diff options
Diffstat (limited to 'drivers/net/ethernet/intel')
109 files changed, 11055 insertions, 1662 deletions
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index 5aa86318ed3e..c1d155690341 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -294,6 +294,7 @@ config ICE tristate "Intel(R) Ethernet Connection E800 Series Support" default n depends on PCI_MSI + select DIMLIB select NET_DEVLINK select PLDMFW help diff --git a/drivers/net/ethernet/intel/e1000/e1000_hw.c b/drivers/net/ethernet/intel/e1000/e1000_hw.c index 4c0c9433bd60..19cf36360933 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_hw.c +++ b/drivers/net/ethernet/intel/e1000/e1000_hw.c @@ -1183,6 +1183,7 @@ static s32 e1000_copper_link_igp_setup(struct e1000_hw *hw) break; case e1000_ms_auto: phy_data &= ~CR_1000T_MS_ENABLE; + break; default: break; } diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 0ac8d79a7987..590ad110d383 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -2745,7 +2745,7 @@ release: } /** - * e1000_k1_gig_workaround_lv - K1 Si workaround + * e1000_k1_workaround_lv - K1 Si workaround * @hw: pointer to the HW structure * * Workaround to set the K1 beacon duration for 82579 parts in 10Mbps @@ -5220,7 +5220,7 @@ void e1000e_set_kmrn_lock_loss_workaround_ich8lan(struct e1000_hw *hw, } /** - * e1000_ipg3_phy_powerdown_workaround_ich8lan - Power down workaround on D3 + * e1000e_igp3_phy_powerdown_workaround_ich8lan - Power down workaround on D3 * @hw: pointer to the HW structure * * Workaround for 82566 power-down on D3 entry: diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index a0948002ddf8..88e9035b75cf 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -25,6 +25,7 @@ #include <linux/pm_runtime.h> #include <linux/aer.h> #include <linux/prefetch.h> +#include <linux/suspend.h> #include "e1000.h" @@ -5990,7 +5991,7 @@ static void e1000_reset_task(struct work_struct *work) } /** - * e1000_get_stats64 - Get System Network Statistics + * e1000e_get_stats64 - Get System Network Statistics * @netdev: network interface device structure * @stats: rtnl_link_stats64 pointer * @@ -6163,7 +6164,7 @@ static int e1000_mii_ioctl(struct net_device *netdev, struct ifreq *ifr, } /** - * e1000e_hwtstamp_ioctl - control hardware time stamping + * e1000e_hwtstamp_set - control hardware time stamping * @netdev: network interface device structure * @ifr: interface request * @@ -6821,7 +6822,7 @@ static void e1000e_disable_aspm(struct pci_dev *pdev, u16 state) } /** - * e1000e_disable_aspm_locked Disable ASPM states. + * e1000e_disable_aspm_locked - Disable ASPM states. * @pdev: pointer to PCI device struct * @state: bit-mask of ASPM states to disable * @@ -6922,6 +6923,12 @@ static int __e1000_resume(struct pci_dev *pdev) return 0; } +static __maybe_unused int e1000e_pm_prepare(struct device *dev) +{ + return pm_runtime_suspended(dev) && + pm_suspend_via_firmware(); +} + static __maybe_unused int e1000e_pm_suspend(struct device *dev) { struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev)); @@ -7630,9 +7637,9 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) e1000_print_device_info(adapter); - dev_pm_set_driver_flags(&pdev->dev, DPM_FLAG_NO_DIRECT_COMPLETE); + dev_pm_set_driver_flags(&pdev->dev, DPM_FLAG_SMART_PREPARE); - if (pci_dev_run_wake(pdev) && hw->mac.type < e1000_pch_cnp) + if (pci_dev_run_wake(pdev) && hw->mac.type != e1000_pch_cnp) pm_runtime_put_noidle(&pdev->dev); return 0; @@ -7855,6 +7862,7 @@ MODULE_DEVICE_TABLE(pci, e1000_pci_tbl); static const struct dev_pm_ops e1000_pm_ops = { #ifdef CONFIG_PM_SLEEP + .prepare = e1000e_pm_prepare, .suspend = e1000e_pm_suspend, .resume = e1000e_pm_resume, .freeze = e1000e_pm_freeze, diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c index bdd9dc163f15..1db35b2c7750 100644 --- a/drivers/net/ethernet/intel/e1000e/phy.c +++ b/drivers/net/ethernet/intel/e1000e/phy.c @@ -371,7 +371,7 @@ s32 e1000e_read_phy_reg_igp_locked(struct e1000_hw *hw, u32 offset, u16 *data) } /** - * e1000e_write_phy_reg_igp - Write igp PHY register + * __e1000e_write_phy_reg_igp - Write igp PHY register * @hw: pointer to the HW structure * @offset: register offset to write to * @data: data to write at register offset diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c index f3f671311855..9e79d672f4f1 100644 --- a/drivers/net/ethernet/intel/e1000e/ptp.c +++ b/drivers/net/ethernet/intel/e1000e/ptp.c @@ -142,7 +142,7 @@ static int e1000e_phc_get_syncdevicetime(ktime_t *device, } /** - * e1000e_phc_getsynctime - Reads the current system/device cross timestamp + * e1000e_phc_getcrosststamp - Reads the current system/device cross timestamp * @ptp: ptp clock structure * @xtstamp: structure containing timestamp * diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c b/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c index c45315472245..86397c564dfc 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c @@ -105,7 +105,7 @@ static int fm10k_dcbnl_ieee_setpfc(struct net_device *dev, struct ieee_pfc *pfc) } /** - * fm10k_dcbnl_ieee_getdcbx - get the DCBX configuration for the device + * fm10k_dcbnl_getdcbx - get the DCBX configuration for the device * @dev: netdev interface for the device * * Returns that we support only IEEE DCB for this interface @@ -116,7 +116,7 @@ static u8 fm10k_dcbnl_getdcbx(struct net_device __always_unused *dev) } /** - * fm10k_dcbnl_ieee_setdcbx - get the DCBX configuration for the device + * fm10k_dcbnl_setdcbx - get the DCBX configuration for the device * @dev: netdev interface for the device * @mode: new mode for this device * diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c index 1d27b2fb23af..5c77054d67c6 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c @@ -185,7 +185,7 @@ void fm10k_dbg_q_vector_init(struct fm10k_q_vector *q_vector) } /** - * fm10k_dbg_free_q_vector_dir - setup debugfs for the q_vectors + * fm10k_dbg_q_vector_exit - setup debugfs for the q_vectors * @q_vector: q_vector to allocate directories for **/ void fm10k_dbg_q_vector_exit(struct fm10k_q_vector *q_vector) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 247f44f4cb30..3362f26d7f99 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -1774,7 +1774,7 @@ static void fm10k_free_q_vectors(struct fm10k_intfc *interface) } /** - * f10k_reset_msix_capability - reset MSI-X capability + * fm10k_reset_msix_capability - reset MSI-X capability * @interface: board private structure to initialize * * Reset the MSI-X capability back to its starting state @@ -1787,7 +1787,7 @@ static void fm10k_reset_msix_capability(struct fm10k_intfc *interface) } /** - * f10k_init_msix_capability - configure MSI-X capability + * fm10k_init_msix_capability - configure MSI-X capability * @interface: board private structure to initialize * * Attempt to configure the interrupts using the best available diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c index 8e2e92bf3cd4..30ca9ee1900b 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c @@ -692,7 +692,7 @@ static bool fm10k_mbx_tx_complete(struct fm10k_mbx_info *mbx) } /** - * fm10k_mbx_deqeueue_rx - Dequeues the message from the head in the Rx FIFO + * fm10k_mbx_dequeue_rx - Dequeues the message from the head in the Rx FIFO * @hw: pointer to hardware structure * @mbx: pointer to mailbox * @@ -1039,6 +1039,7 @@ static s32 fm10k_mbx_create_reply(struct fm10k_hw *hw, case FM10K_STATE_CLOSED: /* generate new header based on data */ fm10k_mbx_create_disconnect_hdr(mbx); + break; default: break; } @@ -2017,6 +2018,7 @@ static s32 fm10k_sm_mbx_process_reset(struct fm10k_hw *hw, case FM10K_STATE_CONNECT: /* Update remote value to match local value */ mbx->remote = mbx->local; + break; default: break; } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c index c0780c3624c8..af1b0cde3670 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c @@ -1417,7 +1417,7 @@ s32 fm10k_iov_msg_lport_state_pf(struct fm10k_hw *hw, u32 **results, } /** - * fm10k_update_stats_hw_pf - Updates hardware related statistics of PF + * fm10k_update_hw_stats_pf - Updates hardware related statistics of PF * @hw: pointer to hardware structure * @stats: pointer to the stats structure to update * diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 15f93b355099..9067cd3ce243 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -66,6 +66,8 @@ #define I40E_FDIR_RING_COUNT 32 #define I40E_MAX_AQ_BUF_SIZE 4096 #define I40E_AQ_LEN 256 +#define I40E_MIN_ARQ_LEN 1 +#define I40E_MIN_ASQ_LEN 2 #define I40E_AQ_WORK_LIMIT 66 /* max number of VFs + a little */ #define I40E_MAX_USER_PRIORITY 8 #define I40E_DEFAULT_TRAFFIC_CLASS BIT(0) diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index ec19e18305ec..41b813fe07a5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -2332,7 +2332,7 @@ i40e_status i40e_aq_set_vsi_vlan_promisc(struct i40e_hw *hw, } /** - * i40e_get_vsi_params - get VSI configuration info + * i40e_aq_get_vsi_params - get VSI configuration info * @hw: pointer to the hw struct * @vsi_ctx: pointer to a vsi context struct * @cmd_details: pointer to command details structure or NULL @@ -2586,7 +2586,7 @@ i40e_status i40e_get_link_status(struct i40e_hw *hw, bool *link_up) } /** - * i40e_updatelink_status - update status of the HW network link + * i40e_update_link_info - update status of the HW network link * @hw: pointer to the hw struct **/ noinline_for_stack i40e_status i40e_update_link_info(struct i40e_hw *hw) @@ -5059,7 +5059,7 @@ u8 i40e_get_phy_address(struct i40e_hw *hw, u8 dev_num) } /** - * i40e_blink_phy_led + * i40e_blink_phy_link_led * @hw: pointer to the HW structure * @time: time how long led will blinks in secs * @interval: gap between LED on and off in msecs diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.c b/drivers/net/ethernet/intel/i40e/i40e_dcb.c index 243b0d2b7b72..673f341f4c0c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_dcb.c +++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.c @@ -234,7 +234,7 @@ static void i40e_parse_ieee_app_tlv(struct i40e_lldp_org_tlv *tlv, } /** - * i40e_parse_ieee_etsrec_tlv + * i40e_parse_ieee_tlv * @tlv: IEEE 802.1Qaz TLV * @dcbcfg: Local store to update ETS REC data * @@ -1588,7 +1588,7 @@ void i40e_dcb_hw_rx_ets_bw_config(struct i40e_hw *hw, u8 *bw_share, } /** - * i40e_dcb_hw_rx_ets_bw_config + * i40e_dcb_hw_rx_up2tc_config * @hw: pointer to the hw struct * @prio_tc: priority to tc assignment indexed by priority * diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c b/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c index 0345132a0ef5..e32c61909b31 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c +++ b/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c @@ -392,7 +392,7 @@ static void i40e_dcbnl_set_pg_tc_cfg_tx(struct net_device *netdev, int tc, } /** - * i40e_dcbnl_set_pg_tc_cfg_tx - Set CEE PG Tx BW config + * i40e_dcbnl_set_pg_bwg_cfg_tx - Set CEE PG Tx BW config * @netdev: the corresponding netdev * @pgid: the corresponding traffic class * @bw_pct: the BW percentage for the specified traffic class diff --git a/drivers/net/ethernet/intel/i40e/i40e_ddp.c b/drivers/net/ethernet/intel/i40e/i40e_ddp.c index 5e08f100c413..e1069ae658ad 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ddp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ddp.c @@ -77,7 +77,7 @@ static bool i40e_ddp_profiles_overlap(struct i40e_profile_info *new, } /** - * i40e_ddp_does_profiles_ - checks if DDP overlaps with existing one. + * i40e_ddp_does_profile_overlap - checks if DDP overlaps with existing one. * @hw: HW data structure * @pinfo: DDP profile information structure * diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index d627b59ad446..291e61ac3e44 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -654,7 +654,7 @@ static void i40e_dbg_dump_vsi_no_seid(struct i40e_pf *pf) } /** - * i40e_dbg_dump_stats - handles dump stats write into command datum + * i40e_dbg_dump_eth_stats - handles dump stats write into command datum * @pf: the i40e_pf created in command write * @estats: the eth stats structure to be dumped **/ @@ -1641,7 +1641,7 @@ static const struct file_operations i40e_dbg_command_fops = { static char i40e_dbg_netdev_ops_buf[256] = ""; /** - * i40e_dbg_netdev_ops - read for netdev_ops datum + * i40e_dbg_netdev_ops_read - read for netdev_ops datum * @filp: the opened file * @buffer: where to write the data for the user to read * @count: the size of the user's buffer diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 0e92668012e3..040a01400b85 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -212,7 +212,7 @@ static void __i40e_add_stat_strings(u8 **p, const struct i40e_stats stats[], } /** - * 40e_add_stat_strings - copy stat strings into ethtool buffer + * i40e_add_stat_strings - copy stat strings into ethtool buffer * @p: ethtool supplied buffer * @stats: stat definitions array * @@ -2409,21 +2409,15 @@ static void i40e_get_priv_flag_strings(struct net_device *netdev, u8 *data) struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; - char *p = (char *)data; unsigned int i; + u8 *p = data; - for (i = 0; i < I40E_PRIV_FLAGS_STR_LEN; i++) { - snprintf(p, ETH_GSTRING_LEN, "%s", - i40e_gstrings_priv_flags[i].flag_string); - p += ETH_GSTRING_LEN; - } + for (i = 0; i < I40E_PRIV_FLAGS_STR_LEN; i++) + ethtool_sprintf(&p, i40e_gstrings_priv_flags[i].flag_string); if (pf->hw.pf_id != 0) return; - for (i = 0; i < I40E_GL_PRIV_FLAGS_STR_LEN; i++) { - snprintf(p, ETH_GSTRING_LEN, "%s", - i40e_gl_gstrings_priv_flags[i].flag_string); - p += ETH_GSTRING_LEN; - } + for (i = 0; i < I40E_GL_PRIV_FLAGS_STR_LEN; i++) + ethtool_sprintf(&p, i40e_gl_gstrings_priv_flags[i].flag_string); } static void i40e_get_strings(struct net_device *netdev, u32 stringset, diff --git a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c index a3da422ab05b..d6e92ecddfbd 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c +++ b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c @@ -511,7 +511,7 @@ configure_lan_hmc_out: } /** - * i40e_delete_hmc_object - remove hmc objects + * i40e_delete_lan_hmc_object - remove hmc objects * @hw: pointer to the HW structure * @info: pointer to i40e_hmc_delete_obj_info struct * diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 527023ee4c07..c2d145a56b5e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -6,6 +6,7 @@ #include <linux/pci.h> #include <linux/bpf.h> #include <generated/utsrelease.h> +#include <linux/crash_dump.h> /* Local includes */ #include "i40e.h" @@ -2023,7 +2024,7 @@ static void i40e_undo_add_filter_entries(struct i40e_vsi *vsi, } /** - * i40e_next_entry - Get the next non-broadcast filter from a list + * i40e_next_filter - Get the next non-broadcast filter from a list * @next: pointer to filter in list * * Returns the next non-broadcast filter in the list. Required so that we @@ -5203,7 +5204,7 @@ static u8 i40e_pf_get_num_tc(struct i40e_pf *pf) } /** - * i40e_pf_get_pf_tc_map - Get bitmap for enabled traffic classes + * i40e_pf_get_tc_map - Get bitmap for enabled traffic classes * @pf: PF being queried * * Return a bitmap for enabled traffic classes for this PF. @@ -7338,7 +7339,7 @@ static void i40e_vsi_set_default_tc_config(struct i40e_vsi *vsi) qcount = min_t(int, vsi->alloc_queue_pairs, i40e_pf_get_max_q_per_tc(vsi->back)); for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { - /* For the TC that is not enabled set the offset to to default + /* For the TC that is not enabled set the offset to default * queue and allocate one queue for the given TC. */ vsi->tc_config.tc_info[i].qoffset = 0; @@ -9466,7 +9467,7 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf) } /** - * i40e_get_current_atr_count - Get the count of total FD ATR filters programmed + * i40e_get_current_atr_cnt - Get the count of total FD ATR filters programmed * @pf: board private structure **/ u32 i40e_get_current_atr_cnt(struct i40e_pf *pf) @@ -10623,7 +10624,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) * need to rebuild the switch model in the HW. * * If there were VEBs but the reconstitution failed, we'll try - * try to recover minimal use by getting the basic PF VSI working. + * to recover minimal use by getting the basic PF VSI working. */ if (vsi->uplink_seid != pf->mac_seid) { dev_dbg(&pf->pdev->dev, "attempting to rebuild switch\n"); @@ -11039,6 +11040,11 @@ static int i40e_set_num_rings_in_vsi(struct i40e_vsi *vsi) return -ENODATA; } + if (is_kdump_kernel()) { + vsi->num_tx_desc = I40E_MIN_NUM_DESCRIPTORS; + vsi->num_rx_desc = I40E_MIN_NUM_DESCRIPTORS; + } + return 0; } @@ -15342,8 +15348,13 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) i40e_check_recovery_mode(pf); - hw->aq.num_arq_entries = I40E_AQ_LEN; - hw->aq.num_asq_entries = I40E_AQ_LEN; + if (is_kdump_kernel()) { + hw->aq.num_arq_entries = I40E_MIN_ARQ_LEN; + hw->aq.num_asq_entries = I40E_MIN_ASQ_LEN; + } else { + hw->aq.num_arq_entries = I40E_AQ_LEN; + hw->aq.num_asq_entries = I40E_AQ_LEN; + } hw->aq.arq_buf_size = I40E_MAX_AQ_BUF_SIZE; hw->aq.asq_buf_size = I40E_MAX_AQ_BUF_SIZE; pf->adminq_work_limit = I40E_AQ_WORK_LIMIT; @@ -15506,6 +15517,14 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto err_switch_setup; + /* Reduce Tx and Rx pairs for kdump + * When MSI-X is enabled, it's not allowed to use more TC queue + * pairs than MSI-X vectors (pf->num_lan_msix) exist. Thus + * vsi->num_queue_pairs will be equal to pf->num_lan_msix, i.e., 1. + */ + if (is_kdump_kernel()) + pf->num_lan_msix = 1; + pf->udp_tunnel_nic.set_port = i40e_udp_tunnel_set_port; pf->udp_tunnel_nic.unset_port = i40e_udp_tunnel_unset_port; pf->udp_tunnel_nic.flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP; diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c index 7164f4ad8120..fe6dca846028 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c +++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c @@ -4,7 +4,7 @@ #include "i40e_prototype.h" /** - * i40e_init_nvm_ops - Initialize NVM function pointers + * i40e_init_nvm - Initialize NVM function pointers * @hw: pointer to the HW structure * * Setup the function pointers and the NVM info structure. Should be called diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index 7a879614ca55..f1f6fc3744e9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -216,7 +216,7 @@ static int i40e_ptp_feature_enable(struct ptp_clock_info *ptp, } /** - * i40e_ptp_update_latch_events - Read I40E_PRTTSYN_STAT_1 and latch events + * i40e_ptp_get_rx_events - Read I40E_PRTTSYN_STAT_1 and latch events * @pf: the PF data structure * * This function reads I40E_PRTTSYN_STAT_1 and updates the corresponding timers diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 06b4271219b1..121cd99fdeff 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -3331,7 +3331,7 @@ static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, } /** - * i40e_create_tx_ctx Build the Tx context descriptor + * i40e_create_tx_ctx - Build the Tx context descriptor * @tx_ring: ring to create the descriptor on * @cd_type_cmd_tso_mss: Quad Word 1 * @cd_tunneling: Quad Word 0 - bits 0-31 @@ -3833,8 +3833,8 @@ netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev) * @frames: array of XDP buffer pointers * @flags: XDP extra info * - * Returns number of frames successfully sent. Frames that fail are - * free'ed via XDP return API. + * Returns number of frames successfully sent. Failed frames + * will be free'ed by XDP core. * * For error cases, a negative errno code is returned and no-frames * are transmitted (caller must handle freeing frames). @@ -3847,7 +3847,7 @@ int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; struct i40e_ring *xdp_ring; - int drops = 0; + int nxmit = 0; int i; if (test_bit(__I40E_VSI_DOWN, vsi->state)) @@ -3867,14 +3867,13 @@ int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, int err; err = i40e_xmit_xdp_ring(xdpf, xdp_ring); - if (err != I40E_XDP_TX) { - xdp_return_frame_rx_napi(xdpf); - drops++; - } + if (err != I40E_XDP_TX) + break; + nxmit++; } if (unlikely(flags & XDP_XMIT_FLUSH)) i40e_xdp_ring_update_tail(xdp_ring); - return n - drops; + return nxmit; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 5d301a466f5c..eff0a30790dd 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -40,6 +40,66 @@ static void i40e_vc_vf_broadcast(struct i40e_pf *pf, } /** + * i40e_vc_link_speed2mbps + * converts i40e_aq_link_speed to integer value of Mbps + * @link_speed: the speed to convert + * + * return the speed as direct value of Mbps. + **/ +static u32 +i40e_vc_link_speed2mbps(enum i40e_aq_link_speed link_speed) +{ + switch (link_speed) { + case I40E_LINK_SPEED_100MB: + return SPEED_100; + case I40E_LINK_SPEED_1GB: + return SPEED_1000; + case I40E_LINK_SPEED_2_5GB: + return SPEED_2500; + case I40E_LINK_SPEED_5GB: + return SPEED_5000; + case I40E_LINK_SPEED_10GB: + return SPEED_10000; + case I40E_LINK_SPEED_20GB: + return SPEED_20000; + case I40E_LINK_SPEED_25GB: + return SPEED_25000; + case I40E_LINK_SPEED_40GB: + return SPEED_40000; + case I40E_LINK_SPEED_UNKNOWN: + return SPEED_UNKNOWN; + } + return SPEED_UNKNOWN; +} + +/** + * i40e_set_vf_link_state + * @vf: pointer to the VF structure + * @pfe: pointer to PF event structure + * @ls: pointer to link status structure + * + * set a link state on a single vf + **/ +static void i40e_set_vf_link_state(struct i40e_vf *vf, + struct virtchnl_pf_event *pfe, struct i40e_link_status *ls) +{ + u8 link_status = ls->link_info & I40E_AQ_LINK_UP; + + if (vf->link_forced) + link_status = vf->link_up; + + if (vf->driver_caps & VIRTCHNL_VF_CAP_ADV_LINK_SPEED) { + pfe->event_data.link_event_adv.link_speed = link_status ? + i40e_vc_link_speed2mbps(ls->link_speed) : 0; + pfe->event_data.link_event_adv.link_status = link_status; + } else { + pfe->event_data.link_event.link_speed = link_status ? + i40e_virtchnl_link_speed(ls->link_speed) : 0; + pfe->event_data.link_event.link_status = link_status; + } +} + +/** * i40e_vc_notify_vf_link_state * @vf: pointer to the VF structure * @@ -55,16 +115,9 @@ static void i40e_vc_notify_vf_link_state(struct i40e_vf *vf) pfe.event = VIRTCHNL_EVENT_LINK_CHANGE; pfe.severity = PF_EVENT_SEVERITY_INFO; - if (vf->link_forced) { - pfe.event_data.link_event.link_status = vf->link_up; - pfe.event_data.link_event.link_speed = - (vf->link_up ? i40e_virtchnl_link_speed(ls->link_speed) : 0); - } else { - pfe.event_data.link_event.link_status = - ls->link_info & I40E_AQ_LINK_UP; - pfe.event_data.link_event.link_speed = - i40e_virtchnl_link_speed(ls->link_speed); - } + + i40e_set_vf_link_state(vf, &pfe, ls); + i40e_aq_send_msg_to_vf(hw, abs_vf_id, VIRTCHNL_OP_EVENT, 0, (u8 *)&pfe, sizeof(pfe), NULL); } @@ -1949,6 +2002,7 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg) VIRTCHNL_VF_OFFLOAD_VLAN; vfres->vf_cap_flags = VIRTCHNL_VF_OFFLOAD_L2; + vfres->vf_cap_flags |= VIRTCHNL_VF_CAP_ADV_LINK_SPEED; vsi = pf->vsi[vf->lan_vsi_idx]; if (!vsi->info.pvid) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_VLAN; @@ -3696,26 +3750,8 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg) } /* get link speed in MB to validate rate limit */ - switch (ls->link_speed) { - case VIRTCHNL_LINK_SPEED_100MB: - speed = SPEED_100; - break; - case VIRTCHNL_LINK_SPEED_1GB: - speed = SPEED_1000; - break; - case VIRTCHNL_LINK_SPEED_10GB: - speed = SPEED_10000; - break; - case VIRTCHNL_LINK_SPEED_20GB: - speed = SPEED_20000; - break; - case VIRTCHNL_LINK_SPEED_25GB: - speed = SPEED_25000; - break; - case VIRTCHNL_LINK_SPEED_40GB: - speed = SPEED_40000; - break; - default: + speed = i40e_vc_link_speed2mbps(ls->link_speed); + if (speed == SPEED_UNKNOWN) { dev_err(&pf->pdev->dev, "Cannot detect link speed\n"); aq_ret = I40E_ERR_PARAM; @@ -4464,23 +4500,17 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link) switch (link) { case IFLA_VF_LINK_STATE_AUTO: vf->link_forced = false; - pfe.event_data.link_event.link_status = - pf->hw.phy.link_info.link_info & I40E_AQ_LINK_UP; - pfe.event_data.link_event.link_speed = - (enum virtchnl_link_speed) - pf->hw.phy.link_info.link_speed; + i40e_set_vf_link_state(vf, &pfe, ls); break; case IFLA_VF_LINK_STATE_ENABLE: vf->link_forced = true; vf->link_up = true; - pfe.event_data.link_event.link_status = true; - pfe.event_data.link_event.link_speed = i40e_virtchnl_link_speed(ls->link_speed); + i40e_set_vf_link_state(vf, &pfe, ls); break; case IFLA_VF_LINK_STATE_DISABLE: vf->link_forced = true; vf->link_up = false; - pfe.event_data.link_event.link_status = false; - pfe.event_data.link_event.link_speed = 0; + i40e_set_vf_link_state(vf, &pfe, ls); break; default: ret = -EINVAL; diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 12ca84113587..46d884417c63 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -160,6 +160,13 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp) xdp_prog = READ_ONCE(rx_ring->xdp_prog); act = bpf_prog_run_xdp(xdp_prog, xdp); + if (likely(act == XDP_REDIRECT)) { + err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); + result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED; + rcu_read_unlock(); + return result; + } + switch (act) { case XDP_PASS: break; @@ -167,10 +174,6 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp) xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index]; result = i40e_xmit_xdp_tx_ring(xdp, xdp_ring); break; - case XDP_REDIRECT: - err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); - result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED; - break; default: bpf_warn_invalid_xdp_action(act); fallthrough; @@ -625,7 +628,7 @@ void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring) } /** - * i40e_xsk_clean_xdp_ring - Clean the XDP Tx ring on shutdown + * i40e_xsk_clean_tx_ring - Clean the XDP Tx ring on shutdown * @tx_ring: XDP Tx ring **/ void i40e_xsk_clean_tx_ring(struct i40e_ring *tx_ring) diff --git a/drivers/net/ethernet/intel/iavf/Makefile b/drivers/net/ethernet/intel/iavf/Makefile index c997063ed728..9c3e45c54d01 100644 --- a/drivers/net/ethernet/intel/iavf/Makefile +++ b/drivers/net/ethernet/intel/iavf/Makefile @@ -11,5 +11,6 @@ subdir-ccflags-y += -I$(src) obj-$(CONFIG_IAVF) += iavf.o -iavf-objs := iavf_main.o iavf_ethtool.o iavf_virtchnl.o \ +iavf-objs := iavf_main.o iavf_ethtool.o iavf_virtchnl.o iavf_fdir.o \ + iavf_adv_rss.o \ iavf_txrx.o iavf_common.o iavf_adminq.o iavf_client.o diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 8a65525a7c0d..e8bd04100ecd 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -37,6 +37,8 @@ #include "iavf_type.h" #include <linux/avf/virtchnl.h> #include "iavf_txrx.h" +#include "iavf_fdir.h" +#include "iavf_adv_rss.h" #define DEFAULT_DEBUG_LEVEL_SHIFT 3 #define PFX "iavf: " @@ -300,6 +302,10 @@ struct iavf_adapter { #define IAVF_FLAG_AQ_DISABLE_CHANNELS BIT(22) #define IAVF_FLAG_AQ_ADD_CLOUD_FILTER BIT(23) #define IAVF_FLAG_AQ_DEL_CLOUD_FILTER BIT(24) +#define IAVF_FLAG_AQ_ADD_FDIR_FILTER BIT(25) +#define IAVF_FLAG_AQ_DEL_FDIR_FILTER BIT(26) +#define IAVF_FLAG_AQ_ADD_ADV_RSS_CFG BIT(27) +#define IAVF_FLAG_AQ_DEL_ADV_RSS_CFG BIT(28) /* OS defined structs */ struct net_device *netdev; @@ -340,6 +346,10 @@ struct iavf_adapter { VIRTCHNL_VF_OFFLOAD_VLAN) #define ADV_LINK_SUPPORT(_a) ((_a)->vf_res->vf_cap_flags & \ VIRTCHNL_VF_CAP_ADV_LINK_SPEED) +#define FDIR_FLTR_SUPPORT(_a) ((_a)->vf_res->vf_cap_flags & \ + VIRTCHNL_VF_OFFLOAD_FDIR_PF) +#define ADV_RSS_SUPPORT(_a) ((_a)->vf_res->vf_cap_flags & \ + VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF) struct virtchnl_vf_resource *vf_res; /* incl. all VSIs */ struct virtchnl_vsi_resource *vsi_res; /* our LAN VSI */ struct virtchnl_version_info pf_version; @@ -362,6 +372,14 @@ struct iavf_adapter { /* lock to protect access to the cloud filter list */ spinlock_t cloud_filter_list_lock; u16 num_cloud_filters; + +#define IAVF_MAX_FDIR_FILTERS 128 /* max allowed Flow Director filters */ + u16 fdir_active_fltr; + struct list_head fdir_list_head; + spinlock_t fdir_fltr_lock; /* protect the Flow Director filter list */ + + struct list_head adv_rss_list_head; + spinlock_t adv_rss_lock; /* protect the RSS management list */ }; @@ -432,6 +450,10 @@ void iavf_enable_channels(struct iavf_adapter *adapter); void iavf_disable_channels(struct iavf_adapter *adapter); void iavf_add_cloud_filter(struct iavf_adapter *adapter); void iavf_del_cloud_filter(struct iavf_adapter *adapter); +void iavf_add_fdir_filter(struct iavf_adapter *adapter); +void iavf_del_fdir_filter(struct iavf_adapter *adapter); +void iavf_add_adv_rss_cfg(struct iavf_adapter *adapter); +void iavf_del_adv_rss_cfg(struct iavf_adapter *adapter); struct iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter, const u8 *macaddr); #endif /* _IAVF_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_adv_rss.c b/drivers/net/ethernet/intel/iavf/iavf_adv_rss.c new file mode 100644 index 000000000000..6edbf134b73f --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_adv_rss.c @@ -0,0 +1,218 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021, Intel Corporation. */ + +/* advanced RSS configuration ethtool support for iavf */ + +#include "iavf.h" + +/** + * iavf_fill_adv_rss_ip4_hdr - fill the IPv4 RSS protocol header + * @hdr: the virtchnl message protocol header data structure + * @hash_flds: the RSS configuration protocol hash fields + */ +static void +iavf_fill_adv_rss_ip4_hdr(struct virtchnl_proto_hdr *hdr, u64 hash_flds) +{ + VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, IPV4); + + if (hash_flds & IAVF_ADV_RSS_HASH_FLD_IPV4_SA) + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, IPV4, SRC); + + if (hash_flds & IAVF_ADV_RSS_HASH_FLD_IPV4_DA) + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, IPV4, DST); +} + +/** + * iavf_fill_adv_rss_ip6_hdr - fill the IPv6 RSS protocol header + * @hdr: the virtchnl message protocol header data structure + * @hash_flds: the RSS configuration protocol hash fields + */ +static void +iavf_fill_adv_rss_ip6_hdr(struct virtchnl_proto_hdr *hdr, u64 hash_flds) +{ + VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, IPV6); + + if (hash_flds & IAVF_ADV_RSS_HASH_FLD_IPV6_SA) + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, IPV6, SRC); + + if (hash_flds & IAVF_ADV_RSS_HASH_FLD_IPV6_DA) + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, IPV6, DST); +} + +/** + * iavf_fill_adv_rss_tcp_hdr - fill the TCP RSS protocol header + * @hdr: the virtchnl message protocol header data structure + * @hash_flds: the RSS configuration protocol hash fields + */ +static void +iavf_fill_adv_rss_tcp_hdr(struct virtchnl_proto_hdr *hdr, u64 hash_flds) +{ + VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, TCP); + + if (hash_flds & IAVF_ADV_RSS_HASH_FLD_TCP_SRC_PORT) + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, TCP, SRC_PORT); + + if (hash_flds & IAVF_ADV_RSS_HASH_FLD_TCP_DST_PORT) + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, TCP, DST_PORT); +} + +/** + * iavf_fill_adv_rss_udp_hdr - fill the UDP RSS protocol header + * @hdr: the virtchnl message protocol header data structure + * @hash_flds: the RSS configuration protocol hash fields + */ +static void +iavf_fill_adv_rss_udp_hdr(struct virtchnl_proto_hdr *hdr, u64 hash_flds) +{ + VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, UDP); + + if (hash_flds & IAVF_ADV_RSS_HASH_FLD_UDP_SRC_PORT) + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, UDP, SRC_PORT); + + if (hash_flds & IAVF_ADV_RSS_HASH_FLD_UDP_DST_PORT) + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, UDP, DST_PORT); +} + +/** + * iavf_fill_adv_rss_sctp_hdr - fill the SCTP RSS protocol header + * @hdr: the virtchnl message protocol header data structure + * @hash_flds: the RSS configuration protocol hash fields + */ +static void +iavf_fill_adv_rss_sctp_hdr(struct virtchnl_proto_hdr *hdr, u64 hash_flds) +{ + VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, SCTP); + + if (hash_flds & IAVF_ADV_RSS_HASH_FLD_SCTP_SRC_PORT) + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, SCTP, SRC_PORT); + + if (hash_flds & IAVF_ADV_RSS_HASH_FLD_SCTP_DST_PORT) + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, SCTP, DST_PORT); +} + +/** + * iavf_fill_adv_rss_cfg_msg - fill the RSS configuration into virtchnl message + * @rss_cfg: the virtchnl message to be filled with RSS configuration setting + * @packet_hdrs: the RSS configuration protocol header types + * @hash_flds: the RSS configuration protocol hash fields + * + * Returns 0 if the RSS configuration virtchnl message is filled successfully + */ +int +iavf_fill_adv_rss_cfg_msg(struct virtchnl_rss_cfg *rss_cfg, + u32 packet_hdrs, u64 hash_flds) +{ + struct virtchnl_proto_hdrs *proto_hdrs = &rss_cfg->proto_hdrs; + struct virtchnl_proto_hdr *hdr; + + rss_cfg->rss_algorithm = VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC; + + proto_hdrs->tunnel_level = 0; /* always outer layer */ + + hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++]; + switch (packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_L3) { + case IAVF_ADV_RSS_FLOW_SEG_HDR_IPV4: + iavf_fill_adv_rss_ip4_hdr(hdr, hash_flds); + break; + case IAVF_ADV_RSS_FLOW_SEG_HDR_IPV6: + iavf_fill_adv_rss_ip6_hdr(hdr, hash_flds); + break; + default: + return -EINVAL; + } + + hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++]; + switch (packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_L4) { + case IAVF_ADV_RSS_FLOW_SEG_HDR_TCP: + iavf_fill_adv_rss_tcp_hdr(hdr, hash_flds); + break; + case IAVF_ADV_RSS_FLOW_SEG_HDR_UDP: + iavf_fill_adv_rss_udp_hdr(hdr, hash_flds); + break; + case IAVF_ADV_RSS_FLOW_SEG_HDR_SCTP: + iavf_fill_adv_rss_sctp_hdr(hdr, hash_flds); + break; + default: + return -EINVAL; + } + + return 0; +} + +/** + * iavf_find_adv_rss_cfg_by_hdrs - find RSS configuration with header type + * @adapter: pointer to the VF adapter structure + * @packet_hdrs: protocol header type to find. + * + * Returns pointer to advance RSS configuration if found or null + */ +struct iavf_adv_rss * +iavf_find_adv_rss_cfg_by_hdrs(struct iavf_adapter *adapter, u32 packet_hdrs) +{ + struct iavf_adv_rss *rss; + + list_for_each_entry(rss, &adapter->adv_rss_list_head, list) + if (rss->packet_hdrs == packet_hdrs) + return rss; + + return NULL; +} + +/** + * iavf_print_adv_rss_cfg + * @adapter: pointer to the VF adapter structure + * @rss: pointer to the advance RSS configuration to print + * @action: the string description about how to handle the RSS + * @result: the string description about the virtchnl result + * + * Print the advance RSS configuration + **/ +void +iavf_print_adv_rss_cfg(struct iavf_adapter *adapter, struct iavf_adv_rss *rss, + const char *action, const char *result) +{ + u32 packet_hdrs = rss->packet_hdrs; + u64 hash_flds = rss->hash_flds; + static char hash_opt[300]; + const char *proto; + + if (packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_TCP) + proto = "TCP"; + else if (packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_UDP) + proto = "UDP"; + else if (packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_SCTP) + proto = "SCTP"; + else + return; + + memset(hash_opt, 0, sizeof(hash_opt)); + + strcat(hash_opt, proto); + if (packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_IPV4) + strcat(hash_opt, "v4 "); + else + strcat(hash_opt, "v6 "); + + if (hash_flds & (IAVF_ADV_RSS_HASH_FLD_IPV4_SA | + IAVF_ADV_RSS_HASH_FLD_IPV6_SA)) + strcat(hash_opt, "IP SA,"); + if (hash_flds & (IAVF_ADV_RSS_HASH_FLD_IPV4_DA | + IAVF_ADV_RSS_HASH_FLD_IPV6_DA)) + strcat(hash_opt, "IP DA,"); + if (hash_flds & (IAVF_ADV_RSS_HASH_FLD_TCP_SRC_PORT | + IAVF_ADV_RSS_HASH_FLD_UDP_SRC_PORT | + IAVF_ADV_RSS_HASH_FLD_SCTP_SRC_PORT)) + strcat(hash_opt, "src port,"); + if (hash_flds & (IAVF_ADV_RSS_HASH_FLD_TCP_DST_PORT | + IAVF_ADV_RSS_HASH_FLD_UDP_DST_PORT | + IAVF_ADV_RSS_HASH_FLD_SCTP_DST_PORT)) + strcat(hash_opt, "dst port,"); + + if (!action) + action = ""; + + if (!result) + result = ""; + + dev_info(&adapter->pdev->dev, "%s %s %s\n", action, hash_opt, result); +} diff --git a/drivers/net/ethernet/intel/iavf/iavf_adv_rss.h b/drivers/net/ethernet/intel/iavf/iavf_adv_rss.h new file mode 100644 index 000000000000..4d3be11af7aa --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_adv_rss.h @@ -0,0 +1,95 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2021, Intel Corporation. */ + +#ifndef _IAVF_ADV_RSS_H_ +#define _IAVF_ADV_RSS_H_ + +struct iavf_adapter; + +/* State of advanced RSS configuration */ +enum iavf_adv_rss_state_t { + IAVF_ADV_RSS_ADD_REQUEST, /* User requests to add RSS */ + IAVF_ADV_RSS_ADD_PENDING, /* RSS pending add by the PF */ + IAVF_ADV_RSS_DEL_REQUEST, /* Driver requests to delete RSS */ + IAVF_ADV_RSS_DEL_PENDING, /* RSS pending delete by the PF */ + IAVF_ADV_RSS_ACTIVE, /* RSS configuration is active */ +}; + +enum iavf_adv_rss_flow_seg_hdr { + IAVF_ADV_RSS_FLOW_SEG_HDR_NONE = 0x00000000, + IAVF_ADV_RSS_FLOW_SEG_HDR_IPV4 = 0x00000001, + IAVF_ADV_RSS_FLOW_SEG_HDR_IPV6 = 0x00000002, + IAVF_ADV_RSS_FLOW_SEG_HDR_TCP = 0x00000004, + IAVF_ADV_RSS_FLOW_SEG_HDR_UDP = 0x00000008, + IAVF_ADV_RSS_FLOW_SEG_HDR_SCTP = 0x00000010, +}; + +#define IAVF_ADV_RSS_FLOW_SEG_HDR_L3 \ + (IAVF_ADV_RSS_FLOW_SEG_HDR_IPV4 | \ + IAVF_ADV_RSS_FLOW_SEG_HDR_IPV6) + +#define IAVF_ADV_RSS_FLOW_SEG_HDR_L4 \ + (IAVF_ADV_RSS_FLOW_SEG_HDR_TCP | \ + IAVF_ADV_RSS_FLOW_SEG_HDR_UDP | \ + IAVF_ADV_RSS_FLOW_SEG_HDR_SCTP) + +enum iavf_adv_rss_flow_field { + /* L3 */ + IAVF_ADV_RSS_FLOW_FIELD_IDX_IPV4_SA, + IAVF_ADV_RSS_FLOW_FIELD_IDX_IPV4_DA, + IAVF_ADV_RSS_FLOW_FIELD_IDX_IPV6_SA, + IAVF_ADV_RSS_FLOW_FIELD_IDX_IPV6_DA, + /* L4 */ + IAVF_ADV_RSS_FLOW_FIELD_IDX_TCP_SRC_PORT, + IAVF_ADV_RSS_FLOW_FIELD_IDX_TCP_DST_PORT, + IAVF_ADV_RSS_FLOW_FIELD_IDX_UDP_SRC_PORT, + IAVF_ADV_RSS_FLOW_FIELD_IDX_UDP_DST_PORT, + IAVF_ADV_RSS_FLOW_FIELD_IDX_SCTP_SRC_PORT, + IAVF_ADV_RSS_FLOW_FIELD_IDX_SCTP_DST_PORT, + + /* The total number of enums must not exceed 64 */ + IAVF_ADV_RSS_FLOW_FIELD_IDX_MAX +}; + +#define IAVF_ADV_RSS_HASH_INVALID 0 +#define IAVF_ADV_RSS_HASH_FLD_IPV4_SA \ + BIT_ULL(IAVF_ADV_RSS_FLOW_FIELD_IDX_IPV4_SA) +#define IAVF_ADV_RSS_HASH_FLD_IPV6_SA \ + BIT_ULL(IAVF_ADV_RSS_FLOW_FIELD_IDX_IPV6_SA) +#define IAVF_ADV_RSS_HASH_FLD_IPV4_DA \ + BIT_ULL(IAVF_ADV_RSS_FLOW_FIELD_IDX_IPV4_DA) +#define IAVF_ADV_RSS_HASH_FLD_IPV6_DA \ + BIT_ULL(IAVF_ADV_RSS_FLOW_FIELD_IDX_IPV6_DA) +#define IAVF_ADV_RSS_HASH_FLD_TCP_SRC_PORT \ + BIT_ULL(IAVF_ADV_RSS_FLOW_FIELD_IDX_TCP_SRC_PORT) +#define IAVF_ADV_RSS_HASH_FLD_TCP_DST_PORT \ + BIT_ULL(IAVF_ADV_RSS_FLOW_FIELD_IDX_TCP_DST_PORT) +#define IAVF_ADV_RSS_HASH_FLD_UDP_SRC_PORT \ + BIT_ULL(IAVF_ADV_RSS_FLOW_FIELD_IDX_UDP_SRC_PORT) +#define IAVF_ADV_RSS_HASH_FLD_UDP_DST_PORT \ + BIT_ULL(IAVF_ADV_RSS_FLOW_FIELD_IDX_UDP_DST_PORT) +#define IAVF_ADV_RSS_HASH_FLD_SCTP_SRC_PORT \ + BIT_ULL(IAVF_ADV_RSS_FLOW_FIELD_IDX_SCTP_SRC_PORT) +#define IAVF_ADV_RSS_HASH_FLD_SCTP_DST_PORT \ + BIT_ULL(IAVF_ADV_RSS_FLOW_FIELD_IDX_SCTP_DST_PORT) + +/* bookkeeping of advanced RSS configuration */ +struct iavf_adv_rss { + enum iavf_adv_rss_state_t state; + struct list_head list; + + u32 packet_hdrs; + u64 hash_flds; + + struct virtchnl_rss_cfg cfg_msg; +}; + +int +iavf_fill_adv_rss_cfg_msg(struct virtchnl_rss_cfg *rss_cfg, + u32 packet_hdrs, u64 hash_flds); +struct iavf_adv_rss * +iavf_find_adv_rss_cfg_by_hdrs(struct iavf_adapter *adapter, u32 packet_hdrs); +void +iavf_print_adv_rss_cfg(struct iavf_adapter *adapter, struct iavf_adv_rss *rss, + const char *action, const char *result); +#endif /* _IAVF_ADV_RSS_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index c93567f4d0f7..af43fbd8cb75 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -828,6 +828,872 @@ static int iavf_set_per_queue_coalesce(struct net_device *netdev, u32 queue, } /** + * iavf_fltr_to_ethtool_flow - convert filter type values to ethtool + * flow type values + * @flow: filter type to be converted + * + * Returns the corresponding ethtool flow type. + */ +static int iavf_fltr_to_ethtool_flow(enum iavf_fdir_flow_type flow) +{ + switch (flow) { + case IAVF_FDIR_FLOW_IPV4_TCP: + return TCP_V4_FLOW; + case IAVF_FDIR_FLOW_IPV4_UDP: + return UDP_V4_FLOW; + case IAVF_FDIR_FLOW_IPV4_SCTP: + return SCTP_V4_FLOW; + case IAVF_FDIR_FLOW_IPV4_AH: + return AH_V4_FLOW; + case IAVF_FDIR_FLOW_IPV4_ESP: + return ESP_V4_FLOW; + case IAVF_FDIR_FLOW_IPV4_OTHER: + return IPV4_USER_FLOW; + case IAVF_FDIR_FLOW_IPV6_TCP: + return TCP_V6_FLOW; + case IAVF_FDIR_FLOW_IPV6_UDP: + return UDP_V6_FLOW; + case IAVF_FDIR_FLOW_IPV6_SCTP: + return SCTP_V6_FLOW; + case IAVF_FDIR_FLOW_IPV6_AH: + return AH_V6_FLOW; + case IAVF_FDIR_FLOW_IPV6_ESP: + return ESP_V6_FLOW; + case IAVF_FDIR_FLOW_IPV6_OTHER: + return IPV6_USER_FLOW; + case IAVF_FDIR_FLOW_NON_IP_L2: + return ETHER_FLOW; + default: + /* 0 is undefined ethtool flow */ + return 0; + } +} + +/** + * iavf_ethtool_flow_to_fltr - convert ethtool flow type to filter enum + * @eth: Ethtool flow type to be converted + * + * Returns flow enum + */ +static enum iavf_fdir_flow_type iavf_ethtool_flow_to_fltr(int eth) +{ + switch (eth) { + case TCP_V4_FLOW: + return IAVF_FDIR_FLOW_IPV4_TCP; + case UDP_V4_FLOW: + return IAVF_FDIR_FLOW_IPV4_UDP; + case SCTP_V4_FLOW: + return IAVF_FDIR_FLOW_IPV4_SCTP; + case AH_V4_FLOW: + return IAVF_FDIR_FLOW_IPV4_AH; + case ESP_V4_FLOW: + return IAVF_FDIR_FLOW_IPV4_ESP; + case IPV4_USER_FLOW: + return IAVF_FDIR_FLOW_IPV4_OTHER; + case TCP_V6_FLOW: + return IAVF_FDIR_FLOW_IPV6_TCP; + case UDP_V6_FLOW: + return IAVF_FDIR_FLOW_IPV6_UDP; + case SCTP_V6_FLOW: + return IAVF_FDIR_FLOW_IPV6_SCTP; + case AH_V6_FLOW: + return IAVF_FDIR_FLOW_IPV6_AH; + case ESP_V6_FLOW: + return IAVF_FDIR_FLOW_IPV6_ESP; + case IPV6_USER_FLOW: + return IAVF_FDIR_FLOW_IPV6_OTHER; + case ETHER_FLOW: + return IAVF_FDIR_FLOW_NON_IP_L2; + default: + return IAVF_FDIR_FLOW_NONE; + } +} + +/** + * iavf_is_mask_valid - check mask field set + * @mask: full mask to check + * @field: field for which mask should be valid + * + * If the mask is fully set return true. If it is not valid for field return + * false. + */ +static bool iavf_is_mask_valid(u64 mask, u64 field) +{ + return (mask & field) == field; +} + +/** + * iavf_parse_rx_flow_user_data - deconstruct user-defined data + * @fsp: pointer to ethtool Rx flow specification + * @fltr: pointer to Flow Director filter for userdef data storage + * + * Returns 0 on success, negative error value on failure + */ +static int +iavf_parse_rx_flow_user_data(struct ethtool_rx_flow_spec *fsp, + struct iavf_fdir_fltr *fltr) +{ + struct iavf_flex_word *flex; + int i, cnt = 0; + + if (!(fsp->flow_type & FLOW_EXT)) + return 0; + + for (i = 0; i < IAVF_FLEX_WORD_NUM; i++) { +#define IAVF_USERDEF_FLEX_WORD_M GENMASK(15, 0) +#define IAVF_USERDEF_FLEX_OFFS_S 16 +#define IAVF_USERDEF_FLEX_OFFS_M GENMASK(31, IAVF_USERDEF_FLEX_OFFS_S) +#define IAVF_USERDEF_FLEX_FLTR_M GENMASK(31, 0) + u32 value = be32_to_cpu(fsp->h_ext.data[i]); + u32 mask = be32_to_cpu(fsp->m_ext.data[i]); + + if (!value || !mask) + continue; + + if (!iavf_is_mask_valid(mask, IAVF_USERDEF_FLEX_FLTR_M)) + return -EINVAL; + + /* 504 is the maximum value for offsets, and offset is measured + * from the start of the MAC address. + */ +#define IAVF_USERDEF_FLEX_MAX_OFFS_VAL 504 + flex = &fltr->flex_words[cnt++]; + flex->word = value & IAVF_USERDEF_FLEX_WORD_M; + flex->offset = (value & IAVF_USERDEF_FLEX_OFFS_M) >> + IAVF_USERDEF_FLEX_OFFS_S; + if (flex->offset > IAVF_USERDEF_FLEX_MAX_OFFS_VAL) + return -EINVAL; + } + + fltr->flex_cnt = cnt; + + return 0; +} + +/** + * iavf_fill_rx_flow_ext_data - fill the additional data + * @fsp: pointer to ethtool Rx flow specification + * @fltr: pointer to Flow Director filter to get additional data + */ +static void +iavf_fill_rx_flow_ext_data(struct ethtool_rx_flow_spec *fsp, + struct iavf_fdir_fltr *fltr) +{ + if (!fltr->ext_mask.usr_def[0] && !fltr->ext_mask.usr_def[1]) + return; + + fsp->flow_type |= FLOW_EXT; + + memcpy(fsp->h_ext.data, fltr->ext_data.usr_def, sizeof(fsp->h_ext.data)); + memcpy(fsp->m_ext.data, fltr->ext_mask.usr_def, sizeof(fsp->m_ext.data)); +} + +/** + * iavf_get_ethtool_fdir_entry - fill ethtool structure with Flow Director filter data + * @adapter: the VF adapter structure that contains filter list + * @cmd: ethtool command data structure to receive the filter data + * + * Returns 0 as expected for success by ethtool + */ +static int +iavf_get_ethtool_fdir_entry(struct iavf_adapter *adapter, + struct ethtool_rxnfc *cmd) +{ + struct ethtool_rx_flow_spec *fsp = (struct ethtool_rx_flow_spec *)&cmd->fs; + struct iavf_fdir_fltr *rule = NULL; + int ret = 0; + + if (!FDIR_FLTR_SUPPORT(adapter)) + return -EOPNOTSUPP; + + spin_lock_bh(&adapter->fdir_fltr_lock); + + rule = iavf_find_fdir_fltr_by_loc(adapter, fsp->location); + if (!rule) { + ret = -EINVAL; + goto release_lock; + } + + fsp->flow_type = iavf_fltr_to_ethtool_flow(rule->flow_type); + + memset(&fsp->m_u, 0, sizeof(fsp->m_u)); + memset(&fsp->m_ext, 0, sizeof(fsp->m_ext)); + + switch (fsp->flow_type) { + case TCP_V4_FLOW: + case UDP_V4_FLOW: + case SCTP_V4_FLOW: + fsp->h_u.tcp_ip4_spec.ip4src = rule->ip_data.v4_addrs.src_ip; + fsp->h_u.tcp_ip4_spec.ip4dst = rule->ip_data.v4_addrs.dst_ip; + fsp->h_u.tcp_ip4_spec.psrc = rule->ip_data.src_port; + fsp->h_u.tcp_ip4_spec.pdst = rule->ip_data.dst_port; + fsp->h_u.tcp_ip4_spec.tos = rule->ip_data.tos; + fsp->m_u.tcp_ip4_spec.ip4src = rule->ip_mask.v4_addrs.src_ip; + fsp->m_u.tcp_ip4_spec.ip4dst = rule->ip_mask.v4_addrs.dst_ip; + fsp->m_u.tcp_ip4_spec.psrc = rule->ip_mask.src_port; + fsp->m_u.tcp_ip4_spec.pdst = rule->ip_mask.dst_port; + fsp->m_u.tcp_ip4_spec.tos = rule->ip_mask.tos; + break; + case AH_V4_FLOW: + case ESP_V4_FLOW: + fsp->h_u.ah_ip4_spec.ip4src = rule->ip_data.v4_addrs.src_ip; + fsp->h_u.ah_ip4_spec.ip4dst = rule->ip_data.v4_addrs.dst_ip; + fsp->h_u.ah_ip4_spec.spi = rule->ip_data.spi; + fsp->h_u.ah_ip4_spec.tos = rule->ip_data.tos; + fsp->m_u.ah_ip4_spec.ip4src = rule->ip_mask.v4_addrs.src_ip; + fsp->m_u.ah_ip4_spec.ip4dst = rule->ip_mask.v4_addrs.dst_ip; + fsp->m_u.ah_ip4_spec.spi = rule->ip_mask.spi; + fsp->m_u.ah_ip4_spec.tos = rule->ip_mask.tos; + break; + case IPV4_USER_FLOW: + fsp->h_u.usr_ip4_spec.ip4src = rule->ip_data.v4_addrs.src_ip; + fsp->h_u.usr_ip4_spec.ip4dst = rule->ip_data.v4_addrs.dst_ip; + fsp->h_u.usr_ip4_spec.l4_4_bytes = rule->ip_data.l4_header; + fsp->h_u.usr_ip4_spec.tos = rule->ip_data.tos; + fsp->h_u.usr_ip4_spec.ip_ver = ETH_RX_NFC_IP4; + fsp->h_u.usr_ip4_spec.proto = rule->ip_data.proto; + fsp->m_u.usr_ip4_spec.ip4src = rule->ip_mask.v4_addrs.src_ip; + fsp->m_u.usr_ip4_spec.ip4dst = rule->ip_mask.v4_addrs.dst_ip; + fsp->m_u.usr_ip4_spec.l4_4_bytes = rule->ip_mask.l4_header; + fsp->m_u.usr_ip4_spec.tos = rule->ip_mask.tos; + fsp->m_u.usr_ip4_spec.ip_ver = 0xFF; + fsp->m_u.usr_ip4_spec.proto = rule->ip_mask.proto; + break; + case TCP_V6_FLOW: + case UDP_V6_FLOW: + case SCTP_V6_FLOW: + memcpy(fsp->h_u.usr_ip6_spec.ip6src, &rule->ip_data.v6_addrs.src_ip, + sizeof(struct in6_addr)); + memcpy(fsp->h_u.usr_ip6_spec.ip6dst, &rule->ip_data.v6_addrs.dst_ip, + sizeof(struct in6_addr)); + fsp->h_u.tcp_ip6_spec.psrc = rule->ip_data.src_port; + fsp->h_u.tcp_ip6_spec.pdst = rule->ip_data.dst_port; + fsp->h_u.tcp_ip6_spec.tclass = rule->ip_data.tclass; + memcpy(fsp->m_u.usr_ip6_spec.ip6src, &rule->ip_mask.v6_addrs.src_ip, + sizeof(struct in6_addr)); + memcpy(fsp->m_u.usr_ip6_spec.ip6dst, &rule->ip_mask.v6_addrs.dst_ip, + sizeof(struct in6_addr)); + fsp->m_u.tcp_ip6_spec.psrc = rule->ip_mask.src_port; + fsp->m_u.tcp_ip6_spec.pdst = rule->ip_mask.dst_port; + fsp->m_u.tcp_ip6_spec.tclass = rule->ip_mask.tclass; + break; + case AH_V6_FLOW: + case ESP_V6_FLOW: + memcpy(fsp->h_u.ah_ip6_spec.ip6src, &rule->ip_data.v6_addrs.src_ip, + sizeof(struct in6_addr)); + memcpy(fsp->h_u.ah_ip6_spec.ip6dst, &rule->ip_data.v6_addrs.dst_ip, + sizeof(struct in6_addr)); + fsp->h_u.ah_ip6_spec.spi = rule->ip_data.spi; + fsp->h_u.ah_ip6_spec.tclass = rule->ip_data.tclass; + memcpy(fsp->m_u.ah_ip6_spec.ip6src, &rule->ip_mask.v6_addrs.src_ip, + sizeof(struct in6_addr)); + memcpy(fsp->m_u.ah_ip6_spec.ip6dst, &rule->ip_mask.v6_addrs.dst_ip, + sizeof(struct in6_addr)); + fsp->m_u.ah_ip6_spec.spi = rule->ip_mask.spi; + fsp->m_u.ah_ip6_spec.tclass = rule->ip_mask.tclass; + break; + case IPV6_USER_FLOW: + memcpy(fsp->h_u.usr_ip6_spec.ip6src, &rule->ip_data.v6_addrs.src_ip, + sizeof(struct in6_addr)); + memcpy(fsp->h_u.usr_ip6_spec.ip6dst, &rule->ip_data.v6_addrs.dst_ip, + sizeof(struct in6_addr)); + fsp->h_u.usr_ip6_spec.l4_4_bytes = rule->ip_data.l4_header; + fsp->h_u.usr_ip6_spec.tclass = rule->ip_data.tclass; + fsp->h_u.usr_ip6_spec.l4_proto = rule->ip_data.proto; + memcpy(fsp->m_u.usr_ip6_spec.ip6src, &rule->ip_mask.v6_addrs.src_ip, + sizeof(struct in6_addr)); + memcpy(fsp->m_u.usr_ip6_spec.ip6dst, &rule->ip_mask.v6_addrs.dst_ip, + sizeof(struct in6_addr)); + fsp->m_u.usr_ip6_spec.l4_4_bytes = rule->ip_mask.l4_header; + fsp->m_u.usr_ip6_spec.tclass = rule->ip_mask.tclass; + fsp->m_u.usr_ip6_spec.l4_proto = rule->ip_mask.proto; + break; + case ETHER_FLOW: + fsp->h_u.ether_spec.h_proto = rule->eth_data.etype; + fsp->m_u.ether_spec.h_proto = rule->eth_mask.etype; + break; + default: + ret = -EINVAL; + break; + } + + iavf_fill_rx_flow_ext_data(fsp, rule); + + if (rule->action == VIRTCHNL_ACTION_DROP) + fsp->ring_cookie = RX_CLS_FLOW_DISC; + else + fsp->ring_cookie = rule->q_index; + +release_lock: + spin_unlock_bh(&adapter->fdir_fltr_lock); + return ret; +} + +/** + * iavf_get_fdir_fltr_ids - fill buffer with filter IDs of active filters + * @adapter: the VF adapter structure containing the filter list + * @cmd: ethtool command data structure + * @rule_locs: ethtool array passed in from OS to receive filter IDs + * + * Returns 0 as expected for success by ethtool + */ +static int +iavf_get_fdir_fltr_ids(struct iavf_adapter *adapter, struct ethtool_rxnfc *cmd, + u32 *rule_locs) +{ + struct iavf_fdir_fltr *fltr; + unsigned int cnt = 0; + int val = 0; + + if (!FDIR_FLTR_SUPPORT(adapter)) + return -EOPNOTSUPP; + + cmd->data = IAVF_MAX_FDIR_FILTERS; + + spin_lock_bh(&adapter->fdir_fltr_lock); + + list_for_each_entry(fltr, &adapter->fdir_list_head, list) { + if (cnt == cmd->rule_cnt) { + val = -EMSGSIZE; + goto release_lock; + } + rule_locs[cnt] = fltr->loc; + cnt++; + } + +release_lock: + spin_unlock_bh(&adapter->fdir_fltr_lock); + if (!val) + cmd->rule_cnt = cnt; + + return val; +} + +/** + * iavf_add_fdir_fltr_info - Set the input set for Flow Director filter + * @adapter: pointer to the VF adapter structure + * @fsp: pointer to ethtool Rx flow specification + * @fltr: filter structure + */ +static int +iavf_add_fdir_fltr_info(struct iavf_adapter *adapter, struct ethtool_rx_flow_spec *fsp, + struct iavf_fdir_fltr *fltr) +{ + u32 flow_type, q_index = 0; + enum virtchnl_action act; + int err; + + if (fsp->ring_cookie == RX_CLS_FLOW_DISC) { + act = VIRTCHNL_ACTION_DROP; + } else { + q_index = fsp->ring_cookie; + if (q_index >= adapter->num_active_queues) + return -EINVAL; + + act = VIRTCHNL_ACTION_QUEUE; + } + + fltr->action = act; + fltr->loc = fsp->location; + fltr->q_index = q_index; + + if (fsp->flow_type & FLOW_EXT) { + memcpy(fltr->ext_data.usr_def, fsp->h_ext.data, + sizeof(fltr->ext_data.usr_def)); + memcpy(fltr->ext_mask.usr_def, fsp->m_ext.data, + sizeof(fltr->ext_mask.usr_def)); + } + + flow_type = fsp->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS); + fltr->flow_type = iavf_ethtool_flow_to_fltr(flow_type); + + switch (flow_type) { + case TCP_V4_FLOW: + case UDP_V4_FLOW: + case SCTP_V4_FLOW: + fltr->ip_data.v4_addrs.src_ip = fsp->h_u.tcp_ip4_spec.ip4src; + fltr->ip_data.v4_addrs.dst_ip = fsp->h_u.tcp_ip4_spec.ip4dst; + fltr->ip_data.src_port = fsp->h_u.tcp_ip4_spec.psrc; + fltr->ip_data.dst_port = fsp->h_u.tcp_ip4_spec.pdst; + fltr->ip_data.tos = fsp->h_u.tcp_ip4_spec.tos; + fltr->ip_mask.v4_addrs.src_ip = fsp->m_u.tcp_ip4_spec.ip4src; + fltr->ip_mask.v4_addrs.dst_ip = fsp->m_u.tcp_ip4_spec.ip4dst; + fltr->ip_mask.src_port = fsp->m_u.tcp_ip4_spec.psrc; + fltr->ip_mask.dst_port = fsp->m_u.tcp_ip4_spec.pdst; + fltr->ip_mask.tos = fsp->m_u.tcp_ip4_spec.tos; + break; + case AH_V4_FLOW: + case ESP_V4_FLOW: + fltr->ip_data.v4_addrs.src_ip = fsp->h_u.ah_ip4_spec.ip4src; + fltr->ip_data.v4_addrs.dst_ip = fsp->h_u.ah_ip4_spec.ip4dst; + fltr->ip_data.spi = fsp->h_u.ah_ip4_spec.spi; + fltr->ip_data.tos = fsp->h_u.ah_ip4_spec.tos; + fltr->ip_mask.v4_addrs.src_ip = fsp->m_u.ah_ip4_spec.ip4src; + fltr->ip_mask.v4_addrs.dst_ip = fsp->m_u.ah_ip4_spec.ip4dst; + fltr->ip_mask.spi = fsp->m_u.ah_ip4_spec.spi; + fltr->ip_mask.tos = fsp->m_u.ah_ip4_spec.tos; + break; + case IPV4_USER_FLOW: + fltr->ip_data.v4_addrs.src_ip = fsp->h_u.usr_ip4_spec.ip4src; + fltr->ip_data.v4_addrs.dst_ip = fsp->h_u.usr_ip4_spec.ip4dst; + fltr->ip_data.l4_header = fsp->h_u.usr_ip4_spec.l4_4_bytes; + fltr->ip_data.tos = fsp->h_u.usr_ip4_spec.tos; + fltr->ip_data.proto = fsp->h_u.usr_ip4_spec.proto; + fltr->ip_mask.v4_addrs.src_ip = fsp->m_u.usr_ip4_spec.ip4src; + fltr->ip_mask.v4_addrs.dst_ip = fsp->m_u.usr_ip4_spec.ip4dst; + fltr->ip_mask.l4_header = fsp->m_u.usr_ip4_spec.l4_4_bytes; + fltr->ip_mask.tos = fsp->m_u.usr_ip4_spec.tos; + fltr->ip_mask.proto = fsp->m_u.usr_ip4_spec.proto; + break; + case TCP_V6_FLOW: + case UDP_V6_FLOW: + case SCTP_V6_FLOW: + memcpy(&fltr->ip_data.v6_addrs.src_ip, fsp->h_u.usr_ip6_spec.ip6src, + sizeof(struct in6_addr)); + memcpy(&fltr->ip_data.v6_addrs.dst_ip, fsp->h_u.usr_ip6_spec.ip6dst, + sizeof(struct in6_addr)); + fltr->ip_data.src_port = fsp->h_u.tcp_ip6_spec.psrc; + fltr->ip_data.dst_port = fsp->h_u.tcp_ip6_spec.pdst; + fltr->ip_data.tclass = fsp->h_u.tcp_ip6_spec.tclass; + memcpy(&fltr->ip_mask.v6_addrs.src_ip, fsp->m_u.usr_ip6_spec.ip6src, + sizeof(struct in6_addr)); + memcpy(&fltr->ip_mask.v6_addrs.dst_ip, fsp->m_u.usr_ip6_spec.ip6dst, + sizeof(struct in6_addr)); + fltr->ip_mask.src_port = fsp->m_u.tcp_ip6_spec.psrc; + fltr->ip_mask.dst_port = fsp->m_u.tcp_ip6_spec.pdst; + fltr->ip_mask.tclass = fsp->m_u.tcp_ip6_spec.tclass; + break; + case AH_V6_FLOW: + case ESP_V6_FLOW: + memcpy(&fltr->ip_data.v6_addrs.src_ip, fsp->h_u.ah_ip6_spec.ip6src, + sizeof(struct in6_addr)); + memcpy(&fltr->ip_data.v6_addrs.dst_ip, fsp->h_u.ah_ip6_spec.ip6dst, + sizeof(struct in6_addr)); + fltr->ip_data.spi = fsp->h_u.ah_ip6_spec.spi; + fltr->ip_data.tclass = fsp->h_u.ah_ip6_spec.tclass; + memcpy(&fltr->ip_mask.v6_addrs.src_ip, fsp->m_u.ah_ip6_spec.ip6src, + sizeof(struct in6_addr)); + memcpy(&fltr->ip_mask.v6_addrs.dst_ip, fsp->m_u.ah_ip6_spec.ip6dst, + sizeof(struct in6_addr)); + fltr->ip_mask.spi = fsp->m_u.ah_ip6_spec.spi; + fltr->ip_mask.tclass = fsp->m_u.ah_ip6_spec.tclass; + break; + case IPV6_USER_FLOW: + memcpy(&fltr->ip_data.v6_addrs.src_ip, fsp->h_u.usr_ip6_spec.ip6src, + sizeof(struct in6_addr)); + memcpy(&fltr->ip_data.v6_addrs.dst_ip, fsp->h_u.usr_ip6_spec.ip6dst, + sizeof(struct in6_addr)); + fltr->ip_data.l4_header = fsp->h_u.usr_ip6_spec.l4_4_bytes; + fltr->ip_data.tclass = fsp->h_u.usr_ip6_spec.tclass; + fltr->ip_data.proto = fsp->h_u.usr_ip6_spec.l4_proto; + memcpy(&fltr->ip_mask.v6_addrs.src_ip, fsp->m_u.usr_ip6_spec.ip6src, + sizeof(struct in6_addr)); + memcpy(&fltr->ip_mask.v6_addrs.dst_ip, fsp->m_u.usr_ip6_spec.ip6dst, + sizeof(struct in6_addr)); + fltr->ip_mask.l4_header = fsp->m_u.usr_ip6_spec.l4_4_bytes; + fltr->ip_mask.tclass = fsp->m_u.usr_ip6_spec.tclass; + fltr->ip_mask.proto = fsp->m_u.usr_ip6_spec.l4_proto; + break; + case ETHER_FLOW: + fltr->eth_data.etype = fsp->h_u.ether_spec.h_proto; + fltr->eth_mask.etype = fsp->m_u.ether_spec.h_proto; + break; + default: + /* not doing un-parsed flow types */ + return -EINVAL; + } + + if (iavf_fdir_is_dup_fltr(adapter, fltr)) + return -EEXIST; + + err = iavf_parse_rx_flow_user_data(fsp, fltr); + if (err) + return err; + + return iavf_fill_fdir_add_msg(adapter, fltr); +} + +/** + * iavf_add_fdir_ethtool - add Flow Director filter + * @adapter: pointer to the VF adapter structure + * @cmd: command to add Flow Director filter + * + * Returns 0 on success and negative values for failure + */ +static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rxnfc *cmd) +{ + struct ethtool_rx_flow_spec *fsp = &cmd->fs; + struct iavf_fdir_fltr *fltr; + int count = 50; + int err; + + if (!FDIR_FLTR_SUPPORT(adapter)) + return -EOPNOTSUPP; + + if (fsp->flow_type & FLOW_MAC_EXT) + return -EINVAL; + + if (adapter->fdir_active_fltr >= IAVF_MAX_FDIR_FILTERS) { + dev_err(&adapter->pdev->dev, + "Unable to add Flow Director filter because VF reached the limit of max allowed filters (%u)\n", + IAVF_MAX_FDIR_FILTERS); + return -ENOSPC; + } + + spin_lock_bh(&adapter->fdir_fltr_lock); + if (iavf_find_fdir_fltr_by_loc(adapter, fsp->location)) { + dev_err(&adapter->pdev->dev, "Failed to add Flow Director filter, it already exists\n"); + spin_unlock_bh(&adapter->fdir_fltr_lock); + return -EEXIST; + } + spin_unlock_bh(&adapter->fdir_fltr_lock); + + fltr = kzalloc(sizeof(*fltr), GFP_KERNEL); + if (!fltr) + return -ENOMEM; + + while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK, + &adapter->crit_section)) { + if (--count == 0) { + kfree(fltr); + return -EINVAL; + } + udelay(1); + } + + err = iavf_add_fdir_fltr_info(adapter, fsp, fltr); + if (err) + goto ret; + + spin_lock_bh(&adapter->fdir_fltr_lock); + iavf_fdir_list_add_fltr(adapter, fltr); + adapter->fdir_active_fltr++; + fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST; + adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER; + spin_unlock_bh(&adapter->fdir_fltr_lock); + + mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0); + +ret: + if (err && fltr) + kfree(fltr); + + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); + return err; +} + +/** + * iavf_del_fdir_ethtool - delete Flow Director filter + * @adapter: pointer to the VF adapter structure + * @cmd: command to delete Flow Director filter + * + * Returns 0 on success and negative values for failure + */ +static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rxnfc *cmd) +{ + struct ethtool_rx_flow_spec *fsp = (struct ethtool_rx_flow_spec *)&cmd->fs; + struct iavf_fdir_fltr *fltr = NULL; + int err = 0; + + if (!FDIR_FLTR_SUPPORT(adapter)) + return -EOPNOTSUPP; + + spin_lock_bh(&adapter->fdir_fltr_lock); + fltr = iavf_find_fdir_fltr_by_loc(adapter, fsp->location); + if (fltr) { + if (fltr->state == IAVF_FDIR_FLTR_ACTIVE) { + fltr->state = IAVF_FDIR_FLTR_DEL_REQUEST; + adapter->aq_required |= IAVF_FLAG_AQ_DEL_FDIR_FILTER; + } else { + err = -EBUSY; + } + } else if (adapter->fdir_active_fltr) { + err = -EINVAL; + } + spin_unlock_bh(&adapter->fdir_fltr_lock); + + if (fltr && fltr->state == IAVF_FDIR_FLTR_DEL_REQUEST) + mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0); + + return err; +} + +/** + * iavf_adv_rss_parse_hdrs - parses headers from RSS hash input + * @cmd: ethtool rxnfc command + * + * This function parses the rxnfc command and returns intended + * header types for RSS configuration + */ +static u32 iavf_adv_rss_parse_hdrs(struct ethtool_rxnfc *cmd) +{ + u32 hdrs = IAVF_ADV_RSS_FLOW_SEG_HDR_NONE; + + switch (cmd->flow_type) { + case TCP_V4_FLOW: + hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_TCP | + IAVF_ADV_RSS_FLOW_SEG_HDR_IPV4; + break; + case UDP_V4_FLOW: + hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_UDP | + IAVF_ADV_RSS_FLOW_SEG_HDR_IPV4; + break; + case SCTP_V4_FLOW: + hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_SCTP | + IAVF_ADV_RSS_FLOW_SEG_HDR_IPV4; + break; + case TCP_V6_FLOW: + hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_TCP | + IAVF_ADV_RSS_FLOW_SEG_HDR_IPV6; + break; + case UDP_V6_FLOW: + hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_UDP | + IAVF_ADV_RSS_FLOW_SEG_HDR_IPV6; + break; + case SCTP_V6_FLOW: + hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_SCTP | + IAVF_ADV_RSS_FLOW_SEG_HDR_IPV6; + break; + default: + break; + } + + return hdrs; +} + +/** + * iavf_adv_rss_parse_hash_flds - parses hash fields from RSS hash input + * @cmd: ethtool rxnfc command + * + * This function parses the rxnfc command and returns intended hash fields for + * RSS configuration + */ +static u64 iavf_adv_rss_parse_hash_flds(struct ethtool_rxnfc *cmd) +{ + u64 hfld = IAVF_ADV_RSS_HASH_INVALID; + + if (cmd->data & RXH_IP_SRC || cmd->data & RXH_IP_DST) { + switch (cmd->flow_type) { + case TCP_V4_FLOW: + case UDP_V4_FLOW: + case SCTP_V4_FLOW: + if (cmd->data & RXH_IP_SRC) + hfld |= IAVF_ADV_RSS_HASH_FLD_IPV4_SA; + if (cmd->data & RXH_IP_DST) + hfld |= IAVF_ADV_RSS_HASH_FLD_IPV4_DA; + break; + case TCP_V6_FLOW: + case UDP_V6_FLOW: + case SCTP_V6_FLOW: + if (cmd->data & RXH_IP_SRC) + hfld |= IAVF_ADV_RSS_HASH_FLD_IPV6_SA; + if (cmd->data & RXH_IP_DST) + hfld |= IAVF_ADV_RSS_HASH_FLD_IPV6_DA; + break; + default: + break; + } + } + + if (cmd->data & RXH_L4_B_0_1 || cmd->data & RXH_L4_B_2_3) { + switch (cmd->flow_type) { + case TCP_V4_FLOW: + case TCP_V6_FLOW: + if (cmd->data & RXH_L4_B_0_1) + hfld |= IAVF_ADV_RSS_HASH_FLD_TCP_SRC_PORT; + if (cmd->data & RXH_L4_B_2_3) + hfld |= IAVF_ADV_RSS_HASH_FLD_TCP_DST_PORT; + break; + case UDP_V4_FLOW: + case UDP_V6_FLOW: + if (cmd->data & RXH_L4_B_0_1) + hfld |= IAVF_ADV_RSS_HASH_FLD_UDP_SRC_PORT; + if (cmd->data & RXH_L4_B_2_3) + hfld |= IAVF_ADV_RSS_HASH_FLD_UDP_DST_PORT; + break; + case SCTP_V4_FLOW: + case SCTP_V6_FLOW: + if (cmd->data & RXH_L4_B_0_1) + hfld |= IAVF_ADV_RSS_HASH_FLD_SCTP_SRC_PORT; + if (cmd->data & RXH_L4_B_2_3) + hfld |= IAVF_ADV_RSS_HASH_FLD_SCTP_DST_PORT; + break; + default: + break; + } + } + + return hfld; +} + +/** + * iavf_set_adv_rss_hash_opt - Enable/Disable flow types for RSS hash + * @adapter: pointer to the VF adapter structure + * @cmd: ethtool rxnfc command + * + * Returns Success if the flow input set is supported. + */ +static int +iavf_set_adv_rss_hash_opt(struct iavf_adapter *adapter, + struct ethtool_rxnfc *cmd) +{ + struct iavf_adv_rss *rss_old, *rss_new; + bool rss_new_add = false; + int count = 50, err = 0; + u64 hash_flds; + u32 hdrs; + + if (!ADV_RSS_SUPPORT(adapter)) + return -EOPNOTSUPP; + + hdrs = iavf_adv_rss_parse_hdrs(cmd); + if (hdrs == IAVF_ADV_RSS_FLOW_SEG_HDR_NONE) + return -EINVAL; + + hash_flds = iavf_adv_rss_parse_hash_flds(cmd); + if (hash_flds == IAVF_ADV_RSS_HASH_INVALID) + return -EINVAL; + + rss_new = kzalloc(sizeof(*rss_new), GFP_KERNEL); + if (!rss_new) + return -ENOMEM; + + if (iavf_fill_adv_rss_cfg_msg(&rss_new->cfg_msg, hdrs, hash_flds)) { + kfree(rss_new); + return -EINVAL; + } + + while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK, + &adapter->crit_section)) { + if (--count == 0) { + kfree(rss_new); + return -EINVAL; + } + + udelay(1); + } + + spin_lock_bh(&adapter->adv_rss_lock); + rss_old = iavf_find_adv_rss_cfg_by_hdrs(adapter, hdrs); + if (rss_old) { + if (rss_old->state != IAVF_ADV_RSS_ACTIVE) { + err = -EBUSY; + } else if (rss_old->hash_flds != hash_flds) { + rss_old->state = IAVF_ADV_RSS_ADD_REQUEST; + rss_old->hash_flds = hash_flds; + memcpy(&rss_old->cfg_msg, &rss_new->cfg_msg, + sizeof(rss_new->cfg_msg)); + adapter->aq_required |= IAVF_FLAG_AQ_ADD_ADV_RSS_CFG; + } else { + err = -EEXIST; + } + } else { + rss_new_add = true; + rss_new->state = IAVF_ADV_RSS_ADD_REQUEST; + rss_new->packet_hdrs = hdrs; + rss_new->hash_flds = hash_flds; + list_add_tail(&rss_new->list, &adapter->adv_rss_list_head); + adapter->aq_required |= IAVF_FLAG_AQ_ADD_ADV_RSS_CFG; + } + spin_unlock_bh(&adapter->adv_rss_lock); + + if (!err) + mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0); + + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); + + if (!rss_new_add) + kfree(rss_new); + + return err; +} + +/** + * iavf_get_adv_rss_hash_opt - Retrieve hash fields for a given flow-type + * @adapter: pointer to the VF adapter structure + * @cmd: ethtool rxnfc command + * + * Returns Success if the flow input set is supported. + */ +static int +iavf_get_adv_rss_hash_opt(struct iavf_adapter *adapter, + struct ethtool_rxnfc *cmd) +{ + struct iavf_adv_rss *rss; + u64 hash_flds; + u32 hdrs; + + if (!ADV_RSS_SUPPORT(adapter)) + return -EOPNOTSUPP; + + cmd->data = 0; + + hdrs = iavf_adv_rss_parse_hdrs(cmd); + if (hdrs == IAVF_ADV_RSS_FLOW_SEG_HDR_NONE) + return -EINVAL; + + spin_lock_bh(&adapter->adv_rss_lock); + rss = iavf_find_adv_rss_cfg_by_hdrs(adapter, hdrs); + if (rss) + hash_flds = rss->hash_flds; + else + hash_flds = IAVF_ADV_RSS_HASH_INVALID; + spin_unlock_bh(&adapter->adv_rss_lock); + + if (hash_flds == IAVF_ADV_RSS_HASH_INVALID) + return -EINVAL; + + if (hash_flds & (IAVF_ADV_RSS_HASH_FLD_IPV4_SA | + IAVF_ADV_RSS_HASH_FLD_IPV6_SA)) + cmd->data |= (u64)RXH_IP_SRC; + + if (hash_flds & (IAVF_ADV_RSS_HASH_FLD_IPV4_DA | + IAVF_ADV_RSS_HASH_FLD_IPV6_DA)) + cmd->data |= (u64)RXH_IP_DST; + + if (hash_flds & (IAVF_ADV_RSS_HASH_FLD_TCP_SRC_PORT | + IAVF_ADV_RSS_HASH_FLD_UDP_SRC_PORT | + IAVF_ADV_RSS_HASH_FLD_SCTP_SRC_PORT)) + cmd->data |= (u64)RXH_L4_B_0_1; + + if (hash_flds & (IAVF_ADV_RSS_HASH_FLD_TCP_DST_PORT | + IAVF_ADV_RSS_HASH_FLD_UDP_DST_PORT | + IAVF_ADV_RSS_HASH_FLD_SCTP_DST_PORT)) + cmd->data |= (u64)RXH_L4_B_2_3; + + return 0; +} + +/** + * iavf_set_rxnfc - command to set Rx flow rules. + * @netdev: network interface device structure + * @cmd: ethtool rxnfc command + * + * Returns 0 for success and negative values for errors + */ +static int iavf_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + int ret = -EOPNOTSUPP; + + switch (cmd->cmd) { + case ETHTOOL_SRXCLSRLINS: + ret = iavf_add_fdir_ethtool(adapter, cmd); + break; + case ETHTOOL_SRXCLSRLDEL: + ret = iavf_del_fdir_ethtool(adapter, cmd); + break; + case ETHTOOL_SRXFH: + ret = iavf_set_adv_rss_hash_opt(adapter, cmd); + break; + default: + break; + } + + return ret; +} + +/** * iavf_get_rxnfc - command to get RX flow classification rules * @netdev: network interface device structure * @cmd: ethtool rxnfc command @@ -846,9 +1712,21 @@ static int iavf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, cmd->data = adapter->num_active_queues; ret = 0; break; + case ETHTOOL_GRXCLSRLCNT: + if (!FDIR_FLTR_SUPPORT(adapter)) + break; + cmd->rule_cnt = adapter->fdir_active_fltr; + cmd->data = IAVF_MAX_FDIR_FILTERS; + ret = 0; + break; + case ETHTOOL_GRXCLSRULE: + ret = iavf_get_ethtool_fdir_entry(adapter, cmd); + break; + case ETHTOOL_GRXCLSRLALL: + ret = iavf_get_fdir_fltr_ids(adapter, cmd, (u32 *)rule_locs); + break; case ETHTOOL_GRXFH: - netdev_info(netdev, - "RSS hash info is not available to vf, use pf.\n"); + ret = iavf_get_adv_rss_hash_opt(adapter, cmd); break; default: break; @@ -1025,6 +1903,7 @@ static const struct ethtool_ops iavf_ethtool_ops = { .set_coalesce = iavf_set_coalesce, .get_per_queue_coalesce = iavf_get_per_queue_coalesce, .set_per_queue_coalesce = iavf_set_per_queue_coalesce, + .set_rxnfc = iavf_set_rxnfc, .get_rxnfc = iavf_get_rxnfc, .get_rxfh_indir_size = iavf_get_rxfh_indir_size, .get_rxfh = iavf_get_rxfh, diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.c b/drivers/net/ethernet/intel/iavf/iavf_fdir.c new file mode 100644 index 000000000000..6146203efd84 --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.c @@ -0,0 +1,779 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020, Intel Corporation. */ + +/* flow director ethtool support for iavf */ + +#include "iavf.h" + +#define GTPU_PORT 2152 +#define NAT_T_ESP_PORT 4500 +#define PFCP_PORT 8805 + +static const struct in6_addr ipv6_addr_full_mask = { + .in6_u = { + .u6_addr8 = { + 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, + 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, + } + } +}; + +/** + * iavf_pkt_udp_no_pay_len - the length of UDP packet without payload + * @fltr: Flow Director filter data structure + */ +static u16 iavf_pkt_udp_no_pay_len(struct iavf_fdir_fltr *fltr) +{ + return sizeof(struct ethhdr) + + (fltr->ip_ver == 4 ? sizeof(struct iphdr) : sizeof(struct ipv6hdr)) + + sizeof(struct udphdr); +} + +/** + * iavf_fill_fdir_gtpu_hdr - fill the GTP-U protocol header + * @fltr: Flow Director filter data structure + * @proto_hdrs: Flow Director protocol headers data structure + * + * Returns 0 if the GTP-U protocol header is set successfully + */ +static int +iavf_fill_fdir_gtpu_hdr(struct iavf_fdir_fltr *fltr, + struct virtchnl_proto_hdrs *proto_hdrs) +{ + struct virtchnl_proto_hdr *uhdr = &proto_hdrs->proto_hdr[proto_hdrs->count - 1]; + struct virtchnl_proto_hdr *ghdr = &proto_hdrs->proto_hdr[proto_hdrs->count++]; + struct virtchnl_proto_hdr *ehdr = NULL; /* Extension Header if it exists */ + u16 adj_offs, hdr_offs; + int i; + + VIRTCHNL_SET_PROTO_HDR_TYPE(ghdr, GTPU_IP); + + adj_offs = iavf_pkt_udp_no_pay_len(fltr); + + for (i = 0; i < fltr->flex_cnt; i++) { +#define IAVF_GTPU_HDR_TEID_OFFS0 4 +#define IAVF_GTPU_HDR_TEID_OFFS1 6 +#define IAVF_GTPU_HDR_N_PDU_AND_NEXT_EXTHDR_OFFS 10 +#define IAVF_GTPU_HDR_NEXT_EXTHDR_TYPE_MASK 0x00FF /* skip N_PDU */ +/* PDU Session Container Extension Header (PSC) */ +#define IAVF_GTPU_PSC_EXTHDR_TYPE 0x85 +#define IAVF_GTPU_HDR_PSC_PDU_TYPE_AND_QFI_OFFS 13 +#define IAVF_GTPU_HDR_PSC_PDU_QFI_MASK 0x3F /* skip Type */ +#define IAVF_GTPU_EH_QFI_IDX 1 + + if (fltr->flex_words[i].offset < adj_offs) + return -EINVAL; + + hdr_offs = fltr->flex_words[i].offset - adj_offs; + + switch (hdr_offs) { + case IAVF_GTPU_HDR_TEID_OFFS0: + case IAVF_GTPU_HDR_TEID_OFFS1: { + __be16 *pay_word = (__be16 *)ghdr->buffer; + + pay_word[hdr_offs >> 1] = htons(fltr->flex_words[i].word); + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(ghdr, GTPU_IP, TEID); + } + break; + case IAVF_GTPU_HDR_N_PDU_AND_NEXT_EXTHDR_OFFS: + if ((fltr->flex_words[i].word & + IAVF_GTPU_HDR_NEXT_EXTHDR_TYPE_MASK) != + IAVF_GTPU_PSC_EXTHDR_TYPE) + return -EOPNOTSUPP; + if (!ehdr) + ehdr = &proto_hdrs->proto_hdr[proto_hdrs->count++]; + VIRTCHNL_SET_PROTO_HDR_TYPE(ehdr, GTPU_EH); + break; + case IAVF_GTPU_HDR_PSC_PDU_TYPE_AND_QFI_OFFS: + if (!ehdr) + return -EINVAL; + ehdr->buffer[IAVF_GTPU_EH_QFI_IDX] = + fltr->flex_words[i].word & + IAVF_GTPU_HDR_PSC_PDU_QFI_MASK; + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(ehdr, GTPU_EH, QFI); + break; + default: + return -EINVAL; + } + } + + uhdr->field_selector = 0; /* The PF ignores the UDP header fields */ + + return 0; +} + +/** + * iavf_fill_fdir_pfcp_hdr - fill the PFCP protocol header + * @fltr: Flow Director filter data structure + * @proto_hdrs: Flow Director protocol headers data structure + * + * Returns 0 if the PFCP protocol header is set successfully + */ +static int +iavf_fill_fdir_pfcp_hdr(struct iavf_fdir_fltr *fltr, + struct virtchnl_proto_hdrs *proto_hdrs) +{ + struct virtchnl_proto_hdr *uhdr = &proto_hdrs->proto_hdr[proto_hdrs->count - 1]; + struct virtchnl_proto_hdr *hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++]; + u16 adj_offs, hdr_offs; + int i; + + VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, PFCP); + + adj_offs = iavf_pkt_udp_no_pay_len(fltr); + + for (i = 0; i < fltr->flex_cnt; i++) { +#define IAVF_PFCP_HDR_SFIELD_AND_MSG_TYPE_OFFS 0 + if (fltr->flex_words[i].offset < adj_offs) + return -EINVAL; + + hdr_offs = fltr->flex_words[i].offset - adj_offs; + + switch (hdr_offs) { + case IAVF_PFCP_HDR_SFIELD_AND_MSG_TYPE_OFFS: + hdr->buffer[0] = (fltr->flex_words[i].word >> 8) & 0xff; + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, PFCP, S_FIELD); + break; + default: + return -EINVAL; + } + } + + uhdr->field_selector = 0; /* The PF ignores the UDP header fields */ + + return 0; +} + +/** + * iavf_fill_fdir_nat_t_esp_hdr - fill the NAT-T-ESP protocol header + * @fltr: Flow Director filter data structure + * @proto_hdrs: Flow Director protocol headers data structure + * + * Returns 0 if the NAT-T-ESP protocol header is set successfully + */ +static int +iavf_fill_fdir_nat_t_esp_hdr(struct iavf_fdir_fltr *fltr, + struct virtchnl_proto_hdrs *proto_hdrs) +{ + struct virtchnl_proto_hdr *uhdr = &proto_hdrs->proto_hdr[proto_hdrs->count - 1]; + struct virtchnl_proto_hdr *hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++]; + u16 adj_offs, hdr_offs; + u32 spi = 0; + int i; + + VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, ESP); + + adj_offs = iavf_pkt_udp_no_pay_len(fltr); + + for (i = 0; i < fltr->flex_cnt; i++) { +#define IAVF_NAT_T_ESP_SPI_OFFS0 0 +#define IAVF_NAT_T_ESP_SPI_OFFS1 2 + if (fltr->flex_words[i].offset < adj_offs) + return -EINVAL; + + hdr_offs = fltr->flex_words[i].offset - adj_offs; + + switch (hdr_offs) { + case IAVF_NAT_T_ESP_SPI_OFFS0: + spi |= fltr->flex_words[i].word << 16; + break; + case IAVF_NAT_T_ESP_SPI_OFFS1: + spi |= fltr->flex_words[i].word; + break; + default: + return -EINVAL; + } + } + + if (!spi) + return -EOPNOTSUPP; /* Not support IKE Header Format with SPI 0 */ + + *(__be32 *)hdr->buffer = htonl(spi); + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, ESP, SPI); + + uhdr->field_selector = 0; /* The PF ignores the UDP header fields */ + + return 0; +} + +/** + * iavf_fill_fdir_udp_flex_pay_hdr - fill the UDP payload header + * @fltr: Flow Director filter data structure + * @proto_hdrs: Flow Director protocol headers data structure + * + * Returns 0 if the UDP payload defined protocol header is set successfully + */ +static int +iavf_fill_fdir_udp_flex_pay_hdr(struct iavf_fdir_fltr *fltr, + struct virtchnl_proto_hdrs *proto_hdrs) +{ + int err; + + switch (ntohs(fltr->ip_data.dst_port)) { + case GTPU_PORT: + err = iavf_fill_fdir_gtpu_hdr(fltr, proto_hdrs); + break; + case NAT_T_ESP_PORT: + err = iavf_fill_fdir_nat_t_esp_hdr(fltr, proto_hdrs); + break; + case PFCP_PORT: + err = iavf_fill_fdir_pfcp_hdr(fltr, proto_hdrs); + break; + default: + err = -EOPNOTSUPP; + break; + } + + return err; +} + +/** + * iavf_fill_fdir_ip4_hdr - fill the IPv4 protocol header + * @fltr: Flow Director filter data structure + * @proto_hdrs: Flow Director protocol headers data structure + * + * Returns 0 if the IPv4 protocol header is set successfully + */ +static int +iavf_fill_fdir_ip4_hdr(struct iavf_fdir_fltr *fltr, + struct virtchnl_proto_hdrs *proto_hdrs) +{ + struct virtchnl_proto_hdr *hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++]; + struct iphdr *iph = (struct iphdr *)hdr->buffer; + + VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, IPV4); + + if (fltr->ip_mask.tos == U8_MAX) { + iph->tos = fltr->ip_data.tos; + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, IPV4, DSCP); + } + + if (fltr->ip_mask.proto == U8_MAX) { + iph->protocol = fltr->ip_data.proto; + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, IPV4, PROT); + } + + if (fltr->ip_mask.v4_addrs.src_ip == htonl(U32_MAX)) { + iph->saddr = fltr->ip_data.v4_addrs.src_ip; + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, IPV4, SRC); + } + + if (fltr->ip_mask.v4_addrs.dst_ip == htonl(U32_MAX)) { + iph->daddr = fltr->ip_data.v4_addrs.dst_ip; + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, IPV4, DST); + } + + fltr->ip_ver = 4; + + return 0; +} + +/** + * iavf_fill_fdir_ip6_hdr - fill the IPv6 protocol header + * @fltr: Flow Director filter data structure + * @proto_hdrs: Flow Director protocol headers data structure + * + * Returns 0 if the IPv6 protocol header is set successfully + */ +static int +iavf_fill_fdir_ip6_hdr(struct iavf_fdir_fltr *fltr, + struct virtchnl_proto_hdrs *proto_hdrs) +{ + struct virtchnl_proto_hdr *hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++]; + struct ipv6hdr *iph = (struct ipv6hdr *)hdr->buffer; + + VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, IPV6); + + if (fltr->ip_mask.tclass == U8_MAX) { + iph->priority = (fltr->ip_data.tclass >> 4) & 0xF; + iph->flow_lbl[0] = (fltr->ip_data.tclass << 4) & 0xF0; + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, IPV6, TC); + } + + if (fltr->ip_mask.proto == U8_MAX) { + iph->nexthdr = fltr->ip_data.proto; + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, IPV6, PROT); + } + + if (!memcmp(&fltr->ip_mask.v6_addrs.src_ip, &ipv6_addr_full_mask, + sizeof(struct in6_addr))) { + memcpy(&iph->saddr, &fltr->ip_data.v6_addrs.src_ip, + sizeof(struct in6_addr)); + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, IPV6, SRC); + } + + if (!memcmp(&fltr->ip_mask.v6_addrs.dst_ip, &ipv6_addr_full_mask, + sizeof(struct in6_addr))) { + memcpy(&iph->daddr, &fltr->ip_data.v6_addrs.dst_ip, + sizeof(struct in6_addr)); + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, IPV6, DST); + } + + fltr->ip_ver = 6; + + return 0; +} + +/** + * iavf_fill_fdir_tcp_hdr - fill the TCP protocol header + * @fltr: Flow Director filter data structure + * @proto_hdrs: Flow Director protocol headers data structure + * + * Returns 0 if the TCP protocol header is set successfully + */ +static int +iavf_fill_fdir_tcp_hdr(struct iavf_fdir_fltr *fltr, + struct virtchnl_proto_hdrs *proto_hdrs) +{ + struct virtchnl_proto_hdr *hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++]; + struct tcphdr *tcph = (struct tcphdr *)hdr->buffer; + + VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, TCP); + + if (fltr->ip_mask.src_port == htons(U16_MAX)) { + tcph->source = fltr->ip_data.src_port; + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, TCP, SRC_PORT); + } + + if (fltr->ip_mask.dst_port == htons(U16_MAX)) { + tcph->dest = fltr->ip_data.dst_port; + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, TCP, DST_PORT); + } + + return 0; +} + +/** + * iavf_fill_fdir_udp_hdr - fill the UDP protocol header + * @fltr: Flow Director filter data structure + * @proto_hdrs: Flow Director protocol headers data structure + * + * Returns 0 if the UDP protocol header is set successfully + */ +static int +iavf_fill_fdir_udp_hdr(struct iavf_fdir_fltr *fltr, + struct virtchnl_proto_hdrs *proto_hdrs) +{ + struct virtchnl_proto_hdr *hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++]; + struct udphdr *udph = (struct udphdr *)hdr->buffer; + + VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, UDP); + + if (fltr->ip_mask.src_port == htons(U16_MAX)) { + udph->source = fltr->ip_data.src_port; + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, UDP, SRC_PORT); + } + + if (fltr->ip_mask.dst_port == htons(U16_MAX)) { + udph->dest = fltr->ip_data.dst_port; + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, UDP, DST_PORT); + } + + if (!fltr->flex_cnt) + return 0; + + return iavf_fill_fdir_udp_flex_pay_hdr(fltr, proto_hdrs); +} + +/** + * iavf_fill_fdir_sctp_hdr - fill the SCTP protocol header + * @fltr: Flow Director filter data structure + * @proto_hdrs: Flow Director protocol headers data structure + * + * Returns 0 if the SCTP protocol header is set successfully + */ +static int +iavf_fill_fdir_sctp_hdr(struct iavf_fdir_fltr *fltr, + struct virtchnl_proto_hdrs *proto_hdrs) +{ + struct virtchnl_proto_hdr *hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++]; + struct sctphdr *sctph = (struct sctphdr *)hdr->buffer; + + VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, SCTP); + + if (fltr->ip_mask.src_port == htons(U16_MAX)) { + sctph->source = fltr->ip_data.src_port; + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, SCTP, SRC_PORT); + } + + if (fltr->ip_mask.dst_port == htons(U16_MAX)) { + sctph->dest = fltr->ip_data.dst_port; + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, SCTP, DST_PORT); + } + + return 0; +} + +/** + * iavf_fill_fdir_ah_hdr - fill the AH protocol header + * @fltr: Flow Director filter data structure + * @proto_hdrs: Flow Director protocol headers data structure + * + * Returns 0 if the AH protocol header is set successfully + */ +static int +iavf_fill_fdir_ah_hdr(struct iavf_fdir_fltr *fltr, + struct virtchnl_proto_hdrs *proto_hdrs) +{ + struct virtchnl_proto_hdr *hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++]; + struct ip_auth_hdr *ah = (struct ip_auth_hdr *)hdr->buffer; + + VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, AH); + + if (fltr->ip_mask.spi == htonl(U32_MAX)) { + ah->spi = fltr->ip_data.spi; + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, AH, SPI); + } + + return 0; +} + +/** + * iavf_fill_fdir_esp_hdr - fill the ESP protocol header + * @fltr: Flow Director filter data structure + * @proto_hdrs: Flow Director protocol headers data structure + * + * Returns 0 if the ESP protocol header is set successfully + */ +static int +iavf_fill_fdir_esp_hdr(struct iavf_fdir_fltr *fltr, + struct virtchnl_proto_hdrs *proto_hdrs) +{ + struct virtchnl_proto_hdr *hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++]; + struct ip_esp_hdr *esph = (struct ip_esp_hdr *)hdr->buffer; + + VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, ESP); + + if (fltr->ip_mask.spi == htonl(U32_MAX)) { + esph->spi = fltr->ip_data.spi; + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, ESP, SPI); + } + + return 0; +} + +/** + * iavf_fill_fdir_l4_hdr - fill the L4 protocol header + * @fltr: Flow Director filter data structure + * @proto_hdrs: Flow Director protocol headers data structure + * + * Returns 0 if the L4 protocol header is set successfully + */ +static int +iavf_fill_fdir_l4_hdr(struct iavf_fdir_fltr *fltr, + struct virtchnl_proto_hdrs *proto_hdrs) +{ + struct virtchnl_proto_hdr *hdr; + __be32 *l4_4_data; + + if (!fltr->ip_mask.proto) /* IPv4/IPv6 header only */ + return 0; + + hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++]; + l4_4_data = (__be32 *)hdr->buffer; + + /* L2TPv3 over IP with 'Session ID' */ + if (fltr->ip_data.proto == 115 && fltr->ip_mask.l4_header == htonl(U32_MAX)) { + VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, L2TPV3); + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, L2TPV3, SESS_ID); + + *l4_4_data = fltr->ip_data.l4_header; + } else { + return -EOPNOTSUPP; + } + + return 0; +} + +/** + * iavf_fill_fdir_eth_hdr - fill the Ethernet protocol header + * @fltr: Flow Director filter data structure + * @proto_hdrs: Flow Director protocol headers data structure + * + * Returns 0 if the Ethernet protocol header is set successfully + */ +static int +iavf_fill_fdir_eth_hdr(struct iavf_fdir_fltr *fltr, + struct virtchnl_proto_hdrs *proto_hdrs) +{ + struct virtchnl_proto_hdr *hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++]; + struct ethhdr *ehdr = (struct ethhdr *)hdr->buffer; + + VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, ETH); + + if (fltr->eth_mask.etype == htons(U16_MAX)) { + if (fltr->eth_data.etype == htons(ETH_P_IP) || + fltr->eth_data.etype == htons(ETH_P_IPV6)) + return -EOPNOTSUPP; + + ehdr->h_proto = fltr->eth_data.etype; + VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, ETH, ETHERTYPE); + } + + return 0; +} + +/** + * iavf_fill_fdir_add_msg - fill the Flow Director filter into virtchnl message + * @adapter: pointer to the VF adapter structure + * @fltr: Flow Director filter data structure + * + * Returns 0 if the add Flow Director virtchnl message is filled successfully + */ +int iavf_fill_fdir_add_msg(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr) +{ + struct virtchnl_fdir_add *vc_msg = &fltr->vc_add_msg; + struct virtchnl_proto_hdrs *proto_hdrs; + int err; + + proto_hdrs = &vc_msg->rule_cfg.proto_hdrs; + + err = iavf_fill_fdir_eth_hdr(fltr, proto_hdrs); /* L2 always exists */ + if (err) + return err; + + switch (fltr->flow_type) { + case IAVF_FDIR_FLOW_IPV4_TCP: + err = iavf_fill_fdir_ip4_hdr(fltr, proto_hdrs) | + iavf_fill_fdir_tcp_hdr(fltr, proto_hdrs); + break; + case IAVF_FDIR_FLOW_IPV4_UDP: + err = iavf_fill_fdir_ip4_hdr(fltr, proto_hdrs) | + iavf_fill_fdir_udp_hdr(fltr, proto_hdrs); + break; + case IAVF_FDIR_FLOW_IPV4_SCTP: + err = iavf_fill_fdir_ip4_hdr(fltr, proto_hdrs) | + iavf_fill_fdir_sctp_hdr(fltr, proto_hdrs); + break; + case IAVF_FDIR_FLOW_IPV4_AH: + err = iavf_fill_fdir_ip4_hdr(fltr, proto_hdrs) | + iavf_fill_fdir_ah_hdr(fltr, proto_hdrs); + break; + case IAVF_FDIR_FLOW_IPV4_ESP: + err = iavf_fill_fdir_ip4_hdr(fltr, proto_hdrs) | + iavf_fill_fdir_esp_hdr(fltr, proto_hdrs); + break; + case IAVF_FDIR_FLOW_IPV4_OTHER: + err = iavf_fill_fdir_ip4_hdr(fltr, proto_hdrs) | + iavf_fill_fdir_l4_hdr(fltr, proto_hdrs); + break; + case IAVF_FDIR_FLOW_IPV6_TCP: + err = iavf_fill_fdir_ip6_hdr(fltr, proto_hdrs) | + iavf_fill_fdir_tcp_hdr(fltr, proto_hdrs); + break; + case IAVF_FDIR_FLOW_IPV6_UDP: + err = iavf_fill_fdir_ip6_hdr(fltr, proto_hdrs) | + iavf_fill_fdir_udp_hdr(fltr, proto_hdrs); + break; + case IAVF_FDIR_FLOW_IPV6_SCTP: + err = iavf_fill_fdir_ip6_hdr(fltr, proto_hdrs) | + iavf_fill_fdir_sctp_hdr(fltr, proto_hdrs); + break; + case IAVF_FDIR_FLOW_IPV6_AH: + err = iavf_fill_fdir_ip6_hdr(fltr, proto_hdrs) | + iavf_fill_fdir_ah_hdr(fltr, proto_hdrs); + break; + case IAVF_FDIR_FLOW_IPV6_ESP: + err = iavf_fill_fdir_ip6_hdr(fltr, proto_hdrs) | + iavf_fill_fdir_esp_hdr(fltr, proto_hdrs); + break; + case IAVF_FDIR_FLOW_IPV6_OTHER: + err = iavf_fill_fdir_ip6_hdr(fltr, proto_hdrs) | + iavf_fill_fdir_l4_hdr(fltr, proto_hdrs); + break; + case IAVF_FDIR_FLOW_NON_IP_L2: + break; + default: + err = -EINVAL; + break; + } + + if (err) + return err; + + vc_msg->vsi_id = adapter->vsi.id; + vc_msg->rule_cfg.action_set.count = 1; + vc_msg->rule_cfg.action_set.actions[0].type = fltr->action; + vc_msg->rule_cfg.action_set.actions[0].act_conf.queue.index = fltr->q_index; + + return 0; +} + +/** + * iavf_fdir_flow_proto_name - get the flow protocol name + * @flow_type: Flow Director filter flow type + **/ +static const char *iavf_fdir_flow_proto_name(enum iavf_fdir_flow_type flow_type) +{ + switch (flow_type) { + case IAVF_FDIR_FLOW_IPV4_TCP: + case IAVF_FDIR_FLOW_IPV6_TCP: + return "TCP"; + case IAVF_FDIR_FLOW_IPV4_UDP: + case IAVF_FDIR_FLOW_IPV6_UDP: + return "UDP"; + case IAVF_FDIR_FLOW_IPV4_SCTP: + case IAVF_FDIR_FLOW_IPV6_SCTP: + return "SCTP"; + case IAVF_FDIR_FLOW_IPV4_AH: + case IAVF_FDIR_FLOW_IPV6_AH: + return "AH"; + case IAVF_FDIR_FLOW_IPV4_ESP: + case IAVF_FDIR_FLOW_IPV6_ESP: + return "ESP"; + case IAVF_FDIR_FLOW_IPV4_OTHER: + case IAVF_FDIR_FLOW_IPV6_OTHER: + return "Other"; + case IAVF_FDIR_FLOW_NON_IP_L2: + return "Ethernet"; + default: + return NULL; + } +} + +/** + * iavf_print_fdir_fltr + * @adapter: adapter structure + * @fltr: Flow Director filter to print + * + * Print the Flow Director filter + **/ +void iavf_print_fdir_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr) +{ + const char *proto = iavf_fdir_flow_proto_name(fltr->flow_type); + + if (!proto) + return; + + switch (fltr->flow_type) { + case IAVF_FDIR_FLOW_IPV4_TCP: + case IAVF_FDIR_FLOW_IPV4_UDP: + case IAVF_FDIR_FLOW_IPV4_SCTP: + dev_info(&adapter->pdev->dev, "Rule ID: %u dst_ip: %pI4 src_ip %pI4 %s: dst_port %hu src_port %hu\n", + fltr->loc, + &fltr->ip_data.v4_addrs.dst_ip, + &fltr->ip_data.v4_addrs.src_ip, + proto, + ntohs(fltr->ip_data.dst_port), + ntohs(fltr->ip_data.src_port)); + break; + case IAVF_FDIR_FLOW_IPV4_AH: + case IAVF_FDIR_FLOW_IPV4_ESP: + dev_info(&adapter->pdev->dev, "Rule ID: %u dst_ip: %pI4 src_ip %pI4 %s: SPI %u\n", + fltr->loc, + &fltr->ip_data.v4_addrs.dst_ip, + &fltr->ip_data.v4_addrs.src_ip, + proto, + ntohl(fltr->ip_data.spi)); + break; + case IAVF_FDIR_FLOW_IPV4_OTHER: + dev_info(&adapter->pdev->dev, "Rule ID: %u dst_ip: %pI4 src_ip %pI4 proto: %u L4_bytes: 0x%x\n", + fltr->loc, + &fltr->ip_data.v4_addrs.dst_ip, + &fltr->ip_data.v4_addrs.src_ip, + fltr->ip_data.proto, + ntohl(fltr->ip_data.l4_header)); + break; + case IAVF_FDIR_FLOW_IPV6_TCP: + case IAVF_FDIR_FLOW_IPV6_UDP: + case IAVF_FDIR_FLOW_IPV6_SCTP: + dev_info(&adapter->pdev->dev, "Rule ID: %u dst_ip: %pI6 src_ip %pI6 %s: dst_port %hu src_port %hu\n", + fltr->loc, + &fltr->ip_data.v6_addrs.dst_ip, + &fltr->ip_data.v6_addrs.src_ip, + proto, + ntohs(fltr->ip_data.dst_port), + ntohs(fltr->ip_data.src_port)); + break; + case IAVF_FDIR_FLOW_IPV6_AH: + case IAVF_FDIR_FLOW_IPV6_ESP: + dev_info(&adapter->pdev->dev, "Rule ID: %u dst_ip: %pI6 src_ip %pI6 %s: SPI %u\n", + fltr->loc, + &fltr->ip_data.v6_addrs.dst_ip, + &fltr->ip_data.v6_addrs.src_ip, + proto, + ntohl(fltr->ip_data.spi)); + break; + case IAVF_FDIR_FLOW_IPV6_OTHER: + dev_info(&adapter->pdev->dev, "Rule ID: %u dst_ip: %pI6 src_ip %pI6 proto: %u L4_bytes: 0x%x\n", + fltr->loc, + &fltr->ip_data.v6_addrs.dst_ip, + &fltr->ip_data.v6_addrs.src_ip, + fltr->ip_data.proto, + ntohl(fltr->ip_data.l4_header)); + break; + case IAVF_FDIR_FLOW_NON_IP_L2: + dev_info(&adapter->pdev->dev, "Rule ID: %u eth_type: 0x%x\n", + fltr->loc, + ntohs(fltr->eth_data.etype)); + break; + default: + break; + } +} + +/** + * iavf_fdir_is_dup_fltr - test if filter is already in list + * @adapter: pointer to the VF adapter structure + * @fltr: Flow Director filter data structure + * + * Returns true if the filter is found in the list + */ +bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr) +{ + struct iavf_fdir_fltr *tmp; + + list_for_each_entry(tmp, &adapter->fdir_list_head, list) { + if (tmp->flow_type != fltr->flow_type) + continue; + + if (!memcmp(&tmp->eth_data, &fltr->eth_data, + sizeof(fltr->eth_data)) && + !memcmp(&tmp->ip_data, &fltr->ip_data, + sizeof(fltr->ip_data)) && + !memcmp(&tmp->ext_data, &fltr->ext_data, + sizeof(fltr->ext_data))) + return true; + } + + return false; +} + +/** + * iavf_find_fdir_fltr_by_loc - find filter with location + * @adapter: pointer to the VF adapter structure + * @loc: location to find. + * + * Returns pointer to Flow Director filter if found or null + */ +struct iavf_fdir_fltr *iavf_find_fdir_fltr_by_loc(struct iavf_adapter *adapter, u32 loc) +{ + struct iavf_fdir_fltr *rule; + + list_for_each_entry(rule, &adapter->fdir_list_head, list) + if (rule->loc == loc) + return rule; + + return NULL; +} + +/** + * iavf_fdir_list_add_fltr - add a new node to the flow director filter list + * @adapter: pointer to the VF adapter structure + * @fltr: filter node to add to structure + */ +void iavf_fdir_list_add_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr) +{ + struct iavf_fdir_fltr *rule, *parent = NULL; + + list_for_each_entry(rule, &adapter->fdir_list_head, list) { + if (rule->loc >= fltr->loc) + break; + parent = rule; + } + + if (parent) + list_add(&fltr->list, &parent->list); + else + list_add(&fltr->list, &adapter->fdir_list_head); +} diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.h b/drivers/net/ethernet/intel/iavf/iavf_fdir.h new file mode 100644 index 000000000000..33c55c366315 --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.h @@ -0,0 +1,118 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2021, Intel Corporation. */ + +#ifndef _IAVF_FDIR_H_ +#define _IAVF_FDIR_H_ + +struct iavf_adapter; + +/* State of Flow Director filter */ +enum iavf_fdir_fltr_state_t { + IAVF_FDIR_FLTR_ADD_REQUEST, /* User requests to add filter */ + IAVF_FDIR_FLTR_ADD_PENDING, /* Filter pending add by the PF */ + IAVF_FDIR_FLTR_DEL_REQUEST, /* User requests to delete filter */ + IAVF_FDIR_FLTR_DEL_PENDING, /* Filter pending delete by the PF */ + IAVF_FDIR_FLTR_ACTIVE, /* Filter is active */ +}; + +enum iavf_fdir_flow_type { + /* NONE - used for undef/error */ + IAVF_FDIR_FLOW_NONE = 0, + IAVF_FDIR_FLOW_IPV4_TCP, + IAVF_FDIR_FLOW_IPV4_UDP, + IAVF_FDIR_FLOW_IPV4_SCTP, + IAVF_FDIR_FLOW_IPV4_AH, + IAVF_FDIR_FLOW_IPV4_ESP, + IAVF_FDIR_FLOW_IPV4_OTHER, + IAVF_FDIR_FLOW_IPV6_TCP, + IAVF_FDIR_FLOW_IPV6_UDP, + IAVF_FDIR_FLOW_IPV6_SCTP, + IAVF_FDIR_FLOW_IPV6_AH, + IAVF_FDIR_FLOW_IPV6_ESP, + IAVF_FDIR_FLOW_IPV6_OTHER, + IAVF_FDIR_FLOW_NON_IP_L2, + /* MAX - this must be last and add anything new just above it */ + IAVF_FDIR_FLOW_PTYPE_MAX, +}; + +/* Must not exceed the array element number of '__be32 data[2]' in the ethtool + * 'struct ethtool_rx_flow_spec.m_ext.data[2]' to express the flex-byte (word). + */ +#define IAVF_FLEX_WORD_NUM 2 + +struct iavf_flex_word { + u16 offset; + u16 word; +}; + +struct iavf_ipv4_addrs { + __be32 src_ip; + __be32 dst_ip; +}; + +struct iavf_ipv6_addrs { + struct in6_addr src_ip; + struct in6_addr dst_ip; +}; + +struct iavf_fdir_eth { + __be16 etype; +}; + +struct iavf_fdir_ip { + union { + struct iavf_ipv4_addrs v4_addrs; + struct iavf_ipv6_addrs v6_addrs; + }; + __be16 src_port; + __be16 dst_port; + __be32 l4_header; /* first 4 bytes of the layer 4 header */ + __be32 spi; /* security parameter index for AH/ESP */ + union { + u8 tos; + u8 tclass; + }; + u8 proto; +}; + +struct iavf_fdir_extra { + u32 usr_def[IAVF_FLEX_WORD_NUM]; +}; + +/* bookkeeping of Flow Director filters */ +struct iavf_fdir_fltr { + enum iavf_fdir_fltr_state_t state; + struct list_head list; + + enum iavf_fdir_flow_type flow_type; + + struct iavf_fdir_eth eth_data; + struct iavf_fdir_eth eth_mask; + + struct iavf_fdir_ip ip_data; + struct iavf_fdir_ip ip_mask; + + struct iavf_fdir_extra ext_data; + struct iavf_fdir_extra ext_mask; + + enum virtchnl_action action; + + /* flex byte filter data */ + u8 ip_ver; /* used to adjust the flex offset, 4 : IPv4, 6 : IPv6 */ + u8 flex_cnt; + struct iavf_flex_word flex_words[IAVF_FLEX_WORD_NUM]; + + u32 flow_id; + + u32 loc; /* Rule location inside the flow table */ + u32 q_index; + + struct virtchnl_fdir_add vc_add_msg; +}; + +int iavf_fill_fdir_add_msg(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); +void iavf_print_fdir_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); +bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); +void iavf_fdir_list_add_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); +struct iavf_fdir_fltr *iavf_find_fdir_fltr_by_loc(struct iavf_adapter *adapter, u32 loc); +#endif /* _IAVF_FDIR_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index dc5b3c06d1e0..e612c24fa384 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -959,8 +959,10 @@ void iavf_down(struct iavf_adapter *adapter) { struct net_device *netdev = adapter->netdev; struct iavf_vlan_filter *vlf; - struct iavf_mac_filter *f; struct iavf_cloud_filter *cf; + struct iavf_fdir_fltr *fdir; + struct iavf_mac_filter *f; + struct iavf_adv_rss *rss; if (adapter->state <= __IAVF_DOWN_PENDING) return; @@ -996,6 +998,19 @@ void iavf_down(struct iavf_adapter *adapter) } spin_unlock_bh(&adapter->cloud_filter_list_lock); + /* remove all Flow Director filters */ + spin_lock_bh(&adapter->fdir_fltr_lock); + list_for_each_entry(fdir, &adapter->fdir_list_head, list) { + fdir->state = IAVF_FDIR_FLTR_DEL_REQUEST; + } + spin_unlock_bh(&adapter->fdir_fltr_lock); + + /* remove all advance RSS configuration */ + spin_lock_bh(&adapter->adv_rss_lock); + list_for_each_entry(rss, &adapter->adv_rss_list_head, list) + 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) { /* cancel any current operation */ @@ -1007,6 +1022,8 @@ void iavf_down(struct iavf_adapter *adapter) adapter->aq_required = IAVF_FLAG_AQ_DEL_MAC_FILTER; adapter->aq_required |= IAVF_FLAG_AQ_DEL_VLAN_FILTER; adapter->aq_required |= IAVF_FLAG_AQ_DEL_CLOUD_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_DEL_FDIR_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_DEL_ADV_RSS_CFG; adapter->aq_required |= IAVF_FLAG_AQ_DISABLE_QUEUES; } @@ -1629,6 +1646,22 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter) iavf_add_cloud_filter(adapter); return 0; } + if (adapter->aq_required & IAVF_FLAG_AQ_ADD_FDIR_FILTER) { + iavf_add_fdir_filter(adapter); + return IAVF_SUCCESS; + } + if (adapter->aq_required & IAVF_FLAG_AQ_DEL_FDIR_FILTER) { + iavf_del_fdir_filter(adapter); + return IAVF_SUCCESS; + } + if (adapter->aq_required & IAVF_FLAG_AQ_ADD_ADV_RSS_CFG) { + iavf_add_adv_rss_cfg(adapter); + return 0; + } + if (adapter->aq_required & IAVF_FLAG_AQ_DEL_ADV_RSS_CFG) { + iavf_del_adv_rss_cfg(adapter); + return 0; + } return -EAGAIN; } @@ -2529,7 +2562,7 @@ validate_bw: } /** - * iavf_validate_channel_config - validate queue mapping info + * iavf_validate_ch_config - validate queue mapping info * @adapter: board private structure * @mqprio_qopt: queue parameters * @@ -3525,6 +3558,8 @@ int iavf_process_config(struct iavf_adapter *adapter) /* Enable cloud filter if ADQ is supported */ if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) hw_features |= NETIF_F_HW_TC; + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_USO) + hw_features |= NETIF_F_GSO_UDP_L4; netdev->hw_features |= hw_features; @@ -3738,10 +3773,14 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) spin_lock_init(&adapter->mac_vlan_list_lock); spin_lock_init(&adapter->cloud_filter_list_lock); + spin_lock_init(&adapter->fdir_fltr_lock); + spin_lock_init(&adapter->adv_rss_lock); INIT_LIST_HEAD(&adapter->mac_filter_list); INIT_LIST_HEAD(&adapter->vlan_filter_list); INIT_LIST_HEAD(&adapter->cloud_filter_list); + INIT_LIST_HEAD(&adapter->fdir_list_head); + INIT_LIST_HEAD(&adapter->adv_rss_list_head); INIT_WORK(&adapter->reset_task, iavf_reset_task); INIT_WORK(&adapter->adminq_task, iavf_adminq_task); @@ -3845,7 +3884,9 @@ 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_fdir_fltr *fdir, *fdirtmp; struct iavf_vlan_filter *vlf, *vlftmp; + struct iavf_adv_rss *rss, *rsstmp; struct iavf_mac_filter *f, *ftmp; struct iavf_cloud_filter *cf, *cftmp; struct iavf_hw *hw = &adapter->hw; @@ -3899,8 +3940,6 @@ static void iavf_remove(struct pci_dev *pdev) iounmap(hw->hw_addr); pci_release_regions(pdev); - iavf_free_all_tx_resources(adapter); - iavf_free_all_rx_resources(adapter); iavf_free_queues(adapter); kfree(adapter->vf_res); spin_lock_bh(&adapter->mac_vlan_list_lock); @@ -3926,6 +3965,21 @@ static void iavf_remove(struct pci_dev *pdev) } spin_unlock_bh(&adapter->cloud_filter_list_lock); + spin_lock_bh(&adapter->fdir_fltr_lock); + list_for_each_entry_safe(fdir, fdirtmp, &adapter->fdir_list_head, list) { + list_del(&fdir->list); + kfree(fdir); + } + spin_unlock_bh(&adapter->fdir_fltr_lock); + + spin_lock_bh(&adapter->adv_rss_lock); + list_for_each_entry_safe(rss, rsstmp, &adapter->adv_rss_list_head, + list) { + list_del(&rss->list); + kfree(rss); + } + spin_unlock_bh(&adapter->adv_rss_lock); + free_netdev(netdev); pci_disable_pcie_error_reporting(pdev); diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index ffaf2742a2e0..3525eab8e9f9 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -1905,13 +1905,20 @@ static int iavf_tso(struct iavf_tx_buffer *first, u8 *hdr_len, /* determine offset of inner transport header */ l4_offset = l4.hdr - skb->data; - /* remove payload length from inner checksum */ paylen = skb->len - l4_offset; - csum_replace_by_diff(&l4.tcp->check, (__force __wsum)htonl(paylen)); - /* compute length of segmentation header */ - *hdr_len = (l4.tcp->doff * 4) + l4_offset; + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) { + csum_replace_by_diff(&l4.udp->check, + (__force __wsum)htonl(paylen)); + /* compute length of UDP segmentation header */ + *hdr_len = (u8)sizeof(l4.udp) + l4_offset; + } else { + csum_replace_by_diff(&l4.tcp->check, + (__force __wsum)htonl(paylen)); + /* compute length of TCP segmentation header */ + *hdr_len = (u8)((l4.tcp->doff * 4) + l4_offset); + } /* pull values out of skb_shinfo */ gso_size = skb_shinfo(skb)->gso_size; @@ -2098,7 +2105,7 @@ static int iavf_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, } /** - * iavf_create_tx_ctx Build the Tx context descriptor + * iavf_create_tx_ctx - Build the Tx context descriptor * @tx_ring: ring to create the descriptor on * @cd_type_cmd_tso_mss: Quad Word 1 * @cd_tunneling: Quad Word 0 - bits 0-31 diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 647e7fde11b4..0eab3c43bdc5 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -140,6 +140,9 @@ int iavf_send_vf_config_msg(struct iavf_adapter *adapter) VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM | VIRTCHNL_VF_OFFLOAD_REQ_QUEUES | VIRTCHNL_VF_OFFLOAD_ADQ | + VIRTCHNL_VF_OFFLOAD_USO | + VIRTCHNL_VF_OFFLOAD_FDIR_PF | + VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF | VIRTCHNL_VF_CAP_ADV_LINK_SPEED; adapter->current_op = VIRTCHNL_OP_GET_VF_RESOURCES; @@ -1005,7 +1008,7 @@ iavf_set_adapter_link_speed_from_vpe(struct iavf_adapter *adapter, } /** - * iavf_enable_channel + * iavf_enable_channels * @adapter: adapter structure * * Request that the PF enable channels as specified by @@ -1046,7 +1049,7 @@ void iavf_enable_channels(struct iavf_adapter *adapter) } /** - * iavf_disable_channel + * iavf_disable_channels * @adapter: adapter structure * * Request that the PF disable channels that are configured @@ -1198,6 +1201,200 @@ void iavf_del_cloud_filter(struct iavf_adapter *adapter) } /** + * iavf_add_fdir_filter + * @adapter: the VF adapter structure + * + * Request that the PF add Flow Director filters as specified + * by the user via ethtool. + **/ +void iavf_add_fdir_filter(struct iavf_adapter *adapter) +{ + struct iavf_fdir_fltr *fdir; + struct virtchnl_fdir_add *f; + bool process_fltr = false; + int len; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot add Flow Director filter, command %d pending\n", + adapter->current_op); + return; + } + + len = sizeof(struct virtchnl_fdir_add); + f = kzalloc(len, GFP_KERNEL); + if (!f) + return; + + spin_lock_bh(&adapter->fdir_fltr_lock); + list_for_each_entry(fdir, &adapter->fdir_list_head, list) { + if (fdir->state == IAVF_FDIR_FLTR_ADD_REQUEST) { + process_fltr = true; + fdir->state = IAVF_FDIR_FLTR_ADD_PENDING; + memcpy(f, &fdir->vc_add_msg, len); + break; + } + } + spin_unlock_bh(&adapter->fdir_fltr_lock); + + if (!process_fltr) { + /* prevent iavf_add_fdir_filter() from being called when there + * are no filters to add + */ + adapter->aq_required &= ~IAVF_FLAG_AQ_ADD_FDIR_FILTER; + kfree(f); + return; + } + adapter->current_op = VIRTCHNL_OP_ADD_FDIR_FILTER; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_ADD_FDIR_FILTER, (u8 *)f, len); + kfree(f); +} + +/** + * iavf_del_fdir_filter + * @adapter: the VF adapter structure + * + * Request that the PF delete Flow Director filters as specified + * by the user via ethtool. + **/ +void iavf_del_fdir_filter(struct iavf_adapter *adapter) +{ + struct iavf_fdir_fltr *fdir; + struct virtchnl_fdir_del f; + bool process_fltr = false; + int len; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot remove Flow Director filter, command %d pending\n", + adapter->current_op); + return; + } + + len = sizeof(struct virtchnl_fdir_del); + + spin_lock_bh(&adapter->fdir_fltr_lock); + list_for_each_entry(fdir, &adapter->fdir_list_head, list) { + if (fdir->state == IAVF_FDIR_FLTR_DEL_REQUEST) { + process_fltr = true; + memset(&f, 0, len); + f.vsi_id = fdir->vc_add_msg.vsi_id; + f.flow_id = fdir->flow_id; + fdir->state = IAVF_FDIR_FLTR_DEL_PENDING; + break; + } + } + spin_unlock_bh(&adapter->fdir_fltr_lock); + + if (!process_fltr) { + adapter->aq_required &= ~IAVF_FLAG_AQ_DEL_FDIR_FILTER; + return; + } + + adapter->current_op = VIRTCHNL_OP_DEL_FDIR_FILTER; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_DEL_FDIR_FILTER, (u8 *)&f, len); +} + +/** + * iavf_add_adv_rss_cfg + * @adapter: the VF adapter structure + * + * Request that the PF add RSS configuration as specified + * by the user via ethtool. + **/ +void iavf_add_adv_rss_cfg(struct iavf_adapter *adapter) +{ + struct virtchnl_rss_cfg *rss_cfg; + struct iavf_adv_rss *rss; + bool process_rss = false; + int len; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot add RSS configuration, command %d pending\n", + adapter->current_op); + return; + } + + len = sizeof(struct virtchnl_rss_cfg); + rss_cfg = kzalloc(len, GFP_KERNEL); + if (!rss_cfg) + return; + + spin_lock_bh(&adapter->adv_rss_lock); + list_for_each_entry(rss, &adapter->adv_rss_list_head, list) { + if (rss->state == IAVF_ADV_RSS_ADD_REQUEST) { + process_rss = true; + rss->state = IAVF_ADV_RSS_ADD_PENDING; + memcpy(rss_cfg, &rss->cfg_msg, len); + iavf_print_adv_rss_cfg(adapter, rss, + "Input set change for", + "is pending"); + break; + } + } + spin_unlock_bh(&adapter->adv_rss_lock); + + if (process_rss) { + adapter->current_op = VIRTCHNL_OP_ADD_RSS_CFG; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_ADD_RSS_CFG, + (u8 *)rss_cfg, len); + } else { + adapter->aq_required &= ~IAVF_FLAG_AQ_ADD_ADV_RSS_CFG; + } + + kfree(rss_cfg); +} + +/** + * iavf_del_adv_rss_cfg + * @adapter: the VF adapter structure + * + * Request that the PF delete RSS configuration as specified + * by the user via ethtool. + **/ +void iavf_del_adv_rss_cfg(struct iavf_adapter *adapter) +{ + struct virtchnl_rss_cfg *rss_cfg; + struct iavf_adv_rss *rss; + bool process_rss = false; + int len; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot remove RSS configuration, command %d pending\n", + adapter->current_op); + return; + } + + len = sizeof(struct virtchnl_rss_cfg); + rss_cfg = kzalloc(len, GFP_KERNEL); + if (!rss_cfg) + return; + + spin_lock_bh(&adapter->adv_rss_lock); + list_for_each_entry(rss, &adapter->adv_rss_list_head, list) { + if (rss->state == IAVF_ADV_RSS_DEL_REQUEST) { + process_rss = true; + rss->state = IAVF_ADV_RSS_DEL_PENDING; + memcpy(rss_cfg, &rss->cfg_msg, len); + break; + } + } + spin_unlock_bh(&adapter->adv_rss_lock); + + if (process_rss) { + adapter->current_op = VIRTCHNL_OP_DEL_RSS_CFG; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_DEL_RSS_CFG, + (u8 *)rss_cfg, len); + } else { + adapter->aq_required &= ~IAVF_FLAG_AQ_DEL_ADV_RSS_CFG; + } + + kfree(rss_cfg); +} + +/** * iavf_request_reset * @adapter: adapter structure * @@ -1357,6 +1554,84 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, } } break; + case VIRTCHNL_OP_ADD_FDIR_FILTER: { + struct iavf_fdir_fltr *fdir, *fdir_tmp; + + spin_lock_bh(&adapter->fdir_fltr_lock); + list_for_each_entry_safe(fdir, fdir_tmp, + &adapter->fdir_list_head, + list) { + if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING) { + dev_info(&adapter->pdev->dev, "Failed to add Flow Director filter, error %s\n", + iavf_stat_str(&adapter->hw, + v_retval)); + iavf_print_fdir_fltr(adapter, fdir); + if (msglen) + dev_err(&adapter->pdev->dev, + "%s\n", msg); + list_del(&fdir->list); + kfree(fdir); + adapter->fdir_active_fltr--; + } + } + spin_unlock_bh(&adapter->fdir_fltr_lock); + } + break; + case VIRTCHNL_OP_DEL_FDIR_FILTER: { + struct iavf_fdir_fltr *fdir; + + spin_lock_bh(&adapter->fdir_fltr_lock); + list_for_each_entry(fdir, &adapter->fdir_list_head, + list) { + if (fdir->state == IAVF_FDIR_FLTR_DEL_PENDING) { + fdir->state = IAVF_FDIR_FLTR_ACTIVE; + dev_info(&adapter->pdev->dev, "Failed to del Flow Director filter, error %s\n", + iavf_stat_str(&adapter->hw, + v_retval)); + iavf_print_fdir_fltr(adapter, fdir); + } + } + spin_unlock_bh(&adapter->fdir_fltr_lock); + } + break; + case VIRTCHNL_OP_ADD_RSS_CFG: { + struct iavf_adv_rss *rss, *rss_tmp; + + spin_lock_bh(&adapter->adv_rss_lock); + list_for_each_entry_safe(rss, rss_tmp, + &adapter->adv_rss_list_head, + list) { + if (rss->state == IAVF_ADV_RSS_ADD_PENDING) { + iavf_print_adv_rss_cfg(adapter, rss, + "Failed to change the input set for", + NULL); + list_del(&rss->list); + kfree(rss); + } + } + spin_unlock_bh(&adapter->adv_rss_lock); + } + break; + case VIRTCHNL_OP_DEL_RSS_CFG: { + struct iavf_adv_rss *rss; + + spin_lock_bh(&adapter->adv_rss_lock); + list_for_each_entry(rss, &adapter->adv_rss_list_head, + list) { + if (rss->state == IAVF_ADV_RSS_DEL_PENDING) { + rss->state = IAVF_ADV_RSS_ACTIVE; + dev_err(&adapter->pdev->dev, "Failed to delete RSS configuration, error %s\n", + iavf_stat_str(&adapter->hw, + v_retval)); + } + } + spin_unlock_bh(&adapter->adv_rss_lock); + } + break; + case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING: + case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING: + dev_warn(&adapter->pdev->dev, "Changing VLAN Stripping is not allowed when Port VLAN is configured\n"); + break; default: dev_err(&adapter->pdev->dev, "PF returned error %d (%s) to our request %d\n", v_retval, iavf_stat_str(&adapter->hw, v_retval), @@ -1490,6 +1765,87 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, } } break; + case VIRTCHNL_OP_ADD_FDIR_FILTER: { + struct virtchnl_fdir_add *add_fltr = (struct virtchnl_fdir_add *)msg; + struct iavf_fdir_fltr *fdir, *fdir_tmp; + + spin_lock_bh(&adapter->fdir_fltr_lock); + list_for_each_entry_safe(fdir, fdir_tmp, + &adapter->fdir_list_head, + list) { + if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING) { + if (add_fltr->status == VIRTCHNL_FDIR_SUCCESS) { + dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is added\n", + fdir->loc); + fdir->state = IAVF_FDIR_FLTR_ACTIVE; + fdir->flow_id = add_fltr->flow_id; + } else { + dev_info(&adapter->pdev->dev, "Failed to add Flow Director filter with status: %d\n", + add_fltr->status); + iavf_print_fdir_fltr(adapter, fdir); + list_del(&fdir->list); + kfree(fdir); + adapter->fdir_active_fltr--; + } + } + } + spin_unlock_bh(&adapter->fdir_fltr_lock); + } + break; + case VIRTCHNL_OP_DEL_FDIR_FILTER: { + struct virtchnl_fdir_del *del_fltr = (struct virtchnl_fdir_del *)msg; + struct iavf_fdir_fltr *fdir, *fdir_tmp; + + spin_lock_bh(&adapter->fdir_fltr_lock); + list_for_each_entry_safe(fdir, fdir_tmp, &adapter->fdir_list_head, + list) { + if (fdir->state == IAVF_FDIR_FLTR_DEL_PENDING) { + if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS) { + dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is deleted\n", + fdir->loc); + list_del(&fdir->list); + kfree(fdir); + adapter->fdir_active_fltr--; + } else { + fdir->state = IAVF_FDIR_FLTR_ACTIVE; + dev_info(&adapter->pdev->dev, "Failed to delete Flow Director filter with status: %d\n", + del_fltr->status); + iavf_print_fdir_fltr(adapter, fdir); + } + } + } + spin_unlock_bh(&adapter->fdir_fltr_lock); + } + break; + case VIRTCHNL_OP_ADD_RSS_CFG: { + struct iavf_adv_rss *rss; + + spin_lock_bh(&adapter->adv_rss_lock); + list_for_each_entry(rss, &adapter->adv_rss_list_head, list) { + if (rss->state == IAVF_ADV_RSS_ADD_PENDING) { + iavf_print_adv_rss_cfg(adapter, rss, + "Input set change for", + "successful"); + rss->state = IAVF_ADV_RSS_ACTIVE; + } + } + spin_unlock_bh(&adapter->adv_rss_lock); + } + break; + case VIRTCHNL_OP_DEL_RSS_CFG: { + struct iavf_adv_rss *rss, *rss_tmp; + + spin_lock_bh(&adapter->adv_rss_lock); + list_for_each_entry_safe(rss, rss_tmp, + &adapter->adv_rss_list_head, list) { + if (rss->state == IAVF_ADV_RSS_DEL_PENDING) { + list_del(&rss->list); + kfree(rss); + } + } + spin_unlock_bh(&adapter->adv_rss_lock); + } + 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/Makefile b/drivers/net/ethernet/intel/ice/Makefile index 73da4f71f530..07fe857e9e3a 100644 --- a/drivers/net/ethernet/intel/ice/Makefile +++ b/drivers/net/ethernet/intel/ice/Makefile @@ -26,7 +26,8 @@ ice-y := ice_main.o \ ice_fw_update.o \ ice_lag.o \ ice_ethtool.o -ice-$(CONFIG_PCI_IOV) += ice_virtchnl_pf.o ice_sriov.o +ice-$(CONFIG_PCI_IOV) += ice_virtchnl_allowlist.o +ice-$(CONFIG_PCI_IOV) += ice_virtchnl_pf.o ice_sriov.o ice_virtchnl_fdir.o ice-$(CONFIG_DCB) += ice_dcb.o ice_dcb_nl.o ice_dcb_lib.o ice-$(CONFIG_RFS_ACCEL) += ice_arfs.o ice-$(CONFIG_XDP_SOCKETS) += ice_xsk.o diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 17101c45cbcd..e35db3ff583b 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -36,6 +36,7 @@ #include <linux/bpf.h> #include <linux/avf/virtchnl.h> #include <linux/cpu_rmap.h> +#include <linux/dim.h> #include <net/devlink.h> #include <net/ipv6.h> #include <net/xdp_sock.h> @@ -44,6 +45,9 @@ #include <net/gre.h> #include <net/udp_tunnel.h> #include <net/vxlan.h> +#if IS_ENABLED(CONFIG_DCB) +#include <scsi/iscsi_proto.h> +#endif /* CONFIG_DCB */ #include "ice_devids.h" #include "ice_type.h" #include "ice_txrx.h" @@ -73,7 +77,7 @@ #define ICE_MIN_LAN_TXRX_MSIX 1 #define ICE_MIN_LAN_OICR_MSIX 1 #define ICE_MIN_MSIX (ICE_MIN_LAN_TXRX_MSIX + ICE_MIN_LAN_OICR_MSIX) -#define ICE_FDIR_MSIX 1 +#define ICE_FDIR_MSIX 2 #define ICE_NO_VSI 0xffff #define ICE_VSI_MAP_CONTIG 0 #define ICE_VSI_MAP_SCATTER 1 @@ -84,9 +88,12 @@ #define ICE_MAX_LG_RSS_QS 256 #define ICE_RES_VALID_BIT 0x8000 #define ICE_RES_MISC_VEC_ID (ICE_RES_VALID_BIT - 1) +/* All VF control VSIs share the same IRQ, so assign a unique ID for them */ +#define ICE_RES_VF_CTRL_VEC_ID (ICE_RES_MISC_VEC_ID - 1) #define ICE_INVAL_Q_INDEX 0xffff #define ICE_INVAL_VFID 256 +#define ICE_MAX_RXQS_PER_TC 256 /* Used when setting VSI context per TC Rx queues */ #define ICE_MAX_RESET_WAIT 20 #define ICE_VSIQF_HKEY_ARRAY_SIZE ((VSIQF_HKEY_MAX_INDEX + 1) * 4) @@ -190,53 +197,58 @@ struct ice_sw { u8 dflt_vsi_ena:1; /* true if above dflt_vsi is enabled */ }; -enum ice_state { - __ICE_TESTING, - __ICE_DOWN, - __ICE_NEEDS_RESTART, - __ICE_PREPARED_FOR_RESET, /* set by driver when prepared */ - __ICE_RESET_OICR_RECV, /* set by driver after rcv reset OICR */ - __ICE_PFR_REQ, /* set by driver and peers */ - __ICE_CORER_REQ, /* set by driver and peers */ - __ICE_GLOBR_REQ, /* set by driver and peers */ - __ICE_CORER_RECV, /* set by OICR handler */ - __ICE_GLOBR_RECV, /* set by OICR handler */ - __ICE_EMPR_RECV, /* set by OICR handler */ - __ICE_SUSPENDED, /* set on module remove path */ - __ICE_RESET_FAILED, /* set by reset/rebuild */ +enum ice_pf_state { + ICE_TESTING, + ICE_DOWN, + ICE_NEEDS_RESTART, + ICE_PREPARED_FOR_RESET, /* set by driver when prepared */ + ICE_RESET_OICR_RECV, /* set by driver after rcv reset OICR */ + ICE_PFR_REQ, /* set by driver and peers */ + ICE_CORER_REQ, /* set by driver and peers */ + ICE_GLOBR_REQ, /* set by driver and peers */ + ICE_CORER_RECV, /* set by OICR handler */ + ICE_GLOBR_RECV, /* set by OICR handler */ + ICE_EMPR_RECV, /* set by OICR handler */ + ICE_SUSPENDED, /* set on module remove path */ + ICE_RESET_FAILED, /* set by reset/rebuild */ /* When checking for the PF to be in a nominal operating state, the * bits that are grouped at the beginning of the list need to be - * checked. Bits occurring before __ICE_STATE_NOMINAL_CHECK_BITS will + * checked. Bits occurring before ICE_STATE_NOMINAL_CHECK_BITS will * be checked. If you need to add a bit into consideration for nominal * operating state, it must be added before - * __ICE_STATE_NOMINAL_CHECK_BITS. Do not move this entry's position + * ICE_STATE_NOMINAL_CHECK_BITS. Do not move this entry's position * without appropriate consideration. */ - __ICE_STATE_NOMINAL_CHECK_BITS, - __ICE_ADMINQ_EVENT_PENDING, - __ICE_MAILBOXQ_EVENT_PENDING, - __ICE_MDD_EVENT_PENDING, - __ICE_VFLR_EVENT_PENDING, - __ICE_FLTR_OVERFLOW_PROMISC, - __ICE_VF_DIS, - __ICE_CFG_BUSY, - __ICE_SERVICE_SCHED, - __ICE_SERVICE_DIS, - __ICE_FD_FLUSH_REQ, - __ICE_OICR_INTR_DIS, /* Global OICR interrupt disabled */ - __ICE_MDD_VF_PRINT_PENDING, /* set when MDD event handle */ - __ICE_VF_RESETS_DISABLED, /* disable resets during ice_remove */ - __ICE_LINK_DEFAULT_OVERRIDE_PENDING, - __ICE_PHY_INIT_COMPLETE, - __ICE_STATE_NBITS /* must be last */ + ICE_STATE_NOMINAL_CHECK_BITS, + ICE_ADMINQ_EVENT_PENDING, + ICE_MAILBOXQ_EVENT_PENDING, + ICE_MDD_EVENT_PENDING, + ICE_VFLR_EVENT_PENDING, + ICE_FLTR_OVERFLOW_PROMISC, + ICE_VF_DIS, + ICE_CFG_BUSY, + ICE_SERVICE_SCHED, + ICE_SERVICE_DIS, + ICE_FD_FLUSH_REQ, + ICE_OICR_INTR_DIS, /* Global OICR interrupt disabled */ + ICE_MDD_VF_PRINT_PENDING, /* set when MDD event handle */ + ICE_VF_RESETS_DISABLED, /* disable resets during ice_remove */ + ICE_LINK_DEFAULT_OVERRIDE_PENDING, + ICE_PHY_INIT_COMPLETE, + ICE_FD_VF_FLUSH_CTX, /* set at FD Rx IRQ or timeout */ + ICE_STATE_NBITS /* must be last */ }; -enum ice_vsi_flags { - ICE_VSI_FLAG_UMAC_FLTR_CHANGED, - ICE_VSI_FLAG_MMAC_FLTR_CHANGED, - ICE_VSI_FLAG_VLAN_FLTR_CHANGED, - ICE_VSI_FLAG_PROMISC_CHANGED, - ICE_VSI_FLAG_NBITS /* must be last */ +enum ice_vsi_state { + ICE_VSI_DOWN, + ICE_VSI_NEEDS_RESTART, + ICE_VSI_NETDEV_ALLOCD, + ICE_VSI_NETDEV_REGISTERED, + ICE_VSI_UMAC_FLTR_CHANGED, + ICE_VSI_MMAC_FLTR_CHANGED, + ICE_VSI_VLAN_FLTR_CHANGED, + ICE_VSI_PROMISC_CHANGED, + ICE_VSI_STATE_NBITS /* must be last */ }; /* struct that defines a VSI, associated with a dev */ @@ -252,14 +264,12 @@ struct ice_vsi { irqreturn_t (*irq_handler)(int irq, void *data); u64 tx_linearize; - DECLARE_BITMAP(state, __ICE_STATE_NBITS); - DECLARE_BITMAP(flags, ICE_VSI_FLAG_NBITS); + DECLARE_BITMAP(state, ICE_VSI_STATE_NBITS); unsigned int current_netdev_flags; u32 tx_restart; u32 tx_busy; u32 rx_buf_failed; u32 rx_page_failed; - u32 rx_gro_dropped; u16 num_q_vectors; u16 base_vector; /* IRQ base for OS reserved vectors */ enum ice_vsi_type type; @@ -342,7 +352,7 @@ struct ice_q_vector { u16 reg_idx; u8 num_ring_rx; /* total number of Rx rings in vector */ u8 num_ring_tx; /* total number of Tx rings in vector */ - u8 itr_countdown; /* when 0 should adjust adaptive ITR */ + u8 wb_on_itr:1; /* if true, WB on ITR is enabled */ /* in usecs, need to use ice_intrl_to_usecs_reg() before writing this * value to the device */ @@ -357,6 +367,8 @@ struct ice_q_vector { struct irq_affinity_notify affinity_notify; char name[ICE_INT_NAME_STR_LEN]; + + u16 total_events; /* net_dim(): number of interrupts processed */ } ____cacheline_internodealigned_in_smp; enum ice_pf_flags { @@ -414,7 +426,8 @@ struct ice_pf { u16 num_msix_per_vf; /* used to ratelimit the MDD event logging */ unsigned long last_printed_mdd_jiffies; - DECLARE_BITMAP(state, __ICE_STATE_NBITS); + DECLARE_BITMAP(malvfs, ICE_MAX_VF_COUNT); + DECLARE_BITMAP(state, ICE_STATE_NBITS); DECLARE_BITMAP(flags, ICE_PF_FLAGS_NBITS); unsigned long *avail_txqs; /* bitmap to track PF Tx queue usage */ unsigned long *avail_rxqs; /* bitmap to track PF Rx queue usage */ @@ -499,7 +512,7 @@ ice_irq_dynamic_ena(struct ice_hw *hw, struct ice_vsi *vsi, val = GLINT_DYN_CTL_INTENA_M | GLINT_DYN_CTL_CLEARPBA_M | (itr << GLINT_DYN_CTL_ITR_INDX_S); if (vsi) - if (test_bit(__ICE_DOWN, vsi->state)) + if (test_bit(ICE_VSI_DOWN, vsi->state)) return; wr32(hw, GLINT_DYN_CTL(vector), val); } @@ -616,8 +629,10 @@ int ice_destroy_xdp_rings(struct ice_vsi *vsi); int ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags); -int ice_set_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size); -int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size); +int ice_set_rss_lut(struct ice_vsi *vsi, u8 *lut, u16 lut_size); +int ice_get_rss_lut(struct ice_vsi *vsi, u8 *lut, u16 lut_size); +int ice_set_rss_key(struct ice_vsi *vsi, u8 *seed); +int ice_get_rss_key(struct ice_vsi *vsi, u8 *seed); void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size); int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset); void ice_print_link_msg(struct ice_vsi *vsi, bool isup); diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 80186589153b..5cdfe406af84 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -877,16 +877,18 @@ struct ice_aqc_get_phy_caps { __le16 param0; /* 18.0 - Report qualified modules */ #define ICE_AQC_GET_PHY_RQM BIT(0) - /* 18.1 - 18.2 : Report mode - * 00b - Report NVM capabilities - * 01b - Report topology capabilities - * 10b - Report SW configured + /* 18.1 - 18.3 : Report mode + * 000b - Report NVM capabilities + * 001b - Report topology capabilities + * 010b - Report SW configured + * 100b - Report default capabilities */ -#define ICE_AQC_REPORT_MODE_S 1 -#define ICE_AQC_REPORT_MODE_M (3 << ICE_AQC_REPORT_MODE_S) -#define ICE_AQC_REPORT_NVM_CAP 0 -#define ICE_AQC_REPORT_TOPO_CAP BIT(1) -#define ICE_AQC_REPORT_SW_CFG BIT(2) +#define ICE_AQC_REPORT_MODE_S 1 +#define ICE_AQC_REPORT_MODE_M (7 << ICE_AQC_REPORT_MODE_S) +#define ICE_AQC_REPORT_TOPO_CAP_NO_MEDIA 0 +#define ICE_AQC_REPORT_TOPO_CAP_MEDIA BIT(1) +#define ICE_AQC_REPORT_ACTIVE_CFG BIT(2) +#define ICE_AQC_REPORT_DFLT_CFG BIT(3) __le32 reserved1; __le32 addr_high; __le32 addr_low; @@ -1407,8 +1409,7 @@ struct ice_aqc_nvm_comp_tbl { u8 cvs[]; /* Component Version String */ } __packed; -/* - * Send to PF command (indirect 0x0801) ID is only used by PF +/* Send to PF command (indirect 0x0801) ID is only used by PF * * Send to VF command (indirect 0x0802) ID is only used by PF * @@ -1790,6 +1791,7 @@ struct ice_pkg_ver { }; #define ICE_PKG_NAME_SIZE 32 +#define ICE_SEG_ID_SIZE 28 #define ICE_SEG_NAME_SIZE 28 struct ice_aqc_get_pkg_info { diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c index 6560acd76c94..88d98c9e5f91 100644 --- a/drivers/net/ethernet/intel/ice/ice_arfs.c +++ b/drivers/net/ethernet/intel/ice/ice_arfs.c @@ -581,8 +581,7 @@ void ice_free_cpu_rx_rmap(struct ice_vsi *vsi) return; netdev = vsi->netdev; - if (!netdev || !netdev->rx_cpu_rmap || - netdev->reg_state != NETREG_REGISTERED) + if (!netdev || !netdev->rx_cpu_rmap) return; free_irq_cpu_rmap(netdev->rx_cpu_rmap); @@ -604,8 +603,7 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi) pf = vsi->back; netdev = vsi->netdev; - if (!pf || !netdev || !vsi->num_q_vectors || - vsi->netdev->reg_state != NETREG_REGISTERED) + if (!pf || !netdev || !vsi->num_q_vectors) return -EINVAL; netdev_dbg(netdev, "Setup CPU RMAP: vsi type 0x%x, ifname %s, q_vectors %d\n", diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 1148d768f8ed..5985a7e5ca8a 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -113,6 +113,9 @@ static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, u16 v_idx) q_vector->v_idx = v_idx; q_vector->tx.itr_setting = ICE_DFLT_TX_ITR; q_vector->rx.itr_setting = ICE_DFLT_RX_ITR; + q_vector->tx.itr_mode = ITR_DYNAMIC; + q_vector->rx.itr_mode = ITR_DYNAMIC; + if (vsi->type == ICE_VSI_VF) goto out; /* only set affinity_mask if the CPU is online */ @@ -215,6 +218,26 @@ static u16 ice_calc_q_handle(struct ice_vsi *vsi, struct ice_ring *ring, u8 tc) } /** + * ice_cfg_xps_tx_ring - Configure XPS for a Tx ring + * @ring: The Tx ring to configure + * + * This enables/disables XPS for a given Tx descriptor ring + * based on the TCs enabled for the VSI that ring belongs to. + */ +static void ice_cfg_xps_tx_ring(struct ice_ring *ring) +{ + if (!ring->q_vector || !ring->netdev) + return; + + /* We only initialize XPS once, so as not to overwrite user settings */ + if (test_and_set_bit(ICE_TX_XPS_INIT_DONE, ring->xps_state)) + return; + + netif_set_xps_queue(ring->netdev, &ring->q_vector->affinity_mask, + ring->q_index); +} + +/** * ice_setup_tx_ctx - setup a struct ice_tlan_ctx instance * @ring: The Tx ring to configure * @tlan_ctx: Pointer to the Tx LAN queue context structure to be initialized @@ -664,6 +687,9 @@ ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_ring *ring, u16 pf_q; u8 tc; + /* Configure XPS */ + ice_cfg_xps_tx_ring(ring); + pf_q = ring->reg_idx; ice_setup_tx_ctx(ring, &tlan_ctx, pf_q); /* copy context contents into the qg_buf */ @@ -717,25 +743,13 @@ void ice_cfg_itr(struct ice_hw *hw, struct ice_q_vector *q_vector) { ice_cfg_itr_gran(hw); - if (q_vector->num_ring_rx) { - struct ice_ring_container *rc = &q_vector->rx; - - rc->target_itr = ITR_TO_REG(rc->itr_setting); - rc->next_update = jiffies + 1; - rc->current_itr = rc->target_itr; - wr32(hw, GLINT_ITR(rc->itr_idx, q_vector->reg_idx), - ITR_REG_ALIGN(rc->current_itr) >> ICE_ITR_GRAN_S); - } + if (q_vector->num_ring_rx) + ice_write_itr(&q_vector->rx, q_vector->rx.itr_setting); - if (q_vector->num_ring_tx) { - struct ice_ring_container *rc = &q_vector->tx; + if (q_vector->num_ring_tx) + ice_write_itr(&q_vector->tx, q_vector->tx.itr_setting); - rc->target_itr = ITR_TO_REG(rc->itr_setting); - rc->next_update = jiffies + 1; - rc->current_itr = rc->target_itr; - wr32(hw, GLINT_ITR(rc->itr_idx, q_vector->reg_idx), - ITR_REG_ALIGN(rc->current_itr) >> ICE_ITR_GRAN_S); - } + ice_write_intrl(q_vector, q_vector->intrl); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index a20edf1538a0..e93b1e40f627 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -158,6 +158,10 @@ ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode, return ICE_ERR_PARAM; hw = pi->hw; + if (report_mode == ICE_AQC_REPORT_DFLT_CFG && + !ice_fw_supports_report_dflt_cfg(hw)) + return ICE_ERR_PARAM; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_phy_caps); if (qual_mods) @@ -191,7 +195,7 @@ ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode, ice_debug(hw, ICE_DBG_LINK, " module_type[2] = 0x%x\n", pcaps->module_type[2]); - if (!status && report_mode == ICE_AQC_REPORT_TOPO_CAP) { + if (!status && report_mode == ICE_AQC_REPORT_TOPO_CAP_MEDIA) { pi->phy.phy_type_low = le64_to_cpu(pcaps->phy_type_low); pi->phy.phy_type_high = le64_to_cpu(pcaps->phy_type_high); memcpy(pi->phy.link_info.module_type, &pcaps->module_type, @@ -922,7 +926,8 @@ enum ice_status ice_init_hw(struct ice_hw *hw) /* Initialize port_info struct with PHY capabilities */ status = ice_aq_get_phy_caps(hw->port_info, false, - ICE_AQC_REPORT_TOPO_CAP, pcaps, NULL); + ICE_AQC_REPORT_TOPO_CAP_MEDIA, pcaps, + NULL); devm_kfree(ice_hw_to_dev(hw), pcaps); if (status) dev_warn(ice_hw_to_dev(hw), "Get PHY capabilities failed status = %d, continuing anyway\n", @@ -1293,6 +1298,85 @@ const struct ice_ctx_ele ice_tlan_ctx_info[] = { DEFINE_MUTEX(ice_global_cfg_lock_sw); /** + * ice_should_retry_sq_send_cmd + * @opcode: AQ opcode + * + * Decide if we should retry the send command routine for the ATQ, depending + * on the opcode. + */ +static bool ice_should_retry_sq_send_cmd(u16 opcode) +{ + switch (opcode) { + case ice_aqc_opc_get_link_topo: + case ice_aqc_opc_lldp_stop: + case ice_aqc_opc_lldp_start: + case ice_aqc_opc_lldp_filter_ctrl: + return true; + } + + return false; +} + +/** + * ice_sq_send_cmd_retry - send command to Control Queue (ATQ) + * @hw: pointer to the HW struct + * @cq: pointer to the specific Control queue + * @desc: prefilled descriptor describing the command + * @buf: buffer to use for indirect commands (or NULL for direct commands) + * @buf_size: size of buffer for indirect commands (or 0 for direct commands) + * @cd: pointer to command details structure + * + * Retry sending the FW Admin Queue command, multiple times, to the FW Admin + * Queue if the EBUSY AQ error is returned. + */ +static enum ice_status +ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq, + struct ice_aq_desc *desc, void *buf, u16 buf_size, + struct ice_sq_cd *cd) +{ + struct ice_aq_desc desc_cpy; + enum ice_status status; + bool is_cmd_for_retry; + u8 *buf_cpy = NULL; + u8 idx = 0; + u16 opcode; + + opcode = le16_to_cpu(desc->opcode); + is_cmd_for_retry = ice_should_retry_sq_send_cmd(opcode); + memset(&desc_cpy, 0, sizeof(desc_cpy)); + + if (is_cmd_for_retry) { + if (buf) { + buf_cpy = kzalloc(buf_size, GFP_KERNEL); + if (!buf_cpy) + return ICE_ERR_NO_MEMORY; + } + + memcpy(&desc_cpy, desc, sizeof(desc_cpy)); + } + + do { + status = ice_sq_send_cmd(hw, cq, desc, buf, buf_size, cd); + + if (!is_cmd_for_retry || !status || + hw->adminq.sq_last_status != ICE_AQ_RC_EBUSY) + break; + + if (buf_cpy) + memcpy(buf, buf_cpy, buf_size); + + memcpy(desc, &desc_cpy, sizeof(desc_cpy)); + + mdelay(ICE_SQ_SEND_DELAY_TIME_MS); + + } while (++idx < ICE_SQ_SEND_MAX_EXECUTE); + + kfree(buf_cpy); + + return status; +} + +/** * ice_aq_send_cmd - send FW Admin Queue command to FW Admin Queue * @hw: pointer to the HW struct * @desc: descriptor describing the command @@ -1333,7 +1417,7 @@ ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf, break; } - status = ice_sq_send_cmd(hw, &hw->adminq, desc, buf, buf_size, cd); + status = ice_sq_send_cmd_retry(hw, &hw->adminq, desc, buf, buf_size, cd); if (lock_acquired) mutex_unlock(&ice_global_cfg_lock_sw); @@ -2655,7 +2739,7 @@ enum ice_status ice_update_link_info(struct ice_port_info *pi) if (!pcaps) return ICE_ERR_NO_MEMORY; - status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP, + status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP_MEDIA, pcaps, NULL); devm_kfree(ice_hw_to_dev(hw), pcaps); @@ -2815,8 +2899,8 @@ ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool ena_auto_link_update) return ICE_ERR_NO_MEMORY; /* Get the current PHY config */ - status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG, pcaps, - NULL); + status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_ACTIVE_CFG, + pcaps, NULL); if (status) { *aq_failures = ICE_SET_FC_AQ_FAIL_GET; goto out; @@ -2929,17 +3013,6 @@ ice_copy_phy_caps_to_cfg(struct ice_port_info *pi, cfg->link_fec_opt = caps->link_fec_options; cfg->module_compliance_enforcement = caps->module_compliance_enforcement; - - if (ice_fw_supports_link_override(pi->hw)) { - struct ice_link_default_override_tlv tlv; - - if (ice_get_link_default_override(&tlv, pi)) - return; - - if (tlv.options & ICE_LINK_OVERRIDE_STRICT_MODE) - cfg->module_compliance_enforcement |= - ICE_LINK_OVERRIDE_STRICT_MODE; - } } /** @@ -2954,16 +3027,21 @@ ice_cfg_phy_fec(struct ice_port_info *pi, struct ice_aqc_set_phy_cfg_data *cfg, { struct ice_aqc_get_phy_caps_data *pcaps; enum ice_status status; + struct ice_hw *hw; if (!pi || !cfg) return ICE_ERR_BAD_PTR; + hw = pi->hw; + pcaps = kzalloc(sizeof(*pcaps), GFP_KERNEL); if (!pcaps) return ICE_ERR_NO_MEMORY; - status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP, pcaps, - NULL); + status = ice_aq_get_phy_caps(pi, false, + (ice_fw_supports_report_dflt_cfg(hw) ? + ICE_AQC_REPORT_DFLT_CFG : + ICE_AQC_REPORT_TOPO_CAP_MEDIA), pcaps, NULL); if (status) goto out; @@ -3002,7 +3080,8 @@ ice_cfg_phy_fec(struct ice_port_info *pi, struct ice_aqc_set_phy_cfg_data *cfg, break; } - if (fec == ICE_FEC_AUTO && ice_fw_supports_link_override(pi->hw)) { + 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; if (ice_get_link_default_override(&tlv, pi)) @@ -3186,7 +3265,7 @@ ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr, ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_sff_eeprom); cmd = &desc.params.read_write_sff_param; - desc.flags = cpu_to_le16(ICE_AQ_FLAG_RD | ICE_AQ_FLAG_BUF); + desc.flags = cpu_to_le16(ICE_AQ_FLAG_RD); cmd->lport_num = (u8)(lport & 0xff); cmd->lport_num_valid = (u8)((lport >> 8) & 0x01); cmd->i2c_bus_addr = cpu_to_le16(((bus_addr >> 1) & @@ -3206,23 +3285,33 @@ ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr, /** * __ice_aq_get_set_rss_lut * @hw: pointer to the hardware structure - * @vsi_id: VSI FW index - * @lut_type: LUT table type - * @lut: pointer to the LUT buffer provided by the caller - * @lut_size: size of the LUT buffer - * @glob_lut_idx: global LUT index + * @params: RSS LUT parameters * @set: set true to set the table, false to get the table * * Internal function to get (0x0B05) or set (0x0B03) RSS look up table */ static enum ice_status -__ice_aq_get_set_rss_lut(struct ice_hw *hw, u16 vsi_id, u8 lut_type, u8 *lut, - u16 lut_size, u8 glob_lut_idx, bool set) +__ice_aq_get_set_rss_lut(struct ice_hw *hw, struct ice_aq_get_set_rss_lut_params *params, bool set) { + u16 flags = 0, vsi_id, lut_type, lut_size, glob_lut_idx, vsi_handle; struct ice_aqc_get_set_rss_lut *cmd_resp; struct ice_aq_desc desc; enum ice_status status; - u16 flags = 0; + u8 *lut; + + if (!params) + return ICE_ERR_PARAM; + + vsi_handle = params->vsi_handle; + lut = params->lut; + + if (!ice_is_vsi_valid(hw, vsi_handle) || !lut) + return ICE_ERR_PARAM; + + lut_size = params->lut_size; + lut_type = params->lut_type; + glob_lut_idx = params->global_lut_id; + vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); cmd_resp = &desc.params.get_set_rss_lut; @@ -3296,43 +3385,27 @@ ice_aq_get_set_rss_lut_exit: /** * ice_aq_get_rss_lut * @hw: pointer to the hardware structure - * @vsi_handle: software VSI handle - * @lut_type: LUT table type - * @lut: pointer to the LUT buffer provided by the caller - * @lut_size: size of the LUT buffer + * @get_params: RSS LUT parameters used to specify which RSS LUT to get * * get the RSS lookup table, PF or VSI type */ enum ice_status -ice_aq_get_rss_lut(struct ice_hw *hw, u16 vsi_handle, u8 lut_type, - u8 *lut, u16 lut_size) +ice_aq_get_rss_lut(struct ice_hw *hw, struct ice_aq_get_set_rss_lut_params *get_params) { - if (!ice_is_vsi_valid(hw, vsi_handle) || !lut) - return ICE_ERR_PARAM; - - return __ice_aq_get_set_rss_lut(hw, ice_get_hw_vsi_num(hw, vsi_handle), - lut_type, lut, lut_size, 0, false); + return __ice_aq_get_set_rss_lut(hw, get_params, false); } /** * ice_aq_set_rss_lut * @hw: pointer to the hardware structure - * @vsi_handle: software VSI handle - * @lut_type: LUT table type - * @lut: pointer to the LUT buffer provided by the caller - * @lut_size: size of the LUT buffer + * @set_params: RSS LUT parameters used to specify how to set the RSS LUT * * set the RSS lookup table, PF or VSI type */ enum ice_status -ice_aq_set_rss_lut(struct ice_hw *hw, u16 vsi_handle, u8 lut_type, - u8 *lut, u16 lut_size) +ice_aq_set_rss_lut(struct ice_hw *hw, struct ice_aq_get_set_rss_lut_params *set_params) { - if (!ice_is_vsi_valid(hw, vsi_handle) || !lut) - return ICE_ERR_PARAM; - - return __ice_aq_get_set_rss_lut(hw, ice_get_hw_vsi_num(hw, vsi_handle), - lut_type, lut, lut_size, 0, true); + return __ice_aq_get_set_rss_lut(hw, set_params, true); } /** @@ -4373,7 +4446,7 @@ ice_aq_set_lldp_mib(struct ice_hw *hw, u8 mib_type, void *buf, u16 buf_size, } /** - * ice_fw_supports_lldp_fltr - check NVM version supports lldp_fltr_ctrl + * ice_fw_supports_lldp_fltr_ctrl - check NVM version supports lldp_fltr_ctrl * @hw: pointer to HW struct */ bool ice_fw_supports_lldp_fltr_ctrl(struct ice_hw *hw) @@ -4418,3 +4491,23 @@ ice_lldp_fltr_add_remove(struct ice_hw *hw, u16 vsi_num, bool add) return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); } + +/** + * ice_fw_supports_report_dflt_cfg + * @hw: pointer to the hardware structure + * + * Checks if the firmware supports report default configuration + */ +bool ice_fw_supports_report_dflt_cfg(struct ice_hw *hw) +{ + if (hw->api_maj_ver == ICE_FW_API_REPORT_DFLT_CFG_MAJ) { + if (hw->api_min_ver > ICE_FW_API_REPORT_DFLT_CFG_MIN) + return true; + if (hw->api_min_ver == ICE_FW_API_REPORT_DFLT_CFG_MIN && + hw->api_patch >= ICE_FW_API_REPORT_DFLT_CFG_PATCH) + return true; + } else if (hw->api_maj_ver > ICE_FW_API_REPORT_DFLT_CFG_MAJ) { + return true; + } + return false; +} diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index baf4064fcbfe..7a9d2dfb21a2 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -11,6 +11,9 @@ #include "ice_switch.h" #include <linux/avf/virtchnl.h> +#define ICE_SQ_SEND_DELAY_TIME_MS 10 +#define ICE_SQ_SEND_MAX_EXECUTE 3 + enum ice_status ice_init_hw(struct ice_hw *hw); void ice_deinit_hw(struct ice_hw *hw); enum ice_status ice_check_reset(struct ice_hw *hw); @@ -51,11 +54,9 @@ ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx, u32 rxq_index); enum ice_status -ice_aq_get_rss_lut(struct ice_hw *hw, u16 vsi_handle, u8 lut_type, u8 *lut, - u16 lut_size); +ice_aq_get_rss_lut(struct ice_hw *hw, struct ice_aq_get_set_rss_lut_params *get_params); enum ice_status -ice_aq_set_rss_lut(struct ice_hw *hw, u16 vsi_handle, u8 lut_type, u8 *lut, - u16 lut_size); +ice_aq_set_rss_lut(struct ice_hw *hw, struct ice_aq_get_set_rss_lut_params *set_params); enum ice_status ice_aq_get_rss_key(struct ice_hw *hw, u16 vsi_handle, struct ice_aqc_get_set_rss_keys *keys); @@ -178,4 +179,5 @@ ice_aq_set_lldp_mib(struct ice_hw *hw, u8 mib_type, void *buf, u16 buf_size, bool ice_fw_supports_lldp_fltr_ctrl(struct ice_hw *hw); enum ice_status ice_lldp_fltr_add_remove(struct ice_hw *hw, u16 vsi_num, bool add); +bool ice_fw_supports_report_dflt_cfg(struct ice_hw *hw); #endif /* _ICE_COMMON_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c index b2d8a5932b1d..87b33bdd4960 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.c +++ b/drivers/net/ethernet/intel/ice/ice_controlq.c @@ -892,7 +892,7 @@ static bool ice_sq_done(struct ice_hw *hw, struct ice_ctl_q_info *cq) * ice_sq_send_cmd - send command to Control Queue (ATQ) * @hw: pointer to the HW struct * @cq: pointer to the specific Control queue - * @desc: prefilled descriptor describing the command (non DMA mem) + * @desc: prefilled descriptor describing the command * @buf: buffer to use for indirect commands (or NULL for direct commands) * @buf_size: size of buffer for indirect commands (or 0 for direct commands) * @cd: pointer to command details structure @@ -1097,6 +1097,7 @@ ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq, struct ice_rq_event_info *e, u16 *pending) { u16 ntc = cq->rq.next_to_clean; + enum ice_aq_err rq_last_status; enum ice_status ret_code = 0; struct ice_aq_desc *desc; struct ice_dma_mem *bi; @@ -1130,13 +1131,12 @@ ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq, desc = ICE_CTL_Q_DESC(cq->rq, ntc); desc_idx = ntc; - cq->rq_last_status = (enum ice_aq_err)le16_to_cpu(desc->retval); + rq_last_status = (enum ice_aq_err)le16_to_cpu(desc->retval); flags = le16_to_cpu(desc->flags); if (flags & ICE_AQ_FLAG_ERR) { ret_code = ICE_ERR_AQ_ERROR; ice_debug(hw, ICE_DBG_AQ_MSG, "Control Receive Queue Event 0x%04X received with error 0x%X\n", - le16_to_cpu(desc->opcode), - cq->rq_last_status); + le16_to_cpu(desc->opcode), rq_last_status); } memcpy(&e->desc, desc, sizeof(e->desc)); datalen = le16_to_cpu(desc->datalen); diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.h b/drivers/net/ethernet/intel/ice/ice_controlq.h index 68866f4f0eb0..fe75871e48ca 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.h +++ b/drivers/net/ethernet/intel/ice/ice_controlq.h @@ -14,8 +14,8 @@ (&(((struct ice_aq_desc *)((R).desc_buf.va))[i])) #define ICE_CTL_Q_DESC_UNUSED(R) \ - (u16)((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \ - (R)->next_to_clean - (R)->next_to_use - 1) + ((u16)((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \ + (R)->next_to_clean - (R)->next_to_use - 1)) /* Defines that help manage the driver vs FW API checks. * Take a look at ice_aq_ver_check in ice_controlq.c for actual usage. @@ -83,7 +83,6 @@ struct ice_rq_event_info { /* Control Queue information */ struct ice_ctl_q_info { enum ice_ctl_q qtype; - enum ice_aq_err rq_last_status; /* last status on receive queue */ struct ice_ctl_q_ring rq; /* receive queue */ struct ice_ctl_q_ring sq; /* send queue */ u32 sq_cmd_timeout; /* send queue cmd write back timeout */ diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.c b/drivers/net/ethernet/intel/ice/ice_dcb.c index 28e834a128c0..849fcf605479 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb.c @@ -804,7 +804,7 @@ ice_cee_to_dcb_cfg(struct ice_aqc_get_cee_dcb_cfg_resp *cee_cfg, ice_aqc_cee_app_mask = ICE_AQC_CEE_APP_FCOE_M; ice_aqc_cee_app_shift = ICE_AQC_CEE_APP_FCOE_S; ice_app_sel_type = ICE_APP_SEL_ETHTYPE; - ice_app_prot_id_type = ICE_APP_PROT_ID_FCOE; + ice_app_prot_id_type = ETH_P_FCOE; } else if (i == 1) { /* iSCSI APP */ ice_aqc_cee_status_mask = ICE_AQC_CEE_ISCSI_STATUS_M; @@ -812,14 +812,14 @@ ice_cee_to_dcb_cfg(struct ice_aqc_get_cee_dcb_cfg_resp *cee_cfg, ice_aqc_cee_app_mask = ICE_AQC_CEE_APP_ISCSI_M; ice_aqc_cee_app_shift = ICE_AQC_CEE_APP_ISCSI_S; ice_app_sel_type = ICE_APP_SEL_TCPIP; - ice_app_prot_id_type = ICE_APP_PROT_ID_ISCSI; + ice_app_prot_id_type = ISCSI_LISTEN_PORT; for (j = 0; j < cmp_dcbcfg->numapps; j++) { u16 prot_id = cmp_dcbcfg->app[j].prot_id; u8 sel = cmp_dcbcfg->app[j].selector; if (sel == ICE_APP_SEL_TCPIP && - (prot_id == ICE_APP_PROT_ID_ISCSI || + (prot_id == ISCSI_LISTEN_PORT || prot_id == ICE_APP_PROT_ID_ISCSI_860)) { ice_app_prot_id_type = prot_id; break; @@ -832,7 +832,7 @@ ice_cee_to_dcb_cfg(struct ice_aqc_get_cee_dcb_cfg_resp *cee_cfg, ice_aqc_cee_app_mask = ICE_AQC_CEE_APP_FIP_M; ice_aqc_cee_app_shift = ICE_AQC_CEE_APP_FIP_S; ice_app_sel_type = ICE_APP_SEL_ETHTYPE; - ice_app_prot_id_type = ICE_APP_PROT_ID_FIP; + ice_app_prot_id_type = ETH_P_FIP; } status = (tlv_status & ice_aqc_cee_status_mask) >> @@ -857,7 +857,7 @@ ice_cee_to_dcb_cfg(struct ice_aqc_get_cee_dcb_cfg_resp *cee_cfg, } /** - * ice_get_ieee_dcb_cfg + * ice_get_ieee_or_cee_dcb_cfg * @pi: port information structure * @dcbx_mode: mode of DCBX (IEEE or CEE) * diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index 1e8f71ffc8ce..df02cffdf209 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -563,7 +563,7 @@ static int ice_dcb_sw_dflt_cfg(struct ice_pf *pf, bool ets_willing, bool locked) dcbcfg->numapps = 1; dcbcfg->app[0].selector = ICE_APP_SEL_ETHTYPE; dcbcfg->app[0].priority = 3; - dcbcfg->app[0].prot_id = ICE_APP_PROT_ID_FCOE; + dcbcfg->app[0].prot_id = ETH_P_FCOE; ret = ice_pf_dcb_cfg(pf, dcbcfg, locked); kfree(dcbcfg); diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 32ba71a16165..d9ddd0bcf65f 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -60,7 +60,6 @@ static const struct ice_stats ice_gstrings_vsi_stats[] = { ICE_VSI_STAT("rx_unknown_protocol", eth_stats.rx_unknown_protocol), ICE_VSI_STAT("rx_alloc_fail", rx_buf_failed), ICE_VSI_STAT("rx_pg_alloc_fail", rx_page_failed), - ICE_VSI_STAT("rx_gro_dropped", rx_gro_dropped), ICE_VSI_STAT("tx_errors", eth_stats.tx_errors), ICE_VSI_STAT("tx_linearize", tx_linearize), ICE_VSI_STAT("tx_busy", tx_busy), @@ -807,7 +806,7 @@ ice_self_test(struct net_device *netdev, struct ethtool_test *eth_test, if (eth_test->flags == ETH_TEST_FL_OFFLINE) { netdev_info(netdev, "offline testing starting\n"); - set_bit(__ICE_TESTING, pf->state); + set_bit(ICE_TESTING, pf->state); if (ice_active_vfs(pf)) { dev_warn(dev, "Please take active VFs and Netqueues offline and restart the adapter before running NIC diagnostics\n"); @@ -817,7 +816,7 @@ ice_self_test(struct net_device *netdev, struct ethtool_test *eth_test, data[ICE_ETH_TEST_LOOP] = 1; data[ICE_ETH_TEST_LINK] = 1; eth_test->flags |= ETH_TEST_FL_FAILED; - clear_bit(__ICE_TESTING, pf->state); + clear_bit(ICE_TESTING, pf->state); goto skip_ol_tests; } /* If the device is online then take it offline */ @@ -838,7 +837,7 @@ ice_self_test(struct net_device *netdev, struct ethtool_test *eth_test, data[ICE_ETH_TEST_REG]) eth_test->flags |= ETH_TEST_FL_FAILED; - clear_bit(__ICE_TESTING, pf->state); + clear_bit(ICE_TESTING, pf->state); if (if_running) { int status = ice_open(netdev); @@ -871,68 +870,47 @@ static void ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data) { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; - char *p = (char *)data; unsigned int i; + u8 *p = data; switch (stringset) { case ETH_SS_STATS: - for (i = 0; i < ICE_VSI_STATS_LEN; i++) { - snprintf(p, ETH_GSTRING_LEN, "%s", - ice_gstrings_vsi_stats[i].stat_string); - p += ETH_GSTRING_LEN; - } + for (i = 0; i < ICE_VSI_STATS_LEN; i++) + ethtool_sprintf(&p, + ice_gstrings_vsi_stats[i].stat_string); ice_for_each_alloc_txq(vsi, i) { - snprintf(p, ETH_GSTRING_LEN, - "tx_queue_%u_packets", i); - p += ETH_GSTRING_LEN; - snprintf(p, ETH_GSTRING_LEN, "tx_queue_%u_bytes", i); - p += ETH_GSTRING_LEN; + ethtool_sprintf(&p, "tx_queue_%u_packets", i); + ethtool_sprintf(&p, "tx_queue_%u_bytes", i); } ice_for_each_alloc_rxq(vsi, i) { - snprintf(p, ETH_GSTRING_LEN, - "rx_queue_%u_packets", i); - p += ETH_GSTRING_LEN; - snprintf(p, ETH_GSTRING_LEN, "rx_queue_%u_bytes", i); - p += ETH_GSTRING_LEN; + ethtool_sprintf(&p, "rx_queue_%u_packets", i); + ethtool_sprintf(&p, "rx_queue_%u_bytes", i); } if (vsi->type != ICE_VSI_PF) return; - for (i = 0; i < ICE_PF_STATS_LEN; i++) { - snprintf(p, ETH_GSTRING_LEN, "%s", - ice_gstrings_pf_stats[i].stat_string); - p += ETH_GSTRING_LEN; - } + for (i = 0; i < ICE_PF_STATS_LEN; i++) + ethtool_sprintf(&p, + ice_gstrings_pf_stats[i].stat_string); for (i = 0; i < ICE_MAX_USER_PRIORITY; i++) { - snprintf(p, ETH_GSTRING_LEN, - "tx_priority_%u_xon.nic", i); - p += ETH_GSTRING_LEN; - snprintf(p, ETH_GSTRING_LEN, - "tx_priority_%u_xoff.nic", i); - p += ETH_GSTRING_LEN; + ethtool_sprintf(&p, "tx_priority_%u_xon.nic", i); + ethtool_sprintf(&p, "tx_priority_%u_xoff.nic", i); } for (i = 0; i < ICE_MAX_USER_PRIORITY; i++) { - snprintf(p, ETH_GSTRING_LEN, - "rx_priority_%u_xon.nic", i); - p += ETH_GSTRING_LEN; - snprintf(p, ETH_GSTRING_LEN, - "rx_priority_%u_xoff.nic", i); - p += ETH_GSTRING_LEN; + ethtool_sprintf(&p, "rx_priority_%u_xon.nic", i); + ethtool_sprintf(&p, "rx_priority_%u_xoff.nic", i); } break; case ETH_SS_TEST: memcpy(data, ice_gstrings_test, ICE_TEST_LEN * ETH_GSTRING_LEN); break; case ETH_SS_PRIV_FLAGS: - for (i = 0; i < ICE_PRIV_FLAG_ARRAY_SIZE; i++) { - snprintf(p, ETH_GSTRING_LEN, "%s", - ice_gstrings_priv_flags[i].name); - p += ETH_GSTRING_LEN; - } + for (i = 0; i < ICE_PRIV_FLAG_ARRAY_SIZE; i++) + ethtool_sprintf(&p, ice_gstrings_priv_flags[i].name); break; default: break; @@ -1081,7 +1059,7 @@ ice_get_fecparam(struct net_device *netdev, struct ethtool_fecparam *fecparam) if (!caps) return -ENOMEM; - status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP, + status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP_MEDIA, caps, NULL); if (status) { err = -EAGAIN; @@ -1116,24 +1094,15 @@ static int ice_nway_reset(struct net_device *netdev) { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; - struct ice_port_info *pi; - enum ice_status status; + int err; - pi = vsi->port_info; /* If VSI state is up, then restart autoneg with link up */ - if (!test_bit(__ICE_DOWN, vsi->back->state)) - status = ice_aq_set_link_restart_an(pi, true, NULL); + if (!test_bit(ICE_DOWN, vsi->back->state)) + err = ice_set_link(vsi, true); else - status = ice_aq_set_link_restart_an(pi, false, NULL); + err = ice_set_link(vsi, false); - if (status) { - netdev_info(netdev, "link restart failed, err %s aq_err %s\n", - ice_stat_str(status), - ice_aq_str(pi->hw->adminq.sq_last_status)); - return -EIO; - } - - return 0; + return err; } /** @@ -1475,8 +1444,8 @@ void ice_mask_min_supported_speeds(u64 phy_types_high, u64 *phy_types_low) do { \ if (req_speeds & (aq_link_speed) || \ (!req_speeds && \ - (adv_phy_type_lo & phy_type_mask_lo || \ - adv_phy_type_hi & phy_type_mask_hi))) \ + (advert_phy_type_lo & phy_type_mask_lo || \ + advert_phy_type_hi & phy_type_mask_hi))) \ ethtool_link_ksettings_add_link_mode(ks, advertising,\ ethtool_link_mode); \ } while (0) @@ -1493,10 +1462,10 @@ ice_phy_type_to_ethtool(struct net_device *netdev, struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; + u64 advert_phy_type_lo = 0; + u64 advert_phy_type_hi = 0; u64 phy_type_mask_lo = 0; u64 phy_type_mask_hi = 0; - u64 adv_phy_type_lo = 0; - u64 adv_phy_type_hi = 0; u64 phy_types_high = 0; u64 phy_types_low = 0; u16 req_speeds; @@ -1514,28 +1483,35 @@ ice_phy_type_to_ethtool(struct net_device *netdev, * requested by user. */ if (test_bit(ICE_FLAG_LINK_LENIENT_MODE_ENA, pf->flags)) { - struct ice_link_default_override_tlv *ldo; - - ldo = &pf->link_dflt_override; phy_types_low = le64_to_cpu(pf->nvm_phy_type_lo); phy_types_high = le64_to_cpu(pf->nvm_phy_type_hi); ice_mask_min_supported_speeds(phy_types_high, &phy_types_low); - - /* If override enabled and PHY mask set, then - * Advertising link mode is the intersection of the PHY - * types without media and the override PHY mask. + /* determine advertised modes based on link override only + * if it's supported and if the FW doesn't abstract the + * driver from having to account for link overrides */ - if (ldo->options & ICE_LINK_OVERRIDE_EN && - (ldo->phy_type_low || ldo->phy_type_high)) { - adv_phy_type_lo = - le64_to_cpu(pf->nvm_phy_type_lo) & - ldo->phy_type_low; - adv_phy_type_hi = - le64_to_cpu(pf->nvm_phy_type_hi) & - ldo->phy_type_high; + if (ice_fw_supports_link_override(&pf->hw) && + !ice_fw_supports_report_dflt_cfg(&pf->hw)) { + struct ice_link_default_override_tlv *ldo; + + ldo = &pf->link_dflt_override; + /* If override enabled and PHY mask set, then + * Advertising link mode is the intersection of the PHY + * types without media and the override PHY mask. + */ + if (ldo->options & ICE_LINK_OVERRIDE_EN && + (ldo->phy_type_low || ldo->phy_type_high)) { + advert_phy_type_lo = + le64_to_cpu(pf->nvm_phy_type_lo) & + ldo->phy_type_low; + advert_phy_type_hi = + le64_to_cpu(pf->nvm_phy_type_hi) & + ldo->phy_type_high; + } } } else { + /* strict mode */ phy_types_low = vsi->port_info->phy.phy_type_low; phy_types_high = vsi->port_info->phy.phy_type_high; } @@ -1543,9 +1519,9 @@ ice_phy_type_to_ethtool(struct net_device *netdev, /* If Advertising link mode PHY type is not using override PHY type, * then use PHY type with media. */ - if (!adv_phy_type_lo && !adv_phy_type_hi) { - adv_phy_type_lo = vsi->port_info->phy.phy_type_low; - adv_phy_type_hi = vsi->port_info->phy.phy_type_high; + if (!advert_phy_type_lo && !advert_phy_type_hi) { + advert_phy_type_lo = vsi->port_info->phy.phy_type_low; + advert_phy_type_hi = vsi->port_info->phy.phy_type_high; } ethtool_link_ksettings_zero_link_mode(ks, supported); @@ -2021,7 +1997,7 @@ ice_get_link_ksettings(struct net_device *netdev, return -ENOMEM; status = ice_aq_get_phy_caps(vsi->port_info, false, - ICE_AQC_REPORT_SW_CFG, caps, NULL); + ICE_AQC_REPORT_ACTIVE_CFG, caps, NULL); if (status) { err = -EIO; goto done; @@ -2058,7 +2034,7 @@ ice_get_link_ksettings(struct net_device *netdev, ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS); status = ice_aq_get_phy_caps(vsi->port_info, false, - ICE_AQC_REPORT_TOPO_CAP, caps, NULL); + ICE_AQC_REPORT_TOPO_CAP_MEDIA, caps, NULL); if (status) { err = -EIO; goto done; @@ -2225,13 +2201,14 @@ ice_set_link_ksettings(struct net_device *netdev, const struct ethtool_link_ksettings *ks) { struct ice_netdev_priv *np = netdev_priv(netdev); - struct ethtool_link_ksettings safe_ks, copy_ks; - struct ice_aqc_get_phy_caps_data *abilities; u8 autoneg, timeout = TEST_SET_BITS_TIMEOUT; - u16 adv_link_speed, curr_link_speed, idx; + struct ethtool_link_ksettings copy_ks = *ks; + struct ethtool_link_ksettings safe_ks = {}; + struct ice_aqc_get_phy_caps_data *phy_caps; struct ice_aqc_set_phy_cfg_data config; + u16 adv_link_speed, curr_link_speed; struct ice_pf *pf = np->vsi->back; - struct ice_port_info *p; + struct ice_port_info *pi; u8 autoneg_changed = 0; enum ice_status status; u64 phy_type_high = 0; @@ -2239,46 +2216,37 @@ ice_set_link_ksettings(struct net_device *netdev, int err = 0; bool linkup; - p = np->vsi->port_info; - - if (!p) - return -EOPNOTSUPP; + pi = np->vsi->port_info; - /* Check if this is LAN VSI */ - ice_for_each_vsi(pf, idx) - if (pf->vsi[idx]->type == ICE_VSI_PF) { - if (np->vsi != pf->vsi[idx]) - return -EOPNOTSUPP; - break; - } + if (!pi) + return -EIO; - if (p->phy.media_type != ICE_MEDIA_BASET && - p->phy.media_type != ICE_MEDIA_FIBER && - p->phy.media_type != ICE_MEDIA_BACKPLANE && - p->phy.media_type != ICE_MEDIA_DA && - p->phy.link_info.link_info & ICE_AQ_LINK_UP) + if (pi->phy.media_type != ICE_MEDIA_BASET && + pi->phy.media_type != ICE_MEDIA_FIBER && + pi->phy.media_type != ICE_MEDIA_BACKPLANE && + pi->phy.media_type != ICE_MEDIA_DA && + pi->phy.link_info.link_info & ICE_AQ_LINK_UP) return -EOPNOTSUPP; - abilities = kzalloc(sizeof(*abilities), GFP_KERNEL); - if (!abilities) + phy_caps = kzalloc(sizeof(*phy_caps), GFP_KERNEL); + if (!phy_caps) return -ENOMEM; /* Get the PHY capabilities based on media */ - status = ice_aq_get_phy_caps(p, false, ICE_AQC_REPORT_TOPO_CAP, - abilities, NULL); + if (ice_fw_supports_report_dflt_cfg(pi->hw)) + status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_DFLT_CFG, + phy_caps, NULL); + else + status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP_MEDIA, + phy_caps, NULL); if (status) { - err = -EAGAIN; + err = -EIO; goto done; } - /* copy the ksettings to copy_ks to avoid modifying the original */ - memcpy(©_ks, ks, sizeof(copy_ks)); - /* save autoneg out of ksettings */ autoneg = copy_ks.base.autoneg; - memset(&safe_ks, 0, sizeof(safe_ks)); - /* Get link modes supported by hardware.*/ ice_phy_type_to_ethtool(netdev, &safe_ks); @@ -2290,7 +2258,7 @@ ice_set_link_ksettings(struct net_device *netdev, __ETHTOOL_LINK_MODE_MASK_NBITS)) { if (!test_bit(ICE_FLAG_LINK_LENIENT_MODE_ENA, pf->flags)) netdev_info(netdev, "The selected speed is not supported by the current media. Please select a link speed that is supported by the current media.\n"); - err = -EINVAL; + err = -EOPNOTSUPP; goto done; } @@ -2314,7 +2282,7 @@ ice_set_link_ksettings(struct net_device *netdev, goto done; } - while (test_and_set_bit(__ICE_CFG_BUSY, pf->state)) { + while (test_and_set_bit(ICE_CFG_BUSY, pf->state)) { timeout--; if (!timeout) { err = -EBUSY; @@ -2327,26 +2295,26 @@ ice_set_link_ksettings(struct net_device *netdev, * configuration is initialized during probe from PHY capabilities * software mode, and updated on set PHY configuration. */ - memcpy(&config, &p->phy.curr_user_phy_cfg, sizeof(config)); + config = pi->phy.curr_user_phy_cfg; config.caps |= ICE_AQ_PHY_ENA_AUTO_LINK_UPDT; /* Check autoneg */ - err = ice_setup_autoneg(p, &safe_ks, &config, autoneg, &autoneg_changed, + err = ice_setup_autoneg(pi, &safe_ks, &config, autoneg, &autoneg_changed, netdev); if (err) goto done; /* Call to get the current link speed */ - p->phy.get_link_info = true; - status = ice_get_link_status(p, &linkup); + pi->phy.get_link_info = true; + status = ice_get_link_status(pi, &linkup); if (status) { - err = -EAGAIN; + err = -EIO; goto done; } - curr_link_speed = p->phy.link_info.link_speed; + curr_link_speed = pi->phy.link_info.link_speed; adv_link_speed = ice_ksettings_find_adv_link_speed(ks); /* If speed didn't get set, set it to what it currently is. @@ -2365,7 +2333,7 @@ ice_set_link_ksettings(struct net_device *netdev, } /* save the requested speeds */ - p->phy.link_info.req_speeds = adv_link_speed; + pi->phy.link_info.req_speeds = adv_link_speed; /* set link and auto negotiation so changes take effect */ config.caps |= ICE_AQ_PHY_ENA_LINK; @@ -2373,7 +2341,7 @@ ice_set_link_ksettings(struct net_device *netdev, /* check if there is a PHY type for the requested advertised speed */ if (!(phy_type_low || phy_type_high)) { netdev_info(netdev, "The selected speed is not supported by the current media. Please select a link speed that is supported by the current media.\n"); - err = -EAGAIN; + err = -EOPNOTSUPP; goto done; } @@ -2381,9 +2349,9 @@ ice_set_link_ksettings(struct net_device *netdev, * for set PHY configuration */ config.phy_type_high = cpu_to_le64(phy_type_high) & - abilities->phy_type_high; + phy_caps->phy_type_high; config.phy_type_low = cpu_to_le64(phy_type_low) & - abilities->phy_type_low; + phy_caps->phy_type_low; if (!(config.phy_type_high || config.phy_type_low)) { /* If there is no intersection and lenient mode is enabled, then @@ -2397,13 +2365,13 @@ ice_set_link_ksettings(struct net_device *netdev, pf->nvm_phy_type_lo; } else { netdev_info(netdev, "The selected speed is not supported by the current media. Please select a link speed that is supported by the current media.\n"); - err = -EAGAIN; + err = -EOPNOTSUPP; goto done; } } /* If link is up put link down */ - if (p->phy.link_info.link_info & ICE_AQ_LINK_UP) { + if (pi->phy.link_info.link_info & ICE_AQ_LINK_UP) { /* Tell the OS link is going down, the link will go * back up when fw says it is ready asynchronously */ @@ -2413,18 +2381,18 @@ ice_set_link_ksettings(struct net_device *netdev, } /* make the aq call */ - status = ice_aq_set_phy_cfg(&pf->hw, p, &config, NULL); + status = ice_aq_set_phy_cfg(&pf->hw, pi, &config, NULL); if (status) { netdev_info(netdev, "Set phy config failed,\n"); - err = -EAGAIN; + err = -EIO; goto done; } /* Save speed request */ - p->phy.curr_user_speed_req = adv_link_speed; + pi->phy.curr_user_speed_req = adv_link_speed; done: - kfree(abilities); - clear_bit(__ICE_CFG_BUSY, pf->state); + kfree(phy_caps); + clear_bit(ICE_CFG_BUSY, pf->state); return err; } @@ -2780,7 +2748,7 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) if (ice_xsk_any_rx_ring_ena(vsi)) return -EBUSY; - while (test_and_set_bit(__ICE_CFG_BUSY, pf->state)) { + while (test_and_set_bit(ICE_CFG_BUSY, pf->state)) { timeout--; if (!timeout) return -EBUSY; @@ -2907,7 +2875,7 @@ process_link: /* Bring interface down, copy in the new ring info, then restore the * interface. if VSI is up, bring it down and then back up */ - if (!test_and_set_bit(__ICE_DOWN, vsi->state)) { + if (!test_and_set_bit(ICE_VSI_DOWN, vsi->state)) { ice_down(vsi); if (tx_rings) { @@ -2959,7 +2927,7 @@ free_tx: } done: - clear_bit(__ICE_CFG_BUSY, pf->state); + clear_bit(ICE_CFG_BUSY, pf->state); return err; } @@ -2993,7 +2961,7 @@ ice_get_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) return; /* Get current PHY config */ - status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG, pcaps, + status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_ACTIVE_CFG, pcaps, NULL); if (status) goto out; @@ -3060,7 +3028,7 @@ ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) return -ENOMEM; /* Get current PHY config */ - status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG, pcaps, + status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_ACTIVE_CFG, pcaps, NULL); if (status) { kfree(pcaps); @@ -3078,7 +3046,7 @@ ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) } /* If we have link and don't have autoneg */ - if (!test_bit(__ICE_DOWN, pf->state) && + if (!test_bit(ICE_DOWN, pf->state) && !(hw_link_info->an_info & ICE_AQ_AN_COMPLETED)) { /* Send message that it might not necessarily work*/ netdev_info(netdev, "Autoneg did not complete so changing settings may not result in an actual change.\n"); @@ -3161,7 +3129,7 @@ ice_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, u8 *hfunc) struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; - int ret = 0, i; + int err, i; u8 *lut; if (hfunc) @@ -3180,17 +3148,20 @@ ice_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, u8 *hfunc) if (!lut) return -ENOMEM; - if (ice_get_rss(vsi, key, lut, vsi->rss_table_size)) { - ret = -EIO; + err = ice_get_rss_key(vsi, key); + if (err) + goto out; + + err = ice_get_rss_lut(vsi, lut, vsi->rss_table_size); + if (err) goto out; - } for (i = 0; i < vsi->rss_table_size; i++) indir[i] = (u32)(lut[i]); out: kfree(lut); - return ret; + return err; } /** @@ -3211,7 +3182,7 @@ ice_set_rxfh(struct net_device *netdev, const u32 *indir, const u8 *key, struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; struct device *dev; - u8 *seed = NULL; + int err; dev = ice_pf_to_dev(pf); if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) @@ -3232,7 +3203,10 @@ ice_set_rxfh(struct net_device *netdev, const u32 *indir, const u8 *key, return -ENOMEM; } memcpy(vsi->rss_hkey_user, key, ICE_VSIQF_HKEY_ARRAY_SIZE); - seed = vsi->rss_hkey_user; + + err = ice_set_rss_key(vsi, vsi->rss_hkey_user); + if (err) + return err; } if (!vsi->rss_lut_user) { @@ -3253,8 +3227,9 @@ ice_set_rxfh(struct net_device *netdev, const u32 *indir, const u8 *key, vsi->rss_size); } - if (ice_set_rss(vsi, seed, vsi->rss_lut_user, vsi->rss_table_size)) - return -EIO; + err = ice_set_rss_lut(vsi, vsi->rss_lut_user, vsi->rss_table_size); + if (err) + return err; return 0; } @@ -3350,10 +3325,9 @@ static int ice_get_valid_rss_size(struct ice_hw *hw, int new_size) static int ice_vsi_set_dflt_rss_lut(struct ice_vsi *vsi, int req_rss_size) { struct ice_pf *pf = vsi->back; - enum ice_status status; struct device *dev; struct ice_hw *hw; - int err = 0; + int err; u8 *lut; dev = ice_pf_to_dev(pf); @@ -3374,14 +3348,10 @@ static int ice_vsi_set_dflt_rss_lut(struct ice_vsi *vsi, int req_rss_size) /* create/set RSS LUT */ ice_fill_rss_lut(lut, vsi->rss_table_size, vsi->rss_size); - status = ice_aq_set_rss_lut(hw, vsi->idx, vsi->rss_lut_type, lut, - vsi->rss_table_size); - if (status) { - dev_err(dev, "Cannot set RSS lut, err %s aq_err %s\n", - ice_stat_str(status), + err = ice_set_rss_lut(vsi, lut, vsi->rss_table_size); + if (err) + dev_err(dev, "Cannot set RSS lut, err %d aq_err %s\n", err, ice_aq_str(hw->adminq.sq_last_status)); - err = -EIO; - } kfree(lut); return err; @@ -3540,13 +3510,13 @@ ice_get_rc_coalesce(struct ethtool_coalesce *ec, enum ice_container_type c_type, switch (c_type) { case ICE_RX_CONTAINER: - ec->use_adaptive_rx_coalesce = ITR_IS_DYNAMIC(rc->itr_setting); - ec->rx_coalesce_usecs = rc->itr_setting & ~ICE_ITR_DYNAMIC; + ec->use_adaptive_rx_coalesce = ITR_IS_DYNAMIC(rc); + ec->rx_coalesce_usecs = rc->itr_setting; ec->rx_coalesce_usecs_high = rc->ring->q_vector->intrl; break; case ICE_TX_CONTAINER: - ec->use_adaptive_tx_coalesce = ITR_IS_DYNAMIC(rc->itr_setting); - ec->tx_coalesce_usecs = rc->itr_setting & ~ICE_ITR_DYNAMIC; + ec->use_adaptive_tx_coalesce = ITR_IS_DYNAMIC(rc); + ec->tx_coalesce_usecs = rc->itr_setting; break; default: dev_dbg(ice_pf_to_dev(pf), "Invalid c_type %d\n", c_type); @@ -3664,11 +3634,16 @@ ice_set_rc_coalesce(enum ice_container_type c_type, struct ethtool_coalesce *ec, ICE_MAX_INTRL); return -EINVAL; } + if (ec->rx_coalesce_usecs_high != rc->ring->q_vector->intrl && + (ec->use_adaptive_rx_coalesce || ec->use_adaptive_tx_coalesce)) { + netdev_info(vsi->netdev, "Invalid value, %s-usecs-high cannot be changed if adaptive-tx or adaptive-rx is enabled\n", + c_type_str); + return -EINVAL; + } if (ec->rx_coalesce_usecs_high != rc->ring->q_vector->intrl) { rc->ring->q_vector->intrl = ec->rx_coalesce_usecs_high; - wr32(&pf->hw, GLINT_RATE(rc->ring->q_vector->reg_idx), - ice_intrl_usec_to_reg(ec->rx_coalesce_usecs_high, - pf->hw.intrl_gran)); + ice_write_intrl(rc->ring->q_vector, + ec->rx_coalesce_usecs_high); } use_adaptive_coalesce = ec->use_adaptive_rx_coalesce; @@ -3686,7 +3661,7 @@ ice_set_rc_coalesce(enum ice_container_type c_type, struct ethtool_coalesce *ec, return -EINVAL; } - itr_setting = rc->itr_setting & ~ICE_ITR_DYNAMIC; + itr_setting = rc->itr_setting; if (coalesce_usecs != itr_setting && use_adaptive_coalesce) { netdev_info(vsi->netdev, "%s interrupt throttling cannot be changed if adaptive-%s is enabled\n", c_type_str, c_type_str); @@ -3700,12 +3675,18 @@ ice_set_rc_coalesce(enum ice_container_type c_type, struct ethtool_coalesce *ec, } if (use_adaptive_coalesce) { - rc->itr_setting |= ICE_ITR_DYNAMIC; + rc->itr_mode = ITR_DYNAMIC; } else { - /* save the user set usecs */ + rc->itr_mode = ITR_STATIC; + /* store user facing value how it was set */ rc->itr_setting = coalesce_usecs; - /* device ITR granularity is in 2 usec increments */ - rc->target_itr = ITR_REG_ALIGN(rc->itr_setting); + /* write the change to the register */ + ice_write_itr(rc, coalesce_usecs); + /* force writes to take effect immediately, the flush shouldn't + * be done in the functions above because the intent is for + * them to do lazy writes. + */ + ice_flush(&pf->hw); } return 0; @@ -3767,8 +3748,6 @@ ice_print_if_odd_usecs(struct net_device *netdev, u16 itr_setting, if (use_adaptive_coalesce) return; - itr_setting = ITR_TO_REG(itr_setting); - if (itr_setting != coalesce_usecs && (coalesce_usecs % 2)) netdev_info(netdev, "User set %s-usecs to %d, device only supports even values. Rounding down and attempting to set %s-usecs to %d\n", c_type_str, coalesce_usecs, c_type_str, @@ -3823,7 +3802,6 @@ __ice_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec, return -EINVAL; set_complete: - return 0; } @@ -3936,30 +3914,33 @@ ice_get_module_eeprom(struct net_device *netdev, struct ethtool_eeprom *ee, u8 *data) { struct ice_netdev_priv *np = netdev_priv(netdev); +#define SFF_READ_BLOCK_SIZE 8 + u8 value[SFF_READ_BLOCK_SIZE] = { 0 }; u8 addr = ICE_I2C_EEPROM_DEV_ADDR; struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; enum ice_status status; bool is_sfp = false; - unsigned int i; + unsigned int i, j; u16 offset = 0; - u8 value = 0; u8 page = 0; - status = ice_aq_sff_eeprom(hw, 0, addr, offset, page, 0, - &value, 1, 0, NULL); - if (status) - return -EIO; - if (!ee || !ee->len || !data) return -EINVAL; - if (value == ICE_MODULE_TYPE_SFP) + status = ice_aq_sff_eeprom(hw, 0, addr, offset, page, 0, value, 1, 0, + NULL); + if (status) + return -EIO; + + if (value[0] == ICE_MODULE_TYPE_SFP) is_sfp = true; - for (i = 0; i < ee->len; i++) { + memset(data, 0, ee->len); + for (i = 0; i < ee->len; i += SFF_READ_BLOCK_SIZE) { offset = i + ee->offset; + page = 0; /* Check if we need to access the other memory page */ if (is_sfp) { @@ -3975,11 +3956,37 @@ ice_get_module_eeprom(struct net_device *netdev, } } - status = ice_aq_sff_eeprom(hw, 0, addr, offset, page, !is_sfp, - &value, 1, 0, NULL); - if (status) - value = 0; - data[i] = value; + /* Bit 2 of EEPROM address 0x02 declares upper + * pages are disabled on QSFP modules. + * SFP modules only ever use page 0. + */ + if (page == 0 || !(data[0x2] & 0x4)) { + /* If i2c bus is busy due to slow page change or + * link management access, call can fail. This is normal. + * So we retry this a few times. + */ + for (j = 0; j < 4; j++) { + status = ice_aq_sff_eeprom(hw, 0, addr, offset, page, + !is_sfp, value, + SFF_READ_BLOCK_SIZE, + 0, NULL); + netdev_dbg(netdev, "SFF %02X %02X %02X %X = %02X%02X%02X%02X.%02X%02X%02X%02X (%X)\n", + addr, offset, page, is_sfp, + value[0], value[1], value[2], value[3], + value[4], value[5], value[6], value[7], + status); + if (status) { + usleep_range(1500, 2500); + memset(value, 0, SFF_READ_BLOCK_SIZE); + continue; + } + break; + } + + /* Make sure we have enough room for the new block */ + if ((i + SFF_READ_BLOCK_SIZE) < ee->len) + memcpy(data + i, value, SFF_READ_BLOCK_SIZE); + } } return 0; } diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c index 192729546bbf..16de603b280c 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c @@ -1452,7 +1452,7 @@ int ice_del_fdir_ethtool(struct ice_vsi *vsi, struct ethtool_rxnfc *cmd) return -EBUSY; } - if (test_bit(__ICE_FD_FLUSH_REQ, pf->state)) + if (test_bit(ICE_FD_FLUSH_REQ, pf->state)) return -EBUSY; mutex_lock(&hw->fdir_fltr_lock); @@ -1679,6 +1679,10 @@ int ice_add_fdir_ethtool(struct ice_vsi *vsi, struct ethtool_rxnfc *cmd) input->flex_offset = userdata.flex_offset; } + input->cnt_ena = ICE_FXD_FLTR_QW0_STAT_ENA_PKTS; + input->fdid_prio = ICE_FXD_FLTR_QW1_FDID_PRI_THREE; + input->comp_report = ICE_FXD_FLTR_QW0_COMP_REPORT_SW_FAIL; + /* input struct is added to the HW filter list */ ice_fdir_update_list_entry(pf, input, fsp->location); diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.c b/drivers/net/ethernet/intel/ice/ice_fdir.c index 59c0c6a0f8c5..59ef68f072c0 100644 --- a/drivers/net/ethernet/intel/ice/ice_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_fdir.c @@ -40,6 +40,204 @@ static const u8 ice_fdir_ipv4_pkt[] = { 0x00, 0x00 }; +static const u8 ice_fdir_udp4_gtpu4_pkt[] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x08, 0x00, 0x45, 0x00, + 0x00, 0x4c, 0x00, 0x00, 0x40, 0x00, 0x40, 0x11, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x08, 0x68, 0x08, 0x68, 0x00, 0x00, + 0x00, 0x00, 0x34, 0xff, 0x00, 0x28, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x85, 0x02, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x45, 0x00, + 0x00, 0x1c, 0x00, 0x00, 0x40, 0x00, 0x40, 0x11, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, +}; + +static const u8 ice_fdir_tcp4_gtpu4_pkt[] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x08, 0x00, 0x45, 0x00, + 0x00, 0x58, 0x00, 0x00, 0x40, 0x00, 0x40, 0x11, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x08, 0x68, 0x08, 0x68, 0x00, 0x00, + 0x00, 0x00, 0x34, 0xff, 0x00, 0x28, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x85, 0x02, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x45, 0x00, + 0x00, 0x28, 0x00, 0x00, 0x40, 0x00, 0x40, 0x06, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +}; + +static const u8 ice_fdir_icmp4_gtpu4_pkt[] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x08, 0x00, 0x45, 0x00, + 0x00, 0x4c, 0x00, 0x00, 0x40, 0x00, 0x40, 0x11, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x08, 0x68, 0x08, 0x68, 0x00, 0x00, + 0x00, 0x00, 0x34, 0xff, 0x00, 0x28, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x85, 0x02, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x45, 0x00, + 0x00, 0x1c, 0x00, 0x00, 0x40, 0x00, 0x40, 0x01, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, +}; + +static const u8 ice_fdir_ipv4_gtpu4_pkt[] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x08, 0x00, 0x45, 0x00, + 0x00, 0x44, 0x00, 0x00, 0x40, 0x00, 0x40, 0x11, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x08, 0x68, 0x08, 0x68, 0x00, 0x00, + 0x00, 0x00, 0x34, 0xff, 0x00, 0x28, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x85, 0x02, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x45, 0x00, + 0x00, 0x14, 0x00, 0x00, 0x40, 0x00, 0x40, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, +}; + +static const u8 ice_fdir_ipv4_l2tpv3_pkt[] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x08, 0x00, 0x45, 0x00, + 0x00, 0x14, 0x00, 0x00, 0x40, 0x00, 0x40, 0x73, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +}; + +static const u8 ice_fdir_ipv6_l2tpv3_pkt[] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x86, 0xDD, 0x60, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x73, 0x40, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, +}; + +static const u8 ice_fdir_ipv4_esp_pkt[] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x08, 0x00, 0x45, 0x00, + 0x00, 0x14, 0x00, 0x00, 0x40, 0x00, 0x40, 0x32, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00 +}; + +static const u8 ice_fdir_ipv6_esp_pkt[] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x86, 0xDD, 0x60, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x32, 0x40, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +}; + +static const u8 ice_fdir_ipv4_ah_pkt[] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x08, 0x00, 0x45, 0x00, + 0x00, 0x14, 0x00, 0x00, 0x40, 0x00, 0x40, 0x33, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00 +}; + +static const u8 ice_fdir_ipv6_ah_pkt[] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x86, 0xDD, 0x60, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x33, 0x40, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +}; + +static const u8 ice_fdir_ipv4_nat_t_esp_pkt[] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x08, 0x00, 0x45, 0x00, + 0x00, 0x1C, 0x00, 0x00, 0x40, 0x00, 0x40, 0x11, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x11, 0x94, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, +}; + +static const u8 ice_fdir_ipv6_nat_t_esp_pkt[] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x86, 0xDD, 0x60, 0x00, + 0x00, 0x00, 0x00, 0x08, 0x11, 0x40, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x11, 0x94, 0x00, 0x00, 0x00, 0x08, +}; + +static const u8 ice_fdir_ipv4_pfcp_node_pkt[] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x08, 0x00, 0x45, 0x00, + 0x00, 0x2C, 0x00, 0x00, 0x40, 0x00, 0x40, 0x11, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x22, 0x65, 0x22, 0x65, 0x00, 0x00, + 0x00, 0x00, 0x20, 0x00, 0x00, 0x10, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, +}; + +static const u8 ice_fdir_ipv4_pfcp_session_pkt[] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x08, 0x00, 0x45, 0x00, + 0x00, 0x2C, 0x00, 0x00, 0x40, 0x00, 0x40, 0x11, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x22, 0x65, 0x22, 0x65, 0x00, 0x00, + 0x00, 0x00, 0x21, 0x00, 0x00, 0x10, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, +}; + +static const u8 ice_fdir_ipv6_pfcp_node_pkt[] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x86, 0xDD, 0x60, 0x00, + 0x00, 0x00, 0x00, 0x18, 0x11, 0x40, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x22, 0x65, + 0x22, 0x65, 0x00, 0x00, 0x00, 0x00, 0x20, 0x00, + 0x00, 0x10, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +}; + +static const u8 ice_fdir_ipv6_pfcp_session_pkt[] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x86, 0xDD, 0x60, 0x00, + 0x00, 0x00, 0x00, 0x18, 0x11, 0x40, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x22, 0x65, + 0x22, 0x65, 0x00, 0x00, 0x00, 0x00, 0x21, 0x00, + 0x00, 0x10, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +}; + +static const u8 ice_fdir_non_ip_l2_pkt[] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +}; + static const u8 ice_fdir_tcpv6_pkt[] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x86, 0xDD, 0x60, 0x00, @@ -239,6 +437,111 @@ static const struct ice_fdir_base_pkt ice_fdir_pkt[] = { sizeof(ice_fdir_ip4_tun_pkt), ice_fdir_ip4_tun_pkt, }, { + ICE_FLTR_PTYPE_NONF_IPV4_GTPU_IPV4_UDP, + sizeof(ice_fdir_udp4_gtpu4_pkt), + ice_fdir_udp4_gtpu4_pkt, + sizeof(ice_fdir_udp4_gtpu4_pkt), + ice_fdir_udp4_gtpu4_pkt, + }, + { + ICE_FLTR_PTYPE_NONF_IPV4_GTPU_IPV4_TCP, + sizeof(ice_fdir_tcp4_gtpu4_pkt), + ice_fdir_tcp4_gtpu4_pkt, + sizeof(ice_fdir_tcp4_gtpu4_pkt), + ice_fdir_tcp4_gtpu4_pkt, + }, + { + ICE_FLTR_PTYPE_NONF_IPV4_GTPU_IPV4_ICMP, + sizeof(ice_fdir_icmp4_gtpu4_pkt), + ice_fdir_icmp4_gtpu4_pkt, + sizeof(ice_fdir_icmp4_gtpu4_pkt), + ice_fdir_icmp4_gtpu4_pkt, + }, + { + ICE_FLTR_PTYPE_NONF_IPV4_GTPU_IPV4_OTHER, + sizeof(ice_fdir_ipv4_gtpu4_pkt), + ice_fdir_ipv4_gtpu4_pkt, + sizeof(ice_fdir_ipv4_gtpu4_pkt), + ice_fdir_ipv4_gtpu4_pkt, + }, + { + ICE_FLTR_PTYPE_NONF_IPV4_L2TPV3, + sizeof(ice_fdir_ipv4_l2tpv3_pkt), ice_fdir_ipv4_l2tpv3_pkt, + sizeof(ice_fdir_ipv4_l2tpv3_pkt), ice_fdir_ipv4_l2tpv3_pkt, + }, + { + ICE_FLTR_PTYPE_NONF_IPV6_L2TPV3, + sizeof(ice_fdir_ipv6_l2tpv3_pkt), ice_fdir_ipv6_l2tpv3_pkt, + sizeof(ice_fdir_ipv6_l2tpv3_pkt), ice_fdir_ipv6_l2tpv3_pkt, + }, + { + ICE_FLTR_PTYPE_NONF_IPV4_ESP, + sizeof(ice_fdir_ipv4_esp_pkt), ice_fdir_ipv4_esp_pkt, + sizeof(ice_fdir_ipv4_esp_pkt), ice_fdir_ipv4_esp_pkt, + }, + { + ICE_FLTR_PTYPE_NONF_IPV6_ESP, + sizeof(ice_fdir_ipv6_esp_pkt), ice_fdir_ipv6_esp_pkt, + sizeof(ice_fdir_ipv6_esp_pkt), ice_fdir_ipv6_esp_pkt, + }, + { + ICE_FLTR_PTYPE_NONF_IPV4_AH, + sizeof(ice_fdir_ipv4_ah_pkt), ice_fdir_ipv4_ah_pkt, + sizeof(ice_fdir_ipv4_ah_pkt), ice_fdir_ipv4_ah_pkt, + }, + { + ICE_FLTR_PTYPE_NONF_IPV6_AH, + sizeof(ice_fdir_ipv6_ah_pkt), ice_fdir_ipv6_ah_pkt, + sizeof(ice_fdir_ipv6_ah_pkt), ice_fdir_ipv6_ah_pkt, + }, + { + ICE_FLTR_PTYPE_NONF_IPV4_NAT_T_ESP, + sizeof(ice_fdir_ipv4_nat_t_esp_pkt), + ice_fdir_ipv4_nat_t_esp_pkt, + sizeof(ice_fdir_ipv4_nat_t_esp_pkt), + ice_fdir_ipv4_nat_t_esp_pkt, + }, + { + ICE_FLTR_PTYPE_NONF_IPV6_NAT_T_ESP, + sizeof(ice_fdir_ipv6_nat_t_esp_pkt), + ice_fdir_ipv6_nat_t_esp_pkt, + sizeof(ice_fdir_ipv6_nat_t_esp_pkt), + ice_fdir_ipv6_nat_t_esp_pkt, + }, + { + ICE_FLTR_PTYPE_NONF_IPV4_PFCP_NODE, + sizeof(ice_fdir_ipv4_pfcp_node_pkt), + ice_fdir_ipv4_pfcp_node_pkt, + sizeof(ice_fdir_ipv4_pfcp_node_pkt), + ice_fdir_ipv4_pfcp_node_pkt, + }, + { + ICE_FLTR_PTYPE_NONF_IPV4_PFCP_SESSION, + sizeof(ice_fdir_ipv4_pfcp_session_pkt), + ice_fdir_ipv4_pfcp_session_pkt, + sizeof(ice_fdir_ipv4_pfcp_session_pkt), + ice_fdir_ipv4_pfcp_session_pkt, + }, + { + ICE_FLTR_PTYPE_NONF_IPV6_PFCP_NODE, + sizeof(ice_fdir_ipv6_pfcp_node_pkt), + ice_fdir_ipv6_pfcp_node_pkt, + sizeof(ice_fdir_ipv6_pfcp_node_pkt), + ice_fdir_ipv6_pfcp_node_pkt, + }, + { + ICE_FLTR_PTYPE_NONF_IPV6_PFCP_SESSION, + sizeof(ice_fdir_ipv6_pfcp_session_pkt), + ice_fdir_ipv6_pfcp_session_pkt, + sizeof(ice_fdir_ipv6_pfcp_session_pkt), + ice_fdir_ipv6_pfcp_session_pkt, + }, + { + ICE_FLTR_PTYPE_NON_IP_L2, + sizeof(ice_fdir_non_ip_l2_pkt), ice_fdir_non_ip_l2_pkt, + sizeof(ice_fdir_non_ip_l2_pkt), ice_fdir_non_ip_l2_pkt, + }, + { ICE_FLTR_PTYPE_NONF_IPV6_TCP, sizeof(ice_fdir_tcpv6_pkt), ice_fdir_tcpv6_pkt, sizeof(ice_fdir_tcp6_tun_pkt), ice_fdir_tcp6_tun_pkt, @@ -374,21 +677,31 @@ ice_fdir_get_prgm_desc(struct ice_hw *hw, struct ice_fdir_fltr *input, if (input->dest_ctl == ICE_FLTR_PRGM_DESC_DEST_DROP_PKT) { fdir_fltr_ctx.drop = ICE_FXD_FLTR_QW0_DROP_YES; fdir_fltr_ctx.qindex = 0; + } else if (input->dest_ctl == + ICE_FLTR_PRGM_DESC_DEST_DIRECT_PKT_OTHER) { + fdir_fltr_ctx.drop = ICE_FXD_FLTR_QW0_DROP_NO; + fdir_fltr_ctx.qindex = 0; } else { + if (input->dest_ctl == + ICE_FLTR_PRGM_DESC_DEST_DIRECT_PKT_QGROUP) + fdir_fltr_ctx.toq = input->q_region; fdir_fltr_ctx.drop = ICE_FXD_FLTR_QW0_DROP_NO; fdir_fltr_ctx.qindex = input->q_index; } - fdir_fltr_ctx.cnt_ena = ICE_FXD_FLTR_QW0_STAT_ENA_PKTS; + fdir_fltr_ctx.cnt_ena = input->cnt_ena; fdir_fltr_ctx.cnt_index = input->cnt_index; fdir_fltr_ctx.fd_vsi = ice_get_hw_vsi_num(hw, input->dest_vsi); fdir_fltr_ctx.evict_ena = ICE_FXD_FLTR_QW0_EVICT_ENA_FALSE; - fdir_fltr_ctx.toq_prio = 3; + if (input->dest_ctl == ICE_FLTR_PRGM_DESC_DEST_DIRECT_PKT_OTHER) + fdir_fltr_ctx.toq_prio = 0; + else + fdir_fltr_ctx.toq_prio = 3; fdir_fltr_ctx.pcmd = add ? ICE_FXD_FLTR_QW1_PCMD_ADD : ICE_FXD_FLTR_QW1_PCMD_REMOVE; fdir_fltr_ctx.swap = ICE_FXD_FLTR_QW1_SWAP_NOT_SET; fdir_fltr_ctx.comp_q = ICE_FXD_FLTR_QW0_COMP_Q_ZERO; - fdir_fltr_ctx.comp_report = ICE_FXD_FLTR_QW0_COMP_REPORT_SW_FAIL; - fdir_fltr_ctx.fdid_prio = 3; + fdir_fltr_ctx.comp_report = input->comp_report; + fdir_fltr_ctx.fdid_prio = input->fdid_prio; fdir_fltr_ctx.desc_prof = 1; fdir_fltr_ctx.desc_prof_prio = 3; ice_set_fd_desc_val(&fdir_fltr_ctx, fdesc); @@ -471,6 +784,55 @@ static void ice_pkt_insert_ipv6_addr(u8 *pkt, int offset, __be32 *addr) } /** + * ice_pkt_insert_u6_qfi - insert a u6 value QFI into a memory buffer for GTPU + * @pkt: packet buffer + * @offset: offset into buffer + * @data: 8 bit value to convert and insert into pkt at offset + * + * This function is designed for inserting QFI (6 bits) for GTPU. + */ +static void ice_pkt_insert_u6_qfi(u8 *pkt, int offset, u8 data) +{ + u8 ret; + + ret = (data & 0x3F) + (*(pkt + offset) & 0xC0); + memcpy(pkt + offset, &ret, sizeof(ret)); +} + +/** + * ice_pkt_insert_u8 - insert a u8 value into a memory buffer. + * @pkt: packet buffer + * @offset: offset into buffer + * @data: 8 bit value to convert and insert into pkt at offset + */ +static void ice_pkt_insert_u8(u8 *pkt, int offset, u8 data) +{ + memcpy(pkt + offset, &data, sizeof(data)); +} + +/** + * ice_pkt_insert_u8_tc - insert a u8 value into a memory buffer for TC ipv6. + * @pkt: packet buffer + * @offset: offset into buffer + * @data: 8 bit value to convert and insert into pkt at offset + * + * This function is designed for inserting Traffic Class (TC) for IPv6, + * since that TC is not aligned in number of bytes. Here we split it out + * into two part and fill each byte with data copy from pkt, then insert + * the two bytes data one by one. + */ +static void ice_pkt_insert_u8_tc(u8 *pkt, int offset, u8 data) +{ + u8 high, low; + + high = (data >> 4) + (*(pkt + offset) & 0xF0); + memcpy(pkt + offset, &high, sizeof(high)); + + low = (*(pkt + offset + 1) & 0x0F) + ((data & 0x0F) << 4); + memcpy(pkt + offset + 1, &low, sizeof(low)); +} + +/** * ice_pkt_insert_u16 - insert a be16 value into a memory buffer * @pkt: packet buffer * @offset: offset into buffer @@ -493,6 +855,16 @@ static void ice_pkt_insert_u32(u8 *pkt, int offset, __be32 data) } /** + * ice_pkt_insert_mac_addr - insert a MAC addr into a memory buffer. + * @pkt: packet buffer + * @addr: MAC address to convert and insert into pkt at offset + */ +static void ice_pkt_insert_mac_addr(u8 *pkt, u8 *addr) +{ + ether_addr_copy(pkt, addr); +} + +/** * ice_fdir_get_gen_prgm_pkt - generate a training packet * @hw: pointer to the hardware structure * @input: flow director filter data structure @@ -520,11 +892,9 @@ ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input, case IPPROTO_SCTP: flow = ICE_FLTR_PTYPE_NONF_IPV4_SCTP; break; - case IPPROTO_IP: + default: flow = ICE_FLTR_PTYPE_NONF_IPV4_OTHER; break; - default: - return ICE_ERR_PARAM; } } else if (input->flow_type == ICE_FLTR_PTYPE_NONF_IPV6_OTHER) { switch (input->ip.v6.proto) { @@ -537,11 +907,9 @@ ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input, case IPPROTO_SCTP: flow = ICE_FLTR_PTYPE_NONF_IPV6_SCTP; break; - case IPPROTO_IP: + default: flow = ICE_FLTR_PTYPE_NONF_IPV6_OTHER; break; - default: - return ICE_ERR_PARAM; } } else { flow = input->flow_type; @@ -580,6 +948,9 @@ ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input, input->ip.v4.dst_ip); ice_pkt_insert_u16(loc, ICE_IPV4_TCP_SRC_PORT_OFFSET, input->ip.v4.dst_port); + ice_pkt_insert_u8(loc, ICE_IPV4_TOS_OFFSET, input->ip.v4.tos); + ice_pkt_insert_u8(loc, ICE_IPV4_TTL_OFFSET, input->ip.v4.ttl); + ice_pkt_insert_mac_addr(loc, input->ext_data.dst_mac); if (frag) loc[20] = ICE_FDIR_IPV4_PKT_FLAG_DF; break; @@ -592,6 +963,11 @@ ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input, input->ip.v4.dst_ip); ice_pkt_insert_u16(loc, ICE_IPV4_UDP_SRC_PORT_OFFSET, input->ip.v4.dst_port); + ice_pkt_insert_u8(loc, ICE_IPV4_TOS_OFFSET, input->ip.v4.tos); + ice_pkt_insert_u8(loc, ICE_IPV4_TTL_OFFSET, input->ip.v4.ttl); + ice_pkt_insert_mac_addr(loc, input->ext_data.dst_mac); + ice_pkt_insert_mac_addr(loc + ETH_ALEN, + input->ext_data.src_mac); break; case ICE_FLTR_PTYPE_NONF_IPV4_SCTP: ice_pkt_insert_u32(loc, ICE_IPV4_DST_ADDR_OFFSET, @@ -602,13 +978,87 @@ ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input, input->ip.v4.dst_ip); ice_pkt_insert_u16(loc, ICE_IPV4_SCTP_SRC_PORT_OFFSET, input->ip.v4.dst_port); + ice_pkt_insert_u8(loc, ICE_IPV4_TOS_OFFSET, input->ip.v4.tos); + ice_pkt_insert_u8(loc, ICE_IPV4_TTL_OFFSET, input->ip.v4.ttl); + ice_pkt_insert_mac_addr(loc, input->ext_data.dst_mac); break; case ICE_FLTR_PTYPE_NONF_IPV4_OTHER: ice_pkt_insert_u32(loc, ICE_IPV4_DST_ADDR_OFFSET, input->ip.v4.src_ip); ice_pkt_insert_u32(loc, ICE_IPV4_SRC_ADDR_OFFSET, input->ip.v4.dst_ip); - ice_pkt_insert_u16(loc, ICE_IPV4_PROTO_OFFSET, 0); + ice_pkt_insert_u8(loc, ICE_IPV4_TOS_OFFSET, input->ip.v4.tos); + ice_pkt_insert_u8(loc, ICE_IPV4_TTL_OFFSET, input->ip.v4.ttl); + ice_pkt_insert_u8(loc, ICE_IPV4_PROTO_OFFSET, + input->ip.v4.proto); + ice_pkt_insert_mac_addr(loc, input->ext_data.dst_mac); + break; + case ICE_FLTR_PTYPE_NONF_IPV4_GTPU_IPV4_UDP: + case ICE_FLTR_PTYPE_NONF_IPV4_GTPU_IPV4_TCP: + case ICE_FLTR_PTYPE_NONF_IPV4_GTPU_IPV4_ICMP: + case ICE_FLTR_PTYPE_NONF_IPV4_GTPU_IPV4_OTHER: + ice_pkt_insert_u32(loc, ICE_IPV4_DST_ADDR_OFFSET, + input->ip.v4.src_ip); + ice_pkt_insert_u32(loc, ICE_IPV4_SRC_ADDR_OFFSET, + input->ip.v4.dst_ip); + ice_pkt_insert_u32(loc, ICE_IPV4_GTPU_TEID_OFFSET, + input->gtpu_data.teid); + ice_pkt_insert_u6_qfi(loc, ICE_IPV4_GTPU_QFI_OFFSET, + input->gtpu_data.qfi); + break; + case ICE_FLTR_PTYPE_NONF_IPV4_L2TPV3: + ice_pkt_insert_u32(loc, ICE_IPV4_L2TPV3_SESS_ID_OFFSET, + input->l2tpv3_data.session_id); + break; + case ICE_FLTR_PTYPE_NONF_IPV6_L2TPV3: + ice_pkt_insert_u32(loc, ICE_IPV6_L2TPV3_SESS_ID_OFFSET, + input->l2tpv3_data.session_id); + break; + case ICE_FLTR_PTYPE_NONF_IPV4_ESP: + ice_pkt_insert_u32(loc, ICE_IPV4_ESP_SPI_OFFSET, + input->ip.v4.sec_parm_idx); + break; + case ICE_FLTR_PTYPE_NONF_IPV6_ESP: + ice_pkt_insert_u32(loc, ICE_IPV6_ESP_SPI_OFFSET, + input->ip.v6.sec_parm_idx); + break; + case ICE_FLTR_PTYPE_NONF_IPV4_AH: + ice_pkt_insert_u32(loc, ICE_IPV4_AH_SPI_OFFSET, + input->ip.v4.sec_parm_idx); + break; + case ICE_FLTR_PTYPE_NONF_IPV6_AH: + ice_pkt_insert_u32(loc, ICE_IPV6_AH_SPI_OFFSET, + input->ip.v6.sec_parm_idx); + break; + case ICE_FLTR_PTYPE_NONF_IPV4_NAT_T_ESP: + ice_pkt_insert_u32(loc, ICE_IPV4_DST_ADDR_OFFSET, + input->ip.v4.src_ip); + ice_pkt_insert_u32(loc, ICE_IPV4_SRC_ADDR_OFFSET, + input->ip.v4.dst_ip); + ice_pkt_insert_u32(loc, ICE_IPV4_NAT_T_ESP_SPI_OFFSET, + input->ip.v4.sec_parm_idx); + break; + case ICE_FLTR_PTYPE_NONF_IPV6_NAT_T_ESP: + ice_pkt_insert_ipv6_addr(loc, ICE_IPV6_DST_ADDR_OFFSET, + input->ip.v6.src_ip); + ice_pkt_insert_ipv6_addr(loc, ICE_IPV6_SRC_ADDR_OFFSET, + input->ip.v6.dst_ip); + ice_pkt_insert_u32(loc, ICE_IPV6_NAT_T_ESP_SPI_OFFSET, + input->ip.v6.sec_parm_idx); + break; + case ICE_FLTR_PTYPE_NONF_IPV4_PFCP_NODE: + case ICE_FLTR_PTYPE_NONF_IPV4_PFCP_SESSION: + ice_pkt_insert_u16(loc, ICE_IPV4_UDP_SRC_PORT_OFFSET, + input->ip.v4.dst_port); + break; + case ICE_FLTR_PTYPE_NONF_IPV6_PFCP_NODE: + case ICE_FLTR_PTYPE_NONF_IPV6_PFCP_SESSION: + ice_pkt_insert_u16(loc, ICE_IPV6_UDP_SRC_PORT_OFFSET, + input->ip.v6.dst_port); + break; + case ICE_FLTR_PTYPE_NON_IP_L2: + ice_pkt_insert_u16(loc, ICE_MAC_ETHTYPE_OFFSET, + input->ext_data.ether_type); break; case ICE_FLTR_PTYPE_NONF_IPV6_TCP: ice_pkt_insert_ipv6_addr(loc, ICE_IPV6_DST_ADDR_OFFSET, @@ -619,6 +1069,9 @@ ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input, input->ip.v6.src_port); ice_pkt_insert_u16(loc, ICE_IPV6_TCP_SRC_PORT_OFFSET, input->ip.v6.dst_port); + ice_pkt_insert_u8_tc(loc, ICE_IPV6_TC_OFFSET, input->ip.v6.tc); + ice_pkt_insert_u8(loc, ICE_IPV6_HLIM_OFFSET, input->ip.v6.hlim); + ice_pkt_insert_mac_addr(loc, input->ext_data.dst_mac); break; case ICE_FLTR_PTYPE_NONF_IPV6_UDP: ice_pkt_insert_ipv6_addr(loc, ICE_IPV6_DST_ADDR_OFFSET, @@ -629,6 +1082,9 @@ ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input, input->ip.v6.src_port); ice_pkt_insert_u16(loc, ICE_IPV6_UDP_SRC_PORT_OFFSET, input->ip.v6.dst_port); + ice_pkt_insert_u8_tc(loc, ICE_IPV6_TC_OFFSET, input->ip.v6.tc); + ice_pkt_insert_u8(loc, ICE_IPV6_HLIM_OFFSET, input->ip.v6.hlim); + ice_pkt_insert_mac_addr(loc, input->ext_data.dst_mac); break; case ICE_FLTR_PTYPE_NONF_IPV6_SCTP: ice_pkt_insert_ipv6_addr(loc, ICE_IPV6_DST_ADDR_OFFSET, @@ -639,12 +1095,20 @@ ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input, input->ip.v6.src_port); ice_pkt_insert_u16(loc, ICE_IPV6_SCTP_SRC_PORT_OFFSET, input->ip.v6.dst_port); + ice_pkt_insert_u8_tc(loc, ICE_IPV6_TC_OFFSET, input->ip.v6.tc); + ice_pkt_insert_u8(loc, ICE_IPV6_HLIM_OFFSET, input->ip.v6.hlim); + ice_pkt_insert_mac_addr(loc, input->ext_data.dst_mac); break; case ICE_FLTR_PTYPE_NONF_IPV6_OTHER: ice_pkt_insert_ipv6_addr(loc, ICE_IPV6_DST_ADDR_OFFSET, input->ip.v6.src_ip); ice_pkt_insert_ipv6_addr(loc, ICE_IPV6_SRC_ADDR_OFFSET, input->ip.v6.dst_ip); + ice_pkt_insert_u8_tc(loc, ICE_IPV6_TC_OFFSET, input->ip.v6.tc); + ice_pkt_insert_u8(loc, ICE_IPV6_HLIM_OFFSET, input->ip.v6.hlim); + ice_pkt_insert_u8(loc, ICE_IPV6_PROTO_OFFSET, + input->ip.v6.proto); + ice_pkt_insert_mac_addr(loc, input->ext_data.dst_mac); break; default: return ICE_ERR_PARAM; @@ -671,7 +1135,7 @@ bool ice_fdir_has_frag(enum ice_fltr_ptype flow) } /** - * ice_fdir_find_by_idx - find filter with idx + * ice_fdir_find_fltr_by_idx - find filter with idx * @hw: pointer to hardware structure * @fltr_idx: index to find. * diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.h b/drivers/net/ethernet/intel/ice/ice_fdir.h index 1c587766daab..d2d40e18ae8a 100644 --- a/drivers/net/ethernet/intel/ice/ice_fdir.h +++ b/drivers/net/ethernet/intel/ice/ice_fdir.h @@ -25,6 +25,25 @@ #define ICE_IPV6_UDP_DST_PORT_OFFSET 56 #define ICE_IPV6_SCTP_SRC_PORT_OFFSET 54 #define ICE_IPV6_SCTP_DST_PORT_OFFSET 56 +#define ICE_MAC_ETHTYPE_OFFSET 12 +#define ICE_IPV4_TOS_OFFSET 15 +#define ICE_IPV4_TTL_OFFSET 22 +#define ICE_IPV6_TC_OFFSET 14 +#define ICE_IPV6_HLIM_OFFSET 21 +#define ICE_IPV6_PROTO_OFFSET 20 +#define ICE_IPV4_GTPU_TEID_OFFSET 46 +#define ICE_IPV4_GTPU_QFI_OFFSET 56 +#define ICE_IPV4_L2TPV3_SESS_ID_OFFSET 34 +#define ICE_IPV6_L2TPV3_SESS_ID_OFFSET 54 +#define ICE_IPV4_ESP_SPI_OFFSET 34 +#define ICE_IPV6_ESP_SPI_OFFSET 54 +#define ICE_IPV4_AH_SPI_OFFSET 38 +#define ICE_IPV6_AH_SPI_OFFSET 58 +#define ICE_IPV4_NAT_T_ESP_SPI_OFFSET 42 +#define ICE_IPV6_NAT_T_ESP_SPI_OFFSET 62 + +#define ICE_FDIR_MAX_FLTRS 16384 + /* IP v4 has 2 flag bits that enable fragment processing: DF and MF. DF * requests that the packet not be fragmented. MF indicates that a packet has * been fragmented. @@ -34,6 +53,8 @@ enum ice_fltr_prgm_desc_dest { ICE_FLTR_PRGM_DESC_DEST_DROP_PKT, ICE_FLTR_PRGM_DESC_DEST_DIRECT_PKT_QINDEX, + ICE_FLTR_PRGM_DESC_DEST_DIRECT_PKT_QGROUP, + ICE_FLTR_PRGM_DESC_DEST_DIRECT_PKT_OTHER, }; enum ice_fltr_prgm_desc_fd_status { @@ -86,6 +107,7 @@ struct ice_fdir_v4 { u8 tos; u8 ip_ver; u8 proto; + u8 ttl; }; #define ICE_IPV6_ADDR_LEN_AS_U32 4 @@ -99,10 +121,35 @@ struct ice_fdir_v6 { __be32 sec_parm_idx; /* security parameter index */ u8 tc; u8 proto; + u8 hlim; +}; + +struct ice_fdir_udp_gtp { + u8 flags; + u8 msg_type; + __be16 rsrvd_len; + __be32 teid; + __be16 rsrvd_seq_nbr; + u8 rsrvd_n_pdu_nbr; + u8 rsrvd_next_ext_type; + u8 rsvrd_ext_len; + u8 pdu_type:4, + spare:4; + u8 ppp:1, + rqi:1, + qfi:6; + u32 rsvrd; + u8 next_ext; +}; + +struct ice_fdir_l2tpv3 { + __be32 session_id; }; struct ice_fdir_extra { u8 dst_mac[ETH_ALEN]; /* dest MAC address */ + u8 src_mac[ETH_ALEN]; /* src MAC address */ + __be16 ether_type; /* for NON_IP_L2 */ u32 usr_def[2]; /* user data */ __be16 vlan_type; /* VLAN ethertype */ __be16 vlan_tag; /* VLAN tag info */ @@ -117,11 +164,19 @@ struct ice_fdir_fltr { struct ice_fdir_v6 v6; } ip, mask; + struct ice_fdir_udp_gtp gtpu_data; + struct ice_fdir_udp_gtp gtpu_mask; + + struct ice_fdir_l2tpv3 l2tpv3_data; + struct ice_fdir_l2tpv3 l2tpv3_mask; + struct ice_fdir_extra ext_data; struct ice_fdir_extra ext_mask; /* flex byte filter data */ __be16 flex_word; + /* queue region size (=2^q_region) */ + u8 q_region; u16 flex_offset; u16 flex_fltr; @@ -129,9 +184,12 @@ struct ice_fdir_fltr { u16 q_index; u16 dest_vsi; u8 dest_ctl; + u8 cnt_ena; u8 fltr_status; u16 cnt_index; u32 fltr_id; + u8 fdid_prio; + u8 comp_report; }; /* Dummy packet filter definition structure */ diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c index 5e1fd30c0a0f..06ac9badee77 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c @@ -334,6 +334,7 @@ ice_boost_tcam_handler(u32 sect_type, void *section, u32 index, u32 *offset) if (sect_type != ICE_SID_RXPARSER_BOOST_TCAM) return NULL; + /* cppcheck-suppress nullPointer */ if (index > ICE_MAX_BST_TCAMS_IN_BUF) return NULL; @@ -404,6 +405,7 @@ ice_label_enum_handler(u32 __always_unused sect_type, void *section, u32 index, if (!section) return NULL; + /* cppcheck-suppress nullPointer */ if (index > ICE_MAX_LABELS_IN_BUF) return NULL; @@ -1063,32 +1065,36 @@ ice_download_pkg(struct ice_hw *hw, struct ice_seg *ice_seg) static enum ice_status ice_init_pkg_info(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr) { - struct ice_global_metadata_seg *meta_seg; struct ice_generic_seg_hdr *seg_hdr; if (!pkg_hdr) return ICE_ERR_PARAM; - meta_seg = (struct ice_global_metadata_seg *) - ice_find_seg_in_pkg(hw, SEGMENT_TYPE_METADATA, pkg_hdr); - if (meta_seg) { - hw->pkg_ver = meta_seg->pkg_ver; - memcpy(hw->pkg_name, meta_seg->pkg_name, sizeof(hw->pkg_name)); + seg_hdr = ice_find_seg_in_pkg(hw, SEGMENT_TYPE_ICE, pkg_hdr); + if (seg_hdr) { + struct ice_meta_sect *meta; + struct ice_pkg_enum state; + + memset(&state, 0, sizeof(state)); + + /* Get package information from the Metadata Section */ + meta = ice_pkg_enum_section((struct ice_seg *)seg_hdr, &state, + ICE_SID_METADATA); + if (!meta) { + ice_debug(hw, ICE_DBG_INIT, "Did not find ice metadata section in package\n"); + return ICE_ERR_CFG; + } + + hw->pkg_ver = meta->ver; + memcpy(hw->pkg_name, meta->name, sizeof(meta->name)); ice_debug(hw, ICE_DBG_PKG, "Pkg: %d.%d.%d.%d, %s\n", - meta_seg->pkg_ver.major, meta_seg->pkg_ver.minor, - meta_seg->pkg_ver.update, meta_seg->pkg_ver.draft, - meta_seg->pkg_name); - } else { - ice_debug(hw, ICE_DBG_INIT, "Did not find metadata segment in driver package\n"); - return ICE_ERR_CFG; - } + meta->ver.major, meta->ver.minor, meta->ver.update, + meta->ver.draft, meta->name); - seg_hdr = ice_find_seg_in_pkg(hw, SEGMENT_TYPE_ICE, pkg_hdr); - if (seg_hdr) { - hw->ice_pkg_ver = seg_hdr->seg_format_ver; - memcpy(hw->ice_pkg_name, seg_hdr->seg_id, - sizeof(hw->ice_pkg_name)); + hw->ice_seg_fmt_ver = seg_hdr->seg_format_ver; + memcpy(hw->ice_seg_id, seg_hdr->seg_id, + sizeof(hw->ice_seg_id)); ice_debug(hw, ICE_DBG_PKG, "Ice Seg: %d.%d.%d.%d, %s\n", seg_hdr->seg_format_ver.major, @@ -2063,6 +2069,7 @@ ice_match_prop_lst(struct list_head *list1, struct list_head *list2) count++; list_for_each_entry(tmp2, list2, list) chk_count++; + /* cppcheck-suppress knownConditionTrueFalse */ if (!count || count != chk_count) return false; @@ -2361,18 +2368,82 @@ ice_vsig_add_mv_vsi(struct ice_hw *hw, enum ice_block blk, u16 vsi, u16 vsig) } /** - * ice_find_prof_id - find profile ID for a given field vector + * ice_prof_has_mask_idx - determine if profile index masking is identical + * @hw: pointer to the hardware structure + * @blk: HW block + * @prof: profile to check + * @idx: profile index to check + * @mask: mask to match + */ +static bool +ice_prof_has_mask_idx(struct ice_hw *hw, enum ice_block blk, u8 prof, u16 idx, + u16 mask) +{ + bool expect_no_mask = false; + bool found = false; + bool match = false; + u16 i; + + /* If mask is 0x0000 or 0xffff, then there is no masking */ + if (mask == 0 || mask == 0xffff) + expect_no_mask = true; + + /* Scan the enabled masks on this profile, for the specified idx */ + for (i = hw->blk[blk].masks.first; i < hw->blk[blk].masks.first + + hw->blk[blk].masks.count; i++) + if (hw->blk[blk].es.mask_ena[prof] & BIT(i)) + if (hw->blk[blk].masks.masks[i].in_use && + hw->blk[blk].masks.masks[i].idx == idx) { + found = true; + if (hw->blk[blk].masks.masks[i].mask == mask) + match = true; + break; + } + + if (expect_no_mask) { + if (found) + return false; + } else { + if (!match) + return false; + } + + return true; +} + +/** + * ice_prof_has_mask - determine if profile masking is identical + * @hw: pointer to the hardware structure + * @blk: HW block + * @prof: profile to check + * @masks: masks to match + */ +static bool +ice_prof_has_mask(struct ice_hw *hw, enum ice_block blk, u8 prof, u16 *masks) +{ + u16 i; + + /* es->mask_ena[prof] will have the mask */ + for (i = 0; i < hw->blk[blk].es.fvw; i++) + if (!ice_prof_has_mask_idx(hw, blk, prof, i, masks[i])) + return false; + + return true; +} + +/** + * ice_find_prof_id_with_mask - find profile ID for a given field vector * @hw: pointer to the hardware structure * @blk: HW block * @fv: field vector to search for + * @masks: masks for FV * @prof_id: receives the profile ID */ static enum ice_status -ice_find_prof_id(struct ice_hw *hw, enum ice_block blk, - struct ice_fv_word *fv, u8 *prof_id) +ice_find_prof_id_with_mask(struct ice_hw *hw, enum ice_block blk, + struct ice_fv_word *fv, u16 *masks, u8 *prof_id) { struct ice_es *es = &hw->blk[blk].es; - u16 off; u8 i; /* For FD, we don't want to re-use a existed profile with the same @@ -2382,11 +2453,15 @@ ice_find_prof_id(struct ice_hw *hw, enum ice_block blk, return ICE_ERR_DOES_NOT_EXIST; for (i = 0; i < (u8)es->count; i++) { - off = i * es->fvw; + u16 off = i * es->fvw; if (memcmp(&es->t[off], fv, es->fvw * sizeof(*fv))) continue; + /* check if masks settings are the same for this profile */ + if (masks && !ice_prof_has_mask(hw, blk, i, masks)) + continue; + *prof_id = i; return 0; } @@ -2438,20 +2513,22 @@ static bool ice_tcam_ent_rsrc_type(enum ice_block blk, u16 *rsrc_type) * ice_alloc_tcam_ent - allocate hardware TCAM entry * @hw: pointer to the HW struct * @blk: the block to allocate the TCAM for + * @btm: true to allocate from bottom of table, false to allocate from top * @tcam_idx: pointer to variable to receive the TCAM entry * * This function allocates a new entry in a Profile ID TCAM for a specific * block. */ static enum ice_status -ice_alloc_tcam_ent(struct ice_hw *hw, enum ice_block blk, u16 *tcam_idx) +ice_alloc_tcam_ent(struct ice_hw *hw, enum ice_block blk, bool btm, + u16 *tcam_idx) { u16 res_type; if (!ice_tcam_ent_rsrc_type(blk, &res_type)) return ICE_ERR_PARAM; - return ice_alloc_hw_res(hw, res_type, 1, true, tcam_idx); + return ice_alloc_hw_res(hw, res_type, 1, btm, tcam_idx); } /** @@ -2537,6 +2614,330 @@ ice_prof_inc_ref(struct ice_hw *hw, enum ice_block blk, u8 prof_id) } /** + * ice_write_prof_mask_reg - write profile mask register + * @hw: pointer to the HW struct + * @blk: hardware block + * @mask_idx: mask index + * @idx: index of the FV which will use the mask + * @mask: the 16-bit mask + */ +static void +ice_write_prof_mask_reg(struct ice_hw *hw, enum ice_block blk, u16 mask_idx, + u16 idx, u16 mask) +{ + u32 offset; + u32 val; + + switch (blk) { + case ICE_BLK_RSS: + offset = GLQF_HMASK(mask_idx); + val = (idx << GLQF_HMASK_MSK_INDEX_S) & GLQF_HMASK_MSK_INDEX_M; + val |= (mask << GLQF_HMASK_MASK_S) & GLQF_HMASK_MASK_M; + break; + case ICE_BLK_FD: + offset = GLQF_FDMASK(mask_idx); + val = (idx << GLQF_FDMASK_MSK_INDEX_S) & GLQF_FDMASK_MSK_INDEX_M; + val |= (mask << GLQF_FDMASK_MASK_S) & GLQF_FDMASK_MASK_M; + break; + default: + ice_debug(hw, ICE_DBG_PKG, "No profile masks for block %d\n", + blk); + return; + } + + wr32(hw, offset, val); + ice_debug(hw, ICE_DBG_PKG, "write mask, blk %d (%d): %x = %x\n", + blk, idx, offset, val); +} + +/** + * ice_write_prof_mask_enable_res - write profile mask enable register + * @hw: pointer to the HW struct + * @blk: hardware block + * @prof_id: profile ID + * @enable_mask: enable mask + */ +static void +ice_write_prof_mask_enable_res(struct ice_hw *hw, enum ice_block blk, + u16 prof_id, u32 enable_mask) +{ + u32 offset; + + switch (blk) { + case ICE_BLK_RSS: + offset = GLQF_HMASK_SEL(prof_id); + break; + case ICE_BLK_FD: + offset = GLQF_FDMASK_SEL(prof_id); + break; + default: + ice_debug(hw, ICE_DBG_PKG, "No profile masks for block %d\n", + blk); + return; + } + + wr32(hw, offset, enable_mask); + ice_debug(hw, ICE_DBG_PKG, "write mask enable, blk %d (%d): %x = %x\n", + blk, prof_id, offset, enable_mask); +} + +/** + * ice_init_prof_masks - initial prof masks + * @hw: pointer to the HW struct + * @blk: hardware block + */ +static void ice_init_prof_masks(struct ice_hw *hw, enum ice_block blk) +{ + u16 per_pf; + u16 i; + + mutex_init(&hw->blk[blk].masks.lock); + + per_pf = ICE_PROF_MASK_COUNT / hw->dev_caps.num_funcs; + + hw->blk[blk].masks.count = per_pf; + hw->blk[blk].masks.first = hw->pf_id * per_pf; + + memset(hw->blk[blk].masks.masks, 0, sizeof(hw->blk[blk].masks.masks)); + + for (i = hw->blk[blk].masks.first; + i < hw->blk[blk].masks.first + hw->blk[blk].masks.count; i++) + ice_write_prof_mask_reg(hw, blk, i, 0, 0); +} + +/** + * ice_init_all_prof_masks - initialize all prof masks + * @hw: pointer to the HW struct + */ +static void ice_init_all_prof_masks(struct ice_hw *hw) +{ + ice_init_prof_masks(hw, ICE_BLK_RSS); + ice_init_prof_masks(hw, ICE_BLK_FD); +} + +/** + * ice_alloc_prof_mask - allocate profile mask + * @hw: pointer to the HW struct + * @blk: hardware block + * @idx: index of FV which will use the mask + * @mask: the 16-bit mask + * @mask_idx: variable to receive the mask index + */ +static enum ice_status +ice_alloc_prof_mask(struct ice_hw *hw, enum ice_block blk, u16 idx, u16 mask, + u16 *mask_idx) +{ + bool found_unused = false, found_copy = false; + enum ice_status status = ICE_ERR_MAX_LIMIT; + u16 unused_idx = 0, copy_idx = 0; + u16 i; + + if (blk != ICE_BLK_RSS && blk != ICE_BLK_FD) + return ICE_ERR_PARAM; + + mutex_lock(&hw->blk[blk].masks.lock); + + for (i = hw->blk[blk].masks.first; + i < hw->blk[blk].masks.first + hw->blk[blk].masks.count; i++) + if (hw->blk[blk].masks.masks[i].in_use) { + /* if mask is in use and it exactly duplicates the + * desired mask and index, then in can be reused + */ + if (hw->blk[blk].masks.masks[i].mask == mask && + hw->blk[blk].masks.masks[i].idx == idx) { + found_copy = true; + copy_idx = i; + break; + } + } else { + /* save off unused index, but keep searching in case + * there is an exact match later on + */ + if (!found_unused) { + found_unused = true; + unused_idx = i; + } + } + + if (found_copy) + i = copy_idx; + else if (found_unused) + i = unused_idx; + else + goto err_ice_alloc_prof_mask; + + /* update mask for a new entry */ + if (found_unused) { + hw->blk[blk].masks.masks[i].in_use = true; + hw->blk[blk].masks.masks[i].mask = mask; + hw->blk[blk].masks.masks[i].idx = idx; + hw->blk[blk].masks.masks[i].ref = 0; + ice_write_prof_mask_reg(hw, blk, i, idx, mask); + } + + hw->blk[blk].masks.masks[i].ref++; + *mask_idx = i; + status = 0; + +err_ice_alloc_prof_mask: + mutex_unlock(&hw->blk[blk].masks.lock); + + return status; +} + +/** + * ice_free_prof_mask - free profile mask + * @hw: pointer to the HW struct + * @blk: hardware block + * @mask_idx: index of mask + */ +static enum ice_status +ice_free_prof_mask(struct ice_hw *hw, enum ice_block blk, u16 mask_idx) +{ + if (blk != ICE_BLK_RSS && blk != ICE_BLK_FD) + return ICE_ERR_PARAM; + + if (!(mask_idx >= hw->blk[blk].masks.first && + mask_idx < hw->blk[blk].masks.first + hw->blk[blk].masks.count)) + return ICE_ERR_DOES_NOT_EXIST; + + mutex_lock(&hw->blk[blk].masks.lock); + + if (!hw->blk[blk].masks.masks[mask_idx].in_use) + goto exit_ice_free_prof_mask; + + if (hw->blk[blk].masks.masks[mask_idx].ref > 1) { + hw->blk[blk].masks.masks[mask_idx].ref--; + goto exit_ice_free_prof_mask; + } + + /* remove mask */ + hw->blk[blk].masks.masks[mask_idx].in_use = false; + hw->blk[blk].masks.masks[mask_idx].mask = 0; + hw->blk[blk].masks.masks[mask_idx].idx = 0; + + /* update mask as unused entry */ + ice_debug(hw, ICE_DBG_PKG, "Free mask, blk %d, mask %d\n", blk, + mask_idx); + ice_write_prof_mask_reg(hw, blk, mask_idx, 0, 0); + +exit_ice_free_prof_mask: + mutex_unlock(&hw->blk[blk].masks.lock); + + return 0; +} + +/** + * ice_free_prof_masks - free all profile masks for a profile + * @hw: pointer to the HW struct + * @blk: hardware block + * @prof_id: profile ID + */ +static enum ice_status +ice_free_prof_masks(struct ice_hw *hw, enum ice_block blk, u16 prof_id) +{ + u32 mask_bm; + u16 i; + + if (blk != ICE_BLK_RSS && blk != ICE_BLK_FD) + return ICE_ERR_PARAM; + + mask_bm = hw->blk[blk].es.mask_ena[prof_id]; + for (i = 0; i < BITS_PER_BYTE * sizeof(mask_bm); i++) + if (mask_bm & BIT(i)) + ice_free_prof_mask(hw, blk, i); + + return 0; +} + +/** + * ice_shutdown_prof_masks - releases lock for masking + * @hw: pointer to the HW struct + * @blk: hardware block + * + * This should be called before unloading the driver + */ +static void ice_shutdown_prof_masks(struct ice_hw *hw, enum ice_block blk) +{ + u16 i; + + mutex_lock(&hw->blk[blk].masks.lock); + + for (i = hw->blk[blk].masks.first; + i < hw->blk[blk].masks.first + hw->blk[blk].masks.count; i++) { + ice_write_prof_mask_reg(hw, blk, i, 0, 0); + + hw->blk[blk].masks.masks[i].in_use = false; + hw->blk[blk].masks.masks[i].idx = 0; + hw->blk[blk].masks.masks[i].mask = 0; + } + + mutex_unlock(&hw->blk[blk].masks.lock); + mutex_destroy(&hw->blk[blk].masks.lock); +} + +/** + * ice_shutdown_all_prof_masks - releases all locks for masking + * @hw: pointer to the HW struct + * + * This should be called before unloading the driver + */ +static void ice_shutdown_all_prof_masks(struct ice_hw *hw) +{ + ice_shutdown_prof_masks(hw, ICE_BLK_RSS); + ice_shutdown_prof_masks(hw, ICE_BLK_FD); +} + +/** + * ice_update_prof_masking - set registers according to masking + * @hw: pointer to the HW struct + * @blk: hardware block + * @prof_id: profile ID + * @masks: masks + */ +static enum ice_status +ice_update_prof_masking(struct ice_hw *hw, enum ice_block blk, u16 prof_id, + u16 *masks) +{ + bool err = false; + u32 ena_mask = 0; + u16 idx; + u16 i; + + /* Only support FD and RSS masking, otherwise nothing to be done */ + if (blk != ICE_BLK_RSS && blk != ICE_BLK_FD) + return 0; + + for (i = 0; i < hw->blk[blk].es.fvw; i++) + if (masks[i] && masks[i] != 0xFFFF) { + if (!ice_alloc_prof_mask(hw, blk, i, masks[i], &idx)) { + ena_mask |= BIT(idx); + } else { + /* not enough bitmaps */ + err = true; + break; + } + } + + if (err) { + /* free any bitmaps we have allocated */ + for (i = 0; i < BITS_PER_BYTE * sizeof(ena_mask); i++) + if (ena_mask & BIT(i)) + ice_free_prof_mask(hw, blk, i); + + return ICE_ERR_OUT_OF_RANGE; + } + + /* enable the masks for this profile */ + ice_write_prof_mask_enable_res(hw, blk, prof_id, ena_mask); + + /* store enabled masks with profile so that they can be freed later */ + hw->blk[blk].es.mask_ena[prof_id] = ena_mask; + + return 0; +} + +/** * ice_write_es - write an extraction sequence to hardware * @hw: pointer to the HW struct * @blk: the block in which to write the extraction sequence @@ -2575,6 +2976,7 @@ ice_prof_dec_ref(struct ice_hw *hw, enum ice_block blk, u8 prof_id) if (hw->blk[blk].es.ref_count[prof_id] > 0) { if (!--hw->blk[blk].es.ref_count[prof_id]) { ice_write_es(hw, blk, prof_id, NULL); + ice_free_prof_masks(hw, blk, prof_id); return ice_free_prof_id(hw, blk, prof_id); } } @@ -2937,6 +3339,7 @@ void ice_free_hw_tbls(struct ice_hw *hw) devm_kfree(ice_hw_to_dev(hw), hw->blk[i].es.t); devm_kfree(ice_hw_to_dev(hw), hw->blk[i].es.ref_count); devm_kfree(ice_hw_to_dev(hw), hw->blk[i].es.written); + devm_kfree(ice_hw_to_dev(hw), hw->blk[i].es.mask_ena); } list_for_each_entry_safe(r, rt, &hw->rss_list_head, l_entry) { @@ -2944,6 +3347,7 @@ void ice_free_hw_tbls(struct ice_hw *hw) devm_kfree(ice_hw_to_dev(hw), r); } mutex_destroy(&hw->rss_locks); + ice_shutdown_all_prof_masks(hw); memset(hw->blk, 0, sizeof(hw->blk)); } @@ -2997,6 +3401,7 @@ void ice_clear_hw_tbls(struct ice_hw *hw) memset(es->t, 0, es->count * sizeof(*es->t) * es->fvw); memset(es->ref_count, 0, es->count * sizeof(*es->ref_count)); memset(es->written, 0, es->count * sizeof(*es->written)); + memset(es->mask_ena, 0, es->count * sizeof(*es->mask_ena)); } } @@ -3010,6 +3415,7 @@ enum ice_status ice_init_hw_tbls(struct ice_hw *hw) mutex_init(&hw->rss_locks); INIT_LIST_HEAD(&hw->rss_list_head); + ice_init_all_prof_masks(hw); for (i = 0; i < ICE_BLK_COUNT; i++) { struct ice_prof_redir *prof_redir = &hw->blk[i].prof_redir; struct ice_prof_tcam *prof = &hw->blk[i].prof; @@ -3112,6 +3518,11 @@ enum ice_status ice_init_hw_tbls(struct ice_hw *hw) sizeof(*es->written), GFP_KERNEL); if (!es->written) goto err; + + es->mask_ena = devm_kcalloc(ice_hw_to_dev(hw), es->count, + sizeof(*es->mask_ena), GFP_KERNEL); + if (!es->mask_ena) + goto err; } return 0; @@ -3711,22 +4122,79 @@ ice_update_fd_swap(struct ice_hw *hw, u16 prof_id, struct ice_fv_word *es) return 0; } +/* The entries here needs to match the order of enum ice_ptype_attrib */ +static const struct ice_ptype_attrib_info ice_ptype_attributes[] = { + { ICE_GTP_PDU_EH, ICE_GTP_PDU_FLAG_MASK }, + { ICE_GTP_SESSION, ICE_GTP_FLAGS_MASK }, + { ICE_GTP_DOWNLINK, ICE_GTP_FLAGS_MASK }, + { ICE_GTP_UPLINK, ICE_GTP_FLAGS_MASK }, +}; + +/** + * ice_get_ptype_attrib_info - get PTYPE attribute information + * @type: attribute type + * @info: pointer to variable to the attribute information + */ +static void +ice_get_ptype_attrib_info(enum ice_ptype_attrib_type type, + struct ice_ptype_attrib_info *info) +{ + *info = ice_ptype_attributes[type]; +} + +/** + * ice_add_prof_attrib - add any PTG with attributes to profile + * @prof: pointer to the profile to which PTG entries will be added + * @ptg: PTG to be added + * @ptype: PTYPE that needs to be looked up + * @attr: array of attributes that will be considered + * @attr_cnt: number of elements in the attribute array + */ +static enum ice_status +ice_add_prof_attrib(struct ice_prof_map *prof, u8 ptg, u16 ptype, + const struct ice_ptype_attributes *attr, u16 attr_cnt) +{ + bool found = false; + u16 i; + + for (i = 0; i < attr_cnt; i++) + if (attr[i].ptype == ptype) { + found = true; + + prof->ptg[prof->ptg_cnt] = ptg; + ice_get_ptype_attrib_info(attr[i].attrib, + &prof->attr[prof->ptg_cnt]); + + if (++prof->ptg_cnt >= ICE_MAX_PTG_PER_PROFILE) + return ICE_ERR_MAX_LIMIT; + } + + if (!found) + return ICE_ERR_DOES_NOT_EXIST; + + return 0; +} + /** * ice_add_prof - add profile * @hw: pointer to the HW struct * @blk: hardware block * @id: profile tracking ID * @ptypes: array of bitmaps indicating ptypes (ICE_FLOW_PTYPE_MAX bits) + * @attr: array of attributes + * @attr_cnt: number of elements in attr array * @es: extraction sequence (length of array is determined by the block) + * @masks: mask for extraction sequence * - * This function registers a profile, which matches a set of PTGs with a + * This function registers a profile, which matches a set of PTYPES with a * particular extraction sequence. While the hardware profile is allocated * it will not be written until the first call to ice_add_flow that specifies * the ID value used here. */ enum ice_status ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], - struct ice_fv_word *es) + const struct ice_ptype_attributes *attr, u16 attr_cnt, + struct ice_fv_word *es, u16 *masks) { u32 bytes = DIV_ROUND_UP(ICE_FLOW_PTYPE_MAX, BITS_PER_BYTE); DECLARE_BITMAP(ptgs_used, ICE_XLT1_CNT); @@ -3740,7 +4208,7 @@ ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], mutex_lock(&hw->blk[blk].es.prof_map_lock); /* search for existing profile */ - status = ice_find_prof_id(hw, blk, es, &prof_id); + status = ice_find_prof_id_with_mask(hw, blk, es, masks, &prof_id); if (status) { /* allocate profile ID */ status = ice_alloc_prof_id(hw, blk, &prof_id); @@ -3758,6 +4226,9 @@ ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], if (status) goto err_ice_add_prof; } + status = ice_update_prof_masking(hw, blk, prof_id, masks); + if (status) + goto err_ice_add_prof; /* and write new es */ ice_write_es(hw, blk, prof_id, es); @@ -3792,7 +4263,6 @@ ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], BITS_PER_BYTE) { u16 ptype; u8 ptg; - u8 m; ptype = byte * BITS_PER_BYTE + bit; @@ -3807,15 +4277,25 @@ ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], continue; set_bit(ptg, ptgs_used); - prof->ptg[prof->ptg_cnt] = ptg; - - if (++prof->ptg_cnt >= ICE_MAX_PTG_PER_PROFILE) + /* Check to see there are any attributes for + * this PTYPE, and add them if found. + */ + status = ice_add_prof_attrib(prof, ptg, ptype, + attr, attr_cnt); + if (status == ICE_ERR_MAX_LIMIT) break; + if (status) { + /* This is simple a PTYPE/PTG with no + * attribute + */ + prof->ptg[prof->ptg_cnt] = ptg; + prof->attr[prof->ptg_cnt].flags = 0; + prof->attr[prof->ptg_cnt].mask = 0; - /* nothing left in byte, then exit */ - m = ~(u8)((1 << (bit + 1)) - 1); - if (!(ptypes[byte] & m)) - break; + if (++prof->ptg_cnt >= + ICE_MAX_PTG_PER_PROFILE) + break; + } } bytes--; @@ -4326,7 +4806,12 @@ ice_prof_tcam_ena_dis(struct ice_hw *hw, enum ice_block blk, bool enable, } /* for re-enabling, reallocate a TCAM */ - status = ice_alloc_tcam_ent(hw, blk, &tcam->tcam_idx); + /* for entries with empty attribute masks, allocate entry from + * the bottom of the TCAM table; otherwise, allocate from the + * top of the table in order to give it higher priority + */ + status = ice_alloc_tcam_ent(hw, blk, tcam->attr.mask == 0, + &tcam->tcam_idx); if (status) return status; @@ -4336,8 +4821,8 @@ ice_prof_tcam_ena_dis(struct ice_hw *hw, enum ice_block blk, bool enable, return ICE_ERR_NO_MEMORY; status = ice_tcam_write_entry(hw, blk, tcam->tcam_idx, tcam->prof_id, - tcam->ptg, vsig, 0, 0, vl_msk, dc_msk, - nm_msk); + tcam->ptg, vsig, 0, tcam->attr.flags, + vl_msk, dc_msk, nm_msk); if (status) goto err_ice_prof_tcam_ena_dis; @@ -4485,7 +4970,12 @@ ice_add_prof_id_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, u64 hdl, } /* allocate the TCAM entry index */ - status = ice_alloc_tcam_ent(hw, blk, &tcam_idx); + /* for entries with empty attribute masks, allocate entry from + * the bottom of the TCAM table; otherwise, allocate from the + * top of the table in order to give it higher priority + */ + status = ice_alloc_tcam_ent(hw, blk, map->attr[i].mask == 0, + &tcam_idx); if (status) { devm_kfree(ice_hw_to_dev(hw), p); goto err_ice_add_prof_id_vsig; @@ -4494,6 +4984,7 @@ ice_add_prof_id_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, u64 hdl, t->tcam[i].ptg = map->ptg[i]; t->tcam[i].prof_id = map->prof_id; t->tcam[i].tcam_idx = tcam_idx; + t->tcam[i].attr = map->attr[i]; t->tcam[i].in_use = true; p->type = ICE_TCAM_ADD; diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h index 20deddb807c5..8a58e79729b9 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h @@ -27,7 +27,8 @@ int ice_udp_tunnel_unset_port(struct net_device *netdev, unsigned int table, enum ice_status ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], - struct ice_fv_word *es); + const struct ice_ptype_attributes *attr, u16 attr_cnt, + struct ice_fv_word *es, u16 *masks); enum ice_status ice_add_prof_id_flow(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl); enum ice_status diff --git a/drivers/net/ethernet/intel/ice/ice_flex_type.h b/drivers/net/ethernet/intel/ice/ice_flex_type.h index 24063c1351b2..7d8b517a63c9 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_type.h +++ b/drivers/net/ethernet/intel/ice/ice_flex_type.h @@ -109,6 +109,7 @@ struct ice_buf_hdr { (ent_sz)) /* ice package section IDs */ +#define ICE_SID_METADATA 1 #define ICE_SID_XLT0_SW 10 #define ICE_SID_XLT_KEY_BUILDER_SW 11 #define ICE_SID_XLT1_SW 12 @@ -117,6 +118,14 @@ struct ice_buf_hdr { #define ICE_SID_PROFID_REDIR_SW 15 #define ICE_SID_FLD_VEC_SW 16 #define ICE_SID_CDID_KEY_BUILDER_SW 17 + +struct ice_meta_sect { + struct ice_pkg_ver ver; +#define ICE_META_SECT_NAME_SIZE 28 + char name[ICE_META_SECT_NAME_SIZE]; + __le32 track_id; +}; + #define ICE_SID_CDID_REDIR_SW 18 #define ICE_SID_XLT0_ACL 20 @@ -190,6 +199,64 @@ enum ice_sect { ICE_SECT_COUNT }; +#define ICE_MAC_IPV4_GTPU_IPV4_FRAG 331 +#define ICE_MAC_IPV4_GTPU_IPV4_PAY 332 +#define ICE_MAC_IPV4_GTPU_IPV4_UDP_PAY 333 +#define ICE_MAC_IPV4_GTPU_IPV4_TCP 334 +#define ICE_MAC_IPV4_GTPU_IPV4_ICMP 335 +#define ICE_MAC_IPV6_GTPU_IPV4_FRAG 336 +#define ICE_MAC_IPV6_GTPU_IPV4_PAY 337 +#define ICE_MAC_IPV6_GTPU_IPV4_UDP_PAY 338 +#define ICE_MAC_IPV6_GTPU_IPV4_TCP 339 +#define ICE_MAC_IPV6_GTPU_IPV4_ICMP 340 +#define ICE_MAC_IPV4_GTPU_IPV6_FRAG 341 +#define ICE_MAC_IPV4_GTPU_IPV6_PAY 342 +#define ICE_MAC_IPV4_GTPU_IPV6_UDP_PAY 343 +#define ICE_MAC_IPV4_GTPU_IPV6_TCP 344 +#define ICE_MAC_IPV4_GTPU_IPV6_ICMPV6 345 +#define ICE_MAC_IPV6_GTPU_IPV6_FRAG 346 +#define ICE_MAC_IPV6_GTPU_IPV6_PAY 347 +#define ICE_MAC_IPV6_GTPU_IPV6_UDP_PAY 348 +#define ICE_MAC_IPV6_GTPU_IPV6_TCP 349 +#define ICE_MAC_IPV6_GTPU_IPV6_ICMPV6 350 + +/* Attributes that can modify PTYPE definitions. + * + * These values will represent special attributes for PTYPEs, which will + * resolve into metadata packet flags definitions that can be used in the TCAM + * for identifying a PTYPE with specific characteristics. + */ +enum ice_ptype_attrib_type { + /* GTP PTYPEs */ + ICE_PTYPE_ATTR_GTP_PDU_EH, + ICE_PTYPE_ATTR_GTP_SESSION, + ICE_PTYPE_ATTR_GTP_DOWNLINK, + ICE_PTYPE_ATTR_GTP_UPLINK, +}; + +struct ice_ptype_attrib_info { + u16 flags; + u16 mask; +}; + +/* TCAM flag definitions */ +#define ICE_GTP_PDU BIT(14) +#define ICE_GTP_PDU_LINK BIT(13) + +/* GTP attributes */ +#define ICE_GTP_PDU_FLAG_MASK (ICE_GTP_PDU) +#define ICE_GTP_PDU_EH ICE_GTP_PDU + +#define ICE_GTP_FLAGS_MASK (ICE_GTP_PDU | ICE_GTP_PDU_LINK) +#define ICE_GTP_SESSION 0 +#define ICE_GTP_DOWNLINK ICE_GTP_PDU +#define ICE_GTP_UPLINK (ICE_GTP_PDU | ICE_GTP_PDU_LINK) + +struct ice_ptype_attributes { + u16 ptype; + enum ice_ptype_attrib_type attrib; +}; + /* package labels */ struct ice_label { __le16 value; @@ -335,6 +402,7 @@ struct ice_es { u16 count; u16 fvw; u16 *ref_count; + u32 *mask_ena; struct list_head prof_map; struct ice_fv_word *t; struct mutex prof_map_lock; /* protect access to profiles list */ @@ -372,12 +440,14 @@ struct ice_prof_map { u8 prof_id; u8 ptg_cnt; u8 ptg[ICE_MAX_PTG_PER_PROFILE]; + struct ice_ptype_attrib_info attr[ICE_MAX_PTG_PER_PROFILE]; }; #define ICE_INVALID_TCAM 0xFFFF struct ice_tcam_inf { u16 tcam_idx; + struct ice_ptype_attrib_info attr; u8 ptg; u8 prof_id; u8 in_use; @@ -427,8 +497,8 @@ struct ice_xlt1 { #define ICE_PF_NUM_S 13 #define ICE_PF_NUM_M (0x07 << ICE_PF_NUM_S) #define ICE_VSIG_VALUE(vsig, pf_id) \ - (u16)((((u16)(vsig)) & ICE_VSIG_IDX_M) | \ - (((u16)(pf_id) << ICE_PF_NUM_S) & ICE_PF_NUM_M)) + ((u16)((((u16)(vsig)) & ICE_VSIG_IDX_M) | \ + (((u16)(pf_id) << ICE_PF_NUM_S) & ICE_PF_NUM_M))) #define ICE_DEFAULT_VSIG 0 /* XLT2 Table */ @@ -478,6 +548,21 @@ struct ice_prof_redir { u16 count; }; +struct ice_mask { + u16 mask; /* 16-bit mask */ + u16 idx; /* index */ + u16 ref; /* reference count */ + u8 in_use; /* non-zero if used */ +}; + +struct ice_masks { + struct mutex lock; /* lock to protect this structure */ + u16 first; /* first mask owned by the PF */ + u16 count; /* number of masks owned by the PF */ +#define ICE_PROF_MASK_COUNT 32 + struct ice_mask masks[ICE_PROF_MASK_COUNT]; +}; + /* Tables per block */ struct ice_blk_info { struct ice_xlt1 xlt1; @@ -485,6 +570,7 @@ struct ice_blk_info { struct ice_prof_tcam prof; struct ice_prof_redir prof_redir; struct ice_es es; + struct ice_masks masks; u8 overwrite; /* set to true to allow overwrite of table entries */ u8 is_list_init; }; @@ -513,6 +599,7 @@ struct ice_chs_chg { u16 vsig; u16 orig_vsig; u16 tcam_idx; + struct ice_ptype_attrib_info attr; }; #define ICE_FLOW_PTYPE_MAX ICE_XLT1_CNT diff --git a/drivers/net/ethernet/intel/ice/ice_flow.c b/drivers/net/ethernet/intel/ice/ice_flow.c index 89a0cef20506..f160672448a0 100644 --- a/drivers/net/ethernet/intel/ice/ice_flow.c +++ b/drivers/net/ethernet/intel/ice/ice_flow.c @@ -9,18 +9,50 @@ struct ice_flow_field_info { enum ice_flow_seg_hdr hdr; s16 off; /* Offset from start of a protocol header, in bits */ u16 size; /* Size of fields in bits */ + u16 mask; /* 16-bit mask for field */ }; #define ICE_FLOW_FLD_INFO(_hdr, _offset_bytes, _size_bytes) { \ .hdr = _hdr, \ .off = (_offset_bytes) * BITS_PER_BYTE, \ .size = (_size_bytes) * BITS_PER_BYTE, \ + .mask = 0, \ +} + +#define ICE_FLOW_FLD_INFO_MSK(_hdr, _offset_bytes, _size_bytes, _mask) { \ + .hdr = _hdr, \ + .off = (_offset_bytes) * BITS_PER_BYTE, \ + .size = (_size_bytes) * BITS_PER_BYTE, \ + .mask = _mask, \ } /* Table containing properties of supported protocol header fields */ static const struct ice_flow_field_info ice_flds_info[ICE_FLOW_FIELD_IDX_MAX] = { + /* Ether */ + /* ICE_FLOW_FIELD_IDX_ETH_DA */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_ETH, 0, ETH_ALEN), + /* ICE_FLOW_FIELD_IDX_ETH_SA */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_ETH, ETH_ALEN, ETH_ALEN), + /* ICE_FLOW_FIELD_IDX_S_VLAN */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_VLAN, 12, sizeof(__be16)), + /* ICE_FLOW_FIELD_IDX_C_VLAN */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_VLAN, 14, sizeof(__be16)), + /* ICE_FLOW_FIELD_IDX_ETH_TYPE */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_ETH, 0, sizeof(__be16)), /* IPv4 / IPv6 */ + /* ICE_FLOW_FIELD_IDX_IPV4_DSCP */ + ICE_FLOW_FLD_INFO_MSK(ICE_FLOW_SEG_HDR_IPV4, 0, 1, 0x00fc), + /* ICE_FLOW_FIELD_IDX_IPV6_DSCP */ + ICE_FLOW_FLD_INFO_MSK(ICE_FLOW_SEG_HDR_IPV6, 0, 1, 0x0ff0), + /* ICE_FLOW_FIELD_IDX_IPV4_TTL */ + ICE_FLOW_FLD_INFO_MSK(ICE_FLOW_SEG_HDR_NONE, 8, 1, 0xff00), + /* ICE_FLOW_FIELD_IDX_IPV4_PROT */ + ICE_FLOW_FLD_INFO_MSK(ICE_FLOW_SEG_HDR_NONE, 8, 1, 0x00ff), + /* ICE_FLOW_FIELD_IDX_IPV6_TTL */ + ICE_FLOW_FLD_INFO_MSK(ICE_FLOW_SEG_HDR_NONE, 6, 1, 0x00ff), + /* ICE_FLOW_FIELD_IDX_IPV6_PROT */ + ICE_FLOW_FLD_INFO_MSK(ICE_FLOW_SEG_HDR_NONE, 6, 1, 0xff00), /* ICE_FLOW_FIELD_IDX_IPV4_SA */ ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV4, 12, sizeof(struct in_addr)), /* ICE_FLOW_FIELD_IDX_IPV4_DA */ @@ -42,22 +74,112 @@ struct ice_flow_field_info ice_flds_info[ICE_FLOW_FIELD_IDX_MAX] = { ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_SCTP, 0, sizeof(__be16)), /* ICE_FLOW_FIELD_IDX_SCTP_DST_PORT */ ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_SCTP, 2, sizeof(__be16)), + /* ICE_FLOW_FIELD_IDX_TCP_FLAGS */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_TCP, 13, 1), + /* ARP */ + /* ICE_FLOW_FIELD_IDX_ARP_SIP */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_ARP, 14, sizeof(struct in_addr)), + /* ICE_FLOW_FIELD_IDX_ARP_DIP */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_ARP, 24, sizeof(struct in_addr)), + /* ICE_FLOW_FIELD_IDX_ARP_SHA */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_ARP, 8, ETH_ALEN), + /* ICE_FLOW_FIELD_IDX_ARP_DHA */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_ARP, 18, ETH_ALEN), + /* ICE_FLOW_FIELD_IDX_ARP_OP */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_ARP, 6, sizeof(__be16)), + /* ICMP */ + /* ICE_FLOW_FIELD_IDX_ICMP_TYPE */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_ICMP, 0, 1), + /* ICE_FLOW_FIELD_IDX_ICMP_CODE */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_ICMP, 1, 1), /* GRE */ /* ICE_FLOW_FIELD_IDX_GRE_KEYID */ ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_GRE, 12, sizeof_field(struct gre_full_hdr, key)), + /* GTP */ + /* ICE_FLOW_FIELD_IDX_GTPC_TEID */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_GTPC_TEID, 12, sizeof(__be32)), + /* ICE_FLOW_FIELD_IDX_GTPU_IP_TEID */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_GTPU_IP, 12, sizeof(__be32)), + /* ICE_FLOW_FIELD_IDX_GTPU_EH_TEID */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_GTPU_EH, 12, sizeof(__be32)), + /* ICE_FLOW_FIELD_IDX_GTPU_EH_QFI */ + ICE_FLOW_FLD_INFO_MSK(ICE_FLOW_SEG_HDR_GTPU_EH, 22, sizeof(__be16), + 0x3f00), + /* ICE_FLOW_FIELD_IDX_GTPU_UP_TEID */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_GTPU_UP, 12, sizeof(__be32)), + /* ICE_FLOW_FIELD_IDX_GTPU_DWN_TEID */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_GTPU_DWN, 12, sizeof(__be32)), + /* PPPoE */ + /* ICE_FLOW_FIELD_IDX_PPPOE_SESS_ID */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_PPPOE, 2, sizeof(__be16)), + /* PFCP */ + /* ICE_FLOW_FIELD_IDX_PFCP_SEID */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_PFCP_SESSION, 12, sizeof(__be64)), + /* L2TPv3 */ + /* ICE_FLOW_FIELD_IDX_L2TPV3_SESS_ID */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_L2TPV3, 0, sizeof(__be32)), + /* ESP */ + /* ICE_FLOW_FIELD_IDX_ESP_SPI */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_ESP, 0, sizeof(__be32)), + /* AH */ + /* ICE_FLOW_FIELD_IDX_AH_SPI */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_AH, 4, sizeof(__be32)), + /* NAT_T_ESP */ + /* ICE_FLOW_FIELD_IDX_NAT_T_ESP_SPI */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_NAT_T_ESP, 8, sizeof(__be32)), }; /* Bitmaps indicating relevant packet types for a particular protocol header * - * Packet types for packets with an Outer/First/Single IPv4 header + * Packet types for packets with an Outer/First/Single MAC header + */ +static const u32 ice_ptypes_mac_ofos[] = { + 0xFDC00846, 0xBFBF7F7E, 0xF70001DF, 0xFEFDFDFB, + 0x0000077E, 0x00000000, 0x00000000, 0x00000000, + 0x00400000, 0x03FFF000, 0x7FFFFFE0, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, +}; + +/* Packet types for packets with an Innermost/Last MAC VLAN header */ +static const u32 ice_ptypes_macvlan_il[] = { + 0x00000000, 0xBC000000, 0x000001DF, 0xF0000000, + 0x0000077E, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, +}; + +/* Packet types for packets with an Outer/First/Single IPv4 header, does NOT + * include IPv4 other PTYPEs */ static const u32 ice_ptypes_ipv4_ofos[] = { 0x1DC00000, 0x04000800, 0x00000000, 0x00000000, + 0x00000000, 0x00000155, 0x00000000, 0x00000000, + 0x00000000, 0x000FC000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, +}; + +/* Packet types for packets with an Outer/First/Single IPv4 header, includes + * IPv4 other PTYPEs + */ +static const u32 ice_ptypes_ipv4_ofos_all[] = { + 0x1DC00000, 0x04000800, 0x00000000, 0x00000000, + 0x00000000, 0x00000155, 0x00000000, 0x00000000, + 0x00000000, 0x000FC000, 0x83E0F800, 0x00000101, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, @@ -67,7 +189,7 @@ static const u32 ice_ptypes_ipv4_ofos[] = { static const u32 ice_ptypes_ipv4_il[] = { 0xE0000000, 0xB807700E, 0x80000003, 0xE01DC03B, 0x0000000E, 0x00000000, 0x00000000, 0x00000000, - 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x001FF800, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, @@ -75,11 +197,27 @@ static const u32 ice_ptypes_ipv4_il[] = { 0x00000000, 0x00000000, 0x00000000, 0x00000000, }; -/* Packet types for packets with an Outer/First/Single IPv6 header */ +/* Packet types for packets with an Outer/First/Single IPv6 header, does NOT + * include IPv6 other PTYPEs + */ static const u32 ice_ptypes_ipv6_ofos[] = { 0x00000000, 0x00000000, 0x77000000, 0x10002000, + 0x00000000, 0x000002AA, 0x00000000, 0x00000000, + 0x00000000, 0x03F00000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, +}; + +/* Packet types for packets with an Outer/First/Single IPv6 header, includes + * IPv6 other PTYPEs + */ +static const u32 ice_ptypes_ipv6_ofos_all[] = { + 0x00000000, 0x00000000, 0x77000000, 0x10002000, + 0x00000000, 0x000002AA, 0x00000000, 0x00000000, + 0x00080F00, 0x03F00000, 0x7C1F0000, 0x00000206, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, @@ -91,7 +229,7 @@ static const u32 ice_ptypes_ipv6_ofos[] = { static const u32 ice_ptypes_ipv6_il[] = { 0x00000000, 0x03B80770, 0x000001DC, 0x0EE00000, 0x00000770, 0x00000000, 0x00000000, 0x00000000, - 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x7FE00000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, @@ -100,7 +238,7 @@ static const u32 ice_ptypes_ipv6_il[] = { }; /* Packet types for packets with an Outer/First/Single IPv4 header - no L4 */ -static const u32 ice_ipv4_ofos_no_l4[] = { +static const u32 ice_ptypes_ipv4_ofos_no_l4[] = { 0x10C00000, 0x04000800, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, @@ -111,8 +249,20 @@ static const u32 ice_ipv4_ofos_no_l4[] = { 0x00000000, 0x00000000, 0x00000000, 0x00000000, }; +/* Packet types for packets with an Outermost/First ARP header */ +static const u32 ice_ptypes_arp_of[] = { + 0x00000800, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, +}; + /* Packet types for packets with an Innermost/Last IPv4 header - no L4 */ -static const u32 ice_ipv4_il_no_l4[] = { +static const u32 ice_ptypes_ipv4_il_no_l4[] = { 0x60000000, 0x18043008, 0x80000002, 0x6010c021, 0x00000008, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, @@ -124,7 +274,7 @@ static const u32 ice_ipv4_il_no_l4[] = { }; /* Packet types for packets with an Outer/First/Single IPv6 header - no L4 */ -static const u32 ice_ipv6_ofos_no_l4[] = { +static const u32 ice_ptypes_ipv6_ofos_no_l4[] = { 0x00000000, 0x00000000, 0x43000000, 0x10002000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, @@ -136,7 +286,7 @@ static const u32 ice_ipv6_ofos_no_l4[] = { }; /* Packet types for packets with an Innermost/Last IPv6 header - no L4 */ -static const u32 ice_ipv6_il_no_l4[] = { +static const u32 ice_ptypes_ipv6_il_no_l4[] = { 0x00000000, 0x02180430, 0x0000010c, 0x086010c0, 0x00000430, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, @@ -153,7 +303,7 @@ static const u32 ice_ipv6_il_no_l4[] = { static const u32 ice_ptypes_udp_il[] = { 0x81000000, 0x20204040, 0x04000010, 0x80810102, 0x00000040, 0x00000000, 0x00000000, 0x00000000, - 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00410000, 0x90842000, 0x00000007, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, @@ -165,7 +315,7 @@ static const u32 ice_ptypes_udp_il[] = { static const u32 ice_ptypes_tcp_il[] = { 0x04000000, 0x80810102, 0x10000040, 0x02040408, 0x00000102, 0x00000000, 0x00000000, 0x00000000, - 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00820000, 0x21084000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, @@ -177,6 +327,18 @@ static const u32 ice_ptypes_tcp_il[] = { static const u32 ice_ptypes_sctp_il[] = { 0x08000000, 0x01020204, 0x20000081, 0x04080810, 0x00000204, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x01040000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, +}; + +/* Packet types for packets with an Outermost/First ICMP header */ +static const u32 ice_ptypes_icmp_of[] = { + 0x10000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, @@ -185,6 +347,18 @@ static const u32 ice_ptypes_sctp_il[] = { 0x00000000, 0x00000000, 0x00000000, 0x00000000, }; +/* Packet types for packets with an Innermost/Last ICMP header */ +static const u32 ice_ptypes_icmp_il[] = { + 0x00000000, 0x02040408, 0x40000102, 0x08101020, + 0x00000408, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x42108000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, +}; + /* Packet types for packets with an Outermost/First GRE header */ static const u32 ice_ptypes_gre_of[] = { 0x00000000, 0xBFBF7800, 0x000001DF, 0xFEFDE000, @@ -197,6 +371,218 @@ static const u32 ice_ptypes_gre_of[] = { 0x00000000, 0x00000000, 0x00000000, 0x00000000, }; +/* Packet types for packets with an Innermost/Last MAC header */ +static const u32 ice_ptypes_mac_il[] = { + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, +}; + +/* Packet types for GTPC */ +static const u32 ice_ptypes_gtpc[] = { + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000180, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, +}; + +/* Packet types for GTPC with TEID */ +static const u32 ice_ptypes_gtpc_tid[] = { + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000060, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, +}; + +/* Packet types for GTPU */ +static const struct ice_ptype_attributes ice_attr_gtpu_eh[] = { + { ICE_MAC_IPV4_GTPU_IPV4_FRAG, ICE_PTYPE_ATTR_GTP_PDU_EH }, + { ICE_MAC_IPV4_GTPU_IPV4_PAY, ICE_PTYPE_ATTR_GTP_PDU_EH }, + { ICE_MAC_IPV4_GTPU_IPV4_UDP_PAY, ICE_PTYPE_ATTR_GTP_PDU_EH }, + { ICE_MAC_IPV4_GTPU_IPV4_TCP, ICE_PTYPE_ATTR_GTP_PDU_EH }, + { ICE_MAC_IPV4_GTPU_IPV4_ICMP, ICE_PTYPE_ATTR_GTP_PDU_EH }, + { ICE_MAC_IPV6_GTPU_IPV4_FRAG, ICE_PTYPE_ATTR_GTP_PDU_EH }, + { ICE_MAC_IPV6_GTPU_IPV4_PAY, ICE_PTYPE_ATTR_GTP_PDU_EH }, + { ICE_MAC_IPV6_GTPU_IPV4_UDP_PAY, ICE_PTYPE_ATTR_GTP_PDU_EH }, + { ICE_MAC_IPV6_GTPU_IPV4_TCP, ICE_PTYPE_ATTR_GTP_PDU_EH }, + { ICE_MAC_IPV6_GTPU_IPV4_ICMP, ICE_PTYPE_ATTR_GTP_PDU_EH }, + { ICE_MAC_IPV4_GTPU_IPV6_FRAG, ICE_PTYPE_ATTR_GTP_PDU_EH }, + { ICE_MAC_IPV4_GTPU_IPV6_PAY, ICE_PTYPE_ATTR_GTP_PDU_EH }, + { ICE_MAC_IPV4_GTPU_IPV6_UDP_PAY, ICE_PTYPE_ATTR_GTP_PDU_EH }, + { ICE_MAC_IPV4_GTPU_IPV6_TCP, ICE_PTYPE_ATTR_GTP_PDU_EH }, + { ICE_MAC_IPV4_GTPU_IPV6_ICMPV6, ICE_PTYPE_ATTR_GTP_PDU_EH }, + { ICE_MAC_IPV6_GTPU_IPV6_FRAG, ICE_PTYPE_ATTR_GTP_PDU_EH }, + { ICE_MAC_IPV6_GTPU_IPV6_PAY, ICE_PTYPE_ATTR_GTP_PDU_EH }, + { ICE_MAC_IPV6_GTPU_IPV6_UDP_PAY, ICE_PTYPE_ATTR_GTP_PDU_EH }, + { ICE_MAC_IPV6_GTPU_IPV6_TCP, ICE_PTYPE_ATTR_GTP_PDU_EH }, + { ICE_MAC_IPV6_GTPU_IPV6_ICMPV6, ICE_PTYPE_ATTR_GTP_PDU_EH }, +}; + +static const struct ice_ptype_attributes ice_attr_gtpu_down[] = { + { ICE_MAC_IPV4_GTPU_IPV4_FRAG, ICE_PTYPE_ATTR_GTP_DOWNLINK }, + { ICE_MAC_IPV4_GTPU_IPV4_PAY, ICE_PTYPE_ATTR_GTP_DOWNLINK }, + { ICE_MAC_IPV4_GTPU_IPV4_UDP_PAY, ICE_PTYPE_ATTR_GTP_DOWNLINK }, + { ICE_MAC_IPV4_GTPU_IPV4_TCP, ICE_PTYPE_ATTR_GTP_DOWNLINK }, + { ICE_MAC_IPV4_GTPU_IPV4_ICMP, ICE_PTYPE_ATTR_GTP_DOWNLINK }, + { ICE_MAC_IPV6_GTPU_IPV4_FRAG, ICE_PTYPE_ATTR_GTP_DOWNLINK }, + { ICE_MAC_IPV6_GTPU_IPV4_PAY, ICE_PTYPE_ATTR_GTP_DOWNLINK }, + { ICE_MAC_IPV6_GTPU_IPV4_UDP_PAY, ICE_PTYPE_ATTR_GTP_DOWNLINK }, + { ICE_MAC_IPV6_GTPU_IPV4_TCP, ICE_PTYPE_ATTR_GTP_DOWNLINK }, + { ICE_MAC_IPV6_GTPU_IPV4_ICMP, ICE_PTYPE_ATTR_GTP_DOWNLINK }, + { ICE_MAC_IPV4_GTPU_IPV6_FRAG, ICE_PTYPE_ATTR_GTP_DOWNLINK }, + { ICE_MAC_IPV4_GTPU_IPV6_PAY, ICE_PTYPE_ATTR_GTP_DOWNLINK }, + { ICE_MAC_IPV4_GTPU_IPV6_UDP_PAY, ICE_PTYPE_ATTR_GTP_DOWNLINK }, + { ICE_MAC_IPV4_GTPU_IPV6_TCP, ICE_PTYPE_ATTR_GTP_DOWNLINK }, + { ICE_MAC_IPV4_GTPU_IPV6_ICMPV6, ICE_PTYPE_ATTR_GTP_DOWNLINK }, + { ICE_MAC_IPV6_GTPU_IPV6_FRAG, ICE_PTYPE_ATTR_GTP_DOWNLINK }, + { ICE_MAC_IPV6_GTPU_IPV6_PAY, ICE_PTYPE_ATTR_GTP_DOWNLINK }, + { ICE_MAC_IPV6_GTPU_IPV6_UDP_PAY, ICE_PTYPE_ATTR_GTP_DOWNLINK }, + { ICE_MAC_IPV6_GTPU_IPV6_TCP, ICE_PTYPE_ATTR_GTP_DOWNLINK }, + { ICE_MAC_IPV6_GTPU_IPV6_ICMPV6, ICE_PTYPE_ATTR_GTP_DOWNLINK }, +}; + +static const struct ice_ptype_attributes ice_attr_gtpu_up[] = { + { ICE_MAC_IPV4_GTPU_IPV4_FRAG, ICE_PTYPE_ATTR_GTP_UPLINK }, + { ICE_MAC_IPV4_GTPU_IPV4_PAY, ICE_PTYPE_ATTR_GTP_UPLINK }, + { ICE_MAC_IPV4_GTPU_IPV4_UDP_PAY, ICE_PTYPE_ATTR_GTP_UPLINK }, + { ICE_MAC_IPV4_GTPU_IPV4_TCP, ICE_PTYPE_ATTR_GTP_UPLINK }, + { ICE_MAC_IPV4_GTPU_IPV4_ICMP, ICE_PTYPE_ATTR_GTP_UPLINK }, + { ICE_MAC_IPV6_GTPU_IPV4_FRAG, ICE_PTYPE_ATTR_GTP_UPLINK }, + { ICE_MAC_IPV6_GTPU_IPV4_PAY, ICE_PTYPE_ATTR_GTP_UPLINK }, + { ICE_MAC_IPV6_GTPU_IPV4_UDP_PAY, ICE_PTYPE_ATTR_GTP_UPLINK }, + { ICE_MAC_IPV6_GTPU_IPV4_TCP, ICE_PTYPE_ATTR_GTP_UPLINK }, + { ICE_MAC_IPV6_GTPU_IPV4_ICMP, ICE_PTYPE_ATTR_GTP_UPLINK }, + { ICE_MAC_IPV4_GTPU_IPV6_FRAG, ICE_PTYPE_ATTR_GTP_UPLINK }, + { ICE_MAC_IPV4_GTPU_IPV6_PAY, ICE_PTYPE_ATTR_GTP_UPLINK }, + { ICE_MAC_IPV4_GTPU_IPV6_UDP_PAY, ICE_PTYPE_ATTR_GTP_UPLINK }, + { ICE_MAC_IPV4_GTPU_IPV6_TCP, ICE_PTYPE_ATTR_GTP_UPLINK }, + { ICE_MAC_IPV4_GTPU_IPV6_ICMPV6, ICE_PTYPE_ATTR_GTP_UPLINK }, + { ICE_MAC_IPV6_GTPU_IPV6_FRAG, ICE_PTYPE_ATTR_GTP_UPLINK }, + { ICE_MAC_IPV6_GTPU_IPV6_PAY, ICE_PTYPE_ATTR_GTP_UPLINK }, + { ICE_MAC_IPV6_GTPU_IPV6_UDP_PAY, ICE_PTYPE_ATTR_GTP_UPLINK }, + { ICE_MAC_IPV6_GTPU_IPV6_TCP, ICE_PTYPE_ATTR_GTP_UPLINK }, + { ICE_MAC_IPV6_GTPU_IPV6_ICMPV6, ICE_PTYPE_ATTR_GTP_UPLINK }, +}; + +static const u32 ice_ptypes_gtpu[] = { + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x7FFFFE00, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, +}; + +/* Packet types for PPPoE */ +static const u32 ice_ptypes_pppoe[] = { + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x03ffe000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, +}; + +/* Packet types for packets with PFCP NODE header */ +static const u32 ice_ptypes_pfcp_node[] = { + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x80000000, 0x00000002, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, +}; + +/* Packet types for packets with PFCP SESSION header */ +static const u32 ice_ptypes_pfcp_session[] = { + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000005, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, +}; + +/* Packet types for L2TPv3 */ +static const u32 ice_ptypes_l2tpv3[] = { + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000300, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, +}; + +/* Packet types for ESP */ +static const u32 ice_ptypes_esp[] = { + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000003, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, +}; + +/* Packet types for AH */ +static const u32 ice_ptypes_ah[] = { + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x0000000C, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, +}; + +/* Packet types for packets with NAT_T ESP header */ +static const u32 ice_ptypes_nat_t_esp[] = { + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000030, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, +}; + +static const u32 ice_ptypes_mac_non_ip_ofos[] = { + 0x00000846, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00400000, 0x03FFF000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, +}; + /* Manage parameters and info. used during the creation of a flow profile */ struct ice_flow_prof_params { enum ice_block blk; @@ -208,12 +594,30 @@ struct ice_flow_prof_params { * This will give us the direction flags. */ struct ice_fv_word es[ICE_MAX_FV_WORDS]; + /* attributes can be used to add attributes to a particular PTYPE */ + const struct ice_ptype_attributes *attr; + u16 attr_cnt; + + u16 mask[ICE_MAX_FV_WORDS]; DECLARE_BITMAP(ptypes, ICE_FLOW_PTYPE_MAX); }; +#define ICE_FLOW_RSS_HDRS_INNER_MASK \ + (ICE_FLOW_SEG_HDR_PPPOE | ICE_FLOW_SEG_HDR_GTPC | \ + ICE_FLOW_SEG_HDR_GTPC_TEID | ICE_FLOW_SEG_HDR_GTPU | \ + ICE_FLOW_SEG_HDR_PFCP_SESSION | ICE_FLOW_SEG_HDR_L2TPV3 | \ + ICE_FLOW_SEG_HDR_ESP | ICE_FLOW_SEG_HDR_AH | \ + ICE_FLOW_SEG_HDR_NAT_T_ESP) + +#define ICE_FLOW_SEG_HDRS_L2_MASK \ + (ICE_FLOW_SEG_HDR_ETH | ICE_FLOW_SEG_HDR_VLAN) #define ICE_FLOW_SEG_HDRS_L3_MASK \ - (ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_IPV6) + (ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_IPV6 | ICE_FLOW_SEG_HDR_ARP) #define ICE_FLOW_SEG_HDRS_L4_MASK \ + (ICE_FLOW_SEG_HDR_ICMP | ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_UDP | \ + ICE_FLOW_SEG_HDR_SCTP) +/* mask for L4 protocols that are NOT part of IPv4/6 OTHER PTYPE groups */ +#define ICE_FLOW_SEG_HDRS_L4_MASK_NO_OTHER \ (ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_SCTP) /** @@ -243,8 +647,11 @@ ice_flow_val_hdrs(struct ice_flow_seg_info *segs, u8 segs_cnt) /* Sizes of fixed known protocol headers without header options */ #define ICE_FLOW_PROT_HDR_SZ_MAC 14 +#define ICE_FLOW_PROT_HDR_SZ_MAC_VLAN (ICE_FLOW_PROT_HDR_SZ_MAC + 2) #define ICE_FLOW_PROT_HDR_SZ_IPV4 20 #define ICE_FLOW_PROT_HDR_SZ_IPV6 40 +#define ICE_FLOW_PROT_HDR_SZ_ARP 28 +#define ICE_FLOW_PROT_HDR_SZ_ICMP 8 #define ICE_FLOW_PROT_HDR_SZ_TCP 20 #define ICE_FLOW_PROT_HDR_SZ_UDP 8 #define ICE_FLOW_PROT_HDR_SZ_SCTP 12 @@ -256,16 +663,27 @@ ice_flow_val_hdrs(struct ice_flow_seg_info *segs, u8 segs_cnt) */ static u16 ice_flow_calc_seg_sz(struct ice_flow_prof_params *params, u8 seg) { - u16 sz = ICE_FLOW_PROT_HDR_SZ_MAC; + u16 sz; + + /* L2 headers */ + sz = (params->prof->segs[seg].hdrs & ICE_FLOW_SEG_HDR_VLAN) ? + ICE_FLOW_PROT_HDR_SZ_MAC_VLAN : ICE_FLOW_PROT_HDR_SZ_MAC; /* L3 headers */ if (params->prof->segs[seg].hdrs & ICE_FLOW_SEG_HDR_IPV4) sz += ICE_FLOW_PROT_HDR_SZ_IPV4; else if (params->prof->segs[seg].hdrs & ICE_FLOW_SEG_HDR_IPV6) sz += ICE_FLOW_PROT_HDR_SZ_IPV6; + else if (params->prof->segs[seg].hdrs & ICE_FLOW_SEG_HDR_ARP) + sz += ICE_FLOW_PROT_HDR_SZ_ARP; + else if (params->prof->segs[seg].hdrs & ICE_FLOW_SEG_HDRS_L4_MASK) + /* An L3 header is required if L4 is specified */ + return 0; /* L4 headers */ - if (params->prof->segs[seg].hdrs & ICE_FLOW_SEG_HDR_TCP) + if (params->prof->segs[seg].hdrs & ICE_FLOW_SEG_HDR_ICMP) + sz += ICE_FLOW_PROT_HDR_SZ_ICMP; + else if (params->prof->segs[seg].hdrs & ICE_FLOW_SEG_HDR_TCP) sz += ICE_FLOW_PROT_HDR_SZ_TCP; else if (params->prof->segs[seg].hdrs & ICE_FLOW_SEG_HDR_UDP) sz += ICE_FLOW_PROT_HDR_SZ_UDP; @@ -298,10 +716,41 @@ ice_flow_proc_seg_hdrs(struct ice_flow_prof_params *params) hdrs = prof->segs[i].hdrs; + if (hdrs & ICE_FLOW_SEG_HDR_ETH) { + src = !i ? (const unsigned long *)ice_ptypes_mac_ofos : + (const unsigned long *)ice_ptypes_mac_il; + bitmap_and(params->ptypes, params->ptypes, src, + ICE_FLOW_PTYPE_MAX); + } + + if (i && hdrs & ICE_FLOW_SEG_HDR_VLAN) { + src = (const unsigned long *)ice_ptypes_macvlan_il; + bitmap_and(params->ptypes, params->ptypes, src, + ICE_FLOW_PTYPE_MAX); + } + + if (!i && hdrs & ICE_FLOW_SEG_HDR_ARP) { + bitmap_and(params->ptypes, params->ptypes, + (const unsigned long *)ice_ptypes_arp_of, + ICE_FLOW_PTYPE_MAX); + } + if ((hdrs & ICE_FLOW_SEG_HDR_IPV4) && - !(hdrs & ICE_FLOW_SEG_HDRS_L4_MASK)) { - src = !i ? (const unsigned long *)ice_ipv4_ofos_no_l4 : - (const unsigned long *)ice_ipv4_il_no_l4; + (hdrs & ICE_FLOW_SEG_HDR_IPV_OTHER)) { + src = i ? (const unsigned long *)ice_ptypes_ipv4_il : + (const unsigned long *)ice_ptypes_ipv4_ofos_all; + bitmap_and(params->ptypes, params->ptypes, src, + ICE_FLOW_PTYPE_MAX); + } else if ((hdrs & ICE_FLOW_SEG_HDR_IPV6) && + (hdrs & ICE_FLOW_SEG_HDR_IPV_OTHER)) { + src = i ? (const unsigned long *)ice_ptypes_ipv6_il : + (const unsigned long *)ice_ptypes_ipv6_ofos_all; + bitmap_and(params->ptypes, params->ptypes, src, + ICE_FLOW_PTYPE_MAX); + } else if ((hdrs & ICE_FLOW_SEG_HDR_IPV4) && + !(hdrs & ICE_FLOW_SEG_HDRS_L4_MASK_NO_OTHER)) { + src = !i ? (const unsigned long *)ice_ptypes_ipv4_ofos_no_l4 : + (const unsigned long *)ice_ptypes_ipv4_il_no_l4; bitmap_and(params->ptypes, params->ptypes, src, ICE_FLOW_PTYPE_MAX); } else if (hdrs & ICE_FLOW_SEG_HDR_IPV4) { @@ -310,9 +759,9 @@ ice_flow_proc_seg_hdrs(struct ice_flow_prof_params *params) bitmap_and(params->ptypes, params->ptypes, src, ICE_FLOW_PTYPE_MAX); } else if ((hdrs & ICE_FLOW_SEG_HDR_IPV6) && - !(hdrs & ICE_FLOW_SEG_HDRS_L4_MASK)) { - src = !i ? (const unsigned long *)ice_ipv6_ofos_no_l4 : - (const unsigned long *)ice_ipv6_il_no_l4; + !(hdrs & ICE_FLOW_SEG_HDRS_L4_MASK_NO_OTHER)) { + src = !i ? (const unsigned long *)ice_ptypes_ipv6_ofos_no_l4 : + (const unsigned long *)ice_ptypes_ipv6_il_no_l4; bitmap_and(params->ptypes, params->ptypes, src, ICE_FLOW_PTYPE_MAX); } else if (hdrs & ICE_FLOW_SEG_HDR_IPV6) { @@ -322,6 +771,20 @@ ice_flow_proc_seg_hdrs(struct ice_flow_prof_params *params) ICE_FLOW_PTYPE_MAX); } + if (hdrs & ICE_FLOW_SEG_HDR_ETH_NON_IP) { + src = (const unsigned long *)ice_ptypes_mac_non_ip_ofos; + bitmap_and(params->ptypes, params->ptypes, src, + ICE_FLOW_PTYPE_MAX); + } else if (hdrs & ICE_FLOW_SEG_HDR_PPPOE) { + src = (const unsigned long *)ice_ptypes_pppoe; + bitmap_and(params->ptypes, params->ptypes, src, + ICE_FLOW_PTYPE_MAX); + } else { + src = (const unsigned long *)ice_ptypes_pppoe; + bitmap_andnot(params->ptypes, params->ptypes, src, + ICE_FLOW_PTYPE_MAX); + } + if (hdrs & ICE_FLOW_SEG_HDR_UDP) { src = (const unsigned long *)ice_ptypes_udp_il; bitmap_and(params->ptypes, params->ptypes, src, @@ -334,12 +797,89 @@ ice_flow_proc_seg_hdrs(struct ice_flow_prof_params *params) src = (const unsigned long *)ice_ptypes_sctp_il; bitmap_and(params->ptypes, params->ptypes, src, ICE_FLOW_PTYPE_MAX); + } + + if (hdrs & ICE_FLOW_SEG_HDR_ICMP) { + src = !i ? (const unsigned long *)ice_ptypes_icmp_of : + (const unsigned long *)ice_ptypes_icmp_il; + bitmap_and(params->ptypes, params->ptypes, src, + ICE_FLOW_PTYPE_MAX); } else if (hdrs & ICE_FLOW_SEG_HDR_GRE) { if (!i) { src = (const unsigned long *)ice_ptypes_gre_of; bitmap_and(params->ptypes, params->ptypes, src, ICE_FLOW_PTYPE_MAX); } + } else if (hdrs & ICE_FLOW_SEG_HDR_GTPC) { + src = (const unsigned long *)ice_ptypes_gtpc; + bitmap_and(params->ptypes, params->ptypes, src, + ICE_FLOW_PTYPE_MAX); + } else if (hdrs & ICE_FLOW_SEG_HDR_GTPC_TEID) { + src = (const unsigned long *)ice_ptypes_gtpc_tid; + bitmap_and(params->ptypes, params->ptypes, src, + ICE_FLOW_PTYPE_MAX); + } else if (hdrs & ICE_FLOW_SEG_HDR_GTPU_DWN) { + src = (const unsigned long *)ice_ptypes_gtpu; + bitmap_and(params->ptypes, params->ptypes, src, + ICE_FLOW_PTYPE_MAX); + + /* Attributes for GTP packet with downlink */ + params->attr = ice_attr_gtpu_down; + params->attr_cnt = ARRAY_SIZE(ice_attr_gtpu_down); + } else if (hdrs & ICE_FLOW_SEG_HDR_GTPU_UP) { + src = (const unsigned long *)ice_ptypes_gtpu; + bitmap_and(params->ptypes, params->ptypes, src, + ICE_FLOW_PTYPE_MAX); + + /* Attributes for GTP packet with uplink */ + params->attr = ice_attr_gtpu_up; + params->attr_cnt = ARRAY_SIZE(ice_attr_gtpu_up); + } else if (hdrs & ICE_FLOW_SEG_HDR_GTPU_EH) { + src = (const unsigned long *)ice_ptypes_gtpu; + bitmap_and(params->ptypes, params->ptypes, src, + ICE_FLOW_PTYPE_MAX); + + /* Attributes for GTP packet with Extension Header */ + params->attr = ice_attr_gtpu_eh; + params->attr_cnt = ARRAY_SIZE(ice_attr_gtpu_eh); + } else if (hdrs & ICE_FLOW_SEG_HDR_GTPU_IP) { + src = (const unsigned long *)ice_ptypes_gtpu; + bitmap_and(params->ptypes, params->ptypes, src, + ICE_FLOW_PTYPE_MAX); + } else if (hdrs & ICE_FLOW_SEG_HDR_L2TPV3) { + src = (const unsigned long *)ice_ptypes_l2tpv3; + bitmap_and(params->ptypes, params->ptypes, src, + ICE_FLOW_PTYPE_MAX); + } else if (hdrs & ICE_FLOW_SEG_HDR_ESP) { + src = (const unsigned long *)ice_ptypes_esp; + bitmap_and(params->ptypes, params->ptypes, src, + ICE_FLOW_PTYPE_MAX); + } else if (hdrs & ICE_FLOW_SEG_HDR_AH) { + src = (const unsigned long *)ice_ptypes_ah; + bitmap_and(params->ptypes, params->ptypes, src, + ICE_FLOW_PTYPE_MAX); + } else if (hdrs & ICE_FLOW_SEG_HDR_NAT_T_ESP) { + src = (const unsigned long *)ice_ptypes_nat_t_esp; + bitmap_and(params->ptypes, params->ptypes, src, + ICE_FLOW_PTYPE_MAX); + } + + if (hdrs & ICE_FLOW_SEG_HDR_PFCP) { + if (hdrs & ICE_FLOW_SEG_HDR_PFCP_NODE) + src = (const unsigned long *)ice_ptypes_pfcp_node; + else + src = (const unsigned long *)ice_ptypes_pfcp_session; + + bitmap_and(params->ptypes, params->ptypes, src, + ICE_FLOW_PTYPE_MAX); + } else { + src = (const unsigned long *)ice_ptypes_pfcp_node; + bitmap_andnot(params->ptypes, params->ptypes, src, + ICE_FLOW_PTYPE_MAX); + + src = (const unsigned long *)ice_ptypes_pfcp_session; + bitmap_andnot(params->ptypes, params->ptypes, src, + ICE_FLOW_PTYPE_MAX); } } @@ -352,6 +892,7 @@ ice_flow_proc_seg_hdrs(struct ice_flow_prof_params *params) * @params: information about the flow to be processed * @seg: packet segment index of the field to be extracted * @fld: ID of field to be extracted + * @match: bit field of all fields * * This function determines the protocol ID, offset, and size of the given * field. It then allocates one or more extraction sequence entries for the @@ -359,17 +900,73 @@ ice_flow_proc_seg_hdrs(struct ice_flow_prof_params *params) */ static enum ice_status ice_flow_xtract_fld(struct ice_hw *hw, struct ice_flow_prof_params *params, - u8 seg, enum ice_flow_field fld) + u8 seg, enum ice_flow_field fld, u64 match) { + enum ice_flow_field sib = ICE_FLOW_FIELD_IDX_MAX; enum ice_prot_id prot_id = ICE_PROT_ID_INVAL; u8 fv_words = hw->blk[params->blk].es.fvw; struct ice_flow_fld_info *flds; u16 cnt, ese_bits, i; + u16 sib_mask = 0; + u16 mask; u16 off; flds = params->prof->segs[seg].fields; switch (fld) { + case ICE_FLOW_FIELD_IDX_ETH_DA: + case ICE_FLOW_FIELD_IDX_ETH_SA: + case ICE_FLOW_FIELD_IDX_S_VLAN: + case ICE_FLOW_FIELD_IDX_C_VLAN: + prot_id = seg == 0 ? ICE_PROT_MAC_OF_OR_S : ICE_PROT_MAC_IL; + break; + case ICE_FLOW_FIELD_IDX_ETH_TYPE: + prot_id = seg == 0 ? ICE_PROT_ETYPE_OL : ICE_PROT_ETYPE_IL; + break; + case ICE_FLOW_FIELD_IDX_IPV4_DSCP: + prot_id = seg == 0 ? ICE_PROT_IPV4_OF_OR_S : ICE_PROT_IPV4_IL; + break; + case ICE_FLOW_FIELD_IDX_IPV6_DSCP: + prot_id = seg == 0 ? ICE_PROT_IPV6_OF_OR_S : ICE_PROT_IPV6_IL; + break; + case ICE_FLOW_FIELD_IDX_IPV4_TTL: + case ICE_FLOW_FIELD_IDX_IPV4_PROT: + prot_id = seg == 0 ? ICE_PROT_IPV4_OF_OR_S : ICE_PROT_IPV4_IL; + + /* TTL and PROT share the same extraction seq. entry. + * Each is considered a sibling to the other in terms of sharing + * the same extraction sequence entry. + */ + if (fld == ICE_FLOW_FIELD_IDX_IPV4_TTL) + sib = ICE_FLOW_FIELD_IDX_IPV4_PROT; + else if (fld == ICE_FLOW_FIELD_IDX_IPV4_PROT) + sib = ICE_FLOW_FIELD_IDX_IPV4_TTL; + + /* If the sibling field is also included, that field's + * mask needs to be included. + */ + if (match & BIT(sib)) + sib_mask = ice_flds_info[sib].mask; + break; + case ICE_FLOW_FIELD_IDX_IPV6_TTL: + case ICE_FLOW_FIELD_IDX_IPV6_PROT: + prot_id = seg == 0 ? ICE_PROT_IPV6_OF_OR_S : ICE_PROT_IPV6_IL; + + /* TTL and PROT share the same extraction seq. entry. + * Each is considered a sibling to the other in terms of sharing + * the same extraction sequence entry. + */ + if (fld == ICE_FLOW_FIELD_IDX_IPV6_TTL) + sib = ICE_FLOW_FIELD_IDX_IPV6_PROT; + else if (fld == ICE_FLOW_FIELD_IDX_IPV6_PROT) + sib = ICE_FLOW_FIELD_IDX_IPV6_TTL; + + /* If the sibling field is also included, that field's + * mask needs to be included. + */ + if (match & BIT(sib)) + sib_mask = ice_flds_info[sib].mask; + break; case ICE_FLOW_FIELD_IDX_IPV4_SA: case ICE_FLOW_FIELD_IDX_IPV4_DA: prot_id = seg == 0 ? ICE_PROT_IPV4_OF_OR_S : ICE_PROT_IPV4_IL; @@ -380,6 +977,7 @@ ice_flow_xtract_fld(struct ice_hw *hw, struct ice_flow_prof_params *params, break; case ICE_FLOW_FIELD_IDX_TCP_SRC_PORT: case ICE_FLOW_FIELD_IDX_TCP_DST_PORT: + case ICE_FLOW_FIELD_IDX_TCP_FLAGS: prot_id = ICE_PROT_TCP_IL; break; case ICE_FLOW_FIELD_IDX_UDP_SRC_PORT: @@ -390,6 +988,49 @@ ice_flow_xtract_fld(struct ice_hw *hw, struct ice_flow_prof_params *params, case ICE_FLOW_FIELD_IDX_SCTP_DST_PORT: prot_id = ICE_PROT_SCTP_IL; break; + case ICE_FLOW_FIELD_IDX_GTPC_TEID: + case ICE_FLOW_FIELD_IDX_GTPU_IP_TEID: + case ICE_FLOW_FIELD_IDX_GTPU_UP_TEID: + case ICE_FLOW_FIELD_IDX_GTPU_DWN_TEID: + case ICE_FLOW_FIELD_IDX_GTPU_EH_TEID: + case ICE_FLOW_FIELD_IDX_GTPU_EH_QFI: + /* GTP is accessed through UDP OF protocol */ + prot_id = ICE_PROT_UDP_OF; + break; + case ICE_FLOW_FIELD_IDX_PPPOE_SESS_ID: + prot_id = ICE_PROT_PPPOE; + break; + case ICE_FLOW_FIELD_IDX_PFCP_SEID: + prot_id = ICE_PROT_UDP_IL_OR_S; + break; + case ICE_FLOW_FIELD_IDX_L2TPV3_SESS_ID: + prot_id = ICE_PROT_L2TPV3; + break; + case ICE_FLOW_FIELD_IDX_ESP_SPI: + prot_id = ICE_PROT_ESP_F; + break; + case ICE_FLOW_FIELD_IDX_AH_SPI: + prot_id = ICE_PROT_ESP_2; + break; + case ICE_FLOW_FIELD_IDX_NAT_T_ESP_SPI: + prot_id = ICE_PROT_UDP_IL_OR_S; + break; + case ICE_FLOW_FIELD_IDX_ARP_SIP: + case ICE_FLOW_FIELD_IDX_ARP_DIP: + case ICE_FLOW_FIELD_IDX_ARP_SHA: + case ICE_FLOW_FIELD_IDX_ARP_DHA: + case ICE_FLOW_FIELD_IDX_ARP_OP: + prot_id = ICE_PROT_ARP_OF; + break; + case ICE_FLOW_FIELD_IDX_ICMP_TYPE: + case ICE_FLOW_FIELD_IDX_ICMP_CODE: + /* ICMP type and code share the same extraction seq. entry */ + prot_id = (params->prof->segs[seg].hdrs & ICE_FLOW_SEG_HDR_IPV4) ? + ICE_PROT_ICMP_IL : ICE_PROT_ICMPV6_IL; + sib = fld == ICE_FLOW_FIELD_IDX_ICMP_TYPE ? + ICE_FLOW_FIELD_IDX_ICMP_CODE : + ICE_FLOW_FIELD_IDX_ICMP_TYPE; + break; case ICE_FLOW_FIELD_IDX_GRE_KEYID: prot_id = ICE_PROT_GRE_OF; break; @@ -407,6 +1048,7 @@ ice_flow_xtract_fld(struct ice_hw *hw, struct ice_flow_prof_params *params, ICE_FLOW_FV_EXTRACT_SZ; flds[fld].xtrct.disp = (u8)(ice_flds_info[fld].off % ese_bits); flds[fld].xtrct.idx = params->es_cnt; + flds[fld].xtrct.mask = ice_flds_info[fld].mask; /* Adjust the next field-entry index after accommodating the number of * entries this field consumes @@ -416,24 +1058,34 @@ ice_flow_xtract_fld(struct ice_hw *hw, struct ice_flow_prof_params *params, /* Fill in the extraction sequence entries needed for this field */ off = flds[fld].xtrct.off; + mask = flds[fld].xtrct.mask; for (i = 0; i < cnt; i++) { - u8 idx; - - /* Make sure the number of extraction sequence required - * does not exceed the block's capability + /* Only consume an extraction sequence entry if there is no + * sibling field associated with this field or the sibling entry + * already extracts the word shared with this field. */ - if (params->es_cnt >= fv_words) - return ICE_ERR_MAX_LIMIT; + if (sib == ICE_FLOW_FIELD_IDX_MAX || + flds[sib].xtrct.prot_id == ICE_PROT_ID_INVAL || + flds[sib].xtrct.off != off) { + u8 idx; - /* some blocks require a reversed field vector layout */ - if (hw->blk[params->blk].es.reverse) - idx = fv_words - params->es_cnt - 1; - else - idx = params->es_cnt; + /* Make sure the number of extraction sequence required + * does not exceed the block's capability + */ + if (params->es_cnt >= fv_words) + return ICE_ERR_MAX_LIMIT; - params->es[idx].prot_id = prot_id; - params->es[idx].off = off; - params->es_cnt++; + /* some blocks require a reversed field vector layout */ + if (hw->blk[params->blk].es.reverse) + idx = fv_words - params->es_cnt - 1; + else + idx = params->es_cnt; + + params->es[idx].prot_id = prot_id; + params->es[idx].off = off; + params->mask[idx] = mask | sib_mask; + params->es_cnt++; + } off += ICE_FLOW_FV_EXTRACT_SZ; } @@ -533,14 +1185,15 @@ ice_flow_create_xtrct_seq(struct ice_hw *hw, u8 i; for (i = 0; i < prof->segs_cnt; i++) { - u8 j; + u64 match = params->prof->segs[i].match; + enum ice_flow_field j; - for_each_set_bit(j, (unsigned long *)&prof->segs[i].match, + for_each_set_bit(j, (unsigned long *)&match, ICE_FLOW_FIELD_IDX_MAX) { - status = ice_flow_xtract_fld(hw, params, i, - (enum ice_flow_field)j); + status = ice_flow_xtract_fld(hw, params, i, j, match); if (status) return status; + clear_bit(j, (unsigned long *)&match); } /* Process raw matching bytes */ @@ -751,7 +1404,8 @@ ice_flow_add_prof_sync(struct ice_hw *hw, enum ice_block blk, /* Add a HW profile for this flow profile */ status = ice_add_prof(hw, blk, prof_id, (u8 *)params->ptypes, - params->es); + params->attr, params->attr_cnt, params->es, + params->mask); if (status) { ice_debug(hw, ICE_DBG_FLOW, "Error adding a HW flow profile\n"); goto out; @@ -1158,6 +1812,9 @@ ice_flow_add_fld_raw(struct ice_flow_seg_info *seg, u16 off, u8 len, seg->raws_cnt++; } +#define ICE_FLOW_RSS_SEG_HDR_L2_MASKS \ + (ICE_FLOW_SEG_HDR_ETH | ICE_FLOW_SEG_HDR_VLAN) + #define ICE_FLOW_RSS_SEG_HDR_L3_MASKS \ (ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_IPV6) @@ -1165,7 +1822,8 @@ ice_flow_add_fld_raw(struct ice_flow_seg_info *seg, u16 off, u8 len, (ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_SCTP) #define ICE_FLOW_RSS_SEG_HDR_VAL_MASKS \ - (ICE_FLOW_RSS_SEG_HDR_L3_MASKS | \ + (ICE_FLOW_RSS_SEG_HDR_L2_MASKS | \ + ICE_FLOW_RSS_SEG_HDR_L3_MASKS | \ ICE_FLOW_RSS_SEG_HDR_L4_MASKS) /** @@ -1193,7 +1851,8 @@ ice_flow_set_rss_seg_info(struct ice_flow_seg_info *segs, u64 hash_fields, ICE_FLOW_SET_HDRS(segs, flow_hdr); - if (segs->hdrs & ~ICE_FLOW_RSS_SEG_HDR_VAL_MASKS) + if (segs->hdrs & ~ICE_FLOW_RSS_SEG_HDR_VAL_MASKS & + ~ICE_FLOW_RSS_HDRS_INNER_MASK & ~ICE_FLOW_SEG_HDR_IPV_OTHER) return ICE_ERR_PARAM; val = (u64)(segs->hdrs & ICE_FLOW_RSS_SEG_HDR_L3_MASKS); @@ -1349,9 +2008,9 @@ ice_add_rss_list(struct ice_hw *hw, u16 vsi_handle, struct ice_flow_prof *prof) * [63] - Encapsulation flag, 0 if non-tunneled, 1 if tunneled */ #define ICE_FLOW_GEN_PROFID(hash, hdr, segs_cnt) \ - (u64)(((u64)(hash) & ICE_FLOW_PROF_HASH_M) | \ - (((u64)(hdr) << ICE_FLOW_PROF_HDR_S) & ICE_FLOW_PROF_HDR_M) | \ - ((u8)((segs_cnt) - 1) ? ICE_FLOW_PROF_ENCAP_M : 0)) + ((u64)(((u64)(hash) & ICE_FLOW_PROF_HASH_M) | \ + (((u64)(hdr) << ICE_FLOW_PROF_HDR_S) & ICE_FLOW_PROF_HDR_M) | \ + ((u8)((segs_cnt) - 1) ? ICE_FLOW_PROF_ENCAP_M : 0))) /** * ice_add_rss_cfg_sync - add an RSS configuration @@ -1490,6 +2149,94 @@ ice_add_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds, return status; } +/** + * ice_rem_rss_cfg_sync - remove an existing RSS configuration + * @hw: pointer to the hardware structure + * @vsi_handle: software VSI handle + * @hashed_flds: Packet hash types (ICE_FLOW_HASH_*) to remove + * @addl_hdrs: Protocol header fields within a packet segment + * @segs_cnt: packet segment count + * + * Assumption: lock has already been acquired for RSS list + */ +static enum ice_status +ice_rem_rss_cfg_sync(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds, + u32 addl_hdrs, u8 segs_cnt) +{ + const enum ice_block blk = ICE_BLK_RSS; + struct ice_flow_seg_info *segs; + struct ice_flow_prof *prof; + enum ice_status status; + + segs = kcalloc(segs_cnt, sizeof(*segs), GFP_KERNEL); + if (!segs) + return ICE_ERR_NO_MEMORY; + + /* Construct the packet segment info from the hashed fields */ + status = ice_flow_set_rss_seg_info(&segs[segs_cnt - 1], hashed_flds, + addl_hdrs); + if (status) + goto out; + + prof = ice_flow_find_prof_conds(hw, blk, ICE_FLOW_RX, segs, segs_cnt, + vsi_handle, + ICE_FLOW_FIND_PROF_CHK_FLDS); + if (!prof) { + status = ICE_ERR_DOES_NOT_EXIST; + goto out; + } + + status = ice_flow_disassoc_prof(hw, blk, prof, vsi_handle); + if (status) + goto out; + + /* Remove RSS configuration from VSI context before deleting + * the flow profile. + */ + ice_rem_rss_list(hw, vsi_handle, prof); + + if (bitmap_empty(prof->vsis, ICE_MAX_VSI)) + status = ice_flow_rem_prof(hw, blk, prof->id); + +out: + kfree(segs); + return status; +} + +/** + * ice_rem_rss_cfg - remove an existing RSS config with matching hashed fields + * @hw: pointer to the hardware structure + * @vsi_handle: software VSI handle + * @hashed_flds: Packet hash types (ICE_FLOW_HASH_*) to remove + * @addl_hdrs: Protocol header fields within a packet segment + * + * This function will lookup the flow profile based on the input + * hash field bitmap, iterate through the profile entry list of + * that profile and find entry associated with input VSI to be + * removed. Calls are made to underlying flow s which will APIs + * turn build or update buffers for RSS XLT1 section. + */ +enum ice_status __maybe_unused +ice_rem_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds, + u32 addl_hdrs) +{ + enum ice_status status; + + if (hashed_flds == ICE_HASH_INVALID || + !ice_is_vsi_valid(hw, vsi_handle)) + return ICE_ERR_PARAM; + + mutex_lock(&hw->rss_locks); + status = ice_rem_rss_cfg_sync(hw, vsi_handle, hashed_flds, addl_hdrs, + ICE_RSS_OUTER_HEADERS); + if (!status) + status = ice_rem_rss_cfg_sync(hw, vsi_handle, hashed_flds, + addl_hdrs, ICE_RSS_INNER_HEADERS); + mutex_unlock(&hw->rss_locks); + + return status; +} + /* Mapping of AVF hash bit fields to an L3-L4 hash combination. * As the ice_flow_avf_hdr_field represent individual bit shifts in a hash, * convert its values to their appropriate flow L3, L4 values. diff --git a/drivers/net/ethernet/intel/ice/ice_flow.h b/drivers/net/ethernet/intel/ice/ice_flow.h index 829f90b1e998..2a2d8c1536cb 100644 --- a/drivers/net/ethernet/intel/ice/ice_flow.h +++ b/drivers/net/ethernet/intel/ice/ice_flow.h @@ -8,6 +8,9 @@ #define ICE_FLOW_FLD_OFF_INVAL 0xffff /* Generate flow hash field from flow field type(s) */ +#define ICE_FLOW_HASH_ETH \ + (BIT_ULL(ICE_FLOW_FIELD_IDX_ETH_DA) | \ + BIT_ULL(ICE_FLOW_FIELD_IDX_ETH_SA)) #define ICE_FLOW_HASH_IPV4 \ (BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA) | \ BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA)) @@ -30,6 +33,80 @@ #define ICE_HASH_UDP_IPV4 (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_UDP_PORT) #define ICE_HASH_UDP_IPV6 (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_UDP_PORT) +#define ICE_FLOW_HASH_GTP_TEID \ + (BIT_ULL(ICE_FLOW_FIELD_IDX_GTPC_TEID)) + +#define ICE_FLOW_HASH_GTP_IPV4_TEID \ + (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_GTP_TEID) +#define ICE_FLOW_HASH_GTP_IPV6_TEID \ + (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_GTP_TEID) + +#define ICE_FLOW_HASH_GTP_U_TEID \ + (BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_IP_TEID)) + +#define ICE_FLOW_HASH_GTP_U_IPV4_TEID \ + (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_GTP_U_TEID) +#define ICE_FLOW_HASH_GTP_U_IPV6_TEID \ + (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_GTP_U_TEID) + +#define ICE_FLOW_HASH_GTP_U_EH_TEID \ + (BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_EH_TEID)) + +#define ICE_FLOW_HASH_GTP_U_EH_QFI \ + (BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_EH_QFI)) + +#define ICE_FLOW_HASH_GTP_U_IPV4_EH \ + (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_GTP_U_EH_TEID | \ + ICE_FLOW_HASH_GTP_U_EH_QFI) +#define ICE_FLOW_HASH_GTP_U_IPV6_EH \ + (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_GTP_U_EH_TEID | \ + ICE_FLOW_HASH_GTP_U_EH_QFI) + +#define ICE_FLOW_HASH_PPPOE_SESS_ID \ + (BIT_ULL(ICE_FLOW_FIELD_IDX_PPPOE_SESS_ID)) + +#define ICE_FLOW_HASH_PPPOE_SESS_ID_ETH \ + (ICE_FLOW_HASH_ETH | ICE_FLOW_HASH_PPPOE_SESS_ID) +#define ICE_FLOW_HASH_PPPOE_TCP_ID \ + (ICE_FLOW_HASH_TCP_PORT | ICE_FLOW_HASH_PPPOE_SESS_ID) +#define ICE_FLOW_HASH_PPPOE_UDP_ID \ + (ICE_FLOW_HASH_UDP_PORT | ICE_FLOW_HASH_PPPOE_SESS_ID) + +#define ICE_FLOW_HASH_PFCP_SEID \ + (BIT_ULL(ICE_FLOW_FIELD_IDX_PFCP_SEID)) +#define ICE_FLOW_HASH_PFCP_IPV4_SEID \ + (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_PFCP_SEID) +#define ICE_FLOW_HASH_PFCP_IPV6_SEID \ + (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_PFCP_SEID) + +#define ICE_FLOW_HASH_L2TPV3_SESS_ID \ + (BIT_ULL(ICE_FLOW_FIELD_IDX_L2TPV3_SESS_ID)) +#define ICE_FLOW_HASH_L2TPV3_IPV4_SESS_ID \ + (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_L2TPV3_SESS_ID) +#define ICE_FLOW_HASH_L2TPV3_IPV6_SESS_ID \ + (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_L2TPV3_SESS_ID) + +#define ICE_FLOW_HASH_ESP_SPI \ + (BIT_ULL(ICE_FLOW_FIELD_IDX_ESP_SPI)) +#define ICE_FLOW_HASH_ESP_IPV4_SPI \ + (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_ESP_SPI) +#define ICE_FLOW_HASH_ESP_IPV6_SPI \ + (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_ESP_SPI) + +#define ICE_FLOW_HASH_AH_SPI \ + (BIT_ULL(ICE_FLOW_FIELD_IDX_AH_SPI)) +#define ICE_FLOW_HASH_AH_IPV4_SPI \ + (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_AH_SPI) +#define ICE_FLOW_HASH_AH_IPV6_SPI \ + (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_AH_SPI) + +#define ICE_FLOW_HASH_NAT_T_ESP_SPI \ + (BIT_ULL(ICE_FLOW_FIELD_IDX_NAT_T_ESP_SPI)) +#define ICE_FLOW_HASH_NAT_T_ESP_IPV4_SPI \ + (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_NAT_T_ESP_SPI) +#define ICE_FLOW_HASH_NAT_T_ESP_IPV6_SPI \ + (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_NAT_T_ESP_SPI) + /* Protocol header fields within a packet segment. A segment consists of one or * more protocol headers that make up a logical group of protocol headers. Each * logical group of protocol headers encapsulates or is encapsulated using/by @@ -38,16 +115,66 @@ */ enum ice_flow_seg_hdr { ICE_FLOW_SEG_HDR_NONE = 0x00000000, + ICE_FLOW_SEG_HDR_ETH = 0x00000001, + ICE_FLOW_SEG_HDR_VLAN = 0x00000002, ICE_FLOW_SEG_HDR_IPV4 = 0x00000004, ICE_FLOW_SEG_HDR_IPV6 = 0x00000008, + ICE_FLOW_SEG_HDR_ARP = 0x00000010, + ICE_FLOW_SEG_HDR_ICMP = 0x00000020, ICE_FLOW_SEG_HDR_TCP = 0x00000040, ICE_FLOW_SEG_HDR_UDP = 0x00000080, ICE_FLOW_SEG_HDR_SCTP = 0x00000100, ICE_FLOW_SEG_HDR_GRE = 0x00000200, + ICE_FLOW_SEG_HDR_GTPC = 0x00000400, + ICE_FLOW_SEG_HDR_GTPC_TEID = 0x00000800, + ICE_FLOW_SEG_HDR_GTPU_IP = 0x00001000, + ICE_FLOW_SEG_HDR_GTPU_EH = 0x00002000, + ICE_FLOW_SEG_HDR_GTPU_DWN = 0x00004000, + ICE_FLOW_SEG_HDR_GTPU_UP = 0x00008000, + ICE_FLOW_SEG_HDR_PPPOE = 0x00010000, + ICE_FLOW_SEG_HDR_PFCP_NODE = 0x00020000, + ICE_FLOW_SEG_HDR_PFCP_SESSION = 0x00040000, + ICE_FLOW_SEG_HDR_L2TPV3 = 0x00080000, + ICE_FLOW_SEG_HDR_ESP = 0x00100000, + ICE_FLOW_SEG_HDR_AH = 0x00200000, + ICE_FLOW_SEG_HDR_NAT_T_ESP = 0x00400000, + ICE_FLOW_SEG_HDR_ETH_NON_IP = 0x00800000, + /* The following is an additive bit for ICE_FLOW_SEG_HDR_IPV4 and + * ICE_FLOW_SEG_HDR_IPV6 which include the IPV4 other PTYPEs + */ + ICE_FLOW_SEG_HDR_IPV_OTHER = 0x20000000, }; +/* These segments all have the same PTYPES, but are otherwise distinguished by + * the value of the gtp_eh_pdu and gtp_eh_pdu_link flags: + * + * gtp_eh_pdu gtp_eh_pdu_link + * ICE_FLOW_SEG_HDR_GTPU_IP 0 0 + * ICE_FLOW_SEG_HDR_GTPU_EH 1 don't care + * ICE_FLOW_SEG_HDR_GTPU_DWN 1 0 + * ICE_FLOW_SEG_HDR_GTPU_UP 1 1 + */ +#define ICE_FLOW_SEG_HDR_GTPU (ICE_FLOW_SEG_HDR_GTPU_IP | \ + ICE_FLOW_SEG_HDR_GTPU_EH | \ + ICE_FLOW_SEG_HDR_GTPU_DWN | \ + ICE_FLOW_SEG_HDR_GTPU_UP) +#define ICE_FLOW_SEG_HDR_PFCP (ICE_FLOW_SEG_HDR_PFCP_NODE | \ + ICE_FLOW_SEG_HDR_PFCP_SESSION) + enum ice_flow_field { + /* L2 */ + ICE_FLOW_FIELD_IDX_ETH_DA, + ICE_FLOW_FIELD_IDX_ETH_SA, + ICE_FLOW_FIELD_IDX_S_VLAN, + ICE_FLOW_FIELD_IDX_C_VLAN, + ICE_FLOW_FIELD_IDX_ETH_TYPE, /* L3 */ + ICE_FLOW_FIELD_IDX_IPV4_DSCP, + ICE_FLOW_FIELD_IDX_IPV6_DSCP, + ICE_FLOW_FIELD_IDX_IPV4_TTL, + ICE_FLOW_FIELD_IDX_IPV4_PROT, + ICE_FLOW_FIELD_IDX_IPV6_TTL, + ICE_FLOW_FIELD_IDX_IPV6_PROT, ICE_FLOW_FIELD_IDX_IPV4_SA, ICE_FLOW_FIELD_IDX_IPV4_DA, ICE_FLOW_FIELD_IDX_IPV6_SA, @@ -59,9 +186,42 @@ enum ice_flow_field { ICE_FLOW_FIELD_IDX_UDP_DST_PORT, ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT, ICE_FLOW_FIELD_IDX_SCTP_DST_PORT, + ICE_FLOW_FIELD_IDX_TCP_FLAGS, + /* ARP */ + ICE_FLOW_FIELD_IDX_ARP_SIP, + ICE_FLOW_FIELD_IDX_ARP_DIP, + ICE_FLOW_FIELD_IDX_ARP_SHA, + ICE_FLOW_FIELD_IDX_ARP_DHA, + ICE_FLOW_FIELD_IDX_ARP_OP, + /* ICMP */ + ICE_FLOW_FIELD_IDX_ICMP_TYPE, + ICE_FLOW_FIELD_IDX_ICMP_CODE, /* GRE */ ICE_FLOW_FIELD_IDX_GRE_KEYID, - /* The total number of enums must not exceed 64 */ + /* GTPC_TEID */ + ICE_FLOW_FIELD_IDX_GTPC_TEID, + /* GTPU_IP */ + ICE_FLOW_FIELD_IDX_GTPU_IP_TEID, + /* GTPU_EH */ + ICE_FLOW_FIELD_IDX_GTPU_EH_TEID, + ICE_FLOW_FIELD_IDX_GTPU_EH_QFI, + /* GTPU_UP */ + ICE_FLOW_FIELD_IDX_GTPU_UP_TEID, + /* GTPU_DWN */ + ICE_FLOW_FIELD_IDX_GTPU_DWN_TEID, + /* PPPoE */ + ICE_FLOW_FIELD_IDX_PPPOE_SESS_ID, + /* PFCP */ + ICE_FLOW_FIELD_IDX_PFCP_SEID, + /* L2TPv3 */ + ICE_FLOW_FIELD_IDX_L2TPV3_SESS_ID, + /* ESP */ + ICE_FLOW_FIELD_IDX_ESP_SPI, + /* AH */ + ICE_FLOW_FIELD_IDX_AH_SPI, + /* NAT_T ESP */ + ICE_FLOW_FIELD_IDX_NAT_T_ESP_SPI, + /* The total number of enums must not exceed 64 */ ICE_FLOW_FIELD_IDX_MAX }; @@ -138,6 +298,7 @@ struct ice_flow_seg_xtrct { u16 off; /* Starting offset of the field in header in bytes */ u8 idx; /* Index of FV entry used */ u8 disp; /* Displacement of field in bits fr. FV entry's start */ + u16 mask; /* Mask for field */ }; enum ice_flow_fld_match_type { @@ -248,5 +409,8 @@ enum ice_status ice_rem_vsi_rss_cfg(struct ice_hw *hw, u16 vsi_handle); enum ice_status ice_add_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds, u32 addl_hdrs); +enum ice_status +ice_rem_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds, + u32 addl_hdrs); u64 ice_get_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u32 hdrs); #endif /* _ICE_FLOW_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index 093a1818a392..de38a0fc9665 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -130,6 +130,7 @@ #define GLINT_DYN_CTL_ITR_INDX_M ICE_M(0x3, 3) #define GLINT_DYN_CTL_INTERVAL_S 5 #define GLINT_DYN_CTL_INTERVAL_M ICE_M(0xFFF, 5) +#define GLINT_DYN_CTL_SW_ITR_INDX_ENA_M BIT(24) #define GLINT_DYN_CTL_SW_ITR_INDX_M ICE_M(0x3, 25) #define GLINT_DYN_CTL_WB_ON_ITR_M BIT(30) #define GLINT_DYN_CTL_INTENA_MSK_M BIT(31) @@ -306,8 +307,23 @@ #define GLQF_FD_SIZE_FD_BSIZE_S 16 #define GLQF_FD_SIZE_FD_BSIZE_M ICE_M(0x7FFF, 16) #define GLQF_FDINSET(_i, _j) (0x00412000 + ((_i) * 4 + (_j) * 512)) +#define GLQF_FDMASK(_i) (0x00410800 + ((_i) * 4)) +#define GLQF_FDMASK_MAX_INDEX 31 +#define GLQF_FDMASK_MSK_INDEX_S 0 +#define GLQF_FDMASK_MSK_INDEX_M ICE_M(0x1F, 0) +#define GLQF_FDMASK_MASK_S 16 +#define GLQF_FDMASK_MASK_M ICE_M(0xFFFF, 16) #define GLQF_FDMASK_SEL(_i) (0x00410400 + ((_i) * 4)) #define GLQF_FDSWAP(_i, _j) (0x00413000 + ((_i) * 4 + (_j) * 512)) +#define GLQF_HMASK(_i) (0x0040FC00 + ((_i) * 4)) +#define GLQF_HMASK_MAX_INDEX 31 +#define GLQF_HMASK_MSK_INDEX_S 0 +#define GLQF_HMASK_MSK_INDEX_M ICE_M(0x1F, 0) +#define GLQF_HMASK_MASK_S 16 +#define GLQF_HMASK_MASK_M ICE_M(0xFFFF, 16) +#define GLQF_HMASK_SEL(_i) (0x00410000 + ((_i) * 4)) +#define GLQF_HMASK_SEL_MAX_INDEX 127 +#define GLQF_HMASK_SEL_MASK_SEL_S 0 #define PFQF_FD_ENA 0x0043A000 #define PFQF_FD_ENA_FD_ENA_M BIT(0) #define PFQF_FD_SIZE 0x00460100 @@ -369,6 +385,9 @@ #define VSIQF_FD_CNT(_VSI) (0x00464000 + ((_VSI) * 4)) #define VSIQF_FD_CNT_FD_GCNT_S 0 #define VSIQF_FD_CNT_FD_GCNT_M ICE_M(0x3FFF, 0) +#define VSIQF_FD_CNT_FD_BCNT_S 16 +#define VSIQF_FD_CNT_FD_BCNT_M ICE_M(0x3FFF, 16) +#define VSIQF_FD_SIZE(_VSI) (0x00462000 + ((_VSI) * 4)) #define VSIQF_HKEY_MAX_INDEX 12 #define VSIQF_HLUT_MAX_INDEX 15 #define PFPM_APM 0x000B8080 diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h index 4ec24c3e813f..21329ed3087e 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -55,6 +55,7 @@ struct ice_fltr_desc { #define ICE_FXD_FLTR_QW0_COMP_REPORT_M \ (0x3ULL << ICE_FXD_FLTR_QW0_COMP_REPORT_S) #define ICE_FXD_FLTR_QW0_COMP_REPORT_SW_FAIL 0x1ULL +#define ICE_FXD_FLTR_QW0_COMP_REPORT_SW 0x2ULL #define ICE_FXD_FLTR_QW0_FD_SPACE_S 14 #define ICE_FXD_FLTR_QW0_FD_SPACE_M (0x3ULL << ICE_FXD_FLTR_QW0_FD_SPACE_S) @@ -128,6 +129,7 @@ struct ice_fltr_desc { #define ICE_FXD_FLTR_QW1_FDID_PRI_S 25 #define ICE_FXD_FLTR_QW1_FDID_PRI_M (0x7ULL << ICE_FXD_FLTR_QW1_FDID_PRI_S) #define ICE_FXD_FLTR_QW1_FDID_PRI_ONE 0x1ULL +#define ICE_FXD_FLTR_QW1_FDID_PRI_THREE 0x3ULL #define ICE_FXD_FLTR_QW1_FDID_MDID_S 28 #define ICE_FXD_FLTR_QW1_FDID_MDID_M (0xFULL << ICE_FXD_FLTR_QW1_FDID_MDID_S) @@ -138,6 +140,26 @@ struct ice_fltr_desc { (0xFFFFFFFFULL << ICE_FXD_FLTR_QW1_FDID_S) #define ICE_FXD_FLTR_QW1_FDID_ZERO 0x0ULL +/* definition for FD filter programming status descriptor WB format */ +#define ICE_FXD_FLTR_WB_QW1_DD_S 0 +#define ICE_FXD_FLTR_WB_QW1_DD_M (0x1ULL << ICE_FXD_FLTR_WB_QW1_DD_S) +#define ICE_FXD_FLTR_WB_QW1_DD_YES 0x1ULL + +#define ICE_FXD_FLTR_WB_QW1_PROG_ID_S 1 +#define ICE_FXD_FLTR_WB_QW1_PROG_ID_M \ + (0x3ULL << ICE_FXD_FLTR_WB_QW1_PROG_ID_S) +#define ICE_FXD_FLTR_WB_QW1_PROG_ADD 0x0ULL +#define ICE_FXD_FLTR_WB_QW1_PROG_DEL 0x1ULL + +#define ICE_FXD_FLTR_WB_QW1_FAIL_S 4 +#define ICE_FXD_FLTR_WB_QW1_FAIL_M (0x1ULL << ICE_FXD_FLTR_WB_QW1_FAIL_S) +#define ICE_FXD_FLTR_WB_QW1_FAIL_YES 0x1ULL + +#define ICE_FXD_FLTR_WB_QW1_FAIL_PROF_S 5 +#define ICE_FXD_FLTR_WB_QW1_FAIL_PROF_M \ + (0x1ULL << ICE_FXD_FLTR_WB_QW1_FAIL_PROF_S) +#define ICE_FXD_FLTR_WB_QW1_FAIL_PROF_YES 0x1ULL + struct ice_rx_ptype_decoded { u32 ptype:10; u32 known:1; diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index d13c7fc8fb0a..82e2ce23df3d 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -158,6 +158,8 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi, u16 vf_id) if (vsi->type == ICE_VSI_VF) vsi->vf_id = vf_id; + else + vsi->vf_id = ICE_INVAL_VFID; switch (vsi->type) { case ICE_VSI_PF: @@ -343,6 +345,9 @@ static int ice_vsi_clear(struct ice_vsi *vsi) pf->vsi[vsi->idx] = NULL; if (vsi->idx < pf->next_vsi && vsi->type != ICE_VSI_CTRL) pf->next_vsi = vsi->idx; + if (vsi->idx < pf->next_vsi && vsi->type == ICE_VSI_CTRL && + vsi->vf_id != ICE_INVAL_VFID) + pf->next_vsi = vsi->idx; ice_vsi_free_arrays(vsi); mutex_unlock(&pf->sw_mutex); @@ -382,6 +387,8 @@ static irqreturn_t ice_msix_clean_rings(int __always_unused irq, void *data) if (!q_vector->tx.ring && !q_vector->rx.ring) return IRQ_HANDLED; + q_vector->total_events++; + napi_schedule(&q_vector->napi); return IRQ_HANDLED; @@ -419,7 +426,7 @@ ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type vsi_type, u16 vf_id) vsi->type = vsi_type; vsi->back = pf; - set_bit(__ICE_DOWN, vsi->state); + set_bit(ICE_VSI_DOWN, vsi->state); if (vsi_type == ICE_VSI_VF) ice_vsi_set_num_qs(vsi, vf_id); @@ -454,8 +461,8 @@ ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type vsi_type, u16 vf_id) goto unlock_pf; } - if (vsi->type == ICE_VSI_CTRL) { - /* Use the last VSI slot as the index for the control VSI */ + if (vsi->type == ICE_VSI_CTRL && vf_id == ICE_INVAL_VFID) { + /* Use the last VSI slot as the index for PF control VSI */ vsi->idx = pf->num_alloc_vsi - 1; pf->ctrl_vsi_idx = vsi->idx; pf->vsi[vsi->idx] = vsi; @@ -468,6 +475,9 @@ ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type vsi_type, u16 vf_id) pf->next_vsi = ice_get_free_slot(pf->vsi, pf->num_alloc_vsi, pf->next_vsi); } + + if (vsi->type == ICE_VSI_CTRL && vf_id != ICE_INVAL_VFID) + pf->vf[vf_id].ctrl_vsi_idx = vsi->idx; goto unlock_pf; err_rings: @@ -506,7 +516,7 @@ static int ice_alloc_fd_res(struct ice_vsi *vsi) if (!b_val) return -EPERM; - if (vsi->type != ICE_VSI_PF) + if (!(vsi->type == ICE_VSI_PF || vsi->type == ICE_VSI_VF)) return -EPERM; if (!test_bit(ICE_FLAG_FD_ENA, pf->flags)) @@ -517,6 +527,13 @@ static int ice_alloc_fd_res(struct ice_vsi *vsi) /* each VSI gets same "best_effort" quota */ vsi->num_bfltr = b_val; + if (vsi->type == ICE_VSI_VF) { + vsi->num_gfltr = 0; + + /* each VSI gets same "best_effort" quota */ + vsi->num_bfltr = b_val; + } + return 0; } @@ -729,11 +746,10 @@ static void ice_set_dflt_vsi_ctx(struct ice_vsi_ctx *ctxt) */ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) { - u16 offset = 0, qmap = 0, tx_count = 0; + u16 offset = 0, qmap = 0, tx_count = 0, pow = 0; + u16 num_txq_per_tc, num_rxq_per_tc; u16 qcount_tx = vsi->alloc_txq; u16 qcount_rx = vsi->alloc_rxq; - u16 tx_numq_tc, rx_numq_tc; - u16 pow = 0, max_rss = 0; bool ena_tc0 = false; u8 netdev_tc = 0; int i; @@ -751,12 +767,15 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) vsi->tc_cfg.ena_tc |= 1; } - rx_numq_tc = qcount_rx / vsi->tc_cfg.numtc; - if (!rx_numq_tc) - rx_numq_tc = 1; - tx_numq_tc = qcount_tx / vsi->tc_cfg.numtc; - if (!tx_numq_tc) - tx_numq_tc = 1; + num_rxq_per_tc = min_t(u16, qcount_rx / vsi->tc_cfg.numtc, ICE_MAX_RXQS_PER_TC); + if (!num_rxq_per_tc) + num_rxq_per_tc = 1; + num_txq_per_tc = qcount_tx / vsi->tc_cfg.numtc; + if (!num_txq_per_tc) + num_txq_per_tc = 1; + + /* find the (rounded up) power-of-2 of qcount */ + pow = (u16)order_base_2(num_rxq_per_tc); /* TC mapping is a function of the number of Rx queues assigned to the * VSI for each traffic class and the offset of these queues. @@ -769,26 +788,6 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) * * Setup number and offset of Rx queues for all TCs for the VSI */ - - qcount_rx = rx_numq_tc; - - /* qcount will change if RSS is enabled */ - if (test_bit(ICE_FLAG_RSS_ENA, vsi->back->flags)) { - if (vsi->type == ICE_VSI_PF || vsi->type == ICE_VSI_VF) { - if (vsi->type == ICE_VSI_PF) - max_rss = ICE_MAX_LG_RSS_QS; - else - max_rss = ICE_MAX_RSS_QS_PER_VF; - qcount_rx = min_t(u16, rx_numq_tc, max_rss); - if (!vsi->req_rxq) - qcount_rx = min_t(u16, qcount_rx, - vsi->rss_size); - } - } - - /* find the (rounded up) power-of-2 of qcount */ - pow = (u16)order_base_2(qcount_rx); - ice_for_each_traffic_class(i) { if (!(vsi->tc_cfg.ena_tc & BIT(i))) { /* TC is not enabled */ @@ -802,16 +801,16 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) /* TC is enabled */ vsi->tc_cfg.tc_info[i].qoffset = offset; - vsi->tc_cfg.tc_info[i].qcount_rx = qcount_rx; - vsi->tc_cfg.tc_info[i].qcount_tx = tx_numq_tc; + vsi->tc_cfg.tc_info[i].qcount_rx = num_rxq_per_tc; + vsi->tc_cfg.tc_info[i].qcount_tx = num_txq_per_tc; vsi->tc_cfg.tc_info[i].netdev_tc = netdev_tc++; qmap = ((offset << ICE_AQ_VSI_TC_Q_OFFSET_S) & ICE_AQ_VSI_TC_Q_OFFSET_M) | ((pow << ICE_AQ_VSI_TC_Q_NUM_S) & ICE_AQ_VSI_TC_Q_NUM_M); - offset += qcount_rx; - tx_count += tx_numq_tc; + offset += num_rxq_per_tc; + tx_count += num_txq_per_tc; ctxt->info.tc_mapping[i] = cpu_to_le16(qmap); } @@ -824,7 +823,7 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) if (offset) vsi->num_rxq = offset; else - vsi->num_rxq = qcount_rx; + vsi->num_rxq = num_rxq_per_tc; vsi->num_txq = tx_count; @@ -856,7 +855,8 @@ static void ice_set_fd_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi) u8 dflt_q_group, dflt_q_prio; u16 dflt_q, report_q, val; - if (vsi->type != ICE_VSI_PF && vsi->type != ICE_VSI_CTRL) + if (vsi->type != ICE_VSI_PF && vsi->type != ICE_VSI_CTRL && + vsi->type != ICE_VSI_VF) return; val = ICE_AQ_VSI_PROP_FLOW_DIR_VALID; @@ -1179,7 +1179,24 @@ static int ice_vsi_setup_vector_base(struct ice_vsi *vsi) num_q_vectors = vsi->num_q_vectors; /* reserve slots from OS requested IRQs */ - base = ice_get_res(pf, pf->irq_tracker, num_q_vectors, vsi->idx); + if (vsi->type == ICE_VSI_CTRL && vsi->vf_id != ICE_INVAL_VFID) { + struct ice_vf *vf; + int i; + + ice_for_each_vf(pf, i) { + vf = &pf->vf[i]; + if (i != vsi->vf_id && vf->ctrl_vsi_idx != ICE_NO_VSI) { + base = pf->vsi[vf->ctrl_vsi_idx]->base_vector; + break; + } + } + if (i == pf->num_alloc_vfs) + base = ice_get_res(pf, pf->irq_tracker, num_q_vectors, + ICE_RES_VF_CTRL_VEC_ID); + } else { + base = ice_get_res(pf, pf->irq_tracker, num_q_vectors, + vsi->idx); + } if (base < 0) { dev_err(dev, "%d MSI-X interrupts available. %s %d failed to get %d MSI-X vectors\n", @@ -1296,14 +1313,13 @@ err_out: * LUT, while in the event of enable request for RSS, it will reconfigure RSS * LUT. */ -int ice_vsi_manage_rss_lut(struct ice_vsi *vsi, bool ena) +void ice_vsi_manage_rss_lut(struct ice_vsi *vsi, bool ena) { - int err = 0; u8 *lut; lut = kzalloc(vsi->rss_table_size, GFP_KERNEL); if (!lut) - return -ENOMEM; + return; if (ena) { if (vsi->rss_lut_user) @@ -1313,9 +1329,8 @@ int ice_vsi_manage_rss_lut(struct ice_vsi *vsi, bool ena) vsi->rss_size); } - err = ice_set_rss(vsi, NULL, lut, vsi->rss_table_size); + ice_set_rss_lut(vsi, lut, vsi->rss_table_size); kfree(lut); - return err; } /** @@ -1324,12 +1339,10 @@ int ice_vsi_manage_rss_lut(struct ice_vsi *vsi, bool ena) */ static int ice_vsi_cfg_rss_lut_key(struct ice_vsi *vsi) { - struct ice_aqc_get_set_rss_keys *key; struct ice_pf *pf = vsi->back; - enum ice_status status; struct device *dev; - int err = 0; - u8 *lut; + u8 *lut, *key; + int err; dev = ice_pf_to_dev(pf); vsi->rss_size = min_t(u16, vsi->rss_size, vsi->num_rxq); @@ -1343,37 +1356,26 @@ static int ice_vsi_cfg_rss_lut_key(struct ice_vsi *vsi) else ice_fill_rss_lut(lut, vsi->rss_table_size, vsi->rss_size); - status = ice_aq_set_rss_lut(&pf->hw, vsi->idx, vsi->rss_lut_type, lut, - vsi->rss_table_size); - - if (status) { - dev_err(dev, "set_rss_lut failed, error %s\n", - ice_stat_str(status)); - err = -EIO; + err = ice_set_rss_lut(vsi, lut, vsi->rss_table_size); + if (err) { + dev_err(dev, "set_rss_lut failed, error %d\n", err); goto ice_vsi_cfg_rss_exit; } - key = kzalloc(sizeof(*key), GFP_KERNEL); + key = kzalloc(ICE_GET_SET_RSS_KEY_EXTEND_KEY_SIZE, GFP_KERNEL); if (!key) { err = -ENOMEM; goto ice_vsi_cfg_rss_exit; } if (vsi->rss_hkey_user) - memcpy(key, - (struct ice_aqc_get_set_rss_keys *)vsi->rss_hkey_user, - ICE_GET_SET_RSS_KEY_EXTEND_KEY_SIZE); + memcpy(key, vsi->rss_hkey_user, ICE_GET_SET_RSS_KEY_EXTEND_KEY_SIZE); else - netdev_rss_key_fill((void *)key, - ICE_GET_SET_RSS_KEY_EXTEND_KEY_SIZE); + netdev_rss_key_fill((void *)key, ICE_GET_SET_RSS_KEY_EXTEND_KEY_SIZE); - status = ice_aq_set_rss_key(&pf->hw, vsi->idx, key); - - if (status) { - dev_err(dev, "set_rss_key failed, error %s\n", - ice_stat_str(status)); - err = -EIO; - } + err = ice_set_rss_key(vsi, key); + if (err) + dev_err(dev, "set_rss_key failed, error %d\n", err); kfree(key); ice_vsi_cfg_rss_exit: @@ -1502,13 +1504,13 @@ static void ice_vsi_set_rss_flow_fld(struct ice_vsi *vsi) */ bool ice_pf_state_is_nominal(struct ice_pf *pf) { - DECLARE_BITMAP(check_bits, __ICE_STATE_NBITS) = { 0 }; + DECLARE_BITMAP(check_bits, ICE_STATE_NBITS) = { 0 }; if (!pf) return false; - bitmap_set(check_bits, 0, __ICE_STATE_NOMINAL_CHECK_BITS); - if (bitmap_intersects(pf->state, check_bits, __ICE_STATE_NBITS)) + bitmap_set(check_bits, 0, ICE_STATE_NOMINAL_CHECK_BITS); + if (bitmap_intersects(pf->state, check_bits, ICE_STATE_NBITS)) return false; return true; @@ -1773,7 +1775,7 @@ int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi) * This function converts a decimal interrupt rate limit in usecs to the format * expected by firmware. */ -u32 ice_intrl_usec_to_reg(u8 intrl, u8 gran) +static u32 ice_intrl_usec_to_reg(u8 intrl, u8 gran) { u32 val = intrl / gran; @@ -1783,6 +1785,51 @@ u32 ice_intrl_usec_to_reg(u8 intrl, u8 gran) } /** + * ice_write_intrl - write throttle rate limit to interrupt specific register + * @q_vector: pointer to interrupt specific structure + * @intrl: throttle rate limit in microseconds to write + */ +void ice_write_intrl(struct ice_q_vector *q_vector, u8 intrl) +{ + struct ice_hw *hw = &q_vector->vsi->back->hw; + + wr32(hw, GLINT_RATE(q_vector->reg_idx), + ice_intrl_usec_to_reg(intrl, ICE_INTRL_GRAN_ABOVE_25)); +} + +/** + * __ice_write_itr - write throttle rate to register + * @q_vector: pointer to interrupt data structure + * @rc: pointer to ring container + * @itr: throttle rate in microseconds to write + */ +static void __ice_write_itr(struct ice_q_vector *q_vector, + struct ice_ring_container *rc, u16 itr) +{ + struct ice_hw *hw = &q_vector->vsi->back->hw; + + wr32(hw, GLINT_ITR(rc->itr_idx, q_vector->reg_idx), + ITR_REG_ALIGN(itr) >> ICE_ITR_GRAN_S); +} + +/** + * ice_write_itr - write throttle rate to queue specific register + * @rc: pointer to ring container + * @itr: throttle rate in microseconds to write + */ +void ice_write_itr(struct ice_ring_container *rc, u16 itr) +{ + struct ice_q_vector *q_vector; + + if (!rc->ring) + return; + + q_vector = rc->ring->q_vector; + + __ice_write_itr(q_vector, rc, itr); +} + +/** * ice_vsi_cfg_msix - MSIX mode Interrupt Config in the HW * @vsi: the VSI being configured * @@ -1802,9 +1849,6 @@ void ice_vsi_cfg_msix(struct ice_vsi *vsi) ice_cfg_itr(hw, q_vector); - wr32(hw, GLINT_RATE(reg_idx), - ice_intrl_usec_to_reg(q_vector->intrl, hw->intrl_gran)); - /* Both Transmit Queue Interrupt Cause Control register * and Receive Queue Interrupt Cause control register * expects MSIX_INDX field to be the vector index @@ -2308,7 +2352,7 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, struct ice_vsi *vsi; int ret, i; - if (vsi_type == ICE_VSI_VF) + if (vsi_type == ICE_VSI_VF || vsi_type == ICE_VSI_CTRL) vsi = ice_vsi_alloc(pf, vsi_type, vf_id); else vsi = ice_vsi_alloc(pf, vsi_type, ICE_INVAL_VFID); @@ -2323,7 +2367,7 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, if (vsi->type == ICE_VSI_PF) vsi->ethtype = ETH_P_PAUSE; - if (vsi->type == ICE_VSI_VF) + if (vsi->type == ICE_VSI_VF || vsi->type == ICE_VSI_CTRL) vsi->vf_id = vf_id; ice_alloc_fd_res(vsi); @@ -2492,11 +2536,10 @@ static void ice_vsi_release_msix(struct ice_vsi *vsi) for (i = 0; i < vsi->num_q_vectors; i++) { struct ice_q_vector *q_vector = vsi->q_vectors[i]; - u16 reg_idx = q_vector->reg_idx; - wr32(hw, GLINT_ITR(ICE_IDX_ITR0, reg_idx), 0); - wr32(hw, GLINT_ITR(ICE_IDX_ITR1, reg_idx), 0); + ice_write_intrl(q_vector, 0); for (q = 0; q < q_vector->num_ring_tx; q++) { + ice_write_itr(&q_vector->tx, 0); wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), 0); if (ice_is_xdp_ena_vsi(vsi)) { u32 xdp_txq = txq + vsi->num_xdp_txq; @@ -2507,6 +2550,7 @@ static void ice_vsi_release_msix(struct ice_vsi *vsi) } for (q = 0; q < q_vector->num_ring_rx; q++) { + ice_write_itr(&q_vector->rx, 0); wr32(hw, QINT_RQCTL(vsi->rxq_map[rxq]), 0); rxq++; } @@ -2593,7 +2637,7 @@ void ice_vsi_free_rx_rings(struct ice_vsi *vsi) */ void ice_vsi_close(struct ice_vsi *vsi) { - if (!test_and_set_bit(__ICE_DOWN, vsi->state)) + if (!test_and_set_bit(ICE_VSI_DOWN, vsi->state)) ice_down(vsi); ice_vsi_free_irq(vsi); @@ -2610,10 +2654,10 @@ int ice_ena_vsi(struct ice_vsi *vsi, bool locked) { int err = 0; - if (!test_bit(__ICE_NEEDS_RESTART, vsi->state)) + if (!test_bit(ICE_VSI_NEEDS_RESTART, vsi->state)) return 0; - clear_bit(__ICE_NEEDS_RESTART, vsi->state); + clear_bit(ICE_VSI_NEEDS_RESTART, vsi->state); if (vsi->netdev && vsi->type == ICE_VSI_PF) { if (netif_running(vsi->netdev)) { @@ -2639,10 +2683,10 @@ int ice_ena_vsi(struct ice_vsi *vsi, bool locked) */ void ice_dis_vsi(struct ice_vsi *vsi, bool locked) { - if (test_bit(__ICE_DOWN, vsi->state)) + if (test_bit(ICE_VSI_DOWN, vsi->state)) return; - set_bit(__ICE_NEEDS_RESTART, vsi->state); + set_bit(ICE_VSI_NEEDS_RESTART, vsi->state); if (vsi->type == ICE_VSI_PF && vsi->netdev) { if (netif_running(vsi->netdev)) { @@ -2752,11 +2796,14 @@ int ice_vsi_release(struct ice_vsi *vsi) * PF that is running the work queue items currently. This is done to * avoid check_flush_dependency() warning on this wq */ - if (vsi->netdev && !ice_is_reset_in_progress(pf->state)) { + if (vsi->netdev && !ice_is_reset_in_progress(pf->state) && + (test_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state))) { unregister_netdev(vsi->netdev); - ice_devlink_destroy_port(vsi); + clear_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state); } + ice_devlink_destroy_port(vsi); + if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) ice_rss_clean(vsi); @@ -2770,7 +2817,24 @@ int ice_vsi_release(struct ice_vsi *vsi) * many interrupts each VF needs. SR-IOV MSIX resources are also * cleared in the same manner. */ - if (vsi->type != ICE_VSI_VF) { + if (vsi->type == ICE_VSI_CTRL && vsi->vf_id != ICE_INVAL_VFID) { + struct ice_vf *vf; + int i; + + ice_for_each_vf(pf, i) { + vf = &pf->vf[i]; + if (i != vsi->vf_id && vf->ctrl_vsi_idx != ICE_NO_VSI) + break; + } + if (i == pf->num_alloc_vfs) { + /* No other VFs left that have control VSI, reclaim SW + * interrupts back to the common pool + */ + ice_free_res(pf->irq_tracker, vsi->base_vector, + ICE_RES_VF_CTRL_VEC_ID); + pf->num_avail_sw_msix += vsi->num_q_vectors; + } + } else if (vsi->type != ICE_VSI_VF) { /* reclaim SW interrupts back to the common pool */ ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx); pf->num_avail_sw_msix += vsi->num_q_vectors; @@ -2794,10 +2858,16 @@ int ice_vsi_release(struct ice_vsi *vsi) ice_vsi_delete(vsi); ice_vsi_free_q_vectors(vsi); - /* make sure unregister_netdev() was called by checking __ICE_DOWN */ - if (vsi->netdev && test_bit(__ICE_DOWN, vsi->state)) { - free_netdev(vsi->netdev); - vsi->netdev = NULL; + if (vsi->netdev) { + if (test_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state)) { + unregister_netdev(vsi->netdev); + clear_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state); + } + if (test_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state)) { + free_netdev(vsi->netdev); + vsi->netdev = NULL; + clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); + } } if (vsi->type == ICE_VSI_VF && @@ -2818,39 +2888,6 @@ int ice_vsi_release(struct ice_vsi *vsi) } /** - * ice_vsi_rebuild_update_coalesce - set coalesce for a q_vector - * @q_vector: pointer to q_vector which is being updated - * @coalesce: pointer to array of struct with stored coalesce - * - * Set coalesce param in q_vector and update these parameters in HW. - */ -static void -ice_vsi_rebuild_update_coalesce(struct ice_q_vector *q_vector, - struct ice_coalesce_stored *coalesce) -{ - struct ice_ring_container *rx_rc = &q_vector->rx; - struct ice_ring_container *tx_rc = &q_vector->tx; - struct ice_hw *hw = &q_vector->vsi->back->hw; - - tx_rc->itr_setting = coalesce->itr_tx; - rx_rc->itr_setting = coalesce->itr_rx; - - /* dynamic ITR values will be updated during Tx/Rx */ - if (!ITR_IS_DYNAMIC(tx_rc->itr_setting)) - wr32(hw, GLINT_ITR(tx_rc->itr_idx, q_vector->reg_idx), - ITR_REG_ALIGN(tx_rc->itr_setting) >> - ICE_ITR_GRAN_S); - if (!ITR_IS_DYNAMIC(rx_rc->itr_setting)) - wr32(hw, GLINT_ITR(rx_rc->itr_idx, q_vector->reg_idx), - ITR_REG_ALIGN(rx_rc->itr_setting) >> - ICE_ITR_GRAN_S); - - q_vector->intrl = coalesce->intrl; - wr32(hw, GLINT_RATE(q_vector->reg_idx), - ice_intrl_usec_to_reg(q_vector->intrl, hw->intrl_gran)); -} - -/** * ice_vsi_rebuild_get_coalesce - get coalesce from all q_vectors * @vsi: VSI connected with q_vectors * @coalesce: array of struct with stored coalesce @@ -2869,6 +2906,11 @@ ice_vsi_rebuild_get_coalesce(struct ice_vsi *vsi, coalesce[i].itr_tx = q_vector->tx.itr_setting; coalesce[i].itr_rx = q_vector->rx.itr_setting; coalesce[i].intrl = q_vector->intrl; + + if (i < vsi->num_txq) + coalesce[i].tx_valid = true; + if (i < vsi->num_rxq) + coalesce[i].rx_valid = true; } return vsi->num_q_vectors; @@ -2888,22 +2930,75 @@ static void ice_vsi_rebuild_set_coalesce(struct ice_vsi *vsi, struct ice_coalesce_stored *coalesce, int size) { + struct ice_ring_container *rc; int i; if ((size && !coalesce) || !vsi) return; - for (i = 0; i < size && i < vsi->num_q_vectors; i++) - ice_vsi_rebuild_update_coalesce(vsi->q_vectors[i], - &coalesce[i]); + /* There are a couple of cases that have to be handled here: + * 1. The case where the number of queue vectors stays the same, but + * the number of Tx or Rx rings changes (the first for loop) + * 2. The case where the number of queue vectors increased (the + * second for loop) + */ + for (i = 0; i < size && i < vsi->num_q_vectors; i++) { + /* There are 2 cases to handle here and they are the same for + * both Tx and Rx: + * if the entry was valid previously (coalesce[i].[tr]x_valid + * and the loop variable is less than the number of rings + * allocated, then write the previous values + * + * if the entry was not valid previously, but the number of + * rings is less than are allocated (this means the number of + * rings increased from previously), then write out the + * values in the first element + * + * Also, always write the ITR, even if in ITR_IS_DYNAMIC + * as there is no harm because the dynamic algorithm + * will just overwrite. + */ + if (i < vsi->alloc_rxq && coalesce[i].rx_valid) { + rc = &vsi->q_vectors[i]->rx; + rc->itr_setting = coalesce[i].itr_rx; + ice_write_itr(rc, rc->itr_setting); + } else if (i < vsi->alloc_rxq) { + rc = &vsi->q_vectors[i]->rx; + rc->itr_setting = coalesce[0].itr_rx; + ice_write_itr(rc, rc->itr_setting); + } + + if (i < vsi->alloc_txq && coalesce[i].tx_valid) { + rc = &vsi->q_vectors[i]->tx; + rc->itr_setting = coalesce[i].itr_tx; + ice_write_itr(rc, rc->itr_setting); + } else if (i < vsi->alloc_txq) { + rc = &vsi->q_vectors[i]->tx; + rc->itr_setting = coalesce[0].itr_tx; + ice_write_itr(rc, rc->itr_setting); + } + + vsi->q_vectors[i]->intrl = coalesce[i].intrl; + ice_write_intrl(vsi->q_vectors[i], coalesce[i].intrl); + } - /* number of q_vectors increased, so assume coalesce settings were - * changed globally (i.e. ethtool -C eth0 instead of per-queue) and use - * the previous settings from q_vector 0 for all of the new q_vectors + /* the number of queue vectors increased so write whatever is in + * the first element */ - for (; i < vsi->num_q_vectors; i++) - ice_vsi_rebuild_update_coalesce(vsi->q_vectors[i], - &coalesce[0]); + for (; i < vsi->num_q_vectors; i++) { + /* transmit */ + rc = &vsi->q_vectors[i]->tx; + rc->itr_setting = coalesce[0].itr_tx; + ice_write_itr(rc, rc->itr_setting); + + /* receive */ + rc = &vsi->q_vectors[i]->rx; + rc->itr_setting = coalesce[0].itr_rx; + ice_write_itr(rc, rc->itr_setting); + + vsi->q_vectors[i]->intrl = coalesce[0].intrl; + ice_write_intrl(vsi->q_vectors[i], coalesce[0].intrl); + } } /** @@ -2919,6 +3014,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) struct ice_coalesce_stored *coalesce; int prev_num_q_vectors = 0; struct ice_vf *vf = NULL; + enum ice_vsi_type vtype; enum ice_status status; struct ice_pf *pf; int ret, i; @@ -2927,14 +3023,17 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) return -EINVAL; pf = vsi->back; - if (vsi->type == ICE_VSI_VF) + vtype = vsi->type; + if (vtype == ICE_VSI_VF) vf = &pf->vf[vsi->vf_id]; coalesce = kcalloc(vsi->num_q_vectors, sizeof(struct ice_coalesce_stored), GFP_KERNEL); - if (coalesce) - prev_num_q_vectors = ice_vsi_rebuild_get_coalesce(vsi, - coalesce); + if (!coalesce) + return -ENOMEM; + + prev_num_q_vectors = ice_vsi_rebuild_get_coalesce(vsi, coalesce); + ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx); ice_vsi_free_q_vectors(vsi); @@ -2943,7 +3042,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) * many interrupts each VF needs. SR-IOV MSIX resources are also * cleared in the same manner. */ - if (vsi->type != ICE_VSI_VF) { + if (vtype != ICE_VSI_VF) { /* reclaim SW interrupts back to the common pool */ ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx); pf->num_avail_sw_msix += vsi->num_q_vectors; @@ -2958,7 +3057,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) ice_vsi_put_qs(vsi); ice_vsi_clear_rings(vsi); ice_vsi_free_arrays(vsi); - if (vsi->type == ICE_VSI_VF) + if (vtype == ICE_VSI_VF) ice_vsi_set_num_qs(vsi, vf->vf_id); else ice_vsi_set_num_qs(vsi, ICE_INVAL_VFID); @@ -2977,7 +3076,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) if (ret < 0) goto err_vsi; - switch (vsi->type) { + switch (vtype) { case ICE_VSI_CTRL: case ICE_VSI_PF: ret = ice_vsi_alloc_q_vectors(vsi); @@ -3004,7 +3103,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) goto err_vectors; } /* ICE_VSI_CTRL does not need RSS so skip RSS processing */ - if (vsi->type != ICE_VSI_CTRL) + if (vtype != ICE_VSI_CTRL) /* Do not exit if configuring RSS had an issue, at * least receive traffic on first queue. Hence no * need to capture return value @@ -3066,7 +3165,7 @@ err_rings: } err_vsi: ice_vsi_clear(vsi); - set_bit(__ICE_RESET_FAILED, pf->state); + set_bit(ICE_RESET_FAILED, pf->state); kfree(coalesce); return ret; } @@ -3077,10 +3176,10 @@ err_vsi: */ bool ice_is_reset_in_progress(unsigned long *state) { - return test_bit(__ICE_RESET_OICR_RECV, state) || - test_bit(__ICE_PFR_REQ, state) || - test_bit(__ICE_CORER_REQ, state) || - test_bit(__ICE_GLOBR_REQ, state); + return test_bit(ICE_RESET_OICR_RECV, state) || + test_bit(ICE_PFR_REQ, state) || + test_bit(ICE_CORER_REQ, state) || + test_bit(ICE_GLOBR_REQ, state); } #ifdef CONFIG_DCB @@ -3168,20 +3267,15 @@ out: /** * ice_update_ring_stats - Update ring statistics * @ring: ring to update - * @cont: used to increment per-vector counters * @pkts: number of processed packets * @bytes: number of processed bytes * * This function assumes that caller has acquired a u64_stats_sync lock. */ -static void -ice_update_ring_stats(struct ice_ring *ring, struct ice_ring_container *cont, - u64 pkts, u64 bytes) +static void ice_update_ring_stats(struct ice_ring *ring, u64 pkts, u64 bytes) { ring->stats.bytes += bytes; ring->stats.pkts += pkts; - cont->total_bytes += bytes; - cont->total_pkts += pkts; } /** @@ -3193,7 +3287,7 @@ ice_update_ring_stats(struct ice_ring *ring, struct ice_ring_container *cont, void ice_update_tx_ring_stats(struct ice_ring *tx_ring, u64 pkts, u64 bytes) { u64_stats_update_begin(&tx_ring->syncp); - ice_update_ring_stats(tx_ring, &tx_ring->q_vector->tx, pkts, bytes); + ice_update_ring_stats(tx_ring, pkts, bytes); u64_stats_update_end(&tx_ring->syncp); } @@ -3206,7 +3300,7 @@ void ice_update_tx_ring_stats(struct ice_ring *tx_ring, u64 pkts, u64 bytes) void ice_update_rx_ring_stats(struct ice_ring *rx_ring, u64 pkts, u64 bytes) { u64_stats_update_begin(&rx_ring->syncp); - ice_update_ring_stats(rx_ring, &rx_ring->q_vector->rx, pkts, bytes); + ice_update_ring_stats(rx_ring, pkts, bytes); u64_stats_update_end(&rx_ring->syncp); } @@ -3348,3 +3442,40 @@ int ice_clear_dflt_vsi(struct ice_sw *sw) return 0; } + +/** + * ice_set_link - turn on/off physical link + * @vsi: VSI to modify physical link on + * @ena: turn on/off physical link + */ +int ice_set_link(struct ice_vsi *vsi, bool ena) +{ + struct device *dev = ice_pf_to_dev(vsi->back); + struct ice_port_info *pi = vsi->port_info; + struct ice_hw *hw = pi->hw; + enum ice_status status; + + if (vsi->type != ICE_VSI_PF) + return -EINVAL; + + status = ice_aq_set_link_restart_an(pi, ena, NULL); + + /* if link is owned by manageability, FW will return ICE_AQ_RC_EMODE. + * this is not a fatal error, so print a warning message and return + * a success code. Return an error if FW returns an error code other + * than ICE_AQ_RC_EMODE + */ + if (status == ICE_ERR_AQ_ERROR) { + if (hw->adminq.sq_last_status == ICE_AQ_RC_EMODE) + dev_warn(dev, "can't set link to %s, err %s aq_err %s. not fatal, continuing\n", + (ena ? "ON" : "OFF"), ice_stat_str(status), + ice_aq_str(hw->adminq.sq_last_status)); + } else if (status) { + dev_err(dev, "can't set link to %s, err %s aq_err %s\n", + (ena ? "ON" : "OFF"), ice_stat_str(status), + ice_aq_str(hw->adminq.sq_last_status)); + return -EIO; + } + + return 0; +} diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index 3da17895a2b1..511c2316c40c 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -45,6 +45,8 @@ int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena, bool vlan_promisc); void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create); +int ice_set_link(struct ice_vsi *vsi, bool ena); + #ifdef CONFIG_DCB int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc); #endif /* CONFIG_DCB */ @@ -83,7 +85,7 @@ void ice_vsi_free_rx_rings(struct ice_vsi *vsi); void ice_vsi_free_tx_rings(struct ice_vsi *vsi); -int ice_vsi_manage_rss_lut(struct ice_vsi *vsi, bool ena); +void ice_vsi_manage_rss_lut(struct ice_vsi *vsi, bool ena); void ice_update_tx_ring_stats(struct ice_ring *ring, u64 pkts, u64 bytes); @@ -93,7 +95,8 @@ void ice_vsi_cfg_frame_size(struct ice_vsi *vsi); int ice_status_to_errno(enum ice_status err); -u32 ice_intrl_usec_to_reg(u8 intrl, u8 gran); +void ice_write_intrl(struct ice_q_vector *q_vector, u8 intrl); +void ice_write_itr(struct ice_ring_container *rc, u16 itr); enum ice_status ice_vsi_cfg_mac_fltr(struct ice_vsi *vsi, const u8 *macaddr, bool set); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index d821c687f239..4ee85a217c6f 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -84,7 +84,7 @@ static void ice_check_for_hang_subtask(struct ice_pf *pf) break; } - if (!vsi || test_bit(__ICE_DOWN, vsi->state)) + if (!vsi || test_bit(ICE_VSI_DOWN, vsi->state)) return; if (!(vsi->netdev && netif_carrier_ok(vsi->netdev))) @@ -140,21 +140,10 @@ static int ice_init_mac_fltr(struct ice_pf *pf) perm_addr = vsi->port_info->mac.perm_addr; status = ice_fltr_add_mac_and_broadcast(vsi, perm_addr, ICE_FWD_TO_VSI); - if (!status) - return 0; - - /* We aren't useful with no MAC filters, so unregister if we - * had an error - */ - if (vsi->netdev->reg_state == NETREG_REGISTERED) { - dev_err(ice_pf_to_dev(pf), "Could not add MAC filters error %s. Unregistering device\n", - ice_stat_str(status)); - unregister_netdev(vsi->netdev); - free_netdev(vsi->netdev); - vsi->netdev = NULL; - } + if (status) + return -EIO; - return -EIO; + return 0; } /** @@ -209,9 +198,9 @@ static int ice_add_mac_to_unsync_list(struct net_device *netdev, const u8 *addr) */ static bool ice_vsi_fltr_changed(struct ice_vsi *vsi) { - return test_bit(ICE_VSI_FLAG_UMAC_FLTR_CHANGED, vsi->flags) || - test_bit(ICE_VSI_FLAG_MMAC_FLTR_CHANGED, vsi->flags) || - test_bit(ICE_VSI_FLAG_VLAN_FLTR_CHANGED, vsi->flags); + return test_bit(ICE_VSI_UMAC_FLTR_CHANGED, vsi->state) || + test_bit(ICE_VSI_MMAC_FLTR_CHANGED, vsi->state) || + test_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); } /** @@ -268,7 +257,7 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) if (!vsi->netdev) return -EINVAL; - while (test_and_set_bit(__ICE_CFG_BUSY, vsi->state)) + while (test_and_set_bit(ICE_CFG_BUSY, vsi->state)) usleep_range(1000, 2000); changed_flags = vsi->current_netdev_flags ^ vsi->netdev->flags; @@ -278,9 +267,9 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) INIT_LIST_HEAD(&vsi->tmp_unsync_list); if (ice_vsi_fltr_changed(vsi)) { - clear_bit(ICE_VSI_FLAG_UMAC_FLTR_CHANGED, vsi->flags); - clear_bit(ICE_VSI_FLAG_MMAC_FLTR_CHANGED, vsi->flags); - clear_bit(ICE_VSI_FLAG_VLAN_FLTR_CHANGED, vsi->flags); + clear_bit(ICE_VSI_UMAC_FLTR_CHANGED, vsi->state); + clear_bit(ICE_VSI_MMAC_FLTR_CHANGED, vsi->state); + clear_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); /* grab the netdev's addr_list_lock */ netif_addr_lock_bh(netdev); @@ -318,7 +307,7 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) * space reserved for promiscuous filters. */ if (hw->adminq.sq_last_status == ICE_AQ_RC_ENOSPC && - !test_and_set_bit(__ICE_FLTR_OVERFLOW_PROMISC, + !test_and_set_bit(ICE_FLTR_OVERFLOW_PROMISC, vsi->state)) { promisc_forced_on = true; netdev_warn(netdev, "Reached MAC filter limit, forcing promisc mode on VSI %d\n", @@ -361,8 +350,8 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) } if (((changed_flags & IFF_PROMISC) || promisc_forced_on) || - test_bit(ICE_VSI_FLAG_PROMISC_CHANGED, vsi->flags)) { - clear_bit(ICE_VSI_FLAG_PROMISC_CHANGED, vsi->flags); + test_bit(ICE_VSI_PROMISC_CHANGED, vsi->state)) { + clear_bit(ICE_VSI_PROMISC_CHANGED, vsi->state); if (vsi->current_netdev_flags & IFF_PROMISC) { /* Apply Rx filter rule to get traffic from wire */ if (!ice_is_dflt_vsi_in_use(pf->first_sw)) { @@ -395,14 +384,14 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) goto exit; out_promisc: - set_bit(ICE_VSI_FLAG_PROMISC_CHANGED, vsi->flags); + set_bit(ICE_VSI_PROMISC_CHANGED, vsi->state); goto exit; out: /* if something went wrong then set the changed flag so we try again */ - set_bit(ICE_VSI_FLAG_UMAC_FLTR_CHANGED, vsi->flags); - set_bit(ICE_VSI_FLAG_MMAC_FLTR_CHANGED, vsi->flags); + set_bit(ICE_VSI_UMAC_FLTR_CHANGED, vsi->state); + set_bit(ICE_VSI_MMAC_FLTR_CHANGED, vsi->state); exit: - clear_bit(__ICE_CFG_BUSY, vsi->state); + clear_bit(ICE_CFG_BUSY, vsi->state); return err; } @@ -447,7 +436,6 @@ static void ice_pf_dis_all_vsi(struct ice_pf *pf, bool locked) for (node = 0; node < ICE_MAX_VF_AGG_NODES; node++) pf->vf_agg_node[node].num_vsis = 0; - } /** @@ -463,7 +451,7 @@ ice_prepare_for_reset(struct ice_pf *pf) unsigned int i; /* already prepared for reset */ - if (test_bit(__ICE_PREPARED_FOR_RESET, pf->state)) + if (test_bit(ICE_PREPARED_FOR_RESET, pf->state)) return; /* Notify VFs of impending reset */ @@ -484,7 +472,7 @@ ice_prepare_for_reset(struct ice_pf *pf) ice_shutdown_all_ctrlq(hw); - set_bit(__ICE_PREPARED_FOR_RESET, pf->state); + set_bit(ICE_PREPARED_FOR_RESET, pf->state); } /** @@ -505,12 +493,12 @@ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type) /* trigger the reset */ if (ice_reset(hw, reset_type)) { dev_err(dev, "reset %d failed\n", reset_type); - set_bit(__ICE_RESET_FAILED, pf->state); - clear_bit(__ICE_RESET_OICR_RECV, pf->state); - clear_bit(__ICE_PREPARED_FOR_RESET, pf->state); - clear_bit(__ICE_PFR_REQ, pf->state); - clear_bit(__ICE_CORER_REQ, pf->state); - clear_bit(__ICE_GLOBR_REQ, pf->state); + set_bit(ICE_RESET_FAILED, pf->state); + clear_bit(ICE_RESET_OICR_RECV, pf->state); + clear_bit(ICE_PREPARED_FOR_RESET, pf->state); + clear_bit(ICE_PFR_REQ, pf->state); + clear_bit(ICE_CORER_REQ, pf->state); + clear_bit(ICE_GLOBR_REQ, pf->state); return; } @@ -521,8 +509,8 @@ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type) if (reset_type == ICE_RESET_PFR) { pf->pfr_count++; ice_rebuild(pf, reset_type); - clear_bit(__ICE_PREPARED_FOR_RESET, pf->state); - clear_bit(__ICE_PFR_REQ, pf->state); + clear_bit(ICE_PREPARED_FOR_RESET, pf->state); + clear_bit(ICE_PFR_REQ, pf->state); ice_reset_all_vfs(pf, true); } } @@ -538,20 +526,20 @@ static void ice_reset_subtask(struct ice_pf *pf) /* When a CORER/GLOBR/EMPR is about to happen, the hardware triggers an * OICR interrupt. The OICR handler (ice_misc_intr) determines what type * of reset is pending and sets bits in pf->state indicating the reset - * type and __ICE_RESET_OICR_RECV. So, if the latter bit is set + * type and ICE_RESET_OICR_RECV. So, if the latter bit is set * prepare for pending reset if not already (for PF software-initiated * global resets the software should already be prepared for it as - * indicated by __ICE_PREPARED_FOR_RESET; for global resets initiated + * indicated by ICE_PREPARED_FOR_RESET; for global resets initiated * by firmware or software on other PFs, that bit is not set so prepare * for the reset now), poll for reset done, rebuild and return. */ - if (test_bit(__ICE_RESET_OICR_RECV, pf->state)) { + if (test_bit(ICE_RESET_OICR_RECV, pf->state)) { /* Perform the largest reset requested */ - if (test_and_clear_bit(__ICE_CORER_RECV, pf->state)) + if (test_and_clear_bit(ICE_CORER_RECV, pf->state)) reset_type = ICE_RESET_CORER; - if (test_and_clear_bit(__ICE_GLOBR_RECV, pf->state)) + if (test_and_clear_bit(ICE_GLOBR_RECV, pf->state)) reset_type = ICE_RESET_GLOBR; - if (test_and_clear_bit(__ICE_EMPR_RECV, pf->state)) + if (test_and_clear_bit(ICE_EMPR_RECV, pf->state)) reset_type = ICE_RESET_EMPR; /* return if no valid reset type requested */ if (reset_type == ICE_RESET_INVAL) @@ -560,7 +548,7 @@ static void ice_reset_subtask(struct ice_pf *pf) /* make sure we are ready to rebuild */ if (ice_check_reset(&pf->hw)) { - set_bit(__ICE_RESET_FAILED, pf->state); + set_bit(ICE_RESET_FAILED, pf->state); } else { /* done with reset. start rebuild */ pf->hw.reset_ongoing = false; @@ -568,11 +556,11 @@ static void ice_reset_subtask(struct ice_pf *pf) /* clear bit to resume normal operations, but * ICE_NEEDS_RESTART bit is set in case rebuild failed */ - clear_bit(__ICE_RESET_OICR_RECV, pf->state); - clear_bit(__ICE_PREPARED_FOR_RESET, pf->state); - clear_bit(__ICE_PFR_REQ, pf->state); - clear_bit(__ICE_CORER_REQ, pf->state); - clear_bit(__ICE_GLOBR_REQ, pf->state); + clear_bit(ICE_RESET_OICR_RECV, pf->state); + clear_bit(ICE_PREPARED_FOR_RESET, pf->state); + clear_bit(ICE_PFR_REQ, pf->state); + clear_bit(ICE_CORER_REQ, pf->state); + clear_bit(ICE_GLOBR_REQ, pf->state); ice_reset_all_vfs(pf, true); } @@ -580,19 +568,19 @@ static void ice_reset_subtask(struct ice_pf *pf) } /* No pending resets to finish processing. Check for new resets */ - if (test_bit(__ICE_PFR_REQ, pf->state)) + if (test_bit(ICE_PFR_REQ, pf->state)) reset_type = ICE_RESET_PFR; - if (test_bit(__ICE_CORER_REQ, pf->state)) + if (test_bit(ICE_CORER_REQ, pf->state)) reset_type = ICE_RESET_CORER; - if (test_bit(__ICE_GLOBR_REQ, pf->state)) + if (test_bit(ICE_GLOBR_REQ, pf->state)) reset_type = ICE_RESET_GLOBR; /* If no valid reset type requested just return */ if (reset_type == ICE_RESET_INVAL) return; /* reset if not already down or busy */ - if (!test_bit(__ICE_DOWN, pf->state) && - !test_bit(__ICE_CFG_BUSY, pf->state)) { + if (!test_bit(ICE_DOWN, pf->state) && + !test_bit(ICE_CFG_BUSY, pf->state)) { ice_do_reset(pf, reset_type); } } @@ -609,7 +597,7 @@ static void ice_print_topo_conflict(struct ice_vsi *vsi) case ICE_AQ_LINK_TOPO_UNREACH_PRT: case ICE_AQ_LINK_TOPO_UNDRUTIL_PRT: case ICE_AQ_LINK_TOPO_UNDRUTIL_MEDIA: - netdev_info(vsi->netdev, "Possible mis-configuration of the Ethernet port detected, please use the Intel(R) Ethernet Port Configuration Tool application to address the issue.\n"); + netdev_info(vsi->netdev, "Potential misconfiguration of the Ethernet port detected. If it was not intended, please use the Intel (R) Ethernet Port Configuration Tool to address the issue.\n"); break; case ICE_AQ_LINK_TOPO_UNSUPP_MEDIA: netdev_info(vsi->netdev, "Rx/Tx is disabled on this device because an unsupported module type was detected. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for a list of supported modules.\n"); @@ -731,7 +719,7 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup) } status = ice_aq_get_phy_caps(vsi->port_info, false, - ICE_AQC_REPORT_SW_CFG, caps, NULL); + ICE_AQC_REPORT_ACTIVE_CFG, caps, NULL); if (status) netdev_info(vsi->netdev, "Get phy capability failed.\n"); @@ -764,7 +752,7 @@ static void ice_vsi_link_event(struct ice_vsi *vsi, bool link_up) if (!vsi) return; - if (test_bit(__ICE_DOWN, vsi->state) || !vsi->netdev) + if (test_bit(ICE_VSI_DOWN, vsi->state) || !vsi->netdev) return; if (vsi->type == ICE_VSI_PF) { @@ -884,10 +872,10 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up, { struct device *dev = ice_pf_to_dev(pf); struct ice_phy_info *phy_info; + enum ice_status status; struct ice_vsi *vsi; u16 old_link_speed; bool old_link; - int result; phy_info = &pi->phy; phy_info->link_info_old = phy_info->link_info; @@ -898,10 +886,11 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up, /* update the link info structures and re-enable link events, * don't bail on failure due to other book keeping needed */ - result = ice_update_link_info(pi); - if (result) - dev_dbg(dev, "Failed to update link status and re-enable link events for port %d\n", - pi->lport); + status = ice_update_link_info(pi); + if (status) + dev_dbg(dev, "Failed to update link status on port %d, err %s aq_err %s\n", + pi->lport, ice_stat_str(status), + ice_aq_str(pi->hw->adminq.sq_last_status)); /* Check if the link state is up after updating link info, and treat * this event as an UP event since the link is actually UP now. @@ -917,18 +906,12 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up, if (!test_bit(ICE_FLAG_NO_MEDIA, pf->flags) && !(pi->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE)) { set_bit(ICE_FLAG_NO_MEDIA, pf->flags); - - result = ice_aq_set_link_restart_an(pi, false, NULL); - if (result) { - dev_dbg(dev, "Failed to set link down, VSI %d error %d\n", - vsi->vsi_num, result); - return result; - } + ice_set_link(vsi, false); } /* if the old link up/down and speed is the same as the new */ if (link_up == old_link && link_speed == old_link_speed) - return result; + return 0; if (ice_is_dcb_active(pf)) { if (test_bit(ICE_FLAG_DCB_ENA, pf->flags)) @@ -942,7 +925,7 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up, ice_vc_notify_link_state(pf); - return result; + return 0; } /** @@ -954,8 +937,8 @@ static void ice_watchdog_subtask(struct ice_pf *pf) int i; /* if interface is down do nothing */ - if (test_bit(__ICE_DOWN, pf->state) || - test_bit(__ICE_CFG_BUSY, pf->state)) + if (test_bit(ICE_DOWN, pf->state) || + test_bit(ICE_CFG_BUSY, pf->state)) return; /* make sure we don't do these things too often */ @@ -1044,7 +1027,7 @@ struct ice_aq_task { }; /** - * ice_wait_for_aq_event - Wait for an AdminQ event from firmware + * ice_aq_wait_for_event - Wait for an AdminQ event from firmware * @pf: pointer to the PF private structure * @opcode: the opcode to wait for * @timeout: how long to wait, in jiffies @@ -1199,7 +1182,7 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) u32 oldval, val; /* Do not clean control queue if/when PF reset fails */ - if (test_bit(__ICE_RESET_FAILED, pf->state)) + if (test_bit(ICE_RESET_FAILED, pf->state)) return 0; switch (q_type) { @@ -1210,6 +1193,10 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) case ICE_CTL_Q_MAILBOX: cq = &hw->mailboxq; qtype = "Mailbox"; + /* we are going to try to detect a malicious VF, so set the + * state to begin detection + */ + hw->mbx_snapshot.mbx_buf.state = ICE_MAL_VF_DETECT_STATE_NEW_SNAPSHOT; break; default: dev_warn(dev, "Unknown control queue type 0x%x\n", q_type); @@ -1291,7 +1278,8 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) ice_vf_lan_overflow_event(pf, &event); break; case ice_mbx_opc_send_msg_to_pf: - ice_vc_process_vf_msg(pf, &event); + if (!ice_is_malicious_vf(pf, &event, i, pending)) + ice_vc_process_vf_msg(pf, &event); break; case ice_aqc_opc_fw_logging: ice_output_fw_log(hw, &event.desc, event.msg_buf); @@ -1334,13 +1322,13 @@ static void ice_clean_adminq_subtask(struct ice_pf *pf) { struct ice_hw *hw = &pf->hw; - if (!test_bit(__ICE_ADMINQ_EVENT_PENDING, pf->state)) + if (!test_bit(ICE_ADMINQ_EVENT_PENDING, pf->state)) return; if (__ice_clean_ctrlq(pf, ICE_CTL_Q_ADMIN)) return; - clear_bit(__ICE_ADMINQ_EVENT_PENDING, pf->state); + clear_bit(ICE_ADMINQ_EVENT_PENDING, pf->state); /* There might be a situation where new messages arrive to a control * queue between processing the last message and clearing the @@ -1361,13 +1349,13 @@ static void ice_clean_mailboxq_subtask(struct ice_pf *pf) { struct ice_hw *hw = &pf->hw; - if (!test_bit(__ICE_MAILBOXQ_EVENT_PENDING, pf->state)) + if (!test_bit(ICE_MAILBOXQ_EVENT_PENDING, pf->state)) return; if (__ice_clean_ctrlq(pf, ICE_CTL_Q_MAILBOX)) return; - clear_bit(__ICE_MAILBOXQ_EVENT_PENDING, pf->state); + clear_bit(ICE_MAILBOXQ_EVENT_PENDING, pf->state); if (ice_ctrlq_pending(hw, &hw->mailboxq)) __ice_clean_ctrlq(pf, ICE_CTL_Q_MAILBOX); @@ -1383,9 +1371,9 @@ static void ice_clean_mailboxq_subtask(struct ice_pf *pf) */ void ice_service_task_schedule(struct ice_pf *pf) { - if (!test_bit(__ICE_SERVICE_DIS, pf->state) && - !test_and_set_bit(__ICE_SERVICE_SCHED, pf->state) && - !test_bit(__ICE_NEEDS_RESTART, pf->state)) + if (!test_bit(ICE_SERVICE_DIS, pf->state) && + !test_and_set_bit(ICE_SERVICE_SCHED, pf->state) && + !test_bit(ICE_NEEDS_RESTART, pf->state)) queue_work(ice_wq, &pf->serv_task); } @@ -1395,32 +1383,32 @@ void ice_service_task_schedule(struct ice_pf *pf) */ static void ice_service_task_complete(struct ice_pf *pf) { - WARN_ON(!test_bit(__ICE_SERVICE_SCHED, pf->state)); + WARN_ON(!test_bit(ICE_SERVICE_SCHED, pf->state)); /* force memory (pf->state) to sync before next service task */ smp_mb__before_atomic(); - clear_bit(__ICE_SERVICE_SCHED, pf->state); + clear_bit(ICE_SERVICE_SCHED, pf->state); } /** * ice_service_task_stop - stop service task and cancel works * @pf: board private structure * - * Return 0 if the __ICE_SERVICE_DIS bit was not already set, + * Return 0 if the ICE_SERVICE_DIS bit was not already set, * 1 otherwise. */ static int ice_service_task_stop(struct ice_pf *pf) { int ret; - ret = test_and_set_bit(__ICE_SERVICE_DIS, pf->state); + ret = test_and_set_bit(ICE_SERVICE_DIS, pf->state); if (pf->serv_tmr.function) del_timer_sync(&pf->serv_tmr); if (pf->serv_task.func) cancel_work_sync(&pf->serv_task); - clear_bit(__ICE_SERVICE_SCHED, pf->state); + clear_bit(ICE_SERVICE_SCHED, pf->state); return ret; } @@ -1432,7 +1420,7 @@ static int ice_service_task_stop(struct ice_pf *pf) */ static void ice_service_task_restart(struct ice_pf *pf) { - clear_bit(__ICE_SERVICE_DIS, pf->state); + clear_bit(ICE_SERVICE_DIS, pf->state); ice_service_task_schedule(pf); } @@ -1465,7 +1453,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf) unsigned int i; u32 reg; - if (!test_and_clear_bit(__ICE_MDD_EVENT_PENDING, pf->state)) { + if (!test_and_clear_bit(ICE_MDD_EVENT_PENDING, pf->state)) { /* Since the VF MDD event logging is rate limited, check if * there are pending MDD events. */ @@ -1557,7 +1545,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf) if (reg & VP_MDET_TX_PQM_VALID_M) { wr32(hw, VP_MDET_TX_PQM(i), 0xFFFF); vf->mdd_tx_events.count++; - set_bit(__ICE_MDD_VF_PRINT_PENDING, pf->state); + set_bit(ICE_MDD_VF_PRINT_PENDING, pf->state); if (netif_msg_tx_err(pf)) dev_info(dev, "Malicious Driver Detection event TX_PQM detected on VF %d\n", i); @@ -1567,7 +1555,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf) if (reg & VP_MDET_TX_TCLAN_VALID_M) { wr32(hw, VP_MDET_TX_TCLAN(i), 0xFFFF); vf->mdd_tx_events.count++; - set_bit(__ICE_MDD_VF_PRINT_PENDING, pf->state); + set_bit(ICE_MDD_VF_PRINT_PENDING, pf->state); if (netif_msg_tx_err(pf)) dev_info(dev, "Malicious Driver Detection event TX_TCLAN detected on VF %d\n", i); @@ -1577,7 +1565,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf) if (reg & VP_MDET_TX_TDPU_VALID_M) { wr32(hw, VP_MDET_TX_TDPU(i), 0xFFFF); vf->mdd_tx_events.count++; - set_bit(__ICE_MDD_VF_PRINT_PENDING, pf->state); + set_bit(ICE_MDD_VF_PRINT_PENDING, pf->state); if (netif_msg_tx_err(pf)) dev_info(dev, "Malicious Driver Detection event TX_TDPU detected on VF %d\n", i); @@ -1587,7 +1575,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf) if (reg & VP_MDET_RX_VALID_M) { wr32(hw, VP_MDET_RX(i), 0xFFFF); vf->mdd_rx_events.count++; - set_bit(__ICE_MDD_VF_PRINT_PENDING, pf->state); + set_bit(ICE_MDD_VF_PRINT_PENDING, pf->state); if (netif_msg_rx_err(pf)) dev_info(dev, "Malicious Driver Detection event RX detected on VF %d\n", i); @@ -1642,7 +1630,7 @@ static int ice_force_phys_link_state(struct ice_vsi *vsi, bool link_up) if (!pcaps) return -ENOMEM; - retcode = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG, pcaps, + retcode = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_ACTIVE_CFG, pcaps, NULL); if (retcode) { dev_err(dev, "Failed to get phy capabilities, VSI %d error %d\n", @@ -1702,7 +1690,7 @@ static int ice_init_nvm_phy_type(struct ice_port_info *pi) if (!pcaps) return -ENOMEM; - status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_NVM_CAP, pcaps, + status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP_NO_MEDIA, pcaps, NULL); if (status) { @@ -1748,15 +1736,18 @@ static void ice_init_link_dflt_override(struct ice_port_info *pi) * ice_init_phy_cfg_dflt_override - Initialize PHY cfg default override settings * @pi: port info structure * - * If default override is enabled, initialized the user PHY cfg speed and FEC + * If default override is enabled, initialize the user PHY cfg speed and FEC * settings using the default override mask from the NVM. * * The PHY should only be configured with the default override settings the - * first time media is available. The __ICE_LINK_DEFAULT_OVERRIDE_PENDING state + * first time media is available. The ICE_LINK_DEFAULT_OVERRIDE_PENDING state * is used to indicate that the user PHY cfg default override is initialized * and the PHY has not been configured with the default override settings. The * state is set here, and cleared in ice_configure_phy the first time the PHY is * configured. + * + * This function should be called only if the FW doesn't support default + * configuration mode, as reported by ice_fw_supports_report_dflt_cfg. */ static void ice_init_phy_cfg_dflt_override(struct ice_port_info *pi) { @@ -1781,7 +1772,7 @@ static void ice_init_phy_cfg_dflt_override(struct ice_port_info *pi) cfg->link_fec_opt = ldo->fec_options; phy->curr_user_fec_req = ICE_FEC_AUTO; - set_bit(__ICE_LINK_DEFAULT_OVERRIDE_PENDING, pf->state); + set_bit(ICE_LINK_DEFAULT_OVERRIDE_PENDING, pf->state); } /** @@ -1804,22 +1795,21 @@ static int ice_init_phy_user_cfg(struct ice_port_info *pi) struct ice_phy_info *phy = &pi->phy; struct ice_pf *pf = pi->hw->back; enum ice_status status; - struct ice_vsi *vsi; int err = 0; if (!(phy->link_info.link_info & ICE_AQ_MEDIA_AVAILABLE)) return -EIO; - vsi = ice_get_main_vsi(pf); - if (!vsi) - return -EINVAL; - pcaps = kzalloc(sizeof(*pcaps), GFP_KERNEL); if (!pcaps) return -ENOMEM; - status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP, pcaps, - NULL); + if (ice_fw_supports_report_dflt_cfg(pi->hw)) + status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_DFLT_CFG, + pcaps, NULL); + else + status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP_MEDIA, + pcaps, NULL); if (status) { dev_err(ice_pf_to_dev(pf), "Get PHY capability failed.\n"); err = -EIO; @@ -1829,22 +1819,24 @@ static int ice_init_phy_user_cfg(struct ice_port_info *pi) ice_copy_phy_caps_to_cfg(pi, pcaps, &pi->phy.curr_user_phy_cfg); /* check if lenient mode is supported and enabled */ - if (ice_fw_supports_link_override(&vsi->back->hw) && + if (ice_fw_supports_link_override(pi->hw) && !(pcaps->module_compliance_enforcement & ICE_AQC_MOD_ENFORCE_STRICT_MODE)) { set_bit(ICE_FLAG_LINK_LENIENT_MODE_ENA, pf->flags); - /* if link default override is enabled, initialize user PHY - * configuration with link default override values + /* if the FW supports default PHY configuration mode, then the driver + * does not have to apply link override settings. If not, + * initialize user PHY configuration with link override values */ - if (pf->link_dflt_override.options & ICE_LINK_OVERRIDE_EN) { + if (!ice_fw_supports_report_dflt_cfg(pi->hw) && + (pf->link_dflt_override.options & ICE_LINK_OVERRIDE_EN)) { ice_init_phy_cfg_dflt_override(pi); goto out; } } - /* if link default override is not enabled, initialize PHY using - * topology with media + /* if link default override is not enabled, set user flow control and + * FEC settings based on what get_phy_caps returned */ phy->curr_user_fec_req = ice_caps_to_fec_mode(pcaps->caps, pcaps->link_fec_options); @@ -1852,7 +1844,7 @@ static int ice_init_phy_user_cfg(struct ice_port_info *pi) out: phy->curr_user_speed_req = ICE_AQ_LINK_SPEED_M; - set_bit(__ICE_PHY_INIT_COMPLETE, pf->state); + set_bit(ICE_PHY_INIT_COMPLETE, pf->state); err_out: kfree(pcaps); return err; @@ -1869,27 +1861,24 @@ err_out: static int ice_configure_phy(struct ice_vsi *vsi) { struct device *dev = ice_pf_to_dev(vsi->back); + struct ice_port_info *pi = vsi->port_info; struct ice_aqc_get_phy_caps_data *pcaps; struct ice_aqc_set_phy_cfg_data *cfg; - struct ice_port_info *pi; + struct ice_phy_info *phy = &pi->phy; + struct ice_pf *pf = vsi->back; enum ice_status status; int err = 0; - pi = vsi->port_info; - if (!pi) - return -EINVAL; - /* Ensure we have media as we cannot configure a medialess port */ - if (!(pi->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE)) + if (!(phy->link_info.link_info & ICE_AQ_MEDIA_AVAILABLE)) return -EPERM; ice_print_topo_conflict(vsi); - if (vsi->port_info->phy.link_info.topo_media_conflict == - ICE_AQ_LINK_TOPO_UNSUPP_MEDIA) + if (phy->link_info.topo_media_conflict == ICE_AQ_LINK_TOPO_UNSUPP_MEDIA) return -EPERM; - if (test_bit(ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, vsi->back->flags)) + if (test_bit(ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, pf->flags)) return ice_force_phys_link_state(vsi, true); pcaps = kzalloc(sizeof(*pcaps), GFP_KERNEL); @@ -1897,7 +1886,7 @@ static int ice_configure_phy(struct ice_vsi *vsi) return -ENOMEM; /* Get current PHY config */ - status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG, pcaps, + status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_ACTIVE_CFG, pcaps, NULL); if (status) { dev_err(dev, "Failed to get PHY configuration, VSI %d error %s\n", @@ -1910,15 +1899,19 @@ static int ice_configure_phy(struct ice_vsi *vsi) * there's nothing to do */ if (pcaps->caps & ICE_AQC_PHY_EN_LINK && - ice_phy_caps_equals_cfg(pcaps, &pi->phy.curr_user_phy_cfg)) + ice_phy_caps_equals_cfg(pcaps, &phy->curr_user_phy_cfg)) goto done; /* Use PHY topology as baseline for configuration */ memset(pcaps, 0, sizeof(*pcaps)); - status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP, pcaps, - NULL); + if (ice_fw_supports_report_dflt_cfg(pi->hw)) + status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_DFLT_CFG, + pcaps, NULL); + else + status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP_MEDIA, + pcaps, NULL); if (status) { - dev_err(dev, "Failed to get PHY topology, VSI %d error %s\n", + dev_err(dev, "Failed to get PHY caps, VSI %d error %s\n", vsi->vsi_num, ice_stat_str(status)); err = -EIO; goto done; @@ -1935,10 +1928,10 @@ static int ice_configure_phy(struct ice_vsi *vsi) /* Speed - If default override pending, use curr_user_phy_cfg set in * ice_init_phy_user_cfg_ldo. */ - if (test_and_clear_bit(__ICE_LINK_DEFAULT_OVERRIDE_PENDING, + if (test_and_clear_bit(ICE_LINK_DEFAULT_OVERRIDE_PENDING, vsi->back->state)) { - cfg->phy_type_low = pi->phy.curr_user_phy_cfg.phy_type_low; - cfg->phy_type_high = pi->phy.curr_user_phy_cfg.phy_type_high; + cfg->phy_type_low = phy->curr_user_phy_cfg.phy_type_low; + cfg->phy_type_high = phy->curr_user_phy_cfg.phy_type_high; } else { u64 phy_low = 0, phy_high = 0; @@ -1956,7 +1949,7 @@ static int ice_configure_phy(struct ice_vsi *vsi) } /* FEC */ - ice_cfg_phy_fec(pi, cfg, pi->phy.curr_user_fec_req); + ice_cfg_phy_fec(pi, cfg, phy->curr_user_fec_req); /* Can't provide what was requested; use PHY capabilities */ if (cfg->link_fec_opt != @@ -1968,12 +1961,12 @@ static int ice_configure_phy(struct ice_vsi *vsi) /* Flow Control - always supported; no need to check against * capabilities */ - ice_cfg_phy_fc(pi, cfg, pi->phy.curr_user_fc_req); + ice_cfg_phy_fc(pi, cfg, phy->curr_user_fc_req); /* Enable link and link update */ cfg->caps |= ICE_AQ_PHY_ENA_AUTO_LINK_UPDT | ICE_AQ_PHY_ENA_LINK; - status = ice_aq_set_phy_cfg(&vsi->back->hw, pi, cfg, NULL); + status = ice_aq_set_phy_cfg(&pf->hw, pi, cfg, NULL); if (status) { dev_err(dev, "Failed to set phy config, VSI %d error %s\n", vsi->vsi_num, ice_stat_str(status)); @@ -2014,13 +2007,13 @@ static void ice_check_media_subtask(struct ice_pf *pf) return; if (pi->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE) { - if (!test_bit(__ICE_PHY_INIT_COMPLETE, pf->state)) + if (!test_bit(ICE_PHY_INIT_COMPLETE, pf->state)) ice_init_phy_user_cfg(pi); /* PHY settings are reset on media insertion, reconfigure * PHY to preserve settings. */ - if (test_bit(__ICE_DOWN, vsi->state) && + if (test_bit(ICE_VSI_DOWN, vsi->state) && test_bit(ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, vsi->back->flags)) return; @@ -2050,8 +2043,8 @@ static void ice_service_task(struct work_struct *work) /* bail if a reset/recovery cycle is pending or rebuild failed */ if (ice_is_reset_in_progress(pf->state) || - test_bit(__ICE_SUSPENDED, pf->state) || - test_bit(__ICE_NEEDS_RESTART, pf->state)) { + test_bit(ICE_SUSPENDED, pf->state) || + test_bit(ICE_NEEDS_RESTART, pf->state)) { ice_service_task_complete(pf); return; } @@ -2071,7 +2064,9 @@ static void ice_service_task(struct work_struct *work) ice_process_vflr_event(pf); ice_clean_mailboxq_subtask(pf); ice_sync_arfs_fltrs(pf); - /* Clear __ICE_SERVICE_SCHED flag to allow scheduling next event */ + ice_flush_fdir_ctx(pf); + + /* Clear ICE_SERVICE_SCHED flag to allow scheduling next event */ ice_service_task_complete(pf); /* If the tasks have taken longer than one service timer period @@ -2079,10 +2074,11 @@ static void ice_service_task(struct work_struct *work) * schedule the service task now. */ if (time_after(jiffies, (start_time + pf->serv_tmr_period)) || - test_bit(__ICE_MDD_EVENT_PENDING, pf->state) || - test_bit(__ICE_VFLR_EVENT_PENDING, pf->state) || - test_bit(__ICE_MAILBOXQ_EVENT_PENDING, pf->state) || - test_bit(__ICE_ADMINQ_EVENT_PENDING, pf->state)) + test_bit(ICE_MDD_EVENT_PENDING, pf->state) || + test_bit(ICE_VFLR_EVENT_PENDING, pf->state) || + test_bit(ICE_MAILBOXQ_EVENT_PENDING, pf->state) || + test_bit(ICE_FD_VF_FLUSH_CTX, pf->state) || + test_bit(ICE_ADMINQ_EVENT_PENDING, pf->state)) mod_timer(&pf->serv_tmr, jiffies); } @@ -2112,7 +2108,7 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset) struct device *dev = ice_pf_to_dev(pf); /* bail out if earlier reset has failed */ - if (test_bit(__ICE_RESET_FAILED, pf->state)) { + if (test_bit(ICE_RESET_FAILED, pf->state)) { dev_dbg(dev, "earlier reset has failed\n"); return -EIO; } @@ -2124,13 +2120,13 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset) switch (reset) { case ICE_RESET_PFR: - set_bit(__ICE_PFR_REQ, pf->state); + set_bit(ICE_PFR_REQ, pf->state); break; case ICE_RESET_CORER: - set_bit(__ICE_CORER_REQ, pf->state); + set_bit(ICE_CORER_REQ, pf->state); break; case ICE_RESET_GLOBR: - set_bit(__ICE_GLOBR_REQ, pf->state); + set_bit(ICE_GLOBR_REQ, pf->state); break; default: return -EINVAL; @@ -2220,8 +2216,13 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) /* skip this unused q_vector */ continue; } - err = devm_request_irq(dev, irq_num, vsi->irq_handler, 0, - q_vector->name, q_vector); + if (vsi->type == ICE_VSI_CTRL && vsi->vf_id != ICE_INVAL_VFID) + err = devm_request_irq(dev, irq_num, vsi->irq_handler, + IRQF_SHARED, q_vector->name, + q_vector); + else + err = devm_request_irq(dev, irq_num, vsi->irq_handler, + 0, q_vector->name, q_vector); if (err) { netdev_err(vsi->netdev, "MSIX request_irq failed, error: %d\n", err); @@ -2524,7 +2525,7 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, } /* need to stop netdev while setting up the program for Rx rings */ - if (if_running && !test_and_set_bit(__ICE_DOWN, vsi->state)) { + if (if_running && !test_and_set_bit(ICE_VSI_DOWN, vsi->state)) { ret = ice_down(vsi); if (ret) { NL_SET_ERR_MSG_MOD(extack, "Preparing device for XDP attach failed"); @@ -2630,8 +2631,8 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) u32 oicr, ena_mask; dev = ice_pf_to_dev(pf); - set_bit(__ICE_ADMINQ_EVENT_PENDING, pf->state); - set_bit(__ICE_MAILBOXQ_EVENT_PENDING, pf->state); + set_bit(ICE_ADMINQ_EVENT_PENDING, pf->state); + set_bit(ICE_MAILBOXQ_EVENT_PENDING, pf->state); oicr = rd32(hw, PFINT_OICR); ena_mask = rd32(hw, PFINT_OICR_ENA); @@ -2643,18 +2644,18 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) if (oicr & PFINT_OICR_MAL_DETECT_M) { ena_mask &= ~PFINT_OICR_MAL_DETECT_M; - set_bit(__ICE_MDD_EVENT_PENDING, pf->state); + set_bit(ICE_MDD_EVENT_PENDING, pf->state); } if (oicr & PFINT_OICR_VFLR_M) { /* disable any further VFLR event notifications */ - if (test_bit(__ICE_VF_RESETS_DISABLED, pf->state)) { + if (test_bit(ICE_VF_RESETS_DISABLED, pf->state)) { u32 reg = rd32(hw, PFINT_OICR_ENA); reg &= ~PFINT_OICR_VFLR_M; wr32(hw, PFINT_OICR_ENA, reg); } else { ena_mask &= ~PFINT_OICR_VFLR_M; - set_bit(__ICE_VFLR_EVENT_PENDING, pf->state); + set_bit(ICE_VFLR_EVENT_PENDING, pf->state); } } @@ -2680,13 +2681,13 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) * We also make note of which reset happened so that peer * devices/drivers can be informed. */ - if (!test_and_set_bit(__ICE_RESET_OICR_RECV, pf->state)) { + if (!test_and_set_bit(ICE_RESET_OICR_RECV, pf->state)) { if (reset == ICE_RESET_CORER) - set_bit(__ICE_CORER_RECV, pf->state); + set_bit(ICE_CORER_RECV, pf->state); else if (reset == ICE_RESET_GLOBR) - set_bit(__ICE_GLOBR_RECV, pf->state); + set_bit(ICE_GLOBR_RECV, pf->state); else - set_bit(__ICE_EMPR_RECV, pf->state); + set_bit(ICE_EMPR_RECV, pf->state); /* There are couple of different bits at play here. * hw->reset_ongoing indicates whether the hardware is @@ -2694,7 +2695,7 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) * is received and set back to false after the driver * has determined that the hardware is out of reset. * - * __ICE_RESET_OICR_RECV in pf->state indicates + * ICE_RESET_OICR_RECV in pf->state indicates * that a post reset rebuild is required before the * driver is operational again. This is set above. * @@ -2722,7 +2723,7 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) if (oicr & (PFINT_OICR_PE_CRITERR_M | PFINT_OICR_PCI_EXCEPTION_M | PFINT_OICR_ECC_ERR_M)) { - set_bit(__ICE_PFR_REQ, pf->state); + set_bit(ICE_PFR_REQ, pf->state); ice_service_task_schedule(pf); } } @@ -2975,19 +2976,13 @@ static int ice_cfg_netdev(struct ice_vsi *vsi) struct ice_netdev_priv *np; struct net_device *netdev; u8 mac_addr[ETH_ALEN]; - int err; - - err = ice_devlink_create_port(vsi); - if (err) - return err; netdev = alloc_etherdev_mqs(sizeof(*np), vsi->alloc_txq, vsi->alloc_rxq); - if (!netdev) { - err = -ENOMEM; - goto err_destroy_devlink_port; - } + if (!netdev) + return -ENOMEM; + set_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); vsi->netdev = netdev; np = netdev_priv(netdev); np->vsi = vsi; @@ -3014,25 +3009,7 @@ static int ice_cfg_netdev(struct ice_vsi *vsi) netdev->min_mtu = ETH_MIN_MTU; netdev->max_mtu = ICE_MAX_MTU; - err = register_netdev(vsi->netdev); - if (err) - goto err_free_netdev; - - devlink_port_type_eth_set(&vsi->devlink_port, vsi->netdev); - - netif_carrier_off(vsi->netdev); - - /* make sure transmit queues start off as stopped */ - netif_tx_stop_all_queues(vsi->netdev); - return 0; - -err_free_netdev: - free_netdev(vsi->netdev); - vsi->netdev = NULL; -err_destroy_devlink_port: - ice_devlink_destroy_port(vsi); - return err; } /** @@ -3107,15 +3084,6 @@ ice_vlan_rx_add_vid(struct net_device *netdev, __always_unused __be16 proto, struct ice_vsi *vsi = np->vsi; int ret; - if (vid >= VLAN_N_VID) { - netdev_err(netdev, "VLAN id requested %d is out of range %d\n", - vid, VLAN_N_VID); - return -EINVAL; - } - - if (vsi->info.pvid) - return -EINVAL; - /* VLAN 0 is added by default during load/reset */ if (!vid) return 0; @@ -3132,7 +3100,7 @@ ice_vlan_rx_add_vid(struct net_device *netdev, __always_unused __be16 proto, */ ret = ice_vsi_add_vlan(vsi, vid, ICE_FWD_TO_VSI); if (!ret) - set_bit(ICE_VSI_FLAG_VLAN_FLTR_CHANGED, vsi->flags); + set_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); return ret; } @@ -3153,9 +3121,6 @@ ice_vlan_rx_kill_vid(struct net_device *netdev, __always_unused __be16 proto, struct ice_vsi *vsi = np->vsi; int ret; - if (vsi->info.pvid) - return -EINVAL; - /* don't allow removal of VLAN 0 */ if (!vid) return 0; @@ -3171,7 +3136,7 @@ ice_vlan_rx_kill_vid(struct net_device *netdev, __always_unused __be16 proto, if (vsi->num_vlan == 1 && ice_vsi_is_vlan_pruning_ena(vsi)) ret = ice_cfg_vlan_pruning(vsi, false, false); - set_bit(ICE_VSI_FLAG_VLAN_FLTR_CHANGED, vsi->flags); + set_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); return ret; } @@ -3230,8 +3195,7 @@ unroll_napi_add: if (vsi) { ice_napi_del(vsi); if (vsi->netdev) { - if (vsi->netdev->reg_state == NETREG_REGISTERED) - unregister_netdev(vsi->netdev); + clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); free_netdev(vsi->netdev); vsi->netdev = NULL; } @@ -3365,7 +3329,7 @@ static int ice_init_pf(struct ice_pf *pf) timer_setup(&pf->serv_tmr, ice_service_timer, 0); pf->serv_tmr_period = HZ; INIT_WORK(&pf->serv_task, ice_service_task); - clear_bit(__ICE_SERVICE_SCHED, pf->state); + clear_bit(ICE_SERVICE_SCHED, pf->state); mutex_init(&pf->avail_q_mutex); pf->avail_txqs = bitmap_zalloc(pf->max_pf_txqs, GFP_KERNEL); @@ -3574,7 +3538,7 @@ int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx) if (!new_rx && !new_tx) return -EINVAL; - while (test_and_set_bit(__ICE_CFG_BUSY, pf->state)) { + while (test_and_set_bit(ICE_CFG_BUSY, pf->state)) { timeout--; if (!timeout) return -EBUSY; @@ -3598,7 +3562,7 @@ int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx) ice_pf_dcb_recfg(pf); ice_vsi_open(vsi); done: - clear_bit(__ICE_CFG_BUSY, pf->state); + clear_bit(ICE_CFG_BUSY, pf->state); return err; } @@ -3985,6 +3949,43 @@ static void ice_print_wake_reason(struct ice_pf *pf) } /** + * ice_register_netdev - register netdev and devlink port + * @pf: pointer to the PF struct + */ +static int ice_register_netdev(struct ice_pf *pf) +{ + struct ice_vsi *vsi; + int err = 0; + + vsi = ice_get_main_vsi(pf); + if (!vsi || !vsi->netdev) + return -EIO; + + err = register_netdev(vsi->netdev); + if (err) + goto err_register_netdev; + + set_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state); + netif_carrier_off(vsi->netdev); + netif_tx_stop_all_queues(vsi->netdev); + err = ice_devlink_create_port(vsi); + if (err) + goto err_devlink_create; + + devlink_port_type_eth_set(&vsi->devlink_port, vsi->netdev); + + return 0; +err_devlink_create: + unregister_netdev(vsi->netdev); + clear_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state); +err_register_netdev: + free_netdev(vsi->netdev); + vsi->netdev = NULL; + clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); + return err; +} + +/** * ice_probe - Device initialization routine * @pdev: PCI device information struct * @ent: entry in ice_pci_tbl @@ -4006,7 +4007,7 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) if (err) return err; - err = pcim_iomap_regions(pdev, BIT(ICE_BAR0), pci_name(pdev)); + err = pcim_iomap_regions(pdev, BIT(ICE_BAR0), dev_driver_string(dev)); if (err) { dev_err(dev, "BAR0 I/O map error %d\n", err); return err; @@ -4030,9 +4031,9 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) pf->pdev = pdev; pci_set_drvdata(pdev, pf); - set_bit(__ICE_DOWN, pf->state); + set_bit(ICE_DOWN, pf->state); /* Disable service task until DOWN bit is cleared */ - set_bit(__ICE_SERVICE_DIS, pf->state); + set_bit(ICE_SERVICE_DIS, pf->state); hw = &pf->hw; hw->hw_addr = pcim_iomap_table(pdev)[ICE_BAR0]; @@ -4172,7 +4173,7 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) goto err_alloc_sw_unroll; } - clear_bit(__ICE_SERVICE_DIS, pf->state); + clear_bit(ICE_SERVICE_DIS, pf->state); /* tell the firmware we are up */ err = ice_send_version(pf); @@ -4261,15 +4262,20 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) pcie_print_link_status(pf->pdev); probe_done: + err = ice_register_netdev(pf); + if (err) + goto err_netdev_reg; + /* ready to go, so clear down state bit */ - clear_bit(__ICE_DOWN, pf->state); + clear_bit(ICE_DOWN, pf->state); return 0; +err_netdev_reg: err_send_version_unroll: ice_vsi_release_all(pf); err_alloc_sw_unroll: - set_bit(__ICE_SERVICE_DIS, pf->state); - set_bit(__ICE_DOWN, pf->state); + set_bit(ICE_SERVICE_DIS, pf->state); + set_bit(ICE_DOWN, pf->state); devm_kfree(dev, pf->first_sw); err_msix_misc_unroll: ice_free_irq_msix_misc(pf); @@ -4310,7 +4316,7 @@ static void ice_set_wake(struct ice_pf *pf) } /** - * ice_setup_magic_mc_wake - setup device to wake on multicast magic packet + * ice_setup_mc_magic_wake - setup device to wake on multicast magic packet * @pf: pointer to the PF struct * * Issue firmware command to enable multicast magic wake, making @@ -4369,11 +4375,11 @@ static void ice_remove(struct pci_dev *pdev) } if (test_bit(ICE_FLAG_SRIOV_ENA, pf->flags)) { - set_bit(__ICE_VF_RESETS_DISABLED, pf->state); + set_bit(ICE_VF_RESETS_DISABLED, pf->state); ice_free_vfs(pf); } - set_bit(__ICE_DOWN, pf->state); + set_bit(ICE_DOWN, pf->state); ice_service_task_stop(pf); ice_aq_cancel_waiting_tasks(pf); @@ -4533,13 +4539,13 @@ static int __maybe_unused ice_suspend(struct device *dev) disabled = ice_service_task_stop(pf); /* Already suspended?, then there is nothing to do */ - if (test_and_set_bit(__ICE_SUSPENDED, pf->state)) { + if (test_and_set_bit(ICE_SUSPENDED, pf->state)) { if (!disabled) ice_service_task_restart(pf); return 0; } - if (test_bit(__ICE_DOWN, pf->state) || + if (test_bit(ICE_DOWN, pf->state) || ice_is_reset_in_progress(pf->state)) { dev_err(dev, "can't suspend device in reset or already down\n"); if (!disabled) @@ -4611,16 +4617,16 @@ static int __maybe_unused ice_resume(struct device *dev) if (ret) dev_err(dev, "Cannot restore interrupt scheme: %d\n", ret); - clear_bit(__ICE_DOWN, pf->state); + clear_bit(ICE_DOWN, pf->state); /* Now perform PF reset and rebuild */ reset_type = ICE_RESET_PFR; /* re-enable service task for reset, but allow reset to schedule it */ - clear_bit(__ICE_SERVICE_DIS, pf->state); + clear_bit(ICE_SERVICE_DIS, pf->state); if (ice_schedule_reset(pf, reset_type)) dev_err(dev, "Reset during resume failed.\n"); - clear_bit(__ICE_SUSPENDED, pf->state); + clear_bit(ICE_SUSPENDED, pf->state); ice_service_task_restart(pf); /* Restart the service task */ @@ -4649,11 +4655,11 @@ ice_pci_err_detected(struct pci_dev *pdev, pci_channel_state_t err) return PCI_ERS_RESULT_DISCONNECT; } - if (!test_bit(__ICE_SUSPENDED, pf->state)) { + if (!test_bit(ICE_SUSPENDED, pf->state)) { ice_service_task_stop(pf); - if (!test_bit(__ICE_PREPARED_FOR_RESET, pf->state)) { - set_bit(__ICE_PFR_REQ, pf->state); + if (!test_bit(ICE_PREPARED_FOR_RESET, pf->state)) { + set_bit(ICE_PFR_REQ, pf->state); ice_prepare_for_reset(pf); } } @@ -4720,7 +4726,7 @@ static void ice_pci_err_resume(struct pci_dev *pdev) return; } - if (test_bit(__ICE_SUSPENDED, pf->state)) { + if (test_bit(ICE_SUSPENDED, pf->state)) { dev_dbg(&pdev->dev, "%s failed to resume normal operations!\n", __func__); return; @@ -4741,11 +4747,11 @@ static void ice_pci_err_reset_prepare(struct pci_dev *pdev) { struct ice_pf *pf = pci_get_drvdata(pdev); - if (!test_bit(__ICE_SUSPENDED, pf->state)) { + if (!test_bit(ICE_SUSPENDED, pf->state)) { ice_service_task_stop(pf); - if (!test_bit(__ICE_PREPARED_FOR_RESET, pf->state)) { - set_bit(__ICE_PFR_REQ, pf->state); + if (!test_bit(ICE_PREPARED_FOR_RESET, pf->state)) { + set_bit(ICE_PFR_REQ, pf->state); ice_prepare_for_reset(pf); } } @@ -4892,7 +4898,7 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi) return 0; } - if (test_bit(__ICE_DOWN, pf->state) || + if (test_bit(ICE_DOWN, pf->state) || ice_is_reset_in_progress(pf->state)) { netdev_err(netdev, "can't set mac %pM. device not ready\n", mac); @@ -4961,8 +4967,8 @@ static void ice_set_rx_mode(struct net_device *netdev) * ndo_set_rx_mode may be triggered even without a change in netdev * flags */ - set_bit(ICE_VSI_FLAG_UMAC_FLTR_CHANGED, vsi->flags); - set_bit(ICE_VSI_FLAG_MMAC_FLTR_CHANGED, vsi->flags); + set_bit(ICE_VSI_UMAC_FLTR_CHANGED, vsi->state); + set_bit(ICE_VSI_MMAC_FLTR_CHANGED, vsi->state); set_bit(ICE_FLAG_FLTR_SYNC, vsi->back->flags); /* schedule our worker thread which will take care of @@ -5111,10 +5117,10 @@ ice_set_features(struct net_device *netdev, netdev_features_t features) * separate if/else statements to guarantee each feature is checked */ if (features & NETIF_F_RXHASH && !(netdev->features & NETIF_F_RXHASH)) - ret = ice_vsi_manage_rss_lut(vsi, true); + ice_vsi_manage_rss_lut(vsi, true); else if (!(features & NETIF_F_RXHASH) && netdev->features & NETIF_F_RXHASH) - ret = ice_vsi_manage_rss_lut(vsi, false); + ice_vsi_manage_rss_lut(vsi, false); if ((features & NETIF_F_HW_VLAN_CTAG_RX) && !(netdev->features & NETIF_F_HW_VLAN_CTAG_RX)) @@ -5195,6 +5201,105 @@ int ice_vsi_cfg(struct ice_vsi *vsi) return err; } +/* THEORY OF MODERATION: + * The below code creates custom DIM profiles for use by this driver, because + * the ice driver hardware works differently than the hardware that DIMLIB was + * originally made for. ice hardware doesn't have packet count limits that + * can trigger an interrupt, but it *does* have interrupt rate limit support, + * and this code adds that capability to be used by the driver when it's using + * DIMLIB. The DIMLIB code was always designed to be a suggestion to the driver + * for how to "respond" to traffic and interrupts, so this driver uses a + * slightly different set of moderation parameters to get best performance. + */ +struct ice_dim { + /* the throttle rate for interrupts, basically worst case delay before + * an initial interrupt fires, value is stored in microseconds. + */ + u16 itr; + /* the rate limit for interrupts, which can cap a delay from a small + * ITR at a certain amount of interrupts per second. f.e. a 2us ITR + * could yield as much as 500,000 interrupts per second, but with a + * 10us rate limit, it limits to 100,000 interrupts per second. Value + * is stored in microseconds. + */ + u16 intrl; +}; + +/* Make a different profile for Rx that doesn't allow quite so aggressive + * moderation at the high end (it maxes out at 128us or about 8k interrupts a + * second. The INTRL/rate parameters here are only useful to cap small ITR + * values, which is why for larger ITR's - like 128, which can only generate + * 8k interrupts per second, there is no point to rate limit and the values + * are set to zero. The rate limit values do affect latency, and so must + * be reasonably small so to not impact latency sensitive tests. + */ +static const struct ice_dim rx_profile[] = { + {2, 10}, + {8, 16}, + {32, 0}, + {96, 0}, + {128, 0} +}; + +/* The transmit profile, which has the same sorts of values + * as the previous struct + */ +static const struct ice_dim tx_profile[] = { + {2, 10}, + {8, 16}, + {64, 0}, + {128, 0}, + {256, 0} +}; + +static void ice_tx_dim_work(struct work_struct *work) +{ + struct ice_ring_container *rc; + struct ice_q_vector *q_vector; + struct dim *dim; + u16 itr, intrl; + + dim = container_of(work, struct dim, work); + rc = container_of(dim, struct ice_ring_container, dim); + q_vector = container_of(rc, struct ice_q_vector, tx); + + if (dim->profile_ix >= ARRAY_SIZE(tx_profile)) + dim->profile_ix = ARRAY_SIZE(tx_profile) - 1; + + /* look up the values in our local table */ + itr = tx_profile[dim->profile_ix].itr; + intrl = tx_profile[dim->profile_ix].intrl; + + ice_write_itr(rc, itr); + ice_write_intrl(q_vector, intrl); + + dim->state = DIM_START_MEASURE; +} + +static void ice_rx_dim_work(struct work_struct *work) +{ + struct ice_ring_container *rc; + struct ice_q_vector *q_vector; + struct dim *dim; + u16 itr, intrl; + + dim = container_of(work, struct dim, work); + rc = container_of(dim, struct ice_ring_container, dim); + q_vector = container_of(rc, struct ice_q_vector, rx); + + if (dim->profile_ix >= ARRAY_SIZE(rx_profile)) + dim->profile_ix = ARRAY_SIZE(rx_profile) - 1; + + /* look up the values in our local table */ + itr = rx_profile[dim->profile_ix].itr; + intrl = rx_profile[dim->profile_ix].intrl; + + ice_write_itr(rc, itr); + ice_write_intrl(q_vector, intrl); + + dim->state = DIM_START_MEASURE; +} + /** * ice_napi_enable_all - Enable NAPI for all q_vectors in the VSI * @vsi: the VSI being configured @@ -5209,6 +5314,12 @@ static void ice_napi_enable_all(struct ice_vsi *vsi) ice_for_each_q_vector(vsi, q_idx) { struct ice_q_vector *q_vector = vsi->q_vectors[q_idx]; + INIT_WORK(&q_vector->tx.dim.work, ice_tx_dim_work); + q_vector->tx.dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE; + + INIT_WORK(&q_vector->rx.dim.work, ice_rx_dim_work); + q_vector->rx.dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE; + if (q_vector->rx.ring || q_vector->tx.ring) napi_enable(&q_vector->napi); } @@ -5235,7 +5346,7 @@ static int ice_up_complete(struct ice_vsi *vsi) if (err) return err; - clear_bit(__ICE_DOWN, vsi->state); + clear_bit(ICE_VSI_DOWN, vsi->state); ice_napi_enable_all(vsi); ice_vsi_ena_irq(vsi); @@ -5342,7 +5453,6 @@ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi) vsi->tx_linearize = 0; vsi->rx_buf_failed = 0; vsi->rx_page_failed = 0; - vsi->rx_gro_dropped = 0; rcu_read_lock(); @@ -5357,7 +5467,6 @@ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi) vsi_stats->rx_bytes += bytes; vsi->rx_buf_failed += ring->rx_stats.alloc_buf_failed; vsi->rx_page_failed += ring->rx_stats.alloc_page_failed; - vsi->rx_gro_dropped += ring->rx_stats.gro_dropped; } /* update XDP Tx rings counters */ @@ -5378,8 +5487,8 @@ void ice_update_vsi_stats(struct ice_vsi *vsi) struct ice_eth_stats *cur_es = &vsi->eth_stats; struct ice_pf *pf = vsi->back; - if (test_bit(__ICE_DOWN, vsi->state) || - test_bit(__ICE_CFG_BUSY, pf->state)) + if (test_bit(ICE_VSI_DOWN, vsi->state) || + test_bit(ICE_CFG_BUSY, pf->state)) return; /* get stats as recorded by Tx/Rx rings */ @@ -5389,7 +5498,7 @@ void ice_update_vsi_stats(struct ice_vsi *vsi) ice_update_eth_stats(vsi); cur_ns->tx_errors = cur_es->tx_errors; - cur_ns->rx_dropped = cur_es->rx_discards + vsi->rx_gro_dropped; + cur_ns->rx_dropped = cur_es->rx_discards; cur_ns->tx_dropped = cur_es->tx_discards; cur_ns->multicast = cur_es->rx_multicast; @@ -5583,7 +5692,7 @@ void ice_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats) * But, only call the update routine and read the registers if VSI is * not down. */ - if (!test_bit(__ICE_DOWN, vsi->state)) + if (!test_bit(ICE_VSI_DOWN, vsi->state)) ice_update_vsi_ring_stats(vsi); stats->tx_packets = vsi_stats->tx_packets; stats->tx_bytes = vsi_stats->tx_bytes; @@ -5619,6 +5728,9 @@ static void ice_napi_disable_all(struct ice_vsi *vsi) if (q_vector->rx.ring || q_vector->tx.ring) napi_disable(&q_vector->napi); + + cancel_work_sync(&q_vector->tx.dim.work); + cancel_work_sync(&q_vector->rx.dim.work); } } @@ -5631,7 +5743,7 @@ int ice_down(struct ice_vsi *vsi) int i, tx_err, rx_err, link_err = 0; /* Caller of this function is expected to set the - * vsi->state __ICE_DOWN bit + * vsi->state ICE_DOWN bit */ if (vsi->netdev) { netif_carrier_off(vsi->netdev); @@ -5783,7 +5895,7 @@ int ice_vsi_open_ctrl(struct ice_vsi *vsi) if (err) goto err_up_complete; - clear_bit(__ICE_DOWN, vsi->state); + clear_bit(ICE_VSI_DOWN, vsi->state); ice_vsi_ena_irq(vsi); return 0; @@ -5979,7 +6091,7 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) enum ice_status ret; int err; - if (test_bit(__ICE_DOWN, pf->state)) + if (test_bit(ICE_DOWN, pf->state)) goto clear_recovery; dev_dbg(dev, "rebuilding PF after reset_type=%d\n", reset_type); @@ -6095,7 +6207,7 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) ice_replay_post(hw); /* if we get here, reset flow is successful */ - clear_bit(__ICE_RESET_FAILED, pf->state); + clear_bit(ICE_RESET_FAILED, pf->state); return; err_vsi_rebuild: @@ -6103,10 +6215,10 @@ err_sched_init_port: ice_sched_cleanup_all(hw); err_init_ctrlq: ice_shutdown_all_ctrlq(hw); - set_bit(__ICE_RESET_FAILED, pf->state); + set_bit(ICE_RESET_FAILED, pf->state); clear_recovery: /* set this bit in PF state to control service task scheduling */ - set_bit(__ICE_NEEDS_RESTART, pf->state); + set_bit(ICE_NEEDS_RESTART, pf->state); dev_err(dev, "Rebuild failed, unload and reload driver\n"); } @@ -6170,7 +6282,7 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) netdev->mtu = (unsigned int)new_mtu; /* if VSI is up, bring it down and then back up */ - if (!test_and_set_bit(__ICE_DOWN, vsi->state)) { + if (!test_and_set_bit(ICE_VSI_DOWN, vsi->state)) { int err; err = ice_down(vsi); @@ -6305,89 +6417,118 @@ const char *ice_stat_str(enum ice_status stat_err) } /** - * ice_set_rss - Set RSS keys and lut + * ice_set_rss_lut - Set RSS LUT * @vsi: Pointer to VSI structure - * @seed: RSS hash seed * @lut: Lookup table * @lut_size: Lookup table size * * Returns 0 on success, negative on failure */ -int ice_set_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size) +int ice_set_rss_lut(struct ice_vsi *vsi, u8 *lut, u16 lut_size) { - struct ice_pf *pf = vsi->back; - struct ice_hw *hw = &pf->hw; + struct ice_aq_get_set_rss_lut_params params = {}; + struct ice_hw *hw = &vsi->back->hw; enum ice_status status; - struct device *dev; - dev = ice_pf_to_dev(pf); - if (seed) { - struct ice_aqc_get_set_rss_keys *buf = - (struct ice_aqc_get_set_rss_keys *)seed; + if (!lut) + return -EINVAL; - status = ice_aq_set_rss_key(hw, vsi->idx, buf); + params.vsi_handle = vsi->idx; + params.lut_size = lut_size; + params.lut_type = vsi->rss_lut_type; + params.lut = lut; - if (status) { - dev_err(dev, "Cannot set RSS key, err %s aq_err %s\n", - ice_stat_str(status), - ice_aq_str(hw->adminq.sq_last_status)); - return -EIO; - } + status = ice_aq_set_rss_lut(hw, ¶ms); + if (status) { + dev_err(ice_pf_to_dev(vsi->back), "Cannot set RSS lut, err %s aq_err %s\n", + ice_stat_str(status), + ice_aq_str(hw->adminq.sq_last_status)); + return -EIO; } - if (lut) { - status = ice_aq_set_rss_lut(hw, vsi->idx, vsi->rss_lut_type, - lut, lut_size); - if (status) { - dev_err(dev, "Cannot set RSS lut, err %s aq_err %s\n", - ice_stat_str(status), - ice_aq_str(hw->adminq.sq_last_status)); - return -EIO; - } + return 0; +} + +/** + * ice_set_rss_key - Set RSS key + * @vsi: Pointer to the VSI structure + * @seed: RSS hash seed + * + * Returns 0 on success, negative on failure + */ +int ice_set_rss_key(struct ice_vsi *vsi, u8 *seed) +{ + struct ice_hw *hw = &vsi->back->hw; + enum ice_status status; + + if (!seed) + return -EINVAL; + + status = ice_aq_set_rss_key(hw, vsi->idx, (struct ice_aqc_get_set_rss_keys *)seed); + if (status) { + dev_err(ice_pf_to_dev(vsi->back), "Cannot set RSS key, err %s aq_err %s\n", + ice_stat_str(status), + ice_aq_str(hw->adminq.sq_last_status)); + return -EIO; } return 0; } /** - * ice_get_rss - Get RSS keys and lut + * ice_get_rss_lut - Get RSS LUT * @vsi: Pointer to VSI structure - * @seed: Buffer to store the keys * @lut: Buffer to store the lookup table entries * @lut_size: Size of buffer to store the lookup table entries * * Returns 0 on success, negative on failure */ -int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size) +int ice_get_rss_lut(struct ice_vsi *vsi, u8 *lut, u16 lut_size) { - struct ice_pf *pf = vsi->back; - struct ice_hw *hw = &pf->hw; + struct ice_aq_get_set_rss_lut_params params = {}; + struct ice_hw *hw = &vsi->back->hw; enum ice_status status; - struct device *dev; - dev = ice_pf_to_dev(pf); - if (seed) { - struct ice_aqc_get_set_rss_keys *buf = - (struct ice_aqc_get_set_rss_keys *)seed; + if (!lut) + return -EINVAL; - status = ice_aq_get_rss_key(hw, vsi->idx, buf); - if (status) { - dev_err(dev, "Cannot get RSS key, err %s aq_err %s\n", - ice_stat_str(status), - ice_aq_str(hw->adminq.sq_last_status)); - return -EIO; - } + params.vsi_handle = vsi->idx; + params.lut_size = lut_size; + params.lut_type = vsi->rss_lut_type; + params.lut = lut; + + status = ice_aq_get_rss_lut(hw, ¶ms); + if (status) { + dev_err(ice_pf_to_dev(vsi->back), "Cannot get RSS lut, err %s aq_err %s\n", + ice_stat_str(status), + ice_aq_str(hw->adminq.sq_last_status)); + return -EIO; } - if (lut) { - status = ice_aq_get_rss_lut(hw, vsi->idx, vsi->rss_lut_type, - lut, lut_size); - if (status) { - dev_err(dev, "Cannot get RSS lut, err %s aq_err %s\n", - ice_stat_str(status), - ice_aq_str(hw->adminq.sq_last_status)); - return -EIO; - } + return 0; +} + +/** + * ice_get_rss_key - Get RSS key + * @vsi: Pointer to VSI structure + * @seed: Buffer to store the key in + * + * Returns 0 on success, negative on failure + */ +int ice_get_rss_key(struct ice_vsi *vsi, u8 *seed) +{ + struct ice_hw *hw = &vsi->back->hw; + enum ice_status status; + + if (!seed) + return -EINVAL; + + status = ice_aq_get_rss_key(hw, vsi->idx, (struct ice_aqc_get_set_rss_keys *)seed); + if (status) { + dev_err(ice_pf_to_dev(vsi->back), "Cannot get RSS key, err %s aq_err %s\n", + ice_stat_str(status), + ice_aq_str(hw->adminq.sq_last_status)); + return -EIO; } return 0; @@ -6599,19 +6740,19 @@ static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue) switch (pf->tx_timeout_recovery_level) { case 1: - set_bit(__ICE_PFR_REQ, pf->state); + set_bit(ICE_PFR_REQ, pf->state); break; case 2: - set_bit(__ICE_CORER_REQ, pf->state); + set_bit(ICE_CORER_REQ, pf->state); break; case 3: - set_bit(__ICE_GLOBR_REQ, pf->state); + set_bit(ICE_GLOBR_REQ, pf->state); break; default: netdev_err(netdev, "tx_timeout recovery unsuccessful, device is in unrecoverable state.\n"); - set_bit(__ICE_DOWN, pf->state); - set_bit(__ICE_NEEDS_RESTART, vsi->state); - set_bit(__ICE_SERVICE_DIS, pf->state); + set_bit(ICE_DOWN, pf->state); + set_bit(ICE_VSI_NEEDS_RESTART, vsi->state); + set_bit(ICE_SERVICE_DIS, pf->state); break; } @@ -6659,32 +6800,28 @@ int ice_open_internal(struct net_device *netdev) struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; struct ice_port_info *pi; + enum ice_status status; int err; - if (test_bit(__ICE_NEEDS_RESTART, pf->state)) { + if (test_bit(ICE_NEEDS_RESTART, pf->state)) { netdev_err(netdev, "driver needs to be unloaded and reloaded\n"); return -EIO; } - if (test_bit(__ICE_DOWN, pf->state)) { - netdev_err(netdev, "device is not ready yet\n"); - return -EBUSY; - } - netif_carrier_off(netdev); pi = vsi->port_info; - err = ice_update_link_info(pi); - if (err) { - netdev_err(netdev, "Failed to get link info, error %d\n", - err); - return err; + status = ice_update_link_info(pi); + if (status) { + netdev_err(netdev, "Failed to get link info, error %s\n", + ice_stat_str(status)); + return -EIO; } /* Set PHY if there is media, otherwise, turn off PHY */ if (pi->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE) { clear_bit(ICE_FLAG_NO_MEDIA, pf->flags); - if (!test_bit(__ICE_PHY_INIT_COMPLETE, pf->state)) { + if (!test_bit(ICE_PHY_INIT_COMPLETE, pf->state)) { err = ice_init_phy_user_cfg(pi); if (err) { netdev_err(netdev, "Failed to initialize PHY settings, error %d\n", @@ -6701,12 +6838,7 @@ int ice_open_internal(struct net_device *netdev) } } else { set_bit(ICE_FLAG_NO_MEDIA, pf->flags); - err = ice_aq_set_link_restart_an(pi, false, NULL); - if (err) { - netdev_err(netdev, "Failed to set PHY state, VSI %d error %d\n", - vsi->vsi_num, err); - return err; - } + ice_set_link(vsi, false); } err = ice_vsi_open(vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c index 75ccbfc07f99..fee37a5844cf 100644 --- a/drivers/net/ethernet/intel/ice/ice_nvm.c +++ b/drivers/net/ethernet/intel/ice/ice_nvm.c @@ -644,6 +644,7 @@ ice_get_orom_civd_data(struct ice_hw *hw, enum ice_bank_select bank, /* Verify that the simple checksum is zero */ for (i = 0; i < sizeof(tmp); i++) + /* cppcheck-suppress objectIndex */ sum += ((u8 *)&tmp)[i]; if (sum) { diff --git a/drivers/net/ethernet/intel/ice/ice_protocol_type.h b/drivers/net/ethernet/intel/ice/ice_protocol_type.h index 7f4c1ec1eff2..199aa5b71540 100644 --- a/drivers/net/ethernet/intel/ice/ice_protocol_type.h +++ b/drivers/net/ethernet/intel/ice/ice_protocol_type.h @@ -13,6 +13,9 @@ enum ice_prot_id { ICE_PROT_ID_INVAL = 0, ICE_PROT_MAC_OF_OR_S = 1, + ICE_PROT_MAC_IL = 4, + ICE_PROT_ETYPE_OL = 9, + ICE_PROT_ETYPE_IL = 10, ICE_PROT_IPV4_OF_OR_S = 32, ICE_PROT_IPV4_IL = 33, ICE_PROT_IPV6_OF_OR_S = 40, @@ -21,7 +24,14 @@ enum ice_prot_id { ICE_PROT_UDP_OF = 52, ICE_PROT_UDP_IL_OR_S = 53, ICE_PROT_GRE_OF = 64, + ICE_PROT_ESP_F = 88, + ICE_PROT_ESP_2 = 89, ICE_PROT_SCTP_IL = 96, + ICE_PROT_ICMP_IL = 98, + ICE_PROT_ICMPV6_IL = 100, + ICE_PROT_PPPOE = 103, + ICE_PROT_L2TPV3 = 104, + ICE_PROT_ARP_OF = 118, ICE_PROT_META_ID = 255, /* when offset == metadata */ ICE_PROT_INVALID = 255 /* when offset == ICE_FV_OFFSET_INVAL */ }; diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index 2403cb38b93c..2f097637e405 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -919,7 +919,7 @@ ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node, } /** - * ice_sched_add_nodes_to_layer - Add nodes to a given layer + * ice_sched_add_nodes_to_hw_layer - Add nodes to HW layer * @pi: port information structure * @tc_node: pointer to TC node * @parent: pointer to parent node @@ -928,82 +928,107 @@ ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node, * @first_node_teid: pointer to the first node TEID * @num_nodes_added: pointer to number of nodes added * - * This function add nodes to a given layer. + * Add nodes into specific HW layer. */ static enum ice_status -ice_sched_add_nodes_to_layer(struct ice_port_info *pi, - struct ice_sched_node *tc_node, - struct ice_sched_node *parent, u8 layer, - u16 num_nodes, u32 *first_node_teid, - u16 *num_nodes_added) +ice_sched_add_nodes_to_hw_layer(struct ice_port_info *pi, + struct ice_sched_node *tc_node, + struct ice_sched_node *parent, u8 layer, + u16 num_nodes, u32 *first_node_teid, + u16 *num_nodes_added) { - u32 *first_teid_ptr = first_node_teid; - u16 new_num_nodes, max_child_nodes; - enum ice_status status = 0; - struct ice_hw *hw = pi->hw; - u16 num_added = 0; - u32 temp; + u16 max_child_nodes; *num_nodes_added = 0; if (!num_nodes) - return status; + return 0; - if (!parent || layer < hw->sw_entry_point_layer) + if (!parent || layer < pi->hw->sw_entry_point_layer) return ICE_ERR_PARAM; /* max children per node per layer */ - max_child_nodes = hw->max_children[parent->tx_sched_layer]; + max_child_nodes = pi->hw->max_children[parent->tx_sched_layer]; - /* current number of children + required nodes exceed max children ? */ + /* current number of children + required nodes exceed max children */ if ((parent->num_children + num_nodes) > max_child_nodes) { /* Fail if the parent is a TC node */ if (parent == tc_node) return ICE_ERR_CFG; + return ICE_ERR_MAX_LIMIT; + } + + return ice_sched_add_elems(pi, tc_node, parent, layer, num_nodes, + num_nodes_added, first_node_teid); +} + +/** + * ice_sched_add_nodes_to_layer - Add nodes to a given layer + * @pi: port information structure + * @tc_node: pointer to TC node + * @parent: pointer to parent node + * @layer: layer number to add nodes + * @num_nodes: number of nodes to be added + * @first_node_teid: pointer to the first node TEID + * @num_nodes_added: pointer to number of nodes added + * + * This function add nodes to a given layer. + */ +static enum ice_status +ice_sched_add_nodes_to_layer(struct ice_port_info *pi, + struct ice_sched_node *tc_node, + struct ice_sched_node *parent, u8 layer, + u16 num_nodes, u32 *first_node_teid, + u16 *num_nodes_added) +{ + u32 *first_teid_ptr = first_node_teid; + u16 new_num_nodes = num_nodes; + enum ice_status status = 0; + *num_nodes_added = 0; + while (*num_nodes_added < num_nodes) { + u16 max_child_nodes, num_added = 0; + /* cppcheck-suppress unusedVariable */ + u32 temp; + + status = ice_sched_add_nodes_to_hw_layer(pi, tc_node, parent, + layer, new_num_nodes, + first_teid_ptr, + &num_added); + if (!status) + *num_nodes_added += num_added; + /* added more nodes than requested ? */ + if (*num_nodes_added > num_nodes) { + ice_debug(pi->hw, ICE_DBG_SCHED, "added extra nodes %d %d\n", num_nodes, + *num_nodes_added); + status = ICE_ERR_CFG; + break; + } + /* break if all the nodes are added successfully */ + if (!status && (*num_nodes_added == num_nodes)) + break; + /* break if the error is not max limit */ + if (status && status != ICE_ERR_MAX_LIMIT) + break; + /* Exceeded the max children */ + max_child_nodes = pi->hw->max_children[parent->tx_sched_layer]; /* utilize all the spaces if the parent is not full */ if (parent->num_children < max_child_nodes) { new_num_nodes = max_child_nodes - parent->num_children; - /* this recursion is intentional, and wouldn't - * go more than 2 calls + } else { + /* This parent is full, try the next sibling */ + parent = parent->sibling; + /* Don't modify the first node TEID memory if the + * first node was added already in the above call. + * Instead send some temp memory for all other + * recursive calls. */ - status = ice_sched_add_nodes_to_layer(pi, tc_node, - parent, layer, - new_num_nodes, - first_node_teid, - &num_added); - if (status) - return status; + if (num_added) + first_teid_ptr = &temp; - *num_nodes_added += num_added; + new_num_nodes = num_nodes - *num_nodes_added; } - /* Don't modify the first node TEID memory if the first node was - * added already in the above call. Instead send some temp - * memory for all other recursive calls. - */ - if (num_added) - first_teid_ptr = &temp; - - new_num_nodes = num_nodes - num_added; - - /* This parent is full, try the next sibling */ - parent = parent->sibling; - - /* this recursion is intentional, for 1024 queues - * per VSI, it goes max of 16 iterations. - * 1024 / 8 = 128 layer 8 nodes - * 128 /8 = 16 (add 8 nodes per iteration) - */ - status = ice_sched_add_nodes_to_layer(pi, tc_node, parent, - layer, new_num_nodes, - first_teid_ptr, - &num_added); - *num_nodes_added += num_added; - return status; } - - status = ice_sched_add_elems(pi, tc_node, parent, layer, num_nodes, - num_nodes_added, first_node_teid); return status; } @@ -1857,7 +1882,7 @@ ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 maxqs, } /** - * ice_sched_rm_agg_vsi_entry - remove aggregator related VSI info entry + * ice_sched_rm_agg_vsi_info - remove aggregator related VSI info entry * @pi: port information structure * @vsi_handle: software VSI handle * diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index 554f567476f3..aa11d07793d4 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -2,7 +2,6 @@ /* Copyright (c) 2018, Intel Corporation. */ #include "ice_common.h" -#include "ice_adminq_cmd.h" #include "ice_sriov.h" /** @@ -132,3 +131,402 @@ u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed) return speed; } + +/* The mailbox overflow detection algorithm helps to check if there + * is a possibility of a malicious VF transmitting too many MBX messages to the + * PF. + * 1. The mailbox snapshot structure, ice_mbx_snapshot, is initialized during + * driver initialization in ice_init_hw() using ice_mbx_init_snapshot(). + * The struct ice_mbx_snapshot helps to track and traverse a static window of + * messages within the mailbox queue while looking for a malicious VF. + * + * 2. When the caller starts processing its mailbox queue in response to an + * interrupt, the structure ice_mbx_snapshot is expected to be cleared before + * the algorithm can be run for the first time for that interrupt. This can be + * done via ice_mbx_reset_snapshot(). + * + * 3. For every message read by the caller from the MBX Queue, the caller must + * call the detection algorithm's entry function ice_mbx_vf_state_handler(). + * Before every call to ice_mbx_vf_state_handler() the struct ice_mbx_data is + * filled as it is required to be passed to the algorithm. + * + * 4. Every time a message is read from the MBX queue, a VFId is received which + * is passed to the state handler. The boolean output is_malvf of the state + * handler ice_mbx_vf_state_handler() serves as an indicator to the caller + * whether this VF is malicious or not. + * + * 5. When a VF is identified to be malicious, the caller can send a message + * to the system administrator. The caller can invoke ice_mbx_report_malvf() + * to help determine if a malicious VF is to be reported or not. This function + * requires the caller to maintain a global bitmap to track all malicious VFs + * and pass that to ice_mbx_report_malvf() along with the VFID which was identified + * to be malicious by ice_mbx_vf_state_handler(). + * + * 6. The global bitmap maintained by PF can be cleared completely if PF is in + * reset or the bit corresponding to a VF can be cleared if that VF is in reset. + * When a VF is shut down and brought back up, we assume that the new VF + * brought up is not malicious and hence report it if found malicious. + * + * 7. The function ice_mbx_reset_snapshot() is called to reset the information + * in ice_mbx_snapshot for every new mailbox interrupt handled. + * + * 8. The memory allocated for variables in ice_mbx_snapshot is de-allocated + * when driver is unloaded. + */ +#define ICE_RQ_DATA_MASK(rq_data) ((rq_data) & PF_MBX_ARQH_ARQH_M) +/* Using the highest value for an unsigned 16-bit value 0xFFFF to indicate that + * the max messages check must be ignored in the algorithm + */ +#define ICE_IGNORE_MAX_MSG_CNT 0xFFFF + +/** + * ice_mbx_traverse - Pass through mailbox snapshot + * @hw: pointer to the HW struct + * @new_state: new algorithm state + * + * Traversing the mailbox static snapshot without checking + * for malicious VFs. + */ +static void +ice_mbx_traverse(struct ice_hw *hw, + enum ice_mbx_snapshot_state *new_state) +{ + struct ice_mbx_snap_buffer_data *snap_buf; + u32 num_iterations; + + snap_buf = &hw->mbx_snapshot.mbx_buf; + + /* As mailbox buffer is circular, applying a mask + * on the incremented iteration count. + */ + num_iterations = ICE_RQ_DATA_MASK(++snap_buf->num_iterations); + + /* Checking either of the below conditions to exit snapshot traversal: + * Condition-1: If the number of iterations in the mailbox is equal to + * the mailbox head which would indicate that we have reached the end + * of the static snapshot. + * Condition-2: If the maximum messages serviced in the mailbox for a + * given interrupt is the highest possible value then there is no need + * to check if the number of messages processed is equal to it. If not + * check if the number of messages processed is greater than or equal + * to the maximum number of mailbox entries serviced in current work item. + */ + if (num_iterations == snap_buf->head || + (snap_buf->max_num_msgs_mbx < ICE_IGNORE_MAX_MSG_CNT && + ++snap_buf->num_msg_proc >= snap_buf->max_num_msgs_mbx)) + *new_state = ICE_MAL_VF_DETECT_STATE_NEW_SNAPSHOT; +} + +/** + * ice_mbx_detect_malvf - Detect malicious VF in snapshot + * @hw: pointer to the HW struct + * @vf_id: relative virtual function ID + * @new_state: new algorithm state + * @is_malvf: boolean output to indicate if VF is malicious + * + * This function tracks the number of asynchronous messages + * sent per VF and marks the VF as malicious if it exceeds + * the permissible number of messages to send. + */ +static enum ice_status +ice_mbx_detect_malvf(struct ice_hw *hw, u16 vf_id, + enum ice_mbx_snapshot_state *new_state, + bool *is_malvf) +{ + struct ice_mbx_snapshot *snap = &hw->mbx_snapshot; + + if (vf_id >= snap->mbx_vf.vfcntr_len) + return ICE_ERR_OUT_OF_RANGE; + + /* increment the message count in the VF array */ + snap->mbx_vf.vf_cntr[vf_id]++; + + if (snap->mbx_vf.vf_cntr[vf_id] >= ICE_ASYNC_VF_MSG_THRESHOLD) + *is_malvf = true; + + /* continue to iterate through the mailbox snapshot */ + ice_mbx_traverse(hw, new_state); + + return 0; +} + +/** + * ice_mbx_reset_snapshot - Reset mailbox snapshot structure + * @snap: pointer to mailbox snapshot structure in the ice_hw struct + * + * Reset the mailbox snapshot structure and clear VF counter array. + */ +static void ice_mbx_reset_snapshot(struct ice_mbx_snapshot *snap) +{ + u32 vfcntr_len; + + if (!snap || !snap->mbx_vf.vf_cntr) + return; + + /* Clear VF counters. */ + vfcntr_len = snap->mbx_vf.vfcntr_len; + if (vfcntr_len) + memset(snap->mbx_vf.vf_cntr, 0, + (vfcntr_len * sizeof(*snap->mbx_vf.vf_cntr))); + + /* Reset mailbox snapshot for a new capture. */ + memset(&snap->mbx_buf, 0, sizeof(snap->mbx_buf)); + snap->mbx_buf.state = ICE_MAL_VF_DETECT_STATE_NEW_SNAPSHOT; +} + +/** + * ice_mbx_vf_state_handler - Handle states of the overflow algorithm + * @hw: pointer to the HW struct + * @mbx_data: pointer to structure containing mailbox data + * @vf_id: relative virtual function (VF) ID + * @is_malvf: boolean output to indicate if VF is malicious + * + * The function serves as an entry point for the malicious VF + * detection algorithm by handling the different states and state + * transitions of the algorithm: + * New snapshot: This state is entered when creating a new static + * snapshot. The data from any previous mailbox snapshot is + * cleared and a new capture of the mailbox head and tail is + * logged. This will be the new static snapshot to detect + * asynchronous messages sent by VFs. On capturing the snapshot + * and depending on whether the number of pending messages in that + * snapshot exceed the watermark value, the state machine enters + * traverse or detect states. + * Traverse: If pending message count is below watermark then iterate + * through the snapshot without any action on VF. + * Detect: If pending message count exceeds watermark traverse + * the static snapshot and look for a malicious VF. + */ +enum ice_status +ice_mbx_vf_state_handler(struct ice_hw *hw, + struct ice_mbx_data *mbx_data, u16 vf_id, + bool *is_malvf) +{ + struct ice_mbx_snapshot *snap = &hw->mbx_snapshot; + struct ice_mbx_snap_buffer_data *snap_buf; + struct ice_ctl_q_info *cq = &hw->mailboxq; + enum ice_mbx_snapshot_state new_state; + enum ice_status status = 0; + + if (!is_malvf || !mbx_data) + return ICE_ERR_BAD_PTR; + + /* When entering the mailbox state machine assume that the VF + * is not malicious until detected. + */ + *is_malvf = false; + + /* Checking if max messages allowed to be processed while servicing current + * interrupt is not less than the defined AVF message threshold. + */ + if (mbx_data->max_num_msgs_mbx <= ICE_ASYNC_VF_MSG_THRESHOLD) + return ICE_ERR_INVAL_SIZE; + + /* The watermark value should not be lesser than the threshold limit + * set for the number of asynchronous messages a VF can send to mailbox + * nor should it be greater than the maximum number of messages in the + * mailbox serviced in current interrupt. + */ + if (mbx_data->async_watermark_val < ICE_ASYNC_VF_MSG_THRESHOLD || + mbx_data->async_watermark_val > mbx_data->max_num_msgs_mbx) + return ICE_ERR_PARAM; + + new_state = ICE_MAL_VF_DETECT_STATE_INVALID; + snap_buf = &snap->mbx_buf; + + switch (snap_buf->state) { + case ICE_MAL_VF_DETECT_STATE_NEW_SNAPSHOT: + /* Clear any previously held data in mailbox snapshot structure. */ + ice_mbx_reset_snapshot(snap); + + /* Collect the pending ARQ count, number of messages processed and + * the maximum number of messages allowed to be processed from the + * Mailbox for current interrupt. + */ + snap_buf->num_pending_arq = mbx_data->num_pending_arq; + snap_buf->num_msg_proc = mbx_data->num_msg_proc; + snap_buf->max_num_msgs_mbx = mbx_data->max_num_msgs_mbx; + + /* Capture a new static snapshot of the mailbox by logging the + * head and tail of snapshot and set num_iterations to the tail + * value to mark the start of the iteration through the snapshot. + */ + snap_buf->head = ICE_RQ_DATA_MASK(cq->rq.next_to_clean + + mbx_data->num_pending_arq); + snap_buf->tail = ICE_RQ_DATA_MASK(cq->rq.next_to_clean - 1); + snap_buf->num_iterations = snap_buf->tail; + + /* Pending ARQ messages returned by ice_clean_rq_elem + * is the difference between the head and tail of the + * mailbox queue. Comparing this value against the watermark + * helps to check if we potentially have malicious VFs. + */ + if (snap_buf->num_pending_arq >= + mbx_data->async_watermark_val) { + new_state = ICE_MAL_VF_DETECT_STATE_DETECT; + status = ice_mbx_detect_malvf(hw, vf_id, &new_state, is_malvf); + } else { + new_state = ICE_MAL_VF_DETECT_STATE_TRAVERSE; + ice_mbx_traverse(hw, &new_state); + } + break; + + case ICE_MAL_VF_DETECT_STATE_TRAVERSE: + new_state = ICE_MAL_VF_DETECT_STATE_TRAVERSE; + ice_mbx_traverse(hw, &new_state); + break; + + case ICE_MAL_VF_DETECT_STATE_DETECT: + new_state = ICE_MAL_VF_DETECT_STATE_DETECT; + status = ice_mbx_detect_malvf(hw, vf_id, &new_state, is_malvf); + break; + + default: + new_state = ICE_MAL_VF_DETECT_STATE_INVALID; + status = ICE_ERR_CFG; + } + + snap_buf->state = new_state; + + return status; +} + +/** + * ice_mbx_report_malvf - Track and note malicious VF + * @hw: pointer to the HW struct + * @all_malvfs: all malicious VFs tracked by PF + * @bitmap_len: length of bitmap in bits + * @vf_id: relative virtual function ID of the malicious VF + * @report_malvf: boolean to indicate if malicious VF must be reported + * + * This function will update a bitmap that keeps track of the malicious + * VFs attached to the PF. A malicious VF must be reported only once if + * discovered between VF resets or loading so the function checks + * the input vf_id against the bitmap to verify if the VF has been + * detected in any previous mailbox iterations. + */ +enum ice_status +ice_mbx_report_malvf(struct ice_hw *hw, unsigned long *all_malvfs, + u16 bitmap_len, u16 vf_id, bool *report_malvf) +{ + if (!all_malvfs || !report_malvf) + return ICE_ERR_PARAM; + + *report_malvf = false; + + if (bitmap_len < hw->mbx_snapshot.mbx_vf.vfcntr_len) + return ICE_ERR_INVAL_SIZE; + + if (vf_id >= bitmap_len) + return ICE_ERR_OUT_OF_RANGE; + + /* If the vf_id is found in the bitmap set bit and boolean to true */ + if (!test_and_set_bit(vf_id, all_malvfs)) + *report_malvf = true; + + return 0; +} + +/** + * ice_mbx_clear_malvf - Clear VF bitmap and counter for VF ID + * @snap: pointer to the mailbox snapshot structure + * @all_malvfs: all malicious VFs tracked by PF + * @bitmap_len: length of bitmap in bits + * @vf_id: relative virtual function ID of the malicious VF + * + * In case of a VF reset, this function can be called to clear + * the bit corresponding to the VF ID in the bitmap tracking all + * malicious VFs attached to the PF. The function also clears the + * VF counter array at the index of the VF ID. This is to ensure + * that the new VF loaded is not considered malicious before going + * through the overflow detection algorithm. + */ +enum ice_status +ice_mbx_clear_malvf(struct ice_mbx_snapshot *snap, unsigned long *all_malvfs, + u16 bitmap_len, u16 vf_id) +{ + if (!snap || !all_malvfs) + return ICE_ERR_PARAM; + + if (bitmap_len < snap->mbx_vf.vfcntr_len) + return ICE_ERR_INVAL_SIZE; + + /* Ensure VF ID value is not larger than bitmap or VF counter length */ + if (vf_id >= bitmap_len || vf_id >= snap->mbx_vf.vfcntr_len) + return ICE_ERR_OUT_OF_RANGE; + + /* Clear VF ID bit in the bitmap tracking malicious VFs attached to PF */ + clear_bit(vf_id, all_malvfs); + + /* Clear the VF counter in the mailbox snapshot structure for that VF ID. + * This is to ensure that if a VF is unloaded and a new one brought back + * up with the same VF ID for a snapshot currently in traversal or detect + * state the counter for that VF ID does not increment on top of existing + * values in the mailbox overflow detection algorithm. + */ + snap->mbx_vf.vf_cntr[vf_id] = 0; + + return 0; +} + +/** + * ice_mbx_init_snapshot - Initialize mailbox snapshot structure + * @hw: pointer to the hardware structure + * @vf_count: number of VFs allocated on a PF + * + * Clear the mailbox snapshot structure and allocate memory + * for the VF counter array based on the number of VFs allocated + * on that PF. + * + * Assumption: This function will assume ice_get_caps() has already been + * called to ensure that the vf_count can be compared against the number + * of VFs supported as defined in the functional capabilities of the device. + */ +enum ice_status ice_mbx_init_snapshot(struct ice_hw *hw, u16 vf_count) +{ + struct ice_mbx_snapshot *snap = &hw->mbx_snapshot; + + /* Ensure that the number of VFs allocated is non-zero and + * is not greater than the number of supported VFs defined in + * the functional capabilities of the PF. + */ + if (!vf_count || vf_count > hw->func_caps.num_allocd_vfs) + return ICE_ERR_INVAL_SIZE; + + snap->mbx_vf.vf_cntr = devm_kcalloc(ice_hw_to_dev(hw), vf_count, + sizeof(*snap->mbx_vf.vf_cntr), + GFP_KERNEL); + if (!snap->mbx_vf.vf_cntr) + return ICE_ERR_NO_MEMORY; + + /* Setting the VF counter length to the number of allocated + * VFs for given PF's functional capabilities. + */ + snap->mbx_vf.vfcntr_len = vf_count; + + /* Clear mbx_buf in the mailbox snaphot structure and setting the + * mailbox snapshot state to a new capture. + */ + memset(&snap->mbx_buf, 0, sizeof(snap->mbx_buf)); + snap->mbx_buf.state = ICE_MAL_VF_DETECT_STATE_NEW_SNAPSHOT; + + return 0; +} + +/** + * ice_mbx_deinit_snapshot - Free mailbox snapshot structure + * @hw: pointer to the hardware structure + * + * Clear the mailbox snapshot structure and free the VF counter array. + */ +void ice_mbx_deinit_snapshot(struct ice_hw *hw) +{ + struct ice_mbx_snapshot *snap = &hw->mbx_snapshot; + + /* Free VF counter array and reset VF counter length */ + devm_kfree(ice_hw_to_dev(hw), snap->mbx_vf.vf_cntr); + snap->mbx_vf.vfcntr_len = 0; + + /* Clear mbx_buf in the mailbox snaphot structure */ + memset(&snap->mbx_buf, 0, sizeof(snap->mbx_buf)); +} diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.h b/drivers/net/ethernet/intel/ice/ice_sriov.h index 3d78a0795138..161dc55d9e9c 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.h +++ b/drivers/net/ethernet/intel/ice/ice_sriov.h @@ -4,7 +4,14 @@ #ifndef _ICE_SRIOV_H_ #define _ICE_SRIOV_H_ -#include "ice_common.h" +#include "ice_type.h" +#include "ice_controlq.h" + +/* Defining the mailbox message threshold as 63 asynchronous + * pending messages. Normal VF functionality does not require + * sending more than 63 asynchronous pending message. + */ +#define ICE_ASYNC_VF_MSG_THRESHOLD 63 #ifdef CONFIG_PCI_IOV enum ice_status @@ -12,6 +19,17 @@ ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval, u8 *msg, u16 msglen, struct ice_sq_cd *cd); u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed); +enum ice_status +ice_mbx_vf_state_handler(struct ice_hw *hw, struct ice_mbx_data *mbx_data, + u16 vf_id, bool *is_mal_vf); +enum ice_status +ice_mbx_clear_malvf(struct ice_mbx_snapshot *snap, unsigned long *all_malvfs, + u16 bitmap_len, u16 vf_id); +enum ice_status ice_mbx_init_snapshot(struct ice_hw *hw, u16 vf_count); +void ice_mbx_deinit_snapshot(struct ice_hw *hw); +enum ice_status +ice_mbx_report_malvf(struct ice_hw *hw, unsigned long *all_malvfs, + u16 bitmap_len, u16 vf_id, bool *report_malvf); #else /* CONFIG_PCI_IOV */ static inline enum ice_status ice_aq_send_msg_to_vf(struct ice_hw __always_unused *hw, diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 834cbd3f7b31..357d3073d814 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -920,7 +920,7 @@ ice_create_vsi_list_map(struct ice_hw *hw, u16 *vsi_handle_arr, u16 num_vsi, struct ice_vsi_list_map_info *v_map; int i; - v_map = devm_kcalloc(ice_hw_to_dev(hw), 1, sizeof(*v_map), GFP_KERNEL); + v_map = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*v_map), GFP_KERNEL); if (!v_map) return NULL; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index b91dcfd12727..e2b4b29ea207 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -309,7 +309,7 @@ static bool ice_clean_tx_irq(struct ice_ring *tx_ring, int napi_budget) smp_mb(); if (__netif_subqueue_stopped(tx_ring->netdev, tx_ring->q_index) && - !test_bit(__ICE_DOWN, vsi->state)) { + !test_bit(ICE_VSI_DOWN, vsi->state)) { netif_wake_subqueue(tx_ring->netdev, tx_ring->q_index); ++tx_ring->tx_stats.restart_q; @@ -554,8 +554,8 @@ ice_run_xdp(struct ice_ring *rx_ring, struct xdp_buff *xdp, * @frames: XDP frames to be transmitted * @flags: transmit flags * - * Returns number of frames successfully sent. Frames that fail are - * free'ed via XDP return API. + * Returns number of frames successfully sent. Failed frames + * will be free'ed by XDP core. * For error cases, a negative errno code is returned and no-frames * are transmitted (caller must handle freeing frames). */ @@ -567,9 +567,9 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, unsigned int queue_index = smp_processor_id(); struct ice_vsi *vsi = np->vsi; struct ice_ring *xdp_ring; - int drops = 0, i; + int nxmit = 0, i; - if (test_bit(__ICE_DOWN, vsi->state)) + if (test_bit(ICE_VSI_DOWN, vsi->state)) return -ENETDOWN; if (!ice_is_xdp_ena_vsi(vsi) || queue_index >= vsi->num_xdp_txq) @@ -584,16 +584,15 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, int err; err = ice_xmit_xdp_ring(xdpf->data, xdpf->len, xdp_ring); - if (err != ICE_XDP_TX) { - xdp_return_frame_rx_napi(xdpf); - drops++; - } + if (err != ICE_XDP_TX) + break; + nxmit++; } if (unlikely(flags & XDP_XMIT_FLUSH)) ice_xdp_ring_update_tail(xdp_ring); - return n - drops; + return nxmit; } /** @@ -1098,6 +1097,11 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) dma_rmb(); if (rx_desc->wb.rxdid == FDIR_DESC_RXDID || !rx_ring->netdev) { + struct ice_vsi *ctrl_vsi = rx_ring->vsi; + + if (rx_desc->wb.rxdid == FDIR_DESC_RXDID && + ctrl_vsi->vf_id != ICE_INVAL_VFID) + ice_vc_fdir_irq_handler(ctrl_vsi, rx_desc); ice_put_rx_buf(rx_ring, NULL, 0); cleaned_count++; continue; @@ -1219,216 +1223,50 @@ construct_skb: } /** - * ice_adjust_itr_by_size_and_speed - Adjust ITR based on current traffic - * @port_info: port_info structure containing the current link speed - * @avg_pkt_size: average size of Tx or Rx packets based on clean routine - * @itr: ITR value to update - * - * Calculate how big of an increment should be applied to the ITR value passed - * in based on wmem_default, SKB overhead, ethernet overhead, and the current - * link speed. - * - * The following is a calculation derived from: - * wmem_default / (size + overhead) = desired_pkts_per_int - * rate / bits_per_byte / (size + ethernet overhead) = pkt_rate - * (desired_pkt_rate / pkt_rate) * usecs_per_sec = ITR value + * ice_net_dim - Update net DIM algorithm + * @q_vector: the vector associated with the interrupt * - * Assuming wmem_default is 212992 and overhead is 640 bytes per - * packet, (256 skb, 64 headroom, 320 shared info), we can reduce the - * formula down to: + * Create a DIM sample and notify net_dim() so that it can possibly decide + * a new ITR value based on incoming packets, bytes, and interrupts. * - * wmem_default * bits_per_byte * usecs_per_sec pkt_size + 24 - * ITR = -------------------------------------------- * -------------- - * rate pkt_size + 640 + * This function is a no-op if the ring is not configured to dynamic ITR. */ -static unsigned int -ice_adjust_itr_by_size_and_speed(struct ice_port_info *port_info, - unsigned int avg_pkt_size, - unsigned int itr) +static void ice_net_dim(struct ice_q_vector *q_vector) { - switch (port_info->phy.link_info.link_speed) { - case ICE_AQ_LINK_SPEED_100GB: - itr += DIV_ROUND_UP(17 * (avg_pkt_size + 24), - avg_pkt_size + 640); - break; - case ICE_AQ_LINK_SPEED_50GB: - itr += DIV_ROUND_UP(34 * (avg_pkt_size + 24), - avg_pkt_size + 640); - break; - case ICE_AQ_LINK_SPEED_40GB: - itr += DIV_ROUND_UP(43 * (avg_pkt_size + 24), - avg_pkt_size + 640); - break; - case ICE_AQ_LINK_SPEED_25GB: - itr += DIV_ROUND_UP(68 * (avg_pkt_size + 24), - avg_pkt_size + 640); - break; - case ICE_AQ_LINK_SPEED_20GB: - itr += DIV_ROUND_UP(85 * (avg_pkt_size + 24), - avg_pkt_size + 640); - break; - case ICE_AQ_LINK_SPEED_10GB: - default: - itr += DIV_ROUND_UP(170 * (avg_pkt_size + 24), - avg_pkt_size + 640); - break; - } - - if ((itr & ICE_ITR_MASK) > ICE_ITR_ADAPTIVE_MAX_USECS) { - itr &= ICE_ITR_ADAPTIVE_LATENCY; - itr += ICE_ITR_ADAPTIVE_MAX_USECS; - } + struct ice_ring_container *tx = &q_vector->tx; + struct ice_ring_container *rx = &q_vector->rx; - return itr; -} + if (ITR_IS_DYNAMIC(tx)) { + struct dim_sample dim_sample = {}; + u64 packets = 0, bytes = 0; + struct ice_ring *ring; -/** - * ice_update_itr - update the adaptive ITR value based on statistics - * @q_vector: structure containing interrupt and ring information - * @rc: structure containing ring performance data - * - * Stores a new ITR value based on packets and byte - * counts during the last interrupt. The advantage of per interrupt - * computation is faster updates and more accurate ITR for the current - * traffic pattern. Constants in this function were computed - * based on theoretical maximum wire speed and thresholds were set based - * on testing data as well as attempting to minimize response time - * while increasing bulk throughput. - */ -static void -ice_update_itr(struct ice_q_vector *q_vector, struct ice_ring_container *rc) -{ - unsigned long next_update = jiffies; - unsigned int packets, bytes, itr; - bool container_is_rx; + ice_for_each_ring(ring, q_vector->tx) { + packets += ring->stats.pkts; + bytes += ring->stats.bytes; + } - if (!rc->ring || !ITR_IS_DYNAMIC(rc->itr_setting)) - return; + dim_update_sample(q_vector->total_events, packets, bytes, + &dim_sample); - /* If itr_countdown is set it means we programmed an ITR within - * the last 4 interrupt cycles. This has a side effect of us - * potentially firing an early interrupt. In order to work around - * this we need to throw out any data received for a few - * interrupts following the update. - */ - if (q_vector->itr_countdown) { - itr = rc->target_itr; - goto clear_counts; + net_dim(&tx->dim, dim_sample); } - container_is_rx = (&q_vector->rx == rc); - /* For Rx we want to push the delay up and default to low latency. - * for Tx we want to pull the delay down and default to high latency. - */ - itr = container_is_rx ? - ICE_ITR_ADAPTIVE_MIN_USECS | ICE_ITR_ADAPTIVE_LATENCY : - ICE_ITR_ADAPTIVE_MAX_USECS | ICE_ITR_ADAPTIVE_LATENCY; - - /* If we didn't update within up to 1 - 2 jiffies we can assume - * that either packets are coming in so slow there hasn't been - * any work, or that there is so much work that NAPI is dealing - * with interrupt moderation and we don't need to do anything. - */ - if (time_after(next_update, rc->next_update)) - goto clear_counts; - - prefetch(q_vector->vsi->port_info); - - packets = rc->total_pkts; - bytes = rc->total_bytes; + if (ITR_IS_DYNAMIC(rx)) { + struct dim_sample dim_sample = {}; + u64 packets = 0, bytes = 0; + struct ice_ring *ring; - if (container_is_rx) { - /* If Rx there are 1 to 4 packets and bytes are less than - * 9000 assume insufficient data to use bulk rate limiting - * approach unless Tx is already in bulk rate limiting. We - * are likely latency driven. - */ - if (packets && packets < 4 && bytes < 9000 && - (q_vector->tx.target_itr & ICE_ITR_ADAPTIVE_LATENCY)) { - itr = ICE_ITR_ADAPTIVE_LATENCY; - goto adjust_by_size_and_speed; + ice_for_each_ring(ring, q_vector->rx) { + packets += ring->stats.pkts; + bytes += ring->stats.bytes; } - } else if (packets < 4) { - /* If we have Tx and Rx ITR maxed and Tx ITR is running in - * bulk mode and we are receiving 4 or fewer packets just - * reset the ITR_ADAPTIVE_LATENCY bit for latency mode so - * that the Rx can relax. - */ - if (rc->target_itr == ICE_ITR_ADAPTIVE_MAX_USECS && - (q_vector->rx.target_itr & ICE_ITR_MASK) == - ICE_ITR_ADAPTIVE_MAX_USECS) - goto clear_counts; - } else if (packets > 32) { - /* If we have processed over 32 packets in a single interrupt - * for Tx assume we need to switch over to "bulk" mode. - */ - rc->target_itr &= ~ICE_ITR_ADAPTIVE_LATENCY; - } - - /* We have no packets to actually measure against. This means - * either one of the other queues on this vector is active or - * we are a Tx queue doing TSO with too high of an interrupt rate. - * - * Between 4 and 56 we can assume that our current interrupt delay - * is only slightly too low. As such we should increase it by a small - * fixed amount. - */ - if (packets < 56) { - itr = rc->target_itr + ICE_ITR_ADAPTIVE_MIN_INC; - if ((itr & ICE_ITR_MASK) > ICE_ITR_ADAPTIVE_MAX_USECS) { - itr &= ICE_ITR_ADAPTIVE_LATENCY; - itr += ICE_ITR_ADAPTIVE_MAX_USECS; - } - goto clear_counts; - } - - if (packets <= 256) { - itr = min(q_vector->tx.current_itr, q_vector->rx.current_itr); - itr &= ICE_ITR_MASK; - /* Between 56 and 112 is our "goldilocks" zone where we are - * working out "just right". Just report that our current - * ITR is good for us. - */ - if (packets <= 112) - goto clear_counts; - - /* If packet count is 128 or greater we are likely looking - * at a slight overrun of the delay we want. Try halving - * our delay to see if that will cut the number of packets - * in half per interrupt. - */ - itr >>= 1; - itr &= ICE_ITR_MASK; - if (itr < ICE_ITR_ADAPTIVE_MIN_USECS) - itr = ICE_ITR_ADAPTIVE_MIN_USECS; + dim_update_sample(q_vector->total_events, packets, bytes, + &dim_sample); - goto clear_counts; + net_dim(&rx->dim, dim_sample); } - - /* The paths below assume we are dealing with a bulk ITR since - * number of packets is greater than 256. We are just going to have - * to compute a value and try to bring the count under control, - * though for smaller packet sizes there isn't much we can do as - * NAPI polling will likely be kicking in sooner rather than later. - */ - itr = ICE_ITR_ADAPTIVE_BULK; - -adjust_by_size_and_speed: - - /* based on checks above packets cannot be 0 so division is safe */ - itr = ice_adjust_itr_by_size_and_speed(q_vector->vsi->port_info, - bytes / packets, itr); - -clear_counts: - /* write back value */ - rc->target_itr = itr; - - /* next update should occur within next jiffy */ - rc->next_update = next_update + 1; - - rc->total_bytes = 0; - rc->total_pkts = 0; } /** @@ -1452,72 +1290,46 @@ static u32 ice_buildreg_itr(u16 itr_idx, u16 itr) (itr << (GLINT_DYN_CTL_INTERVAL_S - ICE_ITR_GRAN_S)); } -/* The act of updating the ITR will cause it to immediately trigger. In order - * to prevent this from throwing off adaptive update statistics we defer the - * update so that it can only happen so often. So after either Tx or Rx are - * updated we make the adaptive scheme wait until either the ITR completely - * expires via the next_update expiration or we have been through at least - * 3 interrupts. - */ -#define ITR_COUNTDOWN_START 3 - /** - * ice_update_ena_itr - Update ITR and re-enable MSIX interrupt - * @q_vector: q_vector for which ITR is being updated and interrupt enabled + * ice_update_ena_itr - Update ITR moderation and re-enable MSI-X interrupt + * @q_vector: the vector associated with the interrupt to enable + * + * Update the net_dim() algorithm and re-enable the interrupt associated with + * this vector. + * + * If the VSI is down, the interrupt will not be re-enabled. */ static void ice_update_ena_itr(struct ice_q_vector *q_vector) { - struct ice_ring_container *tx = &q_vector->tx; - struct ice_ring_container *rx = &q_vector->rx; struct ice_vsi *vsi = q_vector->vsi; + bool wb_en = q_vector->wb_on_itr; u32 itr_val; - /* when exiting WB_ON_ITR just reset the countdown and let ITR - * resume it's normal "interrupts-enabled" path - */ - if (q_vector->itr_countdown == ICE_IN_WB_ON_ITR_MODE) - q_vector->itr_countdown = 0; - - /* This will do nothing if dynamic updates are not enabled */ - ice_update_itr(q_vector, tx); - ice_update_itr(q_vector, rx); + if (test_bit(ICE_DOWN, vsi->state)) + return; - /* This block of logic allows us to get away with only updating - * one ITR value with each interrupt. The idea is to perform a - * pseudo-lazy update with the following criteria. - * - * 1. Rx is given higher priority than Tx if both are in same state - * 2. If we must reduce an ITR that is given highest priority. - * 3. We then give priority to increasing ITR based on amount. + /* When exiting WB_ON_ITR, let ITR resume its normal + * interrupts-enabled path. */ - if (rx->target_itr < rx->current_itr) { - /* Rx ITR needs to be reduced, this is highest priority */ - itr_val = ice_buildreg_itr(rx->itr_idx, rx->target_itr); - rx->current_itr = rx->target_itr; - q_vector->itr_countdown = ITR_COUNTDOWN_START; - } else if ((tx->target_itr < tx->current_itr) || - ((rx->target_itr - rx->current_itr) < - (tx->target_itr - tx->current_itr))) { - /* Tx ITR needs to be reduced, this is second priority - * Tx ITR needs to be increased more than Rx, fourth priority - */ - itr_val = ice_buildreg_itr(tx->itr_idx, tx->target_itr); - tx->current_itr = tx->target_itr; - q_vector->itr_countdown = ITR_COUNTDOWN_START; - } else if (rx->current_itr != rx->target_itr) { - /* Rx ITR needs to be increased, third priority */ - itr_val = ice_buildreg_itr(rx->itr_idx, rx->target_itr); - rx->current_itr = rx->target_itr; - q_vector->itr_countdown = ITR_COUNTDOWN_START; - } else { - /* Still have to re-enable the interrupts */ - itr_val = ice_buildreg_itr(ICE_ITR_NONE, 0); - if (q_vector->itr_countdown) - q_vector->itr_countdown--; + if (wb_en) + q_vector->wb_on_itr = false; + + /* This will do nothing if dynamic updates are not enabled. */ + ice_net_dim(q_vector); + + /* net_dim() updates ITR out-of-band using a work item */ + itr_val = ice_buildreg_itr(ICE_ITR_NONE, 0); + /* trigger an immediate software interrupt when exiting + * busy poll, to make sure to catch any pending cleanups + * that might have been missed due to interrupt state + * transition. + */ + if (wb_en) { + itr_val |= GLINT_DYN_CTL_SWINT_TRIG_M | + GLINT_DYN_CTL_SW_ITR_INDX_M | + GLINT_DYN_CTL_SW_ITR_INDX_ENA_M; } - - if (!test_bit(__ICE_DOWN, vsi->state)) - wr32(&vsi->back->hw, GLINT_DYN_CTL(q_vector->reg_idx), itr_val); + wr32(&vsi->back->hw, GLINT_DYN_CTL(q_vector->reg_idx), itr_val); } /** @@ -1539,7 +1351,7 @@ static void ice_set_wb_on_itr(struct ice_q_vector *q_vector) struct ice_vsi *vsi = q_vector->vsi; /* already in wb_on_itr mode no need to change it */ - if (q_vector->itr_countdown == ICE_IN_WB_ON_ITR_MODE) + if (q_vector->wb_on_itr) return; /* use previously set ITR values for all of the ITR indices by @@ -1551,7 +1363,7 @@ static void ice_set_wb_on_itr(struct ice_q_vector *q_vector) GLINT_DYN_CTL_ITR_INDX_M) | GLINT_DYN_CTL_INTENA_MSK_M | GLINT_DYN_CTL_WB_ON_ITR_M); - q_vector->itr_countdown = ICE_IN_WB_ON_ITR_MODE; + q_vector->wb_on_itr = true; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index 5dab77504fa5..c5a92ac787d6 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -192,7 +192,11 @@ struct ice_rxq_stats { u64 non_eop_descs; u64 alloc_page_failed; u64 alloc_buf_failed; - u64 gro_dropped; /* GRO returned dropped */ +}; + +enum ice_ring_state_t { + ICE_TX_XPS_INIT_DONE, + ICE_TX_NBITS, }; /* this enum matches hardware bits and is meant to be used by DYN_CTLN @@ -219,23 +223,20 @@ enum ice_rx_dtype { #define ICE_TX_ITR ICE_IDX_ITR1 #define ICE_ITR_8K 124 #define ICE_ITR_20K 50 -#define ICE_ITR_MAX 8160 -#define ICE_DFLT_TX_ITR (ICE_ITR_20K | ICE_ITR_DYNAMIC) -#define ICE_DFLT_RX_ITR (ICE_ITR_20K | ICE_ITR_DYNAMIC) -#define ICE_ITR_DYNAMIC 0x8000 /* used as flag for itr_setting */ -#define ITR_IS_DYNAMIC(setting) (!!((setting) & ICE_ITR_DYNAMIC)) -#define ITR_TO_REG(setting) ((setting) & ~ICE_ITR_DYNAMIC) +#define ICE_ITR_MAX 8160 /* 0x1FE0 */ +#define ICE_DFLT_TX_ITR ICE_ITR_20K +#define ICE_DFLT_RX_ITR ICE_ITR_20K +enum ice_dynamic_itr { + ITR_STATIC = 0, + ITR_DYNAMIC = 1 +}; + +#define ITR_IS_DYNAMIC(rc) ((rc)->itr_mode == ITR_DYNAMIC) #define ICE_ITR_GRAN_S 1 /* ITR granularity is always 2us */ #define ICE_ITR_GRAN_US BIT(ICE_ITR_GRAN_S) #define ICE_ITR_MASK 0x1FFE /* ITR register value alignment mask */ #define ITR_REG_ALIGN(setting) ((setting) & ICE_ITR_MASK) -#define ICE_ITR_ADAPTIVE_MIN_INC 0x0002 -#define ICE_ITR_ADAPTIVE_MIN_USECS 0x0002 -#define ICE_ITR_ADAPTIVE_MAX_USECS 0x00FA -#define ICE_ITR_ADAPTIVE_LATENCY 0x8000 -#define ICE_ITR_ADAPTIVE_BULK 0x0000 - #define ICE_DFLT_INTRL 0 #define ICE_MAX_INTRL 236 @@ -292,6 +293,7 @@ struct ice_ring { }; struct rcu_head rcu; /* to avoid race on free */ + DECLARE_BITMAP(xps_state, ICE_TX_NBITS); /* XPS Config State */ struct bpf_prog *xdp_prog; struct xsk_buff_pool *xsk_pool; u16 rx_offset; @@ -334,23 +336,22 @@ static inline bool ice_ring_is_xdp(struct ice_ring *ring) struct ice_ring_container { /* head of linked-list of rings */ struct ice_ring *ring; - unsigned long next_update; /* jiffies value of next queue update */ - unsigned int total_bytes; /* total bytes processed this int */ - unsigned int total_pkts; /* total packets processed this int */ + struct dim dim; /* data for net_dim algorithm */ u16 itr_idx; /* index in the interrupt vector */ - u16 target_itr; /* value in usecs divided by the hw->itr_gran */ - u16 current_itr; /* value in usecs divided by the hw->itr_gran */ - /* high bit set means dynamic ITR, rest is used to store user - * readable ITR value in usecs and must be converted before programming - * to a register. + /* this matches the maximum number of ITR bits, but in usec + * values, so it is shifted left one bit (bit zero is ignored) */ - u16 itr_setting; + u16 itr_setting:13; + u16 itr_reserved:2; + u16 itr_mode:1; }; struct ice_coalesce_stored { u16 itr_tx; u16 itr_rx; u8 intrl; + u8 tx_valid; + u8 rx_valid; }; /* iterator for handling rings in ring container */ diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c index 02b12736ea80..207f6ee3a7f6 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c @@ -143,6 +143,7 @@ ice_rx_csum(struct ice_ring *ring, struct sk_buff *skb, case ICE_RX_PTYPE_INNER_PROT_UDP: case ICE_RX_PTYPE_INNER_PROT_SCTP: skb->ip_summed = CHECKSUM_UNNECESSARY; + break; default: break; } diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index 266036b7a49a..4474dd6a7ba1 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -192,6 +192,24 @@ enum ice_fltr_ptype { ICE_FLTR_PTYPE_NONF_IPV4_TCP, ICE_FLTR_PTYPE_NONF_IPV4_SCTP, ICE_FLTR_PTYPE_NONF_IPV4_OTHER, + ICE_FLTR_PTYPE_NONF_IPV4_GTPU_IPV4_UDP, + ICE_FLTR_PTYPE_NONF_IPV4_GTPU_IPV4_TCP, + ICE_FLTR_PTYPE_NONF_IPV4_GTPU_IPV4_ICMP, + ICE_FLTR_PTYPE_NONF_IPV4_GTPU_IPV4_OTHER, + ICE_FLTR_PTYPE_NONF_IPV6_GTPU_IPV6_OTHER, + ICE_FLTR_PTYPE_NONF_IPV4_L2TPV3, + ICE_FLTR_PTYPE_NONF_IPV6_L2TPV3, + ICE_FLTR_PTYPE_NONF_IPV4_ESP, + ICE_FLTR_PTYPE_NONF_IPV6_ESP, + ICE_FLTR_PTYPE_NONF_IPV4_AH, + ICE_FLTR_PTYPE_NONF_IPV6_AH, + ICE_FLTR_PTYPE_NONF_IPV4_NAT_T_ESP, + ICE_FLTR_PTYPE_NONF_IPV6_NAT_T_ESP, + ICE_FLTR_PTYPE_NONF_IPV4_PFCP_NODE, + ICE_FLTR_PTYPE_NONF_IPV4_PFCP_SESSION, + ICE_FLTR_PTYPE_NONF_IPV6_PFCP_NODE, + ICE_FLTR_PTYPE_NONF_IPV6_PFCP_SESSION, + ICE_FLTR_PTYPE_NON_IP_L2, ICE_FLTR_PTYPE_FRAG_IPV4, ICE_FLTR_PTYPE_NONF_IPV6_UDP, ICE_FLTR_PTYPE_NONF_IPV6_TCP, @@ -533,10 +551,7 @@ struct ice_dcb_app_priority_table { #define ICE_TLV_STATUS_OPER 0x1 #define ICE_TLV_STATUS_SYNC 0x2 #define ICE_TLV_STATUS_ERR 0x4 -#define ICE_APP_PROT_ID_FCOE 0x8906 -#define ICE_APP_PROT_ID_ISCSI 0x0cbc #define ICE_APP_PROT_ID_ISCSI_860 0x035c -#define ICE_APP_PROT_ID_FIP 0x8914 #define ICE_APP_SEL_ETHTYPE 0x1 #define ICE_APP_SEL_TCPIP 0x2 #define ICE_CEE_APP_SEL_ETHTYPE 0x0 @@ -615,6 +630,80 @@ struct ice_fw_log_cfg { struct ice_fw_log_evnt evnts[ICE_AQC_FW_LOG_ID_MAX]; }; +/* Enum defining the different states of the mailbox snapshot in the + * PF-VF mailbox overflow detection algorithm. The snapshot can be in + * states: + * 1. ICE_MAL_VF_DETECT_STATE_NEW_SNAPSHOT - generate a new static snapshot + * within the mailbox buffer. + * 2. ICE_MAL_VF_DETECT_STATE_TRAVERSE - iterate through the mailbox snaphot + * 3. ICE_MAL_VF_DETECT_STATE_DETECT - track the messages sent per VF via the + * mailbox and mark any VFs sending more messages than the threshold limit set. + * 4. ICE_MAL_VF_DETECT_STATE_INVALID - Invalid mailbox state set to 0xFFFFFFFF. + */ +enum ice_mbx_snapshot_state { + ICE_MAL_VF_DETECT_STATE_NEW_SNAPSHOT = 0, + ICE_MAL_VF_DETECT_STATE_TRAVERSE, + ICE_MAL_VF_DETECT_STATE_DETECT, + ICE_MAL_VF_DETECT_STATE_INVALID = 0xFFFFFFFF, +}; + +/* Structure to hold information of the static snapshot and the mailbox + * buffer data used to generate and track the snapshot. + * 1. state: the state of the mailbox snapshot in the malicious VF + * detection state handler ice_mbx_vf_state_handler() + * 2. head: head of the mailbox snapshot in a circular mailbox buffer + * 3. tail: tail of the mailbox snapshot in a circular mailbox buffer + * 4. num_iterations: number of messages traversed in circular mailbox buffer + * 5. num_msg_proc: number of messages processed in mailbox + * 6. num_pending_arq: number of pending asynchronous messages + * 7. max_num_msgs_mbx: maximum messages in mailbox for currently + * serviced work item or interrupt. + */ +struct ice_mbx_snap_buffer_data { + enum ice_mbx_snapshot_state state; + u32 head; + u32 tail; + u32 num_iterations; + u16 num_msg_proc; + u16 num_pending_arq; + u16 max_num_msgs_mbx; +}; + +/* Structure to track messages sent by VFs on mailbox: + * 1. vf_cntr: a counter array of VFs to track the number of + * asynchronous messages sent by each VF + * 2. vfcntr_len: number of entries in VF counter array + */ +struct ice_mbx_vf_counter { + u32 *vf_cntr; + u32 vfcntr_len; +}; + +/* Structure to hold data relevant to the captured static snapshot + * of the PF-VF mailbox. + */ +struct ice_mbx_snapshot { + struct ice_mbx_snap_buffer_data mbx_buf; + struct ice_mbx_vf_counter mbx_vf; +}; + +/* Structure to hold data to be used for capturing or updating a + * static snapshot. + * 1. num_msg_proc: number of messages processed in mailbox + * 2. num_pending_arq: number of pending asynchronous messages + * 3. max_num_msgs_mbx: maximum messages in mailbox for currently + * serviced work item or interrupt. + * 4. async_watermark_val: An upper threshold set by caller to determine + * if the pending arq count is large enough to assume that there is + * the possibility of a mailicious VF. + */ +struct ice_mbx_data { + u16 num_msg_proc; + u16 num_pending_arq; + u16 max_num_msgs_mbx; + u16 async_watermark_val; +}; + /* Port hardware description */ struct ice_hw { u8 __iomem *hw_addr; @@ -703,13 +792,13 @@ struct ice_hw { enum ice_aq_err pkg_dwnld_status; - /* Driver's package ver - (from the Metadata seg) */ + /* Driver's package ver - (from the Ice Metadata section) */ struct ice_pkg_ver pkg_ver; u8 pkg_name[ICE_PKG_NAME_SIZE]; - /* Driver's Ice package version (from the Ice seg) */ - struct ice_pkg_ver ice_pkg_ver; - u8 ice_pkg_name[ICE_PKG_NAME_SIZE]; + /* Driver's Ice segment format version and ID (from the Ice seg) */ + struct ice_pkg_ver ice_seg_fmt_ver; + u8 ice_seg_id[ICE_SEG_ID_SIZE]; /* Pointer to the ice segment */ struct ice_seg *seg; @@ -746,6 +835,7 @@ struct ice_hw { DECLARE_BITMAP(fdir_perfect_fltr, ICE_FLTR_PTYPE_MAX); struct mutex rss_locks; /* protect RSS configuration */ struct list_head rss_list_head; + struct ice_mbx_snapshot mbx_snapshot; }; /* Statistics collected by each port, VSI, VEB, and S-channel */ @@ -810,6 +900,14 @@ struct ice_hw_port_stats { u64 fd_sb_match; }; +struct ice_aq_get_set_rss_lut_params { + u16 vsi_handle; /* software VSI handle */ + u16 lut_size; /* size of the LUT buffer */ + u8 lut_type; /* type of the LUT (i.e. VSI, PF, Global) */ + u8 *lut; /* input RSS LUT for set and output RSS LUT for get */ + u8 global_lut_id; /* only valid when lut_type is global */ +}; + /* Checksum and Shadow RAM pointers */ #define ICE_SR_NVM_CTRL_WORD 0x00 #define ICE_SR_BOOT_CFG_PTR 0x132 @@ -916,4 +1014,9 @@ struct ice_hw_port_stats { #define ICE_FW_API_LLDP_FLTR_MIN 7 #define ICE_FW_API_LLDP_FLTR_PATCH 1 +/* AQ API version for report default configuration */ +#define ICE_FW_API_REPORT_DFLT_CFG_MAJ 1 +#define ICE_FW_API_REPORT_DFLT_CFG_MIN 7 +#define ICE_FW_API_REPORT_DFLT_CFG_PATCH 3 + #endif /* _ICE_TYPE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c new file mode 100644 index 000000000000..9feebe5f556c --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c @@ -0,0 +1,171 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2021, Intel Corporation. */ + +#include "ice_virtchnl_allowlist.h" + +/* Purpose of this file is to share functionality to allowlist or denylist + * opcodes used in PF <-> VF communication. Group of opcodes: + * - default -> should be always allowed after creating VF, + * default_allowlist_opcodes + * - opcodes needed by VF to work correctly, but not associated with caps -> + * should be allowed after successful VF resources allocation, + * working_allowlist_opcodes + * - opcodes needed by VF when caps are activated + * + * Caps that don't use new opcodes (no opcodes should be allowed): + * - VIRTCHNL_VF_OFFLOAD_RSS_AQ + * - VIRTCHNL_VF_OFFLOAD_RSS_REG + * - VIRTCHNL_VF_OFFLOAD_WB_ON_ITR + * - VIRTCHNL_VF_OFFLOAD_CRC + * - VIRTCHNL_VF_OFFLOAD_RX_POLLING + * - VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 + * - VIRTCHNL_VF_OFFLOAD_ENCAP + * - VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM + * - VIRTCHNL_VF_OFFLOAD_RX_ENCAP_CSUM + * - VIRTCHNL_VF_OFFLOAD_USO + */ + +/* default opcodes to communicate with VF */ +static const u32 default_allowlist_opcodes[] = { + VIRTCHNL_OP_GET_VF_RESOURCES, VIRTCHNL_OP_VERSION, VIRTCHNL_OP_RESET_VF, +}; + +/* opcodes supported after successful VIRTCHNL_OP_GET_VF_RESOURCES */ +static const u32 working_allowlist_opcodes[] = { + VIRTCHNL_OP_CONFIG_TX_QUEUE, VIRTCHNL_OP_CONFIG_RX_QUEUE, + VIRTCHNL_OP_CONFIG_VSI_QUEUES, VIRTCHNL_OP_CONFIG_IRQ_MAP, + VIRTCHNL_OP_ENABLE_QUEUES, VIRTCHNL_OP_DISABLE_QUEUES, + VIRTCHNL_OP_GET_STATS, VIRTCHNL_OP_EVENT, +}; + +/* VIRTCHNL_VF_OFFLOAD_L2 */ +static const u32 l2_allowlist_opcodes[] = { + VIRTCHNL_OP_ADD_ETH_ADDR, VIRTCHNL_OP_DEL_ETH_ADDR, + VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE, +}; + +/* VIRTCHNL_VF_OFFLOAD_REQ_QUEUES */ +static const u32 req_queues_allowlist_opcodes[] = { + VIRTCHNL_OP_REQUEST_QUEUES, +}; + +/* VIRTCHNL_VF_OFFLOAD_VLAN */ +static const u32 vlan_allowlist_opcodes[] = { + VIRTCHNL_OP_ADD_VLAN, VIRTCHNL_OP_DEL_VLAN, + VIRTCHNL_OP_ENABLE_VLAN_STRIPPING, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING, +}; + +/* VIRTCHNL_VF_OFFLOAD_RSS_PF */ +static const u32 rss_pf_allowlist_opcodes[] = { + VIRTCHNL_OP_CONFIG_RSS_KEY, VIRTCHNL_OP_CONFIG_RSS_LUT, + VIRTCHNL_OP_GET_RSS_HENA_CAPS, VIRTCHNL_OP_SET_RSS_HENA, +}; + +/* VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF */ +static const u32 adv_rss_pf_allowlist_opcodes[] = { + VIRTCHNL_OP_ADD_RSS_CFG, VIRTCHNL_OP_DEL_RSS_CFG, +}; + +/* VIRTCHNL_VF_OFFLOAD_FDIR_PF */ +static const u32 fdir_pf_allowlist_opcodes[] = { + VIRTCHNL_OP_ADD_FDIR_FILTER, VIRTCHNL_OP_DEL_FDIR_FILTER, +}; + +struct allowlist_opcode_info { + const u32 *opcodes; + size_t size; +}; + +#define BIT_INDEX(caps) (HWEIGHT((caps) - 1)) +#define ALLOW_ITEM(caps, list) \ + [BIT_INDEX(caps)] = { \ + .opcodes = list, \ + .size = ARRAY_SIZE(list) \ + } +static const struct allowlist_opcode_info allowlist_opcodes[] = { + ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_L2, l2_allowlist_opcodes), + ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_REQ_QUEUES, req_queues_allowlist_opcodes), + ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_VLAN, vlan_allowlist_opcodes), + ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_RSS_PF, rss_pf_allowlist_opcodes), + ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF, adv_rss_pf_allowlist_opcodes), + ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_FDIR_PF, fdir_pf_allowlist_opcodes), +}; + +/** + * ice_vc_is_opcode_allowed - check if this opcode is allowed on this VF + * @vf: pointer to VF structure + * @opcode: virtchnl opcode + * + * Return true if message is allowed on this VF + */ +bool ice_vc_is_opcode_allowed(struct ice_vf *vf, u32 opcode) +{ + if (opcode >= VIRTCHNL_OP_MAX) + return false; + + return test_bit(opcode, vf->opcodes_allowlist); +} + +/** + * ice_vc_allowlist_opcodes - allowlist selected opcodes + * @vf: pointer to VF structure + * @opcodes: array of opocodes to allowlist + * @size: size of opcodes array + * + * Function should be called to allowlist opcodes on VF. + */ +static void +ice_vc_allowlist_opcodes(struct ice_vf *vf, const u32 *opcodes, size_t size) +{ + unsigned int i; + + for (i = 0; i < size; i++) + set_bit(opcodes[i], vf->opcodes_allowlist); +} + +/** + * ice_vc_clear_allowlist - clear all allowlist opcodes + * @vf: pointer to VF structure + */ +static void ice_vc_clear_allowlist(struct ice_vf *vf) +{ + bitmap_zero(vf->opcodes_allowlist, VIRTCHNL_OP_MAX); +} + +/** + * ice_vc_set_default_allowlist - allowlist default opcodes for VF + * @vf: pointer to VF structure + */ +void ice_vc_set_default_allowlist(struct ice_vf *vf) +{ + ice_vc_clear_allowlist(vf); + ice_vc_allowlist_opcodes(vf, default_allowlist_opcodes, + ARRAY_SIZE(default_allowlist_opcodes)); +} + +/** + * ice_vc_set_working_allowlist - allowlist opcodes needed to by VF to work + * @vf: pointer to VF structure + * + * allowlist opcodes that aren't associated with specific caps, but + * are needed by VF to work. + */ +void ice_vc_set_working_allowlist(struct ice_vf *vf) +{ + ice_vc_allowlist_opcodes(vf, working_allowlist_opcodes, + ARRAY_SIZE(working_allowlist_opcodes)); +} + +/** + * ice_vc_set_caps_allowlist - allowlist VF opcodes according caps + * @vf: pointer to VF structure + */ +void ice_vc_set_caps_allowlist(struct ice_vf *vf) +{ + unsigned long caps = vf->driver_caps; + unsigned int i; + + for_each_set_bit(i, &caps, ARRAY_SIZE(allowlist_opcodes)) + ice_vc_allowlist_opcodes(vf, allowlist_opcodes[i].opcodes, + allowlist_opcodes[i].size); +} diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.h new file mode 100644 index 000000000000..d3ae86ded219 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2021, Intel Corporation. */ + +#ifndef _ICE_VIRTCHNL_ALLOWLIST_H_ +#define _ICE_VIRTCHNL_ALLOWLIST_H_ +#include "ice.h" + +bool ice_vc_is_opcode_allowed(struct ice_vf *vf, u32 opcode); + +void ice_vc_set_default_allowlist(struct ice_vf *vf); +void ice_vc_set_working_allowlist(struct ice_vf *vf); +void ice_vc_set_caps_allowlist(struct ice_vf *vf); +#endif /* _ICE_VIRTCHNL_ALLOWLIST_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c new file mode 100644 index 000000000000..eee180d8c024 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c @@ -0,0 +1,2204 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2021, Intel Corporation. */ + +#include "ice.h" +#include "ice_base.h" +#include "ice_lib.h" +#include "ice_flow.h" + +#define to_fltr_conf_from_desc(p) \ + container_of(p, struct virtchnl_fdir_fltr_conf, input) + +#define ICE_FLOW_PROF_TYPE_S 0 +#define ICE_FLOW_PROF_TYPE_M (0xFFFFFFFFULL << ICE_FLOW_PROF_TYPE_S) +#define ICE_FLOW_PROF_VSI_S 32 +#define ICE_FLOW_PROF_VSI_M (0xFFFFFFFFULL << ICE_FLOW_PROF_VSI_S) + +/* Flow profile ID format: + * [0:31] - flow type, flow + tun_offs + * [32:63] - VSI index + */ +#define ICE_FLOW_PROF_FD(vsi, flow, tun_offs) \ + ((u64)(((((flow) + (tun_offs)) & ICE_FLOW_PROF_TYPE_M)) | \ + (((u64)(vsi) << ICE_FLOW_PROF_VSI_S) & ICE_FLOW_PROF_VSI_M))) + +#define GTPU_TEID_OFFSET 4 +#define GTPU_EH_QFI_OFFSET 1 +#define GTPU_EH_QFI_MASK 0x3F +#define PFCP_S_OFFSET 0 +#define PFCP_S_MASK 0x1 +#define PFCP_PORT_NR 8805 + +#define FDIR_INSET_FLAG_ESP_S 0 +#define FDIR_INSET_FLAG_ESP_M BIT_ULL(FDIR_INSET_FLAG_ESP_S) +#define FDIR_INSET_FLAG_ESP_UDP BIT_ULL(FDIR_INSET_FLAG_ESP_S) +#define FDIR_INSET_FLAG_ESP_IPSEC (0ULL << FDIR_INSET_FLAG_ESP_S) + +enum ice_fdir_tunnel_type { + ICE_FDIR_TUNNEL_TYPE_NONE = 0, + ICE_FDIR_TUNNEL_TYPE_GTPU, + ICE_FDIR_TUNNEL_TYPE_GTPU_EH, +}; + +struct virtchnl_fdir_fltr_conf { + struct ice_fdir_fltr input; + enum ice_fdir_tunnel_type ttype; + u64 inset_flag; + u32 flow_id; +}; + +static enum virtchnl_proto_hdr_type vc_pattern_ether[] = { + VIRTCHNL_PROTO_HDR_ETH, + VIRTCHNL_PROTO_HDR_NONE, +}; + +static enum virtchnl_proto_hdr_type vc_pattern_ipv4[] = { + VIRTCHNL_PROTO_HDR_ETH, + VIRTCHNL_PROTO_HDR_IPV4, + VIRTCHNL_PROTO_HDR_NONE, +}; + +static enum virtchnl_proto_hdr_type vc_pattern_ipv4_tcp[] = { + VIRTCHNL_PROTO_HDR_ETH, + VIRTCHNL_PROTO_HDR_IPV4, + VIRTCHNL_PROTO_HDR_TCP, + VIRTCHNL_PROTO_HDR_NONE, +}; + +static enum virtchnl_proto_hdr_type vc_pattern_ipv4_udp[] = { + VIRTCHNL_PROTO_HDR_ETH, + VIRTCHNL_PROTO_HDR_IPV4, + VIRTCHNL_PROTO_HDR_UDP, + VIRTCHNL_PROTO_HDR_NONE, +}; + +static enum virtchnl_proto_hdr_type vc_pattern_ipv4_sctp[] = { + VIRTCHNL_PROTO_HDR_ETH, + VIRTCHNL_PROTO_HDR_IPV4, + VIRTCHNL_PROTO_HDR_SCTP, + VIRTCHNL_PROTO_HDR_NONE, +}; + +static enum virtchnl_proto_hdr_type vc_pattern_ipv6[] = { + VIRTCHNL_PROTO_HDR_ETH, + VIRTCHNL_PROTO_HDR_IPV6, + VIRTCHNL_PROTO_HDR_NONE, +}; + +static enum virtchnl_proto_hdr_type vc_pattern_ipv6_tcp[] = { + VIRTCHNL_PROTO_HDR_ETH, + VIRTCHNL_PROTO_HDR_IPV6, + VIRTCHNL_PROTO_HDR_TCP, + VIRTCHNL_PROTO_HDR_NONE, +}; + +static enum virtchnl_proto_hdr_type vc_pattern_ipv6_udp[] = { + VIRTCHNL_PROTO_HDR_ETH, + VIRTCHNL_PROTO_HDR_IPV6, + VIRTCHNL_PROTO_HDR_UDP, + VIRTCHNL_PROTO_HDR_NONE, +}; + +static enum virtchnl_proto_hdr_type vc_pattern_ipv6_sctp[] = { + VIRTCHNL_PROTO_HDR_ETH, + VIRTCHNL_PROTO_HDR_IPV6, + VIRTCHNL_PROTO_HDR_SCTP, + VIRTCHNL_PROTO_HDR_NONE, +}; + +static enum virtchnl_proto_hdr_type vc_pattern_ipv4_gtpu[] = { + VIRTCHNL_PROTO_HDR_ETH, + VIRTCHNL_PROTO_HDR_IPV4, + VIRTCHNL_PROTO_HDR_UDP, + VIRTCHNL_PROTO_HDR_GTPU_IP, + VIRTCHNL_PROTO_HDR_NONE, +}; + +static enum virtchnl_proto_hdr_type vc_pattern_ipv4_gtpu_eh[] = { + VIRTCHNL_PROTO_HDR_ETH, + VIRTCHNL_PROTO_HDR_IPV4, + VIRTCHNL_PROTO_HDR_UDP, + VIRTCHNL_PROTO_HDR_GTPU_IP, + VIRTCHNL_PROTO_HDR_GTPU_EH, + VIRTCHNL_PROTO_HDR_NONE, +}; + +static enum virtchnl_proto_hdr_type vc_pattern_ipv4_l2tpv3[] = { + VIRTCHNL_PROTO_HDR_ETH, + VIRTCHNL_PROTO_HDR_IPV4, + VIRTCHNL_PROTO_HDR_L2TPV3, + VIRTCHNL_PROTO_HDR_NONE, +}; + +static enum virtchnl_proto_hdr_type vc_pattern_ipv6_l2tpv3[] = { + VIRTCHNL_PROTO_HDR_ETH, + VIRTCHNL_PROTO_HDR_IPV6, + VIRTCHNL_PROTO_HDR_L2TPV3, + VIRTCHNL_PROTO_HDR_NONE, +}; + +static enum virtchnl_proto_hdr_type vc_pattern_ipv4_esp[] = { + VIRTCHNL_PROTO_HDR_ETH, + VIRTCHNL_PROTO_HDR_IPV4, + VIRTCHNL_PROTO_HDR_ESP, + VIRTCHNL_PROTO_HDR_NONE, +}; + +static enum virtchnl_proto_hdr_type vc_pattern_ipv6_esp[] = { + VIRTCHNL_PROTO_HDR_ETH, + VIRTCHNL_PROTO_HDR_IPV6, + VIRTCHNL_PROTO_HDR_ESP, + VIRTCHNL_PROTO_HDR_NONE, +}; + +static enum virtchnl_proto_hdr_type vc_pattern_ipv4_ah[] = { + VIRTCHNL_PROTO_HDR_ETH, + VIRTCHNL_PROTO_HDR_IPV4, + VIRTCHNL_PROTO_HDR_AH, + VIRTCHNL_PROTO_HDR_NONE, +}; + +static enum virtchnl_proto_hdr_type vc_pattern_ipv6_ah[] = { + VIRTCHNL_PROTO_HDR_ETH, + VIRTCHNL_PROTO_HDR_IPV6, + VIRTCHNL_PROTO_HDR_AH, + VIRTCHNL_PROTO_HDR_NONE, +}; + +static enum virtchnl_proto_hdr_type vc_pattern_ipv4_nat_t_esp[] = { + VIRTCHNL_PROTO_HDR_ETH, + VIRTCHNL_PROTO_HDR_IPV4, + VIRTCHNL_PROTO_HDR_UDP, + VIRTCHNL_PROTO_HDR_ESP, + VIRTCHNL_PROTO_HDR_NONE, +}; + +static enum virtchnl_proto_hdr_type vc_pattern_ipv6_nat_t_esp[] = { + VIRTCHNL_PROTO_HDR_ETH, + VIRTCHNL_PROTO_HDR_IPV6, + VIRTCHNL_PROTO_HDR_UDP, + VIRTCHNL_PROTO_HDR_ESP, + VIRTCHNL_PROTO_HDR_NONE, +}; + +static enum virtchnl_proto_hdr_type vc_pattern_ipv4_pfcp[] = { + VIRTCHNL_PROTO_HDR_ETH, + VIRTCHNL_PROTO_HDR_IPV4, + VIRTCHNL_PROTO_HDR_UDP, + VIRTCHNL_PROTO_HDR_PFCP, + VIRTCHNL_PROTO_HDR_NONE, +}; + +static enum virtchnl_proto_hdr_type vc_pattern_ipv6_pfcp[] = { + VIRTCHNL_PROTO_HDR_ETH, + VIRTCHNL_PROTO_HDR_IPV6, + VIRTCHNL_PROTO_HDR_UDP, + VIRTCHNL_PROTO_HDR_PFCP, + VIRTCHNL_PROTO_HDR_NONE, +}; + +struct virtchnl_fdir_pattern_match_item { + enum virtchnl_proto_hdr_type *list; + u64 input_set; + u64 *meta; +}; + +static const struct virtchnl_fdir_pattern_match_item vc_fdir_pattern_os[] = { + {vc_pattern_ipv4, 0, NULL}, + {vc_pattern_ipv4_tcp, 0, NULL}, + {vc_pattern_ipv4_udp, 0, NULL}, + {vc_pattern_ipv4_sctp, 0, NULL}, + {vc_pattern_ipv6, 0, NULL}, + {vc_pattern_ipv6_tcp, 0, NULL}, + {vc_pattern_ipv6_udp, 0, NULL}, + {vc_pattern_ipv6_sctp, 0, NULL}, +}; + +static const struct virtchnl_fdir_pattern_match_item vc_fdir_pattern_comms[] = { + {vc_pattern_ipv4, 0, NULL}, + {vc_pattern_ipv4_tcp, 0, NULL}, + {vc_pattern_ipv4_udp, 0, NULL}, + {vc_pattern_ipv4_sctp, 0, NULL}, + {vc_pattern_ipv6, 0, NULL}, + {vc_pattern_ipv6_tcp, 0, NULL}, + {vc_pattern_ipv6_udp, 0, NULL}, + {vc_pattern_ipv6_sctp, 0, NULL}, + {vc_pattern_ether, 0, NULL}, + {vc_pattern_ipv4_gtpu, 0, NULL}, + {vc_pattern_ipv4_gtpu_eh, 0, NULL}, + {vc_pattern_ipv4_l2tpv3, 0, NULL}, + {vc_pattern_ipv6_l2tpv3, 0, NULL}, + {vc_pattern_ipv4_esp, 0, NULL}, + {vc_pattern_ipv6_esp, 0, NULL}, + {vc_pattern_ipv4_ah, 0, NULL}, + {vc_pattern_ipv6_ah, 0, NULL}, + {vc_pattern_ipv4_nat_t_esp, 0, NULL}, + {vc_pattern_ipv6_nat_t_esp, 0, NULL}, + {vc_pattern_ipv4_pfcp, 0, NULL}, + {vc_pattern_ipv6_pfcp, 0, NULL}, +}; + +struct virtchnl_fdir_inset_map { + enum virtchnl_proto_hdr_field field; + enum ice_flow_field fld; + u64 flag; + u64 mask; +}; + +static const struct virtchnl_fdir_inset_map fdir_inset_map[] = { + {VIRTCHNL_PROTO_HDR_ETH_ETHERTYPE, ICE_FLOW_FIELD_IDX_ETH_TYPE, 0, 0}, + {VIRTCHNL_PROTO_HDR_IPV4_SRC, ICE_FLOW_FIELD_IDX_IPV4_SA, 0, 0}, + {VIRTCHNL_PROTO_HDR_IPV4_DST, ICE_FLOW_FIELD_IDX_IPV4_DA, 0, 0}, + {VIRTCHNL_PROTO_HDR_IPV4_DSCP, ICE_FLOW_FIELD_IDX_IPV4_DSCP, 0, 0}, + {VIRTCHNL_PROTO_HDR_IPV4_TTL, ICE_FLOW_FIELD_IDX_IPV4_TTL, 0, 0}, + {VIRTCHNL_PROTO_HDR_IPV4_PROT, ICE_FLOW_FIELD_IDX_IPV4_PROT, 0, 0}, + {VIRTCHNL_PROTO_HDR_IPV6_SRC, ICE_FLOW_FIELD_IDX_IPV6_SA, 0, 0}, + {VIRTCHNL_PROTO_HDR_IPV6_DST, ICE_FLOW_FIELD_IDX_IPV6_DA, 0, 0}, + {VIRTCHNL_PROTO_HDR_IPV6_TC, ICE_FLOW_FIELD_IDX_IPV6_DSCP, 0, 0}, + {VIRTCHNL_PROTO_HDR_IPV6_HOP_LIMIT, ICE_FLOW_FIELD_IDX_IPV6_TTL, 0, 0}, + {VIRTCHNL_PROTO_HDR_IPV6_PROT, ICE_FLOW_FIELD_IDX_IPV6_PROT, 0, 0}, + {VIRTCHNL_PROTO_HDR_UDP_SRC_PORT, ICE_FLOW_FIELD_IDX_UDP_SRC_PORT, 0, 0}, + {VIRTCHNL_PROTO_HDR_UDP_DST_PORT, ICE_FLOW_FIELD_IDX_UDP_DST_PORT, 0, 0}, + {VIRTCHNL_PROTO_HDR_TCP_SRC_PORT, ICE_FLOW_FIELD_IDX_TCP_SRC_PORT, 0, 0}, + {VIRTCHNL_PROTO_HDR_TCP_DST_PORT, ICE_FLOW_FIELD_IDX_TCP_DST_PORT, 0, 0}, + {VIRTCHNL_PROTO_HDR_SCTP_SRC_PORT, ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT, 0, 0}, + {VIRTCHNL_PROTO_HDR_SCTP_DST_PORT, ICE_FLOW_FIELD_IDX_SCTP_DST_PORT, 0, 0}, + {VIRTCHNL_PROTO_HDR_GTPU_IP_TEID, ICE_FLOW_FIELD_IDX_GTPU_IP_TEID, 0, 0}, + {VIRTCHNL_PROTO_HDR_GTPU_EH_QFI, ICE_FLOW_FIELD_IDX_GTPU_EH_QFI, 0, 0}, + {VIRTCHNL_PROTO_HDR_ESP_SPI, ICE_FLOW_FIELD_IDX_ESP_SPI, + FDIR_INSET_FLAG_ESP_IPSEC, FDIR_INSET_FLAG_ESP_M}, + {VIRTCHNL_PROTO_HDR_ESP_SPI, ICE_FLOW_FIELD_IDX_NAT_T_ESP_SPI, + FDIR_INSET_FLAG_ESP_UDP, FDIR_INSET_FLAG_ESP_M}, + {VIRTCHNL_PROTO_HDR_AH_SPI, ICE_FLOW_FIELD_IDX_AH_SPI, 0, 0}, + {VIRTCHNL_PROTO_HDR_L2TPV3_SESS_ID, ICE_FLOW_FIELD_IDX_L2TPV3_SESS_ID, 0, 0}, + {VIRTCHNL_PROTO_HDR_PFCP_S_FIELD, ICE_FLOW_FIELD_IDX_UDP_DST_PORT, 0, 0}, +}; + +/** + * ice_vc_fdir_param_check + * @vf: pointer to the VF structure + * @vsi_id: VF relative VSI ID + * + * Check for the valid VSI ID, PF's state and VF's state + * + * Return: 0 on success, and -EINVAL on error. + */ +static int +ice_vc_fdir_param_check(struct ice_vf *vf, u16 vsi_id) +{ + struct ice_pf *pf = vf->pf; + + if (!test_bit(ICE_FLAG_FD_ENA, pf->flags)) + return -EINVAL; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) + return -EINVAL; + + if (!(vf->driver_caps & VIRTCHNL_VF_OFFLOAD_FDIR_PF)) + return -EINVAL; + + if (vsi_id != vf->lan_vsi_num) + return -EINVAL; + + if (!ice_vc_isvalid_vsi_id(vf, vsi_id)) + return -EINVAL; + + if (!pf->vsi[vf->lan_vsi_idx]) + return -EINVAL; + + return 0; +} + +/** + * ice_vf_start_ctrl_vsi + * @vf: pointer to the VF structure + * + * Allocate ctrl_vsi for the first time and open the ctrl_vsi port for VF + * + * Return: 0 on success, and other on error. + */ +static int ice_vf_start_ctrl_vsi(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + struct ice_vsi *ctrl_vsi; + struct device *dev; + int err; + + dev = ice_pf_to_dev(pf); + if (vf->ctrl_vsi_idx != ICE_NO_VSI) + return -EEXIST; + + ctrl_vsi = ice_vf_ctrl_vsi_setup(vf); + if (!ctrl_vsi) { + dev_dbg(dev, "Could not setup control VSI for VF %d\n", + vf->vf_id); + return -ENOMEM; + } + + err = ice_vsi_open_ctrl(ctrl_vsi); + if (err) { + dev_dbg(dev, "Could not open control VSI for VF %d\n", + vf->vf_id); + goto err_vsi_open; + } + + return 0; + +err_vsi_open: + ice_vsi_release(ctrl_vsi); + if (vf->ctrl_vsi_idx != ICE_NO_VSI) { + pf->vsi[vf->ctrl_vsi_idx] = NULL; + vf->ctrl_vsi_idx = ICE_NO_VSI; + } + return err; +} + +/** + * ice_vc_fdir_alloc_prof - allocate profile for this filter flow type + * @vf: pointer to the VF structure + * @flow: filter flow type + * + * Return: 0 on success, and other on error. + */ +static int +ice_vc_fdir_alloc_prof(struct ice_vf *vf, enum ice_fltr_ptype flow) +{ + struct ice_vf_fdir *fdir = &vf->fdir; + + if (!fdir->fdir_prof) { + fdir->fdir_prof = devm_kcalloc(ice_pf_to_dev(vf->pf), + ICE_FLTR_PTYPE_MAX, + sizeof(*fdir->fdir_prof), + GFP_KERNEL); + if (!fdir->fdir_prof) + return -ENOMEM; + } + + if (!fdir->fdir_prof[flow]) { + fdir->fdir_prof[flow] = devm_kzalloc(ice_pf_to_dev(vf->pf), + sizeof(**fdir->fdir_prof), + GFP_KERNEL); + if (!fdir->fdir_prof[flow]) + return -ENOMEM; + } + + return 0; +} + +/** + * ice_vc_fdir_free_prof - free profile for this filter flow type + * @vf: pointer to the VF structure + * @flow: filter flow type + */ +static void +ice_vc_fdir_free_prof(struct ice_vf *vf, enum ice_fltr_ptype flow) +{ + struct ice_vf_fdir *fdir = &vf->fdir; + + if (!fdir->fdir_prof) + return; + + if (!fdir->fdir_prof[flow]) + return; + + devm_kfree(ice_pf_to_dev(vf->pf), fdir->fdir_prof[flow]); + fdir->fdir_prof[flow] = NULL; +} + +/** + * ice_vc_fdir_free_prof_all - free all the profile for this VF + * @vf: pointer to the VF structure + */ +static void ice_vc_fdir_free_prof_all(struct ice_vf *vf) +{ + struct ice_vf_fdir *fdir = &vf->fdir; + enum ice_fltr_ptype flow; + + if (!fdir->fdir_prof) + return; + + for (flow = ICE_FLTR_PTYPE_NONF_NONE; flow < ICE_FLTR_PTYPE_MAX; flow++) + ice_vc_fdir_free_prof(vf, flow); + + devm_kfree(ice_pf_to_dev(vf->pf), fdir->fdir_prof); + fdir->fdir_prof = NULL; +} + +/** + * ice_vc_fdir_parse_flow_fld + * @proto_hdr: virtual channel protocol filter header + * @conf: FDIR configuration for each filter + * @fld: field type array + * @fld_cnt: field counter + * + * Parse the virtual channel filter header and store them into field type array + * + * Return: 0 on success, and other on error. + */ +static int +ice_vc_fdir_parse_flow_fld(struct virtchnl_proto_hdr *proto_hdr, + struct virtchnl_fdir_fltr_conf *conf, + enum ice_flow_field *fld, int *fld_cnt) +{ + struct virtchnl_proto_hdr hdr; + u32 i; + + memcpy(&hdr, proto_hdr, sizeof(hdr)); + + for (i = 0; (i < ARRAY_SIZE(fdir_inset_map)) && + VIRTCHNL_GET_PROTO_HDR_FIELD(&hdr); i++) + if (VIRTCHNL_TEST_PROTO_HDR(&hdr, fdir_inset_map[i].field)) { + if (fdir_inset_map[i].mask && + ((fdir_inset_map[i].mask & conf->inset_flag) != + fdir_inset_map[i].flag)) + continue; + + fld[*fld_cnt] = fdir_inset_map[i].fld; + *fld_cnt += 1; + if (*fld_cnt >= ICE_FLOW_FIELD_IDX_MAX) + return -EINVAL; + VIRTCHNL_DEL_PROTO_HDR_FIELD(&hdr, + fdir_inset_map[i].field); + } + + return 0; +} + +/** + * ice_vc_fdir_set_flow_fld + * @vf: pointer to the VF structure + * @fltr: virtual channel add cmd buffer + * @conf: FDIR configuration for each filter + * @seg: array of one or more packet segments that describe the flow + * + * Parse the virtual channel add msg buffer's field vector and store them into + * flow's packet segment field + * + * Return: 0 on success, and other on error. + */ +static int +ice_vc_fdir_set_flow_fld(struct ice_vf *vf, struct virtchnl_fdir_add *fltr, + struct virtchnl_fdir_fltr_conf *conf, + struct ice_flow_seg_info *seg) +{ + struct virtchnl_fdir_rule *rule = &fltr->rule_cfg; + enum ice_flow_field fld[ICE_FLOW_FIELD_IDX_MAX]; + struct device *dev = ice_pf_to_dev(vf->pf); + struct virtchnl_proto_hdrs *proto; + int fld_cnt = 0; + int i; + + proto = &rule->proto_hdrs; + for (i = 0; i < proto->count; i++) { + struct virtchnl_proto_hdr *hdr = &proto->proto_hdr[i]; + int ret; + + ret = ice_vc_fdir_parse_flow_fld(hdr, conf, fld, &fld_cnt); + if (ret) + return ret; + } + + if (fld_cnt == 0) { + dev_dbg(dev, "Empty input set for VF %d\n", vf->vf_id); + return -EINVAL; + } + + for (i = 0; i < fld_cnt; i++) + ice_flow_set_fld(seg, fld[i], + ICE_FLOW_FLD_OFF_INVAL, + ICE_FLOW_FLD_OFF_INVAL, + ICE_FLOW_FLD_OFF_INVAL, false); + + return 0; +} + +/** + * ice_vc_fdir_set_flow_hdr - config the flow's packet segment header + * @vf: pointer to the VF structure + * @conf: FDIR configuration for each filter + * @seg: array of one or more packet segments that describe the flow + * + * Return: 0 on success, and other on error. + */ +static int +ice_vc_fdir_set_flow_hdr(struct ice_vf *vf, + struct virtchnl_fdir_fltr_conf *conf, + struct ice_flow_seg_info *seg) +{ + enum ice_fltr_ptype flow = conf->input.flow_type; + enum ice_fdir_tunnel_type ttype = conf->ttype; + struct device *dev = ice_pf_to_dev(vf->pf); + + switch (flow) { + case ICE_FLTR_PTYPE_NON_IP_L2: + ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_ETH_NON_IP); + break; + case ICE_FLTR_PTYPE_NONF_IPV4_L2TPV3: + ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_L2TPV3 | + ICE_FLOW_SEG_HDR_IPV4 | + ICE_FLOW_SEG_HDR_IPV_OTHER); + break; + case ICE_FLTR_PTYPE_NONF_IPV4_ESP: + ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_ESP | + ICE_FLOW_SEG_HDR_IPV4 | + ICE_FLOW_SEG_HDR_IPV_OTHER); + break; + case ICE_FLTR_PTYPE_NONF_IPV4_AH: + ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_AH | + ICE_FLOW_SEG_HDR_IPV4 | + ICE_FLOW_SEG_HDR_IPV_OTHER); + break; + case ICE_FLTR_PTYPE_NONF_IPV4_NAT_T_ESP: + ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_NAT_T_ESP | + ICE_FLOW_SEG_HDR_IPV4 | + ICE_FLOW_SEG_HDR_IPV_OTHER); + break; + case ICE_FLTR_PTYPE_NONF_IPV4_PFCP_NODE: + ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_PFCP_NODE | + ICE_FLOW_SEG_HDR_IPV4 | + ICE_FLOW_SEG_HDR_IPV_OTHER); + break; + case ICE_FLTR_PTYPE_NONF_IPV4_PFCP_SESSION: + ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_PFCP_SESSION | + ICE_FLOW_SEG_HDR_IPV4 | + ICE_FLOW_SEG_HDR_IPV_OTHER); + break; + case ICE_FLTR_PTYPE_NONF_IPV4_OTHER: + ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_IPV4 | + ICE_FLOW_SEG_HDR_IPV_OTHER); + break; + case ICE_FLTR_PTYPE_NONF_IPV4_TCP: + ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_TCP | + ICE_FLOW_SEG_HDR_IPV4 | + ICE_FLOW_SEG_HDR_IPV_OTHER); + break; + case ICE_FLTR_PTYPE_NONF_IPV4_UDP: + ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_UDP | + ICE_FLOW_SEG_HDR_IPV4 | + ICE_FLOW_SEG_HDR_IPV_OTHER); + break; + case ICE_FLTR_PTYPE_NONF_IPV4_GTPU_IPV4_UDP: + case ICE_FLTR_PTYPE_NONF_IPV4_GTPU_IPV4_TCP: + case ICE_FLTR_PTYPE_NONF_IPV4_GTPU_IPV4_ICMP: + case ICE_FLTR_PTYPE_NONF_IPV4_GTPU_IPV4_OTHER: + if (ttype == ICE_FDIR_TUNNEL_TYPE_GTPU) { + ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_GTPU_IP | + ICE_FLOW_SEG_HDR_IPV4 | + ICE_FLOW_SEG_HDR_IPV_OTHER); + } else if (ttype == ICE_FDIR_TUNNEL_TYPE_GTPU_EH) { + ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_GTPU_EH | + ICE_FLOW_SEG_HDR_GTPU_IP | + ICE_FLOW_SEG_HDR_IPV4 | + ICE_FLOW_SEG_HDR_IPV_OTHER); + } else { + dev_dbg(dev, "Invalid tunnel type 0x%x for VF %d\n", + flow, vf->vf_id); + return -EINVAL; + } + break; + case ICE_FLTR_PTYPE_NONF_IPV4_SCTP: + ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_SCTP | + ICE_FLOW_SEG_HDR_IPV4 | + ICE_FLOW_SEG_HDR_IPV_OTHER); + break; + case ICE_FLTR_PTYPE_NONF_IPV6_L2TPV3: + ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_L2TPV3 | + ICE_FLOW_SEG_HDR_IPV6 | + ICE_FLOW_SEG_HDR_IPV_OTHER); + break; + case ICE_FLTR_PTYPE_NONF_IPV6_ESP: + ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_ESP | + ICE_FLOW_SEG_HDR_IPV6 | + ICE_FLOW_SEG_HDR_IPV_OTHER); + break; + case ICE_FLTR_PTYPE_NONF_IPV6_AH: + ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_AH | + ICE_FLOW_SEG_HDR_IPV6 | + ICE_FLOW_SEG_HDR_IPV_OTHER); + break; + case ICE_FLTR_PTYPE_NONF_IPV6_NAT_T_ESP: + ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_NAT_T_ESP | + ICE_FLOW_SEG_HDR_IPV6 | + ICE_FLOW_SEG_HDR_IPV_OTHER); + break; + case ICE_FLTR_PTYPE_NONF_IPV6_PFCP_NODE: + ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_PFCP_NODE | + ICE_FLOW_SEG_HDR_IPV6 | + ICE_FLOW_SEG_HDR_IPV_OTHER); + break; + case ICE_FLTR_PTYPE_NONF_IPV6_PFCP_SESSION: + ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_PFCP_SESSION | + ICE_FLOW_SEG_HDR_IPV6 | + ICE_FLOW_SEG_HDR_IPV_OTHER); + break; + case ICE_FLTR_PTYPE_NONF_IPV6_OTHER: + ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_IPV6 | + ICE_FLOW_SEG_HDR_IPV_OTHER); + break; + case ICE_FLTR_PTYPE_NONF_IPV6_TCP: + ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_TCP | + ICE_FLOW_SEG_HDR_IPV6 | + ICE_FLOW_SEG_HDR_IPV_OTHER); + break; + case ICE_FLTR_PTYPE_NONF_IPV6_UDP: + ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_UDP | + ICE_FLOW_SEG_HDR_IPV6 | + ICE_FLOW_SEG_HDR_IPV_OTHER); + break; + case ICE_FLTR_PTYPE_NONF_IPV6_SCTP: + ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_SCTP | + ICE_FLOW_SEG_HDR_IPV6 | + ICE_FLOW_SEG_HDR_IPV_OTHER); + break; + default: + dev_dbg(dev, "Invalid flow type 0x%x for VF %d failed\n", + flow, vf->vf_id); + return -EINVAL; + } + + return 0; +} + +/** + * ice_vc_fdir_rem_prof - remove profile for this filter flow type + * @vf: pointer to the VF structure + * @flow: filter flow type + * @tun: 0 implies non-tunnel type filter, 1 implies tunnel type filter + */ +static void +ice_vc_fdir_rem_prof(struct ice_vf *vf, enum ice_fltr_ptype flow, int tun) +{ + struct ice_vf_fdir *fdir = &vf->fdir; + struct ice_fd_hw_prof *vf_prof; + struct ice_pf *pf = vf->pf; + struct ice_vsi *vf_vsi; + struct device *dev; + struct ice_hw *hw; + u64 prof_id; + int i; + + dev = ice_pf_to_dev(pf); + hw = &pf->hw; + if (!fdir->fdir_prof || !fdir->fdir_prof[flow]) + return; + + vf_prof = fdir->fdir_prof[flow]; + + vf_vsi = pf->vsi[vf->lan_vsi_idx]; + if (!vf_vsi) { + dev_dbg(dev, "NULL vf %d vsi pointer\n", vf->vf_id); + return; + } + + if (!fdir->prof_entry_cnt[flow][tun]) + return; + + prof_id = ICE_FLOW_PROF_FD(vf_vsi->vsi_num, + flow, tun ? ICE_FLTR_PTYPE_MAX : 0); + + for (i = 0; i < fdir->prof_entry_cnt[flow][tun]; i++) + if (vf_prof->entry_h[i][tun]) { + u16 vsi_num = ice_get_hw_vsi_num(hw, vf_prof->vsi_h[i]); + + ice_rem_prof_id_flow(hw, ICE_BLK_FD, vsi_num, prof_id); + ice_flow_rem_entry(hw, ICE_BLK_FD, + vf_prof->entry_h[i][tun]); + vf_prof->entry_h[i][tun] = 0; + } + + ice_flow_rem_prof(hw, ICE_BLK_FD, prof_id); + devm_kfree(dev, vf_prof->fdir_seg[tun]); + vf_prof->fdir_seg[tun] = NULL; + + for (i = 0; i < vf_prof->cnt; i++) + vf_prof->vsi_h[i] = 0; + + fdir->prof_entry_cnt[flow][tun] = 0; +} + +/** + * ice_vc_fdir_rem_prof_all - remove profile for this VF + * @vf: pointer to the VF structure + */ +static void ice_vc_fdir_rem_prof_all(struct ice_vf *vf) +{ + enum ice_fltr_ptype flow; + + for (flow = ICE_FLTR_PTYPE_NONF_NONE; + flow < ICE_FLTR_PTYPE_MAX; flow++) { + ice_vc_fdir_rem_prof(vf, flow, 0); + ice_vc_fdir_rem_prof(vf, flow, 1); + } +} + +/** + * ice_vc_fdir_write_flow_prof + * @vf: pointer to the VF structure + * @flow: filter flow type + * @seg: array of one or more packet segments that describe the flow + * @tun: 0 implies non-tunnel type filter, 1 implies tunnel type filter + * + * Write the flow's profile config and packet segment into the hardware + * + * Return: 0 on success, and other on error. + */ +static int +ice_vc_fdir_write_flow_prof(struct ice_vf *vf, enum ice_fltr_ptype flow, + struct ice_flow_seg_info *seg, int tun) +{ + struct ice_vf_fdir *fdir = &vf->fdir; + struct ice_vsi *vf_vsi, *ctrl_vsi; + struct ice_flow_seg_info *old_seg; + struct ice_flow_prof *prof = NULL; + struct ice_fd_hw_prof *vf_prof; + enum ice_status status; + struct device *dev; + struct ice_pf *pf; + struct ice_hw *hw; + u64 entry1_h = 0; + u64 entry2_h = 0; + u64 prof_id; + int ret; + + pf = vf->pf; + dev = ice_pf_to_dev(pf); + hw = &pf->hw; + vf_vsi = pf->vsi[vf->lan_vsi_idx]; + if (!vf_vsi) + return -EINVAL; + + ctrl_vsi = pf->vsi[vf->ctrl_vsi_idx]; + if (!ctrl_vsi) + return -EINVAL; + + vf_prof = fdir->fdir_prof[flow]; + old_seg = vf_prof->fdir_seg[tun]; + if (old_seg) { + if (!memcmp(old_seg, seg, sizeof(*seg))) { + dev_dbg(dev, "Duplicated profile for VF %d!\n", + vf->vf_id); + return -EEXIST; + } + + if (fdir->fdir_fltr_cnt[flow][tun]) { + ret = -EINVAL; + dev_dbg(dev, "Input set conflicts for VF %d\n", + vf->vf_id); + goto err_exit; + } + + /* remove previously allocated profile */ + ice_vc_fdir_rem_prof(vf, flow, tun); + } + + prof_id = ICE_FLOW_PROF_FD(vf_vsi->vsi_num, flow, + tun ? ICE_FLTR_PTYPE_MAX : 0); + + status = ice_flow_add_prof(hw, ICE_BLK_FD, ICE_FLOW_RX, prof_id, seg, + tun + 1, &prof); + ret = ice_status_to_errno(status); + if (ret) { + dev_dbg(dev, "Could not add VSI flow 0x%x for VF %d\n", + flow, vf->vf_id); + goto err_exit; + } + + status = ice_flow_add_entry(hw, ICE_BLK_FD, prof_id, vf_vsi->idx, + vf_vsi->idx, ICE_FLOW_PRIO_NORMAL, + seg, &entry1_h); + ret = ice_status_to_errno(status); + if (ret) { + dev_dbg(dev, "Could not add flow 0x%x VSI entry for VF %d\n", + flow, vf->vf_id); + goto err_prof; + } + + status = ice_flow_add_entry(hw, ICE_BLK_FD, prof_id, vf_vsi->idx, + ctrl_vsi->idx, ICE_FLOW_PRIO_NORMAL, + seg, &entry2_h); + ret = ice_status_to_errno(status); + if (ret) { + dev_dbg(dev, + "Could not add flow 0x%x Ctrl VSI entry for VF %d\n", + flow, vf->vf_id); + goto err_entry_1; + } + + vf_prof->fdir_seg[tun] = seg; + vf_prof->cnt = 0; + fdir->prof_entry_cnt[flow][tun] = 0; + + vf_prof->entry_h[vf_prof->cnt][tun] = entry1_h; + vf_prof->vsi_h[vf_prof->cnt] = vf_vsi->idx; + vf_prof->cnt++; + fdir->prof_entry_cnt[flow][tun]++; + + vf_prof->entry_h[vf_prof->cnt][tun] = entry2_h; + vf_prof->vsi_h[vf_prof->cnt] = ctrl_vsi->idx; + vf_prof->cnt++; + fdir->prof_entry_cnt[flow][tun]++; + + return 0; + +err_entry_1: + ice_rem_prof_id_flow(hw, ICE_BLK_FD, + ice_get_hw_vsi_num(hw, vf_vsi->idx), prof_id); + ice_flow_rem_entry(hw, ICE_BLK_FD, entry1_h); +err_prof: + ice_flow_rem_prof(hw, ICE_BLK_FD, prof_id); +err_exit: + return ret; +} + +/** + * ice_vc_fdir_config_input_set + * @vf: pointer to the VF structure + * @fltr: virtual channel add cmd buffer + * @conf: FDIR configuration for each filter + * @tun: 0 implies non-tunnel type filter, 1 implies tunnel type filter + * + * Config the input set type and value for virtual channel add msg buffer + * + * Return: 0 on success, and other on error. + */ +static int +ice_vc_fdir_config_input_set(struct ice_vf *vf, struct virtchnl_fdir_add *fltr, + struct virtchnl_fdir_fltr_conf *conf, int tun) +{ + struct ice_fdir_fltr *input = &conf->input; + struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_flow_seg_info *seg; + enum ice_fltr_ptype flow; + int ret; + + flow = input->flow_type; + ret = ice_vc_fdir_alloc_prof(vf, flow); + if (ret) { + dev_dbg(dev, "Alloc flow prof for VF %d failed\n", vf->vf_id); + return ret; + } + + seg = devm_kzalloc(dev, sizeof(*seg), GFP_KERNEL); + if (!seg) + return -ENOMEM; + + ret = ice_vc_fdir_set_flow_fld(vf, fltr, conf, seg); + if (ret) { + dev_dbg(dev, "Set flow field for VF %d failed\n", vf->vf_id); + goto err_exit; + } + + ret = ice_vc_fdir_set_flow_hdr(vf, conf, seg); + if (ret) { + dev_dbg(dev, "Set flow hdr for VF %d failed\n", vf->vf_id); + goto err_exit; + } + + ret = ice_vc_fdir_write_flow_prof(vf, flow, seg, tun); + if (ret == -EEXIST) { + devm_kfree(dev, seg); + } else if (ret) { + dev_dbg(dev, "Write flow profile for VF %d failed\n", + vf->vf_id); + goto err_exit; + } + + return 0; + +err_exit: + devm_kfree(dev, seg); + return ret; +} + +/** + * ice_vc_fdir_match_pattern + * @fltr: virtual channel add cmd buffer + * @type: virtual channel protocol filter header type + * + * Matching the header type by comparing fltr and type's value. + * + * Return: true on success, and false on error. + */ +static bool +ice_vc_fdir_match_pattern(struct virtchnl_fdir_add *fltr, + enum virtchnl_proto_hdr_type *type) +{ + struct virtchnl_proto_hdrs *proto = &fltr->rule_cfg.proto_hdrs; + int i = 0; + + while ((i < proto->count) && + (*type == proto->proto_hdr[i].type) && + (*type != VIRTCHNL_PROTO_HDR_NONE)) { + type++; + i++; + } + + return ((i == proto->count) && (*type == VIRTCHNL_PROTO_HDR_NONE)); +} + +/** + * ice_vc_fdir_get_pattern - get while list pattern + * @vf: pointer to the VF info + * @len: filter list length + * + * Return: pointer to allowed filter list + */ +static const struct virtchnl_fdir_pattern_match_item * +ice_vc_fdir_get_pattern(struct ice_vf *vf, int *len) +{ + const struct virtchnl_fdir_pattern_match_item *item; + struct ice_pf *pf = vf->pf; + struct ice_hw *hw; + + hw = &pf->hw; + if (!strncmp(hw->active_pkg_name, "ICE COMMS Package", + sizeof(hw->active_pkg_name))) { + item = vc_fdir_pattern_comms; + *len = ARRAY_SIZE(vc_fdir_pattern_comms); + } else { + item = vc_fdir_pattern_os; + *len = ARRAY_SIZE(vc_fdir_pattern_os); + } + + return item; +} + +/** + * ice_vc_fdir_search_pattern + * @vf: pointer to the VF info + * @fltr: virtual channel add cmd buffer + * + * Search for matched pattern from supported pattern list + * + * Return: 0 on success, and other on error. + */ +static int +ice_vc_fdir_search_pattern(struct ice_vf *vf, struct virtchnl_fdir_add *fltr) +{ + const struct virtchnl_fdir_pattern_match_item *pattern; + int len, i; + + pattern = ice_vc_fdir_get_pattern(vf, &len); + + for (i = 0; i < len; i++) + if (ice_vc_fdir_match_pattern(fltr, pattern[i].list)) + return 0; + + return -EINVAL; +} + +/** + * ice_vc_fdir_parse_pattern + * @vf: pointer to the VF info + * @fltr: virtual channel add cmd buffer + * @conf: FDIR configuration for each filter + * + * Parse the virtual channel filter's pattern and store them into conf + * + * Return: 0 on success, and other on error. + */ +static int +ice_vc_fdir_parse_pattern(struct ice_vf *vf, struct virtchnl_fdir_add *fltr, + struct virtchnl_fdir_fltr_conf *conf) +{ + struct virtchnl_proto_hdrs *proto = &fltr->rule_cfg.proto_hdrs; + enum virtchnl_proto_hdr_type l3 = VIRTCHNL_PROTO_HDR_NONE; + enum virtchnl_proto_hdr_type l4 = VIRTCHNL_PROTO_HDR_NONE; + struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_fdir_fltr *input = &conf->input; + int i; + + if (proto->count > VIRTCHNL_MAX_NUM_PROTO_HDRS) { + dev_dbg(dev, "Invalid protocol count:0x%x for VF %d\n", + proto->count, vf->vf_id); + return -EINVAL; + } + + for (i = 0; i < proto->count; i++) { + struct virtchnl_proto_hdr *hdr = &proto->proto_hdr[i]; + struct ip_esp_hdr *esph; + struct ip_auth_hdr *ah; + struct sctphdr *sctph; + struct ipv6hdr *ip6h; + struct udphdr *udph; + struct tcphdr *tcph; + struct ethhdr *eth; + struct iphdr *iph; + u8 s_field; + u8 *rawh; + + switch (hdr->type) { + case VIRTCHNL_PROTO_HDR_ETH: + eth = (struct ethhdr *)hdr->buffer; + input->flow_type = ICE_FLTR_PTYPE_NON_IP_L2; + + if (hdr->field_selector) + input->ext_data.ether_type = eth->h_proto; + break; + case VIRTCHNL_PROTO_HDR_IPV4: + iph = (struct iphdr *)hdr->buffer; + l3 = VIRTCHNL_PROTO_HDR_IPV4; + input->flow_type = ICE_FLTR_PTYPE_NONF_IPV4_OTHER; + + if (hdr->field_selector) { + input->ip.v4.src_ip = iph->saddr; + input->ip.v4.dst_ip = iph->daddr; + input->ip.v4.tos = iph->tos; + input->ip.v4.proto = iph->protocol; + } + break; + case VIRTCHNL_PROTO_HDR_IPV6: + ip6h = (struct ipv6hdr *)hdr->buffer; + l3 = VIRTCHNL_PROTO_HDR_IPV6; + input->flow_type = ICE_FLTR_PTYPE_NONF_IPV6_OTHER; + + if (hdr->field_selector) { + memcpy(input->ip.v6.src_ip, + ip6h->saddr.in6_u.u6_addr8, + sizeof(ip6h->saddr)); + memcpy(input->ip.v6.dst_ip, + ip6h->daddr.in6_u.u6_addr8, + sizeof(ip6h->daddr)); + input->ip.v6.tc = ((u8)(ip6h->priority) << 4) | + (ip6h->flow_lbl[0] >> 4); + input->ip.v6.proto = ip6h->nexthdr; + } + break; + case VIRTCHNL_PROTO_HDR_TCP: + tcph = (struct tcphdr *)hdr->buffer; + if (l3 == VIRTCHNL_PROTO_HDR_IPV4) + input->flow_type = ICE_FLTR_PTYPE_NONF_IPV4_TCP; + else if (l3 == VIRTCHNL_PROTO_HDR_IPV6) + input->flow_type = ICE_FLTR_PTYPE_NONF_IPV6_TCP; + + if (hdr->field_selector) { + if (l3 == VIRTCHNL_PROTO_HDR_IPV4) { + input->ip.v4.src_port = tcph->source; + input->ip.v4.dst_port = tcph->dest; + } else if (l3 == VIRTCHNL_PROTO_HDR_IPV6) { + input->ip.v6.src_port = tcph->source; + input->ip.v6.dst_port = tcph->dest; + } + } + break; + case VIRTCHNL_PROTO_HDR_UDP: + udph = (struct udphdr *)hdr->buffer; + if (l3 == VIRTCHNL_PROTO_HDR_IPV4) + input->flow_type = ICE_FLTR_PTYPE_NONF_IPV4_UDP; + else if (l3 == VIRTCHNL_PROTO_HDR_IPV6) + input->flow_type = ICE_FLTR_PTYPE_NONF_IPV6_UDP; + + if (hdr->field_selector) { + if (l3 == VIRTCHNL_PROTO_HDR_IPV4) { + input->ip.v4.src_port = udph->source; + input->ip.v4.dst_port = udph->dest; + } else if (l3 == VIRTCHNL_PROTO_HDR_IPV6) { + input->ip.v6.src_port = udph->source; + input->ip.v6.dst_port = udph->dest; + } + } + break; + case VIRTCHNL_PROTO_HDR_SCTP: + sctph = (struct sctphdr *)hdr->buffer; + if (l3 == VIRTCHNL_PROTO_HDR_IPV4) + input->flow_type = + ICE_FLTR_PTYPE_NONF_IPV4_SCTP; + else if (l3 == VIRTCHNL_PROTO_HDR_IPV6) + input->flow_type = + ICE_FLTR_PTYPE_NONF_IPV6_SCTP; + + if (hdr->field_selector) { + if (l3 == VIRTCHNL_PROTO_HDR_IPV4) { + input->ip.v4.src_port = sctph->source; + input->ip.v4.dst_port = sctph->dest; + } else if (l3 == VIRTCHNL_PROTO_HDR_IPV6) { + input->ip.v6.src_port = sctph->source; + input->ip.v6.dst_port = sctph->dest; + } + } + break; + case VIRTCHNL_PROTO_HDR_L2TPV3: + if (l3 == VIRTCHNL_PROTO_HDR_IPV4) + input->flow_type = ICE_FLTR_PTYPE_NONF_IPV4_L2TPV3; + else if (l3 == VIRTCHNL_PROTO_HDR_IPV6) + input->flow_type = ICE_FLTR_PTYPE_NONF_IPV6_L2TPV3; + + if (hdr->field_selector) + input->l2tpv3_data.session_id = *((__be32 *)hdr->buffer); + break; + case VIRTCHNL_PROTO_HDR_ESP: + esph = (struct ip_esp_hdr *)hdr->buffer; + if (l3 == VIRTCHNL_PROTO_HDR_IPV4 && + l4 == VIRTCHNL_PROTO_HDR_UDP) + input->flow_type = ICE_FLTR_PTYPE_NONF_IPV4_NAT_T_ESP; + else if (l3 == VIRTCHNL_PROTO_HDR_IPV6 && + l4 == VIRTCHNL_PROTO_HDR_UDP) + input->flow_type = ICE_FLTR_PTYPE_NONF_IPV6_NAT_T_ESP; + else if (l3 == VIRTCHNL_PROTO_HDR_IPV4 && + l4 == VIRTCHNL_PROTO_HDR_NONE) + input->flow_type = ICE_FLTR_PTYPE_NONF_IPV4_ESP; + else if (l3 == VIRTCHNL_PROTO_HDR_IPV6 && + l4 == VIRTCHNL_PROTO_HDR_NONE) + input->flow_type = ICE_FLTR_PTYPE_NONF_IPV6_ESP; + + if (l4 == VIRTCHNL_PROTO_HDR_UDP) + conf->inset_flag |= FDIR_INSET_FLAG_ESP_UDP; + else + conf->inset_flag |= FDIR_INSET_FLAG_ESP_IPSEC; + + if (hdr->field_selector) { + if (l3 == VIRTCHNL_PROTO_HDR_IPV4) + input->ip.v4.sec_parm_idx = esph->spi; + else if (l3 == VIRTCHNL_PROTO_HDR_IPV6) + input->ip.v6.sec_parm_idx = esph->spi; + } + break; + case VIRTCHNL_PROTO_HDR_AH: + ah = (struct ip_auth_hdr *)hdr->buffer; + if (l3 == VIRTCHNL_PROTO_HDR_IPV4) + input->flow_type = ICE_FLTR_PTYPE_NONF_IPV4_AH; + else if (l3 == VIRTCHNL_PROTO_HDR_IPV6) + input->flow_type = ICE_FLTR_PTYPE_NONF_IPV6_AH; + + if (hdr->field_selector) { + if (l3 == VIRTCHNL_PROTO_HDR_IPV4) + input->ip.v4.sec_parm_idx = ah->spi; + else if (l3 == VIRTCHNL_PROTO_HDR_IPV6) + input->ip.v6.sec_parm_idx = ah->spi; + } + break; + case VIRTCHNL_PROTO_HDR_PFCP: + rawh = (u8 *)hdr->buffer; + s_field = (rawh[0] >> PFCP_S_OFFSET) & PFCP_S_MASK; + if (l3 == VIRTCHNL_PROTO_HDR_IPV4 && s_field == 0) + input->flow_type = ICE_FLTR_PTYPE_NONF_IPV4_PFCP_NODE; + else if (l3 == VIRTCHNL_PROTO_HDR_IPV4 && s_field == 1) + input->flow_type = ICE_FLTR_PTYPE_NONF_IPV4_PFCP_SESSION; + else if (l3 == VIRTCHNL_PROTO_HDR_IPV6 && s_field == 0) + input->flow_type = ICE_FLTR_PTYPE_NONF_IPV6_PFCP_NODE; + else if (l3 == VIRTCHNL_PROTO_HDR_IPV6 && s_field == 1) + input->flow_type = ICE_FLTR_PTYPE_NONF_IPV6_PFCP_SESSION; + + if (hdr->field_selector) { + if (l3 == VIRTCHNL_PROTO_HDR_IPV4) + input->ip.v4.dst_port = cpu_to_be16(PFCP_PORT_NR); + else if (l3 == VIRTCHNL_PROTO_HDR_IPV6) + input->ip.v6.dst_port = cpu_to_be16(PFCP_PORT_NR); + } + break; + case VIRTCHNL_PROTO_HDR_GTPU_IP: + rawh = (u8 *)hdr->buffer; + input->flow_type = ICE_FLTR_PTYPE_NONF_IPV4_GTPU_IPV4_OTHER; + + if (hdr->field_selector) + input->gtpu_data.teid = *(__be32 *)(&rawh[GTPU_TEID_OFFSET]); + conf->ttype = ICE_FDIR_TUNNEL_TYPE_GTPU; + break; + case VIRTCHNL_PROTO_HDR_GTPU_EH: + rawh = (u8 *)hdr->buffer; + + if (hdr->field_selector) + input->gtpu_data.qfi = rawh[GTPU_EH_QFI_OFFSET] & GTPU_EH_QFI_MASK; + conf->ttype = ICE_FDIR_TUNNEL_TYPE_GTPU_EH; + break; + default: + dev_dbg(dev, "Invalid header type 0x:%x for VF %d\n", + hdr->type, vf->vf_id); + return -EINVAL; + } + } + + return 0; +} + +/** + * ice_vc_fdir_parse_action + * @vf: pointer to the VF info + * @fltr: virtual channel add cmd buffer + * @conf: FDIR configuration for each filter + * + * Parse the virtual channel filter's action and store them into conf + * + * Return: 0 on success, and other on error. + */ +static int +ice_vc_fdir_parse_action(struct ice_vf *vf, struct virtchnl_fdir_add *fltr, + struct virtchnl_fdir_fltr_conf *conf) +{ + struct virtchnl_filter_action_set *as = &fltr->rule_cfg.action_set; + struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_fdir_fltr *input = &conf->input; + u32 dest_num = 0; + u32 mark_num = 0; + int i; + + if (as->count > VIRTCHNL_MAX_NUM_ACTIONS) { + dev_dbg(dev, "Invalid action numbers:0x%x for VF %d\n", + as->count, vf->vf_id); + return -EINVAL; + } + + for (i = 0; i < as->count; i++) { + struct virtchnl_filter_action *action = &as->actions[i]; + + switch (action->type) { + case VIRTCHNL_ACTION_PASSTHRU: + dest_num++; + input->dest_ctl = ICE_FLTR_PRGM_DESC_DEST_DIRECT_PKT_OTHER; + break; + case VIRTCHNL_ACTION_DROP: + dest_num++; + input->dest_ctl = ICE_FLTR_PRGM_DESC_DEST_DROP_PKT; + break; + case VIRTCHNL_ACTION_QUEUE: + dest_num++; + input->dest_ctl = ICE_FLTR_PRGM_DESC_DEST_DIRECT_PKT_QINDEX; + input->q_index = action->act_conf.queue.index; + break; + case VIRTCHNL_ACTION_Q_REGION: + dest_num++; + input->dest_ctl = ICE_FLTR_PRGM_DESC_DEST_DIRECT_PKT_QGROUP; + input->q_index = action->act_conf.queue.index; + input->q_region = action->act_conf.queue.region; + break; + case VIRTCHNL_ACTION_MARK: + mark_num++; + input->fltr_id = action->act_conf.mark_id; + input->fdid_prio = ICE_FXD_FLTR_QW1_FDID_PRI_THREE; + break; + default: + dev_dbg(dev, "Invalid action type:0x%x for VF %d\n", + action->type, vf->vf_id); + return -EINVAL; + } + } + + if (dest_num == 0 || dest_num >= 2) { + dev_dbg(dev, "Invalid destination action for VF %d\n", + vf->vf_id); + return -EINVAL; + } + + if (mark_num >= 2) { + dev_dbg(dev, "Too many mark actions for VF %d\n", vf->vf_id); + return -EINVAL; + } + + return 0; +} + +/** + * ice_vc_validate_fdir_fltr - validate the virtual channel filter + * @vf: pointer to the VF info + * @fltr: virtual channel add cmd buffer + * @conf: FDIR configuration for each filter + * + * Return: 0 on success, and other on error. + */ +static int +ice_vc_validate_fdir_fltr(struct ice_vf *vf, struct virtchnl_fdir_add *fltr, + struct virtchnl_fdir_fltr_conf *conf) +{ + int ret; + + ret = ice_vc_fdir_search_pattern(vf, fltr); + if (ret) + return ret; + + ret = ice_vc_fdir_parse_pattern(vf, fltr, conf); + if (ret) + return ret; + + return ice_vc_fdir_parse_action(vf, fltr, conf); +} + +/** + * ice_vc_fdir_comp_rules - compare if two filter rules have the same value + * @conf_a: FDIR configuration for filter a + * @conf_b: FDIR configuration for filter b + * + * Return: 0 on success, and other on error. + */ +static bool +ice_vc_fdir_comp_rules(struct virtchnl_fdir_fltr_conf *conf_a, + struct virtchnl_fdir_fltr_conf *conf_b) +{ + struct ice_fdir_fltr *a = &conf_a->input; + struct ice_fdir_fltr *b = &conf_b->input; + + if (conf_a->ttype != conf_b->ttype) + return false; + if (a->flow_type != b->flow_type) + return false; + if (memcmp(&a->ip, &b->ip, sizeof(a->ip))) + return false; + if (memcmp(&a->mask, &b->mask, sizeof(a->mask))) + return false; + if (memcmp(&a->gtpu_data, &b->gtpu_data, sizeof(a->gtpu_data))) + return false; + if (memcmp(&a->gtpu_mask, &b->gtpu_mask, sizeof(a->gtpu_mask))) + return false; + if (memcmp(&a->l2tpv3_data, &b->l2tpv3_data, sizeof(a->l2tpv3_data))) + return false; + if (memcmp(&a->l2tpv3_mask, &b->l2tpv3_mask, sizeof(a->l2tpv3_mask))) + return false; + if (memcmp(&a->ext_data, &b->ext_data, sizeof(a->ext_data))) + return false; + if (memcmp(&a->ext_mask, &b->ext_mask, sizeof(a->ext_mask))) + return false; + + return true; +} + +/** + * ice_vc_fdir_is_dup_fltr + * @vf: pointer to the VF info + * @conf: FDIR configuration for each filter + * + * Check if there is duplicated rule with same conf value + * + * Return: 0 true success, and false on error. + */ +static bool +ice_vc_fdir_is_dup_fltr(struct ice_vf *vf, struct virtchnl_fdir_fltr_conf *conf) +{ + struct ice_fdir_fltr *desc; + bool ret; + + list_for_each_entry(desc, &vf->fdir.fdir_rule_list, fltr_node) { + struct virtchnl_fdir_fltr_conf *node = + to_fltr_conf_from_desc(desc); + + ret = ice_vc_fdir_comp_rules(node, conf); + if (ret) + return true; + } + + return false; +} + +/** + * ice_vc_fdir_insert_entry + * @vf: pointer to the VF info + * @conf: FDIR configuration for each filter + * @id: pointer to ID value allocated by driver + * + * Insert FDIR conf entry into list and allocate ID for this filter + * + * Return: 0 true success, and other on error. + */ +static int +ice_vc_fdir_insert_entry(struct ice_vf *vf, + struct virtchnl_fdir_fltr_conf *conf, u32 *id) +{ + struct ice_fdir_fltr *input = &conf->input; + int i; + + /* alloc ID corresponding with conf */ + i = idr_alloc(&vf->fdir.fdir_rule_idr, conf, 0, + ICE_FDIR_MAX_FLTRS, GFP_KERNEL); + if (i < 0) + return -EINVAL; + *id = i; + + list_add(&input->fltr_node, &vf->fdir.fdir_rule_list); + return 0; +} + +/** + * ice_vc_fdir_remove_entry - remove FDIR conf entry by ID value + * @vf: pointer to the VF info + * @conf: FDIR configuration for each filter + * @id: filter rule's ID + */ +static void +ice_vc_fdir_remove_entry(struct ice_vf *vf, + struct virtchnl_fdir_fltr_conf *conf, u32 id) +{ + struct ice_fdir_fltr *input = &conf->input; + + idr_remove(&vf->fdir.fdir_rule_idr, id); + list_del(&input->fltr_node); +} + +/** + * ice_vc_fdir_lookup_entry - lookup FDIR conf entry by ID value + * @vf: pointer to the VF info + * @id: filter rule's ID + * + * Return: NULL on error, and other on success. + */ +static struct virtchnl_fdir_fltr_conf * +ice_vc_fdir_lookup_entry(struct ice_vf *vf, u32 id) +{ + return idr_find(&vf->fdir.fdir_rule_idr, id); +} + +/** + * ice_vc_fdir_flush_entry - remove all FDIR conf entry + * @vf: pointer to the VF info + */ +static void ice_vc_fdir_flush_entry(struct ice_vf *vf) +{ + struct virtchnl_fdir_fltr_conf *conf; + struct ice_fdir_fltr *desc, *temp; + + list_for_each_entry_safe(desc, temp, + &vf->fdir.fdir_rule_list, fltr_node) { + conf = to_fltr_conf_from_desc(desc); + list_del(&desc->fltr_node); + devm_kfree(ice_pf_to_dev(vf->pf), conf); + } +} + +/** + * ice_vc_fdir_write_fltr - write filter rule into hardware + * @vf: pointer to the VF info + * @conf: FDIR configuration for each filter + * @add: true implies add rule, false implies del rules + * @is_tun: false implies non-tunnel type filter, true implies tunnel filter + * + * Return: 0 on success, and other on error. + */ +static int ice_vc_fdir_write_fltr(struct ice_vf *vf, + struct virtchnl_fdir_fltr_conf *conf, + bool add, bool is_tun) +{ + struct ice_fdir_fltr *input = &conf->input; + struct ice_vsi *vsi, *ctrl_vsi; + struct ice_fltr_desc desc; + enum ice_status status; + struct device *dev; + struct ice_pf *pf; + struct ice_hw *hw; + int ret; + u8 *pkt; + + pf = vf->pf; + dev = ice_pf_to_dev(pf); + hw = &pf->hw; + vsi = pf->vsi[vf->lan_vsi_idx]; + if (!vsi) { + dev_dbg(dev, "Invalid vsi for VF %d\n", vf->vf_id); + return -EINVAL; + } + + input->dest_vsi = vsi->idx; + input->comp_report = ICE_FXD_FLTR_QW0_COMP_REPORT_SW; + + ctrl_vsi = pf->vsi[vf->ctrl_vsi_idx]; + if (!ctrl_vsi) { + dev_dbg(dev, "Invalid ctrl_vsi for VF %d\n", vf->vf_id); + return -EINVAL; + } + + pkt = devm_kzalloc(dev, ICE_FDIR_MAX_RAW_PKT_SIZE, GFP_KERNEL); + if (!pkt) + return -ENOMEM; + + ice_fdir_get_prgm_desc(hw, input, &desc, add); + status = ice_fdir_get_gen_prgm_pkt(hw, input, pkt, false, is_tun); + ret = ice_status_to_errno(status); + if (ret) { + dev_dbg(dev, "Gen training pkt for VF %d ptype %d failed\n", + vf->vf_id, input->flow_type); + goto err_free_pkt; + } + + ret = ice_prgm_fdir_fltr(ctrl_vsi, &desc, pkt); + if (ret) + goto err_free_pkt; + + return 0; + +err_free_pkt: + devm_kfree(dev, pkt); + return ret; +} + +/** + * ice_vf_fdir_timer - FDIR program waiting timer interrupt handler + * @t: pointer to timer_list + */ +static void ice_vf_fdir_timer(struct timer_list *t) +{ + struct ice_vf_fdir_ctx *ctx_irq = from_timer(ctx_irq, t, rx_tmr); + struct ice_vf_fdir_ctx *ctx_done; + struct ice_vf_fdir *fdir; + unsigned long flags; + struct ice_vf *vf; + struct ice_pf *pf; + + fdir = container_of(ctx_irq, struct ice_vf_fdir, ctx_irq); + vf = container_of(fdir, struct ice_vf, fdir); + ctx_done = &fdir->ctx_done; + pf = vf->pf; + spin_lock_irqsave(&fdir->ctx_lock, flags); + if (!(ctx_irq->flags & ICE_VF_FDIR_CTX_VALID)) { + spin_unlock_irqrestore(&fdir->ctx_lock, flags); + WARN_ON_ONCE(1); + return; + } + + ctx_irq->flags &= ~ICE_VF_FDIR_CTX_VALID; + + ctx_done->flags |= ICE_VF_FDIR_CTX_VALID; + ctx_done->conf = ctx_irq->conf; + ctx_done->stat = ICE_FDIR_CTX_TIMEOUT; + ctx_done->v_opcode = ctx_irq->v_opcode; + spin_unlock_irqrestore(&fdir->ctx_lock, flags); + + set_bit(ICE_FD_VF_FLUSH_CTX, pf->state); + ice_service_task_schedule(pf); +} + +/** + * ice_vc_fdir_irq_handler - ctrl_vsi Rx queue interrupt handler + * @ctrl_vsi: pointer to a VF's CTRL VSI + * @rx_desc: pointer to FDIR Rx queue descriptor + */ +void +ice_vc_fdir_irq_handler(struct ice_vsi *ctrl_vsi, + union ice_32b_rx_flex_desc *rx_desc) +{ + struct ice_pf *pf = ctrl_vsi->back; + struct ice_vf_fdir_ctx *ctx_done; + struct ice_vf_fdir_ctx *ctx_irq; + struct ice_vf_fdir *fdir; + unsigned long flags; + struct device *dev; + struct ice_vf *vf; + int ret; + + vf = &pf->vf[ctrl_vsi->vf_id]; + + fdir = &vf->fdir; + ctx_done = &fdir->ctx_done; + ctx_irq = &fdir->ctx_irq; + dev = ice_pf_to_dev(pf); + spin_lock_irqsave(&fdir->ctx_lock, flags); + if (!(ctx_irq->flags & ICE_VF_FDIR_CTX_VALID)) { + spin_unlock_irqrestore(&fdir->ctx_lock, flags); + WARN_ON_ONCE(1); + return; + } + + ctx_irq->flags &= ~ICE_VF_FDIR_CTX_VALID; + + ctx_done->flags |= ICE_VF_FDIR_CTX_VALID; + ctx_done->conf = ctx_irq->conf; + ctx_done->stat = ICE_FDIR_CTX_IRQ; + ctx_done->v_opcode = ctx_irq->v_opcode; + memcpy(&ctx_done->rx_desc, rx_desc, sizeof(*rx_desc)); + spin_unlock_irqrestore(&fdir->ctx_lock, flags); + + ret = del_timer(&ctx_irq->rx_tmr); + if (!ret) + dev_err(dev, "VF %d: Unexpected inactive timer!\n", vf->vf_id); + + set_bit(ICE_FD_VF_FLUSH_CTX, pf->state); + ice_service_task_schedule(pf); +} + +/** + * ice_vf_fdir_dump_info - dump FDIR information for diagnosis + * @vf: pointer to the VF info + */ +static void ice_vf_fdir_dump_info(struct ice_vf *vf) +{ + struct ice_vsi *vf_vsi; + u32 fd_size, fd_cnt; + struct device *dev; + struct ice_pf *pf; + struct ice_hw *hw; + u16 vsi_num; + + pf = vf->pf; + hw = &pf->hw; + dev = ice_pf_to_dev(pf); + vf_vsi = pf->vsi[vf->lan_vsi_idx]; + vsi_num = ice_get_hw_vsi_num(hw, vf_vsi->idx); + + fd_size = rd32(hw, VSIQF_FD_SIZE(vsi_num)); + fd_cnt = rd32(hw, VSIQF_FD_CNT(vsi_num)); + dev_dbg(dev, "VF %d: space allocated: guar:0x%x, be:0x%x, space consumed: guar:0x%x, be:0x%x", + vf->vf_id, + (fd_size & VSIQF_FD_CNT_FD_GCNT_M) >> VSIQF_FD_CNT_FD_GCNT_S, + (fd_size & VSIQF_FD_CNT_FD_BCNT_M) >> VSIQF_FD_CNT_FD_BCNT_S, + (fd_cnt & VSIQF_FD_CNT_FD_GCNT_M) >> VSIQF_FD_CNT_FD_GCNT_S, + (fd_cnt & VSIQF_FD_CNT_FD_BCNT_M) >> VSIQF_FD_CNT_FD_BCNT_S); +} + +/** + * ice_vf_verify_rx_desc - verify received FDIR programming status descriptor + * @vf: pointer to the VF info + * @ctx: FDIR context info for post processing + * @status: virtchnl FDIR program status + * + * Return: 0 on success, and other on error. + */ +static int +ice_vf_verify_rx_desc(struct ice_vf *vf, struct ice_vf_fdir_ctx *ctx, + enum virtchnl_fdir_prgm_status *status) +{ + struct device *dev = ice_pf_to_dev(vf->pf); + u32 stat_err, error, prog_id; + int ret; + + stat_err = le16_to_cpu(ctx->rx_desc.wb.status_error0); + if (((stat_err & ICE_FXD_FLTR_WB_QW1_DD_M) >> + ICE_FXD_FLTR_WB_QW1_DD_S) != ICE_FXD_FLTR_WB_QW1_DD_YES) { + *status = VIRTCHNL_FDIR_FAILURE_RULE_NORESOURCE; + dev_err(dev, "VF %d: Desc Done not set\n", vf->vf_id); + ret = -EINVAL; + goto err_exit; + } + + prog_id = (stat_err & ICE_FXD_FLTR_WB_QW1_PROG_ID_M) >> + ICE_FXD_FLTR_WB_QW1_PROG_ID_S; + if (prog_id == ICE_FXD_FLTR_WB_QW1_PROG_ADD && + ctx->v_opcode != VIRTCHNL_OP_ADD_FDIR_FILTER) { + dev_err(dev, "VF %d: Desc show add, but ctx not", + vf->vf_id); + *status = VIRTCHNL_FDIR_FAILURE_RULE_INVALID; + ret = -EINVAL; + goto err_exit; + } + + if (prog_id == ICE_FXD_FLTR_WB_QW1_PROG_DEL && + ctx->v_opcode != VIRTCHNL_OP_DEL_FDIR_FILTER) { + dev_err(dev, "VF %d: Desc show del, but ctx not", + vf->vf_id); + *status = VIRTCHNL_FDIR_FAILURE_RULE_INVALID; + ret = -EINVAL; + goto err_exit; + } + + error = (stat_err & ICE_FXD_FLTR_WB_QW1_FAIL_M) >> + ICE_FXD_FLTR_WB_QW1_FAIL_S; + if (error == ICE_FXD_FLTR_WB_QW1_FAIL_YES) { + if (prog_id == ICE_FXD_FLTR_WB_QW1_PROG_ADD) { + dev_err(dev, "VF %d, Failed to add FDIR rule due to no space in the table", + vf->vf_id); + *status = VIRTCHNL_FDIR_FAILURE_RULE_NORESOURCE; + } else { + dev_err(dev, "VF %d, Failed to remove FDIR rule, attempt to remove non-existent entry", + vf->vf_id); + *status = VIRTCHNL_FDIR_FAILURE_RULE_NONEXIST; + } + ret = -EINVAL; + goto err_exit; + } + + error = (stat_err & ICE_FXD_FLTR_WB_QW1_FAIL_PROF_M) >> + ICE_FXD_FLTR_WB_QW1_FAIL_PROF_S; + if (error == ICE_FXD_FLTR_WB_QW1_FAIL_PROF_YES) { + dev_err(dev, "VF %d: Profile matching error", vf->vf_id); + *status = VIRTCHNL_FDIR_FAILURE_RULE_NORESOURCE; + ret = -EINVAL; + goto err_exit; + } + + *status = VIRTCHNL_FDIR_SUCCESS; + + return 0; + +err_exit: + ice_vf_fdir_dump_info(vf); + return ret; +} + +/** + * ice_vc_add_fdir_fltr_post + * @vf: pointer to the VF structure + * @ctx: FDIR context info for post processing + * @status: virtchnl FDIR program status + * @success: true implies success, false implies failure + * + * Post process for flow director add command. If success, then do post process + * and send back success msg by virtchnl. Otherwise, do context reversion and + * send back failure msg by virtchnl. + * + * Return: 0 on success, and other on error. + */ +static int +ice_vc_add_fdir_fltr_post(struct ice_vf *vf, struct ice_vf_fdir_ctx *ctx, + enum virtchnl_fdir_prgm_status status, + bool success) +{ + struct virtchnl_fdir_fltr_conf *conf = ctx->conf; + struct device *dev = ice_pf_to_dev(vf->pf); + enum virtchnl_status_code v_ret; + struct virtchnl_fdir_add *resp; + int ret, len, is_tun; + + v_ret = VIRTCHNL_STATUS_SUCCESS; + len = sizeof(*resp); + resp = kzalloc(len, GFP_KERNEL); + if (!resp) { + len = 0; + v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; + dev_dbg(dev, "VF %d: Alloc resp buf fail", vf->vf_id); + goto err_exit; + } + + if (!success) + goto err_exit; + + is_tun = 0; + resp->status = status; + resp->flow_id = conf->flow_id; + vf->fdir.fdir_fltr_cnt[conf->input.flow_type][is_tun]++; + + ret = ice_vc_send_msg_to_vf(vf, ctx->v_opcode, v_ret, + (u8 *)resp, len); + kfree(resp); + + dev_dbg(dev, "VF %d: flow_id:0x%X, FDIR %s success!\n", + vf->vf_id, conf->flow_id, + (ctx->v_opcode == VIRTCHNL_OP_ADD_FDIR_FILTER) ? + "add" : "del"); + return ret; + +err_exit: + if (resp) + resp->status = status; + ice_vc_fdir_remove_entry(vf, conf, conf->flow_id); + devm_kfree(dev, conf); + + ret = ice_vc_send_msg_to_vf(vf, ctx->v_opcode, v_ret, + (u8 *)resp, len); + kfree(resp); + return ret; +} + +/** + * ice_vc_del_fdir_fltr_post + * @vf: pointer to the VF structure + * @ctx: FDIR context info for post processing + * @status: virtchnl FDIR program status + * @success: true implies success, false implies failure + * + * Post process for flow director del command. If success, then do post process + * and send back success msg by virtchnl. Otherwise, do context reversion and + * send back failure msg by virtchnl. + * + * Return: 0 on success, and other on error. + */ +static int +ice_vc_del_fdir_fltr_post(struct ice_vf *vf, struct ice_vf_fdir_ctx *ctx, + enum virtchnl_fdir_prgm_status status, + bool success) +{ + struct virtchnl_fdir_fltr_conf *conf = ctx->conf; + struct device *dev = ice_pf_to_dev(vf->pf); + enum virtchnl_status_code v_ret; + struct virtchnl_fdir_del *resp; + int ret, len, is_tun; + + v_ret = VIRTCHNL_STATUS_SUCCESS; + len = sizeof(*resp); + resp = kzalloc(len, GFP_KERNEL); + if (!resp) { + len = 0; + v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; + dev_dbg(dev, "VF %d: Alloc resp buf fail", vf->vf_id); + goto err_exit; + } + + if (!success) + goto err_exit; + + is_tun = 0; + resp->status = status; + ice_vc_fdir_remove_entry(vf, conf, conf->flow_id); + vf->fdir.fdir_fltr_cnt[conf->input.flow_type][is_tun]--; + + ret = ice_vc_send_msg_to_vf(vf, ctx->v_opcode, v_ret, + (u8 *)resp, len); + kfree(resp); + + dev_dbg(dev, "VF %d: flow_id:0x%X, FDIR %s success!\n", + vf->vf_id, conf->flow_id, + (ctx->v_opcode == VIRTCHNL_OP_ADD_FDIR_FILTER) ? + "add" : "del"); + devm_kfree(dev, conf); + return ret; + +err_exit: + if (resp) + resp->status = status; + if (success) + devm_kfree(dev, conf); + + ret = ice_vc_send_msg_to_vf(vf, ctx->v_opcode, v_ret, + (u8 *)resp, len); + kfree(resp); + return ret; +} + +/** + * ice_flush_fdir_ctx + * @pf: pointer to the PF structure + * + * Flush all the pending event on ctx_done list and process them. + */ +void ice_flush_fdir_ctx(struct ice_pf *pf) +{ + int i; + + if (!test_and_clear_bit(ICE_FD_VF_FLUSH_CTX, pf->state)) + return; + + ice_for_each_vf(pf, i) { + struct device *dev = ice_pf_to_dev(pf); + enum virtchnl_fdir_prgm_status status; + struct ice_vf *vf = &pf->vf[i]; + struct ice_vf_fdir_ctx *ctx; + unsigned long flags; + int ret; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) + continue; + + if (vf->ctrl_vsi_idx == ICE_NO_VSI) + continue; + + ctx = &vf->fdir.ctx_done; + spin_lock_irqsave(&vf->fdir.ctx_lock, flags); + if (!(ctx->flags & ICE_VF_FDIR_CTX_VALID)) { + spin_unlock_irqrestore(&vf->fdir.ctx_lock, flags); + continue; + } + spin_unlock_irqrestore(&vf->fdir.ctx_lock, flags); + + WARN_ON(ctx->stat == ICE_FDIR_CTX_READY); + if (ctx->stat == ICE_FDIR_CTX_TIMEOUT) { + status = VIRTCHNL_FDIR_FAILURE_RULE_TIMEOUT; + dev_err(dev, "VF %d: ctrl_vsi irq timeout\n", + vf->vf_id); + goto err_exit; + } + + ret = ice_vf_verify_rx_desc(vf, ctx, &status); + if (ret) + goto err_exit; + + if (ctx->v_opcode == VIRTCHNL_OP_ADD_FDIR_FILTER) + ice_vc_add_fdir_fltr_post(vf, ctx, status, true); + else if (ctx->v_opcode == VIRTCHNL_OP_DEL_FDIR_FILTER) + ice_vc_del_fdir_fltr_post(vf, ctx, status, true); + else + dev_err(dev, "VF %d: Unsupported opcode\n", vf->vf_id); + + spin_lock_irqsave(&vf->fdir.ctx_lock, flags); + ctx->flags &= ~ICE_VF_FDIR_CTX_VALID; + spin_unlock_irqrestore(&vf->fdir.ctx_lock, flags); + continue; +err_exit: + if (ctx->v_opcode == VIRTCHNL_OP_ADD_FDIR_FILTER) + ice_vc_add_fdir_fltr_post(vf, ctx, status, false); + else if (ctx->v_opcode == VIRTCHNL_OP_DEL_FDIR_FILTER) + ice_vc_del_fdir_fltr_post(vf, ctx, status, false); + else + dev_err(dev, "VF %d: Unsupported opcode\n", vf->vf_id); + + spin_lock_irqsave(&vf->fdir.ctx_lock, flags); + ctx->flags &= ~ICE_VF_FDIR_CTX_VALID; + spin_unlock_irqrestore(&vf->fdir.ctx_lock, flags); + } +} + +/** + * ice_vc_fdir_set_irq_ctx - set FDIR context info for later IRQ handler + * @vf: pointer to the VF structure + * @conf: FDIR configuration for each filter + * @v_opcode: virtual channel operation code + * + * Return: 0 on success, and other on error. + */ +static int +ice_vc_fdir_set_irq_ctx(struct ice_vf *vf, struct virtchnl_fdir_fltr_conf *conf, + enum virtchnl_ops v_opcode) +{ + struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_vf_fdir_ctx *ctx; + unsigned long flags; + + ctx = &vf->fdir.ctx_irq; + spin_lock_irqsave(&vf->fdir.ctx_lock, flags); + if ((vf->fdir.ctx_irq.flags & ICE_VF_FDIR_CTX_VALID) || + (vf->fdir.ctx_done.flags & ICE_VF_FDIR_CTX_VALID)) { + spin_unlock_irqrestore(&vf->fdir.ctx_lock, flags); + dev_dbg(dev, "VF %d: Last request is still in progress\n", + vf->vf_id); + return -EBUSY; + } + ctx->flags |= ICE_VF_FDIR_CTX_VALID; + spin_unlock_irqrestore(&vf->fdir.ctx_lock, flags); + + ctx->conf = conf; + ctx->v_opcode = v_opcode; + ctx->stat = ICE_FDIR_CTX_READY; + timer_setup(&ctx->rx_tmr, ice_vf_fdir_timer, 0); + + mod_timer(&ctx->rx_tmr, round_jiffies(msecs_to_jiffies(10) + jiffies)); + + return 0; +} + +/** + * ice_vc_fdir_clear_irq_ctx - clear FDIR context info for IRQ handler + * @vf: pointer to the VF structure + * + * Return: 0 on success, and other on error. + */ +static void ice_vc_fdir_clear_irq_ctx(struct ice_vf *vf) +{ + struct ice_vf_fdir_ctx *ctx = &vf->fdir.ctx_irq; + unsigned long flags; + + del_timer(&ctx->rx_tmr); + spin_lock_irqsave(&vf->fdir.ctx_lock, flags); + ctx->flags &= ~ICE_VF_FDIR_CTX_VALID; + spin_unlock_irqrestore(&vf->fdir.ctx_lock, flags); +} + +/** + * ice_vc_add_fdir_fltr - add a FDIR filter for VF by the msg buffer + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * Return: 0 on success, and other on error. + */ +int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_fdir_add *fltr = (struct virtchnl_fdir_add *)msg; + struct virtchnl_fdir_add *stat = NULL; + struct virtchnl_fdir_fltr_conf *conf; + enum virtchnl_status_code v_ret; + struct device *dev; + struct ice_pf *pf; + int is_tun = 0; + int len = 0; + int ret; + + pf = vf->pf; + dev = ice_pf_to_dev(pf); + ret = ice_vc_fdir_param_check(vf, fltr->vsi_id); + if (ret) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + dev_dbg(dev, "Parameter check for VF %d failed\n", vf->vf_id); + goto err_exit; + } + + ret = ice_vf_start_ctrl_vsi(vf); + if (ret && (ret != -EEXIST)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + dev_err(dev, "Init FDIR for VF %d failed, ret:%d\n", + vf->vf_id, ret); + goto err_exit; + } + + stat = kzalloc(sizeof(*stat), GFP_KERNEL); + if (!stat) { + v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; + dev_dbg(dev, "Alloc stat for VF %d failed\n", vf->vf_id); + goto err_exit; + } + + conf = devm_kzalloc(dev, sizeof(*conf), GFP_KERNEL); + if (!conf) { + v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; + dev_dbg(dev, "Alloc conf for VF %d failed\n", vf->vf_id); + goto err_exit; + } + + len = sizeof(*stat); + ret = ice_vc_validate_fdir_fltr(vf, fltr, conf); + if (ret) { + v_ret = VIRTCHNL_STATUS_SUCCESS; + stat->status = VIRTCHNL_FDIR_FAILURE_RULE_INVALID; + dev_dbg(dev, "Invalid FDIR filter from VF %d\n", vf->vf_id); + goto err_free_conf; + } + + if (fltr->validate_only) { + v_ret = VIRTCHNL_STATUS_SUCCESS; + stat->status = VIRTCHNL_FDIR_SUCCESS; + devm_kfree(dev, conf); + ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ADD_FDIR_FILTER, + v_ret, (u8 *)stat, len); + goto exit; + } + + ret = ice_vc_fdir_config_input_set(vf, fltr, conf, is_tun); + if (ret) { + v_ret = VIRTCHNL_STATUS_SUCCESS; + stat->status = VIRTCHNL_FDIR_FAILURE_RULE_CONFLICT; + dev_err(dev, "VF %d: FDIR input set configure failed, ret:%d\n", + vf->vf_id, ret); + goto err_free_conf; + } + + ret = ice_vc_fdir_is_dup_fltr(vf, conf); + if (ret) { + v_ret = VIRTCHNL_STATUS_SUCCESS; + stat->status = VIRTCHNL_FDIR_FAILURE_RULE_EXIST; + dev_dbg(dev, "VF %d: duplicated FDIR rule detected\n", + vf->vf_id); + goto err_free_conf; + } + + ret = ice_vc_fdir_insert_entry(vf, conf, &conf->flow_id); + if (ret) { + v_ret = VIRTCHNL_STATUS_SUCCESS; + stat->status = VIRTCHNL_FDIR_FAILURE_RULE_NORESOURCE; + dev_dbg(dev, "VF %d: insert FDIR list failed\n", vf->vf_id); + goto err_free_conf; + } + + ret = ice_vc_fdir_set_irq_ctx(vf, conf, VIRTCHNL_OP_ADD_FDIR_FILTER); + if (ret) { + v_ret = VIRTCHNL_STATUS_SUCCESS; + stat->status = VIRTCHNL_FDIR_FAILURE_RULE_NORESOURCE; + dev_dbg(dev, "VF %d: set FDIR context failed\n", vf->vf_id); + goto err_free_conf; + } + + ret = ice_vc_fdir_write_fltr(vf, conf, true, is_tun); + if (ret) { + v_ret = VIRTCHNL_STATUS_SUCCESS; + stat->status = VIRTCHNL_FDIR_FAILURE_RULE_NORESOURCE; + dev_err(dev, "VF %d: writing FDIR rule failed, ret:%d\n", + vf->vf_id, ret); + goto err_rem_entry; + } + +exit: + kfree(stat); + return ret; + +err_rem_entry: + ice_vc_fdir_clear_irq_ctx(vf); + ice_vc_fdir_remove_entry(vf, conf, conf->flow_id); +err_free_conf: + devm_kfree(dev, conf); +err_exit: + ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ADD_FDIR_FILTER, v_ret, + (u8 *)stat, len); + kfree(stat); + return ret; +} + +/** + * ice_vc_del_fdir_fltr - delete a FDIR filter for VF by the msg buffer + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * Return: 0 on success, and other on error. + */ +int ice_vc_del_fdir_fltr(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_fdir_del *fltr = (struct virtchnl_fdir_del *)msg; + struct virtchnl_fdir_del *stat = NULL; + struct virtchnl_fdir_fltr_conf *conf; + enum virtchnl_status_code v_ret; + struct device *dev; + struct ice_pf *pf; + int is_tun = 0; + int len = 0; + int ret; + + pf = vf->pf; + dev = ice_pf_to_dev(pf); + ret = ice_vc_fdir_param_check(vf, fltr->vsi_id); + if (ret) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + dev_dbg(dev, "Parameter check for VF %d failed\n", vf->vf_id); + goto err_exit; + } + + stat = kzalloc(sizeof(*stat), GFP_KERNEL); + if (!stat) { + v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; + dev_dbg(dev, "Alloc stat for VF %d failed\n", vf->vf_id); + goto err_exit; + } + + len = sizeof(*stat); + + conf = ice_vc_fdir_lookup_entry(vf, fltr->flow_id); + if (!conf) { + v_ret = VIRTCHNL_STATUS_SUCCESS; + stat->status = VIRTCHNL_FDIR_FAILURE_RULE_NONEXIST; + dev_dbg(dev, "VF %d: FDIR invalid flow_id:0x%X\n", + vf->vf_id, fltr->flow_id); + goto err_exit; + } + + /* Just return failure when ctrl_vsi idx is invalid */ + if (vf->ctrl_vsi_idx == ICE_NO_VSI) { + v_ret = VIRTCHNL_STATUS_SUCCESS; + stat->status = VIRTCHNL_FDIR_FAILURE_RULE_NORESOURCE; + dev_err(dev, "Invalid FDIR ctrl_vsi for VF %d\n", vf->vf_id); + goto err_exit; + } + + ret = ice_vc_fdir_set_irq_ctx(vf, conf, VIRTCHNL_OP_DEL_FDIR_FILTER); + if (ret) { + v_ret = VIRTCHNL_STATUS_SUCCESS; + stat->status = VIRTCHNL_FDIR_FAILURE_RULE_NORESOURCE; + dev_dbg(dev, "VF %d: set FDIR context failed\n", vf->vf_id); + goto err_exit; + } + + ret = ice_vc_fdir_write_fltr(vf, conf, false, is_tun); + if (ret) { + v_ret = VIRTCHNL_STATUS_SUCCESS; + stat->status = VIRTCHNL_FDIR_FAILURE_RULE_NORESOURCE; + dev_err(dev, "VF %d: writing FDIR rule failed, ret:%d\n", + vf->vf_id, ret); + goto err_del_tmr; + } + + kfree(stat); + + return ret; + +err_del_tmr: + ice_vc_fdir_clear_irq_ctx(vf); +err_exit: + ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DEL_FDIR_FILTER, v_ret, + (u8 *)stat, len); + kfree(stat); + return ret; +} + +/** + * ice_vf_fdir_init - init FDIR resource for VF + * @vf: pointer to the VF info + */ +void ice_vf_fdir_init(struct ice_vf *vf) +{ + struct ice_vf_fdir *fdir = &vf->fdir; + + idr_init(&fdir->fdir_rule_idr); + INIT_LIST_HEAD(&fdir->fdir_rule_list); + + spin_lock_init(&fdir->ctx_lock); + fdir->ctx_irq.flags = 0; + fdir->ctx_done.flags = 0; +} + +/** + * ice_vf_fdir_exit - destroy FDIR resource for VF + * @vf: pointer to the VF info + */ +void ice_vf_fdir_exit(struct ice_vf *vf) +{ + ice_vc_fdir_flush_entry(vf); + idr_destroy(&vf->fdir.fdir_rule_idr); + ice_vc_fdir_rem_prof_all(vf); + ice_vc_fdir_free_prof_all(vf); +} diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.h new file mode 100644 index 000000000000..f4e629f4c09b --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2021, Intel Corporation. */ + +#ifndef _ICE_VIRTCHNL_FDIR_H_ +#define _ICE_VIRTCHNL_FDIR_H_ + +struct ice_vf; +struct ice_pf; + +enum ice_fdir_ctx_stat { + ICE_FDIR_CTX_READY, + ICE_FDIR_CTX_IRQ, + ICE_FDIR_CTX_TIMEOUT, +}; + +struct ice_vf_fdir_ctx { + struct timer_list rx_tmr; + enum virtchnl_ops v_opcode; + enum ice_fdir_ctx_stat stat; + union ice_32b_rx_flex_desc rx_desc; +#define ICE_VF_FDIR_CTX_VALID BIT(0) + u32 flags; + + void *conf; +}; + +/* VF FDIR information structure */ +struct ice_vf_fdir { + u16 fdir_fltr_cnt[ICE_FLTR_PTYPE_MAX][ICE_FD_HW_SEG_MAX]; + int prof_entry_cnt[ICE_FLTR_PTYPE_MAX][ICE_FD_HW_SEG_MAX]; + struct ice_fd_hw_prof **fdir_prof; + + struct idr fdir_rule_idr; + struct list_head fdir_rule_list; + + spinlock_t ctx_lock; /* protects FDIR context info */ + struct ice_vf_fdir_ctx ctx_irq; + struct ice_vf_fdir_ctx ctx_done; +}; + +#ifdef CONFIG_PCI_IOV +int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg); +int ice_vc_del_fdir_fltr(struct ice_vf *vf, u8 *msg); +void ice_vf_fdir_init(struct ice_vf *vf); +void ice_vf_fdir_exit(struct ice_vf *vf); +void +ice_vc_fdir_irq_handler(struct ice_vsi *ctrl_vsi, + union ice_32b_rx_flex_desc *rx_desc); +void ice_flush_fdir_ctx(struct ice_pf *pf); +#else +static inline void +ice_vc_fdir_irq_handler(struct ice_vsi *ctrl_vsi, union ice_32b_rx_flex_desc *rx_desc) { } +static inline void ice_flush_fdir_ctx(struct ice_pf *pf) { } +#endif /* CONFIG_PCI_IOV */ +#endif /* _ICE_VIRTCHNL_FDIR_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index 1f38a8d0c525..a1d22d2aa0bd 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -5,6 +5,256 @@ #include "ice_base.h" #include "ice_lib.h" #include "ice_fltr.h" +#include "ice_flow.h" +#include "ice_virtchnl_allowlist.h" + +#define FIELD_SELECTOR(proto_hdr_field) \ + BIT((proto_hdr_field) & PROTO_HDR_FIELD_MASK) + +struct ice_vc_hdr_match_type { + u32 vc_hdr; /* virtchnl headers (VIRTCHNL_PROTO_HDR_XXX) */ + u32 ice_hdr; /* ice headers (ICE_FLOW_SEG_HDR_XXX) */ +}; + +static const struct ice_vc_hdr_match_type ice_vc_hdr_list_os[] = { + {VIRTCHNL_PROTO_HDR_NONE, ICE_FLOW_SEG_HDR_NONE}, + {VIRTCHNL_PROTO_HDR_IPV4, ICE_FLOW_SEG_HDR_IPV4 | + ICE_FLOW_SEG_HDR_IPV_OTHER}, + {VIRTCHNL_PROTO_HDR_IPV6, ICE_FLOW_SEG_HDR_IPV6 | + ICE_FLOW_SEG_HDR_IPV_OTHER}, + {VIRTCHNL_PROTO_HDR_TCP, ICE_FLOW_SEG_HDR_TCP}, + {VIRTCHNL_PROTO_HDR_UDP, ICE_FLOW_SEG_HDR_UDP}, + {VIRTCHNL_PROTO_HDR_SCTP, ICE_FLOW_SEG_HDR_SCTP}, +}; + +static const struct ice_vc_hdr_match_type ice_vc_hdr_list_comms[] = { + {VIRTCHNL_PROTO_HDR_NONE, ICE_FLOW_SEG_HDR_NONE}, + {VIRTCHNL_PROTO_HDR_ETH, ICE_FLOW_SEG_HDR_ETH}, + {VIRTCHNL_PROTO_HDR_S_VLAN, ICE_FLOW_SEG_HDR_VLAN}, + {VIRTCHNL_PROTO_HDR_C_VLAN, ICE_FLOW_SEG_HDR_VLAN}, + {VIRTCHNL_PROTO_HDR_IPV4, ICE_FLOW_SEG_HDR_IPV4 | + ICE_FLOW_SEG_HDR_IPV_OTHER}, + {VIRTCHNL_PROTO_HDR_IPV6, ICE_FLOW_SEG_HDR_IPV6 | + ICE_FLOW_SEG_HDR_IPV_OTHER}, + {VIRTCHNL_PROTO_HDR_TCP, ICE_FLOW_SEG_HDR_TCP}, + {VIRTCHNL_PROTO_HDR_UDP, ICE_FLOW_SEG_HDR_UDP}, + {VIRTCHNL_PROTO_HDR_SCTP, ICE_FLOW_SEG_HDR_SCTP}, + {VIRTCHNL_PROTO_HDR_PPPOE, ICE_FLOW_SEG_HDR_PPPOE}, + {VIRTCHNL_PROTO_HDR_GTPU_IP, ICE_FLOW_SEG_HDR_GTPU_IP}, + {VIRTCHNL_PROTO_HDR_GTPU_EH, ICE_FLOW_SEG_HDR_GTPU_EH}, + {VIRTCHNL_PROTO_HDR_GTPU_EH_PDU_DWN, + ICE_FLOW_SEG_HDR_GTPU_DWN}, + {VIRTCHNL_PROTO_HDR_GTPU_EH_PDU_UP, + ICE_FLOW_SEG_HDR_GTPU_UP}, + {VIRTCHNL_PROTO_HDR_L2TPV3, ICE_FLOW_SEG_HDR_L2TPV3}, + {VIRTCHNL_PROTO_HDR_ESP, ICE_FLOW_SEG_HDR_ESP}, + {VIRTCHNL_PROTO_HDR_AH, ICE_FLOW_SEG_HDR_AH}, + {VIRTCHNL_PROTO_HDR_PFCP, ICE_FLOW_SEG_HDR_PFCP_SESSION}, +}; + +struct ice_vc_hash_field_match_type { + u32 vc_hdr; /* virtchnl headers + * (VIRTCHNL_PROTO_HDR_XXX) + */ + u32 vc_hash_field; /* virtchnl hash fields selector + * FIELD_SELECTOR((VIRTCHNL_PROTO_HDR_ETH_XXX)) + */ + u64 ice_hash_field; /* ice hash fields + * (BIT_ULL(ICE_FLOW_FIELD_IDX_XXX)) + */ +}; + +static const struct +ice_vc_hash_field_match_type ice_vc_hash_field_list_os[] = { + {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA)}, + {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA)}, + {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST), + ICE_FLOW_HASH_IPV4}, + {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT), + ICE_FLOW_HASH_IPV4 | BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_SA)}, + {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_DA)}, + {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST), + ICE_FLOW_HASH_IPV6}, + {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_SA) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_DA) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT), + ICE_FLOW_HASH_IPV6 | BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)}, + {VIRTCHNL_PROTO_HDR_TCP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_SRC_PORT), + BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_SRC_PORT)}, + {VIRTCHNL_PROTO_HDR_TCP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_DST_PORT), + BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_DST_PORT)}, + {VIRTCHNL_PROTO_HDR_TCP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_SRC_PORT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_DST_PORT), + ICE_FLOW_HASH_TCP_PORT}, + {VIRTCHNL_PROTO_HDR_UDP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_SRC_PORT), + BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_SRC_PORT)}, + {VIRTCHNL_PROTO_HDR_UDP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_DST_PORT), + BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_DST_PORT)}, + {VIRTCHNL_PROTO_HDR_UDP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_SRC_PORT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_DST_PORT), + ICE_FLOW_HASH_UDP_PORT}, + {VIRTCHNL_PROTO_HDR_SCTP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_SRC_PORT), + BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT)}, + {VIRTCHNL_PROTO_HDR_SCTP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_DST_PORT), + BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_DST_PORT)}, + {VIRTCHNL_PROTO_HDR_SCTP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_SRC_PORT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_DST_PORT), + ICE_FLOW_HASH_SCTP_PORT}, +}; + +static const struct +ice_vc_hash_field_match_type ice_vc_hash_field_list_comms[] = { + {VIRTCHNL_PROTO_HDR_ETH, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ETH_SRC), + BIT_ULL(ICE_FLOW_FIELD_IDX_ETH_SA)}, + {VIRTCHNL_PROTO_HDR_ETH, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ETH_DST), + BIT_ULL(ICE_FLOW_FIELD_IDX_ETH_DA)}, + {VIRTCHNL_PROTO_HDR_ETH, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ETH_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ETH_DST), + ICE_FLOW_HASH_ETH}, + {VIRTCHNL_PROTO_HDR_ETH, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ETH_ETHERTYPE), + BIT_ULL(ICE_FLOW_FIELD_IDX_ETH_TYPE)}, + {VIRTCHNL_PROTO_HDR_S_VLAN, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_S_VLAN_ID), + BIT_ULL(ICE_FLOW_FIELD_IDX_S_VLAN)}, + {VIRTCHNL_PROTO_HDR_C_VLAN, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_C_VLAN_ID), + BIT_ULL(ICE_FLOW_FIELD_IDX_C_VLAN)}, + {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA)}, + {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA)}, + {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST), + ICE_FLOW_HASH_IPV4}, + {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT), + ICE_FLOW_HASH_IPV4 | BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_SA)}, + {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_DA)}, + {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST), + ICE_FLOW_HASH_IPV6}, + {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_SA) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_DA) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT), + ICE_FLOW_HASH_IPV6 | BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)}, + {VIRTCHNL_PROTO_HDR_TCP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_SRC_PORT), + BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_SRC_PORT)}, + {VIRTCHNL_PROTO_HDR_TCP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_DST_PORT), + BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_DST_PORT)}, + {VIRTCHNL_PROTO_HDR_TCP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_SRC_PORT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_DST_PORT), + ICE_FLOW_HASH_TCP_PORT}, + {VIRTCHNL_PROTO_HDR_UDP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_SRC_PORT), + BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_SRC_PORT)}, + {VIRTCHNL_PROTO_HDR_UDP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_DST_PORT), + BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_DST_PORT)}, + {VIRTCHNL_PROTO_HDR_UDP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_SRC_PORT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_DST_PORT), + ICE_FLOW_HASH_UDP_PORT}, + {VIRTCHNL_PROTO_HDR_SCTP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_SRC_PORT), + BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT)}, + {VIRTCHNL_PROTO_HDR_SCTP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_DST_PORT), + BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_DST_PORT)}, + {VIRTCHNL_PROTO_HDR_SCTP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_SRC_PORT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_DST_PORT), + ICE_FLOW_HASH_SCTP_PORT}, + {VIRTCHNL_PROTO_HDR_PPPOE, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_PPPOE_SESS_ID), + BIT_ULL(ICE_FLOW_FIELD_IDX_PPPOE_SESS_ID)}, + {VIRTCHNL_PROTO_HDR_GTPU_IP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_GTPU_IP_TEID), + BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_IP_TEID)}, + {VIRTCHNL_PROTO_HDR_L2TPV3, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_L2TPV3_SESS_ID), + BIT_ULL(ICE_FLOW_FIELD_IDX_L2TPV3_SESS_ID)}, + {VIRTCHNL_PROTO_HDR_ESP, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ESP_SPI), + BIT_ULL(ICE_FLOW_FIELD_IDX_ESP_SPI)}, + {VIRTCHNL_PROTO_HDR_AH, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_AH_SPI), + BIT_ULL(ICE_FLOW_FIELD_IDX_AH_SPI)}, + {VIRTCHNL_PROTO_HDR_PFCP, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_PFCP_SEID), + BIT_ULL(ICE_FLOW_FIELD_IDX_PFCP_SEID)}, +}; + +/** + * ice_get_vf_vsi - get VF's VSI based on the stored index + * @vf: VF used to get VSI + */ +static struct ice_vsi *ice_get_vf_vsi(struct ice_vf *vf) +{ + return vf->pf->vsi[vf->lan_vsi_idx]; +} /** * ice_validate_vf_id - helper to check if VF ID is valid @@ -197,11 +447,30 @@ static void ice_vf_invalidate_vsi(struct ice_vf *vf) */ static void ice_vf_vsi_release(struct ice_vf *vf) { - ice_vsi_release(vf->pf->vsi[vf->lan_vsi_idx]); + ice_vsi_release(ice_get_vf_vsi(vf)); ice_vf_invalidate_vsi(vf); } /** + * ice_vf_ctrl_invalidate_vsi - invalidate ctrl_vsi_idx to remove VSI access + * @vf: VF that control VSI is being invalidated on + */ +static void ice_vf_ctrl_invalidate_vsi(struct ice_vf *vf) +{ + vf->ctrl_vsi_idx = ICE_NO_VSI; +} + +/** + * ice_vf_ctrl_vsi_release - invalidate the VF's control VSI after freeing it + * @vf: VF that control VSI is being released on + */ +static void ice_vf_ctrl_vsi_release(struct ice_vf *vf) +{ + ice_vsi_release(vf->pf->vsi[vf->ctrl_vsi_idx]); + ice_vf_ctrl_invalidate_vsi(vf); +} + +/** * ice_free_vf_res - Free a VF's resources * @vf: pointer to the VF info */ @@ -214,6 +483,10 @@ static void ice_free_vf_res(struct ice_vf *vf) * accessing the VF's VSI after it's freed or invalidated. */ clear_bit(ICE_VF_STATE_INIT, vf->vf_states); + ice_vf_fdir_exit(vf); + /* free VF control VSI */ + if (vf->ctrl_vsi_idx != ICE_NO_VSI) + ice_vf_ctrl_vsi_release(vf); /* free VSI and disconnect it from the parent uplink */ if (vf->lan_vsi_idx != ICE_NO_VSI) { @@ -250,7 +523,7 @@ static void ice_dis_vf_mappings(struct ice_vf *vf) struct ice_hw *hw; hw = &pf->hw; - vsi = pf->vsi[vf->lan_vsi_idx]; + vsi = ice_get_vf_vsi(vf); dev = ice_pf_to_dev(pf); wr32(hw, VPINT_ALLOC(vf->vf_id), 0); @@ -325,10 +598,7 @@ void ice_set_vf_state_qs_dis(struct ice_vf *vf) */ static void ice_dis_vf_qs(struct ice_vf *vf) { - struct ice_pf *pf = vf->pf; - struct ice_vsi *vsi; - - vsi = pf->vsi[vf->lan_vsi_idx]; + struct ice_vsi *vsi = ice_get_vf_vsi(vf); ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, vf->vf_id); ice_vsi_stop_all_rx_rings(vsi); @@ -348,7 +618,7 @@ void ice_free_vfs(struct ice_pf *pf) if (!pf->vf) return; - while (test_and_set_bit(__ICE_VF_DIS, pf->state)) + while (test_and_set_bit(ICE_VF_DIS, pf->state)) usleep_range(1000, 2000); /* Disable IOV before freeing resources. This lets any VF drivers @@ -401,7 +671,15 @@ void ice_free_vfs(struct ice_pf *pf) wr32(hw, GLGEN_VFLRSTAT(reg_idx), BIT(bit_idx)); } } - clear_bit(__ICE_VF_DIS, pf->state); + + /* clear malicious info if the VFs are getting released */ + for (i = 0; i < tmp; i++) + if (ice_mbx_clear_malvf(&hw->mbx_snapshot, pf->malvfs, + ICE_MAX_VF_COUNT, i)) + dev_dbg(dev, "failed to clear malicious VF state for VF %u\n", + i); + + clear_bit(ICE_VF_DIS, pf->state); clear_bit(ICE_FLAG_SRIOV_ENA, pf->flags); } @@ -560,6 +838,28 @@ static struct ice_vsi *ice_vf_vsi_setup(struct ice_vf *vf) } /** + * ice_vf_ctrl_vsi_setup - Set up a VF control VSI + * @vf: VF to setup control VSI for + * + * Returns pointer to the successfully allocated VSI struct on success, + * otherwise returns NULL on failure. + */ +struct ice_vsi *ice_vf_ctrl_vsi_setup(struct ice_vf *vf) +{ + struct ice_port_info *pi = ice_vf_get_port_info(vf); + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + + vsi = ice_vsi_setup(pf, pi, ICE_VSI_CTRL, vf->vf_id); + if (!vsi) { + dev_err(ice_pf_to_dev(pf), "Failed to create VF control VSI\n"); + ice_vf_ctrl_invalidate_vsi(vf); + } + + return vsi; +} + +/** * ice_calc_vf_first_vector_idx - Calculate MSIX vector index in the PF space * @pf: pointer to PF structure * @vf: pointer to VF that the first MSIX vector index is being calculated for @@ -585,8 +885,8 @@ static int ice_calc_vf_first_vector_idx(struct ice_pf *pf, struct ice_vf *vf) */ static int ice_vf_rebuild_host_vlan_cfg(struct ice_vf *vf) { - struct ice_vsi *vsi = vf->pf->vsi[vf->lan_vsi_idx]; struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_vsi *vsi = ice_get_vf_vsi(vf); u16 vlan_id = 0; int err; @@ -622,8 +922,8 @@ static int ice_vf_rebuild_host_vlan_cfg(struct ice_vf *vf) */ static int ice_vf_rebuild_host_mac_cfg(struct ice_vf *vf) { - struct ice_vsi *vsi = vf->pf->vsi[vf->lan_vsi_idx]; struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_vsi *vsi = ice_get_vf_vsi(vf); enum ice_status status; u8 broadcast[ETH_ALEN]; @@ -724,8 +1024,8 @@ static void ice_ena_vf_msix_mappings(struct ice_vf *vf) */ static void ice_ena_vf_q_mappings(struct ice_vf *vf, u16 max_txq, u16 max_rxq) { - struct ice_vsi *vsi = vf->pf->vsi[vf->lan_vsi_idx]; struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_vsi *vsi = ice_get_vf_vsi(vf); struct ice_hw *hw = &vf->pf->hw; u32 reg; @@ -772,7 +1072,7 @@ static void ice_ena_vf_q_mappings(struct ice_vf *vf, u16 max_txq, u16 max_rxq) */ static void ice_ena_vf_mappings(struct ice_vf *vf) { - struct ice_vsi *vsi = vf->pf->vsi[vf->lan_vsi_idx]; + struct ice_vsi *vsi = ice_get_vf_vsi(vf); ice_ena_vf_msix_mappings(vf); ice_ena_vf_q_mappings(vf, vsi->alloc_txq, vsi->alloc_rxq); @@ -1035,7 +1335,7 @@ ice_vf_set_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m, static void ice_vf_clear_counters(struct ice_vf *vf) { - struct ice_vsi *vsi = vf->pf->vsi[vf->lan_vsi_idx]; + struct ice_vsi *vsi = ice_get_vf_vsi(vf); vf->num_mac = 0; vsi->num_vlan = 0; @@ -1095,8 +1395,8 @@ static void ice_vf_rebuild_aggregator_node_cfg(struct ice_vsi *vsi) */ static void ice_vf_rebuild_host_cfg(struct ice_vf *vf) { - struct ice_vsi *vsi = vf->pf->vsi[vf->lan_vsi_idx]; struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_vsi *vsi = ice_get_vf_vsi(vf); ice_vf_set_host_trust_cfg(vf); @@ -1136,10 +1436,8 @@ static int ice_vf_rebuild_vsi_with_release(struct ice_vf *vf) */ static int ice_vf_rebuild_vsi(struct ice_vf *vf) { + struct ice_vsi *vsi = ice_get_vf_vsi(vf); struct ice_pf *pf = vf->pf; - struct ice_vsi *vsi; - - vsi = pf->vsi[vf->lan_vsi_idx]; if (ice_vsi_rebuild(vsi, true)) { dev_err(ice_pf_to_dev(pf), "failed to rebuild VF %d VSI\n", @@ -1212,8 +1510,13 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr) if (!pf->num_alloc_vfs) return false; + /* clear all malicious info if the VFs are getting reset */ + ice_for_each_vf(pf, i) + if (ice_mbx_clear_malvf(&hw->mbx_snapshot, pf->malvfs, ICE_MAX_VF_COUNT, i)) + dev_dbg(dev, "failed to clear malicious VF state for VF %u\n", i); + /* If VFs have been disabled, there is no need to reset */ - if (test_and_set_bit(__ICE_VF_DIS, pf->state)) + if (test_and_set_bit(ICE_VF_DIS, pf->state)) return false; /* Begin reset on all VFs at once */ @@ -1256,13 +1559,23 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr) ice_for_each_vf(pf, v) { vf = &pf->vf[v]; + vf->driver_caps = 0; + ice_vc_set_default_allowlist(vf); + + ice_vf_fdir_exit(vf); + /* clean VF control VSI when resetting VFs since it should be + * setup only when VF creates its first FDIR rule. + */ + if (vf->ctrl_vsi_idx != ICE_NO_VSI) + ice_vf_ctrl_invalidate_vsi(vf); + ice_vf_pre_vsi_rebuild(vf); ice_vf_rebuild_vsi(vf); ice_vf_post_vsi_rebuild(vf); } ice_flush(hw); - clear_bit(__ICE_VF_DIS, pf->state); + clear_bit(ICE_VF_DIS, pf->state); return true; } @@ -1282,7 +1595,7 @@ static bool ice_is_vf_disabled(struct ice_vf *vf) * means something else is resetting the VF, so we shouldn't continue. * Otherwise, set disable VF state bit for actual reset, and continue. */ - return (test_bit(__ICE_VF_DIS, pf->state) || + return (test_bit(ICE_VF_DIS, pf->state) || test_bit(ICE_VF_STATE_DIS, vf->vf_states)); } @@ -1307,7 +1620,7 @@ bool ice_reset_vf(struct ice_vf *vf, bool is_vflr) dev = ice_pf_to_dev(pf); - if (test_bit(__ICE_VF_RESETS_DISABLED, pf->state)) { + if (test_bit(ICE_VF_RESETS_DISABLED, pf->state)) { dev_dbg(dev, "Trying to reset VF %d, but all VF resets are disabled\n", vf->vf_id); return true; @@ -1323,7 +1636,7 @@ bool ice_reset_vf(struct ice_vf *vf, bool is_vflr) set_bit(ICE_VF_STATE_DIS, vf->vf_states); ice_trigger_vf_reset(vf, is_vflr, false); - vsi = pf->vsi[vf->lan_vsi_idx]; + vsi = ice_get_vf_vsi(vf); if (test_bit(ICE_VF_STATE_QS_ENA, vf->vf_states)) ice_dis_vf_qs(vf); @@ -1353,6 +1666,9 @@ bool ice_reset_vf(struct ice_vf *vf, bool is_vflr) usleep_range(10, 20); } + vf->driver_caps = 0; + ice_vc_set_default_allowlist(vf); + /* Display a warning if VF didn't manage to reset in time, but need to * continue on with the operation. */ @@ -1369,15 +1685,26 @@ bool ice_reset_vf(struct ice_vf *vf, bool is_vflr) else promisc_m = ICE_UCAST_PROMISC_BITS; - vsi = pf->vsi[vf->lan_vsi_idx]; + vsi = ice_get_vf_vsi(vf); if (ice_vf_set_vsi_promisc(vf, vsi, promisc_m, true)) dev_err(dev, "disabling promiscuous mode failed\n"); } + ice_vf_fdir_exit(vf); + /* clean VF control VSI when resetting VF since it should be setup + * only when VF creates its first FDIR rule. + */ + if (vf->ctrl_vsi_idx != ICE_NO_VSI) + ice_vf_ctrl_vsi_release(vf); + ice_vf_pre_vsi_rebuild(vf); ice_vf_rebuild_vsi_with_release(vf); ice_vf_post_vsi_rebuild(vf); + /* if the VF has been reset allow it to come up again */ + if (ice_mbx_clear_malvf(&hw->mbx_snapshot, pf->malvfs, ICE_MAX_VF_COUNT, vf->vf_id)) + dev_dbg(dev, "failed to clear malicious VF state for VF %u\n", i); + return true; } @@ -1532,7 +1859,7 @@ teardown: } /** - * ice_set_dflt_settings - set VF defaults during initialization/creation + * ice_set_dflt_settings_vfs - set VF defaults during initialization/creation * @pf: PF holding reference to all VFs for default configuration */ static void ice_set_dflt_settings_vfs(struct ice_pf *pf) @@ -1549,6 +1876,13 @@ static void ice_set_dflt_settings_vfs(struct ice_pf *pf) set_bit(ICE_VIRTCHNL_VF_CAP_L2, &vf->vf_caps); vf->spoofchk = true; vf->num_vf_qs = pf->num_qps_per_vf; + ice_vc_set_default_allowlist(vf); + + /* ctrl_vsi_idx will be set to a valid value only when VF + * creates its first fdir rule. + */ + ice_vf_ctrl_invalidate_vsi(vf); + ice_vf_fdir_init(vf); } } @@ -1586,7 +1920,7 @@ static int ice_ena_vfs(struct ice_pf *pf, u16 num_vfs) /* Disable global interrupt 0 so we don't try to handle the VFLR. */ wr32(hw, GLINT_DYN_CTL(pf->oicr_idx), ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S); - set_bit(__ICE_OICR_INTR_DIS, pf->state); + set_bit(ICE_OICR_INTR_DIS, pf->state); ice_flush(hw); ret = pci_enable_sriov(pf->pdev, num_vfs); @@ -1614,7 +1948,7 @@ static int ice_ena_vfs(struct ice_pf *pf, u16 num_vfs) goto err_unroll_sriov; } - clear_bit(__ICE_VF_DIS, pf->state); + clear_bit(ICE_VF_DIS, pf->state); return 0; err_unroll_sriov: @@ -1626,7 +1960,7 @@ err_pci_disable_sriov: err_unroll_intr: /* rearm interrupts here */ ice_irq_dynamic_ena(hw, NULL, NULL); - clear_bit(__ICE_OICR_INTR_DIS, pf->state); + clear_bit(ICE_OICR_INTR_DIS, pf->state); return ret; } @@ -1704,6 +2038,7 @@ int ice_sriov_configure(struct pci_dev *pdev, int num_vfs) { struct ice_pf *pf = pci_get_drvdata(pdev); struct device *dev = ice_pf_to_dev(pf); + enum ice_status status; int err; err = ice_check_sriov_allowed(pf); @@ -1712,6 +2047,7 @@ int ice_sriov_configure(struct pci_dev *pdev, int num_vfs) if (!num_vfs) { if (!pci_vfs_assigned(pdev)) { + ice_mbx_deinit_snapshot(&pf->hw); ice_free_vfs(pf); if (pf->lag) ice_enable_lag(pf->lag); @@ -1722,9 +2058,15 @@ int ice_sriov_configure(struct pci_dev *pdev, int num_vfs) return -EBUSY; } + status = ice_mbx_init_snapshot(&pf->hw, num_vfs); + if (status) + return ice_status_to_errno(status); + err = ice_pci_sriov_ena(pf, num_vfs); - if (err) + if (err) { + ice_mbx_deinit_snapshot(&pf->hw); return err; + } if (pf->lag) ice_disable_lag(pf->lag); @@ -1744,7 +2086,7 @@ void ice_process_vflr_event(struct ice_pf *pf) unsigned int vf_id; u32 reg; - if (!test_and_clear_bit(__ICE_VFLR_EVENT_PENDING, pf->state) || + if (!test_and_clear_bit(ICE_VFLR_EVENT_PENDING, pf->state) || !pf->num_alloc_vfs) return; @@ -1789,7 +2131,7 @@ static struct ice_vf *ice_get_vf_from_pfq(struct ice_pf *pf, u16 pfq) struct ice_vsi *vsi; u16 rxq_idx; - vsi = pf->vsi[vf->lan_vsi_idx]; + vsi = ice_get_vf_vsi(vf); ice_for_each_rxq(vsi, rxq_idx) if (vsi->rxq_map[rxq_idx] == pfq) @@ -1848,7 +2190,7 @@ ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event) * * send msg to VF */ -static int +int ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode, enum virtchnl_status_code v_retval, u8 *msg, u16 msglen) { @@ -1929,8 +2271,7 @@ static int ice_vc_get_ver_msg(struct ice_vf *vf, u8 *msg) */ static u16 ice_vc_get_max_frame_size(struct ice_vf *vf) { - struct ice_vsi *vsi = vf->pf->vsi[vf->lan_vsi_idx]; - struct ice_port_info *pi = vsi->port_info; + struct ice_port_info *pi = ice_vf_get_port_info(vf); u16 max_frame_size; max_frame_size = pi->phy.link_info.max_frame_size; @@ -1978,7 +2319,7 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) VIRTCHNL_VF_OFFLOAD_VLAN; vfres->vf_cap_flags = VIRTCHNL_VF_OFFLOAD_L2; - vsi = pf->vsi[vf->lan_vsi_idx]; + vsi = ice_get_vf_vsi(vf); if (!vsi) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto err; @@ -1996,6 +2337,9 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_REG; } + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_FDIR_PF) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_FDIR_PF; + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2; @@ -2017,6 +2361,12 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) if (vf->driver_caps & VIRTCHNL_VF_CAP_ADV_LINK_SPEED) vfres->vf_cap_flags |= VIRTCHNL_VF_CAP_ADV_LINK_SPEED; + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF; + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_USO) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_USO; + vfres->num_vsis = 1; /* Tx and Rx queue are equal for VF */ vfres->num_queue_pairs = vsi->num_txq; @@ -2034,6 +2384,9 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) /* match guest capabilities */ vf->driver_caps = vfres->vf_cap_flags; + ice_vc_set_caps_allowlist(vf); + ice_vc_set_working_allowlist(vf); + set_bit(ICE_VF_STATE_ACTIVE, vf->vf_states); err: @@ -2084,7 +2437,7 @@ static struct ice_vsi *ice_find_vsi_from_id(struct ice_pf *pf, u16 id) * * check for the valid VSI ID */ -static bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id) +bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id) { struct ice_pf *pf = vf->pf; struct ice_vsi *vsi; @@ -2125,6 +2478,222 @@ static bool ice_vc_isvalid_ring_len(u16 ring_len) } /** + * ice_vc_parse_rss_cfg - parses hash fields and headers from + * a specific virtchnl RSS cfg + * @hw: pointer to the hardware + * @rss_cfg: pointer to the virtchnl RSS cfg + * @addl_hdrs: pointer to the protocol header fields (ICE_FLOW_SEG_HDR_*) + * to configure + * @hash_flds: pointer to the hash bit fields (ICE_FLOW_HASH_*) to configure + * + * Return true if all the protocol header and hash fields in the RSS cfg could + * be parsed, else return false + * + * This function parses the virtchnl RSS cfg to be the intended + * hash fields and the intended header for RSS configuration + */ +static bool +ice_vc_parse_rss_cfg(struct ice_hw *hw, struct virtchnl_rss_cfg *rss_cfg, + u32 *addl_hdrs, u64 *hash_flds) +{ + const struct ice_vc_hash_field_match_type *hf_list; + const struct ice_vc_hdr_match_type *hdr_list; + int i, hf_list_len, hdr_list_len; + + if (!strncmp(hw->active_pkg_name, "ICE COMMS Package", + sizeof(hw->active_pkg_name))) { + hf_list = ice_vc_hash_field_list_comms; + hf_list_len = ARRAY_SIZE(ice_vc_hash_field_list_comms); + hdr_list = ice_vc_hdr_list_comms; + hdr_list_len = ARRAY_SIZE(ice_vc_hdr_list_comms); + } else { + hf_list = ice_vc_hash_field_list_os; + hf_list_len = ARRAY_SIZE(ice_vc_hash_field_list_os); + hdr_list = ice_vc_hdr_list_os; + hdr_list_len = ARRAY_SIZE(ice_vc_hdr_list_os); + } + + for (i = 0; i < rss_cfg->proto_hdrs.count; i++) { + struct virtchnl_proto_hdr *proto_hdr = + &rss_cfg->proto_hdrs.proto_hdr[i]; + bool hdr_found = false; + int j; + + /* Find matched ice headers according to virtchnl headers. */ + for (j = 0; j < hdr_list_len; j++) { + struct ice_vc_hdr_match_type hdr_map = hdr_list[j]; + + if (proto_hdr->type == hdr_map.vc_hdr) { + *addl_hdrs |= hdr_map.ice_hdr; + hdr_found = true; + } + } + + if (!hdr_found) + return false; + + /* Find matched ice hash fields according to + * virtchnl hash fields. + */ + for (j = 0; j < hf_list_len; j++) { + struct ice_vc_hash_field_match_type hf_map = hf_list[j]; + + if (proto_hdr->type == hf_map.vc_hdr && + proto_hdr->field_selector == hf_map.vc_hash_field) { + *hash_flds |= hf_map.ice_hash_field; + break; + } + } + } + + return true; +} + +/** + * ice_vf_adv_rss_offload_ena - determine if capabilities support advanced + * RSS offloads + * @caps: VF driver negotiated capabilities + * + * Return true if VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF capability is set, + * else return false + */ +static bool ice_vf_adv_rss_offload_ena(u32 caps) +{ + return !!(caps & VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF); +} + +/** + * ice_vc_handle_rss_cfg + * @vf: pointer to the VF info + * @msg: pointer to the message buffer + * @add: add a RSS config if true, otherwise delete a RSS config + * + * This function adds/deletes a RSS config + */ +static int ice_vc_handle_rss_cfg(struct ice_vf *vf, u8 *msg, bool add) +{ + u32 v_opcode = add ? VIRTCHNL_OP_ADD_RSS_CFG : VIRTCHNL_OP_DEL_RSS_CFG; + struct virtchnl_rss_cfg *rss_cfg = (struct virtchnl_rss_cfg *)msg; + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_hw *hw = &vf->pf->hw; + struct ice_vsi *vsi; + + if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) { + dev_dbg(dev, "VF %d attempting to configure RSS, but RSS is not supported by the PF\n", + vf->vf_id); + v_ret = VIRTCHNL_STATUS_ERR_NOT_SUPPORTED; + goto error_param; + } + + if (!ice_vf_adv_rss_offload_ena(vf->driver_caps)) { + dev_dbg(dev, "VF %d attempting to configure RSS, but Advanced RSS offload is not supported\n", + vf->vf_id); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (rss_cfg->proto_hdrs.count > VIRTCHNL_MAX_NUM_PROTO_HDRS || + rss_cfg->rss_algorithm < VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC || + rss_cfg->rss_algorithm > VIRTCHNL_RSS_ALG_XOR_SYMMETRIC) { + dev_dbg(dev, "VF %d attempting to configure RSS, but RSS configuration is not valid\n", + vf->vf_id); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (rss_cfg->rss_algorithm == VIRTCHNL_RSS_ALG_R_ASYMMETRIC) { + struct ice_vsi_ctx *ctx; + enum ice_status status; + u8 lut_type, hash_type; + + lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_VSI; + hash_type = add ? ICE_AQ_VSI_Q_OPT_RSS_XOR : + ICE_AQ_VSI_Q_OPT_RSS_TPLZ; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) { + v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; + goto error_param; + } + + ctx->info.q_opt_rss = ((lut_type << + ICE_AQ_VSI_Q_OPT_RSS_LUT_S) & + ICE_AQ_VSI_Q_OPT_RSS_LUT_M) | + (hash_type & + ICE_AQ_VSI_Q_OPT_RSS_HASH_M); + + /* Preserve existing queueing option setting */ + ctx->info.q_opt_rss |= (vsi->info.q_opt_rss & + ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_M); + ctx->info.q_opt_tc = vsi->info.q_opt_tc; + ctx->info.q_opt_flags = vsi->info.q_opt_rss; + + ctx->info.valid_sections = + cpu_to_le16(ICE_AQ_VSI_PROP_Q_OPT_VALID); + + status = ice_update_vsi(hw, vsi->idx, ctx, NULL); + if (status) { + dev_err(dev, "update VSI for RSS failed, err %s aq_err %s\n", + ice_stat_str(status), + ice_aq_str(hw->adminq.sq_last_status)); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + } else { + vsi->info.q_opt_rss = ctx->info.q_opt_rss; + } + + kfree(ctx); + } else { + u32 addl_hdrs = ICE_FLOW_SEG_HDR_NONE; + u64 hash_flds = ICE_HASH_INVALID; + + if (!ice_vc_parse_rss_cfg(hw, rss_cfg, &addl_hdrs, + &hash_flds)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + if (add) { + if (ice_add_rss_cfg(hw, vsi->idx, hash_flds, + addl_hdrs)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + dev_err(dev, "ice_add_rss_cfg failed for vsi = %d, v_ret = %d\n", + vsi->vsi_num, v_ret); + } + } else { + enum ice_status status; + + status = ice_rem_rss_cfg(hw, vsi->idx, hash_flds, + addl_hdrs); + /* We just ignore ICE_ERR_DOES_NOT_EXIST, because + * if two configurations share the same profile remove + * one of them actually removes both, since the + * profile is deleted. + */ + if (status && status != ICE_ERR_DOES_NOT_EXIST) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + dev_err(dev, "ice_rem_rss_cfg failed for VF ID:%d, error:%s\n", + vf->vf_id, ice_stat_str(status)); + } + } + } + +error_param: + return ice_vc_send_msg_to_vf(vf, v_opcode, v_ret, NULL, 0); +} + +/** * ice_vc_config_rss_key * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -2136,7 +2705,6 @@ static int ice_vc_config_rss_key(struct ice_vf *vf, u8 *msg) enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; struct virtchnl_rss_key *vrk = (struct virtchnl_rss_key *)msg; - struct ice_pf *pf = vf->pf; struct ice_vsi *vsi; if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { @@ -2159,13 +2727,13 @@ static int ice_vc_config_rss_key(struct ice_vf *vf, u8 *msg) goto error_param; } - vsi = pf->vsi[vf->lan_vsi_idx]; + vsi = ice_get_vf_vsi(vf); if (!vsi) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } - if (ice_set_rss(vsi, vrk->key, NULL, 0)) + if (ice_set_rss_key(vsi, vrk->key)) v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR; error_param: return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_KEY, v_ret, @@ -2183,7 +2751,6 @@ static int ice_vc_config_rss_lut(struct ice_vf *vf, u8 *msg) { struct virtchnl_rss_lut *vrl = (struct virtchnl_rss_lut *)msg; enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; - struct ice_pf *pf = vf->pf; struct ice_vsi *vsi; if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { @@ -2206,13 +2773,13 @@ static int ice_vc_config_rss_lut(struct ice_vf *vf, u8 *msg) goto error_param; } - vsi = pf->vsi[vf->lan_vsi_idx]; + vsi = ice_get_vf_vsi(vf); if (!vsi) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } - if (ice_set_rss(vsi, NULL, vrl->lut, ICE_VSIQF_HLUT_ARRAY_SIZE)) + if (ice_set_rss_lut(vsi, vrl->lut, ICE_VSIQF_HLUT_ARRAY_SIZE)) v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR; error_param: return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_LUT, v_ret, @@ -2289,7 +2856,7 @@ int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena) if (ret) return ret; - vf_vsi = pf->vsi[vf->lan_vsi_idx]; + vf_vsi = ice_get_vf_vsi(vf); if (!vf_vsi) { netdev_err(netdev, "VSI %d for VF %d is null\n", vf->lan_vsi_idx, vf->vf_id); @@ -2394,7 +2961,7 @@ static int ice_vc_cfg_promiscuous_mode_msg(struct ice_vf *vf, u8 *msg) goto error_param; } - vsi = pf->vsi[vf->lan_vsi_idx]; + vsi = ice_get_vf_vsi(vf); if (!vsi) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; @@ -2530,7 +3097,6 @@ static int ice_vc_get_stats_msg(struct ice_vf *vf, u8 *msg) struct virtchnl_queue_select *vqs = (struct virtchnl_queue_select *)msg; struct ice_eth_stats stats = { 0 }; - struct ice_pf *pf = vf->pf; struct ice_vsi *vsi; if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { @@ -2543,7 +3109,7 @@ static int ice_vc_get_stats_msg(struct ice_vf *vf, u8 *msg) goto error_param; } - vsi = pf->vsi[vf->lan_vsi_idx]; + vsi = ice_get_vf_vsi(vf); if (!vsi) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; @@ -2633,7 +3199,6 @@ static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg) enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; struct virtchnl_queue_select *vqs = (struct virtchnl_queue_select *)msg; - struct ice_pf *pf = vf->pf; struct ice_vsi *vsi; unsigned long q_map; u16 vf_q_id; @@ -2653,7 +3218,7 @@ static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg) goto error_param; } - vsi = pf->vsi[vf->lan_vsi_idx]; + vsi = ice_get_vf_vsi(vf); if (!vsi) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; @@ -2685,7 +3250,6 @@ static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg) set_bit(vf_q_id, vf->rxq_ena); } - vsi = pf->vsi[vf->lan_vsi_idx]; q_map = vqs->tx_queues; for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { @@ -2724,7 +3288,6 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; struct virtchnl_queue_select *vqs = (struct virtchnl_queue_select *)msg; - struct ice_pf *pf = vf->pf; struct ice_vsi *vsi; unsigned long q_map; u16 vf_q_id; @@ -2745,7 +3308,7 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) goto error_param; } - vsi = pf->vsi[vf->lan_vsi_idx]; + vsi = ice_get_vf_vsi(vf); if (!vsi) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; @@ -2910,7 +3473,7 @@ static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg) goto error_param; } - vsi = pf->vsi[vf->lan_vsi_idx]; + vsi = ice_get_vf_vsi(vf); if (!vsi) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; @@ -2987,7 +3550,7 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) goto error_param; } - vsi = pf->vsi[vf->lan_vsi_idx]; + vsi = ice_get_vf_vsi(vf); if (!vsi) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; @@ -3222,7 +3785,7 @@ ice_vc_handle_mac_addr_msg(struct ice_vf *vf, u8 *msg, bool set) goto handle_mac_exit; } - vsi = pf->vsi[vf->lan_vsi_idx]; + vsi = ice_get_vf_vsi(vf); if (!vsi) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto handle_mac_exit; @@ -3454,7 +4017,7 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) } hw = &pf->hw; - vsi = pf->vsi[vf->lan_vsi_idx]; + vsi = ice_get_vf_vsi(vf); if (!vsi) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; @@ -3621,7 +4184,6 @@ static int ice_vc_remove_vlan_msg(struct ice_vf *vf, u8 *msg) static int ice_vc_ena_vlan_stripping(struct ice_vf *vf) { enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; - struct ice_pf *pf = vf->pf; struct ice_vsi *vsi; if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { @@ -3634,7 +4196,7 @@ static int ice_vc_ena_vlan_stripping(struct ice_vf *vf) goto error_param; } - vsi = pf->vsi[vf->lan_vsi_idx]; + vsi = ice_get_vf_vsi(vf); if (ice_vsi_manage_vlan_stripping(vsi, true)) v_ret = VIRTCHNL_STATUS_ERR_PARAM; @@ -3652,7 +4214,6 @@ error_param: static int ice_vc_dis_vlan_stripping(struct ice_vf *vf) { enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; - struct ice_pf *pf = vf->pf; struct ice_vsi *vsi; if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { @@ -3665,7 +4226,7 @@ static int ice_vc_dis_vlan_stripping(struct ice_vf *vf) goto error_param; } - vsi = pf->vsi[vf->lan_vsi_idx]; + vsi = ice_get_vf_vsi(vf); if (!vsi) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; @@ -3691,7 +4252,7 @@ error_param: */ static int ice_vf_init_vlan_stripping(struct ice_vf *vf) { - struct ice_vsi *vsi = vf->pf->vsi[vf->lan_vsi_idx]; + struct ice_vsi *vsi = ice_get_vf_vsi(vf); if (!vsi) return -EINVAL; @@ -3747,6 +4308,13 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) err = -EINVAL; } + if (!ice_vc_is_opcode_allowed(vf, v_opcode)) { + ice_vc_send_msg_to_vf(vf, v_opcode, + VIRTCHNL_STATUS_ERR_NOT_SUPPORTED, NULL, + 0); + return; + } + error_handler: if (err) { ice_vc_send_msg_to_vf(vf, v_opcode, VIRTCHNL_STATUS_ERR_PARAM, @@ -3816,6 +4384,18 @@ error_handler: case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING: err = ice_vc_dis_vlan_stripping(vf); break; + case VIRTCHNL_OP_ADD_FDIR_FILTER: + err = ice_vc_add_fdir_fltr(vf, msg); + break; + case VIRTCHNL_OP_DEL_FDIR_FILTER: + err = ice_vc_del_fdir_fltr(vf, msg); + break; + case VIRTCHNL_OP_ADD_RSS_CFG: + err = ice_vc_handle_rss_cfg(vf, msg, true); + break; + case VIRTCHNL_OP_DEL_RSS_CFG: + err = ice_vc_handle_rss_cfg(vf, msg, false); + break; case VIRTCHNL_OP_UNKNOWN: default: dev_err(dev, "Unsupported opcode %d from VF %d\n", v_opcode, @@ -4066,7 +4646,7 @@ int ice_get_vf_stats(struct net_device *netdev, int vf_id, if (ret) return ret; - vsi = pf->vsi[vf->lan_vsi_idx]; + vsi = ice_get_vf_vsi(vf); if (!vsi) return -EINVAL; @@ -4108,7 +4688,7 @@ void ice_print_vf_rx_mdd_event(struct ice_vf *vf) } /** - * ice_print_vfs_mdd_event - print VFs malicious driver detect event + * ice_print_vfs_mdd_events - print VFs malicious driver detect event * @pf: pointer to the PF structure * * Called from ice_handle_mdd_event to rate limit and print VFs MDD events. @@ -4120,7 +4700,7 @@ void ice_print_vfs_mdd_events(struct ice_pf *pf) int i; /* check that there are pending MDD events to print */ - if (!test_and_clear_bit(__ICE_MDD_VF_PRINT_PENDING, pf->state)) + if (!test_and_clear_bit(ICE_MDD_VF_PRINT_PENDING, pf->state)) return; /* VF MDD event logs are rate limited to one second intervals */ @@ -4160,7 +4740,6 @@ void ice_print_vfs_mdd_events(struct ice_pf *pf) */ void ice_restore_all_vfs_msi_state(struct pci_dev *pdev) { - struct pci_dev *vfdev; u16 vf_id; int pos; @@ -4169,6 +4748,8 @@ void ice_restore_all_vfs_msi_state(struct pci_dev *pdev) pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV); if (pos) { + struct pci_dev *vfdev; + pci_read_config_word(pdev, pos + PCI_SRIOV_VF_DID, &vf_id); vfdev = pci_get_device(pdev->vendor, vf_id, NULL); @@ -4180,3 +4761,70 @@ void ice_restore_all_vfs_msi_state(struct pci_dev *pdev) } } } + +/** + * ice_is_malicious_vf - helper function to detect a malicious VF + * @pf: ptr to struct ice_pf + * @event: pointer to the AQ event + * @num_msg_proc: the number of messages processed so far + * @num_msg_pending: the number of messages peinding in admin queue + */ +bool +ice_is_malicious_vf(struct ice_pf *pf, struct ice_rq_event_info *event, + u16 num_msg_proc, u16 num_msg_pending) +{ + s16 vf_id = le16_to_cpu(event->desc.retval); + struct device *dev = ice_pf_to_dev(pf); + struct ice_mbx_data mbxdata; + enum ice_status status; + bool malvf = false; + struct ice_vf *vf; + + if (ice_validate_vf_id(pf, vf_id)) + return false; + + vf = &pf->vf[vf_id]; + /* Check if VF is disabled. */ + if (test_bit(ICE_VF_STATE_DIS, vf->vf_states)) + return false; + + mbxdata.num_msg_proc = num_msg_proc; + mbxdata.num_pending_arq = num_msg_pending; + mbxdata.max_num_msgs_mbx = pf->hw.mailboxq.num_rq_entries; +#define ICE_MBX_OVERFLOW_WATERMARK 64 + mbxdata.async_watermark_val = ICE_MBX_OVERFLOW_WATERMARK; + + /* check to see if we have a malicious VF */ + status = ice_mbx_vf_state_handler(&pf->hw, &mbxdata, vf_id, &malvf); + if (status) + return false; + + if (malvf) { + bool report_vf = false; + + /* if the VF is malicious and we haven't let the user + * know about it, then let them know now + */ + status = ice_mbx_report_malvf(&pf->hw, pf->malvfs, + ICE_MAX_VF_COUNT, vf_id, + &report_vf); + if (status) + dev_dbg(dev, "Error reporting malicious VF\n"); + + if (report_vf) { + struct ice_vsi *pf_vsi = ice_get_main_vsi(pf); + + if (pf_vsi) + dev_warn(dev, "VF MAC %pM on PF MAC %pM is generating asynchronous messages and may be overflowing the PF message queue. Please see the Adapter User Guide for more information\n", + &vf->dflt_lan_addr.addr[0], + pf_vsi->netdev->dev_addr); + } + + return true; + } + + /* if there was an error in detection or the VF is not malicious then + * return false + */ + return false; +} diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h index 0f519fba3770..d800ed83d6c3 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h @@ -4,6 +4,7 @@ #ifndef _ICE_VIRTCHNL_PF_H_ #define _ICE_VIRTCHNL_PF_H_ #include "ice.h" +#include "ice_virtchnl_fdir.h" /* Restrict number of MAC Addr and VLAN that non-trusted VF can programmed */ #define ICE_MAX_VLAN_PER_VF 8 @@ -70,6 +71,8 @@ struct ice_vf { u16 vf_id; /* VF ID in the PF space */ u16 lan_vsi_idx; /* index into PF struct */ + u16 ctrl_vsi_idx; + struct ice_vf_fdir fdir; /* first vector index of this VF in the PF space */ int first_vector_idx; struct ice_sw *vf_sw_id; /* switch ID the VF VSIs connect to */ @@ -100,6 +103,7 @@ struct ice_vf { u16 num_vf_qs; /* num of queue configured per VF */ struct ice_mdd_vf_events mdd_rx_events; struct ice_mdd_vf_events mdd_tx_events; + DECLARE_BITMAP(opcodes_allowlist, VIRTCHNL_OP_MAX); }; #ifdef CONFIG_PCI_IOV @@ -116,6 +120,9 @@ void ice_vc_notify_reset(struct ice_pf *pf); bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr); bool ice_reset_vf(struct ice_vf *vf, bool is_vflr); void ice_restore_all_vfs_msi_state(struct pci_dev *pdev); +bool +ice_is_malicious_vf(struct ice_pf *pf, struct ice_rq_event_info *event, + u16 num_msg_proc, u16 num_msg_pending); int ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, @@ -138,6 +145,11 @@ void ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event); void ice_print_vfs_mdd_events(struct ice_pf *pf); void ice_print_vf_rx_mdd_event(struct ice_vf *vf); +struct ice_vsi *ice_vf_ctrl_vsi_setup(struct ice_vf *vf); +int +ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode, + enum virtchnl_status_code v_retval, u8 *msg, u16 msglen); +bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id); #else /* CONFIG_PCI_IOV */ #define ice_process_vflr_event(pf) do {} while (0) #define ice_free_vfs(pf) do {} while (0) @@ -151,6 +163,15 @@ void ice_print_vf_rx_mdd_event(struct ice_vf *vf); #define ice_restore_all_vfs_msi_state(pdev) do {} while (0) static inline bool +ice_is_malicious_vf(struct ice_pf __always_unused *pf, + struct ice_rq_event_info __always_unused *event, + u16 __always_unused num_msg_proc, + u16 __always_unused num_msg_pending) +{ + return false; +} + +static inline bool ice_reset_all_vfs(struct ice_pf __always_unused *pf, bool __always_unused is_vflr) { diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 9f94d9159acd..faa7b8d96adb 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -108,9 +108,6 @@ ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector) ice_cfg_itr(hw, q_vector); - wr32(hw, GLINT_RATE(reg_idx), - ice_intrl_usec_to_reg(q_vector->intrl, hw->intrl_gran)); - ice_for_each_ring(ring, q_vector->tx) ice_cfg_txq_interrupt(vsi, ring->reg_idx, reg_idx, q_vector->tx.itr_idx); @@ -159,7 +156,7 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) rx_ring = vsi->rx_rings[q_idx]; q_vector = rx_ring->q_vector; - while (test_and_set_bit(__ICE_CFG_BUSY, vsi->state)) { + while (test_and_set_bit(ICE_CFG_BUSY, vsi->state)) { timeout--; if (!timeout) return -EBUSY; @@ -249,7 +246,7 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) if (err) goto free_buf; - clear_bit(__ICE_CFG_BUSY, vsi->state); + clear_bit(ICE_CFG_BUSY, vsi->state); ice_qvec_toggle_napi(vsi, q_vector, true); ice_qvec_ena_irq(vsi, q_vector); @@ -473,6 +470,14 @@ ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp) xdp_prog = READ_ONCE(rx_ring->xdp_prog); act = bpf_prog_run_xdp(xdp_prog, xdp); + + if (likely(act == XDP_REDIRECT)) { + err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); + result = !err ? ICE_XDP_REDIR : ICE_XDP_CONSUMED; + rcu_read_unlock(); + return result; + } + switch (act) { case XDP_PASS: break; @@ -480,10 +485,6 @@ ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp) xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->q_index]; result = ice_xmit_xdp_buff(xdp, xdp_ring); break; - case XDP_REDIRECT: - err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); - result = !err ? ICE_XDP_REDIR : ICE_XDP_CONSUMED; - break; default: bpf_warn_invalid_xdp_action(act); fallthrough; @@ -754,7 +755,7 @@ 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_DOWN, vsi->state)) return -ENETDOWN; if (!ice_is_xdp_ena_vsi(vsi)) diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h index d2e2c50ce257..ca5429774994 100644 --- a/drivers/net/ethernet/intel/igb/e1000_defines.h +++ b/drivers/net/ethernet/intel/igb/e1000_defines.h @@ -340,10 +340,10 @@ #define I210_RXPBSIZE_PB_32KB 0x00000020 #define I210_TXPBSIZE_DEFAULT 0x04000014 /* TXPBSIZE default */ #define I210_TXPBSIZE_MASK 0xC0FFFFFF -#define I210_TXPBSIZE_PB0_8KB (8 << 0) -#define I210_TXPBSIZE_PB1_8KB (8 << 6) -#define I210_TXPBSIZE_PB2_4KB (4 << 12) -#define I210_TXPBSIZE_PB3_4KB (4 << 18) +#define I210_TXPBSIZE_PB0_6KB (6 << 0) +#define I210_TXPBSIZE_PB1_6KB (6 << 6) +#define I210_TXPBSIZE_PB2_6KB (6 << 12) +#define I210_TXPBSIZE_PB3_6KB (6 << 18) #define I210_DTXMXPKTSZ_DEFAULT 0x00000098 diff --git a/drivers/net/ethernet/intel/igb/e1000_mac.c b/drivers/net/ethernet/intel/igb/e1000_mac.c index fd8eb2f9ab9d..e63ee3cca5ea 100644 --- a/drivers/net/ethernet/intel/igb/e1000_mac.c +++ b/drivers/net/ethernet/intel/igb/e1000_mac.c @@ -484,6 +484,31 @@ static u32 igb_hash_mc_addr(struct e1000_hw *hw, u8 *mc_addr) } /** + * igb_i21x_hw_doublecheck - double checks potential HW issue in i21X + * @hw: pointer to the HW structure + * + * Checks if multicast array is wrote correctly + * If not then rewrites again to register + **/ +static void igb_i21x_hw_doublecheck(struct e1000_hw *hw) +{ + bool is_failed; + int i; + + do { + is_failed = false; + for (i = hw->mac.mta_reg_count - 1; i >= 0; i--) { + if (array_rd32(E1000_MTA, i) != hw->mac.mta_shadow[i]) { + is_failed = true; + array_wr32(E1000_MTA, i, hw->mac.mta_shadow[i]); + wrfl(); + break; + } + } + } while (is_failed); +} + +/** * igb_update_mc_addr_list - Update Multicast addresses * @hw: pointer to the HW structure * @mc_addr_list: array of multicast addresses to program @@ -516,6 +541,8 @@ void igb_update_mc_addr_list(struct e1000_hw *hw, for (i = hw->mac.mta_reg_count - 1; i >= 0; i--) array_wr32(E1000_MTA, i, hw->mac.mta_shadow[i]); wrfl(); + if (hw->mac.type == e1000_i210 || hw->mac.type == e1000_i211) + igb_i21x_hw_doublecheck(hw); } /** diff --git a/drivers/net/ethernet/intel/igb/e1000_mbx.c b/drivers/net/ethernet/intel/igb/e1000_mbx.c index 33cceb77e960..29383112bc19 100644 --- a/drivers/net/ethernet/intel/igb/e1000_mbx.c +++ b/drivers/net/ethernet/intel/igb/e1000_mbx.c @@ -441,7 +441,7 @@ out_no_read: } /** - * e1000_init_mbx_params_pf - set initial values for pf mailbox + * igb_init_mbx_params_pf - set initial values for pf mailbox * @hw: pointer to the HW structure * * Initializes the hw->mbx struct to correct values for pf mailbox diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.c b/drivers/net/ethernet/intel/igb/e1000_phy.c index 8c8eb82e6272..a018000f7db9 100644 --- a/drivers/net/ethernet/intel/igb/e1000_phy.c +++ b/drivers/net/ethernet/intel/igb/e1000_phy.c @@ -836,6 +836,7 @@ s32 igb_copper_link_setup_igp(struct e1000_hw *hw) break; case e1000_ms_auto: data &= ~CR_1000T_MS_ENABLE; + break; default: break; } diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 28baf203459a..7545da216d8b 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -2347,35 +2347,23 @@ static void igb_get_strings(struct net_device *netdev, u32 stringset, u8 *data) IGB_TEST_LEN*ETH_GSTRING_LEN); break; case ETH_SS_STATS: - for (i = 0; i < IGB_GLOBAL_STATS_LEN; i++) { - memcpy(p, igb_gstrings_stats[i].stat_string, - ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - } - for (i = 0; i < IGB_NETDEV_STATS_LEN; i++) { - memcpy(p, igb_gstrings_net_stats[i].stat_string, - ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - } + for (i = 0; i < IGB_GLOBAL_STATS_LEN; i++) + ethtool_sprintf(&p, + igb_gstrings_stats[i].stat_string); + for (i = 0; i < IGB_NETDEV_STATS_LEN; i++) + ethtool_sprintf(&p, + igb_gstrings_net_stats[i].stat_string); for (i = 0; i < adapter->num_tx_queues; i++) { - sprintf(p, "tx_queue_%u_packets", i); - p += ETH_GSTRING_LEN; - sprintf(p, "tx_queue_%u_bytes", i); - p += ETH_GSTRING_LEN; - sprintf(p, "tx_queue_%u_restart", i); - p += ETH_GSTRING_LEN; + ethtool_sprintf(&p, "tx_queue_%u_packets", i); + ethtool_sprintf(&p, "tx_queue_%u_bytes", i); + ethtool_sprintf(&p, "tx_queue_%u_restart", i); } for (i = 0; i < adapter->num_rx_queues; i++) { - sprintf(p, "rx_queue_%u_packets", i); - p += ETH_GSTRING_LEN; - sprintf(p, "rx_queue_%u_bytes", i); - p += ETH_GSTRING_LEN; - sprintf(p, "rx_queue_%u_drops", i); - p += ETH_GSTRING_LEN; - sprintf(p, "rx_queue_%u_csum_err", i); - p += ETH_GSTRING_LEN; - sprintf(p, "rx_queue_%u_alloc_failed", i); - p += ETH_GSTRING_LEN; + ethtool_sprintf(&p, "rx_queue_%u_packets", i); + ethtool_sprintf(&p, "rx_queue_%u_bytes", i); + ethtool_sprintf(&p, "rx_queue_%u_drops", i); + ethtool_sprintf(&p, "rx_queue_%u_csum_err", i); + ethtool_sprintf(&p, "rx_queue_%u_alloc_failed", i); } /* BUG_ON(p - data != IGB_STATS_LEN * ETH_GSTRING_LEN); */ break; @@ -3022,6 +3010,7 @@ static int igb_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) break; case ETHTOOL_SRXCLSRLDEL: ret = igb_del_ethtool_nfc_entry(adapter, cmd); + break; default: break; } diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index a45cd2b416c8..038a9fd1af44 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -1921,8 +1921,8 @@ static void igb_setup_tx_mode(struct igb_adapter *adapter) */ val = rd32(E1000_TXPBS); val &= ~I210_TXPBSIZE_MASK; - val |= I210_TXPBSIZE_PB0_8KB | I210_TXPBSIZE_PB1_8KB | - I210_TXPBSIZE_PB2_4KB | I210_TXPBSIZE_PB3_4KB; + val |= I210_TXPBSIZE_PB0_6KB | I210_TXPBSIZE_PB1_6KB | + I210_TXPBSIZE_PB2_6KB | I210_TXPBSIZE_PB3_6KB; wr32(E1000_TXPBS, val); val = rd32(E1000_RXPBS); @@ -2037,7 +2037,7 @@ static void igb_power_down_link(struct igb_adapter *adapter) } /** - * Detect and switch function for Media Auto Sense + * igb_check_swap_media - Detect and switch function for Media Auto Sense * @adapter: address of the board private structure **/ static void igb_check_swap_media(struct igb_adapter *adapter) @@ -2934,7 +2934,7 @@ static int igb_xdp_xmit(struct net_device *dev, int n, int cpu = smp_processor_id(); struct igb_ring *tx_ring; struct netdev_queue *nq; - int drops = 0; + int nxmit = 0; int i; if (unlikely(test_bit(__IGB_DOWN, &adapter->state))) @@ -2961,10 +2961,9 @@ static int igb_xdp_xmit(struct net_device *dev, int n, int err; err = igb_xmit_xdp_ring(adapter, tx_ring, xdpf); - if (err != IGB_XDP_TX) { - xdp_return_frame_rx_napi(xdpf); - drops++; - } + if (err != IGB_XDP_TX) + break; + nxmit++; } __netif_tx_unlock(nq); @@ -2972,7 +2971,7 @@ static int igb_xdp_xmit(struct net_device *dev, int n, if (unlikely(flags & XDP_XMIT_FLUSH)) igb_xdp_ring_update_tail(tx_ring); - return n - drops; + return nxmit; } static const struct net_device_ops igb_netdev_ops = { @@ -3115,7 +3114,7 @@ static s32 igb_init_i2c(struct igb_adapter *adapter) return 0; /* Initialize the i2c bus which is controlled by the registers. - * This bus will use the i2c_algo_bit structue that implements + * This bus will use the i2c_algo_bit structure that implements * the protocol through toggling of the 4 bits in the register. */ adapter->i2c_adap.owner = THIS_MODULE; @@ -4020,7 +4019,7 @@ static int igb_sw_init(struct igb_adapter *adapter) } /** - * igb_open - Called when a network interface is made active + * __igb_open - Called when a network interface is made active * @netdev: network interface device structure * @resuming: indicates whether we are in a resume call * @@ -4138,7 +4137,7 @@ int igb_open(struct net_device *netdev) } /** - * igb_close - Disables a network interface + * __igb_close - Disables a network interface * @netdev: network interface device structure * @suspending: indicates we are in a suspend call * @@ -5856,7 +5855,7 @@ static void igb_tx_ctxtdesc(struct igb_ring *tx_ring, */ if (tx_ring->launchtime_enable) { ts = ktime_to_timespec64(first->skb->tstamp); - first->skb->tstamp = ktime_set(0, 0); + skb_txtime_consumed(first->skb); context_desc->seqnum_seed = cpu_to_le32(ts.tv_nsec / 32); } else { context_desc->seqnum_seed = 0; diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 86a576201f5f..ba61fe9bfaf4 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -1025,6 +1025,7 @@ static int igb_ptp_set_timestamp_mode(struct igb_adapter *adapter, switch (config->tx_type) { case HWTSTAMP_TX_OFF: tsync_tx_ctl = 0; + break; case HWTSTAMP_TX_ON: break; default: diff --git a/drivers/net/ethernet/intel/igc/Makefile b/drivers/net/ethernet/intel/igc/Makefile index 1c3051db9085..95d1e8c490a4 100644 --- a/drivers/net/ethernet/intel/igc/Makefile +++ b/drivers/net/ethernet/intel/igc/Makefile @@ -8,4 +8,4 @@ obj-$(CONFIG_IGC) += igc.o igc-objs := igc_main.o igc_mac.o igc_i225.o igc_base.o igc_nvm.o igc_phy.o \ -igc_diag.o igc_ethtool.o igc_ptp.o igc_dump.o igc_tsn.o +igc_diag.o igc_ethtool.o igc_ptp.o igc_dump.o igc_tsn.o igc_xdp.o diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 1b08a7dc7bc4..25871351730b 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -28,6 +28,11 @@ void igc_ethtool_set_ops(struct net_device *); #define MAX_ETYPE_FILTER 8 #define IGC_RETA_SIZE 128 +/* SDP support */ +#define IGC_N_EXTTS 2 +#define IGC_N_PEROUT 2 +#define IGC_N_SDP 4 + enum igc_mac_filter_type { IGC_MAC_FILTER_TYPE_DST = 0, IGC_MAC_FILTER_TYPE_SRC @@ -111,6 +116,8 @@ struct igc_ring { struct sk_buff *skb; }; }; + + struct xdp_rxq_info xdp_rxq; } ____cacheline_internodealigned_in_smp; /* Board specific private data structure */ @@ -219,6 +226,16 @@ struct igc_adapter { ktime_t ptp_reset_start; /* Reset time in clock mono */ char fw_version[32]; + + struct bpf_prog *xdp_prog; + + bool pps_sys_wrap_on; + + struct ptp_pin_desc sdp_config[IGC_N_SDP]; + struct { + struct timespec64 start; + struct timespec64 period; + } perout[IGC_N_PEROUT]; }; void igc_up(struct igc_adapter *adapter); @@ -373,6 +390,8 @@ enum igc_tx_flags { /* olinfo flags */ IGC_TX_FLAGS_IPV4 = 0x10, IGC_TX_FLAGS_CSUM = 0x20, + + IGC_TX_FLAGS_XDP = 0x100, }; enum igc_boards { @@ -395,7 +414,10 @@ enum igc_boards { struct igc_tx_buffer { union igc_adv_tx_desc *next_to_watch; unsigned long time_stamp; - struct sk_buff *skb; + union { + struct sk_buff *skb; + struct xdp_frame *xdpf; + }; unsigned int bytecount; u16 gso_segs; __be16 protocol; @@ -504,6 +526,10 @@ enum igc_ring_flags_t { #define ring_uses_large_buffer(ring) \ test_bit(IGC_RING_FLAG_RX_3K_BUFFER, &(ring)->flags) +#define set_ring_uses_large_buffer(ring) \ + set_bit(IGC_RING_FLAG_RX_3K_BUFFER, &(ring)->flags) +#define clear_ring_uses_large_buffer(ring) \ + clear_bit(IGC_RING_FLAG_RX_3K_BUFFER, &(ring)->flags) #define ring_uses_build_skb(ring) \ test_bit(IGC_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags) @@ -547,8 +573,7 @@ void igc_ptp_init(struct igc_adapter *adapter); void igc_ptp_reset(struct igc_adapter *adapter); void igc_ptp_suspend(struct igc_adapter *adapter); void igc_ptp_stop(struct igc_adapter *adapter); -void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, __le32 *va, - struct sk_buff *skb); +ktime_t igc_ptp_rx_pktstamp(struct igc_adapter *adapter, __le32 *buf); int igc_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr); int igc_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr); void igc_ptp_tx_hang(struct igc_adapter *adapter); diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index b909f00a79e6..0103dda32f39 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -8,6 +8,8 @@ #define REQ_TX_DESCRIPTOR_MULTIPLE 8 #define REQ_RX_DESCRIPTOR_MULTIPLE 8 +#define IGC_CTRL_EXT_SDP2_DIR 0x00000400 /* SDP2 Data direction */ +#define IGC_CTRL_EXT_SDP3_DIR 0x00000800 /* SDP3 Data direction */ #define IGC_CTRL_EXT_DRV_LOAD 0x10000000 /* Drv loaded bit for FW */ /* Definitions for power management and wakeup registers */ @@ -96,6 +98,9 @@ #define IGC_CTRL_RFCE 0x08000000 /* Receive Flow Control enable */ #define IGC_CTRL_TFCE 0x10000000 /* Transmit flow control enable */ +#define IGC_CTRL_SDP0_DIR 0x00400000 /* SDP0 Data direction */ +#define IGC_CTRL_SDP1_DIR 0x00800000 /* SDP1 Data direction */ + /* As per the EAS the maximum supported size is 9.5KB (9728 bytes) */ #define MAX_JUMBO_FRAME_SIZE 0x2600 @@ -403,6 +408,64 @@ #define IGC_TSYNCTXCTL_START_SYNC 0x80000000 /* initiate sync */ #define IGC_TSYNCTXCTL_TXSYNSIG 0x00000020 /* Sample TX tstamp in PHY sop */ +/* Timer selection bits */ +#define IGC_AUX_IO_TIMER_SEL_SYSTIM0 (0u << 30) /* Select SYSTIM0 for auxiliary time stamp */ +#define IGC_AUX_IO_TIMER_SEL_SYSTIM1 (1u << 30) /* Select SYSTIM1 for auxiliary time stamp */ +#define IGC_AUX_IO_TIMER_SEL_SYSTIM2 (2u << 30) /* Select SYSTIM2 for auxiliary time stamp */ +#define IGC_AUX_IO_TIMER_SEL_SYSTIM3 (3u << 30) /* Select SYSTIM3 for auxiliary time stamp */ +#define IGC_TT_IO_TIMER_SEL_SYSTIM0 (0u << 30) /* Select SYSTIM0 for target time stamp */ +#define IGC_TT_IO_TIMER_SEL_SYSTIM1 (1u << 30) /* Select SYSTIM1 for target time stamp */ +#define IGC_TT_IO_TIMER_SEL_SYSTIM2 (2u << 30) /* Select SYSTIM2 for target time stamp */ +#define IGC_TT_IO_TIMER_SEL_SYSTIM3 (3u << 30) /* Select SYSTIM3 for target time stamp */ + +/* TSAUXC Configuration Bits */ +#define IGC_TSAUXC_EN_TT0 BIT(0) /* Enable target time 0. */ +#define IGC_TSAUXC_EN_TT1 BIT(1) /* Enable target time 1. */ +#define IGC_TSAUXC_EN_CLK0 BIT(2) /* Enable Configurable Frequency Clock 0. */ +#define IGC_TSAUXC_EN_CLK1 BIT(5) /* Enable Configurable Frequency Clock 1. */ +#define IGC_TSAUXC_EN_TS0 BIT(8) /* Enable hardware timestamp 0. */ +#define IGC_TSAUXC_AUTT0 BIT(9) /* Auxiliary Timestamp Taken. */ +#define IGC_TSAUXC_EN_TS1 BIT(10) /* Enable hardware timestamp 0. */ +#define IGC_TSAUXC_AUTT1 BIT(11) /* Auxiliary Timestamp Taken. */ +#define IGC_TSAUXC_PLSG BIT(17) /* Generate a pulse. */ +#define IGC_TSAUXC_DISABLE1 BIT(27) /* Disable SYSTIM0 Count Operation. */ +#define IGC_TSAUXC_DISABLE2 BIT(28) /* Disable SYSTIM1 Count Operation. */ +#define IGC_TSAUXC_DISABLE3 BIT(29) /* Disable SYSTIM2 Count Operation. */ +#define IGC_TSAUXC_DIS_TS_CLEAR BIT(30) /* Disable EN_TT0/1 auto clear. */ +#define IGC_TSAUXC_DISABLE0 BIT(31) /* Disable SYSTIM0 Count Operation. */ + +/* SDP Configuration Bits */ +#define IGC_AUX0_SEL_SDP0 (0u << 0) /* Assign SDP0 to auxiliary time stamp 0. */ +#define IGC_AUX0_SEL_SDP1 (1u << 0) /* Assign SDP1 to auxiliary time stamp 0. */ +#define IGC_AUX0_SEL_SDP2 (2u << 0) /* Assign SDP2 to auxiliary time stamp 0. */ +#define IGC_AUX0_SEL_SDP3 (3u << 0) /* Assign SDP3 to auxiliary time stamp 0. */ +#define IGC_AUX0_TS_SDP_EN (1u << 2) /* Enable auxiliary time stamp trigger 0. */ +#define IGC_AUX1_SEL_SDP0 (0u << 3) /* Assign SDP0 to auxiliary time stamp 1. */ +#define IGC_AUX1_SEL_SDP1 (1u << 3) /* Assign SDP1 to auxiliary time stamp 1. */ +#define IGC_AUX1_SEL_SDP2 (2u << 3) /* Assign SDP2 to auxiliary time stamp 1. */ +#define IGC_AUX1_SEL_SDP3 (3u << 3) /* Assign SDP3 to auxiliary time stamp 1. */ +#define IGC_AUX1_TS_SDP_EN (1u << 5) /* Enable auxiliary time stamp trigger 1. */ +#define IGC_TS_SDP0_SEL_TT0 (0u << 6) /* Target time 0 is output on SDP0. */ +#define IGC_TS_SDP0_SEL_TT1 (1u << 6) /* Target time 1 is output on SDP0. */ +#define IGC_TS_SDP0_SEL_FC0 (2u << 6) /* Freq clock 0 is output on SDP0. */ +#define IGC_TS_SDP0_SEL_FC1 (3u << 6) /* Freq clock 1 is output on SDP0. */ +#define IGC_TS_SDP0_EN (1u << 8) /* SDP0 is assigned to Tsync. */ +#define IGC_TS_SDP1_SEL_TT0 (0u << 9) /* Target time 0 is output on SDP1. */ +#define IGC_TS_SDP1_SEL_TT1 (1u << 9) /* Target time 1 is output on SDP1. */ +#define IGC_TS_SDP1_SEL_FC0 (2u << 9) /* Freq clock 0 is output on SDP1. */ +#define IGC_TS_SDP1_SEL_FC1 (3u << 9) /* Freq clock 1 is output on SDP1. */ +#define IGC_TS_SDP1_EN (1u << 11) /* SDP1 is assigned to Tsync. */ +#define IGC_TS_SDP2_SEL_TT0 (0u << 12) /* Target time 0 is output on SDP2. */ +#define IGC_TS_SDP2_SEL_TT1 (1u << 12) /* Target time 1 is output on SDP2. */ +#define IGC_TS_SDP2_SEL_FC0 (2u << 12) /* Freq clock 0 is output on SDP2. */ +#define IGC_TS_SDP2_SEL_FC1 (3u << 12) /* Freq clock 1 is output on SDP2. */ +#define IGC_TS_SDP2_EN (1u << 14) /* SDP2 is assigned to Tsync. */ +#define IGC_TS_SDP3_SEL_TT0 (0u << 15) /* Target time 0 is output on SDP3. */ +#define IGC_TS_SDP3_SEL_TT1 (1u << 15) /* Target time 1 is output on SDP3. */ +#define IGC_TS_SDP3_SEL_FC0 (2u << 15) /* Freq clock 0 is output on SDP3. */ +#define IGC_TS_SDP3_SEL_FC1 (3u << 15) /* Freq clock 1 is output on SDP3. */ +#define IGC_TS_SDP3_EN (1u << 17) /* SDP3 is assigned to Tsync. */ + /* Transmit Scheduling */ #define IGC_TQAVCTRL_TRANSMIT_MODE_TSN 0x00000001 #define IGC_TQAVCTRL_ENHANCED_QAV 0x00000008 @@ -441,11 +504,6 @@ #define MII_CR_RESTART_AUTO_NEG 0x0200 /* Restart auto negotiation */ #define MII_CR_POWER_DOWN 0x0800 /* Power down */ #define MII_CR_AUTO_NEG_EN 0x1000 /* Auto Neg Enable */ -#define MII_CR_LOOPBACK 0x4000 /* 0 = normal, 1 = loopback */ -#define MII_CR_RESET 0x8000 /* 0 = normal, 1 = PHY reset */ -#define MII_CR_SPEED_1000 0x0040 -#define MII_CR_SPEED_100 0x2000 -#define MII_CR_SPEED_10 0x0000 /* PHY Status Register */ #define MII_SR_LINK_STATUS 0x0004 /* Link Status 1 = link */ diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index 8722294ab90c..9722449d7633 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -65,6 +65,8 @@ static const struct igc_stats igc_gstrings_stats[] = { IGC_STAT("tx_hwtstamp_timeouts", tx_hwtstamp_timeouts), IGC_STAT("tx_hwtstamp_skipped", tx_hwtstamp_skipped), IGC_STAT("rx_hwtstamp_cleared", rx_hwtstamp_cleared), + IGC_STAT("tx_lpi_counter", stats.tlpic), + IGC_STAT("rx_lpi_counter", stats.rlpic), }; #define IGC_NETDEV_STAT(_net_stat) { \ diff --git a/drivers/net/ethernet/intel/igc/igc_i225.c b/drivers/net/ethernet/intel/igc/igc_i225.c index 7ec04e48860c..b2ef9fde97b3 100644 --- a/drivers/net/ethernet/intel/igc/igc_i225.c +++ b/drivers/net/ethernet/intel/igc/igc_i225.c @@ -6,7 +6,7 @@ #include "igc_hw.h" /** - * igc_get_hw_semaphore_i225 - Acquire hardware semaphore + * igc_acquire_nvm_i225 - Acquire exclusive access to EEPROM * @hw: pointer to the HW structure * * Acquire the necessary semaphores for exclusive access to the EEPROM. @@ -229,10 +229,11 @@ static s32 igc_write_nvm_srwr(struct igc_hw *hw, u16 offset, u16 words, if (offset >= nvm->word_size || (words > (nvm->word_size - offset)) || words == 0) { hw_dbg("nvm parameter(s) out of bounds\n"); - goto out; + return ret_val; } for (i = 0; i < words; i++) { + ret_val = -IGC_ERR_NVM; eewr = ((offset + i) << IGC_NVM_RW_ADDR_SHIFT) | (data[i] << IGC_NVM_RW_REG_DATA) | IGC_NVM_RW_REG_START; @@ -254,7 +255,6 @@ static s32 igc_write_nvm_srwr(struct igc_hw *hw, u16 offset, u16 words, } } -out: return ret_val; } diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 4d989ebc9713..069471b7ffb0 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -10,17 +10,24 @@ #include <linux/ip.h> #include <linux/pm_runtime.h> #include <net/pkt_sched.h> +#include <linux/bpf_trace.h> #include <net/ipv6.h> #include "igc.h" #include "igc_hw.h" #include "igc_tsn.h" +#include "igc_xdp.h" #define DRV_SUMMARY "Intel(R) 2.5G Ethernet Linux Driver" #define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK) +#define IGC_XDP_PASS 0 +#define IGC_XDP_CONSUMED BIT(0) +#define IGC_XDP_TX BIT(1) +#define IGC_XDP_REDIRECT BIT(2) + static int debug = -1; MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); @@ -176,8 +183,10 @@ static void igc_clean_tx_ring(struct igc_ring *tx_ring) while (i != tx_ring->next_to_use) { union igc_adv_tx_desc *eop_desc, *tx_desc; - /* Free all the Tx ring sk_buffs */ - dev_kfree_skb_any(tx_buffer->skb); + if (tx_buffer->tx_flags & IGC_TX_FLAGS_XDP) + xdp_return_frame(tx_buffer->xdpf); + else + dev_kfree_skb_any(tx_buffer->skb); /* unmap skb header data */ dma_unmap_single(tx_ring->dev, @@ -375,6 +384,8 @@ static void igc_clean_rx_ring(struct igc_ring *rx_ring) i = 0; } + clear_ring_uses_large_buffer(rx_ring); + rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; @@ -403,6 +414,8 @@ void igc_free_rx_resources(struct igc_ring *rx_ring) { igc_clean_rx_ring(rx_ring); + igc_xdp_unregister_rxq_info(rx_ring); + vfree(rx_ring->rx_buffer_info); rx_ring->rx_buffer_info = NULL; @@ -440,7 +453,11 @@ int igc_setup_rx_resources(struct igc_ring *rx_ring) { struct net_device *ndev = rx_ring->netdev; struct device *dev = rx_ring->dev; - int size, desc_len; + int size, desc_len, res; + + res = igc_xdp_register_rxq_info(rx_ring); + if (res < 0) + return res; size = sizeof(struct igc_rx_buffer) * rx_ring->count; rx_ring->rx_buffer_info = vzalloc(size); @@ -466,6 +483,7 @@ int igc_setup_rx_resources(struct igc_ring *rx_ring) return 0; err: + igc_xdp_unregister_rxq_info(rx_ring); vfree(rx_ring->rx_buffer_info); rx_ring->rx_buffer_info = NULL; netdev_err(ndev, "Unable to allocate memory for Rx descriptor ring\n"); @@ -497,6 +515,11 @@ static int igc_setup_all_rx_resources(struct igc_adapter *adapter) return err; } +static bool igc_xdp_is_enabled(struct igc_adapter *adapter) +{ + return !!adapter->xdp_prog; +} + /** * igc_configure_rx_ring - Configure a receive ring after Reset * @adapter: board private structure @@ -513,6 +536,9 @@ static void igc_configure_rx_ring(struct igc_adapter *adapter, u32 srrctl = 0, rxdctl = 0; u64 rdba = ring->dma; + if (igc_xdp_is_enabled(adapter)) + set_ring_uses_large_buffer(ring); + /* disable the queue */ wr32(IGC_RXDCTL(reg_idx), 0); @@ -941,7 +967,7 @@ static void igc_tx_ctxtdesc(struct igc_ring *tx_ring, struct igc_adapter *adapter = netdev_priv(tx_ring->netdev); ktime_t txtime = first->skb->tstamp; - first->skb->tstamp = ktime_set(0, 0); + skb_txtime_consumed(first->skb); context_desc->launch_time = igc_tx_launchtime(adapter, txtime); } else { @@ -1029,7 +1055,7 @@ static inline int igc_maybe_stop_tx(struct igc_ring *tx_ring, const u16 size) ((u32)((_input) & (_flag)) * ((_result) / (_flag))) : \ ((u32)((_input) & (_flag)) / ((_flag) / (_result)))) -static u32 igc_tx_cmd_type(struct sk_buff *skb, u32 tx_flags) +static u32 igc_tx_cmd_type(u32 tx_flags) { /* set type for advanced descriptor with frame checksum insertion */ u32 cmd_type = IGC_ADVTXD_DTYP_DATA | @@ -1078,7 +1104,7 @@ static int igc_tx_map(struct igc_ring *tx_ring, u16 i = tx_ring->next_to_use; unsigned int data_len, size; dma_addr_t dma; - u32 cmd_type = igc_tx_cmd_type(skb, tx_flags); + u32 cmd_type = igc_tx_cmd_type(tx_flags); tx_desc = IGC_TX_DESC(tx_ring, i); @@ -1480,11 +1506,18 @@ static void igc_process_skb_fields(struct igc_ring *rx_ring, } static struct igc_rx_buffer *igc_get_rx_buffer(struct igc_ring *rx_ring, - const unsigned int size) + const unsigned int size, + int *rx_buffer_pgcnt) { struct igc_rx_buffer *rx_buffer; rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + *rx_buffer_pgcnt = +#if (PAGE_SIZE < 8192) + page_count(rx_buffer->page); +#else + 0; +#endif prefetchw(rx_buffer->page); /* we are reusing so sync this buffer for CPU use */ @@ -1499,6 +1532,32 @@ static struct igc_rx_buffer *igc_get_rx_buffer(struct igc_ring *rx_ring, return rx_buffer; } +static void igc_rx_buffer_flip(struct igc_rx_buffer *buffer, + unsigned int truesize) +{ +#if (PAGE_SIZE < 8192) + buffer->page_offset ^= truesize; +#else + buffer->page_offset += truesize; +#endif +} + +static unsigned int igc_get_rx_frame_truesize(struct igc_ring *ring, + unsigned int size) +{ + unsigned int truesize; + +#if (PAGE_SIZE < 8192) + truesize = igc_rx_pg_size(ring) / 2; +#else + truesize = ring_uses_build_skb(ring) ? + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) + + SKB_DATA_ALIGN(IGC_SKB_PAD + size) : + SKB_DATA_ALIGN(size); +#endif + return truesize; +} + /** * igc_add_rx_frag - Add contents of Rx buffer to sk_buff * @rx_ring: rx descriptor ring to transact packets on @@ -1513,20 +1572,19 @@ static void igc_add_rx_frag(struct igc_ring *rx_ring, struct sk_buff *skb, unsigned int size) { -#if (PAGE_SIZE < 8192) - unsigned int truesize = igc_rx_pg_size(rx_ring) / 2; + unsigned int truesize; - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page, - rx_buffer->page_offset, size, truesize); - rx_buffer->page_offset ^= truesize; +#if (PAGE_SIZE < 8192) + truesize = igc_rx_pg_size(rx_ring) / 2; #else - unsigned int truesize = ring_uses_build_skb(rx_ring) ? - SKB_DATA_ALIGN(IGC_SKB_PAD + size) : - SKB_DATA_ALIGN(size); + truesize = ring_uses_build_skb(rx_ring) ? + SKB_DATA_ALIGN(IGC_SKB_PAD + size) : + SKB_DATA_ALIGN(size); +#endif skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page, rx_buffer->page_offset, size, truesize); - rx_buffer->page_offset += truesize; -#endif + + igc_rx_buffer_flip(rx_buffer, truesize); } static struct sk_buff *igc_build_skb(struct igc_ring *rx_ring, @@ -1535,12 +1593,7 @@ static struct sk_buff *igc_build_skb(struct igc_ring *rx_ring, unsigned int size) { void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; -#if (PAGE_SIZE < 8192) - unsigned int truesize = igc_rx_pg_size(rx_ring) / 2; -#else - unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) + - SKB_DATA_ALIGN(IGC_SKB_PAD + size); -#endif + unsigned int truesize = igc_get_rx_frame_truesize(rx_ring, size); struct sk_buff *skb; /* prefetch first cache line of first page */ @@ -1555,27 +1608,18 @@ static struct sk_buff *igc_build_skb(struct igc_ring *rx_ring, skb_reserve(skb, IGC_SKB_PAD); __skb_put(skb, size); - /* update buffer offset */ -#if (PAGE_SIZE < 8192) - rx_buffer->page_offset ^= truesize; -#else - rx_buffer->page_offset += truesize; -#endif - + igc_rx_buffer_flip(rx_buffer, truesize); return skb; } static struct sk_buff *igc_construct_skb(struct igc_ring *rx_ring, struct igc_rx_buffer *rx_buffer, - union igc_adv_rx_desc *rx_desc, - unsigned int size) + struct xdp_buff *xdp, + ktime_t timestamp) { - void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; -#if (PAGE_SIZE < 8192) - unsigned int truesize = igc_rx_pg_size(rx_ring) / 2; -#else - unsigned int truesize = SKB_DATA_ALIGN(size); -#endif + unsigned int size = xdp->data_end - xdp->data; + unsigned int truesize = igc_get_rx_frame_truesize(rx_ring, size); + void *va = xdp->data; unsigned int headlen; struct sk_buff *skb; @@ -1587,11 +1631,8 @@ static struct sk_buff *igc_construct_skb(struct igc_ring *rx_ring, if (unlikely(!skb)) return NULL; - if (unlikely(igc_test_staterr(rx_desc, IGC_RXDADV_STAT_TSIP))) { - igc_ptp_rx_pktstamp(rx_ring->q_vector, va, skb); - va += IGC_TS_HDR_LEN; - size -= IGC_TS_HDR_LEN; - } + if (timestamp) + skb_hwtstamps(skb)->hwtstamp = timestamp; /* Determine available headroom for copy */ headlen = size; @@ -1607,11 +1648,7 @@ static struct sk_buff *igc_construct_skb(struct igc_ring *rx_ring, skb_add_rx_frag(skb, 0, rx_buffer->page, (va + headlen) - page_address(rx_buffer->page), size, truesize); -#if (PAGE_SIZE < 8192) - rx_buffer->page_offset ^= truesize; -#else - rx_buffer->page_offset += truesize; -#endif + igc_rx_buffer_flip(rx_buffer, truesize); } else { rx_buffer->pagecnt_bias++; } @@ -1648,7 +1685,8 @@ static void igc_reuse_rx_page(struct igc_ring *rx_ring, new_buff->pagecnt_bias = old_buff->pagecnt_bias; } -static bool igc_can_reuse_rx_page(struct igc_rx_buffer *rx_buffer) +static bool igc_can_reuse_rx_page(struct igc_rx_buffer *rx_buffer, + int rx_buffer_pgcnt) { unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; struct page *page = rx_buffer->page; @@ -1659,7 +1697,7 @@ static bool igc_can_reuse_rx_page(struct igc_rx_buffer *rx_buffer) #if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ - if (unlikely((page_ref_count(page) - pagecnt_bias) > 1)) + if (unlikely((rx_buffer_pgcnt - pagecnt_bias) > 1)) return false; #else #define IGC_LAST_OFFSET \ @@ -1673,8 +1711,8 @@ static bool igc_can_reuse_rx_page(struct igc_rx_buffer *rx_buffer) * the pagecnt_bias and page count so that we fully restock the * number of references the driver holds. */ - if (unlikely(!pagecnt_bias)) { - page_ref_add(page, USHRT_MAX); + if (unlikely(pagecnt_bias == 1)) { + page_ref_add(page, USHRT_MAX - 1); rx_buffer->pagecnt_bias = USHRT_MAX; } @@ -1726,6 +1764,10 @@ static bool igc_cleanup_headers(struct igc_ring *rx_ring, union igc_adv_rx_desc *rx_desc, struct sk_buff *skb) { + /* XDP packets use error pointer so abort at this point */ + if (IS_ERR(skb)) + return true; + if (unlikely(igc_test_staterr(rx_desc, IGC_RXDEXT_STATERR_RXE))) { struct net_device *netdev = rx_ring->netdev; @@ -1743,9 +1785,10 @@ static bool igc_cleanup_headers(struct igc_ring *rx_ring, } static void igc_put_rx_buffer(struct igc_ring *rx_ring, - struct igc_rx_buffer *rx_buffer) + struct igc_rx_buffer *rx_buffer, + int rx_buffer_pgcnt) { - if (igc_can_reuse_rx_page(rx_buffer)) { + if (igc_can_reuse_rx_page(rx_buffer, rx_buffer_pgcnt)) { /* hand second half of page back to the ring */ igc_reuse_rx_page(rx_ring, rx_buffer); } else { @@ -1765,7 +1808,14 @@ static void igc_put_rx_buffer(struct igc_ring *rx_ring, static inline unsigned int igc_rx_offset(struct igc_ring *rx_ring) { - return ring_uses_build_skb(rx_ring) ? IGC_SKB_PAD : 0; + struct igc_adapter *adapter = rx_ring->q_vector->adapter; + + if (ring_uses_build_skb(rx_ring)) + return IGC_SKB_PAD; + if (igc_xdp_is_enabled(adapter)) + return XDP_PACKET_HEADROOM; + + return 0; } static bool igc_alloc_mapped_page(struct igc_ring *rx_ring, @@ -1804,7 +1854,8 @@ static bool igc_alloc_mapped_page(struct igc_ring *rx_ring, bi->dma = dma; bi->page = page; bi->page_offset = igc_rx_offset(rx_ring); - bi->pagecnt_bias = 1; + page_ref_add(page, USHRT_MAX - 1); + bi->pagecnt_bias = USHRT_MAX; return true; } @@ -1879,17 +1930,196 @@ static void igc_alloc_rx_buffers(struct igc_ring *rx_ring, u16 cleaned_count) } } +static int igc_xdp_init_tx_buffer(struct igc_tx_buffer *buffer, + struct xdp_frame *xdpf, + struct igc_ring *ring) +{ + dma_addr_t dma; + + dma = dma_map_single(ring->dev, xdpf->data, xdpf->len, DMA_TO_DEVICE); + if (dma_mapping_error(ring->dev, dma)) { + netdev_err_once(ring->netdev, "Failed to map DMA for TX\n"); + return -ENOMEM; + } + + buffer->xdpf = xdpf; + buffer->tx_flags = IGC_TX_FLAGS_XDP; + buffer->protocol = 0; + buffer->bytecount = xdpf->len; + buffer->gso_segs = 1; + buffer->time_stamp = jiffies; + dma_unmap_len_set(buffer, len, xdpf->len); + dma_unmap_addr_set(buffer, dma, dma); + return 0; +} + +/* This function requires __netif_tx_lock is held by the caller. */ +static int igc_xdp_init_tx_descriptor(struct igc_ring *ring, + struct xdp_frame *xdpf) +{ + struct igc_tx_buffer *buffer; + union igc_adv_tx_desc *desc; + u32 cmd_type, olinfo_status; + int err; + + if (!igc_desc_unused(ring)) + return -EBUSY; + + buffer = &ring->tx_buffer_info[ring->next_to_use]; + err = igc_xdp_init_tx_buffer(buffer, xdpf, ring); + if (err) + return err; + + cmd_type = IGC_ADVTXD_DTYP_DATA | IGC_ADVTXD_DCMD_DEXT | + IGC_ADVTXD_DCMD_IFCS | IGC_TXD_DCMD | + buffer->bytecount; + olinfo_status = buffer->bytecount << IGC_ADVTXD_PAYLEN_SHIFT; + + desc = IGC_TX_DESC(ring, ring->next_to_use); + desc->read.cmd_type_len = cpu_to_le32(cmd_type); + desc->read.olinfo_status = cpu_to_le32(olinfo_status); + desc->read.buffer_addr = cpu_to_le64(dma_unmap_addr(buffer, dma)); + + netdev_tx_sent_queue(txring_txq(ring), buffer->bytecount); + + buffer->next_to_watch = desc; + + ring->next_to_use++; + if (ring->next_to_use == ring->count) + ring->next_to_use = 0; + + return 0; +} + +static struct igc_ring *igc_xdp_get_tx_ring(struct igc_adapter *adapter, + int cpu) +{ + int index = cpu; + + if (unlikely(index < 0)) + index = 0; + + while (index >= adapter->num_tx_queues) + index -= adapter->num_tx_queues; + + return adapter->tx_ring[index]; +} + +static int igc_xdp_xmit_back(struct igc_adapter *adapter, struct xdp_buff *xdp) +{ + struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp); + int cpu = smp_processor_id(); + struct netdev_queue *nq; + struct igc_ring *ring; + int res; + + if (unlikely(!xdpf)) + return -EFAULT; + + ring = igc_xdp_get_tx_ring(adapter, cpu); + nq = txring_txq(ring); + + __netif_tx_lock(nq, cpu); + res = igc_xdp_init_tx_descriptor(ring, xdpf); + __netif_tx_unlock(nq); + return res; +} + +static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter, + struct xdp_buff *xdp) +{ + struct bpf_prog *prog; + int res; + u32 act; + + rcu_read_lock(); + + prog = READ_ONCE(adapter->xdp_prog); + if (!prog) { + res = IGC_XDP_PASS; + goto unlock; + } + + act = bpf_prog_run_xdp(prog, xdp); + switch (act) { + case XDP_PASS: + res = IGC_XDP_PASS; + break; + case XDP_TX: + if (igc_xdp_xmit_back(adapter, xdp) < 0) + res = IGC_XDP_CONSUMED; + else + res = IGC_XDP_TX; + break; + case XDP_REDIRECT: + if (xdp_do_redirect(adapter->netdev, xdp, prog) < 0) + res = IGC_XDP_CONSUMED; + else + res = IGC_XDP_REDIRECT; + break; + default: + bpf_warn_invalid_xdp_action(act); + fallthrough; + case XDP_ABORTED: + trace_xdp_exception(adapter->netdev, prog, act); + fallthrough; + case XDP_DROP: + res = IGC_XDP_CONSUMED; + break; + } + +unlock: + rcu_read_unlock(); + return ERR_PTR(-res); +} + +/* This function assumes __netif_tx_lock is held by the caller. */ +static void igc_flush_tx_descriptors(struct igc_ring *ring) +{ + /* Once tail pointer is updated, hardware can fetch the descriptors + * any time so we issue a write membar here to ensure all memory + * writes are complete before the tail pointer is updated. + */ + wmb(); + writel(ring->next_to_use, ring->tail); +} + +static void igc_finalize_xdp(struct igc_adapter *adapter, int status) +{ + int cpu = smp_processor_id(); + struct netdev_queue *nq; + struct igc_ring *ring; + + if (status & IGC_XDP_TX) { + ring = igc_xdp_get_tx_ring(adapter, cpu); + nq = txring_txq(ring); + + __netif_tx_lock(nq, cpu); + igc_flush_tx_descriptors(ring); + __netif_tx_unlock(nq); + } + + if (status & IGC_XDP_REDIRECT) + xdp_do_flush(); +} + static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) { unsigned int total_bytes = 0, total_packets = 0; + struct igc_adapter *adapter = q_vector->adapter; struct igc_ring *rx_ring = q_vector->rx.ring; struct sk_buff *skb = rx_ring->skb; u16 cleaned_count = igc_desc_unused(rx_ring); + int xdp_status = 0, rx_buffer_pgcnt; while (likely(total_packets < budget)) { union igc_adv_rx_desc *rx_desc; struct igc_rx_buffer *rx_buffer; - unsigned int size; + unsigned int size, truesize; + ktime_t timestamp = 0; + struct xdp_buff xdp; + int pkt_offset = 0; + void *pktbuf; /* return some buffers to hardware, one at a time is too slow */ if (cleaned_count >= IGC_RX_BUFFER_WRITE) { @@ -1908,16 +2138,52 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) */ dma_rmb(); - rx_buffer = igc_get_rx_buffer(rx_ring, size); + rx_buffer = igc_get_rx_buffer(rx_ring, size, &rx_buffer_pgcnt); + truesize = igc_get_rx_frame_truesize(rx_ring, size); + + pktbuf = page_address(rx_buffer->page) + rx_buffer->page_offset; - /* retrieve a buffer from the ring */ - if (skb) + if (igc_test_staterr(rx_desc, IGC_RXDADV_STAT_TSIP)) { + timestamp = igc_ptp_rx_pktstamp(q_vector->adapter, + pktbuf); + pkt_offset = IGC_TS_HDR_LEN; + size -= IGC_TS_HDR_LEN; + } + + if (!skb) { + xdp.data = pktbuf + pkt_offset; + xdp.data_end = xdp.data + size; + xdp.data_hard_start = pktbuf - igc_rx_offset(rx_ring); + xdp_set_data_meta_invalid(&xdp); + xdp.frame_sz = truesize; + xdp.rxq = &rx_ring->xdp_rxq; + + skb = igc_xdp_run_prog(adapter, &xdp); + } + + if (IS_ERR(skb)) { + unsigned int xdp_res = -PTR_ERR(skb); + + switch (xdp_res) { + case IGC_XDP_CONSUMED: + rx_buffer->pagecnt_bias++; + break; + case IGC_XDP_TX: + case IGC_XDP_REDIRECT: + igc_rx_buffer_flip(rx_buffer, truesize); + xdp_status |= xdp_res; + break; + } + + total_packets++; + total_bytes += size; + } else if (skb) igc_add_rx_frag(rx_ring, rx_buffer, skb, size); else if (ring_uses_build_skb(rx_ring)) skb = igc_build_skb(rx_ring, rx_buffer, rx_desc, size); else - skb = igc_construct_skb(rx_ring, rx_buffer, - rx_desc, size); + skb = igc_construct_skb(rx_ring, rx_buffer, &xdp, + timestamp); /* exit if we failed to retrieve a buffer */ if (!skb) { @@ -1926,7 +2192,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) break; } - igc_put_rx_buffer(rx_ring, rx_buffer); + igc_put_rx_buffer(rx_ring, rx_buffer, rx_buffer_pgcnt); cleaned_count++; /* fetch next buffer in frame if non-eop */ @@ -1954,6 +2220,9 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) total_packets++; } + if (xdp_status) + igc_finalize_xdp(adapter, xdp_status); + /* place incomplete frames back on ring for completion */ rx_ring->skb = skb; @@ -2015,8 +2284,10 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget) total_bytes += tx_buffer->bytecount; total_packets += tx_buffer->gso_segs; - /* free the skb */ - napi_consume_skb(tx_buffer->skb, napi_budget); + if (tx_buffer->tx_flags & IGC_TX_FLAGS_XDP) + xdp_return_frame(tx_buffer->xdpf); + else + napi_consume_skb(tx_buffer->skb, napi_budget); /* unmap skb header data */ dma_unmap_single(tx_ring->dev, @@ -3580,7 +3851,7 @@ void igc_up(struct igc_adapter *adapter) netif_tx_start_all_queues(adapter->netdev); /* start the watchdog. */ - hw->mac.get_link_status = 1; + hw->mac.get_link_status = true; schedule_work(&adapter->watchdog_task); } @@ -3858,6 +4129,11 @@ static int igc_change_mtu(struct net_device *netdev, int new_mtu) int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; struct igc_adapter *adapter = netdev_priv(netdev); + if (igc_xdp_is_enabled(adapter) && new_mtu > ETH_DATA_LEN) { + netdev_dbg(netdev, "Jumbo frames not supported with XDP"); + return -EINVAL; + } + /* adjust max frame to be at least the size of a standard frame */ if (max_frame < (ETH_FRAME_LEN + ETH_FCS_LEN)) max_frame = ETH_FRAME_LEN + ETH_FCS_LEN; @@ -3974,9 +4250,20 @@ igc_features_check(struct sk_buff *skb, struct net_device *dev, static void igc_tsync_interrupt(struct igc_adapter *adapter) { + u32 ack, tsauxc, sec, nsec, tsicr; struct igc_hw *hw = &adapter->hw; - u32 tsicr = rd32(IGC_TSICR); - u32 ack = 0; + struct ptp_clock_event event; + struct timespec64 ts; + + tsicr = rd32(IGC_TSICR); + ack = 0; + + if (tsicr & IGC_TSICR_SYS_WRAP) { + event.type = PTP_CLOCK_PPS; + if (adapter->ptp_caps.pps) + ptp_clock_event(adapter->ptp_clock, &event); + ack |= IGC_TSICR_SYS_WRAP; + } if (tsicr & IGC_TSICR_TXTS) { /* retrieve hardware timestamp */ @@ -3984,6 +4271,54 @@ static void igc_tsync_interrupt(struct igc_adapter *adapter) ack |= IGC_TSICR_TXTS; } + if (tsicr & IGC_TSICR_TT0) { + spin_lock(&adapter->tmreg_lock); + ts = timespec64_add(adapter->perout[0].start, + adapter->perout[0].period); + wr32(IGC_TRGTTIML0, ts.tv_nsec | IGC_TT_IO_TIMER_SEL_SYSTIM0); + wr32(IGC_TRGTTIMH0, (u32)ts.tv_sec); + tsauxc = rd32(IGC_TSAUXC); + tsauxc |= IGC_TSAUXC_EN_TT0; + wr32(IGC_TSAUXC, tsauxc); + adapter->perout[0].start = ts; + spin_unlock(&adapter->tmreg_lock); + ack |= IGC_TSICR_TT0; + } + + if (tsicr & IGC_TSICR_TT1) { + spin_lock(&adapter->tmreg_lock); + ts = timespec64_add(adapter->perout[1].start, + adapter->perout[1].period); + wr32(IGC_TRGTTIML1, ts.tv_nsec | IGC_TT_IO_TIMER_SEL_SYSTIM0); + wr32(IGC_TRGTTIMH1, (u32)ts.tv_sec); + tsauxc = rd32(IGC_TSAUXC); + tsauxc |= IGC_TSAUXC_EN_TT1; + wr32(IGC_TSAUXC, tsauxc); + adapter->perout[1].start = ts; + spin_unlock(&adapter->tmreg_lock); + ack |= IGC_TSICR_TT1; + } + + if (tsicr & IGC_TSICR_AUTT0) { + nsec = rd32(IGC_AUXSTMPL0); + sec = rd32(IGC_AUXSTMPH0); + event.type = PTP_CLOCK_EXTTS; + event.index = 0; + event.timestamp = sec * NSEC_PER_SEC + nsec; + ptp_clock_event(adapter->ptp_clock, &event); + ack |= IGC_TSICR_AUTT0; + } + + if (tsicr & IGC_TSICR_AUTT1) { + nsec = rd32(IGC_AUXSTMPL1); + sec = rd32(IGC_AUXSTMPH1); + event.type = PTP_CLOCK_EXTTS; + event.index = 1; + event.timestamp = sec * NSEC_PER_SEC + nsec; + ptp_clock_event(adapter->ptp_clock, &event); + ack |= IGC_TSICR_AUTT1; + } + /* acknowledge the interrupts */ wr32(IGC_TSICR, ack); } @@ -4009,7 +4344,7 @@ static irqreturn_t igc_msix_other(int irq, void *data) } if (icr & IGC_ICR_LSC) { - hw->mac.get_link_status = 1; + hw->mac.get_link_status = true; /* guard against interrupt when we're going down */ if (!test_bit(__IGC_DOWN, &adapter->state)) mod_timer(&adapter->watchdog_timer, jiffies + 1); @@ -4387,7 +4722,7 @@ static irqreturn_t igc_intr_msi(int irq, void *data) } if (icr & (IGC_ICR_RXSEQ | IGC_ICR_LSC)) { - hw->mac.get_link_status = 1; + hw->mac.get_link_status = true; if (!test_bit(__IGC_DOWN, &adapter->state)) mod_timer(&adapter->watchdog_timer, jiffies + 1); } @@ -4429,7 +4764,7 @@ static irqreturn_t igc_intr(int irq, void *data) } if (icr & (IGC_ICR_RXSEQ | IGC_ICR_LSC)) { - hw->mac.get_link_status = 1; + hw->mac.get_link_status = true; /* guard against interrupt when we're going down */ if (!test_bit(__IGC_DOWN, &adapter->state)) mod_timer(&adapter->watchdog_timer, jiffies + 1); @@ -4583,7 +4918,7 @@ static int __igc_open(struct net_device *netdev, bool resuming) netif_tx_start_all_queues(netdev); /* start the watchdog. */ - hw->mac.get_link_status = 1; + hw->mac.get_link_status = true; schedule_work(&adapter->watchdog_task); return IGC_SUCCESS; @@ -4844,6 +5179,58 @@ static int igc_setup_tc(struct net_device *dev, enum tc_setup_type type, } } +static int igc_bpf(struct net_device *dev, struct netdev_bpf *bpf) +{ + struct igc_adapter *adapter = netdev_priv(dev); + + switch (bpf->command) { + case XDP_SETUP_PROG: + return igc_xdp_set_prog(adapter, bpf->prog, bpf->extack); + default: + return -EOPNOTSUPP; + } +} + +static int igc_xdp_xmit(struct net_device *dev, int num_frames, + struct xdp_frame **frames, u32 flags) +{ + struct igc_adapter *adapter = netdev_priv(dev); + int cpu = smp_processor_id(); + struct netdev_queue *nq; + struct igc_ring *ring; + int i, drops; + + if (unlikely(test_bit(__IGC_DOWN, &adapter->state))) + return -ENETDOWN; + + if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) + return -EINVAL; + + ring = igc_xdp_get_tx_ring(adapter, cpu); + nq = txring_txq(ring); + + __netif_tx_lock(nq, cpu); + + drops = 0; + for (i = 0; i < num_frames; i++) { + int err; + struct xdp_frame *xdpf = frames[i]; + + err = igc_xdp_init_tx_descriptor(ring, xdpf); + if (err) { + xdp_return_frame_rx_napi(xdpf); + drops++; + } + } + + if (flags & XDP_XMIT_FLUSH) + igc_flush_tx_descriptors(ring); + + __netif_tx_unlock(nq); + + return num_frames - drops; +} + static const struct net_device_ops igc_netdev_ops = { .ndo_open = igc_open, .ndo_stop = igc_close, @@ -4857,6 +5244,8 @@ static const struct net_device_ops igc_netdev_ops = { .ndo_features_check = igc_features_check, .ndo_do_ioctl = igc_ioctl, .ndo_setup_tc = igc_setup_tc, + .ndo_bpf = igc_bpf, + .ndo_xdp_xmit = igc_xdp_xmit, }; /* PCIe configuration access */ @@ -4924,7 +5313,7 @@ int igc_set_spd_dplx(struct igc_adapter *adapter, u32 spd, u8 dplx) { struct igc_mac_info *mac = &adapter->hw.mac; - mac->autoneg = 0; + mac->autoneg = false; /* Make sure dplx is at most 1 bit and lsb of speed is not set * for the switch() below to work @@ -4946,13 +5335,13 @@ int igc_set_spd_dplx(struct igc_adapter *adapter, u32 spd, u8 dplx) mac->forced_speed_duplex = ADVERTISE_100_FULL; break; case SPEED_1000 + DUPLEX_FULL: - mac->autoneg = 1; + mac->autoneg = true; adapter->hw.phy.autoneg_advertised = ADVERTISE_1000_FULL; break; case SPEED_1000 + DUPLEX_HALF: /* not supported */ goto err_inval; case SPEED_2500 + DUPLEX_FULL: - mac->autoneg = 1; + mac->autoneg = true; adapter->hw.phy.autoneg_advertised = ADVERTISE_2500_FULL; break; case SPEED_2500 + DUPLEX_HALF: /* not supported */ diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 545f4d0e67cf..69617d2c1be2 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -120,12 +120,289 @@ static int igc_ptp_settime_i225(struct ptp_clock_info *ptp, return 0; } +static void igc_pin_direction(int pin, int input, u32 *ctrl, u32 *ctrl_ext) +{ + u32 *ptr = pin < 2 ? ctrl : ctrl_ext; + static const u32 mask[IGC_N_SDP] = { + IGC_CTRL_SDP0_DIR, + IGC_CTRL_SDP1_DIR, + IGC_CTRL_EXT_SDP2_DIR, + IGC_CTRL_EXT_SDP3_DIR, + }; + + if (input) + *ptr &= ~mask[pin]; + else + *ptr |= mask[pin]; +} + +static void igc_pin_perout(struct igc_adapter *igc, int chan, int pin, int freq) +{ + static const u32 igc_aux0_sel_sdp[IGC_N_SDP] = { + IGC_AUX0_SEL_SDP0, IGC_AUX0_SEL_SDP1, IGC_AUX0_SEL_SDP2, IGC_AUX0_SEL_SDP3, + }; + static const u32 igc_aux1_sel_sdp[IGC_N_SDP] = { + IGC_AUX1_SEL_SDP0, IGC_AUX1_SEL_SDP1, IGC_AUX1_SEL_SDP2, IGC_AUX1_SEL_SDP3, + }; + static const u32 igc_ts_sdp_en[IGC_N_SDP] = { + IGC_TS_SDP0_EN, IGC_TS_SDP1_EN, IGC_TS_SDP2_EN, IGC_TS_SDP3_EN, + }; + static const u32 igc_ts_sdp_sel_tt0[IGC_N_SDP] = { + IGC_TS_SDP0_SEL_TT0, IGC_TS_SDP1_SEL_TT0, + IGC_TS_SDP2_SEL_TT0, IGC_TS_SDP3_SEL_TT0, + }; + static const u32 igc_ts_sdp_sel_tt1[IGC_N_SDP] = { + IGC_TS_SDP0_SEL_TT1, IGC_TS_SDP1_SEL_TT1, + IGC_TS_SDP2_SEL_TT1, IGC_TS_SDP3_SEL_TT1, + }; + static const u32 igc_ts_sdp_sel_fc0[IGC_N_SDP] = { + IGC_TS_SDP0_SEL_FC0, IGC_TS_SDP1_SEL_FC0, + IGC_TS_SDP2_SEL_FC0, IGC_TS_SDP3_SEL_FC0, + }; + static const u32 igc_ts_sdp_sel_fc1[IGC_N_SDP] = { + IGC_TS_SDP0_SEL_FC1, IGC_TS_SDP1_SEL_FC1, + IGC_TS_SDP2_SEL_FC1, IGC_TS_SDP3_SEL_FC1, + }; + static const u32 igc_ts_sdp_sel_clr[IGC_N_SDP] = { + IGC_TS_SDP0_SEL_FC1, IGC_TS_SDP1_SEL_FC1, + IGC_TS_SDP2_SEL_FC1, IGC_TS_SDP3_SEL_FC1, + }; + struct igc_hw *hw = &igc->hw; + u32 ctrl, ctrl_ext, tssdp = 0; + + ctrl = rd32(IGC_CTRL); + ctrl_ext = rd32(IGC_CTRL_EXT); + tssdp = rd32(IGC_TSSDP); + + igc_pin_direction(pin, 0, &ctrl, &ctrl_ext); + + /* Make sure this pin is not enabled as an input. */ + if ((tssdp & IGC_AUX0_SEL_SDP3) == igc_aux0_sel_sdp[pin]) + tssdp &= ~IGC_AUX0_TS_SDP_EN; + + if ((tssdp & IGC_AUX1_SEL_SDP3) == igc_aux1_sel_sdp[pin]) + tssdp &= ~IGC_AUX1_TS_SDP_EN; + + tssdp &= ~igc_ts_sdp_sel_clr[pin]; + if (freq) { + if (chan == 1) + tssdp |= igc_ts_sdp_sel_fc1[pin]; + else + tssdp |= igc_ts_sdp_sel_fc0[pin]; + } else { + if (chan == 1) + tssdp |= igc_ts_sdp_sel_tt1[pin]; + else + tssdp |= igc_ts_sdp_sel_tt0[pin]; + } + tssdp |= igc_ts_sdp_en[pin]; + + wr32(IGC_TSSDP, tssdp); + wr32(IGC_CTRL, ctrl); + wr32(IGC_CTRL_EXT, ctrl_ext); +} + +static void igc_pin_extts(struct igc_adapter *igc, int chan, int pin) +{ + static const u32 igc_aux0_sel_sdp[IGC_N_SDP] = { + IGC_AUX0_SEL_SDP0, IGC_AUX0_SEL_SDP1, IGC_AUX0_SEL_SDP2, IGC_AUX0_SEL_SDP3, + }; + static const u32 igc_aux1_sel_sdp[IGC_N_SDP] = { + IGC_AUX1_SEL_SDP0, IGC_AUX1_SEL_SDP1, IGC_AUX1_SEL_SDP2, IGC_AUX1_SEL_SDP3, + }; + static const u32 igc_ts_sdp_en[IGC_N_SDP] = { + IGC_TS_SDP0_EN, IGC_TS_SDP1_EN, IGC_TS_SDP2_EN, IGC_TS_SDP3_EN, + }; + struct igc_hw *hw = &igc->hw; + u32 ctrl, ctrl_ext, tssdp = 0; + + ctrl = rd32(IGC_CTRL); + ctrl_ext = rd32(IGC_CTRL_EXT); + tssdp = rd32(IGC_TSSDP); + + igc_pin_direction(pin, 1, &ctrl, &ctrl_ext); + + /* Make sure this pin is not enabled as an output. */ + tssdp &= ~igc_ts_sdp_en[pin]; + + if (chan == 1) { + tssdp &= ~IGC_AUX1_SEL_SDP3; + tssdp |= igc_aux1_sel_sdp[pin] | IGC_AUX1_TS_SDP_EN; + } else { + tssdp &= ~IGC_AUX0_SEL_SDP3; + tssdp |= igc_aux0_sel_sdp[pin] | IGC_AUX0_TS_SDP_EN; + } + + wr32(IGC_TSSDP, tssdp); + wr32(IGC_CTRL, ctrl); + wr32(IGC_CTRL_EXT, ctrl_ext); +} + static int igc_ptp_feature_enable_i225(struct ptp_clock_info *ptp, struct ptp_clock_request *rq, int on) { + struct igc_adapter *igc = + container_of(ptp, struct igc_adapter, ptp_caps); + struct igc_hw *hw = &igc->hw; + unsigned long flags; + struct timespec64 ts; + int use_freq = 0, pin = -1; + u32 tsim, tsauxc, tsauxc_mask, tsim_mask, trgttiml, trgttimh, freqout; + s64 ns; + + switch (rq->type) { + case PTP_CLK_REQ_EXTTS: + /* Reject requests with unsupported flags */ + if (rq->extts.flags & ~(PTP_ENABLE_FEATURE | + PTP_RISING_EDGE | + PTP_FALLING_EDGE | + PTP_STRICT_FLAGS)) + return -EOPNOTSUPP; + + /* Reject requests failing to enable both edges. */ + if ((rq->extts.flags & PTP_STRICT_FLAGS) && + (rq->extts.flags & PTP_ENABLE_FEATURE) && + (rq->extts.flags & PTP_EXTTS_EDGES) != PTP_EXTTS_EDGES) + return -EOPNOTSUPP; + + if (on) { + pin = ptp_find_pin(igc->ptp_clock, PTP_PF_EXTTS, + rq->extts.index); + if (pin < 0) + return -EBUSY; + } + if (rq->extts.index == 1) { + tsauxc_mask = IGC_TSAUXC_EN_TS1; + tsim_mask = IGC_TSICR_AUTT1; + } else { + tsauxc_mask = IGC_TSAUXC_EN_TS0; + tsim_mask = IGC_TSICR_AUTT0; + } + spin_lock_irqsave(&igc->tmreg_lock, flags); + tsauxc = rd32(IGC_TSAUXC); + tsim = rd32(IGC_TSIM); + if (on) { + igc_pin_extts(igc, rq->extts.index, pin); + tsauxc |= tsauxc_mask; + tsim |= tsim_mask; + } else { + tsauxc &= ~tsauxc_mask; + tsim &= ~tsim_mask; + } + wr32(IGC_TSAUXC, tsauxc); + wr32(IGC_TSIM, tsim); + spin_unlock_irqrestore(&igc->tmreg_lock, flags); + return 0; + + case PTP_CLK_REQ_PEROUT: + /* Reject requests with unsupported flags */ + if (rq->perout.flags) + return -EOPNOTSUPP; + + if (on) { + pin = ptp_find_pin(igc->ptp_clock, PTP_PF_PEROUT, + rq->perout.index); + if (pin < 0) + return -EBUSY; + } + ts.tv_sec = rq->perout.period.sec; + ts.tv_nsec = rq->perout.period.nsec; + ns = timespec64_to_ns(&ts); + ns = ns >> 1; + if (on && (ns <= 70000000LL || ns == 125000000LL || + ns == 250000000LL || ns == 500000000LL)) { + if (ns < 8LL) + return -EINVAL; + use_freq = 1; + } + ts = ns_to_timespec64(ns); + if (rq->perout.index == 1) { + if (use_freq) { + tsauxc_mask = IGC_TSAUXC_EN_CLK1; + tsim_mask = 0; + } else { + tsauxc_mask = IGC_TSAUXC_EN_TT1; + tsim_mask = IGC_TSICR_TT1; + } + trgttiml = IGC_TRGTTIML1; + trgttimh = IGC_TRGTTIMH1; + freqout = IGC_FREQOUT1; + } else { + if (use_freq) { + tsauxc_mask = IGC_TSAUXC_EN_CLK0; + tsim_mask = 0; + } else { + tsauxc_mask = IGC_TSAUXC_EN_TT0; + tsim_mask = IGC_TSICR_TT0; + } + trgttiml = IGC_TRGTTIML0; + trgttimh = IGC_TRGTTIMH0; + freqout = IGC_FREQOUT0; + } + spin_lock_irqsave(&igc->tmreg_lock, flags); + tsauxc = rd32(IGC_TSAUXC); + tsim = rd32(IGC_TSIM); + if (rq->perout.index == 1) { + tsauxc &= ~(IGC_TSAUXC_EN_TT1 | IGC_TSAUXC_EN_CLK1); + tsim &= ~IGC_TSICR_TT1; + } else { + tsauxc &= ~(IGC_TSAUXC_EN_TT0 | IGC_TSAUXC_EN_CLK0); + tsim &= ~IGC_TSICR_TT0; + } + if (on) { + int i = rq->perout.index; + + igc_pin_perout(igc, i, pin, use_freq); + igc->perout[i].start.tv_sec = rq->perout.start.sec; + igc->perout[i].start.tv_nsec = rq->perout.start.nsec; + igc->perout[i].period.tv_sec = ts.tv_sec; + igc->perout[i].period.tv_nsec = ts.tv_nsec; + wr32(trgttimh, rq->perout.start.sec); + /* For now, always select timer 0 as source. */ + wr32(trgttiml, rq->perout.start.nsec | IGC_TT_IO_TIMER_SEL_SYSTIM0); + if (use_freq) + wr32(freqout, ns); + tsauxc |= tsauxc_mask; + tsim |= tsim_mask; + } + wr32(IGC_TSAUXC, tsauxc); + wr32(IGC_TSIM, tsim); + spin_unlock_irqrestore(&igc->tmreg_lock, flags); + return 0; + + case PTP_CLK_REQ_PPS: + spin_lock_irqsave(&igc->tmreg_lock, flags); + tsim = rd32(IGC_TSIM); + if (on) + tsim |= IGC_TSICR_SYS_WRAP; + else + tsim &= ~IGC_TSICR_SYS_WRAP; + igc->pps_sys_wrap_on = on; + wr32(IGC_TSIM, tsim); + spin_unlock_irqrestore(&igc->tmreg_lock, flags); + return 0; + + default: + break; + } + return -EOPNOTSUPP; } +static int igc_ptp_verify_pin(struct ptp_clock_info *ptp, unsigned int pin, + enum ptp_pin_function func, unsigned int chan) +{ + switch (func) { + case PTP_PF_NONE: + case PTP_PF_EXTTS: + case PTP_PF_PEROUT: + break; + case PTP_PF_PHYSYNC: + return -1; + } + return 0; +} + /** * igc_ptp_systim_to_hwtstamp - convert system time value to HW timestamp * @adapter: board private structure @@ -153,20 +430,20 @@ static void igc_ptp_systim_to_hwtstamp(struct igc_adapter *adapter, /** * igc_ptp_rx_pktstamp - Retrieve timestamp from Rx packet buffer - * @q_vector: Pointer to interrupt specific structure - * @va: Pointer to address containing Rx buffer - * @skb: Buffer containing timestamp and packet + * @adapter: Pointer to adapter the packet buffer belongs to + * @buf: Pointer to packet buffer * * This function retrieves the timestamp saved in the beginning of packet * buffer. While two timestamps are available, one in timer0 reference and the * other in timer1 reference, this function considers only the timestamp in * timer0 reference. + * + * Returns timestamp value. */ -void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, __le32 *va, - struct sk_buff *skb) +ktime_t igc_ptp_rx_pktstamp(struct igc_adapter *adapter, __le32 *buf) { - struct igc_adapter *adapter = q_vector->adapter; - u64 regval; + ktime_t timestamp; + u32 secs, nsecs; int adjust; /* Timestamps are saved in little endian at the beginning of the packet @@ -178,9 +455,10 @@ void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, __le32 *va, * SYSTIML holds the nanoseconds part while SYSTIMH holds the seconds * part of the timestamp. */ - regval = le32_to_cpu(va[2]); - regval |= (u64)le32_to_cpu(va[3]) << 32; - igc_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), regval); + nsecs = le32_to_cpu(buf[2]); + secs = le32_to_cpu(buf[3]); + + timestamp = ktime_set(secs, nsecs); /* Adjust timestamp for the RX latency based on link speed */ switch (adapter->link_speed) { @@ -201,8 +479,8 @@ void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, __le32 *va, netdev_warn_once(adapter->netdev, "Imprecise timestamp\n"); break; } - skb_hwtstamps(skb)->hwtstamp = - ktime_sub_ns(skb_hwtstamps(skb)->hwtstamp, adjust); + + return ktime_sub_ns(timestamp, adjust); } static void igc_ptp_disable_rx_timestamp(struct igc_adapter *adapter) @@ -485,9 +763,17 @@ void igc_ptp_init(struct igc_adapter *adapter) { struct net_device *netdev = adapter->netdev; struct igc_hw *hw = &adapter->hw; + int i; switch (hw->mac.type) { case igc_i225: + for (i = 0; i < IGC_N_SDP; i++) { + struct ptp_pin_desc *ppd = &adapter->sdp_config[i]; + + snprintf(ppd->name, sizeof(ppd->name), "SDP%d", i); + ppd->index = i; + ppd->func = PTP_PF_NONE; + } snprintf(adapter->ptp_caps.name, 16, "%pm", netdev->dev_addr); adapter->ptp_caps.owner = THIS_MODULE; adapter->ptp_caps.max_adj = 62499999; @@ -496,6 +782,12 @@ void igc_ptp_init(struct igc_adapter *adapter) adapter->ptp_caps.gettimex64 = igc_ptp_gettimex64_i225; adapter->ptp_caps.settime64 = igc_ptp_settime_i225; adapter->ptp_caps.enable = igc_ptp_feature_enable_i225; + adapter->ptp_caps.pps = 1; + adapter->ptp_caps.pin_config = adapter->sdp_config; + adapter->ptp_caps.n_ext_ts = IGC_N_EXTTS; + adapter->ptp_caps.n_per_out = IGC_N_PEROUT; + adapter->ptp_caps.n_pins = IGC_N_SDP; + adapter->ptp_caps.verify = igc_ptp_verify_pin; break; default: adapter->ptp_clock = NULL; @@ -597,7 +889,9 @@ void igc_ptp_reset(struct igc_adapter *adapter) case igc_i225: wr32(IGC_TSAUXC, 0x0); wr32(IGC_TSSDP, 0x0); - wr32(IGC_TSIM, IGC_TSICR_INTERRUPTS); + wr32(IGC_TSIM, + IGC_TSICR_INTERRUPTS | + (adapter->pps_sys_wrap_on ? IGC_TSICR_SYS_WRAP : 0)); wr32(IGC_IMS, IGC_IMS_TS); break; default: diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h index 3e5cb7aef9da..cc174853554b 100644 --- a/drivers/net/ethernet/intel/igc/igc_regs.h +++ b/drivers/net/ethernet/intel/igc/igc_regs.h @@ -192,6 +192,16 @@ #define IGC_TSYNCTXCTL 0x0B614 /* Tx Time Sync Control register - RW */ #define IGC_TSYNCRXCFG 0x05F50 /* Time Sync Rx Configuration - RW */ #define IGC_TSSDP 0x0003C /* Time Sync SDP Configuration Register - RW */ +#define IGC_TRGTTIML0 0x0B644 /* Target Time Register 0 Low - RW */ +#define IGC_TRGTTIMH0 0x0B648 /* Target Time Register 0 High - RW */ +#define IGC_TRGTTIML1 0x0B64C /* Target Time Register 1 Low - RW */ +#define IGC_TRGTTIMH1 0x0B650 /* Target Time Register 1 High - RW */ +#define IGC_FREQOUT0 0x0B654 /* Frequency Out 0 Control Register - RW */ +#define IGC_FREQOUT1 0x0B658 /* Frequency Out 1 Control Register - RW */ +#define IGC_AUXSTMPL0 0x0B65C /* Auxiliary Time Stamp 0 Register Low - RO */ +#define IGC_AUXSTMPH0 0x0B660 /* Auxiliary Time Stamp 0 Register High - RO */ +#define IGC_AUXSTMPL1 0x0B664 /* Auxiliary Time Stamp 1 Register Low - RO */ +#define IGC_AUXSTMPH1 0x0B668 /* Auxiliary Time Stamp 1 Register High - RO */ #define IGC_IMIR(_i) (0x05A80 + ((_i) * 4)) /* Immediate Interrupt */ #define IGC_IMIREXT(_i) (0x05AA0 + ((_i) * 4)) /* Immediate INTR Ext*/ diff --git a/drivers/net/ethernet/intel/igc/igc_xdp.c b/drivers/net/ethernet/intel/igc/igc_xdp.c new file mode 100644 index 000000000000..11133c4619bb --- /dev/null +++ b/drivers/net/ethernet/intel/igc/igc_xdp.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020, Intel Corporation. */ + +#include "igc.h" +#include "igc_xdp.h" + +int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog, + struct netlink_ext_ack *extack) +{ + struct net_device *dev = adapter->netdev; + bool if_running = netif_running(dev); + struct bpf_prog *old_prog; + + if (dev->mtu > ETH_DATA_LEN) { + /* For now, the driver doesn't support XDP functionality with + * jumbo frames so we return error. + */ + NL_SET_ERR_MSG_MOD(extack, "Jumbo frames not supported"); + return -EOPNOTSUPP; + } + + if (if_running) + igc_close(dev); + + old_prog = xchg(&adapter->xdp_prog, prog); + if (old_prog) + bpf_prog_put(old_prog); + + if (if_running) + igc_open(dev); + + return 0; +} + +int igc_xdp_register_rxq_info(struct igc_ring *ring) +{ + struct net_device *dev = ring->netdev; + int err; + + err = xdp_rxq_info_reg(&ring->xdp_rxq, dev, ring->queue_index, 0); + if (err) { + netdev_err(dev, "Failed to register xdp rxq info\n"); + return err; + } + + err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_PAGE_SHARED, + NULL); + if (err) { + netdev_err(dev, "Failed to register xdp rxq mem model\n"); + xdp_rxq_info_unreg(&ring->xdp_rxq); + return err; + } + + return 0; +} + +void igc_xdp_unregister_rxq_info(struct igc_ring *ring) +{ + xdp_rxq_info_unreg(&ring->xdp_rxq); +} diff --git a/drivers/net/ethernet/intel/igc/igc_xdp.h b/drivers/net/ethernet/intel/igc/igc_xdp.h new file mode 100644 index 000000000000..cfecb515b718 --- /dev/null +++ b/drivers/net/ethernet/intel/igc/igc_xdp.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2020, Intel Corporation. */ + +#ifndef _IGC_XDP_H_ +#define _IGC_XDP_H_ + +int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog, + struct netlink_ext_ack *extack); + +int igc_xdp_register_rxq_info(struct igc_ring *ring); +void igc_xdp_unregister_rxq_info(struct igc_ring *ring); + +#endif /* _IGC_XDP_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c index 8d3798a32f0e..e324e42fab2d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c @@ -1351,7 +1351,7 @@ static u32 ixgbe_atr_compute_sig_hash_82599(union ixgbe_atr_hash_dword input, } /** - * ixgbe_atr_add_signature_filter_82599 - Adds a signature hash filter + * ixgbe_fdir_add_signature_filter_82599 - Adds a signature hash filter * @hw: pointer to hardware structure * @input: unique input dword * @common: compressed common input dword @@ -1542,6 +1542,7 @@ s32 ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw, switch (input_mask->formatted.vm_pool & 0x7F) { case 0x0: fdirm |= IXGBE_FDIRM_POOL; + break; case 0x7F: break; default: @@ -1557,6 +1558,7 @@ s32 ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw, hw_dbg(hw, " Error on src/dst port mask\n"); return IXGBE_ERR_CONFIG; } + break; case IXGBE_ATR_L4TYPE_MASK: break; default: diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 62ddb452f862..03ccbe6b66d2 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -93,6 +93,7 @@ bool ixgbe_device_supports_autoneg_fc(struct ixgbe_hw *hw) default: break; } + break; default: break; } @@ -2707,7 +2708,7 @@ s32 ixgbe_disable_rx_buff_generic(struct ixgbe_hw *hw) } /** - * ixgbe_enable_rx_buff - Enables the receive data path + * ixgbe_enable_rx_buff_generic - Enables the receive data path * @hw: pointer to hardware structure * * Enables the receive data path @@ -3029,14 +3030,14 @@ s32 ixgbe_set_vmdq_generic(struct ixgbe_hw *hw, u32 rar, u32 vmdq) } /** + * ixgbe_set_vmdq_san_mac_generic - Associate VMDq pool index with a rx address + * @hw: pointer to hardware struct + * @vmdq: VMDq pool index + * * This function should only be involved in the IOV mode. * In IOV mode, Default pool is next pool after the number of * VFs advertized and not 0. * MPSAR table needs to be updated for SAN_MAC RAR [hw->mac.san_mac_rar_index] - * - * ixgbe_set_vmdq_san_mac - Associate default VMDq pool index with a rx address - * @hw: pointer to hardware struct - * @vmdq: VMDq pool index **/ s32 ixgbe_set_vmdq_san_mac_generic(struct ixgbe_hw *hw, u32 vmdq) { @@ -3896,7 +3897,7 @@ static s32 ixgbe_get_ets_data(struct ixgbe_hw *hw, u16 *ets_cfg, } /** - * ixgbe_get_thermal_sensor_data - Gathers thermal sensor data + * ixgbe_get_thermal_sensor_data_generic - Gathers thermal sensor data * @hw: pointer to hardware structure * * Returns the thermal sensor data structure @@ -4054,8 +4055,7 @@ void ixgbe_get_orom_version(struct ixgbe_hw *hw, } /** - * ixgbe_get_oem_prod_version Etrack ID from EEPROM - * + * ixgbe_get_oem_prod_version - Etrack ID from EEPROM * @hw: pointer to hardware structure * @nvm_ver: pointer to output structure * diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c index c00332d2e02a..72e6ebffea33 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c @@ -361,7 +361,7 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev) } #ifdef IXGBE_FCOE - /* Reprogam FCoE hardware offloads when the traffic class + /* Reprogram FCoE hardware offloads when the traffic class * FCoE is using changes. This happens if the APP info * changes or the up2tc mapping is updated. */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index a280aa34ca1d..4ceaca0f6ce3 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -1368,45 +1368,33 @@ static void ixgbe_get_ethtool_stats(struct net_device *netdev, static void ixgbe_get_strings(struct net_device *netdev, u32 stringset, u8 *data) { - char *p = (char *)data; unsigned int i; + u8 *p = data; switch (stringset) { case ETH_SS_TEST: - for (i = 0; i < IXGBE_TEST_LEN; i++) { - memcpy(data, ixgbe_gstrings_test[i], ETH_GSTRING_LEN); - data += ETH_GSTRING_LEN; - } + for (i = 0; i < IXGBE_TEST_LEN; i++) + ethtool_sprintf(&p, ixgbe_gstrings_test[i]); break; case ETH_SS_STATS: - for (i = 0; i < IXGBE_GLOBAL_STATS_LEN; i++) { - memcpy(p, ixgbe_gstrings_stats[i].stat_string, - ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - } + for (i = 0; i < IXGBE_GLOBAL_STATS_LEN; i++) + ethtool_sprintf(&p, + ixgbe_gstrings_stats[i].stat_string); for (i = 0; i < netdev->num_tx_queues; i++) { - sprintf(p, "tx_queue_%u_packets", i); - p += ETH_GSTRING_LEN; - sprintf(p, "tx_queue_%u_bytes", i); - p += ETH_GSTRING_LEN; + ethtool_sprintf(&p, "tx_queue_%u_packets", i); + ethtool_sprintf(&p, "tx_queue_%u_bytes", i); } for (i = 0; i < IXGBE_NUM_RX_QUEUES; i++) { - sprintf(p, "rx_queue_%u_packets", i); - p += ETH_GSTRING_LEN; - sprintf(p, "rx_queue_%u_bytes", i); - p += ETH_GSTRING_LEN; + ethtool_sprintf(&p, "rx_queue_%u_packets", i); + ethtool_sprintf(&p, "rx_queue_%u_bytes", i); } for (i = 0; i < IXGBE_MAX_PACKET_BUFFERS; i++) { - sprintf(p, "tx_pb_%u_pxon", i); - p += ETH_GSTRING_LEN; - sprintf(p, "tx_pb_%u_pxoff", i); - p += ETH_GSTRING_LEN; + ethtool_sprintf(&p, "tx_pb_%u_pxon", i); + ethtool_sprintf(&p, "tx_pb_%u_pxoff", i); } for (i = 0; i < IXGBE_MAX_PACKET_BUFFERS; i++) { - sprintf(p, "rx_pb_%u_pxon", i); - p += ETH_GSTRING_LEN; - sprintf(p, "rx_pb_%u_pxoff", i); - p += ETH_GSTRING_LEN; + ethtool_sprintf(&p, "rx_pb_%u_pxon", i); + ethtool_sprintf(&p, "rx_pb_%u_pxoff", i); } /* BUG_ON(p - data != IXGBE_STATS_LEN * ETH_GSTRING_LEN); */ break; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c index df389a11d3af..0218f6c9b925 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -132,6 +132,7 @@ static void ixgbe_get_first_reg_idx(struct ixgbe_adapter *adapter, u8 tc, else *tx = (tc + 4) << 4; /* 96, 112 */ } + break; default: break; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index cffb95f8f632..c5ec17d19c59 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -225,7 +225,7 @@ static s32 ixgbe_get_parent_bus_info(struct ixgbe_adapter *adapter) } /** - * ixgbe_check_from_parent - Determine whether PCIe info should come from parent + * ixgbe_pcie_from_parent - Determine whether PCIe info should come from parent * @hw: hw specific details * * This function is used by probe to determine whether a device's PCI-Express @@ -6158,7 +6158,7 @@ void ixgbe_down(struct ixgbe_adapter *adapter) } /** - * ixgbe_eee_capable - helper function to determine EEE support on X550 + * ixgbe_set_eee_capable - helper function to determine EEE support on X550 * @adapter: board private structure */ static void ixgbe_set_eee_capable(struct ixgbe_adapter *adapter) @@ -10201,7 +10201,7 @@ static int ixgbe_xdp_xmit(struct net_device *dev, int n, { struct ixgbe_adapter *adapter = netdev_priv(dev); struct ixgbe_ring *ring; - int drops = 0; + int nxmit = 0; int i; if (unlikely(test_bit(__IXGBE_DOWN, &adapter->state))) @@ -10225,16 +10225,15 @@ static int ixgbe_xdp_xmit(struct net_device *dev, int n, int err; err = ixgbe_xmit_xdp_ring(adapter, xdpf); - if (err != IXGBE_XDP_TX) { - xdp_return_frame_rx_napi(xdpf); - drops++; - } + if (err != IXGBE_XDP_TX) + break; + nxmit++; } if (unlikely(flags & XDP_XMIT_FLUSH)) ixgbe_xdp_ring_update_tail(ring); - return n - drops; + return nxmit; } static const struct net_device_ops ixgbe_netdev_ops = { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c index fc389eecdd2b..24aa97f993ca 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c @@ -380,6 +380,9 @@ static enum ixgbe_phy_type ixgbe_get_phy_type_from_id(u32 phy_id) case X557_PHY_ID2: phy_type = ixgbe_phy_x550em_ext_t; break; + case BCM54616S_E_PHY_ID: + phy_type = ixgbe_phy_ext_1g_t; + break; default: phy_type = ixgbe_phy_unknown; break; @@ -461,12 +464,13 @@ s32 ixgbe_reset_phy_generic(struct ixgbe_hw *hw) } /** - * ixgbe_read_phy_mdi - Reads a value from a specified PHY register without - * the SWFW lock + * ixgbe_read_phy_reg_mdi - read PHY register * @hw: pointer to hardware structure * @reg_addr: 32 bit address of PHY register to read * @device_type: 5 bit device type * @phy_data: Pointer to read data from PHY register + * + * Reads a value from a specified PHY register without the SWFW lock **/ s32 ixgbe_read_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, u32 device_type, u16 *phy_data) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index 22a874eee2e8..23ddfd79fc8b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -999,6 +999,7 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter, switch (config->tx_type) { case HWTSTAMP_TX_OFF: tsync_tx_ctl = 0; + break; case HWTSTAMP_TX_ON: break; default: diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h index 2be1c4c72435..2647937f7f4d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h @@ -1407,6 +1407,7 @@ struct ixgbe_nvm_version { #define QT2022_PHY_ID 0x0043A400 #define ATH_PHY_ID 0x03429050 #define AQ_FW_REV 0x20 +#define BCM54616S_E_PHY_ID 0x03625D10 /* Special PHY Init Routine */ #define IXGBE_PHY_INIT_OFFSET_NL 0x002B @@ -3383,10 +3384,6 @@ struct ixgbe_hw_stats { /* forward declaration */ struct ixgbe_hw; -/* iterator type for walking multicast address lists */ -typedef u8* (*ixgbe_mc_addr_itr) (struct ixgbe_hw *hw, u8 **mc_addr_ptr, - u32 *vmdq); - /* Function pointer table */ struct ixgbe_eeprom_operations { s32 (*init_params)(struct ixgbe_hw *); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c index 4b93ba149ec5..d5cfb51ff648 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c @@ -701,7 +701,7 @@ static s32 ixgbe_get_swfw_sync_semaphore(struct ixgbe_hw *hw) } /** - * ixgbe_release_nvm_semaphore - Release hardware semaphore + * ixgbe_release_swfw_sync_semaphore - Release hardware semaphore * @hw: pointer to hardware structure * * This function clears hardware semaphore bits. diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index 5e339afa682a..9724ffb16518 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -1248,7 +1248,7 @@ static s32 ixgbe_get_bus_info_X550em(struct ixgbe_hw *hw) } /** - * ixgbe_fw_recovery_mode - Check FW NVM recovery mode + * ixgbe_fw_recovery_mode_X550 - Check FW NVM recovery mode * @hw: pointer t hardware structure * * Returns true if in FW NVM recovery mode. diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index 3771857cf887..91ad5b902673 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -104,6 +104,13 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter, xdp_prog = READ_ONCE(rx_ring->xdp_prog); act = bpf_prog_run_xdp(xdp_prog, xdp); + if (likely(act == XDP_REDIRECT)) { + err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); + result = !err ? IXGBE_XDP_REDIR : IXGBE_XDP_CONSUMED; + rcu_read_unlock(); + return result; + } + switch (act) { case XDP_PASS: break; @@ -115,10 +122,6 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter, } result = ixgbe_xmit_xdp_ring(adapter, xdpf); break; - case XDP_REDIRECT: - err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); - result = !err ? IXGBE_XDP_REDIR : IXGBE_XDP_CONSUMED; - break; default: bpf_warn_invalid_xdp_action(act); fallthrough; diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 449d7d5b280d..ba2ed8a43d2d 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -2633,6 +2633,7 @@ static void ixgbevf_set_num_queues(struct ixgbevf_adapter *adapter) adapter->num_rx_queues = rss; adapter->num_tx_queues = rss; adapter->num_xdp_queues = adapter->xdp_prog ? rss : 0; + break; default: break; } diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c index bfe6dfcec4ab..5fc347abab3c 100644 --- a/drivers/net/ethernet/intel/ixgbevf/vf.c +++ b/drivers/net/ethernet/intel/ixgbevf/vf.c @@ -121,9 +121,11 @@ static s32 ixgbevf_reset_hw_vf(struct ixgbe_hw *hw) } /** + * ixgbevf_hv_reset_hw_vf - reset via Hyper-V + * @hw: pointer to private hardware struct + * * Hyper-V variant; the VF/PF communication is through the PCI * config space. - * @hw: pointer to private hardware struct */ static s32 ixgbevf_hv_reset_hw_vf(struct ixgbe_hw *hw) { @@ -513,9 +515,11 @@ static s32 ixgbevf_update_mc_addr_list_vf(struct ixgbe_hw *hw, } /** - * Hyper-V variant - just a stub. + * ixgbevf_hv_update_mc_addr_list_vf - stub * @hw: unused * @netdev: unused + * + * Hyper-V variant - just a stub. */ static s32 ixgbevf_hv_update_mc_addr_list_vf(struct ixgbe_hw *hw, struct net_device *netdev) @@ -564,9 +568,11 @@ static s32 ixgbevf_update_xcast_mode(struct ixgbe_hw *hw, int xcast_mode) } /** - * Hyper-V variant - just a stub. + * ixgbevf_hv_update_xcast_mode - stub * @hw: unused * @xcast_mode: unused + * + * Hyper-V variant - just a stub. */ static s32 ixgbevf_hv_update_xcast_mode(struct ixgbe_hw *hw, int xcast_mode) { @@ -608,7 +614,7 @@ mbx_err: } /** - * Hyper-V variant - just a stub. + * ixgbevf_hv_set_vfta_vf - * Hyper-V variant - just a stub. * @hw: unused * @vlan: unused * @vind: unused @@ -726,11 +732,13 @@ out: } /** - * Hyper-V variant; there is no mailbox communication. + * ixgbevf_hv_check_mac_link_vf - check link * @hw: pointer to private hardware struct * @speed: pointer to link speed * @link_up: true is link is up, false otherwise * @autoneg_wait_to_complete: unused + * + * Hyper-V variant; there is no mailbox communication. */ static s32 ixgbevf_hv_check_mac_link_vf(struct ixgbe_hw *hw, ixgbe_link_speed *speed, diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.h b/drivers/net/ethernet/intel/ixgbevf/vf.h index d1e9e306653b..1d8209df4162 100644 --- a/drivers/net/ethernet/intel/ixgbevf/vf.h +++ b/drivers/net/ethernet/intel/ixgbevf/vf.h @@ -16,9 +16,6 @@ struct ixgbe_hw; -/* iterator type for walking multicast address lists */ -typedef u8* (*ixgbe_mc_addr_itr) (struct ixgbe_hw *hw, u8 **mc_addr_ptr, - u32 *vmdq); struct ixgbe_mac_operations { s32 (*init_hw)(struct ixgbe_hw *); s32 (*reset_hw)(struct ixgbe_hw *); |