diff options
230 files changed, 7151 insertions, 2840 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index fc044884c472..2b916990d7f0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15444,7 +15444,7 @@ NXP C45 TJA11XX PHY DRIVER M: Radu Pirea <[email protected]> S: Maintained -F: drivers/net/phy/nxp-c45-tja11xx.c +F: drivers/net/phy/nxp-c45-tja11xx* NXP FSPI DRIVER M: Han Xu <[email protected]> diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index e01a246124ac..f3543a2df68d 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -289,7 +289,7 @@ static int dpaa2_switch_port_add_vlan(struct ethsw_port_priv *port_priv, int err; if (port_priv->vlans[vid]) { - netdev_warn(netdev, "VLAN %d already configured\n", vid); + netdev_err(netdev, "VLAN %d already configured\n", vid); return -EEXIST; } @@ -1509,9 +1509,9 @@ static irqreturn_t dpaa2_switch_irq0_handler_thread(int irq_num, void *arg) struct device *dev = (struct device *)arg; struct ethsw_core *ethsw = dev_get_drvdata(dev); struct ethsw_port_priv *port_priv; - u32 status = ~0; int err, if_id; bool had_mac; + u32 status; err = dpsw_get_irq_status(ethsw->mc_io, 0, ethsw->dpsw_handle, DPSW_IRQ_INDEX_IF, &status); @@ -1523,12 +1523,11 @@ static irqreturn_t dpaa2_switch_irq0_handler_thread(int irq_num, void *arg) if_id = (status & 0xFFFF0000) >> 16; port_priv = ethsw->ports[if_id]; - if (status & DPSW_IRQ_EVENT_LINK_CHANGED) { + if (status & DPSW_IRQ_EVENT_LINK_CHANGED) dpaa2_switch_port_link_state_update(port_priv->netdev); - dpaa2_switch_port_set_mac_addr(port_priv); - } if (status & DPSW_IRQ_EVENT_ENDPOINT_CHANGED) { + dpaa2_switch_port_set_mac_addr(port_priv); /* We can avoid locking because the "endpoint changed" IRQ * handler is the only one who changes priv->mac at runtime, * so we are not racing with anyone. @@ -1540,20 +1539,20 @@ static irqreturn_t dpaa2_switch_irq0_handler_thread(int irq_num, void *arg) dpaa2_switch_port_connect_mac(port_priv); } -out: err = dpsw_clear_irq_status(ethsw->mc_io, 0, ethsw->dpsw_handle, DPSW_IRQ_INDEX_IF, status); if (err) dev_err(dev, "Can't clear irq status (err %d)\n", err); +out: return IRQ_HANDLED; } static int dpaa2_switch_setup_irqs(struct fsl_mc_device *sw_dev) { + u32 mask = DPSW_IRQ_EVENT_LINK_CHANGED | DPSW_IRQ_EVENT_ENDPOINT_CHANGED; struct device *dev = &sw_dev->dev; struct ethsw_core *ethsw = dev_get_drvdata(dev); - u32 mask = DPSW_IRQ_EVENT_LINK_CHANGED; struct fsl_mc_device_irq *irq; int err; @@ -1775,8 +1774,10 @@ int dpaa2_switch_port_vlans_add(struct net_device *netdev, /* Make sure that the VLAN is not already configured * on the switch port */ - if (port_priv->vlans[vlan->vid] & ETHSW_VLAN_MEMBER) + if (port_priv->vlans[vlan->vid] & ETHSW_VLAN_MEMBER) { + netdev_err(netdev, "VLAN %d already configured\n", vlan->vid); return -EEXIST; + } /* Check if there is space for a new VLAN */ err = dpsw_get_attributes(ethsw->mc_io, 0, ethsw->dpsw_handle, @@ -2003,25 +2004,11 @@ static int dpaa2_switch_port_bridge_join(struct net_device *netdev, struct netlink_ext_ack *extack) { struct ethsw_port_priv *port_priv = netdev_priv(netdev); + struct dpaa2_switch_fdb *old_fdb = port_priv->fdb; struct ethsw_core *ethsw = port_priv->ethsw_data; - struct ethsw_port_priv *other_port_priv; - struct net_device *other_dev; - struct list_head *iter; bool learn_ena; int err; - netdev_for_each_lower_dev(upper_dev, other_dev, iter) { - if (!dpaa2_switch_port_dev_check(other_dev)) - continue; - - other_port_priv = netdev_priv(other_dev); - if (other_port_priv->ethsw_data != port_priv->ethsw_data) { - NL_SET_ERR_MSG_MOD(extack, - "Interface from a different DPSW is in the bridge already"); - return -EINVAL; - } - } - /* Delete the previously manually installed VLAN 1 */ err = dpaa2_switch_port_del_vlan(port_priv, 1); if (err) @@ -2039,6 +2026,11 @@ static int dpaa2_switch_port_bridge_join(struct net_device *netdev, if (err) goto err_egress_flood; + /* Recreate the egress flood domain of the FDB that we just left. */ + err = dpaa2_switch_fdb_set_egress_flood(ethsw, old_fdb->fdb_id); + if (err) + goto err_egress_flood; + err = switchdev_bridge_port_offload(netdev, netdev, NULL, NULL, NULL, false, extack); if (err) @@ -2155,6 +2147,10 @@ dpaa2_switch_prechangeupper_sanity_checks(struct net_device *netdev, struct net_device *upper_dev, struct netlink_ext_ack *extack) { + struct ethsw_port_priv *port_priv = netdev_priv(netdev); + struct ethsw_port_priv *other_port_priv; + struct net_device *other_dev; + struct list_head *iter; int err; if (!br_vlan_enabled(upper_dev)) { @@ -2169,54 +2165,93 @@ dpaa2_switch_prechangeupper_sanity_checks(struct net_device *netdev, return 0; } + netdev_for_each_lower_dev(upper_dev, other_dev, iter) { + if (!dpaa2_switch_port_dev_check(other_dev)) + continue; + + other_port_priv = netdev_priv(other_dev); + if (other_port_priv->ethsw_data != port_priv->ethsw_data) { + NL_SET_ERR_MSG_MOD(extack, + "Interface from a different DPSW is in the bridge already"); + return -EINVAL; + } + } + return 0; } -static int dpaa2_switch_port_netdevice_event(struct notifier_block *nb, - unsigned long event, void *ptr) +static int dpaa2_switch_port_prechangeupper(struct net_device *netdev, + struct netdev_notifier_changeupper_info *info) { - struct net_device *netdev = netdev_notifier_info_to_dev(ptr); - struct netdev_notifier_changeupper_info *info = ptr; struct netlink_ext_ack *extack; struct net_device *upper_dev; - int err = 0; + int err; if (!dpaa2_switch_port_dev_check(netdev)) - return NOTIFY_DONE; + return 0; extack = netdev_notifier_info_to_extack(&info->info); - - switch (event) { - case NETDEV_PRECHANGEUPPER: - upper_dev = info->upper_dev; - if (!netif_is_bridge_master(upper_dev)) - break; - + upper_dev = info->upper_dev; + if (netif_is_bridge_master(upper_dev)) { err = dpaa2_switch_prechangeupper_sanity_checks(netdev, upper_dev, extack); if (err) - goto out; + return err; if (!info->linking) dpaa2_switch_port_pre_bridge_leave(netdev); + } + + return 0; +} + +static int dpaa2_switch_port_changeupper(struct net_device *netdev, + struct netdev_notifier_changeupper_info *info) +{ + struct netlink_ext_ack *extack; + struct net_device *upper_dev; + + if (!dpaa2_switch_port_dev_check(netdev)) + return 0; + + extack = netdev_notifier_info_to_extack(&info->info); + + upper_dev = info->upper_dev; + if (netif_is_bridge_master(upper_dev)) { + if (info->linking) + return dpaa2_switch_port_bridge_join(netdev, + upper_dev, + extack); + else + return dpaa2_switch_port_bridge_leave(netdev); + } + + return 0; +} + +static int dpaa2_switch_port_netdevice_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + int err = 0; + + switch (event) { + case NETDEV_PRECHANGEUPPER: + err = dpaa2_switch_port_prechangeupper(netdev, ptr); + if (err) + return notifier_from_errno(err); break; case NETDEV_CHANGEUPPER: - upper_dev = info->upper_dev; - if (netif_is_bridge_master(upper_dev)) { - if (info->linking) - err = dpaa2_switch_port_bridge_join(netdev, - upper_dev, - extack); - else - err = dpaa2_switch_port_bridge_leave(netdev); - } + err = dpaa2_switch_port_changeupper(netdev, ptr); + if (err) + return notifier_from_errno(err); + break; } -out: - return notifier_from_errno(err); + return NOTIFY_DONE; } struct ethsw_switchdev_event_work { @@ -3294,6 +3329,7 @@ static int dpaa2_switch_probe_port(struct ethsw_core *ethsw, port_netdev->features = NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER | NETIF_F_HW_TC; + port_netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE; err = dpaa2_switch_port_init(port_priv, port_idx); if (err) diff --git a/drivers/net/ethernet/intel/e1000/e1000_hw.c b/drivers/net/ethernet/intel/e1000/e1000_hw.c index 4542e2bc28e8..f9328f2e669f 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_hw.c +++ b/drivers/net/ethernet/intel/e1000/e1000_hw.c @@ -5,6 +5,7 @@ * Shared functions for accessing and configuring the MAC */ +#include <linux/bitfield.h> #include "e1000.h" static s32 e1000_check_downshift(struct e1000_hw *hw); @@ -3260,8 +3261,7 @@ static s32 e1000_phy_igp_get_info(struct e1000_hw *hw, return ret_val; phy_info->mdix_mode = - (e1000_auto_x_mode) ((phy_data & IGP01E1000_PSSR_MDIX) >> - IGP01E1000_PSSR_MDIX_SHIFT); + (e1000_auto_x_mode)FIELD_GET(IGP01E1000_PSSR_MDIX, phy_data); if ((phy_data & IGP01E1000_PSSR_SPEED_MASK) == IGP01E1000_PSSR_SPEED_1000MBPS) { @@ -3272,11 +3272,11 @@ static s32 e1000_phy_igp_get_info(struct e1000_hw *hw, if (ret_val) return ret_val; - phy_info->local_rx = ((phy_data & SR_1000T_LOCAL_RX_STATUS) >> - SR_1000T_LOCAL_RX_STATUS_SHIFT) ? + phy_info->local_rx = FIELD_GET(SR_1000T_LOCAL_RX_STATUS, + phy_data) ? e1000_1000t_rx_status_ok : e1000_1000t_rx_status_not_ok; - phy_info->remote_rx = ((phy_data & SR_1000T_REMOTE_RX_STATUS) >> - SR_1000T_REMOTE_RX_STATUS_SHIFT) ? + phy_info->remote_rx = FIELD_GET(SR_1000T_REMOTE_RX_STATUS, + phy_data) ? e1000_1000t_rx_status_ok : e1000_1000t_rx_status_not_ok; /* Get cable length */ @@ -3326,14 +3326,12 @@ static s32 e1000_phy_m88_get_info(struct e1000_hw *hw, return ret_val; phy_info->extended_10bt_distance = - ((phy_data & M88E1000_PSCR_10BT_EXT_DIST_ENABLE) >> - M88E1000_PSCR_10BT_EXT_DIST_ENABLE_SHIFT) ? + FIELD_GET(M88E1000_PSCR_10BT_EXT_DIST_ENABLE, phy_data) ? e1000_10bt_ext_dist_enable_lower : e1000_10bt_ext_dist_enable_normal; phy_info->polarity_correction = - ((phy_data & M88E1000_PSCR_POLARITY_REVERSAL) >> - M88E1000_PSCR_POLARITY_REVERSAL_SHIFT) ? + FIELD_GET(M88E1000_PSCR_POLARITY_REVERSAL, phy_data) ? e1000_polarity_reversal_disabled : e1000_polarity_reversal_enabled; /* Check polarity status */ @@ -3347,27 +3345,25 @@ static s32 e1000_phy_m88_get_info(struct e1000_hw *hw, return ret_val; phy_info->mdix_mode = - (e1000_auto_x_mode) ((phy_data & M88E1000_PSSR_MDIX) >> - M88E1000_PSSR_MDIX_SHIFT); + (e1000_auto_x_mode)FIELD_GET(M88E1000_PSSR_MDIX, phy_data); if ((phy_data & M88E1000_PSSR_SPEED) == M88E1000_PSSR_1000MBS) { /* Cable Length Estimation and Local/Remote Receiver Information * are only valid at 1000 Mbps. */ phy_info->cable_length = - (e1000_cable_length) ((phy_data & - M88E1000_PSSR_CABLE_LENGTH) >> - M88E1000_PSSR_CABLE_LENGTH_SHIFT); + (e1000_cable_length)FIELD_GET(M88E1000_PSSR_CABLE_LENGTH, + phy_data); ret_val = e1000_read_phy_reg(hw, PHY_1000T_STATUS, &phy_data); if (ret_val) return ret_val; - phy_info->local_rx = ((phy_data & SR_1000T_LOCAL_RX_STATUS) >> - SR_1000T_LOCAL_RX_STATUS_SHIFT) ? + phy_info->local_rx = FIELD_GET(SR_1000T_LOCAL_RX_STATUS, + phy_data) ? e1000_1000t_rx_status_ok : e1000_1000t_rx_status_not_ok; - phy_info->remote_rx = ((phy_data & SR_1000T_REMOTE_RX_STATUS) >> - SR_1000T_REMOTE_RX_STATUS_SHIFT) ? + phy_info->remote_rx = FIELD_GET(SR_1000T_REMOTE_RX_STATUS, + phy_data) ? e1000_1000t_rx_status_ok : e1000_1000t_rx_status_not_ok; } @@ -3515,7 +3511,7 @@ s32 e1000_init_eeprom_params(struct e1000_hw *hw) if (ret_val) return ret_val; eeprom_size = - (eeprom_size & EEPROM_SIZE_MASK) >> EEPROM_SIZE_SHIFT; + FIELD_GET(EEPROM_SIZE_MASK, eeprom_size); /* 256B eeprom size was not supported in earlier hardware, so we * bump eeprom_size up one to ensure that "1" (which maps to * 256B) is never the result used in the shifting logic below. @@ -4891,8 +4887,7 @@ static s32 e1000_get_cable_length(struct e1000_hw *hw, u16 *min_length, &phy_data); if (ret_val) return ret_val; - cable_length = (phy_data & M88E1000_PSSR_CABLE_LENGTH) >> - M88E1000_PSSR_CABLE_LENGTH_SHIFT; + cable_length = FIELD_GET(M88E1000_PSSR_CABLE_LENGTH, phy_data); /* Convert the enum value to ranged values */ switch (cable_length) { @@ -5001,8 +4996,7 @@ static s32 e1000_check_polarity(struct e1000_hw *hw, &phy_data); if (ret_val) return ret_val; - *polarity = ((phy_data & M88E1000_PSSR_REV_POLARITY) >> - M88E1000_PSSR_REV_POLARITY_SHIFT) ? + *polarity = FIELD_GET(M88E1000_PSSR_REV_POLARITY, phy_data) ? e1000_rev_polarity_reversed : e1000_rev_polarity_normal; } else if (hw->phy_type == e1000_phy_igp) { @@ -5072,8 +5066,8 @@ static s32 e1000_check_downshift(struct e1000_hw *hw) if (ret_val) return ret_val; - hw->speed_downgraded = (phy_data & M88E1000_PSSR_DOWNSHIFT) >> - M88E1000_PSSR_DOWNSHIFT_SHIFT; + hw->speed_downgraded = FIELD_GET(M88E1000_PSSR_DOWNSHIFT, + phy_data); } return E1000_SUCCESS; diff --git a/drivers/net/ethernet/intel/e1000e/80003es2lan.c b/drivers/net/ethernet/intel/e1000e/80003es2lan.c index be9c695dde12..4eb1ceaf865a 100644 --- a/drivers/net/ethernet/intel/e1000e/80003es2lan.c +++ b/drivers/net/ethernet/intel/e1000e/80003es2lan.c @@ -92,8 +92,7 @@ static s32 e1000_init_nvm_params_80003es2lan(struct e1000_hw *hw) nvm->type = e1000_nvm_eeprom_spi; - size = (u16)((eecd & E1000_EECD_SIZE_EX_MASK) >> - E1000_EECD_SIZE_EX_SHIFT); + size = (u16)FIELD_GET(E1000_EECD_SIZE_EX_MASK, eecd); /* Added to a constant, "size" becomes the left-shift value * for setting word_size. @@ -1035,17 +1034,18 @@ static s32 e1000_setup_copper_link_80003es2lan(struct e1000_hw *hw) * iteration and increase the max iterations when * polling the phy; this fixes erroneous timeouts at 10Mbps. */ - ret_val = e1000_write_kmrn_reg_80003es2lan(hw, GG82563_REG(0x34, 4), - 0xFFFF); + /* these next three accesses were always meant to use page 0x34 using + * GG82563_REG(0x34, N) but never did, so we've just corrected the call + * to not drop bits + */ + ret_val = e1000_write_kmrn_reg_80003es2lan(hw, 4, 0xFFFF); if (ret_val) return ret_val; - ret_val = e1000_read_kmrn_reg_80003es2lan(hw, GG82563_REG(0x34, 9), - ®_data); + ret_val = e1000_read_kmrn_reg_80003es2lan(hw, 9, ®_data); if (ret_val) return ret_val; reg_data |= 0x3F; - ret_val = e1000_write_kmrn_reg_80003es2lan(hw, GG82563_REG(0x34, 9), - reg_data); + ret_val = e1000_write_kmrn_reg_80003es2lan(hw, 9, reg_data); if (ret_val) return ret_val; ret_val = @@ -1209,8 +1209,8 @@ static s32 e1000_read_kmrn_reg_80003es2lan(struct e1000_hw *hw, u32 offset, if (ret_val) return ret_val; - kmrnctrlsta = ((offset << E1000_KMRNCTRLSTA_OFFSET_SHIFT) & - E1000_KMRNCTRLSTA_OFFSET) | E1000_KMRNCTRLSTA_REN; + kmrnctrlsta = FIELD_PREP(E1000_KMRNCTRLSTA_OFFSET, offset) | + E1000_KMRNCTRLSTA_REN; ew32(KMRNCTRLSTA, kmrnctrlsta); e1e_flush(); @@ -1244,8 +1244,7 @@ static s32 e1000_write_kmrn_reg_80003es2lan(struct e1000_hw *hw, u32 offset, if (ret_val) return ret_val; - kmrnctrlsta = ((offset << E1000_KMRNCTRLSTA_OFFSET_SHIFT) & - E1000_KMRNCTRLSTA_OFFSET) | data; + kmrnctrlsta = FIELD_PREP(E1000_KMRNCTRLSTA_OFFSET, offset) | data; ew32(KMRNCTRLSTA, kmrnctrlsta); e1e_flush(); diff --git a/drivers/net/ethernet/intel/e1000e/82571.c b/drivers/net/ethernet/intel/e1000e/82571.c index 0b1e890dd583..969f855a79ee 100644 --- a/drivers/net/ethernet/intel/e1000e/82571.c +++ b/drivers/net/ethernet/intel/e1000e/82571.c @@ -157,8 +157,7 @@ static s32 e1000_init_nvm_params_82571(struct e1000_hw *hw) fallthrough; default: nvm->type = e1000_nvm_eeprom_spi; - size = (u16)((eecd & E1000_EECD_SIZE_EX_MASK) >> - E1000_EECD_SIZE_EX_SHIFT); + size = (u16)FIELD_GET(E1000_EECD_SIZE_EX_MASK, eecd); /* Added to a constant, "size" becomes the left-shift value * for setting word_size. */ diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index 9835e6a90d56..fc0f98ea6133 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -654,8 +654,8 @@ static void e1000_get_drvinfo(struct net_device *netdev, */ snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%d.%d-%d", - (adapter->eeprom_vers & 0xF000) >> 12, - (adapter->eeprom_vers & 0x0FF0) >> 4, + FIELD_GET(0xF000, adapter->eeprom_vers), + FIELD_GET(0x0FF0, adapter->eeprom_vers), (adapter->eeprom_vers & 0x000F)); strscpy(drvinfo->bus_info, pci_name(adapter->pdev), @@ -925,8 +925,7 @@ static int e1000_reg_test(struct e1000_adapter *adapter, u64 *data) } if (mac->type >= e1000_pch_lpt) - wlock_mac = (er32(FWSM) & E1000_FWSM_WLOCK_MAC_MASK) >> - E1000_FWSM_WLOCK_MAC_SHIFT; + wlock_mac = FIELD_GET(E1000_FWSM_WLOCK_MAC_MASK, er32(FWSM)); for (i = 0; i < mac->rar_entry_count; i++) { if (mac->type >= e1000_pch_lpt) { diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 39e9fc601bf5..a2788fd5f8bb 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -1072,13 +1072,11 @@ static s32 e1000_platform_pm_pch_lpt(struct e1000_hw *hw, bool link) lat_enc_d = (lat_enc & E1000_LTRV_VALUE_MASK) * (1U << (E1000_LTRV_SCALE_FACTOR * - ((lat_enc & E1000_LTRV_SCALE_MASK) - >> E1000_LTRV_SCALE_SHIFT))); + FIELD_GET(E1000_LTRV_SCALE_MASK, lat_enc))); max_ltr_enc_d = (max_ltr_enc & E1000_LTRV_VALUE_MASK) * - (1U << (E1000_LTRV_SCALE_FACTOR * - ((max_ltr_enc & E1000_LTRV_SCALE_MASK) - >> E1000_LTRV_SCALE_SHIFT))); + (1U << (E1000_LTRV_SCALE_FACTOR * + FIELD_GET(E1000_LTRV_SCALE_MASK, max_ltr_enc))); if (lat_enc_d > max_ltr_enc_d) lat_enc = max_ltr_enc; @@ -2075,8 +2073,7 @@ static s32 e1000_write_smbus_addr(struct e1000_hw *hw) { u16 phy_data; u32 strap = er32(STRAP); - u32 freq = (strap & E1000_STRAP_SMT_FREQ_MASK) >> - E1000_STRAP_SMT_FREQ_SHIFT; + u32 freq = FIELD_GET(E1000_STRAP_SMT_FREQ_MASK, strap); s32 ret_val; strap &= E1000_STRAP_SMBUS_ADDRESS_MASK; @@ -2562,8 +2559,7 @@ void e1000_copy_rx_addrs_to_phy_ich8lan(struct e1000_hw *hw) hw->phy.ops.write_reg_page(hw, BM_RAR_H(i), (u16)(mac_reg & 0xFFFF)); hw->phy.ops.write_reg_page(hw, BM_RAR_CTRL(i), - (u16)((mac_reg & E1000_RAH_AV) - >> 16)); + FIELD_GET(E1000_RAH_AV, mac_reg)); } e1000_disable_phy_wakeup_reg_access_bm(hw, &phy_reg); @@ -3205,7 +3201,7 @@ static s32 e1000_valid_nvm_bank_detect_ich8lan(struct e1000_hw *hw, u32 *bank) &nvm_dword); if (ret_val) return ret_val; - sig_byte = (u8)((nvm_dword & 0xFF00) >> 8); + sig_byte = FIELD_GET(0xFF00, nvm_dword); if ((sig_byte & E1000_ICH_NVM_VALID_SIG_MASK) == E1000_ICH_NVM_SIG_VALUE) { *bank = 0; @@ -3218,7 +3214,7 @@ static s32 e1000_valid_nvm_bank_detect_ich8lan(struct e1000_hw *hw, u32 *bank) &nvm_dword); if (ret_val) return ret_val; - sig_byte = (u8)((nvm_dword & 0xFF00) >> 8); + sig_byte = FIELD_GET(0xFF00, nvm_dword); if ((sig_byte & E1000_ICH_NVM_VALID_SIG_MASK) == E1000_ICH_NVM_SIG_VALUE) { *bank = 1; diff --git a/drivers/net/ethernet/intel/e1000e/mac.c b/drivers/net/ethernet/intel/e1000e/mac.c index 8c3d9c5962f2..d7df2a0ed629 100644 --- a/drivers/net/ethernet/intel/e1000e/mac.c +++ b/drivers/net/ethernet/intel/e1000e/mac.c @@ -50,7 +50,7 @@ void e1000_set_lan_id_multi_port_pcie(struct e1000_hw *hw) * for the device regardless of function swap state. */ reg = er32(STATUS); - bus->func = (reg & E1000_STATUS_FUNC_MASK) >> E1000_STATUS_FUNC_SHIFT; + bus->func = FIELD_GET(E1000_STATUS_FUNC_MASK, reg); } /** diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index f536c856727c..af5d9d97a0d6 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -1788,8 +1788,7 @@ static irqreturn_t e1000_intr_msi(int __always_unused irq, void *data) adapter->corr_errors += pbeccsts & E1000_PBECCSTS_CORR_ERR_CNT_MASK; adapter->uncorr_errors += - (pbeccsts & E1000_PBECCSTS_UNCORR_ERR_CNT_MASK) >> - E1000_PBECCSTS_UNCORR_ERR_CNT_SHIFT; + FIELD_GET(E1000_PBECCSTS_UNCORR_ERR_CNT_MASK, pbeccsts); /* Do the reset outside of interrupt context */ schedule_work(&adapter->reset_task); @@ -1868,8 +1867,7 @@ static irqreturn_t e1000_intr(int __always_unused irq, void *data) adapter->corr_errors += pbeccsts & E1000_PBECCSTS_CORR_ERR_CNT_MASK; adapter->uncorr_errors += - (pbeccsts & E1000_PBECCSTS_UNCORR_ERR_CNT_MASK) >> - E1000_PBECCSTS_UNCORR_ERR_CNT_SHIFT; + FIELD_GET(E1000_PBECCSTS_UNCORR_ERR_CNT_MASK, pbeccsts); /* Do the reset outside of interrupt context */ schedule_work(&adapter->reset_task); @@ -5031,8 +5029,7 @@ static void e1000e_update_stats(struct e1000_adapter *adapter) adapter->corr_errors += pbeccsts & E1000_PBECCSTS_CORR_ERR_CNT_MASK; adapter->uncorr_errors += - (pbeccsts & E1000_PBECCSTS_UNCORR_ERR_CNT_MASK) >> - E1000_PBECCSTS_UNCORR_ERR_CNT_SHIFT; + FIELD_GET(E1000_PBECCSTS_UNCORR_ERR_CNT_MASK, pbeccsts); } } @@ -6249,7 +6246,7 @@ static int e1000_init_phy_wakeup(struct e1000_adapter *adapter, u32 wufc) phy_reg |= BM_RCTL_MPE; phy_reg &= ~(BM_RCTL_MO_MASK); if (mac_reg & E1000_RCTL_MO_3) - phy_reg |= (((mac_reg & E1000_RCTL_MO_3) >> E1000_RCTL_MO_SHIFT) + phy_reg |= (FIELD_GET(E1000_RCTL_MO_3, mac_reg) << BM_RCTL_MO_SHIFT); if (mac_reg & E1000_RCTL_BAM) phy_reg |= BM_RCTL_BAM; diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c index 08c3d477dd6f..5e329156d1ba 100644 --- a/drivers/net/ethernet/intel/e1000e/phy.c +++ b/drivers/net/ethernet/intel/e1000e/phy.c @@ -154,10 +154,9 @@ s32 e1000e_read_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 *data) e_dbg("MDI Read PHY Reg Address %d Error\n", offset); return -E1000_ERR_PHY; } - if (((mdic & E1000_MDIC_REG_MASK) >> E1000_MDIC_REG_SHIFT) != offset) { + if (FIELD_GET(E1000_MDIC_REG_MASK, mdic) != offset) { e_dbg("MDI Read offset error - requested %d, returned %d\n", - offset, - (mdic & E1000_MDIC_REG_MASK) >> E1000_MDIC_REG_SHIFT); + offset, FIELD_GET(E1000_MDIC_REG_MASK, mdic)); return -E1000_ERR_PHY; } *data = (u16)mdic; @@ -167,7 +166,6 @@ s32 e1000e_read_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 *data) */ if (hw->mac.type == e1000_pch2lan) udelay(100); - return 0; } @@ -218,10 +216,9 @@ s32 e1000e_write_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 data) e_dbg("MDI Write PHY Red Address %d Error\n", offset); return -E1000_ERR_PHY; } - if (((mdic & E1000_MDIC_REG_MASK) >> E1000_MDIC_REG_SHIFT) != offset) { + if (FIELD_GET(E1000_MDIC_REG_MASK, mdic) != offset) { e_dbg("MDI Write offset error - requested %d, returned %d\n", - offset, - (mdic & E1000_MDIC_REG_MASK) >> E1000_MDIC_REG_SHIFT); + offset, FIELD_GET(E1000_MDIC_REG_MASK, mdic)); return -E1000_ERR_PHY; } @@ -463,8 +460,8 @@ static s32 __e1000_read_kmrn_reg(struct e1000_hw *hw, u32 offset, u16 *data, return ret_val; } - kmrnctrlsta = ((offset << E1000_KMRNCTRLSTA_OFFSET_SHIFT) & - E1000_KMRNCTRLSTA_OFFSET) | E1000_KMRNCTRLSTA_REN; + kmrnctrlsta = FIELD_PREP(E1000_KMRNCTRLSTA_OFFSET, offset) | + E1000_KMRNCTRLSTA_REN; ew32(KMRNCTRLSTA, kmrnctrlsta); e1e_flush(); @@ -536,8 +533,7 @@ static s32 __e1000_write_kmrn_reg(struct e1000_hw *hw, u32 offset, u16 data, return ret_val; } - kmrnctrlsta = ((offset << E1000_KMRNCTRLSTA_OFFSET_SHIFT) & - E1000_KMRNCTRLSTA_OFFSET) | data; + kmrnctrlsta = FIELD_PREP(E1000_KMRNCTRLSTA_OFFSET, offset) | data; ew32(KMRNCTRLSTA, kmrnctrlsta); e1e_flush(); @@ -1793,8 +1789,7 @@ s32 e1000e_get_cable_length_m88(struct e1000_hw *hw) if (ret_val) return ret_val; - index = ((phy_data & M88E1000_PSSR_CABLE_LENGTH) >> - M88E1000_PSSR_CABLE_LENGTH_SHIFT); + index = FIELD_GET(M88E1000_PSSR_CABLE_LENGTH, phy_data); if (index >= M88E1000_CABLE_LENGTH_TABLE_SIZE - 1) return -E1000_ERR_PHY; @@ -3234,8 +3229,7 @@ s32 e1000_get_cable_length_82577(struct e1000_hw *hw) if (ret_val) return ret_val; - length = ((phy_data & I82577_DSTATUS_CABLE_LENGTH) >> - I82577_DSTATUS_CABLE_LENGTH_SHIFT); + length = FIELD_GET(I82577_DSTATUS_CABLE_LENGTH, phy_data); if (length == E1000_CABLE_LENGTH_UNDEFINED) return -E1000_ERR_PHY; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c index af1b0cde3670..98861cc6df7c 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2019 Intel Corporation. */ +#include <linux/bitfield.h> #include "fm10k_pf.h" #include "fm10k_vf.h" @@ -865,8 +866,7 @@ static s32 fm10k_iov_assign_default_mac_vlan_pf(struct fm10k_hw *hw, * register is RO from the VF, so the PF must do this even in the * case of notifying the VF of a new VID via the mailbox. */ - txqctl = ((u32)vf_vid << FM10K_TXQCTL_VID_SHIFT) & - FM10K_TXQCTL_VID_MASK; + txqctl = FIELD_PREP(FM10K_TXQCTL_VID_MASK, vf_vid); txqctl |= (vf_idx << FM10K_TXQCTL_TC_SHIFT) | FM10K_TXQCTL_VF | vf_idx; @@ -1575,8 +1575,7 @@ static s32 fm10k_get_fault_pf(struct fm10k_hw *hw, int type, if (func & FM10K_FAULT_FUNC_PF) fault->func = 0; else - fault->func = 1 + ((func & FM10K_FAULT_FUNC_VF_MASK) >> - FM10K_FAULT_FUNC_VF_SHIFT); + fault->func = 1 + FIELD_GET(FM10K_FAULT_FUNC_VF_MASK, func); /* record fault type */ fault->type = func & FM10K_FAULT_FUNC_TYPE_MASK; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c index dc8ccd378ec9..7fb1961f2921 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2019 Intel Corporation. */ +#include <linux/bitfield.h> #include "fm10k_vf.h" /** @@ -126,15 +127,14 @@ static s32 fm10k_init_hw_vf(struct fm10k_hw *hw) hw->mac.max_queues = i; /* fetch default VLAN and ITR scale */ - hw->mac.default_vid = (fm10k_read_reg(hw, FM10K_TXQCTL(0)) & - FM10K_TXQCTL_VID_MASK) >> FM10K_TXQCTL_VID_SHIFT; + hw->mac.default_vid = FIELD_GET(FM10K_TXQCTL_VID_MASK, + fm10k_read_reg(hw, FM10K_TXQCTL(0))); /* Read the ITR scale from TDLEN. See the definition of * FM10K_TDLEN_ITR_SCALE_SHIFT for more information about how TDLEN is * used here. */ - hw->mac.itr_scale = (fm10k_read_reg(hw, FM10K_TDLEN(0)) & - FM10K_TDLEN_ITR_SCALE_MASK) >> - FM10K_TDLEN_ITR_SCALE_SHIFT; + hw->mac.itr_scale = FIELD_GET(FM10K_TDLEN_ITR_SCALE_MASK, + fm10k_read_reg(hw, FM10K_TDLEN(0))); return 0; diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index bd52b73cf61f..de6ca6295742 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -2,6 +2,7 @@ /* Copyright(c) 2013 - 2021 Intel Corporation. */ #include <linux/avf/virtchnl.h> +#include <linux/bitfield.h> #include <linux/delay.h> #include <linux/etherdevice.h> #include <linux/pci.h> @@ -248,6 +249,7 @@ static int i40e_aq_get_set_rss_lut(struct i40e_hw *hw, struct i40e_aqc_get_set_rss_lut *cmd_resp = (struct i40e_aqc_get_set_rss_lut *)&desc.params.raw; int status; + u16 flags; if (set) i40e_fill_default_direct_cmd_desc(&desc, @@ -260,23 +262,18 @@ static int i40e_aq_get_set_rss_lut(struct i40e_hw *hw, desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF); desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_RD); - cmd_resp->vsi_id = - cpu_to_le16((u16)((vsi_id << - I40E_AQC_SET_RSS_LUT_VSI_ID_SHIFT) & - I40E_AQC_SET_RSS_LUT_VSI_ID_MASK)); - cmd_resp->vsi_id |= cpu_to_le16((u16)I40E_AQC_SET_RSS_LUT_VSI_VALID); + vsi_id = FIELD_PREP(I40E_AQC_SET_RSS_LUT_VSI_ID_MASK, vsi_id) | + FIELD_PREP(I40E_AQC_SET_RSS_LUT_VSI_VALID, 1); + cmd_resp->vsi_id = cpu_to_le16(vsi_id); if (pf_lut) - cmd_resp->flags |= cpu_to_le16((u16) - ((I40E_AQC_SET_RSS_LUT_TABLE_TYPE_PF << - I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) & - I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK)); + flags = FIELD_PREP(I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK, + I40E_AQC_SET_RSS_LUT_TABLE_TYPE_PF); else - cmd_resp->flags |= cpu_to_le16((u16) - ((I40E_AQC_SET_RSS_LUT_TABLE_TYPE_VSI << - I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) & - I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK)); + flags = FIELD_PREP(I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK, + I40E_AQC_SET_RSS_LUT_TABLE_TYPE_VSI); + cmd_resp->flags = cpu_to_le16(flags); status = i40e_asq_send_command(hw, &desc, lut, lut_size, NULL); return status; @@ -346,11 +343,9 @@ static int i40e_aq_get_set_rss_key(struct i40e_hw *hw, desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF); desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_RD); - cmd_resp->vsi_id = - cpu_to_le16((u16)((vsi_id << - I40E_AQC_SET_RSS_KEY_VSI_ID_SHIFT) & - I40E_AQC_SET_RSS_KEY_VSI_ID_MASK)); - cmd_resp->vsi_id |= cpu_to_le16((u16)I40E_AQC_SET_RSS_KEY_VSI_VALID); + vsi_id = FIELD_PREP(I40E_AQC_SET_RSS_KEY_VSI_ID_MASK, vsi_id) | + FIELD_PREP(I40E_AQC_SET_RSS_KEY_VSI_VALID, 1); + cmd_resp->vsi_id = cpu_to_le16(vsi_id); status = i40e_asq_send_command(hw, &desc, key, key_size, NULL); @@ -669,11 +664,11 @@ int i40e_init_shared_code(struct i40e_hw *hw) hw->phy.get_link_info = true; /* Determine port number and PF number*/ - port = (rd32(hw, I40E_PFGEN_PORTNUM) & I40E_PFGEN_PORTNUM_PORT_NUM_MASK) - >> I40E_PFGEN_PORTNUM_PORT_NUM_SHIFT; + port = FIELD_GET(I40E_PFGEN_PORTNUM_PORT_NUM_MASK, + rd32(hw, I40E_PFGEN_PORTNUM)); hw->port = (u8)port; - ari = (rd32(hw, I40E_GLPCI_CAPSUP) & I40E_GLPCI_CAPSUP_ARI_EN_MASK) >> - I40E_GLPCI_CAPSUP_ARI_EN_SHIFT; + ari = FIELD_GET(I40E_GLPCI_CAPSUP_ARI_EN_MASK, + rd32(hw, I40E_GLPCI_CAPSUP)); func_rid = rd32(hw, I40E_PF_FUNC_RID); if (ari) hw->pf_id = (u8)(func_rid & 0xff); @@ -991,9 +986,8 @@ int i40e_pf_reset(struct i40e_hw *hw) * The grst delay value is in 100ms units, and we'll wait a * couple counts longer to be sure we don't just miss the end. */ - grst_del = (rd32(hw, I40E_GLGEN_RSTCTL) & - I40E_GLGEN_RSTCTL_GRSTDEL_MASK) >> - I40E_GLGEN_RSTCTL_GRSTDEL_SHIFT; + grst_del = FIELD_GET(I40E_GLGEN_RSTCTL_GRSTDEL_MASK, + rd32(hw, I40E_GLGEN_RSTCTL)); /* It can take upto 15 secs for GRST steady state. * Bump it to 16 secs max to be safe. @@ -1085,26 +1079,20 @@ void i40e_clear_hw(struct i40e_hw *hw) /* get number of interrupts, queues, and VFs */ val = rd32(hw, I40E_GLPCI_CNF2); - num_pf_int = (val & I40E_GLPCI_CNF2_MSI_X_PF_N_MASK) >> - I40E_GLPCI_CNF2_MSI_X_PF_N_SHIFT; - num_vf_int = (val & I40E_GLPCI_CNF2_MSI_X_VF_N_MASK) >> - I40E_GLPCI_CNF2_MSI_X_VF_N_SHIFT; + num_pf_int = FIELD_GET(I40E_GLPCI_CNF2_MSI_X_PF_N_MASK, val); + num_vf_int = FIELD_GET(I40E_GLPCI_CNF2_MSI_X_VF_N_MASK, val); val = rd32(hw, I40E_PFLAN_QALLOC); - base_queue = (val & I40E_PFLAN_QALLOC_FIRSTQ_MASK) >> - I40E_PFLAN_QALLOC_FIRSTQ_SHIFT; - j = (val & I40E_PFLAN_QALLOC_LASTQ_MASK) >> - I40E_PFLAN_QALLOC_LASTQ_SHIFT; + base_queue = FIELD_GET(I40E_PFLAN_QALLOC_FIRSTQ_MASK, val); + j = FIELD_GET(I40E_PFLAN_QALLOC_LASTQ_MASK, val); if (val & I40E_PFLAN_QALLOC_VALID_MASK && j >= base_queue) num_queues = (j - base_queue) + 1; else num_queues = 0; val = rd32(hw, I40E_PF_VT_PFALLOC); - i = (val & I40E_PF_VT_PFALLOC_FIRSTVF_MASK) >> - I40E_PF_VT_PFALLOC_FIRSTVF_SHIFT; - j = (val & I40E_PF_VT_PFALLOC_LASTVF_MASK) >> - I40E_PF_VT_PFALLOC_LASTVF_SHIFT; + i = FIELD_GET(I40E_PF_VT_PFALLOC_FIRSTVF_MASK, val); + j = FIELD_GET(I40E_PF_VT_PFALLOC_LASTVF_MASK, val); if (val & I40E_PF_VT_PFALLOC_VALID_MASK && j >= i) num_vfs = (j - i) + 1; else @@ -1199,8 +1187,7 @@ static u32 i40e_led_is_mine(struct i40e_hw *hw, int idx) !hw->func_caps.led[idx]) return 0; gpio_val = rd32(hw, I40E_GLGEN_GPIO_CTL(idx)); - port = (gpio_val & I40E_GLGEN_GPIO_CTL_PRT_NUM_MASK) >> - I40E_GLGEN_GPIO_CTL_PRT_NUM_SHIFT; + port = FIELD_GET(I40E_GLGEN_GPIO_CTL_PRT_NUM_MASK, gpio_val); /* if PRT_NUM_NA is 1 then this LED is not port specific, OR * if it is not our port then ignore @@ -1244,8 +1231,7 @@ u32 i40e_led_get(struct i40e_hw *hw) if (!gpio_val) continue; - mode = (gpio_val & I40E_GLGEN_GPIO_CTL_LED_MODE_MASK) >> - I40E_GLGEN_GPIO_CTL_LED_MODE_SHIFT; + mode = FIELD_GET(I40E_GLGEN_GPIO_CTL_LED_MODE_MASK, gpio_val); break; } @@ -1288,14 +1274,14 @@ void i40e_led_set(struct i40e_hw *hw, u32 mode, bool blink) pin_func = I40E_PIN_FUNC_LED; gpio_val &= ~I40E_GLGEN_GPIO_CTL_PIN_FUNC_MASK; - gpio_val |= ((pin_func << - I40E_GLGEN_GPIO_CTL_PIN_FUNC_SHIFT) & - I40E_GLGEN_GPIO_CTL_PIN_FUNC_MASK); + gpio_val |= + FIELD_PREP(I40E_GLGEN_GPIO_CTL_PIN_FUNC_MASK, + pin_func); } gpio_val &= ~I40E_GLGEN_GPIO_CTL_LED_MODE_MASK; /* this & is a bit of paranoia, but serves as a range check */ - gpio_val |= ((mode << I40E_GLGEN_GPIO_CTL_LED_MODE_SHIFT) & - I40E_GLGEN_GPIO_CTL_LED_MODE_MASK); + gpio_val |= FIELD_PREP(I40E_GLGEN_GPIO_CTL_LED_MODE_MASK, + mode); if (blink) gpio_val |= BIT(I40E_GLGEN_GPIO_CTL_LED_BLINK_SHIFT); @@ -3514,8 +3500,7 @@ int i40e_aq_get_lldp_mib(struct i40e_hw *hw, u8 bridge_type, desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF); cmd->type = mib_type & I40E_AQ_LLDP_MIB_TYPE_MASK; - cmd->type |= ((bridge_type << I40E_AQ_LLDP_BRIDGE_TYPE_SHIFT) & - I40E_AQ_LLDP_BRIDGE_TYPE_MASK); + cmd->type |= FIELD_PREP(I40E_AQ_LLDP_BRIDGE_TYPE_MASK, bridge_type); desc.datalen = cpu_to_le16(buff_size); @@ -4196,8 +4181,7 @@ i40e_validate_filter_settings(struct i40e_hw *hw, /* FCHSIZE + FCDSIZE should not be greater than PMFCOEFMAX */ val = rd32(hw, I40E_GLHMC_FCOEFMAX); - fcoe_fmax = (val & I40E_GLHMC_FCOEFMAX_PMFCOEFMAX_MASK) - >> I40E_GLHMC_FCOEFMAX_PMFCOEFMAX_SHIFT; + fcoe_fmax = FIELD_GET(I40E_GLHMC_FCOEFMAX_PMFCOEFMAX_MASK, val); if (fcoe_filt_size + fcoe_cntx_size > fcoe_fmax) return -EINVAL; @@ -4233,30 +4217,25 @@ int i40e_set_filter_control(struct i40e_hw *hw, /* Program required PE hash buckets for the PF */ val &= ~I40E_PFQF_CTL_0_PEHSIZE_MASK; - val |= ((u32)settings->pe_filt_num << I40E_PFQF_CTL_0_PEHSIZE_SHIFT) & - I40E_PFQF_CTL_0_PEHSIZE_MASK; + val |= FIELD_PREP(I40E_PFQF_CTL_0_PEHSIZE_MASK, settings->pe_filt_num); /* Program required PE contexts for the PF */ val &= ~I40E_PFQF_CTL_0_PEDSIZE_MASK; - val |= ((u32)settings->pe_cntx_num << I40E_PFQF_CTL_0_PEDSIZE_SHIFT) & - I40E_PFQF_CTL_0_PEDSIZE_MASK; + val |= FIELD_PREP(I40E_PFQF_CTL_0_PEDSIZE_MASK, settings->pe_cntx_num); /* Program required FCoE hash buckets for the PF */ val &= ~I40E_PFQF_CTL_0_PFFCHSIZE_MASK; - val |= ((u32)settings->fcoe_filt_num << - I40E_PFQF_CTL_0_PFFCHSIZE_SHIFT) & - I40E_PFQF_CTL_0_PFFCHSIZE_MASK; + val |= FIELD_PREP(I40E_PFQF_CTL_0_PFFCHSIZE_MASK, + settings->fcoe_filt_num); /* Program required FCoE DDP contexts for the PF */ val &= ~I40E_PFQF_CTL_0_PFFCDSIZE_MASK; - val |= ((u32)settings->fcoe_cntx_num << - I40E_PFQF_CTL_0_PFFCDSIZE_SHIFT) & - I40E_PFQF_CTL_0_PFFCDSIZE_MASK; + val |= FIELD_PREP(I40E_PFQF_CTL_0_PFFCDSIZE_MASK, + settings->fcoe_cntx_num); /* Program Hash LUT size for the PF */ val &= ~I40E_PFQF_CTL_0_HASHLUTSIZE_MASK; if (settings->hash_lut_size == I40E_HASH_LUT_SIZE_512) hash_lut_size = 1; - val |= (hash_lut_size << I40E_PFQF_CTL_0_HASHLUTSIZE_SHIFT) & - I40E_PFQF_CTL_0_HASHLUTSIZE_MASK; + val |= FIELD_PREP(I40E_PFQF_CTL_0_HASHLUTSIZE_MASK, hash_lut_size); /* Enable FDIR, Ethertype and MACVLAN filters for PF and VFs */ if (settings->enable_fdir) @@ -4657,8 +4636,7 @@ int i40e_read_phy_register_clause22(struct i40e_hw *hw, "PHY: Can't write command to external PHY.\n"); } else { command = rd32(hw, I40E_GLGEN_MSRWD(port_num)); - *value = (command & I40E_GLGEN_MSRWD_MDIRDDATA_MASK) >> - I40E_GLGEN_MSRWD_MDIRDDATA_SHIFT; + *value = FIELD_GET(I40E_GLGEN_MSRWD_MDIRDDATA_MASK, command); } return status; @@ -4767,8 +4745,7 @@ int i40e_read_phy_register_clause45(struct i40e_hw *hw, if (!status) { command = rd32(hw, I40E_GLGEN_MSRWD(port_num)); - *value = (command & I40E_GLGEN_MSRWD_MDIRDDATA_MASK) >> - I40E_GLGEN_MSRWD_MDIRDDATA_SHIFT; + *value = FIELD_GET(I40E_GLGEN_MSRWD_MDIRDDATA_MASK, command); } else { i40e_debug(hw, I40E_DEBUG_PHY, "PHY: Can't read register value from external PHY.\n"); @@ -5318,16 +5295,17 @@ static void i40e_mdio_if_number_selection(struct i40e_hw *hw, bool set_mdio, u8 mdio_num, struct i40e_aqc_phy_register_access *cmd) { - if (set_mdio && cmd->phy_interface == I40E_AQ_PHY_REG_ACCESS_EXTERNAL) { - if (test_bit(I40E_HW_CAP_AQ_PHY_ACCESS_EXTENDED, hw->caps)) - cmd->cmd_flags |= - I40E_AQ_PHY_REG_ACCESS_SET_MDIO_IF_NUMBER | - ((mdio_num << - I40E_AQ_PHY_REG_ACCESS_MDIO_IF_NUMBER_SHIFT) & - I40E_AQ_PHY_REG_ACCESS_MDIO_IF_NUMBER_MASK); - else - i40e_debug(hw, I40E_DEBUG_PHY, - "MDIO I/F number selection not supported by current FW version.\n"); + if (!set_mdio || + cmd->phy_interface != I40E_AQ_PHY_REG_ACCESS_EXTERNAL) + return; + + if (test_bit(I40E_HW_CAP_AQ_PHY_ACCESS_EXTENDED, hw->caps)) { + cmd->cmd_flags |= + I40E_AQ_PHY_REG_ACCESS_SET_MDIO_IF_NUMBER | + FIELD_PREP(I40E_AQ_PHY_REG_ACCESS_MDIO_IF_NUMBER_MASK, + mdio_num); + } else { + i40e_debug(hw, I40E_DEBUG_PHY, "MDIO I/F number selection not supported by current FW version.\n"); } } @@ -5912,9 +5890,8 @@ i40e_aq_add_cloud_filters_bb(struct i40e_hw *hw, u16 seid, u16 tnl_type; u32 ti; - tnl_type = (le16_to_cpu(filters[i].element.flags) & - I40E_AQC_ADD_CLOUD_TNL_TYPE_MASK) >> - I40E_AQC_ADD_CLOUD_TNL_TYPE_SHIFT; + tnl_type = le16_get_bits(filters[i].element.flags, + I40E_AQC_ADD_CLOUD_TNL_TYPE_MASK); /* Due to hardware eccentricities, the VNI for Geneve is shifted * one more byte further than normally used for Tenant ID in @@ -6006,9 +5983,8 @@ i40e_aq_rem_cloud_filters_bb(struct i40e_hw *hw, u16 seid, u16 tnl_type; u32 ti; - tnl_type = (le16_to_cpu(filters[i].element.flags) & - I40E_AQC_ADD_CLOUD_TNL_TYPE_MASK) >> - I40E_AQC_ADD_CLOUD_TNL_TYPE_SHIFT; + tnl_type = le16_get_bits(filters[i].element.flags, + I40E_AQC_ADD_CLOUD_TNL_TYPE_MASK); /* Due to hardware eccentricities, the VNI for Geneve is shifted * one more byte further than normally used for Tenant ID in diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.c b/drivers/net/ethernet/intel/i40e/i40e_dcb.c index 498728e16a37..9d88ed6105fd 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_dcb.c +++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2021 Intel Corporation. */ +#include <linux/bitfield.h> +#include "i40e_adminq.h" #include "i40e_alloc.h" #include "i40e_dcb.h" #include "i40e_prototype.h" @@ -20,8 +22,7 @@ int i40e_get_dcbx_status(struct i40e_hw *hw, u16 *status) return -EINVAL; reg = rd32(hw, I40E_PRTDCB_GENS); - *status = (u16)((reg & I40E_PRTDCB_GENS_DCBX_STATUS_MASK) >> - I40E_PRTDCB_GENS_DCBX_STATUS_SHIFT); + *status = FIELD_GET(I40E_PRTDCB_GENS_DCBX_STATUS_MASK, reg); return 0; } @@ -50,12 +51,9 @@ static void i40e_parse_ieee_etscfg_tlv(struct i40e_lldp_org_tlv *tlv, * |1bit | 1bit|3 bits|3bits| */ etscfg = &dcbcfg->etscfg; - etscfg->willing = (u8)((buf[offset] & I40E_IEEE_ETS_WILLING_MASK) >> - I40E_IEEE_ETS_WILLING_SHIFT); - etscfg->cbs = (u8)((buf[offset] & I40E_IEEE_ETS_CBS_MASK) >> - I40E_IEEE_ETS_CBS_SHIFT); - etscfg->maxtcs = (u8)((buf[offset] & I40E_IEEE_ETS_MAXTC_MASK) >> - I40E_IEEE_ETS_MAXTC_SHIFT); + etscfg->willing = FIELD_GET(I40E_IEEE_ETS_WILLING_MASK, buf[offset]); + etscfg->cbs = FIELD_GET(I40E_IEEE_ETS_CBS_MASK, buf[offset]); + etscfg->maxtcs = FIELD_GET(I40E_IEEE_ETS_MAXTC_MASK, buf[offset]); /* Move offset to Priority Assignment Table */ offset++; @@ -69,11 +67,9 @@ static void i40e_parse_ieee_etscfg_tlv(struct i40e_lldp_org_tlv *tlv, * ----------------------------------------- */ for (i = 0; i < 4; i++) { - priority = (u8)((buf[offset] & I40E_IEEE_ETS_PRIO_1_MASK) >> - I40E_IEEE_ETS_PRIO_1_SHIFT); - etscfg->prioritytable[i * 2] = priority; - priority = (u8)((buf[offset] & I40E_IEEE_ETS_PRIO_0_MASK) >> - I40E_IEEE_ETS_PRIO_0_SHIFT); + priority = FIELD_GET(I40E_IEEE_ETS_PRIO_1_MASK, buf[offset]); + etscfg->prioritytable[i * 2] = priority; + priority = FIELD_GET(I40E_IEEE_ETS_PRIO_0_MASK, buf[offset]); etscfg->prioritytable[i * 2 + 1] = priority; offset++; } @@ -124,12 +120,10 @@ static void i40e_parse_ieee_etsrec_tlv(struct i40e_lldp_org_tlv *tlv, * ----------------------------------------- */ for (i = 0; i < 4; i++) { - priority = (u8)((buf[offset] & I40E_IEEE_ETS_PRIO_1_MASK) >> - I40E_IEEE_ETS_PRIO_1_SHIFT); - dcbcfg->etsrec.prioritytable[i*2] = priority; - priority = (u8)((buf[offset] & I40E_IEEE_ETS_PRIO_0_MASK) >> - I40E_IEEE_ETS_PRIO_0_SHIFT); - dcbcfg->etsrec.prioritytable[i*2 + 1] = priority; + priority = FIELD_GET(I40E_IEEE_ETS_PRIO_1_MASK, buf[offset]); + dcbcfg->etsrec.prioritytable[i * 2] = priority; + priority = FIELD_GET(I40E_IEEE_ETS_PRIO_0_MASK, buf[offset]); + dcbcfg->etsrec.prioritytable[(i * 2) + 1] = priority; offset++; } @@ -170,12 +164,9 @@ static void i40e_parse_ieee_pfccfg_tlv(struct i40e_lldp_org_tlv *tlv, * ----------------------------------------- * |1bit | 1bit|2 bits|4bits| 1 octet | */ - dcbcfg->pfc.willing = (u8)((buf[0] & I40E_IEEE_PFC_WILLING_MASK) >> - I40E_IEEE_PFC_WILLING_SHIFT); - dcbcfg->pfc.mbc = (u8)((buf[0] & I40E_IEEE_PFC_MBC_MASK) >> - I40E_IEEE_PFC_MBC_SHIFT); - dcbcfg->pfc.pfccap = (u8)((buf[0] & I40E_IEEE_PFC_CAP_MASK) >> - I40E_IEEE_PFC_CAP_SHIFT); + dcbcfg->pfc.willing = FIELD_GET(I40E_IEEE_PFC_WILLING_MASK, buf[0]); + dcbcfg->pfc.mbc = FIELD_GET(I40E_IEEE_PFC_MBC_MASK, buf[0]); + dcbcfg->pfc.pfccap = FIELD_GET(I40E_IEEE_PFC_CAP_MASK, buf[0]); dcbcfg->pfc.pfcenable = buf[1]; } @@ -196,8 +187,7 @@ static void i40e_parse_ieee_app_tlv(struct i40e_lldp_org_tlv *tlv, u8 *buf; typelength = ntohs(tlv->typelength); - length = (u16)((typelength & I40E_LLDP_TLV_LEN_MASK) >> - I40E_LLDP_TLV_LEN_SHIFT); + length = FIELD_GET(I40E_LLDP_TLV_LEN_MASK, typelength); buf = tlv->tlvinfo; /* The App priority table starts 5 octets after TLV header */ @@ -215,12 +205,10 @@ static void i40e_parse_ieee_app_tlv(struct i40e_lldp_org_tlv *tlv, * ----------------------------------------- */ while (offset < length) { - dcbcfg->app[i].priority = (u8)((buf[offset] & - I40E_IEEE_APP_PRIO_MASK) >> - I40E_IEEE_APP_PRIO_SHIFT); - dcbcfg->app[i].selector = (u8)((buf[offset] & - I40E_IEEE_APP_SEL_MASK) >> - I40E_IEEE_APP_SEL_SHIFT); + dcbcfg->app[i].priority = FIELD_GET(I40E_IEEE_APP_PRIO_MASK, + buf[offset]); + dcbcfg->app[i].selector = FIELD_GET(I40E_IEEE_APP_SEL_MASK, + buf[offset]); dcbcfg->app[i].protocolid = (buf[offset + 1] << 0x8) | buf[offset + 2]; /* Move to next app */ @@ -248,8 +236,7 @@ static void i40e_parse_ieee_tlv(struct i40e_lldp_org_tlv *tlv, u8 subtype; ouisubtype = ntohl(tlv->ouisubtype); - subtype = (u8)((ouisubtype & I40E_LLDP_TLV_SUBTYPE_MASK) >> - I40E_LLDP_TLV_SUBTYPE_SHIFT); + subtype = FIELD_GET(I40E_LLDP_TLV_SUBTYPE_MASK, ouisubtype); switch (subtype) { case I40E_IEEE_SUBTYPE_ETS_CFG: i40e_parse_ieee_etscfg_tlv(tlv, dcbcfg); @@ -299,11 +286,9 @@ static void i40e_parse_cee_pgcfg_tlv(struct i40e_cee_feat_tlv *tlv, * ----------------------------------------- */ for (i = 0; i < 4; i++) { - priority = (u8)((buf[offset] & I40E_CEE_PGID_PRIO_1_MASK) >> - I40E_CEE_PGID_PRIO_1_SHIFT); - etscfg->prioritytable[i * 2] = priority; - priority = (u8)((buf[offset] & I40E_CEE_PGID_PRIO_0_MASK) >> - I40E_CEE_PGID_PRIO_0_SHIFT); + priority = FIELD_GET(I40E_CEE_PGID_PRIO_1_MASK, buf[offset]); + etscfg->prioritytable[i * 2] = priority; + priority = FIELD_GET(I40E_CEE_PGID_PRIO_0_MASK, buf[offset]); etscfg->prioritytable[i * 2 + 1] = priority; offset++; } @@ -360,8 +345,7 @@ static void i40e_parse_cee_app_tlv(struct i40e_cee_feat_tlv *tlv, u8 i; typelength = ntohs(tlv->hdr.typelen); - length = (u16)((typelength & I40E_LLDP_TLV_LEN_MASK) >> - I40E_LLDP_TLV_LEN_SHIFT); + length = FIELD_GET(I40E_LLDP_TLV_LEN_MASK, typelength); dcbcfg->numapps = length / sizeof(*app); @@ -417,15 +401,13 @@ static void i40e_parse_cee_tlv(struct i40e_lldp_org_tlv *tlv, u32 ouisubtype; ouisubtype = ntohl(tlv->ouisubtype); - subtype = (u8)((ouisubtype & I40E_LLDP_TLV_SUBTYPE_MASK) >> - I40E_LLDP_TLV_SUBTYPE_SHIFT); + subtype = FIELD_GET(I40E_LLDP_TLV_SUBTYPE_MASK, ouisubtype); /* Return if not CEE DCBX */ if (subtype != I40E_CEE_DCBX_TYPE) return; typelength = ntohs(tlv->typelength); - tlvlen = (u16)((typelength & I40E_LLDP_TLV_LEN_MASK) >> - I40E_LLDP_TLV_LEN_SHIFT); + tlvlen = FIELD_GET(I40E_LLDP_TLV_LEN_MASK, typelength); len = sizeof(tlv->typelength) + sizeof(ouisubtype) + sizeof(struct i40e_cee_ctrl_tlv); /* Return if no CEE DCBX Feature TLVs */ @@ -435,11 +417,8 @@ static void i40e_parse_cee_tlv(struct i40e_lldp_org_tlv *tlv, sub_tlv = (struct i40e_cee_feat_tlv *)((char *)tlv + len); while (feat_tlv_count < I40E_CEE_MAX_FEAT_TYPE) { typelength = ntohs(sub_tlv->hdr.typelen); - sublen = (u16)((typelength & - I40E_LLDP_TLV_LEN_MASK) >> - I40E_LLDP_TLV_LEN_SHIFT); - subtype = (u8)((typelength & I40E_LLDP_TLV_TYPE_MASK) >> - I40E_LLDP_TLV_TYPE_SHIFT); + sublen = FIELD_GET(I40E_LLDP_TLV_LEN_MASK, typelength); + subtype = FIELD_GET(I40E_LLDP_TLV_TYPE_MASK, typelength); switch (subtype) { case I40E_CEE_SUBTYPE_PG_CFG: i40e_parse_cee_pgcfg_tlv(sub_tlv, dcbcfg); @@ -476,8 +455,7 @@ static void i40e_parse_org_tlv(struct i40e_lldp_org_tlv *tlv, u32 oui; ouisubtype = ntohl(tlv->ouisubtype); - oui = (u32)((ouisubtype & I40E_LLDP_TLV_OUI_MASK) >> - I40E_LLDP_TLV_OUI_SHIFT); + oui = FIELD_GET(I40E_LLDP_TLV_OUI_MASK, ouisubtype); switch (oui) { case I40E_IEEE_8021QAZ_OUI: i40e_parse_ieee_tlv(tlv, dcbcfg); @@ -515,10 +493,8 @@ int i40e_lldp_to_dcb_config(u8 *lldpmib, tlv = (struct i40e_lldp_org_tlv *)lldpmib; while (1) { typelength = ntohs(tlv->typelength); - type = (u16)((typelength & I40E_LLDP_TLV_TYPE_MASK) >> - I40E_LLDP_TLV_TYPE_SHIFT); - length = (u16)((typelength & I40E_LLDP_TLV_LEN_MASK) >> - I40E_LLDP_TLV_LEN_SHIFT); + type = FIELD_GET(I40E_LLDP_TLV_TYPE_MASK, typelength); + length = FIELD_GET(I40E_LLDP_TLV_LEN_MASK, typelength); offset += sizeof(typelength) + length; /* END TLV or beyond LLDPDU size */ @@ -592,7 +568,7 @@ static void i40e_cee_to_dcb_v1_config( { u16 status, tlv_status = le16_to_cpu(cee_cfg->tlv_status); u16 app_prio = le16_to_cpu(cee_cfg->oper_app_prio); - u8 i, tc, err; + u8 i, err; /* CEE PG data to ETS config */ dcbcfg->etscfg.maxtcs = cee_cfg->oper_num_tc; @@ -601,13 +577,13 @@ static void i40e_cee_to_dcb_v1_config( * from those in the CEE Priority Group sub-TLV. */ for (i = 0; i < 4; i++) { - tc = (u8)((cee_cfg->oper_prio_tc[i] & - I40E_CEE_PGID_PRIO_0_MASK) >> - I40E_CEE_PGID_PRIO_0_SHIFT); - dcbcfg->etscfg.prioritytable[i * 2] = tc; - tc = (u8)((cee_cfg->oper_prio_tc[i] & - I40E_CEE_PGID_PRIO_1_MASK) >> - I40E_CEE_PGID_PRIO_1_SHIFT); + u8 tc; + + tc = FIELD_GET(I40E_CEE_PGID_PRIO_0_MASK, + cee_cfg->oper_prio_tc[i]); + dcbcfg->etscfg.prioritytable[i * 2] = tc; + tc = FIELD_GET(I40E_CEE_PGID_PRIO_1_MASK, + cee_cfg->oper_prio_tc[i]); dcbcfg->etscfg.prioritytable[i*2 + 1] = tc; } @@ -629,8 +605,7 @@ static void i40e_cee_to_dcb_v1_config( dcbcfg->pfc.pfcenable = cee_cfg->oper_pfc_en; dcbcfg->pfc.pfccap = I40E_MAX_TRAFFIC_CLASS; - status = (tlv_status & I40E_AQC_CEE_APP_STATUS_MASK) >> - I40E_AQC_CEE_APP_STATUS_SHIFT; + status = FIELD_GET(I40E_AQC_CEE_APP_STATUS_MASK, tlv_status); err = (status & I40E_TLV_STATUS_ERR) ? 1 : 0; /* Add APPs if Error is False */ if (!err) { @@ -639,22 +614,19 @@ static void i40e_cee_to_dcb_v1_config( /* FCoE APP */ dcbcfg->app[0].priority = - (app_prio & I40E_AQC_CEE_APP_FCOE_MASK) >> - I40E_AQC_CEE_APP_FCOE_SHIFT; + FIELD_GET(I40E_AQC_CEE_APP_FCOE_MASK, app_prio); dcbcfg->app[0].selector = I40E_APP_SEL_ETHTYPE; dcbcfg->app[0].protocolid = I40E_APP_PROTOID_FCOE; /* iSCSI APP */ dcbcfg->app[1].priority = - (app_prio & I40E_AQC_CEE_APP_ISCSI_MASK) >> - I40E_AQC_CEE_APP_ISCSI_SHIFT; + FIELD_GET(I40E_AQC_CEE_APP_ISCSI_MASK, app_prio); dcbcfg->app[1].selector = I40E_APP_SEL_TCPIP; dcbcfg->app[1].protocolid = I40E_APP_PROTOID_ISCSI; /* FIP APP */ dcbcfg->app[2].priority = - (app_prio & I40E_AQC_CEE_APP_FIP_MASK) >> - I40E_AQC_CEE_APP_FIP_SHIFT; + FIELD_GET(I40E_AQC_CEE_APP_FIP_MASK, app_prio); dcbcfg->app[2].selector = I40E_APP_SEL_ETHTYPE; dcbcfg->app[2].protocolid = I40E_APP_PROTOID_FIP; } @@ -673,7 +645,7 @@ static void i40e_cee_to_dcb_config( { u32 status, tlv_status = le32_to_cpu(cee_cfg->tlv_status); u16 app_prio = le16_to_cpu(cee_cfg->oper_app_prio); - u8 i, tc, err, sync, oper; + u8 i, err, sync, oper; /* CEE PG data to ETS config */ dcbcfg->etscfg.maxtcs = cee_cfg->oper_num_tc; @@ -682,13 +654,13 @@ static void i40e_cee_to_dcb_config( * from those in the CEE Priority Group sub-TLV. */ for (i = 0; i < 4; i++) { - tc = (u8)((cee_cfg->oper_prio_tc[i] & - I40E_CEE_PGID_PRIO_0_MASK) >> - I40E_CEE_PGID_PRIO_0_SHIFT); - dcbcfg->etscfg.prioritytable[i * 2] = tc; - tc = (u8)((cee_cfg->oper_prio_tc[i] & - I40E_CEE_PGID_PRIO_1_MASK) >> - I40E_CEE_PGID_PRIO_1_SHIFT); + u8 tc; + + tc = FIELD_GET(I40E_CEE_PGID_PRIO_0_MASK, + cee_cfg->oper_prio_tc[i]); + dcbcfg->etscfg.prioritytable[i * 2] = tc; + tc = FIELD_GET(I40E_CEE_PGID_PRIO_1_MASK, + cee_cfg->oper_prio_tc[i]); dcbcfg->etscfg.prioritytable[i * 2 + 1] = tc; } @@ -711,8 +683,7 @@ static void i40e_cee_to_dcb_config( dcbcfg->pfc.pfccap = I40E_MAX_TRAFFIC_CLASS; i = 0; - status = (tlv_status & I40E_AQC_CEE_FCOE_STATUS_MASK) >> - I40E_AQC_CEE_FCOE_STATUS_SHIFT; + status = FIELD_GET(I40E_AQC_CEE_FCOE_STATUS_MASK, tlv_status); err = (status & I40E_TLV_STATUS_ERR) ? 1 : 0; sync = (status & I40E_TLV_STATUS_SYNC) ? 1 : 0; oper = (status & I40E_TLV_STATUS_OPER) ? 1 : 0; @@ -720,15 +691,13 @@ static void i40e_cee_to_dcb_config( if (!err && sync && oper) { /* FCoE APP */ dcbcfg->app[i].priority = - (app_prio & I40E_AQC_CEE_APP_FCOE_MASK) >> - I40E_AQC_CEE_APP_FCOE_SHIFT; + FIELD_GET(I40E_AQC_CEE_APP_FCOE_MASK, app_prio); dcbcfg->app[i].selector = I40E_APP_SEL_ETHTYPE; dcbcfg->app[i].protocolid = I40E_APP_PROTOID_FCOE; i++; } - status = (tlv_status & I40E_AQC_CEE_ISCSI_STATUS_MASK) >> - I40E_AQC_CEE_ISCSI_STATUS_SHIFT; + status = FIELD_GET(I40E_AQC_CEE_ISCSI_STATUS_MASK, tlv_status); err = (status & I40E_TLV_STATUS_ERR) ? 1 : 0; sync = (status & I40E_TLV_STATUS_SYNC) ? 1 : 0; oper = (status & I40E_TLV_STATUS_OPER) ? 1 : 0; @@ -736,15 +705,13 @@ static void i40e_cee_to_dcb_config( if (!err && sync && oper) { /* iSCSI APP */ dcbcfg->app[i].priority = - (app_prio & I40E_AQC_CEE_APP_ISCSI_MASK) >> - I40E_AQC_CEE_APP_ISCSI_SHIFT; + FIELD_GET(I40E_AQC_CEE_APP_ISCSI_MASK, app_prio); dcbcfg->app[i].selector = I40E_APP_SEL_TCPIP; dcbcfg->app[i].protocolid = I40E_APP_PROTOID_ISCSI; i++; } - status = (tlv_status & I40E_AQC_CEE_FIP_STATUS_MASK) >> - I40E_AQC_CEE_FIP_STATUS_SHIFT; + status = FIELD_GET(I40E_AQC_CEE_FIP_STATUS_MASK, tlv_status); err = (status & I40E_TLV_STATUS_ERR) ? 1 : 0; sync = (status & I40E_TLV_STATUS_SYNC) ? 1 : 0; oper = (status & I40E_TLV_STATUS_OPER) ? 1 : 0; @@ -752,8 +719,7 @@ static void i40e_cee_to_dcb_config( if (!err && sync && oper) { /* FIP APP */ dcbcfg->app[i].priority = - (app_prio & I40E_AQC_CEE_APP_FIP_MASK) >> - I40E_AQC_CEE_APP_FIP_SHIFT; + FIELD_GET(I40E_AQC_CEE_APP_FIP_MASK, app_prio); dcbcfg->app[i].selector = I40E_APP_SEL_ETHTYPE; dcbcfg->app[i].protocolid = I40E_APP_PROTOID_FIP; i++; @@ -1186,7 +1152,7 @@ static void i40e_add_ieee_app_pri_tlv(struct i40e_lldp_org_tlv *tlv, selector = dcbcfg->app[i].selector & 0x7; buf[offset] = (priority << I40E_IEEE_APP_PRIO_SHIFT) | selector; buf[offset + 1] = (dcbcfg->app[i].protocolid >> 0x8) & 0xFF; - buf[offset + 2] = dcbcfg->app[i].protocolid & 0xFF; + buf[offset + 2] = dcbcfg->app[i].protocolid & 0xFF; /* Move to next app */ offset += 3; i++; @@ -1282,8 +1248,7 @@ int i40e_dcb_config_to_lldp(u8 *lldpmib, u16 *miblen, do { i40e_add_dcb_tlv(tlv, dcbcfg, tlvid++); typelength = ntohs(tlv->typelength); - length = (u16)((typelength & I40E_LLDP_TLV_LEN_MASK) >> - I40E_LLDP_TLV_LEN_SHIFT); + length = FIELD_GET(I40E_LLDP_TLV_LEN_MASK, typelength); if (length) offset += length + I40E_IEEE_TLV_HEADER_LENGTH; /* END TLV or beyond LLDPDU size */ @@ -1318,20 +1283,16 @@ void i40e_dcb_hw_rx_fifo_config(struct i40e_hw *hw, u32 reg = rd32(hw, I40E_PRTDCB_RETSC); reg &= ~I40E_PRTDCB_RETSC_ETS_MODE_MASK; - reg |= ((u32)ets_mode << I40E_PRTDCB_RETSC_ETS_MODE_SHIFT) & - I40E_PRTDCB_RETSC_ETS_MODE_MASK; + reg |= FIELD_PREP(I40E_PRTDCB_RETSC_ETS_MODE_MASK, ets_mode); reg &= ~I40E_PRTDCB_RETSC_NON_ETS_MODE_MASK; - reg |= ((u32)non_ets_mode << I40E_PRTDCB_RETSC_NON_ETS_MODE_SHIFT) & - I40E_PRTDCB_RETSC_NON_ETS_MODE_MASK; + reg |= FIELD_PREP(I40E_PRTDCB_RETSC_NON_ETS_MODE_MASK, non_ets_mode); reg &= ~I40E_PRTDCB_RETSC_ETS_MAX_EXP_MASK; - reg |= (max_exponent << I40E_PRTDCB_RETSC_ETS_MAX_EXP_SHIFT) & - I40E_PRTDCB_RETSC_ETS_MAX_EXP_MASK; + reg |= FIELD_PREP(I40E_PRTDCB_RETSC_ETS_MAX_EXP_MASK, max_exponent); reg &= ~I40E_PRTDCB_RETSC_LLTC_MASK; - reg |= (lltc_map << I40E_PRTDCB_RETSC_LLTC_SHIFT) & - I40E_PRTDCB_RETSC_LLTC_MASK; + reg |= FIELD_PREP(I40E_PRTDCB_RETSC_LLTC_MASK, lltc_map); wr32(hw, I40E_PRTDCB_RETSC, reg); } @@ -1386,14 +1347,12 @@ void i40e_dcb_hw_rx_cmd_monitor_config(struct i40e_hw *hw, */ reg = rd32(hw, I40E_PRT_SWR_PM_THR); reg &= ~I40E_PRT_SWR_PM_THR_THRESHOLD_MASK; - reg |= (threshold << I40E_PRT_SWR_PM_THR_THRESHOLD_SHIFT) & - I40E_PRT_SWR_PM_THR_THRESHOLD_MASK; + reg |= FIELD_PREP(I40E_PRT_SWR_PM_THR_THRESHOLD_MASK, threshold); wr32(hw, I40E_PRT_SWR_PM_THR, reg); reg = rd32(hw, I40E_PRTDCB_RPPMC); reg &= ~I40E_PRTDCB_RPPMC_RX_FIFO_SIZE_MASK; - reg |= (fifo_size << I40E_PRTDCB_RPPMC_RX_FIFO_SIZE_SHIFT) & - I40E_PRTDCB_RPPMC_RX_FIFO_SIZE_MASK; + reg |= FIELD_PREP(I40E_PRTDCB_RPPMC_RX_FIFO_SIZE_MASK, fifo_size); wr32(hw, I40E_PRTDCB_RPPMC, reg); } @@ -1435,19 +1394,17 @@ void i40e_dcb_hw_pfc_config(struct i40e_hw *hw, reg &= ~I40E_PRTDCB_MFLCN_RFCE_MASK; reg &= ~I40E_PRTDCB_MFLCN_RPFCE_MASK; if (pfc_en) { - reg |= BIT(I40E_PRTDCB_MFLCN_RPFCM_SHIFT) & - I40E_PRTDCB_MFLCN_RPFCM_MASK; - reg |= ((u32)pfc_en << I40E_PRTDCB_MFLCN_RPFCE_SHIFT) & - I40E_PRTDCB_MFLCN_RPFCE_MASK; + reg |= FIELD_PREP(I40E_PRTDCB_MFLCN_RPFCM_MASK, 1); + reg |= FIELD_PREP(I40E_PRTDCB_MFLCN_RPFCE_MASK, + pfc_en); } wr32(hw, I40E_PRTDCB_MFLCN, reg); reg = rd32(hw, I40E_PRTDCB_FCCFG); reg &= ~I40E_PRTDCB_FCCFG_TFCE_MASK; if (pfc_en) - reg |= (I40E_DCB_PFC_ENABLED << - I40E_PRTDCB_FCCFG_TFCE_SHIFT) & - I40E_PRTDCB_FCCFG_TFCE_MASK; + reg |= FIELD_PREP(I40E_PRTDCB_FCCFG_TFCE_MASK, + I40E_DCB_PFC_ENABLED); wr32(hw, I40E_PRTDCB_FCCFG, reg); /* FCTTV and FCRTV to be set by default */ @@ -1465,25 +1422,22 @@ void i40e_dcb_hw_pfc_config(struct i40e_hw *hw, reg = rd32(hw, I40E_PRTMAC_HSEC_CTL_RX_PAUSE_ENABLE); reg &= ~I40E_PRTMAC_HSEC_CTL_RX_PAUSE_ENABLE_MASK; - reg |= ((u32)pfc_en << - I40E_PRTMAC_HSEC_CTL_RX_PAUSE_ENABLE_SHIFT) & - I40E_PRTMAC_HSEC_CTL_RX_PAUSE_ENABLE_MASK; + reg |= FIELD_PREP(I40E_PRTMAC_HSEC_CTL_RX_PAUSE_ENABLE_MASK, + pfc_en); wr32(hw, I40E_PRTMAC_HSEC_CTL_RX_PAUSE_ENABLE, reg); reg = rd32(hw, I40E_PRTMAC_HSEC_CTL_TX_PAUSE_ENABLE); reg &= ~I40E_PRTMAC_HSEC_CTL_TX_PAUSE_ENABLE_MASK; - reg |= ((u32)pfc_en << - I40E_PRTMAC_HSEC_CTL_TX_PAUSE_ENABLE_SHIFT) & - I40E_PRTMAC_HSEC_CTL_TX_PAUSE_ENABLE_MASK; + reg |= FIELD_PREP(I40E_PRTMAC_HSEC_CTL_TX_PAUSE_ENABLE_MASK, + pfc_en); wr32(hw, I40E_PRTMAC_HSEC_CTL_TX_PAUSE_ENABLE, reg); for (i = 0; i < I40E_PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_MAX_INDEX; i++) { reg = rd32(hw, I40E_PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER(i)); reg &= ~I40E_PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_MASK; if (pfc_en) { - reg |= ((u32)refresh_time << - I40E_PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_SHIFT) & - I40E_PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_MASK; + reg |= FIELD_PREP(I40E_PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_MASK, + refresh_time); } wr32(hw, I40E_PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER(i), reg); } @@ -1495,14 +1449,12 @@ void i40e_dcb_hw_pfc_config(struct i40e_hw *hw, reg = rd32(hw, I40E_PRTDCB_TC2PFC); reg &= ~I40E_PRTDCB_TC2PFC_TC2PFC_MASK; - reg |= ((u32)tc2pfc << I40E_PRTDCB_TC2PFC_TC2PFC_SHIFT) & - I40E_PRTDCB_TC2PFC_TC2PFC_MASK; + reg |= FIELD_PREP(I40E_PRTDCB_TC2PFC_TC2PFC_MASK, tc2pfc); wr32(hw, I40E_PRTDCB_TC2PFC, reg); reg = rd32(hw, I40E_PRTDCB_RUP); reg &= ~I40E_PRTDCB_RUP_NOVLANUP_MASK; - reg |= ((u32)first_pfc_prio << I40E_PRTDCB_RUP_NOVLANUP_SHIFT) & - I40E_PRTDCB_RUP_NOVLANUP_MASK; + reg |= FIELD_PREP(I40E_PRTDCB_RUP_NOVLANUP_MASK, first_pfc_prio); wr32(hw, I40E_PRTDCB_RUP, reg); reg = rd32(hw, I40E_PRTDCB_TDPMC); @@ -1534,8 +1486,7 @@ void i40e_dcb_hw_set_num_tc(struct i40e_hw *hw, u8 num_tc) u32 reg = rd32(hw, I40E_PRTDCB_GENC); reg &= ~I40E_PRTDCB_GENC_NUMTC_MASK; - reg |= ((u32)num_tc << I40E_PRTDCB_GENC_NUMTC_SHIFT) & - I40E_PRTDCB_GENC_NUMTC_MASK; + reg |= FIELD_PREP(I40E_PRTDCB_GENC_NUMTC_MASK, num_tc); wr32(hw, I40E_PRTDCB_GENC, reg); } @@ -1549,8 +1500,7 @@ u8 i40e_dcb_hw_get_num_tc(struct i40e_hw *hw) { u32 reg = rd32(hw, I40E_PRTDCB_GENC); - return (u8)((reg & I40E_PRTDCB_GENC_NUMTC_MASK) >> - I40E_PRTDCB_GENC_NUMTC_SHIFT); + return FIELD_GET(I40E_PRTDCB_GENC_NUMTC_MASK, reg); } /** @@ -1574,12 +1524,12 @@ void i40e_dcb_hw_rx_ets_bw_config(struct i40e_hw *hw, u8 *bw_share, reg &= ~(I40E_PRTDCB_RETSTCC_BWSHARE_MASK | I40E_PRTDCB_RETSTCC_UPINTC_MODE_MASK | I40E_PRTDCB_RETSTCC_ETSTC_SHIFT); - reg |= ((u32)bw_share[i] << I40E_PRTDCB_RETSTCC_BWSHARE_SHIFT) & - I40E_PRTDCB_RETSTCC_BWSHARE_MASK; - reg |= ((u32)mode[i] << I40E_PRTDCB_RETSTCC_UPINTC_MODE_SHIFT) & - I40E_PRTDCB_RETSTCC_UPINTC_MODE_MASK; - reg |= ((u32)prio_type[i] << I40E_PRTDCB_RETSTCC_ETSTC_SHIFT) & - I40E_PRTDCB_RETSTCC_ETSTC_MASK; + reg |= FIELD_PREP(I40E_PRTDCB_RETSTCC_BWSHARE_MASK, + bw_share[i]); + reg |= FIELD_PREP(I40E_PRTDCB_RETSTCC_UPINTC_MODE_MASK, + mode[i]); + reg |= FIELD_PREP(I40E_PRTDCB_RETSTCC_ETSTC_MASK, + prio_type[i]); wr32(hw, I40E_PRTDCB_RETSTCC(i), reg); } } @@ -1719,8 +1669,7 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw, if (new_val < old_val) { reg = rd32(hw, I40E_PRTRPB_SLW); reg &= ~I40E_PRTRPB_SLW_SLW_MASK; - reg |= (new_val << I40E_PRTRPB_SLW_SLW_SHIFT) & - I40E_PRTRPB_SLW_SLW_MASK; + reg |= FIELD_PREP(I40E_PRTRPB_SLW_SLW_MASK, new_val); wr32(hw, I40E_PRTRPB_SLW, reg); } @@ -1733,8 +1682,8 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw, if (new_val < old_val) { reg = rd32(hw, I40E_PRTRPB_SLT(i)); reg &= ~I40E_PRTRPB_SLT_SLT_TCN_MASK; - reg |= (new_val << I40E_PRTRPB_SLT_SLT_TCN_SHIFT) & - I40E_PRTRPB_SLT_SLT_TCN_MASK; + reg |= FIELD_PREP(I40E_PRTRPB_SLT_SLT_TCN_MASK, + new_val); wr32(hw, I40E_PRTRPB_SLT(i), reg); } @@ -1743,8 +1692,8 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw, if (new_val < old_val) { reg = rd32(hw, I40E_PRTRPB_DLW(i)); reg &= ~I40E_PRTRPB_DLW_DLW_TCN_MASK; - reg |= (new_val << I40E_PRTRPB_DLW_DLW_TCN_SHIFT) & - I40E_PRTRPB_DLW_DLW_TCN_MASK; + reg |= FIELD_PREP(I40E_PRTRPB_DLW_DLW_TCN_MASK, + new_val); wr32(hw, I40E_PRTRPB_DLW(i), reg); } } @@ -1755,8 +1704,7 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw, if (new_val < old_val) { reg = rd32(hw, I40E_PRTRPB_SHW); reg &= ~I40E_PRTRPB_SHW_SHW_MASK; - reg |= (new_val << I40E_PRTRPB_SHW_SHW_SHIFT) & - I40E_PRTRPB_SHW_SHW_MASK; + reg |= FIELD_PREP(I40E_PRTRPB_SHW_SHW_MASK, new_val); wr32(hw, I40E_PRTRPB_SHW, reg); } @@ -1769,8 +1717,8 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw, if (new_val < old_val) { reg = rd32(hw, I40E_PRTRPB_SHT(i)); reg &= ~I40E_PRTRPB_SHT_SHT_TCN_MASK; - reg |= (new_val << I40E_PRTRPB_SHT_SHT_TCN_SHIFT) & - I40E_PRTRPB_SHT_SHT_TCN_MASK; + reg |= FIELD_PREP(I40E_PRTRPB_SHT_SHT_TCN_MASK, + new_val); wr32(hw, I40E_PRTRPB_SHT(i), reg); } @@ -1779,8 +1727,8 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw, if (new_val < old_val) { reg = rd32(hw, I40E_PRTRPB_DHW(i)); reg &= ~I40E_PRTRPB_DHW_DHW_TCN_MASK; - reg |= (new_val << I40E_PRTRPB_DHW_DHW_TCN_SHIFT) & - I40E_PRTRPB_DHW_DHW_TCN_MASK; + reg |= FIELD_PREP(I40E_PRTRPB_DHW_DHW_TCN_MASK, + new_val); wr32(hw, I40E_PRTRPB_DHW(i), reg); } } @@ -1790,8 +1738,7 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw, new_val = new_pb_cfg->tc_pool_size[i]; reg = rd32(hw, I40E_PRTRPB_DPS(i)); reg &= ~I40E_PRTRPB_DPS_DPS_TCN_MASK; - reg |= (new_val << I40E_PRTRPB_DPS_DPS_TCN_SHIFT) & - I40E_PRTRPB_DPS_DPS_TCN_MASK; + reg |= FIELD_PREP(I40E_PRTRPB_DPS_DPS_TCN_MASK, new_val); wr32(hw, I40E_PRTRPB_DPS(i), reg); } @@ -1799,8 +1746,7 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw, new_val = new_pb_cfg->shared_pool_size; reg = rd32(hw, I40E_PRTRPB_SPS); reg &= ~I40E_PRTRPB_SPS_SPS_MASK; - reg |= (new_val << I40E_PRTRPB_SPS_SPS_SHIFT) & - I40E_PRTRPB_SPS_SPS_MASK; + reg |= FIELD_PREP(I40E_PRTRPB_SPS_SPS_MASK, new_val); wr32(hw, I40E_PRTRPB_SPS, reg); /* Program the shared pool low water mark per port if increasing */ @@ -1809,8 +1755,7 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw, if (new_val > old_val) { reg = rd32(hw, I40E_PRTRPB_SLW); reg &= ~I40E_PRTRPB_SLW_SLW_MASK; - reg |= (new_val << I40E_PRTRPB_SLW_SLW_SHIFT) & - I40E_PRTRPB_SLW_SLW_MASK; + reg |= FIELD_PREP(I40E_PRTRPB_SLW_SLW_MASK, new_val); wr32(hw, I40E_PRTRPB_SLW, reg); } @@ -1823,8 +1768,8 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw, if (new_val > old_val) { reg = rd32(hw, I40E_PRTRPB_SLT(i)); reg &= ~I40E_PRTRPB_SLT_SLT_TCN_MASK; - reg |= (new_val << I40E_PRTRPB_SLT_SLT_TCN_SHIFT) & - I40E_PRTRPB_SLT_SLT_TCN_MASK; + reg |= FIELD_PREP(I40E_PRTRPB_SLT_SLT_TCN_MASK, + new_val); wr32(hw, I40E_PRTRPB_SLT(i), reg); } @@ -1833,8 +1778,8 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw, if (new_val > old_val) { reg = rd32(hw, I40E_PRTRPB_DLW(i)); reg &= ~I40E_PRTRPB_DLW_DLW_TCN_MASK; - reg |= (new_val << I40E_PRTRPB_DLW_DLW_TCN_SHIFT) & - I40E_PRTRPB_DLW_DLW_TCN_MASK; + reg |= FIELD_PREP(I40E_PRTRPB_DLW_DLW_TCN_MASK, + new_val); wr32(hw, I40E_PRTRPB_DLW(i), reg); } } @@ -1845,8 +1790,7 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw, if (new_val > old_val) { reg = rd32(hw, I40E_PRTRPB_SHW); reg &= ~I40E_PRTRPB_SHW_SHW_MASK; - reg |= (new_val << I40E_PRTRPB_SHW_SHW_SHIFT) & - I40E_PRTRPB_SHW_SHW_MASK; + reg |= FIELD_PREP(I40E_PRTRPB_SHW_SHW_MASK, new_val); wr32(hw, I40E_PRTRPB_SHW, reg); } @@ -1859,8 +1803,8 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw, if (new_val > old_val) { reg = rd32(hw, I40E_PRTRPB_SHT(i)); reg &= ~I40E_PRTRPB_SHT_SHT_TCN_MASK; - reg |= (new_val << I40E_PRTRPB_SHT_SHT_TCN_SHIFT) & - I40E_PRTRPB_SHT_SHT_TCN_MASK; + reg |= FIELD_PREP(I40E_PRTRPB_SHT_SHT_TCN_MASK, + new_val); wr32(hw, I40E_PRTRPB_SHT(i), reg); } @@ -1869,8 +1813,8 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw, if (new_val > old_val) { reg = rd32(hw, I40E_PRTRPB_DHW(i)); reg &= ~I40E_PRTRPB_DHW_DHW_TCN_MASK; - reg |= (new_val << I40E_PRTRPB_DHW_DHW_TCN_SHIFT) & - I40E_PRTRPB_DHW_DHW_TCN_MASK; + reg |= FIELD_PREP(I40E_PRTRPB_DHW_DHW_TCN_MASK, + new_val); wr32(hw, I40E_PRTRPB_DHW(i), reg); } } diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c b/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c index 4721845fda6e..b96a92187ab3 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c +++ b/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c @@ -21,8 +21,7 @@ static void i40e_get_pfc_delay(struct i40e_hw *hw, u16 *delay) u32 val; val = rd32(hw, I40E_PRTDCB_GENC); - *delay = (u16)((val & I40E_PRTDCB_GENC_PFCLDA_MASK) >> - I40E_PRTDCB_GENC_PFCLDA_SHIFT); + *delay = FIELD_GET(I40E_PRTDCB_GENC_PFCLDA_MASK, val); } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_ddp.c b/drivers/net/ethernet/intel/i40e/i40e_ddp.c index cf25bfc5dc3f..2f53f0f53bc3 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ddp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ddp.c @@ -81,8 +81,8 @@ static int i40e_ddp_does_profile_exist(struct i40e_hw *hw, static bool i40e_ddp_profiles_overlap(struct i40e_profile_info *new, struct i40e_profile_info *old) { - unsigned int group_id_old = (u8)((old->track_id & 0x00FF0000) >> 16); - unsigned int group_id_new = (u8)((new->track_id & 0x00FF0000) >> 16); + unsigned int group_id_old = FIELD_GET(0x00FF0000, old->track_id); + unsigned int group_id_new = FIELD_GET(0x00FF0000, new->track_id); /* 0x00 group must be only the first */ if (group_id_new == 0) diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 26778c448090..8cc5697e2109 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -1952,9 +1952,8 @@ static int i40e_get_eeprom_len(struct net_device *netdev) val = X722_EEPROM_SCOPE_LIMIT + 1; return val; } - val = (rd32(hw, I40E_GLPCI_LBARCTRL) - & I40E_GLPCI_LBARCTRL_FL_SIZE_MASK) - >> I40E_GLPCI_LBARCTRL_FL_SIZE_SHIFT; + val = FIELD_GET(I40E_GLPCI_LBARCTRL_FL_SIZE_MASK, + rd32(hw, I40E_GLPCI_LBARCTRL)); /* register returns value in power of 2, 64Kbyte chunks. */ val = (64 * 1024) * BIT(val); return val; @@ -3284,7 +3283,7 @@ static int i40e_parse_rx_flow_user_data(struct ethtool_rx_flow_spec *fsp, } else if (valid) { data->flex_word = value & I40E_USERDEF_FLEX_WORD; data->flex_offset = - (value & I40E_USERDEF_FLEX_OFFSET) >> 16; + FIELD_GET(I40E_USERDEF_FLEX_OFFSET, value); data->flex_filter = true; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index dc642efe1cfa..6be281a8727f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1197,11 +1197,9 @@ static void i40e_update_pf_stats(struct i40e_pf *pf) val = rd32(hw, I40E_PRTPM_EEE_STAT); nsd->tx_lpi_status = - (val & I40E_PRTPM_EEE_STAT_TX_LPI_STATUS_MASK) >> - I40E_PRTPM_EEE_STAT_TX_LPI_STATUS_SHIFT; + FIELD_GET(I40E_PRTPM_EEE_STAT_TX_LPI_STATUS_MASK, val); nsd->rx_lpi_status = - (val & I40E_PRTPM_EEE_STAT_RX_LPI_STATUS_MASK) >> - I40E_PRTPM_EEE_STAT_RX_LPI_STATUS_SHIFT; + FIELD_GET(I40E_PRTPM_EEE_STAT_RX_LPI_STATUS_MASK, val); i40e_stat_update32(hw, I40E_PRTPM_TLPIC, pf->stat_offsets_loaded, &osd->tx_lpi_count, &nsd->tx_lpi_count); @@ -3536,21 +3534,19 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring) else return -EINVAL; - qtx_ctl |= (ring->ch->vsi_number << - I40E_QTX_CTL_VFVM_INDX_SHIFT) & - I40E_QTX_CTL_VFVM_INDX_MASK; + qtx_ctl |= FIELD_PREP(I40E_QTX_CTL_VFVM_INDX_MASK, + ring->ch->vsi_number); } else { if (vsi->type == I40E_VSI_VMDQ2) { qtx_ctl = I40E_QTX_CTL_VM_QUEUE; - qtx_ctl |= ((vsi->id) << I40E_QTX_CTL_VFVM_INDX_SHIFT) & - I40E_QTX_CTL_VFVM_INDX_MASK; + qtx_ctl |= FIELD_PREP(I40E_QTX_CTL_VFVM_INDX_MASK, + vsi->id); } else { qtx_ctl = I40E_QTX_CTL_PF_QUEUE; } } - qtx_ctl |= ((hw->pf_id << I40E_QTX_CTL_PF_INDX_SHIFT) & - I40E_QTX_CTL_PF_INDX_MASK); + qtx_ctl |= FIELD_PREP(I40E_QTX_CTL_PF_INDX_MASK, hw->pf_id); wr32(hw, I40E_QTX_CTL(pf_q), qtx_ctl); i40e_flush(hw); @@ -4342,8 +4338,7 @@ static irqreturn_t i40e_intr(int irq, void *data) set_bit(__I40E_RESET_INTR_RECEIVED, pf->state); ena_mask &= ~I40E_PFINT_ICR0_ENA_GRST_MASK; val = rd32(hw, I40E_GLGEN_RSTAT); - val = (val & I40E_GLGEN_RSTAT_RESET_TYPE_MASK) - >> I40E_GLGEN_RSTAT_RESET_TYPE_SHIFT; + val = FIELD_GET(I40E_GLGEN_RSTAT_RESET_TYPE_MASK, val); if (val == I40E_RESET_CORER) { pf->corer_count++; } else if (val == I40E_RESET_GLOBR) { @@ -5005,8 +5000,8 @@ static void i40e_vsi_free_irq(struct i40e_vsi *vsi) * next_q field of the registers. */ val = rd32(hw, I40E_PFINT_LNKLSTN(vector - 1)); - qp = (val & I40E_PFINT_LNKLSTN_FIRSTQ_INDX_MASK) - >> I40E_PFINT_LNKLSTN_FIRSTQ_INDX_SHIFT; + qp = FIELD_GET(I40E_PFINT_LNKLSTN_FIRSTQ_INDX_MASK, + val); val |= I40E_QUEUE_END_OF_LIST << I40E_PFINT_LNKLSTN_FIRSTQ_INDX_SHIFT; wr32(hw, I40E_PFINT_LNKLSTN(vector - 1), val); @@ -5028,8 +5023,8 @@ static void i40e_vsi_free_irq(struct i40e_vsi *vsi) val = rd32(hw, I40E_QINT_TQCTL(qp)); - next = (val & I40E_QINT_TQCTL_NEXTQ_INDX_MASK) - >> I40E_QINT_TQCTL_NEXTQ_INDX_SHIFT; + next = FIELD_GET(I40E_QINT_TQCTL_NEXTQ_INDX_MASK, + val); val &= ~(I40E_QINT_TQCTL_MSIX_INDX_MASK | I40E_QINT_TQCTL_MSIX0_INDX_MASK | @@ -5047,8 +5042,7 @@ static void i40e_vsi_free_irq(struct i40e_vsi *vsi) free_irq(pf->pdev->irq, pf); val = rd32(hw, I40E_PFINT_LNKLST0); - qp = (val & I40E_PFINT_LNKLSTN_FIRSTQ_INDX_MASK) - >> I40E_PFINT_LNKLSTN_FIRSTQ_INDX_SHIFT; + qp = FIELD_GET(I40E_PFINT_LNKLSTN_FIRSTQ_INDX_MASK, val); val |= I40E_QUEUE_END_OF_LIST << I40E_PFINT_LNKLST0_FIRSTQ_INDX_SHIFT; wr32(hw, I40E_PFINT_LNKLST0, val); @@ -9551,18 +9545,18 @@ static void i40e_handle_lan_overflow_event(struct i40e_pf *pf, dev_dbg(&pf->pdev->dev, "overflow Rx Queue Number = %d QTX_CTL=0x%08x\n", queue, qtx_ctl); + if (FIELD_GET(I40E_QTX_CTL_PFVF_Q_MASK, qtx_ctl) != + I40E_QTX_CTL_VF_QUEUE) + return; + /* Queue belongs to VF, find the VF and issue VF reset */ - if (((qtx_ctl & I40E_QTX_CTL_PFVF_Q_MASK) - >> I40E_QTX_CTL_PFVF_Q_SHIFT) == I40E_QTX_CTL_VF_QUEUE) { - vf_id = (u16)((qtx_ctl & I40E_QTX_CTL_VFVM_INDX_MASK) - >> I40E_QTX_CTL_VFVM_INDX_SHIFT); - vf_id -= hw->func_caps.vf_base_id; - vf = &pf->vf[vf_id]; - i40e_vc_notify_vf_reset(vf); - /* Allow VF to process pending reset notification */ - msleep(20); - i40e_reset_vf(vf, false); - } + vf_id = FIELD_GET(I40E_QTX_CTL_VFVM_INDX_MASK, qtx_ctl); + vf_id -= hw->func_caps.vf_base_id; + vf = &pf->vf[vf_id]; + i40e_vc_notify_vf_reset(vf); + /* Allow VF to process pending reset notification */ + msleep(20); + i40e_reset_vf(vf, false); } /** @@ -9588,8 +9582,7 @@ u32 i40e_get_current_fd_count(struct i40e_pf *pf) val = rd32(&pf->hw, I40E_PFQF_FDSTAT); fcnt_prog = (val & I40E_PFQF_FDSTAT_GUARANT_CNT_MASK) + - ((val & I40E_PFQF_FDSTAT_BEST_CNT_MASK) >> - I40E_PFQF_FDSTAT_BEST_CNT_SHIFT); + FIELD_GET(I40E_PFQF_FDSTAT_BEST_CNT_MASK, val); return fcnt_prog; } @@ -9603,8 +9596,7 @@ u32 i40e_get_global_fd_count(struct i40e_pf *pf) val = rd32(&pf->hw, I40E_GLQF_FDCNT_0); fcnt_prog = (val & I40E_GLQF_FDCNT_0_GUARANT_CNT_MASK) + - ((val & I40E_GLQF_FDCNT_0_BESTCNT_MASK) >> - I40E_GLQF_FDCNT_0_BESTCNT_SHIFT); + FIELD_GET(I40E_GLQF_FDCNT_0_BESTCNT_MASK, val); return fcnt_prog; } @@ -11186,14 +11178,10 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf) /* find what triggered the MDD event */ reg = rd32(hw, I40E_GL_MDET_TX); if (reg & I40E_GL_MDET_TX_VALID_MASK) { - u8 pf_num = (reg & I40E_GL_MDET_TX_PF_NUM_MASK) >> - I40E_GL_MDET_TX_PF_NUM_SHIFT; - u16 vf_num = (reg & I40E_GL_MDET_TX_VF_NUM_MASK) >> - I40E_GL_MDET_TX_VF_NUM_SHIFT; - u8 event = (reg & I40E_GL_MDET_TX_EVENT_MASK) >> - I40E_GL_MDET_TX_EVENT_SHIFT; - u16 queue = ((reg & I40E_GL_MDET_TX_QUEUE_MASK) >> - I40E_GL_MDET_TX_QUEUE_SHIFT) - + u8 pf_num = FIELD_GET(I40E_GL_MDET_TX_PF_NUM_MASK, reg); + u16 vf_num = FIELD_GET(I40E_GL_MDET_TX_VF_NUM_MASK, reg); + u8 event = FIELD_GET(I40E_GL_MDET_TX_EVENT_MASK, reg); + u16 queue = FIELD_GET(I40E_GL_MDET_TX_QUEUE_MASK, reg) - pf->hw.func_caps.base_queue; if (netif_msg_tx_err(pf)) dev_info(&pf->pdev->dev, "Malicious Driver Detection event 0x%02x on TX queue %d PF number 0x%02x VF number 0x%02x\n", @@ -11203,12 +11191,9 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf) } reg = rd32(hw, I40E_GL_MDET_RX); if (reg & I40E_GL_MDET_RX_VALID_MASK) { - u8 func = (reg & I40E_GL_MDET_RX_FUNCTION_MASK) >> - I40E_GL_MDET_RX_FUNCTION_SHIFT; - u8 event = (reg & I40E_GL_MDET_RX_EVENT_MASK) >> - I40E_GL_MDET_RX_EVENT_SHIFT; - u16 queue = ((reg & I40E_GL_MDET_RX_QUEUE_MASK) >> - I40E_GL_MDET_RX_QUEUE_SHIFT) - + u8 func = FIELD_GET(I40E_GL_MDET_RX_FUNCTION_MASK, reg); + u8 event = FIELD_GET(I40E_GL_MDET_RX_EVENT_MASK, reg); + u16 queue = FIELD_GET(I40E_GL_MDET_RX_QUEUE_MASK, reg) - pf->hw.func_caps.base_queue; if (netif_msg_rx_err(pf)) dev_info(&pf->pdev->dev, "Malicious Driver Detection event 0x%02x on RX queue %d of function 0x%02x\n", @@ -16172,8 +16157,8 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* make sure the MFS hasn't been set lower than the default */ #define MAX_FRAME_SIZE_DEFAULT 0x2600 - val = (rd32(&pf->hw, I40E_PRTGL_SAH) & - I40E_PRTGL_SAH_MFS_MASK) >> I40E_PRTGL_SAH_MFS_SHIFT; + val = FIELD_GET(I40E_PRTGL_SAH_MFS_MASK, + rd32(&pf->hw, I40E_PRTGL_SAH)); if (val < MAX_FRAME_SIZE_DEFAULT) dev_warn(&pdev->dev, "MFS for port %x has been set below the default: %x\n", pf->hw.port, val); diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c index 62eb34871094..605fd82f5d20 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c +++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2018 Intel Corporation. */ +#include <linux/bitfield.h> #include <linux/delay.h> #include "i40e_alloc.h" #include "i40e_prototype.h" @@ -26,8 +27,7 @@ int i40e_init_nvm(struct i40e_hw *hw) * as the blank mode may be used in the factory line. */ gens = rd32(hw, I40E_GLNVM_GENS); - sr_size = ((gens & I40E_GLNVM_GENS_SR_SIZE_MASK) >> - I40E_GLNVM_GENS_SR_SIZE_SHIFT); + sr_size = FIELD_GET(I40E_GLNVM_GENS_SR_SIZE_MASK, gens); /* Switching to words (sr_size contains power of 2KB) */ nvm->sr_size = BIT(sr_size) * I40E_SR_WORDS_IN_1KB; @@ -193,9 +193,8 @@ static int i40e_read_nvm_word_srctl(struct i40e_hw *hw, u16 offset, ret_code = i40e_poll_sr_srctl_done_bit(hw); if (!ret_code) { sr_reg = rd32(hw, I40E_GLNVM_SRDATA); - *data = (u16)((sr_reg & - I40E_GLNVM_SRDATA_RDDATA_MASK) - >> I40E_GLNVM_SRDATA_RDDATA_SHIFT); + *data = FIELD_GET(I40E_GLNVM_SRDATA_RDDATA_MASK, + sr_reg); } } if (ret_code) @@ -771,13 +770,12 @@ static inline u8 i40e_nvmupd_get_module(u32 val) } static inline u8 i40e_nvmupd_get_transaction(u32 val) { - return (u8)((val & I40E_NVM_TRANS_MASK) >> I40E_NVM_TRANS_SHIFT); + return FIELD_GET(I40E_NVM_TRANS_MASK, val); } static inline u8 i40e_nvmupd_get_preservation_flags(u32 val) { - return (u8)((val & I40E_NVM_PRESERVATION_FLAGS_MASK) >> - I40E_NVM_PRESERVATION_FLAGS_SHIFT); + return FIELD_GET(I40E_NVM_PRESERVATION_FLAGS_MASK, val); } static const char * const i40e_nvm_update_state_str[] = { diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index 1cf993a79438..e7ebcb09f23c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -1480,8 +1480,8 @@ void i40e_ptp_init(struct i40e_pf *pf) /* Only one PF is assigned to control 1588 logic per port. Do not * enable any support for PFs not assigned via PRTTSYN_CTL0.PF_ID */ - pf_id = (rd32(hw, I40E_PRTTSYN_CTL0) & I40E_PRTTSYN_CTL0_PF_ID_MASK) >> - I40E_PRTTSYN_CTL0_PF_ID_SHIFT; + pf_id = FIELD_GET(I40E_PRTTSYN_CTL0_PF_ID_MASK, + rd32(hw, I40E_PRTTSYN_CTL0)); if (hw->pf_id != pf_id) { clear_bit(I40E_FLAG_PTP_ENA, pf->flags); dev_info(&pf->pdev->dev, "%s: PTP not supported on %s\n", diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index b82df5bdfac0..971ba3322038 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -33,19 +33,16 @@ static void i40e_fdir(struct i40e_ring *tx_ring, i++; tx_ring->next_to_use = (i < tx_ring->count) ? i : 0; - flex_ptype = I40E_TXD_FLTR_QW0_QINDEX_MASK & - (fdata->q_index << I40E_TXD_FLTR_QW0_QINDEX_SHIFT); + flex_ptype = FIELD_PREP(I40E_TXD_FLTR_QW0_QINDEX_MASK, fdata->q_index); - flex_ptype |= I40E_TXD_FLTR_QW0_FLEXOFF_MASK & - (fdata->flex_off << I40E_TXD_FLTR_QW0_FLEXOFF_SHIFT); + flex_ptype |= FIELD_PREP(I40E_TXD_FLTR_QW0_FLEXOFF_MASK, + fdata->flex_off); - flex_ptype |= I40E_TXD_FLTR_QW0_PCTYPE_MASK & - (fdata->pctype << I40E_TXD_FLTR_QW0_PCTYPE_SHIFT); + flex_ptype |= FIELD_PREP(I40E_TXD_FLTR_QW0_PCTYPE_MASK, fdata->pctype); /* Use LAN VSI Id if not programmed by user */ - flex_ptype |= I40E_TXD_FLTR_QW0_DEST_VSI_MASK & - ((u32)(fdata->dest_vsi ? : pf->vsi[pf->lan_vsi]->id) << - I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT); + flex_ptype |= FIELD_PREP(I40E_TXD_FLTR_QW0_DEST_VSI_MASK, + fdata->dest_vsi ? : pf->vsi[pf->lan_vsi]->id); dtype_cmd = I40E_TX_DESC_DTYPE_FILTER_PROG; @@ -55,17 +52,15 @@ static void i40e_fdir(struct i40e_ring *tx_ring, I40E_FILTER_PROGRAM_DESC_PCMD_REMOVE << I40E_TXD_FLTR_QW1_PCMD_SHIFT; - dtype_cmd |= I40E_TXD_FLTR_QW1_DEST_MASK & - (fdata->dest_ctl << I40E_TXD_FLTR_QW1_DEST_SHIFT); + dtype_cmd |= FIELD_PREP(I40E_TXD_FLTR_QW1_DEST_MASK, fdata->dest_ctl); - dtype_cmd |= I40E_TXD_FLTR_QW1_FD_STATUS_MASK & - (fdata->fd_status << I40E_TXD_FLTR_QW1_FD_STATUS_SHIFT); + dtype_cmd |= FIELD_PREP(I40E_TXD_FLTR_QW1_FD_STATUS_MASK, + fdata->fd_status); if (fdata->cnt_index) { dtype_cmd |= I40E_TXD_FLTR_QW1_CNT_ENA_MASK; - dtype_cmd |= I40E_TXD_FLTR_QW1_CNTINDEX_MASK & - ((u32)fdata->cnt_index << - I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT); + dtype_cmd |= FIELD_PREP(I40E_TXD_FLTR_QW1_CNTINDEX_MASK, + fdata->cnt_index); } fdir_desc->qindex_flex_ptype_vsi = cpu_to_le32(flex_ptype); @@ -691,8 +686,7 @@ static void i40e_fd_handle_status(struct i40e_ring *rx_ring, u64 qword0_raw, u32 error; qw0 = (struct i40e_16b_rx_wb_qw0 *)&qword0_raw; - error = (qword1 & I40E_RX_PROG_STATUS_DESC_QW1_ERROR_MASK) >> - I40E_RX_PROG_STATUS_DESC_QW1_ERROR_SHIFT; + error = FIELD_GET(I40E_RX_PROG_STATUS_DESC_QW1_ERROR_MASK, qword1); if (error == BIT(I40E_RX_PROG_STATUS_DESC_FD_TBL_FULL_SHIFT)) { pf->fd_inv = le32_to_cpu(qw0->hi_dword.fd_id); @@ -1403,8 +1397,7 @@ void i40e_clean_programming_status(struct i40e_ring *rx_ring, u64 qword0_raw, { u8 id; - id = (qword1 & I40E_RX_PROG_STATUS_DESC_QW1_PROGID_MASK) >> - I40E_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT; + id = FIELD_GET(I40E_RX_PROG_STATUS_DESC_QW1_PROGID_MASK, qword1); if (id == I40E_RX_PROG_STATUS_DESC_FD_FILTER_STATUS) i40e_fd_handle_status(rx_ring, qword0_raw, qword1, id); @@ -1764,11 +1757,9 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi, u64 qword; qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >> I40E_RXD_QW1_PTYPE_SHIFT; - rx_error = (qword & I40E_RXD_QW1_ERROR_MASK) >> - I40E_RXD_QW1_ERROR_SHIFT; - rx_status = (qword & I40E_RXD_QW1_STATUS_MASK) >> - I40E_RXD_QW1_STATUS_SHIFT; + ptype = FIELD_GET(I40E_RXD_QW1_PTYPE_MASK, qword); + rx_error = FIELD_GET(I40E_RXD_QW1_ERROR_MASK, qword); + rx_status = FIELD_GET(I40E_RXD_QW1_STATUS_MASK, qword); decoded = decode_rx_desc_ptype(ptype); skb->ip_summed = CHECKSUM_NONE; @@ -1901,13 +1892,10 @@ void i40e_process_skb_fields(struct i40e_ring *rx_ring, union i40e_rx_desc *rx_desc, struct sk_buff *skb) { u64 qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - u32 rx_status = (qword & I40E_RXD_QW1_STATUS_MASK) >> - I40E_RXD_QW1_STATUS_SHIFT; + u32 rx_status = FIELD_GET(I40E_RXD_QW1_STATUS_MASK, qword); u32 tsynvalid = rx_status & I40E_RXD_QW1_STATUS_TSYNVALID_MASK; - u32 tsyn = (rx_status & I40E_RXD_QW1_STATUS_TSYNINDX_MASK) >> - I40E_RXD_QW1_STATUS_TSYNINDX_SHIFT; - u8 rx_ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >> - I40E_RXD_QW1_PTYPE_SHIFT; + u32 tsyn = FIELD_GET(I40E_RXD_QW1_STATUS_TSYNINDX_MASK, rx_status); + u8 rx_ptype = FIELD_GET(I40E_RXD_QW1_PTYPE_MASK, qword); if (unlikely(tsynvalid)) i40e_ptp_rx_hwtstamp(rx_ring->vsi->back, skb, tsyn); @@ -2554,8 +2542,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget, continue; } - size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >> - I40E_RXD_QW1_LENGTH_PBUF_SHIFT; + size = FIELD_GET(I40E_RXD_QW1_LENGTH_PBUF_MASK, qword); if (!size) break; @@ -2959,8 +2946,8 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb, i++; tx_ring->next_to_use = (i < tx_ring->count) ? i : 0; - flex_ptype = (tx_ring->queue_index << I40E_TXD_FLTR_QW0_QINDEX_SHIFT) & - I40E_TXD_FLTR_QW0_QINDEX_MASK; + flex_ptype = FIELD_PREP(I40E_TXD_FLTR_QW0_QINDEX_MASK, + tx_ring->queue_index); flex_ptype |= (tx_flags & I40E_TX_FLAGS_IPV4) ? (I40E_FILTER_PCTYPE_NONF_IPV4_TCP << I40E_TXD_FLTR_QW0_PCTYPE_SHIFT) : @@ -2986,14 +2973,12 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb, dtype_cmd |= I40E_TXD_FLTR_QW1_CNT_ENA_MASK; if (!(tx_flags & I40E_TX_FLAGS_UDP_TUNNEL)) dtype_cmd |= - ((u32)I40E_FD_ATR_STAT_IDX(pf->hw.pf_id) << - I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT) & - I40E_TXD_FLTR_QW1_CNTINDEX_MASK; + FIELD_PREP(I40E_TXD_FLTR_QW1_CNTINDEX_MASK, + I40E_FD_ATR_STAT_IDX(pf->hw.pf_id)); else dtype_cmd |= - ((u32)I40E_FD_ATR_TUNNEL_STAT_IDX(pf->hw.pf_id) << - I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT) & - I40E_TXD_FLTR_QW1_CNTINDEX_MASK; + FIELD_PREP(I40E_TXD_FLTR_QW1_CNTINDEX_MASK, + I40E_FD_ATR_TUNNEL_STAT_IDX(pf->hw.pf_id)); if (test_bit(I40E_FLAG_HW_ATR_EVICT_ENA, pf->flags)) dtype_cmd |= I40E_TXD_FLTR_QW1_ATR_MASK; @@ -3601,8 +3586,7 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, if (tx_flags & I40E_TX_FLAGS_HW_VLAN) { td_cmd |= I40E_TX_DESC_CMD_IL2TAG1; - td_tag = (tx_flags & I40E_TX_FLAGS_VLAN_MASK) >> - I40E_TX_FLAGS_VLAN_SHIFT; + td_tag = FIELD_GET(I40E_TX_FLAGS_VLAN_MASK, tx_flags); } first->tx_flags = tx_flags; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 37cca484abb8..0de8e00ad291 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -474,10 +474,10 @@ static void i40e_release_rdma_qvlist(struct i40e_vf *vf) */ reg_idx = (msix_vf - 1) * vf->vf_id + qv_info->ceq_idx; reg = rd32(hw, I40E_VPINT_CEQCTL(reg_idx)); - next_q_index = (reg & I40E_VPINT_CEQCTL_NEXTQ_INDX_MASK) - >> I40E_VPINT_CEQCTL_NEXTQ_INDX_SHIFT; - next_q_type = (reg & I40E_VPINT_CEQCTL_NEXTQ_TYPE_MASK) - >> I40E_VPINT_CEQCTL_NEXTQ_TYPE_SHIFT; + next_q_index = FIELD_GET(I40E_VPINT_CEQCTL_NEXTQ_INDX_MASK, + reg); + next_q_type = FIELD_GET(I40E_VPINT_CEQCTL_NEXTQ_TYPE_MASK, + reg); reg_idx = ((msix_vf - 1) * vf->vf_id) + (v_idx - 1); reg = (next_q_index & @@ -555,10 +555,10 @@ i40e_config_rdma_qvlist(struct i40e_vf *vf, * queue on top. Also link it with the new queue in CEQCTL. */ reg = rd32(hw, I40E_VPINT_LNKLSTN(reg_idx)); - next_q_idx = ((reg & I40E_VPINT_LNKLSTN_FIRSTQ_INDX_MASK) >> - I40E_VPINT_LNKLSTN_FIRSTQ_INDX_SHIFT); - next_q_type = ((reg & I40E_VPINT_LNKLSTN_FIRSTQ_TYPE_MASK) >> - I40E_VPINT_LNKLSTN_FIRSTQ_TYPE_SHIFT); + next_q_idx = FIELD_GET(I40E_VPINT_LNKLSTN_FIRSTQ_INDX_MASK, + reg); + next_q_type = FIELD_GET(I40E_VPINT_LNKLSTN_FIRSTQ_TYPE_MASK, + reg); if (qv_info->ceq_idx != I40E_QUEUE_INVALID_IDX) { reg_idx = (msix_vf - 1) * vf->vf_id + qv_info->ceq_idx; @@ -659,11 +659,9 @@ static int i40e_config_vsi_tx_queue(struct i40e_vf *vf, u16 vsi_id, /* associate this queue with the PCI VF function */ qtx_ctl = I40E_QTX_CTL_VF_QUEUE; - qtx_ctl |= ((hw->pf_id << I40E_QTX_CTL_PF_INDX_SHIFT) - & I40E_QTX_CTL_PF_INDX_MASK); - qtx_ctl |= (((vf->vf_id + hw->func_caps.vf_base_id) - << I40E_QTX_CTL_VFVM_INDX_SHIFT) - & I40E_QTX_CTL_VFVM_INDX_MASK); + qtx_ctl |= FIELD_PREP(I40E_QTX_CTL_PF_INDX_MASK, hw->pf_id); + qtx_ctl |= FIELD_PREP(I40E_QTX_CTL_VFVM_INDX_MASK, + vf->vf_id + hw->func_caps.vf_base_id); wr32(hw, I40E_QTX_CTL(pf_queue_id), qtx_ctl); i40e_flush(hw); @@ -4675,9 +4673,8 @@ int i40e_ndo_get_vf_config(struct net_device *netdev, ivi->max_tx_rate = vf->tx_rate; ivi->min_tx_rate = 0; - ivi->vlan = le16_to_cpu(vsi->info.pvid) & I40E_VLAN_MASK; - ivi->qos = (le16_to_cpu(vsi->info.pvid) & I40E_PRIORITY_MASK) >> - I40E_VLAN_PRIORITY_SHIFT; + ivi->vlan = le16_get_bits(vsi->info.pvid, I40E_VLAN_MASK); + ivi->qos = le16_get_bits(vsi->info.pvid, I40E_PRIORITY_MASK); if (vf->link_forced == false) ivi->linkstate = IFLA_VF_LINK_STATE_AUTO; else if (vf->link_up == true) diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index e99fa854d17f..af7d5fa6cdc1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -476,8 +476,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) continue; } - size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >> - I40E_RXD_QW1_LENGTH_PBUF_SHIFT; + size = FIELD_GET(I40E_RXD_QW1_LENGTH_PBUF_MASK, qword); if (!size) break; diff --git a/drivers/net/ethernet/intel/iavf/iavf_common.c b/drivers/net/ethernet/intel/iavf/iavf_common.c index 89d2bce529ae..5a25233a89d5 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_common.c +++ b/drivers/net/ethernet/intel/iavf/iavf_common.c @@ -1,10 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2018 Intel Corporation. */ +#include <linux/avf/virtchnl.h> +#include <linux/bitfield.h> #include "iavf_type.h" #include "iavf_adminq.h" #include "iavf_prototype.h" -#include <linux/avf/virtchnl.h> /** * iavf_aq_str - convert AQ err code to a string @@ -330,6 +331,7 @@ static enum iavf_status iavf_aq_get_set_rss_lut(struct iavf_hw *hw, struct iavf_aq_desc desc; struct iavf_aqc_get_set_rss_lut *cmd_resp = (struct iavf_aqc_get_set_rss_lut *)&desc.params.raw; + u16 flags; if (set) iavf_fill_default_direct_cmd_desc(&desc, @@ -342,22 +344,18 @@ static enum iavf_status iavf_aq_get_set_rss_lut(struct iavf_hw *hw, desc.flags |= cpu_to_le16((u16)IAVF_AQ_FLAG_BUF); desc.flags |= cpu_to_le16((u16)IAVF_AQ_FLAG_RD); - cmd_resp->vsi_id = - cpu_to_le16((u16)((vsi_id << - IAVF_AQC_SET_RSS_LUT_VSI_ID_SHIFT) & - IAVF_AQC_SET_RSS_LUT_VSI_ID_MASK)); - cmd_resp->vsi_id |= cpu_to_le16((u16)IAVF_AQC_SET_RSS_LUT_VSI_VALID); + vsi_id = FIELD_PREP(IAVF_AQC_SET_RSS_LUT_VSI_ID_MASK, vsi_id) | + FIELD_PREP(IAVF_AQC_SET_RSS_LUT_VSI_VALID, 1); + cmd_resp->vsi_id = cpu_to_le16(vsi_id); if (pf_lut) - cmd_resp->flags |= cpu_to_le16((u16) - ((IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_PF << - IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) & - IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_MASK)); + flags = FIELD_PREP(IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_MASK, + IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_PF); else - cmd_resp->flags |= cpu_to_le16((u16) - ((IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_VSI << - IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) & - IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_MASK)); + flags = FIELD_PREP(IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_MASK, + IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_VSI); + + cmd_resp->flags = cpu_to_le16(flags); status = iavf_asq_send_command(hw, &desc, lut, lut_size, NULL); @@ -411,11 +409,9 @@ iavf_status iavf_aq_get_set_rss_key(struct iavf_hw *hw, u16 vsi_id, desc.flags |= cpu_to_le16((u16)IAVF_AQ_FLAG_BUF); desc.flags |= cpu_to_le16((u16)IAVF_AQ_FLAG_RD); - cmd_resp->vsi_id = - cpu_to_le16((u16)((vsi_id << - IAVF_AQC_SET_RSS_KEY_VSI_ID_SHIFT) & - IAVF_AQC_SET_RSS_KEY_VSI_ID_MASK)); - cmd_resp->vsi_id |= cpu_to_le16((u16)IAVF_AQC_SET_RSS_KEY_VSI_VALID); + vsi_id = FIELD_PREP(IAVF_AQC_SET_RSS_KEY_VSI_ID_MASK, vsi_id) | + FIELD_PREP(IAVF_AQC_SET_RSS_KEY_VSI_VALID, 1); + cmd_resp->vsi_id = cpu_to_le16(vsi_id); status = iavf_asq_send_command(hw, &desc, key, key_size, NULL); diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index cdb4849f5db4..378c3e9ddf9d 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -1,11 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2018 Intel Corporation. */ +#include <linux/bitfield.h> +#include <linux/uaccess.h> + /* ethtool support for iavf */ #include "iavf.h" -#include <linux/uaccess.h> - /* ethtool statistics helpers */ /** @@ -1016,8 +1017,7 @@ iavf_parse_rx_flow_user_data(struct ethtool_rx_flow_spec *fsp, #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; + flex->offset = FIELD_GET(IAVF_USERDEF_FLEX_OFFS_M, value); if (flex->offset > IAVF_USERDEF_FLEX_MAX_OFFS_VAL) return -EINVAL; } diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.c b/drivers/net/ethernet/intel/iavf/iavf_fdir.c index 03e774bd2a5b..2d47b0b4640e 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_fdir.c +++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.c @@ -3,6 +3,7 @@ /* flow director ethtool support for iavf */ +#include <linux/bitfield.h> #include "iavf.h" #define GTPU_PORT 2152 @@ -357,7 +358,7 @@ iavf_fill_fdir_ip6_hdr(struct iavf_fdir_fltr *fltr, 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; + iph->flow_lbl[0] = FIELD_PREP(0xF0, fltr->ip_data.tclass); VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, IPV6, TC); } diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index d64c4997136b..b71484c87a84 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2018 Intel Corporation. */ +#include <linux/bitfield.h> #include <linux/prefetch.h> #include "iavf.h" @@ -988,11 +989,9 @@ static void iavf_rx_checksum(struct iavf_vsi *vsi, u64 qword; qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - ptype = (qword & IAVF_RXD_QW1_PTYPE_MASK) >> IAVF_RXD_QW1_PTYPE_SHIFT; - rx_error = (qword & IAVF_RXD_QW1_ERROR_MASK) >> - IAVF_RXD_QW1_ERROR_SHIFT; - rx_status = (qword & IAVF_RXD_QW1_STATUS_MASK) >> - IAVF_RXD_QW1_STATUS_SHIFT; + ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword); + rx_error = FIELD_GET(IAVF_RXD_QW1_ERROR_MASK, qword); + rx_status = FIELD_GET(IAVF_RXD_QW1_STATUS_MASK, qword); decoded = decode_rx_desc_ptype(ptype); skb->ip_summed = CHECKSUM_NONE; @@ -1533,8 +1532,7 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget) if (!iavf_test_staterr(rx_desc, IAVF_RXD_DD)) break; - size = (qword & IAVF_RXD_QW1_LENGTH_PBUF_MASK) >> - IAVF_RXD_QW1_LENGTH_PBUF_SHIFT; + size = FIELD_GET(IAVF_RXD_QW1_LENGTH_PBUF_MASK, qword); iavf_trace(clean_rx_irq, rx_ring, rx_desc, skb); rx_buffer = iavf_get_rx_buffer(rx_ring, size); @@ -1581,8 +1579,7 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget) total_rx_bytes += skb->len; qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - rx_ptype = (qword & IAVF_RXD_QW1_PTYPE_MASK) >> - IAVF_RXD_QW1_PTYPE_SHIFT; + rx_ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword); /* populate checksum, VLAN, and protocol */ iavf_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype); @@ -2290,8 +2287,7 @@ static void iavf_tx_map(struct iavf_ring *tx_ring, struct sk_buff *skb, if (tx_flags & IAVF_TX_FLAGS_HW_VLAN) { td_cmd |= IAVF_TX_DESC_CMD_IL2TAG1; - td_tag = (tx_flags & IAVF_TX_FLAGS_VLAN_MASK) >> - IAVF_TX_FLAGS_VLAN_SHIFT; + td_tag = FIELD_GET(IAVF_TX_FLAGS_VLAN_MASK, tx_flags); } first->tx_flags = tx_flags; @@ -2467,8 +2463,7 @@ static netdev_tx_t iavf_xmit_frame_ring(struct sk_buff *skb, if (tx_flags & IAVF_TX_FLAGS_HW_OUTER_SINGLE_VLAN) { cd_type_cmd_tso_mss |= IAVF_TX_CTX_DESC_IL2TAG2 << IAVF_TXD_CTX_QW1_CMD_SHIFT; - cd_l2tag2 = (tx_flags & IAVF_TX_FLAGS_VLAN_MASK) >> - IAVF_TX_FLAGS_VLAN_SHIFT; + cd_l2tag2 = FIELD_GET(IAVF_TX_FLAGS_VLAN_MASK, tx_flags); } /* obtain protocol of skb */ diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 12c510bb1d9b..6a5e974a1776 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -422,10 +422,10 @@ struct ice_aqc_vsi_props { #define ICE_AQ_VSI_INNER_VLAN_INSERT_PVID BIT(2) #define ICE_AQ_VSI_INNER_VLAN_EMODE_S 3 #define ICE_AQ_VSI_INNER_VLAN_EMODE_M (0x3 << ICE_AQ_VSI_INNER_VLAN_EMODE_S) -#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR_BOTH (0x0 << ICE_AQ_VSI_INNER_VLAN_EMODE_S) -#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR_UP (0x1 << ICE_AQ_VSI_INNER_VLAN_EMODE_S) -#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR (0x2 << ICE_AQ_VSI_INNER_VLAN_EMODE_S) -#define ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING (0x3 << ICE_AQ_VSI_INNER_VLAN_EMODE_S) +#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR_BOTH 0x0U +#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR_UP 0x1U +#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR 0x2U +#define ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING 0x3U u8 inner_vlan_reserved2[3]; /* ingress egress up sections */ __le32 ingress_table; /* bitmap, 3 bits per up */ @@ -491,7 +491,7 @@ struct ice_aqc_vsi_props { #define ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_S 2 #define ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_M (0xF << ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_S) #define ICE_AQ_VSI_Q_OPT_RSS_HASH_S 6 -#define ICE_AQ_VSI_Q_OPT_RSS_HASH_M (0x3 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) +#define ICE_AQ_VSI_Q_OPT_RSS_HASH_M GENMASK(7, 6) #define ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ 0x0U #define ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ 0x1U #define ICE_AQ_VSI_Q_OPT_RSS_HASH_XOR 0x2U diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index b25b7f415965..6e3694145f59 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -232,24 +232,16 @@ static void ice_cfg_itr_gran(struct ice_hw *hw) /* no need to update global register if ITR gran is already set */ if (!(regval & GLINT_CTL_DIS_AUTOMASK_M) && - (((regval & GLINT_CTL_ITR_GRAN_200_M) >> - GLINT_CTL_ITR_GRAN_200_S) == ICE_ITR_GRAN_US) && - (((regval & GLINT_CTL_ITR_GRAN_100_M) >> - GLINT_CTL_ITR_GRAN_100_S) == ICE_ITR_GRAN_US) && - (((regval & GLINT_CTL_ITR_GRAN_50_M) >> - GLINT_CTL_ITR_GRAN_50_S) == ICE_ITR_GRAN_US) && - (((regval & GLINT_CTL_ITR_GRAN_25_M) >> - GLINT_CTL_ITR_GRAN_25_S) == ICE_ITR_GRAN_US)) + (FIELD_GET(GLINT_CTL_ITR_GRAN_200_M, regval) == ICE_ITR_GRAN_US) && + (FIELD_GET(GLINT_CTL_ITR_GRAN_100_M, regval) == ICE_ITR_GRAN_US) && + (FIELD_GET(GLINT_CTL_ITR_GRAN_50_M, regval) == ICE_ITR_GRAN_US) && + (FIELD_GET(GLINT_CTL_ITR_GRAN_25_M, regval) == ICE_ITR_GRAN_US)) return; - regval = ((ICE_ITR_GRAN_US << GLINT_CTL_ITR_GRAN_200_S) & - GLINT_CTL_ITR_GRAN_200_M) | - ((ICE_ITR_GRAN_US << GLINT_CTL_ITR_GRAN_100_S) & - GLINT_CTL_ITR_GRAN_100_M) | - ((ICE_ITR_GRAN_US << GLINT_CTL_ITR_GRAN_50_S) & - GLINT_CTL_ITR_GRAN_50_M) | - ((ICE_ITR_GRAN_US << GLINT_CTL_ITR_GRAN_25_S) & - GLINT_CTL_ITR_GRAN_25_M); + regval = FIELD_PREP(GLINT_CTL_ITR_GRAN_200_M, ICE_ITR_GRAN_US) | + FIELD_PREP(GLINT_CTL_ITR_GRAN_100_M, ICE_ITR_GRAN_US) | + FIELD_PREP(GLINT_CTL_ITR_GRAN_50_M, ICE_ITR_GRAN_US) | + FIELD_PREP(GLINT_CTL_ITR_GRAN_25_M, ICE_ITR_GRAN_US); wr32(hw, GLINT_CTL, regval); } @@ -936,10 +928,10 @@ ice_cfg_txq_interrupt(struct ice_vsi *vsi, u16 txq, u16 msix_idx, u16 itr_idx) struct ice_hw *hw = &pf->hw; u32 val; - itr_idx = (itr_idx << QINT_TQCTL_ITR_INDX_S) & QINT_TQCTL_ITR_INDX_M; + itr_idx = FIELD_PREP(QINT_TQCTL_ITR_INDX_M, itr_idx); val = QINT_TQCTL_CAUSE_ENA_M | itr_idx | - ((msix_idx << QINT_TQCTL_MSIX_INDX_S) & QINT_TQCTL_MSIX_INDX_M); + FIELD_PREP(QINT_TQCTL_MSIX_INDX_M, msix_idx); wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), val); if (ice_is_xdp_ena_vsi(vsi)) { @@ -968,10 +960,10 @@ ice_cfg_rxq_interrupt(struct ice_vsi *vsi, u16 rxq, u16 msix_idx, u16 itr_idx) struct ice_hw *hw = &pf->hw; u32 val; - itr_idx = (itr_idx << QINT_RQCTL_ITR_INDX_S) & QINT_RQCTL_ITR_INDX_M; + itr_idx = FIELD_PREP(QINT_RQCTL_ITR_INDX_M, itr_idx); val = QINT_RQCTL_CAUSE_ENA_M | itr_idx | - ((msix_idx << QINT_RQCTL_MSIX_INDX_S) & QINT_RQCTL_MSIX_INDX_M); + FIELD_PREP(QINT_RQCTL_MSIX_INDX_M, msix_idx); wr32(hw, QINT_RQCTL(vsi->rxq_map[rxq]), val); diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 08a1f699a34f..6fb0c1e8ae7c 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -942,9 +942,8 @@ static void ice_cleanup_fltr_mgmt_struct(struct ice_hw *hw) */ static void ice_get_itr_intrl_gran(struct ice_hw *hw) { - u8 max_agg_bw = (rd32(hw, GL_PWR_MODE_CTL) & - GL_PWR_MODE_CTL_CAR_MAX_BW_M) >> - GL_PWR_MODE_CTL_CAR_MAX_BW_S; + u8 max_agg_bw = FIELD_GET(GL_PWR_MODE_CTL_CAR_MAX_BW_M, + rd32(hw, GL_PWR_MODE_CTL)); switch (max_agg_bw) { case ICE_MAX_AGG_BW_200G: @@ -976,9 +975,7 @@ int ice_init_hw(struct ice_hw *hw) if (status) return status; - hw->pf_id = (u8)(rd32(hw, PF_FUNC_RID) & - PF_FUNC_RID_FUNC_NUM_M) >> - PF_FUNC_RID_FUNC_NUM_S; + hw->pf_id = FIELD_GET(PF_FUNC_RID_FUNC_NUM_M, rd32(hw, PF_FUNC_RID)); status = ice_reset(hw, ICE_RESET_PFR); if (status) @@ -1163,8 +1160,8 @@ int ice_check_reset(struct ice_hw *hw) * or EMPR has occurred. The grst delay value is in 100ms units. * Add 1sec for outstanding AQ commands that can take a long time. */ - grst_timeout = ((rd32(hw, GLGEN_RSTCTL) & GLGEN_RSTCTL_GRSTDEL_M) >> - GLGEN_RSTCTL_GRSTDEL_S) + 10; + grst_timeout = FIELD_GET(GLGEN_RSTCTL_GRSTDEL_M, + rd32(hw, GLGEN_RSTCTL)) + 10; for (cnt = 0; cnt < grst_timeout; cnt++) { mdelay(100); @@ -2248,7 +2245,7 @@ ice_parse_1588_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p, info->tmr_index_owned = ((number & ICE_TS_TMR_IDX_OWND_M) != 0); info->tmr_index_assoc = ((number & ICE_TS_TMR_IDX_ASSOC_M) != 0); - info->clk_freq = (number & ICE_TS_CLK_FREQ_M) >> ICE_TS_CLK_FREQ_S; + info->clk_freq = FIELD_GET(ICE_TS_CLK_FREQ_M, number); info->clk_src = ((number & ICE_TS_CLK_SRC_M) != 0); if (info->clk_freq < NUM_ICE_TIME_REF_FREQ) { @@ -2449,7 +2446,7 @@ ice_parse_1588_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, info->tmr0_owned = ((number & ICE_TS_TMR0_OWND_M) != 0); info->tmr0_ena = ((number & ICE_TS_TMR0_ENA_M) != 0); - info->tmr1_owner = (number & ICE_TS_TMR1_OWNR_M) >> ICE_TS_TMR1_OWNR_S; + info->tmr1_owner = FIELD_GET(ICE_TS_TMR1_OWNR_M, number); info->tmr1_owned = ((number & ICE_TS_TMR1_OWND_M) != 0); info->tmr1_ena = ((number & ICE_TS_TMR1_ENA_M) != 0); @@ -3884,6 +3881,7 @@ ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr, { struct ice_aqc_sff_eeprom *cmd; struct ice_aq_desc desc; + u16 i2c_bus_addr; int status; if (!data || (mem_addr & 0xff00)) @@ -3894,15 +3892,13 @@ ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr, 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) & - ICE_AQC_SFF_I2CBUS_7BIT_M) | - ((set_page << - ICE_AQC_SFF_SET_EEPROM_PAGE_S) & - ICE_AQC_SFF_SET_EEPROM_PAGE_M)); - cmd->i2c_mem_addr = cpu_to_le16(mem_addr & 0xff); - cmd->eeprom_page = cpu_to_le16((u16)page << ICE_AQC_SFF_EEPROM_PAGE_S); + i2c_bus_addr = FIELD_PREP(ICE_AQC_SFF_I2CBUS_7BIT_M, bus_addr >> 1) | + FIELD_PREP(ICE_AQC_SFF_SET_EEPROM_PAGE_M, set_page); if (write) - cmd->i2c_bus_addr |= cpu_to_le16(ICE_AQC_SFF_IS_WRITE); + i2c_bus_addr |= ICE_AQC_SFF_IS_WRITE; + cmd->i2c_bus_addr = cpu_to_le16(i2c_bus_addr); + cmd->i2c_mem_addr = cpu_to_le16(mem_addr & 0xff); + cmd->eeprom_page = le16_encode_bits(page, ICE_AQC_SFF_EEPROM_PAGE_M); status = ice_aq_send_cmd(hw, &desc, data, length, cd); return status; @@ -4157,6 +4153,7 @@ ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps, struct ice_aqc_dis_txq_item *item; struct ice_aqc_dis_txqs *cmd; struct ice_aq_desc desc; + u16 vmvf_and_timeout; u16 i, sz = 0; int status; @@ -4172,27 +4169,26 @@ ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps, cmd->num_entries = num_qgrps; - cmd->vmvf_and_timeout = cpu_to_le16((5 << ICE_AQC_Q_DIS_TIMEOUT_S) & - ICE_AQC_Q_DIS_TIMEOUT_M); + vmvf_and_timeout = FIELD_PREP(ICE_AQC_Q_DIS_TIMEOUT_M, 5); switch (rst_src) { case ICE_VM_RESET: cmd->cmd_type = ICE_AQC_Q_DIS_CMD_VM_RESET; - cmd->vmvf_and_timeout |= - cpu_to_le16(vmvf_num & ICE_AQC_Q_DIS_VMVF_NUM_M); + vmvf_and_timeout |= vmvf_num & ICE_AQC_Q_DIS_VMVF_NUM_M; break; case ICE_VF_RESET: cmd->cmd_type = ICE_AQC_Q_DIS_CMD_VF_RESET; /* In this case, FW expects vmvf_num to be absolute VF ID */ - cmd->vmvf_and_timeout |= - cpu_to_le16((vmvf_num + hw->func_caps.vf_base_id) & - ICE_AQC_Q_DIS_VMVF_NUM_M); + vmvf_and_timeout |= (vmvf_num + hw->func_caps.vf_base_id) & + ICE_AQC_Q_DIS_VMVF_NUM_M; break; case ICE_NO_RESET: default: break; } + cmd->vmvf_and_timeout = cpu_to_le16(vmvf_and_timeout); + /* flush pipe on time out */ cmd->cmd_type |= ICE_AQC_Q_DIS_CMD_FLUSH_PIPE; /* If no queue group info, we are in a reset flow. Issue the AQ */ @@ -4267,10 +4263,8 @@ ice_aq_cfg_lan_txq(struct ice_hw *hw, struct ice_aqc_cfg_txqs_buf *buf, cmd->cmd_type = ICE_AQC_Q_CFG_TC_CHNG; cmd->num_qs = num_qs; cmd->port_num_chng = (oldport & ICE_AQC_Q_CFG_SRC_PRT_M); - cmd->port_num_chng |= (newport << ICE_AQC_Q_CFG_DST_PRT_S) & - ICE_AQC_Q_CFG_DST_PRT_M; - cmd->time_out = (5 << ICE_AQC_Q_CFG_TIMEOUT_S) & - ICE_AQC_Q_CFG_TIMEOUT_M; + cmd->port_num_chng |= FIELD_PREP(ICE_AQC_Q_CFG_DST_PRT_M, newport); + cmd->time_out = FIELD_PREP(ICE_AQC_Q_CFG_TIMEOUT_M, 5); cmd->blocked_cgds = 0; status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd); @@ -5776,7 +5770,7 @@ ice_get_link_default_override(struct ice_link_default_override_tlv *ldo, ice_debug(hw, ICE_DBG_INIT, "Failed to read override link options.\n"); return status; } - ldo->options = buf & ICE_LINK_OVERRIDE_OPT_M; + ldo->options = FIELD_GET(ICE_LINK_OVERRIDE_OPT_M, buf); ldo->phy_config = (buf & ICE_LINK_OVERRIDE_PHY_CFG_M) >> ICE_LINK_OVERRIDE_PHY_CFG_S; diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.c b/drivers/net/ethernet/intel/ice/ice_dcb.c index 396e555023aa..74418c445cc4 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb.c @@ -35,8 +35,7 @@ ice_aq_get_lldp_mib(struct ice_hw *hw, u8 bridge_type, u8 mib_type, void *buf, ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_get_mib); cmd->type = mib_type & ICE_AQ_LLDP_MIB_TYPE_M; - cmd->type |= (bridge_type << ICE_AQ_LLDP_BRID_TYPE_S) & - ICE_AQ_LLDP_BRID_TYPE_M; + cmd->type |= FIELD_PREP(ICE_AQ_LLDP_BRID_TYPE_M, bridge_type); desc.datalen = cpu_to_le16(buf_size); @@ -147,8 +146,7 @@ static u8 ice_get_dcbx_status(struct ice_hw *hw) u32 reg; reg = rd32(hw, PRTDCB_GENS); - return (u8)((reg & PRTDCB_GENS_DCBX_STATUS_M) >> - PRTDCB_GENS_DCBX_STATUS_S); + return FIELD_GET(PRTDCB_GENS_DCBX_STATUS_M, reg); } /** @@ -174,11 +172,9 @@ ice_parse_ieee_ets_common_tlv(u8 *buf, struct ice_dcb_ets_cfg *ets_cfg) */ for (i = 0; i < 4; i++) { ets_cfg->prio_table[i * 2] = - ((buf[offset] & ICE_IEEE_ETS_PRIO_1_M) >> - ICE_IEEE_ETS_PRIO_1_S); + FIELD_GET(ICE_IEEE_ETS_PRIO_1_M, buf[offset]); ets_cfg->prio_table[i * 2 + 1] = - ((buf[offset] & ICE_IEEE_ETS_PRIO_0_M) >> - ICE_IEEE_ETS_PRIO_0_S); + FIELD_GET(ICE_IEEE_ETS_PRIO_0_M, buf[offset]); offset++; } @@ -222,11 +218,9 @@ ice_parse_ieee_etscfg_tlv(struct ice_lldp_org_tlv *tlv, * |1bit | 1bit|3 bits|3bits| */ etscfg = &dcbcfg->etscfg; - etscfg->willing = ((buf[0] & ICE_IEEE_ETS_WILLING_M) >> - ICE_IEEE_ETS_WILLING_S); - etscfg->cbs = ((buf[0] & ICE_IEEE_ETS_CBS_M) >> ICE_IEEE_ETS_CBS_S); - etscfg->maxtcs = ((buf[0] & ICE_IEEE_ETS_MAXTC_M) >> - ICE_IEEE_ETS_MAXTC_S); + etscfg->willing = FIELD_GET(ICE_IEEE_ETS_WILLING_M, buf[0]); + etscfg->cbs = FIELD_GET(ICE_IEEE_ETS_CBS_M, buf[0]); + etscfg->maxtcs = FIELD_GET(ICE_IEEE_ETS_MAXTC_M, buf[0]); /* Begin parsing at Priority Assignment Table (offset 1 in buf) */ ice_parse_ieee_ets_common_tlv(&buf[1], etscfg); @@ -268,11 +262,9 @@ ice_parse_ieee_pfccfg_tlv(struct ice_lldp_org_tlv *tlv, * ----------------------------------------- * |1bit | 1bit|2 bits|4bits| 1 octet | */ - dcbcfg->pfc.willing = ((buf[0] & ICE_IEEE_PFC_WILLING_M) >> - ICE_IEEE_PFC_WILLING_S); - dcbcfg->pfc.mbc = ((buf[0] & ICE_IEEE_PFC_MBC_M) >> ICE_IEEE_PFC_MBC_S); - dcbcfg->pfc.pfccap = ((buf[0] & ICE_IEEE_PFC_CAP_M) >> - ICE_IEEE_PFC_CAP_S); + dcbcfg->pfc.willing = FIELD_GET(ICE_IEEE_PFC_WILLING_M, buf[0]); + dcbcfg->pfc.mbc = FIELD_GET(ICE_IEEE_PFC_MBC_M, buf[0]); + dcbcfg->pfc.pfccap = FIELD_GET(ICE_IEEE_PFC_CAP_M, buf[0]); dcbcfg->pfc.pfcena = buf[1]; } @@ -294,7 +286,7 @@ ice_parse_ieee_app_tlv(struct ice_lldp_org_tlv *tlv, u8 *buf; typelen = ntohs(tlv->typelen); - len = ((typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S); + len = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen); buf = tlv->tlvinfo; /* Removing sizeof(ouisubtype) and reserved byte from len. @@ -314,12 +306,10 @@ ice_parse_ieee_app_tlv(struct ice_lldp_org_tlv *tlv, * ----------------------------------------- */ while (offset < len) { - dcbcfg->app[i].priority = ((buf[offset] & - ICE_IEEE_APP_PRIO_M) >> - ICE_IEEE_APP_PRIO_S); - dcbcfg->app[i].selector = ((buf[offset] & - ICE_IEEE_APP_SEL_M) >> - ICE_IEEE_APP_SEL_S); + dcbcfg->app[i].priority = FIELD_GET(ICE_IEEE_APP_PRIO_M, + buf[offset]); + dcbcfg->app[i].selector = FIELD_GET(ICE_IEEE_APP_SEL_M, + buf[offset]); dcbcfg->app[i].prot_id = (buf[offset + 1] << 0x8) | buf[offset + 2]; /* Move to next app */ @@ -347,8 +337,7 @@ ice_parse_ieee_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg) u8 subtype; ouisubtype = ntohl(tlv->ouisubtype); - subtype = (u8)((ouisubtype & ICE_LLDP_TLV_SUBTYPE_M) >> - ICE_LLDP_TLV_SUBTYPE_S); + subtype = FIELD_GET(ICE_LLDP_TLV_SUBTYPE_M, ouisubtype); switch (subtype) { case ICE_IEEE_SUBTYPE_ETS_CFG: ice_parse_ieee_etscfg_tlv(tlv, dcbcfg); @@ -399,11 +388,9 @@ ice_parse_cee_pgcfg_tlv(struct ice_cee_feat_tlv *tlv, */ for (i = 0; i < 4; i++) { etscfg->prio_table[i * 2] = - ((buf[offset] & ICE_CEE_PGID_PRIO_1_M) >> - ICE_CEE_PGID_PRIO_1_S); + FIELD_GET(ICE_CEE_PGID_PRIO_1_M, buf[offset]); etscfg->prio_table[i * 2 + 1] = - ((buf[offset] & ICE_CEE_PGID_PRIO_0_M) >> - ICE_CEE_PGID_PRIO_0_S); + FIELD_GET(ICE_CEE_PGID_PRIO_0_M, buf[offset]); offset++; } @@ -466,7 +453,7 @@ ice_parse_cee_app_tlv(struct ice_cee_feat_tlv *tlv, struct ice_dcbx_cfg *dcbcfg) u8 i; typelen = ntohs(tlv->hdr.typelen); - len = ((typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S); + len = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen); dcbcfg->numapps = len / sizeof(*app); if (!dcbcfg->numapps) @@ -521,14 +508,13 @@ ice_parse_cee_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg) u32 ouisubtype; ouisubtype = ntohl(tlv->ouisubtype); - subtype = (u8)((ouisubtype & ICE_LLDP_TLV_SUBTYPE_M) >> - ICE_LLDP_TLV_SUBTYPE_S); + subtype = FIELD_GET(ICE_LLDP_TLV_SUBTYPE_M, ouisubtype); /* Return if not CEE DCBX */ if (subtype != ICE_CEE_DCBX_TYPE) return; typelen = ntohs(tlv->typelen); - tlvlen = ((typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S); + tlvlen = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen); len = sizeof(tlv->typelen) + sizeof(ouisubtype) + sizeof(struct ice_cee_ctrl_tlv); /* Return if no CEE DCBX Feature TLVs */ @@ -540,9 +526,8 @@ ice_parse_cee_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg) u16 sublen; typelen = ntohs(sub_tlv->hdr.typelen); - sublen = ((typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S); - subtype = (u8)((typelen & ICE_LLDP_TLV_TYPE_M) >> - ICE_LLDP_TLV_TYPE_S); + sublen = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen); + subtype = FIELD_GET(ICE_LLDP_TLV_TYPE_M, typelen); switch (subtype) { case ICE_CEE_SUBTYPE_PG_CFG: ice_parse_cee_pgcfg_tlv(sub_tlv, dcbcfg); @@ -579,7 +564,7 @@ ice_parse_org_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg) u32 oui; ouisubtype = ntohl(tlv->ouisubtype); - oui = ((ouisubtype & ICE_LLDP_TLV_OUI_M) >> ICE_LLDP_TLV_OUI_S); + oui = FIELD_GET(ICE_LLDP_TLV_OUI_M, ouisubtype); switch (oui) { case ICE_IEEE_8021QAZ_OUI: ice_parse_ieee_tlv(tlv, dcbcfg); @@ -616,8 +601,8 @@ static int ice_lldp_to_dcb_cfg(u8 *lldpmib, struct ice_dcbx_cfg *dcbcfg) tlv = (struct ice_lldp_org_tlv *)lldpmib; while (1) { typelen = ntohs(tlv->typelen); - type = ((typelen & ICE_LLDP_TLV_TYPE_M) >> ICE_LLDP_TLV_TYPE_S); - len = ((typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S); + type = FIELD_GET(ICE_LLDP_TLV_TYPE_M, typelen); + len = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen); offset += sizeof(typelen) + len; /* END TLV or beyond LLDPDU size */ @@ -806,11 +791,11 @@ ice_cee_to_dcb_cfg(struct ice_aqc_get_cee_dcb_cfg_resp *cee_cfg, */ for (i = 0; i < ICE_MAX_TRAFFIC_CLASS / 2; i++) { dcbcfg->etscfg.prio_table[i * 2] = - ((cee_cfg->oper_prio_tc[i] & ICE_CEE_PGID_PRIO_0_M) >> - ICE_CEE_PGID_PRIO_0_S); + FIELD_GET(ICE_CEE_PGID_PRIO_0_M, + cee_cfg->oper_prio_tc[i]); dcbcfg->etscfg.prio_table[i * 2 + 1] = - ((cee_cfg->oper_prio_tc[i] & ICE_CEE_PGID_PRIO_1_M) >> - ICE_CEE_PGID_PRIO_1_S); + FIELD_GET(ICE_CEE_PGID_PRIO_1_M, + cee_cfg->oper_prio_tc[i]); } ice_for_each_traffic_class(i) { @@ -982,7 +967,7 @@ void ice_get_dcb_cfg_from_mib_change(struct ice_port_info *pi, mib = (struct ice_aqc_lldp_get_mib *)&event->desc.params.raw; - change_type = FIELD_GET(ICE_AQ_LLDP_MIB_TYPE_M, mib->type); + change_type = FIELD_GET(ICE_AQ_LLDP_MIB_TYPE_M, mib->type); if (change_type == ICE_AQ_LLDP_MIB_REMOTE) dcbx_cfg = &pi->qos_cfg.remote_dcbx_cfg; @@ -1483,7 +1468,7 @@ ice_dcb_cfg_to_lldp(u8 *lldpmib, u16 *miblen, struct ice_dcbx_cfg *dcbcfg) while (1) { ice_add_dcb_tlv(tlv, dcbcfg, tlvid++); typelen = ntohs(tlv->typelen); - len = (typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S; + len = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen); if (len) offset += len + 2; /* END TLV or beyond LLDPDU size */ diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index 850db8e0e6b0..6e20ee610022 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -934,7 +934,7 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring, skb->priority != TC_PRIO_CONTROL) { first->vid &= ~VLAN_PRIO_MASK; /* Mask the lower 3 bits to set the 802.1p priority */ - first->vid |= (skb->priority << VLAN_PRIO_SHIFT) & VLAN_PRIO_MASK; + first->vid |= FIELD_PREP(VLAN_PRIO_MASK, skb->priority); /* if this is not already set it means a VLAN 0 + priority needs * to be offloaded */ diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c index e1fbc6de452d..6d50b90a7359 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c @@ -227,7 +227,7 @@ static void ice_get_pfc_delay(struct ice_hw *hw, u16 *delay) u32 val; val = rd32(hw, PRTDCB_GENC); - *delay = (u16)((val & PRTDCB_GENC_PFCLDA_M) >> PRTDCB_GENC_PFCLDA_S); + *delay = FIELD_GET(PRTDCB_GENC_PFCLDA_M, val); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index ca118bc37e44..9069725c71b4 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -358,8 +358,8 @@ ice_eswitch_set_target_vsi(struct sk_buff *skb, off->cd_qw1 |= (cd_cmd | ICE_TX_DESC_DTYPE_CTX); } else { cd_cmd = ICE_TX_CTX_DESC_SWTCH_VSI << ICE_TXD_CTX_QW1_CMD_S; - dst_vsi = ((u64)dst->u.port_info.port_id << - ICE_TXD_CTX_QW1_VSI_S) & ICE_TXD_CTX_QW1_VSI_M; + dst_vsi = FIELD_PREP(ICE_TXD_CTX_QW1_VSI_M, + dst->u.port_info.port_id); off->cd_qw1 = cd_cmd | dst_vsi | ICE_TX_DESC_DTYPE_CTX; } } diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c index 54e4536219aa..9a1a04f5f146 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c @@ -503,8 +503,7 @@ ice_parse_rx_flow_user_data(struct ethtool_rx_flow_spec *fsp, return -EINVAL; data->flex_word = value & ICE_USERDEF_FLEX_WORD_M; - data->flex_offset = (value & ICE_USERDEF_FLEX_OFFS_M) >> - ICE_USERDEF_FLEX_OFFS_S; + data->flex_offset = FIELD_GET(ICE_USERDEF_FLEX_OFFS_M, value); if (data->flex_offset > ICE_USERDEF_FLEX_MAX_OFFS_VAL) return -EINVAL; diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.c b/drivers/net/ethernet/intel/ice/ice_fdir.c index ae089d32ee9d..5840c3e04a5b 100644 --- a/drivers/net/ethernet/intel/ice/ice_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_fdir.c @@ -604,55 +604,32 @@ ice_set_fd_desc_val(struct ice_fd_fltr_desc_ctx *ctx, u64 qword; /* prep QW0 of FD filter programming desc */ - qword = ((u64)ctx->qindex << ICE_FXD_FLTR_QW0_QINDEX_S) & - ICE_FXD_FLTR_QW0_QINDEX_M; - qword |= ((u64)ctx->comp_q << ICE_FXD_FLTR_QW0_COMP_Q_S) & - ICE_FXD_FLTR_QW0_COMP_Q_M; - qword |= ((u64)ctx->comp_report << ICE_FXD_FLTR_QW0_COMP_REPORT_S) & - ICE_FXD_FLTR_QW0_COMP_REPORT_M; - qword |= ((u64)ctx->fd_space << ICE_FXD_FLTR_QW0_FD_SPACE_S) & - ICE_FXD_FLTR_QW0_FD_SPACE_M; - qword |= ((u64)ctx->cnt_index << ICE_FXD_FLTR_QW0_STAT_CNT_S) & - ICE_FXD_FLTR_QW0_STAT_CNT_M; - qword |= ((u64)ctx->cnt_ena << ICE_FXD_FLTR_QW0_STAT_ENA_S) & - ICE_FXD_FLTR_QW0_STAT_ENA_M; - qword |= ((u64)ctx->evict_ena << ICE_FXD_FLTR_QW0_EVICT_ENA_S) & - ICE_FXD_FLTR_QW0_EVICT_ENA_M; - qword |= ((u64)ctx->toq << ICE_FXD_FLTR_QW0_TO_Q_S) & - ICE_FXD_FLTR_QW0_TO_Q_M; - qword |= ((u64)ctx->toq_prio << ICE_FXD_FLTR_QW0_TO_Q_PRI_S) & - ICE_FXD_FLTR_QW0_TO_Q_PRI_M; - qword |= ((u64)ctx->dpu_recipe << ICE_FXD_FLTR_QW0_DPU_RECIPE_S) & - ICE_FXD_FLTR_QW0_DPU_RECIPE_M; - qword |= ((u64)ctx->drop << ICE_FXD_FLTR_QW0_DROP_S) & - ICE_FXD_FLTR_QW0_DROP_M; - qword |= ((u64)ctx->flex_prio << ICE_FXD_FLTR_QW0_FLEX_PRI_S) & - ICE_FXD_FLTR_QW0_FLEX_PRI_M; - qword |= ((u64)ctx->flex_mdid << ICE_FXD_FLTR_QW0_FLEX_MDID_S) & - ICE_FXD_FLTR_QW0_FLEX_MDID_M; - qword |= ((u64)ctx->flex_val << ICE_FXD_FLTR_QW0_FLEX_VAL_S) & - ICE_FXD_FLTR_QW0_FLEX_VAL_M; + qword = FIELD_PREP(ICE_FXD_FLTR_QW0_QINDEX_M, ctx->qindex); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_COMP_Q_M, ctx->comp_q); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_COMP_REPORT_M, ctx->comp_report); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_FD_SPACE_M, ctx->fd_space); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_STAT_CNT_M, ctx->cnt_index); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_STAT_ENA_M, ctx->cnt_ena); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_EVICT_ENA_M, ctx->evict_ena); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_TO_Q_M, ctx->toq); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_TO_Q_PRI_M, ctx->toq_prio); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_DPU_RECIPE_M, ctx->dpu_recipe); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_DROP_M, ctx->drop); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_FLEX_PRI_M, ctx->flex_prio); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_FLEX_MDID_M, ctx->flex_mdid); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW0_FLEX_VAL_M, ctx->flex_val); fdir_desc->qidx_compq_space_stat = cpu_to_le64(qword); /* prep QW1 of FD filter programming desc */ - qword = ((u64)ctx->dtype << ICE_FXD_FLTR_QW1_DTYPE_S) & - ICE_FXD_FLTR_QW1_DTYPE_M; - qword |= ((u64)ctx->pcmd << ICE_FXD_FLTR_QW1_PCMD_S) & - ICE_FXD_FLTR_QW1_PCMD_M; - qword |= ((u64)ctx->desc_prof_prio << ICE_FXD_FLTR_QW1_PROF_PRI_S) & - ICE_FXD_FLTR_QW1_PROF_PRI_M; - qword |= ((u64)ctx->desc_prof << ICE_FXD_FLTR_QW1_PROF_S) & - ICE_FXD_FLTR_QW1_PROF_M; - qword |= ((u64)ctx->fd_vsi << ICE_FXD_FLTR_QW1_FD_VSI_S) & - ICE_FXD_FLTR_QW1_FD_VSI_M; - qword |= ((u64)ctx->swap << ICE_FXD_FLTR_QW1_SWAP_S) & - ICE_FXD_FLTR_QW1_SWAP_M; - qword |= ((u64)ctx->fdid_prio << ICE_FXD_FLTR_QW1_FDID_PRI_S) & - ICE_FXD_FLTR_QW1_FDID_PRI_M; - qword |= ((u64)ctx->fdid_mdid << ICE_FXD_FLTR_QW1_FDID_MDID_S) & - ICE_FXD_FLTR_QW1_FDID_MDID_M; - qword |= ((u64)ctx->fdid << ICE_FXD_FLTR_QW1_FDID_S) & - ICE_FXD_FLTR_QW1_FDID_M; + qword = FIELD_PREP(ICE_FXD_FLTR_QW1_DTYPE_M, ctx->dtype); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW1_PCMD_M, ctx->pcmd); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW1_PROF_PRI_M, ctx->desc_prof_prio); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW1_PROF_M, ctx->desc_prof); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW1_FD_VSI_M, ctx->fd_vsi); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW1_SWAP_M, ctx->swap); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW1_FDID_PRI_M, ctx->fdid_prio); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW1_FDID_MDID_M, ctx->fdid_mdid); + qword |= FIELD_PREP(ICE_FXD_FLTR_QW1_FDID_M, ctx->fdid); fdir_desc->dtype_cmd_vsi_fdid = cpu_to_le64(qword); } diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c index 85c57ec315c4..20d5db88c99f 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c @@ -1414,13 +1414,13 @@ ice_write_prof_mask_reg(struct ice_hw *hw, enum ice_block blk, u16 mask_idx, 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; + val = FIELD_PREP(GLQF_HMASK_MSK_INDEX_M, idx); + val |= FIELD_PREP(GLQF_HMASK_MASK_M, mask); 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; + val = FIELD_PREP(GLQF_FDMASK_MSK_INDEX_M, idx); + val |= FIELD_PREP(GLQF_FDMASK_MASK_M, mask); break; default: ice_debug(hw, ICE_DBG_PKG, "No profile masks for block %d\n", diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c index b47cd43ae871..2a25323105e5 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.c +++ b/drivers/net/ethernet/intel/ice/ice_lag.c @@ -208,8 +208,7 @@ ice_lag_cfg_fltr(struct ice_lag *lag, u32 act, u16 recipe_id, u16 *rule_idx, eth_hdr = s_rule->hdr_data; ice_fill_eth_hdr(eth_hdr); - act |= (vsi_num << ICE_SINGLE_ACT_VSI_ID_S) & - ICE_SINGLE_ACT_VSI_ID_M; + act |= FIELD_PREP(ICE_SINGLE_ACT_VSI_ID_M, vsi_num); s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX); s_rule->recipe_id = cpu_to_le16(recipe_id); @@ -754,9 +753,7 @@ ice_lag_cfg_cp_fltr(struct ice_lag *lag, bool add) s_rule->act = cpu_to_le32(ICE_FWD_TO_VSI | ICE_SINGLE_ACT_LAN_ENABLE | ICE_SINGLE_ACT_VALID_BIT | - ((vsi->vsi_num << - ICE_SINGLE_ACT_VSI_ID_S) & - ICE_SINGLE_ACT_VSI_ID_M)); + FIELD_PREP(ICE_SINGLE_ACT_VSI_ID_M, vsi->vsi_num)); s_rule->hdr_len = cpu_to_le16(ICE_LAG_SRIOV_TRAIN_PKT_LEN); memcpy(s_rule->hdr_data, lacp_train_pkt, LACP_TRAIN_PKT_LEN); opc = ice_aqc_opc_add_sw_rules; diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 5af45932f460..9be724291ef8 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -974,9 +974,8 @@ static void ice_set_dflt_vsi_ctx(struct ice_hw *hw, struct ice_vsi_ctx *ctxt) /* Traffic from VSI can be sent to LAN */ ctxt->info.sw_flags2 = ICE_AQ_VSI_SW_FLAG_LAN_ENA; /* allow all untagged/tagged packets by default on Tx */ - ctxt->info.inner_vlan_flags = ((ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL & - ICE_AQ_VSI_INNER_VLAN_TX_MODE_M) >> - ICE_AQ_VSI_INNER_VLAN_TX_MODE_S); + ctxt->info.inner_vlan_flags = FIELD_PREP(ICE_AQ_VSI_INNER_VLAN_TX_MODE_M, + ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL); /* SVM - by default bits 3 and 4 in inner_vlan_flags are 0's which * results in legacy behavior (show VLAN, DEI, and UP) in descriptor. * @@ -984,15 +983,14 @@ static void ice_set_dflt_vsi_ctx(struct ice_hw *hw, struct ice_vsi_ctx *ctxt) */ if (ice_is_dvm_ena(hw)) { ctxt->info.inner_vlan_flags |= - ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING; + FIELD_PREP(ICE_AQ_VSI_INNER_VLAN_EMODE_M, + ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING); ctxt->info.outer_vlan_flags = - (ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL << - ICE_AQ_VSI_OUTER_VLAN_TX_MODE_S) & - ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M; + FIELD_PREP(ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M, + ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL); ctxt->info.outer_vlan_flags |= - (ICE_AQ_VSI_OUTER_TAG_VLAN_8100 << - ICE_AQ_VSI_OUTER_TAG_TYPE_S) & - ICE_AQ_VSI_OUTER_TAG_TYPE_M; + FIELD_PREP(ICE_AQ_VSI_OUTER_TAG_TYPE_M, + ICE_AQ_VSI_OUTER_TAG_VLAN_8100); ctxt->info.outer_vlan_flags |= FIELD_PREP(ICE_AQ_VSI_OUTER_VLAN_EMODE_M, ICE_AQ_VSI_OUTER_VLAN_EMODE_NOTHING); @@ -1071,10 +1069,8 @@ static int ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) 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); + qmap = FIELD_PREP(ICE_AQ_VSI_TC_Q_OFFSET_M, offset); + qmap |= FIELD_PREP(ICE_AQ_VSI_TC_Q_NUM_M, pow); offset += num_rxq_per_tc; tx_count += num_txq_per_tc; ctxt->info.tc_mapping[i] = cpu_to_le16(qmap); @@ -1157,18 +1153,14 @@ static void ice_set_fd_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi) ctxt->info.max_fd_fltr_shared = cpu_to_le16(vsi->num_bfltr); /* default queue index within the VSI of the default FD */ - val = ((dflt_q << ICE_AQ_VSI_FD_DEF_Q_S) & - ICE_AQ_VSI_FD_DEF_Q_M); + val = FIELD_PREP(ICE_AQ_VSI_FD_DEF_Q_M, dflt_q); /* target queue or queue group to the FD filter */ - val |= ((dflt_q_group << ICE_AQ_VSI_FD_DEF_GRP_S) & - ICE_AQ_VSI_FD_DEF_GRP_M); + val |= FIELD_PREP(ICE_AQ_VSI_FD_DEF_GRP_M, dflt_q_group); ctxt->info.fd_def_q = cpu_to_le16(val); /* queue index on which FD filter completion is reported */ - val = ((report_q << ICE_AQ_VSI_FD_REPORT_Q_S) & - ICE_AQ_VSI_FD_REPORT_Q_M); + val = FIELD_PREP(ICE_AQ_VSI_FD_REPORT_Q_M, report_q); /* priority of the default qindex action */ - val |= ((dflt_q_prio << ICE_AQ_VSI_FD_DEF_PRIORITY_S) & - ICE_AQ_VSI_FD_DEF_PRIORITY_M); + val |= FIELD_PREP(ICE_AQ_VSI_FD_DEF_PRIORITY_M, dflt_q_prio); ctxt->info.fd_report_opt = cpu_to_le16(val); } @@ -1221,10 +1213,8 @@ ice_chnl_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) qcount = min_t(int, vsi->num_rxq, pf->num_lan_msix); pow = order_base_2(qcount); - 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); + qmap = FIELD_PREP(ICE_AQ_VSI_TC_Q_OFFSET_M, offset); + qmap |= FIELD_PREP(ICE_AQ_VSI_TC_Q_NUM_M, pow); ctxt->info.tc_mapping[0] = cpu_to_le16(qmap); ctxt->info.mapping_flags |= cpu_to_le16(ICE_AQ_VSI_Q_MAP_CONTIG); @@ -1795,11 +1785,8 @@ ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio, QRXFLXP_CNTXT_RXDID_PRIO_M | QRXFLXP_CNTXT_TS_M); - regval |= (rxdid << QRXFLXP_CNTXT_RXDID_IDX_S) & - QRXFLXP_CNTXT_RXDID_IDX_M; - - regval |= (prio << QRXFLXP_CNTXT_RXDID_PRIO_S) & - QRXFLXP_CNTXT_RXDID_PRIO_M; + regval |= FIELD_PREP(QRXFLXP_CNTXT_RXDID_IDX_M, rxdid); + regval |= FIELD_PREP(QRXFLXP_CNTXT_RXDID_PRIO_M, prio); if (ena_ts) /* Enable TimeSync on this queue */ @@ -3391,9 +3378,8 @@ ice_vsi_setup_q_map_mqprio(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt, vsi->tc_cfg.ena_tc = ena_tc ? ena_tc : 1; pow = order_base_2(tc0_qcount); - qmap = ((tc0_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); + qmap = FIELD_PREP(ICE_AQ_VSI_TC_Q_OFFSET_M, tc0_offset); + qmap |= FIELD_PREP(ICE_AQ_VSI_TC_Q_NUM_M, pow); ice_for_each_traffic_class(i) { if (!(vsi->tc_cfg.ena_tc & BIT(i))) { diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index b97d116650be..d460d4231b1d 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -980,7 +980,7 @@ static void ice_set_dflt_mib(struct ice_pf *pf) * Octets 13 - 20 are TSA values - leave as zeros */ buf[5] = 0x64; - len = (typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S; + len = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen); offset += len + 2; tlv = (struct ice_lldp_org_tlv *) ((char *)tlv + sizeof(tlv->typelen) + len); @@ -1014,7 +1014,7 @@ static void ice_set_dflt_mib(struct ice_pf *pf) /* Octet 1 left as all zeros - PFC disabled */ buf[0] = 0x08; - len = (typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S; + len = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen); offset += len + 2; if (ice_aq_set_lldp_mib(hw, mib_type, (void *)lldpmib, offset, NULL)) @@ -1771,14 +1771,10 @@ static void ice_handle_mdd_event(struct ice_pf *pf) /* find what triggered an MDD event */ reg = rd32(hw, GL_MDET_TX_PQM); if (reg & GL_MDET_TX_PQM_VALID_M) { - u8 pf_num = (reg & GL_MDET_TX_PQM_PF_NUM_M) >> - GL_MDET_TX_PQM_PF_NUM_S; - u16 vf_num = (reg & GL_MDET_TX_PQM_VF_NUM_M) >> - GL_MDET_TX_PQM_VF_NUM_S; - u8 event = (reg & GL_MDET_TX_PQM_MAL_TYPE_M) >> - GL_MDET_TX_PQM_MAL_TYPE_S; - u16 queue = ((reg & GL_MDET_TX_PQM_QNUM_M) >> - GL_MDET_TX_PQM_QNUM_S); + u8 pf_num = FIELD_GET(GL_MDET_TX_PQM_PF_NUM_M, reg); + u16 vf_num = FIELD_GET(GL_MDET_TX_PQM_VF_NUM_M, reg); + u8 event = FIELD_GET(GL_MDET_TX_PQM_MAL_TYPE_M, reg); + u16 queue = FIELD_GET(GL_MDET_TX_PQM_QNUM_M, reg); if (netif_msg_tx_err(pf)) dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n", @@ -1788,14 +1784,10 @@ static void ice_handle_mdd_event(struct ice_pf *pf) reg = rd32(hw, GL_MDET_TX_TCLAN_BY_MAC(hw)); if (reg & GL_MDET_TX_TCLAN_VALID_M) { - u8 pf_num = (reg & GL_MDET_TX_TCLAN_PF_NUM_M) >> - GL_MDET_TX_TCLAN_PF_NUM_S; - u16 vf_num = (reg & GL_MDET_TX_TCLAN_VF_NUM_M) >> - GL_MDET_TX_TCLAN_VF_NUM_S; - u8 event = (reg & GL_MDET_TX_TCLAN_MAL_TYPE_M) >> - GL_MDET_TX_TCLAN_MAL_TYPE_S; - u16 queue = ((reg & GL_MDET_TX_TCLAN_QNUM_M) >> - GL_MDET_TX_TCLAN_QNUM_S); + u8 pf_num = FIELD_GET(GL_MDET_TX_TCLAN_PF_NUM_M, reg); + u16 vf_num = FIELD_GET(GL_MDET_TX_TCLAN_VF_NUM_M, reg); + u8 event = FIELD_GET(GL_MDET_TX_TCLAN_MAL_TYPE_M, reg); + u16 queue = FIELD_GET(GL_MDET_TX_TCLAN_QNUM_M, reg); if (netif_msg_tx_err(pf)) dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n", @@ -1805,14 +1797,10 @@ static void ice_handle_mdd_event(struct ice_pf *pf) reg = rd32(hw, GL_MDET_RX); if (reg & GL_MDET_RX_VALID_M) { - u8 pf_num = (reg & GL_MDET_RX_PF_NUM_M) >> - GL_MDET_RX_PF_NUM_S; - u16 vf_num = (reg & GL_MDET_RX_VF_NUM_M) >> - GL_MDET_RX_VF_NUM_S; - u8 event = (reg & GL_MDET_RX_MAL_TYPE_M) >> - GL_MDET_RX_MAL_TYPE_S; - u16 queue = ((reg & GL_MDET_RX_QNUM_M) >> - GL_MDET_RX_QNUM_S); + u8 pf_num = FIELD_GET(GL_MDET_RX_PF_NUM_M, reg); + u16 vf_num = FIELD_GET(GL_MDET_RX_VF_NUM_M, reg); + u8 event = FIELD_GET(GL_MDET_RX_MAL_TYPE_M, reg); + u16 queue = FIELD_GET(GL_MDET_RX_QNUM_M, reg); if (netif_msg_rx_err(pf)) dev_info(dev, "Malicious Driver Detection event %d on RX queue %d PF# %d VF# %d\n", @@ -3135,8 +3123,8 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) /* we have a reset warning */ ena_mask &= ~PFINT_OICR_GRST_M; - reset = (rd32(hw, GLGEN_RSTAT) & GLGEN_RSTAT_RESET_TYPE_M) >> - GLGEN_RSTAT_RESET_TYPE_S; + reset = FIELD_GET(GLGEN_RSTAT_RESET_TYPE_M, + rd32(hw, GLGEN_RSTAT)); if (reset == ICE_RESET_CORER) pf->corer_count++; @@ -8016,8 +8004,8 @@ static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue) struct ice_hw *hw = &pf->hw; u32 head, val = 0; - head = (rd32(hw, QTX_COMM_HEAD(vsi->txq_map[txqueue])) & - QTX_COMM_HEAD_HEAD_M) >> QTX_COMM_HEAD_HEAD_S; + head = FIELD_GET(QTX_COMM_HEAD_HEAD_M, + rd32(hw, QTX_COMM_HEAD(vsi->txq_map[txqueue]))); /* Read interrupt register */ val = rd32(hw, GLINT_DYN_CTL(tx_ring->q_vector->reg_idx)); diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c index f6f52a248066..d4e05d2cb30c 100644 --- a/drivers/net/ethernet/intel/ice/ice_nvm.c +++ b/drivers/net/ethernet/intel/ice/ice_nvm.c @@ -571,8 +571,8 @@ ice_get_nvm_ver_info(struct ice_hw *hw, enum ice_bank_select bank, struct ice_nv return status; } - nvm->major = (ver & ICE_NVM_VER_HI_MASK) >> ICE_NVM_VER_HI_SHIFT; - nvm->minor = (ver & ICE_NVM_VER_LO_MASK) >> ICE_NVM_VER_LO_SHIFT; + nvm->major = FIELD_GET(ICE_NVM_VER_HI_MASK, ver); + nvm->minor = FIELD_GET(ICE_NVM_VER_LO_MASK, ver); status = ice_read_nvm_sr_copy(hw, bank, ICE_SR_NVM_EETRACK_LO, &eetrack_lo); if (status) { @@ -706,9 +706,9 @@ ice_get_orom_ver_info(struct ice_hw *hw, enum ice_bank_select bank, struct ice_o combo_ver = le32_to_cpu(civd.combo_ver); - orom->major = (u8)((combo_ver & ICE_OROM_VER_MASK) >> ICE_OROM_VER_SHIFT); - orom->patch = (u8)(combo_ver & ICE_OROM_VER_PATCH_MASK); - orom->build = (u16)((combo_ver & ICE_OROM_VER_BUILD_MASK) >> ICE_OROM_VER_BUILD_SHIFT); + orom->major = FIELD_GET(ICE_OROM_VER_MASK, combo_ver); + orom->patch = FIELD_GET(ICE_OROM_VER_PATCH_MASK, combo_ver); + orom->build = FIELD_GET(ICE_OROM_VER_BUILD_MASK, combo_ver); return 0; } @@ -950,7 +950,8 @@ static int ice_determine_active_flash_banks(struct ice_hw *hw) } /* Check that the control word indicates validity */ - if ((ctrl_word & ICE_SR_CTRL_WORD_1_M) >> ICE_SR_CTRL_WORD_1_S != ICE_SR_CTRL_WORD_VALID) { + if (FIELD_GET(ICE_SR_CTRL_WORD_1_M, ctrl_word) != + ICE_SR_CTRL_WORD_VALID) { ice_debug(hw, ICE_DBG_NVM, "Shadow RAM control word is invalid\n"); return -EIO; } @@ -1027,7 +1028,7 @@ int ice_init_nvm(struct ice_hw *hw) * as the blank mode may be used in the factory line. */ gens_stat = rd32(hw, GLNVM_GENS); - sr_size = (gens_stat & GLNVM_GENS_SR_SIZE_M) >> GLNVM_GENS_SR_SIZE_S; + sr_size = FIELD_GET(GLNVM_GENS_SR_SIZE_M, gens_stat); /* Switching to words (sr_size contains power of 2) */ flash->sr_words = BIT(sr_size) * ICE_SR_WORDS_IN_1KB; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index 239cf8a2ee80..95d4c4ed4a62 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -1140,9 +1140,9 @@ static int ice_ptp_check_tx_fifo(struct ice_ptp_port *port) } if (offs & 0x1) - phy_sts = (val & Q_REG_FIFO13_M) >> Q_REG_FIFO13_S; + phy_sts = FIELD_GET(Q_REG_FIFO13_M, val); else - phy_sts = (val & Q_REG_FIFO02_M) >> Q_REG_FIFO02_S; + phy_sts = FIELD_GET(Q_REG_FIFO02_M, val); if (phy_sts & FIFO_EMPTY) { port->tx_fifo_busy_cnt = FIFO_OK; @@ -1359,8 +1359,8 @@ static int ice_ptp_tx_ena_intr(struct ice_pf *pf, bool ena, u32 threshold) if (ena) { val |= Q_REG_TX_MEM_GBL_CFG_INTR_ENA_M; val &= ~Q_REG_TX_MEM_GBL_CFG_INTR_THR_M; - val |= ((threshold << Q_REG_TX_MEM_GBL_CFG_INTR_THR_S) & - Q_REG_TX_MEM_GBL_CFG_INTR_THR_M); + val |= FIELD_PREP(Q_REG_TX_MEM_GBL_CFG_INTR_THR_M, + threshold); } else { val &= ~Q_REG_TX_MEM_GBL_CFG_INTR_ENA_M; } @@ -1505,8 +1505,7 @@ ice_ptp_cfg_extts(struct ice_pf *pf, bool ena, unsigned int chan, u32 gpio_pin, * + num_in_channels * tmr_idx */ func = 1 + chan + (tmr_idx * 3); - gpio_reg = ((func << GLGEN_GPIO_CTL_PIN_FUNC_S) & - GLGEN_GPIO_CTL_PIN_FUNC_M); + gpio_reg = FIELD_PREP(GLGEN_GPIO_CTL_PIN_FUNC_M, func); pf->ptp.ext_ts_chan |= (1 << chan); } else { /* clear the values we set to reset defaults */ @@ -1616,7 +1615,7 @@ static int ice_ptp_cfg_clkout(struct ice_pf *pf, unsigned int chan, /* 4. write GPIO CTL reg */ func = 8 + chan + (tmr_idx * 4); val = GLGEN_GPIO_CTL_PIN_DIR_M | - ((func << GLGEN_GPIO_CTL_PIN_FUNC_S) & GLGEN_GPIO_CTL_PIN_FUNC_M); + FIELD_PREP(GLGEN_GPIO_CTL_PIN_FUNC_M, func); wr32(hw, GLGEN_GPIO_CTL(gpio_pin), val); /* Store the value if requested */ diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index 2f4a621254e8..d174a4eeb899 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -1387,8 +1387,7 @@ void ice_sched_get_psm_clk_freq(struct ice_hw *hw) u32 val, clk_src; val = rd32(hw, GLGEN_CLKSTAT_SRC); - clk_src = (val & GLGEN_CLKSTAT_SRC_PSM_CLK_SRC_M) >> - GLGEN_CLKSTAT_SRC_PSM_CLK_SRC_S; + clk_src = FIELD_GET(GLGEN_CLKSTAT_SRC_PSM_CLK_SRC_M, val); #define PSM_CLK_SRC_367_MHZ 0x0 #define PSM_CLK_SRC_416_MHZ 0x1 diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index 6d33dd647c78..4ee349fe6409 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -106,10 +106,8 @@ static void ice_dis_vf_mappings(struct ice_vf *vf) for (v = first; v <= last; v++) { u32 reg; - reg = (((1 << GLINT_VECT2FUNC_IS_PF_S) & - GLINT_VECT2FUNC_IS_PF_M) | - ((hw->pf_id << GLINT_VECT2FUNC_PF_NUM_S) & - GLINT_VECT2FUNC_PF_NUM_M)); + reg = FIELD_PREP(GLINT_VECT2FUNC_IS_PF_M, 1) | + FIELD_PREP(GLINT_VECT2FUNC_PF_NUM_M, hw->pf_id); wr32(hw, GLINT_VECT2FUNC(v), reg); } @@ -275,24 +273,20 @@ static void ice_ena_vf_msix_mappings(struct ice_vf *vf) (device_based_first_msix + vf->num_msix) - 1; device_based_vf_id = vf->vf_id + hw->func_caps.vf_base_id; - reg = (((device_based_first_msix << VPINT_ALLOC_FIRST_S) & - VPINT_ALLOC_FIRST_M) | - ((device_based_last_msix << VPINT_ALLOC_LAST_S) & - VPINT_ALLOC_LAST_M) | VPINT_ALLOC_VALID_M); + reg = FIELD_PREP(VPINT_ALLOC_FIRST_M, device_based_first_msix) | + FIELD_PREP(VPINT_ALLOC_LAST_M, device_based_last_msix) | + VPINT_ALLOC_VALID_M; wr32(hw, VPINT_ALLOC(vf->vf_id), reg); - reg = (((device_based_first_msix << VPINT_ALLOC_PCI_FIRST_S) - & VPINT_ALLOC_PCI_FIRST_M) | - ((device_based_last_msix << VPINT_ALLOC_PCI_LAST_S) & - VPINT_ALLOC_PCI_LAST_M) | VPINT_ALLOC_PCI_VALID_M); + reg = FIELD_PREP(VPINT_ALLOC_PCI_FIRST_M, device_based_first_msix) | + FIELD_PREP(VPINT_ALLOC_PCI_LAST_M, device_based_last_msix) | + VPINT_ALLOC_PCI_VALID_M; wr32(hw, VPINT_ALLOC_PCI(vf->vf_id), reg); /* map the interrupts to its functions */ for (v = pf_based_first_msix; v <= pf_based_last_msix; v++) { - reg = (((device_based_vf_id << GLINT_VECT2FUNC_VF_NUM_S) & - GLINT_VECT2FUNC_VF_NUM_M) | - ((hw->pf_id << GLINT_VECT2FUNC_PF_NUM_S) & - GLINT_VECT2FUNC_PF_NUM_M)); + reg = FIELD_PREP(GLINT_VECT2FUNC_VF_NUM_M, device_based_vf_id) | + FIELD_PREP(GLINT_VECT2FUNC_PF_NUM_M, hw->pf_id); wr32(hw, GLINT_VECT2FUNC(v), reg); } @@ -325,10 +319,8 @@ static void ice_ena_vf_q_mappings(struct ice_vf *vf, u16 max_txq, u16 max_rxq) * VFNUMQ value should be set to (number of queues - 1). A value * of 0 means 1 queue and a value of 255 means 256 queues */ - reg = (((vsi->txq_map[0] << VPLAN_TX_QBASE_VFFIRSTQ_S) & - VPLAN_TX_QBASE_VFFIRSTQ_M) | - (((max_txq - 1) << VPLAN_TX_QBASE_VFNUMQ_S) & - VPLAN_TX_QBASE_VFNUMQ_M)); + reg = FIELD_PREP(VPLAN_TX_QBASE_VFFIRSTQ_M, vsi->txq_map[0]) | + FIELD_PREP(VPLAN_TX_QBASE_VFNUMQ_M, max_txq - 1); wr32(hw, VPLAN_TX_QBASE(vf->vf_id), reg); } else { dev_err(dev, "Scattered mode for VF Tx queues is not yet implemented\n"); @@ -343,10 +335,8 @@ static void ice_ena_vf_q_mappings(struct ice_vf *vf, u16 max_txq, u16 max_rxq) * VFNUMQ value should be set to (number of queues - 1). A value * of 0 means 1 queue and a value of 255 means 256 queues */ - reg = (((vsi->rxq_map[0] << VPLAN_RX_QBASE_VFFIRSTQ_S) & - VPLAN_RX_QBASE_VFFIRSTQ_M) | - (((max_rxq - 1) << VPLAN_RX_QBASE_VFNUMQ_S) & - VPLAN_RX_QBASE_VFNUMQ_M)); + reg = FIELD_PREP(VPLAN_RX_QBASE_VFFIRSTQ_M, vsi->rxq_map[0]) | + FIELD_PREP(VPLAN_RX_QBASE_VFNUMQ_M, max_rxq - 1); wr32(hw, VPLAN_RX_QBASE(vf->vf_id), reg); } else { dev_err(dev, "Scattered mode for VF Rx queues is not yet implemented\n"); @@ -1328,8 +1318,7 @@ ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event) dev_dbg(ice_pf_to_dev(pf), "GLDCB_RTCTQ: 0x%08x\n", gldcb_rtctq); /* event returns device global Rx queue number */ - queue = (gldcb_rtctq & GLDCB_RTCTQ_RXQNUM_M) >> - GLDCB_RTCTQ_RXQNUM_S; + queue = FIELD_GET(GLDCB_RTCTQ_RXQNUM_M, gldcb_rtctq); vf = ice_get_vf_from_pfq(pf, ice_globalq_to_pfq(pf, queue)); if (!vf) diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index ee19f3aa3d19..dc5b34ca2d4a 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -2492,25 +2492,24 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, switch (f_info->fltr_act) { case ICE_FWD_TO_VSI: - act |= (f_info->fwd_id.hw_vsi_id << ICE_SINGLE_ACT_VSI_ID_S) & - ICE_SINGLE_ACT_VSI_ID_M; + act |= FIELD_PREP(ICE_SINGLE_ACT_VSI_ID_M, + f_info->fwd_id.hw_vsi_id); if (f_info->lkup_type != ICE_SW_LKUP_VLAN) act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_VALID_BIT; break; case ICE_FWD_TO_VSI_LIST: act |= ICE_SINGLE_ACT_VSI_LIST; - act |= (f_info->fwd_id.vsi_list_id << - ICE_SINGLE_ACT_VSI_LIST_ID_S) & - ICE_SINGLE_ACT_VSI_LIST_ID_M; + act |= FIELD_PREP(ICE_SINGLE_ACT_VSI_LIST_ID_M, + f_info->fwd_id.vsi_list_id); if (f_info->lkup_type != ICE_SW_LKUP_VLAN) act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_VALID_BIT; break; case ICE_FWD_TO_Q: act |= ICE_SINGLE_ACT_TO_Q; - act |= (f_info->fwd_id.q_id << ICE_SINGLE_ACT_Q_INDEX_S) & - ICE_SINGLE_ACT_Q_INDEX_M; + act |= FIELD_PREP(ICE_SINGLE_ACT_Q_INDEX_M, + f_info->fwd_id.q_id); break; case ICE_DROP_PACKET: act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_DROP | @@ -2520,10 +2519,9 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, q_rgn = f_info->qgrp_size > 0 ? (u8)ilog2(f_info->qgrp_size) : 0; act |= ICE_SINGLE_ACT_TO_Q; - act |= (f_info->fwd_id.q_id << ICE_SINGLE_ACT_Q_INDEX_S) & - ICE_SINGLE_ACT_Q_INDEX_M; - act |= (q_rgn << ICE_SINGLE_ACT_Q_REGION_S) & - ICE_SINGLE_ACT_Q_REGION_M; + act |= FIELD_PREP(ICE_SINGLE_ACT_Q_INDEX_M, + f_info->fwd_id.q_id); + act |= FIELD_PREP(ICE_SINGLE_ACT_Q_REGION_M, q_rgn); break; default: return; @@ -2649,7 +2647,7 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent, m_ent->fltr_info.fwd_id.hw_vsi_id; act = ICE_LG_ACT_VSI_FORWARDING | ICE_LG_ACT_VALID_BIT; - act |= (id << ICE_LG_ACT_VSI_LIST_ID_S) & ICE_LG_ACT_VSI_LIST_ID_M; + act |= FIELD_PREP(ICE_LG_ACT_VSI_LIST_ID_M, id); if (m_ent->vsi_count > 1) act |= ICE_LG_ACT_VSI_LIST; lg_act->act[0] = cpu_to_le32(act); @@ -2657,16 +2655,15 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent, /* Second action descriptor type */ act = ICE_LG_ACT_GENERIC; - act |= (1 << ICE_LG_ACT_GENERIC_VALUE_S) & ICE_LG_ACT_GENERIC_VALUE_M; + act |= FIELD_PREP(ICE_LG_ACT_GENERIC_VALUE_M, 1); lg_act->act[1] = cpu_to_le32(act); - act = (ICE_LG_ACT_GENERIC_OFF_RX_DESC_PROF_IDX << - ICE_LG_ACT_GENERIC_OFFSET_S) & ICE_LG_ACT_GENERIC_OFFSET_M; + act = FIELD_PREP(ICE_LG_ACT_GENERIC_OFFSET_M, + ICE_LG_ACT_GENERIC_OFF_RX_DESC_PROF_IDX); /* Third action Marker value */ act |= ICE_LG_ACT_GENERIC; - act |= (sw_marker << ICE_LG_ACT_GENERIC_VALUE_S) & - ICE_LG_ACT_GENERIC_VALUE_M; + act |= FIELD_PREP(ICE_LG_ACT_GENERIC_VALUE_M, sw_marker); lg_act->act[2] = cpu_to_le32(act); @@ -2675,9 +2672,9 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent, ice_aqc_opc_update_sw_rules); /* Update the action to point to the large action ID */ - rx_tx->act = cpu_to_le32(ICE_SINGLE_ACT_PTR | - ((l_id << ICE_SINGLE_ACT_PTR_VAL_S) & - ICE_SINGLE_ACT_PTR_VAL_M)); + act = ICE_SINGLE_ACT_PTR; + act |= FIELD_PREP(ICE_SINGLE_ACT_PTR_VAL_M, l_id); + rx_tx->act = cpu_to_le32(act); /* Use the filter rule ID of the previously created rule with single * act. Once the update happens, hardware will treat this as large @@ -4426,8 +4423,8 @@ ice_alloc_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, int status; buf->num_elems = cpu_to_le16(num_items); - buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) & - ICE_AQC_RES_TYPE_M) | alloc_shared); + buf->res_type = cpu_to_le16(FIELD_PREP(ICE_AQC_RES_TYPE_M, type) | + alloc_shared); status = ice_aq_alloc_free_res(hw, buf, buf_len, ice_aqc_opc_alloc_res); if (status) @@ -4454,8 +4451,8 @@ ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, int status; buf->num_elems = cpu_to_le16(num_items); - buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) & - ICE_AQC_RES_TYPE_M) | alloc_shared); + buf->res_type = cpu_to_le16(FIELD_PREP(ICE_AQC_RES_TYPE_M, type) | + alloc_shared); buf->elem[0].e.sw_resp = cpu_to_le16(counter_id); status = ice_aq_alloc_free_res(hw, buf, buf_len, ice_aqc_opc_free_res); @@ -4481,18 +4478,15 @@ int ice_share_res(struct ice_hw *hw, u16 type, u8 shared, u16 res_id) { DEFINE_FLEX(struct ice_aqc_alloc_free_res_elem, buf, elem, 1); u16 buf_len = __struct_size(buf); + u16 res_type; int status; buf->num_elems = cpu_to_le16(1); + res_type = FIELD_PREP(ICE_AQC_RES_TYPE_M, type); if (shared) - buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) & - ICE_AQC_RES_TYPE_M) | - ICE_AQC_RES_TYPE_FLAG_SHARED); - else - buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) & - ICE_AQC_RES_TYPE_M) & - ~ICE_AQC_RES_TYPE_FLAG_SHARED); + res_type |= ICE_AQC_RES_TYPE_FLAG_SHARED; + buf->res_type = cpu_to_le16(res_type); buf->elem[0].e.sw_resp = cpu_to_le16(res_id); status = ice_aq_alloc_free_res(hw, buf, buf_len, ice_aqc_opc_share_res); @@ -5024,8 +5018,8 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, entry->chain_idx = chain_idx; content->result_indx = ICE_AQ_RECIPE_RESULT_EN | - ((chain_idx << ICE_AQ_RECIPE_RESULT_DATA_S) & - ICE_AQ_RECIPE_RESULT_DATA_M); + FIELD_PREP(ICE_AQ_RECIPE_RESULT_DATA_M, + chain_idx); clear_bit(chain_idx, result_idx_bm); chain_idx = find_first_bit(result_idx_bm, ICE_MAX_FV_WORDS); @@ -6125,23 +6119,22 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, switch (rinfo->sw_act.fltr_act) { case ICE_FWD_TO_VSI: - act |= (rinfo->sw_act.fwd_id.hw_vsi_id << - ICE_SINGLE_ACT_VSI_ID_S) & ICE_SINGLE_ACT_VSI_ID_M; + act |= FIELD_PREP(ICE_SINGLE_ACT_VSI_ID_M, + rinfo->sw_act.fwd_id.hw_vsi_id); act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_VALID_BIT; break; case ICE_FWD_TO_Q: act |= ICE_SINGLE_ACT_TO_Q; - act |= (rinfo->sw_act.fwd_id.q_id << ICE_SINGLE_ACT_Q_INDEX_S) & - ICE_SINGLE_ACT_Q_INDEX_M; + act |= FIELD_PREP(ICE_SINGLE_ACT_Q_INDEX_M, + rinfo->sw_act.fwd_id.q_id); break; case ICE_FWD_TO_QGRP: q_rgn = rinfo->sw_act.qgrp_size > 0 ? (u8)ilog2(rinfo->sw_act.qgrp_size) : 0; act |= ICE_SINGLE_ACT_TO_Q; - act |= (rinfo->sw_act.fwd_id.q_id << ICE_SINGLE_ACT_Q_INDEX_S) & - ICE_SINGLE_ACT_Q_INDEX_M; - act |= (q_rgn << ICE_SINGLE_ACT_Q_REGION_S) & - ICE_SINGLE_ACT_Q_REGION_M; + act |= FIELD_PREP(ICE_SINGLE_ACT_Q_INDEX_M, + rinfo->sw_act.fwd_id.q_id); + act |= FIELD_PREP(ICE_SINGLE_ACT_Q_REGION_M, q_rgn); break; case ICE_DROP_PACKET: act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_DROP | diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 59617f055e35..74d13cc5a3a7 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -1493,9 +1493,9 @@ static void ice_set_wb_on_itr(struct ice_q_vector *q_vector) * be static in non-adaptive mode (user configured) */ wr32(&vsi->back->hw, GLINT_DYN_CTL(q_vector->reg_idx), - ((ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S) & - GLINT_DYN_CTL_ITR_INDX_M) | GLINT_DYN_CTL_INTENA_MSK_M | - GLINT_DYN_CTL_WB_ON_ITR_M); + FIELD_PREP(GLINT_DYN_CTL_ITR_INDX_M, ICE_ITR_NONE) | + FIELD_PREP(GLINT_DYN_CTL_INTENA_MSK_M, 1) | + FIELD_PREP(GLINT_DYN_CTL_WB_ON_ITR_M, 1)); q_vector->wb_on_itr = true; } diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index d4ad0739b57b..c925813ec9ca 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -3102,7 +3102,7 @@ static struct ice_vlan ice_vc_to_vlan(struct virtchnl_vlan *vc_vlan) { struct ice_vlan vlan = { 0 }; - vlan.prio = (vc_vlan->tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; + vlan.prio = FIELD_GET(VLAN_PRIO_MASK, vc_vlan->tci); vlan.vid = vc_vlan->tci & VLAN_VID_MASK; vlan.tpid = vc_vlan->tpid; diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c index 9ee7ab207b37..f001553e1a1a 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c @@ -1463,16 +1463,15 @@ ice_vf_verify_rx_desc(struct ice_vf *vf, struct ice_vf_fdir_ctx *ctx, 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) { + if (FIELD_GET(ICE_FXD_FLTR_WB_QW1_DD_M, stat_err) != + 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; + prog_id = FIELD_GET(ICE_FXD_FLTR_WB_QW1_PROG_ID_M, stat_err); 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", @@ -1491,8 +1490,7 @@ ice_vf_verify_rx_desc(struct ice_vf *vf, struct ice_vf_fdir_ctx *ctx, goto err_exit; } - error = (stat_err & ICE_FXD_FLTR_WB_QW1_FAIL_M) >> - ICE_FXD_FLTR_WB_QW1_FAIL_S; + error = FIELD_GET(ICE_FXD_FLTR_WB_QW1_FAIL_M, stat_err); 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", @@ -1507,8 +1505,7 @@ ice_vf_verify_rx_desc(struct ice_vf *vf, struct ice_vf_fdir_ctx *ctx, goto err_exit; } - error = (stat_err & ICE_FXD_FLTR_WB_QW1_FAIL_PROF_M) >> - ICE_FXD_FLTR_WB_QW1_FAIL_PROF_S; + error = FIELD_GET(ICE_FXD_FLTR_WB_QW1_FAIL_PROF_M, stat_err); 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; diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c index 76266e709a39..2e9ad27cb9d1 100644 --- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c @@ -131,6 +131,7 @@ static int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena) { struct ice_hw *hw = &vsi->back->hw; struct ice_vsi_ctx *ctxt; + u8 *ivf; int err; /* do not allow modifying VLAN stripping when a port VLAN is configured @@ -143,19 +144,24 @@ static int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena) if (!ctxt) return -ENOMEM; + ivf = &ctxt->info.inner_vlan_flags; + /* Here we are configuring what the VSI should do with the VLAN tag in * the Rx packet. We can either leave the tag in the packet or put it in * the Rx descriptor. */ - if (ena) + if (ena) { /* Strip VLAN tag from Rx packet and put it in the desc */ - ctxt->info.inner_vlan_flags = ICE_AQ_VSI_INNER_VLAN_EMODE_STR_BOTH; - else + *ivf = FIELD_PREP(ICE_AQ_VSI_INNER_VLAN_EMODE_M, + ICE_AQ_VSI_INNER_VLAN_EMODE_STR_BOTH); + } else { /* Disable stripping. Leave tag in packet */ - ctxt->info.inner_vlan_flags = ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING; + *ivf = FIELD_PREP(ICE_AQ_VSI_INNER_VLAN_EMODE_M, + ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING); + } /* Allow all packets untagged/tagged */ - ctxt->info.inner_vlan_flags |= ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL; + *ivf |= ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL; ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID); @@ -481,10 +487,11 @@ int ice_vsi_ena_outer_stripping(struct ice_vsi *vsi, u16 tpid) ctxt->info.outer_vlan_flags = vsi->info.outer_vlan_flags & ~(ICE_AQ_VSI_OUTER_VLAN_EMODE_M | ICE_AQ_VSI_OUTER_TAG_TYPE_M); ctxt->info.outer_vlan_flags |= - ((ICE_AQ_VSI_OUTER_VLAN_EMODE_SHOW_BOTH << - ICE_AQ_VSI_OUTER_VLAN_EMODE_S) | - ((tag_type << ICE_AQ_VSI_OUTER_TAG_TYPE_S) & - ICE_AQ_VSI_OUTER_TAG_TYPE_M)); + /* we want EMODE_SHOW_BOTH, but that value is zero, so the line + * above clears it well enough that we don't need to try to set + * zero here, so just do the tag type + */ + FIELD_PREP(ICE_AQ_VSI_OUTER_TAG_TYPE_M, tag_type); err = ice_update_vsi(hw, vsi->idx, ctxt, NULL); if (err) @@ -589,11 +596,9 @@ int ice_vsi_ena_outer_insertion(struct ice_vsi *vsi, u16 tpid) ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M | ICE_AQ_VSI_OUTER_TAG_TYPE_M); ctxt->info.outer_vlan_flags |= - ((ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL << - ICE_AQ_VSI_OUTER_VLAN_TX_MODE_S) & - ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M) | - ((tag_type << ICE_AQ_VSI_OUTER_TAG_TYPE_S) & - ICE_AQ_VSI_OUTER_TAG_TYPE_M); + FIELD_PREP(ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M, + ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL) | + FIELD_PREP(ICE_AQ_VSI_OUTER_TAG_TYPE_M, tag_type); err = ice_update_vsi(hw, vsi->idx, ctxt, NULL); if (err) @@ -642,9 +647,8 @@ int ice_vsi_dis_outer_insertion(struct ice_vsi *vsi) ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M); ctxt->info.outer_vlan_flags |= ICE_AQ_VSI_OUTER_VLAN_BLOCK_TX_DESC | - ((ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL << - ICE_AQ_VSI_OUTER_VLAN_TX_MODE_S) & - ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M); + FIELD_PREP(ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M, + ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL); err = ice_update_vsi(hw, vsi->idx, ctxt, NULL); if (err) @@ -702,8 +706,7 @@ __ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, u16 vlan_info, u16 tpid) ctxt->info.outer_vlan_flags = (ICE_AQ_VSI_OUTER_VLAN_EMODE_SHOW << ICE_AQ_VSI_OUTER_VLAN_EMODE_S) | - ((tag_type << ICE_AQ_VSI_OUTER_TAG_TYPE_S) & - ICE_AQ_VSI_OUTER_TAG_TYPE_M) | + FIELD_PREP(ICE_AQ_VSI_OUTER_TAG_TYPE_M, tag_type) | ICE_AQ_VSI_OUTER_VLAN_BLOCK_TX_DESC | (ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ACCEPTUNTAGGED << ICE_AQ_VSI_OUTER_VLAN_TX_MODE_S) | diff --git a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c index 81288a17da2a..447753495c53 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c @@ -328,10 +328,9 @@ static void idpf_tx_singleq_build_ctx_desc(struct idpf_queue *txq, if (offload->tso_segs) { qw1 |= IDPF_TX_CTX_DESC_TSO << IDPF_TXD_CTX_QW1_CMD_S; - qw1 |= ((u64)offload->tso_len << IDPF_TXD_CTX_QW1_TSO_LEN_S) & - IDPF_TXD_CTX_QW1_TSO_LEN_M; - qw1 |= ((u64)offload->mss << IDPF_TXD_CTX_QW1_MSS_S) & - IDPF_TXD_CTX_QW1_MSS_M; + qw1 |= FIELD_PREP(IDPF_TXD_CTX_QW1_TSO_LEN_M, + offload->tso_len); + qw1 |= FIELD_PREP(IDPF_TXD_CTX_QW1_MSS_M, offload->mss); u64_stats_update_begin(&txq->stats_sync); u64_stats_inc(&txq->q_stats.tx.lso_pkts); diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index a005626129a5..ad730d20fbe6 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -505,9 +505,9 @@ static void idpf_rx_post_buf_refill(struct idpf_sw_queue *refillq, u16 buf_id) /* store the buffer ID and the SW maintained GEN bit to the refillq */ refillq->ring[nta] = - ((buf_id << IDPF_RX_BI_BUFID_S) & IDPF_RX_BI_BUFID_M) | - (!!(test_bit(__IDPF_Q_GEN_CHK, refillq->flags)) << - IDPF_RX_BI_GEN_S); + FIELD_PREP(IDPF_RX_BI_BUFID_M, buf_id) | + FIELD_PREP(IDPF_RX_BI_GEN_M, + test_bit(__IDPF_Q_GEN_CHK, refillq->flags)); if (unlikely(++nta == refillq->desc_count)) { nta = 0; @@ -1825,14 +1825,14 @@ static bool idpf_tx_clean_complq(struct idpf_queue *complq, int budget, u16 gen; /* if the descriptor isn't done, no work yet to do */ - gen = (le16_to_cpu(tx_desc->qid_comptype_gen) & - IDPF_TXD_COMPLQ_GEN_M) >> IDPF_TXD_COMPLQ_GEN_S; + gen = le16_get_bits(tx_desc->qid_comptype_gen, + IDPF_TXD_COMPLQ_GEN_M); if (test_bit(__IDPF_Q_GEN_CHK, complq->flags) != gen) break; /* Find necessary info of TX queue to clean buffers */ - rel_tx_qid = (le16_to_cpu(tx_desc->qid_comptype_gen) & - IDPF_TXD_COMPLQ_QID_M) >> IDPF_TXD_COMPLQ_QID_S; + rel_tx_qid = le16_get_bits(tx_desc->qid_comptype_gen, + IDPF_TXD_COMPLQ_QID_M); if (rel_tx_qid >= complq->txq_grp->num_txq || !complq->txq_grp->txqs[rel_tx_qid]) { dev_err(&complq->vport->adapter->pdev->dev, @@ -1842,9 +1842,8 @@ static bool idpf_tx_clean_complq(struct idpf_queue *complq, int budget, tx_q = complq->txq_grp->txqs[rel_tx_qid]; /* Determine completion type */ - ctype = (le16_to_cpu(tx_desc->qid_comptype_gen) & - IDPF_TXD_COMPLQ_COMPL_TYPE_M) >> - IDPF_TXD_COMPLQ_COMPL_TYPE_S; + ctype = le16_get_bits(tx_desc->qid_comptype_gen, + IDPF_TXD_COMPLQ_COMPL_TYPE_M); switch (ctype) { case IDPF_TXD_COMPLT_RE: hw_head = le16_to_cpu(tx_desc->q_head_compl_tag.q_head); @@ -1945,11 +1944,10 @@ void idpf_tx_splitq_build_ctb(union idpf_tx_flex_desc *desc, u16 td_cmd, u16 size) { desc->q.qw1.cmd_dtype = - cpu_to_le16(params->dtype & IDPF_FLEX_TXD_QW1_DTYPE_M); + le16_encode_bits(params->dtype, IDPF_FLEX_TXD_QW1_DTYPE_M); desc->q.qw1.cmd_dtype |= - cpu_to_le16((td_cmd << IDPF_FLEX_TXD_QW1_CMD_S) & - IDPF_FLEX_TXD_QW1_CMD_M); - desc->q.qw1.buf_size = cpu_to_le16((u16)size); + le16_encode_bits(td_cmd, IDPF_FLEX_TXD_QW1_CMD_M); + desc->q.qw1.buf_size = cpu_to_le16(size); desc->q.qw1.l2tags.l2tag1 = cpu_to_le16(params->td_tag); } @@ -2843,8 +2841,9 @@ static void idpf_rx_splitq_extract_csum_bits(struct virtchnl2_rx_flex_desc_adv_n qword1); csum->ipv6exadd = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_IPV6EXADD_M, qword0); - csum->raw_csum_inv = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_RAW_CSUM_INV_M, - le16_to_cpu(rx_desc->ptype_err_fflags0)); + csum->raw_csum_inv = + le16_get_bits(rx_desc->ptype_err_fflags0, + VIRTCHNL2_RX_FLEX_DESC_ADV_RAW_CSUM_INV_M); csum->raw_csum = le16_to_cpu(rx_desc->misc.raw_cs); } @@ -2938,8 +2937,8 @@ static int idpf_rx_process_skb_fields(struct idpf_queue *rxq, struct idpf_rx_ptype_decoded decoded; u16 rx_ptype; - rx_ptype = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_PTYPE_M, - le16_to_cpu(rx_desc->ptype_err_fflags0)); + rx_ptype = le16_get_bits(rx_desc->ptype_err_fflags0, + VIRTCHNL2_RX_FLEX_DESC_ADV_PTYPE_M); decoded = rxq->vport->rx_ptype_lkup[rx_ptype]; /* If we don't know the ptype we can't do anything else with it. Just @@ -2953,8 +2952,8 @@ static int idpf_rx_process_skb_fields(struct idpf_queue *rxq, skb->protocol = eth_type_trans(skb, rxq->vport->netdev); - if (FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_RSC_M, - le16_to_cpu(rx_desc->hdrlen_flags))) + if (le16_get_bits(rx_desc->hdrlen_flags, + VIRTCHNL2_RX_FLEX_DESC_ADV_RSC_M)) return idpf_rx_rsc(rxq, skb, rx_desc, &decoded); idpf_rx_splitq_extract_csum_bits(rx_desc, &csum_bits); @@ -3148,8 +3147,8 @@ static int idpf_rx_splitq_clean(struct idpf_queue *rxq, int budget) dma_rmb(); /* if the descriptor isn't done, no work yet to do */ - gen_id = le16_to_cpu(rx_desc->pktlen_gen_bufq_id); - gen_id = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_GEN_M, gen_id); + gen_id = le16_get_bits(rx_desc->pktlen_gen_bufq_id, + VIRTCHNL2_RX_FLEX_DESC_ADV_GEN_M); if (test_bit(__IDPF_Q_GEN_CHK, rxq->flags) != gen_id) break; @@ -3164,9 +3163,8 @@ static int idpf_rx_splitq_clean(struct idpf_queue *rxq, int budget) continue; } - pkt_len = le16_to_cpu(rx_desc->pktlen_gen_bufq_id); - pkt_len = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_LEN_PBUF_M, - pkt_len); + pkt_len = le16_get_bits(rx_desc->pktlen_gen_bufq_id, + VIRTCHNL2_RX_FLEX_DESC_ADV_LEN_PBUF_M); hbo = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_HBO_M, rx_desc->status_err0_qw1); @@ -3183,14 +3181,12 @@ static int idpf_rx_splitq_clean(struct idpf_queue *rxq, int budget) goto bypass_hsplit; } - hdr_len = le16_to_cpu(rx_desc->hdrlen_flags); - hdr_len = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_LEN_HDR_M, - hdr_len); + hdr_len = le16_get_bits(rx_desc->hdrlen_flags, + VIRTCHNL2_RX_FLEX_DESC_ADV_LEN_HDR_M); bypass_hsplit: - bufq_id = le16_to_cpu(rx_desc->pktlen_gen_bufq_id); - bufq_id = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_BUFQ_ID_M, - bufq_id); + bufq_id = le16_get_bits(rx_desc->pktlen_gen_bufq_id, + VIRTCHNL2_RX_FLEX_DESC_ADV_BUFQ_ID_M); rxq_set = container_of(rxq, struct idpf_rxq_set, rxq); if (!bufq_id) diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c index 8d6e44ee1895..64dfc362d1dc 100644 --- a/drivers/net/ethernet/intel/igb/e1000_82575.c +++ b/drivers/net/ethernet/intel/igb/e1000_82575.c @@ -222,8 +222,7 @@ static s32 igb_init_phy_params_82575(struct e1000_hw *hw) } /* set lan id */ - hw->bus.func = (rd32(E1000_STATUS) & E1000_STATUS_FUNC_MASK) >> - E1000_STATUS_FUNC_SHIFT; + hw->bus.func = FIELD_GET(E1000_STATUS_FUNC_MASK, rd32(E1000_STATUS)); /* Set phy->phy_addr and phy->id. */ ret_val = igb_get_phy_id_82575(hw); @@ -262,8 +261,8 @@ static s32 igb_init_phy_params_82575(struct e1000_hw *hw) if (ret_val) goto out; - data = (data & E1000_M88E1112_MAC_CTRL_1_MODE_MASK) >> - E1000_M88E1112_MAC_CTRL_1_MODE_SHIFT; + data = FIELD_GET(E1000_M88E1112_MAC_CTRL_1_MODE_MASK, + data); if (data == E1000_M88E1112_AUTO_COPPER_SGMII || data == E1000_M88E1112_AUTO_COPPER_BASEX) hw->mac.ops.check_for_link = @@ -330,8 +329,7 @@ static s32 igb_init_nvm_params_82575(struct e1000_hw *hw) u32 eecd = rd32(E1000_EECD); u16 size; - size = (u16)((eecd & E1000_EECD_SIZE_EX_MASK) >> - E1000_EECD_SIZE_EX_SHIFT); + size = FIELD_GET(E1000_EECD_SIZE_EX_MASK, eecd); /* Added to a constant, "size" becomes the left-shift value * for setting word_size. @@ -2798,7 +2796,7 @@ static s32 igb_get_thermal_sensor_data_generic(struct e1000_hw *hw) return 0; hw->nvm.ops.read(hw, ets_offset, 1, &ets_cfg); - if (((ets_cfg & NVM_ETS_TYPE_MASK) >> NVM_ETS_TYPE_SHIFT) + if (FIELD_GET(NVM_ETS_TYPE_MASK, ets_cfg) != NVM_ETS_TYPE_EMC) return E1000_NOT_IMPLEMENTED; @@ -2808,10 +2806,8 @@ static s32 igb_get_thermal_sensor_data_generic(struct e1000_hw *hw) for (i = 1; i < num_sensors; i++) { hw->nvm.ops.read(hw, (ets_offset + i), 1, &ets_sensor); - sensor_index = ((ets_sensor & NVM_ETS_DATA_INDEX_MASK) >> - NVM_ETS_DATA_INDEX_SHIFT); - sensor_location = ((ets_sensor & NVM_ETS_DATA_LOC_MASK) >> - NVM_ETS_DATA_LOC_SHIFT); + sensor_index = FIELD_GET(NVM_ETS_DATA_INDEX_MASK, ets_sensor); + sensor_location = FIELD_GET(NVM_ETS_DATA_LOC_MASK, ets_sensor); if (sensor_location != 0) hw->phy.ops.read_i2c_byte(hw, @@ -2859,20 +2855,17 @@ static s32 igb_init_thermal_sensor_thresh_generic(struct e1000_hw *hw) return 0; hw->nvm.ops.read(hw, ets_offset, 1, &ets_cfg); - if (((ets_cfg & NVM_ETS_TYPE_MASK) >> NVM_ETS_TYPE_SHIFT) + if (FIELD_GET(NVM_ETS_TYPE_MASK, ets_cfg) != NVM_ETS_TYPE_EMC) return E1000_NOT_IMPLEMENTED; - low_thresh_delta = ((ets_cfg & NVM_ETS_LTHRES_DELTA_MASK) >> - NVM_ETS_LTHRES_DELTA_SHIFT); + low_thresh_delta = FIELD_GET(NVM_ETS_LTHRES_DELTA_MASK, ets_cfg); num_sensors = (ets_cfg & NVM_ETS_NUM_SENSORS_MASK); for (i = 1; i <= num_sensors; i++) { hw->nvm.ops.read(hw, (ets_offset + i), 1, &ets_sensor); - sensor_index = ((ets_sensor & NVM_ETS_DATA_INDEX_MASK) >> - NVM_ETS_DATA_INDEX_SHIFT); - sensor_location = ((ets_sensor & NVM_ETS_DATA_LOC_MASK) >> - NVM_ETS_DATA_LOC_SHIFT); + sensor_index = FIELD_GET(NVM_ETS_DATA_INDEX_MASK, ets_sensor); + sensor_location = FIELD_GET(NVM_ETS_DATA_LOC_MASK, ets_sensor); therm_limit = ets_sensor & NVM_ETS_DATA_HTHRESH_MASK; hw->phy.ops.write_i2c_byte(hw, diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.c b/drivers/net/ethernet/intel/igb/e1000_i210.c index b9b9d35494d2..503b239868e8 100644 --- a/drivers/net/ethernet/intel/igb/e1000_i210.c +++ b/drivers/net/ethernet/intel/igb/e1000_i210.c @@ -5,9 +5,9 @@ * e1000_i211 */ -#include <linux/types.h> +#include <linux/bitfield.h> #include <linux/if_ether.h> - +#include <linux/types.h> #include "e1000_hw.h" #include "e1000_i210.h" @@ -473,7 +473,7 @@ s32 igb_read_invm_version(struct e1000_hw *hw, /* Check if we have second version location used */ else if ((i == 1) && ((*record & E1000_INVM_VER_FIELD_TWO) == 0)) { - version = (*record & E1000_INVM_VER_FIELD_ONE) >> 3; + version = FIELD_GET(E1000_INVM_VER_FIELD_ONE, *record); status = 0; break; } @@ -483,8 +483,8 @@ s32 igb_read_invm_version(struct e1000_hw *hw, else if ((((*record & E1000_INVM_VER_FIELD_ONE) == 0) && ((*record & 0x3) == 0)) || (((*record & 0x3) != 0) && (i != 1))) { - version = (*next_record & E1000_INVM_VER_FIELD_TWO) - >> 13; + version = FIELD_GET(E1000_INVM_VER_FIELD_TWO, + *next_record); status = 0; break; } @@ -493,15 +493,15 @@ s32 igb_read_invm_version(struct e1000_hw *hw, */ else if (((*record & E1000_INVM_VER_FIELD_TWO) == 0) && ((*record & 0x3) == 0)) { - version = (*record & E1000_INVM_VER_FIELD_ONE) >> 3; + version = FIELD_GET(E1000_INVM_VER_FIELD_ONE, *record); status = 0; break; } } if (!status) { - invm_ver->invm_major = (version & E1000_INVM_MAJOR_MASK) - >> E1000_INVM_MAJOR_SHIFT; + invm_ver->invm_major = FIELD_GET(E1000_INVM_MAJOR_MASK, + version); invm_ver->invm_minor = version & E1000_INVM_MINOR_MASK; } /* Read Image Type */ @@ -520,7 +520,8 @@ s32 igb_read_invm_version(struct e1000_hw *hw, ((*record & E1000_INVM_IMGTYPE_FIELD) == 0)) || ((((*record & 0x3) != 0) && (i != 1)))) { invm_ver->invm_img_type = - (*next_record & E1000_INVM_IMGTYPE_FIELD) >> 23; + FIELD_GET(E1000_INVM_IMGTYPE_FIELD, + *next_record); status = 0; break; } diff --git a/drivers/net/ethernet/intel/igb/e1000_mac.c b/drivers/net/ethernet/intel/igb/e1000_mac.c index 5a23b9cfec6c..fa3dfafd2bb1 100644 --- a/drivers/net/ethernet/intel/igb/e1000_mac.c +++ b/drivers/net/ethernet/intel/igb/e1000_mac.c @@ -56,7 +56,7 @@ s32 igb_get_bus_info_pcie(struct e1000_hw *hw) } reg = rd32(E1000_STATUS); - bus->func = (reg & E1000_STATUS_FUNC_MASK) >> E1000_STATUS_FUNC_SHIFT; + bus->func = FIELD_GET(E1000_STATUS_FUNC_MASK, reg); return 0; } diff --git a/drivers/net/ethernet/intel/igb/e1000_nvm.c b/drivers/net/ethernet/intel/igb/e1000_nvm.c index fa136e6e9328..2dcd64d6dec3 100644 --- a/drivers/net/ethernet/intel/igb/e1000_nvm.c +++ b/drivers/net/ethernet/intel/igb/e1000_nvm.c @@ -1,9 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2007 - 2018 Intel Corporation. */ -#include <linux/if_ether.h> +#include <linux/bitfield.h> #include <linux/delay.h> - +#include <linux/if_ether.h> #include "e1000_mac.h" #include "e1000_nvm.h" @@ -708,10 +708,10 @@ void igb_get_fw_version(struct e1000_hw *hw, struct e1000_fw_version *fw_vers) */ if ((etrack_test & NVM_MAJOR_MASK) != NVM_ETRACK_VALID) { hw->nvm.ops.read(hw, NVM_VERSION, 1, &fw_version); - fw_vers->eep_major = (fw_version & NVM_MAJOR_MASK) - >> NVM_MAJOR_SHIFT; - fw_vers->eep_minor = (fw_version & NVM_MINOR_MASK) - >> NVM_MINOR_SHIFT; + fw_vers->eep_major = FIELD_GET(NVM_MAJOR_MASK, + fw_version); + fw_vers->eep_minor = FIELD_GET(NVM_MINOR_MASK, + fw_version); fw_vers->eep_build = (fw_version & NVM_IMAGE_ID_MASK); goto etrack_id; } @@ -753,15 +753,13 @@ void igb_get_fw_version(struct e1000_hw *hw, struct e1000_fw_version *fw_vers) return; } hw->nvm.ops.read(hw, NVM_VERSION, 1, &fw_version); - fw_vers->eep_major = (fw_version & NVM_MAJOR_MASK) - >> NVM_MAJOR_SHIFT; + fw_vers->eep_major = FIELD_GET(NVM_MAJOR_MASK, fw_version); /* check for old style version format in newer images*/ if ((fw_version & NVM_NEW_DEC_MASK) == 0x0) { eeprom_verl = (fw_version & NVM_COMB_VER_MASK); } else { - eeprom_verl = (fw_version & NVM_MINOR_MASK) - >> NVM_MINOR_SHIFT; + eeprom_verl = FIELD_GET(NVM_MINOR_MASK, fw_version); } /* Convert minor value to hex before assigning to output struct * Val to be converted will not be higher than 99, per tool output diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.c b/drivers/net/ethernet/intel/igb/e1000_phy.c index a018000f7db9..cd65008c7ef5 100644 --- a/drivers/net/ethernet/intel/igb/e1000_phy.c +++ b/drivers/net/ethernet/intel/igb/e1000_phy.c @@ -1,9 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2007 - 2018 Intel Corporation. */ -#include <linux/if_ether.h> +#include <linux/bitfield.h> #include <linux/delay.h> - +#include <linux/if_ether.h> #include "e1000_mac.h" #include "e1000_phy.h" @@ -255,7 +255,7 @@ s32 igb_read_phy_reg_i2c(struct e1000_hw *hw, u32 offset, u16 *data) } /* Need to byte-swap the 16-bit value. */ - *data = ((i2ccmd >> 8) & 0x00FF) | ((i2ccmd << 8) & 0xFF00); + *data = ((i2ccmd >> 8) & 0x00FF) | FIELD_PREP(0xFF00, i2ccmd); return 0; } @@ -282,7 +282,7 @@ s32 igb_write_phy_reg_i2c(struct e1000_hw *hw, u32 offset, u16 data) } /* Swap the data bytes for the I2C interface */ - phy_data_swapped = ((data >> 8) & 0x00FF) | ((data << 8) & 0xFF00); + phy_data_swapped = ((data >> 8) & 0x00FF) | FIELD_PREP(0xFF00, data); /* Set up Op-code, Phy Address, and register address in the I2CCMD * register. The MAC will take care of interfacing with the @@ -1682,8 +1682,7 @@ s32 igb_get_cable_length_m88(struct e1000_hw *hw) if (ret_val) goto out; - index = (phy_data & M88E1000_PSSR_CABLE_LENGTH) >> - M88E1000_PSSR_CABLE_LENGTH_SHIFT; + index = FIELD_GET(M88E1000_PSSR_CABLE_LENGTH, phy_data); if (index >= ARRAY_SIZE(e1000_m88_cable_length_table) - 1) { ret_val = -E1000_ERR_PHY; goto out; @@ -1796,8 +1795,7 @@ s32 igb_get_cable_length_m88_gen2(struct e1000_hw *hw) if (ret_val) goto out; - index = (phy_data & M88E1000_PSSR_CABLE_LENGTH) >> - M88E1000_PSSR_CABLE_LENGTH_SHIFT; + index = FIELD_GET(M88E1000_PSSR_CABLE_LENGTH, phy_data); if (index >= ARRAY_SIZE(e1000_m88_cable_length_table) - 1) { ret_val = -E1000_ERR_PHY; goto out; @@ -2578,8 +2576,7 @@ s32 igb_get_cable_length_82580(struct e1000_hw *hw) if (ret_val) goto out; - length = (phy_data & I82580_DSTATUS_CABLE_LENGTH) >> - I82580_DSTATUS_CABLE_LENGTH_SHIFT; + length = FIELD_GET(I82580_DSTATUS_CABLE_LENGTH, phy_data); if (length == E1000_CABLE_LENGTH_UNDEFINED) ret_val = -E1000_ERR_PHY; diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index d868a70732f4..b66199c9bb3a 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -2432,7 +2432,7 @@ static int igb_get_ts_info(struct net_device *dev, } } -#define ETHER_TYPE_FULL_MASK ((__force __be16)~0) +#define ETHER_TYPE_FULL_MASK cpu_to_be16(FIELD_MAX(U16_MAX)) static int igb_get_ethtool_nfc_entry(struct igb_adapter *adapter, struct ethtool_rxnfc *cmd) { @@ -2711,8 +2711,7 @@ static int igb_rxnfc_write_etype_filter(struct igb_adapter *adapter, etqf |= (etype & E1000_ETQF_ETYPE_MASK); etqf &= ~E1000_ETQF_QUEUE_MASK; - etqf |= ((input->action << E1000_ETQF_QUEUE_SHIFT) - & E1000_ETQF_QUEUE_MASK); + etqf |= FIELD_PREP(E1000_ETQF_QUEUE_MASK, input->action); etqf |= E1000_ETQF_QUEUE_ENABLE; wr32(E1000_ETQF(i), etqf); @@ -2731,8 +2730,8 @@ static int igb_rxnfc_write_vlan_prio_filter(struct igb_adapter *adapter, u32 vlapqf; vlapqf = rd32(E1000_VLAPQF); - vlan_priority = (ntohs(input->filter.vlan_tci) & VLAN_PRIO_MASK) - >> VLAN_PRIO_SHIFT; + vlan_priority = FIELD_GET(VLAN_PRIO_MASK, + ntohs(input->filter.vlan_tci)); queue_index = (vlapqf >> (vlan_priority * 4)) & E1000_VLAPQF_QUEUE_MASK; /* check whether this vlan prio is already set */ @@ -2815,7 +2814,7 @@ static void igb_clear_vlan_prio_filter(struct igb_adapter *adapter, u8 vlan_priority; u32 vlapqf; - vlan_priority = (vlan_tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; + vlan_priority = FIELD_GET(VLAN_PRIO_MASK, vlan_tci); vlapqf = rd32(E1000_VLAPQF); vlapqf &= ~E1000_VLAPQF_P_VALID(vlan_priority); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index b2295caa2f0a..4df8d4153aa5 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -7295,7 +7295,7 @@ static int igb_set_vf_promisc(struct igb_adapter *adapter, u32 *msgbuf, u32 vf) static int igb_set_vf_multicasts(struct igb_adapter *adapter, u32 *msgbuf, u32 vf) { - int n = (msgbuf[0] & E1000_VT_MSGINFO_MASK) >> E1000_VT_MSGINFO_SHIFT; + int n = FIELD_GET(E1000_VT_MSGINFO_MASK, msgbuf[0]); u16 *hash_list = (u16 *)&msgbuf[1]; struct vf_data_storage *vf_data = &adapter->vf_data[vf]; int i; @@ -7555,7 +7555,7 @@ static int igb_ndo_set_vf_vlan(struct net_device *netdev, int vf, static int igb_set_vf_vlan_msg(struct igb_adapter *adapter, u32 *msgbuf, u32 vf) { - int add = (msgbuf[0] & E1000_VT_MSGINFO_MASK) >> E1000_VT_MSGINFO_SHIFT; + int add = FIELD_GET(E1000_VT_MSGINFO_MASK, msgbuf[0]); int vid = (msgbuf[1] & E1000_VLVF_VLANID_MASK); int ret; @@ -9810,8 +9810,7 @@ static void igb_set_vf_rate_limit(struct e1000_hw *hw, int vf, int tx_rate, tx_rate; bcnrc_val = E1000_RTTBCNRC_RS_ENA; - bcnrc_val |= ((rf_int << E1000_RTTBCNRC_RF_INT_SHIFT) & - E1000_RTTBCNRC_RF_INT_MASK); + bcnrc_val |= FIELD_PREP(E1000_RTTBCNRC_RF_INT_MASK, rf_int); bcnrc_val |= (rf_dec & E1000_RTTBCNRC_RF_DEC_MASK); } else { bcnrc_val = 0; @@ -10000,8 +9999,7 @@ static void igb_init_dmac(struct igb_adapter *adapter, u32 pba) hwm = 64 * (pba - 6); reg = rd32(E1000_FCRTC); reg &= ~E1000_FCRTC_RTH_COAL_MASK; - reg |= ((hwm << E1000_FCRTC_RTH_COAL_SHIFT) - & E1000_FCRTC_RTH_COAL_MASK); + reg |= FIELD_PREP(E1000_FCRTC_RTH_COAL_MASK, hwm); wr32(E1000_FCRTC, reg); /* Set the DMA Coalescing Rx threshold to PBA - 2 * max @@ -10010,8 +10008,7 @@ static void igb_init_dmac(struct igb_adapter *adapter, u32 pba) dmac_thr = pba - 10; reg = rd32(E1000_DMACR); reg &= ~E1000_DMACR_DMACTHR_MASK; - reg |= ((dmac_thr << E1000_DMACR_DMACTHR_SHIFT) - & E1000_DMACR_DMACTHR_MASK); + reg |= FIELD_PREP(E1000_DMACR_DMACTHR_MASK, dmac_thr); /* transition to L0x or L1 if available..*/ reg |= (E1000_DMACR_DMAC_EN | E1000_DMACR_DMAC_LX_MASK); diff --git a/drivers/net/ethernet/intel/igbvf/mbx.c b/drivers/net/ethernet/intel/igbvf/mbx.c index a3cd7ac48d4b..d15282ee5ea8 100644 --- a/drivers/net/ethernet/intel/igbvf/mbx.c +++ b/drivers/net/ethernet/intel/igbvf/mbx.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2009 - 2018 Intel Corporation. */ +#include <linux/bitfield.h> #include "mbx.h" /** diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index fd712585af27..a4d4f00e6a87 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -3,25 +3,25 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/module.h> -#include <linux/types.h> -#include <linux/init.h> -#include <linux/pci.h> -#include <linux/vmalloc.h> -#include <linux/pagemap.h> +#include <linux/bitfield.h> #include <linux/delay.h> -#include <linux/netdevice.h> -#include <linux/tcp.h> -#include <linux/ipv6.h> -#include <linux/slab.h> -#include <net/checksum.h> -#include <net/ip6_checksum.h> -#include <linux/mii.h> #include <linux/ethtool.h> #include <linux/if_vlan.h> +#include <linux/init.h> +#include <linux/ipv6.h> +#include <linux/mii.h> +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/pagemap.h> +#include <linux/pci.h> #include <linux/prefetch.h> #include <linux/sctp.h> - +#include <linux/slab.h> +#include <linux/tcp.h> +#include <linux/types.h> +#include <linux/vmalloc.h> +#include <net/checksum.h> +#include <net/ip6_checksum.h> #include "igbvf.h" char igbvf_driver_name[] = "igbvf"; @@ -273,9 +273,8 @@ static bool igbvf_clean_rx_irq(struct igbvf_adapter *adapter, * that case, it fills the header buffer and spills the rest * into the page. */ - hlen = (le16_to_cpu(rx_desc->wb.lower.lo_dword.hs_rss.hdr_info) - & E1000_RXDADV_HDRBUFLEN_MASK) >> - E1000_RXDADV_HDRBUFLEN_SHIFT; + hlen = le16_get_bits(rx_desc->wb.lower.lo_dword.hs_rss.hdr_info, + E1000_RXDADV_HDRBUFLEN_MASK); if (hlen > adapter->rx_ps_hdr_size) hlen = adapter->rx_ps_hdr_size; diff --git a/drivers/net/ethernet/intel/igc/igc_base.c b/drivers/net/ethernet/intel/igc/igc_base.c index a1d815af507d..9fae8bdec2a7 100644 --- a/drivers/net/ethernet/intel/igc/igc_base.c +++ b/drivers/net/ethernet/intel/igc/igc_base.c @@ -68,8 +68,7 @@ static s32 igc_init_nvm_params_base(struct igc_hw *hw) u32 eecd = rd32(IGC_EECD); u16 size; - size = (u16)((eecd & IGC_EECD_SIZE_EX_MASK) >> - IGC_EECD_SIZE_EX_SHIFT); + size = FIELD_GET(IGC_EECD_SIZE_EX_MASK, eecd); /* Added to a constant, "size" becomes the left-shift value * for setting word_size. @@ -162,8 +161,7 @@ static s32 igc_init_phy_params_base(struct igc_hw *hw) phy->reset_delay_us = 100; /* set lan id */ - hw->bus.func = (rd32(IGC_STATUS) & IGC_STATUS_FUNC_MASK) >> - IGC_STATUS_FUNC_SHIFT; + hw->bus.func = FIELD_GET(IGC_STATUS_FUNC_MASK, rd32(IGC_STATUS)); /* Make sure the PHY is in a good state. Several people have reported * firmware leaving the PHY's page select register set to something diff --git a/drivers/net/ethernet/intel/igc/igc_i225.c b/drivers/net/ethernet/intel/igc/igc_i225.c index 17546a035ab1..0dd61719f1ed 100644 --- a/drivers/net/ethernet/intel/igc/igc_i225.c +++ b/drivers/net/ethernet/intel/igc/igc_i225.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2018 Intel Corporation */ +#include <linux/bitfield.h> #include <linux/delay.h> #include "igc_hw.h" @@ -578,9 +579,8 @@ s32 igc_set_ltr_i225(struct igc_hw *hw, bool link) /* Calculate tw_system (nsec). */ if (speed == SPEED_100) { - tw_system = ((rd32(IGC_EEE_SU) & - IGC_TW_SYSTEM_100_MASK) >> - IGC_TW_SYSTEM_100_SHIFT) * 500; + tw_system = FIELD_GET(IGC_TW_SYSTEM_100_MASK, + rd32(IGC_EEE_SU)) * 500; } else { tw_system = (rd32(IGC_EEE_SU) & IGC_TW_SYSTEM_1000_MASK) * 500; diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 61db1d3bfa0b..ba8d3fe186ae 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -3452,8 +3452,8 @@ static int igc_write_flex_filter_ll(struct igc_adapter *adapter, /* Configure filter */ queuing = input->length & IGC_FHFT_LENGTH_MASK; - queuing |= (input->rx_queue << IGC_FHFT_QUEUE_SHIFT) & IGC_FHFT_QUEUE_MASK; - queuing |= (input->prio << IGC_FHFT_PRIO_SHIFT) & IGC_FHFT_PRIO_MASK; + queuing |= FIELD_PREP(IGC_FHFT_QUEUE_MASK, input->rx_queue); + queuing |= FIELD_PREP(IGC_FHFT_PRIO_MASK, input->prio); if (input->immediate_irq) queuing |= IGC_FHFT_IMM_INT; @@ -3712,8 +3712,7 @@ static int igc_enable_nfc_rule(struct igc_adapter *adapter, } if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) { - int prio = (rule->filter.vlan_tci & VLAN_PRIO_MASK) >> - VLAN_PRIO_SHIFT; + int prio = FIELD_GET(VLAN_PRIO_MASK, rule->filter.vlan_tci); err = igc_add_vlan_prio_filter(adapter, prio, rule->action); if (err) @@ -3735,8 +3734,7 @@ static void igc_disable_nfc_rule(struct igc_adapter *adapter, igc_del_etype_filter(adapter, rule->filter.etype); if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) { - int prio = (rule->filter.vlan_tci & VLAN_PRIO_MASK) >> - VLAN_PRIO_SHIFT; + int prio = FIELD_GET(VLAN_PRIO_MASK, rule->filter.vlan_tci); igc_del_vlan_prio_filter(adapter, prio); } diff --git a/drivers/net/ethernet/intel/igc/igc_phy.c b/drivers/net/ethernet/intel/igc/igc_phy.c index 53b77c969c85..7cd8716d2ffa 100644 --- a/drivers/net/ethernet/intel/igc/igc_phy.c +++ b/drivers/net/ethernet/intel/igc/igc_phy.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2018 Intel Corporation */ +#include <linux/bitfield.h> #include "igc_phy.h" /** @@ -726,7 +727,7 @@ static s32 igc_write_xmdio_reg(struct igc_hw *hw, u16 addr, */ s32 igc_write_phy_reg_gpy(struct igc_hw *hw, u32 offset, u16 data) { - u8 dev_addr = (offset & GPY_MMD_MASK) >> GPY_MMD_SHIFT; + u8 dev_addr = FIELD_GET(GPY_MMD_MASK, offset); s32 ret_val; offset = offset & GPY_REG_MASK; @@ -757,7 +758,7 @@ s32 igc_write_phy_reg_gpy(struct igc_hw *hw, u32 offset, u16 data) */ s32 igc_read_phy_reg_gpy(struct igc_hw *hw, u32 offset, u16 *data) { - u8 dev_addr = (offset & GPY_MMD_MASK) >> GPY_MMD_SHIFT; + u8 dev_addr = FIELD_GET(GPY_MMD_MASK, offset); s32 ret_val; offset = offset & GPY_REG_MASK; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c index 100388968e4d..0470b69d834c 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c @@ -794,7 +794,7 @@ static s32 ixgbe_set_vmdq_82598(struct ixgbe_hw *hw, u32 rar, u32 vmdq) rar_high = IXGBE_READ_REG(hw, IXGBE_RAH(rar)); rar_high &= ~IXGBE_RAH_VIND_MASK; - rar_high |= ((vmdq << IXGBE_RAH_VIND_SHIFT) & IXGBE_RAH_VIND_MASK); + rar_high |= FIELD_PREP(IXGBE_RAH_VIND_MASK, vmdq); IXGBE_WRITE_REG(hw, IXGBE_RAH(rar), rar_high); return 0; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 878dd8dff528..7d7bd44448c4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -684,7 +684,7 @@ void ixgbe_set_lan_id_multi_port_pcie(struct ixgbe_hw *hw) u32 reg; reg = IXGBE_READ_REG(hw, IXGBE_STATUS); - bus->func = (reg & IXGBE_STATUS_LAN_ID) >> IXGBE_STATUS_LAN_ID_SHIFT; + bus->func = FIELD_GET(IXGBE_STATUS_LAN_ID, reg); bus->lan_id = bus->func; /* check for a port swap */ @@ -695,8 +695,8 @@ void ixgbe_set_lan_id_multi_port_pcie(struct ixgbe_hw *hw) /* Get MAC instance from EEPROM for configuring CS4227 */ if (hw->device_id == IXGBE_DEV_ID_X550EM_A_SFP) { hw->eeprom.ops.read(hw, IXGBE_EEPROM_CTRL_4, &ee_ctrl_4); - bus->instance_id = (ee_ctrl_4 & IXGBE_EE_CTRL_4_INST_ID) >> - IXGBE_EE_CTRL_4_INST_ID_SHIFT; + bus->instance_id = FIELD_GET(IXGBE_EE_CTRL_4_INST_ID, + ee_ctrl_4); } } @@ -870,10 +870,9 @@ s32 ixgbe_init_eeprom_params_generic(struct ixgbe_hw *hw) * SPI EEPROM is assumed here. This code would need to * change if a future EEPROM is not SPI. */ - eeprom_size = (u16)((eec & IXGBE_EEC_SIZE) >> - IXGBE_EEC_SIZE_SHIFT); + eeprom_size = FIELD_GET(IXGBE_EEC_SIZE, eec); eeprom->word_size = BIT(eeprom_size + - IXGBE_EEPROM_WORD_SIZE_SHIFT); + IXGBE_EEPROM_WORD_SIZE_SHIFT); } if (eec & IXGBE_EEC_ADDR_SIZE) @@ -3946,10 +3945,10 @@ s32 ixgbe_get_thermal_sensor_data_generic(struct ixgbe_hw *hw) if (status) return status; - sensor_index = ((ets_sensor & IXGBE_ETS_DATA_INDEX_MASK) >> - IXGBE_ETS_DATA_INDEX_SHIFT); - sensor_location = ((ets_sensor & IXGBE_ETS_DATA_LOC_MASK) >> - IXGBE_ETS_DATA_LOC_SHIFT); + sensor_index = FIELD_GET(IXGBE_ETS_DATA_INDEX_MASK, + ets_sensor); + sensor_location = FIELD_GET(IXGBE_ETS_DATA_LOC_MASK, + ets_sensor); if (sensor_location != 0) { status = hw->phy.ops.read_i2c_byte(hw, @@ -3993,8 +3992,7 @@ s32 ixgbe_init_thermal_sensor_thresh_generic(struct ixgbe_hw *hw) if (status) return status; - low_thresh_delta = ((ets_cfg & IXGBE_ETS_LTHRES_DELTA_MASK) >> - IXGBE_ETS_LTHRES_DELTA_SHIFT); + low_thresh_delta = FIELD_GET(IXGBE_ETS_LTHRES_DELTA_MASK, ets_cfg); num_sensors = (ets_cfg & IXGBE_ETS_NUM_SENSORS_MASK); if (num_sensors > IXGBE_MAX_SENSORS) num_sensors = IXGBE_MAX_SENSORS; @@ -4008,10 +4006,10 @@ s32 ixgbe_init_thermal_sensor_thresh_generic(struct ixgbe_hw *hw) ets_offset + 1 + i); continue; } - sensor_index = ((ets_sensor & IXGBE_ETS_DATA_INDEX_MASK) >> - IXGBE_ETS_DATA_INDEX_SHIFT); - sensor_location = ((ets_sensor & IXGBE_ETS_DATA_LOC_MASK) >> - IXGBE_ETS_DATA_LOC_SHIFT); + sensor_index = FIELD_GET(IXGBE_ETS_DATA_INDEX_MASK, + ets_sensor); + sensor_location = FIELD_GET(IXGBE_ETS_DATA_LOC_MASK, + ets_sensor); therm_limit = ets_sensor & IXGBE_ETS_DATA_HTHRESH_MASK; hw->phy.ops.write_i2c_byte(hw, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c index 7311bd545acf..18d63c8c2ff4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c @@ -670,8 +670,8 @@ void ixgbe_configure_fcoe(struct ixgbe_adapter *adapter) int fcoe_i_h = fcoe->offset + ((i + fcreta_size) % fcoe->indices); fcoe_q_h = adapter->rx_ring[fcoe_i_h]->reg_idx; - fcoe_q_h = (fcoe_q_h << IXGBE_FCRETA_ENTRY_HIGH_SHIFT) & - IXGBE_FCRETA_ENTRY_HIGH_MASK; + fcoe_q_h = FIELD_PREP(IXGBE_FCRETA_ENTRY_HIGH_MASK, + fcoe_q_h); } fcoe_i = fcoe->offset + (i % fcoe->indices); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 94bde2cad0f4..227415d61efc 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -11371,7 +11371,7 @@ static pci_ers_result_t ixgbe_io_error_detected(struct pci_dev *pdev, if ((pf_func & 1) == (pdev->devfn & 1)) { unsigned int device_id; - vf = (req_id & 0x7F) >> 1; + vf = FIELD_GET(0x7F, req_id); e_dev_err("VF %d has caused a PCIe error\n", vf); e_dev_err("TLP: dw0: %8.8x\tdw1: %8.8x\tdw2: " "%8.8x\tdw3: %8.8x\n", diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c index 689470c1e8ad..ca31638c6fb8 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c @@ -276,9 +276,8 @@ s32 ixgbe_identify_phy_generic(struct ixgbe_hw *hw) return 0; if (hw->phy.nw_mng_if_sel) { - phy_addr = (hw->phy.nw_mng_if_sel & - IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD) >> - IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD_SHIFT; + phy_addr = FIELD_GET(IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD, + hw->phy.nw_mng_if_sel); if (ixgbe_probe_phy(hw, phy_addr)) return 0; else @@ -1448,8 +1447,7 @@ s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw) ret_val = hw->eeprom.ops.read(hw, data_offset, &eword); if (ret_val) goto err_eeprom; - control = (eword & IXGBE_CONTROL_MASK_NL) >> - IXGBE_CONTROL_SHIFT_NL; + control = FIELD_GET(IXGBE_CONTROL_MASK_NL, eword); edata = eword & IXGBE_DATA_MASK_NL; switch (control) { case IXGBE_DELAY_NL: diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index 9cfdfa8a4355..f8c6ca9fea82 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -363,8 +363,7 @@ int ixgbe_pci_sriov_configure(struct pci_dev *dev, int num_vfs) static int ixgbe_set_vf_multicasts(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) { - int entries = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) - >> IXGBE_VT_MSGINFO_SHIFT; + int entries = FIELD_GET(IXGBE_VT_MSGINFO_MASK, msgbuf[0]); u16 *hash_list = (u16 *)&msgbuf[1]; struct vf_data_storage *vfinfo = &adapter->vfinfo[vf]; struct ixgbe_hw *hw = &adapter->hw; @@ -969,7 +968,7 @@ static int ixgbe_set_vf_mac_addr(struct ixgbe_adapter *adapter, static int ixgbe_set_vf_vlan_msg(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) { - u32 add = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) >> IXGBE_VT_MSGINFO_SHIFT; + u32 add = FIELD_GET(IXGBE_VT_MSGINFO_MASK, msgbuf[0]); u32 vid = (msgbuf[1] & IXGBE_VLVF_VLANID_MASK); u8 tcs = adapter->hw_tcs; @@ -992,8 +991,7 @@ static int ixgbe_set_vf_macvlan_msg(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) { u8 *new_mac = ((u8 *)(&msgbuf[1])); - int index = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) >> - IXGBE_VT_MSGINFO_SHIFT; + int index = FIELD_GET(IXGBE_VT_MSGINFO_MASK, msgbuf[0]); int err; if (adapter->vfinfo[vf].pf_set_mac && !adapter->vfinfo[vf].trusted && diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c index d5cfb51ff648..e127070a59f4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c @@ -187,16 +187,16 @@ s32 ixgbe_start_hw_X540(struct ixgbe_hw *hw) s32 ixgbe_init_eeprom_params_X540(struct ixgbe_hw *hw) { struct ixgbe_eeprom_info *eeprom = &hw->eeprom; - u32 eec; - u16 eeprom_size; if (eeprom->type == ixgbe_eeprom_uninitialized) { + u16 eeprom_size; + u32 eec; + eeprom->semaphore_delay = 10; eeprom->type = ixgbe_flash; eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw)); - eeprom_size = (u16)((eec & IXGBE_EEC_SIZE) >> - IXGBE_EEC_SIZE_SHIFT); + eeprom_size = FIELD_GET(IXGBE_EEC_SIZE, eec); eeprom->word_size = BIT(eeprom_size + IXGBE_EEPROM_WORD_SIZE_SHIFT); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index aa4bf6c9a2f7..b3509b617a4e 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -628,16 +628,16 @@ static s32 ixgbe_fc_autoneg_fw(struct ixgbe_hw *hw) static s32 ixgbe_init_eeprom_params_X550(struct ixgbe_hw *hw) { struct ixgbe_eeprom_info *eeprom = &hw->eeprom; - u32 eec; - u16 eeprom_size; if (eeprom->type == ixgbe_eeprom_uninitialized) { + u16 eeprom_size; + u32 eec; + eeprom->semaphore_delay = 10; eeprom->type = ixgbe_flash; eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw)); - eeprom_size = (u16)((eec & IXGBE_EEC_SIZE) >> - IXGBE_EEC_SIZE_SHIFT); + eeprom_size = FIELD_GET(IXGBE_EEC_SIZE, eec); eeprom->word_size = BIT(eeprom_size + IXGBE_EEPROM_WORD_SIZE_SHIFT); @@ -712,8 +712,7 @@ static s32 ixgbe_read_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr, ret = ixgbe_iosf_wait(hw, &command); if ((command & IXGBE_SB_IOSF_CTRL_RESP_STAT_MASK) != 0) { - error = (command & IXGBE_SB_IOSF_CTRL_CMPL_ERR_MASK) >> - IXGBE_SB_IOSF_CTRL_CMPL_ERR_SHIFT; + error = FIELD_GET(IXGBE_SB_IOSF_CTRL_CMPL_ERR_MASK, command); hw_dbg(hw, "Failed to read, error %x\n", error); return IXGBE_ERR_PHY; } @@ -1412,8 +1411,7 @@ static s32 ixgbe_write_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr, ret = ixgbe_iosf_wait(hw, &command); if ((command & IXGBE_SB_IOSF_CTRL_RESP_STAT_MASK) != 0) { - error = (command & IXGBE_SB_IOSF_CTRL_CMPL_ERR_MASK) >> - IXGBE_SB_IOSF_CTRL_CMPL_ERR_SHIFT; + error = FIELD_GET(IXGBE_SB_IOSF_CTRL_CMPL_ERR_MASK, command); hw_dbg(hw, "Failed to write, error %x\n", error); return IXGBE_ERR_PHY; } @@ -3222,9 +3220,8 @@ static void ixgbe_read_mng_if_sel_x550em(struct ixgbe_hw *hw) */ if (hw->mac.type == ixgbe_mac_x550em_a && hw->phy.nw_mng_if_sel & IXGBE_NW_MNG_IF_SEL_MDIO_ACT) { - hw->phy.mdio.prtad = (hw->phy.nw_mng_if_sel & - IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD) >> - IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD_SHIFT; + hw->phy.mdio.prtad = FIELD_GET(IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD, + hw->phy.nw_mng_if_sel); } } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 513c4fe86967..7f30e08b580f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -1990,7 +1990,7 @@ free_entry_map: free_bmap_reverse: kfree(mcam->bmap_reverse); free_bmap: - kfree(mcam->counters.bmap); + kfree(mcam->bmap); return -ENOMEM; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index c44870b175f9..f36232dead1a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -29,7 +29,7 @@ mlx5_core-$(CONFIG_MLX5_CORE_EN) += en/rqt.o en/tir.o en/rss.o en/rx_res.o \ en/reporter_tx.o en/reporter_rx.o en/params.o en/xsk/pool.o \ en/xsk/setup.o en/xsk/rx.o en/xsk/tx.o en/devlink.o en/ptp.o \ en/qos.o en/htb.o en/trap.o en/fs_tt_redirect.o en/selq.o \ - lib/crypto.o + en/mgmt_pf.o lib/crypto.o lib/sd.o # # Netdev extra diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index cf0477f53dc4..aa1b471e13fa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -190,6 +190,9 @@ bool mlx5_rdma_supported(struct mlx5_core_dev *dev) if (is_mp_supported(dev)) return false; + if (mlx5_core_is_mgmt_pf(dev)) + return false; + return true; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c index d000236ddbac..aa397e3ebe6d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c @@ -75,6 +75,9 @@ int mlx5_ec_init(struct mlx5_core_dev *dev) if (!mlx5_core_is_ecpf(dev)) return 0; + if (mlx5_core_is_mgmt_pf(dev)) + return 0; + return mlx5_host_pf_init(dev); } @@ -85,6 +88,9 @@ void mlx5_ec_cleanup(struct mlx5_core_dev *dev) if (!mlx5_core_is_ecpf(dev)) return; + if (mlx5_core_is_mgmt_pf(dev)) + return; + mlx5_host_pf_cleanup(dev); err = mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_HOST_PF]); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 0bfe1ca8a364..922b63c25154 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -60,8 +60,10 @@ #include "lib/clock.h" #include "en/rx_res.h" #include "en/selq.h" +#include "lib/sd.h" extern const struct net_device_ops mlx5e_netdev_ops; +extern const struct net_device_ops mlx5e_mgmt_netdev_ops; struct page_pool; #define MLX5E_METADATA_ETHER_TYPE (0x8CE4) @@ -791,6 +793,8 @@ struct mlx5e_channel { struct hwtstamp_config *tstamp; DECLARE_BITMAP(state, MLX5E_CHANNEL_NUM_STATES); int ix; + int vec_ix; + int sd_ix; int cpu; /* Sync between icosq recovery and XSK enable/disable. */ struct mutex icosq_recovery_lock; @@ -914,7 +918,7 @@ struct mlx5e_priv { bool tx_ptp_opened; bool rx_ptp_opened; struct hwtstamp_config tstamp; - u16 q_counter; + u16 q_counter[MLX5_SD_MAX_GROUP_SZ]; u16 drop_rq_q_counter; struct notifier_block events_nb; struct notifier_block blocking_events_nb; @@ -1029,12 +1033,12 @@ struct mlx5e_xsk_param; struct mlx5e_rq_param; int mlx5e_open_rq(struct mlx5e_params *params, struct mlx5e_rq_param *param, - struct mlx5e_xsk_param *xsk, int node, + struct mlx5e_xsk_param *xsk, int node, u16 q_counter, struct mlx5e_rq *rq); #define MLX5E_RQ_WQES_TIMEOUT 20000 /* msecs */ int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time); void mlx5e_close_rq(struct mlx5e_rq *rq); -int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param); +int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param, u16 q_counter); void mlx5e_destroy_rq(struct mlx5e_rq *rq); struct mlx5e_sq_param; @@ -1122,9 +1126,10 @@ static inline bool mlx5_tx_swp_supported(struct mlx5_core_dev *mdev) } extern const struct ethtool_ops mlx5e_ethtool_ops; +extern const struct mlx5e_profile mlx5e_mgmt_pf_nic_profile; int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, u32 *mkey); -int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev); +int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises); void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev); int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb, bool enable_mc_lb); @@ -1227,6 +1232,8 @@ netdev_features_t mlx5e_features_check(struct sk_buff *skb, struct net_device *netdev, netdev_features_t features); int mlx5e_set_features(struct net_device *netdev, netdev_features_t features); +void mlx5e_nic_set_rx_mode(struct mlx5e_priv *priv); + #ifdef CONFIG_MLX5_ESWITCH int mlx5e_set_vf_mac(struct net_device *dev, int vf, u8 *mac); int mlx5e_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate, int max_tx_rate); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c index 48581ea3adcb..874a1016623c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c @@ -23,20 +23,26 @@ bool mlx5e_channels_is_xsk(struct mlx5e_channels *chs, unsigned int ix) return test_bit(MLX5E_CHANNEL_STATE_XSK, c->state); } -void mlx5e_channels_get_regular_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn) +void mlx5e_channels_get_regular_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn, + u32 *vhca_id) { struct mlx5e_channel *c = mlx5e_channels_get(chs, ix); *rqn = c->rq.rqn; + if (vhca_id) + *vhca_id = MLX5_CAP_GEN(c->mdev, vhca_id); } -void mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn) +void mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn, + u32 *vhca_id) { struct mlx5e_channel *c = mlx5e_channels_get(chs, ix); WARN_ON_ONCE(!test_bit(MLX5E_CHANNEL_STATE_XSK, c->state)); *rqn = c->xskrq.rqn; + if (vhca_id) + *vhca_id = MLX5_CAP_GEN(c->mdev, vhca_id); } bool mlx5e_channels_get_ptp_rqn(struct mlx5e_channels *chs, u32 *rqn) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h index 637ca90daaa8..6715aa9383b9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h @@ -10,8 +10,10 @@ struct mlx5e_channels; unsigned int mlx5e_channels_get_num(struct mlx5e_channels *chs); bool mlx5e_channels_is_xsk(struct mlx5e_channels *chs, unsigned int ix); -void mlx5e_channels_get_regular_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn); -void mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn); +void mlx5e_channels_get_regular_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn, + u32 *vhca_id); +void mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn, + u32 *vhca_id); bool mlx5e_channels_get_ptp_rqn(struct mlx5e_channels *chs, u32 *rqn); #endif /* __MLX5_EN_CHANNELS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/mgmt_pf.c b/drivers/net/ethernet/mellanox/mlx5/core/en/mgmt_pf.c new file mode 100644 index 000000000000..77b5805895b9 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/mgmt_pf.c @@ -0,0 +1,268 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +#include <linux/kernel.h> +#include "en/params.h" +#include "en/health.h" +#include "lib/eq.h" +#include "en/dcbnl.h" +#include "en_accel/ipsec.h" +#include "en_accel/en_accel.h" +#include "en/trap.h" +#include "en/monitor_stats.h" +#include "en/hv_vhca_stats.h" +#include "en_rep.h" +#include "en.h" + +static int mgmt_pf_async_event(struct notifier_block *nb, unsigned long event, void *data) +{ + struct mlx5e_priv *priv = container_of(nb, struct mlx5e_priv, events_nb); + struct mlx5_eqe *eqe = data; + + if (event != MLX5_EVENT_TYPE_PORT_CHANGE) + return NOTIFY_DONE; + + switch (eqe->sub_type) { + case MLX5_PORT_CHANGE_SUBTYPE_DOWN: + case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE: + queue_work(priv->wq, &priv->update_carrier_work); + break; + default: + return NOTIFY_DONE; + } + + return NOTIFY_OK; +} + +static void mlx5e_mgmt_pf_enable_async_events(struct mlx5e_priv *priv) +{ + priv->events_nb.notifier_call = mgmt_pf_async_event; + mlx5_notifier_register(priv->mdev, &priv->events_nb); +} + +static void mlx5e_disable_mgmt_pf_async_events(struct mlx5e_priv *priv) +{ + mlx5_notifier_unregister(priv->mdev, &priv->events_nb); +} + +static void mlx5e_modify_mgmt_pf_admin_state(struct mlx5_core_dev *mdev, + enum mlx5_port_status state) +{ + struct mlx5_eswitch *esw = mdev->priv.eswitch; + int vport_admin_state; + + mlx5_set_port_admin_status(mdev, state); + + if (state == MLX5_PORT_UP) + vport_admin_state = MLX5_VPORT_ADMIN_STATE_AUTO; + else + vport_admin_state = MLX5_VPORT_ADMIN_STATE_DOWN; + + mlx5_eswitch_set_vport_state(esw, MLX5_VPORT_UPLINK, vport_admin_state); +} + +static void mlx5e_build_mgmt_pf_nic_params(struct mlx5e_priv *priv, u16 mtu) +{ + struct mlx5e_params *params = &priv->channels.params; + struct mlx5_core_dev *mdev = priv->mdev; + u8 rx_cq_period_mode; + + params->sw_mtu = mtu; + params->hard_mtu = MLX5E_ETH_HARD_MTU; + params->num_channels = 1; + + /* SQ */ + params->log_sq_size = is_kdump_kernel() ? + MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE : + MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE; + MLX5E_SET_PFLAG(params, MLX5E_PFLAG_SKB_TX_MPWQE, mlx5e_tx_mpwqe_supported(mdev)); + + MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE, false); + + /* RQ */ + mlx5e_build_rq_params(mdev, params); + + /* CQ moderation params */ + rx_cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ? + MLX5_CQ_PERIOD_MODE_START_FROM_CQE : + MLX5_CQ_PERIOD_MODE_START_FROM_EQE; + params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation); + params->tx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation); + mlx5e_set_rx_cq_mode_params(params, rx_cq_period_mode); + mlx5e_set_tx_cq_mode_params(params, MLX5_CQ_PERIOD_MODE_START_FROM_EQE); + + /* TX inline */ + mlx5_query_min_inline(mdev, ¶ms->tx_min_inline_mode); +} + +static int mlx5e_mgmt_pf_init(struct mlx5_core_dev *mdev, + struct net_device *netdev) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5e_flow_steering *fs; + int err; + + mlx5e_build_mgmt_pf_nic_params(priv, netdev->mtu); + + mlx5e_timestamp_init(priv); + + fs = mlx5e_fs_init(priv->profile, mdev, + !test_bit(MLX5E_STATE_DESTROYING, &priv->state), + priv->dfs_root); + if (!fs) { + err = -ENOMEM; + mlx5_core_err(mdev, "FS initialization failed, %d\n", err); + return err; + } + priv->fs = fs; + + mlx5e_health_create_reporters(priv); + + return 0; +} + +static void mlx5e_mgmt_pf_cleanup(struct mlx5e_priv *priv) +{ + mlx5e_health_destroy_reporters(priv); + mlx5e_fs_cleanup(priv->fs); + priv->fs = NULL; +} + +static int mlx5e_mgmt_pf_init_rx(struct mlx5e_priv *priv) +{ + struct mlx5_core_dev *mdev = priv->mdev; + int err; + + priv->rx_res = mlx5e_rx_res_create(mdev, 0, priv->max_nch, priv->drop_rq.rqn, + &priv->channels.params.packet_merge, + priv->channels.params.num_channels); + if (!priv->rx_res) + return -ENOMEM; + + mlx5e_create_q_counters(priv); + + err = mlx5e_open_drop_rq(priv, &priv->drop_rq); + if (err) { + mlx5_core_err(mdev, "open drop rq failed, %d\n", err); + goto err_destroy_q_counters; + } + + err = mlx5e_create_flow_steering(priv->fs, priv->rx_res, priv->profile, + priv->netdev); + if (err) { + mlx5_core_warn(mdev, "create flow steering failed, %d\n", err); + goto err_destroy_rx_res; + } + + return 0; + +err_destroy_rx_res: + mlx5e_rx_res_destroy(priv->rx_res); + priv->rx_res = NULL; + mlx5e_close_drop_rq(&priv->drop_rq); +err_destroy_q_counters: + mlx5e_destroy_q_counters(priv); + return err; +} + +static void mlx5e_mgmt_pf_cleanup_rx(struct mlx5e_priv *priv) +{ + mlx5e_destroy_flow_steering(priv->fs, !!(priv->netdev->hw_features & NETIF_F_NTUPLE), + priv->profile); + mlx5e_rx_res_destroy(priv->rx_res); + priv->rx_res = NULL; + mlx5e_close_drop_rq(&priv->drop_rq); + mlx5e_destroy_q_counters(priv); +} + +static int mlx5e_mgmt_pf_init_tx(struct mlx5e_priv *priv) +{ + return 0; +} + +static void mlx5e_mgmt_pf_cleanup_tx(struct mlx5e_priv *priv) +{ +} + +static void mlx5e_mgmt_pf_enable(struct mlx5e_priv *priv) +{ + struct net_device *netdev = priv->netdev; + struct mlx5_core_dev *mdev = priv->mdev; + + mlx5e_fs_init_l2_addr(priv->fs, netdev); + + /* Marking the link as currently not needed by the Driver */ + if (!netif_running(netdev)) + mlx5e_modify_mgmt_pf_admin_state(mdev, MLX5_PORT_DOWN); + + mlx5e_set_netdev_mtu_boundaries(priv); + mlx5e_set_dev_port_mtu(priv); + + mlx5e_mgmt_pf_enable_async_events(priv); + if (mlx5e_monitor_counter_supported(priv)) + mlx5e_monitor_counter_init(priv); + + mlx5e_hv_vhca_stats_create(priv); + if (netdev->reg_state != NETREG_REGISTERED) + return; + mlx5e_dcbnl_init_app(priv); + + mlx5e_nic_set_rx_mode(priv); + + rtnl_lock(); + if (netif_running(netdev)) + mlx5e_open(netdev); + udp_tunnel_nic_reset_ntf(priv->netdev); + netif_device_attach(netdev); + rtnl_unlock(); +} + +static void mlx5e_mgmt_pf_disable(struct mlx5e_priv *priv) +{ + if (priv->netdev->reg_state == NETREG_REGISTERED) + mlx5e_dcbnl_delete_app(priv); + + rtnl_lock(); + if (netif_running(priv->netdev)) + mlx5e_close(priv->netdev); + netif_device_detach(priv->netdev); + rtnl_unlock(); + + mlx5e_nic_set_rx_mode(priv); + + mlx5e_hv_vhca_stats_destroy(priv); + if (mlx5e_monitor_counter_supported(priv)) + mlx5e_monitor_counter_cleanup(priv); + + mlx5e_disable_mgmt_pf_async_events(priv); + mlx5e_ipsec_cleanup(priv); +} + +static int mlx5e_mgmt_pf_update_rx(struct mlx5e_priv *priv) +{ + return mlx5e_refresh_tirs(priv, false, false); +} + +static int mlx5e_mgmt_pf_max_nch_limit(struct mlx5_core_dev *mdev) +{ + return 1; +} + +const struct mlx5e_profile mlx5e_mgmt_pf_nic_profile = { + .init = mlx5e_mgmt_pf_init, + .cleanup = mlx5e_mgmt_pf_cleanup, + .init_rx = mlx5e_mgmt_pf_init_rx, + .cleanup_rx = mlx5e_mgmt_pf_cleanup_rx, + .init_tx = mlx5e_mgmt_pf_init_tx, + .cleanup_tx = mlx5e_mgmt_pf_cleanup_tx, + .enable = mlx5e_mgmt_pf_enable, + .disable = mlx5e_mgmt_pf_disable, + .update_rx = mlx5e_mgmt_pf_update_rx, + .update_stats = mlx5e_stats_update_ndo_stats, + .update_carrier = mlx5e_update_carrier, + .rx_handlers = &mlx5e_rx_handlers_nic, + .max_tc = 1, + .max_nch_limit = mlx5e_mgmt_pf_max_nch_limit, + .stats_grps = mlx5e_nic_stats_grps, + .stats_grps_num = mlx5e_nic_stats_grps_num +}; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c index 40c8df111754..e2d8d2754be0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c @@ -20,10 +20,8 @@ #define NUM_REQ_PPCNT_COUNTER_S1 MLX5_CMD_SET_MONITOR_NUM_PPCNT_COUNTER_SET1 #define NUM_REQ_Q_COUNTERS_S1 MLX5_CMD_SET_MONITOR_NUM_Q_COUNTERS_SET1 -int mlx5e_monitor_counter_supported(struct mlx5e_priv *priv) +static int mlx5e_monitor_counter_cap(struct mlx5_core_dev *mdev) { - struct mlx5_core_dev *mdev = priv->mdev; - if (!MLX5_CAP_GEN(mdev, max_num_of_monitor_counters)) return false; if (MLX5_CAP_PCAM_REG(mdev, ppcnt) && @@ -36,24 +34,38 @@ int mlx5e_monitor_counter_supported(struct mlx5e_priv *priv) return true; } -static void mlx5e_monitor_counter_arm(struct mlx5e_priv *priv) +int mlx5e_monitor_counter_supported(struct mlx5e_priv *priv) +{ + struct mlx5_core_dev *pos; + int i; + + mlx5_sd_for_each_dev(i, priv->mdev, pos) + if (!mlx5e_monitor_counter_cap(pos)) + return false; + return true; +} + +static void mlx5e_monitor_counter_arm(struct mlx5_core_dev *mdev) { u32 in[MLX5_ST_SZ_DW(arm_monitor_counter_in)] = {}; MLX5_SET(arm_monitor_counter_in, in, opcode, MLX5_CMD_OP_ARM_MONITOR_COUNTER); - mlx5_cmd_exec_in(priv->mdev, arm_monitor_counter, in); + mlx5_cmd_exec_in(mdev, arm_monitor_counter, in); } static void mlx5e_monitor_counters_work(struct work_struct *work) { struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv, monitor_counters_work); + struct mlx5_core_dev *pos; + int i; mutex_lock(&priv->state_lock); mlx5e_stats_update_ndo_stats(priv); mutex_unlock(&priv->state_lock); - mlx5e_monitor_counter_arm(priv); + mlx5_sd_for_each_dev(i, priv->mdev, pos) + mlx5e_monitor_counter_arm(pos); } static int mlx5e_monitor_event_handler(struct notifier_block *nb, @@ -97,15 +109,13 @@ static int fill_monitor_counter_q_counter_set1(int cnt, int q_counter, u32 *in) } /* check if mlx5e_monitor_counter_supported before calling this function*/ -static void mlx5e_set_monitor_counter(struct mlx5e_priv *priv) +static void mlx5e_set_monitor_counter(struct mlx5_core_dev *mdev, int q_counter) { - struct mlx5_core_dev *mdev = priv->mdev; int max_num_of_counters = MLX5_CAP_GEN(mdev, max_num_of_monitor_counters); int num_q_counters = MLX5_CAP_GEN(mdev, num_q_monitor_counters); int num_ppcnt_counters = !MLX5_CAP_PCAM_REG(mdev, ppcnt) ? 0 : MLX5_CAP_GEN(mdev, num_ppcnt_monitor_counters); u32 in[MLX5_ST_SZ_DW(set_monitor_counter_in)] = {}; - int q_counter = priv->q_counter; int cnt = 0; if (num_ppcnt_counters >= NUM_REQ_PPCNT_COUNTER_S1 && @@ -127,13 +137,17 @@ static void mlx5e_set_monitor_counter(struct mlx5e_priv *priv) /* check if mlx5e_monitor_counter_supported before calling this function*/ void mlx5e_monitor_counter_init(struct mlx5e_priv *priv) { + struct mlx5_core_dev *pos; + int i; + INIT_WORK(&priv->monitor_counters_work, mlx5e_monitor_counters_work); MLX5_NB_INIT(&priv->monitor_counters_nb, mlx5e_monitor_event_handler, MONITOR_COUNTER); - mlx5_eq_notifier_register(priv->mdev, &priv->monitor_counters_nb); - - mlx5e_set_monitor_counter(priv); - mlx5e_monitor_counter_arm(priv); + mlx5_sd_for_each_dev(i, priv->mdev, pos) { + mlx5_eq_notifier_register(pos, &priv->monitor_counters_nb); + mlx5e_set_monitor_counter(pos, priv->q_counter[i]); + mlx5e_monitor_counter_arm(pos); + } queue_work(priv->wq, &priv->update_stats_work); } @@ -141,11 +155,15 @@ void mlx5e_monitor_counter_init(struct mlx5e_priv *priv) void mlx5e_monitor_counter_cleanup(struct mlx5e_priv *priv) { u32 in[MLX5_ST_SZ_DW(set_monitor_counter_in)] = {}; + struct mlx5_core_dev *pos; + int i; MLX5_SET(set_monitor_counter_in, in, opcode, MLX5_CMD_OP_SET_MONITOR_COUNTER); - mlx5_cmd_exec_in(priv->mdev, set_monitor_counter, in); - mlx5_eq_notifier_unregister(priv->mdev, &priv->monitor_counters_nb); + mlx5_sd_for_each_dev(i, priv->mdev, pos) { + mlx5_cmd_exec_in(pos, set_monitor_counter, in); + mlx5_eq_notifier_unregister(pos, &priv->monitor_counters_nb); + } cancel_work_sync(&priv->monitor_counters_work); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 284253b79266..fb10bb166fbb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -674,7 +674,7 @@ void mlx5e_build_create_cq_param(struct mlx5e_create_cq_param *ccp, struct mlx5e .napi = &c->napi, .ch_stats = c->stats, .node = cpu_to_node(c->cpu), - .ix = c->ix, + .ix = c->vec_ix, }; } @@ -945,7 +945,6 @@ static u8 rq_end_pad_mode(struct mlx5_core_dev *mdev, struct mlx5e_params *param int mlx5e_build_rq_param(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, - u16 q_counter, struct mlx5e_rq_param *param) { void *rqc = param->rqc; @@ -1007,7 +1006,6 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev, MLX5_SET(wq, wq, log_wq_stride, mlx5e_get_rqwq_log_stride(params->rq_wq_type, ndsegs)); MLX5_SET(wq, wq, pd, mdev->mlx5e_res.hw_objs.pdn); - MLX5_SET(rqc, rqc, counter_set_id, q_counter); MLX5_SET(rqc, rqc, vsd, params->vlan_strip_disable); MLX5_SET(rqc, rqc, scatter_fcs, params->scatter_fcs_en); @@ -1018,7 +1016,6 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev, } void mlx5e_build_drop_rq_param(struct mlx5_core_dev *mdev, - u16 q_counter, struct mlx5e_rq_param *param) { void *rqc = param->rqc; @@ -1027,7 +1024,6 @@ void mlx5e_build_drop_rq_param(struct mlx5_core_dev *mdev, MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC); MLX5_SET(wq, wq, log_wq_stride, mlx5e_get_rqwq_log_stride(MLX5_WQ_TYPE_CYCLIC, 1)); - MLX5_SET(rqc, rqc, counter_set_id, q_counter); param->wq.buf_numa_node = dev_to_node(mlx5_core_dma_dev(mdev)); } @@ -1292,13 +1288,12 @@ void mlx5e_build_xdpsq_param(struct mlx5_core_dev *mdev, int mlx5e_build_channel_param(struct mlx5_core_dev *mdev, struct mlx5e_params *params, - u16 q_counter, struct mlx5e_channel_param *cparam) { u8 icosq_log_wq_sz, async_icosq_log_wq_sz; int err; - err = mlx5e_build_rq_param(mdev, params, NULL, q_counter, &cparam->rq); + err = mlx5e_build_rq_param(mdev, params, NULL, &cparam->rq); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h index 6800949dafbc..9a781f18b57f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h @@ -130,10 +130,8 @@ void mlx5e_build_create_cq_param(struct mlx5e_create_cq_param *ccp, struct mlx5e int mlx5e_build_rq_param(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, - u16 q_counter, struct mlx5e_rq_param *param); void mlx5e_build_drop_rq_param(struct mlx5_core_dev *mdev, - u16 q_counter, struct mlx5e_rq_param *param); void mlx5e_build_sq_param_common(struct mlx5_core_dev *mdev, struct mlx5e_sq_param *param); @@ -149,7 +147,6 @@ void mlx5e_build_xdpsq_param(struct mlx5_core_dev *mdev, struct mlx5e_sq_param *param); int mlx5e_build_channel_param(struct mlx5_core_dev *mdev, struct mlx5e_params *params, - u16 q_counter, struct mlx5e_channel_param *cparam); u16 mlx5e_calc_sq_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index c206cc0a8483..cafb41895f94 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -646,7 +646,6 @@ static void mlx5e_ptp_build_sq_param(struct mlx5_core_dev *mdev, static void mlx5e_ptp_build_rq_param(struct mlx5_core_dev *mdev, struct net_device *netdev, - u16 q_counter, struct mlx5e_ptp_params *ptp_params) { struct mlx5e_rq_param *rq_params = &ptp_params->rq_param; @@ -655,7 +654,7 @@ static void mlx5e_ptp_build_rq_param(struct mlx5_core_dev *mdev, params->rq_wq_type = MLX5_WQ_TYPE_CYCLIC; mlx5e_init_rq_type_params(mdev, params); params->sw_mtu = netdev->max_mtu; - mlx5e_build_rq_param(mdev, params, NULL, q_counter, rq_params); + mlx5e_build_rq_param(mdev, params, NULL, rq_params); } static void mlx5e_ptp_build_params(struct mlx5e_ptp *c, @@ -681,7 +680,7 @@ static void mlx5e_ptp_build_params(struct mlx5e_ptp *c, /* RQ */ if (test_bit(MLX5E_PTP_STATE_RX, c->state)) { params->vlan_strip_disable = orig->vlan_strip_disable; - mlx5e_ptp_build_rq_param(c->mdev, c->netdev, c->priv->q_counter, cparams); + mlx5e_ptp_build_rq_param(c->mdev, c->netdev, cparams); } } @@ -714,13 +713,16 @@ static int mlx5e_ptp_open_rq(struct mlx5e_ptp *c, struct mlx5e_params *params, struct mlx5e_rq_param *rq_param) { int node = dev_to_node(c->mdev->device); - int err; + int err, sd_ix; + u16 q_counter; err = mlx5e_init_ptp_rq(c, params, &c->rq); if (err) return err; - return mlx5e_open_rq(params, rq_param, NULL, node, &c->rq); + sd_ix = mlx5_sd_ch_ix_get_dev_ix(c->mdev, MLX5E_PTP_CHANNEL_IX); + q_counter = c->priv->q_counter[sd_ix]; + return mlx5e_open_rq(params, rq_param, NULL, node, q_counter, &c->rq); } static int mlx5e_ptp_open_queues(struct mlx5e_ptp *c, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c index 34adf8c3f81a..e87e26f2c669 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c @@ -122,8 +122,8 @@ int mlx5e_open_qos_sq(struct mlx5e_priv *priv, struct mlx5e_channels *chs, memset(¶m_sq, 0, sizeof(param_sq)); memset(¶m_cq, 0, sizeof(param_cq)); - mlx5e_build_sq_param(priv->mdev, params, ¶m_sq); - mlx5e_build_tx_cq_param(priv->mdev, params, ¶m_cq); + mlx5e_build_sq_param(c->mdev, params, ¶m_sq); + mlx5e_build_tx_cq_param(c->mdev, params, ¶m_cq); err = mlx5e_open_cq(c->mdev, params->tx_cq_moderation, ¶m_cq, &ccp, &sq->cq); if (err) goto err_free_sq; @@ -176,7 +176,7 @@ int mlx5e_activate_qos_sq(void *data, u16 node_qid, u32 hw_id) */ smp_wmb(); - qos_dbg(priv->mdev, "Activate QoS SQ qid %u\n", node_qid); + qos_dbg(sq->mdev, "Activate QoS SQ qid %u\n", node_qid); mlx5e_activate_txqsq(sq); return 0; @@ -190,7 +190,7 @@ void mlx5e_deactivate_qos_sq(struct mlx5e_priv *priv, u16 qid) if (!sq) /* Handle the case when the SQ failed to open. */ return; - qos_dbg(priv->mdev, "Deactivate QoS SQ qid %u\n", qid); + qos_dbg(sq->mdev, "Deactivate QoS SQ qid %u\n", qid); mlx5e_deactivate_txqsq(sq); priv->txq2sq[mlx5e_qid_from_qos(&priv->channels, qid)] = NULL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c index 4358798d6ce1..25d751eba99b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c @@ -294,8 +294,8 @@ static void mlx5e_rx_reporter_diagnose_generic_rq(struct mlx5e_rq *rq, params = &priv->channels.params; rq_sz = mlx5e_rqwq_get_size(rq); - real_time = mlx5_is_real_time_rq(priv->mdev); - rq_stride = BIT(mlx5e_mpwqe_get_log_stride_size(priv->mdev, params, NULL)); + real_time = mlx5_is_real_time_rq(rq->mdev); + rq_stride = BIT(mlx5e_mpwqe_get_log_stride_size(rq->mdev, params, NULL)); mlx5e_health_fmsg_named_obj_nest_start(fmsg, "RQ"); devlink_fmsg_u8_pair_put(fmsg, "type", params->rq_wq_type); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index 6b44ddce14e9..0ab9db319530 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -219,7 +219,6 @@ mlx5e_tx_reporter_build_diagnose_output_sq_common(struct devlink_fmsg *fmsg, struct mlx5e_txqsq *sq, int tc) { bool stopped = netif_xmit_stopped(sq->txq); - struct mlx5e_priv *priv = sq->priv; u8 state; int err; @@ -227,7 +226,7 @@ mlx5e_tx_reporter_build_diagnose_output_sq_common(struct devlink_fmsg *fmsg, devlink_fmsg_u32_pair_put(fmsg, "txq ix", sq->txq_ix); devlink_fmsg_u32_pair_put(fmsg, "sqn", sq->sqn); - err = mlx5_core_query_sq_state(priv->mdev, sq->sqn, &state); + err = mlx5_core_query_sq_state(sq->mdev, sq->sqn, &state); if (!err) devlink_fmsg_u8_pair_put(fmsg, "HW state", state); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c index 7b8ff7a71003..bcafb4bf9415 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c @@ -4,6 +4,33 @@ #include "rqt.h" #include <linux/mlx5/transobj.h> +static bool verify_num_vhca_ids(struct mlx5_core_dev *mdev, u32 *vhca_ids, + unsigned int size) +{ + unsigned int max_num_vhca_id = MLX5_CAP_GEN_2(mdev, max_rqt_vhca_id); + int i; + + /* Verify that all vhca_ids are in range [0, max_num_vhca_ids - 1] */ + for (i = 0; i < size; i++) + if (vhca_ids[i] >= max_num_vhca_id) + return false; + return true; +} + +static bool rqt_verify_vhca_ids(struct mlx5_core_dev *mdev, u32 *vhca_ids, + unsigned int size) +{ + if (!vhca_ids) + return true; + + if (!MLX5_CAP_GEN(mdev, cross_vhca_rqt)) + return false; + if (!verify_num_vhca_ids(mdev, vhca_ids, size)) + return false; + + return true; +} + void mlx5e_rss_params_indir_init_uniform(struct mlx5e_rss_params_indir *indir, unsigned int num_channels) { @@ -13,19 +40,38 @@ void mlx5e_rss_params_indir_init_uniform(struct mlx5e_rss_params_indir *indir, indir->table[i] = i % num_channels; } +static void fill_rqn_list(void *rqtc, u32 *rqns, u32 *vhca_ids, unsigned int size) +{ + unsigned int i; + + if (vhca_ids) { + MLX5_SET(rqtc, rqtc, rq_vhca_id_format, 1); + for (i = 0; i < size; i++) { + MLX5_SET(rqtc, rqtc, rq_vhca[i].rq_num, rqns[i]); + MLX5_SET(rqtc, rqtc, rq_vhca[i].rq_vhca_id, vhca_ids[i]); + } + } else { + for (i = 0; i < size; i++) + MLX5_SET(rqtc, rqtc, rq_num[i], rqns[i]); + } +} static int mlx5e_rqt_init(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev, - u16 max_size, u32 *init_rqns, u16 init_size) + u16 max_size, u32 *init_rqns, u32 *init_vhca_ids, u16 init_size) { + int entry_sz; void *rqtc; int inlen; int err; u32 *in; - int i; + + if (!rqt_verify_vhca_ids(mdev, init_vhca_ids, init_size)) + return -EOPNOTSUPP; rqt->mdev = mdev; rqt->size = max_size; - inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + sizeof(u32) * init_size; + entry_sz = init_vhca_ids ? MLX5_ST_SZ_BYTES(rq_vhca) : MLX5_ST_SZ_BYTES(rq_num); + inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + entry_sz * init_size; in = kvzalloc(inlen, GFP_KERNEL); if (!in) return -ENOMEM; @@ -33,10 +79,9 @@ static int mlx5e_rqt_init(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev, rqtc = MLX5_ADDR_OF(create_rqt_in, in, rqt_context); MLX5_SET(rqtc, rqtc, rqt_max_size, rqt->size); - MLX5_SET(rqtc, rqtc, rqt_actual_size, init_size); - for (i = 0; i < init_size; i++) - MLX5_SET(rqtc, rqtc, rq_num[i], init_rqns[i]); + + fill_rqn_list(rqtc, init_rqns, init_vhca_ids, init_size); err = mlx5_core_create_rqt(rqt->mdev, in, inlen, &rqt->rqtn); @@ -49,7 +94,7 @@ int mlx5e_rqt_init_direct(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev, { u16 max_size = indir_enabled ? indir_table_size : 1; - return mlx5e_rqt_init(rqt, mdev, max_size, &init_rqn, 1); + return mlx5e_rqt_init(rqt, mdev, max_size, &init_rqn, NULL, 1); } static int mlx5e_bits_invert(unsigned long a, int size) @@ -63,7 +108,8 @@ static int mlx5e_bits_invert(unsigned long a, int size) return inv; } -static int mlx5e_calc_indir_rqns(u32 *rss_rqns, u32 *rqns, unsigned int num_rqns, +static int mlx5e_calc_indir_rqns(u32 *rss_rqns, u32 *rqns, u32 *rss_vhca_ids, u32 *vhca_ids, + unsigned int num_rqns, u8 hfunc, struct mlx5e_rss_params_indir *indir) { unsigned int i; @@ -82,30 +128,42 @@ static int mlx5e_calc_indir_rqns(u32 *rss_rqns, u32 *rqns, unsigned int num_rqns */ return -EINVAL; rss_rqns[i] = rqns[ix]; + if (vhca_ids) + rss_vhca_ids[i] = vhca_ids[ix]; } return 0; } int mlx5e_rqt_init_indir(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev, - u32 *rqns, unsigned int num_rqns, + u32 *rqns, u32 *vhca_ids, unsigned int num_rqns, u8 hfunc, struct mlx5e_rss_params_indir *indir) { - u32 *rss_rqns; + u32 *rss_rqns, *rss_vhca_ids = NULL; int err; rss_rqns = kvmalloc_array(indir->actual_table_size, sizeof(*rss_rqns), GFP_KERNEL); if (!rss_rqns) return -ENOMEM; - err = mlx5e_calc_indir_rqns(rss_rqns, rqns, num_rqns, hfunc, indir); + if (vhca_ids) { + rss_vhca_ids = kvmalloc_array(indir->actual_table_size, sizeof(*rss_vhca_ids), + GFP_KERNEL); + if (!rss_vhca_ids) { + kvfree(rss_rqns); + return -ENOMEM; + } + } + + err = mlx5e_calc_indir_rqns(rss_rqns, rqns, rss_vhca_ids, vhca_ids, num_rqns, hfunc, indir); if (err) goto out; - err = mlx5e_rqt_init(rqt, mdev, indir->max_table_size, rss_rqns, + err = mlx5e_rqt_init(rqt, mdev, indir->max_table_size, rss_rqns, rss_vhca_ids, indir->actual_table_size); out: + kvfree(rss_vhca_ids); kvfree(rss_rqns); return err; } @@ -126,15 +184,20 @@ void mlx5e_rqt_destroy(struct mlx5e_rqt *rqt) mlx5_core_destroy_rqt(rqt->mdev, rqt->rqtn); } -static int mlx5e_rqt_redirect(struct mlx5e_rqt *rqt, u32 *rqns, unsigned int size) +static int mlx5e_rqt_redirect(struct mlx5e_rqt *rqt, u32 *rqns, u32 *vhca_ids, + unsigned int size) { - unsigned int i; + int entry_sz; void *rqtc; int inlen; u32 *in; int err; - inlen = MLX5_ST_SZ_BYTES(modify_rqt_in) + sizeof(u32) * size; + if (!rqt_verify_vhca_ids(rqt->mdev, vhca_ids, size)) + return -EINVAL; + + entry_sz = vhca_ids ? MLX5_ST_SZ_BYTES(rq_vhca) : MLX5_ST_SZ_BYTES(rq_num); + inlen = MLX5_ST_SZ_BYTES(modify_rqt_in) + entry_sz * size; in = kvzalloc(inlen, GFP_KERNEL); if (!in) return -ENOMEM; @@ -143,8 +206,8 @@ static int mlx5e_rqt_redirect(struct mlx5e_rqt *rqt, u32 *rqns, unsigned int siz MLX5_SET(modify_rqt_in, in, bitmask.rqn_list, 1); MLX5_SET(rqtc, rqtc, rqt_actual_size, size); - for (i = 0; i < size; i++) - MLX5_SET(rqtc, rqtc, rq_num[i], rqns[i]); + + fill_rqn_list(rqtc, rqns, vhca_ids, size); err = mlx5_core_modify_rqt(rqt->mdev, rqt->rqtn, in, inlen); @@ -152,17 +215,21 @@ static int mlx5e_rqt_redirect(struct mlx5e_rqt *rqt, u32 *rqns, unsigned int siz return err; } -int mlx5e_rqt_redirect_direct(struct mlx5e_rqt *rqt, u32 rqn) +int mlx5e_rqt_redirect_direct(struct mlx5e_rqt *rqt, u32 rqn, u32 *vhca_id) { - return mlx5e_rqt_redirect(rqt, &rqn, 1); + return mlx5e_rqt_redirect(rqt, &rqn, vhca_id, 1); } -int mlx5e_rqt_redirect_indir(struct mlx5e_rqt *rqt, u32 *rqns, unsigned int num_rqns, +int mlx5e_rqt_redirect_indir(struct mlx5e_rqt *rqt, u32 *rqns, u32 *vhca_ids, + unsigned int num_rqns, u8 hfunc, struct mlx5e_rss_params_indir *indir) { - u32 *rss_rqns; + u32 *rss_rqns, *rss_vhca_ids = NULL; int err; + if (!rqt_verify_vhca_ids(rqt->mdev, vhca_ids, num_rqns)) + return -EINVAL; + if (WARN_ON(rqt->size != indir->max_table_size)) return -EINVAL; @@ -170,13 +237,23 @@ int mlx5e_rqt_redirect_indir(struct mlx5e_rqt *rqt, u32 *rqns, unsigned int num_ if (!rss_rqns) return -ENOMEM; - err = mlx5e_calc_indir_rqns(rss_rqns, rqns, num_rqns, hfunc, indir); + if (vhca_ids) { + rss_vhca_ids = kvmalloc_array(indir->actual_table_size, sizeof(*rss_vhca_ids), + GFP_KERNEL); + if (!rss_vhca_ids) { + kvfree(rss_rqns); + return -ENOMEM; + } + } + + err = mlx5e_calc_indir_rqns(rss_rqns, rqns, rss_vhca_ids, vhca_ids, num_rqns, hfunc, indir); if (err) goto out; - err = mlx5e_rqt_redirect(rqt, rss_rqns, indir->actual_table_size); + err = mlx5e_rqt_redirect(rqt, rss_rqns, rss_vhca_ids, indir->actual_table_size); out: + kvfree(rss_vhca_ids); kvfree(rss_rqns); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h index 77fba3ebd18d..e0bc30308c77 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h @@ -20,7 +20,7 @@ void mlx5e_rss_params_indir_init_uniform(struct mlx5e_rss_params_indir *indir, unsigned int num_channels); struct mlx5e_rqt { - struct mlx5_core_dev *mdev; + struct mlx5_core_dev *mdev; /* primary */ u32 rqtn; u16 size; }; @@ -28,7 +28,7 @@ struct mlx5e_rqt { int mlx5e_rqt_init_direct(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev, bool indir_enabled, u32 init_rqn, u32 indir_table_size); int mlx5e_rqt_init_indir(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev, - u32 *rqns, unsigned int num_rqns, + u32 *rqns, u32 *vhca_ids, unsigned int num_rqns, u8 hfunc, struct mlx5e_rss_params_indir *indir); void mlx5e_rqt_destroy(struct mlx5e_rqt *rqt); @@ -38,8 +38,9 @@ static inline u32 mlx5e_rqt_get_rqtn(struct mlx5e_rqt *rqt) } u32 mlx5e_rqt_size(struct mlx5_core_dev *mdev, unsigned int num_channels); -int mlx5e_rqt_redirect_direct(struct mlx5e_rqt *rqt, u32 rqn); -int mlx5e_rqt_redirect_indir(struct mlx5e_rqt *rqt, u32 *rqns, unsigned int num_rqns, +int mlx5e_rqt_redirect_direct(struct mlx5e_rqt *rqt, u32 rqn, u32 *vhca_id); +int mlx5e_rqt_redirect_indir(struct mlx5e_rqt *rqt, u32 *rqns, u32 *vhca_ids, + unsigned int num_rqns, u8 hfunc, struct mlx5e_rss_params_indir *indir); #endif /* __MLX5_EN_RQT_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c index c1545a2e8d6d..5f742f896600 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c @@ -74,7 +74,7 @@ struct mlx5e_rss { struct mlx5e_tir *tir[MLX5E_NUM_INDIR_TIRS]; struct mlx5e_tir *inner_tir[MLX5E_NUM_INDIR_TIRS]; struct mlx5e_rqt rqt; - struct mlx5_core_dev *mdev; + struct mlx5_core_dev *mdev; /* primary */ u32 drop_rqn; bool inner_ft_support; bool enabled; @@ -473,21 +473,22 @@ int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss, return 0; } -static int mlx5e_rss_apply(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns) +static int mlx5e_rss_apply(struct mlx5e_rss *rss, u32 *rqns, u32 *vhca_ids, unsigned int num_rqns) { int err; - err = mlx5e_rqt_redirect_indir(&rss->rqt, rqns, num_rqns, rss->hash.hfunc, &rss->indir); + err = mlx5e_rqt_redirect_indir(&rss->rqt, rqns, vhca_ids, num_rqns, rss->hash.hfunc, + &rss->indir); if (err) mlx5e_rss_warn(rss->mdev, "Failed to redirect RQT %#x to channels: err = %d\n", mlx5e_rqt_get_rqtn(&rss->rqt), err); return err; } -void mlx5e_rss_enable(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns) +void mlx5e_rss_enable(struct mlx5e_rss *rss, u32 *rqns, u32 *vhca_ids, unsigned int num_rqns) { rss->enabled = true; - mlx5e_rss_apply(rss, rqns, num_rqns); + mlx5e_rss_apply(rss, rqns, vhca_ids, num_rqns); } void mlx5e_rss_disable(struct mlx5e_rss *rss) @@ -495,7 +496,7 @@ void mlx5e_rss_disable(struct mlx5e_rss *rss) int err; rss->enabled = false; - err = mlx5e_rqt_redirect_direct(&rss->rqt, rss->drop_rqn); + err = mlx5e_rqt_redirect_direct(&rss->rqt, rss->drop_rqn, NULL); if (err) mlx5e_rss_warn(rss->mdev, "Failed to redirect RQT %#x to drop RQ %#x: err = %d\n", mlx5e_rqt_get_rqtn(&rss->rqt), rss->drop_rqn, err); @@ -568,7 +569,7 @@ int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc) int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir, const u8 *key, const u8 *hfunc, - u32 *rqns, unsigned int num_rqns) + u32 *rqns, u32 *vhca_ids, unsigned int num_rqns) { bool changed_indir = false; bool changed_hash = false; @@ -608,7 +609,7 @@ int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir, } if (changed_indir && rss->enabled) { - err = mlx5e_rss_apply(rss, rqns, num_rqns); + err = mlx5e_rss_apply(rss, rqns, vhca_ids, num_rqns); if (err) { mlx5e_rss_copy(rss, old_rss); goto out; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h index d1d0bc350e92..d0df98963c8d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h @@ -39,7 +39,7 @@ int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss, const struct mlx5e_packet_merge_param *init_pkt_merge_param, bool inner, u32 *tirn); -void mlx5e_rss_enable(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns); +void mlx5e_rss_enable(struct mlx5e_rss *rss, u32 *rqns, u32 *vhca_ids, unsigned int num_rqns); void mlx5e_rss_disable(struct mlx5e_rss *rss); int mlx5e_rss_packet_merge_set_param(struct mlx5e_rss *rss, @@ -47,7 +47,7 @@ int mlx5e_rss_packet_merge_set_param(struct mlx5e_rss *rss, int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc); int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir, const u8 *key, const u8 *hfunc, - u32 *rqns, unsigned int num_rqns); + u32 *rqns, u32 *vhca_ids, unsigned int num_rqns); struct mlx5e_rss_params_hash mlx5e_rss_get_hash(struct mlx5e_rss *rss); u8 mlx5e_rss_get_hash_fields(struct mlx5e_rss *rss, enum mlx5_traffic_types tt); int mlx5e_rss_set_hash_fields(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c index b23e224e3763..a86eade9a9e0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c @@ -8,7 +8,7 @@ #define MLX5E_MAX_NUM_RSS 16 struct mlx5e_rx_res { - struct mlx5_core_dev *mdev; + struct mlx5_core_dev *mdev; /* primary */ enum mlx5e_rx_res_features features; unsigned int max_nch; u32 drop_rqn; @@ -19,6 +19,7 @@ struct mlx5e_rx_res { struct mlx5e_rss *rss[MLX5E_MAX_NUM_RSS]; bool rss_active; u32 *rss_rqns; + u32 *rss_vhca_ids; unsigned int rss_nch; struct { @@ -34,6 +35,13 @@ struct mlx5e_rx_res { /* API for rx_res_rss_* */ +static u32 *get_vhca_ids(struct mlx5e_rx_res *res, int offset) +{ + bool multi_vhca = res->features & MLX5E_RX_RES_FEATURE_MULTI_VHCA; + + return multi_vhca ? res->rss_vhca_ids + offset : NULL; +} + void mlx5e_rx_res_rss_update_num_channels(struct mlx5e_rx_res *res, u32 nch) { int i; @@ -85,8 +93,11 @@ int mlx5e_rx_res_rss_init(struct mlx5e_rx_res *res, u32 *rss_idx, unsigned int i return PTR_ERR(rss); mlx5e_rss_set_indir_uniform(rss, init_nch); - if (res->rss_active) - mlx5e_rss_enable(rss, res->rss_rqns, res->rss_nch); + if (res->rss_active) { + u32 *vhca_ids = get_vhca_ids(res, 0); + + mlx5e_rss_enable(rss, res->rss_rqns, vhca_ids, res->rss_nch); + } res->rss[i] = rss; *rss_idx = i; @@ -153,10 +164,12 @@ static void mlx5e_rx_res_rss_enable(struct mlx5e_rx_res *res) for (i = 0; i < MLX5E_MAX_NUM_RSS; i++) { struct mlx5e_rss *rss = res->rss[i]; + u32 *vhca_ids; if (!rss) continue; - mlx5e_rss_enable(rss, res->rss_rqns, res->rss_nch); + vhca_ids = get_vhca_ids(res, 0); + mlx5e_rss_enable(rss, res->rss_rqns, vhca_ids, res->rss_nch); } } @@ -200,6 +213,7 @@ int mlx5e_rx_res_rss_get_rxfh(struct mlx5e_rx_res *res, u32 rss_idx, int mlx5e_rx_res_rss_set_rxfh(struct mlx5e_rx_res *res, u32 rss_idx, const u32 *indir, const u8 *key, const u8 *hfunc) { + u32 *vhca_ids = get_vhca_ids(res, 0); struct mlx5e_rss *rss; if (rss_idx >= MLX5E_MAX_NUM_RSS) @@ -209,7 +223,8 @@ int mlx5e_rx_res_rss_set_rxfh(struct mlx5e_rx_res *res, u32 rss_idx, if (!rss) return -ENOENT; - return mlx5e_rss_set_rxfh(rss, indir, key, hfunc, res->rss_rqns, res->rss_nch); + return mlx5e_rss_set_rxfh(rss, indir, key, hfunc, res->rss_rqns, vhca_ids, + res->rss_nch); } int mlx5e_rx_res_rss_get_hash_fields(struct mlx5e_rx_res *res, u32 rss_idx, @@ -280,11 +295,13 @@ struct mlx5e_rss *mlx5e_rx_res_rss_get(struct mlx5e_rx_res *res, u32 rss_idx) static void mlx5e_rx_res_free(struct mlx5e_rx_res *res) { + kvfree(res->rss_vhca_ids); kvfree(res->rss_rqns); kvfree(res); } -static struct mlx5e_rx_res *mlx5e_rx_res_alloc(struct mlx5_core_dev *mdev, unsigned int max_nch) +static struct mlx5e_rx_res *mlx5e_rx_res_alloc(struct mlx5_core_dev *mdev, unsigned int max_nch, + bool multi_vhca) { struct mlx5e_rx_res *rx_res; @@ -298,6 +315,15 @@ static struct mlx5e_rx_res *mlx5e_rx_res_alloc(struct mlx5_core_dev *mdev, unsig return NULL; } + if (multi_vhca) { + rx_res->rss_vhca_ids = kvcalloc(max_nch, sizeof(*rx_res->rss_vhca_ids), GFP_KERNEL); + if (!rx_res->rss_vhca_ids) { + kvfree(rx_res->rss_rqns); + kvfree(rx_res); + return NULL; + } + } + return rx_res; } @@ -424,10 +450,11 @@ mlx5e_rx_res_create(struct mlx5_core_dev *mdev, enum mlx5e_rx_res_features featu const struct mlx5e_packet_merge_param *init_pkt_merge_param, unsigned int init_nch) { + bool multi_vhca = features & MLX5E_RX_RES_FEATURE_MULTI_VHCA; struct mlx5e_rx_res *res; int err; - res = mlx5e_rx_res_alloc(mdev, max_nch); + res = mlx5e_rx_res_alloc(mdev, max_nch, multi_vhca); if (!res) return ERR_PTR(-ENOMEM); @@ -504,10 +531,11 @@ static void mlx5e_rx_res_channel_activate_direct(struct mlx5e_rx_res *res, struct mlx5e_channels *chs, unsigned int ix) { + u32 *vhca_id = get_vhca_ids(res, ix); u32 rqn = res->rss_rqns[ix]; int err; - err = mlx5e_rqt_redirect_direct(&res->channels[ix].direct_rqt, rqn); + err = mlx5e_rqt_redirect_direct(&res->channels[ix].direct_rqt, rqn, vhca_id); if (err) mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to RQ %#x (channel %u): err = %d\n", mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt), @@ -519,7 +547,7 @@ static void mlx5e_rx_res_channel_deactivate_direct(struct mlx5e_rx_res *res, { int err; - err = mlx5e_rqt_redirect_direct(&res->channels[ix].direct_rqt, res->drop_rqn); + err = mlx5e_rqt_redirect_direct(&res->channels[ix].direct_rqt, res->drop_rqn, NULL); if (err) mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to drop RQ %#x (channel %u): err = %d\n", mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt), @@ -534,10 +562,12 @@ void mlx5e_rx_res_channels_activate(struct mlx5e_rx_res *res, struct mlx5e_chann nch = mlx5e_channels_get_num(chs); for (ix = 0; ix < chs->num; ix++) { + u32 *vhca_id = get_vhca_ids(res, ix); + if (mlx5e_channels_is_xsk(chs, ix)) - mlx5e_channels_get_xsk_rqn(chs, ix, &res->rss_rqns[ix]); + mlx5e_channels_get_xsk_rqn(chs, ix, &res->rss_rqns[ix], vhca_id); else - mlx5e_channels_get_regular_rqn(chs, ix, &res->rss_rqns[ix]); + mlx5e_channels_get_regular_rqn(chs, ix, &res->rss_rqns[ix], vhca_id); } res->rss_nch = chs->num; @@ -554,7 +584,7 @@ void mlx5e_rx_res_channels_activate(struct mlx5e_rx_res *res, struct mlx5e_chann if (!mlx5e_channels_get_ptp_rqn(chs, &rqn)) rqn = res->drop_rqn; - err = mlx5e_rqt_redirect_direct(&res->ptp.rqt, rqn); + err = mlx5e_rqt_redirect_direct(&res->ptp.rqt, rqn, NULL); if (err) mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to RQ %#x (PTP): err = %d\n", mlx5e_rqt_get_rqtn(&res->ptp.rqt), @@ -573,7 +603,7 @@ void mlx5e_rx_res_channels_deactivate(struct mlx5e_rx_res *res) mlx5e_rx_res_channel_deactivate_direct(res, ix); if (res->features & MLX5E_RX_RES_FEATURE_PTP) { - err = mlx5e_rqt_redirect_direct(&res->ptp.rqt, res->drop_rqn); + err = mlx5e_rqt_redirect_direct(&res->ptp.rqt, res->drop_rqn, NULL); if (err) mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to drop RQ %#x (PTP): err = %d\n", mlx5e_rqt_get_rqtn(&res->ptp.rqt), @@ -584,10 +614,12 @@ void mlx5e_rx_res_channels_deactivate(struct mlx5e_rx_res *res) void mlx5e_rx_res_xsk_update(struct mlx5e_rx_res *res, struct mlx5e_channels *chs, unsigned int ix, bool xsk) { + u32 *vhca_id = get_vhca_ids(res, ix); + if (xsk) - mlx5e_channels_get_xsk_rqn(chs, ix, &res->rss_rqns[ix]); + mlx5e_channels_get_xsk_rqn(chs, ix, &res->rss_rqns[ix], vhca_id); else - mlx5e_channels_get_regular_rqn(chs, ix, &res->rss_rqns[ix]); + mlx5e_channels_get_regular_rqn(chs, ix, &res->rss_rqns[ix], vhca_id); mlx5e_rx_res_rss_enable(res); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h index 82aaba8a82b3..7b1a9f0f1874 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h @@ -18,6 +18,7 @@ struct mlx5e_rss_params_hash; enum mlx5e_rx_res_features { MLX5E_RX_RES_FEATURE_INNER_FT = BIT(0), MLX5E_RX_RES_FEATURE_PTP = BIT(1), + MLX5E_RX_RES_FEATURE_MULTI_VHCA = BIT(2), }; /* Setup */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c index ac458a8d10e0..53ca16cb9c41 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c @@ -63,10 +63,12 @@ static int mlx5e_open_trap_rq(struct mlx5e_priv *priv, struct mlx5e_trap *t) struct mlx5e_create_cq_param ccp = {}; struct dim_cq_moder trap_moder = {}; struct mlx5e_rq *rq = &t->rq; + u16 q_counter; int node; int err; node = dev_to_node(mdev->device); + q_counter = priv->q_counter[0]; ccp.netdev = priv->netdev; ccp.wq = priv->wq; @@ -79,7 +81,7 @@ static int mlx5e_open_trap_rq(struct mlx5e_priv *priv, struct mlx5e_trap *t) return err; mlx5e_init_trap_rq(t, &t->params, rq); - err = mlx5e_open_rq(&t->params, rq_param, NULL, node, rq); + err = mlx5e_open_rq(&t->params, rq_param, NULL, node, q_counter, rq); if (err) goto err_destroy_cq; @@ -116,15 +118,14 @@ static int mlx5e_create_trap_direct_rq_tir(struct mlx5_core_dev *mdev, struct ml } static void mlx5e_build_trap_params(struct mlx5_core_dev *mdev, - int max_mtu, u16 q_counter, - struct mlx5e_trap *t) + int max_mtu, struct mlx5e_trap *t) { struct mlx5e_params *params = &t->params; params->rq_wq_type = MLX5_WQ_TYPE_CYCLIC; mlx5e_init_rq_type_params(mdev, params); params->sw_mtu = max_mtu; - mlx5e_build_rq_param(mdev, params, NULL, q_counter, &t->rq_param); + mlx5e_build_rq_param(mdev, params, NULL, &t->rq_param); } static struct mlx5e_trap *mlx5e_open_trap(struct mlx5e_priv *priv) @@ -138,7 +139,7 @@ static struct mlx5e_trap *mlx5e_open_trap(struct mlx5e_priv *priv) if (!t) return ERR_PTR(-ENOMEM); - mlx5e_build_trap_params(priv->mdev, netdev->max_mtu, priv->q_counter, t); + mlx5e_build_trap_params(priv->mdev, netdev->max_mtu, t); t->priv = priv; t->mdev = priv->mdev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c index ebada0c5af3c..db776e515b6a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c @@ -6,10 +6,10 @@ #include "setup.h" #include "en/params.h" -static int mlx5e_xsk_map_pool(struct mlx5e_priv *priv, +static int mlx5e_xsk_map_pool(struct mlx5_core_dev *mdev, struct xsk_buff_pool *pool) { - struct device *dev = mlx5_core_dma_dev(priv->mdev); + struct device *dev = mlx5_core_dma_dev(mdev); return xsk_pool_dma_map(pool, dev, DMA_ATTR_SKIP_CPU_SYNC); } @@ -89,7 +89,7 @@ static int mlx5e_xsk_enable_locked(struct mlx5e_priv *priv, if (unlikely(!mlx5e_xsk_is_pool_sane(pool))) return -EINVAL; - err = mlx5e_xsk_map_pool(priv, pool); + err = mlx5e_xsk_map_pool(mlx5_sd_ch_ix_get_dev(priv->mdev, ix), pool); if (unlikely(err)) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c index 82e6abbc1734..06592b9f0424 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -49,10 +49,9 @@ bool mlx5e_validate_xsk_param(struct mlx5e_params *params, static void mlx5e_build_xsk_cparam(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, - u16 q_counter, struct mlx5e_channel_param *cparam) { - mlx5e_build_rq_param(mdev, params, xsk, q_counter, &cparam->rq); + mlx5e_build_rq_param(mdev, params, xsk, &cparam->rq); mlx5e_build_xdpsq_param(mdev, params, xsk, &cparam->xdp_sq); } @@ -93,6 +92,7 @@ static int mlx5e_open_xsk_rq(struct mlx5e_channel *c, struct mlx5e_params *param struct mlx5e_rq_param *rq_params, struct xsk_buff_pool *pool, struct mlx5e_xsk_param *xsk) { + u16 q_counter = c->priv->q_counter[c->sd_ix]; struct mlx5e_rq *xskrq = &c->xskrq; int err; @@ -100,7 +100,7 @@ static int mlx5e_open_xsk_rq(struct mlx5e_channel *c, struct mlx5e_params *param if (err) return err; - err = mlx5e_open_rq(params, rq_params, xsk, cpu_to_node(c->cpu), xskrq); + err = mlx5e_open_rq(params, rq_params, xsk, cpu_to_node(c->cpu), q_counter, xskrq); if (err) return err; @@ -125,7 +125,7 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params, if (!cparam) return -ENOMEM; - mlx5e_build_xsk_cparam(priv->mdev, params, xsk, priv->q_counter, cparam); + mlx5e_build_xsk_cparam(priv->mdev, params, xsk, cparam); err = mlx5e_open_cq(c->mdev, params->rx_cq_moderation, &cparam->rq.cqp, &ccp, &c->xskrq.cq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c index 984fa04bd331..e3e57c849436 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c @@ -96,7 +96,7 @@ bool mlx5e_is_ktls_rx(struct mlx5_core_dev *mdev) { u8 max_sq_wqebbs = mlx5e_get_max_sq_wqebbs(mdev); - if (is_kdump_kernel() || !MLX5_CAP_GEN(mdev, tls_rx)) + if (is_kdump_kernel() || !MLX5_CAP_GEN(mdev, tls_rx) || mlx5_get_sd(mdev)) return false; /* Check the possibility to post the required ICOSQ WQEs. */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h index f11075e67658..adc6d8ea0960 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h @@ -11,6 +11,7 @@ #ifdef CONFIG_MLX5_EN_TLS #include "lib/crypto.h" +#include "lib/mlx5.h" struct mlx5_crypto_dek *mlx5_ktls_create_key(struct mlx5_crypto_dek_pool *dek_pool, struct tls_crypto_info *crypto_info); @@ -61,7 +62,8 @@ void mlx5e_ktls_rx_resync_destroy_resp_list(struct mlx5e_ktls_resync_resp *resp_ static inline bool mlx5e_is_ktls_tx(struct mlx5_core_dev *mdev) { - return !is_kdump_kernel() && MLX5_CAP_GEN(mdev, tls_tx); + return !is_kdump_kernel() && MLX5_CAP_GEN(mdev, tls_tx) && + !mlx5_get_sd(mdev); } bool mlx5e_is_ktls_rx(struct mlx5_core_dev *mdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c index 9b597cb24598..65ccb33edafb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c @@ -267,7 +267,7 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq, goto err_out; } - pdev = mlx5_core_dma_dev(sq->channel->priv->mdev); + pdev = mlx5_core_dma_dev(sq->channel->mdev); buf->dma_addr = dma_map_single(pdev, &buf->progress, PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(pdev, buf->dma_addr))) { @@ -425,14 +425,12 @@ void mlx5e_ktls_handle_get_psv_completion(struct mlx5e_icosq_wqe_info *wi, { struct mlx5e_ktls_rx_resync_buf *buf = wi->tls_get_params.buf; struct mlx5e_ktls_offload_context_rx *priv_rx; - struct mlx5e_ktls_rx_resync_ctx *resync; u8 tracker_state, auth_state, *ctx; struct device *dev; u32 hw_seq; priv_rx = buf->priv_rx; - resync = &priv_rx->resync; - dev = mlx5_core_dma_dev(resync->priv->mdev); + dev = mlx5_core_dma_dev(sq->channel->mdev); if (unlikely(test_bit(MLX5E_PRIV_RX_FLAG_DELETING, priv_rx->flags))) goto out; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index 67f546683e85..6ed3a32b7e22 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -95,7 +95,7 @@ static void mlx5e_destroy_tises(struct mlx5_core_dev *mdev, u32 tisn[MLX5_MAX_PO { int tc, i; - for (i = 0; i < MLX5_MAX_PORTS; i++) + for (i = 0; i < mlx5e_get_num_lag_ports(mdev); i++) for (tc = 0; tc < MLX5_MAX_NUM_TC; tc++) mlx5e_destroy_tis(mdev, tisn[i][tc]); } @@ -110,7 +110,7 @@ static int mlx5e_create_tises(struct mlx5_core_dev *mdev, u32 tisn[MLX5_MAX_PORT int tc, i; int err; - for (i = 0; i < MLX5_MAX_PORTS; i++) { + for (i = 0; i < mlx5e_get_num_lag_ports(mdev); i++) { for (tc = 0; tc < MLX5_MAX_NUM_TC; tc++) { u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {}; void *tisc; @@ -140,7 +140,7 @@ err_close_tises: return err; } -int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev) +int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises) { struct mlx5e_hw_objs *res = &mdev->mlx5e_res.hw_objs; int err; @@ -169,11 +169,15 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev) goto err_destroy_mkey; } - err = mlx5e_create_tises(mdev, res->tisn); - if (err) { - mlx5_core_err(mdev, "alloc tises failed, %d\n", err); - goto err_destroy_bfreg; + if (create_tises) { + err = mlx5e_create_tises(mdev, res->tisn); + if (err) { + mlx5_core_err(mdev, "alloc tises failed, %d\n", err); + goto err_destroy_bfreg; + } + res->tisn_valid = true; } + INIT_LIST_HEAD(&res->td.tirs_list); mutex_init(&res->td.list_lock); @@ -203,7 +207,8 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev) mlx5_crypto_dek_cleanup(mdev->mlx5e_res.dek_priv); mdev->mlx5e_res.dek_priv = NULL; - mlx5e_destroy_tises(mdev, res->tisn); + if (res->tisn_valid) + mlx5e_destroy_tises(mdev, res->tisn); mlx5_free_bfreg(mdev, &res->bfreg); mlx5_core_destroy_mkey(mdev, res->mkey); mlx5_core_dealloc_transport_domain(mdev, res->td.tdn); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index b5f1c4ca38ba..40626b6108fb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -70,6 +70,7 @@ #include "qos.h" #include "en/trap.h" #include "lib/devcom.h" +#include "lib/sd.h" bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev, u8 page_shift, enum mlx5e_mpwrq_umr_mode umr_mode) @@ -1024,7 +1025,7 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq) mlx5_wq_destroy(&rq->wq_ctrl); } -int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param) +int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param, u16 q_counter) { struct mlx5_core_dev *mdev = rq->mdev; u8 ts_format; @@ -1051,6 +1052,7 @@ int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param) MLX5_SET(rqc, rqc, cqn, rq->cq.mcq.cqn); MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RST); MLX5_SET(rqc, rqc, ts_format, ts_format); + MLX5_SET(rqc, rqc, counter_set_id, q_counter); MLX5_SET(wq, wq, log_wq_pg_sz, rq->wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); MLX5_SET64(wq, wq, dbr_addr, rq->wq_ctrl.db.dma); @@ -1274,7 +1276,7 @@ void mlx5e_free_rx_descs(struct mlx5e_rq *rq) } int mlx5e_open_rq(struct mlx5e_params *params, struct mlx5e_rq_param *param, - struct mlx5e_xsk_param *xsk, int node, + struct mlx5e_xsk_param *xsk, int node, u16 q_counter, struct mlx5e_rq *rq) { struct mlx5_core_dev *mdev = rq->mdev; @@ -1287,7 +1289,7 @@ int mlx5e_open_rq(struct mlx5e_params *params, struct mlx5e_rq_param *param, if (err) return err; - err = mlx5e_create_rq(rq, param); + err = mlx5e_create_rq(rq, param, q_counter); if (err) goto err_free_rq; @@ -2333,13 +2335,14 @@ static int mlx5e_set_tx_maxrate(struct net_device *dev, int index, u32 rate) static int mlx5e_open_rxq_rq(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_rq_param *rq_params) { + u16 q_counter = c->priv->q_counter[c->sd_ix]; int err; err = mlx5e_init_rxq_rq(c, params, rq_params->xdp_frag_size, &c->rq); if (err) return err; - return mlx5e_open_rq(params, rq_params, NULL, cpu_to_node(c->cpu), &c->rq); + return mlx5e_open_rq(params, rq_params, NULL, cpu_to_node(c->cpu), q_counter, &c->rq); } static int mlx5e_open_queues(struct mlx5e_channel *c, @@ -2526,14 +2529,20 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, struct xsk_buff_pool *xsk_pool, struct mlx5e_channel **cp) { - int cpu = mlx5_comp_vector_get_cpu(priv->mdev, ix); struct net_device *netdev = priv->netdev; + struct mlx5_core_dev *mdev; struct mlx5e_xsk_param xsk; struct mlx5e_channel *c; unsigned int irq; + int vec_ix; + int cpu; int err; - err = mlx5_comp_irqn_get(priv->mdev, ix, &irq); + mdev = mlx5_sd_ch_ix_get_dev(priv->mdev, ix); + vec_ix = mlx5_sd_ch_ix_get_vec_ix(mdev, ix); + cpu = mlx5_comp_vector_get_cpu(mdev, vec_ix); + + err = mlx5_comp_irqn_get(mdev, vec_ix, &irq); if (err) return err; @@ -2546,18 +2555,20 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, return -ENOMEM; c->priv = priv; - c->mdev = priv->mdev; + c->mdev = mdev; c->tstamp = &priv->tstamp; c->ix = ix; + c->vec_ix = vec_ix; + c->sd_ix = mlx5_sd_ch_ix_get_dev_ix(mdev, ix); c->cpu = cpu; - c->pdev = mlx5_core_dma_dev(priv->mdev); + c->pdev = mlx5_core_dma_dev(mdev); c->netdev = priv->netdev; - c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey); + c->mkey_be = cpu_to_be32(mdev->mlx5e_res.hw_objs.mkey); c->num_tc = mlx5e_get_dcb_num_tc(params); c->xdp = !!params->xdp_prog; c->stats = &priv->channel_stats[ix]->ch; c->aff_mask = irq_get_effective_affinity_mask(irq); - c->lag_port = mlx5e_enumerate_lag_port(priv->mdev, ix); + c->lag_port = mlx5e_enumerate_lag_port(mdev, ix); netif_napi_add(netdev, &c->napi, mlx5e_napi_poll); @@ -2647,7 +2658,7 @@ int mlx5e_open_channels(struct mlx5e_priv *priv, if (!chs->c || !cparam) goto err_free; - err = mlx5e_build_channel_param(priv->mdev, &chs->params, priv->q_counter, cparam); + err = mlx5e_build_channel_param(priv->mdev, &chs->params, cparam); if (err) goto err_free; @@ -2935,15 +2946,18 @@ static MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_update_netdev_queues); static void mlx5e_set_default_xps_cpumasks(struct mlx5e_priv *priv, struct mlx5e_params *params) { - struct mlx5_core_dev *mdev = priv->mdev; - int num_comp_vectors, ix, irq; - - num_comp_vectors = mlx5_comp_vectors_max(mdev); + int ix; for (ix = 0; ix < params->num_channels; ix++) { + int num_comp_vectors, irq, vec_ix; + struct mlx5_core_dev *mdev; + + mdev = mlx5_sd_ch_ix_get_dev(priv->mdev, ix); + num_comp_vectors = mlx5_comp_vectors_max(mdev); cpumask_clear(priv->scratchpad.cpumask); + vec_ix = mlx5_sd_ch_ix_get_vec_ix(mdev, ix); - for (irq = ix; irq < num_comp_vectors; irq += params->num_channels) { + for (irq = vec_ix; irq < num_comp_vectors; irq += params->num_channels) { int cpu = mlx5_comp_vector_get_cpu(mdev, irq); cpumask_set_cpu(cpu, priv->scratchpad.cpumask); @@ -3335,7 +3349,7 @@ int mlx5e_open_drop_rq(struct mlx5e_priv *priv, struct mlx5e_cq *cq = &drop_rq->cq; int err; - mlx5e_build_drop_rq_param(mdev, priv->drop_rq_q_counter, &rq_param); + mlx5e_build_drop_rq_param(mdev, &rq_param); err = mlx5e_alloc_drop_cq(priv, cq, &cq_param); if (err) @@ -3349,7 +3363,7 @@ int mlx5e_open_drop_rq(struct mlx5e_priv *priv, if (err) goto err_destroy_cq; - err = mlx5e_create_rq(drop_rq, &rq_param); + err = mlx5e_create_rq(drop_rq, &rq_param, priv->drop_rq_q_counter); if (err) goto err_free_rq; @@ -3785,7 +3799,7 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) stats->tx_errors = stats->tx_aborted_errors + stats->tx_carrier_errors; } -static void mlx5e_nic_set_rx_mode(struct mlx5e_priv *priv) +void mlx5e_nic_set_rx_mode(struct mlx5e_priv *priv) { if (mlx5e_is_uplink_rep(priv)) return; /* no rx mode for uplink rep */ @@ -4990,6 +5004,15 @@ const struct net_device_ops mlx5e_netdev_ops = { #endif }; +const struct net_device_ops mlx5e_mgmt_netdev_ops = { + .ndo_open = mlx5e_open, + .ndo_stop = mlx5e_close, + .ndo_start_xmit = mlx5e_xmit, + .ndo_get_stats64 = mlx5e_get_stats, + .ndo_change_mtu = mlx5e_change_nic_mtu, + .ndo_set_rx_mode = mlx5e_set_rx_mode, +}; + static u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout) { int i; @@ -5129,7 +5152,11 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) SET_NETDEV_DEV(netdev, mdev->device); - netdev->netdev_ops = &mlx5e_netdev_ops; + if (mlx5_core_is_mgmt_pf(mdev)) + netdev->netdev_ops = &mlx5e_mgmt_netdev_ops; + else + netdev->netdev_ops = &mlx5e_netdev_ops; + netdev->xdp_metadata_ops = &mlx5e_xdp_metadata_ops; netdev->xsk_tx_metadata_ops = &mlx5e_xsk_tx_metadata_ops; @@ -5264,13 +5291,17 @@ void mlx5e_create_q_counters(struct mlx5e_priv *priv) u32 out[MLX5_ST_SZ_DW(alloc_q_counter_out)] = {}; u32 in[MLX5_ST_SZ_DW(alloc_q_counter_in)] = {}; struct mlx5_core_dev *mdev = priv->mdev; - int err; + struct mlx5_core_dev *pos; + int err, i; MLX5_SET(alloc_q_counter_in, in, opcode, MLX5_CMD_OP_ALLOC_Q_COUNTER); - err = mlx5_cmd_exec_inout(mdev, alloc_q_counter, in, out); - if (!err) - priv->q_counter = - MLX5_GET(alloc_q_counter_out, out, counter_set_id); + + mlx5_sd_for_each_dev(i, mdev, pos) { + err = mlx5_cmd_exec_inout(pos, alloc_q_counter, in, out); + if (!err) + priv->q_counter[i] = + MLX5_GET(alloc_q_counter_out, out, counter_set_id); + } err = mlx5_cmd_exec_inout(mdev, alloc_q_counter, in, out); if (!err) @@ -5281,13 +5312,17 @@ void mlx5e_create_q_counters(struct mlx5e_priv *priv) void mlx5e_destroy_q_counters(struct mlx5e_priv *priv) { u32 in[MLX5_ST_SZ_DW(dealloc_q_counter_in)] = {}; + struct mlx5_core_dev *pos; + int i; MLX5_SET(dealloc_q_counter_in, in, opcode, MLX5_CMD_OP_DEALLOC_Q_COUNTER); - if (priv->q_counter) { - MLX5_SET(dealloc_q_counter_in, in, counter_set_id, - priv->q_counter); - mlx5_cmd_exec_in(priv->mdev, dealloc_q_counter, in); + mlx5_sd_for_each_dev(i, priv->mdev, pos) { + if (priv->q_counter[i]) { + MLX5_SET(dealloc_q_counter_in, in, counter_set_id, + priv->q_counter[i]); + mlx5_cmd_exec_in(pos, dealloc_q_counter, in); + } } if (priv->drop_rq_q_counter) { @@ -5371,6 +5406,8 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv) features = MLX5E_RX_RES_FEATURE_PTP; if (mlx5_tunnel_inner_ft_supported(mdev)) features |= MLX5E_RX_RES_FEATURE_INNER_FT; + if (mlx5_get_sd(priv->mdev)) + features |= MLX5E_RX_RES_FEATURE_MULTI_VHCA; priv->rx_res = mlx5e_rx_res_create(priv->mdev, features, priv->max_nch, priv->drop_rq.rqn, &priv->channels.params.packet_merge, @@ -5980,28 +6017,52 @@ void mlx5e_destroy_netdev(struct mlx5e_priv *priv) free_netdev(netdev); } -static int mlx5e_resume(struct auxiliary_device *adev) +static int _mlx5e_resume(struct auxiliary_device *adev) { struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev); struct mlx5e_priv *priv = mlx5e_dev->priv; struct net_device *netdev = priv->netdev; struct mlx5_core_dev *mdev = edev->mdev; - int err; + struct mlx5_core_dev *pos, *to; + int err, i; if (netif_device_present(netdev)) return 0; - err = mlx5e_create_mdev_resources(mdev); - if (err) - return err; + mlx5_sd_for_each_dev(i, mdev, pos) { + err = mlx5e_create_mdev_resources(pos, true); + if (err) + goto err_destroy_mdev_res; + } err = mlx5e_attach_netdev(priv); - if (err) { - mlx5e_destroy_mdev_resources(mdev); + if (err) + goto err_destroy_mdev_res; + + return 0; + +err_destroy_mdev_res: + to = pos; + mlx5_sd_for_each_dev_to(i, mdev, to, pos) + mlx5e_destroy_mdev_resources(pos); + return err; +} + +static int mlx5e_resume(struct auxiliary_device *adev) +{ + struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); + struct mlx5_core_dev *mdev = edev->mdev; + struct auxiliary_device *actual_adev; + int err; + + err = mlx5_sd_init(mdev); + if (err) return err; - } + actual_adev = mlx5_sd_get_adev(mdev, adev, edev->idx); + if (actual_adev) + return _mlx5e_resume(actual_adev); return 0; } @@ -6011,33 +6072,53 @@ static int _mlx5e_suspend(struct auxiliary_device *adev) struct mlx5e_priv *priv = mlx5e_dev->priv; struct net_device *netdev = priv->netdev; struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5_core_dev *pos; + int i; if (!netif_device_present(netdev)) { if (test_bit(MLX5E_STATE_DESTROYING, &priv->state)) - mlx5e_destroy_mdev_resources(mdev); + mlx5_sd_for_each_dev(i, mdev, pos) + mlx5e_destroy_mdev_resources(pos); return -ENODEV; } mlx5e_detach_netdev(priv); - mlx5e_destroy_mdev_resources(mdev); + mlx5_sd_for_each_dev(i, mdev, pos) + mlx5e_destroy_mdev_resources(pos); + return 0; } static int mlx5e_suspend(struct auxiliary_device *adev, pm_message_t state) { - return _mlx5e_suspend(adev); + struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); + struct mlx5_core_dev *mdev = edev->mdev; + struct auxiliary_device *actual_adev; + int err = 0; + + actual_adev = mlx5_sd_get_adev(mdev, adev, edev->idx); + if (actual_adev) + err = _mlx5e_suspend(actual_adev); + + mlx5_sd_cleanup(mdev); + return err; } static int _mlx5e_probe(struct auxiliary_device *adev) { struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); - const struct mlx5e_profile *profile = &mlx5e_nic_profile; struct mlx5_core_dev *mdev = edev->mdev; + const struct mlx5e_profile *profile; struct mlx5e_dev *mlx5e_dev; struct net_device *netdev; struct mlx5e_priv *priv; int err; + if (mlx5_core_is_mgmt_pf(mdev)) + profile = &mlx5e_mgmt_pf_nic_profile; + else + profile = &mlx5e_nic_profile; + mlx5e_dev = mlx5e_create_devlink(&adev->dev, mdev); if (IS_ERR(mlx5e_dev)) return PTR_ERR(mlx5e_dev); @@ -6071,9 +6152,9 @@ static int _mlx5e_probe(struct auxiliary_device *adev) goto err_destroy_netdev; } - err = mlx5e_resume(adev); + err = _mlx5e_resume(adev); if (err) { - mlx5_core_err(mdev, "mlx5e_resume failed, %d\n", err); + mlx5_core_err(mdev, "_mlx5e_resume failed, %d\n", err); goto err_profile_cleanup; } @@ -6104,15 +6185,29 @@ err_devlink_unregister: static int mlx5e_probe(struct auxiliary_device *adev, const struct auxiliary_device_id *id) { - return _mlx5e_probe(adev); + struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); + struct mlx5_core_dev *mdev = edev->mdev; + struct auxiliary_device *actual_adev; + int err; + + err = mlx5_sd_init(mdev); + if (err) + return err; + + actual_adev = mlx5_sd_get_adev(mdev, adev, edev->idx); + if (actual_adev) + return _mlx5e_probe(actual_adev); + return 0; } -static void mlx5e_remove(struct auxiliary_device *adev) +static void _mlx5e_remove(struct auxiliary_device *adev) { + struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev); struct mlx5e_priv *priv = mlx5e_dev->priv; + struct mlx5_core_dev *mdev = edev->mdev; - mlx5_core_uplink_netdev_set(priv->mdev, NULL); + mlx5_core_uplink_netdev_set(mdev, NULL); mlx5e_dcbnl_delete_app(priv); unregister_netdev(priv->netdev); _mlx5e_suspend(adev); @@ -6122,6 +6217,19 @@ static void mlx5e_remove(struct auxiliary_device *adev) mlx5e_destroy_devlink(mlx5e_dev); } +static void mlx5e_remove(struct auxiliary_device *adev) +{ + struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); + struct mlx5_core_dev *mdev = edev->mdev; + struct auxiliary_device *actual_adev; + + actual_adev = mlx5_sd_get_adev(mdev, adev, edev->idx); + if (actual_adev) + _mlx5e_remove(actual_adev); + + mlx5_sd_cleanup(mdev); +} + static const struct auxiliary_device_id mlx5e_id_table[] = { { .name = MLX5_ADEV_NAME ".eth", }, {}, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 4b96ad657145..f3d0898bdbc6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -561,11 +561,23 @@ static const struct counter_desc drop_rq_stats_desc[] = { #define NUM_Q_COUNTERS ARRAY_SIZE(q_stats_desc) #define NUM_DROP_RQ_COUNTERS ARRAY_SIZE(drop_rq_stats_desc) +static bool q_counter_any(struct mlx5e_priv *priv) +{ + struct mlx5_core_dev *pos; + int i; + + mlx5_sd_for_each_dev(i, priv->mdev, pos) + if (priv->q_counter[i++]) + return true; + + return false; +} + static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(qcnt) { int num_stats = 0; - if (priv->q_counter) + if (q_counter_any(priv)) num_stats += NUM_Q_COUNTERS; if (priv->drop_rq_q_counter) @@ -578,7 +590,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(qcnt) { int i; - for (i = 0; i < NUM_Q_COUNTERS && priv->q_counter; i++) + for (i = 0; i < NUM_Q_COUNTERS && q_counter_any(priv); i++) strcpy(data + (idx++) * ETH_GSTRING_LEN, q_stats_desc[i].format); @@ -593,7 +605,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(qcnt) { int i; - for (i = 0; i < NUM_Q_COUNTERS && priv->q_counter; i++) + for (i = 0; i < NUM_Q_COUNTERS && q_counter_any(priv); i++) data[idx++] = MLX5E_READ_CTR32_CPU(&priv->stats.qcnt, q_stats_desc, i); for (i = 0; i < NUM_DROP_RQ_COUNTERS && priv->drop_rq_q_counter; i++) @@ -607,18 +619,23 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(qcnt) struct mlx5e_qcounter_stats *qcnt = &priv->stats.qcnt; u32 out[MLX5_ST_SZ_DW(query_q_counter_out)] = {}; u32 in[MLX5_ST_SZ_DW(query_q_counter_in)] = {}; - int ret; + struct mlx5_core_dev *pos; + u32 rx_out_of_buffer = 0; + int ret, i; MLX5_SET(query_q_counter_in, in, opcode, MLX5_CMD_OP_QUERY_Q_COUNTER); - if (priv->q_counter) { - MLX5_SET(query_q_counter_in, in, counter_set_id, - priv->q_counter); - ret = mlx5_cmd_exec_inout(priv->mdev, query_q_counter, in, out); - if (!ret) - qcnt->rx_out_of_buffer = MLX5_GET(query_q_counter_out, - out, out_of_buffer); + mlx5_sd_for_each_dev(i, priv->mdev, pos) { + if (priv->q_counter[i]) { + MLX5_SET(query_q_counter_in, in, counter_set_id, + priv->q_counter[i]); + ret = mlx5_cmd_exec_inout(pos, query_q_counter, in, out); + if (!ret) + rx_out_of_buffer += MLX5_GET(query_q_counter_out, + out, out_of_buffer); + } } + qcnt->rx_out_of_buffer = rx_out_of_buffer; if (priv->drop_rq_q_counter) { MLX5_SET(query_q_counter_in, in, counter_set_id, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 30932c9c9a8f..b8ceb972df9e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -766,7 +766,7 @@ static int mlx5e_hairpin_create_indirect_rqt(struct mlx5e_hairpin *hp) return err; mlx5e_rss_params_indir_init_uniform(&indir, hp->num_channels); - err = mlx5e_rqt_init_indir(&hp->indir_rqt, mdev, hp->pair->rqn, hp->num_channels, + err = mlx5e_rqt_init_indir(&hp->indir_rqt, mdev, hp->pair->rqn, NULL, hp->num_channels, mlx5e_rx_res_get_current_hash(priv->rx_res).hfunc, &indir); @@ -1169,7 +1169,7 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, MLX5_CAP_GEN(priv->mdev, log_min_hairpin_wq_data_sz), MLX5_CAP_GEN(priv->mdev, log_max_hairpin_wq_data_sz)); - params.q_counter = priv->q_counter; + params.q_counter = priv->q_counter[0]; err = devl_param_driverinit_value_get( devlink, MLX5_DEVLINK_PARAM_ID_HAIRPIN_NUM_QUEUES, &val); if (err) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 3047d7015c52..3bf419d06d53 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1665,7 +1665,7 @@ int mlx5_esw_sf_max_hpf_functions(struct mlx5_core_dev *dev, u16 *max_sfs, u16 * void *hca_caps; int err; - if (!mlx5_core_is_ecpf(dev)) { + if (!mlx5_core_is_ecpf(dev) || mlx5_core_is_mgmt_pf(dev)) { *max_sfs = 0; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 58845121954c..d77be1b4dd9c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -783,7 +783,7 @@ static int mlx5_rdma_setup_rn(struct ib_device *ibdev, u32 port_num, } /* This should only be called once per mdev */ - err = mlx5e_create_mdev_resources(mdev); + err = mlx5e_create_mdev_resources(mdev, false); if (err) goto destroy_ht; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h index ec32b686f586..d58032dd0df7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h @@ -10,6 +10,7 @@ enum mlx5_devcom_component { MLX5_DEVCOM_ESW_OFFLOADS, MLX5_DEVCOM_MPV, MLX5_DEVCOM_HCA_PORTS, + MLX5_DEVCOM_SD_GROUP, MLX5_DEVCOM_NUM_COMPONENTS, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h index 2b5826a785c4..37d5f445598c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h @@ -54,4 +54,16 @@ static inline struct net_device *mlx5_uplink_netdev_get(struct mlx5_core_dev *md { return mdev->mlx5e_res.uplink_netdev; } + +struct mlx5_sd; + +static inline struct mlx5_sd *mlx5_get_sd(struct mlx5_core_dev *dev) +{ + return dev->sd; +} + +static inline void mlx5_set_sd(struct mlx5_core_dev *dev, struct mlx5_sd *sd) +{ + dev->sd = sd; +} #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c new file mode 100644 index 000000000000..f68942277c62 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c @@ -0,0 +1,487 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#include "lib/sd.h" +#include "mlx5_core.h" +#include "lib/mlx5.h" +#include "fs_cmd.h" +#include <linux/mlx5/vport.h> + +#define sd_info(__dev, format, ...) \ + dev_info((__dev)->device, "Socket-Direct: " format, ##__VA_ARGS__) +#define sd_warn(__dev, format, ...) \ + dev_warn((__dev)->device, "Socket-Direct: " format, ##__VA_ARGS__) + +struct mlx5_sd { + u32 group_id; + u8 host_buses; + struct mlx5_devcom_comp_dev *devcom; + bool primary; + union { + struct { /* primary */ + struct mlx5_core_dev *secondaries[MLX5_SD_MAX_GROUP_SZ - 1]; + struct mlx5_flow_table *tx_ft; + }; + struct { /* secondary */ + struct mlx5_core_dev *primary_dev; + u32 alias_obj_id; + }; + }; +}; + +static int mlx5_sd_get_host_buses(struct mlx5_core_dev *dev) +{ + struct mlx5_sd *sd = mlx5_get_sd(dev); + + if (!sd) + return 1; + + return sd->host_buses; +} + +static struct mlx5_core_dev *mlx5_sd_get_primary(struct mlx5_core_dev *dev) +{ + struct mlx5_sd *sd = mlx5_get_sd(dev); + + if (!sd) + return dev; + + return sd->primary ? dev : sd->primary_dev; +} + +struct mlx5_core_dev * +mlx5_sd_primary_get_peer(struct mlx5_core_dev *primary, int idx) +{ + struct mlx5_sd *sd; + + if (idx == 0) + return primary; + + if (idx >= mlx5_sd_get_host_buses(primary)) + return NULL; + + sd = mlx5_get_sd(primary); + return sd->secondaries[idx - 1]; +} + +int mlx5_sd_ch_ix_get_dev_ix(struct mlx5_core_dev *dev, int ch_ix) +{ + return ch_ix % mlx5_sd_get_host_buses(dev); +} + +int mlx5_sd_ch_ix_get_vec_ix(struct mlx5_core_dev *dev, int ch_ix) +{ + return ch_ix / mlx5_sd_get_host_buses(dev); +} + +struct mlx5_core_dev *mlx5_sd_ch_ix_get_dev(struct mlx5_core_dev *primary, int ch_ix) +{ + int mdev_idx = mlx5_sd_ch_ix_get_dev_ix(primary, ch_ix); + + return mlx5_sd_primary_get_peer(primary, mdev_idx); +} + +static bool ft_create_alias_supported(struct mlx5_core_dev *dev) +{ + u64 obj_allowed = MLX5_CAP_GEN_2_64(dev, allowed_object_for_other_vhca_access); + u32 obj_supp = MLX5_CAP_GEN_2(dev, cross_vhca_object_to_object_supported); + + if (!(obj_supp & + MLX5_CROSS_VHCA_OBJ_TO_OBJ_SUPPORTED_LOCAL_FLOW_TABLE_ROOT_TO_REMOTE_FLOW_TABLE)) + return false; + + if (!(obj_allowed & MLX5_ALLOWED_OBJ_FOR_OTHER_VHCA_ACCESS_FLOW_TABLE)) + return false; + + return true; +} + +static bool mlx5_sd_is_supported(struct mlx5_core_dev *dev, u8 host_buses) +{ + /* Feature is currently implemented for PFs only */ + if (!mlx5_core_is_pf(dev)) + return false; + + /* Honor the SW implementation limit */ + if (host_buses > MLX5_SD_MAX_GROUP_SZ) + return false; + + /* Disconnect secondaries from the network */ + if (!MLX5_CAP_GEN(dev, eswitch_manager)) + return false; + if (!MLX5_CAP_GEN(dev, silent_mode)) + return false; + + /* RX steering from primary to secondaries */ + if (!MLX5_CAP_GEN(dev, cross_vhca_rqt)) + return false; + if (host_buses > MLX5_CAP_GEN_2(dev, max_rqt_vhca_id)) + return false; + + /* TX steering from secondaries to primary */ + if (!ft_create_alias_supported(dev)) + return false; + if (!MLX5_CAP_FLOWTABLE_NIC_TX(dev, reset_root_to_default)) + return false; + + return true; +} + +static int mlx5_query_sd(struct mlx5_core_dev *dev, bool *sdm, + u8 *host_buses, u8 *sd_group) +{ + u32 out[MLX5_ST_SZ_DW(mpir_reg)]; + int err; + + err = mlx5_query_mpir_reg(dev, out); + if (err) + return err; + + err = mlx5_query_nic_vport_sd_group(dev, sd_group); + if (err) + return err; + + *sdm = MLX5_GET(mpir_reg, out, sdm); + *host_buses = MLX5_GET(mpir_reg, out, host_buses); + + return 0; +} + +static u32 mlx5_sd_group_id(struct mlx5_core_dev *dev, u8 sd_group) +{ + return (u32)((MLX5_CAP_GEN(dev, native_port_num) << 8) | sd_group); +} + +static int sd_init(struct mlx5_core_dev *dev) +{ + u8 host_buses, sd_group; + struct mlx5_sd *sd; + u32 group_id; + bool sdm; + int err; + + err = mlx5_query_sd(dev, &sdm, &host_buses, &sd_group); + if (err) + return err; + + if (!sdm) + return 0; + + if (!sd_group) + return 0; + + group_id = mlx5_sd_group_id(dev, sd_group); + + if (!mlx5_sd_is_supported(dev, host_buses)) { + sd_warn(dev, "can't support requested netdev combining for group id 0x%x), skipping\n", + group_id); + return 0; + } + + sd = kzalloc(sizeof(*sd), GFP_KERNEL); + if (!sd) + return -ENOMEM; + + sd->host_buses = host_buses; + sd->group_id = group_id; + + mlx5_set_sd(dev, sd); + + return 0; +} + +static void sd_cleanup(struct mlx5_core_dev *dev) +{ + struct mlx5_sd *sd = mlx5_get_sd(dev); + + mlx5_set_sd(dev, NULL); + kfree(sd); +} + +static int sd_register(struct mlx5_core_dev *dev) +{ + struct mlx5_devcom_comp_dev *devcom, *pos; + struct mlx5_core_dev *peer, *primary; + struct mlx5_sd *sd, *primary_sd; + int err, i; + + sd = mlx5_get_sd(dev); + devcom = mlx5_devcom_register_component(dev->priv.devc, MLX5_DEVCOM_SD_GROUP, + sd->group_id, NULL, dev); + if (!devcom) + return -ENOMEM; + + sd->devcom = devcom; + + if (mlx5_devcom_comp_get_size(devcom) != sd->host_buses) + return 0; + + mlx5_devcom_comp_lock(devcom); + mlx5_devcom_comp_set_ready(devcom, true); + mlx5_devcom_comp_unlock(devcom); + + if (!mlx5_devcom_for_each_peer_begin(devcom)) { + err = -ENODEV; + goto err_devcom_unreg; + } + + primary = dev; + mlx5_devcom_for_each_peer_entry(devcom, peer, pos) + if (peer->pdev->bus->number < primary->pdev->bus->number) + primary = peer; + + primary_sd = mlx5_get_sd(primary); + primary_sd->primary = true; + i = 0; + /* loop the secondaries */ + mlx5_devcom_for_each_peer_entry(primary_sd->devcom, peer, pos) { + struct mlx5_sd *peer_sd = mlx5_get_sd(peer); + + primary_sd->secondaries[i++] = peer; + peer_sd->primary = false; + peer_sd->primary_dev = primary; + } + + mlx5_devcom_for_each_peer_end(devcom); + return 0; + +err_devcom_unreg: + mlx5_devcom_comp_lock(sd->devcom); + mlx5_devcom_comp_set_ready(sd->devcom, false); + mlx5_devcom_comp_unlock(sd->devcom); + mlx5_devcom_unregister_component(sd->devcom); + return err; +} + +static void sd_unregister(struct mlx5_core_dev *dev) +{ + struct mlx5_sd *sd = mlx5_get_sd(dev); + + mlx5_devcom_comp_lock(sd->devcom); + mlx5_devcom_comp_set_ready(sd->devcom, false); + mlx5_devcom_comp_unlock(sd->devcom); + mlx5_devcom_unregister_component(sd->devcom); +} + +static int sd_cmd_set_primary(struct mlx5_core_dev *primary, u8 *alias_key) +{ + struct mlx5_cmd_allow_other_vhca_access_attr allow_attr = {}; + struct mlx5_sd *sd = mlx5_get_sd(primary); + struct mlx5_flow_table_attr ft_attr = {}; + struct mlx5_flow_namespace *nic_ns; + struct mlx5_flow_table *ft; + int err; + + nic_ns = mlx5_get_flow_namespace(primary, MLX5_FLOW_NAMESPACE_EGRESS); + if (!nic_ns) + return -EOPNOTSUPP; + + ft = mlx5_create_flow_table(nic_ns, &ft_attr); + if (IS_ERR(ft)) { + err = PTR_ERR(ft); + return err; + } + sd->tx_ft = ft; + memcpy(allow_attr.access_key, alias_key, ACCESS_KEY_LEN); + allow_attr.obj_type = MLX5_GENERAL_OBJECT_TYPES_FLOW_TABLE_ALIAS; + allow_attr.obj_id = (ft->type << FT_ID_FT_TYPE_OFFSET) | ft->id; + + err = mlx5_cmd_allow_other_vhca_access(primary, &allow_attr); + if (err) { + mlx5_core_err(primary, "Failed to allow other vhca access err=%d\n", + err); + mlx5_destroy_flow_table(ft); + return err; + } + + return 0; +} + +static void sd_cmd_unset_primary(struct mlx5_core_dev *primary) +{ + struct mlx5_sd *sd = mlx5_get_sd(primary); + + mlx5_destroy_flow_table(sd->tx_ft); +} + +static int sd_secondary_create_alias_ft(struct mlx5_core_dev *secondary, + struct mlx5_core_dev *primary, + struct mlx5_flow_table *ft, + u32 *obj_id, u8 *alias_key) +{ + u32 aliased_object_id = (ft->type << FT_ID_FT_TYPE_OFFSET) | ft->id; + u16 vhca_id_to_be_accessed = MLX5_CAP_GEN(primary, vhca_id); + struct mlx5_cmd_alias_obj_create_attr alias_attr = {}; + int ret; + + memcpy(alias_attr.access_key, alias_key, ACCESS_KEY_LEN); + alias_attr.obj_id = aliased_object_id; + alias_attr.obj_type = MLX5_GENERAL_OBJECT_TYPES_FLOW_TABLE_ALIAS; + alias_attr.vhca_id = vhca_id_to_be_accessed; + ret = mlx5_cmd_alias_obj_create(secondary, &alias_attr, obj_id); + if (ret) { + mlx5_core_err(secondary, "Failed to create alias object err=%d\n", + ret); + return ret; + } + + return 0; +} + +static void sd_secondary_destroy_alias_ft(struct mlx5_core_dev *secondary) +{ + struct mlx5_sd *sd = mlx5_get_sd(secondary); + + mlx5_cmd_alias_obj_destroy(secondary, sd->alias_obj_id, + MLX5_GENERAL_OBJECT_TYPES_FLOW_TABLE_ALIAS); +} + +static int sd_cmd_set_secondary(struct mlx5_core_dev *secondary, + struct mlx5_core_dev *primary, + u8 *alias_key) +{ + struct mlx5_sd *primary_sd = mlx5_get_sd(primary); + struct mlx5_sd *sd = mlx5_get_sd(secondary); + int err; + + err = mlx5_fs_cmd_set_l2table_entry_silent(secondary, 1); + if (err) + return err; + + err = sd_secondary_create_alias_ft(secondary, primary, primary_sd->tx_ft, + &sd->alias_obj_id, alias_key); + if (err) + goto err_unset_silent; + + err = mlx5_fs_cmd_set_tx_flow_table_root(secondary, sd->alias_obj_id, false); + if (err) + goto err_destroy_alias_ft; + + return 0; + +err_destroy_alias_ft: + sd_secondary_destroy_alias_ft(secondary); +err_unset_silent: + mlx5_fs_cmd_set_l2table_entry_silent(secondary, 0); + return err; +} + +static void sd_cmd_unset_secondary(struct mlx5_core_dev *secondary) +{ + mlx5_fs_cmd_set_tx_flow_table_root(secondary, 0, true); + sd_secondary_destroy_alias_ft(secondary); + mlx5_fs_cmd_set_l2table_entry_silent(secondary, 0); +} + +static void sd_print_group(struct mlx5_core_dev *primary) +{ + struct mlx5_sd *sd = mlx5_get_sd(primary); + struct mlx5_core_dev *pos; + int i; + + sd_info(primary, "group id %#x, primary %s, vhca %u\n", + sd->group_id, pci_name(primary->pdev), + MLX5_CAP_GEN(primary, vhca_id)); + mlx5_sd_for_each_secondary(i, primary, pos) + sd_info(primary, "group id %#x, secondary#%d %s, vhca %u\n", + sd->group_id, i - 1, pci_name(pos->pdev), + MLX5_CAP_GEN(pos, vhca_id)); +} + +int mlx5_sd_init(struct mlx5_core_dev *dev) +{ + struct mlx5_core_dev *primary, *pos, *to; + struct mlx5_sd *sd = mlx5_get_sd(dev); + u8 alias_key[ACCESS_KEY_LEN]; + int err, i; + + err = sd_init(dev); + if (err) + return err; + + sd = mlx5_get_sd(dev); + if (!sd) + return 0; + + err = sd_register(dev); + if (err) + goto err_sd_cleanup; + + if (!mlx5_devcom_comp_is_ready(sd->devcom)) + return 0; + + primary = mlx5_sd_get_primary(dev); + + for (i = 0; i < ACCESS_KEY_LEN; i++) + alias_key[i] = get_random_u8(); + + err = sd_cmd_set_primary(primary, alias_key); + if (err) + goto err_sd_unregister; + + mlx5_sd_for_each_secondary(i, primary, pos) { + err = sd_cmd_set_secondary(pos, primary, alias_key); + if (err) + goto err_unset_secondaries; + } + + sd_info(primary, "group id %#x, size %d, combined\n", + sd->group_id, mlx5_devcom_comp_get_size(sd->devcom)); + sd_print_group(primary); + + return 0; + +err_unset_secondaries: + to = pos; + mlx5_sd_for_each_secondary_to(i, primary, to, pos) + sd_cmd_unset_secondary(pos); + sd_cmd_unset_primary(primary); +err_sd_unregister: + sd_unregister(dev); +err_sd_cleanup: + sd_cleanup(dev); + return err; +} + +void mlx5_sd_cleanup(struct mlx5_core_dev *dev) +{ + struct mlx5_sd *sd = mlx5_get_sd(dev); + struct mlx5_core_dev *primary, *pos; + int i; + + if (!sd) + return; + + if (!mlx5_devcom_comp_is_ready(sd->devcom)) + goto out; + + primary = mlx5_sd_get_primary(dev); + mlx5_sd_for_each_secondary(i, primary, pos) + sd_cmd_unset_secondary(pos); + sd_cmd_unset_primary(primary); + + sd_info(primary, "group id %#x, uncombined\n", sd->group_id); +out: + sd_unregister(dev); + sd_cleanup(dev); +} + +struct auxiliary_device *mlx5_sd_get_adev(struct mlx5_core_dev *dev, + struct auxiliary_device *adev, + int idx) +{ + struct mlx5_sd *sd = mlx5_get_sd(dev); + struct mlx5_core_dev *primary; + + if (!sd) + return adev; + + if (!mlx5_devcom_comp_is_ready(sd->devcom)) + return NULL; + + primary = mlx5_sd_get_primary(dev); + if (dev == primary) + return adev; + + return &primary->priv.adev[idx]->adev; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.h new file mode 100644 index 000000000000..137efaf9aabc --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#ifndef __MLX5_LIB_SD_H__ +#define __MLX5_LIB_SD_H__ + +#define MLX5_SD_MAX_GROUP_SZ 2 + +struct mlx5_sd; + +struct mlx5_core_dev *mlx5_sd_primary_get_peer(struct mlx5_core_dev *primary, int idx); +int mlx5_sd_ch_ix_get_dev_ix(struct mlx5_core_dev *dev, int ch_ix); +int mlx5_sd_ch_ix_get_vec_ix(struct mlx5_core_dev *dev, int ch_ix); +struct mlx5_core_dev *mlx5_sd_ch_ix_get_dev(struct mlx5_core_dev *primary, int ch_ix); +struct auxiliary_device *mlx5_sd_get_adev(struct mlx5_core_dev *dev, + struct auxiliary_device *adev, + int idx); + +int mlx5_sd_init(struct mlx5_core_dev *dev); +void mlx5_sd_cleanup(struct mlx5_core_dev *dev); + +#define mlx5_sd_for_each_dev_from_to(i, primary, ix_from, to, pos) \ + for (i = ix_from; \ + (pos = mlx5_sd_primary_get_peer(primary, i)) && pos != (to); i++) + +#define mlx5_sd_for_each_dev(i, primary, pos) \ + mlx5_sd_for_each_dev_from_to(i, primary, 0, NULL, pos) + +#define mlx5_sd_for_each_dev_to(i, primary, to, pos) \ + mlx5_sd_for_each_dev_from_to(i, primary, 0, to, pos) + +#define mlx5_sd_for_each_secondary(i, primary, pos) \ + mlx5_sd_for_each_dev_from_to(i, primary, 1, NULL, pos) + +#define mlx5_sd_for_each_secondary_to(i, primary, to, pos) \ + mlx5_sd_for_each_dev_from_to(i, primary, 1, to, pos) + +#endif /* __MLX5_LIB_SD_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index 21753f327868..1005bb6935b6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -440,6 +440,27 @@ out: } EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_system_image_guid); +int mlx5_query_nic_vport_sd_group(struct mlx5_core_dev *mdev, u8 *sd_group) +{ + int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out); + u32 *out; + int err; + + out = kvzalloc(outlen, GFP_KERNEL); + if (!out) + return -ENOMEM; + + err = mlx5_query_nic_vport_context(mdev, 0, out); + if (err) + goto out; + + *sd_group = MLX5_GET(query_nic_vport_context_out, out, + nic_vport_context.sd_group); +out: + kvfree(out); + return err; +} + int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid) { u32 *out; diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig index e60b557d59b9..be01450c20dc 100644 --- a/drivers/net/ethernet/ti/Kconfig +++ b/drivers/net/ethernet/ti/Kconfig @@ -134,14 +134,16 @@ config TI_K3_AM65_CPTS protocol, Ethernet Enhanced Scheduled Traffic Operations (CPTS_ESTFn) and PCIe Subsystem Precision Time Measurement (PTM). -config TI_AM65_CPSW_TAS - bool "Enable TAS offload in AM65 CPSW" +config TI_AM65_CPSW_QOS + bool "Enable QoS offload features in AM65 CPSW" depends on TI_K3_AM65_CPSW_NUSS && NET_SCH_TAPRIO && TI_K3_AM65_CPTS help - Say y here to support Time Aware Shaper(TAS) offload in AM65 CPSW. - AM65 CPSW hardware supports Enhanced Scheduled Traffic (EST) - defined in IEEE 802.1Q 2018. The EST scheduler runs on CPTS and the - TAS/EST schedule is updated in the Fetch RAM memory of the CPSW. + This option enables QoS offload features in AM65 CPSW like + Time Aware Shaper (TAS) / Enhanced Scheduled Traffic (EST), + MQPRIO qdisc offload and Frame-Preemption MAC Merge / Interspersing + Express Traffic (IET). + The EST scheduler runs on CPTS and the TAS/EST schedule is + updated in the Fetch RAM memory of the CPSW. config TI_KEYSTONE_NETCP tristate "TI Keystone NETCP Core Support" diff --git a/drivers/net/ethernet/ti/Makefile b/drivers/net/ethernet/ti/Makefile index 27de1d697134..d8590304f3df 100644 --- a/drivers/net/ethernet/ti/Makefile +++ b/drivers/net/ethernet/ti/Makefile @@ -26,7 +26,8 @@ keystone_netcp_ethss-y := netcp_ethss.o netcp_sgmii.o netcp_xgbepcsr.o cpsw_ale. obj-$(CONFIG_TI_K3_CPPI_DESC_POOL) += k3-cppi-desc-pool.o obj-$(CONFIG_TI_K3_AM65_CPSW_NUSS) += ti-am65-cpsw-nuss.o -ti-am65-cpsw-nuss-y := am65-cpsw-nuss.o cpsw_sl.o am65-cpsw-ethtool.o cpsw_ale.o am65-cpsw-qos.o +ti-am65-cpsw-nuss-y := am65-cpsw-nuss.o cpsw_sl.o am65-cpsw-ethtool.o cpsw_ale.o +ti-am65-cpsw-nuss-$(CONFIG_TI_AM65_CPSW_QOS) += am65-cpsw-qos.o ti-am65-cpsw-nuss-$(CONFIG_TI_K3_AM65_CPSW_SWITCHDEV) += am65-cpsw-switchdev.o obj-$(CONFIG_TI_K3_AM65_CPTS) += am65-cpts.o diff --git a/drivers/net/ethernet/ti/am65-cpsw-ethtool.c b/drivers/net/ethernet/ti/am65-cpsw-ethtool.c index b9e1d568604b..35fceba01ea4 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-ethtool.c +++ b/drivers/net/ethernet/ti/am65-cpsw-ethtool.c @@ -11,6 +11,7 @@ #include <linux/pm_runtime.h> #include "am65-cpsw-nuss.h" +#include "am65-cpsw-qos.h" #include "cpsw_ale.h" #include "am65-cpts.h" @@ -670,6 +671,9 @@ static void am65_cpsw_get_eth_mac_stats(struct net_device *ndev, stats = port->stat_base; + if (s->src != ETHTOOL_MAC_STATS_SRC_AGGREGATE) + return; + s->FramesTransmittedOK = readl_relaxed(&stats->tx_good_frames); s->SingleCollisionFrames = readl_relaxed(&stats->tx_single_coll_frames); s->MultipleCollisionFrames = readl_relaxed(&stats->tx_mult_coll_frames); @@ -740,6 +744,240 @@ static int am65_cpsw_set_ethtool_priv_flags(struct net_device *ndev, u32 flags) return 0; } +static void am65_cpsw_port_iet_rx_enable(struct am65_cpsw_port *port, bool enable) +{ + u32 val; + + val = readl(port->port_base + AM65_CPSW_PN_REG_CTL); + if (enable) + val |= AM65_CPSW_PN_CTL_IET_PORT_EN; + else + val &= ~AM65_CPSW_PN_CTL_IET_PORT_EN; + + writel(val, port->port_base + AM65_CPSW_PN_REG_CTL); + am65_cpsw_iet_common_enable(port->common); +} + +static void am65_cpsw_port_iet_tx_enable(struct am65_cpsw_port *port, bool enable) +{ + u32 val; + + val = readl(port->port_base + AM65_CPSW_PN_REG_IET_CTRL); + if (enable) + val |= AM65_CPSW_PN_IET_MAC_PENABLE; + else + val &= ~AM65_CPSW_PN_IET_MAC_PENABLE; + + writel(val, port->port_base + AM65_CPSW_PN_REG_IET_CTRL); +} + +static int am65_cpsw_get_mm(struct net_device *ndev, struct ethtool_mm_state *state) +{ + struct am65_cpsw_port *port = am65_ndev_to_port(ndev); + struct am65_cpsw_ndev_priv *priv = netdev_priv(ndev); + u32 port_ctrl, iet_ctrl, iet_status; + u32 add_frag_size; + + if (!IS_ENABLED(CONFIG_TI_AM65_CPSW_QOS)) + return -EOPNOTSUPP; + + mutex_lock(&priv->mm_lock); + + iet_ctrl = readl(port->port_base + AM65_CPSW_PN_REG_IET_CTRL); + port_ctrl = readl(port->port_base + AM65_CPSW_PN_REG_CTL); + + state->tx_enabled = !!(iet_ctrl & AM65_CPSW_PN_IET_MAC_PENABLE); + state->pmac_enabled = !!(port_ctrl & AM65_CPSW_PN_CTL_IET_PORT_EN); + + iet_status = readl(port->port_base + AM65_CPSW_PN_REG_IET_STATUS); + + if (iet_ctrl & AM65_CPSW_PN_IET_MAC_DISABLEVERIFY) + state->verify_status = ETHTOOL_MM_VERIFY_STATUS_DISABLED; + else if (iet_status & AM65_CPSW_PN_MAC_VERIFIED) + state->verify_status = ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED; + else if (iet_status & AM65_CPSW_PN_MAC_VERIFY_FAIL) + state->verify_status = ETHTOOL_MM_VERIFY_STATUS_FAILED; + else + state->verify_status = ETHTOOL_MM_VERIFY_STATUS_UNKNOWN; + + add_frag_size = AM65_CPSW_PN_IET_MAC_GET_ADDFRAGSIZE(iet_ctrl); + state->tx_min_frag_size = ethtool_mm_frag_size_add_to_min(add_frag_size); + + /* Errata i2208: RX min fragment size cannot be less than 124 */ + state->rx_min_frag_size = 124; + + /* FPE active if common tx_enabled and verification success or disabled (forced) */ + state->tx_active = state->tx_enabled && + (state->verify_status == ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED || + state->verify_status == ETHTOOL_MM_VERIFY_STATUS_DISABLED); + state->verify_enabled = !(iet_ctrl & AM65_CPSW_PN_IET_MAC_DISABLEVERIFY); + + state->verify_time = port->qos.iet.verify_time_ms; + + /* 802.3-2018 clause 30.14.1.6, says that the aMACMergeVerifyTime + * variable has a range between 1 and 128 ms inclusive. Limit to that. + */ + state->max_verify_time = 128; + + mutex_unlock(&priv->mm_lock); + + return 0; +} + +static int am65_cpsw_set_mm(struct net_device *ndev, struct ethtool_mm_cfg *cfg, + struct netlink_ext_ack *extack) +{ + struct am65_cpsw_port *port = am65_ndev_to_port(ndev); + struct am65_cpsw_ndev_priv *priv = netdev_priv(ndev); + struct am65_cpsw_iet *iet = &port->qos.iet; + u32 val, add_frag_size; + int err; + + if (!IS_ENABLED(CONFIG_TI_AM65_CPSW_QOS)) + return -EOPNOTSUPP; + + err = ethtool_mm_frag_size_min_to_add(cfg->tx_min_frag_size, &add_frag_size, extack); + if (err) + return err; + + mutex_lock(&priv->mm_lock); + + if (cfg->pmac_enabled) { + /* change TX & RX FIFO MAX_BLKS as per TRM recommendation */ + if (!iet->original_max_blks) + iet->original_max_blks = readl(port->port_base + AM65_CPSW_PN_REG_MAX_BLKS); + + writel(AM65_CPSW_PN_TX_RX_MAX_BLKS_IET, + port->port_base + AM65_CPSW_PN_REG_MAX_BLKS); + } else if (iet->original_max_blks) { + /* restore RX & TX FIFO MAX_BLKS */ + writel(iet->original_max_blks, + port->port_base + AM65_CPSW_PN_REG_MAX_BLKS); + } + + am65_cpsw_port_iet_rx_enable(port, cfg->pmac_enabled); + am65_cpsw_port_iet_tx_enable(port, cfg->tx_enabled); + + val = readl(port->port_base + AM65_CPSW_PN_REG_IET_CTRL); + if (cfg->verify_enabled) { + val &= ~AM65_CPSW_PN_IET_MAC_DISABLEVERIFY; + /* Reset Verify state machine. Verification won't start here. + * Verification will be done once link-up. + */ + val |= AM65_CPSW_PN_IET_MAC_LINKFAIL; + } else { + val |= AM65_CPSW_PN_IET_MAC_DISABLEVERIFY; + /* Clear LINKFAIL to allow verify/response packets */ + val &= ~AM65_CPSW_PN_IET_MAC_LINKFAIL; + } + + val &= ~AM65_CPSW_PN_IET_MAC_MAC_ADDFRAGSIZE_MASK; + val |= AM65_CPSW_PN_IET_MAC_SET_ADDFRAGSIZE(add_frag_size); + writel(val, port->port_base + AM65_CPSW_PN_REG_IET_CTRL); + + /* verify_timeout_count can only be set at valid link */ + port->qos.iet.verify_time_ms = cfg->verify_time; + + /* enable/disable preemption based on link status */ + am65_cpsw_iet_commit_preemptible_tcs(port); + + mutex_unlock(&priv->mm_lock); + + return 0; +} + +static void am65_cpsw_get_mm_stats(struct net_device *ndev, + struct ethtool_mm_stats *s) +{ + struct am65_cpsw_port *port = am65_ndev_to_port(ndev); + void __iomem *base = port->stat_base; + + s->MACMergeFrameAssOkCount = readl(base + AM65_CPSW_STATN_IET_RX_ASSEMBLY_OK); + s->MACMergeFrameAssErrorCount = readl(base + AM65_CPSW_STATN_IET_RX_ASSEMBLY_ERROR); + s->MACMergeFrameSmdErrorCount = readl(base + AM65_CPSW_STATN_IET_RX_SMD_ERROR); + /* CPSW Functional Spec states: + * "The IET stat aMACMergeFragCountRx is derived by adding the + * Receive Assembly Error count to this value. i.e. AM65_CPSW_STATN_IET_RX_FRAG" + */ + s->MACMergeFragCountRx = readl(base + AM65_CPSW_STATN_IET_RX_FRAG) + s->MACMergeFrameAssErrorCount; + s->MACMergeFragCountTx = readl(base + AM65_CPSW_STATN_IET_TX_FRAG); + s->MACMergeHoldCount = readl(base + AM65_CPSW_STATN_IET_TX_HOLD); +} + +static int am65_cpsw_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) +{ + struct am65_cpsw_common *common = am65_ndev_to_common(ndev); + struct am65_cpsw_tx_chn *tx_chn; + + tx_chn = &common->tx_chns[0]; + + coal->rx_coalesce_usecs = common->rx_pace_timeout / 1000; + coal->tx_coalesce_usecs = tx_chn->tx_pace_timeout / 1000; + + return 0; +} + +static int am65_cpsw_get_per_queue_coalesce(struct net_device *ndev, u32 queue, + struct ethtool_coalesce *coal) +{ + struct am65_cpsw_common *common = am65_ndev_to_common(ndev); + struct am65_cpsw_tx_chn *tx_chn; + + if (queue >= AM65_CPSW_MAX_TX_QUEUES) + return -EINVAL; + + tx_chn = &common->tx_chns[queue]; + + coal->tx_coalesce_usecs = tx_chn->tx_pace_timeout / 1000; + + return 0; +} + +static int am65_cpsw_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) +{ + struct am65_cpsw_common *common = am65_ndev_to_common(ndev); + struct am65_cpsw_tx_chn *tx_chn; + + tx_chn = &common->tx_chns[0]; + + if (coal->rx_coalesce_usecs && coal->rx_coalesce_usecs < 20) + return -EINVAL; + + if (coal->tx_coalesce_usecs && coal->tx_coalesce_usecs < 20) + return -EINVAL; + + common->rx_pace_timeout = coal->rx_coalesce_usecs * 1000; + tx_chn->tx_pace_timeout = coal->tx_coalesce_usecs * 1000; + + return 0; +} + +static int am65_cpsw_set_per_queue_coalesce(struct net_device *ndev, u32 queue, + struct ethtool_coalesce *coal) +{ + struct am65_cpsw_common *common = am65_ndev_to_common(ndev); + struct am65_cpsw_tx_chn *tx_chn; + + if (queue >= AM65_CPSW_MAX_TX_QUEUES) + return -EINVAL; + + tx_chn = &common->tx_chns[queue]; + + if (coal->tx_coalesce_usecs && coal->tx_coalesce_usecs < 20) { + dev_info(common->dev, "defaulting to min value of 20us for tx-usecs for tx-%u\n", + queue); + coal->tx_coalesce_usecs = 20; + } + + tx_chn->tx_pace_timeout = coal->tx_coalesce_usecs * 1000; + + return 0; +} + const struct ethtool_ops am65_cpsw_ethtool_ops_slave = { .begin = am65_cpsw_ethtool_op_begin, .complete = am65_cpsw_ethtool_op_complete, @@ -758,6 +996,11 @@ const struct ethtool_ops am65_cpsw_ethtool_ops_slave = { .get_ts_info = am65_cpsw_get_ethtool_ts_info, .get_priv_flags = am65_cpsw_get_ethtool_priv_flags, .set_priv_flags = am65_cpsw_set_ethtool_priv_flags, + .supported_coalesce_params = ETHTOOL_COALESCE_USECS, + .get_coalesce = am65_cpsw_get_coalesce, + .set_coalesce = am65_cpsw_set_coalesce, + .get_per_queue_coalesce = am65_cpsw_get_per_queue_coalesce, + .set_per_queue_coalesce = am65_cpsw_set_per_queue_coalesce, .get_link = ethtool_op_get_link, .get_link_ksettings = am65_cpsw_get_link_ksettings, @@ -769,4 +1012,7 @@ const struct ethtool_ops am65_cpsw_ethtool_ops_slave = { .get_eee = am65_cpsw_get_eee, .set_eee = am65_cpsw_set_eee, .nway_reset = am65_cpsw_nway_reset, + .get_mm = am65_cpsw_get_mm, + .set_mm = am65_cpsw_set_mm, + .get_mm_stats = am65_cpsw_get_mm_stats, }; diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 7651f90f51f2..faa0561e988e 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -596,8 +596,10 @@ static int am65_cpsw_nuss_common_stop(struct am65_cpsw_common *common) msecs_to_jiffies(1000)); if (!i) dev_err(common->dev, "tx timeout\n"); - for (i = 0; i < common->tx_ch_num; i++) + for (i = 0; i < common->tx_ch_num; i++) { napi_disable(&common->tx_chns[i].napi_tx); + hrtimer_cancel(&common->tx_chns[i].tx_hrtimer); + } for (i = 0; i < common->tx_ch_num; i++) { k3_udma_glue_reset_tx_chn(common->tx_chns[i].tx_chn, @@ -616,6 +618,7 @@ static int am65_cpsw_nuss_common_stop(struct am65_cpsw_common *common) } napi_disable(&common->napi_rx); + hrtimer_cancel(&common->rx_hrtimer); for (i = 0; i < AM65_CPSW_MAX_RX_FLOWS; i++) k3_udma_glue_reset_rx_chn(common->rx_chns.rx_chn, i, @@ -885,6 +888,15 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common, return ret; } +static enum hrtimer_restart am65_cpsw_nuss_rx_timer_callback(struct hrtimer *timer) +{ + struct am65_cpsw_common *common = + container_of(timer, struct am65_cpsw_common, rx_hrtimer); + + enable_irq(common->rx_chns.irq); + return HRTIMER_NORESTART; +} + static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget) { struct am65_cpsw_common *common = am65_cpsw_napi_to_common(napi_rx); @@ -912,7 +924,13 @@ static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget) if (num_rx < budget && napi_complete_done(napi_rx, num_rx)) { if (common->rx_irq_disabled) { common->rx_irq_disabled = false; - enable_irq(common->rx_chns.irq); + if (unlikely(common->rx_pace_timeout)) { + hrtimer_start(&common->rx_hrtimer, + ns_to_ktime(common->rx_pace_timeout), + HRTIMER_MODE_REL_PINNED); + } else { + enable_irq(common->rx_chns.irq); + } } } @@ -968,7 +986,7 @@ static void am65_cpsw_nuss_tx_wake(struct am65_cpsw_tx_chn *tx_chn, struct net_d } static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common, - int chn, unsigned int budget) + int chn, unsigned int budget, bool *tdown) { struct device *dev = common->dev; struct am65_cpsw_tx_chn *tx_chn; @@ -991,6 +1009,7 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common, if (cppi5_desc_is_tdcm(desc_dma)) { if (atomic_dec_and_test(&common->tdown_cnt)) complete(&common->tdown_complete); + *tdown = true; break; } @@ -1013,7 +1032,7 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common, } static int am65_cpsw_nuss_tx_compl_packets_2g(struct am65_cpsw_common *common, - int chn, unsigned int budget) + int chn, unsigned int budget, bool *tdown) { struct device *dev = common->dev; struct am65_cpsw_tx_chn *tx_chn; @@ -1034,6 +1053,7 @@ static int am65_cpsw_nuss_tx_compl_packets_2g(struct am65_cpsw_common *common, if (cppi5_desc_is_tdcm(desc_dma)) { if (atomic_dec_and_test(&common->tdown_cnt)) complete(&common->tdown_complete); + *tdown = true; break; } @@ -1059,21 +1079,40 @@ static int am65_cpsw_nuss_tx_compl_packets_2g(struct am65_cpsw_common *common, return num_tx; } +static enum hrtimer_restart am65_cpsw_nuss_tx_timer_callback(struct hrtimer *timer) +{ + struct am65_cpsw_tx_chn *tx_chns = + container_of(timer, struct am65_cpsw_tx_chn, tx_hrtimer); + + enable_irq(tx_chns->irq); + return HRTIMER_NORESTART; +} + static int am65_cpsw_nuss_tx_poll(struct napi_struct *napi_tx, int budget) { struct am65_cpsw_tx_chn *tx_chn = am65_cpsw_napi_to_tx_chn(napi_tx); + bool tdown = false; int num_tx; if (AM65_CPSW_IS_CPSW2G(tx_chn->common)) - num_tx = am65_cpsw_nuss_tx_compl_packets_2g(tx_chn->common, tx_chn->id, budget); + num_tx = am65_cpsw_nuss_tx_compl_packets_2g(tx_chn->common, tx_chn->id, + budget, &tdown); else - num_tx = am65_cpsw_nuss_tx_compl_packets(tx_chn->common, tx_chn->id, budget); + num_tx = am65_cpsw_nuss_tx_compl_packets(tx_chn->common, + tx_chn->id, budget, &tdown); if (num_tx >= budget) return budget; - if (napi_complete_done(napi_tx, num_tx)) - enable_irq(tx_chn->irq); + if (napi_complete_done(napi_tx, num_tx)) { + if (unlikely(tx_chn->tx_pace_timeout && !tdown)) { + hrtimer_start(&tx_chn->tx_hrtimer, + ns_to_ktime(tx_chn->tx_pace_timeout), + HRTIMER_MODE_REL_PINNED); + } else { + enable_irq(tx_chn->irq); + } + } return 0; } @@ -1705,6 +1744,8 @@ static int am65_cpsw_nuss_ndev_add_tx_napi(struct am65_cpsw_common *common) netif_napi_add_tx(common->dma_ndev, &tx_chn->napi_tx, am65_cpsw_nuss_tx_poll); + hrtimer_init(&tx_chn->tx_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); + tx_chn->tx_hrtimer.function = &am65_cpsw_nuss_tx_timer_callback; ret = devm_request_irq(dev, tx_chn->irq, am65_cpsw_nuss_tx_irq, @@ -1930,6 +1971,8 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common) netif_napi_add(common->dma_ndev, &common->napi_rx, am65_cpsw_nuss_rx_poll); + hrtimer_init(&common->rx_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); + common->rx_hrtimer.function = &am65_cpsw_nuss_rx_timer_callback; ret = devm_request_irq(dev, rx_chn->irq, am65_cpsw_nuss_rx_irq, @@ -2127,6 +2170,9 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) dev_err(dev, "Use random MAC address\n"); } } + + /* Reset all Queue priorities to 0 */ + writel(0, port->port_base + AM65_CPSW_PN_REG_TX_PRI_MAP); } of_node_put(node); @@ -2191,6 +2237,8 @@ am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx) ndev_priv = netdev_priv(port->ndev); ndev_priv->port = port; ndev_priv->msg_enable = AM65_CPSW_DEBUG; + mutex_init(&ndev_priv->mm_lock); + port->qos.link_speed = SPEED_UNKNOWN; SET_NETDEV_DEV(port->ndev, dev); eth_hw_addr_set(port->ndev, port->slave.mac_addr); diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.h b/drivers/net/ethernet/ti/am65-cpsw-nuss.h index f3dad2ab9828..7da0492dc091 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.h +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.h @@ -75,6 +75,8 @@ struct am65_cpsw_tx_chn { struct k3_cppi_desc_pool *desc_pool; struct k3_udma_glue_tx_channel *tx_chn; spinlock_t lock; /* protect TX rings in multi-port mode */ + struct hrtimer tx_hrtimer; + unsigned long tx_pace_timeout; int irq; u32 id; u32 descs_num; @@ -138,6 +140,8 @@ struct am65_cpsw_common { struct napi_struct napi_rx; bool rx_irq_disabled; + struct hrtimer rx_hrtimer; + unsigned long rx_pace_timeout; u32 nuss_ver; u32 cpsw_ver; @@ -145,6 +149,7 @@ struct am65_cpsw_common { bool pf_p0_rx_ptype_rrobin; struct am65_cpts *cpts; int est_enabled; + bool iet_enabled; bool is_emac_mode; u16 br_members; @@ -170,6 +175,10 @@ struct am65_cpsw_ndev_priv { struct am65_cpsw_port *port; struct am65_cpsw_ndev_stats __percpu *stats; bool offload_fwd_mark; + /* Serialize access to MAC Merge state between ethtool requests + * and link state updates + */ + struct mutex mm_lock; }; #define am65_ndev_to_priv(ndev) \ diff --git a/drivers/net/ethernet/ti/am65-cpsw-qos.c b/drivers/net/ethernet/ti/am65-cpsw-qos.c index 9ac2ff05d501..816e73a3d6e4 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-qos.c +++ b/drivers/net/ethernet/ti/am65-cpsw-qos.c @@ -4,10 +4,13 @@ * * quality of service module includes: * Enhanced Scheduler Traffic (EST - P802.1Qbv/D2.2) + * Interspersed Express Traffic (IET - P802.3br/D2.0) */ #include <linux/pm_runtime.h> +#include <linux/math.h> #include <linux/time.h> +#include <linux/units.h> #include <net/pkt_cls.h> #include "am65-cpsw-nuss.h" @@ -15,40 +18,7 @@ #include "am65-cpts.h" #include "cpsw_ale.h" -#define AM65_CPSW_REG_CTL 0x004 -#define AM65_CPSW_PN_REG_CTL 0x004 -#define AM65_CPSW_PN_REG_FIFO_STATUS 0x050 -#define AM65_CPSW_PN_REG_EST_CTL 0x060 -#define AM65_CPSW_PN_REG_PRI_CIR(pri) (0x140 + 4 * (pri)) - -/* AM65_CPSW_REG_CTL register fields */ -#define AM65_CPSW_CTL_EST_EN BIT(18) - -/* AM65_CPSW_PN_REG_CTL register fields */ -#define AM65_CPSW_PN_CTL_EST_PORT_EN BIT(17) - -/* AM65_CPSW_PN_REG_EST_CTL register fields */ -#define AM65_CPSW_PN_EST_ONEBUF BIT(0) -#define AM65_CPSW_PN_EST_BUFSEL BIT(1) -#define AM65_CPSW_PN_EST_TS_EN BIT(2) -#define AM65_CPSW_PN_EST_TS_FIRST BIT(3) -#define AM65_CPSW_PN_EST_ONEPRI BIT(4) -#define AM65_CPSW_PN_EST_TS_PRI_MSK GENMASK(7, 5) - -/* AM65_CPSW_PN_REG_FIFO_STATUS register fields */ -#define AM65_CPSW_PN_FST_TX_PRI_ACTIVE_MSK GENMASK(7, 0) -#define AM65_CPSW_PN_FST_TX_E_MAC_ALLOW_MSK GENMASK(15, 8) -#define AM65_CPSW_PN_FST_EST_CNT_ERR BIT(16) -#define AM65_CPSW_PN_FST_EST_ADD_ERR BIT(17) -#define AM65_CPSW_PN_FST_EST_BUFACT BIT(18) - -/* EST FETCH COMMAND RAM */ -#define AM65_CPSW_FETCH_RAM_CMD_NUM 0x80 -#define AM65_CPSW_FETCH_CNT_MSK GENMASK(21, 8) -#define AM65_CPSW_FETCH_CNT_MAX (AM65_CPSW_FETCH_CNT_MSK >> 8) -#define AM65_CPSW_FETCH_CNT_OFFSET 8 -#define AM65_CPSW_FETCH_ALLOW_MSK GENMASK(7, 0) -#define AM65_CPSW_FETCH_ALLOW_MAX AM65_CPSW_FETCH_ALLOW_MSK +#define TO_MBPS(x) DIV_ROUND_UP((x), BYTES_PER_MBIT) enum timer_act { TACT_PROG, /* need program timer */ @@ -56,6 +26,412 @@ enum timer_act { TACT_SKIP_PROG, /* just buffer can be updated */ }; +static void am65_cpsw_iet_change_preemptible_tcs(struct am65_cpsw_port *port, u8 preemptible_tcs); + +static u32 +am65_cpsw_qos_tx_rate_calc(u32 rate_mbps, unsigned long bus_freq) +{ + u32 ir; + + bus_freq /= 1000000; + ir = DIV_ROUND_UP(((u64)rate_mbps * 32768), bus_freq); + return ir; +} + +static void am65_cpsw_tx_pn_shaper_reset(struct am65_cpsw_port *port) +{ + int prio; + + for (prio = 0; prio < AM65_CPSW_PN_FIFO_PRIO_NUM; prio++) { + writel(0, port->port_base + AM65_CPSW_PN_REG_PRI_CIR(prio)); + writel(0, port->port_base + AM65_CPSW_PN_REG_PRI_EIR(prio)); + } +} + +static void am65_cpsw_tx_pn_shaper_apply(struct am65_cpsw_port *port) +{ + struct am65_cpsw_mqprio *p_mqprio = &port->qos.mqprio; + struct am65_cpsw_common *common = port->common; + struct tc_mqprio_qopt_offload *mqprio; + bool enable, shaper_susp = false; + u32 rate_mbps; + int tc, prio; + + mqprio = &p_mqprio->mqprio_hw; + /* takes care of no link case as well */ + if (p_mqprio->max_rate_total > port->qos.link_speed) + shaper_susp = true; + + am65_cpsw_tx_pn_shaper_reset(port); + + enable = p_mqprio->shaper_en && !shaper_susp; + if (!enable) + return; + + /* Rate limit is specified per Traffic Class but + * for CPSW, rate limit can be applied per priority + * at port FIFO. + * + * We have assigned the same priority (TCn) to all queues + * of a Traffic Class so they share the same shaper + * bandwidth. + */ + for (tc = 0; tc < mqprio->qopt.num_tc; tc++) { + prio = tc; + + rate_mbps = TO_MBPS(mqprio->min_rate[tc]); + rate_mbps = am65_cpsw_qos_tx_rate_calc(rate_mbps, + common->bus_freq); + writel(rate_mbps, + port->port_base + AM65_CPSW_PN_REG_PRI_CIR(prio)); + + rate_mbps = 0; + + if (mqprio->max_rate[tc]) { + rate_mbps = mqprio->max_rate[tc] - mqprio->min_rate[tc]; + rate_mbps = TO_MBPS(rate_mbps); + rate_mbps = am65_cpsw_qos_tx_rate_calc(rate_mbps, + common->bus_freq); + } + + writel(rate_mbps, + port->port_base + AM65_CPSW_PN_REG_PRI_EIR(prio)); + } +} + +static int am65_cpsw_mqprio_verify_shaper(struct am65_cpsw_port *port, + struct tc_mqprio_qopt_offload *mqprio) +{ + struct am65_cpsw_mqprio *p_mqprio = &port->qos.mqprio; + struct netlink_ext_ack *extack = mqprio->extack; + u64 min_rate_total = 0, max_rate_total = 0; + u32 min_rate_msk = 0, max_rate_msk = 0; + bool has_min_rate, has_max_rate; + int num_tc, i; + + if (!(mqprio->flags & TC_MQPRIO_F_SHAPER)) + return 0; + + if (mqprio->shaper != TC_MQPRIO_SHAPER_BW_RATE) + return 0; + + has_min_rate = !!(mqprio->flags & TC_MQPRIO_F_MIN_RATE); + has_max_rate = !!(mqprio->flags & TC_MQPRIO_F_MAX_RATE); + + if (!has_min_rate && has_max_rate) { + NL_SET_ERR_MSG_MOD(extack, "min_rate is required with max_rate"); + return -EOPNOTSUPP; + } + + if (!has_min_rate) + return 0; + + num_tc = mqprio->qopt.num_tc; + + for (i = num_tc - 1; i >= 0; i--) { + u32 ch_msk; + + if (mqprio->min_rate[i]) + min_rate_msk |= BIT(i); + min_rate_total += mqprio->min_rate[i]; + + if (has_max_rate) { + if (mqprio->max_rate[i]) + max_rate_msk |= BIT(i); + max_rate_total += mqprio->max_rate[i]; + + if (!mqprio->min_rate[i] && mqprio->max_rate[i]) { + NL_SET_ERR_MSG_FMT_MOD(extack, + "TX tc%d rate max>0 but min=0", + i); + return -EINVAL; + } + + if (mqprio->max_rate[i] && + mqprio->max_rate[i] < mqprio->min_rate[i]) { + NL_SET_ERR_MSG_FMT_MOD(extack, + "TX tc%d rate min(%llu)>max(%llu)", + i, mqprio->min_rate[i], + mqprio->max_rate[i]); + return -EINVAL; + } + } + + ch_msk = GENMASK(num_tc - 1, i); + if ((min_rate_msk & BIT(i)) && (min_rate_msk ^ ch_msk)) { + NL_SET_ERR_MSG_FMT_MOD(extack, + "Min rate must be set sequentially hi->lo tx_rate_msk%x", + min_rate_msk); + return -EINVAL; + } + + if ((max_rate_msk & BIT(i)) && (max_rate_msk ^ ch_msk)) { + NL_SET_ERR_MSG_FMT_MOD(extack, + "Max rate must be set sequentially hi->lo tx_rate_msk%x", + max_rate_msk); + return -EINVAL; + } + } + + min_rate_total = TO_MBPS(min_rate_total); + max_rate_total = TO_MBPS(max_rate_total); + + p_mqprio->shaper_en = true; + p_mqprio->max_rate_total = max_t(u64, min_rate_total, max_rate_total); + + return 0; +} + +static void am65_cpsw_reset_tc_mqprio(struct net_device *ndev) +{ + struct am65_cpsw_port *port = am65_ndev_to_port(ndev); + struct am65_cpsw_mqprio *p_mqprio = &port->qos.mqprio; + + p_mqprio->shaper_en = false; + p_mqprio->max_rate_total = 0; + + am65_cpsw_tx_pn_shaper_reset(port); + netdev_reset_tc(ndev); + + /* Reset all Queue priorities to 0 */ + writel(0, port->port_base + AM65_CPSW_PN_REG_TX_PRI_MAP); + + am65_cpsw_iet_change_preemptible_tcs(port, 0); +} + +static int am65_cpsw_setup_mqprio(struct net_device *ndev, void *type_data) +{ + struct am65_cpsw_port *port = am65_ndev_to_port(ndev); + struct am65_cpsw_mqprio *p_mqprio = &port->qos.mqprio; + struct tc_mqprio_qopt_offload *mqprio = type_data; + struct am65_cpsw_common *common = port->common; + struct tc_mqprio_qopt *qopt = &mqprio->qopt; + int i, tc, offset, count, prio, ret; + u8 num_tc = qopt->num_tc; + u32 tx_prio_map = 0; + + memcpy(&p_mqprio->mqprio_hw, mqprio, sizeof(*mqprio)); + + ret = pm_runtime_get_sync(common->dev); + if (ret < 0) { + pm_runtime_put_noidle(common->dev); + return ret; + } + + if (!num_tc) { + am65_cpsw_reset_tc_mqprio(ndev); + ret = 0; + goto exit_put; + } + + ret = am65_cpsw_mqprio_verify_shaper(port, mqprio); + if (ret) + goto exit_put; + + netdev_set_num_tc(ndev, num_tc); + + /* Multiple Linux priorities can map to a Traffic Class + * A Traffic Class can have multiple contiguous Queues, + * Queues get mapped to Channels (thread_id), + * if not VLAN tagged, thread_id is used as packet_priority + * if VLAN tagged. VLAN priority is used as packet_priority + * packet_priority gets mapped to header_priority in p0_rx_pri_map, + * header_priority gets mapped to switch_priority in pn_tx_pri_map. + * As p0_rx_pri_map is left at defaults (0x76543210), we can + * assume that Queue_n gets mapped to header_priority_n. We can then + * set the switch priority in pn_tx_pri_map. + */ + + for (tc = 0; tc < num_tc; tc++) { + prio = tc; + + /* For simplicity we assign the same priority (TCn) to + * all queues of a Traffic Class. + */ + for (i = qopt->offset[tc]; i < qopt->offset[tc] + qopt->count[tc]; i++) + tx_prio_map |= prio << (4 * i); + + count = qopt->count[tc]; + offset = qopt->offset[tc]; + netdev_set_tc_queue(ndev, tc, count, offset); + } + + writel(tx_prio_map, port->port_base + AM65_CPSW_PN_REG_TX_PRI_MAP); + + am65_cpsw_tx_pn_shaper_apply(port); + am65_cpsw_iet_change_preemptible_tcs(port, mqprio->preemptible_tcs); + +exit_put: + pm_runtime_put(common->dev); + + return ret; +} + +static int am65_cpsw_iet_set_verify_timeout_count(struct am65_cpsw_port *port) +{ + int verify_time_ms = port->qos.iet.verify_time_ms; + u32 val; + + /* The number of wireside clocks contained in the verify + * timeout counter. The default is 0x1312d0 + * (10ms at 125Mhz in 1G mode). + */ + val = 125 * HZ_PER_MHZ; /* assuming 125MHz wireside clock */ + + val /= MILLIHZ_PER_HZ; /* count per ms timeout */ + val *= verify_time_ms; /* count for timeout ms */ + + if (val > AM65_CPSW_PN_MAC_VERIFY_CNT_MASK) + return -EINVAL; + + writel(val, port->port_base + AM65_CPSW_PN_REG_IET_VERIFY); + + return 0; +} + +static int am65_cpsw_iet_verify_wait(struct am65_cpsw_port *port) +{ + u32 ctrl, status; + int try; + + try = 20; + do { + /* Reset the verify state machine by writing 1 + * to LINKFAIL + */ + ctrl = readl(port->port_base + AM65_CPSW_PN_REG_IET_CTRL); + ctrl |= AM65_CPSW_PN_IET_MAC_LINKFAIL; + writel(ctrl, port->port_base + AM65_CPSW_PN_REG_IET_CTRL); + + /* Clear MAC_LINKFAIL bit to start Verify. */ + ctrl = readl(port->port_base + AM65_CPSW_PN_REG_IET_CTRL); + ctrl &= ~AM65_CPSW_PN_IET_MAC_LINKFAIL; + writel(ctrl, port->port_base + AM65_CPSW_PN_REG_IET_CTRL); + + msleep(port->qos.iet.verify_time_ms); + + status = readl(port->port_base + AM65_CPSW_PN_REG_IET_STATUS); + if (status & AM65_CPSW_PN_MAC_VERIFIED) + return 0; + + if (status & AM65_CPSW_PN_MAC_VERIFY_FAIL) { + netdev_dbg(port->ndev, + "MAC Merge verify failed, trying again\n"); + continue; + } + + if (status & AM65_CPSW_PN_MAC_RESPOND_ERR) { + netdev_dbg(port->ndev, "MAC Merge respond error\n"); + return -ENODEV; + } + + if (status & AM65_CPSW_PN_MAC_VERIFY_ERR) { + netdev_dbg(port->ndev, "MAC Merge verify error\n"); + return -ENODEV; + } + } while (try-- > 0); + + netdev_dbg(port->ndev, "MAC Merge verify timeout\n"); + return -ETIMEDOUT; +} + +static void am65_cpsw_iet_set_preempt_mask(struct am65_cpsw_port *port, u8 preemptible_tcs) +{ + u32 val; + + val = readl(port->port_base + AM65_CPSW_PN_REG_IET_CTRL); + val &= ~AM65_CPSW_PN_IET_MAC_PREMPT_MASK; + val |= AM65_CPSW_PN_IET_MAC_SET_PREEMPT(preemptible_tcs); + writel(val, port->port_base + AM65_CPSW_PN_REG_IET_CTRL); +} + +/* enable common IET_ENABLE only if at least 1 port has rx IET enabled. + * UAPI doesn't allow tx enable without rx enable. + */ +void am65_cpsw_iet_common_enable(struct am65_cpsw_common *common) +{ + struct am65_cpsw_port *port; + bool rx_enable = false; + u32 val; + int i; + + for (i = 0; i < common->port_num; i++) { + port = &common->ports[i]; + val = readl(port->port_base + AM65_CPSW_PN_REG_CTL); + rx_enable = !!(val & AM65_CPSW_PN_CTL_IET_PORT_EN); + if (rx_enable) + break; + } + + val = readl(common->cpsw_base + AM65_CPSW_REG_CTL); + + if (rx_enable) + val |= AM65_CPSW_CTL_IET_EN; + else + val &= ~AM65_CPSW_CTL_IET_EN; + + writel(val, common->cpsw_base + AM65_CPSW_REG_CTL); + common->iet_enabled = rx_enable; +} + +/* CPSW does not have an IRQ to notify changes to the MAC Merge TX status + * (active/inactive), but the preemptible traffic classes should only be + * committed to hardware once TX is active. Resort to polling. + */ +void am65_cpsw_iet_commit_preemptible_tcs(struct am65_cpsw_port *port) +{ + u8 preemptible_tcs; + int err; + u32 val; + + if (port->qos.link_speed == SPEED_UNKNOWN) + return; + + val = readl(port->port_base + AM65_CPSW_PN_REG_CTL); + if (!(val & AM65_CPSW_PN_CTL_IET_PORT_EN)) + return; + + /* update common IET enable */ + am65_cpsw_iet_common_enable(port->common); + + /* update verify count */ + err = am65_cpsw_iet_set_verify_timeout_count(port); + if (err) { + netdev_err(port->ndev, "couldn't set verify count: %d\n", err); + return; + } + + val = readl(port->port_base + AM65_CPSW_PN_REG_IET_CTRL); + if (!(val & AM65_CPSW_PN_IET_MAC_DISABLEVERIFY)) { + err = am65_cpsw_iet_verify_wait(port); + if (err) + return; + } + + preemptible_tcs = port->qos.iet.preemptible_tcs; + am65_cpsw_iet_set_preempt_mask(port, preemptible_tcs); +} + +static void am65_cpsw_iet_change_preemptible_tcs(struct am65_cpsw_port *port, u8 preemptible_tcs) +{ + struct am65_cpsw_ndev_priv *priv = am65_ndev_to_priv(port->ndev); + + port->qos.iet.preemptible_tcs = preemptible_tcs; + mutex_lock(&priv->mm_lock); + am65_cpsw_iet_commit_preemptible_tcs(port); + mutex_unlock(&priv->mm_lock); +} + +static void am65_cpsw_iet_link_state_update(struct net_device *ndev) +{ + struct am65_cpsw_ndev_priv *priv = am65_ndev_to_priv(ndev); + struct am65_cpsw_port *port = am65_ndev_to_port(ndev); + + mutex_lock(&priv->mm_lock); + am65_cpsw_iet_commit_preemptible_tcs(port); + mutex_unlock(&priv->mm_lock); +} + static int am65_cpsw_port_est_enabled(struct am65_cpsw_port *port) { return port->qos.est_oper || port->qos.est_admin; @@ -428,7 +804,7 @@ static void am65_cpsw_stop_est(struct net_device *ndev) am65_cpsw_timer_stop(ndev); } -static void am65_cpsw_purge_est(struct net_device *ndev) +static void am65_cpsw_taprio_destroy(struct net_device *ndev) { struct am65_cpsw_port *port = am65_ndev_to_port(ndev); @@ -439,31 +815,74 @@ static void am65_cpsw_purge_est(struct net_device *ndev) port->qos.est_oper = NULL; port->qos.est_admin = NULL; + + am65_cpsw_reset_tc_mqprio(ndev); } -static int am65_cpsw_configure_taprio(struct net_device *ndev, - struct am65_cpsw_est *est_new) +static void am65_cpsw_cp_taprio(struct tc_taprio_qopt_offload *from, + struct tc_taprio_qopt_offload *to) +{ + int i; + + *to = *from; + for (i = 0; i < from->num_entries; i++) + to->entries[i] = from->entries[i]; +} + +static int am65_cpsw_taprio_replace(struct net_device *ndev, + struct tc_taprio_qopt_offload *taprio) { struct am65_cpsw_common *common = am65_ndev_to_common(ndev); + struct netlink_ext_ack *extack = taprio->mqprio.extack; + struct am65_cpsw_port *port = am65_ndev_to_port(ndev); struct am65_cpts *cpts = common->cpts; - int ret = 0, tact = TACT_PROG; + struct am65_cpsw_est *est_new; + int ret, tact; - am65_cpsw_est_update_state(ndev); + if (!netif_running(ndev)) { + NL_SET_ERR_MSG_MOD(extack, "interface is down, link speed unknown"); + return -ENETDOWN; + } - if (est_new->taprio.cmd == TAPRIO_CMD_DESTROY) { - am65_cpsw_stop_est(ndev); - return ret; + if (common->pf_p0_rx_ptype_rrobin) { + NL_SET_ERR_MSG_MOD(extack, + "p0-rx-ptype-rrobin flag conflicts with taprio qdisc"); + return -EINVAL; } + if (port->qos.link_speed == SPEED_UNKNOWN) + return -ENOLINK; + + if (taprio->cycle_time_extension) { + NL_SET_ERR_MSG_MOD(extack, + "cycle time extension not supported"); + return -EOPNOTSUPP; + } + + est_new = devm_kzalloc(&ndev->dev, + struct_size(est_new, taprio.entries, taprio->num_entries), + GFP_KERNEL); + if (!est_new) + return -ENOMEM; + + ret = am65_cpsw_setup_mqprio(ndev, &taprio->mqprio); + if (ret) + return ret; + + am65_cpsw_cp_taprio(taprio, &est_new->taprio); + + am65_cpsw_est_update_state(ndev); + ret = am65_cpsw_est_check_scheds(ndev, est_new); if (ret < 0) - return ret; + goto fail; tact = am65_cpsw_timer_act(ndev, est_new); if (tact == TACT_NEED_STOP) { - dev_err(&ndev->dev, - "Can't toggle estf timer, stop taprio first"); - return -EINVAL; + NL_SET_ERR_MSG_MOD(extack, + "Can't toggle estf timer, stop taprio first"); + ret = -EINVAL; + goto fail; } if (tact == TACT_PROG) @@ -476,62 +895,26 @@ static int am65_cpsw_configure_taprio(struct net_device *ndev, am65_cpsw_est_set_sched_list(ndev, est_new); am65_cpsw_port_est_assign_buf_num(ndev, est_new->buf); - am65_cpsw_est_set(ndev, est_new->taprio.cmd == TAPRIO_CMD_REPLACE); + am65_cpsw_est_set(ndev, 1); if (tact == TACT_PROG) { ret = am65_cpsw_timer_set(ndev, est_new); if (ret) { - dev_err(&ndev->dev, "Failed to set cycle time"); - return ret; + NL_SET_ERR_MSG_MOD(extack, + "Failed to set cycle time"); + goto fail; } } - return ret; -} - -static void am65_cpsw_cp_taprio(struct tc_taprio_qopt_offload *from, - struct tc_taprio_qopt_offload *to) -{ - int i; - - *to = *from; - for (i = 0; i < from->num_entries; i++) - to->entries[i] = from->entries[i]; -} - -static int am65_cpsw_set_taprio(struct net_device *ndev, void *type_data) -{ - struct am65_cpsw_port *port = am65_ndev_to_port(ndev); - struct tc_taprio_qopt_offload *taprio = type_data; - struct am65_cpsw_est *est_new; - int ret = 0; - - if (taprio->cycle_time_extension) { - dev_err(&ndev->dev, "Failed to set cycle time extension"); - return -EOPNOTSUPP; - } - - est_new = devm_kzalloc(&ndev->dev, - struct_size(est_new, taprio.entries, taprio->num_entries), - GFP_KERNEL); - if (!est_new) - return -ENOMEM; - - am65_cpsw_cp_taprio(taprio, &est_new->taprio); - ret = am65_cpsw_configure_taprio(ndev, est_new); - if (!ret) { - if (taprio->cmd == TAPRIO_CMD_REPLACE) { - devm_kfree(&ndev->dev, port->qos.est_admin); + devm_kfree(&ndev->dev, port->qos.est_admin); + port->qos.est_admin = est_new; + am65_cpsw_iet_change_preemptible_tcs(port, taprio->mqprio.preemptible_tcs); - port->qos.est_admin = est_new; - } else { - devm_kfree(&ndev->dev, est_new); - am65_cpsw_purge_est(ndev); - } - } else { - devm_kfree(&ndev->dev, est_new); - } + return 0; +fail: + am65_cpsw_reset_tc_mqprio(ndev); + devm_kfree(&ndev->dev, est_new); return ret; } @@ -541,7 +924,6 @@ static void am65_cpsw_est_link_up(struct net_device *ndev, int link_speed) ktime_t cur_time; s64 delta; - port->qos.link_speed = link_speed; if (!am65_cpsw_port_est_enabled(port)) return; @@ -558,37 +940,26 @@ static void am65_cpsw_est_link_up(struct net_device *ndev, int link_speed) return; purge_est: - am65_cpsw_purge_est(ndev); + am65_cpsw_taprio_destroy(ndev); } static int am65_cpsw_setup_taprio(struct net_device *ndev, void *type_data) { - struct am65_cpsw_port *port = am65_ndev_to_port(ndev); struct tc_taprio_qopt_offload *taprio = type_data; - struct am65_cpsw_common *common = port->common; - - if (taprio->cmd != TAPRIO_CMD_REPLACE && - taprio->cmd != TAPRIO_CMD_DESTROY) - return -EOPNOTSUPP; - - if (!IS_ENABLED(CONFIG_TI_AM65_CPSW_TAS)) - return -ENODEV; - - if (!netif_running(ndev)) { - dev_err(&ndev->dev, "interface is down, link speed unknown\n"); - return -ENETDOWN; - } - - if (common->pf_p0_rx_ptype_rrobin) { - dev_err(&ndev->dev, - "p0-rx-ptype-rrobin flag conflicts with taprio qdisc\n"); - return -EINVAL; + int err = 0; + + switch (taprio->cmd) { + case TAPRIO_CMD_REPLACE: + err = am65_cpsw_taprio_replace(ndev, taprio); + break; + case TAPRIO_CMD_DESTROY: + am65_cpsw_taprio_destroy(ndev); + break; + default: + err = -EOPNOTSUPP; } - if (port->qos.link_speed == SPEED_UNKNOWN) - return -ENOLINK; - - return am65_cpsw_set_taprio(ndev, type_data); + return err; } static int am65_cpsw_tc_query_caps(struct net_device *ndev, void *type_data) @@ -596,12 +967,17 @@ static int am65_cpsw_tc_query_caps(struct net_device *ndev, void *type_data) struct tc_query_caps_base *base = type_data; switch (base->type) { + case TC_SETUP_QDISC_MQPRIO: { + struct tc_mqprio_caps *caps = base->caps; + + caps->validate_queue_counts = true; + + return 0; + } + case TC_SETUP_QDISC_TAPRIO: { struct tc_taprio_caps *caps = base->caps; - if (!IS_ENABLED(CONFIG_TI_AM65_CPSW_TAS)) - return -EOPNOTSUPP; - caps->gate_mask_per_txq = true; return 0; @@ -787,55 +1163,6 @@ static int am65_cpsw_qos_setup_tc_block(struct net_device *ndev, struct flow_blo port, port, true); } -int am65_cpsw_qos_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type, - void *type_data) -{ - switch (type) { - case TC_QUERY_CAPS: - return am65_cpsw_tc_query_caps(ndev, type_data); - case TC_SETUP_QDISC_TAPRIO: - return am65_cpsw_setup_taprio(ndev, type_data); - case TC_SETUP_BLOCK: - return am65_cpsw_qos_setup_tc_block(ndev, type_data); - default: - return -EOPNOTSUPP; - } -} - -void am65_cpsw_qos_link_up(struct net_device *ndev, int link_speed) -{ - struct am65_cpsw_port *port = am65_ndev_to_port(ndev); - - if (!IS_ENABLED(CONFIG_TI_AM65_CPSW_TAS)) - return; - - am65_cpsw_est_link_up(ndev, link_speed); - port->qos.link_down_time = 0; -} - -void am65_cpsw_qos_link_down(struct net_device *ndev) -{ - struct am65_cpsw_port *port = am65_ndev_to_port(ndev); - - if (!IS_ENABLED(CONFIG_TI_AM65_CPSW_TAS)) - return; - - if (!port->qos.link_down_time) - port->qos.link_down_time = ktime_get(); - - port->qos.link_speed = SPEED_UNKNOWN; -} - -static u32 -am65_cpsw_qos_tx_rate_calc(u32 rate_mbps, unsigned long bus_freq) -{ - u32 ir; - - bus_freq /= 1000000; - ir = DIV_ROUND_UP(((u64)rate_mbps * 32768), bus_freq); - return ir; -} - static void am65_cpsw_qos_tx_p0_rate_apply(struct am65_cpsw_common *common, int tx_ch, u32 rate_mbps) @@ -937,3 +1264,44 @@ void am65_cpsw_qos_tx_p0_rate_init(struct am65_cpsw_common *common) host->port_base + AM65_CPSW_PN_REG_PRI_CIR(tx_ch)); } } + +int am65_cpsw_qos_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type, + void *type_data) +{ + switch (type) { + case TC_QUERY_CAPS: + return am65_cpsw_tc_query_caps(ndev, type_data); + case TC_SETUP_QDISC_TAPRIO: + return am65_cpsw_setup_taprio(ndev, type_data); + case TC_SETUP_QDISC_MQPRIO: + return am65_cpsw_setup_mqprio(ndev, type_data); + case TC_SETUP_BLOCK: + return am65_cpsw_qos_setup_tc_block(ndev, type_data); + default: + return -EOPNOTSUPP; + } +} + +void am65_cpsw_qos_link_up(struct net_device *ndev, int link_speed) +{ + struct am65_cpsw_port *port = am65_ndev_to_port(ndev); + + port->qos.link_speed = link_speed; + am65_cpsw_tx_pn_shaper_apply(port); + am65_cpsw_iet_link_state_update(ndev); + + am65_cpsw_est_link_up(ndev, link_speed); + port->qos.link_down_time = 0; +} + +void am65_cpsw_qos_link_down(struct net_device *ndev) +{ + struct am65_cpsw_port *port = am65_ndev_to_port(ndev); + + port->qos.link_speed = SPEED_UNKNOWN; + am65_cpsw_tx_pn_shaper_apply(port); + am65_cpsw_iet_link_state_update(ndev); + + if (!port->qos.link_down_time) + port->qos.link_down_time = ktime_get(); +} diff --git a/drivers/net/ethernet/ti/am65-cpsw-qos.h b/drivers/net/ethernet/ti/am65-cpsw-qos.h index 0cc2a3b3d7f9..b328e56c5b2b 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-qos.h +++ b/drivers/net/ethernet/ti/am65-cpsw-qos.h @@ -9,6 +9,7 @@ #include <net/pkt_sched.h> struct am65_cpsw_common; +struct am65_cpsw_port; struct am65_cpsw_est { int buf; @@ -16,6 +17,18 @@ struct am65_cpsw_est { struct tc_taprio_qopt_offload taprio; }; +struct am65_cpsw_mqprio { + struct tc_mqprio_qopt_offload mqprio_hw; + u64 max_rate_total; + bool shaper_en; +}; + +struct am65_cpsw_iet { + u8 preemptible_tcs; + u32 original_max_blks; + int verify_time_ms; +}; + struct am65_cpsw_ale_ratelimit { unsigned long cookie; u64 rate_packet_ps; @@ -26,16 +39,189 @@ struct am65_cpsw_qos { struct am65_cpsw_est *est_oper; ktime_t link_down_time; int link_speed; + struct am65_cpsw_mqprio mqprio; + struct am65_cpsw_iet iet; struct am65_cpsw_ale_ratelimit ale_bc_ratelimit; struct am65_cpsw_ale_ratelimit ale_mc_ratelimit; }; +#define AM65_CPSW_REG_CTL 0x004 +#define AM65_CPSW_PN_REG_CTL 0x004 +#define AM65_CPSW_PN_REG_FIFO_STATUS 0x050 +#define AM65_CPSW_PN_REG_EST_CTL 0x060 +#define AM65_CPSW_PN_REG_PRI_CIR(pri) (0x140 + 4 * (pri)) +#define AM65_CPSW_P0_REG_PRI_EIR(pri) (0x160 + 4 * (pri)) + +#define AM65_CPSW_PN_REG_CTL 0x004 +#define AM65_CPSW_PN_REG_TX_PRI_MAP 0x018 +#define AM65_CPSW_PN_REG_RX_PRI_MAP 0x020 +#define AM65_CPSW_PN_REG_FIFO_STATUS 0x050 +#define AM65_CPSW_PN_REG_EST_CTL 0x060 +#define AM65_CPSW_PN_REG_PRI_CIR(pri) (0x140 + 4 * (pri)) +#define AM65_CPSW_PN_REG_PRI_EIR(pri) (0x160 + 4 * (pri)) + +/* AM65_CPSW_REG_CTL register fields */ +#define AM65_CPSW_CTL_EST_EN BIT(18) + +/* AM65_CPSW_PN_REG_CTL register fields */ +#define AM65_CPSW_PN_CTL_EST_PORT_EN BIT(17) + +/* AM65_CPSW_PN_REG_EST_CTL register fields */ +#define AM65_CPSW_PN_EST_ONEBUF BIT(0) +#define AM65_CPSW_PN_EST_BUFSEL BIT(1) +#define AM65_CPSW_PN_EST_TS_EN BIT(2) +#define AM65_CPSW_PN_EST_TS_FIRST BIT(3) +#define AM65_CPSW_PN_EST_ONEPRI BIT(4) +#define AM65_CPSW_PN_EST_TS_PRI_MSK GENMASK(7, 5) + +/* AM65_CPSW_PN_REG_FIFO_STATUS register fields */ +#define AM65_CPSW_PN_FST_TX_PRI_ACTIVE_MSK GENMASK(7, 0) +#define AM65_CPSW_PN_FST_TX_E_MAC_ALLOW_MSK GENMASK(15, 8) +#define AM65_CPSW_PN_FST_EST_CNT_ERR BIT(16) +#define AM65_CPSW_PN_FST_EST_ADD_ERR BIT(17) +#define AM65_CPSW_PN_FST_EST_BUFACT BIT(18) + +/* EST FETCH COMMAND RAM */ +#define AM65_CPSW_FETCH_RAM_CMD_NUM 0x80 +#define AM65_CPSW_FETCH_CNT_MSK GENMASK(21, 8) +#define AM65_CPSW_FETCH_CNT_MAX (AM65_CPSW_FETCH_CNT_MSK >> 8) +#define AM65_CPSW_FETCH_CNT_OFFSET 8 +#define AM65_CPSW_FETCH_ALLOW_MSK GENMASK(7, 0) +#define AM65_CPSW_FETCH_ALLOW_MAX AM65_CPSW_FETCH_ALLOW_MSK + +/* number of priority queues per port FIFO */ +#define AM65_CPSW_PN_FIFO_PRIO_NUM 8 + +#if IS_ENABLED(CONFIG_TI_AM65_CPSW_QOS) int am65_cpsw_qos_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type, void *type_data); void am65_cpsw_qos_link_up(struct net_device *ndev, int link_speed); void am65_cpsw_qos_link_down(struct net_device *ndev); int am65_cpsw_qos_ndo_tx_p0_set_maxrate(struct net_device *ndev, int queue, u32 rate_mbps); void am65_cpsw_qos_tx_p0_rate_init(struct am65_cpsw_common *common); +void am65_cpsw_iet_commit_preemptible_tcs(struct am65_cpsw_port *port); +void am65_cpsw_iet_common_enable(struct am65_cpsw_common *common); +#else +static inline int am65_cpsw_qos_ndo_setup_tc(struct net_device *ndev, + enum tc_setup_type type, + void *type_data) +{ + return -EOPNOTSUPP; +} + +static inline void am65_cpsw_qos_link_up(struct net_device *ndev, + int link_speed) +{ } + +static inline void am65_cpsw_qos_link_down(struct net_device *ndev) +{ } + +static inline int am65_cpsw_qos_ndo_tx_p0_set_maxrate(struct net_device *ndev, + int queue, + u32 rate_mbps) +{ + return 0; +} + +static inline void am65_cpsw_qos_tx_p0_rate_init(struct am65_cpsw_common *common) +{ } +static inline void am65_cpsw_iet_commit_preemptible_tcs(struct am65_cpsw_port *port) +{ } +static inline void am65_cpsw_iet_common_enable(struct am65_cpsw_common *common) +{ } +#endif + +#define AM65_CPSW_REG_CTL 0x004 +#define AM65_CPSW_PN_REG_CTL 0x004 +#define AM65_CPSW_PN_REG_MAX_BLKS 0x008 +#define AM65_CPSW_PN_REG_TX_PRI_MAP 0x018 +#define AM65_CPSW_PN_REG_RX_PRI_MAP 0x020 +#define AM65_CPSW_PN_REG_IET_CTRL 0x040 +#define AM65_CPSW_PN_REG_IET_STATUS 0x044 +#define AM65_CPSW_PN_REG_IET_VERIFY 0x048 +#define AM65_CPSW_PN_REG_FIFO_STATUS 0x050 +#define AM65_CPSW_PN_REG_EST_CTL 0x060 +#define AM65_CPSW_PN_REG_PRI_CIR(pri) (0x140 + 4 * (pri)) +#define AM65_CPSW_PN_REG_PRI_EIR(pri) (0x160 + 4 * (pri)) + +/* AM65_CPSW_REG_CTL register fields */ +#define AM65_CPSW_CTL_IET_EN BIT(17) +#define AM65_CPSW_CTL_EST_EN BIT(18) + +/* AM65_CPSW_PN_REG_CTL register fields */ +#define AM65_CPSW_PN_CTL_IET_PORT_EN BIT(16) +#define AM65_CPSW_PN_CTL_EST_PORT_EN BIT(17) + +/* AM65_CPSW_PN_REG_EST_CTL register fields */ +#define AM65_CPSW_PN_EST_ONEBUF BIT(0) +#define AM65_CPSW_PN_EST_BUFSEL BIT(1) +#define AM65_CPSW_PN_EST_TS_EN BIT(2) +#define AM65_CPSW_PN_EST_TS_FIRST BIT(3) +#define AM65_CPSW_PN_EST_ONEPRI BIT(4) +#define AM65_CPSW_PN_EST_TS_PRI_MSK GENMASK(7, 5) + +/* AM65_CPSW_PN_REG_IET_CTRL register fields */ +#define AM65_CPSW_PN_IET_MAC_PENABLE BIT(0) +#define AM65_CPSW_PN_IET_MAC_DISABLEVERIFY BIT(2) +#define AM65_CPSW_PN_IET_MAC_LINKFAIL BIT(3) +#define AM65_CPSW_PN_IET_MAC_MAC_ADDFRAGSIZE_MASK GENMASK(10, 8) +#define AM65_CPSW_PN_IET_MAC_MAC_ADDFRAGSIZE_OFFSET 8 +#define AM65_CPSW_PN_IET_MAC_PREMPT_MASK GENMASK(23, 16) +#define AM65_CPSW_PN_IET_MAC_PREMPT_OFFSET 16 + +#define AM65_CPSW_PN_IET_MAC_SET_ADDFRAGSIZE(n) (((n) << AM65_CPSW_PN_IET_MAC_MAC_ADDFRAGSIZE_OFFSET) & \ + AM65_CPSW_PN_IET_MAC_MAC_ADDFRAGSIZE_MASK) +#define AM65_CPSW_PN_IET_MAC_GET_ADDFRAGSIZE(n) (((n) & AM65_CPSW_PN_IET_MAC_MAC_ADDFRAGSIZE_MASK) >> \ + AM65_CPSW_PN_IET_MAC_MAC_ADDFRAGSIZE_OFFSET) +#define AM65_CPSW_PN_IET_MAC_SET_PREEMPT(n) (((n) << AM65_CPSW_PN_IET_MAC_PREMPT_OFFSET) & \ + AM65_CPSW_PN_IET_MAC_PREMPT_MASK) +#define AM65_CPSW_PN_IET_MAC_GET_PREEMPT(n) (((n) & AM65_CPSW_PN_IET_MAC_PREMPT_MASK) >> \ + AM65_CPSW_PN_IET_MAC_PREMPT_OFFSET) + +/* AM65_CPSW_PN_REG_IET_STATUS register fields */ +#define AM65_CPSW_PN_MAC_STATUS GENMASK(3, 0) +#define AM65_CPSW_PN_MAC_VERIFIED BIT(0) +#define AM65_CPSW_PN_MAC_VERIFY_FAIL BIT(1) +#define AM65_CPSW_PN_MAC_RESPOND_ERR BIT(2) +#define AM65_CPSW_PN_MAC_VERIFY_ERR BIT(3) + +/* AM65_CPSW_PN_REG_IET_VERIFY register fields */ +#define AM65_CPSW_PN_MAC_VERIFY_CNT_MASK GENMASK(23, 0) +#define AM65_CPSW_PN_MAC_GET_VERIFY_CNT(n) ((n) & AM65_CPSW_PN_MAC_VERIFY_CNT_MASK) +/* 10 msec converted to NSEC */ +#define AM65_CPSW_IET_VERIFY_CNT_MS (10) +#define AM65_CPSW_IET_VERIFY_CNT_NS (AM65_CPSW_IET_VERIFY_CNT_MS * \ + NSEC_PER_MSEC) + +/* AM65_CPSW_PN_REG_FIFO_STATUS register fields */ +#define AM65_CPSW_PN_FST_TX_PRI_ACTIVE_MSK GENMASK(7, 0) +#define AM65_CPSW_PN_FST_TX_E_MAC_ALLOW_MSK GENMASK(15, 8) +#define AM65_CPSW_PN_FST_EST_CNT_ERR BIT(16) +#define AM65_CPSW_PN_FST_EST_ADD_ERR BIT(17) +#define AM65_CPSW_PN_FST_EST_BUFACT BIT(18) + +/* EST FETCH COMMAND RAM */ +#define AM65_CPSW_FETCH_RAM_CMD_NUM 0x80 +#define AM65_CPSW_FETCH_CNT_MSK GENMASK(21, 8) +#define AM65_CPSW_FETCH_CNT_MAX (AM65_CPSW_FETCH_CNT_MSK >> 8) +#define AM65_CPSW_FETCH_CNT_OFFSET 8 +#define AM65_CPSW_FETCH_ALLOW_MSK GENMASK(7, 0) +#define AM65_CPSW_FETCH_ALLOW_MAX AM65_CPSW_FETCH_ALLOW_MSK + +/* AM65_CPSW_PN_REG_MAX_BLKS fields for IET and No IET cases */ +/* 7 blocks for pn_rx_max_blks, 13 for pn_tx_max_blks*/ +#define AM65_CPSW_PN_TX_RX_MAX_BLKS_IET 0xD07 + +/* Slave IET Stats. register offsets */ +#define AM65_CPSW_STATN_IET_RX_ASSEMBLY_ERROR 0x140 +#define AM65_CPSW_STATN_IET_RX_ASSEMBLY_OK 0x144 +#define AM65_CPSW_STATN_IET_RX_SMD_ERROR 0x148 +#define AM65_CPSW_STATN_IET_RX_FRAG 0x14c +#define AM65_CPSW_STATN_IET_TX_HOLD 0x150 +#define AM65_CPSW_STATN_IET_TX_FRAG 0x154 + +/* number of priority queues per port FIFO */ +#define AM65_CPSW_PN_FIFO_PRIO_NUM 8 #endif /* AM65_CPSW_QOS_H_ */ diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 9663050a852d..e34816638569 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -93,6 +93,8 @@ struct pcpu_secy_stats { * @secys: linked list of SecY's on the underlying device * @gro_cells: pointer to the Generic Receive Offload cell * @offload: status of offloading on the MACsec device + * @insert_tx_tag: when offloading, device requires to insert an + * additional tag */ struct macsec_dev { struct macsec_secy secy; @@ -102,6 +104,7 @@ struct macsec_dev { struct list_head secys; struct gro_cells gro_cells; enum macsec_offload offload; + bool insert_tx_tag; }; /** @@ -604,26 +607,11 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb, return ERR_PTR(-EINVAL); } - if (unlikely(skb_headroom(skb) < MACSEC_NEEDED_HEADROOM || - skb_tailroom(skb) < MACSEC_NEEDED_TAILROOM)) { - struct sk_buff *nskb = skb_copy_expand(skb, - MACSEC_NEEDED_HEADROOM, - MACSEC_NEEDED_TAILROOM, - GFP_ATOMIC); - if (likely(nskb)) { - consume_skb(skb); - skb = nskb; - } else { - macsec_txsa_put(tx_sa); - kfree_skb(skb); - return ERR_PTR(-ENOMEM); - } - } else { - skb = skb_unshare(skb, GFP_ATOMIC); - if (!skb) { - macsec_txsa_put(tx_sa); - return ERR_PTR(-ENOMEM); - } + ret = skb_ensure_writable_head_tail(skb, dev); + if (unlikely(ret < 0)) { + macsec_txsa_put(tx_sa); + kfree_skb(skb); + return ERR_PTR(ret); } unprotected_len = skb->len; @@ -2583,6 +2571,33 @@ static bool macsec_is_configured(struct macsec_dev *macsec) return false; } +static bool macsec_needs_tx_tag(struct macsec_dev *macsec, + const struct macsec_ops *ops) +{ + return macsec->offload == MACSEC_OFFLOAD_PHY && + ops->mdo_insert_tx_tag; +} + +static void macsec_set_head_tail_room(struct net_device *dev) +{ + struct macsec_dev *macsec = macsec_priv(dev); + struct net_device *real_dev = macsec->real_dev; + int needed_headroom, needed_tailroom; + const struct macsec_ops *ops; + + ops = macsec_get_ops(macsec, NULL); + if (ops) { + needed_headroom = ops->needed_headroom; + needed_tailroom = ops->needed_tailroom; + } else { + needed_headroom = MACSEC_NEEDED_HEADROOM; + needed_tailroom = MACSEC_NEEDED_TAILROOM; + } + + dev->needed_headroom = real_dev->needed_headroom + needed_headroom; + dev->needed_tailroom = real_dev->needed_tailroom + needed_tailroom; +} + static int macsec_update_offload(struct net_device *dev, enum macsec_offload offload) { enum macsec_offload prev_offload; @@ -2620,8 +2635,13 @@ static int macsec_update_offload(struct net_device *dev, enum macsec_offload off ctx.secy = &macsec->secy; ret = offload == MACSEC_OFFLOAD_OFF ? macsec_offload(ops->mdo_del_secy, &ctx) : macsec_offload(ops->mdo_add_secy, &ctx); - if (ret) + if (ret) { macsec->offload = prev_offload; + return ret; + } + + macsec_set_head_tail_room(dev); + macsec->insert_tx_tag = macsec_needs_tx_tag(macsec, ops); return ret; } @@ -3379,6 +3399,40 @@ static struct genl_family macsec_fam __ro_after_init = { .resv_start_op = MACSEC_CMD_UPD_OFFLOAD + 1, }; +static struct sk_buff *macsec_insert_tx_tag(struct sk_buff *skb, + struct net_device *dev) +{ + struct macsec_dev *macsec = macsec_priv(dev); + const struct macsec_ops *ops; + struct phy_device *phydev; + struct macsec_context ctx; + int skb_final_len; + int err; + + ops = macsec_get_ops(macsec, &ctx); + skb_final_len = skb->len - ETH_HLEN + ops->needed_headroom + + ops->needed_tailroom; + if (unlikely(skb_final_len > macsec->real_dev->mtu)) { + err = -EINVAL; + goto cleanup; + } + + phydev = macsec->real_dev->phydev; + + err = skb_ensure_writable_head_tail(skb, dev); + if (unlikely(err < 0)) + goto cleanup; + + err = ops->mdo_insert_tx_tag(phydev, skb); + if (unlikely(err)) + goto cleanup; + + return skb; +cleanup: + kfree_skb(skb); + return ERR_PTR(err); +} + static netdev_tx_t macsec_start_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -3393,6 +3447,15 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb, skb_dst_drop(skb); dst_hold(&md_dst->dst); skb_dst_set(skb, &md_dst->dst); + + if (macsec->insert_tx_tag) { + skb = macsec_insert_tx_tag(skb, dev); + if (IS_ERR(skb)) { + DEV_STATS_INC(dev, tx_dropped); + return NETDEV_TX_OK; + } + } + skb->dev = macsec->real_dev; return dev_queue_xmit(skb); } @@ -3454,10 +3517,7 @@ static int macsec_dev_init(struct net_device *dev) dev->features = real_dev->features & MACSEC_FEATURES; dev->features |= NETIF_F_LLTX | NETIF_F_GSO_SOFTWARE; - dev->needed_headroom = real_dev->needed_headroom + - MACSEC_NEEDED_HEADROOM; - dev->needed_tailroom = real_dev->needed_tailroom + - MACSEC_NEEDED_TAILROOM; + macsec_set_head_tail_room(dev); if (is_zero_ether_addr(dev->dev_addr)) eth_hw_addr_inherit(dev, real_dev); @@ -3604,21 +3664,19 @@ static int macsec_set_mac_address(struct net_device *dev, void *p) struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; struct sockaddr *addr = p; + u8 old_addr[ETH_ALEN]; int err; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; - if (!(dev->flags & IFF_UP)) - goto out; - - err = dev_uc_add(real_dev, addr->sa_data); - if (err < 0) - return err; - - dev_uc_del(real_dev, dev->dev_addr); + if (dev->flags & IFF_UP) { + err = dev_uc_add(real_dev, addr->sa_data); + if (err < 0) + return err; + } -out: + ether_addr_copy(old_addr, dev->dev_addr); eth_hw_addr_set(dev, addr->sa_data); /* If h/w offloading is available, propagate to the device */ @@ -3627,13 +3685,29 @@ out: struct macsec_context ctx; ops = macsec_get_ops(macsec, &ctx); - if (ops) { - ctx.secy = &macsec->secy; - macsec_offload(ops->mdo_upd_secy, &ctx); + if (!ops) { + err = -EOPNOTSUPP; + goto restore_old_addr; } + + ctx.secy = &macsec->secy; + err = macsec_offload(ops->mdo_upd_secy, &ctx); + if (err) + goto restore_old_addr; } + if (dev->flags & IFF_UP) + dev_uc_del(real_dev, old_addr); + return 0; + +restore_old_addr: + if (dev->flags & IFF_UP) + dev_uc_del(real_dev, addr->sa_data); + + eth_hw_addr_set(dev, old_addr); + + return err; } static int macsec_change_mtu(struct net_device *dev, int new_mtu) @@ -4126,6 +4200,9 @@ static int macsec_newlink(struct net *net, struct net_device *dev, err = macsec_offload(ops->mdo_add_secy, &ctx); if (err) goto del_dev; + + macsec->insert_tx_tag = + macsec_needs_tx_tag(macsec, ops); } } diff --git a/drivers/net/mdio/of_mdio.c b/drivers/net/mdio/of_mdio.c index 64ebcb6d235c..9b6cab6154e0 100644 --- a/drivers/net/mdio/of_mdio.c +++ b/drivers/net/mdio/of_mdio.c @@ -139,6 +139,11 @@ bool of_mdiobus_child_is_phy(struct device_node *child) } EXPORT_SYMBOL(of_mdiobus_child_is_phy); +static void __of_mdiobus_unregister_callback(struct mii_bus *mdio) +{ + of_node_put(mdio->dev.of_node); +} + /** * __of_mdiobus_register - Register mii_bus and create PHYs from the device tree * @mdio: pointer to mii_bus structure @@ -166,6 +171,8 @@ int __of_mdiobus_register(struct mii_bus *mdio, struct device_node *np, * the device tree are populated after the bus has been registered */ mdio->phy_mask = ~0; + mdio->__unregister_callback = __of_mdiobus_unregister_callback; + of_node_get(np); device_set_node(&mdio->dev, of_fwnode_handle(np)); /* Get bus level PHY reset GPIO details */ @@ -177,7 +184,7 @@ int __of_mdiobus_register(struct mii_bus *mdio, struct device_node *np, /* Register the MDIO bus */ rc = __mdiobus_register(mdio, owner); if (rc) - return rc; + goto put_node; /* Loop over the child nodes and register a phy_device for each phy */ for_each_available_child_of_node(np, child) { @@ -237,6 +244,9 @@ int __of_mdiobus_register(struct mii_bus *mdio, struct device_node *np, unregister: of_node_put(child); mdiobus_unregister(mdio); + +put_node: + of_node_put(np); return rc; } EXPORT_SYMBOL(__of_mdiobus_register); diff --git a/drivers/net/netdevsim/macsec.c b/drivers/net/netdevsim/macsec.c index 0d5f50430dd3..aa007b1e4b78 100644 --- a/drivers/net/netdevsim/macsec.c +++ b/drivers/net/netdevsim/macsec.c @@ -3,11 +3,6 @@ #include <net/macsec.h> #include "netdevsim.h" -static inline u64 sci_to_cpu(sci_t sci) -{ - return be64_to_cpu((__force __be64)sci); -} - static int nsim_macsec_find_secy(struct netdevsim *ns, sci_t sci) { int i; diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 2e4667bf9ff5..9e2672800f0b 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -317,9 +317,10 @@ config NXP_CBTX_PHY config NXP_C45_TJA11XX_PHY tristate "NXP C45 TJA11XX PHYs" depends on PTP_1588_CLOCK_OPTIONAL + depends on MACSEC || !MACSEC help Enable support for NXP C45 TJA11XX PHYs. - Currently supports the TJA1103 and TJA1120 PHYs. + Currently supports the TJA1103, TJA1104 and TJA1120 PHYs. config NXP_TJA11XX_PHY tristate "NXP TJA11xx PHYs support" diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index e35ea69d9cb4..6097afd44392 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -84,7 +84,11 @@ obj-$(CONFIG_MICROSEMI_PHY) += mscc/ obj-$(CONFIG_MOTORCOMM_PHY) += motorcomm.o obj-$(CONFIG_NATIONAL_PHY) += national.o obj-$(CONFIG_NCN26000_PHY) += ncn26000.o -obj-$(CONFIG_NXP_C45_TJA11XX_PHY) += nxp-c45-tja11xx.o +nxp-c45-tja-objs += nxp-c45-tja11xx.o +ifdef CONFIG_MACSEC +nxp-c45-tja-objs += nxp-c45-tja11xx-macsec.o +endif +obj-$(CONFIG_NXP_C45_TJA11XX_PHY) += nxp-c45-tja.o obj-$(CONFIG_NXP_CBTX_PHY) += nxp-cbtx.o obj-$(CONFIG_NXP_TJA11XX_PHY) += nxp-tja11xx.o obj-$(CONFIG_QSEMI_PHY) += qsemi.o diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index d5dc927618ab..19cfbf36fe80 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -1781,27 +1781,27 @@ static int qca808x_phy_fast_retrain_config(struct phy_device *phydev) return ret; phy_write_mmd(phydev, MDIO_MMD_AN, QCA808X_PHY_MMD7_TOP_OPTION1, - QCA808X_TOP_OPTION1_DATA); + QCA808X_TOP_OPTION1_DATA); phy_write_mmd(phydev, MDIO_MMD_PMAPMD, QCA808X_PHY_MMD1_MSE_THRESHOLD_20DB, - QCA808X_MSE_THRESHOLD_20DB_VALUE); + QCA808X_MSE_THRESHOLD_20DB_VALUE); phy_write_mmd(phydev, MDIO_MMD_PMAPMD, QCA808X_PHY_MMD1_MSE_THRESHOLD_17DB, - QCA808X_MSE_THRESHOLD_17DB_VALUE); + QCA808X_MSE_THRESHOLD_17DB_VALUE); phy_write_mmd(phydev, MDIO_MMD_PMAPMD, QCA808X_PHY_MMD1_MSE_THRESHOLD_27DB, - QCA808X_MSE_THRESHOLD_27DB_VALUE); + QCA808X_MSE_THRESHOLD_27DB_VALUE); phy_write_mmd(phydev, MDIO_MMD_PMAPMD, QCA808X_PHY_MMD1_MSE_THRESHOLD_28DB, - QCA808X_MSE_THRESHOLD_28DB_VALUE); + QCA808X_MSE_THRESHOLD_28DB_VALUE); phy_write_mmd(phydev, MDIO_MMD_PCS, QCA808X_PHY_MMD3_DEBUG_1, - QCA808X_MMD3_DEBUG_1_VALUE); + QCA808X_MMD3_DEBUG_1_VALUE); phy_write_mmd(phydev, MDIO_MMD_PCS, QCA808X_PHY_MMD3_DEBUG_4, - QCA808X_MMD3_DEBUG_4_VALUE); + QCA808X_MMD3_DEBUG_4_VALUE); phy_write_mmd(phydev, MDIO_MMD_PCS, QCA808X_PHY_MMD3_DEBUG_5, - QCA808X_MMD3_DEBUG_5_VALUE); + QCA808X_MMD3_DEBUG_5_VALUE); phy_write_mmd(phydev, MDIO_MMD_PCS, QCA808X_PHY_MMD3_DEBUG_3, - QCA808X_MMD3_DEBUG_3_VALUE); + QCA808X_MMD3_DEBUG_3_VALUE); phy_write_mmd(phydev, MDIO_MMD_PCS, QCA808X_PHY_MMD3_DEBUG_6, - QCA808X_MMD3_DEBUG_6_VALUE); + QCA808X_MMD3_DEBUG_6_VALUE); phy_write_mmd(phydev, MDIO_MMD_PCS, QCA808X_PHY_MMD3_DEBUG_2, - QCA808X_MMD3_DEBUG_2_VALUE); + QCA808X_MMD3_DEBUG_2_VALUE); return 0; } @@ -1838,13 +1838,14 @@ static int qca808x_config_init(struct phy_device *phydev) /* Active adc&vga on 802.3az for the link 1000M and 100M */ ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, QCA808X_PHY_MMD3_ADDR_CLD_CTRL7, - QCA808X_8023AZ_AFE_CTRL_MASK, QCA808X_8023AZ_AFE_EN); + QCA808X_8023AZ_AFE_CTRL_MASK, QCA808X_8023AZ_AFE_EN); if (ret) return ret; /* Adjust the threshold on 802.3az for the link 1000M */ ret = phy_write_mmd(phydev, MDIO_MMD_PCS, - QCA808X_PHY_MMD3_AZ_TRAINING_CTRL, QCA808X_MMD3_AZ_TRAINING_VAL); + QCA808X_PHY_MMD3_AZ_TRAINING_CTRL, + QCA808X_MMD3_AZ_TRAINING_VAL); if (ret) return ret; @@ -1870,7 +1871,8 @@ static int qca808x_config_init(struct phy_device *phydev) /* Configure adc threshold as 100mv for the link 10M */ return at803x_debug_reg_mask(phydev, QCA808X_PHY_DEBUG_ADC_THRESHOLD, - QCA808X_ADC_THRESHOLD_MASK, QCA808X_ADC_THRESHOLD_100MV); + QCA808X_ADC_THRESHOLD_MASK, + QCA808X_ADC_THRESHOLD_100MV); } static int qca808x_read_status(struct phy_device *phydev) @@ -1883,7 +1885,7 @@ static int qca808x_read_status(struct phy_device *phydev) return ret; linkmode_mod_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, phydev->lp_advertising, - ret & MDIO_AN_10GBT_STAT_LP2_5G); + ret & MDIO_AN_10GBT_STAT_LP2_5G); ret = genphy_read_status(phydev); if (ret) @@ -1913,7 +1915,7 @@ static int qca808x_read_status(struct phy_device *phydev) */ if (qca808x_has_fast_retrain_or_slave_seed(phydev)) { if (phydev->master_slave_state == MASTER_SLAVE_STATE_ERR || - qca808x_is_prefer_master(phydev)) { + qca808x_is_prefer_master(phydev)) { qca808x_phy_ms_seed_enable(phydev, false); } else { qca808x_phy_ms_seed_enable(phydev, true); @@ -2070,18 +2072,22 @@ static int qca808x_cable_test_get_status(struct phy_device *phydev, bool *finish ethnl_cable_test_result(phydev, ETHTOOL_A_CABLE_PAIR_D, qca808x_cable_test_result_trans(pair_d)); - if (qca808x_cdt_fault_length_valid(pair_a)) - ethnl_cable_test_fault_length(phydev, ETHTOOL_A_CABLE_PAIR_A, - qca808x_cdt_fault_length(phydev, ETHTOOL_A_CABLE_PAIR_A)); - if (qca808x_cdt_fault_length_valid(pair_b)) - ethnl_cable_test_fault_length(phydev, ETHTOOL_A_CABLE_PAIR_B, - qca808x_cdt_fault_length(phydev, ETHTOOL_A_CABLE_PAIR_B)); - if (qca808x_cdt_fault_length_valid(pair_c)) - ethnl_cable_test_fault_length(phydev, ETHTOOL_A_CABLE_PAIR_C, - qca808x_cdt_fault_length(phydev, ETHTOOL_A_CABLE_PAIR_C)); - if (qca808x_cdt_fault_length_valid(pair_d)) - ethnl_cable_test_fault_length(phydev, ETHTOOL_A_CABLE_PAIR_D, - qca808x_cdt_fault_length(phydev, ETHTOOL_A_CABLE_PAIR_D)); + if (qca808x_cdt_fault_length_valid(pair_a)) { + val = qca808x_cdt_fault_length(phydev, ETHTOOL_A_CABLE_PAIR_A); + ethnl_cable_test_fault_length(phydev, ETHTOOL_A_CABLE_PAIR_A, val); + } + if (qca808x_cdt_fault_length_valid(pair_b)) { + val = qca808x_cdt_fault_length(phydev, ETHTOOL_A_CABLE_PAIR_B); + ethnl_cable_test_fault_length(phydev, ETHTOOL_A_CABLE_PAIR_B, val); + } + if (qca808x_cdt_fault_length_valid(pair_c)) { + val = qca808x_cdt_fault_length(phydev, ETHTOOL_A_CABLE_PAIR_C); + ethnl_cable_test_fault_length(phydev, ETHTOOL_A_CABLE_PAIR_C, val); + } + if (qca808x_cdt_fault_length_valid(pair_d)) { + val = qca808x_cdt_fault_length(phydev, ETHTOOL_A_CABLE_PAIR_D); + ethnl_cable_test_fault_length(phydev, ETHTOOL_A_CABLE_PAIR_D, val); + } *finished = true; @@ -2148,8 +2154,9 @@ static void qca808x_link_change_notify(struct phy_device *phydev) * the interface device address is always phy address added by 1. */ mdiobus_c45_modify_changed(phydev->mdio.bus, phydev->mdio.addr + 1, - MDIO_MMD_PMAPMD, QCA8081_PHY_SERDES_MMD1_FIFO_CTRL, - QCA8081_PHY_FIFO_RSTN, phydev->link ? QCA8081_PHY_FIFO_RSTN : 0); + MDIO_MMD_PMAPMD, QCA8081_PHY_SERDES_MMD1_FIFO_CTRL, + QCA8081_PHY_FIFO_RSTN, + phydev->link ? QCA8081_PHY_FIFO_RSTN : 0); } static struct phy_driver at803x_driver[] = { diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 6cf73c15635b..4a30757c4ff8 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -787,6 +787,9 @@ void mdiobus_unregister(struct mii_bus *bus) gpiod_set_value_cansleep(bus->reset_gpiod, 1); device_del(&bus->dev); + + if (bus->__unregister_callback) + bus->__unregister_callback(bus); } EXPORT_SYMBOL(mdiobus_unregister); diff --git a/drivers/net/phy/nxp-c45-tja11xx-macsec.c b/drivers/net/phy/nxp-c45-tja11xx-macsec.c new file mode 100644 index 000000000000..550ef08970f4 --- /dev/null +++ b/drivers/net/phy/nxp-c45-tja11xx-macsec.c @@ -0,0 +1,1729 @@ +// SPDX-License-Identifier: GPL-2.0 +/* NXP C45 PTP PHY driver interface + * Copyright 2023 NXP + * Author: Radu Pirea <[email protected]> + */ + +#include <linux/delay.h> +#include <linux/ethtool_netlink.h> +#include <linux/kernel.h> +#include <linux/mii.h> +#include <linux/module.h> +#include <linux/phy.h> +#include <linux/processor.h> +#include <net/dst_metadata.h> +#include <net/macsec.h> + +#include "nxp-c45-tja11xx.h" + +#define MACSEC_REG_SIZE 32 +#define TX_SC_MAX 4 + +#define TX_SC_BIT(secy_id) BIT(MACSEC_REG_SIZE - (secy_id) - 1) + +#define VEND1_MACSEC_BASE 0x9000 + +#define MACSEC_CFG 0x0000 +#define MACSEC_CFG_BYPASS BIT(1) +#define MACSEC_CFG_S0I BIT(0) + +#define MACSEC_TPNET 0x0044 +#define PN_WRAP_THRESHOLD 0xffffffff + +#define MACSEC_RXSCA 0x0080 +#define MACSEC_RXSCKA 0x0084 + +#define MACSEC_TXSCA 0x00C0 +#define MACSEC_TXSCKA 0x00C4 + +#define MACSEC_RXSC_SCI_1H 0x0100 + +#define MACSEC_RXSC_CFG 0x0128 +#define MACSEC_RXSC_CFG_XPN BIT(25) +#define MACSEC_RXSC_CFG_AES_256 BIT(24) +#define MACSEC_RXSC_CFG_SCI_EN BIT(11) +#define MACSEC_RXSC_CFG_RP BIT(10) +#define MACSEC_RXSC_CFG_VF_MASK GENMASK(9, 8) +#define MACSEC_RXSC_CFG_VF_OFF 8 + +#define MACSEC_RPW 0x012C + +#define MACSEC_RXSA_A_CS 0x0180 +#define MACSEC_RXSA_A_NPN 0x0184 +#define MACSEC_RXSA_A_XNPN 0x0188 +#define MACSEC_RXSA_A_LNPN 0x018C +#define MACSEC_RXSA_A_LXNPN 0x0190 + +#define MACSEC_RXSA_B_CS 0x01C0 +#define MACSEC_RXSA_B_NPN 0x01C4 +#define MACSEC_RXSA_B_XNPN 0x01C8 +#define MACSEC_RXSA_B_LNPN 0x01CC +#define MACSEC_RXSA_B_LXNPN 0x01D0 + +#define MACSEC_RXSA_CS_AN_OFF 1 +#define MACSEC_RXSA_CS_EN BIT(0) + +#define MACSEC_TXSC_SCI_1H 0x0200 +#define MACSEC_TXSC_CFG 0x0228 +#define MACSEC_TXSC_CFG_XPN BIT(25) +#define MACSEC_TXSC_CFG_AES_256 BIT(24) +#define MACSEC_TXSC_CFG_AN_MASK GENMASK(19, 18) +#define MACSEC_TXSC_CFG_AN_OFF 18 +#define MACSEC_TXSC_CFG_ASA BIT(17) +#define MACSEC_TXSC_CFG_SCE BIT(16) +#define MACSEC_TXSC_CFG_ENCRYPT BIT(4) +#define MACSEC_TXSC_CFG_PROTECT BIT(3) +#define MACSEC_TXSC_CFG_SEND_SCI BIT(2) +#define MACSEC_TXSC_CFG_END_STATION BIT(1) +#define MACSEC_TXSC_CFG_SCB BIT(0) + +#define MACSEC_TXSA_A_CS 0x0280 +#define MACSEC_TXSA_A_NPN 0x0284 +#define MACSEC_TXSA_A_XNPN 0x0288 + +#define MACSEC_TXSA_B_CS 0x02C0 +#define MACSEC_TXSA_B_NPN 0x02C4 +#define MACSEC_TXSA_B_XNPN 0x02C8 + +#define MACSEC_SA_CS_A BIT(31) + +#define MACSEC_EVR 0x0400 +#define MACSEC_EVER 0x0404 + +#define MACSEC_RXSA_A_KA 0x0700 +#define MACSEC_RXSA_A_SSCI 0x0720 +#define MACSEC_RXSA_A_SALT 0x0724 + +#define MACSEC_RXSA_B_KA 0x0740 +#define MACSEC_RXSA_B_SSCI 0x0760 +#define MACSEC_RXSA_B_SALT 0x0764 + +#define MACSEC_TXSA_A_KA 0x0780 +#define MACSEC_TXSA_A_SSCI 0x07A0 +#define MACSEC_TXSA_A_SALT 0x07A4 + +#define MACSEC_TXSA_B_KA 0x07C0 +#define MACSEC_TXSA_B_SSCI 0x07E0 +#define MACSEC_TXSA_B_SALT 0x07E4 + +#define MACSEC_UPFR0D2 0x0A08 +#define MACSEC_UPFR0M1 0x0A10 +#define MACSEC_OVP BIT(12) + +#define MACSEC_UPFR0M2 0x0A14 +#define ETYPE_MASK 0xffff + +#define MACSEC_UPFR0R 0x0A18 +#define MACSEC_UPFR_EN BIT(0) + +#define ADPTR_CNTRL 0x0F00 +#define ADPTR_CNTRL_CONFIG_EN BIT(14) +#define ADPTR_CNTRL_ADPTR_EN BIT(12) +#define ADPTR_TX_TAG_CNTRL 0x0F0C +#define ADPTR_TX_TAG_CNTRL_ENA BIT(31) + +#define TX_SC_FLT_BASE 0x800 +#define TX_SC_FLT_SIZE 0x10 +#define TX_FLT_BASE(flt_id) (TX_SC_FLT_BASE + \ + TX_SC_FLT_SIZE * (flt_id)) + +#define TX_SC_FLT_OFF_MAC_DA_SA 0x04 +#define TX_SC_FLT_OFF_MAC_SA 0x08 +#define TX_SC_FLT_OFF_MAC_CFG 0x0C +#define TX_SC_FLT_BY_SA BIT(14) +#define TX_SC_FLT_EN BIT(8) + +#define TX_SC_FLT_MAC_DA_SA(base) ((base) + TX_SC_FLT_OFF_MAC_DA_SA) +#define TX_SC_FLT_MAC_SA(base) ((base) + TX_SC_FLT_OFF_MAC_SA) +#define TX_SC_FLT_MAC_CFG(base) ((base) + TX_SC_FLT_OFF_MAC_CFG) + +#define ADAPTER_EN BIT(6) +#define MACSEC_EN BIT(5) + +#define MACSEC_INOV1HS 0x0140 +#define MACSEC_INOV2HS 0x0144 +#define MACSEC_INOD1HS 0x0148 +#define MACSEC_INOD2HS 0x014C +#define MACSEC_RXSCIPUS 0x0150 +#define MACSEC_RXSCIPDS 0x0154 +#define MACSEC_RXSCIPLS 0x0158 +#define MACSEC_RXAN0INUSS 0x0160 +#define MACSEC_RXAN0IPUSS 0x0170 +#define MACSEC_RXSA_A_IPOS 0x0194 +#define MACSEC_RXSA_A_IPIS 0x01B0 +#define MACSEC_RXSA_A_IPNVS 0x01B4 +#define MACSEC_RXSA_B_IPOS 0x01D4 +#define MACSEC_RXSA_B_IPIS 0x01F0 +#define MACSEC_RXSA_B_IPNVS 0x01F4 +#define MACSEC_OPUS 0x021C +#define MACSEC_OPTLS 0x022C +#define MACSEC_OOP1HS 0x0240 +#define MACSEC_OOP2HS 0x0244 +#define MACSEC_OOE1HS 0x0248 +#define MACSEC_OOE2HS 0x024C +#define MACSEC_TXSA_A_OPPS 0x028C +#define MACSEC_TXSA_A_OPES 0x0290 +#define MACSEC_TXSA_B_OPPS 0x02CC +#define MACSEC_TXSA_B_OPES 0x02D0 +#define MACSEC_INPWTS 0x0630 +#define MACSEC_INPBTS 0x0638 +#define MACSEC_IPSNFS 0x063C + +#define TJA11XX_TLV_TX_NEEDED_HEADROOM (32) +#define TJA11XX_TLV_NEEDED_TAILROOM (0) + +#define ETH_P_TJA11XX_TLV (0x4e58) + +enum nxp_c45_sa_type { + TX_SA, + RX_SA, +}; + +struct nxp_c45_sa { + void *sa; + const struct nxp_c45_sa_regs *regs; + enum nxp_c45_sa_type type; + bool is_key_a; + u8 an; + struct list_head list; +}; + +struct nxp_c45_secy { + struct macsec_secy *secy; + struct macsec_rx_sc *rx_sc; + struct list_head sa_list; + int secy_id; + bool rx_sc0_impl; + struct list_head list; +}; + +struct nxp_c45_macsec { + struct list_head secy_list; + DECLARE_BITMAP(secy_bitmap, TX_SC_MAX); + DECLARE_BITMAP(tx_sc_bitmap, TX_SC_MAX); +}; + +struct nxp_c45_sa_regs { + u16 cs; + u16 npn; + u16 xnpn; + u16 lnpn; + u16 lxnpn; + u16 ka; + u16 ssci; + u16 salt; + u16 ipis; + u16 ipnvs; + u16 ipos; + u16 opps; + u16 opes; +}; + +static const struct nxp_c45_sa_regs rx_sa_a_regs = { + .cs = MACSEC_RXSA_A_CS, + .npn = MACSEC_RXSA_A_NPN, + .xnpn = MACSEC_RXSA_A_XNPN, + .lnpn = MACSEC_RXSA_A_LNPN, + .lxnpn = MACSEC_RXSA_A_LXNPN, + .ka = MACSEC_RXSA_A_KA, + .ssci = MACSEC_RXSA_A_SSCI, + .salt = MACSEC_RXSA_A_SALT, + .ipis = MACSEC_RXSA_A_IPIS, + .ipnvs = MACSEC_RXSA_A_IPNVS, + .ipos = MACSEC_RXSA_A_IPOS, +}; + +static const struct nxp_c45_sa_regs rx_sa_b_regs = { + .cs = MACSEC_RXSA_B_CS, + .npn = MACSEC_RXSA_B_NPN, + .xnpn = MACSEC_RXSA_B_XNPN, + .lnpn = MACSEC_RXSA_B_LNPN, + .lxnpn = MACSEC_RXSA_B_LXNPN, + .ka = MACSEC_RXSA_B_KA, + .ssci = MACSEC_RXSA_B_SSCI, + .salt = MACSEC_RXSA_B_SALT, + .ipis = MACSEC_RXSA_B_IPIS, + .ipnvs = MACSEC_RXSA_B_IPNVS, + .ipos = MACSEC_RXSA_B_IPOS, +}; + +static const struct nxp_c45_sa_regs tx_sa_a_regs = { + .cs = MACSEC_TXSA_A_CS, + .npn = MACSEC_TXSA_A_NPN, + .xnpn = MACSEC_TXSA_A_XNPN, + .ka = MACSEC_TXSA_A_KA, + .ssci = MACSEC_TXSA_A_SSCI, + .salt = MACSEC_TXSA_A_SALT, + .opps = MACSEC_TXSA_A_OPPS, + .opes = MACSEC_TXSA_A_OPES, +}; + +static const struct nxp_c45_sa_regs tx_sa_b_regs = { + .cs = MACSEC_TXSA_B_CS, + .npn = MACSEC_TXSA_B_NPN, + .xnpn = MACSEC_TXSA_B_XNPN, + .ka = MACSEC_TXSA_B_KA, + .ssci = MACSEC_TXSA_B_SSCI, + .salt = MACSEC_TXSA_B_SALT, + .opps = MACSEC_TXSA_B_OPPS, + .opes = MACSEC_TXSA_B_OPES, +}; + +static const +struct nxp_c45_sa_regs *nxp_c45_sa_regs_get(enum nxp_c45_sa_type sa_type, + bool key_a) +{ + if (sa_type == RX_SA) + if (key_a) + return &rx_sa_a_regs; + else + return &rx_sa_b_regs; + else if (sa_type == TX_SA) + if (key_a) + return &tx_sa_a_regs; + else + return &tx_sa_b_regs; + else + return NULL; +} + +static int nxp_c45_macsec_write(struct phy_device *phydev, u16 addr, u32 value) +{ + u32 lvalue = value; + u16 laddr; + int ret; + + WARN_ON_ONCE(addr % 4); + + phydev_dbg(phydev, "write addr 0x%x value 0x%x\n", addr, value); + + laddr = VEND1_MACSEC_BASE + addr / 2; + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, laddr, lvalue); + if (ret) + return ret; + + laddr += 1; + lvalue >>= 16; + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, laddr, lvalue); + + return ret; +} + +static int nxp_c45_macsec_read(struct phy_device *phydev, u16 addr, u32 *value) +{ + u32 lvalue; + u16 laddr; + int ret; + + WARN_ON_ONCE(addr % 4); + + laddr = VEND1_MACSEC_BASE + addr / 2; + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, laddr); + if (ret < 0) + return ret; + + laddr += 1; + lvalue = (u32)ret & 0xffff; + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, laddr); + if (ret < 0) + return ret; + + lvalue |= (u32)ret << 16; + *value = lvalue; + + phydev_dbg(phydev, "read addr 0x%x value 0x%x\n", addr, *value); + + return 0; +} + +static void nxp_c45_macsec_read32_64(struct phy_device *phydev, u16 addr, + u64 *value) +{ + u32 lvalue; + + nxp_c45_macsec_read(phydev, addr, &lvalue); + *value = lvalue; +} + +static void nxp_c45_macsec_read64(struct phy_device *phydev, u16 addr, + u64 *value) +{ + u32 lvalue; + + nxp_c45_macsec_read(phydev, addr, &lvalue); + *value = (u64)lvalue << 32; + nxp_c45_macsec_read(phydev, addr + 4, &lvalue); + *value |= lvalue; +} + +static void nxp_c45_secy_irq_en(struct phy_device *phydev, + struct nxp_c45_secy *phy_secy, bool en) +{ + u32 reg; + + nxp_c45_macsec_read(phydev, MACSEC_EVER, ®); + if (en) + reg |= TX_SC_BIT(phy_secy->secy_id); + else + reg &= ~TX_SC_BIT(phy_secy->secy_id); + nxp_c45_macsec_write(phydev, MACSEC_EVER, reg); +} + +static struct nxp_c45_secy *nxp_c45_find_secy(struct list_head *secy_list, + sci_t sci) +{ + struct nxp_c45_secy *pos, *tmp; + + list_for_each_entry_safe(pos, tmp, secy_list, list) + if (pos->secy->sci == sci) + return pos; + + return ERR_PTR(-EINVAL); +} + +static struct +nxp_c45_secy *nxp_c45_find_secy_by_id(struct list_head *secy_list, + int id) +{ + struct nxp_c45_secy *pos, *tmp; + + list_for_each_entry_safe(pos, tmp, secy_list, list) + if (pos->secy_id == id) + return pos; + + return ERR_PTR(-EINVAL); +} + +static void nxp_c45_secy_free(struct nxp_c45_secy *phy_secy) +{ + list_del(&phy_secy->list); + kfree(phy_secy); +} + +static struct nxp_c45_sa *nxp_c45_find_sa(struct list_head *sa_list, + enum nxp_c45_sa_type sa_type, u8 an) +{ + struct nxp_c45_sa *pos, *tmp; + + list_for_each_entry_safe(pos, tmp, sa_list, list) + if (pos->an == an && pos->type == sa_type) + return pos; + + return ERR_PTR(-EINVAL); +} + +static struct nxp_c45_sa *nxp_c45_sa_alloc(struct list_head *sa_list, void *sa, + enum nxp_c45_sa_type sa_type, u8 an) +{ + struct nxp_c45_sa *first = NULL, *pos, *tmp; + int occurrences = 0; + + list_for_each_entry_safe(pos, tmp, sa_list, list) { + if (pos->type != sa_type) + continue; + + if (pos->an == an) + return ERR_PTR(-EINVAL); + + first = pos; + occurrences++; + if (occurrences >= 2) + return ERR_PTR(-ENOSPC); + } + + tmp = kzalloc(sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return ERR_PTR(-ENOMEM); + + if (first) + tmp->is_key_a = !first->is_key_a; + else + tmp->is_key_a = true; + + tmp->sa = sa; + tmp->type = sa_type; + tmp->an = an; + tmp->regs = nxp_c45_sa_regs_get(tmp->type, tmp->is_key_a); + list_add_tail(&tmp->list, sa_list); + + return tmp; +} + +static void nxp_c45_sa_free(struct nxp_c45_sa *sa) +{ + list_del(&sa->list); + kfree(sa); +} + +static void nxp_c45_sa_list_free(struct list_head *sa_list) +{ + struct nxp_c45_sa *pos, *tmp; + + list_for_each_entry_safe(pos, tmp, sa_list, list) + nxp_c45_sa_free(pos); +} + +static void nxp_c45_sa_set_pn(struct phy_device *phydev, + struct nxp_c45_sa *sa, u64 pn, + u32 replay_window) +{ + const struct nxp_c45_sa_regs *sa_regs = sa->regs; + pn_t npn = {.full64 = pn}; + pn_t lnpn; + + nxp_c45_macsec_write(phydev, sa_regs->npn, npn.lower); + nxp_c45_macsec_write(phydev, sa_regs->xnpn, npn.upper); + if (sa->type != RX_SA) + return; + + if (pn > replay_window) + lnpn.full64 = pn - replay_window; + else + lnpn.full64 = 1; + + nxp_c45_macsec_write(phydev, sa_regs->lnpn, lnpn.lower); + nxp_c45_macsec_write(phydev, sa_regs->lxnpn, lnpn.upper); +} + +static void nxp_c45_sa_set_key(struct macsec_context *ctx, + const struct nxp_c45_sa_regs *sa_regs, + u8 *salt, ssci_t ssci) +{ + struct phy_device *phydev = ctx->phydev; + u32 key_size = ctx->secy->key_len / 4; + u32 salt_size = MACSEC_SALT_LEN / 4; + u32 *key_u32 = (u32 *)ctx->sa.key; + u32 *salt_u32 = (u32 *)salt; + u32 reg, value; + int i; + + for (i = 0; i < key_size; i++) { + reg = sa_regs->ka + i * 4; + value = (__force u32)cpu_to_be32(key_u32[i]); + nxp_c45_macsec_write(phydev, reg, value); + } + + if (ctx->secy->xpn) { + for (i = 0; i < salt_size; i++) { + reg = sa_regs->salt + (2 - i) * 4; + value = (__force u32)cpu_to_be32(salt_u32[i]); + nxp_c45_macsec_write(phydev, reg, value); + } + + value = (__force u32)cpu_to_be32((__force u32)ssci); + nxp_c45_macsec_write(phydev, sa_regs->ssci, value); + } + + nxp_c45_macsec_write(phydev, sa_regs->cs, MACSEC_SA_CS_A); +} + +static void nxp_c45_rx_sa_clear_stats(struct phy_device *phydev, + struct nxp_c45_sa *sa) +{ + nxp_c45_macsec_write(phydev, sa->regs->ipis, 0); + nxp_c45_macsec_write(phydev, sa->regs->ipnvs, 0); + nxp_c45_macsec_write(phydev, sa->regs->ipos, 0); + + nxp_c45_macsec_write(phydev, MACSEC_RXAN0INUSS + sa->an * 4, 0); + nxp_c45_macsec_write(phydev, MACSEC_RXAN0IPUSS + sa->an * 4, 0); +} + +static void nxp_c45_rx_sa_read_stats(struct phy_device *phydev, + struct nxp_c45_sa *sa, + struct macsec_rx_sa_stats *stats) +{ + nxp_c45_macsec_read(phydev, sa->regs->ipis, &stats->InPktsInvalid); + nxp_c45_macsec_read(phydev, sa->regs->ipnvs, &stats->InPktsNotValid); + nxp_c45_macsec_read(phydev, sa->regs->ipos, &stats->InPktsOK); +} + +static void nxp_c45_tx_sa_clear_stats(struct phy_device *phydev, + struct nxp_c45_sa *sa) +{ + nxp_c45_macsec_write(phydev, sa->regs->opps, 0); + nxp_c45_macsec_write(phydev, sa->regs->opes, 0); +} + +static void nxp_c45_tx_sa_read_stats(struct phy_device *phydev, + struct nxp_c45_sa *sa, + struct macsec_tx_sa_stats *stats) +{ + nxp_c45_macsec_read(phydev, sa->regs->opps, &stats->OutPktsProtected); + nxp_c45_macsec_read(phydev, sa->regs->opes, &stats->OutPktsEncrypted); +} + +static void nxp_c45_rx_sa_update(struct phy_device *phydev, + struct nxp_c45_sa *sa, bool en) +{ + const struct nxp_c45_sa_regs *sa_regs = sa->regs; + u32 cfg; + + cfg = sa->an << MACSEC_RXSA_CS_AN_OFF; + cfg |= en ? MACSEC_RXSA_CS_EN : 0; + nxp_c45_macsec_write(phydev, sa_regs->cs, cfg); +} + +static void nxp_c45_tx_sa_update(struct phy_device *phydev, + struct nxp_c45_sa *sa, bool en) +{ + u32 cfg = 0; + + nxp_c45_macsec_read(phydev, MACSEC_TXSC_CFG, &cfg); + + cfg &= ~MACSEC_TXSC_CFG_AN_MASK; + cfg |= sa->an << MACSEC_TXSC_CFG_AN_OFF; + + if (sa->is_key_a) + cfg &= ~MACSEC_TXSC_CFG_ASA; + else + cfg |= MACSEC_TXSC_CFG_ASA; + + if (en) + cfg |= MACSEC_TXSC_CFG_SCE; + else + cfg &= ~MACSEC_TXSC_CFG_SCE; + + nxp_c45_macsec_write(phydev, MACSEC_TXSC_CFG, cfg); +} + +static void nxp_c45_set_sci(struct phy_device *phydev, u16 sci_base_addr, + sci_t sci) +{ + u64 lsci = sci_to_cpu(sci); + + nxp_c45_macsec_write(phydev, sci_base_addr, lsci >> 32); + nxp_c45_macsec_write(phydev, sci_base_addr + 4, lsci); +} + +static bool nxp_c45_port_is_1(sci_t sci) +{ + u16 port = sci_to_cpu(sci); + + return port == 1; +} + +static void nxp_c45_select_secy(struct phy_device *phydev, u8 id) +{ + nxp_c45_macsec_write(phydev, MACSEC_RXSCA, id); + nxp_c45_macsec_write(phydev, MACSEC_RXSCKA, id); + nxp_c45_macsec_write(phydev, MACSEC_TXSCA, id); + nxp_c45_macsec_write(phydev, MACSEC_TXSCKA, id); +} + +static bool nxp_c45_secy_valid(struct nxp_c45_secy *phy_secy, + bool can_rx_sc0_impl) +{ + bool end_station = phy_secy->secy->tx_sc.end_station; + bool scb = phy_secy->secy->tx_sc.scb; + + phy_secy->rx_sc0_impl = false; + + if (end_station) { + if (!nxp_c45_port_is_1(phy_secy->secy->sci)) + return false; + if (!phy_secy->rx_sc) + return true; + return nxp_c45_port_is_1(phy_secy->rx_sc->sci); + } + + if (scb) + return false; + + if (!can_rx_sc0_impl) + return false; + + if (phy_secy->secy_id != 0) + return false; + + phy_secy->rx_sc0_impl = true; + + return true; +} + +static bool nxp_c45_rx_sc0_impl(struct nxp_c45_secy *phy_secy) +{ + bool end_station = phy_secy->secy->tx_sc.end_station; + bool send_sci = phy_secy->secy->tx_sc.send_sci; + bool scb = phy_secy->secy->tx_sc.scb; + + return !end_station && !send_sci && !scb; +} + +static bool nxp_c45_mac_addr_free(struct macsec_context *ctx) +{ + struct nxp_c45_phy *priv = ctx->phydev->priv; + struct nxp_c45_secy *pos, *tmp; + + list_for_each_entry_safe(pos, tmp, &priv->macsec->secy_list, list) { + if (pos->secy == ctx->secy) + continue; + + if (memcmp(pos->secy->netdev->dev_addr, + ctx->secy->netdev->dev_addr, ETH_ALEN) == 0) + return false; + } + + return true; +} + +static void nxp_c45_tx_sc_en_flt(struct phy_device *phydev, int secy_id, + bool en) +{ + u32 tx_flt_base = TX_FLT_BASE(secy_id); + u32 reg = 0; + + nxp_c45_macsec_read(phydev, TX_SC_FLT_MAC_CFG(tx_flt_base), ®); + if (en) + reg |= TX_SC_FLT_EN; + else + reg &= ~TX_SC_FLT_EN; + nxp_c45_macsec_write(phydev, TX_SC_FLT_MAC_CFG(tx_flt_base), reg); +} + +static void nxp_c45_tx_sc_set_flt(struct phy_device *phydev, + struct nxp_c45_secy *phy_secy) +{ + const u8 *dev_addr = phy_secy->secy->netdev->dev_addr; + u32 tx_flt_base = TX_FLT_BASE(phy_secy->secy_id); + u32 reg; + + reg = dev_addr[0] << 8 | dev_addr[1]; + nxp_c45_macsec_write(phydev, TX_SC_FLT_MAC_DA_SA(tx_flt_base), reg); + reg = dev_addr[5] | dev_addr[4] << 8 | dev_addr[3] << 16 | + dev_addr[2] << 24; + + nxp_c45_macsec_write(phydev, TX_SC_FLT_MAC_SA(tx_flt_base), reg); + nxp_c45_macsec_read(phydev, TX_SC_FLT_MAC_CFG(tx_flt_base), ®); + reg &= TX_SC_FLT_EN; + reg |= TX_SC_FLT_BY_SA | phy_secy->secy_id; + nxp_c45_macsec_write(phydev, TX_SC_FLT_MAC_CFG(tx_flt_base), reg); +} + +static void nxp_c45_tx_sc_update(struct phy_device *phydev, + struct nxp_c45_secy *phy_secy) +{ + u32 cfg = 0; + + nxp_c45_macsec_read(phydev, MACSEC_TXSC_CFG, &cfg); + + phydev_dbg(phydev, "XPN %s\n", phy_secy->secy->xpn ? "on" : "off"); + if (phy_secy->secy->xpn) + cfg |= MACSEC_TXSC_CFG_XPN; + else + cfg &= ~MACSEC_TXSC_CFG_XPN; + + phydev_dbg(phydev, "key len %u\n", phy_secy->secy->key_len); + if (phy_secy->secy->key_len == 32) + cfg |= MACSEC_TXSC_CFG_AES_256; + else + cfg &= ~MACSEC_TXSC_CFG_AES_256; + + phydev_dbg(phydev, "encryption %s\n", + phy_secy->secy->tx_sc.encrypt ? "on" : "off"); + if (phy_secy->secy->tx_sc.encrypt) + cfg |= MACSEC_TXSC_CFG_ENCRYPT; + else + cfg &= ~MACSEC_TXSC_CFG_ENCRYPT; + + phydev_dbg(phydev, "protect frames %s\n", + phy_secy->secy->protect_frames ? "on" : "off"); + if (phy_secy->secy->protect_frames) + cfg |= MACSEC_TXSC_CFG_PROTECT; + else + cfg &= ~MACSEC_TXSC_CFG_PROTECT; + + phydev_dbg(phydev, "send sci %s\n", + phy_secy->secy->tx_sc.send_sci ? "on" : "off"); + if (phy_secy->secy->tx_sc.send_sci) + cfg |= MACSEC_TXSC_CFG_SEND_SCI; + else + cfg &= ~MACSEC_TXSC_CFG_SEND_SCI; + + phydev_dbg(phydev, "end station %s\n", + phy_secy->secy->tx_sc.end_station ? "on" : "off"); + if (phy_secy->secy->tx_sc.end_station) + cfg |= MACSEC_TXSC_CFG_END_STATION; + else + cfg &= ~MACSEC_TXSC_CFG_END_STATION; + + phydev_dbg(phydev, "scb %s\n", + phy_secy->secy->tx_sc.scb ? "on" : "off"); + if (phy_secy->secy->tx_sc.scb) + cfg |= MACSEC_TXSC_CFG_SCB; + else + cfg &= ~MACSEC_TXSC_CFG_SCB; + + nxp_c45_macsec_write(phydev, MACSEC_TXSC_CFG, cfg); +} + +static void nxp_c45_tx_sc_clear_stats(struct phy_device *phydev, + struct nxp_c45_secy *phy_secy) +{ + struct nxp_c45_sa *pos, *tmp; + + list_for_each_entry_safe(pos, tmp, &phy_secy->sa_list, list) + if (pos->type == TX_SA) + nxp_c45_tx_sa_clear_stats(phydev, pos); + + nxp_c45_macsec_write(phydev, MACSEC_OPUS, 0); + nxp_c45_macsec_write(phydev, MACSEC_OPTLS, 0); + nxp_c45_macsec_write(phydev, MACSEC_OOP1HS, 0); + nxp_c45_macsec_write(phydev, MACSEC_OOP2HS, 0); + nxp_c45_macsec_write(phydev, MACSEC_OOE1HS, 0); + nxp_c45_macsec_write(phydev, MACSEC_OOE2HS, 0); +} + +static void nxp_c45_set_rx_sc0_impl(struct phy_device *phydev, + bool enable) +{ + u32 reg = 0; + + nxp_c45_macsec_read(phydev, MACSEC_CFG, ®); + if (enable) + reg |= MACSEC_CFG_S0I; + else + reg &= ~MACSEC_CFG_S0I; + nxp_c45_macsec_write(phydev, MACSEC_CFG, reg); +} + +static bool nxp_c45_is_rx_sc0_impl(struct list_head *secy_list) +{ + struct nxp_c45_secy *pos, *tmp; + + list_for_each_entry_safe(pos, tmp, secy_list, list) + if (pos->rx_sc0_impl) + return pos->rx_sc0_impl; + + return false; +} + +static void nxp_c45_rx_sc_en(struct phy_device *phydev, + struct macsec_rx_sc *rx_sc, bool en) +{ + u32 reg = 0; + + nxp_c45_macsec_read(phydev, MACSEC_RXSC_CFG, ®); + if (rx_sc->active && en) + reg |= MACSEC_RXSC_CFG_SCI_EN; + else + reg &= ~MACSEC_RXSC_CFG_SCI_EN; + nxp_c45_macsec_write(phydev, MACSEC_RXSC_CFG, reg); +} + +static void nxp_c45_rx_sc_update(struct phy_device *phydev, + struct nxp_c45_secy *phy_secy) +{ + struct macsec_rx_sc *rx_sc = phy_secy->rx_sc; + struct nxp_c45_phy *priv = phydev->priv; + u32 cfg = 0; + + nxp_c45_macsec_read(phydev, MACSEC_RXSC_CFG, &cfg); + cfg &= ~MACSEC_RXSC_CFG_VF_MASK; + cfg = phy_secy->secy->validate_frames << MACSEC_RXSC_CFG_VF_OFF; + + phydev_dbg(phydev, "validate frames %u\n", + phy_secy->secy->validate_frames); + phydev_dbg(phydev, "replay_protect %s window %u\n", + phy_secy->secy->replay_protect ? "on" : "off", + phy_secy->secy->replay_window); + if (phy_secy->secy->replay_protect) { + cfg |= MACSEC_RXSC_CFG_RP; + nxp_c45_macsec_write(phydev, MACSEC_RPW, + phy_secy->secy->replay_window); + } else { + cfg &= ~MACSEC_RXSC_CFG_RP; + } + + phydev_dbg(phydev, "rx_sc->active %s\n", + rx_sc->active ? "on" : "off"); + if (rx_sc->active && + test_bit(phy_secy->secy_id, priv->macsec->secy_bitmap)) + cfg |= MACSEC_RXSC_CFG_SCI_EN; + else + cfg &= ~MACSEC_RXSC_CFG_SCI_EN; + + phydev_dbg(phydev, "key len %u\n", phy_secy->secy->key_len); + if (phy_secy->secy->key_len == 32) + cfg |= MACSEC_RXSC_CFG_AES_256; + else + cfg &= ~MACSEC_RXSC_CFG_AES_256; + + phydev_dbg(phydev, "XPN %s\n", phy_secy->secy->xpn ? "on" : "off"); + if (phy_secy->secy->xpn) + cfg |= MACSEC_RXSC_CFG_XPN; + else + cfg &= ~MACSEC_RXSC_CFG_XPN; + + nxp_c45_macsec_write(phydev, MACSEC_RXSC_CFG, cfg); +} + +static void nxp_c45_rx_sc_clear_stats(struct phy_device *phydev, + struct nxp_c45_secy *phy_secy) +{ + struct nxp_c45_sa *pos, *tmp; + int i; + + list_for_each_entry_safe(pos, tmp, &phy_secy->sa_list, list) + if (pos->type == RX_SA) + nxp_c45_rx_sa_clear_stats(phydev, pos); + + nxp_c45_macsec_write(phydev, MACSEC_INOD1HS, 0); + nxp_c45_macsec_write(phydev, MACSEC_INOD2HS, 0); + + nxp_c45_macsec_write(phydev, MACSEC_INOV1HS, 0); + nxp_c45_macsec_write(phydev, MACSEC_INOV2HS, 0); + + nxp_c45_macsec_write(phydev, MACSEC_RXSCIPDS, 0); + nxp_c45_macsec_write(phydev, MACSEC_RXSCIPLS, 0); + nxp_c45_macsec_write(phydev, MACSEC_RXSCIPUS, 0); + + for (i = 0; i < MACSEC_NUM_AN; i++) { + nxp_c45_macsec_write(phydev, MACSEC_RXAN0INUSS + i * 4, 0); + nxp_c45_macsec_write(phydev, MACSEC_RXAN0IPUSS + i * 4, 0); + } +} + +static void nxp_c45_rx_sc_del(struct phy_device *phydev, + struct nxp_c45_secy *phy_secy) +{ + struct nxp_c45_sa *pos, *tmp; + + nxp_c45_macsec_write(phydev, MACSEC_RXSC_CFG, 0); + nxp_c45_macsec_write(phydev, MACSEC_RPW, 0); + nxp_c45_set_sci(phydev, MACSEC_RXSC_SCI_1H, 0); + + nxp_c45_rx_sc_clear_stats(phydev, phy_secy); + + list_for_each_entry_safe(pos, tmp, &phy_secy->sa_list, list) { + if (pos->type == RX_SA) { + nxp_c45_rx_sa_update(phydev, pos, false); + nxp_c45_sa_free(pos); + } + } +} + +static void nxp_c45_clear_global_stats(struct phy_device *phydev) +{ + nxp_c45_macsec_write(phydev, MACSEC_INPBTS, 0); + nxp_c45_macsec_write(phydev, MACSEC_INPWTS, 0); + nxp_c45_macsec_write(phydev, MACSEC_IPSNFS, 0); +} + +static void nxp_c45_macsec_en(struct phy_device *phydev, bool en) +{ + u32 reg; + + nxp_c45_macsec_read(phydev, MACSEC_CFG, ®); + if (en) + reg |= MACSEC_CFG_BYPASS; + else + reg &= ~MACSEC_CFG_BYPASS; + nxp_c45_macsec_write(phydev, MACSEC_CFG, reg); +} + +static int nxp_c45_mdo_dev_open(struct macsec_context *ctx) +{ + struct phy_device *phydev = ctx->phydev; + struct nxp_c45_phy *priv = phydev->priv; + struct nxp_c45_secy *phy_secy; + int any_bit_set; + + phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci); + if (IS_ERR(phy_secy)) + return PTR_ERR(phy_secy); + + nxp_c45_select_secy(phydev, phy_secy->secy_id); + + nxp_c45_tx_sc_en_flt(phydev, phy_secy->secy_id, true); + nxp_c45_set_rx_sc0_impl(phydev, phy_secy->rx_sc0_impl); + if (phy_secy->rx_sc) + nxp_c45_rx_sc_en(phydev, phy_secy->rx_sc, true); + + any_bit_set = find_first_bit(priv->macsec->secy_bitmap, TX_SC_MAX); + if (any_bit_set == TX_SC_MAX) + nxp_c45_macsec_en(phydev, true); + + set_bit(phy_secy->secy_id, priv->macsec->secy_bitmap); + + return 0; +} + +static int nxp_c45_mdo_dev_stop(struct macsec_context *ctx) +{ + struct phy_device *phydev = ctx->phydev; + struct nxp_c45_phy *priv = phydev->priv; + struct nxp_c45_secy *phy_secy; + int any_bit_set; + + phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci); + if (IS_ERR(phy_secy)) + return PTR_ERR(phy_secy); + + nxp_c45_select_secy(phydev, phy_secy->secy_id); + + nxp_c45_tx_sc_en_flt(phydev, phy_secy->secy_id, false); + if (phy_secy->rx_sc) + nxp_c45_rx_sc_en(phydev, phy_secy->rx_sc, false); + nxp_c45_set_rx_sc0_impl(phydev, false); + + clear_bit(phy_secy->secy_id, priv->macsec->secy_bitmap); + any_bit_set = find_first_bit(priv->macsec->secy_bitmap, TX_SC_MAX); + if (any_bit_set == TX_SC_MAX) + nxp_c45_macsec_en(phydev, false); + + return 0; +} + +static int nxp_c45_mdo_add_secy(struct macsec_context *ctx) +{ + struct phy_device *phydev = ctx->phydev; + struct nxp_c45_phy *priv = phydev->priv; + struct nxp_c45_secy *phy_secy; + bool can_rx_sc0_impl; + int idx; + + phydev_dbg(phydev, "add SecY SCI %016llx\n", + sci_to_cpu(ctx->secy->sci)); + + if (!nxp_c45_mac_addr_free(ctx)) + return -EBUSY; + + if (nxp_c45_is_rx_sc0_impl(&priv->macsec->secy_list)) + return -EBUSY; + + idx = find_first_zero_bit(priv->macsec->tx_sc_bitmap, TX_SC_MAX); + if (idx == TX_SC_MAX) + return -ENOSPC; + + phy_secy = kzalloc(sizeof(*phy_secy), GFP_KERNEL); + if (!phy_secy) + return -ENOMEM; + + INIT_LIST_HEAD(&phy_secy->sa_list); + phy_secy->secy = ctx->secy; + phy_secy->secy_id = idx; + + /* If the point to point mode should be enabled, we should have no + * SecY added yet. + */ + can_rx_sc0_impl = list_count_nodes(&priv->macsec->secy_list) == 0; + if (!nxp_c45_secy_valid(phy_secy, can_rx_sc0_impl)) { + kfree(phy_secy); + return -EINVAL; + } + + phy_secy->rx_sc0_impl = nxp_c45_rx_sc0_impl(phy_secy); + + nxp_c45_select_secy(phydev, phy_secy->secy_id); + nxp_c45_set_sci(phydev, MACSEC_TXSC_SCI_1H, ctx->secy->sci); + nxp_c45_tx_sc_set_flt(phydev, phy_secy); + nxp_c45_tx_sc_update(phydev, phy_secy); + if (phy_interrupt_is_valid(phydev)) + nxp_c45_secy_irq_en(phydev, phy_secy, true); + + set_bit(idx, priv->macsec->tx_sc_bitmap); + list_add_tail(&phy_secy->list, &priv->macsec->secy_list); + + return 0; +} + +static void nxp_c45_tx_sa_next(struct nxp_c45_secy *phy_secy, + struct nxp_c45_sa *next_sa, u8 encoding_sa) +{ + struct nxp_c45_sa *sa; + + sa = nxp_c45_find_sa(&phy_secy->sa_list, TX_SA, encoding_sa); + if (!IS_ERR(sa)) { + memcpy(next_sa, sa, sizeof(*sa)); + } else { + next_sa->is_key_a = true; + next_sa->an = encoding_sa; + } +} + +static int nxp_c45_mdo_upd_secy(struct macsec_context *ctx) +{ + u8 encoding_sa = ctx->secy->tx_sc.encoding_sa; + struct phy_device *phydev = ctx->phydev; + struct nxp_c45_phy *priv = phydev->priv; + struct nxp_c45_secy *phy_secy; + struct nxp_c45_sa next_sa; + bool can_rx_sc0_impl; + + phydev_dbg(phydev, "update SecY SCI %016llx\n", + sci_to_cpu(ctx->secy->sci)); + + phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci); + if (IS_ERR(phy_secy)) + return PTR_ERR(phy_secy); + + if (!nxp_c45_mac_addr_free(ctx)) + return -EBUSY; + + /* If the point to point mode should be enabled, we should have only + * one SecY added, respectively the updated one. + */ + can_rx_sc0_impl = list_count_nodes(&priv->macsec->secy_list) == 1; + if (!nxp_c45_secy_valid(phy_secy, can_rx_sc0_impl)) + return -EINVAL; + phy_secy->rx_sc0_impl = nxp_c45_rx_sc0_impl(phy_secy); + + nxp_c45_select_secy(phydev, phy_secy->secy_id); + nxp_c45_tx_sc_set_flt(phydev, phy_secy); + nxp_c45_tx_sc_update(phydev, phy_secy); + nxp_c45_tx_sa_next(phy_secy, &next_sa, encoding_sa); + nxp_c45_tx_sa_update(phydev, &next_sa, ctx->secy->operational); + + nxp_c45_set_rx_sc0_impl(phydev, phy_secy->rx_sc0_impl); + if (phy_secy->rx_sc) + nxp_c45_rx_sc_update(phydev, phy_secy); + + return 0; +} + +static int nxp_c45_mdo_del_secy(struct macsec_context *ctx) +{ + u8 encoding_sa = ctx->secy->tx_sc.encoding_sa; + struct phy_device *phydev = ctx->phydev; + struct nxp_c45_phy *priv = phydev->priv; + struct nxp_c45_secy *phy_secy; + struct nxp_c45_sa next_sa; + + phydev_dbg(phydev, "delete SecY SCI %016llx\n", + sci_to_cpu(ctx->secy->sci)); + + phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci); + if (IS_ERR(phy_secy)) + return PTR_ERR(phy_secy); + nxp_c45_select_secy(phydev, phy_secy->secy_id); + + nxp_c45_mdo_dev_stop(ctx); + nxp_c45_tx_sa_next(phy_secy, &next_sa, encoding_sa); + nxp_c45_tx_sa_update(phydev, &next_sa, false); + nxp_c45_tx_sc_clear_stats(phydev, phy_secy); + if (phy_secy->rx_sc) + nxp_c45_rx_sc_del(phydev, phy_secy); + + nxp_c45_sa_list_free(&phy_secy->sa_list); + if (phy_interrupt_is_valid(phydev)) + nxp_c45_secy_irq_en(phydev, phy_secy, false); + + clear_bit(phy_secy->secy_id, priv->macsec->tx_sc_bitmap); + nxp_c45_secy_free(phy_secy); + + if (list_empty(&priv->macsec->secy_list)) + nxp_c45_clear_global_stats(phydev); + + return 0; +} + +static int nxp_c45_mdo_add_rxsc(struct macsec_context *ctx) +{ + struct phy_device *phydev = ctx->phydev; + struct nxp_c45_phy *priv = phydev->priv; + struct nxp_c45_secy *phy_secy; + + phydev_dbg(phydev, "add RX SC SCI %016llx %s\n", + sci_to_cpu(ctx->rx_sc->sci), + ctx->rx_sc->active ? "enabled" : "disabled"); + + phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci); + if (IS_ERR(phy_secy)) + return PTR_ERR(phy_secy); + + if (phy_secy->rx_sc) + return -ENOSPC; + + if (phy_secy->secy->tx_sc.end_station && + !nxp_c45_port_is_1(ctx->rx_sc->sci)) + return -EINVAL; + + phy_secy->rx_sc = ctx->rx_sc; + + nxp_c45_select_secy(phydev, phy_secy->secy_id); + nxp_c45_set_sci(phydev, MACSEC_RXSC_SCI_1H, ctx->rx_sc->sci); + nxp_c45_rx_sc_update(phydev, phy_secy); + + return 0; +} + +static int nxp_c45_mdo_upd_rxsc(struct macsec_context *ctx) +{ + struct phy_device *phydev = ctx->phydev; + struct nxp_c45_phy *priv = phydev->priv; + struct nxp_c45_secy *phy_secy; + + phydev_dbg(phydev, "update RX SC SCI %016llx %s\n", + sci_to_cpu(ctx->rx_sc->sci), + ctx->rx_sc->active ? "enabled" : "disabled"); + + phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci); + if (IS_ERR(phy_secy)) + return PTR_ERR(phy_secy); + + nxp_c45_select_secy(phydev, phy_secy->secy_id); + nxp_c45_rx_sc_update(phydev, phy_secy); + + return 0; +} + +static int nxp_c45_mdo_del_rxsc(struct macsec_context *ctx) +{ + struct phy_device *phydev = ctx->phydev; + struct nxp_c45_phy *priv = phydev->priv; + struct nxp_c45_secy *phy_secy; + + phydev_dbg(phydev, "delete RX SC SCI %016llx %s\n", + sci_to_cpu(ctx->rx_sc->sci), + ctx->rx_sc->active ? "enabled" : "disabled"); + + phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci); + if (IS_ERR(phy_secy)) + return PTR_ERR(phy_secy); + + nxp_c45_select_secy(phydev, phy_secy->secy_id); + nxp_c45_rx_sc_del(phydev, phy_secy); + phy_secy->rx_sc = NULL; + + return 0; +} + +static int nxp_c45_mdo_add_rxsa(struct macsec_context *ctx) +{ + struct macsec_rx_sa *rx_sa = ctx->sa.rx_sa; + struct phy_device *phydev = ctx->phydev; + struct nxp_c45_phy *priv = phydev->priv; + struct nxp_c45_secy *phy_secy; + u8 an = ctx->sa.assoc_num; + struct nxp_c45_sa *sa; + + phydev_dbg(phydev, "add RX SA %u %s to RX SC SCI %016llx\n", + an, rx_sa->active ? "enabled" : "disabled", + sci_to_cpu(rx_sa->sc->sci)); + + phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci); + if (IS_ERR(phy_secy)) + return PTR_ERR(phy_secy); + + sa = nxp_c45_sa_alloc(&phy_secy->sa_list, rx_sa, RX_SA, an); + if (IS_ERR(sa)) + return PTR_ERR(sa); + + nxp_c45_select_secy(phydev, phy_secy->secy_id); + nxp_c45_sa_set_pn(phydev, sa, rx_sa->next_pn, + ctx->secy->replay_window); + nxp_c45_sa_set_key(ctx, sa->regs, rx_sa->key.salt.bytes, rx_sa->ssci); + nxp_c45_rx_sa_update(phydev, sa, rx_sa->active); + + return 0; +} + +static int nxp_c45_mdo_upd_rxsa(struct macsec_context *ctx) +{ + struct macsec_rx_sa *rx_sa = ctx->sa.rx_sa; + struct phy_device *phydev = ctx->phydev; + struct nxp_c45_phy *priv = phydev->priv; + struct nxp_c45_secy *phy_secy; + u8 an = ctx->sa.assoc_num; + struct nxp_c45_sa *sa; + + phydev_dbg(phydev, "update RX SA %u %s to RX SC SCI %016llx\n", + an, rx_sa->active ? "enabled" : "disabled", + sci_to_cpu(rx_sa->sc->sci)); + + phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci); + if (IS_ERR(phy_secy)) + return PTR_ERR(phy_secy); + + sa = nxp_c45_find_sa(&phy_secy->sa_list, RX_SA, an); + if (IS_ERR(sa)) + return PTR_ERR(sa); + + nxp_c45_select_secy(phydev, phy_secy->secy_id); + if (ctx->sa.update_pn) + nxp_c45_sa_set_pn(phydev, sa, rx_sa->next_pn, + ctx->secy->replay_window); + nxp_c45_rx_sa_update(phydev, sa, rx_sa->active); + + return 0; +} + +static int nxp_c45_mdo_del_rxsa(struct macsec_context *ctx) +{ + struct macsec_rx_sa *rx_sa = ctx->sa.rx_sa; + struct phy_device *phydev = ctx->phydev; + struct nxp_c45_phy *priv = phydev->priv; + struct nxp_c45_secy *phy_secy; + u8 an = ctx->sa.assoc_num; + struct nxp_c45_sa *sa; + + phydev_dbg(phydev, "delete RX SA %u %s to RX SC SCI %016llx\n", + an, rx_sa->active ? "enabled" : "disabled", + sci_to_cpu(rx_sa->sc->sci)); + + phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci); + if (IS_ERR(phy_secy)) + return PTR_ERR(phy_secy); + + sa = nxp_c45_find_sa(&phy_secy->sa_list, RX_SA, an); + if (IS_ERR(sa)) + return PTR_ERR(sa); + + nxp_c45_select_secy(phydev, phy_secy->secy_id); + nxp_c45_rx_sa_update(phydev, sa, false); + nxp_c45_rx_sa_clear_stats(phydev, sa); + + nxp_c45_sa_free(sa); + + return 0; +} + +static int nxp_c45_mdo_add_txsa(struct macsec_context *ctx) +{ + struct macsec_tx_sa *tx_sa = ctx->sa.tx_sa; + struct phy_device *phydev = ctx->phydev; + struct nxp_c45_phy *priv = phydev->priv; + struct nxp_c45_secy *phy_secy; + u8 an = ctx->sa.assoc_num; + struct nxp_c45_sa *sa; + + phydev_dbg(phydev, "add TX SA %u %s to TX SC %016llx\n", + an, ctx->sa.tx_sa->active ? "enabled" : "disabled", + sci_to_cpu(ctx->secy->sci)); + + phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci); + if (IS_ERR(phy_secy)) + return PTR_ERR(phy_secy); + + sa = nxp_c45_sa_alloc(&phy_secy->sa_list, tx_sa, TX_SA, an); + if (IS_ERR(sa)) + return PTR_ERR(sa); + + nxp_c45_select_secy(phydev, phy_secy->secy_id); + nxp_c45_sa_set_pn(phydev, sa, tx_sa->next_pn, 0); + nxp_c45_sa_set_key(ctx, sa->regs, tx_sa->key.salt.bytes, tx_sa->ssci); + if (ctx->secy->tx_sc.encoding_sa == sa->an) + nxp_c45_tx_sa_update(phydev, sa, tx_sa->active); + + return 0; +} + +static int nxp_c45_mdo_upd_txsa(struct macsec_context *ctx) +{ + struct macsec_tx_sa *tx_sa = ctx->sa.tx_sa; + struct phy_device *phydev = ctx->phydev; + struct nxp_c45_phy *priv = phydev->priv; + struct nxp_c45_secy *phy_secy; + u8 an = ctx->sa.assoc_num; + struct nxp_c45_sa *sa; + + phydev_dbg(phydev, "update TX SA %u %s to TX SC %016llx\n", + an, ctx->sa.tx_sa->active ? "enabled" : "disabled", + sci_to_cpu(ctx->secy->sci)); + + phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci); + if (IS_ERR(phy_secy)) + return PTR_ERR(phy_secy); + + sa = nxp_c45_find_sa(&phy_secy->sa_list, TX_SA, an); + if (IS_ERR(sa)) + return PTR_ERR(sa); + + nxp_c45_select_secy(phydev, phy_secy->secy_id); + if (ctx->sa.update_pn) + nxp_c45_sa_set_pn(phydev, sa, tx_sa->next_pn, 0); + if (ctx->secy->tx_sc.encoding_sa == sa->an) + nxp_c45_tx_sa_update(phydev, sa, tx_sa->active); + + return 0; +} + +static int nxp_c45_mdo_del_txsa(struct macsec_context *ctx) +{ + struct phy_device *phydev = ctx->phydev; + struct nxp_c45_phy *priv = phydev->priv; + struct nxp_c45_secy *phy_secy; + u8 an = ctx->sa.assoc_num; + struct nxp_c45_sa *sa; + + phydev_dbg(phydev, "delete TX SA %u %s to TX SC %016llx\n", + an, ctx->sa.tx_sa->active ? "enabled" : "disabled", + sci_to_cpu(ctx->secy->sci)); + + phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci); + if (IS_ERR(phy_secy)) + return PTR_ERR(phy_secy); + + sa = nxp_c45_find_sa(&phy_secy->sa_list, TX_SA, an); + if (IS_ERR(sa)) + return PTR_ERR(sa); + + nxp_c45_select_secy(phydev, phy_secy->secy_id); + if (ctx->secy->tx_sc.encoding_sa == sa->an) + nxp_c45_tx_sa_update(phydev, sa, false); + nxp_c45_tx_sa_clear_stats(phydev, sa); + + nxp_c45_sa_free(sa); + + return 0; +} + +static int nxp_c45_mdo_get_dev_stats(struct macsec_context *ctx) +{ + struct phy_device *phydev = ctx->phydev; + struct nxp_c45_phy *priv = phydev->priv; + struct macsec_dev_stats *dev_stats; + struct nxp_c45_secy *phy_secy; + + phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci); + if (IS_ERR(phy_secy)) + return PTR_ERR(phy_secy); + + dev_stats = ctx->stats.dev_stats; + nxp_c45_select_secy(phydev, phy_secy->secy_id); + + nxp_c45_macsec_read32_64(phydev, MACSEC_OPUS, + &dev_stats->OutPktsUntagged); + nxp_c45_macsec_read32_64(phydev, MACSEC_OPTLS, + &dev_stats->OutPktsTooLong); + nxp_c45_macsec_read32_64(phydev, MACSEC_INPBTS, + &dev_stats->InPktsBadTag); + + if (phy_secy->secy->validate_frames == MACSEC_VALIDATE_STRICT) + nxp_c45_macsec_read32_64(phydev, MACSEC_INPWTS, + &dev_stats->InPktsNoTag); + else + nxp_c45_macsec_read32_64(phydev, MACSEC_INPWTS, + &dev_stats->InPktsUntagged); + + if (phy_secy->secy->validate_frames == MACSEC_VALIDATE_STRICT) + nxp_c45_macsec_read32_64(phydev, MACSEC_IPSNFS, + &dev_stats->InPktsNoSCI); + else + nxp_c45_macsec_read32_64(phydev, MACSEC_IPSNFS, + &dev_stats->InPktsUnknownSCI); + + /* Always 0. */ + dev_stats->InPktsOverrun = 0; + + return 0; +} + +static int nxp_c45_mdo_get_tx_sc_stats(struct macsec_context *ctx) +{ + struct phy_device *phydev = ctx->phydev; + struct nxp_c45_phy *priv = phydev->priv; + struct macsec_tx_sa_stats tx_sa_stats; + struct macsec_tx_sc_stats *stats; + struct nxp_c45_secy *phy_secy; + struct nxp_c45_sa *pos, *tmp; + + phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci); + if (IS_ERR(phy_secy)) + return PTR_ERR(phy_secy); + + stats = ctx->stats.tx_sc_stats; + nxp_c45_select_secy(phydev, phy_secy->secy_id); + + nxp_c45_macsec_read64(phydev, MACSEC_OOE1HS, + &stats->OutOctetsEncrypted); + nxp_c45_macsec_read64(phydev, MACSEC_OOP1HS, + &stats->OutOctetsProtected); + list_for_each_entry_safe(pos, tmp, &phy_secy->sa_list, list) { + if (pos->type != TX_SA) + continue; + + memset(&tx_sa_stats, 0, sizeof(tx_sa_stats)); + nxp_c45_tx_sa_read_stats(phydev, pos, &tx_sa_stats); + + stats->OutPktsEncrypted += tx_sa_stats.OutPktsEncrypted; + stats->OutPktsProtected += tx_sa_stats.OutPktsProtected; + } + + return 0; +} + +static int nxp_c45_mdo_get_tx_sa_stats(struct macsec_context *ctx) +{ + struct phy_device *phydev = ctx->phydev; + struct nxp_c45_phy *priv = phydev->priv; + struct macsec_tx_sa_stats *stats; + struct nxp_c45_secy *phy_secy; + u8 an = ctx->sa.assoc_num; + struct nxp_c45_sa *sa; + + phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci); + if (IS_ERR(phy_secy)) + return PTR_ERR(phy_secy); + + sa = nxp_c45_find_sa(&phy_secy->sa_list, TX_SA, an); + if (IS_ERR(sa)) + return PTR_ERR(sa); + + stats = ctx->stats.tx_sa_stats; + nxp_c45_select_secy(phydev, phy_secy->secy_id); + nxp_c45_tx_sa_read_stats(phydev, sa, stats); + + return 0; +} + +static int nxp_c45_mdo_get_rx_sc_stats(struct macsec_context *ctx) +{ + struct phy_device *phydev = ctx->phydev; + struct nxp_c45_phy *priv = phydev->priv; + struct macsec_rx_sa_stats rx_sa_stats; + struct macsec_rx_sc_stats *stats; + struct nxp_c45_secy *phy_secy; + struct nxp_c45_sa *pos, *tmp; + u32 reg = 0; + int i; + + phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci); + if (IS_ERR(phy_secy)) + return PTR_ERR(phy_secy); + + if (phy_secy->rx_sc != ctx->rx_sc) + return -EINVAL; + + stats = ctx->stats.rx_sc_stats; + nxp_c45_select_secy(phydev, phy_secy->secy_id); + + list_for_each_entry_safe(pos, tmp, &phy_secy->sa_list, list) { + if (pos->type != RX_SA) + continue; + + memset(&rx_sa_stats, 0, sizeof(rx_sa_stats)); + nxp_c45_rx_sa_read_stats(phydev, pos, &rx_sa_stats); + + stats->InPktsInvalid += rx_sa_stats.InPktsInvalid; + stats->InPktsNotValid += rx_sa_stats.InPktsNotValid; + stats->InPktsOK += rx_sa_stats.InPktsOK; + } + + for (i = 0; i < MACSEC_NUM_AN; i++) { + nxp_c45_macsec_read(phydev, MACSEC_RXAN0INUSS + i * 4, ®); + stats->InPktsNotUsingSA += reg; + nxp_c45_macsec_read(phydev, MACSEC_RXAN0IPUSS + i * 4, ®); + stats->InPktsUnusedSA += reg; + } + + nxp_c45_macsec_read64(phydev, MACSEC_INOD1HS, + &stats->InOctetsDecrypted); + nxp_c45_macsec_read64(phydev, MACSEC_INOV1HS, + &stats->InOctetsValidated); + + nxp_c45_macsec_read32_64(phydev, MACSEC_RXSCIPDS, + &stats->InPktsDelayed); + nxp_c45_macsec_read32_64(phydev, MACSEC_RXSCIPLS, + &stats->InPktsLate); + nxp_c45_macsec_read32_64(phydev, MACSEC_RXSCIPUS, + &stats->InPktsUnchecked); + + return 0; +} + +static int nxp_c45_mdo_get_rx_sa_stats(struct macsec_context *ctx) +{ + struct phy_device *phydev = ctx->phydev; + struct nxp_c45_phy *priv = phydev->priv; + struct macsec_rx_sa_stats *stats; + struct nxp_c45_secy *phy_secy; + u8 an = ctx->sa.assoc_num; + struct nxp_c45_sa *sa; + + phy_secy = nxp_c45_find_secy(&priv->macsec->secy_list, ctx->secy->sci); + if (IS_ERR(phy_secy)) + return PTR_ERR(phy_secy); + + sa = nxp_c45_find_sa(&phy_secy->sa_list, RX_SA, an); + if (IS_ERR(sa)) + return PTR_ERR(sa); + + stats = ctx->stats.rx_sa_stats; + nxp_c45_select_secy(phydev, phy_secy->secy_id); + + nxp_c45_rx_sa_read_stats(phydev, sa, stats); + nxp_c45_macsec_read(phydev, MACSEC_RXAN0INUSS + an * 4, + &stats->InPktsNotUsingSA); + nxp_c45_macsec_read(phydev, MACSEC_RXAN0IPUSS + an * 4, + &stats->InPktsUnusedSA); + + return 0; +} + +struct tja11xx_tlv_header { + struct ethhdr eth; + u8 subtype; + u8 len; + u8 payload[28]; +}; + +static int nxp_c45_mdo_insert_tx_tag(struct phy_device *phydev, + struct sk_buff *skb) +{ + struct tja11xx_tlv_header *tlv; + struct ethhdr *eth; + + eth = eth_hdr(skb); + tlv = skb_push(skb, TJA11XX_TLV_TX_NEEDED_HEADROOM); + memmove(tlv, eth, sizeof(*eth)); + skb_reset_mac_header(skb); + tlv->eth.h_proto = htons(ETH_P_TJA11XX_TLV); + tlv->subtype = 1; + tlv->len = sizeof(tlv->payload); + memset(tlv->payload, 0, sizeof(tlv->payload)); + + return 0; +} + +static const struct macsec_ops nxp_c45_macsec_ops = { + .mdo_dev_open = nxp_c45_mdo_dev_open, + .mdo_dev_stop = nxp_c45_mdo_dev_stop, + .mdo_add_secy = nxp_c45_mdo_add_secy, + .mdo_upd_secy = nxp_c45_mdo_upd_secy, + .mdo_del_secy = nxp_c45_mdo_del_secy, + .mdo_add_rxsc = nxp_c45_mdo_add_rxsc, + .mdo_upd_rxsc = nxp_c45_mdo_upd_rxsc, + .mdo_del_rxsc = nxp_c45_mdo_del_rxsc, + .mdo_add_rxsa = nxp_c45_mdo_add_rxsa, + .mdo_upd_rxsa = nxp_c45_mdo_upd_rxsa, + .mdo_del_rxsa = nxp_c45_mdo_del_rxsa, + .mdo_add_txsa = nxp_c45_mdo_add_txsa, + .mdo_upd_txsa = nxp_c45_mdo_upd_txsa, + .mdo_del_txsa = nxp_c45_mdo_del_txsa, + .mdo_get_dev_stats = nxp_c45_mdo_get_dev_stats, + .mdo_get_tx_sc_stats = nxp_c45_mdo_get_tx_sc_stats, + .mdo_get_tx_sa_stats = nxp_c45_mdo_get_tx_sa_stats, + .mdo_get_rx_sc_stats = nxp_c45_mdo_get_rx_sc_stats, + .mdo_get_rx_sa_stats = nxp_c45_mdo_get_rx_sa_stats, + .mdo_insert_tx_tag = nxp_c45_mdo_insert_tx_tag, + .needed_headroom = TJA11XX_TLV_TX_NEEDED_HEADROOM, + .needed_tailroom = TJA11XX_TLV_NEEDED_TAILROOM, +}; + +int nxp_c45_macsec_config_init(struct phy_device *phydev) +{ + struct nxp_c45_phy *priv = phydev->priv; + int ret; + + if (!priv->macsec) + return 0; + + ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_PORT_FUNC_ENABLES, + MACSEC_EN | ADAPTER_EN); + if (ret) + return ret; + + ret = nxp_c45_macsec_write(phydev, ADPTR_CNTRL, ADPTR_CNTRL_CONFIG_EN | + ADPTR_CNTRL_ADPTR_EN); + if (ret) + return ret; + + ret = nxp_c45_macsec_write(phydev, ADPTR_TX_TAG_CNTRL, + ADPTR_TX_TAG_CNTRL_ENA); + if (ret) + return ret; + + ret = nxp_c45_macsec_write(phydev, ADPTR_CNTRL, ADPTR_CNTRL_ADPTR_EN); + if (ret) + return ret; + + ret = nxp_c45_macsec_write(phydev, MACSEC_TPNET, PN_WRAP_THRESHOLD); + if (ret) + return ret; + + /* Set MKA filter. */ + ret = nxp_c45_macsec_write(phydev, MACSEC_UPFR0D2, ETH_P_PAE); + if (ret) + return ret; + + ret = nxp_c45_macsec_write(phydev, MACSEC_UPFR0M1, MACSEC_OVP); + if (ret) + return ret; + + ret = nxp_c45_macsec_write(phydev, MACSEC_UPFR0M2, ETYPE_MASK); + if (ret) + return ret; + + ret = nxp_c45_macsec_write(phydev, MACSEC_UPFR0R, MACSEC_UPFR_EN); + + return ret; +} + +int nxp_c45_macsec_probe(struct phy_device *phydev) +{ + struct nxp_c45_phy *priv = phydev->priv; + struct device *dev = &phydev->mdio.dev; + + priv->macsec = devm_kzalloc(dev, sizeof(*priv->macsec), GFP_KERNEL); + if (!priv->macsec) + return -ENOMEM; + + INIT_LIST_HEAD(&priv->macsec->secy_list); + phydev->macsec_ops = &nxp_c45_macsec_ops; + + return 0; +} + +void nxp_c45_macsec_remove(struct phy_device *phydev) +{ + struct nxp_c45_phy *priv = phydev->priv; + struct nxp_c45_secy *secy_p, *secy_t; + struct nxp_c45_sa *sa_p, *sa_t; + struct list_head *secy_list; + + if (!priv->macsec) + return; + + secy_list = &priv->macsec->secy_list; + nxp_c45_macsec_en(phydev, false); + + list_for_each_entry_safe(secy_p, secy_t, secy_list, list) { + list_for_each_entry_safe(sa_p, sa_t, &secy_p->sa_list, list) + nxp_c45_sa_free(sa_p); + nxp_c45_secy_free(secy_p); + } +} + +void nxp_c45_handle_macsec_interrupt(struct phy_device *phydev, + irqreturn_t *ret) +{ + struct nxp_c45_phy *priv = phydev->priv; + struct nxp_c45_secy *secy; + struct nxp_c45_sa *sa; + u8 encoding_sa; + int secy_id; + u32 reg = 0; + + if (!priv->macsec) + return; + + do { + nxp_c45_macsec_read(phydev, MACSEC_EVR, ®); + if (!reg) + return; + + secy_id = MACSEC_REG_SIZE - ffs(reg); + secy = nxp_c45_find_secy_by_id(&priv->macsec->secy_list, + secy_id); + if (IS_ERR(secy)) { + WARN_ON(1); + goto macsec_ack_irq; + } + + encoding_sa = secy->secy->tx_sc.encoding_sa; + phydev_dbg(phydev, "pn_wrapped: TX SC %d, encoding_sa %u\n", + secy->secy_id, encoding_sa); + + sa = nxp_c45_find_sa(&secy->sa_list, TX_SA, encoding_sa); + if (!IS_ERR(sa)) + macsec_pn_wrapped(secy->secy, sa->sa); + else + WARN_ON(1); + +macsec_ack_irq: + nxp_c45_macsec_write(phydev, MACSEC_EVR, + TX_SC_BIT(secy_id)); + *ret = IRQ_HANDLED; + } while (reg); +} diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c index 780ad353cf55..3cf614b4cd52 100644 --- a/drivers/net/phy/nxp-c45-tja11xx.c +++ b/drivers/net/phy/nxp-c45-tja11xx.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* NXP C45 PHY driver - * Copyright (C) 2021 NXP + * Copyright 2021-2023 NXP * Author: Radu Pirea <[email protected]> */ @@ -14,9 +14,10 @@ #include <linux/processor.h> #include <linux/property.h> #include <linux/ptp_classify.h> -#include <linux/ptp_clock_kernel.h> #include <linux/net_tstamp.h> +#include "nxp-c45-tja11xx.h" + #define PHY_ID_TJA_1103 0x001BB010 #define PHY_ID_TJA_1120 0x001BB031 @@ -75,9 +76,11 @@ #define PORT_CONTROL_EN BIT(14) #define VEND1_PORT_ABILITIES 0x8046 +#define MACSEC_ABILITY BIT(5) #define PTP_ABILITY BIT(3) #define VEND1_PORT_FUNC_IRQ_EN 0x807A +#define MACSEC_IRQS BIT(5) #define PTP_IRQS BIT(3) #define VEND1_PTP_IRQ_ACK 0x9008 @@ -148,7 +151,6 @@ #define TS_SEC_MASK GENMASK(1, 0) -#define VEND1_PORT_FUNC_ENABLES 0x8048 #define PTP_ENABLE BIT(3) #define PHY_TEST_ENABLE BIT(0) @@ -281,25 +283,6 @@ struct nxp_c45_phy_data { irqreturn_t *irq_status); }; -struct nxp_c45_phy { - const struct nxp_c45_phy_data *phy_data; - struct phy_device *phydev; - struct mii_timestamper mii_ts; - struct ptp_clock *ptp_clock; - struct ptp_clock_info caps; - struct sk_buff_head tx_queue; - struct sk_buff_head rx_queue; - /* used to access the PTP registers atomic */ - struct mutex ptp_lock; - int hwts_tx; - int hwts_rx; - u32 tx_delay; - u32 rx_delay; - struct timespec64 extts_ts; - int extts_index; - bool extts; -}; - static const struct nxp_c45_phy_data *nxp_c45_get_data(struct phy_device *phydev) { @@ -1215,12 +1198,25 @@ static int nxp_c45_start_op(struct phy_device *phydev) static int nxp_c45_config_intr(struct phy_device *phydev) { - if (phydev->interrupts == PHY_INTERRUPT_ENABLED) + int ret; + + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { + ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, + VEND1_PORT_FUNC_IRQ_EN, MACSEC_IRQS); + if (ret) + return ret; + return phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_PHY_IRQ_EN, PHY_IRQ_LINK_EVENT); - else - return phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, - VEND1_PHY_IRQ_EN, PHY_IRQ_LINK_EVENT); + } + + ret = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, + VEND1_PORT_FUNC_IRQ_EN, MACSEC_IRQS); + if (ret) + return ret; + + return phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, + VEND1_PHY_IRQ_EN, PHY_IRQ_LINK_EVENT); } static int tja1103_config_intr(struct phy_device *phydev) @@ -1286,6 +1282,7 @@ static irqreturn_t nxp_c45_handle_interrupt(struct phy_device *phydev) } data->nmi_handler(phydev, &ret); + nxp_c45_handle_macsec_interrupt(phydev, &ret); return ret; } @@ -1611,6 +1608,9 @@ static int nxp_c45_config_init(struct phy_device *phydev) nxp_c45_counters_enable(phydev); nxp_c45_ptp_init(phydev); + ret = nxp_c45_macsec_config_init(phydev); + if (ret) + return ret; return nxp_c45_start_op(phydev); } @@ -1626,7 +1626,9 @@ static int nxp_c45_get_features(struct phy_device *phydev) static int nxp_c45_probe(struct phy_device *phydev) { struct nxp_c45_phy *priv; - int ptp_ability; + bool macsec_ability; + int phy_abilities; + bool ptp_ability; int ret = 0; priv = devm_kzalloc(&phydev->mdio.dev, sizeof(*priv), GFP_KERNEL); @@ -1642,9 +1644,9 @@ static int nxp_c45_probe(struct phy_device *phydev) mutex_init(&priv->ptp_lock); - ptp_ability = phy_read_mmd(phydev, MDIO_MMD_VEND1, - VEND1_PORT_ABILITIES); - ptp_ability = !!(ptp_ability & PTP_ABILITY); + phy_abilities = phy_read_mmd(phydev, MDIO_MMD_VEND1, + VEND1_PORT_ABILITIES); + ptp_ability = !!(phy_abilities & PTP_ABILITY); if (!ptp_ability) { phydev_dbg(phydev, "the phy does not support PTP"); goto no_ptp_support; @@ -1663,6 +1665,20 @@ static int nxp_c45_probe(struct phy_device *phydev) } no_ptp_support: + macsec_ability = !!(phy_abilities & MACSEC_ABILITY); + if (!macsec_ability) { + phydev_info(phydev, "the phy does not support MACsec\n"); + goto no_macsec_support; + } + + if (IS_ENABLED(CONFIG_MACSEC)) { + ret = nxp_c45_macsec_probe(phydev); + phydev_dbg(phydev, "MACsec support enabled."); + } else { + phydev_dbg(phydev, "MACsec support not enabled even if the phy supports it"); + } + +no_macsec_support: return ret; } @@ -1676,6 +1692,7 @@ static void nxp_c45_remove(struct phy_device *phydev) skb_queue_purge(&priv->tx_queue); skb_queue_purge(&priv->rx_queue); + nxp_c45_macsec_remove(phydev); } static void tja1103_counters_enable(struct phy_device *phydev) diff --git a/drivers/net/phy/nxp-c45-tja11xx.h b/drivers/net/phy/nxp-c45-tja11xx.h new file mode 100644 index 000000000000..f364fca68f0b --- /dev/null +++ b/drivers/net/phy/nxp-c45-tja11xx.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* NXP C45 PHY driver header file + * Copyright 2023 NXP + * Author: Radu Pirea <[email protected]> + */ + +#include <linux/ptp_clock_kernel.h> + +#define VEND1_PORT_FUNC_ENABLES 0x8048 + +struct nxp_c45_macsec; + +struct nxp_c45_phy { + const struct nxp_c45_phy_data *phy_data; + struct phy_device *phydev; + struct mii_timestamper mii_ts; + struct ptp_clock *ptp_clock; + struct ptp_clock_info caps; + struct sk_buff_head tx_queue; + struct sk_buff_head rx_queue; + /* used to access the PTP registers atomic */ + struct mutex ptp_lock; + int hwts_tx; + int hwts_rx; + u32 tx_delay; + u32 rx_delay; + struct timespec64 extts_ts; + int extts_index; + bool extts; + struct nxp_c45_macsec *macsec; +}; + +#if IS_ENABLED(CONFIG_MACSEC) +int nxp_c45_macsec_config_init(struct phy_device *phydev); +int nxp_c45_macsec_probe(struct phy_device *phydev); +void nxp_c45_macsec_remove(struct phy_device *phydev); +void nxp_c45_handle_macsec_interrupt(struct phy_device *phydev, + irqreturn_t *ret); +#else +static inline +int nxp_c45_macsec_config_init(struct phy_device *phydev) +{ + return 0; +} + +static inline +int nxp_c45_macsec_probe(struct phy_device *phydev) +{ + return 0; +} + +static inline +void nxp_c45_macsec_remove(struct phy_device *phydev) +{ +} + +static inline +void nxp_c45_handle_macsec_interrupt(struct phy_device *phydev, + irqreturn_t *ret) +{ +} +#endif diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 3780a96d2caa..f75c9eb3958e 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -274,6 +274,7 @@ struct sfp { struct sfp_eeprom_id id; unsigned int module_power_mW; unsigned int module_t_start_up; + unsigned int module_t_wait; unsigned int phy_t_retry; unsigned int rate_kbd; @@ -388,6 +389,12 @@ static void sfp_fixup_fs_10gt(struct sfp *sfp) { sfp_fixup_10gbaset_30m(sfp); sfp_fixup_rollball(sfp); + + /* The RollBall fixup is not enough for FS modules, the AQR chip inside + * them does not return 0xffff for PHY ID registers in all MMDs for the + * while initializing. They need a 4 second wait before accessing PHY. + */ + sfp->module_t_wait = msecs_to_jiffies(4000); } static void sfp_fixup_halny_gsfp(struct sfp *sfp) @@ -2329,6 +2336,7 @@ static int sfp_sm_mod_probe(struct sfp *sfp, bool report) mask |= SFP_F_RS1; sfp->module_t_start_up = T_START_UP; + sfp->module_t_wait = T_WAIT; sfp->phy_t_retry = T_PHY_RETRY; sfp->state_ignore_mask = 0; @@ -2566,9 +2574,10 @@ static void sfp_sm_main(struct sfp *sfp, unsigned int event) /* We need to check the TX_FAULT state, which is not defined * while TX_DISABLE is asserted. The earliest we want to do - * anything (such as probe for a PHY) is 50ms. + * anything (such as probe for a PHY) is 50ms (or more on + * specific modules). */ - sfp_sm_next(sfp, SFP_S_WAIT, T_WAIT); + sfp_sm_next(sfp, SFP_S_WAIT, sfp->module_t_wait); break; case SFP_S_WAIT: @@ -2582,8 +2591,8 @@ static void sfp_sm_main(struct sfp *sfp, unsigned int event) * deasserting. */ timeout = sfp->module_t_start_up; - if (timeout > T_WAIT) - timeout -= T_WAIT; + if (timeout > sfp->module_t_wait) + timeout -= sfp->module_t_wait; else timeout = 1; diff --git a/drivers/s390/net/ism.h b/drivers/s390/net/ism.h index 70c5bbda0fea..047fa6101555 100644 --- a/drivers/s390/net/ism.h +++ b/drivers/s390/net/ism.h @@ -16,7 +16,6 @@ */ #define ISM_DMB_WORD_OFFSET 1 #define ISM_DMB_BIT_OFFSET (ISM_DMB_WORD_OFFSET * 32) -#define ISM_IDENT_MASK 0x00FFFF #define ISM_REG_SBA 0x1 #define ISM_REG_IEQ 0x2 @@ -192,12 +191,6 @@ struct ism_sba { #define ISM_CREATE_REQ(dmb, idx, sf, offset) \ ((dmb) | (idx) << 24 | (sf) << 23 | (offset)) -struct ism_systemeid { - u8 seid_string[24]; - u8 serial_number[4]; - u8 type[4]; -}; - static inline void __ism_read_cmd(struct ism_dev *ism, void *data, unsigned long offset, unsigned long len) { diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c index 81aabbfbbe2c..2c8e964425dc 100644 --- a/drivers/s390/net/ism_drv.c +++ b/drivers/s390/net/ism_drv.c @@ -36,6 +36,7 @@ static struct ism_client *clients[MAX_CLIENTS]; /* use an array rather than */ /* a list for fast mapping */ static u8 max_client; static DEFINE_MUTEX(clients_lock); +static bool ism_v2_capable; struct ism_dev_list { struct list_head list; struct mutex mutex; /* protects ism device list */ @@ -443,32 +444,6 @@ int ism_move(struct ism_dev *ism, u64 dmb_tok, unsigned int idx, bool sf, } EXPORT_SYMBOL_GPL(ism_move); -static struct ism_systemeid SYSTEM_EID = { - .seid_string = "IBM-SYSZ-ISMSEID00000000", - .serial_number = "0000", - .type = "0000", -}; - -static void ism_create_system_eid(void) -{ - struct cpuid id; - u16 ident_tail; - char tmp[5]; - - get_cpu_id(&id); - ident_tail = (u16)(id.ident & ISM_IDENT_MASK); - snprintf(tmp, 5, "%04X", ident_tail); - memcpy(&SYSTEM_EID.serial_number, tmp, 4); - snprintf(tmp, 5, "%04X", id.machine); - memcpy(&SYSTEM_EID.type, tmp, 4); -} - -u8 *ism_get_seid(void) -{ - return SYSTEM_EID.seid_string; -} -EXPORT_SYMBOL_GPL(ism_get_seid); - static void ism_handle_event(struct ism_dev *ism) { struct ism_event *entry; @@ -560,7 +535,9 @@ static int ism_dev_init(struct ism_dev *ism) if (!ism_add_vlan_id(ism, ISM_RESERVED_VLANID)) /* hardware is V2 capable */ - ism_create_system_eid(); + ism_v2_capable = true; + else + ism_v2_capable = false; mutex_lock(&ism_dev_list.mutex); mutex_lock(&clients_lock); @@ -665,8 +642,7 @@ static void ism_dev_exit(struct ism_dev *ism) } mutex_unlock(&clients_lock); - if (SYSTEM_EID.serial_number[0] != '0' || - SYSTEM_EID.type[0] != '0') + if (ism_v2_capable) ism_del_vlan_id(ism, ISM_RESERVED_VLANID); unregister_ieq(ism); unregister_sba(ism); @@ -743,10 +719,10 @@ static int ism_query_rgid(struct ism_dev *ism, u64 rgid, u32 vid_valid, return ism_cmd(ism, &cmd); } -static int smcd_query_rgid(struct smcd_dev *smcd, u64 rgid, u32 vid_valid, - u32 vid) +static int smcd_query_rgid(struct smcd_dev *smcd, struct smcd_gid *rgid, + u32 vid_valid, u32 vid) { - return ism_query_rgid(smcd->priv, rgid, vid_valid, vid); + return ism_query_rgid(smcd->priv, rgid->gid, vid_valid, vid); } static int smcd_register_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb, @@ -797,10 +773,11 @@ static int ism_signal_ieq(struct ism_dev *ism, u64 rgid, u32 trigger_irq, return ism_cmd(ism, &cmd); } -static int smcd_signal_ieq(struct smcd_dev *smcd, u64 rgid, u32 trigger_irq, - u32 event_code, u64 info) +static int smcd_signal_ieq(struct smcd_dev *smcd, struct smcd_gid *rgid, + u32 trigger_irq, u32 event_code, u64 info) { - return ism_signal_ieq(smcd->priv, rgid, trigger_irq, event_code, info); + return ism_signal_ieq(smcd->priv, rgid->gid, + trigger_irq, event_code, info); } static int smcd_move(struct smcd_dev *smcd, u64 dmb_tok, unsigned int idx, @@ -812,8 +789,7 @@ static int smcd_move(struct smcd_dev *smcd, u64 dmb_tok, unsigned int idx, static int smcd_supports_v2(void) { - return SYSTEM_EID.serial_number[0] != '0' || - SYSTEM_EID.type[0] != '0'; + return ism_v2_capable; } static u64 ism_get_local_gid(struct ism_dev *ism) @@ -821,9 +797,11 @@ static u64 ism_get_local_gid(struct ism_dev *ism) return ism->local_gid; } -static u64 smcd_get_local_gid(struct smcd_dev *smcd) +static void smcd_get_local_gid(struct smcd_dev *smcd, + struct smcd_gid *smcd_gid) { - return ism_get_local_gid(smcd->priv); + smcd_gid->gid = ism_get_local_gid(smcd->priv); + smcd_gid->gid_ext = 0; } static u16 ism_get_chid(struct ism_dev *ism) @@ -857,7 +835,6 @@ static const struct smcd_ops ism_ops = { .signal_event = smcd_signal_ieq, .move_data = smcd_move, .supports_v2 = smcd_supports_v2, - .get_system_eid = ism_get_seid, .get_local_gid = smcd_get_local_gid, .get_chid = smcd_get_chid, .get_dev = smcd_get_dev, diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index a44d9dc7e3eb..8e177b67e82f 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -5,6 +5,7 @@ #define _VIRTCHNL_H_ #include <linux/bitops.h> +#include <linux/bits.h> #include <linux/overflow.h> #include <uapi/linux/if_ether.h> diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7a8d4c81a39a..7671530d6e4e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2466,12 +2466,7 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, struct btf_func_model *m); struct bpf_reg_state; -int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog, - struct bpf_reg_state *regs); -int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, - struct bpf_reg_state *regs); -int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, - struct bpf_reg_state *reg, u32 *nargs); +int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog); int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog, struct btf *btf, const struct btf_type *t); const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt, diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index c2819a6579a5..d07d857ca67f 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -606,6 +606,13 @@ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) #define BPF_MAX_SUBPROGS 256 +struct bpf_subprog_arg_info { + enum bpf_arg_type arg_type; + union { + u32 mem_size; + }; +}; + struct bpf_subprog_info { /* 'start' has to be the first field otherwise find_subprog() won't work */ u32 start; /* insn idx of function entry point */ @@ -617,6 +624,10 @@ struct bpf_subprog_info { bool is_cb: 1; bool is_async_cb: 1; bool is_exception_cb: 1; + bool args_cached: 1; + + u8 arg_cnt; + struct bpf_subprog_arg_info args[MAX_BPF_FUNC_REG_ARGS]; }; struct bpf_verifier_env; @@ -727,6 +738,16 @@ struct bpf_verifier_env { char tmp_str_buf[TMP_STR_BUF_LEN]; }; +static inline struct bpf_func_info_aux *subprog_aux(struct bpf_verifier_env *env, int subprog) +{ + return &env->prog->aux->func_info_aux[subprog]; +} + +static inline struct bpf_subprog_info *subprog_info(struct bpf_verifier_env *env, int subprog) +{ + return &env->subprog_info[subprog]; +} + __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, va_list args); __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env, @@ -764,14 +785,6 @@ bpf_prog_offload_replace_insn(struct bpf_verifier_env *env, u32 off, void bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt); -int check_ptr_off_reg(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg, int regno); -int check_func_arg_reg_off(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg, int regno, - enum bpf_arg_type arg_type); -int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, - u32 regno, u32 mem_size); - /* this lives here instead of in bpf.h because it needs to dereference tgt_prog */ static inline u64 bpf_trampoline_compute_key(const struct bpf_prog *tgt_prog, struct btf *btf, u32 btf_id) diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index cfcd952a1d4f..325e0778e937 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -411,8 +411,10 @@ struct ethtool_pause_stats { * not entire FEC data blocks. This is a non-standard statistic. * Reported to user space as %ETHTOOL_A_FEC_STAT_CORR_BITS. * - * @lane: per-lane/PCS-instance counts as defined by the standard - * @total: error counts for the entire port, for drivers incapable of reporting + * For each of the above fields, the two substructure members are: + * + * - @lanes: per-lane/PCS-instance counts as defined by the standard + * - @total: error counts for the entire port, for drivers incapable of reporting * per-lane stats * * Drivers should fill in either only total or per-lane statistics, core diff --git a/include/linux/ism.h b/include/linux/ism.h index 9a4c204df3da..5428edd90982 100644 --- a/include/linux/ism.h +++ b/include/linux/ism.h @@ -86,7 +86,6 @@ int ism_register_dmb(struct ism_dev *dev, struct ism_dmb *dmb, int ism_unregister_dmb(struct ism_dev *dev, struct ism_dmb *dmb); int ism_move(struct ism_dev *dev, u64 dmb_tok, unsigned int idx, bool sf, unsigned int offset, void *data, unsigned int size); -u8 *ism_get_seid(void); const struct smcd_ops *ism_get_smcd_ops(void); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 7ee5b79ff3d6..2bba88c67f58 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -681,6 +681,7 @@ struct mlx5e_resources { struct mlx5_sq_bfreg bfreg; #define MLX5_MAX_NUM_TC 8 u32 tisn[MLX5_MAX_PORTS][MLX5_MAX_NUM_TC]; + bool tisn_valid; } hw_objs; struct net_device *uplink_netdev; struct mutex uplink_netdev_lock; @@ -821,6 +822,7 @@ struct mlx5_core_dev { struct blocking_notifier_head macsec_nh; #endif u64 num_ipsec_offloads; + struct mlx5_sd *sd; }; struct mlx5_db { @@ -1222,6 +1224,14 @@ static inline bool mlx5_core_is_ecpf(const struct mlx5_core_dev *dev) return dev->caps.embedded_cpu; } +static inline bool mlx5_core_is_mgmt_pf(const struct mlx5_core_dev *dev) +{ + if (!MLX5_CAP_GEN_2(dev, local_mng_port_valid)) + return false; + + return MLX5_CAP_GEN_2(dev, local_mng_port); +} + static inline bool mlx5_core_is_ecpf_esw_manager(const struct mlx5_core_dev *dev) { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index fee20fc010c2..586569209254 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1954,8 +1954,10 @@ enum { struct mlx5_ifc_cmd_hca_cap_2_bits { u8 reserved_at_0[0x80]; - u8 migratable[0x1]; - u8 reserved_at_81[0x1f]; + u8 migratable[0x1]; + u8 reserved_at_81[0x19]; + u8 local_mng_port[0x1]; + u8 reserved_at_9b[0x5]; u8 max_reformat_insert_size[0x8]; u8 max_reformat_insert_offset[0x8]; @@ -1973,7 +1975,13 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 allowed_object_for_other_vhca_access[0x40]; - u8 reserved_at_140[0x60]; + u8 reserved_at_140[0x20]; + + u8 reserved_at_160[0xa]; + u8 local_mng_port_valid[0x1]; + u8 reserved_at_16b[0x15]; + + u8 reserved_at_180[0x20]; u8 flow_table_type_2_type[0x8]; u8 reserved_at_1a8[0x3]; @@ -4030,8 +4038,13 @@ struct mlx5_ifc_nic_vport_context_bits { u8 affiliation_criteria[0x4]; u8 affiliated_vhca_id[0x10]; - u8 reserved_at_60[0xd0]; + u8 reserved_at_60[0xa0]; + u8 reserved_at_100[0x1]; + u8 sd_group[0x3]; + u8 reserved_at_104[0x1c]; + + u8 reserved_at_120[0x10]; u8 mtu[0x10]; u8 system_image_guid[0x40]; @@ -10116,8 +10129,7 @@ struct mlx5_ifc_mpir_reg_bits { u8 reserved_at_20[0x20]; u8 local_port[0x8]; - u8 reserved_at_28[0x15]; - u8 sd_group[0x3]; + u8 reserved_at_28[0x18]; u8 reserved_at_60[0x20]; }; diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index fbb9bf447889..c36cc6d82926 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -72,6 +72,7 @@ int mlx5_query_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 *mtu); int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu); int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev, u64 *system_image_guid); +int mlx5_query_nic_vport_sd_group(struct mlx5_core_dev *mdev, u8 *sd_group); int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid); int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev, u16 vport, u64 node_guid); diff --git a/include/linux/phy.h b/include/linux/phy.h index e9e85d347587..ede891776d8b 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -434,6 +434,9 @@ struct mii_bus { /** @shared: shared state across different PHYs */ struct phy_package_shared *shared[PHY_MAX_ADDR]; + + /** @__unregister_callback: called at the last step of unregistration */ + void (*__unregister_callback)(struct mii_bus *bus); }; #define to_mii_bus(d) container_of(d, struct mii_bus, dev) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ea5c8ab3ed00..a5ae952454c8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -754,7 +754,6 @@ typedef unsigned char *sk_buff_data_t; * @dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL * @cb: Control buffer. Free for use by every layer. Put private vars here * @_skb_refdst: destination entry (with norefcount bit) - * @sp: the security path, used for xfrm * @len: Length of actual data * @data_len: Data length * @mac_len: Length of link layer header @@ -788,7 +787,6 @@ typedef unsigned char *sk_buff_data_t; * @tcp_tsorted_anchor: list structure for TCP (tp->tsorted_sent_queue) * @_sk_redir: socket redirection information for skmsg * @_nfct: Associated connection, if any (with nfctinfo bits) - * @nf_bridge: Saved data about a bridged frame - see br_netfilter.c * @skb_iif: ifindex of device we arrived on * @tc_index: Traffic control index * @hash: the packet hash @@ -4009,6 +4007,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features unsigned int offset); struct sk_buff *skb_vlan_untag(struct sk_buff *skb); int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len); +int skb_ensure_writable_head_tail(struct sk_buff *skb, struct net_device *dev); int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 85c63d4f16dd..e61469129402 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -8,16 +8,19 @@ #define GENLMSG_DEFAULT_SIZE (NLMSG_DEFAULT_SIZE - GENL_HDRLEN) +/* Binding to multicast group requires %CAP_NET_ADMIN */ +#define GENL_MCAST_CAP_NET_ADMIN BIT(0) +/* Binding to multicast group requires %CAP_SYS_ADMIN */ +#define GENL_MCAST_CAP_SYS_ADMIN BIT(1) + /** * struct genl_multicast_group - generic netlink multicast group * @name: name of the multicast group, names are per-family - * @flags: GENL_* flags (%GENL_ADMIN_PERM or %GENL_UNS_ADMIN_PERM) - * @cap_sys_admin: whether %CAP_SYS_ADMIN is required for binding + * @flags: GENL_MCAST_* flags */ struct genl_multicast_group { char name[GENL_NAMSIZ]; u8 flags; - u8 cap_sys_admin:1; }; struct genl_split_ops; diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 3ecfeadbfa06..7f1b38458743 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -88,7 +88,7 @@ struct inet_bind_bucket { unsigned short fast_sk_family; bool fast_ipv6_only; struct hlist_node node; - struct hlist_head owners; + struct hlist_head bhash2; }; struct inet_bind2_bucket { @@ -96,22 +96,17 @@ struct inet_bind2_bucket { int l3mdev; unsigned short port; #if IS_ENABLED(CONFIG_IPV6) - unsigned short family; -#endif - union { -#if IS_ENABLED(CONFIG_IPV6) - struct in6_addr v6_rcv_saddr; + unsigned short addr_type; + struct in6_addr v6_rcv_saddr; +#define rcv_saddr v6_rcv_saddr.s6_addr32[3] +#else + __be32 rcv_saddr; #endif - __be32 rcv_saddr; - }; /* Node in the bhash2 inet_bind_hashbucket chain */ struct hlist_node node; + struct hlist_node bhash_node; /* List of sockets hashed to this bucket */ struct hlist_head owners; - /* bhash has twsk in owners, but bhash2 has twsk in - * deathrow not to add a member in struct sock_common. - */ - struct hlist_head deathrow; }; static inline struct net *ib_net(const struct inet_bind_bucket *ib) @@ -241,7 +236,7 @@ bool inet_bind_bucket_match(const struct inet_bind_bucket *tb, struct inet_bind2_bucket * inet_bind2_bucket_create(struct kmem_cache *cachep, struct net *net, struct inet_bind_hashbucket *head, - unsigned short port, int l3mdev, + struct inet_bind_bucket *tb, const struct sock *sk); void inet_bind2_bucket_destroy(struct kmem_cache *cachep, diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index b14999ff55db..f28da08a37b4 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -75,13 +75,9 @@ struct inet_timewait_sock { struct timer_list tw_timer; struct inet_bind_bucket *tw_tb; struct inet_bind2_bucket *tw_tb2; - struct hlist_node tw_bind2_node; }; #define tw_tclass tw_tos -#define twsk_for_each_bound_bhash2(__tw, list) \ - hlist_for_each_entry(__tw, list, tw_bind2_node) - static inline struct inet_timewait_sock *inet_twsk(const struct sock *sk) { return (struct inet_timewait_sock *)sk; diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 78d38dd88aba..cf25ea21d770 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -784,11 +784,6 @@ static inline bool ipv6_addr_v4mapped(const struct in6_addr *a) cpu_to_be32(0x0000ffff))) == 0UL; } -static inline bool ipv6_addr_v4mapped_any(const struct in6_addr *a) -{ - return ipv6_addr_v4mapped(a) && ipv4_is_zeronet(a->s6_addr32[3]); -} - static inline bool ipv6_addr_v4mapped_loopback(const struct in6_addr *a) { return ipv6_addr_v4mapped(a) && ipv4_is_loopback(a->s6_addr32[3]); diff --git a/include/net/iucv/iucv.h b/include/net/iucv/iucv.h index f9e88401d7da..8b2055d64a6b 100644 --- a/include/net/iucv/iucv.h +++ b/include/net/iucv/iucv.h @@ -80,7 +80,7 @@ struct iucv_array { u32 length; } __attribute__ ((aligned (8))); -extern struct bus_type iucv_bus; +extern const struct bus_type iucv_bus; extern struct device *iucv_root; /* @@ -489,7 +489,7 @@ struct iucv_interface { int (*path_sever)(struct iucv_path *path, u8 userdata[16]); int (*iucv_register)(struct iucv_handler *handler, int smp); void (*iucv_unregister)(struct iucv_handler *handler, int smp); - struct bus_type *bus; + const struct bus_type *bus; struct device *root; }; diff --git a/include/net/macsec.h b/include/net/macsec.h index ebf9bc54036a..dbd22180cc5c 100644 --- a/include/net/macsec.h +++ b/include/net/macsec.h @@ -247,6 +247,23 @@ struct macsec_secy { /** * struct macsec_context - MACsec context for hardware offloading + * @netdev: a valid pointer to a struct net_device if @offload == + * MACSEC_OFFLOAD_MAC + * @phydev: a valid pointer to a struct phy_device if @offload == + * MACSEC_OFFLOAD_PHY + * @offload: MACsec offload status + * @secy: pointer to a MACsec SecY + * @rx_sc: pointer to a RX SC + * @update_pn: when updating the SA, update the next PN + * @assoc_num: association number of the target SA + * @key: key of the target SA + * @rx_sa: pointer to an RX SA if a RX SA is added/updated/removed + * @tx_sa: pointer to an TX SA if a TX SA is added/updated/removed + * @tx_sc_stats: pointer to TX SC stats structure + * @tx_sa_stats: pointer to TX SA stats structure + * @rx_sc_stats: pointer to RX SC stats structure + * @rx_sa_stats: pointer to RX SA stats structure + * @dev_stats: pointer to dev stats structure */ struct macsec_context { union { @@ -277,6 +294,33 @@ struct macsec_context { /** * struct macsec_ops - MACsec offloading operations + * @mdo_dev_open: called when the MACsec interface transitions to the up state + * @mdo_dev_stop: called when the MACsec interface transitions to the down + * state + * @mdo_add_secy: called when a new SecY is added + * @mdo_upd_secy: called when the SecY flags are changed or the MAC address of + * the MACsec interface is changed + * @mdo_del_secy: called when the hw offload is disabled or the MACsec + * interface is removed + * @mdo_add_rxsc: called when a new RX SC is added + * @mdo_upd_rxsc: called when a certain RX SC is updated + * @mdo_del_rxsc: called when a certain RX SC is removed + * @mdo_add_rxsa: called when a new RX SA is added + * @mdo_upd_rxsa: called when a certain RX SA is updated + * @mdo_del_rxsa: called when a certain RX SA is removed + * @mdo_add_txsa: called when a new TX SA is added + * @mdo_upd_txsa: called when a certain TX SA is updated + * @mdo_del_txsa: called when a certain TX SA is removed + * @mdo_get_dev_stats: called when dev stats are read + * @mdo_get_tx_sc_stats: called when TX SC stats are read + * @mdo_get_tx_sa_stats: called when TX SA stats are read + * @mdo_get_rx_sc_stats: called when RX SC stats are read + * @mdo_get_rx_sa_stats: called when RX SA stats are read + * @mdo_insert_tx_tag: called to insert the TX tag + * @needed_headroom: number of bytes reserved at the beginning of the sk_buff + * for the TX tag + * @needed_tailroom: number of bytes reserved at the end of the sk_buff for the + * TX tag */ struct macsec_ops { /* Device wide */ @@ -303,6 +347,11 @@ struct macsec_ops { int (*mdo_get_tx_sa_stats)(struct macsec_context *ctx); int (*mdo_get_rx_sc_stats)(struct macsec_context *ctx); int (*mdo_get_rx_sa_stats)(struct macsec_context *ctx); + /* Offload tag */ + int (*mdo_insert_tx_tag)(struct phy_device *phydev, + struct sk_buff *skb); + unsigned int needed_headroom; + unsigned int needed_tailroom; }; void macsec_pn_wrapped(struct macsec_secy *secy, struct macsec_tx_sa *tx_sa); @@ -325,4 +374,9 @@ static inline void *macsec_netdev_priv(const struct net_device *dev) return netdev_priv(dev); } +static inline u64 sci_to_cpu(sci_t sci) +{ + return be64_to_cpu((__force __be64)sci); +} + #endif /* _NET_MACSEC_H_ */ diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 1d70c2c1572f..ba3e1b315de8 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -19,6 +19,7 @@ #include <net/gen_stats.h> #include <net/rtnetlink.h> #include <net/flow_offload.h> +#include <linux/xarray.h> struct Qdisc_ops; struct qdisc_walker; @@ -456,6 +457,7 @@ struct tcf_chain { }; struct tcf_block { + struct xarray ports; /* datapath accessible */ /* Lock protects tcf_block and lifetime-management data of chains * attached to the block (refcnt, action_refcnt, explicitly_created). */ @@ -482,6 +484,8 @@ struct tcf_block { struct mutex proto_destroy_lock; /* Lock for proto_destroy hashtable. */ }; +struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index); + static inline bool lockdep_tcf_chain_is_locked(struct tcf_chain *chain) { return lockdep_is_held(&chain->filter_chain_lock); diff --git a/include/net/smc.h b/include/net/smc.h index a002552be29c..c9dcb30e3fd9 100644 --- a/include/net/smc.h +++ b/include/net/smc.h @@ -52,9 +52,14 @@ struct smcd_dmb { struct smcd_dev; struct ism_client; +struct smcd_gid { + u64 gid; + u64 gid_ext; +}; + struct smcd_ops { - int (*query_remote_gid)(struct smcd_dev *dev, u64 rgid, u32 vid_valid, - u32 vid); + int (*query_remote_gid)(struct smcd_dev *dev, struct smcd_gid *rgid, + u32 vid_valid, u32 vid); int (*register_dmb)(struct smcd_dev *dev, struct smcd_dmb *dmb, struct ism_client *client); int (*unregister_dmb)(struct smcd_dev *dev, struct smcd_dmb *dmb); @@ -62,14 +67,13 @@ struct smcd_ops { int (*del_vlan_id)(struct smcd_dev *dev, u64 vlan_id); int (*set_vlan_required)(struct smcd_dev *dev); int (*reset_vlan_required)(struct smcd_dev *dev); - int (*signal_event)(struct smcd_dev *dev, u64 rgid, u32 trigger_irq, - u32 event_code, u64 info); + int (*signal_event)(struct smcd_dev *dev, struct smcd_gid *rgid, + u32 trigger_irq, u32 event_code, u64 info); int (*move_data)(struct smcd_dev *dev, u64 dmb_tok, unsigned int idx, bool sf, unsigned int offset, void *data, unsigned int size); int (*supports_v2)(void); - u8* (*get_system_eid)(void); - u64 (*get_local_gid)(struct smcd_dev *dev); + void (*get_local_gid)(struct smcd_dev *dev, struct smcd_gid *gid); u16 (*get_chid)(struct smcd_dev *dev); struct device* (*get_dev)(struct smcd_dev *dev); }; diff --git a/include/net/sock.h b/include/net/sock.h index ba6642811db4..a7f815c7cfdf 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -76,19 +76,6 @@ * the other protocols. */ -/* Define this to get the SOCK_DBG debugging facility. */ -#define SOCK_DEBUGGING -#ifdef SOCK_DEBUGGING -#define SOCK_DEBUG(sk, msg...) do { if ((sk) && sock_flag((sk), SOCK_DBG)) \ - printk(KERN_DEBUG msg); } while (0) -#else -/* Validate arguments and do nothing */ -static inline __printf(2, 3) -void SOCK_DEBUG(const struct sock *sk, const char *msg, ...) -{ -} -#endif - /* This is the per-socket lock. The spinlock provides a synchronization * between user contexts and software interrupt processing, whereas the * mini-semaphore synchronizes multiple users amongst themselves. @@ -277,8 +264,6 @@ struct sk_filter; * @sk_pacing_status: Pacing status (requested, handled by sch_fq) * @sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE) * @sk_sndbuf: size of send buffer in bytes - * @__sk_flags_offset: empty field used to determine location of bitfield - * @sk_padding: unused element for alignment * @sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets * @sk_no_check_rx: allow zero checksum in RX packets * @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO) @@ -352,7 +337,6 @@ struct sk_filter; * @sk_txtime_report_errors: set report errors mode for SO_TXTIME * @sk_txtime_unused: unused txtime flags * @ns_tracker: tracker for netns reference - * @sk_bind2_node: bind node in the bhash2 table */ struct sock { /* @@ -544,7 +528,6 @@ struct sock { #endif struct rcu_head sk_rcu; netns_tracker ns_tracker; - struct hlist_node sk_bind2_node; }; enum sk_pacing { @@ -873,16 +856,6 @@ static inline void sk_add_bind_node(struct sock *sk, hlist_add_head(&sk->sk_bind_node, list); } -static inline void __sk_del_bind2_node(struct sock *sk) -{ - __hlist_del(&sk->sk_bind2_node); -} - -static inline void sk_add_bind2_node(struct sock *sk, struct hlist_head *list) -{ - hlist_add_head(&sk->sk_bind2_node, list); -} - #define sk_for_each(__sk, list) \ hlist_for_each_entry(__sk, list, sk_node) #define sk_for_each_rcu(__sk, list) \ @@ -900,8 +873,6 @@ static inline void sk_add_bind2_node(struct sock *sk, struct hlist_head *list) hlist_for_each_entry_safe(__sk, tmp, list, sk_node) #define sk_for_each_bound(__sk, list) \ hlist_for_each_entry(__sk, list, sk_bind_node) -#define sk_for_each_bound_bhash2(__sk, list) \ - hlist_for_each_entry(__sk, list, sk_bind2_node) /** * sk_for_each_entry_offset_rcu - iterate over a list at a given struct offset diff --git a/include/net/tc_act/tc_mirred.h b/include/net/tc_act/tc_mirred.h index 32ce8ea36950..75722d967bf2 100644 --- a/include/net/tc_act/tc_mirred.h +++ b/include/net/tc_act/tc_mirred.h @@ -8,6 +8,7 @@ struct tcf_mirred { struct tc_action common; int tcfm_eaction; + u32 tcfm_blockid; bool tcfm_mac_header_xmit; struct net_device __rcu *tcfm_dev; netdevice_tracker tcfm_dev_tracker; diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 0787d561ace0..85c412c23ab5 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -2139,18 +2139,6 @@ enum ethtool_reset_flags { * refused. For drivers: ignore this field (use kernel's * __ETHTOOL_LINK_MODE_MASK_NBITS instead), any change to it will * be overwritten by kernel. - * @supported: Bitmap with each bit meaning given by - * %ethtool_link_mode_bit_indices for the link modes, physical - * connectors and other link features for which the interface - * supports autonegotiation or auto-detection. Read-only. - * @advertising: Bitmap with each bit meaning given by - * %ethtool_link_mode_bit_indices for the link modes, physical - * connectors and other link features that are advertised through - * autonegotiation or enabled for auto-detection. - * @lp_advertising: Bitmap with each bit meaning given by - * %ethtool_link_mode_bit_indices for the link modes, and other - * link features that the link partner advertised through - * autonegotiation; 0 if unknown or not applicable. Read-only. * @transceiver: Used to distinguish different possible PHY types, * reported consistently by PHYLIB. Read-only. * @master_slave_cfg: Master/slave port mode. @@ -2192,6 +2180,21 @@ enum ethtool_reset_flags { * %set_link_ksettings() should validate all fields other than @cmd * and @link_mode_masks_nwords that are not described as read-only or * deprecated, and must ignore all fields described as read-only. + * + * @link_mode_masks is divided into three bitfields, each of length + * @link_mode_masks_nwords: + * - supported: Bitmap with each bit meaning given by + * %ethtool_link_mode_bit_indices for the link modes, physical + * connectors and other link features for which the interface + * supports autonegotiation or auto-detection. Read-only. + * - advertising: Bitmap with each bit meaning given by + * %ethtool_link_mode_bit_indices for the link modes, physical + * connectors and other link features that are advertised through + * autonegotiation or enabled for auto-detection. + * - lp_advertising: Bitmap with each bit meaning given by + * %ethtool_link_mode_bit_indices for the link modes, and other + * link features that the link partner advertised through + * autonegotiation; 0 if unknown or not applicable. Read-only. */ struct ethtool_link_settings { __u32 cmd; diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index 837fcd4b0abc..b531e3ef011a 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -160,6 +160,8 @@ enum { SMC_NLA_LGR_D_CHID, /* u16 */ SMC_NLA_LGR_D_PAD, /* flag */ SMC_NLA_LGR_D_V2_COMMON, /* nest */ + SMC_NLA_LGR_D_EXT_GID, /* u64 */ + SMC_NLA_LGR_D_PEER_EXT_GID, /* u64 */ __SMC_NLA_LGR_D_MAX, SMC_NLA_LGR_D_MAX = __SMC_NLA_LGR_D_MAX - 1 }; diff --git a/include/uapi/linux/smc_diag.h b/include/uapi/linux/smc_diag.h index 8cb3a6fef553..58eceb7f5df2 100644 --- a/include/uapi/linux/smc_diag.h +++ b/include/uapi/linux/smc_diag.h @@ -107,6 +107,8 @@ struct smcd_diag_dmbinfo { /* SMC-D Socket internals */ __aligned_u64 my_gid; /* My GID */ __aligned_u64 token; /* Token of DMB */ __aligned_u64 peer_token; /* Token of remote DMBE */ + __aligned_u64 peer_gid_ext; /* Peer GID (extended part) */ + __aligned_u64 my_gid_ext; /* My GID (extended part) */ }; #endif /* _UAPI_SMC_DIAG_H_ */ diff --git a/include/uapi/linux/tc_act/tc_mirred.h b/include/uapi/linux/tc_act/tc_mirred.h index 2500a0005d05..c61e76f3c23b 100644 --- a/include/uapi/linux/tc_act/tc_mirred.h +++ b/include/uapi/linux/tc_act/tc_mirred.h @@ -21,6 +21,7 @@ enum { TCA_MIRRED_TM, TCA_MIRRED_PARMS, TCA_MIRRED_PAD, + TCA_MIRRED_BLOCKID, __TCA_MIRRED_MAX }; #define TCA_MIRRED_MAX (__TCA_MIRRED_MAX - 1) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index d56433bf8aba..51e8b4bee0c8 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6765,222 +6765,64 @@ int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *pr return btf_check_func_type_match(log, btf1, t1, btf2, t2); } -static int btf_check_func_arg_match(struct bpf_verifier_env *env, - const struct btf *btf, u32 func_id, - struct bpf_reg_state *regs, - bool ptr_to_mem_ok, - bool processing_call) +static bool btf_is_dynptr_ptr(const struct btf *btf, const struct btf_type *t) { - enum bpf_prog_type prog_type = resolve_prog_type(env->prog); - struct bpf_verifier_log *log = &env->log; - const char *func_name, *ref_tname; - const struct btf_type *t, *ref_t; - const struct btf_param *args; - u32 i, nargs, ref_id; - int ret; - - t = btf_type_by_id(btf, func_id); - if (!t || !btf_type_is_func(t)) { - /* These checks were already done by the verifier while loading - * struct bpf_func_info or in add_kfunc_call(). - */ - bpf_log(log, "BTF of func_id %u doesn't point to KIND_FUNC\n", - func_id); - return -EFAULT; - } - func_name = btf_name_by_offset(btf, t->name_off); - - t = btf_type_by_id(btf, t->type); - if (!t || !btf_type_is_func_proto(t)) { - bpf_log(log, "Invalid BTF of func %s\n", func_name); - return -EFAULT; - } - args = (const struct btf_param *)(t + 1); - nargs = btf_type_vlen(t); - if (nargs > MAX_BPF_FUNC_REG_ARGS) { - bpf_log(log, "Function %s has %d > %d args\n", func_name, nargs, - MAX_BPF_FUNC_REG_ARGS); - return -EINVAL; - } - - /* check that BTF function arguments match actual types that the - * verifier sees. - */ - for (i = 0; i < nargs; i++) { - enum bpf_arg_type arg_type = ARG_DONTCARE; - u32 regno = i + 1; - struct bpf_reg_state *reg = ®s[regno]; - - t = btf_type_skip_modifiers(btf, args[i].type, NULL); - if (btf_type_is_scalar(t)) { - if (reg->type == SCALAR_VALUE) - continue; - bpf_log(log, "R%d is not a scalar\n", regno); - return -EINVAL; - } - - if (!btf_type_is_ptr(t)) { - bpf_log(log, "Unrecognized arg#%d type %s\n", - i, btf_type_str(t)); - return -EINVAL; - } - - ref_t = btf_type_skip_modifiers(btf, t->type, &ref_id); - ref_tname = btf_name_by_offset(btf, ref_t->name_off); - - ret = check_func_arg_reg_off(env, reg, regno, arg_type); - if (ret < 0) - return ret; + const char *name; - if (btf_get_prog_ctx_type(log, btf, t, prog_type, i)) { - /* If function expects ctx type in BTF check that caller - * is passing PTR_TO_CTX. - */ - if (reg->type != PTR_TO_CTX) { - bpf_log(log, - "arg#%d expected pointer to ctx, but got %s\n", - i, btf_type_str(t)); - return -EINVAL; - } - } else if (ptr_to_mem_ok && processing_call) { - const struct btf_type *resolve_ret; - u32 type_size; + t = btf_type_by_id(btf, t->type); /* skip PTR */ - resolve_ret = btf_resolve_size(btf, ref_t, &type_size); - if (IS_ERR(resolve_ret)) { - bpf_log(log, - "arg#%d reference type('%s %s') size cannot be determined: %ld\n", - i, btf_type_str(ref_t), ref_tname, - PTR_ERR(resolve_ret)); - return -EINVAL; - } + while (btf_type_is_modifier(t)) + t = btf_type_by_id(btf, t->type); - if (check_mem_reg(env, reg, regno, type_size)) - return -EINVAL; - } else { - bpf_log(log, "reg type unsupported for arg#%d function %s#%d\n", i, - func_name, func_id); - return -EINVAL; - } + /* allow either struct or struct forward declaration */ + if (btf_type_is_struct(t) || + (btf_type_is_fwd(t) && btf_type_kflag(t) == 0)) { + name = btf_str_by_offset(btf, t->name_off); + return name && strcmp(name, "bpf_dynptr") == 0; } - return 0; -} - -/* Compare BTF of a function declaration with given bpf_reg_state. - * Returns: - * EFAULT - there is a verifier bug. Abort verification. - * EINVAL - there is a type mismatch or BTF is not available. - * 0 - BTF matches with what bpf_reg_state expects. - * Only PTR_TO_CTX and SCALAR_VALUE states are recognized. - */ -int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog, - struct bpf_reg_state *regs) -{ - struct bpf_prog *prog = env->prog; - struct btf *btf = prog->aux->btf; - bool is_global; - u32 btf_id; - int err; - - if (!prog->aux->func_info) - return -EINVAL; - - btf_id = prog->aux->func_info[subprog].type_id; - if (!btf_id) - return -EFAULT; - - if (prog->aux->func_info_aux[subprog].unreliable) - return -EINVAL; - - is_global = prog->aux->func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL; - err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global, false); - - /* Compiler optimizations can remove arguments from static functions - * or mismatched type can be passed into a global function. - * In such cases mark the function as unreliable from BTF point of view. - */ - if (err) - prog->aux->func_info_aux[subprog].unreliable = true; - return err; -} - -/* Compare BTF of a function call with given bpf_reg_state. - * Returns: - * EFAULT - there is a verifier bug. Abort verification. - * EINVAL - there is a type mismatch or BTF is not available. - * 0 - BTF matches with what bpf_reg_state expects. - * Only PTR_TO_CTX and SCALAR_VALUE states are recognized. - * - * NOTE: the code is duplicated from btf_check_subprog_arg_match() - * because btf_check_func_arg_match() is still doing both. Once that - * function is split in 2, we can call from here btf_check_subprog_arg_match() - * first, and then treat the calling part in a new code path. - */ -int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, - struct bpf_reg_state *regs) -{ - struct bpf_prog *prog = env->prog; - struct btf *btf = prog->aux->btf; - bool is_global; - u32 btf_id; - int err; - - if (!prog->aux->func_info) - return -EINVAL; - - btf_id = prog->aux->func_info[subprog].type_id; - if (!btf_id) - return -EFAULT; - - if (prog->aux->func_info_aux[subprog].unreliable) - return -EINVAL; - - is_global = prog->aux->func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL; - err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global, true); - - /* Compiler optimizations can remove arguments from static functions - * or mismatched type can be passed into a global function. - * In such cases mark the function as unreliable from BTF point of view. - */ - if (err) - prog->aux->func_info_aux[subprog].unreliable = true; - return err; + return false; } -/* Convert BTF of a function into bpf_reg_state if possible +/* Process BTF of a function to produce high-level expectation of function + * arguments (like ARG_PTR_TO_CTX, or ARG_PTR_TO_MEM, etc). This information + * is cached in subprog info for reuse. * Returns: * EFAULT - there is a verifier bug. Abort verification. * EINVAL - cannot convert BTF. - * 0 - Successfully converted BTF into bpf_reg_state - * (either PTR_TO_CTX or SCALAR_VALUE). + * 0 - Successfully processed BTF and constructed argument expectations. */ -int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, - struct bpf_reg_state *regs, u32 *arg_cnt) +int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog) { + bool is_global = subprog_aux(env, subprog)->linkage == BTF_FUNC_GLOBAL; + struct bpf_subprog_info *sub = subprog_info(env, subprog); struct bpf_verifier_log *log = &env->log; struct bpf_prog *prog = env->prog; enum bpf_prog_type prog_type = prog->type; struct btf *btf = prog->aux->btf; const struct btf_param *args; - const struct btf_type *t, *ref_t; + const struct btf_type *t, *ref_t, *fn_t; u32 i, nargs, btf_id; const char *tname; - if (!prog->aux->func_info || - prog->aux->func_info_aux[subprog].linkage != BTF_FUNC_GLOBAL) { + if (sub->args_cached) + return 0; + + if (!prog->aux->func_info) { bpf_log(log, "Verifier bug\n"); return -EFAULT; } btf_id = prog->aux->func_info[subprog].type_id; if (!btf_id) { + if (!is_global) /* not fatal for static funcs */ + return -EINVAL; bpf_log(log, "Global functions need valid BTF\n"); return -EFAULT; } - t = btf_type_by_id(btf, btf_id); - if (!t || !btf_type_is_func(t)) { + fn_t = btf_type_by_id(btf, btf_id); + if (!fn_t || !btf_type_is_func(fn_t)) { /* These checks were already done by the verifier while loading * struct bpf_func_info */ @@ -6988,11 +6830,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, subprog); return -EFAULT; } - tname = btf_name_by_offset(btf, t->name_off); - - if (log->level & BPF_LOG_LEVEL) - bpf_log(log, "Validating %s() func#%d...\n", - tname, subprog); + tname = btf_name_by_offset(btf, fn_t->name_off); if (prog->aux->func_info_aux[subprog].unreliable) { bpf_log(log, "Verifier bug in function %s()\n", tname); @@ -7001,7 +6839,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, if (prog_type == BPF_PROG_TYPE_EXT) prog_type = prog->aux->dst_prog->type; - t = btf_type_by_id(btf, t->type); + t = btf_type_by_id(btf, fn_t->type); if (!t || !btf_type_is_func_proto(t)) { bpf_log(log, "Invalid type of function %s()\n", tname); return -EFAULT; @@ -7013,7 +6851,6 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, tname, nargs, MAX_BPF_FUNC_REG_ARGS); return -EINVAL; } - *arg_cnt = nargs; /* check that function returns int, exception cb also requires this */ t = btf_type_by_id(btf, t->type); while (btf_type_is_modifier(t)) @@ -7028,24 +6865,54 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, * Only PTR_TO_CTX and SCALAR are supported atm. */ for (i = 0; i < nargs; i++) { - struct bpf_reg_state *reg = ®s[i + 1]; + bool is_nonnull = false; + const char *tag; t = btf_type_by_id(btf, args[i].type); + + tag = btf_find_decl_tag_value(btf, fn_t, i, "arg:"); + if (IS_ERR(tag) && PTR_ERR(tag) == -ENOENT) { + tag = NULL; + } else if (IS_ERR(tag)) { + bpf_log(log, "arg#%d type's tag fetching failure: %ld\n", i, PTR_ERR(tag)); + return PTR_ERR(tag); + } + /* 'arg:<tag>' decl_tag takes precedence over derivation of + * register type from BTF type itself + */ + if (tag) { + /* disallow arg tags in static subprogs */ + if (!is_global) { + bpf_log(log, "arg#%d type tag is not supported in static functions\n", i); + return -EOPNOTSUPP; + } + if (strcmp(tag, "ctx") == 0) { + sub->args[i].arg_type = ARG_PTR_TO_CTX; + continue; + } + if (strcmp(tag, "nonnull") == 0) + is_nonnull = true; + } + while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); if (btf_type_is_int(t) || btf_is_any_enum(t)) { - reg->type = SCALAR_VALUE; + sub->args[i].arg_type = ARG_ANYTHING; continue; } - if (btf_type_is_ptr(t)) { - if (btf_get_prog_ctx_type(log, btf, t, prog_type, i)) { - reg->type = PTR_TO_CTX; - continue; - } + if (btf_type_is_ptr(t) && btf_get_prog_ctx_type(log, btf, t, prog_type, i)) { + sub->args[i].arg_type = ARG_PTR_TO_CTX; + continue; + } + if (btf_type_is_ptr(t) && btf_is_dynptr_ptr(btf, t)) { + sub->args[i].arg_type = ARG_PTR_TO_DYNPTR | MEM_RDONLY; + continue; + } + if (is_global && btf_type_is_ptr(t)) { + u32 mem_size; t = btf_type_skip_modifiers(btf, t->type, NULL); - - ref_t = btf_resolve_size(btf, t, ®->mem_size); + ref_t = btf_resolve_size(btf, t, &mem_size); if (IS_ERR(ref_t)) { bpf_log(log, "arg#%d reference type('%s %s') size cannot be determined: %ld\n", @@ -7054,15 +6921,22 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, return -EINVAL; } - reg->type = PTR_TO_MEM | PTR_MAYBE_NULL; - reg->id = ++env->id_gen; - + sub->args[i].arg_type = is_nonnull ? ARG_PTR_TO_MEM : ARG_PTR_TO_MEM_OR_NULL; + sub->args[i].mem_size = mem_size; continue; } + if (is_nonnull) { + bpf_log(log, "arg#%d marked as non-null, but is not a pointer type\n", i); + return -EINVAL; + } bpf_log(log, "Arg#%d type %s in %s() is not supported yet.\n", i, btf_type_str(t), tname); return -EINVAL; } + + sub->arg_cnt = nargs; + sub->args_cached = true; + return 0; } diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 1aafb2ff2e95..41e0a55c35f5 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -599,8 +599,15 @@ EXPORT_SYMBOL(bpf_prog_get_type_path); */ static int bpf_show_options(struct seq_file *m, struct dentry *root) { - umode_t mode = d_inode(root)->i_mode & S_IALLUGO & ~S_ISVTX; - + struct inode *inode = d_inode(root); + umode_t mode = inode->i_mode & S_IALLUGO & ~S_ISVTX; + + if (!uid_eq(inode->i_uid, GLOBAL_ROOT_UID)) + seq_printf(m, ",uid=%u", + from_kuid_munged(&init_user_ns, inode->i_uid)); + if (!gid_eq(inode->i_gid, GLOBAL_ROOT_GID)) + seq_printf(m, ",gid=%u", + from_kgid_munged(&init_user_ns, inode->i_gid)); if (mode != S_IRWXUGO) seq_printf(m, ",mode=%o", mode); return 0; @@ -625,15 +632,21 @@ static const struct super_operations bpf_super_ops = { }; enum { + OPT_UID, + OPT_GID, OPT_MODE, }; static const struct fs_parameter_spec bpf_fs_parameters[] = { + fsparam_u32 ("uid", OPT_UID), + fsparam_u32 ("gid", OPT_GID), fsparam_u32oct ("mode", OPT_MODE), {} }; struct bpf_mount_opts { + kuid_t uid; + kgid_t gid; umode_t mode; }; @@ -641,6 +654,8 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct bpf_mount_opts *opts = fc->fs_private; struct fs_parse_result result; + kuid_t uid; + kgid_t gid; int opt; opt = fs_parse(fc, bpf_fs_parameters, param, &result); @@ -662,12 +677,42 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) } switch (opt) { + case OPT_UID: + uid = make_kuid(current_user_ns(), result.uint_32); + if (!uid_valid(uid)) + goto bad_value; + + /* + * The requested uid must be representable in the + * filesystem's idmapping. + */ + if (!kuid_has_mapping(fc->user_ns, uid)) + goto bad_value; + + opts->uid = uid; + break; + case OPT_GID: + gid = make_kgid(current_user_ns(), result.uint_32); + if (!gid_valid(gid)) + goto bad_value; + + /* + * The requested gid must be representable in the + * filesystem's idmapping. + */ + if (!kgid_has_mapping(fc->user_ns, gid)) + goto bad_value; + + opts->gid = gid; + break; case OPT_MODE: opts->mode = result.uint_32 & S_IALLUGO; break; } return 0; +bad_value: + return invalfc(fc, "Bad value for '%s'", param->key); } struct bpf_preload_ops *bpf_preload_ops; @@ -750,6 +795,8 @@ static int bpf_fill_super(struct super_block *sb, struct fs_context *fc) sb->s_op = &bpf_super_ops; inode = sb->s_root->d_inode; + inode->i_uid = opts->uid; + inode->i_gid = opts->gid; inode->i_op = &bpf_dir_iops; inode->i_mode &= ~S_IALLUGO; populate_bpffs(sb->s_root); @@ -785,6 +832,8 @@ static int bpf_init_fs_context(struct fs_context *fc) return -ENOMEM; opts->mode = S_IRWXUGO; + opts->uid = current_fsuid(); + opts->gid = current_fsgid(); fc->fs_private = opts; fc->ops = &bpf_context_ops; diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c index 6a51cfe4c2d6..aa0fbf000a12 100644 --- a/kernel/bpf/memalloc.c +++ b/kernel/bpf/memalloc.c @@ -490,27 +490,6 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu) alloc_bulk(c, c->unit_size <= 256 ? 4 : 1, cpu_to_node(cpu), false); } -static int check_obj_size(struct bpf_mem_cache *c, unsigned int idx) -{ - struct llist_node *first; - unsigned int obj_size; - - first = c->free_llist.first; - if (!first) - return 0; - - if (c->percpu_size) - obj_size = pcpu_alloc_size(((void **)first)[1]); - else - obj_size = ksize(first); - if (obj_size != c->unit_size) { - WARN_ONCE(1, "bpf_mem_cache[%u]: percpu %d, unexpected object size %u, expect %u\n", - idx, c->percpu_size, obj_size, c->unit_size); - return -EINVAL; - } - return 0; -} - /* When size != 0 bpf_mem_cache for each cpu. * This is typical bpf hash map use case when all elements have equal size. * @@ -521,10 +500,10 @@ static int check_obj_size(struct bpf_mem_cache *c, unsigned int idx) int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu) { static u16 sizes[NUM_CACHES] = {96, 192, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096}; - int cpu, i, err, unit_size, percpu_size = 0; struct bpf_mem_caches *cc, __percpu *pcc; struct bpf_mem_cache *c, __percpu *pc; struct obj_cgroup *objcg = NULL; + int cpu, i, unit_size, percpu_size = 0; /* room for llist_node and per-cpu pointer */ if (percpu) @@ -560,7 +539,6 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu) pcc = __alloc_percpu_gfp(sizeof(*cc), 8, GFP_KERNEL); if (!pcc) return -ENOMEM; - err = 0; #ifdef CONFIG_MEMCG_KMEM objcg = get_obj_cgroup_from_current(); #endif @@ -574,28 +552,12 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu) c->tgt = c; init_refill_work(c); - /* Another bpf_mem_cache will be used when allocating - * c->unit_size in bpf_mem_alloc(), so doesn't prefill - * for the bpf_mem_cache because these free objects will - * never be used. - */ - if (i != bpf_mem_cache_idx(c->unit_size)) - continue; prefill_mem_cache(c, cpu); - err = check_obj_size(c, i); - if (err) - goto out; } } -out: ma->caches = pcc; - /* refill_work is either zeroed or initialized, so it is safe to - * call irq_work_sync(). - */ - if (err) - bpf_mem_alloc_destroy(ma); - return err; + return 0; } static void drain_mem_cache(struct bpf_mem_cache *c) @@ -869,7 +831,7 @@ void notrace *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size) void *ret; if (!size) - return ZERO_SIZE_PTR; + return NULL; idx = bpf_mem_cache_idx(size + LLIST_NODE_SZ); if (idx < 0) @@ -879,26 +841,17 @@ void notrace *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size) return !ret ? NULL : ret + LLIST_NODE_SZ; } -static notrace int bpf_mem_free_idx(void *ptr, bool percpu) -{ - size_t size; - - if (percpu) - size = pcpu_alloc_size(*((void **)ptr)); - else - size = ksize(ptr - LLIST_NODE_SZ); - return bpf_mem_cache_idx(size); -} - void notrace bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr) { + struct bpf_mem_cache *c; int idx; if (!ptr) return; - idx = bpf_mem_free_idx(ptr, ma->percpu); - if (idx < 0) + c = *(void **)(ptr - LLIST_NODE_SZ); + idx = bpf_mem_cache_idx(c->unit_size); + if (WARN_ON_ONCE(idx < 0)) return; unit_free(this_cpu_ptr(ma->caches)->cache + idx, ptr); @@ -906,13 +859,15 @@ void notrace bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr) void notrace bpf_mem_free_rcu(struct bpf_mem_alloc *ma, void *ptr) { + struct bpf_mem_cache *c; int idx; if (!ptr) return; - idx = bpf_mem_free_idx(ptr, ma->percpu); - if (idx < 0) + c = *(void **)(ptr - LLIST_NODE_SZ); + idx = bpf_mem_cache_idx(c->unit_size); + if (WARN_ON_ONCE(idx < 0)) return; unit_free_rcu(this_cpu_ptr(ma->caches)->cache + idx, ptr); @@ -986,41 +941,3 @@ void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags) return !ret ? NULL : ret + LLIST_NODE_SZ; } - -/* The alignment of dynamic per-cpu area is 8, so c->unit_size and the - * actual size of dynamic per-cpu area will always be matched and there is - * no need to adjust size_index for per-cpu allocation. However for the - * simplicity of the implementation, use an unified size_index for both - * kmalloc and per-cpu allocation. - */ -static __init int bpf_mem_cache_adjust_size(void) -{ - unsigned int size; - - /* Adjusting the indexes in size_index() according to the object_size - * of underlying slab cache, so bpf_mem_alloc() will select a - * bpf_mem_cache with unit_size equal to the object_size of - * the underlying slab cache. - * - * The maximal value of KMALLOC_MIN_SIZE and __kmalloc_minalign() is - * 256-bytes, so only do adjustment for [8-bytes, 192-bytes]. - */ - for (size = 192; size >= 8; size -= 8) { - unsigned int kmalloc_size, index; - - kmalloc_size = kmalloc_size_roundup(size); - if (kmalloc_size == size) - continue; - - if (kmalloc_size <= 192) - index = size_index[(kmalloc_size - 1) / 8]; - else - index = fls(kmalloc_size - 1) - 1; - /* Only overwrite if necessary */ - if (size_index[(size - 1) / 8] != index) - size_index[(size - 1) / 8] = index; - } - - return 0; -} -subsys_initcall(bpf_mem_cache_adjust_size); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 4ceec8c2a484..a376eb609c41 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -437,16 +437,6 @@ static const char *subprog_name(const struct bpf_verifier_env *env, int subprog) return btf_type_name(env->prog->aux->btf, info->type_id); } -static struct bpf_func_info_aux *subprog_aux(const struct bpf_verifier_env *env, int subprog) -{ - return &env->prog->aux->func_info_aux[subprog]; -} - -static struct bpf_subprog_info *subprog_info(struct bpf_verifier_env *env, int subprog) -{ - return &env->subprog_info[subprog]; -} - static void mark_subprog_exc_cb(struct bpf_verifier_env *env, int subprog) { struct bpf_subprog_info *info = subprog_info(env, subprog); @@ -5137,8 +5127,8 @@ static int __check_ptr_off_reg(struct bpf_verifier_env *env, return 0; } -int check_ptr_off_reg(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg, int regno) +static int check_ptr_off_reg(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int regno) { return __check_ptr_off_reg(env, reg, regno, false); } @@ -7310,8 +7300,8 @@ static int check_mem_size_reg(struct bpf_verifier_env *env, return err; } -int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, - u32 regno, u32 mem_size) +static int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + u32 regno, u32 mem_size) { bool may_be_null = type_may_be_null(reg->type); struct bpf_reg_state saved_reg; @@ -8296,9 +8286,9 @@ reg_find_field_offset(const struct bpf_reg_state *reg, s32 off, u32 fields) return field; } -int check_func_arg_reg_off(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg, int regno, - enum bpf_arg_type arg_type) +static int check_func_arg_reg_off(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int regno, + enum bpf_arg_type arg_type) { u32 type = reg->type; @@ -9259,6 +9249,102 @@ err_out: return err; } +static int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog, + const struct btf *btf, + struct bpf_reg_state *regs) +{ + struct bpf_subprog_info *sub = subprog_info(env, subprog); + struct bpf_verifier_log *log = &env->log; + u32 i; + int ret; + + ret = btf_prepare_func_args(env, subprog); + if (ret) + return ret; + + /* check that BTF function arguments match actual types that the + * verifier sees. + */ + for (i = 0; i < sub->arg_cnt; i++) { + u32 regno = i + 1; + struct bpf_reg_state *reg = ®s[regno]; + struct bpf_subprog_arg_info *arg = &sub->args[i]; + + if (arg->arg_type == ARG_ANYTHING) { + if (reg->type != SCALAR_VALUE) { + bpf_log(log, "R%d is not a scalar\n", regno); + return -EINVAL; + } + } else if (arg->arg_type == ARG_PTR_TO_CTX) { + ret = check_func_arg_reg_off(env, reg, regno, ARG_DONTCARE); + if (ret < 0) + return ret; + /* If function expects ctx type in BTF check that caller + * is passing PTR_TO_CTX. + */ + if (reg->type != PTR_TO_CTX) { + bpf_log(log, "arg#%d expects pointer to ctx\n", i); + return -EINVAL; + } + } else if (base_type(arg->arg_type) == ARG_PTR_TO_MEM) { + ret = check_func_arg_reg_off(env, reg, regno, ARG_DONTCARE); + if (ret < 0) + return ret; + if (check_mem_reg(env, reg, regno, arg->mem_size)) + return -EINVAL; + if (!(arg->arg_type & PTR_MAYBE_NULL) && (reg->type & PTR_MAYBE_NULL)) { + bpf_log(log, "arg#%d is expected to be non-NULL\n", i); + return -EINVAL; + } + } else if (arg->arg_type == (ARG_PTR_TO_DYNPTR | MEM_RDONLY)) { + ret = process_dynptr_func(env, regno, -1, arg->arg_type, 0); + if (ret) + return ret; + } else { + bpf_log(log, "verifier bug: unrecognized arg#%d type %d\n", + i, arg->arg_type); + return -EFAULT; + } + } + + return 0; +} + +/* Compare BTF of a function call with given bpf_reg_state. + * Returns: + * EFAULT - there is a verifier bug. Abort verification. + * EINVAL - there is a type mismatch or BTF is not available. + * 0 - BTF matches with what bpf_reg_state expects. + * Only PTR_TO_CTX and SCALAR_VALUE states are recognized. + */ +static int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, + struct bpf_reg_state *regs) +{ + struct bpf_prog *prog = env->prog; + struct btf *btf = prog->aux->btf; + u32 btf_id; + int err; + + if (!prog->aux->func_info) + return -EINVAL; + + btf_id = prog->aux->func_info[subprog].type_id; + if (!btf_id) + return -EFAULT; + + if (prog->aux->func_info_aux[subprog].unreliable) + return -EINVAL; + + err = btf_check_func_arg_match(env, subprog, btf, regs); + /* Compiler optimizations can remove arguments from static functions + * or mismatched type can be passed into a global function. + * In such cases mark the function as unreliable from BTF point of view. + */ + if (err) + prog->aux->func_info_aux[subprog].unreliable = true; + return err; +} + static int push_callback_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int insn_idx, int subprog, set_callee_state_fn set_callee_state_cb) @@ -9530,7 +9616,7 @@ static int set_find_vma_callback_state(struct bpf_verifier_env *env, callee->regs[BPF_REG_2].type = PTR_TO_BTF_ID; __mark_reg_known_zero(&callee->regs[BPF_REG_2]); callee->regs[BPF_REG_2].btf = btf_vmlinux; - callee->regs[BPF_REG_2].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA], + callee->regs[BPF_REG_2].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA]; /* pointer to stack or null */ callee->regs[BPF_REG_3] = caller->regs[BPF_REG_4]; @@ -14336,7 +14422,43 @@ again: } break; case BPF_JNE: - /* we don't derive any new information for inequality yet */ + if (!is_reg_const(reg2, is_jmp32)) + swap(reg1, reg2); + if (!is_reg_const(reg2, is_jmp32)) + break; + + /* try to recompute the bound of reg1 if reg2 is a const and + * is exactly the edge of reg1. + */ + val = reg_const_value(reg2, is_jmp32); + if (is_jmp32) { + /* u32_min_value is not equal to 0xffffffff at this point, + * because otherwise u32_max_value is 0xffffffff as well, + * in such a case both reg1 and reg2 would be constants, + * jump would be predicted and reg_set_min_max() won't + * be called. + * + * Same reasoning works for all {u,s}{min,max}{32,64} cases + * below. + */ + if (reg1->u32_min_value == (u32)val) + reg1->u32_min_value++; + if (reg1->u32_max_value == (u32)val) + reg1->u32_max_value--; + if (reg1->s32_min_value == (s32)val) + reg1->s32_min_value++; + if (reg1->s32_max_value == (s32)val) + reg1->s32_max_value--; + } else { + if (reg1->umin_value == (u64)val) + reg1->umin_value++; + if (reg1->umax_value == (u64)val) + reg1->umax_value--; + if (reg1->smin_value == (s64)val) + reg1->smin_value++; + if (reg1->smax_value == (s64)val) + reg1->smax_value--; + } break; case BPF_JSET: if (!is_reg_const(reg2, is_jmp32)) @@ -19873,6 +19995,7 @@ static void free_states(struct bpf_verifier_env *env) static int do_check_common(struct bpf_verifier_env *env, int subprog) { bool pop_log = !(env->log.level & BPF_LOG_LEVEL2); + struct bpf_subprog_info *sub = subprog_info(env, subprog); struct bpf_verifier_state *state; struct bpf_reg_state *regs; int ret, i; @@ -19899,54 +20022,71 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog) state->first_insn_idx = env->subprog_info[subprog].start; state->last_insn_idx = -1; + regs = state->frame[state->curframe]->regs; if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) { - u32 nargs; + const char *sub_name = subprog_name(env, subprog); + struct bpf_subprog_arg_info *arg; + struct bpf_reg_state *reg; - ret = btf_prepare_func_args(env, subprog, regs, &nargs); + verbose(env, "Validating %s() func#%d...\n", sub_name, subprog); + ret = btf_prepare_func_args(env, subprog); if (ret) goto out; + if (subprog_is_exc_cb(env, subprog)) { state->frame[0]->in_exception_callback_fn = true; /* We have already ensured that the callback returns an integer, just * like all global subprogs. We need to determine it only has a single * scalar argument. */ - if (nargs != 1 || regs[BPF_REG_1].type != SCALAR_VALUE) { + if (sub->arg_cnt != 1 || sub->args[0].arg_type != ARG_ANYTHING) { verbose(env, "exception cb only supports single integer argument\n"); ret = -EINVAL; goto out; } } - for (i = BPF_REG_1; i <= BPF_REG_5; i++) { - if (regs[i].type == PTR_TO_CTX) + for (i = BPF_REG_1; i <= sub->arg_cnt; i++) { + arg = &sub->args[i - BPF_REG_1]; + reg = ®s[i]; + + if (arg->arg_type == ARG_PTR_TO_CTX) { + reg->type = PTR_TO_CTX; mark_reg_known_zero(env, regs, i); - else if (regs[i].type == SCALAR_VALUE) + } else if (arg->arg_type == ARG_ANYTHING) { + reg->type = SCALAR_VALUE; mark_reg_unknown(env, regs, i); - else if (base_type(regs[i].type) == PTR_TO_MEM) { - const u32 mem_size = regs[i].mem_size; - + } else if (arg->arg_type == (ARG_PTR_TO_DYNPTR | MEM_RDONLY)) { + /* assume unspecial LOCAL dynptr type */ + __mark_dynptr_reg(reg, BPF_DYNPTR_TYPE_LOCAL, true, ++env->id_gen); + } else if (base_type(arg->arg_type) == ARG_PTR_TO_MEM) { + reg->type = PTR_TO_MEM; + if (arg->arg_type & PTR_MAYBE_NULL) + reg->type |= PTR_MAYBE_NULL; mark_reg_known_zero(env, regs, i); - regs[i].mem_size = mem_size; - regs[i].id = ++env->id_gen; + reg->mem_size = arg->mem_size; + reg->id = ++env->id_gen; + } else { + WARN_ONCE(1, "BUG: unhandled arg#%d type %d\n", + i - BPF_REG_1, arg->arg_type); + ret = -EFAULT; + goto out; } } } else { + /* if main BPF program has associated BTF info, validate that + * it's matching expected signature, and otherwise mark BTF + * info for main program as unreliable + */ + if (env->prog->aux->func_info_aux) { + ret = btf_prepare_func_args(env, 0); + if (ret || sub->arg_cnt != 1 || sub->args[0].arg_type != ARG_PTR_TO_CTX) + env->prog->aux->func_info_aux[0].unreliable = true; + } + /* 1st arg to a function */ regs[BPF_REG_1].type = PTR_TO_CTX; mark_reg_known_zero(env, regs, BPF_REG_1); - ret = btf_check_subprog_arg_match(env, subprog, regs); - if (ret == -EFAULT) - /* unlikely verifier bug. abort. - * ret == 0 and ret < 0 are sadly acceptable for - * main() function due to backward compatibility. - * Like socket filter program may be written as: - * int bpf_prog(struct pt_regs *ctx) - * and never dereference that ctx in the program. - * 'struct pt_regs' is a type mismatch for socket - * filter that should be using 'struct __sk_buff'. - */ - goto out; } ret = do_check(env); diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index a852ec093fa8..198f5ba2feae 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1581,7 +1581,7 @@ static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) } /* Build a packet */ - SOCK_DEBUG(sk, "SK %p: Got address.\n", sk); + net_dbg_ratelimited("SK %p: Got address.\n", sk); /* For headers */ size = sizeof(struct ddpehdr) + len + ddp_dl->header_length; @@ -1602,7 +1602,7 @@ static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) dev = rt->dev; - SOCK_DEBUG(sk, "SK %p: Size needed %d, device %s\n", + net_dbg_ratelimited("SK %p: Size needed %d, device %s\n", sk, size, dev->name); hard_header_len = dev->hard_header_len; @@ -1631,7 +1631,7 @@ static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) skb_reserve(skb, hard_header_len); skb->dev = dev; - SOCK_DEBUG(sk, "SK %p: Begin build.\n", sk); + net_dbg_ratelimited("SK %p: Begin build.\n", sk); ddp = skb_put(skb, sizeof(struct ddpehdr)); ddp->deh_len_hops = htons(len + sizeof(*ddp)); @@ -1642,7 +1642,7 @@ static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) ddp->deh_dport = usat->sat_port; ddp->deh_sport = at->src_port; - SOCK_DEBUG(sk, "SK %p: Copy user data (%zd bytes).\n", sk, len); + net_dbg_ratelimited("SK %p: Copy user data (%zd bytes).\n", sk, len); err = memcpy_from_msg(skb_put(skb, len), msg, len); if (err) { @@ -1666,7 +1666,7 @@ static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (skb2) { loopback = 1; - SOCK_DEBUG(sk, "SK %p: send out(copy).\n", sk); + net_dbg_ratelimited("SK %p: send out(copy).\n", sk); /* * If it fails it is queued/sent above in the aarp queue */ @@ -1675,7 +1675,7 @@ static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) } if (dev->flags & IFF_LOOPBACK || loopback) { - SOCK_DEBUG(sk, "SK %p: Loop back.\n", sk); + net_dbg_ratelimited("SK %p: Loop back.\n", sk); /* loop back */ skb_orphan(skb); if (ddp->deh_dnode == ATADDR_BCAST) { @@ -1689,7 +1689,7 @@ static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) } ddp_dl->request(ddp_dl, skb, dev->dev_addr); } else { - SOCK_DEBUG(sk, "SK %p: send out.\n", sk); + net_dbg_ratelimited("SK %p: send out.\n", sk); if (rt->flags & RTF_GATEWAY) { gsat.sat_addr = rt->gateway; usat = &gsat; @@ -1700,7 +1700,7 @@ static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) */ aarp_send_ddp(dev, skb, &usat->sat_addr, NULL); } - SOCK_DEBUG(sk, "SK %p: Done write (%zd).\n", sk, len); + net_dbg_ratelimited("SK %p: Done write (%zd).\n", sk, len); out: release_sock(sk); diff --git a/net/bridge/br_cfm_netlink.c b/net/bridge/br_cfm_netlink.c index 5c4c369f8536..2faab44652e7 100644 --- a/net/bridge/br_cfm_netlink.c +++ b/net/bridge/br_cfm_netlink.c @@ -362,7 +362,7 @@ static int br_cc_ccm_tx_parse(struct net_bridge *br, struct nlattr *attr, memset(&tx_info, 0, sizeof(tx_info)); - instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_RDI_INSTANCE]); + instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_INSTANCE]); nla_memcpy(&tx_info.dmac.addr, tb[IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC], sizeof(tx_info.dmac.addr)); diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index b240d9aae4a6..b0f221d658be 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -183,7 +183,7 @@ out: } static const struct genl_multicast_group dropmon_mcgrps[] = { - { .name = "events", .cap_sys_admin = 1 }, + { .name = "events", .flags = GENL_MCAST_CAP_SYS_ADMIN, }, }; static void send_dm_alert(struct work_struct *work) diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 57cea67b7562..ea55a758a475 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3669,10 +3669,8 @@ static int pktgen_thread_worker(void *arg) if (unlikely(!pkt_dev && t->control == 0)) { if (t->net->pktgen_exiting) break; - wait_event_interruptible_timeout(t->queue, - t->control != 0, - HZ/10); - try_to_freeze(); + wait_event_freezable_timeout(t->queue, + t->control != 0, HZ / 10); continue; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index ce5687ddb768..12d22c0b8551 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5995,6 +5995,31 @@ int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len) } EXPORT_SYMBOL(skb_ensure_writable); +int skb_ensure_writable_head_tail(struct sk_buff *skb, struct net_device *dev) +{ + int needed_headroom = dev->needed_headroom; + int needed_tailroom = dev->needed_tailroom; + + /* For tail taggers, we need to pad short frames ourselves, to ensure + * that the tail tag does not fail at its role of being at the end of + * the packet, once the conduit interface pads the frame. Account for + * that pad length here, and pad later. + */ + if (unlikely(needed_tailroom && skb->len < ETH_ZLEN)) + needed_tailroom += ETH_ZLEN - skb->len; + /* skb_headroom() returns unsigned int... */ + needed_headroom = max_t(int, needed_headroom - skb_headroom(skb), 0); + needed_tailroom = max_t(int, needed_tailroom - skb_tailroom(skb), 0); + + if (likely(!needed_headroom && !needed_tailroom && !skb_cloned(skb))) + /* No reallocation needed, yay! */ + return 0; + + return pskb_expand_head(skb, needed_headroom, needed_tailroom, + GFP_ATOMIC); +} +EXPORT_SYMBOL(skb_ensure_writable_head_tail); + /* remove VLAN header from packet and update csum accordingly. * expects a non skb_vlan_tag_present skb with a vlan tag payload */ diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 06d7324276ec..ded07e09f813 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -889,7 +889,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, u32 exthdrlen = icsk->icsk_ext_hdr_len; struct sockaddr_in sin; - SOCK_DEBUG(sk, "connect: ipv4 mapped\n"); + net_dbg_ratelimited("connect: ipv4 mapped\n"); if (ipv6_only_sock(sk)) return -ENETUNREACH; diff --git a/net/dsa/user.c b/net/dsa/user.c index d438884a4eb0..b738a466e2dc 100644 --- a/net/dsa/user.c +++ b/net/dsa/user.c @@ -920,30 +920,6 @@ netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev) } EXPORT_SYMBOL_GPL(dsa_enqueue_skb); -static int dsa_realloc_skb(struct sk_buff *skb, struct net_device *dev) -{ - int needed_headroom = dev->needed_headroom; - int needed_tailroom = dev->needed_tailroom; - - /* For tail taggers, we need to pad short frames ourselves, to ensure - * that the tail tag does not fail at its role of being at the end of - * the packet, once the conduit interface pads the frame. Account for - * that pad length here, and pad later. - */ - if (unlikely(needed_tailroom && skb->len < ETH_ZLEN)) - needed_tailroom += ETH_ZLEN - skb->len; - /* skb_headroom() returns unsigned int... */ - needed_headroom = max_t(int, needed_headroom - skb_headroom(skb), 0); - needed_tailroom = max_t(int, needed_tailroom - skb_tailroom(skb), 0); - - if (likely(!needed_headroom && !needed_tailroom && !skb_cloned(skb))) - /* No reallocation needed, yay! */ - return 0; - - return pskb_expand_head(skb, needed_headroom, needed_tailroom, - GFP_ATOMIC); -} - static netdev_tx_t dsa_user_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_user_priv *p = netdev_priv(dev); @@ -956,13 +932,14 @@ static netdev_tx_t dsa_user_xmit(struct sk_buff *skb, struct net_device *dev) /* Handle tx timestamp if any */ dsa_skb_tx_timestamp(p, skb); - if (dsa_realloc_skb(skb, dev)) { + if (skb_ensure_writable_head_tail(skb, dev)) { dev_kfree_skb_any(skb); return NETDEV_TX_OK; } /* needed_tailroom should still be 'warm' in the cache line from - * dsa_realloc_skb(), which has also ensured that padding is safe. + * skb_ensure_writable_head_tail(), which has also ensured that + * padding is safe. */ if (dev->needed_tailroom) eth_skb_pad(skb); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index bd325b029dd1..8e2eb1793685 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -159,8 +159,11 @@ static bool inet_use_bhash2_on_bind(const struct sock *sk) if (sk->sk_family == AF_INET6) { int addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr); - return addr_type != IPV6_ADDR_ANY && - addr_type != IPV6_ADDR_MAPPED; + if (addr_type == IPV6_ADDR_ANY) + return false; + + if (addr_type != IPV6_ADDR_MAPPED) + return true; } #endif return sk->sk_rcv_saddr != htonl(INADDR_ANY); @@ -213,18 +216,9 @@ static bool inet_bhash2_conflict(const struct sock *sk, bool relax, bool reuseport_cb_ok, bool reuseport_ok) { - struct inet_timewait_sock *tw2; struct sock *sk2; - sk_for_each_bound_bhash2(sk2, &tb2->owners) { - if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax, - reuseport_cb_ok, reuseport_ok)) - return true; - } - - twsk_for_each_bound_bhash2(tw2, &tb2->deathrow) { - sk2 = (struct sock *)tw2; - + sk_for_each_bound(sk2, &tb2->owners) { if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax, reuseport_cb_ok, reuseport_ok)) return true; @@ -233,15 +227,20 @@ static bool inet_bhash2_conflict(const struct sock *sk, return false; } +#define sk_for_each_bound_bhash(__sk, __tb2, __tb) \ + hlist_for_each_entry(__tb2, &(__tb)->bhash2, bhash_node) \ + sk_for_each_bound(sk2, &(__tb2)->owners) + /* This should be called only when the tb and tb2 hashbuckets' locks are held */ static int inet_csk_bind_conflict(const struct sock *sk, const struct inet_bind_bucket *tb, const struct inet_bind2_bucket *tb2, /* may be null */ bool relax, bool reuseport_ok) { - bool reuseport_cb_ok; - struct sock_reuseport *reuseport_cb; kuid_t uid = sock_i_uid((struct sock *)sk); + struct sock_reuseport *reuseport_cb; + bool reuseport_cb_ok; + struct sock *sk2; rcu_read_lock(); reuseport_cb = rcu_dereference(sk->sk_reuseport_cb); @@ -249,32 +248,29 @@ static int inet_csk_bind_conflict(const struct sock *sk, reuseport_cb_ok = !reuseport_cb || READ_ONCE(reuseport_cb->num_closed_socks); rcu_read_unlock(); - /* - * Unlike other sk lookup places we do not check + /* Conflicts with an existing IPV6_ADDR_ANY (if ipv6) or INADDR_ANY (if + * ipv4) should have been checked already. We need to do these two + * checks separately because their spinlocks have to be acquired/released + * independently of each other, to prevent possible deadlocks + */ + if (inet_use_bhash2_on_bind(sk)) + return tb2 && inet_bhash2_conflict(sk, tb2, uid, relax, + reuseport_cb_ok, reuseport_ok); + + /* Unlike other sk lookup places we do not check * for sk_net here, since _all_ the socks listed * in tb->owners and tb2->owners list belong * to the same net - the one this bucket belongs to. */ + sk_for_each_bound_bhash(sk2, tb2, tb) { + if (!inet_bind_conflict(sk, sk2, uid, relax, reuseport_cb_ok, reuseport_ok)) + continue; - if (!inet_use_bhash2_on_bind(sk)) { - struct sock *sk2; - - sk_for_each_bound(sk2, &tb->owners) - if (inet_bind_conflict(sk, sk2, uid, relax, - reuseport_cb_ok, reuseport_ok) && - inet_rcv_saddr_equal(sk, sk2, true)) - return true; - - return false; + if (inet_rcv_saddr_equal(sk, sk2, true)) + return true; } - /* Conflicts with an existing IPV6_ADDR_ANY (if ipv6) or INADDR_ANY (if - * ipv4) should have been checked already. We need to do these two - * checks separately because their spinlocks have to be acquired/released - * independently of each other, to prevent possible deadlocks - */ - return tb2 && inet_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok, - reuseport_ok); + return false; } /* Determine if there is a bind conflict with an existing IPV6_ADDR_ANY (if ipv6) or @@ -457,7 +453,7 @@ void inet_csk_update_fastreuse(struct inet_bind_bucket *tb, kuid_t uid = sock_i_uid(sk); bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN; - if (hlist_empty(&tb->owners)) { + if (hlist_empty(&tb->bhash2)) { tb->fastreuse = reuse; if (sk->sk_reuseport) { tb->fastreuseport = FASTREUSEPORT_ANY; @@ -549,7 +545,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) } if (!found_port) { - if (!hlist_empty(&tb->owners)) { + if (!hlist_empty(&tb->bhash2)) { if (sk->sk_reuse == SK_FORCE_REUSE || (tb->fastreuse > 0 && reuse) || sk_reuseport_match(tb, sk)) @@ -569,7 +565,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) if (!tb2) { tb2 = inet_bind2_bucket_create(hinfo->bind2_bucket_cachep, - net, head2, port, l3mdev, sk); + net, head2, tb, sk); if (!tb2) goto fail_unlock; bhash2_created = true; @@ -591,11 +587,10 @@ success: fail_unlock: if (ret) { + if (bhash2_created) + inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, tb2); if (bhash_created) inet_bind_bucket_destroy(hinfo->bind_bucket_cachep, tb); - if (bhash2_created) - inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, - tb2); } if (head2_lock_acquired) spin_unlock(&head2->lock); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 46b13962ad02..8e6b6aa0579e 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -1104,7 +1104,7 @@ resume_bind_walk: if (!net_eq(ib2_net(tb2), net)) continue; - sk_for_each_bound_bhash2(sk, &tb2->owners) { + sk_for_each_bound(sk, &tb2->owners) { struct inet_sock *inet = inet_sk(sk); if (num < s_num) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 9ff201bc4e6d..93e9193df544 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -76,7 +76,7 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep, tb->port = snum; tb->fastreuse = 0; tb->fastreuseport = 0; - INIT_HLIST_HEAD(&tb->owners); + INIT_HLIST_HEAD(&tb->bhash2); hlist_add_head(&tb->node, &head->chain); } return tb; @@ -87,7 +87,7 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep, */ void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket *tb) { - if (hlist_empty(&tb->owners)) { + if (hlist_empty(&tb->bhash2)) { __hlist_del(&tb->node); kmem_cache_free(cachep, tb); } @@ -100,47 +100,52 @@ bool inet_bind_bucket_match(const struct inet_bind_bucket *tb, const struct net tb->l3mdev == l3mdev; } -static void inet_bind2_bucket_init(struct inet_bind2_bucket *tb, +static void inet_bind2_bucket_init(struct inet_bind2_bucket *tb2, struct net *net, struct inet_bind_hashbucket *head, - unsigned short port, int l3mdev, + struct inet_bind_bucket *tb, const struct sock *sk) { - write_pnet(&tb->ib_net, net); - tb->l3mdev = l3mdev; - tb->port = port; + write_pnet(&tb2->ib_net, net); + tb2->l3mdev = tb->l3mdev; + tb2->port = tb->port; #if IS_ENABLED(CONFIG_IPV6) - tb->family = sk->sk_family; - if (sk->sk_family == AF_INET6) - tb->v6_rcv_saddr = sk->sk_v6_rcv_saddr; - else + BUILD_BUG_ON(USHRT_MAX < (IPV6_ADDR_ANY | IPV6_ADDR_MAPPED)); + if (sk->sk_family == AF_INET6) { + tb2->addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr); + tb2->v6_rcv_saddr = sk->sk_v6_rcv_saddr; + } else { + tb2->addr_type = IPV6_ADDR_MAPPED; + ipv6_addr_set_v4mapped(sk->sk_rcv_saddr, &tb2->v6_rcv_saddr); + } +#else + tb2->rcv_saddr = sk->sk_rcv_saddr; #endif - tb->rcv_saddr = sk->sk_rcv_saddr; - INIT_HLIST_HEAD(&tb->owners); - INIT_HLIST_HEAD(&tb->deathrow); - hlist_add_head(&tb->node, &head->chain); + INIT_HLIST_HEAD(&tb2->owners); + hlist_add_head(&tb2->node, &head->chain); + hlist_add_head(&tb2->bhash_node, &tb->bhash2); } struct inet_bind2_bucket *inet_bind2_bucket_create(struct kmem_cache *cachep, struct net *net, struct inet_bind_hashbucket *head, - unsigned short port, - int l3mdev, + struct inet_bind_bucket *tb, const struct sock *sk) { - struct inet_bind2_bucket *tb = kmem_cache_alloc(cachep, GFP_ATOMIC); + struct inet_bind2_bucket *tb2 = kmem_cache_alloc(cachep, GFP_ATOMIC); - if (tb) - inet_bind2_bucket_init(tb, net, head, port, l3mdev, sk); + if (tb2) + inet_bind2_bucket_init(tb2, net, head, tb, sk); - return tb; + return tb2; } /* Caller must hold hashbucket lock for this tb with local BH disabled */ void inet_bind2_bucket_destroy(struct kmem_cache *cachep, struct inet_bind2_bucket *tb) { - if (hlist_empty(&tb->owners) && hlist_empty(&tb->deathrow)) { + if (hlist_empty(&tb->owners)) { __hlist_del(&tb->node); + __hlist_del(&tb->bhash_node); kmem_cache_free(cachep, tb); } } @@ -149,18 +154,11 @@ static bool inet_bind2_bucket_addr_match(const struct inet_bind2_bucket *tb2, const struct sock *sk) { #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family != tb2->family) { - if (sk->sk_family == AF_INET) - return ipv6_addr_v4mapped(&tb2->v6_rcv_saddr) && - tb2->v6_rcv_saddr.s6_addr32[3] == sk->sk_rcv_saddr; - - return ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr) && - sk->sk_v6_rcv_saddr.s6_addr32[3] == tb2->rcv_saddr; - } - if (sk->sk_family == AF_INET6) - return ipv6_addr_equal(&tb2->v6_rcv_saddr, - &sk->sk_v6_rcv_saddr); + return ipv6_addr_equal(&tb2->v6_rcv_saddr, &sk->sk_v6_rcv_saddr); + + if (tb2->addr_type != IPV6_ADDR_MAPPED) + return false; #endif return tb2->rcv_saddr == sk->sk_rcv_saddr; } @@ -169,10 +167,9 @@ void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, struct inet_bind2_bucket *tb2, unsigned short port) { inet_sk(sk)->inet_num = port; - sk_add_bind_node(sk, &tb->owners); inet_csk(sk)->icsk_bind_hash = tb; - sk_add_bind2_node(sk, &tb2->owners); inet_csk(sk)->icsk_bind2_hash = tb2; + sk_add_bind_node(sk, &tb2->owners); } /* @@ -192,21 +189,20 @@ static void __inet_put_port(struct sock *sk) spin_lock(&head->lock); tb = inet_csk(sk)->icsk_bind_hash; - __sk_del_bind_node(sk); inet_csk(sk)->icsk_bind_hash = NULL; inet_sk(sk)->inet_num = 0; - inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb); spin_lock(&head2->lock); if (inet_csk(sk)->icsk_bind2_hash) { struct inet_bind2_bucket *tb2 = inet_csk(sk)->icsk_bind2_hash; - __sk_del_bind2_node(sk); + __sk_del_bind_node(sk); inet_csk(sk)->icsk_bind2_hash = NULL; inet_bind2_bucket_destroy(hashinfo->bind2_bucket_cachep, tb2); } spin_unlock(&head2->lock); + inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb); spin_unlock(&head->lock); } @@ -275,8 +271,7 @@ bhash2_find: tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, child); if (!tb2) { tb2 = inet_bind2_bucket_create(table->bind2_bucket_cachep, - net, head2, port, - l3mdev, child); + net, head2, tb, child); if (!tb2) goto error; } @@ -836,16 +831,15 @@ bool inet_bind2_bucket_match_addr_any(const struct inet_bind2_bucket *tb, const return false; #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family != tb->family) { - if (sk->sk_family == AF_INET) - return ipv6_addr_any(&tb->v6_rcv_saddr) || - ipv6_addr_v4mapped_any(&tb->v6_rcv_saddr); + if (tb->addr_type == IPV6_ADDR_ANY) + return true; + if (tb->addr_type != IPV6_ADDR_MAPPED) return false; - } - if (sk->sk_family == AF_INET6) - return ipv6_addr_any(&tb->v6_rcv_saddr); + if (sk->sk_family == AF_INET6 && + !ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) + return false; #endif return tb->rcv_saddr == 0; } @@ -942,7 +936,7 @@ static int __inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family, spin_lock_bh(&head->lock); spin_lock(&head2->lock); - __sk_del_bind2_node(sk); + __sk_del_bind_node(sk); inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, inet_csk(sk)->icsk_bind2_hash); spin_unlock(&head2->lock); @@ -957,10 +951,10 @@ static int __inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family, tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk); if (!tb2) { tb2 = new_tb2; - inet_bind2_bucket_init(tb2, net, head2, port, l3mdev, sk); + inet_bind2_bucket_init(tb2, net, head2, inet_csk(sk)->icsk_bind_hash, sk); } - sk_add_bind2_node(sk, &tb2->owners); inet_csk(sk)->icsk_bind2_hash = tb2; + sk_add_bind_node(sk, &tb2->owners); spin_unlock(&head2->lock); spin_unlock_bh(&head->lock); @@ -1064,7 +1058,7 @@ other_parity_scan: if (tb->fastreuse >= 0 || tb->fastreuseport >= 0) goto next_port; - WARN_ON(hlist_empty(&tb->owners)); + WARN_ON(hlist_empty(&tb->bhash2)); if (!check_established(death_row, sk, port, &tw)) goto ok; @@ -1104,7 +1098,7 @@ ok: tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk); if (!tb2) { tb2 = inet_bind2_bucket_create(hinfo->bind2_bucket_cachep, net, - head2, port, l3mdev, sk); + head2, tb, sk); if (!tb2) goto error; } diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index dd37a5bf6881..5befa4de5b24 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -35,13 +35,11 @@ void inet_twsk_bind_unhash(struct inet_timewait_sock *tw, if (!tb) return; - __hlist_del(&tw->tw_bind_node); + __sk_del_bind_node((struct sock *)tw); tw->tw_tb = NULL; - inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb); - - __hlist_del(&tw->tw_bind2_node); tw->tw_tb2 = NULL; inet_bind2_bucket_destroy(hashinfo->bind2_bucket_cachep, tb2); + inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb); __sock_put((struct sock *)tw); } @@ -94,18 +92,6 @@ static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw, hlist_nulls_add_head_rcu(&tw->tw_node, list); } -static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw, - struct hlist_head *list) -{ - hlist_add_head(&tw->tw_bind_node, list); -} - -static void inet_twsk_add_bind2_node(struct inet_timewait_sock *tw, - struct hlist_head *list) -{ - hlist_add_head(&tw->tw_bind2_node, list); -} - /* * Enter the time wait state. This is called with locally disabled BH. * Essentially we whip up a timewait bucket, copy the relevant info into it @@ -133,11 +119,10 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, tw->tw_tb = icsk->icsk_bind_hash; WARN_ON(!icsk->icsk_bind_hash); - inet_twsk_add_bind_node(tw, &tw->tw_tb->owners); tw->tw_tb2 = icsk->icsk_bind2_hash; WARN_ON(!icsk->icsk_bind2_hash); - inet_twsk_add_bind2_node(tw, &tw->tw_tb2->deathrow); + sk_add_bind_node((struct sock *)tw, &tw->tw_tb2->owners); spin_unlock(&bhead2->lock); spin_unlock(&bhead->lock); diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 0ed6e34d6edd..6334f64f04d5 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -67,7 +67,7 @@ static int iucv_bus_match(struct device *dev, struct device_driver *drv) return 0; } -struct bus_type iucv_bus = { +const struct bus_type iucv_bus = { .name = "iucv", .match = iucv_bus_match, }; diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index bf4d96f6f99a..272e93be1aad 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1100,7 +1100,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc static const struct genl_multicast_group mptcp_pm_mcgrps[] = { [MPTCP_PM_CMD_GRP_OFFSET] = { .name = MPTCP_PM_CMD_GRP_NAME, }, [MPTCP_PM_EV_GRP_OFFSET] = { .name = MPTCP_PM_EV_GRP_NAME, - .flags = GENL_UNS_ADMIN_PERM, + .flags = GENL_MCAST_CAP_NET_ADMIN, }, }; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 5cd5c3f535a8..91e5845d80a9 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -55,28 +55,14 @@ static u64 mptcp_wnd_end(const struct mptcp_sock *msk) return READ_ONCE(msk->wnd_end); } -static bool mptcp_is_tcpsk(struct sock *sk) +static const struct proto_ops *mptcp_fallback_tcp_ops(const struct sock *sk) { - struct socket *sock = sk->sk_socket; - - if (unlikely(sk->sk_prot == &tcp_prot)) { - /* we are being invoked after mptcp_accept() has - * accepted a non-mp-capable flow: sk is a tcp_sk, - * not an mptcp one. - * - * Hand the socket over to tcp so all further socket ops - * bypass mptcp. - */ - WRITE_ONCE(sock->ops, &inet_stream_ops); - return true; #if IS_ENABLED(CONFIG_MPTCP_IPV6) - } else if (unlikely(sk->sk_prot == &tcpv6_prot)) { - WRITE_ONCE(sock->ops, &inet6_stream_ops); - return true; + if (sk->sk_prot == &tcpv6_prot) + return &inet6_stream_ops; #endif - } - - return false; + WARN_ON_ONCE(sk->sk_prot != &tcp_prot); + return &inet_stream_ops; } static int __mptcp_socket_create(struct mptcp_sock *msk) @@ -3258,44 +3244,6 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk) WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd); } -static struct sock *mptcp_accept(struct sock *ssk, int flags, int *err, - bool kern) -{ - struct sock *newsk; - - pr_debug("ssk=%p, listener=%p", ssk, mptcp_subflow_ctx(ssk)); - newsk = inet_csk_accept(ssk, flags, err, kern); - if (!newsk) - return NULL; - - pr_debug("newsk=%p, subflow is mptcp=%d", newsk, sk_is_mptcp(newsk)); - if (sk_is_mptcp(newsk)) { - struct mptcp_subflow_context *subflow; - struct sock *new_mptcp_sock; - - subflow = mptcp_subflow_ctx(newsk); - new_mptcp_sock = subflow->conn; - - /* is_mptcp should be false if subflow->conn is missing, see - * subflow_syn_recv_sock() - */ - if (WARN_ON_ONCE(!new_mptcp_sock)) { - tcp_sk(newsk)->is_mptcp = 0; - goto out; - } - - newsk = new_mptcp_sock; - MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEPASSIVEACK); - } else { - MPTCP_INC_STATS(sock_net(ssk), - MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK); - } - -out: - newsk->sk_kern_sock = kern; - return newsk; -} - void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags) { struct mptcp_subflow_context *subflow, *tmp; @@ -3739,7 +3687,6 @@ static struct proto mptcp_prot = { .connect = mptcp_connect, .disconnect = mptcp_disconnect, .close = mptcp_close, - .accept = mptcp_accept, .setsockopt = mptcp_setsockopt, .getsockopt = mptcp_getsockopt, .shutdown = mptcp_shutdown, @@ -3849,18 +3796,36 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, if (!ssk) return -EINVAL; - newsk = mptcp_accept(ssk, flags, &err, kern); + pr_debug("ssk=%p, listener=%p", ssk, mptcp_subflow_ctx(ssk)); + newsk = inet_csk_accept(ssk, flags, &err, kern); if (!newsk) return err; - lock_sock(newsk); - - __inet_accept(sock, newsock, newsk); - if (!mptcp_is_tcpsk(newsock->sk)) { - struct mptcp_sock *msk = mptcp_sk(newsk); + pr_debug("newsk=%p, subflow is mptcp=%d", newsk, sk_is_mptcp(newsk)); + if (sk_is_mptcp(newsk)) { struct mptcp_subflow_context *subflow; + struct sock *new_mptcp_sock; + + subflow = mptcp_subflow_ctx(newsk); + new_mptcp_sock = subflow->conn; + + /* is_mptcp should be false if subflow->conn is missing, see + * subflow_syn_recv_sock() + */ + if (WARN_ON_ONCE(!new_mptcp_sock)) { + tcp_sk(newsk)->is_mptcp = 0; + goto tcpfallback; + } + + newsk = new_mptcp_sock; + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEPASSIVEACK); + + newsk->sk_kern_sock = kern; + lock_sock(newsk); + __inet_accept(sock, newsock, newsk); set_bit(SOCK_CUSTOM_SOCKOPT, &newsock->flags); + msk = mptcp_sk(newsk); msk->in_accept_queue = 0; /* set ssk->sk_socket of accept()ed flows to mptcp socket. @@ -3882,6 +3847,21 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, if (unlikely(list_is_singular(&msk->conn_list))) inet_sk_state_store(newsk, TCP_CLOSE); } + } else { + MPTCP_INC_STATS(sock_net(ssk), + MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK); +tcpfallback: + newsk->sk_kern_sock = kern; + lock_sock(newsk); + __inet_accept(sock, newsock, newsk); + /* we are being invoked after accepting a non-mp-capable + * flow: sk is a tcp_sk, not an mptcp one. + * + * Hand the socket over to tcp so all further socket ops + * bypass mptcp. + */ + WRITE_ONCE(newsock->sk->sk_socket->ops, + mptcp_fallback_tcp_ops(newsock->sk)); } release_sock(newsk); diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index cabe856b2a45..c40f1428e602 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -440,6 +440,8 @@ static bool mptcp_supported_sockopt(int level, int optname) /* should work fine */ case IP_FREEBIND: case IP_TRANSPARENT: + case IP_BIND_ADDRESS_NO_PORT: + case IP_LOCAL_PORT_RANGE: /* the following are control cmsg related */ case IP_PKTINFO: @@ -455,7 +457,6 @@ static bool mptcp_supported_sockopt(int level, int optname) /* common stuff that need some love */ case IP_TOS: case IP_TTL: - case IP_BIND_ADDRESS_NO_PORT: case IP_MTU_DISCOVER: case IP_RECVERR: @@ -683,8 +684,8 @@ static int mptcp_setsockopt_sol_tcp_nodelay(struct mptcp_sock *msk, sockptr_t op return 0; } -static int mptcp_setsockopt_sol_ip_set_transparent(struct mptcp_sock *msk, int optname, - sockptr_t optval, unsigned int optlen) +static int mptcp_setsockopt_sol_ip_set(struct mptcp_sock *msk, int optname, + sockptr_t optval, unsigned int optlen) { struct sock *sk = (struct sock *)msk; struct sock *ssk; @@ -710,6 +711,14 @@ static int mptcp_setsockopt_sol_ip_set_transparent(struct mptcp_sock *msk, int o inet_assign_bit(TRANSPARENT, ssk, inet_test_bit(TRANSPARENT, sk)); break; + case IP_BIND_ADDRESS_NO_PORT: + inet_assign_bit(BIND_ADDRESS_NO_PORT, ssk, + inet_test_bit(BIND_ADDRESS_NO_PORT, sk)); + break; + case IP_LOCAL_PORT_RANGE: + WRITE_ONCE(inet_sk(ssk)->local_port_range, + READ_ONCE(inet_sk(sk)->local_port_range)); + break; default: release_sock(sk); WARN_ON_ONCE(1); @@ -755,7 +764,9 @@ static int mptcp_setsockopt_v4(struct mptcp_sock *msk, int optname, switch (optname) { case IP_FREEBIND: case IP_TRANSPARENT: - return mptcp_setsockopt_sol_ip_set_transparent(msk, optname, optval, optlen); + case IP_BIND_ADDRESS_NO_PORT: + case IP_LOCAL_PORT_RANGE: + return mptcp_setsockopt_sol_ip_set(msk, optname, optval, optlen); case IP_TOS: return mptcp_setsockopt_v4_set_tos(msk, optname, optval, optlen); } @@ -1350,6 +1361,12 @@ static int mptcp_getsockopt_v4(struct mptcp_sock *msk, int optname, switch (optname) { case IP_TOS: return mptcp_put_int_option(msk, optval, optlen, READ_ONCE(inet_sk(sk)->tos)); + case IP_BIND_ADDRESS_NO_PORT: + return mptcp_put_int_option(msk, optval, optlen, + inet_test_bit(BIND_ADDRESS_NO_PORT, sk)); + case IP_LOCAL_PORT_RANGE: + return mptcp_put_int_option(msk, optval, optlen, + READ_ONCE(inet_sk(sk)->local_port_range)); } return -EOPNOTSUPP; @@ -1450,6 +1467,8 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk) inet_assign_bit(TRANSPARENT, ssk, inet_test_bit(TRANSPARENT, sk)); inet_assign_bit(FREEBIND, ssk, inet_test_bit(FREEBIND, sk)); + inet_assign_bit(BIND_ADDRESS_NO_PORT, ssk, inet_test_bit(BIND_ADDRESS_NO_PORT, sk)); + WRITE_ONCE(inet_sk(ssk)->local_port_range, READ_ONCE(inet_sk(sk)->local_port_range)); } void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk) diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index c0d15470a10b..8c7af02f8454 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1829,10 +1829,10 @@ static int genl_bind(struct net *net, int group) continue; grp = &family->mcgrps[i]; - if ((grp->flags & GENL_UNS_ADMIN_PERM) && + if ((grp->flags & GENL_MCAST_CAP_NET_ADMIN) && !ns_capable(net->user_ns, CAP_NET_ADMIN)) ret = -EPERM; - if (grp->cap_sys_admin && + if ((grp->flags & GENL_MCAST_CAP_SYS_ADMIN) && !ns_capable(net->user_ns, CAP_SYS_ADMIN)) ret = -EPERM; diff --git a/net/psample/psample.c b/net/psample/psample.c index c34e902855db..ddd211a151d0 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -32,7 +32,7 @@ enum psample_nl_multicast_groups { static const struct genl_multicast_group psample_nl_mcgrps[] = { [PSAMPLE_NL_MCGRP_CONFIG] = { .name = PSAMPLE_NL_MCGRP_CONFIG_NAME }, [PSAMPLE_NL_MCGRP_SAMPLE] = { .name = PSAMPLE_NL_MCGRP_SAMPLE_NAME, - .flags = GENL_UNS_ADMIN_PERM }, + .flags = GENL_MCAST_CAP_NET_ADMIN, }, }; static struct genl_family psample_nl_family __ro_after_init; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 0a711c184c29..d1f9794ca9b7 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -85,10 +85,21 @@ static void tcf_mirred_release(struct tc_action *a) static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = { [TCA_MIRRED_PARMS] = { .len = sizeof(struct tc_mirred) }, + [TCA_MIRRED_BLOCKID] = NLA_POLICY_MIN(NLA_U32, 1), }; static struct tc_action_ops act_mirred_ops; +static void tcf_mirred_replace_dev(struct tcf_mirred *m, + struct net_device *ndev) +{ + struct net_device *odev; + + odev = rcu_replace_pointer(m->tcfm_dev, ndev, + lockdep_is_held(&m->tcf_lock)); + netdev_put(odev, &m->tcfm_dev_tracker); +} + static int tcf_mirred_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, struct tcf_proto *tp, @@ -126,6 +137,17 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, if (exists && bind) return 0; + if (tb[TCA_MIRRED_BLOCKID] && parm->ifindex) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot specify Block ID and dev simultaneously"); + if (exists) + tcf_idr_release(*a, bind); + else + tcf_idr_cleanup(tn, index); + + return -EINVAL; + } + switch (parm->eaction) { case TCA_EGRESS_MIRROR: case TCA_EGRESS_REDIR: @@ -142,9 +164,10 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, } if (!exists) { - if (!parm->ifindex) { + if (!parm->ifindex && !tb[TCA_MIRRED_BLOCKID]) { tcf_idr_cleanup(tn, index); - NL_SET_ERR_MSG_MOD(extack, "Specified device does not exist"); + NL_SET_ERR_MSG_MOD(extack, + "Must specify device or block"); return -EINVAL; } ret = tcf_idr_create_from_flags(tn, index, est, a, @@ -170,7 +193,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, spin_lock_bh(&m->tcf_lock); if (parm->ifindex) { - struct net_device *odev, *ndev; + struct net_device *ndev; ndev = dev_get_by_index(net, parm->ifindex); if (!ndev) { @@ -179,11 +202,14 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, goto put_chain; } mac_header_xmit = dev_is_mac_header_xmit(ndev); - odev = rcu_replace_pointer(m->tcfm_dev, ndev, - lockdep_is_held(&m->tcf_lock)); - netdev_put(odev, &m->tcfm_dev_tracker); + tcf_mirred_replace_dev(m, ndev); netdev_tracker_alloc(ndev, &m->tcfm_dev_tracker, GFP_ATOMIC); m->tcfm_mac_header_xmit = mac_header_xmit; + m->tcfm_blockid = 0; + } else if (tb[TCA_MIRRED_BLOCKID]) { + tcf_mirred_replace_dev(m, NULL); + m->tcfm_mac_header_xmit = false; + m->tcfm_blockid = nla_get_u32(tb[TCA_MIRRED_BLOCKID]); } goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); m->tcfm_eaction = parm->eaction; @@ -225,48 +251,26 @@ static int tcf_mirred_forward(bool want_ingress, struct sk_buff *skb) return err; } -TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb, - const struct tc_action *a, - struct tcf_result *res) +static int tcf_mirred_to_dev(struct sk_buff *skb, struct tcf_mirred *m, + struct net_device *dev, + const bool m_mac_header_xmit, int m_eaction, + int retval) { - struct tcf_mirred *m = to_mirred(a); - struct sk_buff *skb2 = skb; - bool m_mac_header_xmit; - struct net_device *dev; - unsigned int nest_level; - int retval, err = 0; - bool use_reinsert; + struct sk_buff *skb_to_send = skb; bool want_ingress; bool is_redirect; bool expects_nh; bool at_ingress; - int m_eaction; + bool dont_clone; int mac_len; bool at_nh; + int err; - nest_level = __this_cpu_inc_return(mirred_nest_level); - if (unlikely(nest_level > MIRRED_NEST_LIMIT)) { - net_warn_ratelimited("Packet exceeded mirred recursion limit on dev %s\n", - netdev_name(skb->dev)); - __this_cpu_dec(mirred_nest_level); - return TC_ACT_SHOT; - } - - tcf_lastuse_update(&m->tcf_tm); - tcf_action_update_bstats(&m->common, skb); - - m_mac_header_xmit = READ_ONCE(m->tcfm_mac_header_xmit); - m_eaction = READ_ONCE(m->tcfm_eaction); - retval = READ_ONCE(m->tcf_action); - dev = rcu_dereference_bh(m->tcfm_dev); - if (unlikely(!dev)) { - pr_notice_once("tc mirred: target device is gone\n"); - goto out; - } - + is_redirect = tcf_mirred_is_act_redirect(m_eaction); if (unlikely(!(dev->flags & IFF_UP)) || !netif_carrier_ok(dev)) { net_notice_ratelimited("tc mirred to Houston: device %s is down\n", dev->name); + err = -ENODEV; goto out; } @@ -274,61 +278,188 @@ TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb, * since we can't easily detect the clsact caller, skip clone only for * ingress - that covers the TC S/W datapath. */ - is_redirect = tcf_mirred_is_act_redirect(m_eaction); at_ingress = skb_at_tc_ingress(skb); - use_reinsert = at_ingress && is_redirect && - tcf_mirred_can_reinsert(retval); - if (!use_reinsert) { - skb2 = skb_clone(skb, GFP_ATOMIC); - if (!skb2) + dont_clone = skb_at_tc_ingress(skb) && is_redirect && + tcf_mirred_can_reinsert(retval); + if (!dont_clone) { + skb_to_send = skb_clone(skb, GFP_ATOMIC); + if (!skb_to_send) { + err = -ENOMEM; goto out; + } } want_ingress = tcf_mirred_act_wants_ingress(m_eaction); /* All mirred/redirected skbs should clear previous ct info */ - nf_reset_ct(skb2); + nf_reset_ct(skb_to_send); if (want_ingress && !at_ingress) /* drop dst for egress -> ingress */ - skb_dst_drop(skb2); + skb_dst_drop(skb_to_send); expects_nh = want_ingress || !m_mac_header_xmit; at_nh = skb->data == skb_network_header(skb); if (at_nh != expects_nh) { - mac_len = skb_at_tc_ingress(skb) ? skb->mac_len : + mac_len = at_ingress ? skb->mac_len : skb_network_offset(skb); if (expects_nh) { /* target device/action expect data at nh */ - skb_pull_rcsum(skb2, mac_len); + skb_pull_rcsum(skb_to_send, mac_len); } else { /* target device/action expect data at mac */ - skb_push_rcsum(skb2, mac_len); + skb_push_rcsum(skb_to_send, mac_len); } } - skb2->skb_iif = skb->dev->ifindex; - skb2->dev = dev; + skb_to_send->skb_iif = skb->dev->ifindex; + skb_to_send->dev = dev; - /* mirror is always swallowed */ if (is_redirect) { - skb_set_redirected(skb2, skb2->tc_at_ingress); - - /* let's the caller reinsert the packet, if possible */ - if (use_reinsert) { - err = tcf_mirred_forward(want_ingress, skb); - if (err) - tcf_action_inc_overlimit_qstats(&m->common); - __this_cpu_dec(mirred_nest_level); - return TC_ACT_CONSUMED; - } + if (skb == skb_to_send) + retval = TC_ACT_CONSUMED; + + skb_set_redirected(skb_to_send, skb_to_send->tc_at_ingress); + + err = tcf_mirred_forward(want_ingress, skb_to_send); + } else { + err = tcf_mirred_forward(want_ingress, skb_to_send); } - err = tcf_mirred_forward(want_ingress, skb2); if (err) { out: tcf_action_inc_overlimit_qstats(&m->common); - if (tcf_mirred_is_act_redirect(m_eaction)) + if (is_redirect) retval = TC_ACT_SHOT; } + + return retval; +} + +static int tcf_blockcast_redir(struct sk_buff *skb, struct tcf_mirred *m, + struct tcf_block *block, int m_eaction, + const u32 exception_ifindex, int retval) +{ + struct net_device *dev_prev = NULL; + struct net_device *dev = NULL; + unsigned long index; + int mirred_eaction; + + mirred_eaction = tcf_mirred_act_wants_ingress(m_eaction) ? + TCA_INGRESS_MIRROR : TCA_EGRESS_MIRROR; + + xa_for_each(&block->ports, index, dev) { + if (index == exception_ifindex) + continue; + + if (!dev_prev) + goto assign_prev; + + tcf_mirred_to_dev(skb, m, dev_prev, + dev_is_mac_header_xmit(dev), + mirred_eaction, retval); +assign_prev: + dev_prev = dev; + } + + if (dev_prev) + return tcf_mirred_to_dev(skb, m, dev_prev, + dev_is_mac_header_xmit(dev_prev), + m_eaction, retval); + + return retval; +} + +static int tcf_blockcast_mirror(struct sk_buff *skb, struct tcf_mirred *m, + struct tcf_block *block, int m_eaction, + const u32 exception_ifindex, int retval) +{ + struct net_device *dev = NULL; + unsigned long index; + + xa_for_each(&block->ports, index, dev) { + if (index == exception_ifindex) + continue; + + tcf_mirred_to_dev(skb, m, dev, + dev_is_mac_header_xmit(dev), + m_eaction, retval); + } + + return retval; +} + +static int tcf_blockcast(struct sk_buff *skb, struct tcf_mirred *m, + const u32 blockid, struct tcf_result *res, + int retval) +{ + const u32 exception_ifindex = skb->dev->ifindex; + struct tcf_block *block; + bool is_redirect; + int m_eaction; + + m_eaction = READ_ONCE(m->tcfm_eaction); + is_redirect = tcf_mirred_is_act_redirect(m_eaction); + + /* we are already under rcu protection, so can call block lookup + * directly. + */ + block = tcf_block_lookup(dev_net(skb->dev), blockid); + if (!block || xa_empty(&block->ports)) { + tcf_action_inc_overlimit_qstats(&m->common); + return retval; + } + + if (is_redirect) + return tcf_blockcast_redir(skb, m, block, m_eaction, + exception_ifindex, retval); + + /* If it's not redirect, it is mirror */ + return tcf_blockcast_mirror(skb, m, block, m_eaction, exception_ifindex, + retval); +} + +TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb, + const struct tc_action *a, + struct tcf_result *res) +{ + struct tcf_mirred *m = to_mirred(a); + int retval = READ_ONCE(m->tcf_action); + unsigned int nest_level; + bool m_mac_header_xmit; + struct net_device *dev; + int m_eaction; + u32 blockid; + + nest_level = __this_cpu_inc_return(mirred_nest_level); + if (unlikely(nest_level > MIRRED_NEST_LIMIT)) { + net_warn_ratelimited("Packet exceeded mirred recursion limit on dev %s\n", + netdev_name(skb->dev)); + retval = TC_ACT_SHOT; + goto dec_nest_level; + } + + tcf_lastuse_update(&m->tcf_tm); + tcf_action_update_bstats(&m->common, skb); + + blockid = READ_ONCE(m->tcfm_blockid); + if (blockid) { + retval = tcf_blockcast(skb, m, blockid, res, retval); + goto dec_nest_level; + } + + dev = rcu_dereference_bh(m->tcfm_dev); + if (unlikely(!dev)) { + pr_notice_once("tc mirred: target device is gone\n"); + tcf_action_inc_overlimit_qstats(&m->common); + goto dec_nest_level; + } + + m_mac_header_xmit = READ_ONCE(m->tcfm_mac_header_xmit); + m_eaction = READ_ONCE(m->tcfm_eaction); + + retval = tcf_mirred_to_dev(skb, m, dev, m_mac_header_xmit, m_eaction, + retval); + +dec_nest_level: __this_cpu_dec(mirred_nest_level); return retval; @@ -356,6 +487,7 @@ static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind, }; struct net_device *dev; struct tcf_t t; + u32 blockid; spin_lock_bh(&m->tcf_lock); opt.action = m->tcf_action; @@ -367,6 +499,10 @@ static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind, if (nla_put(skb, TCA_MIRRED_PARMS, sizeof(opt), &opt)) goto nla_put_failure; + blockid = m->tcfm_blockid; + if (blockid && nla_put_u32(skb, TCA_MIRRED_BLOCKID, blockid)) + goto nla_put_failure; + tcf_tm_dump(&t, &m->tcf_tm); if (nla_put_64bit(skb, TCA_MIRRED_TM, sizeof(t), &t, TCA_MIRRED_PAD)) goto nla_put_failure; @@ -397,6 +533,8 @@ static int mirred_device_event(struct notifier_block *unused, * net_device are already rcu protected. */ RCU_INIT_POINTER(m->tcfm_dev, NULL); + } else if (m->tcfm_blockid) { + m->tcfm_blockid = 0; } spin_unlock_bh(&m->tcf_lock); } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 8978cf5531d0..3c50b4037755 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -531,6 +531,7 @@ static void tcf_block_destroy(struct tcf_block *block) { mutex_destroy(&block->lock); mutex_destroy(&block->proto_destroy_lock); + xa_destroy(&block->ports); kfree_rcu(block, rcu); } @@ -1002,6 +1003,7 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q, refcount_set(&block->refcnt, 1); block->net = net; block->index = block_index; + xa_init(&block->ports); /* Don't store q pointer for blocks which are shared */ if (!tcf_block_shared(block)) @@ -1009,12 +1011,13 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q, return block; } -static struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index) +struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index) { struct tcf_net *tn = net_generic(net, tcf_net_id); return idr_find(&tn->idr, block_index); } +EXPORT_SYMBOL(tcf_block_lookup); static struct tcf_block *tcf_block_refcnt_get(struct net *net, u32 block_index) { diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index e9eaf637220e..299086bb6205 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1180,6 +1180,43 @@ skip: return 0; } +static int qdisc_block_add_dev(struct Qdisc *sch, struct net_device *dev, + struct netlink_ext_ack *extack) +{ + const struct Qdisc_class_ops *cl_ops = sch->ops->cl_ops; + struct tcf_block *block; + int err; + + block = cl_ops->tcf_block(sch, TC_H_MIN_INGRESS, NULL); + if (block) { + err = xa_insert(&block->ports, dev->ifindex, dev, GFP_KERNEL); + if (err) { + NL_SET_ERR_MSG(extack, + "ingress block dev insert failed"); + return err; + } + } + + block = cl_ops->tcf_block(sch, TC_H_MIN_EGRESS, NULL); + if (block) { + err = xa_insert(&block->ports, dev->ifindex, dev, GFP_KERNEL); + if (err) { + NL_SET_ERR_MSG(extack, + "Egress block dev insert failed"); + goto err_out; + } + } + + return 0; + +err_out: + block = cl_ops->tcf_block(sch, TC_H_MIN_INGRESS, NULL); + if (block) + xa_erase(&block->ports, dev->ifindex); + + return err; +} + static int qdisc_block_indexes_set(struct Qdisc *sch, struct nlattr **tca, struct netlink_ext_ack *extack) { @@ -1350,6 +1387,10 @@ static struct Qdisc *qdisc_create(struct net_device *dev, qdisc_hash_add(sch, false); trace_qdisc_create(ops, dev, parent); + err = qdisc_block_add_dev(sch, dev, extack); + if (err) + goto err_out4; + return sch; err_out4: diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 8dd0e5925342..e33568df97a5 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -1051,6 +1051,9 @@ static void qdisc_free_cb(struct rcu_head *head) static void __qdisc_destroy(struct Qdisc *qdisc) { const struct Qdisc_ops *ops = qdisc->ops; + struct net_device *dev = qdisc_dev(qdisc); + const struct Qdisc_class_ops *cops; + struct tcf_block *block; #ifdef CONFIG_NET_SCHED qdisc_hash_del(qdisc); @@ -1061,11 +1064,24 @@ static void __qdisc_destroy(struct Qdisc *qdisc) qdisc_reset(qdisc); + cops = ops->cl_ops; + if (ops->ingress_block_get) { + block = cops->tcf_block(qdisc, TC_H_MIN_INGRESS, NULL); + if (block) + xa_erase(&block->ports, dev->ifindex); + } + + if (ops->egress_block_get) { + block = cops->tcf_block(qdisc, TC_H_MIN_EGRESS, NULL); + if (block) + xa_erase(&block->ports, dev->ifindex); + } + if (ops->destroy) ops->destroy(qdisc); module_put(ops->owner); - netdev_put(qdisc_dev(qdisc), &qdisc->dev_tracker); + netdev_put(dev, &qdisc->dev_tracker); trace_qdisc_destroy(qdisc); diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 7fc2f3c6d248..a2cb30af46cb 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -677,8 +677,6 @@ static bool smc_isascii(char *hostname) static void smc_conn_save_peer_info_fce(struct smc_sock *smc, struct smc_clc_msg_accept_confirm *clc) { - struct smc_clc_msg_accept_confirm_v2 *clc_v2 = - (struct smc_clc_msg_accept_confirm_v2 *)clc; struct smc_clc_first_contact_ext *fce; int clc_v2_len; @@ -687,17 +685,15 @@ static void smc_conn_save_peer_info_fce(struct smc_sock *smc, return; if (smc->conn.lgr->is_smcd) { - memcpy(smc->conn.lgr->negotiated_eid, clc_v2->d1.eid, + memcpy(smc->conn.lgr->negotiated_eid, clc->d1.eid, SMC_MAX_EID_LEN); - clc_v2_len = offsetofend(struct smc_clc_msg_accept_confirm_v2, - d1); + clc_v2_len = offsetofend(struct smc_clc_msg_accept_confirm, d1); } else { - memcpy(smc->conn.lgr->negotiated_eid, clc_v2->r1.eid, + memcpy(smc->conn.lgr->negotiated_eid, clc->r1.eid, SMC_MAX_EID_LEN); - clc_v2_len = offsetofend(struct smc_clc_msg_accept_confirm_v2, - r1); + clc_v2_len = offsetofend(struct smc_clc_msg_accept_confirm, r1); } - fce = (struct smc_clc_first_contact_ext *)(((u8 *)clc_v2) + clc_v2_len); + fce = (struct smc_clc_first_contact_ext *)(((u8 *)clc) + clc_v2_len); smc->conn.lgr->peer_os = fce->os_type; smc->conn.lgr->peer_smc_release = fce->release; if (smc_isascii(fce->hostname)) @@ -1048,7 +1044,8 @@ static int smc_find_ism_v2_device_clnt(struct smc_sock *smc, { int rc = SMC_CLC_DECL_NOSMCDDEV; struct smcd_dev *smcd; - int i = 1; + int i = 1, entry = 1; + bool is_virtual; u16 chid; if (smcd_indicated(ini->smc_type_v1)) @@ -1060,14 +1057,23 @@ static int smc_find_ism_v2_device_clnt(struct smc_sock *smc, chid = smc_ism_get_chid(smcd); if (!smc_find_ism_v2_is_unique_chid(chid, ini, i)) continue; + is_virtual = __smc_ism_is_virtual(chid); if (!smc_pnet_is_pnetid_set(smcd->pnetid) || smc_pnet_is_ndev_pnetid(sock_net(&smc->sk), smcd->pnetid)) { + if (is_virtual && entry == SMCD_CLC_MAX_V2_GID_ENTRIES) + /* It's the last GID-CHID entry left in CLC + * Proposal SMC-Dv2 extension, but a virtual + * ISM device will take two entries. So give + * up it and try the next potential ISM device. + */ + continue; ini->ism_dev[i] = smcd; ini->ism_chid[i] = chid; ini->is_smcd = true; rc = 0; i++; - if (i > SMC_MAX_ISM_DEVS) + entry = is_virtual ? entry + 2 : entry + 1; + if (entry > SMCD_CLC_MAX_V2_GID_ENTRIES) break; } } @@ -1149,13 +1155,13 @@ static int smc_connect_ism_vlan_cleanup(struct smc_sock *smc, } #define SMC_CLC_MAX_ACCEPT_LEN \ - (sizeof(struct smc_clc_msg_accept_confirm_v2) + \ + (sizeof(struct smc_clc_msg_accept_confirm) + \ sizeof(struct smc_clc_first_contact_ext_v2x) + \ sizeof(struct smc_clc_msg_trail)) /* CLC handshake during connect */ static int smc_connect_clc(struct smc_sock *smc, - struct smc_clc_msg_accept_confirm_v2 *aclc2, + struct smc_clc_msg_accept_confirm *aclc, struct smc_init_info *ini) { int rc = 0; @@ -1165,7 +1171,7 @@ static int smc_connect_clc(struct smc_sock *smc, if (rc) return rc; /* receive SMC Accept CLC message */ - return smc_clc_wait_msg(smc, aclc2, SMC_CLC_MAX_ACCEPT_LEN, + return smc_clc_wait_msg(smc, aclc, SMC_CLC_MAX_ACCEPT_LEN, SMC_CLC_ACCEPT, CLC_WAIT_TIME); } @@ -1201,10 +1207,8 @@ static int smc_connect_rdma_v2_prepare(struct smc_sock *smc, struct smc_clc_msg_accept_confirm *aclc, struct smc_init_info *ini) { - struct smc_clc_msg_accept_confirm_v2 *clc_v2 = - (struct smc_clc_msg_accept_confirm_v2 *)aclc; struct smc_clc_first_contact_ext *fce = - smc_get_clc_first_contact_ext(clc_v2, false); + smc_get_clc_first_contact_ext(aclc, false); struct net *net = sock_net(&smc->sk); int rc; @@ -1327,10 +1331,7 @@ static int smc_connect_rdma(struct smc_sock *smc, } if (aclc->hdr.version > SMC_V1) { - struct smc_clc_msg_accept_confirm_v2 *clc_v2 = - (struct smc_clc_msg_accept_confirm_v2 *)aclc; - - eid = clc_v2->r1.eid; + eid = aclc->r1.eid; if (ini->first_contact_local) smc_fill_gid_list(link->lgr, &ini->smcrv2.gidlist, link->smcibdev, link->gid); @@ -1371,7 +1372,7 @@ connect_abort: * Determine from the CHID of the received CLC ACCEPT the ISM device chosen. */ static int -smc_v2_determine_accepted_chid(struct smc_clc_msg_accept_confirm_v2 *aclc, +smc_v2_determine_accepted_chid(struct smc_clc_msg_accept_confirm *aclc, struct smc_init_info *ini) { int i; @@ -1398,12 +1399,9 @@ static int smc_connect_ism(struct smc_sock *smc, ini->first_contact_peer = aclc->hdr.typev2 & SMC_FIRST_CONTACT_MASK; if (aclc->hdr.version == SMC_V2) { - struct smc_clc_msg_accept_confirm_v2 *aclc_v2 = - (struct smc_clc_msg_accept_confirm_v2 *)aclc; - if (ini->first_contact_peer) { struct smc_clc_first_contact_ext *fce = - smc_get_clc_first_contact_ext(aclc_v2, true); + smc_get_clc_first_contact_ext(aclc, true); ini->release_nr = fce->release; rc = smc_clc_clnt_v2x_features_validate(fce, ini); @@ -1411,11 +1409,16 @@ static int smc_connect_ism(struct smc_sock *smc, return rc; } - rc = smc_v2_determine_accepted_chid(aclc_v2, ini); + rc = smc_v2_determine_accepted_chid(aclc, ini); if (rc) return rc; + + if (__smc_ism_is_virtual(ini->ism_chid[ini->ism_selected])) + ini->ism_peer_gid[ini->ism_selected].gid_ext = + ntohll(aclc->d1.gid_ext); + /* for non-virtual ISM devices, peer gid_ext remains 0. */ } - ini->ism_peer_gid[ini->ism_selected] = ntohll(aclc->d0.gid); + ini->ism_peer_gid[ini->ism_selected].gid = ntohll(aclc->d0.gid); /* there is only one lgr role for SMC-D; use server lock */ mutex_lock(&smc_server_lgr_pending); @@ -1437,12 +1440,8 @@ static int smc_connect_ism(struct smc_sock *smc, smc_rx_init(smc); smc_tx_init(smc); - if (aclc->hdr.version > SMC_V1) { - struct smc_clc_msg_accept_confirm_v2 *clc_v2 = - (struct smc_clc_msg_accept_confirm_v2 *)aclc; - - eid = clc_v2->d1.eid; - } + if (aclc->hdr.version > SMC_V1) + eid = aclc->d1.eid; rc = smc_clc_send_confirm(smc, ini->first_contact_local, aclc->hdr.version, eid, ini); @@ -1493,7 +1492,6 @@ static int smc_connect_check_aclc(struct smc_init_info *ini, static int __smc_connect(struct smc_sock *smc) { u8 version = smc_ism_is_v2_capable() ? SMC_V2 : SMC_V1; - struct smc_clc_msg_accept_confirm_v2 *aclc2; struct smc_clc_msg_accept_confirm *aclc; struct smc_init_info *ini = NULL; u8 *buf = NULL; @@ -1541,11 +1539,10 @@ static int __smc_connect(struct smc_sock *smc) rc = SMC_CLC_DECL_MEM; goto fallback; } - aclc2 = (struct smc_clc_msg_accept_confirm_v2 *)buf; - aclc = (struct smc_clc_msg_accept_confirm *)aclc2; + aclc = (struct smc_clc_msg_accept_confirm *)buf; /* perform CLC handshake */ - rc = smc_connect_clc(smc, aclc2, ini); + rc = smc_connect_clc(smc, aclc, ini); if (rc) { /* -EAGAIN on timeout, see tcp_recvmsg() */ if (rc == -EAGAIN) { @@ -2106,7 +2103,8 @@ static bool smc_is_already_selected(struct smcd_dev *smcd, /* check for ISM devices matching proposed ISM devices */ static void smc_check_ism_v2_match(struct smc_init_info *ini, - u16 proposed_chid, u64 proposed_gid, + u16 proposed_chid, + struct smcd_gid *proposed_gid, unsigned int *matches) { struct smcd_dev *smcd; @@ -2118,7 +2116,11 @@ static void smc_check_ism_v2_match(struct smc_init_info *ini, continue; if (smc_ism_get_chid(smcd) == proposed_chid && !smc_ism_cantalk(proposed_gid, ISM_RESERVED_VLANID, smcd)) { - ini->ism_peer_gid[*matches] = proposed_gid; + ini->ism_peer_gid[*matches].gid = proposed_gid->gid; + if (__smc_ism_is_virtual(proposed_chid)) + ini->ism_peer_gid[*matches].gid_ext = + proposed_gid->gid_ext; + /* non-virtual ISM's peer gid_ext remains 0. */ ini->ism_dev[*matches] = smcd; (*matches)++; break; @@ -2140,9 +2142,11 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, struct smc_clc_v2_extension *smc_v2_ext; struct smc_clc_msg_smcd *pclc_smcd; unsigned int matches = 0; + struct smcd_gid smcd_gid; u8 smcd_version; u8 *eid = NULL; int i, rc; + u16 chid; if (!(ini->smcd_version & SMC_V2) || !smcd_indicated(ini->smc_type_v2)) goto not_found; @@ -2152,18 +2156,35 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, smcd_v2_ext = smc_get_clc_smcd_v2_ext(smc_v2_ext); mutex_lock(&smcd_dev_list.mutex); - if (pclc_smcd->ism.chid) + if (pclc_smcd->ism.chid) { /* check for ISM device matching proposed native ISM device */ + smcd_gid.gid = ntohll(pclc_smcd->ism.gid); + smcd_gid.gid_ext = 0; smc_check_ism_v2_match(ini, ntohs(pclc_smcd->ism.chid), - ntohll(pclc_smcd->ism.gid), &matches); - for (i = 1; i <= smc_v2_ext->hdr.ism_gid_cnt; i++) { + &smcd_gid, &matches); + } + for (i = 0; i < smc_v2_ext->hdr.ism_gid_cnt; i++) { /* check for ISM devices matching proposed non-native ISM * devices */ - smc_check_ism_v2_match(ini, - ntohs(smcd_v2_ext->gidchid[i - 1].chid), - ntohll(smcd_v2_ext->gidchid[i - 1].gid), - &matches); + smcd_gid.gid = ntohll(smcd_v2_ext->gidchid[i].gid); + smcd_gid.gid_ext = 0; + chid = ntohs(smcd_v2_ext->gidchid[i].chid); + if (__smc_ism_is_virtual(chid)) { + if ((i + 1) == smc_v2_ext->hdr.ism_gid_cnt || + chid != ntohs(smcd_v2_ext->gidchid[i + 1].chid)) + /* each virtual ISM device takes two GID-CHID + * entries and CHID of the second entry repeats + * that of the first entry. + * + * So check if the next GID-CHID entry exists + * and both two entries' CHIDs are the same. + */ + continue; + smcd_gid.gid_ext = + ntohll(smcd_v2_ext->gidchid[++i].gid); + } + smc_check_ism_v2_match(ini, chid, &smcd_gid, &matches); } mutex_unlock(&smcd_dev_list.mutex); @@ -2212,7 +2233,8 @@ static void smc_find_ism_v1_device_serv(struct smc_sock *new_smc, if (!(ini->smcd_version & SMC_V1) || !smcd_indicated(ini->smc_type_v1)) goto not_found; ini->is_smcd = true; /* prepare ISM check */ - ini->ism_peer_gid[0] = ntohll(pclc_smcd->ism.gid); + ini->ism_peer_gid[0].gid = ntohll(pclc_smcd->ism.gid); + ini->ism_peer_gid[0].gid_ext = 0; rc = smc_find_ism_device(new_smc, ini); if (rc) goto not_found; diff --git a/net/smc/smc.h b/net/smc/smc.h index cd51261b7d9e..df64efd2dee8 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -29,9 +29,6 @@ #define SMCPROTO_SMC 0 /* SMC protocol, IPv4 */ #define SMCPROTO_SMC6 1 /* SMC protocol, IPv6 */ -#define SMC_MAX_ISM_DEVS 8 /* max # of proposed non-native ISM - * devices - */ #define SMC_AUTOCORKING_DEFAULT_SIZE 0x10000 /* 64K by default */ extern struct proto smc_proto; @@ -58,6 +55,13 @@ enum smc_state { /* possible states of an SMC socket */ SMC_PROCESSABORT = 27, }; +enum smc_supplemental_features { + SMC_SPF_VIRT_ISM_DEV = 0, +}; + +#define SMC_FEATURE_MASK \ + (BIT(SMC_SPF_VIRT_ISM_DEV)) + struct smc_link_group; struct smc_wr_rx_hdr { /* common prefix part of LLC and CDC to demultiplex */ diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 95e19aa3e769..9a13709bea1c 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -155,10 +155,12 @@ static int smc_clc_ueid_remove(char *ueid) rc = 0; } } +#if IS_ENABLED(CONFIG_S390) if (!rc && !smc_clc_eid_table.ueid_cnt) { smc_clc_eid_table.seid_enabled = 1; rc = -EAGAIN; /* indicate success and enabling of seid */ } +#endif write_unlock(&smc_clc_eid_table.lock); return rc; } @@ -273,22 +275,30 @@ err: int smc_nl_enable_seid(struct sk_buff *skb, struct genl_info *info) { +#if IS_ENABLED(CONFIG_S390) write_lock(&smc_clc_eid_table.lock); smc_clc_eid_table.seid_enabled = 1; write_unlock(&smc_clc_eid_table.lock); return 0; +#else + return -EOPNOTSUPP; +#endif } int smc_nl_disable_seid(struct sk_buff *skb, struct genl_info *info) { int rc = 0; +#if IS_ENABLED(CONFIG_S390) write_lock(&smc_clc_eid_table.lock); if (!smc_clc_eid_table.ueid_cnt) rc = -ENOENT; else smc_clc_eid_table.seid_enabled = 0; write_unlock(&smc_clc_eid_table.lock); +#else + rc = -EOPNOTSUPP; +#endif return rc; } @@ -377,9 +387,9 @@ static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc) /* check arriving CLC accept or confirm */ static bool -smc_clc_msg_acc_conf_valid(struct smc_clc_msg_accept_confirm_v2 *clc_v2) +smc_clc_msg_acc_conf_valid(struct smc_clc_msg_accept_confirm *clc) { - struct smc_clc_msg_hdr *hdr = &clc_v2->hdr; + struct smc_clc_msg_hdr *hdr = &clc->hdr; if (hdr->typev1 != SMC_TYPE_R && hdr->typev1 != SMC_TYPE_D) return false; @@ -418,15 +428,16 @@ smc_clc_msg_decl_valid(struct smc_clc_msg_decline *dclc) return true; } -static int smc_clc_fill_fce(struct smc_clc_first_contact_ext_v2x *fce, - struct smc_init_info *ini) +static int smc_clc_fill_fce_v2x(struct smc_clc_first_contact_ext_v2x *fce_v2x, + struct smc_init_info *ini) { - int ret = sizeof(*fce); + int ret = sizeof(*fce_v2x); - memset(fce, 0, sizeof(*fce)); - fce->fce_v2_base.os_type = SMC_CLC_OS_LINUX; - fce->fce_v2_base.release = ini->release_nr; - memcpy(fce->fce_v2_base.hostname, smc_hostname, sizeof(smc_hostname)); + memset(fce_v2x, 0, sizeof(*fce_v2x)); + fce_v2x->fce_v2_base.os_type = SMC_CLC_OS_LINUX; + fce_v2x->fce_v2_base.release = ini->release_nr; + memcpy(fce_v2x->fce_v2_base.hostname, + smc_hostname, sizeof(smc_hostname)); if (ini->is_smcd && ini->release_nr < SMC_RELEASE_1) { ret = sizeof(struct smc_clc_first_contact_ext); goto out; @@ -434,9 +445,10 @@ static int smc_clc_fill_fce(struct smc_clc_first_contact_ext_v2x *fce, if (ini->release_nr >= SMC_RELEASE_1) { if (!ini->is_smcd) { - fce->max_conns = ini->max_conns; - fce->max_links = ini->max_links; + fce_v2x->max_conns = ini->max_conns; + fce_v2x->max_links = ini->max_links; } + fce_v2x->feature_mask = htons(ini->feature_mask); } out: @@ -448,7 +460,7 @@ out: */ static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm, bool check_trl) { - struct smc_clc_msg_accept_confirm_v2 *clc_v2; + struct smc_clc_msg_accept_confirm *clc; struct smc_clc_msg_proposal *pclc; struct smc_clc_msg_decline *dclc; struct smc_clc_msg_trail *trl; @@ -466,12 +478,11 @@ static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm, bool check_trl) break; case SMC_CLC_ACCEPT: case SMC_CLC_CONFIRM: - clc_v2 = (struct smc_clc_msg_accept_confirm_v2 *)clcm; - if (!smc_clc_msg_acc_conf_valid(clc_v2)) + clc = (struct smc_clc_msg_accept_confirm *)clcm; + if (!smc_clc_msg_acc_conf_valid(clc)) return false; trl = (struct smc_clc_msg_trail *) - ((u8 *)clc_v2 + ntohs(clc_v2->hdr.length) - - sizeof(*trl)); + ((u8 *)clc + ntohs(clc->hdr.length) - sizeof(*trl)); break; case SMC_CLC_DECLINE: dclc = (struct smc_clc_msg_decline *)clcm; @@ -882,11 +893,13 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) ETH_ALEN); } if (smcd_indicated(ini->smc_type_v1)) { + struct smcd_gid smcd_gid; + /* add SMC-D specifics */ if (ini->ism_dev[0]) { smcd = ini->ism_dev[0]; - pclc_smcd->ism.gid = - htonll(smcd->ops->get_local_gid(smcd)); + smcd->ops->get_local_gid(smcd, &smcd_gid); + pclc_smcd->ism.gid = htonll(smcd_gid.gid); pclc_smcd->ism.chid = htons(smc_ism_get_chid(ini->ism_dev[0])); } @@ -907,6 +920,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) pclc_smcd->v2_ext_offset = htons(v2_ext_offset); plen += sizeof(*v2_ext); + v2_ext->feature_mask = htons(SMC_FEATURE_MASK); read_lock(&smc_clc_eid_table.lock); v2_ext->hdr.eid_cnt = smc_clc_eid_table.ueid_cnt; plen += smc_clc_eid_table.ueid_cnt * SMC_MAX_EID_LEN; @@ -918,10 +932,11 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) read_unlock(&smc_clc_eid_table.lock); } if (smcd_indicated(ini->smc_type_v2)) { + struct smcd_gid smcd_gid; u8 *eid = NULL; + int entry = 0; v2_ext->hdr.flag.seid = smc_clc_eid_table.seid_enabled; - v2_ext->hdr.ism_gid_cnt = ini->ism_offered_cnt; v2_ext->hdr.smcd_v2_ext_offset = htons(sizeof(*v2_ext) - offsetofend(struct smc_clnt_opts_area_hdr, smcd_v2_ext_offset) + @@ -933,14 +948,26 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) if (ini->ism_offered_cnt) { for (i = 1; i <= ini->ism_offered_cnt; i++) { smcd = ini->ism_dev[i]; - gidchids[i - 1].gid = - htonll(smcd->ops->get_local_gid(smcd)); - gidchids[i - 1].chid = + smcd->ops->get_local_gid(smcd, &smcd_gid); + gidchids[entry].chid = htons(smc_ism_get_chid(ini->ism_dev[i])); + gidchids[entry].gid = htonll(smcd_gid.gid); + if (smc_ism_is_virtual(smcd)) { + /* a virtual ISM device takes two + * entries. CHID of the second entry + * repeats that of the first entry. + */ + gidchids[entry + 1].chid = + gidchids[entry].chid; + gidchids[entry + 1].gid = + htonll(smcd_gid.gid_ext); + entry++; + } + entry++; } - plen += ini->ism_offered_cnt * - sizeof(struct smc_clc_smcd_gid_chid); + plen += entry * sizeof(struct smc_clc_smcd_gid_chid); } + v2_ext->hdr.ism_gid_cnt = entry; } if (smcr_indicated(ini->smc_type_v2)) { memcpy(v2_ext->roce, ini->smcrv2.ib_gid_v2, SMC_GID_SIZE); @@ -976,7 +1003,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) vec[i++].iov_len = sizeof(*smcd_v2_ext); if (ini->ism_offered_cnt) { vec[i].iov_base = gidchids; - vec[i++].iov_len = ini->ism_offered_cnt * + vec[i++].iov_len = v2_ext->hdr.ism_gid_cnt * sizeof(struct smc_clc_smcd_gid_chid); } } @@ -997,109 +1024,143 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) return reason_code; } +static void +smcd_clc_prep_confirm_accept(struct smc_connection *conn, + struct smc_clc_msg_accept_confirm *clc, + int first_contact, u8 version, + u8 *eid, struct smc_init_info *ini, + int *fce_len, + struct smc_clc_first_contact_ext_v2x *fce_v2x, + struct smc_clc_msg_trail *trl) +{ + struct smcd_dev *smcd = conn->lgr->smcd; + struct smcd_gid smcd_gid; + u16 chid; + int len; + + /* SMC-D specific settings */ + memcpy(clc->hdr.eyecatcher, SMCD_EYECATCHER, + sizeof(SMCD_EYECATCHER)); + smcd->ops->get_local_gid(smcd, &smcd_gid); + clc->hdr.typev1 = SMC_TYPE_D; + clc->d0.gid = htonll(smcd_gid.gid); + clc->d0.token = htonll(conn->rmb_desc->token); + clc->d0.dmbe_size = conn->rmbe_size_comp; + clc->d0.dmbe_idx = 0; + memcpy(&clc->d0.linkid, conn->lgr->id, SMC_LGR_ID_SIZE); + if (version == SMC_V1) { + clc->hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN); + } else { + chid = smc_ism_get_chid(smcd); + clc->d1.chid = htons(chid); + if (eid && eid[0]) + memcpy(clc->d1.eid, eid, SMC_MAX_EID_LEN); + if (__smc_ism_is_virtual(chid)) + clc->d1.gid_ext = htonll(smcd_gid.gid_ext); + len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2; + if (first_contact) { + *fce_len = smc_clc_fill_fce_v2x(fce_v2x, ini); + len += *fce_len; + } + clc->hdr.length = htons(len); + } + memcpy(trl->eyecatcher, SMCD_EYECATCHER, + sizeof(SMCD_EYECATCHER)); +} + +static void +smcr_clc_prep_confirm_accept(struct smc_connection *conn, + struct smc_clc_msg_accept_confirm *clc, + int first_contact, u8 version, + u8 *eid, struct smc_init_info *ini, + int *fce_len, + struct smc_clc_first_contact_ext_v2x *fce_v2x, + struct smc_clc_fce_gid_ext *gle, + struct smc_clc_msg_trail *trl) +{ + struct smc_link *link = conn->lnk; + int len; + + /* SMC-R specific settings */ + memcpy(clc->hdr.eyecatcher, SMC_EYECATCHER, + sizeof(SMC_EYECATCHER)); + clc->hdr.typev1 = SMC_TYPE_R; + memcpy(clc->r0.lcl.id_for_peer, local_systemid, + sizeof(local_systemid)); + memcpy(&clc->r0.lcl.gid, link->gid, SMC_GID_SIZE); + memcpy(&clc->r0.lcl.mac, &link->smcibdev->mac[link->ibport - 1], + ETH_ALEN); + hton24(clc->r0.qpn, link->roce_qp->qp_num); + clc->r0.rmb_rkey = + htonl(conn->rmb_desc->mr[link->link_idx]->rkey); + clc->r0.rmbe_idx = 1; /* for now: 1 RMB = 1 RMBE */ + clc->r0.rmbe_alert_token = htonl(conn->alert_token_local); + switch (clc->hdr.type) { + case SMC_CLC_ACCEPT: + clc->r0.qp_mtu = link->path_mtu; + break; + case SMC_CLC_CONFIRM: + clc->r0.qp_mtu = min(link->path_mtu, link->peer_mtu); + break; + } + clc->r0.rmbe_size = conn->rmbe_size_comp; + clc->r0.rmb_dma_addr = conn->rmb_desc->is_vm ? + cpu_to_be64((uintptr_t)conn->rmb_desc->cpu_addr) : + cpu_to_be64((u64)sg_dma_address + (conn->rmb_desc->sgt[link->link_idx].sgl)); + hton24(clc->r0.psn, link->psn_initial); + if (version == SMC_V1) { + clc->hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN); + } else { + if (eid && eid[0]) + memcpy(clc->r1.eid, eid, SMC_MAX_EID_LEN); + len = SMCR_CLC_ACCEPT_CONFIRM_LEN_V2; + if (first_contact) { + *fce_len = smc_clc_fill_fce_v2x(fce_v2x, ini); + len += *fce_len; + fce_v2x->fce_v2_base.v2_direct = + !link->lgr->uses_gateway; + if (clc->hdr.type == SMC_CLC_CONFIRM) { + memset(gle, 0, sizeof(*gle)); + gle->gid_cnt = ini->smcrv2.gidlist.len; + len += sizeof(*gle); + len += gle->gid_cnt * sizeof(gle->gid[0]); + } + } + clc->hdr.length = htons(len); + } + memcpy(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); +} + /* build and send CLC CONFIRM / ACCEPT message */ static int smc_clc_send_confirm_accept(struct smc_sock *smc, - struct smc_clc_msg_accept_confirm_v2 *clc_v2, + struct smc_clc_msg_accept_confirm *clc, int first_contact, u8 version, u8 *eid, struct smc_init_info *ini) { + struct smc_clc_first_contact_ext_v2x fce_v2x; struct smc_connection *conn = &smc->conn; - struct smc_clc_first_contact_ext_v2x fce; - struct smcd_dev *smcd = conn->lgr->smcd; - struct smc_clc_msg_accept_confirm *clc; struct smc_clc_fce_gid_ext gle; struct smc_clc_msg_trail trl; - int i, len, fce_len; + int i, fce_len; struct kvec vec[5]; struct msghdr msg; /* send SMC Confirm CLC msg */ - clc = (struct smc_clc_msg_accept_confirm *)clc_v2; clc->hdr.version = version; /* SMC version */ if (first_contact) clc->hdr.typev2 |= SMC_FIRST_CONTACT_MASK; - if (conn->lgr->is_smcd) { - /* SMC-D specific settings */ - memcpy(clc->hdr.eyecatcher, SMCD_EYECATCHER, - sizeof(SMCD_EYECATCHER)); - clc->hdr.typev1 = SMC_TYPE_D; - clc->d0.gid = htonll(smcd->ops->get_local_gid(smcd)); - clc->d0.token = htonll(conn->rmb_desc->token); - clc->d0.dmbe_size = conn->rmbe_size_comp; - clc->d0.dmbe_idx = 0; - memcpy(&clc->d0.linkid, conn->lgr->id, SMC_LGR_ID_SIZE); - if (version == SMC_V1) { - clc->hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN); - } else { - clc_v2->d1.chid = htons(smc_ism_get_chid(smcd)); - if (eid && eid[0]) - memcpy(clc_v2->d1.eid, eid, SMC_MAX_EID_LEN); - len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2; - if (first_contact) { - fce_len = smc_clc_fill_fce(&fce, ini); - len += fce_len; - } - clc_v2->hdr.length = htons(len); - } - memcpy(trl.eyecatcher, SMCD_EYECATCHER, - sizeof(SMCD_EYECATCHER)); - } else { - struct smc_link *link = conn->lnk; - - /* SMC-R specific settings */ - memcpy(clc->hdr.eyecatcher, SMC_EYECATCHER, - sizeof(SMC_EYECATCHER)); - clc->hdr.typev1 = SMC_TYPE_R; - clc->hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN); - memcpy(clc->r0.lcl.id_for_peer, local_systemid, - sizeof(local_systemid)); - memcpy(&clc->r0.lcl.gid, link->gid, SMC_GID_SIZE); - memcpy(&clc->r0.lcl.mac, &link->smcibdev->mac[link->ibport - 1], - ETH_ALEN); - hton24(clc->r0.qpn, link->roce_qp->qp_num); - clc->r0.rmb_rkey = - htonl(conn->rmb_desc->mr[link->link_idx]->rkey); - clc->r0.rmbe_idx = 1; /* for now: 1 RMB = 1 RMBE */ - clc->r0.rmbe_alert_token = htonl(conn->alert_token_local); - switch (clc->hdr.type) { - case SMC_CLC_ACCEPT: - clc->r0.qp_mtu = link->path_mtu; - break; - case SMC_CLC_CONFIRM: - clc->r0.qp_mtu = min(link->path_mtu, link->peer_mtu); - break; - } - clc->r0.rmbe_size = conn->rmbe_size_comp; - clc->r0.rmb_dma_addr = conn->rmb_desc->is_vm ? - cpu_to_be64((uintptr_t)conn->rmb_desc->cpu_addr) : - cpu_to_be64((u64)sg_dma_address - (conn->rmb_desc->sgt[link->link_idx].sgl)); - hton24(clc->r0.psn, link->psn_initial); - if (version == SMC_V1) { - clc->hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN); - } else { - if (eid && eid[0]) - memcpy(clc_v2->r1.eid, eid, SMC_MAX_EID_LEN); - len = SMCR_CLC_ACCEPT_CONFIRM_LEN_V2; - if (first_contact) { - fce_len = smc_clc_fill_fce(&fce, ini); - len += fce_len; - fce.fce_v2_base.v2_direct = !link->lgr->uses_gateway; - if (clc->hdr.type == SMC_CLC_CONFIRM) { - memset(&gle, 0, sizeof(gle)); - gle.gid_cnt = ini->smcrv2.gidlist.len; - len += sizeof(gle); - len += gle.gid_cnt * sizeof(gle.gid[0]); - } - } - clc_v2->hdr.length = htons(len); - } - memcpy(trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); - } - + if (conn->lgr->is_smcd) + smcd_clc_prep_confirm_accept(conn, clc, first_contact, + version, eid, ini, &fce_len, + &fce_v2x, &trl); + else + smcr_clc_prep_confirm_accept(conn, clc, first_contact, + version, eid, ini, &fce_len, + &fce_v2x, &gle, &trl); memset(&msg, 0, sizeof(msg)); i = 0; - vec[i].iov_base = clc_v2; + vec[i].iov_base = clc; if (version > SMC_V1) vec[i++].iov_len = (clc->hdr.typev1 == SMC_TYPE_D ? SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 : @@ -1111,7 +1172,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, SMCR_CLC_ACCEPT_CONFIRM_LEN) - sizeof(trl); if (version > SMC_V1 && first_contact) { - vec[i].iov_base = &fce; + vec[i].iov_base = &fce_v2x; vec[i++].iov_len = fce_len; if (!conn->lgr->is_smcd) { if (clc->hdr.type == SMC_CLC_CONFIRM) { @@ -1133,16 +1194,16 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact, u8 version, u8 *eid, struct smc_init_info *ini) { - struct smc_clc_msg_accept_confirm_v2 cclc_v2; + struct smc_clc_msg_accept_confirm cclc; int reason_code = 0; int len; /* send SMC Confirm CLC msg */ - memset(&cclc_v2, 0, sizeof(cclc_v2)); - cclc_v2.hdr.type = SMC_CLC_CONFIRM; - len = smc_clc_send_confirm_accept(smc, &cclc_v2, clnt_first_contact, + memset(&cclc, 0, sizeof(cclc)); + cclc.hdr.type = SMC_CLC_CONFIRM; + len = smc_clc_send_confirm_accept(smc, &cclc, clnt_first_contact, version, eid, ini); - if (len < ntohs(cclc_v2.hdr.length)) { + if (len < ntohs(cclc.hdr.length)) { if (len >= 0) { reason_code = -ENETUNREACH; smc->sk.sk_err = -reason_code; @@ -1158,14 +1219,14 @@ int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact, int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact, u8 version, u8 *negotiated_eid, struct smc_init_info *ini) { - struct smc_clc_msg_accept_confirm_v2 aclc_v2; + struct smc_clc_msg_accept_confirm aclc; int len; - memset(&aclc_v2, 0, sizeof(aclc_v2)); - aclc_v2.hdr.type = SMC_CLC_ACCEPT; - len = smc_clc_send_confirm_accept(new_smc, &aclc_v2, srv_first_contact, + memset(&aclc, 0, sizeof(aclc)); + aclc.hdr.type = SMC_CLC_ACCEPT; + len = smc_clc_send_confirm_accept(new_smc, &aclc, srv_first_contact, version, negotiated_eid, ini); - if (len < ntohs(aclc_v2.hdr.length)) + if (len < ntohs(aclc.hdr.length)) len = len >= 0 ? -EPROTO : -new_smc->clcsock->sk->sk_err; return len > 0 ? 0 : len; @@ -1180,6 +1241,7 @@ int smc_clc_srv_v2x_features_validate(struct smc_sock *smc, ini->max_conns = SMC_CONN_PER_LGR_MAX; ini->max_links = SMC_LINKS_ADD_LNK_MAX; + ini->feature_mask = SMC_FEATURE_MASK; if ((!(ini->smcd_version & SMC_V2) && !(ini->smcr_version & SMC_V2)) || ini->release_nr < SMC_RELEASE_1) @@ -1223,6 +1285,8 @@ int smc_clc_clnt_v2x_features_validate(struct smc_clc_first_contact_ext *fce, return SMC_CLC_DECL_MAXLINKERR; ini->max_links = fce_v2x->max_links; } + /* common supplemental features of server and client */ + ini->feature_mask = ntohs(fce_v2x->feature_mask) & SMC_FEATURE_MASK; return 0; } @@ -1230,10 +1294,8 @@ int smc_clc_clnt_v2x_features_validate(struct smc_clc_first_contact_ext *fce, int smc_clc_v2x_features_confirm_check(struct smc_clc_msg_accept_confirm *cclc, struct smc_init_info *ini) { - struct smc_clc_msg_accept_confirm_v2 *clc_v2 = - (struct smc_clc_msg_accept_confirm_v2 *)cclc; struct smc_clc_first_contact_ext *fce = - smc_get_clc_first_contact_ext(clc_v2, ini->is_smcd); + smc_get_clc_first_contact_ext(cclc, ini->is_smcd); struct smc_clc_first_contact_ext_v2x *fce_v2x = (struct smc_clc_first_contact_ext_v2x *)fce; @@ -1253,6 +1315,8 @@ int smc_clc_v2x_features_confirm_check(struct smc_clc_msg_accept_confirm *cclc, if (fce_v2x->max_links != ini->max_links) return SMC_CLC_DECL_MAXLINKERR; } + /* common supplemental features returned by client */ + ini->feature_mask = ntohs(fce_v2x->feature_mask); return 0; } @@ -1274,7 +1338,11 @@ void __init smc_clc_init(void) INIT_LIST_HEAD(&smc_clc_eid_table.list); rwlock_init(&smc_clc_eid_table.lock); smc_clc_eid_table.ueid_cnt = 0; +#if IS_ENABLED(CONFIG_S390) smc_clc_eid_table.seid_enabled = 1; +#else + smc_clc_eid_table.seid_enabled = 0; +#endif } void smc_clc_exit(void) diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 1697b84d85be..a9f9bdd26dcd 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -138,7 +138,8 @@ struct smc_clc_v2_extension { u8 roce[16]; /* RoCEv2 GID */ u8 max_conns; u8 max_links; - u8 reserved[14]; + __be16 feature_mask; + u8 reserved[12]; u8 user_eids[][SMC_MAX_EID_LEN]; }; @@ -171,6 +172,11 @@ struct smc_clc_msg_proposal { /* clc proposal message sent by Linux */ #define SMC_CLC_MAX_V6_PREFIX 8 #define SMC_CLC_MAX_UEID 8 +#define SMCD_CLC_MAX_V2_GID_ENTRIES 8 /* max # of CHID-GID entries in CLC + * proposal SMC-Dv2 extension. + * each ISM device takes one entry and + * each virtual ISM takes two entries. + */ struct smc_clc_msg_proposal_area { struct smc_clc_msg_proposal pclc_base; @@ -180,7 +186,8 @@ struct smc_clc_msg_proposal_area { struct smc_clc_v2_extension pclc_v2_ext; u8 user_eids[SMC_CLC_MAX_UEID][SMC_MAX_EID_LEN]; struct smc_clc_smcd_v2_extension pclc_smcd_v2_ext; - struct smc_clc_smcd_gid_chid pclc_gidchids[SMC_MAX_ISM_DEVS]; + struct smc_clc_smcd_gid_chid + pclc_gidchids[SMCD_CLC_MAX_V2_GID_ENTRIES]; struct smc_clc_msg_trail pclc_trl; }; @@ -240,9 +247,14 @@ struct smc_clc_first_contact_ext { struct smc_clc_first_contact_ext_v2x { struct smc_clc_first_contact_ext fce_v2_base; - u8 max_conns; /* for SMC-R only */ - u8 max_links; /* for SMC-R only */ - u8 reserved3[2]; + union { + struct { + u8 max_conns; /* for SMC-R only */ + u8 max_links; /* for SMC-R only */ + }; + u8 reserved3[2]; /* for SMC-D only */ + }; + __be16 feature_mask; __be32 vendor_exp_options; u8 reserved4[8]; } __packed; /* format defined in @@ -259,28 +271,21 @@ struct smc_clc_fce_gid_ext { struct smc_clc_msg_accept_confirm { /* clc accept / confirm message */ struct smc_clc_msg_hdr hdr; union { - struct smcr_clc_msg_accept_confirm r0; /* SMC-R */ - struct { /* SMC-D */ - struct smcd_clc_msg_accept_confirm_common d0; - u32 reserved5[3]; - }; - }; -} __packed; /* format defined in RFC7609 */ - -struct smc_clc_msg_accept_confirm_v2 { /* clc accept / confirm message */ - struct smc_clc_msg_hdr hdr; - union { struct { /* SMC-R */ struct smcr_clc_msg_accept_confirm r0; - u8 eid[SMC_MAX_EID_LEN]; - u8 reserved6[8]; - } r1; + struct { /* v2 only */ + u8 eid[SMC_MAX_EID_LEN]; + u8 reserved6[8]; + } __packed r1; + }; struct { /* SMC-D */ struct smcd_clc_msg_accept_confirm_common d0; - __be16 chid; - u8 eid[SMC_MAX_EID_LEN]; - u8 reserved5[8]; - } d1; + struct { /* v2 only, but 12 bytes reserved in v1 */ + __be16 chid; + u8 eid[SMC_MAX_EID_LEN]; + __be64 gid_ext; + } __packed d1; + }; }; }; @@ -389,24 +394,23 @@ smc_get_clc_smcd_v2_ext(struct smc_clc_v2_extension *prop_v2ext) } static inline struct smc_clc_first_contact_ext * -smc_get_clc_first_contact_ext(struct smc_clc_msg_accept_confirm_v2 *clc_v2, +smc_get_clc_first_contact_ext(struct smc_clc_msg_accept_confirm *clc, bool is_smcd) { int clc_v2_len; - if (clc_v2->hdr.version == SMC_V1 || - !(clc_v2->hdr.typev2 & SMC_FIRST_CONTACT_MASK)) + if (clc->hdr.version == SMC_V1 || + !(clc->hdr.typev2 & SMC_FIRST_CONTACT_MASK)) return NULL; if (is_smcd) clc_v2_len = - offsetofend(struct smc_clc_msg_accept_confirm_v2, d1); + offsetofend(struct smc_clc_msg_accept_confirm, d1); else clc_v2_len = - offsetofend(struct smc_clc_msg_accept_confirm_v2, r1); + offsetofend(struct smc_clc_msg_accept_confirm, r1); - return (struct smc_clc_first_contact_ext *)(((u8 *)clc_v2) + - clc_v2_len); + return (struct smc_clc_first_contact_ext *)(((u8 *)clc) + clc_v2_len); } struct smcd_dev; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index d520ee62c8ec..95cc95458e2d 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -506,6 +506,7 @@ static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr, { char smc_pnet[SMC_MAX_PNETID_LEN + 1]; struct smcd_dev *smcd = lgr->smcd; + struct smcd_gid smcd_gid; struct nlattr *attrs; void *nlh; @@ -521,13 +522,19 @@ static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr, if (nla_put_u32(skb, SMC_NLA_LGR_D_ID, *((u32 *)&lgr->id))) goto errattr; + smcd->ops->get_local_gid(smcd, &smcd_gid); if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_GID, - smcd->ops->get_local_gid(smcd), - SMC_NLA_LGR_D_PAD)) + smcd_gid.gid, SMC_NLA_LGR_D_PAD)) goto errattr; - if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_PEER_GID, lgr->peer_gid, + if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_EXT_GID, + smcd_gid.gid_ext, SMC_NLA_LGR_D_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_PEER_GID, lgr->peer_gid.gid, SMC_NLA_LGR_D_PAD)) goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_PEER_EXT_GID, + lgr->peer_gid.gid_ext, SMC_NLA_LGR_D_PAD)) + goto errattr; if (nla_put_u8(skb, SMC_NLA_LGR_D_VLAN_ID, lgr->vlan_id)) goto errattr; if (nla_put_u32(skb, SMC_NLA_LGR_D_CONNS_NUM, lgr->conns_num)) @@ -876,7 +883,10 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) /* SMC-D specific settings */ smcd = ini->ism_dev[ini->ism_selected]; get_device(smcd->ops->get_dev(smcd)); - lgr->peer_gid = ini->ism_peer_gid[ini->ism_selected]; + lgr->peer_gid.gid = + ini->ism_peer_gid[ini->ism_selected].gid; + lgr->peer_gid.gid_ext = + ini->ism_peer_gid[ini->ism_selected].gid_ext; lgr->smcd = ini->ism_dev[ini->ism_selected]; lgr_list = &ini->ism_dev[ini->ism_selected]->lgr_list; lgr_lock = &lgr->smcd->lgr_lock; @@ -1514,7 +1524,8 @@ void smc_lgr_terminate_sched(struct smc_link_group *lgr) } /* Called when peer lgr shutdown (regularly or abnormally) is received */ -void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid, unsigned short vlan) +void smc_smcd_terminate(struct smcd_dev *dev, struct smcd_gid *peer_gid, + unsigned short vlan) { struct smc_link_group *lgr, *l; LIST_HEAD(lgr_free_list); @@ -1522,9 +1533,12 @@ void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid, unsigned short vlan) /* run common cleanup function and build free list */ spin_lock_bh(&dev->lgr_lock); list_for_each_entry_safe(lgr, l, &dev->lgr_list, list) { - if ((!peer_gid || lgr->peer_gid == peer_gid) && + if ((!peer_gid->gid || + (lgr->peer_gid.gid == peer_gid->gid && + !smc_ism_is_virtual(dev) ? 1 : + lgr->peer_gid.gid_ext == peer_gid->gid_ext)) && (vlan == VLAN_VID_MASK || lgr->vlan_id == vlan)) { - if (peer_gid) /* peer triggered termination */ + if (peer_gid->gid) /* peer triggered termination */ lgr->peer_shutdown = 1; list_move(&lgr->list, &lgr_free_list); lgr->freeing = 1; @@ -1860,9 +1874,12 @@ static bool smcr_lgr_match(struct smc_link_group *lgr, u8 smcr_version, } static bool smcd_lgr_match(struct smc_link_group *lgr, - struct smcd_dev *smcismdev, u64 peer_gid) + struct smcd_dev *smcismdev, + struct smcd_gid *peer_gid) { - return lgr->peer_gid == peer_gid && lgr->smcd == smcismdev; + return lgr->peer_gid.gid == peer_gid->gid && lgr->smcd == smcismdev && + smc_ism_is_virtual(smcismdev) ? + (lgr->peer_gid.gid_ext == peer_gid->gid_ext) : 1; } /* create a new SMC connection (and a new link group if necessary) */ @@ -1892,7 +1909,7 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini) write_lock_bh(&lgr->conns_lock); if ((ini->is_smcd ? smcd_lgr_match(lgr, ini->ism_dev[ini->ism_selected], - ini->ism_peer_gid[ini->ism_selected]) : + &ini->ism_peer_gid[ini->ism_selected]) : smcr_lgr_match(lgr, ini->smcr_version, ini->peer_systemid, ini->peer_gid, ini->peer_mac, role, diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 120027d40469..1f175376037b 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -17,9 +17,11 @@ #include <linux/pci.h> #include <rdma/ib_verbs.h> #include <net/genetlink.h> +#include <net/smc.h> #include "smc.h" #include "smc_ib.h" +#include "smc_clc.h" #define SMC_RMBS_PER_LGR_MAX 255 /* max. # of RMBs per link group */ #define SMC_CONN_PER_LGR_MIN 16 /* min. # of connections per link group */ @@ -355,7 +357,7 @@ struct smc_link_group { /* max links can be added in lgr */ }; struct { /* SMC-D */ - u64 peer_gid; + struct smcd_gid peer_gid; /* Peer GID (remote) */ struct smcd_dev *smcd; /* ISM device for VLAN reg. */ @@ -392,6 +394,11 @@ struct smc_init_info_smcrv2 { struct smc_gidlist gidlist; }; +#define SMC_MAX_V2_ISM_DEVS SMCD_CLC_MAX_V2_GID_ENTRIES + /* max # of proposed non-native ISM devices, + * which can't exceed the max # of CHID-GID + * entries in CLC proposal SMC-Dv2 extension. + */ struct smc_init_info { u8 is_smcd; u8 smc_type_v1; @@ -401,6 +408,7 @@ struct smc_init_info { u8 max_links; u8 first_contact_peer; u8 first_contact_local; + u16 feature_mask; unsigned short vlan_id; u32 rc; u8 negotiated_eid[SMC_MAX_EID_LEN]; @@ -416,9 +424,9 @@ struct smc_init_info { u32 ib_clcqpn; struct smc_init_info_smcrv2 smcrv2; /* SMC-D */ - u64 ism_peer_gid[SMC_MAX_ISM_DEVS + 1]; - struct smcd_dev *ism_dev[SMC_MAX_ISM_DEVS + 1]; - u16 ism_chid[SMC_MAX_ISM_DEVS + 1]; + struct smcd_gid ism_peer_gid[SMC_MAX_V2_ISM_DEVS + 1]; + struct smcd_dev *ism_dev[SMC_MAX_V2_ISM_DEVS + 1]; + u16 ism_chid[SMC_MAX_V2_ISM_DEVS + 1]; u8 ism_offered_cnt; /* # of ISM devices offered */ u8 ism_selected; /* index of selected ISM dev*/ u8 smcd_version; @@ -544,7 +552,7 @@ void smc_lgr_hold(struct smc_link_group *lgr); void smc_lgr_put(struct smc_link_group *lgr); void smcr_port_add(struct smc_ib_device *smcibdev, u8 ibport); void smcr_port_err(struct smc_ib_device *smcibdev, u8 ibport); -void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid, +void smc_smcd_terminate(struct smcd_dev *dev, struct smcd_gid *peer_gid, unsigned short vlan); void smc_smcd_terminate_all(struct smcd_dev *dev); void smc_smcr_terminate_all(struct smc_ib_device *smcibdev); diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index a584613aca12..3fbe14e09ad8 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -21,6 +21,7 @@ #include "smc.h" #include "smc_core.h" +#include "smc_ism.h" struct smc_diag_dump_ctx { int pos[2]; @@ -168,12 +169,16 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, struct smc_connection *conn = &smc->conn; struct smcd_diag_dmbinfo dinfo; struct smcd_dev *smcd = conn->lgr->smcd; + struct smcd_gid smcd_gid; memset(&dinfo, 0, sizeof(dinfo)); dinfo.linkid = *((u32 *)conn->lgr->id); - dinfo.peer_gid = conn->lgr->peer_gid; - dinfo.my_gid = smcd->ops->get_local_gid(smcd); + dinfo.peer_gid = conn->lgr->peer_gid.gid; + dinfo.peer_gid_ext = conn->lgr->peer_gid.gid_ext; + smcd->ops->get_local_gid(smcd, &smcd_gid); + dinfo.my_gid = smcd_gid.gid; + dinfo.my_gid_ext = smcd_gid.gid_ext; dinfo.token = conn->rmb_desc->token; dinfo.peer_token = conn->peer_token; diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c index fbee2493091f..ac88de2a06a0 100644 --- a/net/smc/smc_ism.c +++ b/net/smc/smc_ism.c @@ -43,8 +43,30 @@ static struct ism_client smc_ism_client = { }; #endif +static void smc_ism_create_system_eid(void) +{ + struct smc_ism_seid *seid = + (struct smc_ism_seid *)smc_ism_v2_system_eid; +#if IS_ENABLED(CONFIG_S390) + struct cpuid id; + u16 ident_tail; + char tmp[5]; + + memcpy(seid->seid_string, "IBM-SYSZ-ISMSEID00000000", 24); + get_cpu_id(&id); + ident_tail = (u16)(id.ident & SMC_ISM_IDENT_MASK); + snprintf(tmp, 5, "%04X", ident_tail); + memcpy(seid->serial_number, tmp, 4); + snprintf(tmp, 5, "%04X", id.machine); + memcpy(seid->type, tmp, 4); +#else + memset(seid, 0, SMC_MAX_EID_LEN); +#endif +} + /* Test if an ISM communication is possible - same CPC */ -int smc_ism_cantalk(u64 peer_gid, unsigned short vlan_id, struct smcd_dev *smcd) +int smc_ism_cantalk(struct smcd_gid *peer_gid, unsigned short vlan_id, + struct smcd_dev *smcd) { return smcd->ops->query_remote_gid(smcd, peer_gid, vlan_id ? 1 : 0, vlan_id); @@ -208,7 +230,7 @@ int smc_ism_register_dmb(struct smc_link_group *lgr, int dmb_len, dmb.dmb_len = dmb_len; dmb.sba_idx = dmb_desc->sba_idx; dmb.vlan_id = lgr->vlan_id; - dmb.rgid = lgr->peer_gid; + dmb.rgid = lgr->peer_gid.gid; rc = lgr->smcd->ops->register_dmb(lgr->smcd, &dmb, &smc_ism_client); if (!rc) { dmb_desc->sba_idx = dmb.sba_idx; @@ -340,18 +362,20 @@ union smcd_sw_event_info { static void smcd_handle_sw_event(struct smc_ism_event_work *wrk) { + struct smcd_gid peer_gid = { .gid = wrk->event.tok, + .gid_ext = 0 }; union smcd_sw_event_info ev_info; ev_info.info = wrk->event.info; switch (wrk->event.code) { case ISM_EVENT_CODE_SHUTDOWN: /* Peer shut down DMBs */ - smc_smcd_terminate(wrk->smcd, wrk->event.tok, ev_info.vlan_id); + smc_smcd_terminate(wrk->smcd, &peer_gid, ev_info.vlan_id); break; case ISM_EVENT_CODE_TESTLINK: /* Activity timer */ if (ev_info.code == ISM_EVENT_REQUEST) { ev_info.code = ISM_EVENT_RESPONSE; wrk->smcd->ops->signal_event(wrk->smcd, - wrk->event.tok, + &peer_gid, ISM_EVENT_REQUEST_IR, ISM_EVENT_CODE_TESTLINK, ev_info.info); @@ -365,10 +389,12 @@ static void smc_ism_event_work(struct work_struct *work) { struct smc_ism_event_work *wrk = container_of(work, struct smc_ism_event_work, work); + struct smcd_gid smcd_gid = { .gid = wrk->event.tok, + .gid_ext = 0 }; switch (wrk->event.type) { case ISM_EVENT_GID: /* GID event, token is peer GID */ - smc_smcd_terminate(wrk->smcd, wrk->event.tok, VLAN_VID_MASK); + smc_smcd_terminate(wrk->smcd, &smcd_gid, VLAN_VID_MASK); break; case ISM_EVENT_DMB: break; @@ -426,14 +452,8 @@ static void smcd_register_dev(struct ism_dev *ism) mutex_lock(&smcd_dev_list.mutex); if (list_empty(&smcd_dev_list.list)) { - u8 *system_eid = NULL; - - system_eid = smcd->ops->get_system_eid(); - if (smcd->ops->supports_v2()) { + if (smcd->ops->supports_v2()) smc_ism_v2_capable = true; - memcpy(smc_ism_v2_system_eid, system_eid, - SMC_MAX_EID_LEN); - } } /* sort list: devices without pnetid before devices with pnetid */ if (smcd->pnetid[0]) @@ -525,7 +545,7 @@ int smc_ism_signal_shutdown(struct smc_link_group *lgr) memcpy(ev_info.uid, lgr->id, SMC_LGR_ID_SIZE); ev_info.vlan_id = lgr->vlan_id; ev_info.code = ISM_EVENT_REQUEST; - rc = lgr->smcd->ops->signal_event(lgr->smcd, lgr->peer_gid, + rc = lgr->smcd->ops->signal_event(lgr->smcd, &lgr->peer_gid, ISM_EVENT_REQUEST_IR, ISM_EVENT_CODE_SHUTDOWN, ev_info.info); @@ -537,10 +557,10 @@ int smc_ism_init(void) { int rc = 0; -#if IS_ENABLED(CONFIG_ISM) smc_ism_v2_capable = false; - memset(smc_ism_v2_system_eid, 0, SMC_MAX_EID_LEN); + smc_ism_create_system_eid(); +#if IS_ENABLED(CONFIG_ISM) rc = ism_register_client(&smc_ism_client); #endif return rc; diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h index 832b2f42d79f..ffff40c30a06 100644 --- a/net/smc/smc_ism.h +++ b/net/smc/smc_ism.h @@ -15,6 +15,9 @@ #include "smc.h" +#define SMC_VIRTUAL_ISM_CHID_MASK 0xFF00 +#define SMC_ISM_IDENT_MASK 0x00FFFF + struct smcd_dev_list { /* List of SMCD devices */ struct list_head list; struct mutex mutex; /* Protects list of devices */ @@ -28,9 +31,16 @@ struct smc_ism_vlanid { /* VLAN id set on ISM device */ refcount_t refcnt; /* Reference count */ }; +struct smc_ism_seid { + u8 seid_string[24]; + u8 serial_number[4]; + u8 type[4]; +}; + struct smcd_dev; -int smc_ism_cantalk(u64 peer_gid, unsigned short vlan_id, struct smcd_dev *dev); +int smc_ism_cantalk(struct smcd_gid *peer_gid, unsigned short vlan_id, + struct smcd_dev *dev); void smc_ism_set_conn(struct smc_connection *conn); void smc_ism_unset_conn(struct smc_connection *conn); int smc_ism_get_vlan(struct smcd_dev *dev, unsigned short vlan_id); @@ -56,4 +66,22 @@ static inline int smc_ism_write(struct smcd_dev *smcd, u64 dmb_tok, return rc < 0 ? rc : 0; } +static inline bool __smc_ism_is_virtual(u16 chid) +{ + /* CHIDs in range of 0xFF00 to 0xFFFF are reserved + * for virtual ISM device. + * + * loopback-ism: 0xFFFF + * virtio-ism: 0xFF00 ~ 0xFFFE + */ + return ((chid & 0xFF00) == 0xFF00); +} + +static inline bool smc_ism_is_virtual(struct smcd_dev *smcd) +{ + u16 chid = smcd->ops->get_chid(smcd); + + return __smc_ism_is_virtual(chid); +} + #endif diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 11775401df68..9f2c58c5a86b 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -1103,8 +1103,8 @@ static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev, list_for_each_entry(ismdev, &smcd_dev_list.list, list) { if (smc_pnet_match(ismdev->pnetid, ndev_pnetid) && !ismdev->going_away && - (!ini->ism_peer_gid[0] || - !smc_ism_cantalk(ini->ism_peer_gid[0], ini->vlan_id, + (!ini->ism_peer_gid[0].gid || + !smc_ism_cantalk(&ini->ism_peer_gid[0], ini->vlan_id, ismdev))) { ini->ism_dev[0] = ismdev; break; diff --git a/net/tipc/link.c b/net/tipc/link.c index d0143823658d..0716eb5c8a31 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -82,10 +82,7 @@ struct tipc_stats { * struct tipc_link - TIPC link data structure * @addr: network address of link's peer node * @name: link name character string - * @media_addr: media address to use when sending messages over link - * @timer: link timer * @net: pointer to namespace struct - * @refcnt: reference counter for permanent references (owner node & timer) * @peer_session: link session # being used by peer end of link * @peer_bearer_id: bearer id used by link's peer endpoint * @bearer_id: local bearer id used by link @@ -94,31 +91,19 @@ struct tipc_stats { * @state: current state of link FSM * @peer_caps: bitmap describing capabilities of peer node * @silent_intv_cnt: # of timer intervals without any reception from peer - * @proto_msg: template for control messages generated by link - * @pmsg: convenience pointer to "proto_msg" field * @priority: current link priority * @net_plane: current link network plane ('A' through 'H') * @mon_state: cookie with information needed by link monitor - * @backlog_limit: backlog queue congestion thresholds (indexed by importance) - * @exp_msg_count: # of tunnelled messages expected during link changeover - * @reset_rcv_checkpt: seq # of last acknowledged message at time of link reset * @mtu: current maximum packet size for this link * @advertised_mtu: advertised own mtu when link is being established - * @transmitq: queue for sent, non-acked messages * @backlogq: queue for messages waiting to be sent - * @snt_nxt: next sequence number to use for outbound messages * @ackers: # of peers that needs to ack each packet before it can be released * @acked: # last packet acked by a certain peer. Used for broadcast. * @rcv_nxt: next sequence number to expect for inbound messages - * @deferred_queue: deferred queue saved OOS b'cast message received from node - * @unacked_window: # of inbound messages rx'd without ack'ing back to peer * @inputq: buffer queue for messages to be delivered upwards * @namedq: buffer queue for name table messages to be delivered upwards - * @next_out: ptr to first unsent outbound message in queue * @wakeupq: linked list of wakeup msgs waiting for link congestion to abate - * @long_msg_seq_no: next identifier to use for outbound fragmented messages * @reasm_buf: head of partially reassembled inbound message fragments - * @bc_rcvr: marks that this is a broadcast receiver link * @stats: collects statistics regarding link activity * @session: session to be used by link * @snd_nxt_state: next send seq number diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index aad8ffeaee04..f7a7c7798c3b 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -704,7 +704,7 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) rc = -EINVAL; } release_sock(sk); - SOCK_DEBUG(sk, "x25_bind: socket is bound\n"); + net_dbg_ratelimited("x25_bind: socket is bound\n"); out: return rc; } @@ -1165,10 +1165,10 @@ static int x25_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) goto out; } - SOCK_DEBUG(sk, "x25_sendmsg: sendto: Addresses built.\n"); + net_dbg_ratelimited("x25_sendmsg: sendto: Addresses built.\n"); /* Build a packet */ - SOCK_DEBUG(sk, "x25_sendmsg: sendto: building packet.\n"); + net_dbg_ratelimited("x25_sendmsg: sendto: building packet.\n"); if ((msg->msg_flags & MSG_OOB) && len > 32) len = 32; @@ -1187,7 +1187,7 @@ static int x25_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) /* * Put the data on the end */ - SOCK_DEBUG(sk, "x25_sendmsg: Copying user data\n"); + net_dbg_ratelimited("x25_sendmsg: Copying user data\n"); skb_reset_transport_header(skb); skb_put(skb, len); @@ -1211,7 +1211,7 @@ static int x25_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) /* * Push down the X.25 header */ - SOCK_DEBUG(sk, "x25_sendmsg: Building X.25 Header.\n"); + net_dbg_ratelimited("x25_sendmsg: Building X.25 Header.\n"); if (msg->msg_flags & MSG_OOB) { if (x25->neighbour->extended) { @@ -1245,8 +1245,8 @@ static int x25_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) skb->data[0] |= X25_Q_BIT; } - SOCK_DEBUG(sk, "x25_sendmsg: Built header.\n"); - SOCK_DEBUG(sk, "x25_sendmsg: Transmitting buffer\n"); + net_dbg_ratelimited("x25_sendmsg: Built header.\n"); + net_dbg_ratelimited("x25_sendmsg: Transmitting buffer\n"); rc = -ENOTCONN; if (sk->sk_state != TCP_ESTABLISHED) diff --git a/net/x25/x25_facilities.c b/net/x25/x25_facilities.c index 8e1a49b0c0dc..6dadb217e101 100644 --- a/net/x25/x25_facilities.c +++ b/net/x25/x25_facilities.c @@ -282,7 +282,7 @@ int x25_negotiate_facilities(struct sk_buff *skb, struct sock *sk, * They want reverse charging, we won't accept it. */ if ((theirs.reverse & 0x01 ) && (ours->reverse & 0x01)) { - SOCK_DEBUG(sk, "X.25: rejecting reverse charging request\n"); + net_dbg_ratelimited("X.25: rejecting reverse charging request\n"); return -1; } @@ -294,11 +294,11 @@ int x25_negotiate_facilities(struct sk_buff *skb, struct sock *sk, int ours_in = ours->throughput & 0x0f; int ours_out = ours->throughput & 0xf0; if (!ours_in || theirs_in < ours_in) { - SOCK_DEBUG(sk, "X.25: inbound throughput negotiated\n"); + net_dbg_ratelimited("X.25: inbound throughput negotiated\n"); new->throughput = (new->throughput & 0xf0) | theirs_in; } if (!ours_out || theirs_out < ours_out) { - SOCK_DEBUG(sk, + net_dbg_ratelimited( "X.25: outbound throughput negotiated\n"); new->throughput = (new->throughput & 0x0f) | theirs_out; } @@ -306,22 +306,22 @@ int x25_negotiate_facilities(struct sk_buff *skb, struct sock *sk, if (theirs.pacsize_in && theirs.pacsize_out) { if (theirs.pacsize_in < ours->pacsize_in) { - SOCK_DEBUG(sk, "X.25: packet size inwards negotiated down\n"); + net_dbg_ratelimited("X.25: packet size inwards negotiated down\n"); new->pacsize_in = theirs.pacsize_in; } if (theirs.pacsize_out < ours->pacsize_out) { - SOCK_DEBUG(sk, "X.25: packet size outwards negotiated down\n"); + net_dbg_ratelimited("X.25: packet size outwards negotiated down\n"); new->pacsize_out = theirs.pacsize_out; } } if (theirs.winsize_in && theirs.winsize_out) { if (theirs.winsize_in < ours->winsize_in) { - SOCK_DEBUG(sk, "X.25: window size inwards negotiated down\n"); + net_dbg_ratelimited("X.25: window size inwards negotiated down\n"); new->winsize_in = theirs.winsize_in; } if (theirs.winsize_out < ours->winsize_out) { - SOCK_DEBUG(sk, "X.25: window size outwards negotiated down\n"); + net_dbg_ratelimited("X.25: window size outwards negotiated down\n"); new->winsize_out = theirs.winsize_out; } } diff --git a/net/x25/x25_out.c b/net/x25/x25_out.c index dbc0940bf35f..f8922b0e23a4 100644 --- a/net/x25/x25_out.c +++ b/net/x25/x25_out.c @@ -72,7 +72,7 @@ int x25_output(struct sock *sk, struct sk_buff *skb) kfree_skb(skb); return sent; } - SOCK_DEBUG(sk, "x25_output: fragment alloc" + net_dbg_ratelimited("x25_output: fragment alloc" " failed, err=%d, %d bytes " "sent\n", err, sent); return err; diff --git a/samples/bpf/cpustat_user.c b/samples/bpf/cpustat_user.c index ab90bb08a2b4..356f756cba0d 100644 --- a/samples/bpf/cpustat_user.c +++ b/samples/bpf/cpustat_user.c @@ -66,10 +66,10 @@ static void cpu_stat_print(void) printf("CPU-%-6d ", j); for (i = 0; i < MAX_CSTATE_ENTRIES; i++) - printf("%-11ld ", data->cstate[i] / 1000000); + printf("%-11lu ", data->cstate[i] / 1000000); for (i = 0; i < MAX_PSTATE_ENTRIES; i++) - printf("%-11ld ", data->pstate[i] / 1000000); + printf("%-11lu ", data->pstate[i] / 1000000); printf("\n"); } diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index 77ceea575dc7..2324cc42b017 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -188,6 +188,9 @@ enum libbpf_tristate { !!sym; \ }) +#define __arg_ctx __attribute__((btf_decl_tag("arg:ctx"))) +#define __arg_nonnull __attribute((btf_decl_tag("arg:nonnull"))) + #ifndef ___bpf_concat #define ___bpf_concat(a, b) a ## b #endif diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index ac54ebc0629f..ebcfb2147fbd 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -4355,6 +4355,8 @@ bpf_object__collect_prog_relos(struct bpf_object *obj, Elf64_Shdr *shdr, Elf_Dat scn = elf_sec_by_idx(obj, sec_idx); scn_data = elf_sec_data(obj, scn); + if (!scn_data) + return -LIBBPF_ERRNO__FORMAT; relo_sec_name = elf_sec_str(obj, shdr->sh_name); sec_name = elf_sec_name(obj, scn); diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index 52a2901e8bd0..16bca56002ab 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -719,6 +719,9 @@ static int linker_sanity_check_elf(struct src_obj *obj) return -EINVAL; } + if (is_dwarf_sec_name(sec->sec_name)) + continue; + if (sec->shdr->sh_addralign && !is_pow_of_2(sec->shdr->sh_addralign)) { pr_warn("ELF section #%zu alignment %llu is non pow-of-2 alignment in %s\n", sec->sec_idx, (long long unsigned)sec->shdr->sh_addralign, diff --git a/tools/testing/selftests/bpf/benchs/bench_htab_mem.c b/tools/testing/selftests/bpf/benchs/bench_htab_mem.c index 9146d3f414d2..926ee822143e 100644 --- a/tools/testing/selftests/bpf/benchs/bench_htab_mem.c +++ b/tools/testing/selftests/bpf/benchs/bench_htab_mem.c @@ -335,6 +335,7 @@ static void htab_mem_report_final(struct bench_res res[], int res_cnt) " peak memory usage %7.2lfMiB\n", loop_mean, loop_stddev, mem_mean, mem_stddev, peak_mem / 1048576.0); + close(ctx.fd); cleanup_cgroup_environment(); } diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c index 8ec73fdfcdab..f29fc789c14b 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c @@ -348,7 +348,8 @@ static void test_func_sockmap_update(void) } static void test_obj_load_failure_common(const char *obj_file, - const char *target_obj_file) + const char *target_obj_file, + const char *exp_msg) { /* * standalone test that asserts failure to load freplace prog @@ -356,6 +357,7 @@ static void test_obj_load_failure_common(const char *obj_file, */ struct bpf_object *obj = NULL, *pkt_obj; struct bpf_program *prog; + char log_buf[64 * 1024]; int err, pkt_fd; __u32 duration = 0; @@ -374,11 +376,21 @@ static void test_obj_load_failure_common(const char *obj_file, err = bpf_program__set_attach_target(prog, pkt_fd, NULL); ASSERT_OK(err, "set_attach_target"); + log_buf[0] = '\0'; + if (exp_msg) + bpf_program__set_log_buf(prog, log_buf, sizeof(log_buf)); + if (env.verbosity > VERBOSE_NONE) + bpf_program__set_log_level(prog, 2); + /* It should fail to load the program */ err = bpf_object__load(obj); + if (env.verbosity > VERBOSE_NONE && exp_msg) /* we overtook log */ + printf("VERIFIER LOG:\n================\n%s\n================\n", log_buf); if (CHECK(!err, "bpf_obj_load should fail", "err %d\n", err)) goto close_prog; + if (exp_msg) + ASSERT_HAS_SUBSTR(log_buf, exp_msg, "fail_msg"); close_prog: bpf_object__close(obj); bpf_object__close(pkt_obj); @@ -388,14 +400,24 @@ static void test_func_replace_return_code(void) { /* test invalid return code in the replaced program */ test_obj_load_failure_common("./freplace_connect_v4_prog.bpf.o", - "./connect4_prog.bpf.o"); + "./connect4_prog.bpf.o", NULL); } static void test_func_map_prog_compatibility(void) { /* test with spin lock map value in the replaced program */ test_obj_load_failure_common("./freplace_attach_probe.bpf.o", - "./test_attach_probe.bpf.o"); + "./test_attach_probe.bpf.o", NULL); +} + +static void test_func_replace_unreliable(void) +{ + /* freplace'ing unreliable main prog should fail with error + * "Cannot replace static functions" + */ + test_obj_load_failure_common("freplace_unreliable_prog.bpf.o", + "./verifier_btf_unreliable_prog.bpf.o", + "Cannot replace static functions"); } static void test_func_replace_global_func(void) @@ -563,6 +585,8 @@ void serial_test_fexit_bpf2bpf(void) test_func_replace_return_code(); if (test__start_subtest("func_map_prog_compatibility")) test_func_map_prog_compatibility(); + if (test__start_subtest("func_replace_unreliable")) + test_func_replace_unreliable(); if (test__start_subtest("func_replace_multi")) test_func_replace_multi(); if (test__start_subtest("fmod_ret_freplace")) diff --git a/tools/testing/selftests/bpf/prog_tests/log_fixup.c b/tools/testing/selftests/bpf/prog_tests/log_fixup.c index effd78b2a657..7a3fa2ff567b 100644 --- a/tools/testing/selftests/bpf/prog_tests/log_fixup.c +++ b/tools/testing/selftests/bpf/prog_tests/log_fixup.c @@ -169,9 +169,9 @@ void test_log_fixup(void) if (test__start_subtest("bad_core_relo_trunc_none")) bad_core_relo(0, TRUNC_NONE /* full buf */); if (test__start_subtest("bad_core_relo_trunc_partial")) - bad_core_relo(300, TRUNC_PARTIAL /* truncate original log a bit */); + bad_core_relo(280, TRUNC_PARTIAL /* truncate original log a bit */); if (test__start_subtest("bad_core_relo_trunc_full")) - bad_core_relo(210, TRUNC_FULL /* truncate also libbpf's message patch */); + bad_core_relo(220, TRUNC_FULL /* truncate also libbpf's message patch */); if (test__start_subtest("bad_core_relo_subprog")) bad_core_relo_subprog(); if (test__start_subtest("missing_map")) diff --git a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c index 0c9abd279e18..820d0bcfc474 100644 --- a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c +++ b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c @@ -590,12 +590,7 @@ static void range_cond(enum num_t t, struct range x, struct range y, *newy = range(t, max_t(t, x.a, y.a), min_t(t, x.b, y.b)); break; case OP_NE: - /* generic case, can't derive more information */ - *newx = range(t, x.a, x.b); - *newy = range(t, y.a, y.b); - break; - - /* below extended logic is not supported by verifier just yet */ + /* below logic is supported by the verifier now */ if (x.a == x.b && x.a == y.a) { /* X is a constant matching left side of Y */ *newx = range(t, x.a, x.b); @@ -2097,10 +2092,22 @@ static struct subtest_case crafted_cases[] = { {U32, S32, {0, U32_MAX}, {U32_MAX, U32_MAX}}, - {S32, U64, {(u32)(s32)S32_MIN, (u32)(s32)S32_MIN}, {(u32)(s32)-255, 0}}, - {S32, S64, {(u32)(s32)S32_MIN, (u32)(s32)-255}, {(u32)(s32)-2, 0}}, - {S32, S64, {0, 1}, {(u32)(s32)S32_MIN, (u32)(s32)S32_MIN}}, - {S32, U32, {(u32)(s32)S32_MIN, (u32)(s32)S32_MIN}, {(u32)(s32)S32_MIN, (u32)(s32)S32_MIN}}, + {S32, U64, {(u32)S32_MIN, (u32)S32_MIN}, {(u32)(s32)-255, 0}}, + {S32, S64, {(u32)S32_MIN, (u32)(s32)-255}, {(u32)(s32)-2, 0}}, + {S32, S64, {0, 1}, {(u32)S32_MIN, (u32)S32_MIN}}, + {S32, U32, {(u32)S32_MIN, (u32)S32_MIN}, {(u32)S32_MIN, (u32)S32_MIN}}, + + /* edge overlap testings for BPF_NE */ + {U64, U64, {0, U64_MAX}, {U64_MAX, U64_MAX}}, + {U64, U64, {0, U64_MAX}, {0, 0}}, + {S64, U64, {S64_MIN, 0}, {S64_MIN, S64_MIN}}, + {S64, U64, {S64_MIN, 0}, {0, 0}}, + {S64, U64, {S64_MIN, S64_MAX}, {S64_MAX, S64_MAX}}, + {U32, U32, {0, U32_MAX}, {0, 0}}, + {U32, U32, {0, U32_MAX}, {U32_MAX, U32_MAX}}, + {S32, U32, {(u32)S32_MIN, 0}, {0, 0}}, + {S32, U32, {(u32)S32_MIN, 0}, {(u32)S32_MIN, (u32)S32_MIN}}, + {S32, U32, {(u32)S32_MIN, S32_MAX}, {S32_MAX, S32_MAX}}, }; /* Go over crafted hard-coded cases. This is fast, so we do it as part of diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index ac49ec25211d..d62c5bf00e71 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -14,6 +14,7 @@ #include "verifier_bpf_get_stack.skel.h" #include "verifier_bswap.skel.h" #include "verifier_btf_ctx_access.skel.h" +#include "verifier_btf_unreliable_prog.skel.h" #include "verifier_cfg.skel.h" #include "verifier_cgroup_inv_retcode.skel.h" #include "verifier_cgroup_skb.skel.h" @@ -125,6 +126,7 @@ void test_verifier_bounds_mix_sign_unsign(void) { RUN(verifier_bounds_mix_sign_u void test_verifier_bpf_get_stack(void) { RUN(verifier_bpf_get_stack); } void test_verifier_bswap(void) { RUN(verifier_bswap); } void test_verifier_btf_ctx_access(void) { RUN(verifier_btf_ctx_access); } +void test_verifier_btf_unreliable_prog(void) { RUN(verifier_btf_unreliable_prog); } void test_verifier_cfg(void) { RUN(verifier_cfg); } void test_verifier_cgroup_inv_retcode(void) { RUN(verifier_cgroup_inv_retcode); } void test_verifier_cgroup_skb(void) { RUN(verifier_cgroup_skb); } diff --git a/tools/testing/selftests/bpf/progs/cgrp_kfunc_failure.c b/tools/testing/selftests/bpf/progs/cgrp_kfunc_failure.c index 0fa564a5cc5b..9fe9c4a4e8f6 100644 --- a/tools/testing/selftests/bpf/progs/cgrp_kfunc_failure.c +++ b/tools/testing/selftests/bpf/progs/cgrp_kfunc_failure.c @@ -78,7 +78,7 @@ int BPF_PROG(cgrp_kfunc_acquire_fp, struct cgroup *cgrp, const char *path) } SEC("kretprobe/cgroup_destroy_locked") -__failure __msg("reg type unsupported for arg#0 function") +__failure __msg("calling kernel function bpf_cgroup_acquire is not allowed") int BPF_PROG(cgrp_kfunc_acquire_unsafe_kretprobe, struct cgroup *cgrp) { struct cgroup *acquired; diff --git a/tools/testing/selftests/bpf/progs/freplace_unreliable_prog.c b/tools/testing/selftests/bpf/progs/freplace_unreliable_prog.c new file mode 100644 index 000000000000..624078abf3de --- /dev/null +++ b/tools/testing/selftests/bpf/progs/freplace_unreliable_prog.c @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +SEC("freplace/btf_unreliable_kprobe") +/* context type is what BPF verifier expects for kprobe context, but target + * program has `stuct whatever *ctx` argument, so freplace operation will be + * rejected with the following message: + * + * arg0 replace_btf_unreliable_kprobe(struct pt_regs *) doesn't match btf_unreliable_kprobe(struct whatever *) + */ +int replace_btf_unreliable_kprobe(bpf_user_pt_regs_t *ctx) +{ + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/task_kfunc_failure.c b/tools/testing/selftests/bpf/progs/task_kfunc_failure.c index dcdea3127086..ad88a3796ddf 100644 --- a/tools/testing/selftests/bpf/progs/task_kfunc_failure.c +++ b/tools/testing/selftests/bpf/progs/task_kfunc_failure.c @@ -248,7 +248,7 @@ int BPF_PROG(task_kfunc_from_pid_no_null_check, struct task_struct *task, u64 cl } SEC("lsm/task_free") -__failure __msg("reg type unsupported for arg#0 function") +__failure __msg("R1 must be a rcu pointer") int BPF_PROG(task_kfunc_from_lsm_task_free, struct task_struct *task) { struct task_struct *acquired; diff --git a/tools/testing/selftests/bpf/progs/test_bpf_ma.c b/tools/testing/selftests/bpf/progs/test_bpf_ma.c index b685a4aba6bd..069db9085e78 100644 --- a/tools/testing/selftests/bpf/progs/test_bpf_ma.c +++ b/tools/testing/selftests/bpf/progs/test_bpf_ma.c @@ -17,7 +17,7 @@ struct generic_map_value { char _license[] SEC("license") = "GPL"; -const unsigned int data_sizes[] = {8, 16, 32, 64, 96, 128, 192, 256, 512, 1024, 2048, 4096}; +const unsigned int data_sizes[] = {16, 32, 64, 96, 128, 192, 256, 512, 1024, 2048, 4096}; const volatile unsigned int data_btf_ids[ARRAY_SIZE(data_sizes)] = {}; int err = 0; @@ -166,7 +166,7 @@ static __always_inline void batch_percpu_free(struct bpf_map *map, unsigned int batch_percpu_free((struct bpf_map *)(&array_percpu_##size), batch, idx); \ } while (0) -DEFINE_ARRAY_WITH_KPTR(8); +/* kptr doesn't support bin_data_8 which is a zero-sized array */ DEFINE_ARRAY_WITH_KPTR(16); DEFINE_ARRAY_WITH_KPTR(32); DEFINE_ARRAY_WITH_KPTR(64); @@ -198,21 +198,20 @@ int test_batch_alloc_free(void *ctx) if ((u32)bpf_get_current_pid_tgid() != pid) return 0; - /* Alloc 128 8-bytes objects in batch to trigger refilling, - * then free 128 8-bytes objects in batch to trigger freeing. + /* Alloc 128 16-bytes objects in batch to trigger refilling, + * then free 128 16-bytes objects in batch to trigger freeing. */ - CALL_BATCH_ALLOC_FREE(8, 128, 0); - CALL_BATCH_ALLOC_FREE(16, 128, 1); - CALL_BATCH_ALLOC_FREE(32, 128, 2); - CALL_BATCH_ALLOC_FREE(64, 128, 3); - CALL_BATCH_ALLOC_FREE(96, 128, 4); - CALL_BATCH_ALLOC_FREE(128, 128, 5); - CALL_BATCH_ALLOC_FREE(192, 128, 6); - CALL_BATCH_ALLOC_FREE(256, 128, 7); - CALL_BATCH_ALLOC_FREE(512, 64, 8); - CALL_BATCH_ALLOC_FREE(1024, 32, 9); - CALL_BATCH_ALLOC_FREE(2048, 16, 10); - CALL_BATCH_ALLOC_FREE(4096, 8, 11); + CALL_BATCH_ALLOC_FREE(16, 128, 0); + CALL_BATCH_ALLOC_FREE(32, 128, 1); + CALL_BATCH_ALLOC_FREE(64, 128, 2); + CALL_BATCH_ALLOC_FREE(96, 128, 3); + CALL_BATCH_ALLOC_FREE(128, 128, 4); + CALL_BATCH_ALLOC_FREE(192, 128, 5); + CALL_BATCH_ALLOC_FREE(256, 128, 6); + CALL_BATCH_ALLOC_FREE(512, 64, 7); + CALL_BATCH_ALLOC_FREE(1024, 32, 8); + CALL_BATCH_ALLOC_FREE(2048, 16, 9); + CALL_BATCH_ALLOC_FREE(4096, 8, 10); return 0; } @@ -223,21 +222,20 @@ int test_free_through_map_free(void *ctx) if ((u32)bpf_get_current_pid_tgid() != pid) return 0; - /* Alloc 128 8-bytes objects in batch to trigger refilling, + /* Alloc 128 16-bytes objects in batch to trigger refilling, * then free these objects through map free. */ - CALL_BATCH_ALLOC(8, 128, 0); - CALL_BATCH_ALLOC(16, 128, 1); - CALL_BATCH_ALLOC(32, 128, 2); - CALL_BATCH_ALLOC(64, 128, 3); - CALL_BATCH_ALLOC(96, 128, 4); - CALL_BATCH_ALLOC(128, 128, 5); - CALL_BATCH_ALLOC(192, 128, 6); - CALL_BATCH_ALLOC(256, 128, 7); - CALL_BATCH_ALLOC(512, 64, 8); - CALL_BATCH_ALLOC(1024, 32, 9); - CALL_BATCH_ALLOC(2048, 16, 10); - CALL_BATCH_ALLOC(4096, 8, 11); + CALL_BATCH_ALLOC(16, 128, 0); + CALL_BATCH_ALLOC(32, 128, 1); + CALL_BATCH_ALLOC(64, 128, 2); + CALL_BATCH_ALLOC(96, 128, 3); + CALL_BATCH_ALLOC(128, 128, 4); + CALL_BATCH_ALLOC(192, 128, 5); + CALL_BATCH_ALLOC(256, 128, 6); + CALL_BATCH_ALLOC(512, 64, 7); + CALL_BATCH_ALLOC(1024, 32, 8); + CALL_BATCH_ALLOC(2048, 16, 9); + CALL_BATCH_ALLOC(4096, 8, 10); return 0; } @@ -251,17 +249,17 @@ int test_batch_percpu_alloc_free(void *ctx) /* Alloc 128 16-bytes per-cpu objects in batch to trigger refilling, * then free 128 16-bytes per-cpu objects in batch to trigger freeing. */ - CALL_BATCH_PERCPU_ALLOC_FREE(16, 128, 1); - CALL_BATCH_PERCPU_ALLOC_FREE(32, 128, 2); - CALL_BATCH_PERCPU_ALLOC_FREE(64, 128, 3); - CALL_BATCH_PERCPU_ALLOC_FREE(96, 128, 4); - CALL_BATCH_PERCPU_ALLOC_FREE(128, 128, 5); - CALL_BATCH_PERCPU_ALLOC_FREE(192, 128, 6); - CALL_BATCH_PERCPU_ALLOC_FREE(256, 128, 7); - CALL_BATCH_PERCPU_ALLOC_FREE(512, 64, 8); - CALL_BATCH_PERCPU_ALLOC_FREE(1024, 32, 9); - CALL_BATCH_PERCPU_ALLOC_FREE(2048, 16, 10); - CALL_BATCH_PERCPU_ALLOC_FREE(4096, 8, 11); + CALL_BATCH_PERCPU_ALLOC_FREE(16, 128, 0); + CALL_BATCH_PERCPU_ALLOC_FREE(32, 128, 1); + CALL_BATCH_PERCPU_ALLOC_FREE(64, 128, 2); + CALL_BATCH_PERCPU_ALLOC_FREE(96, 128, 3); + CALL_BATCH_PERCPU_ALLOC_FREE(128, 128, 4); + CALL_BATCH_PERCPU_ALLOC_FREE(192, 128, 5); + CALL_BATCH_PERCPU_ALLOC_FREE(256, 128, 6); + CALL_BATCH_PERCPU_ALLOC_FREE(512, 64, 7); + CALL_BATCH_PERCPU_ALLOC_FREE(1024, 32, 8); + CALL_BATCH_PERCPU_ALLOC_FREE(2048, 16, 9); + CALL_BATCH_PERCPU_ALLOC_FREE(4096, 8, 10); return 0; } @@ -275,17 +273,17 @@ int test_percpu_free_through_map_free(void *ctx) /* Alloc 128 16-bytes per-cpu objects in batch to trigger refilling, * then free these object through map free. */ - CALL_BATCH_PERCPU_ALLOC(16, 128, 1); - CALL_BATCH_PERCPU_ALLOC(32, 128, 2); - CALL_BATCH_PERCPU_ALLOC(64, 128, 3); - CALL_BATCH_PERCPU_ALLOC(96, 128, 4); - CALL_BATCH_PERCPU_ALLOC(128, 128, 5); - CALL_BATCH_PERCPU_ALLOC(192, 128, 6); - CALL_BATCH_PERCPU_ALLOC(256, 128, 7); - CALL_BATCH_PERCPU_ALLOC(512, 64, 8); - CALL_BATCH_PERCPU_ALLOC(1024, 32, 9); - CALL_BATCH_PERCPU_ALLOC(2048, 16, 10); - CALL_BATCH_PERCPU_ALLOC(4096, 8, 11); + CALL_BATCH_PERCPU_ALLOC(16, 128, 0); + CALL_BATCH_PERCPU_ALLOC(32, 128, 1); + CALL_BATCH_PERCPU_ALLOC(64, 128, 2); + CALL_BATCH_PERCPU_ALLOC(96, 128, 3); + CALL_BATCH_PERCPU_ALLOC(128, 128, 4); + CALL_BATCH_PERCPU_ALLOC(192, 128, 5); + CALL_BATCH_PERCPU_ALLOC(256, 128, 6); + CALL_BATCH_PERCPU_ALLOC(512, 64, 7); + CALL_BATCH_PERCPU_ALLOC(1024, 32, 8); + CALL_BATCH_PERCPU_ALLOC(2048, 16, 9); + CALL_BATCH_PERCPU_ALLOC(4096, 8, 10); return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_global_func5.c b/tools/testing/selftests/bpf/progs/test_global_func5.c index cc55aedaf82d..257c0569ff98 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func5.c +++ b/tools/testing/selftests/bpf/progs/test_global_func5.c @@ -26,7 +26,7 @@ int f3(int val, struct __sk_buff *skb) } SEC("tc") -__failure __msg("expected pointer to ctx, but got PTR") +__failure __msg("expects pointer to ctx") int global_func5(struct __sk_buff *skb) { return f1(skb) + f2(2, skb) + f3(3, skb); diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c index ec430b71730b..960998f16306 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bounds.c +++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c @@ -1075,4 +1075,66 @@ l0_%=: r0 = 0; \ : __clobber_all); } +SEC("tc") +__description("bounds check with JMP_NE for reg edge") +__success __retval(0) +__naked void reg_not_equal_const(void) +{ + asm volatile (" \ + r6 = r1; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + call %[bpf_get_prandom_u32]; \ + r4 = r0; \ + r4 &= 7; \ + if r4 != 0 goto l0_%=; \ + r0 = 0; \ + exit; \ +l0_%=: r1 = r6; \ + r2 = 0; \ + r3 = r10; \ + r3 += -8; \ + r5 = 0; \ + /* The 4th argument of bpf_skb_store_bytes is defined as \ + * ARG_CONST_SIZE, so 0 is not allowed. The 'r4 != 0' \ + * is providing us this exclusion of zero from initial \ + * [0, 7] range. \ + */ \ + call %[bpf_skb_store_bytes]; \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32), + __imm(bpf_skb_store_bytes) + : __clobber_all); +} + +SEC("tc") +__description("bounds check with JMP_EQ for reg edge") +__success __retval(0) +__naked void reg_equal_const(void) +{ + asm volatile (" \ + r6 = r1; \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + call %[bpf_get_prandom_u32]; \ + r4 = r0; \ + r4 &= 7; \ + if r4 == 0 goto l0_%=; \ + r1 = r6; \ + r2 = 0; \ + r3 = r10; \ + r3 += -8; \ + r5 = 0; \ + /* Just the same as what we do in reg_not_equal_const() */ \ + call %[bpf_skb_store_bytes]; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32), + __imm(bpf_skb_store_bytes) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_btf_unreliable_prog.c b/tools/testing/selftests/bpf/progs/verifier_btf_unreliable_prog.c new file mode 100644 index 000000000000..36e033a2e02c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_btf_unreliable_prog.c @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2017 Facebook + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> +#include "bpf_misc.h" + +struct whatever {}; + +SEC("kprobe") +__success __log_level(2) +/* context type is wrong, making it impossible to freplace this program */ +int btf_unreliable_kprobe(struct whatever *ctx) +{ + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c index bd696a431244..9eeb2d89cda8 100644 --- a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c +++ b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c @@ -1,12 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ -#include <stdbool.h> -#include <errno.h> -#include <string.h> -#include <linux/bpf.h> +#include <vmlinux.h> #include <bpf/bpf_helpers.h> #include "bpf_misc.h" +#include "xdp_metadata.h" +#include "bpf_kfuncs.h" int arr[1]; int unkn_idx; @@ -98,4 +97,96 @@ int unguarded_unsupp_global_called(void) return global_unsupp(&x); } +long stack[128]; + +__weak int subprog_nullable_ptr_bad(int *p) +{ + return (*p) * 2; /* bad, missing null check */ +} + +SEC("?raw_tp") +__failure __log_level(2) +__msg("invalid mem access 'mem_or_null'") +int arg_tag_nullable_ptr_fail(void *ctx) +{ + int x = 42; + + return subprog_nullable_ptr_bad(&x); +} + +__noinline __weak int subprog_nonnull_ptr_good(int *p1 __arg_nonnull, int *p2 __arg_nonnull) +{ + return (*p1) * (*p2); /* good, no need for NULL checks */ +} + +int x = 47; + +SEC("?raw_tp") +__success __log_level(2) +int arg_tag_nonnull_ptr_good(void *ctx) +{ + int y = 74; + + return subprog_nonnull_ptr_good(&x, &y); +} + +/* this global subprog can be now called from many types of entry progs, each + * with different context type + */ +__weak int subprog_ctx_tag(void *ctx __arg_ctx) +{ + return bpf_get_stack(ctx, stack, sizeof(stack), 0); +} + +SEC("?raw_tp") +__success __log_level(2) +int arg_tag_ctx_raw_tp(void *ctx) +{ + return subprog_ctx_tag(ctx); +} + +SEC("?tp") +__success __log_level(2) +int arg_tag_ctx_tp(void *ctx) +{ + return subprog_ctx_tag(ctx); +} + +SEC("?kprobe") +__success __log_level(2) +int arg_tag_ctx_kprobe(void *ctx) +{ + return subprog_ctx_tag(ctx); +} + +__weak int subprog_dynptr(struct bpf_dynptr *dptr) +{ + long *d, t, buf[1] = {}; + + d = bpf_dynptr_data(dptr, 0, sizeof(long)); + if (!d) + return 0; + + t = *d + 1; + + d = bpf_dynptr_slice(dptr, 0, &buf, sizeof(long)); + if (!d) + return t; + + t = *d + 2; + + return t; +} + +SEC("?xdp") +__success __log_level(2) +int arg_tag_dynptr(struct xdp_md *ctx) +{ + struct bpf_dynptr dptr; + + bpf_dynptr_from_xdp(ctx, 0, &dptr); + + return subprog_dynptr(&dptr); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh index cd2fb43eea61..74954f6a8f94 100644 --- a/tools/testing/selftests/kselftest/runner.sh +++ b/tools/testing/selftests/kselftest/runner.sh @@ -6,6 +6,7 @@ export skip_rc=4 export timeout_rc=124 export logfile=/dev/stdout export per_test_logging= +export RUN_IN_NETNS= # Defaults for "settings" file fields: # "timeout" how many seconds to let each test run before running @@ -47,7 +48,7 @@ run_one() { DIR="$1" TEST="$2" - NUM="$3" + local test_num="$3" BASENAME_TEST=$(basename $TEST) @@ -141,6 +142,33 @@ run_one() fi } +in_netns() +{ + local name=$1 + ip netns exec $name bash <<-EOF + BASE_DIR=$BASE_DIR + source $BASE_DIR/kselftest/runner.sh + logfile=$logfile + run_one $DIR $TEST $test_num + EOF +} + +run_in_netns() +{ + local netns=$(mktemp -u ${BASENAME_TEST}-XXXXXX) + local tmplog="/tmp/$(mktemp -u ${BASENAME_TEST}-XXXXXX)" + ip netns add $netns + if [ $? -ne 0 ]; then + echo "# Warning: Create namespace failed for $BASENAME_TEST" + echo "not ok $test_num selftests: $DIR: $BASENAME_TEST # Create NS failed" + fi + ip -n $netns link set lo up + in_netns $netns &> $tmplog + ip netns del $netns &> /dev/null + cat $tmplog + rm -f $tmplog +} + run_many() { echo "TAP version 13" @@ -155,6 +183,12 @@ run_many() logfile="/tmp/$BASENAME_TEST" cat /dev/null > "$logfile" fi - run_one "$DIR" "$TEST" "$test_num" + if [ -n "$RUN_IN_NETNS" ]; then + run_in_netns & + else + run_one "$DIR" "$TEST" "$test_num" + fi done + + wait } diff --git a/tools/testing/selftests/net/forwarding/ethtool_mm.sh b/tools/testing/selftests/net/forwarding/ethtool_mm.sh index 39e736f30322..50d5bfb17ef1 100755 --- a/tools/testing/selftests/net/forwarding/ethtool_mm.sh +++ b/tools/testing/selftests/net/forwarding/ethtool_mm.sh @@ -25,6 +25,10 @@ traffic_test() local after= local delta= + if [ ${has_pmac_stats[$if]} = false ]; then + src="aggregate" + fi + before=$(ethtool_std_stats_get $if "eth-mac" "FramesTransmittedOK" $src) $MZ $if -q -c $num_pkts -p 64 -b bcast -t ip -R $PREEMPTIBLE_PRIO @@ -155,15 +159,48 @@ manual_failed_verification_h2_to_h1() manual_failed_verification $h2 $h1 } +smallest_supported_add_frag_size() +{ + local iface=$1 + local rx_min_frag_size= + + rx_min_frag_size=$(ethtool --json --show-mm $iface | \ + jq '.[]."rx-min-frag-size"') + + if [ $rx_min_frag_size -le 60 ]; then + echo 0 + elif [ $rx_min_frag_size -le 124 ]; then + echo 1 + elif [ $rx_min_frag_size -le 188 ]; then + echo 2 + elif [ $rx_min_frag_size -le 252 ]; then + echo 3 + else + echo "$iface: RX min frag size $rx_min_frag_size cannot be advertised over LLDP" + exit 1 + fi +} + +expected_add_frag_size() +{ + local iface=$1 + local requested=$2 + local min=$(smallest_supported_add_frag_size $iface) + + [ $requested -le $min ] && echo $min || echo $requested +} + lldp_change_add_frag_size() { local add_frag_size=$1 + local pattern= lldptool -T -i $h1 -V addEthCaps addFragSize=$add_frag_size >/dev/null # Wait for TLVs to be received sleep 2 - lldptool -i $h2 -t -n -V addEthCaps | \ - grep -q "Additional fragment size: $add_frag_size" + pattern=$(printf "Additional fragment size: %d" \ + $(expected_add_frag_size $h1 $add_frag_size)) + lldptool -i $h2 -t -n -V addEthCaps | grep -q "$pattern" } lldp() @@ -284,6 +321,13 @@ for netif in ${NETIFS[@]}; do echo "SKIP: $netif does not support MAC Merge" exit $ksft_skip fi + + if check_ethtool_pmac_std_stats_support $netif eth-mac; then + has_pmac_stats[$netif]=true + else + has_pmac_stats[$netif]=false + echo "$netif does not report pMAC statistics, falling back to aggregate" + fi done trap cleanup EXIT diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index e3740163c384..69ef2a40df21 100755 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -155,6 +155,15 @@ check_ethtool_counter_group_support() fi } +check_ethtool_pmac_std_stats_support() +{ + local dev=$1; shift + local grp=$1; shift + + [ 0 -ne $(ethtool --json -S $dev --all-groups --src pmac 2>/dev/null \ + | jq ".[].\"$grp\" | length") ] +} + check_locked_port_support() { if ! bridge -d link show | grep -q " locked"; then diff --git a/tools/testing/selftests/net/gre_gso.sh b/tools/testing/selftests/net/gre_gso.sh index 3224651db97b..5100d90f92d2 100755 --- a/tools/testing/selftests/net/gre_gso.sh +++ b/tools/testing/selftests/net/gre_gso.sh @@ -2,10 +2,8 @@ # SPDX-License-Identifier: GPL-2.0 # This test is for checking GRE GSO. - +source lib.sh ret=0 -# Kselftest framework requirement - SKIP code is 4. -ksft_skip=4 # all tests in this script. Can be overridden with -t option TESTS="gre_gso" @@ -13,8 +11,6 @@ TESTS="gre_gso" VERBOSE=0 PAUSE_ON_FAIL=no PAUSE=no -IP="ip -netns ns1" -NS_EXEC="ip netns exec ns1" TMPFILE=`mktemp` PID= @@ -50,13 +46,13 @@ log_test() setup() { set -e - ip netns add ns1 - ip netns set ns1 auto - $IP link set dev lo up + setup_ns ns1 + IP="ip -netns $ns1" + NS_EXEC="ip netns exec $ns1" ip link add veth0 type veth peer name veth1 ip link set veth0 up - ip link set veth1 netns ns1 + ip link set veth1 netns $ns1 $IP link set veth1 name veth0 $IP link set veth0 up @@ -70,7 +66,7 @@ cleanup() [ -n "$PID" ] && kill $PID ip link del dev gre1 &> /dev/null ip link del dev veth0 &> /dev/null - ip netns del ns1 + cleanup_ns $ns1 } get_linklocal() @@ -145,7 +141,7 @@ gre6_gso_test() setup a1=$(get_linklocal veth0) - a2=$(get_linklocal veth0 ns1) + a2=$(get_linklocal veth0 $ns1) gre_create_tun $a1 $a2 diff --git a/tools/testing/selftests/net/gro.sh b/tools/testing/selftests/net/gro.sh index 342ad27f631b..19352f106c1d 100755 --- a/tools/testing/selftests/net/gro.sh +++ b/tools/testing/selftests/net/gro.sh @@ -23,11 +23,11 @@ run_test() { # on every try. for tries in {1..3}; do # Actual test starts here - ip netns exec server_ns ./gro "${ARGS[@]}" "--rx" "--iface" "server" \ + ip netns exec $server_ns ./gro "${ARGS[@]}" "--rx" "--iface" "server" \ 1>>log.txt & server_pid=$! sleep 0.5 # to allow for socket init - ip netns exec client_ns ./gro "${ARGS[@]}" "--iface" "client" \ + ip netns exec $client_ns ./gro "${ARGS[@]}" "--iface" "client" \ 1>>log.txt wait "${server_pid}" exit_code=$? diff --git a/tools/testing/selftests/net/ip_local_port_range.c b/tools/testing/selftests/net/ip_local_port_range.c index 75e3fdacdf73..0f217a1cc837 100644 --- a/tools/testing/selftests/net/ip_local_port_range.c +++ b/tools/testing/selftests/net/ip_local_port_range.c @@ -146,6 +146,12 @@ FIXTURE_VARIANT_ADD(ip_local_port_range, ip4_stcp) { .so_protocol = IPPROTO_SCTP, }; +FIXTURE_VARIANT_ADD(ip_local_port_range, ip4_mptcp) { + .so_domain = AF_INET, + .so_type = SOCK_STREAM, + .so_protocol = IPPROTO_MPTCP, +}; + FIXTURE_VARIANT_ADD(ip_local_port_range, ip6_tcp) { .so_domain = AF_INET6, .so_type = SOCK_STREAM, @@ -164,6 +170,12 @@ FIXTURE_VARIANT_ADD(ip_local_port_range, ip6_stcp) { .so_protocol = IPPROTO_SCTP, }; +FIXTURE_VARIANT_ADD(ip_local_port_range, ip6_mptcp) { + .so_domain = AF_INET6, + .so_type = SOCK_STREAM, + .so_protocol = IPPROTO_MPTCP, +}; + TEST_F(ip_local_port_range, invalid_option_value) { __u16 val16; diff --git a/tools/testing/selftests/net/netns-name.sh b/tools/testing/selftests/net/netns-name.sh index 7d3d3fc99461..6974474c26f3 100755 --- a/tools/testing/selftests/net/netns-name.sh +++ b/tools/testing/selftests/net/netns-name.sh @@ -1,9 +1,9 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +source lib.sh set -o pipefail -NS=netns-name-test DEV=dummy-dev0 DEV2=dummy-dev1 ALT_NAME=some-alt-name @@ -11,7 +11,7 @@ ALT_NAME=some-alt-name RET_CODE=0 cleanup() { - ip netns del $NS + cleanup_ns $NS $test_ns } trap cleanup EXIT @@ -21,50 +21,50 @@ fail() { RET_CODE=1 } -ip netns add $NS +setup_ns NS test_ns # # Test basic move without a rename # ip -netns $NS link add name $DEV type dummy || fail -ip -netns $NS link set dev $DEV netns 1 || +ip -netns $NS link set dev $DEV netns $test_ns || fail "Can't perform a netns move" -ip link show dev $DEV >> /dev/null || fail "Device not found after move" -ip link del $DEV || fail +ip -netns $test_ns link show dev $DEV >> /dev/null || fail "Device not found after move" +ip -netns $test_ns link del $DEV || fail # # Test move with a conflict # -ip link add name $DEV type dummy +ip -netns $test_ns link add name $DEV type dummy ip -netns $NS link add name $DEV type dummy || fail -ip -netns $NS link set dev $DEV netns 1 2> /dev/null && +ip -netns $NS link set dev $DEV netns $test_ns 2> /dev/null && fail "Performed a netns move with a name conflict" -ip link show dev $DEV >> /dev/null || fail "Device not found after move" +ip -netns $test_ns link show dev $DEV >> /dev/null || fail "Device not found after move" ip -netns $NS link del $DEV || fail -ip link del $DEV || fail +ip -netns $test_ns link del $DEV || fail # # Test move with a conflict and rename # -ip link add name $DEV type dummy +ip -netns $test_ns link add name $DEV type dummy ip -netns $NS link add name $DEV type dummy || fail -ip -netns $NS link set dev $DEV netns 1 name $DEV2 || +ip -netns $NS link set dev $DEV netns $test_ns name $DEV2 || fail "Can't perform a netns move with rename" -ip link del $DEV2 || fail -ip link del $DEV || fail +ip -netns $test_ns link del $DEV2 || fail +ip -netns $test_ns link del $DEV || fail # # Test dup alt-name with netns move # -ip link add name $DEV type dummy || fail -ip link property add dev $DEV altname $ALT_NAME || fail +ip -netns $test_ns link add name $DEV type dummy || fail +ip -netns $test_ns link property add dev $DEV altname $ALT_NAME || fail ip -netns $NS link add name $DEV2 type dummy || fail ip -netns $NS link property add dev $DEV2 altname $ALT_NAME || fail -ip -netns $NS link set dev $DEV2 netns 1 2> /dev/null && +ip -netns $NS link set dev $DEV2 netns $test_ns 2> /dev/null && fail "Moved with alt-name dup" -ip link del $DEV || fail +ip -netns $test_ns link del $DEV || fail ip -netns $NS link del $DEV2 || fail # @@ -72,11 +72,11 @@ ip -netns $NS link del $DEV2 || fail # ip -netns $NS link add name $DEV type dummy || fail ip -netns $NS link property add dev $DEV altname $ALT_NAME || fail -ip -netns $NS link set dev $DEV netns 1 || fail -ip link show dev $ALT_NAME >> /dev/null || fail "Can't find alt-name after move" -ip -netns $NS link show dev $ALT_NAME 2> /dev/null && +ip -netns $NS link set dev $DEV netns $test_ns || fail +ip -netns $test_ns link show dev $ALT_NAME >> /dev/null || fail "Can't find alt-name after move" +ip -netns $NS link show dev $ALT_NAME 2> /dev/null && fail "Can still find alt-name after move" -ip link del $DEV || fail +ip -netns $test_ns link del $DEV || fail echo -ne "$(basename $0) \t\t\t\t" if [ $RET_CODE -eq 0 ]; then diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index b3b2dc5a630c..175d3d1d773b 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -198,8 +198,7 @@ # - pmtu_ipv6_route_change # Same as above but with IPv6 -# Kselftest framework requirement - SKIP code is 4. -ksft_skip=4 +source ./lib.sh PAUSE_ON_FAIL=no VERBOSE=0 @@ -268,16 +267,6 @@ tests=" pmtu_ipv4_route_change ipv4: PMTU exception w/route replace 1 pmtu_ipv6_route_change ipv6: PMTU exception w/route replace 1" -NS_A="ns-A" -NS_B="ns-B" -NS_C="ns-C" -NS_R1="ns-R1" -NS_R2="ns-R2" -ns_a="ip netns exec ${NS_A}" -ns_b="ip netns exec ${NS_B}" -ns_c="ip netns exec ${NS_C}" -ns_r1="ip netns exec ${NS_R1}" -ns_r2="ip netns exec ${NS_R2}" # Addressing and routing for tests with routers: four network segments, with # index SEGMENT between 1 and 4, a common prefix (PREFIX4 or PREFIX6) and an # identifier ID, which is 1 for hosts (A and B), 2 for routers (R1 and R2). @@ -543,13 +532,17 @@ setup_ip6ip6() { } setup_namespaces() { + setup_ns NS_A NS_B NS_C NS_R1 NS_R2 for n in ${NS_A} ${NS_B} ${NS_C} ${NS_R1} ${NS_R2}; do - ip netns add ${n} || return 1 - # Disable DAD, so that we don't have to wait to use the # configured IPv6 addresses ip netns exec ${n} sysctl -q net/ipv6/conf/default/accept_dad=0 done + ns_a="ip netns exec ${NS_A}" + ns_b="ip netns exec ${NS_B}" + ns_c="ip netns exec ${NS_C}" + ns_r1="ip netns exec ${NS_R1}" + ns_r2="ip netns exec ${NS_R2}" } setup_veth() { @@ -839,7 +832,7 @@ setup_bridge() { run_cmd ${ns_a} ip link set br0 up run_cmd ${ns_c} ip link add veth_C-A type veth peer name veth_A-C - run_cmd ${ns_c} ip link set veth_A-C netns ns-A + run_cmd ${ns_c} ip link set veth_A-C netns ${NS_A} run_cmd ${ns_a} ip link set veth_A-C up run_cmd ${ns_c} ip link set veth_C-A up @@ -944,9 +937,7 @@ cleanup() { done socat_pids= - for n in ${NS_A} ${NS_B} ${NS_C} ${NS_R1} ${NS_R2}; do - ip netns del ${n} 2> /dev/null - done + cleanup_all_ns ip link del veth_A-C 2>/dev/null ip link del veth_A-R1 2>/dev/null diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 26827ea4e3e5..a10a32952f21 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -35,8 +35,7 @@ VERBOSE=0 PAUSE=no PAUSE_ON_FAIL=no -# Kselftest framework requirement - SKIP code is 4. -ksft_skip=4 +source lib.sh # set global exit status, but never reset nonzero one. check_err() @@ -517,9 +516,8 @@ kci_test_encap_fou() # test various encap methods, use netns to avoid unwanted interference kci_test_encap() { - testns="testns" local ret=0 - run_cmd ip netns add "$testns" + setup_ns testns if [ $? -ne 0 ]; then end_test "SKIP encap tests: cannot add net namespace $testns" return $ksft_skip @@ -574,6 +572,10 @@ kci_test_macsec_offload() return $ksft_skip fi + if ! mount | grep -q debugfs; then + mount -t debugfs none /sys/kernel/debug/ &> /dev/null + fi + # setup netdevsim since dummydev doesn't have offload support if [ ! -w /sys/bus/netdevsim/new_device ] ; then run_cmd modprobe -q netdevsim @@ -738,6 +740,10 @@ kci_test_ipsec_offload() sysfsnet=/sys/bus/netdevsim/devices/netdevsim0/net/ probed=false + if ! mount | grep -q debugfs; then + mount -t debugfs none /sys/kernel/debug/ &> /dev/null + fi + # setup netdevsim since dummydev doesn't have offload support if [ ! -w /sys/bus/netdevsim/new_device ] ; then run_cmd modprobe -q netdevsim @@ -836,11 +842,10 @@ EOF kci_test_gretap() { - testns="testns" DEV_NS=gretap00 local ret=0 - run_cmd ip netns add "$testns" + setup_ns testns if [ $? -ne 0 ]; then end_test "SKIP gretap tests: cannot add net namespace $testns" return $ksft_skip @@ -878,11 +883,10 @@ kci_test_gretap() kci_test_ip6gretap() { - testns="testns" DEV_NS=ip6gretap00 local ret=0 - run_cmd ip netns add "$testns" + setup_ns testns if [ $? -ne 0 ]; then end_test "SKIP ip6gretap tests: cannot add net namespace $testns" return $ksft_skip @@ -920,7 +924,6 @@ kci_test_ip6gretap() kci_test_erspan() { - testns="testns" DEV_NS=erspan00 local ret=0 run_cmd_grep "^Usage:" ip link help erspan @@ -928,7 +931,7 @@ kci_test_erspan() end_test "SKIP: erspan: iproute2 too old" return $ksft_skip fi - run_cmd ip netns add "$testns" + setup_ns testns if [ $? -ne 0 ]; then end_test "SKIP erspan tests: cannot add net namespace $testns" return $ksft_skip @@ -970,7 +973,6 @@ kci_test_erspan() kci_test_ip6erspan() { - testns="testns" DEV_NS=ip6erspan00 local ret=0 run_cmd_grep "^Usage:" ip link help ip6erspan @@ -978,7 +980,7 @@ kci_test_ip6erspan() end_test "SKIP: ip6erspan: iproute2 too old" return $ksft_skip fi - run_cmd ip netns add "$testns" + setup_ns testns if [ $? -ne 0 ]; then end_test "SKIP ip6erspan tests: cannot add net namespace $testns" return $ksft_skip @@ -1022,8 +1024,6 @@ kci_test_ip6erspan() kci_test_fdb_get() { - IP="ip -netns testns" - BRIDGE="bridge -netns testns" brdev="test-br0" vxlandev="vxlan10" test_mac=de:ad:be:ef:13:37 @@ -1037,11 +1037,13 @@ kci_test_fdb_get() return $ksft_skip fi - run_cmd ip netns add testns + setup_ns testns if [ $? -ne 0 ]; then end_test "SKIP fdb get tests: cannot add net namespace $testns" return $ksft_skip fi + IP="ip -netns $testns" + BRIDGE="bridge -netns $testns" run_cmd $IP link add "$vxlandev" type vxlan id 10 local $localip \ dstport 4789 run_cmd $IP link add name "$brdev" type bridge @@ -1052,7 +1054,7 @@ kci_test_fdb_get() run_cmd_grep "dev $vxlandev master $brdev" $BRIDGE fdb get $test_mac br "$brdev" run_cmd_grep "dev $vxlandev dst $dstip" $BRIDGE fdb get $test_mac dev "$vxlandev" self - ip netns del testns &>/dev/null + ip netns del $testns &>/dev/null if [ $ret -ne 0 ]; then end_test "FAIL: bridge fdb get" diff --git a/tools/testing/selftests/net/setup_loopback.sh b/tools/testing/selftests/net/setup_loopback.sh index e57bbfbc5208..2070b57849de 100755 --- a/tools/testing/selftests/net/setup_loopback.sh +++ b/tools/testing/selftests/net/setup_loopback.sh @@ -5,6 +5,8 @@ readonly FLUSH_PATH="/sys/class/net/${dev}/gro_flush_timeout" readonly IRQ_PATH="/sys/class/net/${dev}/napi_defer_hard_irqs" readonly FLUSH_TIMEOUT="$(< ${FLUSH_PATH})" readonly HARD_IRQS="$(< ${IRQ_PATH})" +readonly server_ns=$(mktemp -u server-XXXXXXXX) +readonly client_ns=$(mktemp -u client-XXXXXXXX) netdev_check_for_carrier() { local -r dev="$1" @@ -97,12 +99,12 @@ setup_interrupt() { setup_ns() { # Set up server_ns namespace and client_ns namespace - setup_macvlan_ns "${dev}" server_ns server "${SERVER_MAC}" - setup_macvlan_ns "${dev}" client_ns client "${CLIENT_MAC}" + setup_macvlan_ns "${dev}" ${server_ns} server "${SERVER_MAC}" + setup_macvlan_ns "${dev}" ${client_ns} client "${CLIENT_MAC}" } cleanup_ns() { - cleanup_macvlan_ns server_ns server client_ns client + cleanup_macvlan_ns ${server_ns} server ${client_ns} client } setup() { diff --git a/tools/testing/selftests/net/setup_veth.sh b/tools/testing/selftests/net/setup_veth.sh index 1003ddf7b3b2..a9a1759e035c 100644 --- a/tools/testing/selftests/net/setup_veth.sh +++ b/tools/testing/selftests/net/setup_veth.sh @@ -1,6 +1,9 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +readonly server_ns=$(mktemp -u server-XXXXXXXX) +readonly client_ns=$(mktemp -u client-XXXXXXXX) + setup_veth_ns() { local -r link_dev="$1" local -r ns_name="$2" @@ -19,14 +22,14 @@ setup_ns() { # Set up server_ns namespace and client_ns namespace ip link add name server type veth peer name client - setup_veth_ns "${dev}" server_ns server "${SERVER_MAC}" - setup_veth_ns "${dev}" client_ns client "${CLIENT_MAC}" + setup_veth_ns "${dev}" ${server_ns} server "${SERVER_MAC}" + setup_veth_ns "${dev}" ${client_ns} client "${CLIENT_MAC}" } cleanup_ns() { local ns_name - for ns_name in client_ns server_ns; do + for ns_name in ${client_ns} ${server_ns}; do [[ -e /var/run/netns/"${ns_name}" ]] && ip netns del "${ns_name}" done } diff --git a/tools/testing/selftests/net/stress_reuseport_listen.sh b/tools/testing/selftests/net/stress_reuseport_listen.sh index 4de11da4092b..94d5d1a1c90f 100755 --- a/tools/testing/selftests/net/stress_reuseport_listen.sh +++ b/tools/testing/selftests/net/stress_reuseport_listen.sh @@ -2,18 +2,18 @@ # SPDX-License-Identifier: GPL-2.0 # Copyright (c) 2022 Meta Platforms, Inc. and affiliates. -NS='stress_reuseport_listen_ns' +source lib.sh NR_FILES=24100 SAVED_NR_FILES=$(ulimit -n) setup() { - ip netns add $NS + setup_ns NS ip netns exec $NS sysctl -q -w net.ipv6.ip_nonlocal_bind=1 ulimit -n $NR_FILES } cleanup() { - ip netns del $NS + cleanup_ns $NS ulimit -n $SAVED_NR_FILES } diff --git a/tools/testing/selftests/net/tcp_ao/Makefile b/tools/testing/selftests/net/tcp_ao/Makefile index 6343cfcf919b..8e60bae67aa9 100644 --- a/tools/testing/selftests/net/tcp_ao/Makefile +++ b/tools/testing/selftests/net/tcp_ao/Makefile @@ -17,22 +17,18 @@ TEST_IPV6_PROGS := $(TEST_BOTH_AF:%=%_ipv6) TEST_GEN_PROGS := $(TEST_IPV4_PROGS) $(TEST_IPV6_PROGS) top_srcdir := ../../../../.. -KSFT_KHDR_INSTALL := 1 include ../../lib.mk HOSTAR ?= ar -# Drop it on port to linux/master with commit 8ce72dc32578 -.DEFAULT_GOAL := all - LIBDIR := $(OUTPUT)/lib LIB := $(LIBDIR)/libaotst.a LDLIBS += $(LIB) -pthread LIBDEPS := lib/aolib.h Makefile CFLAGS := -Wall -O2 -g -D_GNU_SOURCE -fno-strict-aliasing -CFLAGS += -I ../../../../../usr/include/ -iquote $(LIBDIR) -CFLAGS += -I ../../../../include/ +CFLAGS += $(KHDR_INCLUDES) +CFLAGS += -iquote ./lib/ -I ../../../../include/ # Library LIBSRC := kconfig.c netlink.c proc.c repair.c setup.c sock.c utils.c @@ -43,6 +39,7 @@ $(LIB): $(LIBOBJ) $(HOSTAR) rcs $@ $^ $(LIBDIR)/%.o: ./lib/%.c $(LIBDEPS) + mkdir -p $(LIBDIR) $(CC) $< $(CFLAGS) $(CPPFLAGS) -o $@ -c $(TEST_GEN_PROGS): $(LIB) diff --git a/tools/testing/selftests/net/tcp_ao/connect-deny.c b/tools/testing/selftests/net/tcp_ao/connect-deny.c index 1ca78040d8b7..185a2f6e5ff3 100644 --- a/tools/testing/selftests/net/tcp_ao/connect-deny.c +++ b/tools/testing/selftests/net/tcp_ao/connect-deny.c @@ -55,7 +55,7 @@ static void try_accept(const char *tst_name, unsigned int port, const char *pwd, err = test_wait_fd(lsk, timeout, 0); if (err == -ETIMEDOUT) { if (!fault(TIMEOUT)) - test_fail("timeouted for accept()"); + test_fail("timed out for accept()"); } else if (err < 0) { test_error("test_wait_fd()"); } else { diff --git a/tools/testing/selftests/net/tcp_ao/lib/proc.c b/tools/testing/selftests/net/tcp_ao/lib/proc.c index 2322f4d4676d..2fb6dd8adba6 100644 --- a/tools/testing/selftests/net/tcp_ao/lib/proc.c +++ b/tools/testing/selftests/net/tcp_ao/lib/proc.c @@ -227,7 +227,7 @@ void netstat_print_diff(struct netstat *nsa, struct netstat *nsb) } if (nsb->counters_nr < nsa->counters_nr) - test_error("Unexpected: some counters dissapeared!"); + test_error("Unexpected: some counters disappeared!"); for (j = 0, i = 0; i < nsb->counters_nr; i++) { if (strcmp(nsb->counters[i].name, nsa->counters[j].name)) { @@ -244,7 +244,7 @@ void netstat_print_diff(struct netstat *nsa, struct netstat *nsb) j++; } if (j != nsa->counters_nr) - test_error("Unexpected: some counters dissapeared!"); + test_error("Unexpected: some counters disappeared!"); nsb = nsb->next; nsa = nsa->next; diff --git a/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c index 7e4601b3f6a3..452de131fa3a 100644 --- a/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c +++ b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c @@ -118,7 +118,7 @@ static void setsockopt_checked(int sk, int optname, void *optval, break; default: break; - }; + } __setsockopt_checked(sk, optname, false, optval, &len, err, cmd, tst); } @@ -427,7 +427,7 @@ static void test_einval_del_key(void) sk = prepare_defs(TCP_AO_DEL_KEY, &del); del.set_current = 1; - setsockopt_checked(sk, TCP_AO_DEL_KEY, &del, ENOENT, "set non-exising current key"); + setsockopt_checked(sk, TCP_AO_DEL_KEY, &del, ENOENT, "set non-existing current key"); sk = prepare_defs(TCP_AO_DEL_KEY, &del); del.set_rnext = 1; diff --git a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c index 7cffde02d2be..14addfd46468 100644 --- a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c +++ b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c @@ -72,7 +72,7 @@ static void try_accept(const char *tst_name, unsigned int port, err = test_wait_fd(lsk, timeout, 0); if (err == -ETIMEDOUT) { if (!fault(TIMEOUT)) - test_fail("timeouted for accept()"); + test_fail("timed out for accept()"); } else if (err < 0) { test_error("test_wait_fd()"); } else { diff --git a/tools/testing/selftests/net/toeplitz.sh b/tools/testing/selftests/net/toeplitz.sh index da5bfd834eff..8ff172f7bb1b 100755 --- a/tools/testing/selftests/net/toeplitz.sh +++ b/tools/testing/selftests/net/toeplitz.sh @@ -147,14 +147,14 @@ setup() { setup_loopback_environment "${DEV}" # Set up server_ns namespace and client_ns namespace - setup_macvlan_ns "${DEV}" server_ns server \ + setup_macvlan_ns "${DEV}" $server_ns server \ "${SERVER_MAC}" "${SERVER_IP}" - setup_macvlan_ns "${DEV}" client_ns client \ + setup_macvlan_ns "${DEV}" $client_ns client \ "${CLIENT_MAC}" "${CLIENT_IP}" } cleanup() { - cleanup_macvlan_ns server_ns server client_ns client + cleanup_macvlan_ns $server_ns server $client_ns client cleanup_loopback "${DEV}" } @@ -170,22 +170,22 @@ if [[ "${TEST_RSS}" = true ]]; then # RPS/RFS must be disabled because they move packets between cpus, # which breaks the PACKET_FANOUT_CPU identification of RSS decisions. eval "$(get_disable_rfs_cmd) $(get_disable_rps_cmd)" \ - ip netns exec server_ns ./toeplitz "${IP_FLAG}" "${PROTO_FLAG}" \ + ip netns exec $server_ns ./toeplitz "${IP_FLAG}" "${PROTO_FLAG}" \ -d "${PORT}" -i "${DEV}" -k "${KEY}" -T 1000 \ -C "$(get_rx_irq_cpus)" -s -v & elif [[ ! -z "${RPS_MAP}" ]]; then eval "$(get_disable_rfs_cmd) $(get_set_rps_bitmaps_cmd ${RPS_MAP})" \ - ip netns exec server_ns ./toeplitz "${IP_FLAG}" "${PROTO_FLAG}" \ + ip netns exec $server_ns ./toeplitz "${IP_FLAG}" "${PROTO_FLAG}" \ -d "${PORT}" -i "${DEV}" -k "${KEY}" -T 1000 \ -r "0x${RPS_MAP}" -s -v & else - ip netns exec server_ns ./toeplitz "${IP_FLAG}" "${PROTO_FLAG}" \ + ip netns exec $server_ns ./toeplitz "${IP_FLAG}" "${PROTO_FLAG}" \ -d "${PORT}" -i "${DEV}" -k "${KEY}" -T 1000 -s -v & fi server_pid=$! -ip netns exec client_ns ./toeplitz_client.sh "${PROTO_FLAG}" \ +ip netns exec $client_ns ./toeplitz_client.sh "${PROTO_FLAG}" \ "${IP_FLAG}" "${SERVER_IP%%/*}" "${PORT}" & client_pid=$! diff --git a/tools/testing/selftests/net/xfrm_policy.sh b/tools/testing/selftests/net/xfrm_policy.sh index bdf450eaf60c..457789530645 100755 --- a/tools/testing/selftests/net/xfrm_policy.sh +++ b/tools/testing/selftests/net/xfrm_policy.sh @@ -18,8 +18,7 @@ # ns1: ping 10.0.2.254: does NOT pass via ipsec tunnel (exception) # ns2: ping 10.0.1.254: does NOT pass via ipsec tunnel (exception) -# Kselftest framework requirement - SKIP code is 4. -ksft_skip=4 +source lib.sh ret=0 policy_checks_ok=1 @@ -204,24 +203,24 @@ check_xfrm() { ip=$2 local lret=0 - ip netns exec ns1 ping -q -c 1 10.0.2.$ip > /dev/null + ip netns exec ${ns[1]} ping -q -c 1 10.0.2.$ip > /dev/null - check_ipt_policy_count ns3 + check_ipt_policy_count ${ns[3]} if [ $? -ne $rval ] ; then lret=1 fi - check_ipt_policy_count ns4 + check_ipt_policy_count ${ns[4]} if [ $? -ne $rval ] ; then lret=1 fi - ip netns exec ns2 ping -q -c 1 10.0.1.$ip > /dev/null + ip netns exec ${ns[2]} ping -q -c 1 10.0.1.$ip > /dev/null - check_ipt_policy_count ns3 + check_ipt_policy_count ${ns[3]} if [ $? -ne $rval ] ; then lret=1 fi - check_ipt_policy_count ns4 + check_ipt_policy_count ${ns[4]} if [ $? -ne $rval ] ; then lret=1 fi @@ -270,11 +269,11 @@ check_hthresh_repeat() i=0 for i in $(seq 1 10);do - ip -net ns1 xfrm policy update src e000:0001::0000 dst ff01::0014:0000:0001 dir in tmpl src :: dst :: proto esp mode tunnel priority 100 action allow || break - ip -net ns1 xfrm policy set hthresh6 0 28 || break + ip -net ${ns[1]} xfrm policy update src e000:0001::0000 dst ff01::0014:0000:0001 dir in tmpl src :: dst :: proto esp mode tunnel priority 100 action allow || break + ip -net ${ns[1]} xfrm policy set hthresh6 0 28 || break - ip -net ns1 xfrm policy update src e000:0001::0000 dst ff01::01 dir in tmpl src :: dst :: proto esp mode tunnel priority 100 action allow || break - ip -net ns1 xfrm policy set hthresh6 0 28 || break + ip -net ${ns[1]} xfrm policy update src e000:0001::0000 dst ff01::01 dir in tmpl src :: dst :: proto esp mode tunnel priority 100 action allow || break + ip -net ${ns[1]} xfrm policy set hthresh6 0 28 || break done if [ $i -ne 10 ] ;then @@ -347,79 +346,80 @@ if [ $? -ne 0 ];then exit $ksft_skip fi -for i in 1 2 3 4; do - ip netns add ns$i - ip -net ns$i link set lo up -done +setup_ns ns1 ns2 ns3 ns4 +ns[1]=$ns1 +ns[2]=$ns2 +ns[3]=$ns3 +ns[4]=$ns4 DEV=veth0 -ip link add $DEV netns ns1 type veth peer name eth1 netns ns3 -ip link add $DEV netns ns2 type veth peer name eth1 netns ns4 +ip link add $DEV netns ${ns[1]} type veth peer name eth1 netns ${ns[3]} +ip link add $DEV netns ${ns[2]} type veth peer name eth1 netns ${ns[4]} -ip link add $DEV netns ns3 type veth peer name veth0 netns ns4 +ip link add $DEV netns ${ns[3]} type veth peer name veth0 netns ${ns[4]} DEV=veth0 for i in 1 2; do - ip -net ns$i link set $DEV up - ip -net ns$i addr add 10.0.$i.2/24 dev $DEV - ip -net ns$i addr add dead:$i::2/64 dev $DEV - - ip -net ns$i addr add 10.0.$i.253 dev $DEV - ip -net ns$i addr add 10.0.$i.254 dev $DEV - ip -net ns$i addr add dead:$i::fd dev $DEV - ip -net ns$i addr add dead:$i::fe dev $DEV + ip -net ${ns[$i]} link set $DEV up + ip -net ${ns[$i]} addr add 10.0.$i.2/24 dev $DEV + ip -net ${ns[$i]} addr add dead:$i::2/64 dev $DEV + + ip -net ${ns[$i]} addr add 10.0.$i.253 dev $DEV + ip -net ${ns[$i]} addr add 10.0.$i.254 dev $DEV + ip -net ${ns[$i]} addr add dead:$i::fd dev $DEV + ip -net ${ns[$i]} addr add dead:$i::fe dev $DEV done for i in 3 4; do -ip -net ns$i link set eth1 up -ip -net ns$i link set veth0 up + ip -net ${ns[$i]} link set eth1 up + ip -net ${ns[$i]} link set veth0 up done -ip -net ns1 route add default via 10.0.1.1 -ip -net ns2 route add default via 10.0.2.1 +ip -net ${ns[1]} route add default via 10.0.1.1 +ip -net ${ns[2]} route add default via 10.0.2.1 -ip -net ns3 addr add 10.0.1.1/24 dev eth1 -ip -net ns3 addr add 10.0.3.1/24 dev veth0 -ip -net ns3 addr add 2001:1::1/64 dev eth1 -ip -net ns3 addr add 2001:3::1/64 dev veth0 +ip -net ${ns[3]} addr add 10.0.1.1/24 dev eth1 +ip -net ${ns[3]} addr add 10.0.3.1/24 dev veth0 +ip -net ${ns[3]} addr add 2001:1::1/64 dev eth1 +ip -net ${ns[3]} addr add 2001:3::1/64 dev veth0 -ip -net ns3 route add default via 10.0.3.10 +ip -net ${ns[3]} route add default via 10.0.3.10 -ip -net ns4 addr add 10.0.2.1/24 dev eth1 -ip -net ns4 addr add 10.0.3.10/24 dev veth0 -ip -net ns4 addr add 2001:2::1/64 dev eth1 -ip -net ns4 addr add 2001:3::10/64 dev veth0 -ip -net ns4 route add default via 10.0.3.1 +ip -net ${ns[4]} addr add 10.0.2.1/24 dev eth1 +ip -net ${ns[4]} addr add 10.0.3.10/24 dev veth0 +ip -net ${ns[4]} addr add 2001:2::1/64 dev eth1 +ip -net ${ns[4]} addr add 2001:3::10/64 dev veth0 +ip -net ${ns[4]} route add default via 10.0.3.1 for j in 4 6; do for i in 3 4;do - ip netns exec ns$i sysctl net.ipv$j.conf.eth1.forwarding=1 > /dev/null - ip netns exec ns$i sysctl net.ipv$j.conf.veth0.forwarding=1 > /dev/null + ip netns exec ${ns[$i]} sysctl net.ipv$j.conf.eth1.forwarding=1 > /dev/null + ip netns exec ${ns[$i]} sysctl net.ipv$j.conf.veth0.forwarding=1 > /dev/null done done # abuse iptables rule counter to check if ping matches a policy -ip netns exec ns3 iptables -p icmp -A FORWARD -m policy --dir out --pol ipsec -ip netns exec ns4 iptables -p icmp -A FORWARD -m policy --dir out --pol ipsec +ip netns exec ${ns[3]} iptables -p icmp -A FORWARD -m policy --dir out --pol ipsec +ip netns exec ${ns[4]} iptables -p icmp -A FORWARD -m policy --dir out --pol ipsec if [ $? -ne 0 ];then echo "SKIP: Could not insert iptables rule" - for i in 1 2 3 4;do ip netns del ns$i;done + cleanup_ns $ns1 $ns2 $ns3 $ns4 exit $ksft_skip fi # localip remoteip localnet remotenet -do_esp ns3 10.0.3.1 10.0.3.10 10.0.1.0/24 10.0.2.0/24 $SPI1 $SPI2 -do_esp ns3 dead:3::1 dead:3::10 dead:1::/64 dead:2::/64 $SPI1 $SPI2 -do_esp ns4 10.0.3.10 10.0.3.1 10.0.2.0/24 10.0.1.0/24 $SPI2 $SPI1 -do_esp ns4 dead:3::10 dead:3::1 dead:2::/64 dead:1::/64 $SPI2 $SPI1 +do_esp ${ns[3]} 10.0.3.1 10.0.3.10 10.0.1.0/24 10.0.2.0/24 $SPI1 $SPI2 +do_esp ${ns[3]} dead:3::1 dead:3::10 dead:1::/64 dead:2::/64 $SPI1 $SPI2 +do_esp ${ns[4]} 10.0.3.10 10.0.3.1 10.0.2.0/24 10.0.1.0/24 $SPI2 $SPI1 +do_esp ${ns[4]} dead:3::10 dead:3::1 dead:2::/64 dead:1::/64 $SPI2 $SPI1 -do_dummies4 ns3 -do_dummies6 ns4 +do_dummies4 ${ns[3]} +do_dummies6 ${ns[4]} -do_esp_policy_get_check ns3 10.0.1.0/24 10.0.2.0/24 -do_esp_policy_get_check ns4 10.0.2.0/24 10.0.1.0/24 -do_esp_policy_get_check ns3 dead:1::/64 dead:2::/64 -do_esp_policy_get_check ns4 dead:2::/64 dead:1::/64 +do_esp_policy_get_check ${ns[3]} 10.0.1.0/24 10.0.2.0/24 +do_esp_policy_get_check ${ns[4]} 10.0.2.0/24 10.0.1.0/24 +do_esp_policy_get_check ${ns[3]} dead:1::/64 dead:2::/64 +do_esp_policy_get_check ${ns[4]} dead:2::/64 dead:1::/64 # ping to .254 should use ipsec, exception is not installed. check_xfrm 1 254 @@ -432,11 +432,11 @@ fi # installs exceptions # localip remoteip encryptdst plaindst -do_exception ns3 10.0.3.1 10.0.3.10 10.0.2.253 10.0.2.240/28 -do_exception ns4 10.0.3.10 10.0.3.1 10.0.1.253 10.0.1.240/28 +do_exception ${ns[3]} 10.0.3.1 10.0.3.10 10.0.2.253 10.0.2.240/28 +do_exception ${ns[4]} 10.0.3.10 10.0.3.1 10.0.1.253 10.0.1.240/28 -do_exception ns3 dead:3::1 dead:3::10 dead:2::fd dead:2:f0::/96 -do_exception ns4 dead:3::10 dead:3::1 dead:1::fd dead:1:f0::/96 +do_exception ${ns[3]} dead:3::1 dead:3::10 dead:2::fd dead:2:f0::/96 +do_exception ${ns[4]} dead:3::10 dead:3::1 dead:1::fd dead:1:f0::/96 check_exceptions "exceptions" if [ $? -ne 0 ]; then @@ -444,14 +444,14 @@ if [ $? -ne 0 ]; then fi # insert block policies with adjacent/overlapping netmasks -do_overlap ns3 +do_overlap ${ns[3]} check_exceptions "exceptions and block policies" if [ $? -ne 0 ]; then ret=1 fi -for n in ns3 ns4;do +for n in ${ns[3]} ${ns[4]};do ip -net $n xfrm policy set hthresh4 28 24 hthresh6 126 125 sleep $((RANDOM%5)) done @@ -459,19 +459,19 @@ done check_exceptions "exceptions and block policies after hresh changes" # full flush of policy db, check everything gets freed incl. internal meta data -ip -net ns3 xfrm policy flush +ip -net ${ns[3]} xfrm policy flush -do_esp_policy ns3 10.0.3.1 10.0.3.10 10.0.1.0/24 10.0.2.0/24 -do_exception ns3 10.0.3.1 10.0.3.10 10.0.2.253 10.0.2.240/28 +do_esp_policy ${ns[3]} 10.0.3.1 10.0.3.10 10.0.1.0/24 10.0.2.0/24 +do_exception ${ns[3]} 10.0.3.1 10.0.3.10 10.0.2.253 10.0.2.240/28 # move inexact policies to hash table -ip -net ns3 xfrm policy set hthresh4 16 16 +ip -net ${ns[3]} xfrm policy set hthresh4 16 16 sleep $((RANDOM%5)) check_exceptions "exceptions and block policies after hthresh change in ns3" # restore original hthresh settings -- move policies back to tables -for n in ns3 ns4;do +for n in ${ns[3]} ${ns[4]};do ip -net $n xfrm policy set hthresh4 32 32 hthresh6 128 128 sleep $((RANDOM%5)) done @@ -479,8 +479,8 @@ check_exceptions "exceptions and block policies after htresh change to normal" check_hthresh_repeat "policies with repeated htresh change" -check_random_order ns3 "policies inserted in random order" +check_random_order ${ns[3]} "policies inserted in random order" -for i in 1 2 3 4;do ip netns del ns$i;done +cleanup_ns $ns1 $ns2 $ns3 $ns4 exit $ret diff --git a/tools/testing/selftests/run_kselftest.sh b/tools/testing/selftests/run_kselftest.sh index 92743980e553..a28c1416cb89 100755 --- a/tools/testing/selftests/run_kselftest.sh +++ b/tools/testing/selftests/run_kselftest.sh @@ -20,11 +20,13 @@ usage() { cat <<EOF Usage: $0 [OPTIONS] - -s | --summary Print summary with detailed log in output.log + -s | --summary Print summary with detailed log in output.log (conflict with -p) + -p | --per_test_log Print test log in /tmp with each test name (conflict with -s) -t | --test COLLECTION:TEST Run TEST from COLLECTION -c | --collection COLLECTION Run all tests from COLLECTION -l | --list List the available collection:test entries -d | --dry-run Don't actually run any tests + -n | --netns Run each test in namespace -h | --help Show this usage info -o | --override-timeout Number of seconds after which we timeout EOF @@ -41,6 +43,9 @@ while true; do logfile="$BASE_DIR"/output.log cat /dev/null > $logfile shift ;; + -p | --per-test-log) + per_test_logging=1 + shift ;; -t | --test) TESTS="$TESTS $2" shift 2 ;; @@ -53,6 +58,9 @@ while true; do -d | --dry-run) dryrun="echo" shift ;; + -n | --netns) + RUN_IN_NETNS=1 + shift ;; -o | --override-timeout) kselftest_override_timeout="$2" shift 2 ;; |