diff options
Diffstat (limited to 'drivers/net/ethernet/intel/i40e/i40e_main.c')
| -rw-r--r-- | drivers/net/ethernet/intel/i40e/i40e_main.c | 2278 |
1 files changed, 1574 insertions, 704 deletions
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 8c3e753bfb9d..b5dcd15ced36 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1,17 +1,19 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2021 Intel Corporation. */ #include <linux/etherdevice.h> #include <linux/of_net.h> #include <linux/pci.h> #include <linux/bpf.h> +#include <generated/utsrelease.h> +#include <linux/crash_dump.h> /* Local includes */ #include "i40e.h" #include "i40e_diag.h" #include "i40e_xsk.h" #include <net/udp_tunnel.h> -#include <net/xdp_sock.h> +#include <net/xdp_sock_drv.h> /* All i40e tracepoints are defined by the include below, which * must be included exactly once across the whole kernel with * CREATE_TRACE_POINTS defined @@ -23,15 +25,6 @@ const char i40e_driver_name[] = "i40e"; static const char i40e_driver_string[] = "Intel(R) Ethernet Connection XL710 Network Driver"; -#define DRV_KERN "-k" - -#define DRV_VERSION_MAJOR 2 -#define DRV_VERSION_MINOR 8 -#define DRV_VERSION_BUILD 20 -#define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ - __stringify(DRV_VERSION_MINOR) "." \ - __stringify(DRV_VERSION_BUILD) DRV_KERN -const char i40e_driver_version_str[] = DRV_VERSION; static const char i40e_copyright[] = "Copyright (c) 2013 - 2019 Intel Corporation."; /* a bit of forward declarations */ @@ -39,11 +32,13 @@ static void i40e_vsi_reinit_locked(struct i40e_vsi *vsi); static void i40e_handle_reset_warning(struct i40e_pf *pf, bool lock_acquired); static int i40e_add_vsi(struct i40e_vsi *vsi); static int i40e_add_veb(struct i40e_veb *veb, struct i40e_vsi *vsi); -static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit); +static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit, bool lock_acquired); static int i40e_setup_misc_vector(struct i40e_pf *pf); static void i40e_determine_queue_usage(struct i40e_pf *pf); static int i40e_setup_pf_filter_control(struct i40e_pf *pf); -static void i40e_prep_for_reset(struct i40e_pf *pf, bool lock_acquired); +static void i40e_prep_for_reset(struct i40e_pf *pf); +static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit, + bool lock_acquired); static int i40e_reset(struct i40e_pf *pf); static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired); static int i40e_setup_misc_vector_for_recovery_mode(struct i40e_pf *pf); @@ -54,7 +49,7 @@ static void i40e_fdir_sb_setup(struct i40e_pf *pf); static int i40e_veb_get_bw_info(struct i40e_veb *veb); static int i40e_get_capabilities(struct i40e_pf *pf, enum i40e_admin_queue_opc list_type); - +static bool i40e_is_total_port_shutdown_enabled(struct i40e_pf *pf); /* i40e_pci_tbl - PCI Device ID Table * @@ -71,6 +66,7 @@ static const struct pci_device_id i40e_pci_tbl[] = { {PCI_VDEVICE(INTEL, I40E_DEV_ID_QSFP_A), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_QSFP_B), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_QSFP_C), 0}, + {PCI_VDEVICE(INTEL, I40E_DEV_ID_1G_BASE_T_BC), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T4), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T_BC), 0}, @@ -82,6 +78,7 @@ static const struct pci_device_id i40e_pci_tbl[] = { {PCI_VDEVICE(INTEL, I40E_DEV_ID_1G_BASE_T_X722), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T_X722), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_SFP_I_X722), 0}, + {PCI_VDEVICE(INTEL, I40E_DEV_ID_SFP_X722_A), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_20G_KR2), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_20G_KR2_A), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_X710_N3000), 0}, @@ -101,10 +98,27 @@ MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all), Debug mask (0x8XXXXXXX MODULE_AUTHOR("Intel Corporation, <e1000-devel@lists.sourceforge.net>"); MODULE_DESCRIPTION("Intel(R) Ethernet Connection XL710 Network Driver"); MODULE_LICENSE("GPL v2"); -MODULE_VERSION(DRV_VERSION); static struct workqueue_struct *i40e_wq; +static void netdev_hw_addr_refcnt(struct i40e_mac_filter *f, + struct net_device *netdev, int delta) +{ + struct netdev_hw_addr *ha; + + if (!f || !netdev) + return; + + netdev_for_each_mc_addr(ha, netdev) { + if (ether_addr_equal(ha->addr, f->macaddr)) { + ha->refcount += delta; + if (ha->refcount <= 0) + ha->refcount = 1; + break; + } + } +} + /** * i40e_allocate_dma_mem_d - OS specific memory alloc for shared code * @hw: pointer to the HW structure @@ -184,10 +198,6 @@ int i40e_free_virt_mem_d(struct i40e_hw *hw, struct i40e_virt_mem *mem) * @id: an owner id to stick on the items assigned * * Returns the base item index of the lump, or negative for error - * - * The search_hint trick and lack of advanced fit-finding only work - * because we're highly likely to have all the same size lump requests. - * Linear search time and any fragmentation should be minimal. **/ static int i40e_get_lump(struct i40e_pf *pf, struct i40e_lump_tracking *pile, u16 needed, u16 id) @@ -202,8 +212,21 @@ static int i40e_get_lump(struct i40e_pf *pf, struct i40e_lump_tracking *pile, return -EINVAL; } - /* start the linear search with an imperfect hint */ - i = pile->search_hint; + /* Allocate last queue in the pile for FDIR VSI queue + * so it doesn't fragment the qp_pile + */ + if (pile == pf->qp_pile && pf->vsi[id]->type == I40E_VSI_FDIR) { + if (pile->list[pile->num_entries - 1] & I40E_PILE_VALID_BIT) { + dev_err(&pf->pdev->dev, + "Cannot allocate queue %d for I40E_VSI_FDIR\n", + pile->num_entries - 1); + return -ENOMEM; + } + pile->list[pile->num_entries - 1] = id | I40E_PILE_VALID_BIT; + return pile->num_entries - 1; + } + + i = 0; while (i < pile->num_entries) { /* skip already allocated entries */ if (pile->list[i] & I40E_PILE_VALID_BIT) { @@ -222,7 +245,6 @@ static int i40e_get_lump(struct i40e_pf *pf, struct i40e_lump_tracking *pile, for (j = 0; j < needed; j++) pile->list[i+j] = id | I40E_PILE_VALID_BIT; ret = i; - pile->search_hint = i + j; break; } @@ -245,7 +267,7 @@ static int i40e_put_lump(struct i40e_lump_tracking *pile, u16 index, u16 id) { int valid_id = (id | I40E_PILE_VALID_BIT); int count = 0; - int i; + u16 i; if (!pile || index >= pile->num_entries) return -EINVAL; @@ -257,8 +279,6 @@ static int i40e_put_lump(struct i40e_lump_tracking *pile, u16 index, u16 id) count++; } - if (count && index < pile->search_hint) - pile->search_hint = index; return count; } @@ -296,6 +316,7 @@ void i40e_service_event_schedule(struct i40e_pf *pf) /** * i40e_tx_timeout - Respond to a Tx Hang * @netdev: network interface device structure + * @txqueue: queue number timing out * * If any port has noticed a Tx timeout, it is likely that the whole * device is munged, not just the one netdev port, so go for the full @@ -364,7 +385,9 @@ static void i40e_tx_timeout(struct net_device *netdev, unsigned int txqueue) set_bit(__I40E_GLOBAL_RESET_REQUESTED, pf->state); break; default: - netdev_err(netdev, "tx_timeout recovery unsuccessful\n"); + netdev_err(netdev, "tx_timeout recovery unsuccessful, device is in non-recoverable state.\n"); + set_bit(__I40E_DOWN_REQUESTED, pf->state); + set_bit(__I40E_VSI_DOWN_REQUESTED, vsi->state); break; } @@ -439,11 +462,15 @@ static void i40e_get_netdev_stats_struct(struct net_device *netdev, i40e_get_netdev_stats_struct_tx(ring, stats); if (i40e_enabled_xdp_vsi(vsi)) { - ring++; + ring = READ_ONCE(vsi->xdp_rings[i]); + if (!ring) + continue; i40e_get_netdev_stats_struct_tx(ring, stats); } - ring++; + ring = READ_ONCE(vsi->rx_rings[i]); + if (!ring) + continue; do { start = u64_stats_fetch_begin_irq(&ring->syncp); packets = ring->stats.packets; @@ -527,6 +554,47 @@ void i40e_pf_reset_stats(struct i40e_pf *pf) } /** + * i40e_compute_pci_to_hw_id - compute index form PCI function. + * @vsi: ptr to the VSI to read from. + * @hw: ptr to the hardware info. + **/ +static u32 i40e_compute_pci_to_hw_id(struct i40e_vsi *vsi, struct i40e_hw *hw) +{ + int pf_count = i40e_get_pf_count(hw); + + if (vsi->type == I40E_VSI_SRIOV) + return (hw->port * BIT(7)) / pf_count + vsi->vf_id; + + return hw->port + BIT(7); +} + +/** + * i40e_stat_update64 - read and update a 64 bit stat from the chip. + * @hw: ptr to the hardware info. + * @hireg: the high 32 bit reg to read. + * @loreg: the low 32 bit reg to read. + * @offset_loaded: has the initial offset been loaded yet. + * @offset: ptr to current offset value. + * @stat: ptr to the stat. + * + * Since the device stats are not reset at PFReset, they will not + * be zeroed when the driver starts. We'll save the first values read + * and use them as offsets to be subtracted from the raw values in order + * to report stats that count from zero. + **/ +static void i40e_stat_update64(struct i40e_hw *hw, u32 hireg, u32 loreg, + bool offset_loaded, u64 *offset, u64 *stat) +{ + u64 new_data; + + new_data = rd64(hw, loreg); + + if (!offset_loaded || new_data < *offset) + *offset = new_data; + *stat = new_data - *offset; +} + +/** * i40e_stat_update48 - read and update a 48 bit stat from the chip * @hw: ptr to the hardware info * @hireg: the high 32 bit reg to read @@ -598,6 +666,34 @@ static void i40e_stat_update_and_clear32(struct i40e_hw *hw, u32 reg, u64 *stat) } /** + * i40e_stats_update_rx_discards - update rx_discards. + * @vsi: ptr to the VSI to be updated. + * @hw: ptr to the hardware info. + * @stat_idx: VSI's stat_counter_idx. + * @offset_loaded: ptr to the VSI's stat_offsets_loaded. + * @stat_offset: ptr to stat_offset to store first read of specific register. + * @stat: ptr to VSI's stat to be updated. + **/ +static void +i40e_stats_update_rx_discards(struct i40e_vsi *vsi, struct i40e_hw *hw, + int stat_idx, bool offset_loaded, + struct i40e_eth_stats *stat_offset, + struct i40e_eth_stats *stat) +{ + u64 rx_rdpc, rx_rxerr; + + i40e_stat_update32(hw, I40E_GLV_RDPC(stat_idx), offset_loaded, + &stat_offset->rx_discards, &rx_rdpc); + i40e_stat_update64(hw, + I40E_GL_RXERR1H(i40e_compute_pci_to_hw_id(vsi, hw)), + I40E_GL_RXERR1L(i40e_compute_pci_to_hw_id(vsi, hw)), + offset_loaded, &stat_offset->rx_discards_other, + &rx_rxerr); + + stat->rx_discards = rx_rdpc + rx_rxerr; +} + +/** * i40e_update_eth_stats - Update VSI-specific ethernet statistics counters. * @vsi: the VSI to be updated **/ @@ -656,6 +752,10 @@ void i40e_update_eth_stats(struct i40e_vsi *vsi) I40E_GLV_BPTCL(stat_idx), vsi->stat_offsets_loaded, &oes->tx_broadcast, &es->tx_broadcast); + + i40e_stats_update_rx_discards(vsi, hw, stat_idx, + vsi->stat_offsets_loaded, oes, es); + vsi->stat_offsets_loaded = true; } @@ -750,18 +850,19 @@ void i40e_update_veb_stats(struct i40e_veb *veb) **/ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) { + u64 rx_page, rx_buf, rx_reuse, rx_alloc, rx_waive, rx_busy; struct i40e_pf *pf = vsi->back; struct rtnl_link_stats64 *ons; struct rtnl_link_stats64 *ns; /* netdev stats */ struct i40e_eth_stats *oes; struct i40e_eth_stats *es; /* device's eth stats */ - u32 tx_restart, tx_busy; + u64 tx_restart, tx_busy; struct i40e_ring *p; - u32 rx_page, rx_buf; u64 bytes, packets; unsigned int start; u64 tx_linearize; u64 tx_force_wb; + u64 tx_stopped; u64 rx_p, rx_b; u64 tx_p, tx_b; u16 q; @@ -781,12 +882,19 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) rx_b = rx_p = 0; tx_b = tx_p = 0; tx_restart = tx_busy = tx_linearize = tx_force_wb = 0; + tx_stopped = 0; rx_page = 0; rx_buf = 0; + rx_reuse = 0; + rx_alloc = 0; + rx_waive = 0; + rx_busy = 0; rcu_read_lock(); for (q = 0; q < vsi->num_queue_pairs; q++) { /* locate Tx ring */ p = READ_ONCE(vsi->tx_rings[q]); + if (!p) + continue; do { start = u64_stats_fetch_begin_irq(&p->syncp); @@ -799,9 +907,13 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) tx_busy += p->tx_stats.tx_busy; tx_linearize += p->tx_stats.tx_linearize; tx_force_wb += p->tx_stats.tx_force_wb; + tx_stopped += p->tx_stats.tx_stopped; + + /* locate Rx ring */ + p = READ_ONCE(vsi->rx_rings[q]); + if (!p) + continue; - /* Rx queue is part of the same block as Tx queue */ - p = &p[1]; do { start = u64_stats_fetch_begin_irq(&p->syncp); packets = p->stats.packets; @@ -811,14 +923,42 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) rx_p += packets; rx_buf += p->rx_stats.alloc_buff_failed; rx_page += p->rx_stats.alloc_page_failed; + rx_reuse += p->rx_stats.page_reuse_count; + rx_alloc += p->rx_stats.page_alloc_count; + rx_waive += p->rx_stats.page_waive_count; + rx_busy += p->rx_stats.page_busy_count; + + if (i40e_enabled_xdp_vsi(vsi)) { + /* locate XDP ring */ + p = READ_ONCE(vsi->xdp_rings[q]); + if (!p) + continue; + + do { + start = u64_stats_fetch_begin_irq(&p->syncp); + packets = p->stats.packets; + bytes = p->stats.bytes; + } while (u64_stats_fetch_retry_irq(&p->syncp, start)); + tx_b += bytes; + tx_p += packets; + tx_restart += p->tx_stats.restart_queue; + tx_busy += p->tx_stats.tx_busy; + tx_linearize += p->tx_stats.tx_linearize; + tx_force_wb += p->tx_stats.tx_force_wb; + } } rcu_read_unlock(); vsi->tx_restart = tx_restart; vsi->tx_busy = tx_busy; vsi->tx_linearize = tx_linearize; vsi->tx_force_wb = tx_force_wb; + vsi->tx_stopped = tx_stopped; vsi->rx_page_failed = rx_page; vsi->rx_buf_failed = rx_buf; + vsi->rx_page_reuse = rx_reuse; + vsi->rx_page_alloc = rx_alloc; + vsi->rx_page_waive = rx_waive; + vsi->rx_page_busy = rx_busy; ns->rx_packets = rx_p; ns->rx_bytes = rx_b; @@ -1305,6 +1445,114 @@ static int i40e_correct_mac_vlan_filters(struct i40e_vsi *vsi, } /** + * i40e_get_vf_new_vlan - Get new vlan id on a vf + * @vsi: the vsi to configure + * @new_mac: new mac filter to be added + * @f: existing mac filter, replaced with new_mac->f if new_mac is not NULL + * @vlan_filters: the number of active VLAN filters + * @trusted: flag if the VF is trusted + * + * Get new VLAN id based on current VLAN filters, trust, PVID + * and vf-vlan-prune-disable flag. + * + * Returns the value of the new vlan filter or + * the old value if no new filter is needed. + */ +static s16 i40e_get_vf_new_vlan(struct i40e_vsi *vsi, + struct i40e_new_mac_filter *new_mac, + struct i40e_mac_filter *f, + int vlan_filters, + bool trusted) +{ + s16 pvid = le16_to_cpu(vsi->info.pvid); + struct i40e_pf *pf = vsi->back; + bool is_any; + + if (new_mac) + f = new_mac->f; + + if (pvid && f->vlan != pvid) + return pvid; + + is_any = (trusted || + !(pf->flags & I40E_FLAG_VF_VLAN_PRUNING)); + + if ((vlan_filters && f->vlan == I40E_VLAN_ANY) || + (!is_any && !vlan_filters && f->vlan == I40E_VLAN_ANY) || + (is_any && !vlan_filters && f->vlan == 0)) { + if (is_any) + return I40E_VLAN_ANY; + else + return 0; + } + + return f->vlan; +} + +/** + * i40e_correct_vf_mac_vlan_filters - Correct non-VLAN VF filters if necessary + * @vsi: the vsi to configure + * @tmp_add_list: list of filters ready to be added + * @tmp_del_list: list of filters ready to be deleted + * @vlan_filters: the number of active VLAN filters + * @trusted: flag if the VF is trusted + * + * Correct VF VLAN filters based on current VLAN filters, trust, PVID + * and vf-vlan-prune-disable flag. + * + * In case of memory allocation failure return -ENOMEM. Otherwise, return 0. + * + * This function is only expected to be called from within + * i40e_sync_vsi_filters. + * + * NOTE: This function expects to be called while under the + * mac_filter_hash_lock + */ +static int i40e_correct_vf_mac_vlan_filters(struct i40e_vsi *vsi, + struct hlist_head *tmp_add_list, + struct hlist_head *tmp_del_list, + int vlan_filters, + bool trusted) +{ + struct i40e_mac_filter *f, *add_head; + struct i40e_new_mac_filter *new_mac; + struct hlist_node *h; + int bkt, new_vlan; + + hlist_for_each_entry(new_mac, tmp_add_list, hlist) { + new_mac->f->vlan = i40e_get_vf_new_vlan(vsi, new_mac, NULL, + vlan_filters, trusted); + } + + hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { + new_vlan = i40e_get_vf_new_vlan(vsi, NULL, f, vlan_filters, + trusted); + if (new_vlan != f->vlan) { + add_head = i40e_add_filter(vsi, f->macaddr, new_vlan); + if (!add_head) + return -ENOMEM; + /* Create a temporary i40e_new_mac_filter */ + new_mac = kzalloc(sizeof(*new_mac), GFP_ATOMIC); + if (!new_mac) + return -ENOMEM; + new_mac->f = add_head; + new_mac->state = add_head->state; + + /* Add the new filter to the tmp list */ + hlist_add_head(&new_mac->hlist, tmp_add_list); + + /* Put the original filter into the delete list */ + f->state = I40E_FILTER_REMOVE; + hash_del(&f->hlist); + hlist_add_head(&f->hlist, tmp_del_list); + } + } + + vsi->has_vlan_filter = !!vlan_filters; + return 0; +} + +/** * i40e_rm_default_mac_filter - Remove the default MAC filter set by NVM * @vsi: the PF Main VSI - inappropriate for any other VSI * @macaddr: the MAC address @@ -1564,7 +1812,7 @@ static int i40e_set_mac(struct net_device *netdev, void *p) */ spin_lock_bh(&vsi->mac_filter_hash_lock); i40e_del_mac_filter(vsi, netdev->dev_addr); - ether_addr_copy(netdev->dev_addr, addr->sa_data); + eth_hw_addr_set(netdev, addr->sa_data); i40e_add_mac_filter(vsi, netdev->dev_addr); spin_unlock_bh(&vsi->mac_filter_hash_lock); @@ -1590,6 +1838,8 @@ static int i40e_set_mac(struct net_device *netdev, void *p) * i40e_config_rss_aq - Prepare for RSS using AQ commands * @vsi: vsi structure * @seed: RSS hash seed + * @lut: pointer to lookup table of lut_size + * @lut_size: size of the lookup table **/ static int i40e_config_rss_aq(struct i40e_vsi *vsi, const u8 *seed, u8 *lut, u16 lut_size) @@ -1611,7 +1861,7 @@ static int i40e_config_rss_aq(struct i40e_vsi *vsi, const u8 *seed, } } if (lut) { - bool pf_lut = vsi->type == I40E_VSI_MAIN ? true : false; + bool pf_lut = vsi->type == I40E_VSI_MAIN; ret = i40e_aq_set_rss_lut(hw, vsi->id, pf_lut, lut, lut_size); if (ret) { @@ -1765,6 +2015,7 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, bool is_add) { struct i40e_pf *pf = vsi->back; + u16 num_tc_qps = 0; u16 sections = 0; u8 netdev_tc = 0; u16 numtc = 1; @@ -1772,13 +2023,37 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, u8 offset; u16 qmap; int i; - u16 num_tc_qps = 0; sections = I40E_AQ_VSI_PROP_QUEUE_MAP_VALID; offset = 0; + /* zero out queue mapping, it will get updated on the end of the function */ + memset(ctxt->info.queue_mapping, 0, sizeof(ctxt->info.queue_mapping)); + + if (vsi->type == I40E_VSI_MAIN) { + /* This code helps add more queue to the VSI if we have + * more cores than RSS can support, the higher cores will + * be served by ATR or other filters. Furthermore, the + * non-zero req_queue_pairs says that user requested a new + * queue count via ethtool's set_channels, so use this + * value for queues distribution across traffic classes + * We need at least one queue pair for the interface + * to be usable as we see in else statement. + */ + if (vsi->req_queue_pairs > 0) + vsi->num_queue_pairs = vsi->req_queue_pairs; + else if (pf->flags & I40E_FLAG_MSIX_ENABLED) + vsi->num_queue_pairs = pf->num_lan_msix; + else + vsi->num_queue_pairs = 1; + } /* Number of queues per enabled TC */ - num_tc_qps = vsi->alloc_queue_pairs; + if (vsi->type == I40E_VSI_MAIN || + (vsi->type == I40E_VSI_SRIOV && vsi->num_queue_pairs != 0)) + num_tc_qps = vsi->num_queue_pairs; + else + num_tc_qps = vsi->alloc_queue_pairs; + if (enabled_tc && (vsi->back->flags & I40E_FLAG_DCB_ENABLED)) { /* Find numtc from enabled TC bitmap */ for (i = 0, numtc = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { @@ -1817,7 +2092,7 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, num_tc_qps); break; } - /* fall through */ + fallthrough; case I40E_VSI_FDIR: case I40E_VSI_SRIOV: case I40E_VSI_VMDQ2: @@ -1856,15 +2131,11 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, } ctxt->info.tc_mapping[i] = cpu_to_le16(qmap); } - - /* Set actual Tx/Rx queue pairs */ - vsi->num_queue_pairs = offset; - if ((vsi->type == I40E_VSI_MAIN) && (numtc == 1)) { - if (vsi->req_queue_pairs > 0) - vsi->num_queue_pairs = vsi->req_queue_pairs; - else if (pf->flags & I40E_FLAG_MSIX_ENABLED) - vsi->num_queue_pairs = pf->num_lan_msix; - } + /* Do not change previously set num_queue_pairs for PFs and VFs*/ + if ((vsi->type == I40E_VSI_MAIN && numtc != 1) || + (vsi->type == I40E_VSI_SRIOV && vsi->num_queue_pairs == 0) || + (vsi->type != I40E_VSI_MAIN && vsi->type != I40E_VSI_SRIOV)) + vsi->num_queue_pairs = offset; /* Scheduler section valid can only be set for ADD VSI */ if (is_add) { @@ -1994,12 +2265,13 @@ static void i40e_undo_add_filter_entries(struct i40e_vsi *vsi, hlist_for_each_entry_safe(new, h, from, hlist) { /* We can simply free the wrapper structure */ hlist_del(&new->hlist); + netdev_hw_addr_refcnt(new->f, vsi->netdev, -1); kfree(new); } } /** - * i40e_next_entry - Get the next non-broadcast filter from a list + * i40e_next_filter - Get the next non-broadcast filter from a list * @next: pointer to filter in list * * Returns the next non-broadcast filter in the list. Required so that we @@ -2076,19 +2348,19 @@ void i40e_aqc_del_filters(struct i40e_vsi *vsi, const char *vsi_name, int num_del, int *retval) { struct i40e_hw *hw = &vsi->back->hw; + enum i40e_admin_queue_err aq_status; i40e_status aq_ret; - int aq_err; - aq_ret = i40e_aq_remove_macvlan(hw, vsi->seid, list, num_del, NULL); - aq_err = hw->aq.asq_last_status; + aq_ret = i40e_aq_remove_macvlan_v2(hw, vsi->seid, list, num_del, NULL, + &aq_status); /* Explicitly ignore and do not report when firmware returns ENOENT */ - if (aq_ret && !(aq_err == I40E_AQ_RC_ENOENT)) { + if (aq_ret && !(aq_status == I40E_AQ_RC_ENOENT)) { *retval = -EIO; dev_info(&vsi->back->pdev->dev, "ignoring delete macvlan error on %s, err %s, aq_err %s\n", vsi_name, i40e_stat_str(hw, aq_ret), - i40e_aq_str(hw, aq_err)); + i40e_aq_str(hw, aq_status)); } } @@ -2111,10 +2383,10 @@ void i40e_aqc_add_filters(struct i40e_vsi *vsi, const char *vsi_name, int num_add) { struct i40e_hw *hw = &vsi->back->hw; - int aq_err, fcnt; + enum i40e_admin_queue_err aq_status; + int fcnt; - i40e_aq_add_macvlan(hw, vsi->seid, list, num_add, NULL); - aq_err = hw->aq.asq_last_status; + i40e_aq_add_macvlan_v2(hw, vsi->seid, list, num_add, NULL, &aq_status); fcnt = i40e_update_filter_state(num_add, list, add_head); if (fcnt != num_add) { @@ -2122,17 +2394,19 @@ void i40e_aqc_add_filters(struct i40e_vsi *vsi, const char *vsi_name, 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", - i40e_aq_str(hw, aq_err), vsi_name); + i40e_aq_str(hw, aq_status), vsi_name); } else if (vsi->type == I40E_VSI_SRIOV || vsi->type == I40E_VSI_VMDQ1 || vsi->type == I40E_VSI_VMDQ2) { dev_warn(&vsi->back->pdev->dev, "Error %s adding RX filters on %s, please set promiscuous on manually for %s\n", - i40e_aq_str(hw, aq_err), vsi_name, vsi_name); + i40e_aq_str(hw, aq_status), vsi_name, + vsi_name); } else { dev_warn(&vsi->back->pdev->dev, "Error %s adding RX filters on %s, incorrect VSI type: %i.\n", - i40e_aq_str(hw, aq_err), vsi_name, vsi->type); + i40e_aq_str(hw, aq_status), vsi_name, + vsi->type); } } } @@ -2337,10 +2611,18 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) vlan_filters++; } - retval = i40e_correct_mac_vlan_filters(vsi, - &tmp_add_list, - &tmp_del_list, - vlan_filters); + if (vsi->type != I40E_VSI_SRIOV) + retval = i40e_correct_mac_vlan_filters + (vsi, &tmp_add_list, &tmp_del_list, + vlan_filters); + else + retval = i40e_correct_vf_mac_vlan_filters + (vsi, &tmp_add_list, &tmp_del_list, + vlan_filters, pf->vf[vsi->vf_id].trusted); + + hlist_for_each_entry(new, &tmp_add_list, hlist) + netdev_hw_addr_refcnt(new->f, vsi->netdev, 1); + if (retval) goto err_no_memory_locked; @@ -2473,6 +2755,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) if (new->f->state == I40E_FILTER_NEW) new->f->state = new->state; hlist_del(&new->hlist); + netdev_hw_addr_refcnt(new->f, vsi->netdev, -1); kfree(new); } spin_unlock_bh(&vsi->mac_filter_hash_lock); @@ -2536,8 +2819,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) i40e_stat_str(hw, aq_ret), i40e_aq_str(hw, hw->aq.asq_last_status)); } else { - dev_info(&pf->pdev->dev, "%s is %s allmulti mode.\n", - vsi->netdev->name, + dev_info(&pf->pdev->dev, "%s allmulti mode.\n", cur_multipromisc ? "entering" : "leaving"); } } @@ -2592,14 +2874,15 @@ static void i40e_sync_filters_subtask(struct i40e_pf *pf) return; if (!test_and_clear_bit(__I40E_MACVLAN_SYNC_PENDING, pf->state)) return; - if (test_and_set_bit(__I40E_VF_DISABLE, pf->state)) { + if (test_bit(__I40E_VF_DISABLE, pf->state)) { set_bit(__I40E_MACVLAN_SYNC_PENDING, pf->state); return; } for (v = 0; v < pf->num_alloc_vsi; v++) { if (pf->vsi[v] && - (pf->vsi[v]->flags & I40E_VSI_FLAG_FILTER_CHANGED)) { + (pf->vsi[v]->flags & I40E_VSI_FLAG_FILTER_CHANGED) && + !test_bit(__I40E_VSI_RELEASING, pf->vsi[v]->state)) { int ret = i40e_sync_vsi_filters(pf->vsi[v]); if (ret) { @@ -2610,7 +2893,6 @@ static void i40e_sync_filters_subtask(struct i40e_pf *pf) } } } - clear_bit(__I40E_VF_DISABLE, pf->state); } /** @@ -2765,8 +3047,21 @@ int i40e_add_vlan_all_mac(struct i40e_vsi *vsi, s16 vid) int bkt; hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { - if (f->state == I40E_FILTER_REMOVE) + /* If we're asked to add a filter that has been marked for + * removal, it is safe to simply restore it to active state. + * __i40e_del_filter will have simply deleted any filters which + * were previously marked NEW or FAILED, so if it is currently + * marked REMOVE it must have previously been ACTIVE. Since we + * haven't yet run the sync filters task, just restore this + * filter to the ACTIVE state so that the sync task leaves it + * in place. + */ + if (f->state == I40E_FILTER_REMOVE && f->vlan == vid) { + f->state = I40E_FILTER_ACTIVE; continue; + } else if (f->state == I40E_FILTER_REMOVE) { + continue; + } add_f = i40e_add_filter(vsi, f->macaddr, vid); if (!add_f) { dev_info(&vsi->back->pdev->dev, @@ -3103,12 +3398,12 @@ static void i40e_config_xps_tx_ring(struct i40e_ring *ring) } /** - * i40e_xsk_umem - Retrieve the AF_XDP ZC if XDP and ZC is enabled + * i40e_xsk_pool - Retrieve the AF_XDP buffer pool if XDP and ZC is enabled * @ring: The Tx or Rx ring * - * Returns the UMEM or NULL. + * Returns the AF_XDP buffer pool or NULL. **/ -static struct xdp_umem *i40e_xsk_umem(struct i40e_ring *ring) +static struct xsk_buff_pool *i40e_xsk_pool(struct i40e_ring *ring) { bool xdp_on = i40e_enabled_xdp_vsi(ring->vsi); int qid = ring->queue_index; @@ -3119,7 +3414,7 @@ static struct xdp_umem *i40e_xsk_umem(struct i40e_ring *ring) if (!xdp_on || !test_bit(qid, ring->vsi->af_xdp_zc_qps)) return NULL; - return xdp_get_umem_from_qid(ring->vsi->netdev, qid); + return xsk_get_pool_from_qid(ring->vsi->netdev, qid); } /** @@ -3138,7 +3433,7 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring) u32 qtx_ctl = 0; if (ring_is_xdp(ring)) - ring->xsk_umem = i40e_xsk_umem(ring); + ring->xsk_pool = i40e_xsk_pool(ring); /* some ATR related tx ring init */ if (vsi->back->flags & I40E_FLAG_FD_ATR_ENABLED) { @@ -3236,6 +3531,17 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring) } /** + * i40e_rx_offset - Return expected offset into page to access data + * @rx_ring: Ring we are requesting offset of + * + * Returns the offset value for ring into the data buffer. + */ +static unsigned int i40e_rx_offset(struct i40e_ring *rx_ring) +{ + return ring_uses_build_skb(rx_ring) ? I40E_SKB_PAD : 0; +} + +/** * i40e_configure_rx_ring - Configure a receive ring context * @ring: The Rx ring to configure * @@ -3260,23 +3566,22 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) if (ring->vsi->type == I40E_VSI_MAIN) xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); - ring->xsk_umem = i40e_xsk_umem(ring); - if (ring->xsk_umem) { - ring->rx_buf_len = ring->xsk_umem->chunk_size_nohr - - XDP_PACKET_HEADROOM; + ring->xsk_pool = i40e_xsk_pool(ring); + if (ring->xsk_pool) { + ring->rx_buf_len = + xsk_pool_get_rx_frame_size(ring->xsk_pool); /* For AF_XDP ZC, we disallow packets to span on * multiple buffers, thus letting us skip that * handling in the fast-path. */ chain_len = 1; - ring->zca.free = i40e_zca_free; ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, - MEM_TYPE_ZERO_COPY, - &ring->zca); + MEM_TYPE_XSK_BUFF_POOL, + NULL); if (ret) return ret; dev_info(&vsi->back->pdev->dev, - "Registered XDP mem model MEM_TYPE_ZERO_COPY on Rx ring %d\n", + "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n", ring->queue_index); } else { @@ -3296,8 +3601,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) rx_ctx.base = (ring->dma / 128); rx_ctx.qlen = ring->count; - /* use 32 byte descriptors */ - rx_ctx.dsize = 1; + /* use 16 byte descriptors */ + rx_ctx.dsize = 0; /* descriptor type is always zero * rx_ctx.dtype = 0; @@ -3340,20 +3645,25 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) else set_ring_build_skb_enabled(ring); + ring->rx_offset = i40e_rx_offset(ring); + /* cache tail for quicker writes, and clear the reg before use */ ring->tail = hw->hw_addr + I40E_QRX_TAIL(pf_q); writel(0, ring->tail); - ok = ring->xsk_umem ? - i40e_alloc_rx_buffers_zc(ring, I40E_DESC_UNUSED(ring)) : - !i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring)); + if (ring->xsk_pool) { + xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq); + ok = i40e_alloc_rx_buffers_zc(ring, I40E_DESC_UNUSED(ring)); + } else { + ok = !i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring)); + } if (!ok) { /* Log this in case the user has forgotten to give the kernel * any buffers, even later in the application. */ dev_info(&vsi->back->pdev->dev, "Failed to allocate some buffers on %sRx ring %d (pf_q %d)\n", - ring->xsk_umem ? "UMEM enabled " : "", + ring->xsk_pool ? "AF_XDP ZC enabled " : "", ring->queue_index, pf_q); } @@ -3463,6 +3773,24 @@ static void i40e_set_vsi_rx_mode(struct i40e_vsi *vsi) } /** + * i40e_reset_fdir_filter_cnt - Reset flow director filter counters + * @pf: Pointer to the targeted PF + * + * Set all flow director counters to 0. + */ +static void i40e_reset_fdir_filter_cnt(struct i40e_pf *pf) +{ + pf->fd_tcp4_filter_cnt = 0; + pf->fd_udp4_filter_cnt = 0; + pf->fd_sctp4_filter_cnt = 0; + pf->fd_ip4_filter_cnt = 0; + pf->fd_tcp6_filter_cnt = 0; + pf->fd_udp6_filter_cnt = 0; + pf->fd_sctp6_filter_cnt = 0; + pf->fd_ip6_filter_cnt = 0; +} + +/** * i40e_fdir_filter_restore - Restore the Sideband Flow Director filters * @vsi: Pointer to the targeted VSI * @@ -3479,10 +3807,7 @@ static void i40e_fdir_filter_restore(struct i40e_vsi *vsi) return; /* Reset FDir counters as we're replaying all existing filters */ - pf->fd_tcp4_filter_cnt = 0; - pf->fd_udp4_filter_cnt = 0; - pf->fd_sctp4_filter_cnt = 0; - pf->fd_ip4_filter_cnt = 0; + i40e_reset_fdir_filter_cnt(pf); hlist_for_each_entry_safe(filter, node, &pf->fdir_filter_list, fdir_node) { @@ -3547,7 +3872,7 @@ static void i40e_vsi_configure_msix(struct i40e_vsi *vsi) wr32(hw, I40E_PFINT_RATEN(vector - 1), i40e_intrl_usec_to_reg(vsi->int_rate_limit)); - /* Linked list for the queuepairs assigned to this vector */ + /* begin of linked list for RX queue assigned to this vector */ wr32(hw, I40E_PFINT_LNKLSTN(vector - 1), qp); for (q = 0; q < q_vector->num_ringpairs; q++) { u32 nextqp = has_xdp ? qp + vsi->alloc_queue_pairs : qp; @@ -3563,6 +3888,7 @@ static void i40e_vsi_configure_msix(struct i40e_vsi *vsi) wr32(hw, I40E_QINT_RQCTL(qp), val); if (has_xdp) { + /* TX queue with next queue set to TX */ val = I40E_QINT_TQCTL_CAUSE_ENA_MASK | (I40E_TX_ITR << I40E_QINT_TQCTL_ITR_INDX_SHIFT) | (vector << I40E_QINT_TQCTL_MSIX_INDX_SHIFT) | @@ -3572,7 +3898,7 @@ static void i40e_vsi_configure_msix(struct i40e_vsi *vsi) wr32(hw, I40E_QINT_TQCTL(nextqp), val); } - + /* TX queue with next RX or end of linked list */ val = I40E_QINT_TQCTL_CAUSE_ENA_MASK | (I40E_TX_ITR << I40E_QINT_TQCTL_ITR_INDX_SHIFT) | (vector << I40E_QINT_TQCTL_MSIX_INDX_SHIFT) | @@ -3641,7 +3967,6 @@ static void i40e_configure_msi_and_legacy(struct i40e_vsi *vsi) struct i40e_q_vector *q_vector = vsi->q_vectors[0]; struct i40e_pf *pf = vsi->back; struct i40e_hw *hw = &pf->hw; - u32 val; /* set the ITR configuration */ q_vector->rx.next_update = jiffies + 1; @@ -3658,28 +3983,20 @@ static void i40e_configure_msi_and_legacy(struct i40e_vsi *vsi) /* FIRSTQ_INDX = 0, FIRSTQ_TYPE = 0 (rx) */ wr32(hw, I40E_PFINT_LNKLST0, 0); - /* Associate the queue pair to the vector and enable the queue int */ - val = I40E_QINT_RQCTL_CAUSE_ENA_MASK | - (I40E_RX_ITR << I40E_QINT_RQCTL_ITR_INDX_SHIFT) | - (nextqp << I40E_QINT_RQCTL_NEXTQ_INDX_SHIFT)| - (I40E_QUEUE_TYPE_TX << I40E_QINT_TQCTL_NEXTQ_TYPE_SHIFT); - - wr32(hw, I40E_QINT_RQCTL(0), val); + /* Associate the queue pair to the vector and enable the queue + * interrupt RX queue in linked list with next queue set to TX + */ + wr32(hw, I40E_QINT_RQCTL(0), I40E_QINT_RQCTL_VAL(nextqp, 0, TX)); if (i40e_enabled_xdp_vsi(vsi)) { - val = I40E_QINT_TQCTL_CAUSE_ENA_MASK | - (I40E_TX_ITR << I40E_QINT_TQCTL_ITR_INDX_SHIFT)| - (I40E_QUEUE_TYPE_TX - << I40E_QINT_TQCTL_NEXTQ_TYPE_SHIFT); - - wr32(hw, I40E_QINT_TQCTL(nextqp), val); + /* TX queue in linked list with next queue set to TX */ + wr32(hw, I40E_QINT_TQCTL(nextqp), + I40E_QINT_TQCTL_VAL(nextqp, 0, TX)); } - val = I40E_QINT_TQCTL_CAUSE_ENA_MASK | - (I40E_TX_ITR << I40E_QINT_TQCTL_ITR_INDX_SHIFT) | - (I40E_QUEUE_END_OF_LIST << I40E_QINT_TQCTL_NEXTQ_INDX_SHIFT); - - wr32(hw, I40E_QINT_TQCTL(0), val); + /* last TX queue so the next RX queue doesn't matter */ + wr32(hw, I40E_QINT_TQCTL(0), + I40E_QINT_TQCTL_VAL(I40E_QUEUE_END_OF_LIST, 0, RX)); i40e_flush(hw); } @@ -3813,10 +4130,10 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename) * * get_cpu_mask returns a static constant mask with * a permanent lifetime so it's ok to pass to - * irq_set_affinity_hint without making a copy. + * irq_update_affinity_hint without making a copy. */ cpu = cpumask_local_spread(q_vector->v_idx, -1); - irq_set_affinity_hint(irq_num, get_cpu_mask(cpu)); + irq_update_affinity_hint(irq_num, get_cpu_mask(cpu)); } vsi->irqs_ready = true; @@ -3827,7 +4144,7 @@ free_queue_irqs: vector--; irq_num = pf->msix_entries[base + vector].vector; irq_set_affinity_notifier(irq_num, NULL); - irq_set_affinity_hint(irq_num, NULL); + irq_update_affinity_hint(irq_num, NULL); free_irq(irq_num, &vsi->q_vectors[vector]); } return err; @@ -3910,7 +4227,6 @@ static void i40e_free_misc_vector(struct i40e_pf *pf) i40e_flush(&pf->hw); if (pf->flags & I40E_FLAG_MSIX_ENABLED && pf->msix_entries) { - synchronize_irq(pf->msix_entries[0].vector); free_irq(pf->msix_entries[0].vector, pf); clear_bit(__I40E_MISC_IRQ_REQUESTED, pf->state); } @@ -3979,8 +4295,16 @@ static irqreturn_t i40e_intr(int irq, void *data) } if (icr0 & I40E_PFINT_ICR0_VFLR_MASK) { - ena_mask &= ~I40E_PFINT_ICR0_ENA_VFLR_MASK; - set_bit(__I40E_VFLR_EVENT_PENDING, pf->state); + /* disable any further VFLR event notifications */ + if (test_bit(__I40E_VF_RESETS_DISABLED, pf->state)) { + u32 reg = rd32(hw, I40E_PFINT_ICR0_ENA); + + reg &= ~I40E_PFINT_ICR0_VFLR_MASK; + wr32(hw, I40E_PFINT_ICR0_ENA, reg); + } else { + ena_mask &= ~I40E_PFINT_ICR0_ENA_VFLR_MASK; + set_bit(__I40E_VFLR_EVENT_PENDING, pf->state); + } } if (icr0 & I40E_PFINT_ICR0_GRST_MASK) { @@ -4011,10 +4335,13 @@ static irqreturn_t i40e_intr(int irq, void *data) if (icr0 & I40E_PFINT_ICR0_TIMESYNC_MASK) { u32 prttsyn_stat = rd32(hw, I40E_PRTTSYN_STAT_0); - if (prttsyn_stat & I40E_PRTTSYN_STAT_0_TXTIME_MASK) { - icr0 &= ~I40E_PFINT_ICR0_ENA_TIMESYNC_MASK; + if (prttsyn_stat & I40E_PRTTSYN_STAT_0_EVENT0_MASK) + schedule_work(&pf->ptp_extts0_work); + + if (prttsyn_stat & I40E_PRTTSYN_STAT_0_TXTIME_MASK) i40e_ptp_tx_hwtstamp(pf); - } + + icr0 &= ~I40E_PFINT_ICR0_ENA_TIMESYNC_MASK; } /* If a critical error is pending we have no choice but to reset the @@ -4386,11 +4713,10 @@ int i40e_control_wait_tx_q(int seid, struct i40e_pf *pf, int pf_q, } /** - * i40e_vsi_control_tx - Start or stop a VSI's rings + * i40e_vsi_enable_tx - Start a VSI's rings * @vsi: the VSI being configured - * @enable: start or stop the rings **/ -static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable) +static int i40e_vsi_enable_tx(struct i40e_vsi *vsi) { struct i40e_pf *pf = vsi->back; int i, pf_q, ret = 0; @@ -4399,7 +4725,7 @@ static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable) for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) { ret = i40e_control_wait_tx_q(vsi->seid, pf, pf_q, - false /*is xdp*/, enable); + false /*is xdp*/, true); if (ret) break; @@ -4408,7 +4734,7 @@ static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable) ret = i40e_control_wait_tx_q(vsi->seid, pf, pf_q + vsi->alloc_queue_pairs, - true /*is xdp*/, enable); + true /*is xdp*/, true); if (ret) break; } @@ -4506,32 +4832,25 @@ int i40e_control_wait_rx_q(struct i40e_pf *pf, int pf_q, bool enable) } /** - * i40e_vsi_control_rx - Start or stop a VSI's rings + * i40e_vsi_enable_rx - Start a VSI's rings * @vsi: the VSI being configured - * @enable: start or stop the rings **/ -static int i40e_vsi_control_rx(struct i40e_vsi *vsi, bool enable) +static int i40e_vsi_enable_rx(struct i40e_vsi *vsi) { struct i40e_pf *pf = vsi->back; int i, pf_q, ret = 0; pf_q = vsi->base_queue; for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) { - ret = i40e_control_wait_rx_q(pf, pf_q, enable); + ret = i40e_control_wait_rx_q(pf, pf_q, true); if (ret) { dev_info(&pf->pdev->dev, - "VSI seid %d Rx ring %d %sable timeout\n", - vsi->seid, pf_q, (enable ? "en" : "dis")); + "VSI seid %d Rx ring %d enable timeout\n", + vsi->seid, pf_q); break; } } - /* Due to HW errata, on Rx disable only, the register can indicate done - * before it really is. Needs 50ms to be sure - */ - if (!enable) - mdelay(50); - return ret; } @@ -4544,29 +4863,47 @@ int i40e_vsi_start_rings(struct i40e_vsi *vsi) int ret = 0; /* do rx first for enable and last for disable */ - ret = i40e_vsi_control_rx(vsi, true); + ret = i40e_vsi_enable_rx(vsi); if (ret) return ret; - ret = i40e_vsi_control_tx(vsi, true); + ret = i40e_vsi_enable_tx(vsi); return ret; } +#define I40E_DISABLE_TX_GAP_MSEC 50 + /** * i40e_vsi_stop_rings - Stop a VSI's rings * @vsi: the VSI being configured **/ void i40e_vsi_stop_rings(struct i40e_vsi *vsi) { + struct i40e_pf *pf = vsi->back; + int pf_q, err, q_end; + /* When port TX is suspended, don't wait */ if (test_bit(__I40E_PORT_SUSPENDED, vsi->back->state)) return i40e_vsi_stop_rings_no_wait(vsi); - /* do rx first for enable and last for disable - * Ignore return value, we need to shutdown whatever we can - */ - i40e_vsi_control_tx(vsi, false); - i40e_vsi_control_rx(vsi, false); + q_end = vsi->base_queue + vsi->num_queue_pairs; + for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++) + i40e_pre_tx_queue_cfg(&pf->hw, (u32)pf_q, false); + + for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++) { + err = i40e_control_wait_rx_q(pf, pf_q, false); + if (err) + dev_info(&pf->pdev->dev, + "VSI seid %d Rx ring %d disable timeout\n", + vsi->seid, pf_q); + } + + msleep(I40E_DISABLE_TX_GAP_MSEC); + pf_q = vsi->base_queue; + for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++) + wr32(&pf->hw, I40E_QTX_ENA(pf_q), 0); + + i40e_vsi_wait_queues_disabled(vsi); } /** @@ -4627,8 +4964,7 @@ static void i40e_vsi_free_irq(struct i40e_vsi *vsi) /* clear the affinity notifier in the IRQ descriptor */ irq_set_affinity_notifier(irq_num, NULL); /* remove our suggested affinity mask for this IRQ */ - irq_set_affinity_hint(irq_num, NULL); - synchronize_irq(irq_num); + irq_update_affinity_hint(irq_num, NULL); free_irq(irq_num, vsi->q_vectors[i]); /* Tear down the interrupt queue link list @@ -4790,7 +5126,8 @@ static void i40e_clear_interrupt_scheme(struct i40e_pf *pf) { int i; - i40e_free_misc_vector(pf); + if (test_bit(__I40E_MISC_IRQ_REQUESTED, pf->state)) + i40e_free_misc_vector(pf); i40e_put_lump(pf->irq_pile, pf->iwarp_base_vector, I40E_IWARP_IRQ_PILE_ID); @@ -5111,7 +5448,7 @@ static u8 i40e_pf_get_num_tc(struct i40e_pf *pf) u8 num_tc = 0; struct i40e_dcbx_config *dcbcfg = &hw->local_dcbx_config; - if (pf->flags & I40E_FLAG_TC_MQPRIO) + if (i40e_is_tc_mqprio_enabled(pf)) return pf->vsi[pf->lan_vsi]->mqprio_qopt.qopt.num_tc; /* If neither MQPRIO nor DCB is enabled, then always use single TC */ @@ -5136,14 +5473,14 @@ static u8 i40e_pf_get_num_tc(struct i40e_pf *pf) } /** - * i40e_pf_get_pf_tc_map - Get bitmap for enabled traffic classes + * i40e_pf_get_tc_map - Get bitmap for enabled traffic classes * @pf: PF being queried * * Return a bitmap for enabled traffic classes for this PF. **/ static u8 i40e_pf_get_tc_map(struct i40e_pf *pf) { - if (pf->flags & I40E_FLAG_TC_MQPRIO) + if (i40e_is_tc_mqprio_enabled(pf)) return i40e_mqprio_get_enabled_tc(pf); /* If neither MQPRIO nor DCB is enabled for this PF then just return @@ -5240,7 +5577,7 @@ static int i40e_vsi_configure_bw_alloc(struct i40e_vsi *vsi, u8 enabled_tc, int i; /* There is no need to reset BW when mqprio mode is on. */ - if (pf->flags & I40E_FLAG_TC_MQPRIO) + if (i40e_is_tc_mqprio_enabled(pf)) return 0; if (!vsi->mqprio_qopt.qopt.hw && !(pf->flags & I40E_FLAG_DCB_ENABLED)) { ret = i40e_set_bw_limit(vsi, vsi->seid, 0); @@ -5250,6 +5587,7 @@ static int i40e_vsi_configure_bw_alloc(struct i40e_vsi *vsi, u8 enabled_tc, vsi->seid); return ret; } + memset(&bw_data, 0, sizeof(bw_data)); bw_data.tc_valid_bits = enabled_tc; for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) bw_data.tc_bw_credits[i] = bw_share[i]; @@ -5311,7 +5649,7 @@ static void i40e_vsi_config_netdev_tc(struct i40e_vsi *vsi, u8 enabled_tc) vsi->tc_config.tc_info[i].qoffset); } - if (pf->flags & I40E_FLAG_TC_MQPRIO) + if (i40e_is_tc_mqprio_enabled(pf)) return; /* Assign UP2TC map for the VSI */ @@ -5344,6 +5682,58 @@ static void i40e_vsi_update_queue_map(struct i40e_vsi *vsi, } /** + * i40e_update_adq_vsi_queues - update queue mapping for ADq VSI + * @vsi: the VSI being reconfigured + * @vsi_offset: offset from main VF VSI + */ +int i40e_update_adq_vsi_queues(struct i40e_vsi *vsi, int vsi_offset) +{ + struct i40e_vsi_context ctxt = {}; + struct i40e_pf *pf; + struct i40e_hw *hw; + int ret; + + if (!vsi) + return I40E_ERR_PARAM; + pf = vsi->back; + hw = &pf->hw; + + ctxt.seid = vsi->seid; + ctxt.pf_num = hw->pf_id; + ctxt.vf_num = vsi->vf_id + hw->func_caps.vf_base_id + vsi_offset; + ctxt.uplink_seid = vsi->uplink_seid; + ctxt.connection_type = I40E_AQ_VSI_CONN_TYPE_NORMAL; + ctxt.flags = I40E_AQ_VSI_TYPE_VF; + ctxt.info = vsi->info; + + i40e_vsi_setup_queue_map(vsi, &ctxt, vsi->tc_config.enabled_tc, + false); + if (vsi->reconfig_rss) { + vsi->rss_size = min_t(int, pf->alloc_rss_size, + vsi->num_queue_pairs); + ret = i40e_vsi_config_rss(vsi); + if (ret) { + dev_info(&pf->pdev->dev, "Failed to reconfig rss for num_queues\n"); + return ret; + } + vsi->reconfig_rss = false; + } + + ret = i40e_aq_update_vsi_params(hw, &ctxt, NULL); + if (ret) { + dev_info(&pf->pdev->dev, "Update vsi config failed, err %s aq_err %s\n", + i40e_stat_str(hw, ret), + i40e_aq_str(hw, hw->aq.asq_last_status)); + return ret; + } + /* update the local VSI info with updated queue map */ + i40e_vsi_update_queue_map(vsi, &ctxt); + vsi->info.valid_sections = 0; + + return ret; +} + +/** * i40e_vsi_config_tc - Configure VSI Tx Scheduler for given TC map * @vsi: VSI to be configured * @enabled_tc: TC bitmap @@ -5420,7 +5810,7 @@ static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc) ctxt.vf_num = 0; ctxt.uplink_seid = vsi->uplink_seid; ctxt.info = vsi->info; - if (vsi->back->flags & I40E_FLAG_TC_MQPRIO) { + if (i40e_is_tc_mqprio_enabled(pf)) { ret = i40e_vsi_setup_queue_map_mqprio(vsi, &ctxt, enabled_tc); if (ret) goto out; @@ -5505,6 +5895,26 @@ static int i40e_get_link_speed(struct i40e_vsi *vsi) } /** + * i40e_bw_bytes_to_mbits - Convert max_tx_rate from bytes to mbits + * @vsi: Pointer to vsi structure + * @max_tx_rate: max TX rate in bytes to be converted into Mbits + * + * Helper function to convert units before send to set BW limit + **/ +static u64 i40e_bw_bytes_to_mbits(struct i40e_vsi *vsi, u64 max_tx_rate) +{ + if (max_tx_rate < I40E_BW_MBPS_DIVISOR) { + dev_warn(&vsi->back->pdev->dev, + "Setting max tx rate to minimum usable value of 50Mbps.\n"); + max_tx_rate = I40E_BW_CREDIT_DIVISOR; + } else { + do_div(max_tx_rate, I40E_BW_MBPS_DIVISOR); + } + + return max_tx_rate; +} + +/** * i40e_set_bw_limit - setup BW limit for Tx traffic based on max_tx_rate * @vsi: VSI to be configured * @seid: seid of the channel/VSI @@ -5526,10 +5936,10 @@ int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate) max_tx_rate, seid); return -EINVAL; } - if (max_tx_rate && max_tx_rate < 50) { + if (max_tx_rate && max_tx_rate < I40E_BW_CREDIT_DIVISOR) { dev_warn(&pf->pdev->dev, "Setting max tx rate to minimum usable value of 50Mbps.\n"); - max_tx_rate = 50; + max_tx_rate = I40E_BW_CREDIT_DIVISOR; } /* Tx rate credits are in values of 50Mbps, 0 is disabled */ @@ -5634,24 +6044,6 @@ static void i40e_remove_queue_channels(struct i40e_vsi *vsi) } /** - * i40e_is_any_channel - channel exist or not - * @vsi: ptr to VSI to which channels are associated with - * - * Returns true or false if channel(s) exist for associated VSI or not - **/ -static bool i40e_is_any_channel(struct i40e_vsi *vsi) -{ - struct i40e_channel *ch, *ch_tmp; - - list_for_each_entry_safe(ch, ch_tmp, &vsi->ch_list, list) { - if (ch->initialized) - return true; - } - - return false; -} - -/** * i40e_get_max_queues_for_channel * @vsi: ptr to VSI to which channels are associated with * @@ -5787,7 +6179,6 @@ static int i40e_vsi_reconfig_rss(struct i40e_vsi *vsi, u16 rss_size) /** * i40e_channel_setup_queue_map - Setup a channel queue map * @pf: ptr to PF device - * @vsi: the VSI being setup * @ctxt: VSI context structure * @ch: ptr to channel structure * @@ -5881,7 +6272,7 @@ static int i40e_add_channel(struct i40e_pf *pf, u16 uplink_seid, ch->enabled_tc = !i40e_is_channel_macvlan(ch) && enabled_tc; ch->seid = ctxt.seid; ch->vsi_number = ctxt.vsi_number; - ch->stat_counter_idx = cpu_to_le16(ctxt.info.stat_counter_idx); + ch->stat_counter_idx = le16_to_cpu(ctxt.info.stat_counter_idx); /* copy just the sections touched not the entire info * since not all sections are valid as returned by @@ -5903,6 +6294,7 @@ static int i40e_channel_config_bw(struct i40e_vsi *vsi, struct i40e_channel *ch, i40e_status ret; int i; + memset(&bw_data, 0, sizeof(bw_data)); bw_data.tc_valid_bits = ch->enabled_tc; for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) bw_data.tc_bw_credits[i] = bw_share[i]; @@ -6030,8 +6422,7 @@ static inline int i40e_setup_hw_channel(struct i40e_pf *pf, /** * i40e_setup_channel - setup new channel using uplink element * @pf: ptr to PF device - * @type: type of channel to be created (VMDq2/VF) - * @uplink_seid: underlying HW switching element (VEB) ID + * @vsi: pointer to the VSI to set up the channel within * @ch: ptr to channel structure * * Setup new channel (VSI) based on specified type (VMDq2/VF) @@ -6158,26 +6549,15 @@ int i40e_create_queue_channel(struct i40e_vsi *vsi, /* By default we are in VEPA mode, if this is the first VF/VMDq * VSI to be added switch to VEB mode. */ - if ((!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) || - (!i40e_is_any_channel(vsi))) { - if (!is_power_of_2(vsi->tc_config.tc_info[0].qcount)) { - dev_dbg(&pf->pdev->dev, - "Failed to create channel. Override queues (%u) not power of 2\n", - vsi->tc_config.tc_info[0].qcount); - return -EINVAL; - } - if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) { - pf->flags |= I40E_FLAG_VEB_MODE_ENABLED; + if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) { + pf->flags |= I40E_FLAG_VEB_MODE_ENABLED; - if (vsi->type == I40E_VSI_MAIN) { - if (pf->flags & I40E_FLAG_TC_MQPRIO) - i40e_do_reset(pf, I40E_PF_RESET_FLAG, - true); - else - i40e_do_reset_safe(pf, - I40E_PF_RESET_FLAG); - } + if (vsi->type == I40E_VSI_MAIN) { + if (i40e_is_tc_mqprio_enabled(pf)) + i40e_do_reset(pf, I40E_PF_RESET_FLAG, true); + else + i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG); } /* now onwards for main VSI, number of queues will be value * of TC0's queue count @@ -6285,6 +6665,9 @@ static int i40e_configure_queue_channels(struct i40e_vsi *vsi) vsi->tc_seid_map[i] = ch->seid; } } + + /* reset to reconfigure TX queue contexts */ + i40e_do_reset(vsi->back, I40E_PF_RESET_FLAG, true); return ret; err_free: @@ -6359,6 +6742,9 @@ static void i40e_dcb_reconfigure(struct i40e_pf *pf) /* Enable the TCs available on PF to all VEBs */ tc_map = i40e_pf_get_tc_map(pf); + if (tc_map == I40E_DEFAULT_TRAFFIC_CLASS) + return; + for (v = 0; v < I40E_MAX_VEB; v++) { if (!pf->veb[v]) continue; @@ -6426,6 +6812,316 @@ static int i40e_resume_port_tx(struct i40e_pf *pf) } /** + * i40e_suspend_port_tx - Suspend port Tx + * @pf: PF struct + * + * Suspend a port's Tx and issue a PF reset in case of failure. + **/ +static int i40e_suspend_port_tx(struct i40e_pf *pf) +{ + struct i40e_hw *hw = &pf->hw; + int ret; + + ret = i40e_aq_suspend_port_tx(hw, pf->mac_seid, NULL); + if (ret) { + dev_info(&pf->pdev->dev, + "Suspend Port Tx failed, err %s aq_err %s\n", + i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); + /* Schedule PF reset to recover */ + set_bit(__I40E_PF_RESET_REQUESTED, pf->state); + i40e_service_event_schedule(pf); + } + + return ret; +} + +/** + * i40e_hw_set_dcb_config - Program new DCBX settings into HW + * @pf: PF being configured + * @new_cfg: New DCBX configuration + * + * Program DCB settings into HW and reconfigure VEB/VSIs on + * given PF. Uses "Set LLDP MIB" AQC to program the hardware. + **/ +static int i40e_hw_set_dcb_config(struct i40e_pf *pf, + struct i40e_dcbx_config *new_cfg) +{ + struct i40e_dcbx_config *old_cfg = &pf->hw.local_dcbx_config; + int ret; + + /* Check if need reconfiguration */ + if (!memcmp(&new_cfg, &old_cfg, sizeof(new_cfg))) { + dev_dbg(&pf->pdev->dev, "No Change in DCB Config required.\n"); + return 0; + } + + /* Config change disable all VSIs */ + i40e_pf_quiesce_all_vsi(pf); + + /* Copy the new config to the current config */ + *old_cfg = *new_cfg; + old_cfg->etsrec = old_cfg->etscfg; + ret = i40e_set_dcb_config(&pf->hw); + if (ret) { + dev_info(&pf->pdev->dev, + "Set DCB Config failed, err %s aq_err %s\n", + i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); + goto out; + } + + /* Changes in configuration update VEB/VSI */ + i40e_dcb_reconfigure(pf); +out: + /* In case of reset do not try to resume anything */ + if (!test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) { + /* Re-start the VSIs if disabled */ + ret = i40e_resume_port_tx(pf); + /* In case of error no point in resuming VSIs */ + if (ret) + goto err; + i40e_pf_unquiesce_all_vsi(pf); + } +err: + return ret; +} + +/** + * i40e_hw_dcb_config - Program new DCBX settings into HW + * @pf: PF being configured + * @new_cfg: New DCBX configuration + * + * Program DCB settings into HW and reconfigure VEB/VSIs on + * given PF + **/ +int i40e_hw_dcb_config(struct i40e_pf *pf, struct i40e_dcbx_config *new_cfg) +{ + struct i40e_aqc_configure_switching_comp_ets_data ets_data; + u8 prio_type[I40E_MAX_TRAFFIC_CLASS] = {0}; + u32 mfs_tc[I40E_MAX_TRAFFIC_CLASS]; + struct i40e_dcbx_config *old_cfg; + u8 mode[I40E_MAX_TRAFFIC_CLASS]; + struct i40e_rx_pb_config pb_cfg; + struct i40e_hw *hw = &pf->hw; + u8 num_ports = hw->num_ports; + bool need_reconfig; + int ret = -EINVAL; + u8 lltc_map = 0; + u8 tc_map = 0; + u8 new_numtc; + u8 i; + + dev_dbg(&pf->pdev->dev, "Configuring DCB registers directly\n"); + /* Un-pack information to Program ETS HW via shared API + * numtc, tcmap + * LLTC map + * ETS/NON-ETS arbiter mode + * max exponent (credit refills) + * Total number of ports + * PFC priority bit-map + * Priority Table + * BW % per TC + * Arbiter mode between UPs sharing same TC + * TSA table (ETS or non-ETS) + * EEE enabled or not + * MFS TC table + */ + + new_numtc = i40e_dcb_get_num_tc(new_cfg); + + memset(&ets_data, 0, sizeof(ets_data)); + for (i = 0; i < new_numtc; i++) { + tc_map |= BIT(i); + switch (new_cfg->etscfg.tsatable[i]) { + case I40E_IEEE_TSA_ETS: + prio_type[i] = I40E_DCB_PRIO_TYPE_ETS; + ets_data.tc_bw_share_credits[i] = + new_cfg->etscfg.tcbwtable[i]; + break; + case I40E_IEEE_TSA_STRICT: + prio_type[i] = I40E_DCB_PRIO_TYPE_STRICT; + lltc_map |= BIT(i); + ets_data.tc_bw_share_credits[i] = + I40E_DCB_STRICT_PRIO_CREDITS; + break; + default: + /* Invalid TSA type */ + need_reconfig = false; + goto out; + } + } + + old_cfg = &hw->local_dcbx_config; + /* Check if need reconfiguration */ + need_reconfig = i40e_dcb_need_reconfig(pf, old_cfg, new_cfg); + + /* If needed, enable/disable frame tagging, disable all VSIs + * and suspend port tx + */ + if (need_reconfig) { + /* Enable DCB tagging only when more than one TC */ + if (new_numtc > 1) + pf->flags |= I40E_FLAG_DCB_ENABLED; + else + pf->flags &= ~I40E_FLAG_DCB_ENABLED; + + set_bit(__I40E_PORT_SUSPENDED, pf->state); + /* Reconfiguration needed quiesce all VSIs */ + i40e_pf_quiesce_all_vsi(pf); + ret = i40e_suspend_port_tx(pf); + if (ret) + goto err; + } + + /* Configure Port ETS Tx Scheduler */ + ets_data.tc_valid_bits = tc_map; + ets_data.tc_strict_priority_flags = lltc_map; + ret = i40e_aq_config_switch_comp_ets + (hw, pf->mac_seid, &ets_data, + i40e_aqc_opc_modify_switching_comp_ets, NULL); + if (ret) { + dev_info(&pf->pdev->dev, + "Modify Port ETS failed, err %s aq_err %s\n", + i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); + goto out; + } + + /* Configure Rx ETS HW */ + memset(&mode, I40E_DCB_ARB_MODE_ROUND_ROBIN, sizeof(mode)); + i40e_dcb_hw_set_num_tc(hw, new_numtc); + i40e_dcb_hw_rx_fifo_config(hw, I40E_DCB_ARB_MODE_ROUND_ROBIN, + I40E_DCB_ARB_MODE_STRICT_PRIORITY, + I40E_DCB_DEFAULT_MAX_EXPONENT, + lltc_map); + i40e_dcb_hw_rx_cmd_monitor_config(hw, new_numtc, num_ports); + i40e_dcb_hw_rx_ets_bw_config(hw, new_cfg->etscfg.tcbwtable, mode, + prio_type); + i40e_dcb_hw_pfc_config(hw, new_cfg->pfc.pfcenable, + new_cfg->etscfg.prioritytable); + i40e_dcb_hw_rx_up2tc_config(hw, new_cfg->etscfg.prioritytable); + + /* Configure Rx Packet Buffers in HW */ + for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { + mfs_tc[i] = pf->vsi[pf->lan_vsi]->netdev->mtu; + mfs_tc[i] += I40E_PACKET_HDR_PAD; + } + + i40e_dcb_hw_calculate_pool_sizes(hw, num_ports, + false, new_cfg->pfc.pfcenable, + mfs_tc, &pb_cfg); + i40e_dcb_hw_rx_pb_config(hw, &pf->pb_cfg, &pb_cfg); + + /* Update the local Rx Packet buffer config */ + pf->pb_cfg = pb_cfg; + + /* Inform the FW about changes to DCB configuration */ + ret = i40e_aq_dcb_updated(&pf->hw, NULL); + if (ret) { + dev_info(&pf->pdev->dev, + "DCB Updated failed, err %s aq_err %s\n", + i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); + goto out; + } + + /* Update the port DCBx configuration */ + *old_cfg = *new_cfg; + + /* Changes in configuration update VEB/VSI */ + i40e_dcb_reconfigure(pf); +out: + /* Re-start the VSIs if disabled */ + if (need_reconfig) { + ret = i40e_resume_port_tx(pf); + + clear_bit(__I40E_PORT_SUSPENDED, pf->state); + /* In case of error no point in resuming VSIs */ + if (ret) + goto err; + + /* Wait for the PF's queues to be disabled */ + ret = i40e_pf_wait_queues_disabled(pf); + if (ret) { + /* Schedule PF reset to recover */ + set_bit(__I40E_PF_RESET_REQUESTED, pf->state); + i40e_service_event_schedule(pf); + goto err; + } else { + i40e_pf_unquiesce_all_vsi(pf); + set_bit(__I40E_CLIENT_SERVICE_REQUESTED, pf->state); + set_bit(__I40E_CLIENT_L2_CHANGE, pf->state); + } + /* registers are set, lets apply */ + if (pf->hw_features & I40E_HW_USE_SET_LLDP_MIB) + ret = i40e_hw_set_dcb_config(pf, new_cfg); + } + +err: + return ret; +} + +/** + * i40e_dcb_sw_default_config - Set default DCB configuration when DCB in SW + * @pf: PF being queried + * + * Set default DCB configuration in case DCB is to be done in SW. + **/ +int i40e_dcb_sw_default_config(struct i40e_pf *pf) +{ + struct i40e_dcbx_config *dcb_cfg = &pf->hw.local_dcbx_config; + struct i40e_aqc_configure_switching_comp_ets_data ets_data; + struct i40e_hw *hw = &pf->hw; + int err; + + if (pf->hw_features & I40E_HW_USE_SET_LLDP_MIB) { + /* Update the local cached instance with TC0 ETS */ + memset(&pf->tmp_cfg, 0, sizeof(struct i40e_dcbx_config)); + pf->tmp_cfg.etscfg.willing = I40E_IEEE_DEFAULT_ETS_WILLING; + pf->tmp_cfg.etscfg.maxtcs = 0; + pf->tmp_cfg.etscfg.tcbwtable[0] = I40E_IEEE_DEFAULT_ETS_TCBW; + pf->tmp_cfg.etscfg.tsatable[0] = I40E_IEEE_TSA_ETS; + pf->tmp_cfg.pfc.willing = I40E_IEEE_DEFAULT_PFC_WILLING; + pf->tmp_cfg.pfc.pfccap = I40E_MAX_TRAFFIC_CLASS; + /* FW needs one App to configure HW */ + pf->tmp_cfg.numapps = I40E_IEEE_DEFAULT_NUM_APPS; + pf->tmp_cfg.app[0].selector = I40E_APP_SEL_ETHTYPE; + pf->tmp_cfg.app[0].priority = I40E_IEEE_DEFAULT_APP_PRIO; + pf->tmp_cfg.app[0].protocolid = I40E_APP_PROTOID_FCOE; + + return i40e_hw_set_dcb_config(pf, &pf->tmp_cfg); + } + + memset(&ets_data, 0, sizeof(ets_data)); + ets_data.tc_valid_bits = I40E_DEFAULT_TRAFFIC_CLASS; /* TC0 only */ + ets_data.tc_strict_priority_flags = 0; /* ETS */ + ets_data.tc_bw_share_credits[0] = I40E_IEEE_DEFAULT_ETS_TCBW; /* 100% to TC0 */ + + /* Enable ETS on the Physical port */ + err = i40e_aq_config_switch_comp_ets + (hw, pf->mac_seid, &ets_data, + i40e_aqc_opc_enable_switching_comp_ets, NULL); + if (err) { + dev_info(&pf->pdev->dev, + "Enable Port ETS failed, err %s aq_err %s\n", + i40e_stat_str(&pf->hw, err), + i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); + err = -ENOENT; + goto out; + } + + /* Update the local cached instance with TC0 ETS */ + dcb_cfg->etscfg.willing = I40E_IEEE_DEFAULT_ETS_WILLING; + dcb_cfg->etscfg.cbs = 0; + dcb_cfg->etscfg.maxtcs = I40E_MAX_TRAFFIC_CLASS; + dcb_cfg->etscfg.tcbwtable[0] = I40E_IEEE_DEFAULT_ETS_TCBW; + +out: + return err; +} + +/** * i40e_init_pf_dcb - Initialize DCB configuration * @pf: PF being configured * @@ -6435,18 +7131,31 @@ static int i40e_resume_port_tx(struct i40e_pf *pf) static int i40e_init_pf_dcb(struct i40e_pf *pf) { struct i40e_hw *hw = &pf->hw; - int err = 0; + int err; /* Do not enable DCB for SW1 and SW2 images even if the FW is capable * Also do not enable DCBx if FW LLDP agent is disabled */ - if ((pf->hw_features & I40E_HW_NO_DCB_SUPPORT) || - (pf->flags & I40E_FLAG_DISABLE_FW_LLDP)) { - dev_info(&pf->pdev->dev, "DCB is not supported or FW LLDP is disabled\n"); + if (pf->hw_features & I40E_HW_NO_DCB_SUPPORT) { + dev_info(&pf->pdev->dev, "DCB is not supported.\n"); err = I40E_NOT_SUPPORTED; goto out; } - + if (pf->flags & I40E_FLAG_DISABLE_FW_LLDP) { + dev_info(&pf->pdev->dev, "FW LLDP is disabled, attempting SW DCB\n"); + err = i40e_dcb_sw_default_config(pf); + if (err) { + dev_info(&pf->pdev->dev, "Could not initialize SW DCB\n"); + goto out; + } + dev_info(&pf->pdev->dev, "SW DCB initialization succeeded.\n"); + pf->dcbx_cap = DCB_CAP_DCBX_HOST | + DCB_CAP_DCBX_VER_IEEE; + /* at init capable but disabled */ + pf->flags |= I40E_FLAG_DCB_CAPABLE; + pf->flags &= ~I40E_FLAG_DCB_ENABLED; + goto out; + } err = i40e_init_dcb(hw, true); if (!err) { /* Device/Function is not DCBX capable */ @@ -6484,8 +7193,7 @@ out: return err; } #endif /* CONFIG_I40E_DCB */ -#define SPEED_SIZE 14 -#define FC_SIZE 8 + /** * i40e_print_link_message - print link up or down * @vsi: the VSI for which link needs a message @@ -6597,6 +7305,25 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup) netdev_info(vsi->netdev, "NIC Link is Up, %sbps Full Duplex, Requested FEC: %s, Negotiated FEC: %s, Autoneg: %s, Flow Control: %s\n", speed, req_fec, fec, an, fc); + } else if (pf->hw.device_id == I40E_DEV_ID_KX_X722) { + req_fec = "None"; + fec = "None"; + an = "False"; + + if (pf->hw.phy.link_info.an_info & I40E_AQ_AN_COMPLETED) + an = "True"; + + if (pf->hw.phy.link_info.fec_info & + I40E_AQ_CONFIG_FEC_KR_ENA) + fec = "CL74 FC-FEC/BASE-R"; + + if (pf->hw.phy.link_info.req_fec_info & + I40E_AQ_REQUEST_FEC_KR) + req_fec = "CL74 FC-FEC/BASE-R"; + + netdev_info(vsi->netdev, + "NIC Link is Up, %sbps Full Duplex, Requested FEC: %s, Negotiated FEC: %s, Autoneg: %s, Flow Control: %s\n", + speed, req_fec, fec, an, fc); } else { netdev_info(vsi->netdev, "NIC Link is Up, %sbps Full Duplex, Flow Control: %s\n", @@ -6663,7 +7390,6 @@ static void i40e_vsi_reinit_locked(struct i40e_vsi *vsi) { struct i40e_pf *pf = vsi->back; - WARN_ON(in_interrupt()); while (test_and_set_bit(__I40E_CONFIG_BUSY, pf->state)) usleep_range(1000, 2000); i40e_down(vsi); @@ -6673,21 +7399,6 @@ static void i40e_vsi_reinit_locked(struct i40e_vsi *vsi) } /** - * i40e_up - Bring the connection back up after being down - * @vsi: the VSI being configured - **/ -int i40e_up(struct i40e_vsi *vsi) -{ - int err; - - err = i40e_vsi_configure(vsi); - if (!err) - err = i40e_up_complete(vsi); - - return err; -} - -/** * i40e_force_link_state - Force the link status * @pf: board private structure * @is_up: whether the link state should be forced up or down @@ -6696,6 +7407,7 @@ static i40e_status i40e_force_link_state(struct i40e_pf *pf, bool is_up) { struct i40e_aq_get_phy_abilities_resp abilities; struct i40e_aq_set_phy_config config = {0}; + bool non_zero_phy_type = is_up; struct i40e_hw *hw = &pf->hw; i40e_status err; u64 mask; @@ -6731,8 +7443,11 @@ static i40e_status i40e_force_link_state(struct i40e_pf *pf, bool is_up) /* If link needs to go up, but was not forced to go down, * and its speed values are OK, no need for a flap + * if non_zero_phy_type was set, still need to force up */ - if (is_up && abilities.phy_type != 0 && abilities.link_speed != 0) + if (pf->flags & I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENABLED) + non_zero_phy_type = true; + else if (is_up && abilities.phy_type != 0 && abilities.link_speed != 0) return I40E_SUCCESS; /* To force link we need to set bits for all supported PHY types, @@ -6740,10 +7455,18 @@ static i40e_status i40e_force_link_state(struct i40e_pf *pf, bool is_up) * across two fields. */ mask = I40E_PHY_TYPES_BITMASK; - config.phy_type = is_up ? cpu_to_le32((u32)(mask & 0xffffffff)) : 0; - config.phy_type_ext = is_up ? (u8)((mask >> 32) & 0xff) : 0; + config.phy_type = + non_zero_phy_type ? cpu_to_le32((u32)(mask & 0xffffffff)) : 0; + config.phy_type_ext = + non_zero_phy_type ? (u8)((mask >> 32) & 0xff) : 0; /* Copy the old settings, except of phy_type */ config.abilities = abilities.abilities; + if (pf->flags & I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENABLED) { + if (is_up) + config.abilities |= I40E_AQ_PHY_ENABLE_LINK; + else + config.abilities &= ~(I40E_AQ_PHY_ENABLE_LINK); + } if (abilities.link_speed != 0) config.link_speed = abilities.link_speed; else @@ -6774,12 +7497,32 @@ static i40e_status i40e_force_link_state(struct i40e_pf *pf, bool is_up) i40e_update_link_info(hw); } - i40e_aq_set_link_restart_an(hw, true, NULL); + i40e_aq_set_link_restart_an(hw, is_up, NULL); return I40E_SUCCESS; } /** + * i40e_up - Bring the connection back up after being down + * @vsi: the VSI being configured + **/ +int i40e_up(struct i40e_vsi *vsi) +{ + int err; + + if (vsi->type == I40E_VSI_MAIN && + (vsi->back->flags & I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED || + vsi->back->flags & I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENABLED)) + i40e_force_link_state(vsi->back, true); + + err = i40e_vsi_configure(vsi); + if (!err) + err = i40e_up_complete(vsi); + + return err; +} + +/** * i40e_down - Shutdown the connection processing * @vsi: the VSI being stopped **/ @@ -6797,7 +7540,8 @@ void i40e_down(struct i40e_vsi *vsi) i40e_vsi_disable_irq(vsi); i40e_vsi_stop_rings(vsi); if (vsi->type == I40E_VSI_MAIN && - vsi->back->flags & I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED) + (vsi->back->flags & I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED || + vsi->back->flags & I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENABLED)) i40e_force_link_state(vsi->back, false); i40e_napi_disable_all(vsi); @@ -6851,6 +7595,8 @@ static int i40e_validate_mqprio_qopt(struct i40e_vsi *vsi, } if (vsi->num_queue_pairs < (mqprio_qopt->qopt.offset[i] + mqprio_qopt->qopt.count[i])) { + dev_err(&vsi->back->pdev->dev, + "Failed to create traffic channel, insufficient number of queues.\n"); return -EINVAL; } if (sum_max_rate > i40e_get_link_speed(vsi)) { @@ -6876,7 +7622,7 @@ static void i40e_vsi_set_default_tc_config(struct i40e_vsi *vsi) qcount = min_t(int, vsi->alloc_queue_pairs, i40e_pf_get_max_q_per_tc(vsi->back)); for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { - /* For the TC that is not enabled set the offset to to default + /* For the TC that is not enabled set the offset to default * queue and allocate one queue for the given TC. */ vsi->tc_config.tc_info[i].qoffset = 0; @@ -7019,42 +7765,43 @@ static void i40e_free_macvlan_channels(struct i40e_vsi *vsi) static int i40e_fwd_ring_up(struct i40e_vsi *vsi, struct net_device *vdev, struct i40e_fwd_adapter *fwd) { + struct i40e_channel *ch = NULL, *ch_tmp, *iter; int ret = 0, num_tc = 1, i, aq_err; - struct i40e_channel *ch, *ch_tmp; struct i40e_pf *pf = vsi->back; struct i40e_hw *hw = &pf->hw; - if (list_empty(&vsi->macvlan_list)) - return -EINVAL; - /* Go through the list and find an available channel */ - list_for_each_entry_safe(ch, ch_tmp, &vsi->macvlan_list, list) { - if (!i40e_is_channel_macvlan(ch)) { - ch->fwd = fwd; + list_for_each_entry_safe(iter, ch_tmp, &vsi->macvlan_list, list) { + if (!i40e_is_channel_macvlan(iter)) { + iter->fwd = fwd; /* record configuration for macvlan interface in vdev */ for (i = 0; i < num_tc; i++) netdev_bind_sb_channel_queue(vsi->netdev, vdev, i, - ch->num_queue_pairs, - ch->base_queue); - for (i = 0; i < ch->num_queue_pairs; i++) { + iter->num_queue_pairs, + iter->base_queue); + for (i = 0; i < iter->num_queue_pairs; i++) { struct i40e_ring *tx_ring, *rx_ring; u16 pf_q; - pf_q = ch->base_queue + i; + pf_q = iter->base_queue + i; /* Get to TX ring ptr */ tx_ring = vsi->tx_rings[pf_q]; - tx_ring->ch = ch; + tx_ring->ch = iter; /* Get the RX ring ptr */ rx_ring = vsi->rx_rings[pf_q]; - rx_ring->ch = ch; + rx_ring->ch = iter; } + ch = iter; break; } } + if (!ch) + return -EINVAL; + /* Guarantee all rings are updated before we update the * MAC address filter. */ @@ -7204,7 +7951,7 @@ static void *i40e_fwd_add(struct net_device *netdev, struct net_device *vdev) netdev_info(netdev, "Macvlans are not supported when DCB is enabled\n"); return ERR_PTR(-EINVAL); } - if ((pf->flags & I40E_FLAG_TC_MQPRIO)) { + if (i40e_is_tc_mqprio_enabled(pf)) { netdev_info(netdev, "Macvlans are not supported when HW TC offload is on\n"); return ERR_PTR(-EINVAL); } @@ -7457,7 +8204,7 @@ config_tc: /* Quiesce VSI queues */ i40e_quiesce_vsi(vsi); - if (!hw && !(pf->flags & I40E_FLAG_TC_MQPRIO)) + if (!hw && !i40e_is_tc_mqprio_enabled(pf)) i40e_remove_queue_channels(vsi); /* Configure VSI for enabled TCs */ @@ -7467,17 +8214,25 @@ config_tc: vsi->seid); need_reset = true; goto exit; - } else { - dev_info(&vsi->back->pdev->dev, - "Setup channel (id:%u) utilizing num_queues %d\n", - vsi->seid, vsi->tc_config.tc_info[0].qcount); + } else if (enabled_tc && + (!is_power_of_2(vsi->tc_config.tc_info[0].qcount))) { + netdev_info(netdev, + "Failed to create channel. Override queues (%u) not power of 2\n", + vsi->tc_config.tc_info[0].qcount); + ret = -EINVAL; + need_reset = true; + goto exit; } - if (pf->flags & I40E_FLAG_TC_MQPRIO) { + dev_info(&vsi->back->pdev->dev, + "Setup channel (id:%u) utilizing num_queues %d\n", + vsi->seid, vsi->tc_config.tc_info[0].qcount); + + if (i40e_is_tc_mqprio_enabled(pf)) { if (vsi->mqprio_qopt.max_rate[0]) { - u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0]; + u64 max_tx_rate = i40e_bw_bytes_to_mbits(vsi, + vsi->mqprio_qopt.max_rate[0]); - do_div(max_tx_rate, I40E_BW_MBPS_DIVISOR); ret = i40e_set_bw_limit(vsi, vsi->seid, max_tx_rate); if (!ret) { u64 credits = max_tx_rate; @@ -7526,8 +8281,8 @@ static inline void i40e_set_cld_element(struct i40e_cloud_filter *filter, struct i40e_aqc_cloud_filters_element_data *cld) { - int i, j; u32 ipa; + int i; memset(cld, 0, sizeof(*cld)); ether_addr_copy(cld->outer_mac, filter->dst_mac); @@ -7538,14 +8293,14 @@ i40e_set_cld_element(struct i40e_cloud_filter *filter, if (filter->n_proto == ETH_P_IPV6) { #define IPV6_MAX_INDEX (ARRAY_SIZE(filter->dst_ipv6) - 1) - for (i = 0, j = 0; i < ARRAY_SIZE(filter->dst_ipv6); - i++, j += 2) { + for (i = 0; i < ARRAY_SIZE(filter->dst_ipv6); i++) { ipa = be32_to_cpu(filter->dst_ipv6[IPV6_MAX_INDEX - i]); - ipa = cpu_to_le32(ipa); - memcpy(&cld->ipaddr.raw_v6.data[j], &ipa, sizeof(ipa)); + + *(__le32 *)&cld->ipaddr.raw_v6.data[i * 2] = cpu_to_le32(ipa); } } else { ipa = be32_to_cpu(filter->dst_ipv4); + memcpy(&cld->ipaddr.v4.data, &ipa, sizeof(ipa)); } @@ -7593,6 +8348,8 @@ int i40e_add_del_cloud_filter(struct i40e_vsi *vsi, if (filter->flags >= ARRAY_SIZE(flag_table)) return I40E_ERR_CONFIG; + memset(&cld_filter, 0, sizeof(cld_filter)); + /* copy element needed to add cloud filter from filter */ i40e_set_cld_element(filter, &cld_filter); @@ -7656,10 +8413,13 @@ int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi, return -EOPNOTSUPP; /* adding filter using src_port/src_ip is not supported at this stage */ - if (filter->src_port || filter->src_ipv4 || + if (filter->src_port || + (filter->src_ipv4 && filter->n_proto != ETH_P_IPV6) || !ipv6_addr_any(&filter->ip.v6.src_ip6)) return -EOPNOTSUPP; + memset(&cld_filter, 0, sizeof(cld_filter)); + /* copy element needed to add cloud filter from filter */ i40e_set_cld_element(filter, &cld_filter.element); @@ -7683,7 +8443,7 @@ int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi, cpu_to_le16(I40E_AQC_ADD_CLOUD_FILTER_MAC_VLAN_PORT); } - } else if (filter->dst_ipv4 || + } else if ((filter->dst_ipv4 && filter->n_proto != ETH_P_IPV6) || !ipv6_addr_any(&filter->ip.v6.dst_ip6)) { cld_filter.element.flags = cpu_to_le16(I40E_AQC_ADD_CLOUD_FILTER_IP_PORT); @@ -7735,7 +8495,7 @@ int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi, /** * i40e_parse_cls_flower - Parse tc flower filters provided by kernel * @vsi: Pointer to VSI - * @cls_flower: Pointer to struct flow_cls_offload + * @f: Pointer to struct flow_cls_offload * @filter: Pointer to cloud filter structure * **/ @@ -7993,6 +8753,11 @@ static int i40e_configure_clsflower(struct i40e_vsi *vsi, return -EOPNOTSUPP; } + if (!tc) { + dev_err(&pf->pdev->dev, "Unable to add filter because of invalid destination"); + return -EINVAL; + } + if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state) || test_bit(__I40E_RESET_INTR_RECEIVED, pf->state)) return -EBUSY; @@ -8032,9 +8797,8 @@ static int i40e_configure_clsflower(struct i40e_vsi *vsi, err = i40e_add_del_cloud_filter(vsi, filter, true); if (err) { - dev_err(&pf->pdev->dev, - "Failed to add cloud filter, err %s\n", - i40e_stat_str(&pf->hw, err)); + dev_err(&pf->pdev->dev, "Failed to add cloud filter, err %d\n", + err); goto err; } @@ -8116,8 +8880,8 @@ static int i40e_delete_clsflower(struct i40e_vsi *vsi, /** * i40e_setup_tc_cls_flower - flower classifier offloads - * @netdev: net device to configure - * @type_data: offload data + * @np: net device to configure + * @cls_flower: offload data **/ static int i40e_setup_tc_cls_flower(struct i40e_netdev_priv *np, struct flow_cls_offload *cls_flower) @@ -8213,13 +8977,33 @@ int i40e_open(struct net_device *netdev) TCP_FLAG_FIN | TCP_FLAG_CWR) >> 16); wr32(&pf->hw, I40E_GLLAN_TSOMSK_L, be32_to_cpu(TCP_FLAG_CWR) >> 16); - udp_tunnel_get_rx_info(netdev); return 0; } /** + * i40e_netif_set_realnum_tx_rx_queues - Update number of tx/rx queues + * @vsi: vsi structure + * + * This updates netdev's number of tx/rx queues + * + * Returns status of setting tx/rx queues + **/ +static int i40e_netif_set_realnum_tx_rx_queues(struct i40e_vsi *vsi) +{ + int ret; + + ret = netif_set_real_num_rx_queues(vsi->netdev, + vsi->num_queue_pairs); + if (ret) + return ret; + + return netif_set_real_num_tx_queues(vsi->netdev, + vsi->num_queue_pairs); +} + +/** * i40e_vsi_open - * @vsi: the VSI to open * @@ -8255,13 +9039,7 @@ int i40e_vsi_open(struct i40e_vsi *vsi) goto err_setup_rx; /* Notify the stack of the actual queue counts. */ - err = netif_set_real_num_tx_queues(vsi->netdev, - vsi->num_queue_pairs); - if (err) - goto err_set_queues; - - err = netif_set_real_num_rx_queues(vsi->netdev, - vsi->num_queue_pairs); + err = i40e_netif_set_realnum_tx_rx_queues(vsi); if (err) goto err_set_queues; @@ -8270,6 +9048,8 @@ int i40e_vsi_open(struct i40e_vsi *vsi) dev_driver_string(&pf->pdev->dev), dev_name(&pf->pdev->dev)); err = i40e_vsi_request_irq(vsi, int_name); + if (err) + goto err_setup_rx; } else { err = -EINVAL; @@ -8328,32 +9108,51 @@ static void i40e_fdir_filter_exit(struct i40e_pf *pf) INIT_LIST_HEAD(&pf->l4_flex_pit_list); pf->fdir_pf_active_filters = 0; - pf->fd_tcp4_filter_cnt = 0; - pf->fd_udp4_filter_cnt = 0; - pf->fd_sctp4_filter_cnt = 0; - pf->fd_ip4_filter_cnt = 0; + i40e_reset_fdir_filter_cnt(pf); /* Reprogram the default input set for TCP/IPv4 */ i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_TCP, I40E_L3_SRC_MASK | I40E_L3_DST_MASK | I40E_L4_SRC_MASK | I40E_L4_DST_MASK); + /* Reprogram the default input set for TCP/IPv6 */ + i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV6_TCP, + I40E_L3_V6_SRC_MASK | I40E_L3_V6_DST_MASK | + I40E_L4_SRC_MASK | I40E_L4_DST_MASK); + /* Reprogram the default input set for UDP/IPv4 */ i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_UDP, I40E_L3_SRC_MASK | I40E_L3_DST_MASK | I40E_L4_SRC_MASK | I40E_L4_DST_MASK); + /* Reprogram the default input set for UDP/IPv6 */ + i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV6_UDP, + I40E_L3_V6_SRC_MASK | I40E_L3_V6_DST_MASK | + I40E_L4_SRC_MASK | I40E_L4_DST_MASK); + /* Reprogram the default input set for SCTP/IPv4 */ i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_SCTP, I40E_L3_SRC_MASK | I40E_L3_DST_MASK | I40E_L4_SRC_MASK | I40E_L4_DST_MASK); + /* Reprogram the default input set for SCTP/IPv6 */ + i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV6_SCTP, + I40E_L3_V6_SRC_MASK | I40E_L3_V6_DST_MASK | + I40E_L4_SRC_MASK | I40E_L4_DST_MASK); + /* Reprogram the default input set for Other/IPv4 */ i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_OTHER, I40E_L3_SRC_MASK | I40E_L3_DST_MASK); i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_FRAG_IPV4, I40E_L3_SRC_MASK | I40E_L3_DST_MASK); + + /* Reprogram the default input set for Other/IPv6 */ + i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV6_OTHER, + I40E_L3_SRC_MASK | I40E_L3_DST_MASK); + + i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_FRAG_IPV6, + I40E_L3_SRC_MASK | I40E_L3_DST_MASK); } /** @@ -8418,9 +9217,6 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags, bool lock_acquired) { u32 val; - WARN_ON(in_interrupt()); - - /* do the biggest reset indicated */ if (reset_flags & BIT_ULL(__I40E_GLOBAL_RESET_REQUESTED)) { @@ -8462,6 +9258,13 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags, bool lock_acquired) dev_dbg(&pf->pdev->dev, "PFR requested\n"); i40e_handle_reset_warning(pf, lock_acquired); + } else if (reset_flags & I40E_PF_RESET_AND_REBUILD_FLAG) { + /* Request a PF Reset + * + * Resets PF and reinitializes PFs VSI. + */ + i40e_prep_for_reset(pf); + i40e_reset_and_rebuild(pf, true, lock_acquired); dev_info(&pf->pdev->dev, pf->flags & I40E_FLAG_DISABLE_FW_LLDP ? "FW LLDP is disabled\n" : @@ -8574,6 +9377,14 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf, int ret = 0; u8 type; + /* X710-T*L 2.5G and 5G speeds don't support DCB */ + if (I40E_IS_X710TL_DEVICE(hw->device_id) && + (hw->phy.link_info.link_speed & + ~(I40E_LINK_SPEED_2_5GB | I40E_LINK_SPEED_5GB)) && + !(pf->flags & I40E_FLAG_DCB_CAPABLE)) + /* let firmware decide if the DCB should be disabled */ + pf->flags |= I40E_FLAG_DCB_CAPABLE; + /* Not DCB capable or capability disabled */ if (!(pf->flags & I40E_FLAG_DCB_CAPABLE)) return ret; @@ -8605,10 +9416,20 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf, /* Get updated DCBX data from firmware */ ret = i40e_get_dcb_config(&pf->hw); if (ret) { - dev_info(&pf->pdev->dev, - "Failed querying DCB configuration data from firmware, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), - i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); + /* X710-T*L 2.5G and 5G speeds don't support DCB */ + if (I40E_IS_X710TL_DEVICE(hw->device_id) && + (hw->phy.link_info.link_speed & + (I40E_LINK_SPEED_2_5GB | I40E_LINK_SPEED_5GB))) { + dev_warn(&pf->pdev->dev, + "DCB is not supported for X710-T*L 2.5/5G speeds\n"); + pf->flags &= ~I40E_FLAG_DCB_CAPABLE; + } else { + dev_info(&pf->pdev->dev, + "Failed querying DCB configuration data from firmware, err %s aq_err %s\n", + i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, + pf->hw.aq.asq_last_status)); + } goto exit; } @@ -8812,8 +9633,17 @@ static void i40e_delete_invalid_filter(struct i40e_pf *pf, case SCTP_V4_FLOW: pf->fd_sctp4_filter_cnt--; break; + case TCP_V6_FLOW: + pf->fd_tcp6_filter_cnt--; + break; + case UDP_V6_FLOW: + pf->fd_udp6_filter_cnt--; + break; + case SCTP_V6_FLOW: + pf->fd_udp6_filter_cnt--; + break; case IP_USER_FLOW: - switch (filter->ip4_proto) { + switch (filter->ipl4_proto) { case IPPROTO_TCP: pf->fd_tcp4_filter_cnt--; break; @@ -8828,6 +9658,22 @@ static void i40e_delete_invalid_filter(struct i40e_pf *pf, break; } break; + case IPV6_USER_FLOW: + switch (filter->ipl4_proto) { + case IPPROTO_TCP: + pf->fd_tcp6_filter_cnt--; + break; + case IPPROTO_UDP: + pf->fd_udp6_filter_cnt--; + break; + case IPPROTO_SCTP: + pf->fd_sctp6_filter_cnt--; + break; + case IPPROTO_IP: + pf->fd_ip6_filter_cnt--; + break; + } + break; } /* Remove the filter from the list and free memory */ @@ -8861,7 +9707,7 @@ void i40e_fdir_check_and_reenable(struct i40e_pf *pf) * rules active. */ if ((fcnt_prog < (fcnt_avail - I40E_FDIR_BUFFER_HEAD_ROOM_FOR_ATR)) && - (pf->fd_tcp4_filter_cnt == 0)) + pf->fd_tcp4_filter_cnt == 0 && pf->fd_tcp6_filter_cnt == 0) i40e_reenable_fdir_atr(pf); /* if hw had a problem adding a filter, delete it */ @@ -8934,7 +9780,7 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf) } /** - * i40e_get_current_atr_count - Get the count of total FD ATR filters programmed + * i40e_get_current_atr_cnt - Get the count of total FD ATR filters programmed * @pf: board private structure **/ u32 i40e_get_current_atr_cnt(struct i40e_pf *pf) @@ -8942,13 +9788,6 @@ u32 i40e_get_current_atr_cnt(struct i40e_pf *pf) return i40e_get_current_fd_count(pf) - pf->fdir_pf_active_filters; } -/* We can see up to 256 filter programming desc in transit if the filters are - * being applied really fast; before we see the first - * filter miss error on Rx queue 0. Accumulating enough error messages before - * reacting will make sure we don't cause flush too often. - */ -#define I40E_MAX_FD_PROGRAM_ERROR 256 - /** * i40e_fdir_reinit_subtask - Worker thread to reinit FDIR filter table * @pf: board private structure @@ -9037,6 +9876,9 @@ static void i40e_link_event(struct i40e_pf *pf) u8 new_link_speed, old_link_speed; i40e_status status; bool new_link, old_link; +#ifdef CONFIG_I40E_DCB + int err; +#endif /* CONFIG_I40E_DCB */ /* set this to force the get_link_status call to refresh state */ pf->hw.phy.get_link_info = true; @@ -9080,6 +9922,31 @@ static void i40e_link_event(struct i40e_pf *pf) if (pf->flags & I40E_FLAG_PTP) i40e_ptp_set_increment(pf); +#ifdef CONFIG_I40E_DCB + if (new_link == old_link) + return; + /* Not SW DCB so firmware will take care of default settings */ + if (pf->dcbx_cap & DCB_CAP_DCBX_LLD_MANAGED) + return; + + /* We cover here only link down, as after link up in case of SW DCB + * SW LLDP agent will take care of setting it up + */ + if (!new_link) { + dev_dbg(&pf->pdev->dev, "Reconfig DCB to single TC as result of Link Down\n"); + memset(&pf->tmp_cfg, 0, sizeof(pf->tmp_cfg)); + err = i40e_dcb_sw_default_config(pf); + if (err) { + pf->flags &= ~(I40E_FLAG_DCB_CAPABLE | + I40E_FLAG_DCB_ENABLED); + } else { + pf->dcbx_cap = DCB_CAP_DCBX_HOST | + DCB_CAP_DCBX_VER_IEEE; + pf->flags |= I40E_FLAG_DCB_CAPABLE; + pf->flags &= ~I40E_FLAG_DCB_ENABLED; + } + } +#endif /* CONFIG_I40E_DCB */ } /** @@ -9156,7 +10023,7 @@ static void i40e_reset_subtask(struct i40e_pf *pf) * precedence before starting a new reset sequence. */ if (test_bit(__I40E_RESET_INTR_RECEIVED, pf->state)) { - i40e_prep_for_reset(pf, false); + i40e_prep_for_reset(pf); i40e_reset(pf); i40e_rebuild(pf, false, false); } @@ -9288,7 +10155,9 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf) switch (opcode) { case i40e_aqc_opc_get_link_status: + rtnl_lock(); i40e_handle_link_event(pf, &event); + rtnl_unlock(); break; case i40e_aqc_opc_send_msg_to_pf: ret = i40e_vc_process_vf_msg(pf, @@ -9302,7 +10171,7 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf) dev_dbg(&pf->pdev->dev, "ARQ: Update LLDP MIB event received\n"); #ifdef CONFIG_I40E_DCB rtnl_lock(); - ret = i40e_handle_lldp_event(pf, &event); + i40e_handle_lldp_event(pf, &event); rtnl_unlock(); #endif /* CONFIG_I40E_DCB */ break; @@ -9548,6 +10417,7 @@ end_reconstitute: /** * i40e_get_capabilities - get info about the HW * @pf: the PF struct + * @list_type: AQ capability to be queried **/ static int i40e_get_capabilities(struct i40e_pf *pf, enum i40e_admin_queue_opc list_type) @@ -9573,7 +10443,7 @@ static int i40e_get_capabilities(struct i40e_pf *pf, if (pf->hw.aq.asq_last_status == I40E_AQ_RC_ENOMEM) { /* retry with a larger buffer */ buf_len = data_size; - } else if (pf->hw.aq.asq_last_status != I40E_AQ_RC_OK) { + } else if (pf->hw.aq.asq_last_status != I40E_AQ_RC_OK || err) { dev_info(&pf->pdev->dev, "capability discovery failed, err %s aq_err %s\n", i40e_stat_str(&pf->hw, err), @@ -9787,12 +10657,10 @@ static int i40e_rebuild_channels(struct i40e_vsi *vsi) /** * i40e_prep_for_reset - prep for the core to reset * @pf: board private structure - * @lock_acquired: indicates whether or not the lock has been acquired - * before this function was called. * * Close up the VFs and other things in prep for PF Reset. **/ -static void i40e_prep_for_reset(struct i40e_pf *pf, bool lock_acquired) +static void i40e_prep_for_reset(struct i40e_pf *pf) { struct i40e_hw *hw = &pf->hw; i40e_status ret = 0; @@ -9807,12 +10675,7 @@ static void i40e_prep_for_reset(struct i40e_pf *pf, bool lock_acquired) dev_dbg(&pf->pdev->dev, "Tearing down internal switch for reset\n"); /* quiesce the VSIs and their queues that are not already DOWN */ - /* pf_quiesce_all_vsi modifies netdev structures -rtnl_lock needed */ - if (!lock_acquired) - rtnl_lock(); i40e_pf_quiesce_all_vsi(pf); - if (!lock_acquired) - rtnl_unlock(); for (v = 0; v < pf->num_alloc_vsi; v++) { if (pf->vsi[v]) @@ -9843,11 +10706,11 @@ static void i40e_send_version(struct i40e_pf *pf) { struct i40e_driver_version dv; - dv.major_version = DRV_VERSION_MAJOR; - dv.minor_version = DRV_VERSION_MINOR; - dv.build_version = DRV_VERSION_BUILD; + dv.major_version = 0xff; + dv.minor_version = 0xff; + dv.build_version = 0xff; dv.subbuild_version = 0; - strlcpy(dv.driver_string, DRV_VERSION, sizeof(dv.driver_string)); + strscpy(dv.driver_string, UTS_RELEASE, sizeof(dv.driver_string)); i40e_aq_send_driver_version(&pf->hw, &dv, NULL); } @@ -9925,22 +10788,19 @@ static int i40e_reset(struct i40e_pf *pf) **/ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) { - int old_recovery_mode_bit = test_bit(__I40E_RECOVERY_MODE, pf->state); + const bool is_recovery_mode_reported = i40e_check_recovery_mode(pf); struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; struct i40e_hw *hw = &pf->hw; - u8 set_fc_aq_fail = 0; i40e_status ret; u32 val; int v; if (test_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state) && - i40e_check_recovery_mode(pf)) { + is_recovery_mode_reported) i40e_set_ethtool_ops(pf->vsi[pf->lan_vsi]->netdev); - } if (test_bit(__I40E_DOWN, pf->state) && - !test_bit(__I40E_RECOVERY_MODE, pf->state) && - !old_recovery_mode_bit) + !test_bit(__I40E_RECOVERY_MODE, pf->state)) goto clear_recovery; dev_dbg(&pf->pdev->dev, "Rebuilding internal switch\n"); @@ -9954,15 +10814,9 @@ 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); + if (test_and_clear_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state)) { + /* The following delay is necessary for firmware update. */ + mdelay(1000); } /* re-verify the eeprom if we just had an EMP reset */ @@ -9973,13 +10827,12 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) * accordingly with regard to resources initialization * and deinitialization */ - if (test_bit(__I40E_RECOVERY_MODE, pf->state) || - old_recovery_mode_bit) { + if (test_bit(__I40E_RECOVERY_MODE, pf->state)) { if (i40e_get_capabilities(pf, i40e_aqc_opc_list_func_capabilities)) goto end_unlock; - if (test_bit(__I40E_RECOVERY_MODE, pf->state)) { + if (is_recovery_mode_reported) { /* we're staying in recovery mode so we'll reinitialize * misc vector here */ @@ -10024,21 +10877,37 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) goto end_core_reset; } - /* Enable FW to write a default DCB config on link-up */ - i40e_aq_set_dcb_parameters(hw, true, NULL); - #ifdef CONFIG_I40E_DCB - ret = i40e_init_pf_dcb(pf); - if (ret) { - dev_info(&pf->pdev->dev, "DCB init failed %d, disabled\n", ret); - pf->flags &= ~I40E_FLAG_DCB_CAPABLE; - /* Continue without DCB enabled */ + /* Enable FW to write a default DCB config on link-up + * unless I40E_FLAG_TC_MQPRIO was enabled or DCB + * is not supported with new link speed + */ + if (i40e_is_tc_mqprio_enabled(pf)) { + i40e_aq_set_dcb_parameters(hw, false, NULL); + } else { + if (I40E_IS_X710TL_DEVICE(hw->device_id) && + (hw->phy.link_info.link_speed & + (I40E_LINK_SPEED_2_5GB | I40E_LINK_SPEED_5GB))) { + i40e_aq_set_dcb_parameters(hw, false, NULL); + dev_warn(&pf->pdev->dev, + "DCB is not supported for X710-T*L 2.5/5G speeds\n"); + pf->flags &= ~I40E_FLAG_DCB_CAPABLE; + } else { + i40e_aq_set_dcb_parameters(hw, true, NULL); + ret = i40e_init_pf_dcb(pf); + if (ret) { + dev_info(&pf->pdev->dev, "DCB init failed %d, disabled\n", + ret); + pf->flags &= ~I40E_FLAG_DCB_CAPABLE; + /* Continue without DCB enabled */ + } + } } + #endif /* CONFIG_I40E_DCB */ - /* do basic switch setup */ if (!lock_acquired) rtnl_lock(); - ret = i40e_setup_pf_switch(pf, reinit); + ret = i40e_setup_pf_switch(pf, reinit, true); if (ret) goto end_unlock; @@ -10054,19 +10923,12 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) i40e_stat_str(&pf->hw, ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); - /* make sure our flow control settings are restored */ - ret = i40e_set_fc(&pf->hw, &set_fc_aq_fail, true); - if (ret) - dev_dbg(&pf->pdev->dev, "setting flow control: ret = %s last_status = %s\n", - i40e_stat_str(&pf->hw, ret), - i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); - /* Rebuild the VSIs and VEBs that existed before reset. * They are still in our local switch element arrays, so only * need to rebuild the switch model in the HW. * * If there were VEBs but the reconstitution failed, we'll try - * try to recover minimal use by getting the basic PF VSI working. + * to recover minimal use by getting the basic PF VSI working. */ if (vsi->uplink_seid != pf->mac_seid) { dev_dbg(&pf->pdev->dev, "attempting to rebuild switch\n"); @@ -10115,10 +10977,10 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) } if (vsi->mqprio_qopt.max_rate[0]) { - u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0]; + u64 max_tx_rate = i40e_bw_bytes_to_mbits(vsi, + vsi->mqprio_qopt.max_rate[0]); u64 credits = 0; - do_div(max_tx_rate, I40E_BW_MBPS_DIVISOR); ret = i40e_set_bw_limit(vsi, vsi->seid, max_tx_rate); if (ret) goto end_unlock; @@ -10224,6 +11086,9 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) { int ret; + + if (test_bit(__I40E_IN_REMOVE, pf->state)) + return; /* Now we wait for GRST to settle out. * We don't have to delete the VEBs or VSIs from the hw switch * because the reset will make them disappear. @@ -10244,7 +11109,7 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit, **/ static void i40e_handle_reset_warning(struct i40e_pf *pf, bool lock_acquired) { - i40e_prep_for_reset(pf, lock_acquired); + i40e_prep_for_reset(pf); i40e_reset_and_rebuild(pf, false, lock_acquired); } @@ -10346,106 +11211,6 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf) i40e_flush(hw); } -static const char *i40e_tunnel_name(u8 type) -{ - switch (type) { - case UDP_TUNNEL_TYPE_VXLAN: - return "vxlan"; - case UDP_TUNNEL_TYPE_GENEVE: - return "geneve"; - default: - return "unknown"; - } -} - -/** - * i40e_sync_udp_filters - Trigger a sync event for existing UDP filters - * @pf: board private structure - **/ -static void i40e_sync_udp_filters(struct i40e_pf *pf) -{ - int i; - - /* loop through and set pending bit for all active UDP filters */ - for (i = 0; i < I40E_MAX_PF_UDP_OFFLOAD_PORTS; i++) { - if (pf->udp_ports[i].port) - pf->pending_udp_bitmap |= BIT_ULL(i); - } - - set_bit(__I40E_UDP_FILTER_SYNC_PENDING, pf->state); -} - -/** - * i40e_sync_udp_filters_subtask - Sync the VSI filter list with HW - * @pf: board private structure - **/ -static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf) -{ - struct i40e_hw *hw = &pf->hw; - u8 filter_index, type; - u16 port; - int i; - - if (!test_and_clear_bit(__I40E_UDP_FILTER_SYNC_PENDING, pf->state)) - return; - - /* acquire RTNL to maintain state of flags and port requests */ - rtnl_lock(); - - for (i = 0; i < I40E_MAX_PF_UDP_OFFLOAD_PORTS; i++) { - if (pf->pending_udp_bitmap & BIT_ULL(i)) { - struct i40e_udp_port_config *udp_port; - i40e_status ret = 0; - - udp_port = &pf->udp_ports[i]; - pf->pending_udp_bitmap &= ~BIT_ULL(i); - - port = READ_ONCE(udp_port->port); - type = READ_ONCE(udp_port->type); - filter_index = READ_ONCE(udp_port->filter_index); - - /* release RTNL while we wait on AQ command */ - rtnl_unlock(); - - if (port) - ret = i40e_aq_add_udp_tunnel(hw, port, - type, - &filter_index, - NULL); - else if (filter_index != I40E_UDP_PORT_INDEX_UNUSED) - ret = i40e_aq_del_udp_tunnel(hw, filter_index, - NULL); - - /* reacquire RTNL so we can update filter_index */ - rtnl_lock(); - - if (ret) { - dev_info(&pf->pdev->dev, - "%s %s port %d, index %d failed, err %s aq_err %s\n", - i40e_tunnel_name(type), - port ? "add" : "delete", - port, - filter_index, - i40e_stat_str(&pf->hw, ret), - i40e_aq_str(&pf->hw, - pf->hw.aq.asq_last_status)); - if (port) { - /* failed to add, just reset port, - * drop pending bit for any deletion - */ - udp_port->port = 0; - pf->pending_udp_bitmap &= ~BIT_ULL(i); - } - } else if (port) { - /* record filter index on success */ - udp_port->filter_index = filter_index; - } - } - } - - rtnl_unlock(); -} - /** * i40e_service_task - Run the driver's async subtasks * @work: pointer to work_struct containing our data @@ -10485,7 +11250,6 @@ static void i40e_service_task(struct work_struct *work) pf->vsi[pf->lan_vsi]); } i40e_sync_filters_subtask(pf); - i40e_sync_udp_filters_subtask(pf); } else { i40e_reset_subtask(pf); } @@ -10509,7 +11273,7 @@ static void i40e_service_task(struct work_struct *work) /** * i40e_service_timer - timer callback - * @data: pointer to PF struct + * @t: timer list pointer **/ static void i40e_service_timer(struct timer_list *t) { @@ -10579,6 +11343,11 @@ static int i40e_set_num_rings_in_vsi(struct i40e_vsi *vsi) return -ENODATA; } + if (is_kdump_kernel()) { + vsi->num_tx_desc = I40E_MIN_NUM_DESCRIPTORS; + vsi->num_rx_desc = I40E_MIN_NUM_DESCRIPTORS; + } + return 0; } @@ -10816,10 +11585,10 @@ static void i40e_vsi_clear_rings(struct i40e_vsi *vsi) if (vsi->tx_rings && vsi->tx_rings[0]) { for (i = 0; i < vsi->alloc_queue_pairs; i++) { kfree_rcu(vsi->tx_rings[i], rcu); - vsi->tx_rings[i] = NULL; - vsi->rx_rings[i] = NULL; + WRITE_ONCE(vsi->tx_rings[i], NULL); + WRITE_ONCE(vsi->rx_rings[i], NULL); if (vsi->xdp_rings) - vsi->xdp_rings[i] = NULL; + WRITE_ONCE(vsi->xdp_rings[i], NULL); } } } @@ -10853,7 +11622,7 @@ 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; ring->itr_setting = pf->tx_itr_default; - vsi->tx_rings[i] = ring++; + WRITE_ONCE(vsi->tx_rings[i], ring++); if (!i40e_enabled_xdp_vsi(vsi)) goto setup_rx; @@ -10871,7 +11640,7 @@ static int i40e_alloc_rings(struct i40e_vsi *vsi) ring->flags = I40E_TXR_FLAGS_WB_ON_ITR; set_ring_xdp(ring); ring->itr_setting = pf->tx_itr_default; - vsi->xdp_rings[i] = ring++; + WRITE_ONCE(vsi->xdp_rings[i], ring++); setup_rx: ring->queue_index = i; @@ -10884,7 +11653,7 @@ setup_rx: ring->size = 0; ring->dcb_tc = 0; ring->itr_setting = pf->rx_itr_default; - vsi->rx_rings[i] = ring; + WRITE_ONCE(vsi->rx_rings[i], ring); } return 0; @@ -11148,11 +11917,10 @@ static int i40e_init_msix(struct i40e_pf *pf) * i40e_vsi_alloc_q_vector - Allocate memory for a single interrupt vector * @vsi: the VSI being configured * @v_idx: index of the vector in the vsi struct - * @cpu: cpu to be used on affinity_mask * * We allocate one q_vector. If allocation fails we return -ENOMEM. **/ -static int i40e_vsi_alloc_q_vector(struct i40e_vsi *vsi, int v_idx, int cpu) +static int i40e_vsi_alloc_q_vector(struct i40e_vsi *vsi, int v_idx) { struct i40e_q_vector *q_vector; @@ -11166,8 +11934,7 @@ static int i40e_vsi_alloc_q_vector(struct i40e_vsi *vsi, int v_idx, int cpu) cpumask_copy(&q_vector->affinity_mask, cpu_possible_mask); if (vsi->netdev) - netif_napi_add(vsi->netdev, &q_vector->napi, - i40e_napi_poll, NAPI_POLL_WEIGHT); + netif_napi_add(vsi->netdev, &q_vector->napi, i40e_napi_poll); /* tie q_vector and vsi together */ vsi->q_vectors[v_idx] = q_vector; @@ -11185,7 +11952,7 @@ static int i40e_vsi_alloc_q_vector(struct i40e_vsi *vsi, int v_idx, int cpu) static int i40e_vsi_alloc_q_vectors(struct i40e_vsi *vsi) { struct i40e_pf *pf = vsi->back; - int err, v_idx, num_q_vectors, current_cpu; + int err, v_idx, num_q_vectors; /* if not MSIX, give the one vector only to the LAN VSI */ if (pf->flags & I40E_FLAG_MSIX_ENABLED) @@ -11195,15 +11962,10 @@ static int i40e_vsi_alloc_q_vectors(struct i40e_vsi *vsi) else return -EINVAL; - current_cpu = cpumask_first(cpu_online_mask); - for (v_idx = 0; v_idx < num_q_vectors; v_idx++) { - err = i40e_vsi_alloc_q_vector(vsi, v_idx, current_cpu); + err = i40e_vsi_alloc_q_vector(vsi, v_idx); if (err) goto err_out; - current_cpu = cpumask_next(current_cpu, cpu_online_mask); - if (unlikely(current_cpu >= nr_cpu_ids)) - current_cpu = cpumask_first(cpu_online_mask); } return 0; @@ -11265,7 +12027,6 @@ static int i40e_init_interrupt_scheme(struct i40e_pf *pf) return -ENOMEM; pf->irq_pile->num_entries = vectors; - pf->irq_pile->search_hint = 0; /* track first vector for misc interrupts, ignore return */ (void)i40e_get_lump(pf, pf->irq_pile, 1, I40E_PILE_VALID_BIT - 1); @@ -11436,7 +12197,7 @@ static int i40e_get_rss_aq(struct i40e_vsi *vsi, const u8 *seed, } if (lut) { - bool pf_lut = vsi->type == I40E_VSI_MAIN ? true : false; + bool pf_lut = vsi->type == I40E_VSI_MAIN; ret = i40e_aq_get_rss_lut(hw, vsi->id, pf_lut, lut, lut_size); if (ret) { @@ -11685,7 +12446,9 @@ int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count) u16 qcount; vsi->req_queue_pairs = queue_count; - i40e_prep_for_reset(pf, true); + i40e_prep_for_reset(pf); + if (test_bit(__I40E_IN_REMOVE, pf->state)) + return pf->alloc_rss_size; pf->alloc_rss_size = new_rss_size; @@ -11743,6 +12506,8 @@ i40e_status i40e_set_partition_bw_setting(struct i40e_pf *pf) struct i40e_aqc_configure_partition_bw_data bw_data; i40e_status status; + memset(&bw_data, 0, sizeof(bw_data)); + /* Set the valid bit for this PF */ bw_data.pf_valid_bits = cpu_to_le16(BIT(pf->hw.pf_id)); bw_data.max_bw[pf->hw.pf_id] = pf->max_bw & I40E_ALT_BW_VALUE_MASK; @@ -11838,6 +12603,58 @@ bw_commit_out: } /** + * i40e_is_total_port_shutdown_enabled - read NVM and return value + * if total port shutdown feature is enabled for this PF + * @pf: board private structure + **/ +static bool i40e_is_total_port_shutdown_enabled(struct i40e_pf *pf) +{ +#define I40E_TOTAL_PORT_SHUTDOWN_ENABLED BIT(4) +#define I40E_FEATURES_ENABLE_PTR 0x2A +#define I40E_CURRENT_SETTING_PTR 0x2B +#define I40E_LINK_BEHAVIOR_WORD_OFFSET 0x2D +#define I40E_LINK_BEHAVIOR_WORD_LENGTH 0x1 +#define I40E_LINK_BEHAVIOR_OS_FORCED_ENABLED BIT(0) +#define I40E_LINK_BEHAVIOR_PORT_BIT_LENGTH 4 + i40e_status read_status = I40E_SUCCESS; + u16 sr_emp_sr_settings_ptr = 0; + u16 features_enable = 0; + u16 link_behavior = 0; + bool ret = false; + + read_status = i40e_read_nvm_word(&pf->hw, + I40E_SR_EMP_SR_SETTINGS_PTR, + &sr_emp_sr_settings_ptr); + if (read_status) + goto err_nvm; + read_status = i40e_read_nvm_word(&pf->hw, + sr_emp_sr_settings_ptr + + I40E_FEATURES_ENABLE_PTR, + &features_enable); + if (read_status) + goto err_nvm; + if (I40E_TOTAL_PORT_SHUTDOWN_ENABLED & features_enable) { + read_status = i40e_read_nvm_module_data(&pf->hw, + I40E_SR_EMP_SR_SETTINGS_PTR, + I40E_CURRENT_SETTING_PTR, + I40E_LINK_BEHAVIOR_WORD_OFFSET, + I40E_LINK_BEHAVIOR_WORD_LENGTH, + &link_behavior); + if (read_status) + goto err_nvm; + link_behavior >>= (pf->hw.port * I40E_LINK_BEHAVIOR_PORT_BIT_LENGTH); + ret = I40E_LINK_BEHAVIOR_OS_FORCED_ENABLED & link_behavior; + } + return ret; + +err_nvm: + dev_warn(&pf->pdev->dev, + "total-port-shutdown feature is off due to read nvm error: %s\n", + i40e_stat_str(&pf->hw, read_status)); + return ret; +} + +/** * i40e_sw_init - Initialize general software structures (struct i40e_pf) * @pf: board private structure to initialize * @@ -11849,6 +12666,7 @@ static int i40e_sw_init(struct i40e_pf *pf) { int err = 0; int size; + u16 pow; /* Set default capability flags */ pf->flags = I40E_FLAG_RX_CSUM_ENABLED | @@ -11867,6 +12685,11 @@ static int i40e_sw_init(struct i40e_pf *pf) pf->rss_table_size = pf->hw.func_caps.rss_table_size; pf->rss_size_max = min_t(int, pf->rss_size_max, pf->hw.func_caps.num_tx_qp); + + /* find the next higher power-of-2 of num cpus */ + pow = roundup_pow_of_two(num_online_cpus()); + pf->rss_size_max = min_t(int, pf->rss_size_max, pow); + if (pf->hw.func_caps.rss) { pf->flags |= I40E_FLAG_RSS_ENABLED; pf->alloc_rss_size = min_t(int, pf->rss_size_max, @@ -12008,10 +12831,19 @@ static int i40e_sw_init(struct i40e_pf *pf) goto sw_init_done; } pf->qp_pile->num_entries = pf->hw.func_caps.num_tx_qp; - pf->qp_pile->search_hint = 0; pf->tx_timeout_recovery_level = 1; + if (pf->hw.mac.type != I40E_MAC_X722 && + i40e_is_total_port_shutdown_enabled(pf)) { + /* Link down on close must be on when total port shutdown + * is enabled for a given port + */ + pf->flags |= (I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENABLED | + I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED); + dev_info(&pf->pdev->dev, + "total-port-shutdown was enabled, link-down-on-close is forced on\n"); + } mutex_init(&pf->switch_mutex); sw_init_done: @@ -12112,7 +12944,8 @@ static int i40e_set_features(struct net_device *netdev, else i40e_vlan_stripping_disable(vsi); - if (!(features & NETIF_F_HW_TC) && pf->num_cloud_filters) { + if (!(features & NETIF_F_HW_TC) && + (netdev->features & NETIF_F_HW_TC) && pf->num_cloud_filters) { dev_err(&pf->pdev->dev, "Offloaded tc filters active, can't turn hw_tc_offload off"); return -EINVAL; @@ -12129,131 +12962,48 @@ static int i40e_set_features(struct net_device *netdev, return 0; } -/** - * i40e_get_udp_port_idx - Lookup a possibly offloaded for Rx UDP port - * @pf: board private structure - * @port: The UDP port to look up - * - * Returns the index number or I40E_MAX_PF_UDP_OFFLOAD_PORTS if port not found - **/ -static u8 i40e_get_udp_port_idx(struct i40e_pf *pf, u16 port) -{ - u8 i; - - for (i = 0; i < I40E_MAX_PF_UDP_OFFLOAD_PORTS; i++) { - /* Do not report ports with pending deletions as - * being available. - */ - if (!port && (pf->pending_udp_bitmap & BIT_ULL(i))) - continue; - if (pf->udp_ports[i].port == port) - return i; - } - - return i; -} - -/** - * i40e_udp_tunnel_add - Get notifications about UDP tunnel ports that come up - * @netdev: This physical port's netdev - * @ti: Tunnel endpoint information - **/ -static void i40e_udp_tunnel_add(struct net_device *netdev, - struct udp_tunnel_info *ti) +static int i40e_udp_tunnel_set_port(struct net_device *netdev, + unsigned int table, unsigned int idx, + struct udp_tunnel_info *ti) { struct i40e_netdev_priv *np = netdev_priv(netdev); - struct i40e_vsi *vsi = np->vsi; - struct i40e_pf *pf = vsi->back; - u16 port = ntohs(ti->port); - u8 next_idx; - u8 idx; - - idx = i40e_get_udp_port_idx(pf, port); - - /* Check if port already exists */ - if (idx < I40E_MAX_PF_UDP_OFFLOAD_PORTS) { - netdev_info(netdev, "port %d already offloaded\n", port); - return; - } - - /* Now check if there is space to add the new port */ - next_idx = i40e_get_udp_port_idx(pf, 0); + struct i40e_hw *hw = &np->vsi->back->hw; + u8 type, filter_index; + i40e_status ret; - if (next_idx == I40E_MAX_PF_UDP_OFFLOAD_PORTS) { - netdev_info(netdev, "maximum number of offloaded UDP ports reached, not adding port %d\n", - port); - return; - } + type = ti->type == UDP_TUNNEL_TYPE_VXLAN ? I40E_AQC_TUNNEL_TYPE_VXLAN : + I40E_AQC_TUNNEL_TYPE_NGE; - switch (ti->type) { - case UDP_TUNNEL_TYPE_VXLAN: - pf->udp_ports[next_idx].type = I40E_AQC_TUNNEL_TYPE_VXLAN; - break; - case UDP_TUNNEL_TYPE_GENEVE: - if (!(pf->hw_features & I40E_HW_GENEVE_OFFLOAD_CAPABLE)) - return; - pf->udp_ports[next_idx].type = I40E_AQC_TUNNEL_TYPE_NGE; - break; - default: - return; + ret = i40e_aq_add_udp_tunnel(hw, ntohs(ti->port), type, &filter_index, + NULL); + if (ret) { + netdev_info(netdev, "add UDP port failed, err %s aq_err %s\n", + i40e_stat_str(hw, ret), + i40e_aq_str(hw, hw->aq.asq_last_status)); + return -EIO; } - /* New port: add it and mark its index in the bitmap */ - pf->udp_ports[next_idx].port = port; - pf->udp_ports[next_idx].filter_index = I40E_UDP_PORT_INDEX_UNUSED; - pf->pending_udp_bitmap |= BIT_ULL(next_idx); - set_bit(__I40E_UDP_FILTER_SYNC_PENDING, pf->state); + udp_tunnel_nic_set_port_priv(netdev, table, idx, filter_index); + return 0; } -/** - * i40e_udp_tunnel_del - Get notifications about UDP tunnel ports that go away - * @netdev: This physical port's netdev - * @ti: Tunnel endpoint information - **/ -static void i40e_udp_tunnel_del(struct net_device *netdev, - struct udp_tunnel_info *ti) +static int i40e_udp_tunnel_unset_port(struct net_device *netdev, + unsigned int table, unsigned int idx, + struct udp_tunnel_info *ti) { struct i40e_netdev_priv *np = netdev_priv(netdev); - struct i40e_vsi *vsi = np->vsi; - struct i40e_pf *pf = vsi->back; - u16 port = ntohs(ti->port); - u8 idx; - - idx = i40e_get_udp_port_idx(pf, port); - - /* Check if port already exists */ - if (idx >= I40E_MAX_PF_UDP_OFFLOAD_PORTS) - goto not_found; + struct i40e_hw *hw = &np->vsi->back->hw; + i40e_status ret; - switch (ti->type) { - case UDP_TUNNEL_TYPE_VXLAN: - if (pf->udp_ports[idx].type != I40E_AQC_TUNNEL_TYPE_VXLAN) - goto not_found; - break; - case UDP_TUNNEL_TYPE_GENEVE: - if (pf->udp_ports[idx].type != I40E_AQC_TUNNEL_TYPE_NGE) - goto not_found; - break; - default: - goto not_found; + ret = i40e_aq_del_udp_tunnel(hw, ti->hw_priv, NULL); + if (ret) { + netdev_info(netdev, "delete UDP port failed, err %s aq_err %s\n", + i40e_stat_str(hw, ret), + i40e_aq_str(hw, hw->aq.asq_last_status)); + return -EIO; } - /* if port exists, set it to 0 (mark for deletion) - * and make it pending - */ - pf->udp_ports[idx].port = 0; - - /* Toggle pending bit instead of setting it. This way if we are - * deleting a port that has yet to be added we just clear the pending - * bit and don't have to worry about it. - */ - pf->pending_udp_bitmap ^= BIT_ULL(idx); - set_bit(__I40E_UDP_FILTER_SYNC_PENDING, pf->state); - - return; -not_found: - netdev_warn(netdev, "UDP port %d was not found, not deleting\n", - port); + return 0; } static int i40e_get_phys_port_id(struct net_device *netdev, @@ -12280,6 +13030,7 @@ static int i40e_get_phys_port_id(struct net_device *netdev, * @addr: the MAC address entry being added * @vid: VLAN ID * @flags: instructions from stack about fdb operation + * @extack: netlink extended ack, unused currently */ static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, @@ -12489,7 +13240,7 @@ static netdev_features_t i40e_features_check(struct sk_buff *skb, } /* No need to validate L4LEN as TCP is the only protocol with a - * a flexible value and we support all possible values supported + * flexible value and we support all possible values supported * by TCP, which is at most 15 dwords */ @@ -12502,9 +13253,10 @@ out_err: * i40e_xdp_setup - add/remove an XDP program * @vsi: VSI to changed * @prog: XDP program + * @extack: netlink extended ack **/ -static int i40e_xdp_setup(struct i40e_vsi *vsi, - struct bpf_prog *prog) +static int i40e_xdp_setup(struct i40e_vsi *vsi, struct bpf_prog *prog, + struct netlink_ext_ack *extack) { int frame_size = vsi->netdev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; struct i40e_pf *pf = vsi->back; @@ -12513,17 +13265,20 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, int i; /* Don't allow frames that span over multiple buffers */ - if (frame_size > vsi->rx_buf_len) + if (frame_size > vsi->rx_buf_len) { + NL_SET_ERR_MSG_MOD(extack, "MTU too large to enable XDP"); return -EINVAL; - - if (!i40e_enabled_xdp_vsi(vsi) && !prog) - return 0; + } /* When turning XDP on->off/off->on we reset and rebuild the rings. */ need_reset = (i40e_enabled_xdp_vsi(vsi) != !!prog); if (need_reset) - i40e_prep_for_reset(pf, true); + i40e_prep_for_reset(pf); + + /* VSI shall be deleted in a moment, just return EINVAL */ + if (test_bit(__I40E_IN_REMOVE, pf->state)) + return -EINVAL; old_prog = xchg(&vsi->xdp_prog, prog); @@ -12534,6 +13289,14 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, i40e_reset_and_rebuild(pf, true, true); } + if (!i40e_enabled_xdp_vsi(vsi) && prog) { + if (i40e_realloc_rx_bi_zc(vsi, true)) + return -ENOMEM; + } else if (i40e_enabled_xdp_vsi(vsi) && !prog) { + if (i40e_realloc_rx_bi_zc(vsi, false)) + return -ENOMEM; + } + for (i = 0; i < vsi->num_queue_pairs; i++) WRITE_ONCE(vsi->rx_rings[i]->xdp_prog, vsi->xdp_prog); @@ -12545,7 +13308,7 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, */ if (need_reset && prog) for (i = 0; i < vsi->num_queue_pairs; i++) - if (vsi->xdp_rings[i]->xsk_umem) + if (vsi->xdp_rings[i]->xsk_pool) (void)i40e_xsk_wakeup(vsi->netdev, i, XDP_WAKEUP_RX); @@ -12766,6 +13529,7 @@ int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair) i40e_queue_pair_disable_irq(vsi, queue_pair); err = i40e_queue_pair_toggle_rings(vsi, queue_pair, false /* off */); + i40e_clean_rx_ring(vsi->rx_rings[queue_pair]); i40e_queue_pair_toggle_napi(vsi, queue_pair, false /* off */); i40e_queue_pair_clean_rings(vsi, queue_pair); i40e_queue_pair_reset_stats(vsi, queue_pair); @@ -12823,12 +13587,9 @@ static int i40e_xdp(struct net_device *dev, switch (xdp->command) { case XDP_SETUP_PROG: - return i40e_xdp_setup(vsi, xdp->prog); - case XDP_QUERY_PROG: - xdp->prog_id = vsi->xdp_prog ? vsi->xdp_prog->aux->id : 0; - return 0; - case XDP_SETUP_XSK_UMEM: - return i40e_xsk_umem_setup(vsi, xdp->xsk.umem, + return i40e_xdp_setup(vsi, xdp->prog, xdp->extack); + case XDP_SETUP_XSK_POOL: + return i40e_xsk_pool_setup(vsi, xdp->xsk.pool, xdp->xsk.queue_id); default: return -EINVAL; @@ -12844,7 +13605,7 @@ static const struct net_device_ops i40e_netdev_ops = { .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = i40e_set_mac, .ndo_change_mtu = i40e_change_mtu, - .ndo_do_ioctl = i40e_ioctl, + .ndo_eth_ioctl = i40e_ioctl, .ndo_tx_timeout = i40e_tx_timeout, .ndo_vlan_rx_add_vid = i40e_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = i40e_vlan_rx_kill_vid, @@ -12852,6 +13613,7 @@ static const struct net_device_ops i40e_netdev_ops = { .ndo_poll_controller = i40e_netpoll, #endif .ndo_setup_tc = __i40e_setup_tc, + .ndo_select_queue = i40e_lan_select_queue, .ndo_set_features = i40e_set_features, .ndo_set_vf_mac = i40e_ndo_set_vf_mac, .ndo_set_vf_vlan = i40e_ndo_set_vf_port_vlan, @@ -12861,8 +13623,6 @@ static const struct net_device_ops i40e_netdev_ops = { .ndo_set_vf_link_state = i40e_ndo_set_vf_link_state, .ndo_set_vf_spoofchk = i40e_ndo_set_vf_spoofchk, .ndo_set_vf_trust = i40e_ndo_set_vf_trust, - .ndo_udp_tunnel_add = i40e_udp_tunnel_add, - .ndo_udp_tunnel_del = i40e_udp_tunnel_del, .ndo_get_phys_port_id = i40e_get_phys_port_id, .ndo_fdb_add = i40e_ndo_fdb_add, .ndo_features_check = i40e_features_check, @@ -12903,8 +13663,7 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) np->vsi = vsi; hw_enc_features = NETIF_F_SG | - NETIF_F_IP_CSUM | - NETIF_F_IPV6_CSUM | + NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_SOFT_FEATURES | NETIF_F_TSO | @@ -12926,6 +13685,8 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) if (!(pf->hw_features & I40E_HW_OUTER_UDP_CSUM_CAPABLE)) netdev->gso_partial_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM; + netdev->udp_tunnel_nic_info = &pf->udp_tunnel_nic; + netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM; netdev->hw_enc_features |= hw_enc_features; @@ -12933,6 +13694,23 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) /* record features VLANs can make use of */ netdev->vlan_features |= hw_enc_features | NETIF_F_TSO_MANGLEID; +#define I40E_GSO_PARTIAL_FEATURES (NETIF_F_GSO_GRE | \ + NETIF_F_GSO_GRE_CSUM | \ + NETIF_F_GSO_IPXIP4 | \ + NETIF_F_GSO_IPXIP6 | \ + NETIF_F_GSO_UDP_TUNNEL | \ + NETIF_F_GSO_UDP_TUNNEL_CSUM) + + netdev->gso_partial_features = I40E_GSO_PARTIAL_FEATURES; + netdev->features |= NETIF_F_GSO_PARTIAL | + I40E_GSO_PARTIAL_FEATURES; + + netdev->mpls_features |= NETIF_F_SG; + netdev->mpls_features |= NETIF_F_HW_CSUM; + netdev->mpls_features |= NETIF_F_TSO; + netdev->mpls_features |= NETIF_F_TSO6; + netdev->mpls_features |= I40E_GSO_PARTIAL_FEATURES; + /* enable macvlan offloads */ netdev->hw_features |= NETIF_F_HW_L2FW_DOFFLOAD; @@ -12948,6 +13726,8 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) netdev->features |= hw_features | NETIF_F_HW_VLAN_CTAG_FILTER; netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID; + netdev->features &= ~NETIF_F_HW_TC; + if (vsi->type == I40E_VSI_MAIN) { SET_NETDEV_DEV(netdev, &pf->pdev->dev); ether_addr_copy(mac_addr, hw->mac.perm_addr); @@ -12999,7 +13779,7 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) i40e_add_mac_filter(vsi, broadcast); spin_unlock_bh(&vsi->mac_filter_hash_lock); - ether_addr_copy(netdev->dev_addr, mac_addr); + eth_hw_addr_set(netdev, mac_addr); ether_addr_copy(netdev->perm_addr, mac_addr); /* i40iw_net_event() reads 16 bytes from neigh->primary_key */ @@ -13345,7 +14125,7 @@ int i40e_vsi_release(struct i40e_vsi *vsi) dev_info(&pf->pdev->dev, "Can't remove PF VSI\n"); return -ENODEV; } - + set_bit(__I40E_VSI_RELEASING, vsi->state); uplink_seid = vsi->uplink_seid; if (vsi->type != I40E_VSI_SRIOV) { if (vsi->netdev_registered) { @@ -13677,6 +14457,9 @@ struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type, ret = i40e_config_netdev(vsi); if (ret) goto err_netdev; + ret = i40e_netif_set_realnum_tx_rx_queues(vsi); + if (ret) + goto err_netdev; ret = register_netdev(vsi->netdev); if (ret) goto err_netdev; @@ -13686,8 +14469,7 @@ struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type, /* Setup DCB netlink interface */ i40e_dcbnl_setup(vsi); #endif /* CONFIG_I40E_DCB */ - /* fall through */ - + fallthrough; case I40E_VSI_FDIR: /* set up vectors and rings if needed */ ret = i40e_vsi_setup_vectors(vsi); @@ -13703,7 +14485,6 @@ struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type, i40e_vsi_reset_stats(vsi); break; - default: /* no netdev or rings for the other VSI types */ break; @@ -14222,10 +15003,11 @@ int i40e_fetch_switch_configuration(struct i40e_pf *pf, bool printconfig) * i40e_setup_pf_switch - Setup the HW switch on startup or after reset * @pf: board private structure * @reinit: if the Main VSI needs to re-initialized. + * @lock_acquired: indicates whether or not the lock has been acquired * * Returns 0 on success, negative value on failure **/ -static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit) +static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit, bool lock_acquired) { u16 flags = 0; int ret; @@ -14327,8 +15109,14 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit) i40e_ptp_init(pf); + if (!lock_acquired) + rtnl_lock(); + /* repopulate tunnel port filters */ - i40e_sync_udp_filters(pf); + udp_tunnel_nic_reset_ntf(pf->vsi[pf->lan_vsi]->netdev); + + if (!lock_acquired) + rtnl_unlock(); return ret; } @@ -14478,29 +15266,29 @@ static void i40e_print_features(struct i40e_pf *pf) i = snprintf(buf, INFO_STRING_LEN, "Features: PF-id[%d]", hw->pf_id); #ifdef CONFIG_PCI_IOV - i += snprintf(&buf[i], REMAIN(i), " VFs: %d", pf->num_req_vfs); + i += scnprintf(&buf[i], REMAIN(i), " VFs: %d", pf->num_req_vfs); #endif - i += snprintf(&buf[i], REMAIN(i), " VSIs: %d QP: %d", + i += scnprintf(&buf[i], REMAIN(i), " VSIs: %d QP: %d", pf->hw.func_caps.num_vsis, pf->vsi[pf->lan_vsi]->num_queue_pairs); if (pf->flags & I40E_FLAG_RSS_ENABLED) - i += snprintf(&buf[i], REMAIN(i), " RSS"); + i += scnprintf(&buf[i], REMAIN(i), " RSS"); if (pf->flags & I40E_FLAG_FD_ATR_ENABLED) - i += snprintf(&buf[i], REMAIN(i), " FD_ATR"); + i += scnprintf(&buf[i], REMAIN(i), " FD_ATR"); if (pf->flags & I40E_FLAG_FD_SB_ENABLED) { - i += snprintf(&buf[i], REMAIN(i), " FD_SB"); - i += snprintf(&buf[i], REMAIN(i), " NTUPLE"); + i += scnprintf(&buf[i], REMAIN(i), " FD_SB"); + i += scnprintf(&buf[i], REMAIN(i), " NTUPLE"); } if (pf->flags & I40E_FLAG_DCB_CAPABLE) - i += snprintf(&buf[i], REMAIN(i), " DCB"); - i += snprintf(&buf[i], REMAIN(i), " VxLAN"); - i += snprintf(&buf[i], REMAIN(i), " Geneve"); + i += scnprintf(&buf[i], REMAIN(i), " DCB"); + i += scnprintf(&buf[i], REMAIN(i), " VxLAN"); + i += scnprintf(&buf[i], REMAIN(i), " Geneve"); if (pf->flags & I40E_FLAG_PTP) - i += snprintf(&buf[i], REMAIN(i), " PTP"); + i += scnprintf(&buf[i], REMAIN(i), " PTP"); if (pf->flags & I40E_FLAG_VEB_MODE_ENABLED) - i += snprintf(&buf[i], REMAIN(i), " VEB"); + i += scnprintf(&buf[i], REMAIN(i), " VEB"); else - i += snprintf(&buf[i], REMAIN(i), " VEPA"); + i += scnprintf(&buf[i], REMAIN(i), " VEPA"); dev_info(&pf->pdev->dev, "%s\n", buf); kfree(buf); @@ -14557,28 +15345,17 @@ void i40e_set_fec_in_flags(u8 fec_cfg, u32 *flags) **/ static bool i40e_check_recovery_mode(struct i40e_pf *pf) { - u32 val = rd32(&pf->hw, I40E_GL_FWSTS) & I40E_GL_FWSTS_FWS1B_MASK; - bool is_recovery_mode = false; - - if (pf->hw.mac.type == I40E_MAC_XL710) - is_recovery_mode = - val == I40E_XL710_GL_FWSTS_FWS1B_REC_MOD_CORER_MASK || - val == I40E_XL710_GL_FWSTS_FWS1B_REC_MOD_GLOBR_MASK || - val == I40E_XL710_GL_FWSTS_FWS1B_REC_MOD_TRANSITION_MASK || - val == I40E_XL710_GL_FWSTS_FWS1B_REC_MOD_NVM_MASK; - if (pf->hw.mac.type == I40E_MAC_X722) - is_recovery_mode = - val == I40E_X722_GL_FWSTS_FWS1B_REC_MOD_CORER_MASK || - val == I40E_X722_GL_FWSTS_FWS1B_REC_MOD_GLOBR_MASK; - if (is_recovery_mode) { - dev_notice(&pf->pdev->dev, "Firmware recovery mode detected. Limiting functionality.\n"); - dev_notice(&pf->pdev->dev, "Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode.\n"); + u32 val = rd32(&pf->hw, I40E_GL_FWSTS); + + if (val & I40E_GL_FWSTS_FWS1B_MASK) { + dev_crit(&pf->pdev->dev, "Firmware recovery mode detected. Limiting functionality.\n"); + dev_crit(&pf->pdev->dev, "Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode.\n"); set_bit(__I40E_RECOVERY_MODE, pf->state); return true; } - if (test_and_clear_bit(__I40E_RECOVERY_MODE, pf->state)) - dev_info(&pf->pdev->dev, "Reinitializing in normal mode with full functionality.\n"); + if (test_bit(__I40E_RECOVERY_MODE, pf->state)) + dev_info(&pf->pdev->dev, "Please do Power-On Reset to initialize adapter in normal mode with full functionality.\n"); return false; } @@ -14606,29 +15383,68 @@ static bool i40e_check_recovery_mode(struct i40e_pf *pf) **/ static i40e_status i40e_pf_loop_reset(struct i40e_pf *pf) { - const unsigned short MAX_CNT = 1000; - const unsigned short MSECS = 10; + /* wait max 10 seconds for PF reset to succeed */ + const unsigned long time_end = jiffies + 10 * HZ; + struct i40e_hw *hw = &pf->hw; i40e_status ret; - int cnt; - for (cnt = 0; cnt < MAX_CNT; ++cnt) { + ret = i40e_pf_reset(hw); + while (ret != I40E_SUCCESS && time_before(jiffies, time_end)) { + usleep_range(10000, 20000); ret = i40e_pf_reset(hw); - if (!ret) - break; - msleep(MSECS); } - if (cnt == MAX_CNT) { + if (ret == I40E_SUCCESS) + pf->pfr_count++; + else dev_info(&pf->pdev->dev, "PF reset failed: %d\n", ret); - return ret; - } - pf->pfr_count++; return ret; } /** + * i40e_check_fw_empr - check if FW issued unexpected EMP Reset + * @pf: board private structure + * + * Check FW registers to determine if FW issued unexpected EMP Reset. + * Every time when unexpected EMP Reset occurs the FW increments + * a counter of unexpected EMP Resets. When the counter reaches 10 + * the FW should enter the Recovery mode + * + * Returns true if FW issued unexpected EMP Reset + **/ +static bool i40e_check_fw_empr(struct i40e_pf *pf) +{ + const u32 fw_sts = rd32(&pf->hw, I40E_GL_FWSTS) & + I40E_GL_FWSTS_FWS1B_MASK; + return (fw_sts > I40E_GL_FWSTS_FWS1B_EMPR_0) && + (fw_sts <= I40E_GL_FWSTS_FWS1B_EMPR_10); +} + +/** + * i40e_handle_resets - handle EMP resets and PF resets + * @pf: board private structure + * + * Handle both EMP resets and PF resets and conclude whether there are + * any issues regarding these resets. If there are any issues then + * generate log entry. + * + * Return 0 if NIC is healthy or negative value when there are issues + * with resets + **/ +static i40e_status i40e_handle_resets(struct i40e_pf *pf) +{ + const i40e_status pfr = i40e_pf_loop_reset(pf); + const bool is_empr = i40e_check_fw_empr(pf); + + if (is_empr || pfr != I40E_SUCCESS) + dev_crit(&pf->pdev->dev, "Entering recovery mode due to repeated FW resets. This may take several minutes. Refer to the Intel(R) Ethernet Adapters and Devices User Guide.\n"); + + return is_empr ? I40E_ERR_RESET_FAILED : pfr; +} + +/** * i40e_init_recovery_mode - initialize subsystems needed in recovery mode * @pf: board private structure * @hw: ptr to the hardware info @@ -14679,12 +15495,16 @@ static int i40e_init_recovery_mode(struct i40e_pf *pf, struct i40e_hw *hw) * in order to register the netdev */ v_idx = i40e_vsi_mem_alloc(pf, I40E_VSI_MAIN); - if (v_idx < 0) + if (v_idx < 0) { + err = v_idx; goto err_switch_setup; + } pf->lan_vsi = v_idx; vsi = pf->vsi[v_idx]; - if (!vsi) + if (!vsi) { + err = -EFAULT; goto err_switch_setup; + } vsi->alloc_queue_pairs = 1; err = i40e_config_netdev(vsi); if (err) @@ -14722,6 +15542,22 @@ err_switch_setup: } /** + * i40e_set_subsystem_device_id - set subsystem device id + * @hw: pointer to the hardware info + * + * Set PCI subsystem device id either from a pci_dev structure or + * a specific FW register. + **/ +static inline void i40e_set_subsystem_device_id(struct i40e_hw *hw) +{ + struct pci_dev *pdev = ((struct i40e_pf *)hw->back)->pdev; + + hw->subsystem_device_id = pdev->subsystem_device ? + pdev->subsystem_device : + (ushort)(rd32(hw, I40E_PFPCI_SUBSYSID) & USHRT_MAX); +} + +/** * i40e_probe - Device initialization routine * @pdev: PCI device information struct * @ent: entry in i40e_pci_tbl @@ -14735,6 +15571,10 @@ err_switch_setup: static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { struct i40e_aq_get_phy_abilities_resp abilities; +#ifdef CONFIG_I40E_DCB + enum i40e_get_fw_lldp_status_resp lldp_status; + i40e_status status; +#endif /* CONFIG_I40E_DCB */ struct i40e_pf *pf; struct i40e_hw *hw; static u16 pfs_found; @@ -14743,7 +15583,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) int err; u32 val; u32 i; - u8 set_fc_aq_fail; err = pci_enable_device_mem(pdev); if (err) @@ -14752,12 +15591,9 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* set up for high or low dma */ err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (err) { - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "DMA configuration failed: 0x%x\n", err); - goto err_dma; - } + dev_err(&pdev->dev, + "DMA configuration failed: 0x%x\n", err); + goto err_dma; } /* set up pci connections */ @@ -14813,7 +15649,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw->device_id = pdev->device; pci_read_config_byte(pdev, PCI_REVISION_ID, &hw->revision_id); hw->subsystem_vendor_id = pdev->subsystem_vendor; - hw->subsystem_device_id = pdev->subsystem_device; + i40e_set_subsystem_device_id(hw); hw->bus.device = PCI_SLOT(pdev->devfn); hw->bus.func = PCI_FUNC(pdev->devfn); hw->bus.bus_id = pdev->bus->number; @@ -14864,16 +15700,19 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_pf_reset; } - err = i40e_pf_loop_reset(pf); - if (err) { - dev_info(&pdev->dev, "Initial pf_reset failed: %d\n", err); + err = i40e_handle_resets(pf); + if (err) goto err_pf_reset; - } i40e_check_recovery_mode(pf); - hw->aq.num_arq_entries = I40E_AQ_LEN; - hw->aq.num_asq_entries = I40E_AQ_LEN; + if (is_kdump_kernel()) { + hw->aq.num_arq_entries = I40E_MIN_ARQ_LEN; + hw->aq.num_asq_entries = I40E_MIN_ASQ_LEN; + } else { + hw->aq.num_arq_entries = I40E_AQ_LEN; + hw->aq.num_asq_entries = I40E_AQ_LEN; + } hw->aq.arq_buf_size = I40E_MAX_AQ_BUF_SIZE; hw->aq.asq_buf_size = I40E_MAX_AQ_BUF_SIZE; pf->adminq_work_limit = I40E_AQ_WORK_LIMIT; @@ -14918,8 +15757,8 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR && hw->aq.api_min_ver > I40E_FW_MINOR_VERSION(hw)) - dev_info(&pdev->dev, - "The driver for the device detected a newer version of the NVM image v%u.%u than expected v%u.%u. Please install the most recent version of the network driver.\n", + dev_dbg(&pdev->dev, + "The driver for the device detected a newer version of the NVM image v%u.%u than v%u.%u.\n", hw->aq.api_maj_ver, hw->aq.api_min_ver, I40E_FW_API_VERSION_MAJOR, @@ -14990,9 +15829,16 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (is_valid_ether_addr(hw->mac.port_addr)) pf->hw_features |= I40E_HW_PORT_ID_VALID; + i40e_ptp_alloc_pins(pf); pci_set_drvdata(pdev, pf); pci_save_state(pdev); +#ifdef CONFIG_I40E_DCB + status = i40e_get_fw_lldp_status(&pf->hw, &lldp_status); + (!status && + lldp_status == I40E_GET_FW_LLDP_STATUS_ENABLED) ? + (pf->flags &= ~I40E_FLAG_DISABLE_FW_LLDP) : + (pf->flags |= I40E_FLAG_DISABLE_FW_LLDP); dev_info(&pdev->dev, (pf->flags & I40E_FLAG_DISABLE_FW_LLDP) ? "FW LLDP is disabled\n" : @@ -15001,7 +15847,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Enable FW to write default DCB config on link-up */ i40e_aq_set_dcb_parameters(hw, true, NULL); -#ifdef CONFIG_I40E_DCB err = i40e_init_pf_dcb(pf); if (err) { dev_info(&pdev->dev, "DCB init failed %d, disabled\n", err); @@ -15031,6 +15876,22 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto err_switch_setup; + /* Reduce Tx and Rx pairs for kdump + * When MSI-X is enabled, it's not allowed to use more TC queue + * pairs than MSI-X vectors (pf->num_lan_msix) exist. Thus + * vsi->num_queue_pairs will be equal to pf->num_lan_msix, i.e., 1. + */ + if (is_kdump_kernel()) + pf->num_lan_msix = 1; + + pf->udp_tunnel_nic.set_port = i40e_udp_tunnel_set_port; + pf->udp_tunnel_nic.unset_port = i40e_udp_tunnel_unset_port; + pf->udp_tunnel_nic.flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP; + pf->udp_tunnel_nic.shared = &pf->udp_tunnel_shared; + pf->udp_tunnel_nic.tables[0].n_entries = I40E_MAX_PF_UDP_OFFLOAD_PORTS; + pf->udp_tunnel_nic.tables[0].tunnel_types = UDP_TUNNEL_TYPE_VXLAN | + UDP_TUNNEL_TYPE_GENEVE; + /* The number of VSIs reported by the FW is the minimum guaranteed * to us; HW supports far more and we share the remaining pool with * the other PFs. We allocate space for more than the guarantee with @@ -15040,6 +15901,12 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pf->num_alloc_vsi = I40E_MIN_VSI_ALLOC; else pf->num_alloc_vsi = pf->hw.func_caps.num_vsis; + if (pf->num_alloc_vsi > UDP_TUNNEL_NIC_MAX_SHARING_DEVICES) { + dev_warn(&pf->pdev->dev, + "limiting the VSI count due to UDP tunnel limitation %d > %d\n", + pf->num_alloc_vsi, UDP_TUNNEL_NIC_MAX_SHARING_DEVICES); + pf->num_alloc_vsi = UDP_TUNNEL_NIC_MAX_SHARING_DEVICES; + } /* Set up the *vsi struct and our local tracking of the MAIN PF vsi. */ pf->vsi = kcalloc(pf->num_alloc_vsi, sizeof(struct i40e_vsi *), @@ -15058,31 +15925,13 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pf->flags |= I40E_FLAG_VEB_MODE_ENABLED; } #endif - err = i40e_setup_pf_switch(pf, false); + err = i40e_setup_pf_switch(pf, false, false); if (err) { dev_info(&pdev->dev, "setup_pf_switch failed: %d\n", err); goto err_vsis; } INIT_LIST_HEAD(&pf->vsi[pf->lan_vsi]->ch_list); - /* Make sure flow control is set according to current settings */ - err = i40e_set_fc(hw, &set_fc_aq_fail, true); - if (set_fc_aq_fail & I40E_SET_FC_AQ_FAIL_GET) - dev_dbg(&pf->pdev->dev, - "Set fc with err %s aq_err %s on get_phy_cap\n", - i40e_stat_str(hw, err), - i40e_aq_str(hw, hw->aq.asq_last_status)); - if (set_fc_aq_fail & I40E_SET_FC_AQ_FAIL_SET) - dev_dbg(&pf->pdev->dev, - "Set fc with err %s aq_err %s on set_phy_config\n", - i40e_stat_str(hw, err), - i40e_aq_str(hw, hw->aq.asq_last_status)); - if (set_fc_aq_fail & I40E_SET_FC_AQ_FAIL_UPDATE) - dev_dbg(&pf->pdev->dev, - "Set fc with err %s aq_err %s on get_link_info\n", - i40e_stat_str(hw, err), - i40e_aq_str(hw, hw->aq.asq_last_status)); - /* if FDIR VSI was set up, start it now */ for (i = 0; i < pf->num_alloc_vsi; i++) { if (pf->vsi[i] && pf->vsi[i]->type == I40E_VSI_FDIR) { @@ -15139,6 +15988,8 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) { dev_info(&pdev->dev, "setup of misc vector failed: %d\n", err); + i40e_cloud_filter_exit(pf); + i40e_fdir_teardown(pf); goto err_vsis; } } @@ -15215,23 +16066,23 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) switch (hw->bus.speed) { case i40e_bus_speed_8000: - strlcpy(speed, "8.0", PCI_SPEED_SIZE); break; + strscpy(speed, "8.0", PCI_SPEED_SIZE); break; case i40e_bus_speed_5000: - strlcpy(speed, "5.0", PCI_SPEED_SIZE); break; + strscpy(speed, "5.0", PCI_SPEED_SIZE); break; case i40e_bus_speed_2500: - strlcpy(speed, "2.5", PCI_SPEED_SIZE); break; + strscpy(speed, "2.5", PCI_SPEED_SIZE); break; default: break; } switch (hw->bus.width) { case i40e_bus_width_pcie_x8: - strlcpy(width, "8", PCI_WIDTH_SIZE); break; + strscpy(width, "8", PCI_WIDTH_SIZE); break; case i40e_bus_width_pcie_x4: - strlcpy(width, "4", PCI_WIDTH_SIZE); break; + strscpy(width, "4", PCI_WIDTH_SIZE); break; case i40e_bus_width_pcie_x2: - strlcpy(width, "2", PCI_WIDTH_SIZE); break; + strscpy(width, "2", PCI_WIDTH_SIZE); break; case i40e_bus_width_pcie_x1: - strlcpy(width, "1", PCI_WIDTH_SIZE); break; + strscpy(width, "1", PCI_WIDTH_SIZE); break; default: break; } @@ -15264,6 +16115,14 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) i40e_stat_str(&pf->hw, err), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); + /* make sure the MFS hasn't been set lower than the default */ +#define MAX_FRAME_SIZE_DEFAULT 0x2600 + val = (rd32(&pf->hw, I40E_PRTGL_SAH) & + I40E_PRTGL_SAH_MFS_MASK) >> I40E_PRTGL_SAH_MFS_SHIFT; + if (val < MAX_FRAME_SIZE_DEFAULT) + dev_warn(&pdev->dev, "MFS for port %x has been set below the default: %x\n", + i, val); + /* Add a filter to drop all Flow control frames from any VSI from being * transmitted. By doing so we stop a malicious VF from sending out * PAUSE or PFC frames and potentially controlling traffic for other @@ -15335,6 +16194,19 @@ static void i40e_remove(struct pci_dev *pdev) i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), 0); i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), 0); + /* Grab __I40E_RESET_RECOVERY_PENDING and set __I40E_IN_REMOVE + * flags, once they are set, i40e_rebuild should not be called as + * i40e_prep_for_reset always returns early. + */ + while (test_and_set_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) + usleep_range(1000, 2000); + set_bit(__I40E_IN_REMOVE, pf->state); + + if (pf->flags & I40E_FLAG_SRIOV_ENABLED) { + set_bit(__I40E_VF_RESETS_DISABLED, pf->state); + i40e_free_vfs(pf); + pf->flags &= ~I40E_FLAG_SRIOV_ENABLED; + } /* no more scheduling of any task */ set_bit(__I40E_SUSPENDED, pf->state); set_bit(__I40E_DOWN, pf->state); @@ -15361,11 +16233,6 @@ static void i40e_remove(struct pci_dev *pdev) */ i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], false); - if (pf->flags & I40E_FLAG_SRIOV_ENABLED) { - i40e_free_vfs(pf); - pf->flags &= ~I40E_FLAG_SRIOV_ENABLED; - } - i40e_fdir_teardown(pf); /* If there is a switch structure or any orphans, remove them. @@ -15457,7 +16324,7 @@ unmap: * remediation. **/ static pci_ers_result_t i40e_pci_error_detected(struct pci_dev *pdev, - enum pci_channel_state error) + pci_channel_state_t error) { struct i40e_pf *pf = pci_get_drvdata(pdev); @@ -15471,7 +16338,7 @@ static pci_ers_result_t i40e_pci_error_detected(struct pci_dev *pdev, /* shutdown all operations */ if (!test_bit(__I40E_SUSPENDED, pf->state)) - i40e_prep_for_reset(pf, false); + i40e_prep_for_reset(pf); /* Request a slot reset */ return PCI_ERS_RESULT_NEED_RESET; @@ -15521,7 +16388,7 @@ static void i40e_pci_error_reset_prepare(struct pci_dev *pdev) { struct i40e_pf *pf = pci_get_drvdata(pdev); - i40e_prep_for_reset(pf, false); + i40e_prep_for_reset(pf); } /** @@ -15532,6 +16399,9 @@ static void i40e_pci_error_reset_done(struct pci_dev *pdev) { struct i40e_pf *pf = pci_get_drvdata(pdev); + if (test_bit(__I40E_IN_REMOVE, pf->state)) + return; + i40e_reset_and_rebuild(pf, false, false); } @@ -15625,7 +16495,7 @@ static void i40e_shutdown(struct pci_dev *pdev) if (pf->wol_en && (pf->hw_features & I40E_HW_WOL_MC_MAGIC_PKT_WAKE)) i40e_enable_mc_magic_wake(pf); - i40e_prep_for_reset(pf, false); + i40e_prep_for_reset(pf); wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0)); @@ -15684,7 +16554,7 @@ static int __maybe_unused i40e_suspend(struct device *dev) */ rtnl_lock(); - i40e_prep_for_reset(pf, true); + i40e_prep_for_reset(pf); wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0)); wr32(hw, I40E_PFPM_WUFC, (pf->wol_en ? I40E_PFPM_WUFC_MAG_MASK : 0)); @@ -15774,8 +16644,7 @@ static struct pci_driver i40e_driver = { **/ static int __init i40e_init_module(void) { - pr_info("%s: %s - version %s\n", i40e_driver_name, - i40e_driver_string, i40e_driver_version_str); + pr_info("%s: %s\n", i40e_driver_name, i40e_driver_string); pr_info("%s: %s\n", i40e_driver_name, i40e_copyright); /* There is no need to throttle the number of active tasks because @@ -15806,6 +16675,7 @@ static void __exit i40e_exit_module(void) { pci_unregister_driver(&i40e_driver); destroy_workqueue(i40e_wq); + ida_destroy(&i40e_client_ida); i40e_dbg_exit(); } module_exit(i40e_exit_module); |