diff options
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx4')
22 files changed, 480 insertions, 275 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx4/Kconfig b/drivers/net/ethernet/mellanox/mlx4/Kconfig index 1486ce902a56..9ca3734ebb6b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx4/Kconfig @@ -4,6 +4,7 @@ config MLX4_EN tristate "Mellanox Technologies 1/10/40Gbit Ethernet support" + depends on MAY_USE_DEVLINK depends on PCI select MLX4_CORE select PTP_1588_CLOCK diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c index 715de8affcc9..c7e939945259 100644 --- a/drivers/net/ethernet/mellanox/mlx4/catas.c +++ b/drivers/net/ethernet/mellanox/mlx4/catas.c @@ -182,10 +182,17 @@ void mlx4_enter_error_state(struct mlx4_dev_persistent *persist) err = mlx4_reset_slave(dev); else err = mlx4_reset_master(dev); - BUG_ON(err != 0); + if (!err) { + mlx4_err(dev, "device was reset successfully\n"); + } else { + /* EEH could have disabled the PCI channel during reset. That's + * recoverable and the PCI error flow will handle it. + */ + if (!pci_channel_offline(dev->persist->pdev)) + BUG_ON(1); + } dev->persist->state |= MLX4_DEVICE_STATE_INTERNAL_ERROR; - mlx4_err(dev, "device was reset successfully\n"); mutex_unlock(&persist->device_state_mutex); /* At that step HW was already reset, now notify clients */ diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index d48d5793407d..e94ca1c3fc7c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -2429,7 +2429,7 @@ err_thread: flush_workqueue(priv->mfunc.master.comm_wq); destroy_workqueue(priv->mfunc.master.comm_wq); err_slaves: - while (--i) { + while (i--) { for (port = 1; port <= MLX4_MAX_PORTS; port++) kfree(priv->mfunc.master.slave_state[i].vlan_filter[port]); } diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c index 3348e646db70..a849da92f857 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/cq.c @@ -318,7 +318,9 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, if (timestamp_en) cq_context->flags |= cpu_to_be32(1 << 19); - cq_context->logsize_usrpage = cpu_to_be32((ilog2(nent) << 24) | uar->index); + cq_context->logsize_usrpage = + cpu_to_be32((ilog2(nent) << 24) | + mlx4_to_hw_uar_index(dev, uar->index)); cq_context->comp_eqn = priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(vector)].eqn; cq_context->log_page_size = mtt->page_shift - MLX4_ICM_PAGE_SHIFT; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c index 038f9ce391e6..1494997c4f7e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c @@ -236,6 +236,24 @@ static const struct ptp_clock_info mlx4_en_ptp_clock_info = { .enable = mlx4_en_phc_enable, }; +#define MLX4_EN_WRAP_AROUND_SEC 10ULL + +/* This function calculates the max shift that enables the user range + * of MLX4_EN_WRAP_AROUND_SEC values in the cycles register. + */ +static u32 freq_to_shift(u16 freq) +{ + u32 freq_khz = freq * 1000; + u64 max_val_cycles = freq_khz * 1000 * MLX4_EN_WRAP_AROUND_SEC; + u64 max_val_cycles_rounded = is_power_of_2(max_val_cycles + 1) ? + max_val_cycles : roundup_pow_of_two(max_val_cycles) - 1; + /* calculate max possible multiplier in order to fit in 64bit */ + u64 max_mul = div_u64(0xffffffffffffffffULL, max_val_cycles_rounded); + + /* This comes from the reverse of clocksource_khz2mult */ + return ilog2(div_u64(max_mul * freq_khz, 1000000)); +} + void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev) { struct mlx4_dev *dev = mdev->dev; @@ -254,12 +272,7 @@ void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev) memset(&mdev->cycles, 0, sizeof(mdev->cycles)); mdev->cycles.read = mlx4_en_read_clock; mdev->cycles.mask = CLOCKSOURCE_MASK(48); - /* Using shift to make calculation more accurate. Since current HW - * clock frequency is 427 MHz, and cycles are given using a 48 bits - * register, the biggest shift when calculating using u64, is 14 - * (max_cycles * multiplier < 2^64) - */ - mdev->cycles.shift = 14; + mdev->cycles.shift = freq_to_shift(dev->caps.hca_core_clock); mdev->cycles.mult = clocksource_khz2mult(1000 * dev->caps.hca_core_clock, mdev->cycles.shift); mdev->nominal_c_mult = mdev->cycles.mult; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index dd84cabb2a51..f69584a9b47f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -501,34 +501,30 @@ static u32 mlx4_en_autoneg_get(struct net_device *dev) return autoneg; } -static u32 ptys_get_supported_port(struct mlx4_ptys_reg *ptys_reg) +static void ptys2ethtool_update_supported_port(unsigned long *mask, + struct mlx4_ptys_reg *ptys_reg) { u32 eth_proto = be32_to_cpu(ptys_reg->eth_proto_cap); if (eth_proto & (MLX4_PROT_MASK(MLX4_10GBASE_T) | MLX4_PROT_MASK(MLX4_1000BASE_T) | MLX4_PROT_MASK(MLX4_100BASE_TX))) { - return SUPPORTED_TP; - } - - if (eth_proto & (MLX4_PROT_MASK(MLX4_10GBASE_CR) + __set_bit(ETHTOOL_LINK_MODE_TP_BIT, mask); + } else if (eth_proto & (MLX4_PROT_MASK(MLX4_10GBASE_CR) | MLX4_PROT_MASK(MLX4_10GBASE_SR) | MLX4_PROT_MASK(MLX4_56GBASE_SR4) | MLX4_PROT_MASK(MLX4_40GBASE_CR4) | MLX4_PROT_MASK(MLX4_40GBASE_SR4) | MLX4_PROT_MASK(MLX4_1000BASE_CX_SGMII))) { - return SUPPORTED_FIBRE; - } - - if (eth_proto & (MLX4_PROT_MASK(MLX4_56GBASE_KR4) + __set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, mask); + } else if (eth_proto & (MLX4_PROT_MASK(MLX4_56GBASE_KR4) | MLX4_PROT_MASK(MLX4_40GBASE_KR4) | MLX4_PROT_MASK(MLX4_20GBASE_KR2) | MLX4_PROT_MASK(MLX4_10GBASE_KR) | MLX4_PROT_MASK(MLX4_10GBASE_KX4) | MLX4_PROT_MASK(MLX4_1000BASE_KX))) { - return SUPPORTED_Backplane; + __set_bit(ETHTOOL_LINK_MODE_Backplane_BIT, mask); } - return 0; } static u32 ptys_get_active_port(struct mlx4_ptys_reg *ptys_reg) @@ -574,122 +570,111 @@ static u32 ptys_get_active_port(struct mlx4_ptys_reg *ptys_reg) enum ethtool_report { SUPPORTED = 0, ADVERTISED = 1, - SPEED = 2 }; +struct ptys2ethtool_config { + __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); + __ETHTOOL_DECLARE_LINK_MODE_MASK(advertised); + u32 speed; +}; + +static unsigned long *ptys2ethtool_link_mode(struct ptys2ethtool_config *cfg, + enum ethtool_report report) +{ + switch (report) { + case SUPPORTED: + return cfg->supported; + case ADVERTISED: + return cfg->advertised; + } + return NULL; +} + +#define MLX4_BUILD_PTYS2ETHTOOL_CONFIG(reg_, speed_, ...) \ + ({ \ + struct ptys2ethtool_config *cfg; \ + const unsigned int modes[] = { __VA_ARGS__ }; \ + unsigned int i; \ + cfg = &ptys2ethtool_map[reg_]; \ + cfg->speed = speed_; \ + bitmap_zero(cfg->supported, \ + __ETHTOOL_LINK_MODE_MASK_NBITS); \ + bitmap_zero(cfg->advertised, \ + __ETHTOOL_LINK_MODE_MASK_NBITS); \ + for (i = 0 ; i < ARRAY_SIZE(modes) ; ++i) { \ + __set_bit(modes[i], cfg->supported); \ + __set_bit(modes[i], cfg->advertised); \ + } \ + }) + /* Translates mlx4 link mode to equivalent ethtool Link modes/speed */ -static u32 ptys2ethtool_map[MLX4_LINK_MODES_SZ][3] = { - [MLX4_100BASE_TX] = { - SUPPORTED_100baseT_Full, - ADVERTISED_100baseT_Full, - SPEED_100 - }, - - [MLX4_1000BASE_T] = { - SUPPORTED_1000baseT_Full, - ADVERTISED_1000baseT_Full, - SPEED_1000 - }, - [MLX4_1000BASE_CX_SGMII] = { - SUPPORTED_1000baseKX_Full, - ADVERTISED_1000baseKX_Full, - SPEED_1000 - }, - [MLX4_1000BASE_KX] = { - SUPPORTED_1000baseKX_Full, - ADVERTISED_1000baseKX_Full, - SPEED_1000 - }, - - [MLX4_10GBASE_T] = { - SUPPORTED_10000baseT_Full, - ADVERTISED_10000baseT_Full, - SPEED_10000 - }, - [MLX4_10GBASE_CX4] = { - SUPPORTED_10000baseKX4_Full, - ADVERTISED_10000baseKX4_Full, - SPEED_10000 - }, - [MLX4_10GBASE_KX4] = { - SUPPORTED_10000baseKX4_Full, - ADVERTISED_10000baseKX4_Full, - SPEED_10000 - }, - [MLX4_10GBASE_KR] = { - SUPPORTED_10000baseKR_Full, - ADVERTISED_10000baseKR_Full, - SPEED_10000 - }, - [MLX4_10GBASE_CR] = { - SUPPORTED_10000baseKR_Full, - ADVERTISED_10000baseKR_Full, - SPEED_10000 - }, - [MLX4_10GBASE_SR] = { - SUPPORTED_10000baseKR_Full, - ADVERTISED_10000baseKR_Full, - SPEED_10000 - }, - - [MLX4_20GBASE_KR2] = { - SUPPORTED_20000baseMLD2_Full | SUPPORTED_20000baseKR2_Full, - ADVERTISED_20000baseMLD2_Full | ADVERTISED_20000baseKR2_Full, - SPEED_20000 - }, - - [MLX4_40GBASE_CR4] = { - SUPPORTED_40000baseCR4_Full, - ADVERTISED_40000baseCR4_Full, - SPEED_40000 - }, - [MLX4_40GBASE_KR4] = { - SUPPORTED_40000baseKR4_Full, - ADVERTISED_40000baseKR4_Full, - SPEED_40000 - }, - [MLX4_40GBASE_SR4] = { - SUPPORTED_40000baseSR4_Full, - ADVERTISED_40000baseSR4_Full, - SPEED_40000 - }, - - [MLX4_56GBASE_KR4] = { - SUPPORTED_56000baseKR4_Full, - ADVERTISED_56000baseKR4_Full, - SPEED_56000 - }, - [MLX4_56GBASE_CR4] = { - SUPPORTED_56000baseCR4_Full, - ADVERTISED_56000baseCR4_Full, - SPEED_56000 - }, - [MLX4_56GBASE_SR4] = { - SUPPORTED_56000baseSR4_Full, - ADVERTISED_56000baseSR4_Full, - SPEED_56000 - }, +static struct ptys2ethtool_config ptys2ethtool_map[MLX4_LINK_MODES_SZ]; + +void __init mlx4_en_init_ptys2ethtool_map(void) +{ + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_100BASE_TX, SPEED_100, + ETHTOOL_LINK_MODE_100baseT_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_1000BASE_T, SPEED_1000, + ETHTOOL_LINK_MODE_1000baseT_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_1000BASE_CX_SGMII, SPEED_1000, + ETHTOOL_LINK_MODE_1000baseKX_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_1000BASE_KX, SPEED_1000, + ETHTOOL_LINK_MODE_1000baseKX_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_T, SPEED_10000, + ETHTOOL_LINK_MODE_10000baseT_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_CX4, SPEED_10000, + ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_KX4, SPEED_10000, + ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_KR, SPEED_10000, + ETHTOOL_LINK_MODE_10000baseKR_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_CR, SPEED_10000, + ETHTOOL_LINK_MODE_10000baseKR_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_SR, SPEED_10000, + ETHTOOL_LINK_MODE_10000baseKR_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_20GBASE_KR2, SPEED_20000, + ETHTOOL_LINK_MODE_20000baseMLD2_Full_BIT, + ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_40GBASE_CR4, SPEED_40000, + ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_40GBASE_KR4, SPEED_40000, + ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_40GBASE_SR4, SPEED_40000, + ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_56GBASE_KR4, SPEED_56000, + ETHTOOL_LINK_MODE_56000baseKR4_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_56GBASE_CR4, SPEED_56000, + ETHTOOL_LINK_MODE_56000baseCR4_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_56GBASE_SR4, SPEED_56000, + ETHTOOL_LINK_MODE_56000baseSR4_Full_BIT); }; -static u32 ptys2ethtool_link_modes(u32 eth_proto, enum ethtool_report report) +static void ptys2ethtool_update_link_modes(unsigned long *link_modes, + u32 eth_proto, + enum ethtool_report report) { int i; - u32 link_modes = 0; - for (i = 0; i < MLX4_LINK_MODES_SZ; i++) { if (eth_proto & MLX4_PROT_MASK(i)) - link_modes |= ptys2ethtool_map[i][report]; + bitmap_or(link_modes, link_modes, + ptys2ethtool_link_mode(&ptys2ethtool_map[i], + report), + __ETHTOOL_LINK_MODE_MASK_NBITS); } - return link_modes; } -static u32 ethtool2ptys_link_modes(u32 link_modes, enum ethtool_report report) +static u32 ethtool2ptys_link_modes(const unsigned long *link_modes, + enum ethtool_report report) { int i; u32 ptys_modes = 0; for (i = 0; i < MLX4_LINK_MODES_SZ; i++) { - if (ptys2ethtool_map[i][report] & link_modes) + if (bitmap_intersects( + ptys2ethtool_link_mode(&ptys2ethtool_map[i], + report), + link_modes, + __ETHTOOL_LINK_MODE_MASK_NBITS)) ptys_modes |= 1 << i; } return ptys_modes; @@ -702,14 +687,15 @@ static u32 speed2ptys_link_modes(u32 speed) u32 ptys_modes = 0; for (i = 0; i < MLX4_LINK_MODES_SZ; i++) { - if (ptys2ethtool_map[i][SPEED] == speed) + if (ptys2ethtool_map[i].speed == speed) ptys_modes |= 1 << i; } return ptys_modes; } -static int ethtool_get_ptys_settings(struct net_device *dev, - struct ethtool_cmd *cmd) +static int +ethtool_get_ptys_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *link_ksettings) { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_ptys_reg ptys_reg; @@ -737,79 +723,102 @@ static int ethtool_get_ptys_settings(struct net_device *dev, en_dbg(DRV, priv, "ptys_reg.eth_proto_lp_adv %x\n", be32_to_cpu(ptys_reg.eth_proto_lp_adv)); - cmd->supported = 0; - cmd->advertising = 0; + /* reset supported/advertising masks */ + ethtool_link_ksettings_zero_link_mode(link_ksettings, supported); + ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising); - cmd->supported |= ptys_get_supported_port(&ptys_reg); + ptys2ethtool_update_supported_port(link_ksettings->link_modes.supported, + &ptys_reg); eth_proto = be32_to_cpu(ptys_reg.eth_proto_cap); - cmd->supported |= ptys2ethtool_link_modes(eth_proto, SUPPORTED); + ptys2ethtool_update_link_modes(link_ksettings->link_modes.supported, + eth_proto, SUPPORTED); eth_proto = be32_to_cpu(ptys_reg.eth_proto_admin); - cmd->advertising |= ptys2ethtool_link_modes(eth_proto, ADVERTISED); + ptys2ethtool_update_link_modes(link_ksettings->link_modes.advertising, + eth_proto, ADVERTISED); - cmd->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; - cmd->advertising |= (priv->prof->tx_pause) ? ADVERTISED_Pause : 0; + ethtool_link_ksettings_add_link_mode(link_ksettings, supported, + Pause); + ethtool_link_ksettings_add_link_mode(link_ksettings, supported, + Asym_Pause); - cmd->advertising |= (priv->prof->tx_pause ^ priv->prof->rx_pause) ? - ADVERTISED_Asym_Pause : 0; + if (priv->prof->tx_pause) + ethtool_link_ksettings_add_link_mode(link_ksettings, + advertising, Pause); + if (priv->prof->tx_pause ^ priv->prof->rx_pause) + ethtool_link_ksettings_add_link_mode(link_ksettings, + advertising, Asym_Pause); - cmd->port = ptys_get_active_port(&ptys_reg); - cmd->transceiver = (SUPPORTED_TP & cmd->supported) ? - XCVR_EXTERNAL : XCVR_INTERNAL; + link_ksettings->base.port = ptys_get_active_port(&ptys_reg); if (mlx4_en_autoneg_get(dev)) { - cmd->supported |= SUPPORTED_Autoneg; - cmd->advertising |= ADVERTISED_Autoneg; + ethtool_link_ksettings_add_link_mode(link_ksettings, + supported, Autoneg); + ethtool_link_ksettings_add_link_mode(link_ksettings, + advertising, Autoneg); } - cmd->autoneg = (priv->port_state.flags & MLX4_EN_PORT_ANC) ? + link_ksettings->base.autoneg + = (priv->port_state.flags & MLX4_EN_PORT_ANC) ? AUTONEG_ENABLE : AUTONEG_DISABLE; eth_proto = be32_to_cpu(ptys_reg.eth_proto_lp_adv); - cmd->lp_advertising = ptys2ethtool_link_modes(eth_proto, ADVERTISED); - cmd->lp_advertising |= (priv->port_state.flags & MLX4_EN_PORT_ANC) ? - ADVERTISED_Autoneg : 0; + ethtool_link_ksettings_zero_link_mode(link_ksettings, lp_advertising); + ptys2ethtool_update_link_modes( + link_ksettings->link_modes.lp_advertising, + eth_proto, ADVERTISED); + if (priv->port_state.flags & MLX4_EN_PORT_ANC) + ethtool_link_ksettings_add_link_mode(link_ksettings, + lp_advertising, Autoneg); - cmd->phy_address = 0; - cmd->mdio_support = 0; - cmd->maxtxpkt = 0; - cmd->maxrxpkt = 0; - cmd->eth_tp_mdix = ETH_TP_MDI_INVALID; - cmd->eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO; + link_ksettings->base.phy_address = 0; + link_ksettings->base.mdio_support = 0; + link_ksettings->base.eth_tp_mdix = ETH_TP_MDI_INVALID; + link_ksettings->base.eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO; return ret; } -static void ethtool_get_default_settings(struct net_device *dev, - struct ethtool_cmd *cmd) +static void +ethtool_get_default_link_ksettings( + struct net_device *dev, struct ethtool_link_ksettings *link_ksettings) { struct mlx4_en_priv *priv = netdev_priv(dev); int trans_type; - cmd->autoneg = AUTONEG_DISABLE; - cmd->supported = SUPPORTED_10000baseT_Full; - cmd->advertising = ADVERTISED_10000baseT_Full; - trans_type = priv->port_state.transceiver; + link_ksettings->base.autoneg = AUTONEG_DISABLE; + + ethtool_link_ksettings_zero_link_mode(link_ksettings, supported); + ethtool_link_ksettings_add_link_mode(link_ksettings, supported, + 10000baseT_Full); + ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising); + ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, + 10000baseT_Full); + + trans_type = priv->port_state.transceiver; if (trans_type > 0 && trans_type <= 0xC) { - cmd->port = PORT_FIBRE; - cmd->transceiver = XCVR_EXTERNAL; - cmd->supported |= SUPPORTED_FIBRE; - cmd->advertising |= ADVERTISED_FIBRE; + link_ksettings->base.port = PORT_FIBRE; + ethtool_link_ksettings_add_link_mode(link_ksettings, + supported, FIBRE); + ethtool_link_ksettings_add_link_mode(link_ksettings, + advertising, FIBRE); } else if (trans_type == 0x80 || trans_type == 0) { - cmd->port = PORT_TP; - cmd->transceiver = XCVR_INTERNAL; - cmd->supported |= SUPPORTED_TP; - cmd->advertising |= ADVERTISED_TP; + link_ksettings->base.port = PORT_TP; + ethtool_link_ksettings_add_link_mode(link_ksettings, + supported, TP); + ethtool_link_ksettings_add_link_mode(link_ksettings, + advertising, TP); } else { - cmd->port = -1; - cmd->transceiver = -1; + link_ksettings->base.port = -1; } } -static int mlx4_en_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int +mlx4_en_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *link_ksettings) { struct mlx4_en_priv *priv = netdev_priv(dev); int ret = -EINVAL; @@ -822,16 +831,16 @@ static int mlx4_en_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) priv->port_state.flags & MLX4_EN_PORT_ANE); if (priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_ETH_PROT_CTRL) - ret = ethtool_get_ptys_settings(dev, cmd); + ret = ethtool_get_ptys_link_ksettings(dev, link_ksettings); if (ret) /* ETH PROT CRTL is not supported or PTYS CMD failed */ - ethtool_get_default_settings(dev, cmd); + ethtool_get_default_link_ksettings(dev, link_ksettings); if (netif_carrier_ok(dev)) { - ethtool_cmd_speed_set(cmd, priv->port_state.link_speed); - cmd->duplex = DUPLEX_FULL; + link_ksettings->base.speed = priv->port_state.link_speed; + link_ksettings->base.duplex = DUPLEX_FULL; } else { - ethtool_cmd_speed_set(cmd, SPEED_UNKNOWN); - cmd->duplex = DUPLEX_UNKNOWN; + link_ksettings->base.speed = SPEED_UNKNOWN; + link_ksettings->base.duplex = DUPLEX_UNKNOWN; } return 0; } @@ -855,21 +864,29 @@ static __be32 speed_set_ptys_admin(struct mlx4_en_priv *priv, u32 speed, return proto_admin; } -static int mlx4_en_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int +mlx4_en_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *link_ksettings) { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_ptys_reg ptys_reg; __be32 proto_admin; int ret; - u32 ptys_adv = ethtool2ptys_link_modes(cmd->advertising, ADVERTISED); - int speed = ethtool_cmd_speed(cmd); + u32 ptys_adv = ethtool2ptys_link_modes( + link_ksettings->link_modes.advertising, ADVERTISED); + const int speed = link_ksettings->base.speed; - en_dbg(DRV, priv, "Set Speed=%d adv=0x%x autoneg=%d duplex=%d\n", - speed, cmd->advertising, cmd->autoneg, cmd->duplex); + en_dbg(DRV, priv, + "Set Speed=%d adv={%*pbl} autoneg=%d duplex=%d\n", + speed, __ETHTOOL_LINK_MODE_MASK_NBITS, + link_ksettings->link_modes.advertising, + link_ksettings->base.autoneg, + link_ksettings->base.duplex); - if (!(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_ETH_PROT_CTRL) || - (cmd->duplex == DUPLEX_HALF)) + if (!(priv->mdev->dev->caps.flags2 & + MLX4_DEV_CAP_FLAG2_ETH_PROT_CTRL) || + (link_ksettings->base.duplex == DUPLEX_HALF)) return -EINVAL; memset(&ptys_reg, 0, sizeof(ptys_reg)); @@ -883,7 +900,7 @@ static int mlx4_en_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) return 0; } - proto_admin = cmd->autoneg == AUTONEG_ENABLE ? + proto_admin = link_ksettings->base.autoneg == AUTONEG_ENABLE ? cpu_to_be32(ptys_adv) : speed_set_ptys_admin(priv, speed, ptys_reg.eth_proto_cap); @@ -1982,8 +1999,8 @@ static int mlx4_en_set_phys_id(struct net_device *dev, const struct ethtool_ops mlx4_en_ethtool_ops = { .get_drvinfo = mlx4_en_get_drvinfo, - .get_settings = mlx4_en_get_settings, - .set_settings = mlx4_en_set_settings, + .get_link_ksettings = mlx4_en_get_link_ksettings, + .set_link_ksettings = mlx4_en_set_link_ksettings, .get_link = ethtool_op_get_link, .get_strings = mlx4_en_get_strings, .get_sset_count = mlx4_en_get_sset_count, diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c index e0ec280a7fa1..bf7628db098a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c @@ -382,6 +382,7 @@ static void mlx4_en_verify_params(void) static int __init mlx4_en_init(void) { mlx4_en_verify_params(); + mlx4_en_init_ptys2ethtool_map(); return mlx4_register_interface(&mlx4_en_interface); } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 0c7e3f69a73b..b4b258c8ca47 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -40,6 +40,7 @@ #include <net/ip.h> #include <net/busy_poll.h> #include <net/vxlan.h> +#include <net/devlink.h> #include <linux/mlx4/driver.h> #include <linux/mlx4/device.h> @@ -69,6 +70,15 @@ int mlx4_en_setup_tc(struct net_device *dev, u8 up) return 0; } +static int __mlx4_en_setup_tc(struct net_device *dev, u32 handle, __be16 proto, + struct tc_to_netdev *tc) +{ + if (tc->type != TC_SETUP_MQPRIO) + return -EINVAL; + + return mlx4_en_setup_tc(dev, tc->tc); +} + #ifdef CONFIG_RFS_ACCEL struct mlx4_en_filter { @@ -2024,8 +2034,11 @@ void mlx4_en_destroy_netdev(struct net_device *dev) en_dbg(DRV, priv, "Destroying netdev on port:%d\n", priv->port); /* Unregister device - this will close the port if it was up */ - if (priv->registered) + if (priv->registered) { + devlink_port_type_clear(mlx4_get_devlink_port(mdev->dev, + priv->port)); unregister_netdev(dev); + } if (priv->allocated) mlx4_free_hwq_res(mdev->dev, &priv->res, MLX4_EN_PAGE_SIZE); @@ -2245,7 +2258,7 @@ static int mlx4_en_set_vf_mac(struct net_device *dev, int queue, u8 *mac) struct mlx4_en_dev *mdev = en_priv->mdev; u64 mac_u64 = mlx4_mac_to_u64(mac); - if (!is_valid_ether_addr(mac)) + if (is_multicast_ether_addr(mac)) return -EINVAL; return mlx4_set_vf_mac(mdev->dev, en_priv->port, queue, mac_u64); @@ -2344,8 +2357,6 @@ out: /* set offloads */ priv->dev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_RXCSUM | NETIF_F_TSO | NETIF_F_GSO_UDP_TUNNEL; - priv->dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL; - priv->dev->features |= NETIF_F_GSO_UDP_TUNNEL; } static void mlx4_en_del_vxlan_offloads(struct work_struct *work) @@ -2356,8 +2367,6 @@ static void mlx4_en_del_vxlan_offloads(struct work_struct *work) /* unset offloads */ priv->dev->hw_enc_features &= ~(NETIF_F_IP_CSUM | NETIF_F_RXCSUM | NETIF_F_TSO | NETIF_F_GSO_UDP_TUNNEL); - priv->dev->hw_features &= ~NETIF_F_GSO_UDP_TUNNEL; - priv->dev->features &= ~NETIF_F_GSO_UDP_TUNNEL; ret = mlx4_SET_PORT_VXLAN(priv->mdev->dev, priv->port, VXLAN_STEER_BY_OUTER_MAC, 0); @@ -2466,7 +2475,7 @@ static const struct net_device_ops mlx4_netdev_ops = { #endif .ndo_set_features = mlx4_en_set_features, .ndo_fix_features = mlx4_en_fix_features, - .ndo_setup_tc = mlx4_en_setup_tc, + .ndo_setup_tc = __mlx4_en_setup_tc, #ifdef CONFIG_RFS_ACCEL .ndo_rx_flow_steer = mlx4_en_filter_rfs, #endif @@ -2504,7 +2513,7 @@ static const struct net_device_ops mlx4_netdev_ops_master = { #endif .ndo_set_features = mlx4_en_set_features, .ndo_fix_features = mlx4_en_fix_features, - .ndo_setup_tc = mlx4_en_setup_tc, + .ndo_setup_tc = __mlx4_en_setup_tc, #ifdef CONFIG_RFS_ACCEL .ndo_rx_flow_steer = mlx4_en_filter_rfs, #endif @@ -2980,6 +2989,11 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, priv->rss_hash_fn = ETH_RSS_HASH_TOP; } + if (mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) { + dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL; + dev->features |= NETIF_F_GSO_UDP_TUNNEL; + } + mdev->pndev[port] = dev; mdev->upper[port] = NULL; @@ -3041,6 +3055,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, } priv->registered = 1; + devlink_port_type_eth_set(mlx4_get_devlink_port(mdev->dev, priv->port), + dev); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c index ee99e67187f5..3904b5fc0b7c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_port.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c @@ -238,11 +238,11 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) stats->collisions = 0; stats->rx_dropped = be32_to_cpu(mlx4_en_stats->RDROP); stats->rx_length_errors = be32_to_cpu(mlx4_en_stats->RdropLength); - stats->rx_over_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw); + stats->rx_over_errors = 0; stats->rx_crc_errors = be32_to_cpu(mlx4_en_stats->RCRC); stats->rx_frame_errors = 0; stats->rx_fifo_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw); - stats->rx_missed_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw); + stats->rx_missed_errors = 0; stats->tx_aborted_errors = 0; stats->tx_carrier_errors = 0; stats->tx_fifo_errors = 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_resources.c b/drivers/net/ethernet/mellanox/mlx4/en_resources.c index 12aab5a659d3..02e925d6f734 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_resources.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_resources.c @@ -58,7 +58,8 @@ void mlx4_en_fill_qp_context(struct mlx4_en_priv *priv, int size, int stride, } else { context->sq_size_stride = ilog2(TXBB_SIZE) - 4; } - context->usr_page = cpu_to_be32(mdev->priv_uar.index); + context->usr_page = cpu_to_be32(mlx4_to_hw_uar_index(mdev->dev, + mdev->priv_uar.index)); context->local_qpn = cpu_to_be32(qpn); context->pri_path.ackto = 1 & 0x07; context->pri_path.sched_queue = 0x83 | (priv->port - 1) << 6; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 41440b2b20a3..86bcfe510e4e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -82,8 +82,7 @@ static int mlx4_alloc_pages(struct mlx4_en_priv *priv, /* Not doing get_page() for each frag is a big win * on asymetric workloads. Note we can not use atomic_set(). */ - atomic_add(page_alloc->page_size / frag_info->frag_stride - 1, - &page->_count); + page_ref_add(page, page_alloc->page_size / frag_info->frag_stride - 1); return 0; } @@ -127,7 +126,7 @@ out: dma_unmap_page(priv->ddev, page_alloc[i].dma, page_alloc[i].page_size, PCI_DMA_FROMDEVICE); page = page_alloc[i].page; - atomic_set(&page->_count, 1); + set_page_count(page, 1); put_page(page); } } @@ -165,7 +164,7 @@ static int mlx4_en_init_allocator(struct mlx4_en_priv *priv, en_dbg(DRV, priv, " frag %d allocator: - size:%d frags:%d\n", i, ring->page_alloc[i].page_size, - atomic_read(&ring->page_alloc[i].page->_count)); + page_ref_count(ring->page_alloc[i].page)); } return 0; @@ -177,7 +176,7 @@ out: dma_unmap_page(priv->ddev, page_alloc->dma, page_alloc->page_size, PCI_DMA_FROMDEVICE); page = page_alloc->page; - atomic_set(&page->_count, 1); + set_page_count(page, 1); put_page(page); page_alloc->page = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 4421bf5463f6..c0d7b7296236 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -213,7 +213,9 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv, mlx4_en_fill_qp_context(priv, ring->size, ring->stride, 1, 0, ring->qpn, ring->cqn, user_prio, &ring->context); if (ring->bf_alloced) - ring->context.usr_page = cpu_to_be32(ring->bf.uar->index); + ring->context.usr_page = + cpu_to_be32(mlx4_to_hw_uar_index(mdev->dev, + ring->bf.uar->index)); err = mlx4_qp_to_ready(mdev->dev, &ring->wqres.mtt, &ring->context, &ring->qp, &ring->qp_state); @@ -274,7 +276,8 @@ static void mlx4_en_stamp_wqe(struct mlx4_en_priv *priv, static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv, struct mlx4_en_tx_ring *ring, - int index, u8 owner, u64 timestamp) + int index, u8 owner, u64 timestamp, + int napi_mode) { struct mlx4_en_tx_info *tx_info = &ring->tx_info[index]; struct mlx4_en_tx_desc *tx_desc = ring->buf + index * TXBB_SIZE; @@ -345,7 +348,8 @@ static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv, } } } - dev_consume_skb_any(skb); + napi_consume_skb(skb, napi_mode); + return tx_info->nr_txbb; } @@ -369,7 +373,8 @@ int mlx4_en_free_tx_buf(struct net_device *dev, struct mlx4_en_tx_ring *ring) while (ring->cons != ring->prod) { ring->last_nr_txbb = mlx4_en_free_tx_desc(priv, ring, ring->cons & ring->size_mask, - !!(ring->cons & ring->size), 0); + !!(ring->cons & ring->size), 0, + 0 /* Non-NAPI caller */); ring->cons += ring->last_nr_txbb; cnt++; } @@ -383,7 +388,7 @@ int mlx4_en_free_tx_buf(struct net_device *dev, struct mlx4_en_tx_ring *ring) } static bool mlx4_en_process_tx_cq(struct net_device *dev, - struct mlx4_en_cq *cq) + struct mlx4_en_cq *cq, int napi_budget) { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_cq *mcq = &cq->mcq; @@ -449,7 +454,7 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev, last_nr_txbb = mlx4_en_free_tx_desc( priv, ring, ring_index, !!((ring_cons + txbbs_skipped) & - ring->size), timestamp); + ring->size), timestamp, napi_budget); mlx4_en_stamp_wqe(priv, ring, stamp_index, !!((ring_cons + txbbs_stamp) & @@ -509,7 +514,7 @@ int mlx4_en_poll_tx_cq(struct napi_struct *napi, int budget) struct mlx4_en_priv *priv = netdev_priv(dev); int clean_complete; - clean_complete = mlx4_en_process_tx_cq(dev, cq); + clean_complete = mlx4_en_process_tx_cq(dev, cq, budget); if (!clean_complete) return budget; diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index 4696053165f8..f613977455e0 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -940,9 +940,10 @@ static void __iomem *mlx4_get_eq_uar(struct mlx4_dev *dev, struct mlx4_eq *eq) if (!priv->eq_table.uar_map[index]) { priv->eq_table.uar_map[index] = - ioremap(pci_resource_start(dev->persist->pdev, 2) + - ((eq->eqn / 4) << PAGE_SHIFT), - PAGE_SIZE); + ioremap( + pci_resource_start(dev->persist->pdev, 2) + + ((eq->eqn / 4) << (dev->uar_page_shift)), + (1 << (dev->uar_page_shift))); if (!priv->eq_table.uar_map[index]) { mlx4_err(dev, "Couldn't map EQ doorbell for EQN 0x%06x\n", eq->eqn); diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index d66c690a8597..e97094598b2d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -157,7 +157,8 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags) [29] = "802.1ad offload support", [31] = "Modifying loopback source checks using UPDATE_QP support", [32] = "Loopback source checks support", - [33] = "RoCEv2 support" + [33] = "RoCEv2 support", + [34] = "DMFS Sniffer support (UC & MC)" }; int i; @@ -810,6 +811,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) if (field & 0x80) dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_FS_EN; dev_cap->fs_log_max_ucast_qp_range_size = field & 0x1f; + if (field & 0x20) + dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_DMFS_UC_MC_SNIFFER; MLX4_GET(field, outbox, QUERY_DEV_CAP_PORT_BEACON_OFFSET); if (field & 0x80) dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_PORT_BEACON; diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c index 0472941af820..dec77d6f0ac9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/intf.c +++ b/drivers/net/ethernet/mellanox/mlx4/intf.c @@ -34,6 +34,7 @@ #include <linux/slab.h> #include <linux/export.h> #include <linux/errno.h> +#include <net/devlink.h> #include "mlx4.h" @@ -249,3 +250,11 @@ void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int return result; } EXPORT_SYMBOL_GPL(mlx4_get_protocol_dev); + +struct devlink_port *mlx4_get_devlink_port(struct mlx4_dev *dev, int port) +{ + struct mlx4_port_info *info = &mlx4_priv(dev)->port[port]; + + return &info->devlink_port; +} +EXPORT_SYMBOL_GPL(mlx4_get_devlink_port); diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index f1b6d219e445..358f7230da58 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -42,6 +42,7 @@ #include <linux/io-mapping.h> #include <linux/delay.h> #include <linux/kmod.h> +#include <net/devlink.h> #include <linux/mlx4/device.h> #include <linux/mlx4/doorbell.h> @@ -104,6 +105,11 @@ module_param(enable_64b_cqe_eqe, bool, 0444); MODULE_PARM_DESC(enable_64b_cqe_eqe, "Enable 64 byte CQEs/EQEs when the FW supports this (default: True)"); +static bool enable_4k_uar; +module_param(enable_4k_uar, bool, 0444); +MODULE_PARM_DESC(enable_4k_uar, + "Enable using 4K UAR. Should not be enabled if have VFs which do not support 4K UARs (default: false)"); + #define PF_CONTEXT_BEHAVIOUR_MASK (MLX4_FUNC_CAP_64B_EQE_CQE | \ MLX4_FUNC_CAP_EQE_CQE_STRIDE | \ MLX4_FUNC_CAP_DMFS_A0_STATIC) @@ -168,6 +174,20 @@ struct mlx4_port_config { static atomic_t pf_loading = ATOMIC_INIT(0); +static inline void mlx4_set_num_reserved_uars(struct mlx4_dev *dev, + struct mlx4_dev_cap *dev_cap) +{ + /* The reserved_uars is calculated by system page size unit. + * Therefore, adjustment is added when the uar page size is less + * than the system page size + */ + dev->caps.reserved_uars = + max_t(int, + mlx4_get_num_reserved_uar(dev), + dev_cap->reserved_uars / + (1 << (PAGE_SHIFT - dev->uar_page_shift))); +} + int mlx4_check_port_params(struct mlx4_dev *dev, enum mlx4_port_type *port_type) { @@ -386,8 +406,6 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) dev->caps.reserved_mtts = dev_cap->reserved_mtts; dev->caps.reserved_mrws = dev_cap->reserved_mrws; - /* The first 128 UARs are used for EQ doorbells */ - dev->caps.reserved_uars = max_t(int, 128, dev_cap->reserved_uars); dev->caps.reserved_pds = dev_cap->reserved_pds; dev->caps.reserved_xrcds = (dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC) ? dev_cap->reserved_xrcds : 0; @@ -405,6 +423,19 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) dev->caps.max_gso_sz = dev_cap->max_gso_sz; dev->caps.max_rss_tbl_sz = dev_cap->max_rss_tbl_sz; + /* Save uar page shift */ + if (!mlx4_is_slave(dev)) { + /* Virtual PCI function needs to determine UAR page size from + * firmware. Only master PCI function can set the uar page size + */ + if (enable_4k_uar) + dev->uar_page_shift = DEFAULT_UAR_PAGE_SHIFT; + else + dev->uar_page_shift = PAGE_SHIFT; + + mlx4_set_num_reserved_uars(dev, dev_cap); + } + if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PHV_EN) { struct mlx4_init_hca_param hca_param; @@ -815,16 +846,25 @@ static int mlx4_slave_cap(struct mlx4_dev *dev) return -ENODEV; } - /* slave gets uar page size from QUERY_HCA fw command */ - dev->caps.uar_page_size = 1 << (hca_param.uar_page_sz + 12); + /* Set uar_page_shift for VF */ + dev->uar_page_shift = hca_param.uar_page_sz + 12; - /* TODO: relax this assumption */ - if (dev->caps.uar_page_size != PAGE_SIZE) { - mlx4_err(dev, "UAR size:%d != kernel PAGE_SIZE of %ld\n", - dev->caps.uar_page_size, PAGE_SIZE); - return -ENODEV; + /* Make sure the master uar page size is valid */ + if (dev->uar_page_shift > PAGE_SHIFT) { + mlx4_err(dev, + "Invalid configuration: uar page size is larger than system page size\n"); + return -ENODEV; } + /* Set reserved_uars based on the uar_page_shift */ + mlx4_set_num_reserved_uars(dev, &dev_cap); + + /* Although uar page size in FW differs from system page size, + * upper software layers (mlx4_ib, mlx4_en and part of mlx4_core) + * still works with assumption that uar page size == system page size + */ + dev->caps.uar_page_size = PAGE_SIZE; + memset(&func_cap, 0, sizeof(func_cap)); err = mlx4_QUERY_FUNC_CAP(dev, 0, &func_cap); if (err) { @@ -1051,36 +1091,20 @@ static ssize_t show_port_type(struct device *dev, return strlen(buf); } -static ssize_t set_port_type(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static int __set_port_type(struct mlx4_port_info *info, + enum mlx4_port_type port_type) { - struct mlx4_port_info *info = container_of(attr, struct mlx4_port_info, - port_attr); struct mlx4_dev *mdev = info->dev; struct mlx4_priv *priv = mlx4_priv(mdev); enum mlx4_port_type types[MLX4_MAX_PORTS]; enum mlx4_port_type new_types[MLX4_MAX_PORTS]; - static DEFINE_MUTEX(set_port_type_mutex); int i; int err = 0; - mutex_lock(&set_port_type_mutex); - - if (!strcmp(buf, "ib\n")) - info->tmp_type = MLX4_PORT_TYPE_IB; - else if (!strcmp(buf, "eth\n")) - info->tmp_type = MLX4_PORT_TYPE_ETH; - else if (!strcmp(buf, "auto\n")) - info->tmp_type = MLX4_PORT_TYPE_AUTO; - else { - mlx4_err(mdev, "%s is not supported port type\n", buf); - err = -EINVAL; - goto err_out; - } - mlx4_stop_sense(mdev); mutex_lock(&priv->port_mutex); + info->tmp_type = port_type; + /* Possible type is always the one that was delivered */ mdev->caps.possible_type[info->port] = info->tmp_type; @@ -1122,6 +1146,37 @@ static ssize_t set_port_type(struct device *dev, out: mlx4_start_sense(mdev); mutex_unlock(&priv->port_mutex); + + return err; +} + +static ssize_t set_port_type(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct mlx4_port_info *info = container_of(attr, struct mlx4_port_info, + port_attr); + struct mlx4_dev *mdev = info->dev; + enum mlx4_port_type port_type; + static DEFINE_MUTEX(set_port_type_mutex); + int err; + + mutex_lock(&set_port_type_mutex); + + if (!strcmp(buf, "ib\n")) { + port_type = MLX4_PORT_TYPE_IB; + } else if (!strcmp(buf, "eth\n")) { + port_type = MLX4_PORT_TYPE_ETH; + } else if (!strcmp(buf, "auto\n")) { + port_type = MLX4_PORT_TYPE_AUTO; + } else { + mlx4_err(mdev, "%s is not supported port type\n", buf); + err = -EINVAL; + goto err_out; + } + + err = __set_port_type(info, port_type); + err_out: mutex_unlock(&set_port_type_mutex); @@ -1226,6 +1281,7 @@ err_set_port: static int mlx4_mf_bond(struct mlx4_dev *dev) { int err = 0; + int nvfs; struct mlx4_slaves_pport slaves_port1; struct mlx4_slaves_pport slaves_port2; DECLARE_BITMAP(slaves_port_1_2, MLX4_MFUNC_MAX); @@ -1242,11 +1298,18 @@ static int mlx4_mf_bond(struct mlx4_dev *dev) return -EINVAL; } + /* number of virtual functions is number of total functions minus one + * physical function for each port. + */ + nvfs = bitmap_weight(slaves_port1.slaves, dev->persist->num_vfs + 1) + + bitmap_weight(slaves_port2.slaves, dev->persist->num_vfs + 1) - 2; + /* limit on maximum allowed VFs */ - if ((bitmap_weight(slaves_port1.slaves, dev->persist->num_vfs + 1) + - bitmap_weight(slaves_port2.slaves, dev->persist->num_vfs + 1)) > - MAX_MF_BOND_ALLOWED_SLAVES) + if (nvfs > MAX_MF_BOND_ALLOWED_SLAVES) { + mlx4_warn(dev, "HA mode is not supported for %d VFs (max %d are allowed)\n", + nvfs, MAX_MF_BOND_ALLOWED_SLAVES); return -EINVAL; + } if (dev->caps.steering_mode != MLX4_STEERING_MODE_DEVICE_MANAGED) { mlx4_warn(dev, "HA mode unsupported for NON DMFS steering\n"); @@ -2179,8 +2242,15 @@ static int mlx4_init_hca(struct mlx4_dev *dev) dev->caps.max_fmr_maps = (1 << (32 - ilog2(dev->caps.num_mpts))) - 1; - init_hca.log_uar_sz = ilog2(dev->caps.num_uars); - init_hca.uar_page_sz = PAGE_SHIFT - 12; + if (enable_4k_uar) { + init_hca.log_uar_sz = ilog2(dev->caps.num_uars) + + PAGE_SHIFT - DEFAULT_UAR_PAGE_SHIFT; + init_hca.uar_page_sz = DEFAULT_UAR_PAGE_SHIFT - 12; + } else { + init_hca.log_uar_sz = ilog2(dev->caps.num_uars); + init_hca.uar_page_sz = PAGE_SHIFT - 12; + } + init_hca.mw_enabled = 0; if (dev->caps.flags & MLX4_DEV_CAP_FLAG_MEM_WINDOW || dev->caps.bmme_flags & MLX4_BMME_FLAG_TYPE_2_WIN) @@ -2847,8 +2917,13 @@ no_msi: static int mlx4_init_port_info(struct mlx4_dev *dev, int port) { + struct devlink *devlink = priv_to_devlink(mlx4_priv(dev)); struct mlx4_port_info *info = &mlx4_priv(dev)->port[port]; - int err = 0; + int err; + + err = devlink_port_register(devlink, &info->devlink_port, port); + if (err) + return err; info->dev = dev; info->port = port; @@ -2873,6 +2948,7 @@ static int mlx4_init_port_info(struct mlx4_dev *dev, int port) err = device_create_file(&dev->persist->pdev->dev, &info->port_attr); if (err) { mlx4_err(dev, "Failed to create file for port %d\n", port); + devlink_port_unregister(&info->devlink_port); info->port = -1; } @@ -3644,23 +3720,54 @@ err_disable_pdev: return err; } +static int mlx4_devlink_port_type_set(struct devlink_port *devlink_port, + enum devlink_port_type port_type) +{ + struct mlx4_port_info *info = container_of(devlink_port, + struct mlx4_port_info, + devlink_port); + enum mlx4_port_type mlx4_port_type; + + switch (port_type) { + case DEVLINK_PORT_TYPE_AUTO: + mlx4_port_type = MLX4_PORT_TYPE_AUTO; + break; + case DEVLINK_PORT_TYPE_ETH: + mlx4_port_type = MLX4_PORT_TYPE_ETH; + break; + case DEVLINK_PORT_TYPE_IB: + mlx4_port_type = MLX4_PORT_TYPE_IB; + break; + default: + return -EOPNOTSUPP; + } + + return __set_port_type(info, mlx4_port_type); +} + +static const struct devlink_ops mlx4_devlink_ops = { + .port_type_set = mlx4_devlink_port_type_set, +}; + static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) { + struct devlink *devlink; struct mlx4_priv *priv; struct mlx4_dev *dev; int ret; printk_once(KERN_INFO "%s", mlx4_version); - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (!priv) + devlink = devlink_alloc(&mlx4_devlink_ops, sizeof(*priv)); + if (!devlink) return -ENOMEM; + priv = devlink_priv(devlink); dev = &priv->dev; dev->persist = kzalloc(sizeof(*dev->persist), GFP_KERNEL); if (!dev->persist) { - kfree(priv); - return -ENOMEM; + ret = -ENOMEM; + goto err_devlink_free; } dev->persist->pdev = pdev; dev->persist->dev = dev; @@ -3669,14 +3776,23 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) mutex_init(&dev->persist->device_state_mutex); mutex_init(&dev->persist->interface_state_mutex); + ret = devlink_register(devlink, &pdev->dev); + if (ret) + goto err_persist_free; + ret = __mlx4_init_one(pdev, id->driver_data, priv); - if (ret) { - kfree(dev->persist); - kfree(priv); - } else { - pci_save_state(pdev); - } + if (ret) + goto err_devlink_unregister; + pci_save_state(pdev); + return 0; + +err_devlink_unregister: + devlink_unregister(devlink); +err_persist_free: + kfree(dev->persist); +err_devlink_free: + devlink_free(devlink); return ret; } @@ -3777,6 +3893,7 @@ static void mlx4_remove_one(struct pci_dev *pdev) struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev); struct mlx4_dev *dev = persist->dev; struct mlx4_priv *priv = mlx4_priv(dev); + struct devlink *devlink = priv_to_devlink(priv); int active_vfs = 0; mutex_lock(&persist->interface_state_mutex); @@ -3807,8 +3924,9 @@ static void mlx4_remove_one(struct pci_dev *pdev) pci_release_regions(pdev); pci_disable_device(pdev); + devlink_unregister(devlink); kfree(dev->persist); - kfree(priv); + devlink_free(devlink); pci_set_drvdata(pdev, NULL); } diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c index 1d4e2e054647..6aa73972d478 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mcg.c +++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c @@ -39,8 +39,6 @@ #include "mlx4.h" -static const u8 zero_gid[16]; /* automatically initialized to 0 */ - int mlx4_get_mgm_entry_size(struct mlx4_dev *dev) { return 1 << dev->oper_log_mgm_entry_size; @@ -752,8 +750,10 @@ static const u8 __promisc_mode[] = { [MLX4_FS_REGULAR] = 0x0, [MLX4_FS_ALL_DEFAULT] = 0x1, [MLX4_FS_MC_DEFAULT] = 0x3, - [MLX4_FS_UC_SNIFFER] = 0x4, - [MLX4_FS_MC_SNIFFER] = 0x5, + [MLX4_FS_MIRROR_RX_PORT] = 0x4, + [MLX4_FS_MIRROR_SX_PORT] = 0x5, + [MLX4_FS_UC_SNIFFER] = 0x6, + [MLX4_FS_MC_SNIFFER] = 0x7, }; int mlx4_map_sw_to_hw_steering_mode(struct mlx4_dev *dev, diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 7baef52db6b7..ef9683101ead 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -45,6 +45,7 @@ #include <linux/workqueue.h> #include <linux/interrupt.h> #include <linux/spinlock.h> +#include <net/devlink.h> #include <linux/mlx4/device.h> #include <linux/mlx4/driver.h> @@ -828,6 +829,7 @@ struct mlx4_port_info { struct mlx4_roce_gid_table gid_table; int base_qpn; struct cpu_rmap *rmap; + struct devlink_port devlink_port; }; struct mlx4_sense { diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 35de7d2e6b34..d12ab6a73344 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -607,6 +607,7 @@ static inline struct mlx4_cqe *mlx4_en_get_cqe(void *buf, int idx, int cqe_sz) #define MLX4_EN_WOL_DO_MODIFY (1ULL << 63) +void mlx4_en_init_ptys2ethtool_map(void); void mlx4_en_update_loopback_state(struct net_device *dev, netdev_features_t features); diff --git a/drivers/net/ethernet/mellanox/mlx4/pd.c b/drivers/net/ethernet/mellanox/mlx4/pd.c index 609c59dc854e..b3cc3ab63799 100644 --- a/drivers/net/ethernet/mellanox/mlx4/pd.c +++ b/drivers/net/ethernet/mellanox/mlx4/pd.c @@ -269,9 +269,15 @@ EXPORT_SYMBOL_GPL(mlx4_bf_free); int mlx4_init_uar_table(struct mlx4_dev *dev) { - if (dev->caps.num_uars <= 128) { - mlx4_err(dev, "Only %d UAR pages (need more than 128)\n", - dev->caps.num_uars); + int num_reserved_uar = mlx4_get_num_reserved_uar(dev); + + mlx4_dbg(dev, "uar_page_shift = %d", dev->uar_page_shift); + mlx4_dbg(dev, "Effective reserved_uars=%d", dev->caps.reserved_uars); + + if (dev->caps.num_uars <= num_reserved_uar) { + mlx4_err( + dev, "Only %d UAR pages (need more than %d)\n", + dev->caps.num_uars, num_reserved_uar); mlx4_err(dev, "Increase firmware log2_uar_bar_megabytes?\n"); return -ENODEV; } diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c index 787b7bb54d52..211c65087997 100644 --- a/drivers/net/ethernet/mellanox/mlx4/port.c +++ b/drivers/net/ethernet/mellanox/mlx4/port.c @@ -193,10 +193,10 @@ int __mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac) if (need_mf_bond) { if (port == 1) { mutex_lock(&table->mutex); - mutex_lock(&dup_table->mutex); + mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING); } else { mutex_lock(&dup_table->mutex); - mutex_lock(&table->mutex); + mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING); } } else { mutex_lock(&table->mutex); @@ -389,10 +389,10 @@ void __mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac) if (dup) { if (port == 1) { mutex_lock(&table->mutex); - mutex_lock(&dup_table->mutex); + mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING); } else { mutex_lock(&dup_table->mutex); - mutex_lock(&table->mutex); + mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING); } } else { mutex_lock(&table->mutex); @@ -479,10 +479,10 @@ int __mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac) if (dup) { if (port == 1) { mutex_lock(&table->mutex); - mutex_lock(&dup_table->mutex); + mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING); } else { mutex_lock(&dup_table->mutex); - mutex_lock(&table->mutex); + mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING); } } else { mutex_lock(&table->mutex); @@ -588,10 +588,10 @@ int __mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, if (need_mf_bond) { if (port == 1) { mutex_lock(&table->mutex); - mutex_lock(&dup_table->mutex); + mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING); } else { mutex_lock(&dup_table->mutex); - mutex_lock(&table->mutex); + mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING); } } else { mutex_lock(&table->mutex); @@ -764,10 +764,10 @@ void __mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan) if (dup) { if (port == 1) { mutex_lock(&table->mutex); - mutex_lock(&dup_table->mutex); + mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING); } else { mutex_lock(&dup_table->mutex); - mutex_lock(&table->mutex); + mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING); } } else { mutex_lock(&table->mutex); diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index b46dbe29ef6c..cd9b2b28df88 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -915,11 +915,13 @@ static int handle_existing_counter(struct mlx4_dev *dev, u8 slave, int port, spin_lock_irq(mlx4_tlock(dev)); r = find_res(dev, counter_index, RES_COUNTER); - if (!r || r->owner != slave) + if (!r || r->owner != slave) { ret = -EINVAL; - counter = container_of(r, struct res_counter, com); - if (!counter->port) - counter->port = port; + } else { + counter = container_of(r, struct res_counter, com); + if (!counter->port) + counter->port = port; + } spin_unlock_irq(mlx4_tlock(dev)); return ret; @@ -3139,7 +3141,7 @@ static int verify_qp_parameters(struct mlx4_dev *dev, case QP_TRANS_RTS2RTS: case QP_TRANS_SQD2SQD: case QP_TRANS_SQD2RTS: - if (slave != mlx4_master_func_num(dev)) + if (slave != mlx4_master_func_num(dev)) { if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH) { port = (qp_ctx->pri_path.sched_queue >> 6 & 1) + 1; if (dev->caps.port_mask[port] != MLX4_PORT_TYPE_IB) @@ -3158,6 +3160,7 @@ static int verify_qp_parameters(struct mlx4_dev *dev, if (qp_ctx->alt_path.mgid_index >= num_gids) return -EINVAL; } + } break; default: break; |