diff options
Diffstat (limited to 'drivers/net/ethernet/intel')
29 files changed, 581 insertions, 354 deletions
diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h index bcf680e83811..13382df2f2ef 100644 --- a/drivers/net/ethernet/intel/e1000e/hw.h +++ b/drivers/net/ethernet/intel/e1000e/hw.h @@ -630,6 +630,7 @@ struct e1000_phy_info { bool disable_polarity_correction; bool is_mdix; bool polarity_correction; + bool reset_disable; bool speed_downgraded; bool autoneg_wait_to_complete; }; diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index c908c84b86d2..e6c8e6d5234f 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -1009,8 +1009,8 @@ static s32 e1000_platform_pm_pch_lpt(struct e1000_hw *hw, bool link) { u32 reg = link << (E1000_LTRV_REQ_SHIFT + E1000_LTRV_NOSNOOP_SHIFT) | link << E1000_LTRV_REQ_SHIFT | E1000_LTRV_SEND; - u16 max_ltr_enc_d = 0; /* maximum LTR decoded by platform */ - u16 lat_enc_d = 0; /* latency decoded */ + u32 max_ltr_enc_d = 0; /* maximum LTR decoded by platform */ + u32 lat_enc_d = 0; /* latency decoded */ u16 lat_enc = 0; /* latency encoded */ if (link) { @@ -2050,6 +2050,10 @@ static s32 e1000_check_reset_block_ich8lan(struct e1000_hw *hw) bool blocked = false; int i = 0; + /* Check the PHY (LCD) reset flag */ + if (hw->phy.reset_disable) + return true; + while ((blocked = !(er32(FWSM) & E1000_ICH_FWSM_RSPCIPHY)) && (i++ < 30)) usleep_range(10000, 11000); @@ -4136,9 +4140,9 @@ static s32 e1000_validate_nvm_checksum_ich8lan(struct e1000_hw *hw) return ret_val; if (!(data & valid_csum_mask)) { - e_dbg("NVM Checksum Invalid\n"); + e_dbg("NVM Checksum valid bit not set\n"); - if (hw->mac.type < e1000_pch_cnp) { + if (hw->mac.type < e1000_pch_tgp) { data |= valid_csum_mask; ret_val = e1000_write_nvm(hw, word, 1, &data); if (ret_val) diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.h b/drivers/net/ethernet/intel/e1000e/ich8lan.h index 2504b11c3169..638a3ddd7ada 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.h +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.h @@ -271,6 +271,7 @@ #define I217_CGFREG_ENABLE_MTA_RESET 0x0002 #define I217_MEMPWR PHY_REG(772, 26) #define I217_MEMPWR_DISABLE_SMB_RELEASE 0x0010 +#define I217_MEMPWR_MOEM 0x1000 /* Receive Address Initial CRC Calculation */ #define E1000_PCH_RAICC(_n) (0x05F50 + ((_n) * 4)) diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index af2029bb43e3..ce48e630fe55 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -6992,8 +6992,21 @@ static __maybe_unused int e1000e_pm_suspend(struct device *dev) struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev)); struct e1000_adapter *adapter = netdev_priv(netdev); struct pci_dev *pdev = to_pci_dev(dev); + struct e1000_hw *hw = &adapter->hw; + u16 phy_data; int rc; + if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID && + hw->mac.type >= e1000_pch_adp) { + /* Mask OEM Bits / Gig Disable / Restart AN (772_26[12] = 1) */ + e1e_rphy(hw, I217_MEMPWR, &phy_data); + phy_data |= I217_MEMPWR_MOEM; + e1e_wphy(hw, I217_MEMPWR, phy_data); + + /* Disable LCD reset */ + hw->phy.reset_disable = true; + } + e1000e_flush_lpic(pdev); e1000e_pm_freeze(dev); @@ -7015,6 +7028,8 @@ static __maybe_unused int e1000e_pm_resume(struct device *dev) struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev)); struct e1000_adapter *adapter = netdev_priv(netdev); struct pci_dev *pdev = to_pci_dev(dev); + struct e1000_hw *hw = &adapter->hw; + u16 phy_data; int rc; /* Introduce S0ix implementation */ @@ -7025,6 +7040,17 @@ static __maybe_unused int e1000e_pm_resume(struct device *dev) if (rc) return rc; + if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID && + hw->mac.type >= e1000_pch_adp) { + /* Unmask OEM Bits / Gig Disable / Restart AN 772_26[12] = 0 */ + e1e_rphy(hw, I217_MEMPWR, &phy_data); + phy_data &= ~I217_MEMPWR_MOEM; + e1e_wphy(hw, I217_MEMPWR, phy_data); + + /* Enable LCD reset */ + hw->phy.reset_disable = false; + } + return e1000e_pm_thaw(dev); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 1e57cc8c47d7..9db5001297c7 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -742,10 +742,8 @@ static void i40e_dbg_dump_vf(struct i40e_pf *pf, int vf_id) vsi = pf->vsi[vf->lan_vsi_idx]; dev_info(&pf->pdev->dev, "vf %2d: VSI id=%d, seid=%d, qps=%d\n", vf_id, vf->lan_vsi_id, vsi->seid, vf->num_queue_pairs); - dev_info(&pf->pdev->dev, " num MDD=%lld, invalid msg=%lld, valid msg=%lld\n", - vf->num_mdd_events, - vf->num_invalid_msgs, - vf->num_valid_msgs); + dev_info(&pf->pdev->dev, " num MDD=%lld\n", + vf->num_mdd_events); } else { dev_info(&pf->pdev->dev, "invalid VF id %d\n", vf_id); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 063ded36b902..ad73dd2540e7 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -5372,15 +5372,7 @@ static int i40e_vsi_configure_bw_alloc(struct i40e_vsi *vsi, u8 enabled_tc, /* There is no need to reset BW when mqprio mode is on. */ if (pf->flags & I40E_FLAG_TC_MQPRIO) return 0; - - if (!vsi->mqprio_qopt.qopt.hw) { - if (pf->flags & I40E_FLAG_DCB_ENABLED) - goto skip_reset; - - if (IS_ENABLED(CONFIG_I40E_DCB) && - i40e_dcb_hw_get_num_tc(&pf->hw) == 1) - goto skip_reset; - + if (!vsi->mqprio_qopt.qopt.hw && !(pf->flags & I40E_FLAG_DCB_ENABLED)) { ret = i40e_set_bw_limit(vsi, vsi->seid, 0); if (ret) dev_info(&pf->pdev->dev, @@ -5388,8 +5380,6 @@ static int i40e_vsi_configure_bw_alloc(struct i40e_vsi *vsi, u8 enabled_tc, vsi->seid); return ret; } - -skip_reset: memset(&bw_data, 0, sizeof(bw_data)); bw_data.tc_valid_bits = enabled_tc; for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index c6f643e54c4f..babf8b7fa767 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1917,19 +1917,17 @@ sriov_configure_out: /***********************virtual channel routines******************/ /** - * i40e_vc_send_msg_to_vf_ex + * i40e_vc_send_msg_to_vf * @vf: pointer to the VF info * @v_opcode: virtual channel opcode * @v_retval: virtual channel return value * @msg: pointer to the msg buffer * @msglen: msg length - * @is_quiet: true for not printing unsuccessful return values, false otherwise * * send msg to VF **/ -static int i40e_vc_send_msg_to_vf_ex(struct i40e_vf *vf, u32 v_opcode, - u32 v_retval, u8 *msg, u16 msglen, - bool is_quiet) +static int i40e_vc_send_msg_to_vf(struct i40e_vf *vf, u32 v_opcode, + u32 v_retval, u8 *msg, u16 msglen) { struct i40e_pf *pf; struct i40e_hw *hw; @@ -1944,25 +1942,6 @@ static int i40e_vc_send_msg_to_vf_ex(struct i40e_vf *vf, u32 v_opcode, hw = &pf->hw; abs_vf_id = vf->vf_id + hw->func_caps.vf_base_id; - /* single place to detect unsuccessful return values */ - if (v_retval && !is_quiet) { - vf->num_invalid_msgs++; - dev_info(&pf->pdev->dev, "VF %d failed opcode %d, retval: %d\n", - vf->vf_id, v_opcode, v_retval); - if (vf->num_invalid_msgs > - I40E_DEFAULT_NUM_INVALID_MSGS_ALLOWED) { - dev_err(&pf->pdev->dev, - "Number of invalid messages exceeded for VF %d\n", - vf->vf_id); - dev_err(&pf->pdev->dev, "Use PF Control I/F to enable the VF\n"); - set_bit(I40E_VF_STATE_DISABLED, &vf->vf_states); - } - } else { - vf->num_valid_msgs++; - /* reset the invalid counter, if a valid message is received. */ - vf->num_invalid_msgs = 0; - } - aq_ret = i40e_aq_send_msg_to_vf(hw, abs_vf_id, v_opcode, v_retval, msg, msglen, NULL); if (aq_ret) { @@ -1976,23 +1955,6 @@ static int i40e_vc_send_msg_to_vf_ex(struct i40e_vf *vf, u32 v_opcode, } /** - * i40e_vc_send_msg_to_vf - * @vf: pointer to the VF info - * @v_opcode: virtual channel opcode - * @v_retval: virtual channel return value - * @msg: pointer to the msg buffer - * @msglen: msg length - * - * send msg to VF - **/ -static int i40e_vc_send_msg_to_vf(struct i40e_vf *vf, u32 v_opcode, - u32 v_retval, u8 *msg, u16 msglen) -{ - return i40e_vc_send_msg_to_vf_ex(vf, v_opcode, v_retval, - msg, msglen, false); -} - -/** * i40e_vc_send_resp_to_vf * @vf: pointer to the VF info * @opcode: operation code @@ -2813,7 +2775,6 @@ error_param: * i40e_check_vf_permission * @vf: pointer to the VF info * @al: MAC address list from virtchnl - * @is_quiet: set true for printing msg without opcode info, false otherwise * * Check that the given list of MAC addresses is allowed. Will return -EPERM * if any address in the list is not valid. Checks the following conditions: @@ -2828,15 +2789,13 @@ error_param: * addresses might not be accurate. **/ static inline int i40e_check_vf_permission(struct i40e_vf *vf, - struct virtchnl_ether_addr_list *al, - bool *is_quiet) + struct virtchnl_ether_addr_list *al) { struct i40e_pf *pf = vf->pf; struct i40e_vsi *vsi = pf->vsi[vf->lan_vsi_idx]; int mac2add_cnt = 0; int i; - *is_quiet = false; for (i = 0; i < al->num_elements; i++) { struct i40e_mac_filter *f; u8 *addr = al->list[i].addr; @@ -2860,7 +2819,6 @@ static inline int i40e_check_vf_permission(struct i40e_vf *vf, !ether_addr_equal(addr, vf->default_lan_addr.addr)) { dev_err(&pf->pdev->dev, "VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n"); - *is_quiet = true; return -EPERM; } @@ -2897,7 +2855,6 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg) (struct virtchnl_ether_addr_list *)msg; struct i40e_pf *pf = vf->pf; struct i40e_vsi *vsi = NULL; - bool is_quiet = false; i40e_status ret = 0; int i; @@ -2914,7 +2871,7 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg) */ spin_lock_bh(&vsi->mac_filter_hash_lock); - ret = i40e_check_vf_permission(vf, al, &is_quiet); + ret = i40e_check_vf_permission(vf, al); if (ret) { spin_unlock_bh(&vsi->mac_filter_hash_lock); goto error_param; @@ -2952,8 +2909,8 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg) error_param: /* send the response to the VF */ - return i40e_vc_send_msg_to_vf_ex(vf, VIRTCHNL_OP_ADD_ETH_ADDR, - ret, NULL, 0, is_quiet); + return i40e_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ADD_ETH_ADDR, + ret, NULL, 0); } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 03c42fd0fea1..a554d0a0b09b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -10,8 +10,6 @@ #define I40E_VIRTCHNL_SUPPORTED_QTYPES 2 -#define I40E_DEFAULT_NUM_INVALID_MSGS_ALLOWED 10 - #define I40E_VLAN_PRIORITY_SHIFT 13 #define I40E_VLAN_MASK 0xFFF #define I40E_PRIORITY_MASK 0xE000 @@ -92,9 +90,6 @@ struct i40e_vf { u8 num_queue_pairs; /* num of qps assigned to VF vsis */ u8 num_req_queues; /* num of requested qps */ u64 num_mdd_events; /* num of mdd events detected */ - /* num of continuous malformed or invalid msgs detected */ - u64 num_invalid_msgs; - u64 num_valid_msgs; /* num of valid msgs detected */ unsigned long vf_caps; /* vf's adv. capabilities */ unsigned long vf_states; /* vf's runtime states */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index e7e778ca074c..3f27a8ebe2ec 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -243,21 +243,25 @@ no_buffers: static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp) { + unsigned int totalsize = xdp->data_end - xdp->data_meta; unsigned int metasize = xdp->data - xdp->data_meta; - unsigned int datasize = xdp->data_end - xdp->data; struct sk_buff *skb; + net_prefetch(xdp->data_meta); + /* allocate a skb to store the frags */ - skb = __napi_alloc_skb(&rx_ring->q_vector->napi, - xdp->data_end - xdp->data_hard_start, + skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize, GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) goto out; - skb_reserve(skb, xdp->data - xdp->data_hard_start); - memcpy(__skb_put(skb, datasize), xdp->data, datasize); - if (metasize) + memcpy(__skb_put(skb, totalsize), xdp->data_meta, + ALIGN(totalsize, sizeof(long))); + + if (metasize) { skb_metadata_set(skb, metasize); + __skb_pull(skb, metasize); + } out: xsk_buff_free(xdp); diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 0ae6da2992d0..9a122aea6979 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -178,6 +178,7 @@ enum iavf_state_t { __IAVF_INIT_VERSION_CHECK, /* aq msg sent, awaiting reply */ __IAVF_INIT_GET_RESOURCES, /* aq msg sent, awaiting reply */ __IAVF_INIT_SW, /* got resources, setting up structs */ + __IAVF_INIT_FAILED, /* init failed, restarting procedure */ __IAVF_RESETTING, /* in reset */ __IAVF_COMM_FAILED, /* communication with PF failed */ /* Below here, watchdog is running */ @@ -187,6 +188,10 @@ enum iavf_state_t { __IAVF_RUNNING, /* opened, working */ }; +enum iavf_critical_section_t { + __IAVF_IN_REMOVE_TASK, /* device being removed */ +}; + #define IAVF_CLOUD_FIELD_OMAC 0x01 #define IAVF_CLOUD_FIELD_IMAC 0x02 #define IAVF_CLOUD_FIELD_IVLAN 0x04 @@ -226,14 +231,12 @@ struct iavf_adapter { struct work_struct reset_task; struct work_struct adminq_task; struct delayed_work client_task; - struct delayed_work init_task; wait_queue_head_t down_waitqueue; struct iavf_q_vector *q_vectors; struct list_head vlan_filter_list; struct list_head mac_filter_list; struct mutex crit_lock; struct mutex client_lock; - struct mutex remove_lock; /* Lock to protect accesses to MAC and VLAN lists */ spinlock_t mac_vlan_list_lock; char misc_vector_name[IFNAMSIZ + 9]; @@ -271,6 +274,7 @@ struct iavf_adapter { #define IAVF_FLAG_LEGACY_RX BIT(15) #define IAVF_FLAG_REINIT_ITR_NEEDED BIT(16) #define IAVF_FLAG_QUEUES_DISABLED BIT(17) +#define IAVF_FLAG_SETUP_NETDEV_FEATURES BIT(18) /* duplicates for common code */ #define IAVF_FLAG_DCB_ENABLED 0 /* flags for admin queue service task */ @@ -314,6 +318,7 @@ struct iavf_adapter { struct iavf_hw hw; /* defined in iavf_type.h */ enum iavf_state_t state; + enum iavf_state_t last_state; unsigned long crit_section; struct delayed_work watchdog_task; @@ -395,6 +400,51 @@ struct iavf_device { extern char iavf_driver_name[]; extern struct workqueue_struct *iavf_wq; +static inline const char *iavf_state_str(enum iavf_state_t state) +{ + switch (state) { + case __IAVF_STARTUP: + return "__IAVF_STARTUP"; + case __IAVF_REMOVE: + return "__IAVF_REMOVE"; + case __IAVF_INIT_VERSION_CHECK: + return "__IAVF_INIT_VERSION_CHECK"; + case __IAVF_INIT_GET_RESOURCES: + return "__IAVF_INIT_GET_RESOURCES"; + case __IAVF_INIT_SW: + return "__IAVF_INIT_SW"; + case __IAVF_INIT_FAILED: + return "__IAVF_INIT_FAILED"; + case __IAVF_RESETTING: + return "__IAVF_RESETTING"; + case __IAVF_COMM_FAILED: + return "__IAVF_COMM_FAILED"; + case __IAVF_DOWN: + return "__IAVF_DOWN"; + case __IAVF_DOWN_PENDING: + return "__IAVF_DOWN_PENDING"; + case __IAVF_TESTING: + return "__IAVF_TESTING"; + case __IAVF_RUNNING: + return "__IAVF_RUNNING"; + default: + return "__IAVF_UNKNOWN_STATE"; + } +} + +static inline void iavf_change_state(struct iavf_adapter *adapter, + enum iavf_state_t state) +{ + if (adapter->state != state) { + adapter->last_state = adapter->state; + adapter->state = state; + } + dev_dbg(&adapter->pdev->dev, + "state transition from:%s to:%s\n", + iavf_state_str(adapter->last_state), + iavf_state_str(adapter->state)); +} + int iavf_up(struct iavf_adapter *adapter); void iavf_down(struct iavf_adapter *adapter); int iavf_process_config(struct iavf_adapter *adapter); diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 6502c8056a8e..ca74824d40b8 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -14,7 +14,7 @@ static int iavf_setup_all_tx_resources(struct iavf_adapter *adapter); static int iavf_setup_all_rx_resources(struct iavf_adapter *adapter); static int iavf_close(struct net_device *netdev); -static int iavf_init_get_resources(struct iavf_adapter *adapter); +static void iavf_init_get_resources(struct iavf_adapter *adapter); static int iavf_check_reset_complete(struct iavf_hw *hw); char iavf_driver_name[] = "iavf"; @@ -52,6 +52,15 @@ static const struct net_device_ops iavf_netdev_ops; struct workqueue_struct *iavf_wq; /** + * iavf_pdev_to_adapter - go from pci_dev to adapter + * @pdev: pci_dev pointer + */ +static struct iavf_adapter *iavf_pdev_to_adapter(struct pci_dev *pdev) +{ + return netdev_priv(pci_get_drvdata(pdev)); +} + +/** * iavf_allocate_dma_mem_d - OS specific memory alloc for shared code * @hw: pointer to the HW structure * @mem: ptr to mem struct to fill out @@ -293,8 +302,9 @@ static irqreturn_t iavf_msix_aq(int irq, void *data) rd32(hw, IAVF_VFINT_ICR01); rd32(hw, IAVF_VFINT_ICR0_ENA1); - /* schedule work on the private workqueue */ - queue_work(iavf_wq, &adapter->adminq_task); + if (adapter->state != __IAVF_REMOVE) + /* schedule work on the private workqueue */ + queue_work(iavf_wq, &adapter->adminq_task); return IRQ_HANDLED; } @@ -990,7 +1000,7 @@ static void iavf_configure(struct iavf_adapter *adapter) **/ static void iavf_up_complete(struct iavf_adapter *adapter) { - adapter->state = __IAVF_RUNNING; + iavf_change_state(adapter, __IAVF_RUNNING); clear_bit(__IAVF_VSI_DOWN, adapter->vsi.state); iavf_napi_enable_all(adapter); @@ -1063,8 +1073,7 @@ void iavf_down(struct iavf_adapter *adapter) rss->state = IAVF_ADV_RSS_DEL_REQUEST; spin_unlock_bh(&adapter->adv_rss_lock); - if (!(adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) && - adapter->state != __IAVF_RESETTING) { + if (!(adapter->flags & IAVF_FLAG_PF_COMMS_FAILED)) { /* cancel any current operation */ adapter->current_op = VIRTCHNL_OP_UNKNOWN; /* Schedule operations to close down the HW. Don't wait @@ -1722,9 +1731,9 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter) * * Function process __IAVF_STARTUP driver state. * When success the state is changed to __IAVF_INIT_VERSION_CHECK - * when fails it returns -EAGAIN + * when fails the state is changed to __IAVF_INIT_FAILED **/ -static int iavf_startup(struct iavf_adapter *adapter) +static void iavf_startup(struct iavf_adapter *adapter) { struct pci_dev *pdev = adapter->pdev; struct iavf_hw *hw = &adapter->hw; @@ -1763,9 +1772,10 @@ static int iavf_startup(struct iavf_adapter *adapter) iavf_shutdown_adminq(hw); goto err; } - adapter->state = __IAVF_INIT_VERSION_CHECK; + iavf_change_state(adapter, __IAVF_INIT_VERSION_CHECK); + return; err: - return err; + iavf_change_state(adapter, __IAVF_INIT_FAILED); } /** @@ -1774,9 +1784,9 @@ err: * * Function process __IAVF_INIT_VERSION_CHECK driver state. * When success the state is changed to __IAVF_INIT_GET_RESOURCES - * when fails it returns -EAGAIN + * when fails the state is changed to __IAVF_INIT_FAILED **/ -static int iavf_init_version_check(struct iavf_adapter *adapter) +static void iavf_init_version_check(struct iavf_adapter *adapter) { struct pci_dev *pdev = adapter->pdev; struct iavf_hw *hw = &adapter->hw; @@ -1787,7 +1797,7 @@ static int iavf_init_version_check(struct iavf_adapter *adapter) if (!iavf_asq_done(hw)) { dev_err(&pdev->dev, "Admin queue command never completed\n"); iavf_shutdown_adminq(hw); - adapter->state = __IAVF_STARTUP; + iavf_change_state(adapter, __IAVF_STARTUP); goto err; } @@ -1810,10 +1820,10 @@ static int iavf_init_version_check(struct iavf_adapter *adapter) err); goto err; } - adapter->state = __IAVF_INIT_GET_RESOURCES; - + iavf_change_state(adapter, __IAVF_INIT_GET_RESOURCES); + return; err: - return err; + iavf_change_state(adapter, __IAVF_INIT_FAILED); } /** @@ -1823,9 +1833,9 @@ err: * Function process __IAVF_INIT_GET_RESOURCES driver state and * finishes driver initialization procedure. * When success the state is changed to __IAVF_DOWN - * when fails it returns -EAGAIN + * when fails the state is changed to __IAVF_INIT_FAILED **/ -static int iavf_init_get_resources(struct iavf_adapter *adapter) +static void iavf_init_get_resources(struct iavf_adapter *adapter) { struct net_device *netdev = adapter->netdev; struct pci_dev *pdev = adapter->pdev; @@ -1853,7 +1863,7 @@ static int iavf_init_get_resources(struct iavf_adapter *adapter) */ iavf_shutdown_adminq(hw); dev_err(&pdev->dev, "Unable to get VF config due to PF error condition, not retrying\n"); - return 0; + return; } if (err) { dev_err(&pdev->dev, "Unable to get VF config (%d)\n", err); @@ -1927,7 +1937,7 @@ static int iavf_init_get_resources(struct iavf_adapter *adapter) if (netdev->features & NETIF_F_GRO) dev_info(&pdev->dev, "GRO is enabled\n"); - adapter->state = __IAVF_DOWN; + iavf_change_state(adapter, __IAVF_DOWN); set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); rtnl_unlock(); @@ -1945,7 +1955,7 @@ static int iavf_init_get_resources(struct iavf_adapter *adapter) else iavf_init_rss(adapter); - return err; + return; err_mem: iavf_free_rss(adapter); err_register: @@ -1956,7 +1966,7 @@ err_alloc: kfree(adapter->vf_res); adapter->vf_res = NULL; err: - return err; + iavf_change_state(adapter, __IAVF_INIT_FAILED); } /** @@ -1971,14 +1981,80 @@ static void iavf_watchdog_task(struct work_struct *work) struct iavf_hw *hw = &adapter->hw; u32 reg_val; - if (!mutex_trylock(&adapter->crit_lock)) + if (!mutex_trylock(&adapter->crit_lock)) { + if (adapter->state == __IAVF_REMOVE) + return; + goto restart_watchdog; + } if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) - adapter->state = __IAVF_COMM_FAILED; + iavf_change_state(adapter, __IAVF_COMM_FAILED); + + if (adapter->flags & IAVF_FLAG_RESET_NEEDED) { + adapter->aq_required = 0; + adapter->current_op = VIRTCHNL_OP_UNKNOWN; + mutex_unlock(&adapter->crit_lock); + queue_work(iavf_wq, &adapter->reset_task); + return; + } switch (adapter->state) { + case __IAVF_STARTUP: + iavf_startup(adapter); + mutex_unlock(&adapter->crit_lock); + queue_delayed_work(iavf_wq, &adapter->watchdog_task, + msecs_to_jiffies(30)); + return; + case __IAVF_INIT_VERSION_CHECK: + iavf_init_version_check(adapter); + mutex_unlock(&adapter->crit_lock); + queue_delayed_work(iavf_wq, &adapter->watchdog_task, + msecs_to_jiffies(30)); + return; + case __IAVF_INIT_GET_RESOURCES: + iavf_init_get_resources(adapter); + mutex_unlock(&adapter->crit_lock); + queue_delayed_work(iavf_wq, &adapter->watchdog_task, + msecs_to_jiffies(1)); + return; + case __IAVF_INIT_FAILED: + if (test_bit(__IAVF_IN_REMOVE_TASK, + &adapter->crit_section)) { + /* Do not update the state and do not reschedule + * watchdog task, iavf_remove should handle this state + * as it can loop forever + */ + mutex_unlock(&adapter->crit_lock); + return; + } + if (++adapter->aq_wait_count > IAVF_AQ_MAX_ERR) { + dev_err(&adapter->pdev->dev, + "Failed to communicate with PF; waiting before retry\n"); + adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED; + iavf_shutdown_adminq(hw); + mutex_unlock(&adapter->crit_lock); + queue_delayed_work(iavf_wq, + &adapter->watchdog_task, (5 * HZ)); + return; + } + /* Try again from failed step*/ + iavf_change_state(adapter, adapter->last_state); + mutex_unlock(&adapter->crit_lock); + queue_delayed_work(iavf_wq, &adapter->watchdog_task, HZ); + return; case __IAVF_COMM_FAILED: + if (test_bit(__IAVF_IN_REMOVE_TASK, + &adapter->crit_section)) { + /* Set state to __IAVF_INIT_FAILED and perform remove + * steps. Remove IAVF_FLAG_PF_COMMS_FAILED so the task + * doesn't bring the state back to __IAVF_COMM_FAILED. + */ + iavf_change_state(adapter, __IAVF_INIT_FAILED); + adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED; + mutex_unlock(&adapter->crit_lock); + return; + } reg_val = rd32(hw, IAVF_VFGEN_RSTAT) & IAVF_VFGEN_RSTAT_VFR_STATE_MASK; if (reg_val == VIRTCHNL_VFR_VFACTIVE || @@ -1986,23 +2062,20 @@ static void iavf_watchdog_task(struct work_struct *work) /* A chance for redemption! */ dev_err(&adapter->pdev->dev, "Hardware came out of reset. Attempting reinit.\n"); - adapter->state = __IAVF_STARTUP; - adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED; - queue_delayed_work(iavf_wq, &adapter->init_task, 10); - mutex_unlock(&adapter->crit_lock); - /* Don't reschedule the watchdog, since we've restarted - * the init task. When init_task contacts the PF and + /* When init task contacts the PF and * gets everything set up again, it'll restart the * watchdog for us. Down, boy. Sit. Stay. Woof. */ - return; + iavf_change_state(adapter, __IAVF_STARTUP); + adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED; } adapter->aq_required = 0; adapter->current_op = VIRTCHNL_OP_UNKNOWN; + mutex_unlock(&adapter->crit_lock); queue_delayed_work(iavf_wq, &adapter->watchdog_task, msecs_to_jiffies(10)); - goto watchdog_done; + return; case __IAVF_RESETTING: mutex_unlock(&adapter->crit_lock); queue_delayed_work(iavf_wq, &adapter->watchdog_task, HZ * 2); @@ -2025,15 +2098,16 @@ static void iavf_watchdog_task(struct work_struct *work) adapter->state == __IAVF_RUNNING) iavf_request_stats(adapter); } + if (adapter->state == __IAVF_RUNNING) + iavf_detect_recover_hung(&adapter->vsi); break; case __IAVF_REMOVE: + default: mutex_unlock(&adapter->crit_lock); return; - default: - goto restart_watchdog; } - /* check for hw reset */ + /* check for hw reset */ reg_val = rd32(hw, IAVF_VF_ARQLEN1) & IAVF_VF_ARQLEN1_ARQENABLE_MASK; if (!reg_val) { adapter->flags |= IAVF_FLAG_RESET_PENDING; @@ -2041,24 +2115,31 @@ static void iavf_watchdog_task(struct work_struct *work) adapter->current_op = VIRTCHNL_OP_UNKNOWN; dev_err(&adapter->pdev->dev, "Hardware reset detected\n"); queue_work(iavf_wq, &adapter->reset_task); - goto watchdog_done; + mutex_unlock(&adapter->crit_lock); + queue_delayed_work(iavf_wq, + &adapter->watchdog_task, HZ * 2); + return; } schedule_delayed_work(&adapter->client_task, msecs_to_jiffies(5)); -watchdog_done: - if (adapter->state == __IAVF_RUNNING || - adapter->state == __IAVF_COMM_FAILED) - iavf_detect_recover_hung(&adapter->vsi); mutex_unlock(&adapter->crit_lock); restart_watchdog: + if (adapter->state >= __IAVF_DOWN) + queue_work(iavf_wq, &adapter->adminq_task); if (adapter->aq_required) queue_delayed_work(iavf_wq, &adapter->watchdog_task, msecs_to_jiffies(20)); else queue_delayed_work(iavf_wq, &adapter->watchdog_task, HZ * 2); - queue_work(iavf_wq, &adapter->adminq_task); } +/** + * iavf_disable_vf - disable VF + * @adapter: board private structure + * + * Set communication failed flag and free all resources. + * NOTE: This function is expected to be called with crit_lock being held. + **/ static void iavf_disable_vf(struct iavf_adapter *adapter) { struct iavf_mac_filter *f, *ftmp; @@ -2113,9 +2194,8 @@ static void iavf_disable_vf(struct iavf_adapter *adapter) memset(adapter->vf_res, 0, IAVF_VIRTCHNL_VF_RESOURCE_SIZE); iavf_shutdown_adminq(&adapter->hw); adapter->netdev->flags &= ~IFF_UP; - mutex_unlock(&adapter->crit_lock); adapter->flags &= ~IAVF_FLAG_RESET_PENDING; - adapter->state = __IAVF_DOWN; + iavf_change_state(adapter, __IAVF_DOWN); wake_up(&adapter->down_waitqueue); dev_info(&adapter->pdev->dev, "Reset task did not complete, VF disabled\n"); } @@ -2145,13 +2225,13 @@ static void iavf_reset_task(struct work_struct *work) /* When device is being removed it doesn't make sense to run the reset * task, just return in such a case. */ - if (mutex_is_locked(&adapter->remove_lock)) - return; + if (!mutex_trylock(&adapter->crit_lock)) { + if (adapter->state != __IAVF_REMOVE) + queue_work(iavf_wq, &adapter->reset_task); - if (iavf_lock_timeout(&adapter->crit_lock, 200)) { - schedule_work(&adapter->reset_task); return; } + while (!mutex_trylock(&adapter->client_lock)) usleep_range(500, 1000); if (CLIENT_ENABLED(adapter)) { @@ -2206,6 +2286,7 @@ static void iavf_reset_task(struct work_struct *work) reg_val); iavf_disable_vf(adapter); mutex_unlock(&adapter->client_lock); + mutex_unlock(&adapter->crit_lock); return; /* Do not attempt to reinit. It's dead, Jim. */ } @@ -2214,8 +2295,7 @@ continue_reset: * ndo_open() returning, so we can't assume it means all our open * tasks have finished, since we're not holding the rtnl_lock here. */ - running = ((adapter->state == __IAVF_RUNNING) || - (adapter->state == __IAVF_RESETTING)); + running = adapter->state == __IAVF_RUNNING; if (running) { netif_carrier_off(netdev); @@ -2225,7 +2305,7 @@ continue_reset: } iavf_irq_disable(adapter); - adapter->state = __IAVF_RESETTING; + iavf_change_state(adapter, __IAVF_RESETTING); adapter->flags &= ~IAVF_FLAG_RESET_PENDING; /* free the Tx/Rx rings and descriptors, might be better to just @@ -2319,11 +2399,14 @@ continue_reset: iavf_configure(adapter); + /* iavf_up_complete() will switch device back + * to __IAVF_RUNNING + */ iavf_up_complete(adapter); iavf_irq_enable(adapter, true); } else { - adapter->state = __IAVF_DOWN; + iavf_change_state(adapter, __IAVF_DOWN); wake_up(&adapter->down_waitqueue); } mutex_unlock(&adapter->client_lock); @@ -2333,6 +2416,8 @@ continue_reset: reset_err: mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); + if (running) + iavf_change_state(adapter, __IAVF_RUNNING); dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n"); iavf_close(netdev); } @@ -2355,13 +2440,19 @@ static void iavf_adminq_task(struct work_struct *work) if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) goto out; + if (!mutex_trylock(&adapter->crit_lock)) { + if (adapter->state == __IAVF_REMOVE) + return; + + queue_work(iavf_wq, &adapter->adminq_task); + goto out; + } + event.buf_len = IAVF_MAX_AQ_BUF_SIZE; event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL); if (!event.msg_buf) goto out; - if (iavf_lock_timeout(&adapter->crit_lock, 200)) - goto freedom; do { ret = iavf_clean_arq_element(hw, &event, &pending); v_op = (enum virtchnl_ops)le32_to_cpu(event.desc.cookie_high); @@ -2377,6 +2468,18 @@ static void iavf_adminq_task(struct work_struct *work) } while (pending); mutex_unlock(&adapter->crit_lock); + if ((adapter->flags & IAVF_FLAG_SETUP_NETDEV_FEATURES)) { + if (adapter->netdev_registered || + !test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) { + struct net_device *netdev = adapter->netdev; + + rtnl_lock(); + netdev_update_features(netdev); + rtnl_unlock(); + } + + adapter->flags &= ~IAVF_FLAG_SETUP_NETDEV_FEATURES; + } if ((adapter->flags & (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED)) || adapter->state == __IAVF_RESETTING) @@ -3259,6 +3362,13 @@ static int iavf_open(struct net_device *netdev) goto err_unlock; } + if (adapter->state == __IAVF_RUNNING && + !test_bit(__IAVF_VSI_DOWN, adapter->vsi.state)) { + dev_dbg(&adapter->pdev->dev, "VF is already open.\n"); + err = 0; + goto err_unlock; + } + /* allocate transmit descriptors */ err = iavf_setup_all_tx_resources(adapter); if (err) @@ -3322,18 +3432,19 @@ static int iavf_close(struct net_device *netdev) struct iavf_adapter *adapter = netdev_priv(netdev); int status; - if (adapter->state <= __IAVF_DOWN_PENDING) - return 0; + mutex_lock(&adapter->crit_lock); - while (!mutex_trylock(&adapter->crit_lock)) - usleep_range(500, 1000); + if (adapter->state <= __IAVF_DOWN_PENDING) { + mutex_unlock(&adapter->crit_lock); + return 0; + } set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); if (CLIENT_ENABLED(adapter)) adapter->flags |= IAVF_FLAG_CLIENT_NEEDS_CLOSE; iavf_down(adapter); - adapter->state = __IAVF_DOWN_PENDING; + iavf_change_state(adapter, __IAVF_DOWN_PENDING); iavf_free_traffic_irqs(adapter); mutex_unlock(&adapter->crit_lock); @@ -3373,8 +3484,11 @@ static int iavf_change_mtu(struct net_device *netdev, int new_mtu) iavf_notify_client_l2_params(&adapter->vsi); adapter->flags |= IAVF_FLAG_SERVICE_CLIENT_REQUESTED; } - adapter->flags |= IAVF_FLAG_RESET_NEEDED; - queue_work(iavf_wq, &adapter->reset_task); + + if (netif_running(netdev)) { + adapter->flags |= IAVF_FLAG_RESET_NEEDED; + queue_work(iavf_wq, &adapter->reset_task); + } return 0; } @@ -3673,71 +3787,13 @@ int iavf_process_config(struct iavf_adapter *adapter) } /** - * iavf_init_task - worker thread to perform delayed initialization - * @work: pointer to work_struct containing our data - * - * This task completes the work that was begun in probe. Due to the nature - * of VF-PF communications, we may need to wait tens of milliseconds to get - * responses back from the PF. Rather than busy-wait in probe and bog down the - * whole system, we'll do it in a task so we can sleep. - * This task only runs during driver init. Once we've established - * communications with the PF driver and set up our netdev, the watchdog - * takes over. - **/ -static void iavf_init_task(struct work_struct *work) -{ - struct iavf_adapter *adapter = container_of(work, - struct iavf_adapter, - init_task.work); - struct iavf_hw *hw = &adapter->hw; - - if (iavf_lock_timeout(&adapter->crit_lock, 5000)) { - dev_warn(&adapter->pdev->dev, "failed to acquire crit_lock in %s\n", __FUNCTION__); - return; - } - switch (adapter->state) { - case __IAVF_STARTUP: - if (iavf_startup(adapter) < 0) - goto init_failed; - break; - case __IAVF_INIT_VERSION_CHECK: - if (iavf_init_version_check(adapter) < 0) - goto init_failed; - break; - case __IAVF_INIT_GET_RESOURCES: - if (iavf_init_get_resources(adapter) < 0) - goto init_failed; - goto out; - default: - goto init_failed; - } - - queue_delayed_work(iavf_wq, &adapter->init_task, - msecs_to_jiffies(30)); - goto out; -init_failed: - if (++adapter->aq_wait_count > IAVF_AQ_MAX_ERR) { - dev_err(&adapter->pdev->dev, - "Failed to communicate with PF; waiting before retry\n"); - adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED; - iavf_shutdown_adminq(hw); - adapter->state = __IAVF_STARTUP; - queue_delayed_work(iavf_wq, &adapter->init_task, HZ * 5); - goto out; - } - queue_delayed_work(iavf_wq, &adapter->init_task, HZ); -out: - mutex_unlock(&adapter->crit_lock); -} - -/** * iavf_shutdown - Shutdown the device in preparation for a reboot * @pdev: pci device structure **/ static void iavf_shutdown(struct pci_dev *pdev) { - struct net_device *netdev = pci_get_drvdata(pdev); - struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = iavf_pdev_to_adapter(pdev); + struct net_device *netdev = adapter->netdev; netif_device_detach(netdev); @@ -3747,7 +3803,7 @@ static void iavf_shutdown(struct pci_dev *pdev) if (iavf_lock_timeout(&adapter->crit_lock, 5000)) dev_warn(&adapter->pdev->dev, "failed to acquire crit_lock in %s\n", __FUNCTION__); /* Prevent the watchdog from running. */ - adapter->state = __IAVF_REMOVE; + iavf_change_state(adapter, __IAVF_REMOVE); adapter->aq_required = 0; mutex_unlock(&adapter->crit_lock); @@ -3820,7 +3876,7 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw->back = adapter; adapter->msg_enable = BIT(DEFAULT_DEBUG_LEVEL_SHIFT) - 1; - adapter->state = __IAVF_STARTUP; + iavf_change_state(adapter, __IAVF_STARTUP); /* Call save state here because it relies on the adapter struct. */ pci_save_state(pdev); @@ -3845,7 +3901,6 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) */ mutex_init(&adapter->crit_lock); mutex_init(&adapter->client_lock); - mutex_init(&adapter->remove_lock); mutex_init(&hw->aq.asq_mutex); mutex_init(&hw->aq.arq_mutex); @@ -3864,8 +3919,7 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) INIT_WORK(&adapter->adminq_task, iavf_adminq_task); INIT_DELAYED_WORK(&adapter->watchdog_task, iavf_watchdog_task); INIT_DELAYED_WORK(&adapter->client_task, iavf_client_task); - INIT_DELAYED_WORK(&adapter->init_task, iavf_init_task); - queue_delayed_work(iavf_wq, &adapter->init_task, + queue_delayed_work(iavf_wq, &adapter->watchdog_task, msecs_to_jiffies(5 * (pdev->devfn & 0x07))); /* Setup the wait queue for indicating transition to down status */ @@ -3922,10 +3976,11 @@ static int __maybe_unused iavf_suspend(struct device *dev_d) static int __maybe_unused iavf_resume(struct device *dev_d) { struct pci_dev *pdev = to_pci_dev(dev_d); - struct net_device *netdev = pci_get_drvdata(pdev); - struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter; u32 err; + adapter = iavf_pdev_to_adapter(pdev); + pci_set_master(pdev); rtnl_lock(); @@ -3944,7 +3999,7 @@ static int __maybe_unused iavf_resume(struct device *dev_d) queue_work(iavf_wq, &adapter->reset_task); - netif_device_attach(netdev); + netif_device_attach(adapter->netdev); return err; } @@ -3960,8 +4015,8 @@ static int __maybe_unused iavf_resume(struct device *dev_d) **/ static void iavf_remove(struct pci_dev *pdev) { - struct net_device *netdev = pci_get_drvdata(pdev); - struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = iavf_pdev_to_adapter(pdev); + struct net_device *netdev = adapter->netdev; struct iavf_fdir_fltr *fdir, *fdirtmp; struct iavf_vlan_filter *vlf, *vlftmp; struct iavf_adv_rss *rss, *rsstmp; @@ -3969,14 +4024,37 @@ static void iavf_remove(struct pci_dev *pdev) struct iavf_cloud_filter *cf, *cftmp; struct iavf_hw *hw = &adapter->hw; int err; - /* Indicate we are in remove and not to run reset_task */ - mutex_lock(&adapter->remove_lock); - cancel_delayed_work_sync(&adapter->init_task); - cancel_work_sync(&adapter->reset_task); - cancel_delayed_work_sync(&adapter->client_task); + + /* When reboot/shutdown is in progress no need to do anything + * as the adapter is already REMOVE state that was set during + * iavf_shutdown() callback. + */ + if (adapter->state == __IAVF_REMOVE) + return; + + set_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section); + /* Wait until port initialization is complete. + * There are flows where register/unregister netdev may race. + */ + while (1) { + mutex_lock(&adapter->crit_lock); + if (adapter->state == __IAVF_RUNNING || + adapter->state == __IAVF_DOWN || + adapter->state == __IAVF_INIT_FAILED) { + mutex_unlock(&adapter->crit_lock); + break; + } + + mutex_unlock(&adapter->crit_lock); + usleep_range(500, 1000); + } + cancel_delayed_work_sync(&adapter->watchdog_task); + if (adapter->netdev_registered) { - unregister_netdev(netdev); + rtnl_lock(); + unregister_netdevice(netdev); adapter->netdev_registered = false; + rtnl_unlock(); } if (CLIENT_ALLOWED(adapter)) { err = iavf_lan_del_device(adapter); @@ -3985,6 +4063,10 @@ static void iavf_remove(struct pci_dev *pdev) err); } + mutex_lock(&adapter->crit_lock); + dev_info(&adapter->pdev->dev, "Remove device\n"); + iavf_change_state(adapter, __IAVF_REMOVE); + iavf_request_reset(adapter); msleep(50); /* If the FW isn't responding, kick it once, but only once. */ @@ -3992,24 +4074,24 @@ static void iavf_remove(struct pci_dev *pdev) iavf_request_reset(adapter); msleep(50); } - if (iavf_lock_timeout(&adapter->crit_lock, 5000)) - dev_warn(&adapter->pdev->dev, "failed to acquire crit_lock in %s\n", __FUNCTION__); + iavf_misc_irq_disable(adapter); /* Shut down all the garbage mashers on the detention level */ - adapter->state = __IAVF_REMOVE; + cancel_work_sync(&adapter->reset_task); + cancel_delayed_work_sync(&adapter->watchdog_task); + cancel_work_sync(&adapter->adminq_task); + cancel_delayed_work_sync(&adapter->client_task); + adapter->aq_required = 0; adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; + iavf_free_all_tx_resources(adapter); iavf_free_all_rx_resources(adapter); - iavf_misc_irq_disable(adapter); iavf_free_misc_irq(adapter); + iavf_reset_interrupt_capability(adapter); iavf_free_q_vectors(adapter); - cancel_delayed_work_sync(&adapter->watchdog_task); - - cancel_work_sync(&adapter->adminq_task); - iavf_free_rss(adapter); if (hw->aq.asq.count) @@ -4021,8 +4103,6 @@ static void iavf_remove(struct pci_dev *pdev) mutex_destroy(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); mutex_destroy(&adapter->crit_lock); - mutex_unlock(&adapter->remove_lock); - mutex_destroy(&adapter->remove_lock); iounmap(hw->hw_addr); pci_release_regions(pdev); diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 08302ab35d68..7013769fc038 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -1461,6 +1461,22 @@ void iavf_request_reset(struct iavf_adapter *adapter) } /** + * iavf_netdev_features_vlan_strip_set - update vlan strip status + * @netdev: ptr to netdev being adjusted + * @enable: enable or disable vlan strip + * + * Helper function to change vlan strip status in netdev->features. + */ +static void iavf_netdev_features_vlan_strip_set(struct net_device *netdev, + const bool enable) +{ + if (enable) + netdev->features |= NETIF_F_HW_VLAN_CTAG_RX; + else + netdev->features &= ~NETIF_F_HW_VLAN_CTAG_RX; +} + +/** * iavf_virtchnl_completion * @adapter: adapter structure * @v_opcode: opcode sent by PF @@ -1683,8 +1699,18 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, } break; case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING: + dev_warn(&adapter->pdev->dev, "Changing VLAN Stripping is not allowed when Port VLAN is configured\n"); + /* Vlan stripping could not be enabled by ethtool. + * Disable it in netdev->features. + */ + iavf_netdev_features_vlan_strip_set(netdev, false); + break; case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING: dev_warn(&adapter->pdev->dev, "Changing VLAN Stripping is not allowed when Port VLAN is configured\n"); + /* Vlan stripping could not be disabled by ethtool. + * Enable it in netdev->features. + */ + iavf_netdev_features_vlan_strip_set(netdev, true); break; default: dev_err(&adapter->pdev->dev, "PF returned error %d (%s) to our request %d\n", @@ -1752,19 +1778,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, spin_unlock_bh(&adapter->mac_vlan_list_lock); iavf_process_config(adapter); - - /* unlock crit_lock before acquiring rtnl_lock as other - * processes holding rtnl_lock could be waiting for the same - * crit_lock - */ - mutex_unlock(&adapter->crit_lock); - rtnl_lock(); - netdev_update_features(adapter->netdev); - rtnl_unlock(); - if (iavf_lock_timeout(&adapter->crit_lock, 10000)) - dev_warn(&adapter->pdev->dev, "failed to acquire crit_lock in %s\n", - __FUNCTION__); - + adapter->flags |= IAVF_FLAG_SETUP_NETDEV_FEATURES; } break; case VIRTCHNL_OP_ENABLE_QUEUES: @@ -1776,7 +1790,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, iavf_free_all_tx_resources(adapter); iavf_free_all_rx_resources(adapter); if (adapter->state == __IAVF_DOWN_PENDING) { - adapter->state = __IAVF_DOWN; + iavf_change_state(adapter, __IAVF_DOWN); wake_up(&adapter->down_waitqueue); } break; @@ -1930,6 +1944,20 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, spin_unlock_bh(&adapter->adv_rss_lock); } break; + case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING: + /* PF enabled vlan strip on this VF. + * Update netdev->features if needed to be in sync with ethtool. + */ + if (!v_retval) + iavf_netdev_features_vlan_strip_set(netdev, true); + break; + case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING: + /* PF disabled vlan strip on this VF. + * Update netdev->features if needed to be in sync with ethtool. + */ + if (!v_retval) + iavf_netdev_features_vlan_strip_set(netdev, false); + break; default: if (adapter->current_op && (v_opcode != adapter->current_op)) dev_warn(&adapter->pdev->dev, "Expected response %d from PF, received %d\n", diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index d119812755b7..df65bb494695 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -231,7 +231,6 @@ enum ice_pf_state { ICE_VFLR_EVENT_PENDING, ICE_FLTR_OVERFLOW_PROMISC, ICE_VF_DIS, - ICE_VF_DEINIT_IN_PROGRESS, ICE_CFG_BUSY, ICE_SERVICE_SCHED, ICE_SERVICE_DIS, @@ -242,6 +241,7 @@ enum ice_pf_state { ICE_LINK_DEFAULT_OVERRIDE_PENDING, ICE_PHY_INIT_COMPLETE, ICE_FD_VF_FLUSH_CTX, /* set at FD Rx IRQ or timeout */ + ICE_AUX_ERR_PENDING, ICE_STATE_NBITS /* must be last */ }; @@ -399,6 +399,7 @@ enum ice_pf_flags { ICE_FLAG_MDD_AUTO_RESET_VF, ICE_FLAG_LINK_LENIENT_MODE_ENA, ICE_FLAG_PLUG_AUX_DEV, + ICE_FLAG_MTU_CHANGED, ICE_PF_FLAGS_NBITS /* must be last */ }; @@ -464,6 +465,7 @@ struct ice_pf { wait_queue_head_t reset_wait_queue; u32 hw_csum_rx_error; + u32 oicr_err_reg; u16 oicr_idx; /* Other interrupt cause MSIX vector index */ u16 num_avail_sw_msix; /* remaining MSIX SW vectors left unclaimed */ u16 max_pf_txqs; /* Total Tx queues PF wide */ @@ -550,7 +552,7 @@ static inline struct ice_pf *ice_netdev_to_pf(struct net_device *netdev) static inline bool ice_is_xdp_ena_vsi(struct ice_vsi *vsi) { - return !!vsi->xdp_prog; + return !!READ_ONCE(vsi->xdp_prog); } static inline void ice_set_ring_xdp(struct ice_ring *ring) @@ -703,7 +705,16 @@ static inline void ice_set_rdma_cap(struct ice_pf *pf) */ static inline void ice_clear_rdma_cap(struct ice_pf *pf) { - ice_unplug_aux_dev(pf); + /* We can directly unplug aux device here only if the flag bit + * ICE_FLAG_PLUG_AUX_DEV is not set because ice_unplug_aux_dev() + * could race with ice_plug_aux_dev() called from + * ice_service_task(). In this case we only clear that bit now and + * aux device will be unplugged later once ice_plug_aux_device() + * called from ice_service_task() finishes (see ice_service_task()). + */ + if (!test_and_clear_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags)) + ice_unplug_aux_dev(pf); + clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); clear_bit(ICE_FLAG_AUX_ENA, pf->flags); } diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index f4463e962d52..3de6f16f985a 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -3270,7 +3270,7 @@ ice_cfg_phy_fec(struct ice_port_info *pi, struct ice_aqc_set_phy_cfg_data *cfg, if (fec == ICE_FEC_AUTO && ice_fw_supports_link_override(hw) && !ice_fw_supports_report_dflt_cfg(hw)) { - struct ice_link_default_override_tlv tlv; + struct ice_link_default_override_tlv tlv = { 0 }; status = ice_get_link_default_override(&tlv, pi); if (status) diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index c451cf401e63..38c2d9a5574a 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -2275,7 +2275,7 @@ ice_set_link_ksettings(struct net_device *netdev, goto done; } - curr_link_speed = pi->phy.link_info.link_speed; + curr_link_speed = pi->phy.curr_user_speed_req; adv_link_speed = ice_ksettings_find_adv_link_speed(ks); /* If speed didn't get set, set it to what it currently is. diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c index adcc9a251595..a2714988dd96 100644 --- a/drivers/net/ethernet/intel/ice/ice_idc.c +++ b/drivers/net/ethernet/intel/ice/ice_idc.c @@ -34,6 +34,9 @@ void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_event *event) { struct iidc_auxiliary_drv *iadrv; + if (WARN_ON_ONCE(!in_task())) + return; + if (!pf->adev) return; diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 62bf879dc623..653996e8fd30 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -1306,6 +1306,7 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) ring->tx_tstamps = &pf->ptp.port.tx; ring->dev = dev; ring->count = vsi->num_tx_desc; + ring->txq_teid = ICE_INVAL_TEID; WRITE_ONCE(vsi->tx_rings[i], ring); } @@ -1521,6 +1522,12 @@ static void ice_vsi_set_rss_flow_fld(struct ice_vsi *vsi) if (status) dev_dbg(dev, "ice_add_rss_cfg failed for sctp6 flow, vsi = %d, error = %s\n", vsi_num, ice_stat_str(status)); + + status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_ESP_SPI, + ICE_FLOW_SEG_HDR_ESP); + if (status) + dev_dbg(dev, "ice_add_rss_cfg failed for esp/spi flow, vsi = %d, error = %d\n", + vsi_num, status); } /** @@ -2917,6 +2924,8 @@ int ice_vsi_release(struct ice_vsi *vsi) } } + if (ice_is_vsi_dflt_vsi(pf->first_sw, vsi)) + ice_clear_dflt_vsi(pf->first_sw); ice_fltr_remove_all(vsi); ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx); err = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index ab2dea0d2c1a..f330bd0acf9f 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -1679,7 +1679,9 @@ static void ice_handle_mdd_event(struct ice_pf *pf) * reset, so print the event prior to reset. */ ice_print_vf_rx_mdd_event(vf); + mutex_lock(&pf->vf[i].cfg_lock); ice_reset_vf(&pf->vf[i], false); + mutex_unlock(&pf->vf[i].cfg_lock); } } } @@ -2141,9 +2143,43 @@ static void ice_service_task(struct work_struct *work) return; } - if (test_and_clear_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags)) + if (test_and_clear_bit(ICE_AUX_ERR_PENDING, pf->state)) { + struct iidc_event *event; + + event = kzalloc(sizeof(*event), GFP_KERNEL); + if (event) { + set_bit(IIDC_EVENT_CRIT_ERR, event->type); + /* report the entire OICR value to AUX driver */ + swap(event->reg, pf->oicr_err_reg); + ice_send_event_to_aux(pf, event); + kfree(event); + } + } + + if (test_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags)) { + /* Plug aux device per request */ ice_plug_aux_dev(pf); + /* Mark plugging as done but check whether unplug was + * requested during ice_plug_aux_dev() call + * (e.g. from ice_clear_rdma_cap()) and if so then + * plug aux device. + */ + if (!test_and_clear_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags)) + ice_unplug_aux_dev(pf); + } + + if (test_and_clear_bit(ICE_FLAG_MTU_CHANGED, pf->flags)) { + struct iidc_event *event; + + event = kzalloc(sizeof(*event), GFP_KERNEL); + if (event) { + set_bit(IIDC_EVENT_AFTER_MTU_CHANGE, event->type); + ice_send_event_to_aux(pf, event); + kfree(event); + } + } + ice_clean_adminq_subtask(pf); ice_check_media_subtask(pf); ice_check_for_hang_subtask(pf); @@ -2576,8 +2612,10 @@ free_qmap: for (i = 0; i < vsi->num_xdp_txq; i++) if (vsi->xdp_rings[i]) { - if (vsi->xdp_rings[i]->desc) + if (vsi->xdp_rings[i]->desc) { + synchronize_rcu(); ice_free_tx_ring(vsi->xdp_rings[i]); + } kfree_rcu(vsi->xdp_rings[i], rcu); vsi->xdp_rings[i] = NULL; } @@ -2858,17 +2896,9 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) #define ICE_AUX_CRIT_ERR (PFINT_OICR_PE_CRITERR_M | PFINT_OICR_HMC_ERR_M | PFINT_OICR_PE_PUSH_M) if (oicr & ICE_AUX_CRIT_ERR) { - struct iidc_event *event; - + pf->oicr_err_reg |= oicr; + set_bit(ICE_AUX_ERR_PENDING, pf->state); ena_mask &= ~ICE_AUX_CRIT_ERR; - event = kzalloc(sizeof(*event), GFP_KERNEL); - if (event) { - set_bit(IIDC_EVENT_CRIT_ERR, event->type); - /* report the entire OICR value to AUX driver */ - event->reg = oicr; - ice_send_event_to_aux(pf, event); - kfree(event); - } } /* Report any remaining unexpected interrupts */ @@ -6530,7 +6560,6 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; - struct iidc_event *event; u8 count = 0; int err = 0; @@ -6565,14 +6594,6 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) return -EBUSY; } - event = kzalloc(sizeof(*event), GFP_KERNEL); - if (!event) - return -ENOMEM; - - set_bit(IIDC_EVENT_BEFORE_MTU_CHANGE, event->type); - ice_send_event_to_aux(pf, event); - clear_bit(IIDC_EVENT_BEFORE_MTU_CHANGE, event->type); - netdev->mtu = (unsigned int)new_mtu; /* if VSI is up, bring it down and then back up */ @@ -6580,21 +6601,18 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) err = ice_down(vsi); if (err) { netdev_err(netdev, "change MTU if_down err %d\n", err); - goto event_after; + return err; } err = ice_up(vsi); if (err) { netdev_err(netdev, "change MTU if_up err %d\n", err); - goto event_after; + return err; } } netdev_dbg(netdev, "changed MTU to %d\n", new_mtu); -event_after: - set_bit(IIDC_EVENT_AFTER_MTU_CHANGE, event->type); - ice_send_event_to_aux(pf, event); - kfree(event); + set_bit(ICE_FLAG_MTU_CHANGED, pf->flags); return err; } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index ac27a4fe8b94..eb9193682579 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -846,9 +846,12 @@ exit: static int ice_ptp_adjtime_nonatomic(struct ptp_clock_info *info, s64 delta) { struct timespec64 now, then; + int ret; then = ns_to_timespec64(delta); - ice_ptp_gettimex64(info, &now, NULL); + ret = ice_ptp_gettimex64(info, &now, NULL); + if (ret) + return ret; now = timespec64_add(now, then); return ice_ptp_settime64(info, (const struct timespec64 *)&now); diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index a78e8f00cf71..9d4d58757e04 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -615,8 +615,6 @@ void ice_free_vfs(struct ice_pf *pf) struct ice_hw *hw = &pf->hw; unsigned int tmp, i; - set_bit(ICE_VF_DEINIT_IN_PROGRESS, pf->state); - if (!pf->vf) return; @@ -632,20 +630,26 @@ void ice_free_vfs(struct ice_pf *pf) else dev_warn(dev, "VFs are assigned - not disabling SR-IOV\n"); - /* Avoid wait time by stopping all VFs at the same time */ - ice_for_each_vf(pf, i) - ice_dis_vf_qs(&pf->vf[i]); - tmp = pf->num_alloc_vfs; pf->num_qps_per_vf = 0; pf->num_alloc_vfs = 0; for (i = 0; i < tmp; i++) { - if (test_bit(ICE_VF_STATE_INIT, pf->vf[i].vf_states)) { + struct ice_vf *vf = &pf->vf[i]; + + mutex_lock(&vf->cfg_lock); + + ice_dis_vf_qs(vf); + + if (test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { /* disable VF qp mappings and set VF disable state */ - ice_dis_vf_mappings(&pf->vf[i]); - set_bit(ICE_VF_STATE_DIS, pf->vf[i].vf_states); - ice_free_vf_res(&pf->vf[i]); + ice_dis_vf_mappings(vf); + set_bit(ICE_VF_STATE_DIS, vf->vf_states); + ice_free_vf_res(vf); } + + mutex_unlock(&vf->cfg_lock); + + mutex_destroy(&vf->cfg_lock); } if (ice_sriov_free_msix_res(pf)) @@ -681,7 +685,6 @@ void ice_free_vfs(struct ice_pf *pf) i); clear_bit(ICE_VF_DIS, pf->state); - clear_bit(ICE_VF_DEINIT_IN_PROGRESS, pf->state); clear_bit(ICE_FLAG_SRIOV_ENA, pf->flags); } @@ -1565,6 +1568,8 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr) ice_for_each_vf(pf, v) { vf = &pf->vf[v]; + mutex_lock(&vf->cfg_lock); + vf->driver_caps = 0; ice_vc_set_default_allowlist(vf); @@ -1579,6 +1584,8 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr) ice_vf_pre_vsi_rebuild(vf); ice_vf_rebuild_vsi(vf); ice_vf_post_vsi_rebuild(vf); + + mutex_unlock(&vf->cfg_lock); } ice_flush(hw); @@ -1625,6 +1632,8 @@ bool ice_reset_vf(struct ice_vf *vf, bool is_vflr) u32 reg; int i; + lockdep_assert_held(&vf->cfg_lock); + dev = ice_pf_to_dev(pf); if (test_bit(ICE_VF_RESETS_DISABLED, pf->state)) { @@ -1894,6 +1903,8 @@ static void ice_set_dflt_settings_vfs(struct ice_pf *pf) */ ice_vf_ctrl_invalidate_vsi(vf); ice_vf_fdir_init(vf); + + mutex_init(&vf->cfg_lock); } } @@ -2109,9 +2120,12 @@ void ice_process_vflr_event(struct ice_pf *pf) bit_idx = (hw->func_caps.vf_base_id + vf_id) % 32; /* read GLGEN_VFLRSTAT register to find out the flr VFs */ reg = rd32(hw, GLGEN_VFLRSTAT(reg_idx)); - if (reg & BIT(bit_idx)) + if (reg & BIT(bit_idx)) { /* GLGEN_VFLRSTAT bit will be cleared in ice_reset_vf */ + mutex_lock(&vf->cfg_lock); ice_reset_vf(vf, true); + mutex_unlock(&vf->cfg_lock); + } } } @@ -2188,7 +2202,9 @@ ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event) if (!vf) return; + mutex_lock(&vf->cfg_lock); ice_vc_reset_vf(vf); + mutex_unlock(&vf->cfg_lock); } /** @@ -2218,24 +2234,6 @@ ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode, dev = ice_pf_to_dev(pf); - /* single place to detect unsuccessful return values */ - if (v_retval) { - vf->num_inval_msgs++; - dev_info(dev, "VF %d failed opcode %d, retval: %d\n", vf->vf_id, - v_opcode, v_retval); - if (vf->num_inval_msgs > ICE_DFLT_NUM_INVAL_MSGS_ALLOWED) { - dev_err(dev, "Number of invalid messages exceeded for VF %d\n", - vf->vf_id); - dev_err(dev, "Use PF Control I/F to enable the VF\n"); - set_bit(ICE_VF_STATE_DIS, vf->vf_states); - return -EIO; - } - } else { - vf->num_valid_msgs++; - /* reset the invalid counter, if a valid message is received. */ - vf->num_inval_msgs = 0; - } - aq_ret = ice_aq_send_msg_to_vf(&pf->hw, vf->vf_id, v_opcode, v_retval, msg, msglen, NULL); if (aq_ret && pf->hw.mailboxq.sq_last_status != ICE_AQ_RC_ENOSYS) { @@ -3337,9 +3335,9 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) goto error_param; } - /* Skip queue if not enabled */ if (!test_bit(vf_q_id, vf->txq_ena)) - continue; + dev_dbg(ice_pf_to_dev(vsi->back), "Queue %u on VSI %u is not enabled, but stopping it anyway\n", + vf_q_id, vsi->vsi_num); ice_fill_txq_meta(vsi, ring, &txq_meta); @@ -4082,6 +4080,8 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, return 0; } + mutex_lock(&vf->cfg_lock); + vf->port_vlan_info = vlanprio; if (vf->port_vlan_info) @@ -4091,6 +4091,7 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, dev_info(dev, "Clearing port VLAN on VF %d\n", vf_id); ice_vc_reset_vf(vf); + mutex_unlock(&vf->cfg_lock); return 0; } @@ -4422,10 +4423,6 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) struct device *dev; int err = 0; - /* if de-init is underway, don't process messages from VF */ - if (test_bit(ICE_VF_DEINIT_IN_PROGRESS, pf->state)) - return; - dev = ice_pf_to_dev(pf); if (ice_validate_vf_id(pf, vf_id)) { err = -EINVAL; @@ -4465,6 +4462,15 @@ error_handler: return; } + /* VF is being configured in another context that triggers a VFR, so no + * need to process this message + */ + if (!mutex_trylock(&vf->cfg_lock)) { + dev_info(dev, "VF %u is being configured in another context that will trigger a VFR, so there is no need to handle this message\n", + vf->vf_id); + return; + } + switch (v_opcode) { case VIRTCHNL_OP_VERSION: err = ice_vc_get_ver_msg(vf, msg); @@ -4553,6 +4559,8 @@ error_handler: dev_info(dev, "PF failed to honor VF %d, opcode %d, error %d\n", vf_id, v_opcode, err); } + + mutex_unlock(&vf->cfg_lock); } /** @@ -4668,6 +4676,8 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) return -EINVAL; } + mutex_lock(&vf->cfg_lock); + /* VF is notified of its new MAC via the PF's response to the * VIRTCHNL_OP_GET_VF_RESOURCES message after the VF has been reset */ @@ -4686,6 +4696,7 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) } ice_vc_reset_vf(vf); + mutex_unlock(&vf->cfg_lock); return 0; } @@ -4715,11 +4726,15 @@ int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted) if (trusted == vf->trusted) return 0; + mutex_lock(&vf->cfg_lock); + vf->trusted = trusted; ice_vc_reset_vf(vf); dev_info(ice_pf_to_dev(pf), "VF %u is now %strusted\n", vf_id, trusted ? "" : "un"); + mutex_unlock(&vf->cfg_lock); + return 0; } diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h index 38b4dc82c5c1..532f57f01467 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h @@ -14,7 +14,6 @@ #define ICE_MAX_MACADDR_PER_VF 18 /* Malicious Driver Detection */ -#define ICE_DFLT_NUM_INVAL_MSGS_ALLOWED 10 #define ICE_MDD_EVENTS_THRESHOLD 30 /* Static VF transaction/status register def */ @@ -74,6 +73,11 @@ struct ice_mdd_vf_events { struct ice_vf { struct ice_pf *pf; + /* Used during virtchnl message handling and NDO ops against the VF + * that will trigger a VFR + */ + struct mutex cfg_lock; + u16 vf_id; /* VF ID in the PF space */ u16 lan_vsi_idx; /* index into PF struct */ u16 ctrl_vsi_idx; @@ -102,8 +106,6 @@ struct ice_vf { unsigned int tx_rate; /* Tx bandwidth limit in Mbps */ DECLARE_BITMAP(vf_states, ICE_VF_STATES_NBITS); /* VF runtime states */ - u64 num_inval_msgs; /* number of continuous invalid msgs */ - u64 num_valid_msgs; /* number of valid msgs detected */ unsigned long vf_caps; /* VF's adv. capabilities */ u8 num_req_qs; /* num of queue pairs requested by VF */ u16 num_mac; diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 37c7dc6b44a9..2b1873061912 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -36,8 +36,10 @@ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx) static void ice_qp_clean_rings(struct ice_vsi *vsi, u16 q_idx) { ice_clean_tx_ring(vsi->tx_rings[q_idx]); - if (ice_is_xdp_ena_vsi(vsi)) + if (ice_is_xdp_ena_vsi(vsi)) { + synchronize_rcu(); ice_clean_tx_ring(vsi->xdp_rings[q_idx]); + } ice_clean_rx_ring(vsi->rx_rings[q_idx]); } @@ -759,7 +761,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, struct ice_vsi *vsi = np->vsi; struct ice_ring *ring; - if (test_bit(ICE_DOWN, vsi->state)) + if (test_bit(ICE_VSI_DOWN, vsi->state)) return -ENETDOWN; if (!ice_is_xdp_ena_vsi(vsi)) diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index fb1029352c3e..3cbb5a89b336 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -961,10 +961,6 @@ static int igb_set_ringparam(struct net_device *netdev, memcpy(&temp_ring[i], adapter->rx_ring[i], sizeof(struct igb_ring)); - /* Clear copied XDP RX-queue info */ - memset(&temp_ring[i].xdp_rxq, 0, - sizeof(temp_ring[i].xdp_rxq)); - temp_ring[i].count = new_rx_count; err = igb_setup_rx_resources(&temp_ring[i]); if (err) { diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 82a712f77cb3..bf8ef81f6c0e 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -4345,7 +4345,18 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring) { struct igb_adapter *adapter = netdev_priv(rx_ring->netdev); struct device *dev = rx_ring->dev; - int size; + int size, res; + + /* XDP RX-queue info */ + if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); + res = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, + rx_ring->queue_index, 0); + if (res < 0) { + dev_err(dev, "Failed to register xdp_rxq index %u\n", + rx_ring->queue_index); + return res; + } size = sizeof(struct igb_rx_buffer) * rx_ring->count; @@ -4368,14 +4379,10 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring) rx_ring->xdp_prog = adapter->xdp_prog; - /* XDP RX-queue info */ - if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, - rx_ring->queue_index, 0) < 0) - goto err; - return 0; err: + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); vfree(rx_ring->rx_buffer_info); rx_ring->rx_buffer_info = NULL; dev_err(dev, "Unable to allocate memory for the Rx descriptor ring\n"); diff --git a/drivers/net/ethernet/intel/igc/igc_i225.c b/drivers/net/ethernet/intel/igc/igc_i225.c index b6807e16eea9..a0e2a404d535 100644 --- a/drivers/net/ethernet/intel/igc/igc_i225.c +++ b/drivers/net/ethernet/intel/igc/igc_i225.c @@ -156,8 +156,15 @@ void igc_release_swfw_sync_i225(struct igc_hw *hw, u16 mask) { u32 swfw_sync; - while (igc_get_hw_semaphore_i225(hw)) - ; /* Empty */ + /* Releasing the resource requires first getting the HW semaphore. + * If we fail to get the semaphore, there is nothing we can do, + * except log an error and quit. We are not allowed to hang here + * indefinitely, as it may cause denial of service or system crash. + */ + if (igc_get_hw_semaphore_i225(hw)) { + hw_dbg("Failed to release SW_FW_SYNC.\n"); + return; + } swfw_sync = rd32(IGC_SW_FW_SYNC); swfw_sync &= ~mask; diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index c7fa978cdf02..f99819fc559d 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -504,6 +504,9 @@ int igc_setup_rx_resources(struct igc_ring *rx_ring) u8 index = rx_ring->queue_index; int size, desc_len, res; + /* XDP RX-queue info */ + if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); res = xdp_rxq_info_reg(&rx_ring->xdp_rxq, ndev, index, rx_ring->q_vector->napi.napi_id); if (res < 0) { @@ -2434,19 +2437,20 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) static struct sk_buff *igc_construct_skb_zc(struct igc_ring *ring, struct xdp_buff *xdp) { + unsigned int totalsize = xdp->data_end - xdp->data_meta; unsigned int metasize = xdp->data - xdp->data_meta; - unsigned int datasize = xdp->data_end - xdp->data; - unsigned int totalsize = metasize + datasize; struct sk_buff *skb; - skb = __napi_alloc_skb(&ring->q_vector->napi, - xdp->data_end - xdp->data_hard_start, + net_prefetch(xdp->data_meta); + + skb = __napi_alloc_skb(&ring->q_vector->napi, totalsize, GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL; - skb_reserve(skb, xdp->data_meta - xdp->data_hard_start); - memcpy(__skb_put(skb, totalsize), xdp->data_meta, totalsize); + memcpy(__skb_put(skb, totalsize), xdp->data_meta, + ALIGN(totalsize, sizeof(long))); + if (metasize) { skb_metadata_set(skb, metasize); __skb_pull(skb, metasize); diff --git a/drivers/net/ethernet/intel/igc/igc_phy.c b/drivers/net/ethernet/intel/igc/igc_phy.c index 5cad31c3c7b0..6961f65d36b9 100644 --- a/drivers/net/ethernet/intel/igc/igc_phy.c +++ b/drivers/net/ethernet/intel/igc/igc_phy.c @@ -581,7 +581,7 @@ static s32 igc_read_phy_reg_mdic(struct igc_hw *hw, u32 offset, u16 *data) * the lower time out */ for (i = 0; i < IGC_GEN_POLL_TIMEOUT; i++) { - usleep_range(500, 1000); + udelay(50); mdic = rd32(IGC_MDIC); if (mdic & IGC_MDIC_READY) break; @@ -638,7 +638,7 @@ static s32 igc_write_phy_reg_mdic(struct igc_hw *hw, u32 offset, u16 data) * the lower time out */ for (i = 0; i < IGC_GEN_POLL_TIMEOUT; i++) { - usleep_range(500, 1000); + udelay(50); mdic = rd32(IGC_MDIC); if (mdic & IGC_MDIC_READY) break; @@ -746,8 +746,6 @@ s32 igc_write_phy_reg_gpy(struct igc_hw *hw, u32 offset, u16 data) if (ret_val) return ret_val; ret_val = igc_write_phy_reg_mdic(hw, offset, data); - if (ret_val) - return ret_val; hw->phy.ops.release(hw); } else { ret_val = igc_write_xmdio_reg(hw, (u16)offset, dev_addr, @@ -779,8 +777,6 @@ s32 igc_read_phy_reg_gpy(struct igc_hw *hw, u32 offset, u16 *data) if (ret_val) return ret_val; ret_val = igc_read_phy_reg_mdic(hw, offset, data); - if (ret_val) - return ret_val; hw->phy.ops.release(hw); } else { ret_val = igc_read_xmdio_reg(hw, (u16)offset, dev_addr, diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 4f9245aa79a1..8e521f99b80a 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -996,6 +996,17 @@ static void igc_ptp_time_restore(struct igc_adapter *adapter) igc_ptp_write_i225(adapter, &ts); } +static void igc_ptm_stop(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u32 ctrl; + + ctrl = rd32(IGC_PTM_CTRL); + ctrl &= ~IGC_PTM_CTRL_EN; + + wr32(IGC_PTM_CTRL, ctrl); +} + /** * igc_ptp_suspend - Disable PTP work items and prepare for suspend * @adapter: Board private structure @@ -1013,8 +1024,10 @@ void igc_ptp_suspend(struct igc_adapter *adapter) adapter->ptp_tx_skb = NULL; clear_bit_unlock(__IGC_PTP_TX_IN_PROGRESS, &adapter->state); - if (pci_device_is_present(adapter->pdev)) + if (pci_device_is_present(adapter->pdev)) { igc_ptp_time_save(adapter); + igc_ptm_stop(adapter); + } } /** diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index b1d22e4d5ec9..b399b9c14717 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -201,26 +201,28 @@ bool ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 count) } static struct sk_buff *ixgbe_construct_skb_zc(struct ixgbe_ring *rx_ring, - struct ixgbe_rx_buffer *bi) + const struct xdp_buff *xdp) { - unsigned int metasize = bi->xdp->data - bi->xdp->data_meta; - unsigned int datasize = bi->xdp->data_end - bi->xdp->data; + unsigned int totalsize = xdp->data_end - xdp->data_meta; + unsigned int metasize = xdp->data - xdp->data_meta; struct sk_buff *skb; + net_prefetch(xdp->data_meta); + /* allocate a skb to store the frags */ - skb = __napi_alloc_skb(&rx_ring->q_vector->napi, - bi->xdp->data_end - bi->xdp->data_hard_start, + skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize, GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL; - skb_reserve(skb, bi->xdp->data - bi->xdp->data_hard_start); - memcpy(__skb_put(skb, datasize), bi->xdp->data, datasize); - if (metasize) + memcpy(__skb_put(skb, totalsize), xdp->data_meta, + ALIGN(totalsize, sizeof(long))); + + if (metasize) { skb_metadata_set(skb, metasize); + __skb_pull(skb, metasize); + } - xsk_buff_free(bi->xdp); - bi->xdp = NULL; return skb; } @@ -311,12 +313,15 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector, } /* XDP_PASS path */ - skb = ixgbe_construct_skb_zc(rx_ring, bi); + skb = ixgbe_construct_skb_zc(rx_ring, bi->xdp); if (!skb) { rx_ring->rx_stats.alloc_rx_buff_failed++; break; } + xsk_buff_free(bi->xdp); + bi->xdp = NULL; + cleaned_count++; ixgbe_inc_ntc(rx_ring); @@ -388,12 +393,14 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget) u32 cmd_type; while (budget-- > 0) { - if (unlikely(!ixgbe_desc_unused(xdp_ring)) || - !netif_carrier_ok(xdp_ring->netdev)) { + if (unlikely(!ixgbe_desc_unused(xdp_ring))) { work_done = false; break; } + if (!netif_carrier_ok(xdp_ring->netdev)) + break; + if (!xsk_tx_peek_desc(pool, &desc)) break; |