hw, I40E_VSILAN_QTABLE(j, vf->lan_vsi_id), - reg); - } + i40e_map_pf_to_vf_queues(vf); + i40e_map_pf_queues_to_vsi(vf); i40e_flush(hw); } @@ -824,7 +935,7 @@ static void i40e_free_vf_res(struct i40e_vf *vf) struct i40e_pf *pf = vf->pf; struct i40e_hw *hw = &pf->hw; u32 reg_idx, reg; - int i, msix_vf; + int i, j, msix_vf; /* Start by disabling VF's configuration API to prevent the OS from * accessing the VF's VSI after it's freed / invalidated. @@ -846,6 +957,20 @@ static void i40e_free_vf_res(struct i40e_vf *vf) vf->lan_vsi_id = 0; vf->num_mac = 0; } + + /* do the accounting and remove additional ADq VSI's */ + if (vf->adq_enabled && vf->ch[0].vsi_idx) { + for (j = 0; j < vf->num_tc; j++) { + /* At this point VSI0 is already released so don't + * release it again and only clear their values in + * structure variables + */ + if (j) + i40e_vsi_release(pf->vsi[vf->ch[j].vsi_idx]); + vf->ch[j].vsi_idx = 0; + vf->ch[j].vsi_id = 0; + } + } msix_vf = pf->hw.func_caps.num_msix_vectors_vf; /* disable interrupts so the VF starts in a known state */ @@ -891,7 +1016,7 @@ static int i40e_alloc_vf_res(struct i40e_vf *vf) { struct i40e_pf *pf = vf->pf; int total_queue_pairs = 0; - int ret; + int ret, idx; if (vf->num_req_queues && vf->num_req_queues <= pf->queues_left + I40E_DEFAULT_QUEUES_PER_VF) @@ -900,11 +1025,30 @@ static int i40e_alloc_vf_res(struct i40e_vf *vf) pf->num_vf_qps = I40E_DEFAULT_QUEUES_PER_VF; /* allocate hw vsi context & associated resources */ - ret = i40e_alloc_vsi_res(vf, I40E_VSI_SRIOV); + ret = i40e_alloc_vsi_res(vf, 0); if (ret) goto error_alloc; total_queue_pairs += pf->vsi[vf->lan_vsi_idx]->alloc_queue_pairs; + /* allocate additional VSIs based on tc information for ADq */ + if (vf->adq_enabled) { + if (pf->queues_left >= + (I40E_MAX_VF_QUEUES - I40E_DEFAULT_QUEUES_PER_VF)) { + /* TC 0 always belongs to VF VSI */ + for (idx = 1; idx < vf->num_tc; idx++) { + ret = i40e_alloc_vsi_res(vf, idx); + if (ret) + goto error_alloc; + } + /* send correct number of queues */ + total_queue_pairs = I40E_MAX_VF_QUEUES; + } else { + dev_info(&pf->pdev->dev, "VF %d: Not enough queues to allocate, disabling ADq\n", + vf->vf_id); + vf->adq_enabled = false; + } + } + /* We account for each VF to get a default number of queue pairs. If * the VF has now requested more, we need to account for that to make * certain we never request more queues than we actually have left in @@ -1537,6 +1681,27 @@ static int i40e_vc_get_version_msg(struct i40e_vf *vf, u8 *msg) } /** + * i40e_del_qch - delete all the additional VSIs created as a part of ADq + * @vf: pointer to VF structure + **/ +static void i40e_del_qch(struct i40e_vf *vf) +{ + struct i40e_pf *pf = vf->pf; + int i; + + /* first element in the array belongs to primary VF VSI and we shouldn't + * delete it. We should however delete the rest of the VSIs created + */ + for (i = 1; i < vf->num_tc; i++) { + if (vf->ch[i].vsi_idx) { + i40e_vsi_release(pf->vsi[vf->ch[i].vsi_idx]); + vf->ch[i].vsi_idx = 0; + vf->ch[i].vsi_id = 0; + } + } +} + +/** * i40e_vc_get_vf_resources_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -1631,6 +1796,9 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg) if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_REQ_QUEUES) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_REQ_QUEUES; + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_ADQ) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_ADQ; + vfres->num_vsis = num_vsis; vfres->num_queue_pairs = vf->num_queue_pairs; vfres->max_vectors = pf->hw.func_caps.num_msix_vectors_vf; @@ -1855,27 +2023,37 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) (struct virtchnl_vsi_queue_config_info *)msg; struct virtchnl_queue_pair_info *qpi; struct i40e_pf *pf = vf->pf; - u16 vsi_id, vsi_queue_id; + u16 vsi_id, vsi_queue_id = 0; i40e_status aq_ret = 0; - int i; + int i, j = 0, idx = 0; + + vsi_id = qci->vsi_id; if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { aq_ret = I40E_ERR_PARAM; goto error_param; } - vsi_id = qci->vsi_id; if (!i40e_vc_isvalid_vsi_id(vf, vsi_id)) { aq_ret = I40E_ERR_PARAM; goto error_param; } + for (i = 0; i < qci->num_queue_pairs; i++) { qpi = &qci->qpair[i]; - vsi_queue_id = qpi->txq.queue_id; - if ((qpi->txq.vsi_id != vsi_id) || - (qpi->rxq.vsi_id != vsi_id) || - (qpi->rxq.queue_id != vsi_queue_id) || - !i40e_vc_isvalid_queue_id(vf, vsi_id, vsi_queue_id)) { + + if (!vf->adq_enabled) { + vsi_queue_id = qpi->txq.queue_id; + + if (qpi->txq.vsi_id != qci->vsi_id || + qpi->rxq.vsi_id != qci->vsi_id || + qpi->rxq.queue_id != vsi_queue_id) { + aq_ret = I40E_ERR_PARAM; + goto error_param; + } + } + + if (!i40e_vc_isvalid_queue_id(vf, vsi_id, vsi_queue_id)) { aq_ret = I40E_ERR_PARAM; goto error_param; } @@ -1887,9 +2065,33 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) aq_ret = I40E_ERR_PARAM; goto error_param; } + + /* For ADq there can be up to 4 VSIs with max 4 queues each. + * VF does not know about these additional VSIs and all + * it cares is about its own queues. PF configures these queues + * to its appropriate VSIs based on TC mapping + **/ + if (vf->adq_enabled) { + if (j == (vf->ch[idx].num_qps - 1)) { + idx++; + j = 0; /* resetting the queue count */ + vsi_queue_id = 0; + } else { + j++; + vsi_queue_id++; + } + vsi_id = vf->ch[idx].vsi_id; + } } /* set vsi num_queue_pairs in use to num configured by VF */ - pf->vsi[vf->lan_vsi_idx]->num_queue_pairs = qci->num_queue_pairs; + if (!vf->adq_enabled) { + pf->vsi[vf->lan_vsi_idx]->num_queue_pairs = + qci->num_queue_pairs; + } else { + for (i = 0; i < vf->num_tc; i++) + pf->vsi[vf->ch[i].vsi_idx]->num_queue_pairs = + vf->ch[i].num_qps; + } error_param: /* send the response to the VF */ @@ -1898,6 +2100,33 @@ error_param: } /** + * i40e_validate_queue_map + * @vsi_id: vsi id + * @queuemap: Tx or Rx queue map + * + * check if Tx or Rx queue map is valid + **/ +static int i40e_validate_queue_map(struct i40e_vf *vf, u16 vsi_id, + unsigned long queuemap) +{ + u16 vsi_queue_id, queue_id; + + for_each_set_bit(vsi_queue_id, &queuemap, I40E_MAX_VSI_QP) { + if (vf->adq_enabled) { + vsi_id = vf->ch[vsi_queue_id / I40E_MAX_VF_VSI].vsi_id; + queue_id = (vsi_queue_id % I40E_DEFAULT_QUEUES_PER_VF); + } else { + queue_id = vsi_queue_id; + } + + if (!i40e_vc_isvalid_queue_id(vf, vsi_id, queue_id)) + return -EINVAL; + } + + return 0; +} + +/** * i40e_vc_config_irq_map_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -1911,9 +2140,8 @@ static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) struct virtchnl_irq_map_info *irqmap_info = (struct virtchnl_irq_map_info *)msg; struct virtchnl_vector_map *map; - u16 vsi_id, vsi_queue_id, vector_id; + u16 vsi_id, vector_id; i40e_status aq_ret = 0; - unsigned long tempmap; int i; if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { @@ -1923,7 +2151,6 @@ static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) for (i = 0; i < irqmap_info->num_vectors; i++) { map = &irqmap_info->vecmap[i]; - vector_id = map->vector_id; vsi_id = map->vsi_id; /* validate msg params */ @@ -1933,23 +2160,14 @@ static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) goto error_param; } - /* lookout for the invalid queue index */ - tempmap = map->rxq_map; - for_each_set_bit(vsi_queue_id, &tempmap, I40E_MAX_VSI_QP) { - if (!i40e_vc_isvalid_queue_id(vf, vsi_id, - vsi_queue_id)) { - aq_ret = I40E_ERR_PARAM; - goto error_param; - } + if (i40e_validate_queue_map(vf, vsi_id, map->rxq_map)) { + aq_ret = I40E_ERR_PARAM; + goto error_param; } - tempmap = map->txq_map; - for_each_set_bit(vsi_queue_id, &tempmap, I40E_MAX_VSI_QP) { - if (!i40e_vc_isvalid_queue_id(vf, vsi_id, - vsi_queue_id)) { - aq_ret = I40E_ERR_PARAM; - goto error_param; - } + if (i40e_validate_queue_map(vf, vsi_id, map->txq_map)) { + aq_ret = I40E_ERR_PARAM; + goto error_param; } i40e_config_irq_link_list(vf, vsi_id, map); @@ -1975,6 +2193,7 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) struct i40e_pf *pf = vf->pf; u16 vsi_id = vqs->vsi_id; i40e_status aq_ret = 0; + int i; if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { aq_ret = I40E_ERR_PARAM; @@ -1993,6 +2212,16 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) if (i40e_vsi_start_rings(pf->vsi[vf->lan_vsi_idx])) aq_ret = I40E_ERR_TIMEOUT; + + /* need to start the rings for additional ADq VSI's as well */ + if (vf->adq_enabled) { + /* zero belongs to LAN VSI */ + for (i = 1; i < vf->num_tc; i++) { + if (i40e_vsi_start_rings(pf->vsi[vf->ch[i].vsi_idx])) + aq_ret = I40E_ERR_TIMEOUT; + } + } + error_param: /* send the response to the VF */ return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_ENABLE_QUEUES, @@ -2688,6 +2917,618 @@ err: } /** + * i40e_validate_cloud_filter + * @mask: mask for TC filter + * @data: data for TC filter + * + * This function validates cloud filter programmed as TC filter for ADq + **/ +static int i40e_validate_cloud_filter(struct i40e_vf *vf, + struct virtchnl_filter *tc_filter) +{ + struct virtchnl_l4_spec mask = tc_filter->mask.tcp_spec; + struct virtchnl_l4_spec data = tc_filter->data.tcp_spec; + struct i40e_pf *pf = vf->pf; + struct i40e_vsi *vsi = NULL; + struct i40e_mac_filter *f; + struct hlist_node *h; + bool found = false; + int bkt; + + if (!tc_filter->action) { + dev_info(&pf->pdev->dev, + "VF %d: Currently ADq doesn't support Drop Action\n", + vf->vf_id); + goto err; + } + + /* action_meta is TC number here to which the filter is applied */ + if (!tc_filter->action_meta || + tc_filter->action_meta > I40E_MAX_VF_VSI) { + dev_info(&pf->pdev->dev, "VF %d: Invalid TC number %u\n", + vf->vf_id, tc_filter->action_meta); + goto err; + } + + /* Check filter if it's programmed for advanced mode or basic mode. + * There are two ADq modes (for VF only), + * 1. Basic mode: intended to allow as many filter options as possible + * to be added to a VF in Non-trusted mode. Main goal is + * to add filters to its own MAC and VLAN id. + * 2. Advanced mode: is for allowing filters to be applied other than + * its own MAC or VLAN. This mode requires the VF to be + * Trusted. + */ + if (mask.dst_mac[0] && !mask.dst_ip[0]) { + vsi = pf->vsi[vf->lan_vsi_idx]; + f = i40e_find_mac(vsi, data.dst_mac); + + if (!f) { + dev_info(&pf->pdev->dev, + "Destination MAC %pM doesn't belong to VF %d\n", + data.dst_mac, vf->vf_id); + goto err; + } + + if (mask.vlan_id) { + hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, + hlist) { + if (f->vlan == ntohs(data.vlan_id)) { + found = true; + break; + } + } + if (!found) { + dev_info(&pf->pdev->dev, + "VF %d doesn't have any VLAN id %u\n", + vf->vf_id, ntohs(data.vlan_id)); + goto err; + } + } + } else { + /* Check if VF is trusted */ + if (!test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps)) { + dev_err(&pf->pdev->dev, + "VF %d not trusted, make VF trusted to add advanced mode ADq cloud filters\n", + vf->vf_id); + return I40E_ERR_CONFIG; + } + } + + if (mask.dst_mac[0] & data.dst_mac[0]) { + if (is_broadcast_ether_addr(data.dst_mac) || + is_zero_ether_addr(data.dst_mac)) { + dev_info(&pf->pdev->dev, "VF %d: Invalid Dest MAC addr %pM\n", + vf->vf_id, data.dst_mac); + goto err; + } + } + + if (mask.src_mac[0] & data.src_mac[0]) { + if (is_broadcast_ether_addr(data.src_mac) || + is_zero_ether_addr(data.src_mac)) { + dev_info(&pf->pdev->dev, "VF %d: Invalid Source MAC addr %pM\n", + vf->vf_id, data.src_mac); + goto err; + } + } + + if (mask.dst_port & data.dst_port) { + if (!data.dst_port || be16_to_cpu(data.dst_port) > 0xFFFF) { + dev_info(&pf->pdev->dev, "VF %d: Invalid Dest port\n", + vf->vf_id); + goto err; + } + } + + if (mask.src_port & data.src_port) { + if (!data.src_port || be16_to_cpu(data.src_port) > 0xFFFF) { + dev_info(&pf->pdev->dev, "VF %d: Invalid Source port\n", + vf->vf_id); + goto err; + } + } + + if (tc_filter->flow_type != VIRTCHNL_TCP_V6_FLOW && + tc_filter->flow_type != VIRTCHNL_TCP_V4_FLOW) { + dev_info(&pf->pdev->dev, "VF %d: Invalid Flow type\n", + vf->vf_id); + goto err; + } + + if (mask.vlan_id & data.vlan_id) { + if (ntohs(data.vlan_id) > I40E_MAX_VLANID) { + dev_info(&pf->pdev->dev, "VF %d: invalid VLAN ID\n", + vf->vf_id); + goto err; + } + } + + return I40E_SUCCESS; +err: + return I40E_ERR_CONFIG; +} + +/** + * i40e_find_vsi_from_seid - searches for the vsi with the given seid + * @vf: pointer to the VF info + * @seid - seid of the vsi it is searching for + **/ +static struct i40e_vsi *i40e_find_vsi_from_seid(struct i40e_vf *vf, u16 seid) +{ + struct i40e_pf *pf = vf->pf; + struct i40e_vsi *vsi = NULL; + int i; + + for (i = 0; i < vf->num_tc ; i++) { + vsi = i40e_find_vsi_from_id(pf, vf->ch[i].vsi_id); + if (vsi->seid == seid) + return vsi; + } + return NULL; +} + +/** + * i40e_del_all_cloud_filters + * @vf: pointer to the VF info + * + * This function deletes all cloud filters + **/ +static void i40e_del_all_cloud_filters(struct i40e_vf *vf) +{ + struct i40e_cloud_filter *cfilter = NULL; + struct i40e_pf *pf = vf->pf; + struct i40e_vsi *vsi = NULL; + struct hlist_node *node; + int ret; + + hlist_for_each_entry_safe(cfilter, node, + &vf->cloud_filter_list, cloud_node) { + vsi = i40e_find_vsi_from_seid(vf, cfilter->seid); + + if (!vsi) { + dev_err(&pf->pdev->dev, "VF %d: no VSI found for matching %u seid, can't delete cloud filter\n", + vf->vf_id, cfilter->seid); + continue; + } + + if (cfilter->dst_port) + ret = i40e_add_del_cloud_filter_big_buf(vsi, cfilter, + false); + else + ret = i40e_add_del_cloud_filter(vsi, cfilter, false); + if (ret) + dev_err(&pf->pdev->dev, + "VF %d: Failed to delete cloud filter, err %s aq_err %s\n", + vf->vf_id, i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, + pf->hw.aq.asq_last_status)); + + hlist_del(&cfilter->cloud_node); + kfree(cfilter); + vf->num_cloud_filters--; + } +} + +/** + * i40e_vc_del_cloud_filter + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * This function deletes a cloud filter programmed as TC filter for ADq + **/ +static int i40e_vc_del_cloud_filter(struct i40e_vf *vf, u8 *msg) +{ + struct virtchnl_filter *vcf = (struct virtchnl_filter *)msg; + struct virtchnl_l4_spec mask = vcf->mask.tcp_spec; + struct virtchnl_l4_spec tcf = vcf->data.tcp_spec; + struct i40e_cloud_filter cfilter, *cf = NULL; + struct i40e_pf *pf = vf->pf; + struct i40e_vsi *vsi = NULL; + struct hlist_node *node; + i40e_status aq_ret = 0; + int i, ret; + + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + aq_ret = I40E_ERR_PARAM; + goto err; + } + + if (!vf->adq_enabled) { + dev_info(&pf->pdev->dev, + "VF %d: ADq not enabled, can't apply cloud filter\n", + vf->vf_id); + aq_ret = I40E_ERR_PARAM; + goto err; + } + + if (i40e_validate_cloud_filter(vf, vcf)) { + dev_info(&pf->pdev->dev, + "VF %d: Invalid input, can't apply cloud filter\n", + vf->vf_id); + aq_ret = I40E_ERR_PARAM; + goto err; + } + + memset(&cfilter, 0, sizeof(cfilter)); + /* parse destination mac address */ + for (i = 0; i < ETH_ALEN; i++) + cfilter.dst_mac[i] = mask.dst_mac[i] & tcf.dst_mac[i]; + + /* parse source mac address */ + for (i = 0; i < ETH_ALEN; i++) + cfilter.src_mac[i] = mask.src_mac[i] & tcf.src_mac[i]; + + cfilter.vlan_id = mask.vlan_id & tcf.vlan_id; + cfilter.dst_port = mask.dst_port & tcf.dst_port; + cfilter.src_port = mask.src_port & tcf.src_port; + + switch (vcf->flow_type) { + case VIRTCHNL_TCP_V4_FLOW: + cfilter.n_proto = ETH_P_IP; + if (mask.dst_ip[0] & tcf.dst_ip[0]) + memcpy(&cfilter.ip.v4.dst_ip, tcf.dst_ip, + ARRAY_SIZE(tcf.dst_ip)); + else if (mask.src_ip[0] & tcf.dst_ip[0]) + memcpy(&cfilter.ip.v4.src_ip, tcf.src_ip, + ARRAY_SIZE(tcf.dst_ip)); + break; + case VIRTCHNL_TCP_V6_FLOW: + cfilter.n_proto = ETH_P_IPV6; + if (mask.dst_ip[3] & tcf.dst_ip[3]) + memcpy(&cfilter.ip.v6.dst_ip6, tcf.dst_ip, + sizeof(cfilter.ip.v6.dst_ip6)); + if (mask.src_ip[3] & tcf.src_ip[3]) + memcpy(&cfilter.ip.v6.src_ip6, tcf.src_ip, + sizeof(cfilter.ip.v6.src_ip6)); + break; + default: + /* TC filter can be configured based on different combinations + * and in this case IP is not a part of filter config + */ + dev_info(&pf->pdev->dev, "VF %d: Flow type not configured\n", + vf->vf_id); + } + + /* get the vsi to which the tc belongs to */ + vsi = pf->vsi[vf->ch[vcf->action_meta].vsi_idx]; + cfilter.seid = vsi->seid; + cfilter.flags = vcf->field_flags; + + /* Deleting TC filter */ + if (tcf.dst_port) + ret = i40e_add_del_cloud_filter_big_buf(vsi, &cfilter, false); + else + ret = i40e_add_del_cloud_filter(vsi, &cfilter, false); + if (ret) { + dev_err(&pf->pdev->dev, + "VF %d: Failed to delete cloud filter, err %s aq_err %s\n", + vf->vf_id, i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); + goto err; + } + + hlist_for_each_entry_safe(cf, node, + &vf->cloud_filter_list, cloud_node) { + if (cf->seid != cfilter.seid) + continue; + if (mask.dst_port) + if (cfilter.dst_port != cf->dst_port) + continue; + if (mask.dst_mac[0]) + if (!ether_addr_equal(cf->src_mac, cfilter.src_mac)) + continue; + /* for ipv4 data to be valid, only first byte of mask is set */ + if (cfilter.n_proto == ETH_P_IP && mask.dst_ip[0]) + if (memcmp(&cfilter.ip.v4.dst_ip, &cf->ip.v4.dst_ip, + ARRAY_SIZE(tcf.dst_ip))) + continue; + /* for ipv6, mask is set for all sixteen bytes (4 words) */ + if (cfilter.n_proto == ETH_P_IPV6 && mask.dst_ip[3]) + if (memcmp(&cfilter.ip.v6.dst_ip6, &cf->ip.v6.dst_ip6, + sizeof(cfilter.ip.v6.src_ip6))) + continue; + if (mask.vlan_id) + if (cfilter.vlan_id != cf->vlan_id) + continue; + + hlist_del(&cf->cloud_node); + kfree(cf); + vf->num_cloud_filters--; + } + +err: + return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_DEL_CLOUD_FILTER, + aq_ret); +} + +/** + * i40e_vc_add_cloud_filter + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * This function adds a cloud filter programmed as TC filter for ADq + **/ +static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg) +{ + struct virtchnl_filter *vcf = (struct virtchnl_filter *)msg; + struct virtchnl_l4_spec mask = vcf->mask.tcp_spec; + struct virtchnl_l4_spec tcf = vcf->data.tcp_spec; + struct i40e_cloud_filter *cfilter = NULL; + struct i40e_pf *pf = vf->pf; + struct i40e_vsi *vsi = NULL; + i40e_status aq_ret = 0; + int i, ret; + + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + aq_ret = I40E_ERR_PARAM; + goto err; + } + + if (!vf->adq_enabled) { + dev_info(&pf->pdev->dev, + "VF %d: ADq is not enabled, can't apply cloud filter\n", + vf->vf_id); + aq_ret = I40E_ERR_PARAM; + goto err; + } + + if (i40e_validate_cloud_filter(vf, vcf)) { + dev_info(&pf->pdev->dev, + "VF %d: Invalid input/s, can't apply cloud filter\n", + vf->vf_id); + aq_ret = I40E_ERR_PARAM; + goto err; + } + + cfilter = kzalloc(sizeof(*cfilter), GFP_KERNEL); + if (!cfilter) + return -ENOMEM; + + /* parse destination mac address */ + for (i = 0; i < ETH_ALEN; i++) + cfilter->dst_mac[i] = mask.dst_mac[i] & tcf.dst_mac[i]; + + /* parse source mac address */ + for (i = 0; i < ETH_ALEN; i++) + cfilter->src_mac[i] = mask.src_mac[i] & tcf.src_mac[i]; + + cfilter->vlan_id = mask.vlan_id & tcf.vlan_id; + cfilter->dst_port = mask.dst_port & tcf.dst_port; + cfilter->src_port = mask.src_port & tcf.src_port; + + switch (vcf->flow_type) { + case VIRTCHNL_TCP_V4_FLOW: + cfilter->n_proto = ETH_P_IP; + if (mask.dst_ip[0] & tcf.dst_ip[0]) + memcpy(&cfilter->ip.v4.dst_ip, tcf.dst_ip, + ARRAY_SIZE(tcf.dst_ip)); + else if (mask.src_ip[0] & tcf.dst_ip[0]) + memcpy(&cfilter->ip.v4.src_ip, tcf.src_ip, + ARRAY_SIZE(tcf.dst_ip)); + break; + case VIRTCHNL_TCP_V6_FLOW: + cfilter->n_proto = ETH_P_IPV6; + if (mask.dst_ip[3] & tcf.dst_ip[3]) + memcpy(&cfilter->ip.v6.dst_ip6, tcf.dst_ip, + sizeof(cfilter->ip.v6.dst_ip6)); + if (mask.src_ip[3] & tcf.src_ip[3]) + memcpy(&cfilter->ip.v6.src_ip6, tcf.src_ip, + sizeof(cfilter->ip.v6.src_ip6)); + break; + default: + /* TC filter can be configured based on different combinations + * and in this case IP is not a part of filter config + */ + dev_info(&pf->pdev->dev, "VF %d: Flow type not configured\n", + vf->vf_id); + } + + /* get the VSI to which the TC belongs to */ + vsi = pf->vsi[vf->ch[vcf->action_meta].vsi_idx]; + cfilter->seid = vsi->seid; + cfilter->flags = vcf->field_flags; + + /* Adding cloud filter programmed as TC filter */ + if (tcf.dst_port) + ret = i40e_add_del_cloud_filter_big_buf(vsi, cfilter, true); + else + ret = i40e_add_del_cloud_filter(vsi, cfilter, true); + if (ret) { + dev_err(&pf->pdev->dev, + "VF %d: Failed to add cloud filter, err %s aq_err %s\n", + vf->vf_id, i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); + goto err; + } + + INIT_HLIST_NODE(&cfilter->cloud_node); + hlist_add_head(&cfilter->cloud_node, &vf->cloud_filter_list); + vf->num_cloud_filters++; +err: + return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_ADD_CLOUD_FILTER, + aq_ret); +} + +/** + * i40e_vc_add_qch_msg: Add queue channel and enable ADq + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + **/ +static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg) +{ + struct virtchnl_tc_info *tci = + (struct virtchnl_tc_info *)msg; + struct i40e_pf *pf = vf->pf; + struct i40e_link_status *ls = &pf->hw.phy.link_info; + int i, adq_request_qps = 0, speed = 0; + i40e_status aq_ret = 0; + + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + aq_ret = I40E_ERR_PARAM; + goto err; + } + + /* ADq cannot be applied if spoof check is ON */ + if (vf->spoofchk) { + dev_err(&pf->pdev->dev, + "Spoof check is ON, turn it OFF to enable ADq\n"); + aq_ret = I40E_ERR_PARAM; + goto err; + } + + if (!(vf->driver_caps & VIRTCHNL_VF_OFFLOAD_ADQ)) { + dev_err(&pf->pdev->dev, + "VF %d attempting to enable ADq, but hasn't properly negotiated that capability\n", + vf->vf_id); + aq_ret = I40E_ERR_PARAM; + goto err; + } + + /* max number of traffic classes for VF currently capped at 4 */ + if (!tci->num_tc || tci->num_tc > I40E_MAX_VF_VSI) { + dev_err(&pf->pdev->dev, + "VF %d trying to set %u TCs, valid range 1-4 TCs per VF\n", + vf->vf_id, tci->num_tc); + aq_ret = I40E_ERR_PARAM; + goto err; + } + + /* validate queues for each TC */ + for (i = 0; i < tci->num_tc; i++) + if (!tci->list[i].count || + tci->list[i].count > I40E_DEFAULT_QUEUES_PER_VF) { + dev_err(&pf->pdev->dev, + "VF %d: TC %d trying to set %u queues, valid range 1-4 queues per TC\n", + vf->vf_id, i, tci->list[i].count); + aq_ret = I40E_ERR_PARAM; + goto err; + } + + /* need Max VF queues but already have default number of queues */ + adq_request_qps = I40E_MAX_VF_QUEUES - I40E_DEFAULT_QUEUES_PER_VF; + + if (pf->queues_left < adq_request_qps) { + dev_err(&pf->pdev->dev, + "No queues left to allocate to VF %d\n", + vf->vf_id); + aq_ret = I40E_ERR_PARAM; + goto err; + } else { + /* we need to allocate max VF queues to enable ADq so as to + * make sure ADq enabled VF always gets back queues when it + * goes through a reset. + */ + vf->num_queue_pairs = I40E_MAX_VF_QUEUES; + } + + /* get link speed in MB to validate rate limit */ + switch (ls->link_speed) { + case VIRTCHNL_LINK_SPEED_100MB: + speed = SPEED_100; + break; + case VIRTCHNL_LINK_SPEED_1GB: + speed = SPEED_1000; + break; + case VIRTCHNL_LINK_SPEED_10GB: + speed = SPEED_10000; + break; + case VIRTCHNL_LINK_SPEED_20GB: + speed = SPEED_20000; + break; + case VIRTCHNL_LINK_SPEED_25GB: + speed = SPEED_25000; + break; + case VIRTCHNL_LINK_SPEED_40GB: + speed = SPEED_40000; + break; + default: + dev_err(&pf->pdev->dev, + "Cannot detect link speed\n"); + aq_ret = I40E_ERR_PARAM; + goto err; + } + + /* parse data from the queue channel info */ + vf->num_tc = tci->num_tc; + for (i = 0; i < vf->num_tc; i++) { + if (tci->list[i].max_tx_rate) { + if (tci->list[i].max_tx_rate > speed) { + dev_err(&pf->pdev->dev, + "Invalid max tx rate %llu specified for VF %d.", + tci->list[i].max_tx_rate, + vf->vf_id); + aq_ret = I40E_ERR_PARAM; + goto err; + } else { + vf->ch[i].max_tx_rate = + tci->list[i].max_tx_rate; + } + } + vf->ch[i].num_qps = tci->list[i].count; + } + + /* set this flag only after making sure all inputs are sane */ + vf->adq_enabled = true; + /* num_req_queues is set when user changes number of queues via ethtool + * and this causes issue for default VSI(which depends on this variable) + * when ADq is enabled, hence reset it. + */ + vf->num_req_queues = 0; + + /* reset the VF in order to allocate resources */ + i40e_vc_notify_vf_reset(vf); + i40e_reset_vf(vf, false); + + return I40E_SUCCESS; + + /* send the response to the VF */ +err: + return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_ENABLE_CHANNELS, + aq_ret); +} + +/** + * i40e_vc_del_qch_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + **/ +static int i40e_vc_del_qch_msg(struct i40e_vf *vf, u8 *msg) +{ + struct i40e_pf *pf = vf->pf; + i40e_status aq_ret = 0; + + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + aq_ret = I40E_ERR_PARAM; + goto err; + } + + if (vf->adq_enabled) { + i40e_del_all_cloud_filters(vf); + i40e_del_qch(vf); + vf->adq_enabled = false; + vf->num_tc = 0; + dev_info(&pf->pdev->dev, + "Deleting Queue Channels and cloud filters for ADq on VF %d\n", + vf->vf_id); + } else { + dev_info(&pf->pdev->dev, "VF %d trying to delete queue channels but ADq isn't enabled\n", + vf->vf_id); + aq_ret = I40E_ERR_PARAM; + } + + /* reset the VF in order to allocate resources */ + i40e_vc_notify_vf_reset(vf); + i40e_reset_vf(vf, false); + + return I40E_SUCCESS; + +err: + return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_DISABLE_CHANNELS, + aq_ret); +} + +/** * i40e_vc_process_vf_msg * @pf: pointer to the PF structure * @vf_id: source VF id @@ -2816,7 +3657,18 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode, case VIRTCHNL_OP_REQUEST_QUEUES: ret = i40e_vc_request_queues_msg(vf, msg, msglen); break; - + case VIRTCHNL_OP_ENABLE_CHANNELS: + ret = i40e_vc_add_qch_msg(vf, msg); + break; + case VIRTCHNL_OP_DISABLE_CHANNELS: + ret = i40e_vc_del_qch_msg(vf, msg); + break; + case VIRTCHNL_OP_ADD_CLOUD_FILTER: + ret = i40e_vc_add_cloud_filter(vf, msg); + break; + case VIRTCHNL_OP_DEL_CLOUD_FILTER: + ret = i40e_vc_del_cloud_filter(vf, msg); + break; case VIRTCHNL_OP_UNKNOWN: default: dev_err(&pf->pdev->dev, "Unsupported opcode %d from VF %d\n", @@ -3382,6 +4234,16 @@ int i40e_ndo_set_vf_trust(struct net_device *netdev, int vf_id, bool setting) i40e_vc_disable_vf(vf); dev_info(&pf->pdev->dev, "VF %u is now %strusted\n", vf_id, setting ? "" : "un"); + + if (vf->adq_enabled) { + if (!vf->trusted) { + dev_info(&pf->pdev->dev, + "VF %u no longer Trusted, deleting all cloud filters\n", + vf_id); + i40e_del_all_cloud_filters(vf); + } + } + out: return ret; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 5efc4f92bb37..6852599b2379 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -69,6 +69,19 @@ enum i40e_vf_capabilities { I40E_VIRTCHNL_VF_CAP_IWARP, }; +/* In ADq, max 4 VSI's can be allocated per VF including primary VF VSI. + * These variables are used to store indices, id's and number of queues + * for each VSI including that of primary VF VSI. Each Traffic class is + * termed as channel and each channel can in-turn have 4 queues which + * means max 16 queues overall per VF. + */ +struct i40evf_channel { + u16 vsi_idx; /* index in PF struct for all channel VSIs */ + u16 vsi_id; /* VSI ID used by firmware */ + u16 num_qps; /* number of queue pairs requested by user */ + u64 max_tx_rate; /* bandwidth rate allocation for VSIs */ +}; + /* VF information structure */ struct i40e_vf { struct i40e_pf *pf; @@ -111,6 +124,13 @@ struct i40e_vf { u16 num_mac; u16 num_vlan; + /* ADq related variables */ + bool adq_enabled; /* flag to enable adq */ + u8 num_tc; + struct i40evf_channel ch[I40E_MAX_VF_VSI]; + struct hlist_head cloud_filter_list; + u16 num_cloud_filters; + /* RDMA Client */ struct virtchnl_iwarp_qvlist_info *qvlist_info; }; |