diff options
Diffstat (limited to 'drivers/net/ethernet/intel/i40e/i40e_main.c')
| -rw-r--r-- | drivers/net/ethernet/intel/i40e/i40e_main.c | 711 |
1 files changed, 343 insertions, 368 deletions
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 2a037ec244b9..4f8a2154b93f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -5,13 +5,14 @@ #include <linux/of_net.h> #include <linux/pci.h> #include <linux/bpf.h> +#include <generated/utsrelease.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 +24,6 @@ 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 */ @@ -54,7 +46,7 @@ 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 * @@ -101,7 +93,6 @@ MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all), Debug mask (0x8XXXXXXX MODULE_AUTHOR("Intel Corporation, <[email protected]>"); MODULE_DESCRIPTION("Intel(R) Ethernet Connection XL710 Network Driver"); MODULE_LICENSE("GPL v2"); -MODULE_VERSION(DRV_VERSION); static struct workqueue_struct *i40e_wq; @@ -296,6 +287,7 @@ 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 @@ -439,11 +431,15 @@ 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; @@ -787,6 +783,8 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) 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); @@ -800,8 +798,11 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) tx_linearize += p->tx_stats.tx_linearize; tx_force_wb += p->tx_stats.tx_force_wb; - /* Rx queue is part of the same block as Tx queue */ - p = &p[1]; + /* locate Rx ring */ + p = READ_ONCE(vsi->rx_rings[q]); + if (!p) + continue; + do { start = u64_stats_fetch_begin_irq(&p->syncp); packets = p->stats.packets; @@ -811,6 +812,25 @@ 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; + + 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; @@ -1590,6 +1610,8 @@ 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) @@ -1817,7 +1839,7 @@ 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: @@ -3103,12 +3125,12 @@ 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 +3141,7 @@ 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 +3160,7 @@ 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) { @@ -3260,26 +3282,32 @@ 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; + kfree(ring->rx_bi); + ring->xsk_pool = i40e_xsk_pool(ring); + if (ring->xsk_pool) { + ret = i40e_alloc_rx_bi_zc(ring); + if (ret) + return ret; + 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 { + ret = i40e_alloc_rx_bi(ring); + if (ret) + return ret; ring->rx_buf_len = vsi->rx_buf_len; if (ring->vsi->type == I40E_VSI_MAIN) { ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, @@ -3296,8 +3324,8 @@ 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; @@ -3344,16 +3372,19 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) 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); } @@ -5787,7 +5818,6 @@ 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 * @@ -6030,8 +6060,7 @@ 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) @@ -6484,8 +6513,7 @@ 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 +6625,25 @@ 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 +6710,6 @@ 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 +6719,6 @@ 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 +6727,7 @@ 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 +6763,11 @@ 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 +6775,18 @@ 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 +6817,32 @@ 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 +6860,8 @@ 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); @@ -7735,7 +7799,7 @@ 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 * **/ @@ -8116,8 +8180,8 @@ 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) @@ -8418,9 +8482,6 @@ 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)) { @@ -8942,13 +9003,6 @@ 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 @@ -9548,6 +9602,7 @@ 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) @@ -9843,11 +9898,11 @@ 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)); + strlcpy(dv.driver_string, UTS_RELEASE, sizeof(dv.driver_string)); i40e_aq_send_driver_version(&pf->hw, &dv, NULL); } @@ -10346,106 +10401,6 @@ 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 +10440,6 @@ 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 +10463,7 @@ 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) { @@ -10816,10 +10770,10 @@ 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 +10807,7 @@ 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 +10825,7 @@ 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 +10838,7 @@ 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 +11102,10 @@ 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; @@ -11185,7 +11138,7 @@ 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 +11148,10 @@ 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; @@ -11838,6 +11786,58 @@ 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 * @@ -12012,6 +12012,16 @@ static int i40e_sw_init(struct i40e_pf *pf) 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: @@ -12129,131 +12139,48 @@ 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 +12207,7 @@ 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, @@ -12545,7 +12473,7 @@ 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); @@ -12824,11 +12752,8 @@ 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, + case XDP_SETUP_XSK_POOL: + return i40e_xsk_pool_setup(vsi, xdp->xsk.pool, xdp->xsk.queue_id); default: return -EINVAL; @@ -12861,8 +12786,8 @@ 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_udp_tunnel_add = udp_tunnel_nic_add_port, + .ndo_udp_tunnel_del = udp_tunnel_nic_del_port, .ndo_get_phys_port_id = i40e_get_phys_port_id, .ndo_fdb_add = i40e_ndo_fdb_add, .ndo_features_check = i40e_features_check, @@ -12926,6 +12851,8 @@ 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; @@ -13686,8 +13613,7 @@ 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 +13629,6 @@ 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; @@ -14328,7 +14253,7 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit) i40e_ptp_init(pf); /* repopulate tunnel port filters */ - i40e_sync_udp_filters(pf); + udp_tunnel_nic_reset_ntf(pf->vsi[pf->lan_vsi]->netdev); return ret; } @@ -14478,29 +14403,29 @@ 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 +14482,17 @@ 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 +14520,68 @@ 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 @@ -14864,11 +14817,9 @@ 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); @@ -15031,6 +14982,14 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto err_switch_setup; + 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 +14999,12 @@ 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 *), @@ -15264,6 +15229,14 @@ 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 +15308,9 @@ 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); + while (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) + usleep_range(1000, 2000); + /* no more scheduling of any task */ set_bit(__I40E_SUSPENDED, pf->state); set_bit(__I40E_DOWN, pf->state); @@ -15457,7 +15433,7 @@ 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); @@ -15774,8 +15750,7 @@ 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 |