diff options
Diffstat (limited to 'drivers/net/ethernet/chelsio')
18 files changed, 1477 insertions, 275 deletions
diff --git a/drivers/net/ethernet/chelsio/Kconfig b/drivers/net/ethernet/chelsio/Kconfig index 4686a85a8..5713e83be 100644 --- a/drivers/net/ethernet/chelsio/Kconfig +++ b/drivers/net/ethernet/chelsio/Kconfig @@ -96,17 +96,6 @@ config CHELSIO_T4_DCB If unsure, say N. -config CHELSIO_T4_UWIRE - bool "Unified Wire Support for Chelsio T5 cards" - default n - depends on CHELSIO_T4 - ---help--- - Enable unified-wire offload features. - Say Y here if you want to enable unified-wire over Ethernet - in the driver. - - If unsure, say N. - config CHELSIO_T4_FCOE bool "Fibre Channel over Ethernet (FCoE) Support for Chelsio T5 cards" default n @@ -137,4 +126,9 @@ config CHELSIO_T4VF To compile this driver as a module choose M here; the module will be called cxgb4vf. +config CHELSIO_LIB + tristate + ---help--- + Common library for Chelsio drivers. + endif # NET_VENDOR_CHELSIO diff --git a/drivers/net/ethernet/chelsio/Makefile b/drivers/net/ethernet/chelsio/Makefile index 390510b5e..b6a5eec6e 100644 --- a/drivers/net/ethernet/chelsio/Makefile +++ b/drivers/net/ethernet/chelsio/Makefile @@ -6,3 +6,4 @@ obj-$(CONFIG_CHELSIO_T1) += cxgb/ obj-$(CONFIG_CHELSIO_T3) += cxgb3/ obj-$(CONFIG_CHELSIO_T4) += cxgb4/ obj-$(CONFIG_CHELSIO_T4VF) += cxgb4vf/ +obj-$(CONFIG_CHELSIO_LIB) += libcxgb/ diff --git a/drivers/net/ethernet/chelsio/cxgb4/Makefile b/drivers/net/ethernet/chelsio/cxgb4/Makefile index 85c92821b..ace0ab98d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/Makefile +++ b/drivers/net/ethernet/chelsio/cxgb4/Makefile @@ -7,5 +7,4 @@ obj-$(CONFIG_CHELSIO_T4) += cxgb4.o cxgb4-objs := cxgb4_main.o l2t.o t4_hw.o sge.o clip_tbl.o cxgb4_ethtool.o cxgb4-$(CONFIG_CHELSIO_T4_DCB) += cxgb4_dcb.o cxgb4-$(CONFIG_CHELSIO_T4_FCOE) += cxgb4_fcoe.o -cxgb4-$(CONFIG_CHELSIO_T4_UWIRE) += cxgb4_ppm.o cxgb4-$(CONFIG_DEBUG_FS) += cxgb4_debugfs.o diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index b4fceb924..edd23386b 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -418,8 +418,9 @@ struct trace_params { struct link_config { unsigned short supported; /* link capabilities */ unsigned short advertising; /* advertised capabilities */ - unsigned short requested_speed; /* speed user has requested */ - unsigned short speed; /* actual link speed */ + unsigned short lp_advertising; /* peer advertised capabilities */ + unsigned int requested_speed; /* speed user has requested */ + unsigned int speed; /* actual link speed */ unsigned char requested_fc; /* flow control user has requested */ unsigned char fc; /* actual link flow control */ unsigned char autoneg; /* autonegotiating? */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index 7a0b92b2f..02f80febe 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -480,178 +480,293 @@ static int identify_port(struct net_device *dev, return t4_identify_port(adap, adap->pf, netdev2pinfo(dev)->viid, val); } -static unsigned int from_fw_linkcaps(enum fw_port_type type, unsigned int caps) +/** + * from_fw_port_mod_type - translate Firmware Port/Module type to Ethtool + * @port_type: Firmware Port Type + * @mod_type: Firmware Module Type + * + * Translate Firmware Port/Module type to Ethtool Port Type. + */ +static int from_fw_port_mod_type(enum fw_port_type port_type, + enum fw_port_module_type mod_type) { - unsigned int v = 0; - - if (type == FW_PORT_TYPE_BT_SGMII || type == FW_PORT_TYPE_BT_XFI || - type == FW_PORT_TYPE_BT_XAUI) { - v |= SUPPORTED_TP; - if (caps & FW_PORT_CAP_SPEED_100M) - v |= SUPPORTED_100baseT_Full; - if (caps & FW_PORT_CAP_SPEED_1G) - v |= SUPPORTED_1000baseT_Full; - if (caps & FW_PORT_CAP_SPEED_10G) - v |= SUPPORTED_10000baseT_Full; - } else if (type == FW_PORT_TYPE_KX4 || type == FW_PORT_TYPE_KX) { - v |= SUPPORTED_Backplane; - if (caps & FW_PORT_CAP_SPEED_1G) - v |= SUPPORTED_1000baseKX_Full; - if (caps & FW_PORT_CAP_SPEED_10G) - v |= SUPPORTED_10000baseKX4_Full; - } else if (type == FW_PORT_TYPE_KR) { - v |= SUPPORTED_Backplane | SUPPORTED_10000baseKR_Full; - } else if (type == FW_PORT_TYPE_BP_AP) { - v |= SUPPORTED_Backplane | SUPPORTED_10000baseR_FEC | - SUPPORTED_10000baseKR_Full | SUPPORTED_1000baseKX_Full; - } else if (type == FW_PORT_TYPE_BP4_AP) { - v |= SUPPORTED_Backplane | SUPPORTED_10000baseR_FEC | - SUPPORTED_10000baseKR_Full | SUPPORTED_1000baseKX_Full | - SUPPORTED_10000baseKX4_Full; - } else if (type == FW_PORT_TYPE_FIBER_XFI || - type == FW_PORT_TYPE_FIBER_XAUI || - type == FW_PORT_TYPE_SFP || - type == FW_PORT_TYPE_QSFP_10G || - type == FW_PORT_TYPE_QSA) { - v |= SUPPORTED_FIBRE; - if (caps & FW_PORT_CAP_SPEED_1G) - v |= SUPPORTED_1000baseT_Full; - if (caps & FW_PORT_CAP_SPEED_10G) - v |= SUPPORTED_10000baseT_Full; - } else if (type == FW_PORT_TYPE_BP40_BA || - type == FW_PORT_TYPE_QSFP) { - v |= SUPPORTED_40000baseSR4_Full; - v |= SUPPORTED_FIBRE; + if (port_type == FW_PORT_TYPE_BT_SGMII || + port_type == FW_PORT_TYPE_BT_XFI || + port_type == FW_PORT_TYPE_BT_XAUI) { + return PORT_TP; + } else if (port_type == FW_PORT_TYPE_FIBER_XFI || + port_type == FW_PORT_TYPE_FIBER_XAUI) { + return PORT_FIBRE; + } else if (port_type == FW_PORT_TYPE_SFP || + port_type == FW_PORT_TYPE_QSFP_10G || + port_type == FW_PORT_TYPE_QSA || + port_type == FW_PORT_TYPE_QSFP) { + if (mod_type == FW_PORT_MOD_TYPE_LR || + mod_type == FW_PORT_MOD_TYPE_SR || + mod_type == FW_PORT_MOD_TYPE_ER || + mod_type == FW_PORT_MOD_TYPE_LRM) + return PORT_FIBRE; + else if (mod_type == FW_PORT_MOD_TYPE_TWINAX_PASSIVE || + mod_type == FW_PORT_MOD_TYPE_TWINAX_ACTIVE) + return PORT_DA; + else + return PORT_OTHER; } - if (caps & FW_PORT_CAP_ANEG) - v |= SUPPORTED_Autoneg; - return v; + return PORT_OTHER; } -static unsigned int to_fw_linkcaps(unsigned int caps) +/** + * speed_to_fw_caps - translate Port Speed to Firmware Port Capabilities + * @speed: speed in Kb/s + * + * Translates a specific Port Speed into a Firmware Port Capabilities + * value. + */ +static unsigned int speed_to_fw_caps(int speed) { - unsigned int v = 0; - - if (caps & ADVERTISED_100baseT_Full) - v |= FW_PORT_CAP_SPEED_100M; - if (caps & ADVERTISED_1000baseT_Full) - v |= FW_PORT_CAP_SPEED_1G; - if (caps & ADVERTISED_10000baseT_Full) - v |= FW_PORT_CAP_SPEED_10G; - if (caps & ADVERTISED_40000baseSR4_Full) - v |= FW_PORT_CAP_SPEED_40G; - return v; + if (speed == 100) + return FW_PORT_CAP_SPEED_100M; + if (speed == 1000) + return FW_PORT_CAP_SPEED_1G; + if (speed == 10000) + return FW_PORT_CAP_SPEED_10G; + if (speed == 25000) + return FW_PORT_CAP_SPEED_25G; + if (speed == 40000) + return FW_PORT_CAP_SPEED_40G; + if (speed == 100000) + return FW_PORT_CAP_SPEED_100G; + return 0; } -static int get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +/** + * fw_caps_to_lmm - translate Firmware to ethtool Link Mode Mask + * @port_type: Firmware Port Type + * @fw_caps: Firmware Port Capabilities + * @link_mode_mask: ethtool Link Mode Mask + * + * Translate a Firmware Port Capabilities specification to an ethtool + * Link Mode Mask. + */ +static void fw_caps_to_lmm(enum fw_port_type port_type, + unsigned int fw_caps, + unsigned long *link_mode_mask) { - const struct port_info *p = netdev_priv(dev); - - if (p->port_type == FW_PORT_TYPE_BT_SGMII || - p->port_type == FW_PORT_TYPE_BT_XFI || - p->port_type == FW_PORT_TYPE_BT_XAUI) { - cmd->port = PORT_TP; - } else if (p->port_type == FW_PORT_TYPE_FIBER_XFI || - p->port_type == FW_PORT_TYPE_FIBER_XAUI) { - cmd->port = PORT_FIBRE; - } else if (p->port_type == FW_PORT_TYPE_SFP || - p->port_type == FW_PORT_TYPE_QSFP_10G || - p->port_type == FW_PORT_TYPE_QSA || - p->port_type == FW_PORT_TYPE_QSFP) { - if (p->mod_type == FW_PORT_MOD_TYPE_LR || - p->mod_type == FW_PORT_MOD_TYPE_SR || - p->mod_type == FW_PORT_MOD_TYPE_ER || - p->mod_type == FW_PORT_MOD_TYPE_LRM) - cmd->port = PORT_FIBRE; - else if (p->mod_type == FW_PORT_MOD_TYPE_TWINAX_PASSIVE || - p->mod_type == FW_PORT_MOD_TYPE_TWINAX_ACTIVE) - cmd->port = PORT_DA; - else - cmd->port = PORT_OTHER; + #define SET_LMM(__lmm_name) __set_bit(ETHTOOL_LINK_MODE_ ## __lmm_name \ + ## _BIT, link_mode_mask) + + #define FW_CAPS_TO_LMM(__fw_name, __lmm_name) \ + do { \ + if (fw_caps & FW_PORT_CAP_ ## __fw_name) \ + SET_LMM(__lmm_name); \ + } while (0) + + switch (port_type) { + case FW_PORT_TYPE_BT_SGMII: + case FW_PORT_TYPE_BT_XFI: + case FW_PORT_TYPE_BT_XAUI: + SET_LMM(TP); + FW_CAPS_TO_LMM(SPEED_100M, 100baseT_Full); + FW_CAPS_TO_LMM(SPEED_1G, 1000baseT_Full); + FW_CAPS_TO_LMM(SPEED_10G, 10000baseT_Full); + break; + + case FW_PORT_TYPE_KX4: + case FW_PORT_TYPE_KX: + SET_LMM(Backplane); + FW_CAPS_TO_LMM(SPEED_1G, 1000baseKX_Full); + FW_CAPS_TO_LMM(SPEED_10G, 10000baseKX4_Full); + break; + + case FW_PORT_TYPE_KR: + SET_LMM(Backplane); + SET_LMM(10000baseKR_Full); + break; + + case FW_PORT_TYPE_BP_AP: + SET_LMM(Backplane); + SET_LMM(10000baseR_FEC); + SET_LMM(10000baseKR_Full); + SET_LMM(1000baseKX_Full); + break; + + case FW_PORT_TYPE_BP4_AP: + SET_LMM(Backplane); + SET_LMM(10000baseR_FEC); + SET_LMM(10000baseKR_Full); + SET_LMM(1000baseKX_Full); + SET_LMM(10000baseKX4_Full); + break; + + case FW_PORT_TYPE_FIBER_XFI: + case FW_PORT_TYPE_FIBER_XAUI: + case FW_PORT_TYPE_SFP: + case FW_PORT_TYPE_QSFP_10G: + case FW_PORT_TYPE_QSA: + SET_LMM(FIBRE); + FW_CAPS_TO_LMM(SPEED_1G, 1000baseT_Full); + FW_CAPS_TO_LMM(SPEED_10G, 10000baseT_Full); + break; + + case FW_PORT_TYPE_BP40_BA: + case FW_PORT_TYPE_QSFP: + SET_LMM(FIBRE); + SET_LMM(40000baseSR4_Full); + break; + + case FW_PORT_TYPE_CR_QSFP: + case FW_PORT_TYPE_SFP28: + SET_LMM(FIBRE); + SET_LMM(25000baseCR_Full); + break; + + case FW_PORT_TYPE_KR4_100G: + case FW_PORT_TYPE_CR4_QSFP: + SET_LMM(FIBRE); + SET_LMM(100000baseCR4_Full); + break; + + default: + break; + } + + FW_CAPS_TO_LMM(ANEG, Autoneg); + FW_CAPS_TO_LMM(802_3_PAUSE, Pause); + FW_CAPS_TO_LMM(802_3_ASM_DIR, Asym_Pause); + + #undef FW_CAPS_TO_LMM + #undef SET_LMM +} + +/** + * lmm_to_fw_caps - translate ethtool Link Mode Mask to Firmware + * capabilities + * + * @link_mode_mask: ethtool Link Mode Mask + * + * Translate ethtool Link Mode Mask into a Firmware Port capabilities + * value. + */ +static unsigned int lmm_to_fw_caps(const unsigned long *link_mode_mask) +{ + unsigned int fw_caps = 0; + + #define LMM_TO_FW_CAPS(__lmm_name, __fw_name) \ + do { \ + if (test_bit(ETHTOOL_LINK_MODE_ ## __lmm_name ## _BIT, \ + link_mode_mask)) \ + fw_caps |= FW_PORT_CAP_ ## __fw_name; \ + } while (0) + + LMM_TO_FW_CAPS(100baseT_Full, SPEED_100M); + LMM_TO_FW_CAPS(1000baseT_Full, SPEED_1G); + LMM_TO_FW_CAPS(10000baseT_Full, SPEED_10G); + LMM_TO_FW_CAPS(40000baseSR4_Full, SPEED_40G); + LMM_TO_FW_CAPS(25000baseCR_Full, SPEED_25G); + LMM_TO_FW_CAPS(100000baseCR4_Full, SPEED_100G); + + #undef LMM_TO_FW_CAPS + + return fw_caps; +} + +static int get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *link_ksettings) +{ + const struct port_info *pi = netdev_priv(dev); + struct ethtool_link_settings *base = &link_ksettings->base; + + ethtool_link_ksettings_zero_link_mode(link_ksettings, supported); + ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising); + ethtool_link_ksettings_zero_link_mode(link_ksettings, lp_advertising); + + base->port = from_fw_port_mod_type(pi->port_type, pi->mod_type); + + if (pi->mdio_addr >= 0) { + base->phy_address = pi->mdio_addr; + base->mdio_support = (pi->port_type == FW_PORT_TYPE_BT_SGMII + ? ETH_MDIO_SUPPORTS_C22 + : ETH_MDIO_SUPPORTS_C45); } else { - cmd->port = PORT_OTHER; + base->phy_address = 255; + base->mdio_support = 0; } - if (p->mdio_addr >= 0) { - cmd->phy_address = p->mdio_addr; - cmd->transceiver = XCVR_EXTERNAL; - cmd->mdio_support = p->port_type == FW_PORT_TYPE_BT_SGMII ? - MDIO_SUPPORTS_C22 : MDIO_SUPPORTS_C45; + fw_caps_to_lmm(pi->port_type, pi->link_cfg.supported, + link_ksettings->link_modes.supported); + fw_caps_to_lmm(pi->port_type, pi->link_cfg.advertising, + link_ksettings->link_modes.advertising); + fw_caps_to_lmm(pi->port_type, pi->link_cfg.lp_advertising, + link_ksettings->link_modes.lp_advertising); + + if (netif_carrier_ok(dev)) { + base->speed = pi->link_cfg.speed; + base->duplex = DUPLEX_FULL; } else { - cmd->phy_address = 0; /* not really, but no better option */ - cmd->transceiver = XCVR_INTERNAL; - cmd->mdio_support = 0; + base->speed = SPEED_UNKNOWN; + base->duplex = DUPLEX_UNKNOWN; } - cmd->supported = from_fw_linkcaps(p->port_type, p->link_cfg.supported); - cmd->advertising = from_fw_linkcaps(p->port_type, - p->link_cfg.advertising); - ethtool_cmd_speed_set(cmd, - netif_carrier_ok(dev) ? p->link_cfg.speed : 0); - cmd->duplex = DUPLEX_FULL; - cmd->autoneg = p->link_cfg.autoneg; - cmd->maxtxpkt = 0; - cmd->maxrxpkt = 0; - return 0; -} + base->autoneg = pi->link_cfg.autoneg; + if (pi->link_cfg.supported & FW_PORT_CAP_ANEG) + ethtool_link_ksettings_add_link_mode(link_ksettings, + supported, Autoneg); + if (pi->link_cfg.autoneg) + ethtool_link_ksettings_add_link_mode(link_ksettings, + advertising, Autoneg); -static unsigned int speed_to_caps(int speed) -{ - if (speed == 100) - return FW_PORT_CAP_SPEED_100M; - if (speed == 1000) - return FW_PORT_CAP_SPEED_1G; - if (speed == 10000) - return FW_PORT_CAP_SPEED_10G; - if (speed == 40000) - return FW_PORT_CAP_SPEED_40G; return 0; } -static int set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings + *link_ksettings) { - unsigned int cap; - struct port_info *p = netdev_priv(dev); - struct link_config *lc = &p->link_cfg; - u32 speed = ethtool_cmd_speed(cmd); + struct port_info *pi = netdev_priv(dev); + struct link_config *lc = &pi->link_cfg; + const struct ethtool_link_settings *base = &link_ksettings->base; struct link_config old_lc; - int ret; + unsigned int fw_caps; + int ret = 0; - if (cmd->duplex != DUPLEX_FULL) /* only full-duplex supported */ + /* only full-duplex supported */ + if (base->duplex != DUPLEX_FULL) return -EINVAL; if (!(lc->supported & FW_PORT_CAP_ANEG)) { /* PHY offers a single speed. See if that's what's * being requested. */ - if (cmd->autoneg == AUTONEG_DISABLE && - (lc->supported & speed_to_caps(speed))) + if (base->autoneg == AUTONEG_DISABLE && + (lc->supported & speed_to_fw_caps(base->speed))) return 0; return -EINVAL; } old_lc = *lc; - if (cmd->autoneg == AUTONEG_DISABLE) { - cap = speed_to_caps(speed); + if (base->autoneg == AUTONEG_DISABLE) { + fw_caps = speed_to_fw_caps(base->speed); - if (!(lc->supported & cap)) + if (!(lc->supported & fw_caps)) return -EINVAL; - lc->requested_speed = cap; + lc->requested_speed = fw_caps; lc->advertising = 0; } else { - cap = to_fw_linkcaps(cmd->advertising); - if (!(lc->supported & cap)) + fw_caps = + lmm_to_fw_caps(link_ksettings->link_modes.advertising); + + if (!(lc->supported & fw_caps)) return -EINVAL; lc->requested_speed = 0; - lc->advertising = cap | FW_PORT_CAP_ANEG; + lc->advertising = fw_caps | FW_PORT_CAP_ANEG; } - lc->autoneg = cmd->autoneg; + lc->autoneg = base->autoneg; /* If the firmware rejects the Link Configuration request, back out * the changes and report the error. */ - ret = t4_link_l1cfg(p->adapter, p->adapter->mbox, p->tx_chan, lc); + ret = t4_link_l1cfg(pi->adapter, pi->adapter->mbox, pi->tx_chan, lc); if (ret) *lc = old_lc; @@ -1093,8 +1208,8 @@ static int get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, } static const struct ethtool_ops cxgb_ethtool_ops = { - .get_settings = get_settings, - .set_settings = set_settings, + .get_link_ksettings = get_link_ksettings, + .set_link_ksettings = set_link_ksettings, .get_drvinfo = get_drvinfo, .get_msglevel = get_msglevel, .set_msglevel = set_msglevel, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 6eea06a31..6694233e2 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -64,6 +64,7 @@ #include <net/bonding.h> #include <net/addrconf.h> #include <asm/uaccess.h> +#include <linux/crash_dump.h> #include "cxgb4.h" #include "t4_regs.h" @@ -204,7 +205,7 @@ static int rx_dma_offset = 2; static unsigned int num_vf[NUM_OF_PF_WITH_SRIOV]; module_param_array(num_vf, uint, NULL, 0644); -MODULE_PARM_DESC(num_vf, "number of VFs for each of PFs 0-3"); +MODULE_PARM_DESC(num_vf, "number of VFs for each of PFs 0-3, deprecated parameter - please use the pci sysfs interface."); #endif /* TX Queue select used to determine what algorithm to use for selecting TX @@ -458,11 +459,8 @@ static int set_rxmode(struct net_device *dev, int mtu, bool sleep_ok) struct port_info *pi = netdev_priv(dev); struct adapter *adapter = pi->adapter; - if (!(dev->flags & IFF_PROMISC)) { - __dev_uc_sync(dev, cxgb4_mac_sync, cxgb4_mac_unsync); - if (!(dev->flags & IFF_ALLMULTI)) - __dev_mc_sync(dev, cxgb4_mac_sync, cxgb4_mac_unsync); - } + __dev_uc_sync(dev, cxgb4_mac_sync, cxgb4_mac_unsync); + __dev_mc_sync(dev, cxgb4_mac_sync, cxgb4_mac_unsync); return t4_set_rxmode(adapter, adapter->mbox, pi->viid, mtu, (dev->flags & IFF_PROMISC) ? 1 : 0, @@ -3733,7 +3731,8 @@ static int adap_init0(struct adapter *adap) return ret; /* Contact FW, advertising Master capability */ - ret = t4_fw_hello(adap, adap->mbox, adap->mbox, MASTER_MAY, &state); + ret = t4_fw_hello(adap, adap->mbox, adap->mbox, + is_kdump_kernel() ? MASTER_MUST : MASTER_MAY, &state); if (ret < 0) { dev_err(adap->pdev_dev, "could not connect to FW, error %d\n", ret); @@ -4304,10 +4303,17 @@ static const struct pci_error_handlers cxgb4_eeh = { .resume = eeh_resume, }; +/* Return true if the Link Configuration supports "High Speeds" (those greater + * than 1Gb/s). + */ static inline bool is_x_10g_port(const struct link_config *lc) { - return (lc->supported & FW_PORT_CAP_SPEED_10G) != 0 || - (lc->supported & FW_PORT_CAP_SPEED_40G) != 0; + unsigned int speeds, high_speeds; + + speeds = FW_PORT_CAP_SPEED_V(FW_PORT_CAP_SPEED_G(lc->supported)); + high_speeds = speeds & ~(FW_PORT_CAP_SPEED_100M | FW_PORT_CAP_SPEED_1G); + + return high_speeds != 0; } static inline void init_rspq(struct adapter *adap, struct sge_rspq *q, @@ -4334,6 +4340,11 @@ static void cfg_queues(struct adapter *adap) #endif int ciq_size; + /* Reduce memory usage in kdump environment, disable all offload. + */ + if (is_kdump_kernel()) + adap->params.offload = 0; + for_each_port(adap, i) n10g += is_x_10g_port(&adap2pinfo(adap, i)->link_cfg); #ifdef CONFIG_CHELSIO_T4_DCB @@ -4750,8 +4761,12 @@ static void print_port_info(const struct net_device *dev) bufp += sprintf(bufp, "1000/"); if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_10G) bufp += sprintf(bufp, "10G/"); + if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_25G) + bufp += sprintf(bufp, "25G/"); if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_40G) bufp += sprintf(bufp, "40G/"); + if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_100G) + bufp += sprintf(bufp, "100G/"); if (bufp != buf) --bufp; sprintf(bufp, "BASE-%s", t4_get_port_type_description(pi->port_type)); @@ -4827,6 +4842,60 @@ static int get_chip_type(struct pci_dev *pdev, u32 pl_rev) return -EINVAL; } +#ifdef CONFIG_PCI_IOV +static int cxgb4_iov_configure(struct pci_dev *pdev, int num_vfs) +{ + int err = 0; + int current_vfs = pci_num_vf(pdev); + u32 pcie_fw; + void __iomem *regs; + + regs = pci_ioremap_bar(pdev, 0); + if (!regs) { + dev_err(&pdev->dev, "cannot map device registers\n"); + return -ENOMEM; + } + + pcie_fw = readl(regs + PCIE_FW_A); + iounmap(regs); + /* Check if cxgb4 is the MASTER and fw is initialized */ + if (!(pcie_fw & PCIE_FW_INIT_F) || + !(pcie_fw & PCIE_FW_MASTER_VLD_F) || + PCIE_FW_MASTER_G(pcie_fw) != 4) { + dev_warn(&pdev->dev, + "cxgb4 driver needs to be MASTER to support SRIOV\n"); + return -EOPNOTSUPP; + } + + /* If any of the VF's is already assigned to Guest OS, then + * SRIOV for the same cannot be modified + */ + if (current_vfs && pci_vfs_assigned(pdev)) { + dev_err(&pdev->dev, + "Cannot modify SR-IOV while VFs are assigned\n"); + num_vfs = current_vfs; + return num_vfs; + } + + /* Disable SRIOV when zero is passed. + * One needs to disable SRIOV before modifying it, else + * stack throws the below warning: + * " 'n' VFs already enabled. Disable before enabling 'm' VFs." + */ + if (!num_vfs) { + pci_disable_sriov(pdev); + return num_vfs; + } + + if (num_vfs != current_vfs) { + err = pci_enable_sriov(pdev, num_vfs); + if (err) + return err; + } + return num_vfs; +} +#endif + static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) { int func, i, err, s_qpp, qpp, num_seg; @@ -5160,11 +5229,16 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) sriov: #ifdef CONFIG_PCI_IOV - if (func < ARRAY_SIZE(num_vf) && num_vf[func] > 0) + if (func < ARRAY_SIZE(num_vf) && num_vf[func] > 0) { + dev_warn(&pdev->dev, + "Enabling SR-IOV VFs using the num_vf module " + "parameter is deprecated - please use the pci sysfs " + "interface instead.\n"); if (pci_enable_sriov(pdev, num_vf[func]) == 0) dev_info(&pdev->dev, "instantiated %u virtual functions\n", num_vf[func]); + } #endif return 0; @@ -5257,6 +5331,9 @@ static struct pci_driver cxgb4_driver = { .probe = init_one, .remove = remove_one, .shutdown = remove_one, +#ifdef CONFIG_PCI_IOV + .sriov_configure = cxgb4_iov_configure, +#endif .err_handler = &cxgb4_eeh, }; diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index bad253beb..ad3552df0 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -1192,7 +1192,7 @@ out_free: dev_kfree_skb_any(skb); /* Discard the packet if the length is greater than mtu */ max_pkt_len = ETH_HLEN + dev->mtu; - if (skb_vlan_tag_present(skb)) + if (skb_vlan_tagged(skb)) max_pkt_len += VLAN_HLEN; if (!skb_shinfo(skb)->gso_size && (unlikely(skb->len > max_pkt_len))) goto out_free; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index a63addb4e..660204bff 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -3627,7 +3627,8 @@ void t4_ulprx_read_la(struct adapter *adap, u32 *la_buf) } #define ADVERT_MASK (FW_PORT_CAP_SPEED_100M | FW_PORT_CAP_SPEED_1G |\ - FW_PORT_CAP_SPEED_10G | FW_PORT_CAP_SPEED_40G | \ + FW_PORT_CAP_SPEED_10G | FW_PORT_CAP_SPEED_25G | \ + FW_PORT_CAP_SPEED_40G | FW_PORT_CAP_SPEED_100G | \ FW_PORT_CAP_ANEG) /** @@ -7196,8 +7197,12 @@ void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl) speed = 1000; else if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_10G)) speed = 10000; + else if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_25G)) + speed = 25000; else if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_40G)) speed = 40000; + else if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_100G)) + speed = 100000; lc = &pi->link_cfg; @@ -7219,6 +7224,7 @@ void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl) lc->speed = speed; lc->fc = fc; lc->supported = be16_to_cpu(p->u.info.pcap); + lc->lp_advertising = be16_to_cpu(p->u.info.lpacap); t4_os_link_changed(adap, pi->port_id, link_ok); } } @@ -7284,6 +7290,7 @@ static void get_pci_mode(struct adapter *adapter, struct pci_params *p) static void init_link_config(struct link_config *lc, unsigned int caps) { lc->supported = caps; + lc->lp_advertising = 0; lc->requested_speed = 0; lc->speed = 0; lc->requested_fc = lc->fc = PAUSE_RX | PAUSE_TX; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h index 4705e2dea..e0ebe1378 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h @@ -104,6 +104,8 @@ enum { enum CPL_error { CPL_ERR_NONE = 0, + CPL_ERR_TCAM_PARITY = 1, + CPL_ERR_TCAM_MISS = 2, CPL_ERR_TCAM_FULL = 3, CPL_ERR_BAD_LENGTH = 15, CPL_ERR_BAD_ROUTE = 18, diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h index 392d6644f..30507d444 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h @@ -2249,22 +2249,28 @@ struct fw_acl_vlan_cmd { enum fw_port_cap { FW_PORT_CAP_SPEED_100M = 0x0001, FW_PORT_CAP_SPEED_1G = 0x0002, - FW_PORT_CAP_SPEED_2_5G = 0x0004, + FW_PORT_CAP_SPEED_25G = 0x0004, FW_PORT_CAP_SPEED_10G = 0x0008, FW_PORT_CAP_SPEED_40G = 0x0010, FW_PORT_CAP_SPEED_100G = 0x0020, FW_PORT_CAP_FC_RX = 0x0040, FW_PORT_CAP_FC_TX = 0x0080, FW_PORT_CAP_ANEG = 0x0100, - FW_PORT_CAP_MDI_0 = 0x0200, - FW_PORT_CAP_MDI_1 = 0x0400, - FW_PORT_CAP_BEAN = 0x0800, - FW_PORT_CAP_PMA_LPBK = 0x1000, - FW_PORT_CAP_PCS_LPBK = 0x2000, - FW_PORT_CAP_PHYXS_LPBK = 0x4000, - FW_PORT_CAP_FAR_END_LPBK = 0x8000, + FW_PORT_CAP_MDIX = 0x0200, + FW_PORT_CAP_MDIAUTO = 0x0400, + FW_PORT_CAP_FEC = 0x0800, + FW_PORT_CAP_TECHKR = 0x1000, + FW_PORT_CAP_TECHKX4 = 0x2000, + FW_PORT_CAP_802_3_PAUSE = 0x4000, + FW_PORT_CAP_802_3_ASM_DIR = 0x8000, }; +#define FW_PORT_CAP_SPEED_S 0 +#define FW_PORT_CAP_SPEED_M 0x3f +#define FW_PORT_CAP_SPEED_V(x) ((x) << FW_PORT_CAP_SPEED_S) +#define FW_PORT_CAP_SPEED_G(x) \ + (((x) >> FW_PORT_CAP_SPEED_S) & FW_PORT_CAP_SPEED_M) + enum fw_port_mdi { FW_PORT_CAP_MDI_UNCHANGED, FW_PORT_CAP_MDI_AUTO, @@ -2376,7 +2382,8 @@ struct fw_port_cmd { __u8 cbllen; __u8 auxlinfo; __u8 dcbxdis_pkd; - __u8 r8_lo[3]; + __u8 r8_lo; + __be16 lpacap; __be64 r9; } info; struct fw_port_diags { @@ -2555,6 +2562,11 @@ enum fw_port_type { FW_PORT_TYPE_QSA, FW_PORT_TYPE_QSFP, FW_PORT_TYPE_BP40_BA, + FW_PORT_TYPE_KR4_100G, + FW_PORT_TYPE_CR4_QSFP, + FW_PORT_TYPE_CR_QSFP, + FW_PORT_TYPE_CR2_QSFP, + FW_PORT_TYPE_SFP28, FW_PORT_TYPE_NONE = FW_PORT_CMD_PTYPE_M }; diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h b/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h index 734dd776c..109bc6304 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h +++ b/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h @@ -353,6 +353,10 @@ struct hash_mac_addr { u8 addr[ETH_ALEN]; }; +struct mbox_list { + struct list_head list; +}; + /* * Per-"adapter" (Virtual Function) information. */ @@ -387,6 +391,10 @@ struct adapter { /* various locks */ spinlock_t stats_lock; + /* lock for mailbox cmd list */ + spinlock_t mbox_lock; + struct mbox_list mlist; + /* support for mailbox command/reply logging */ #define T4VF_OS_LOG_MBOX_CMDS 256 struct mbox_cmd_log *mbox_log; diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index 04fc6f6d1..e116bb8d1 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -937,12 +937,8 @@ static int set_rxmode(struct net_device *dev, int mtu, bool sleep_ok) { struct port_info *pi = netdev_priv(dev); - if (!(dev->flags & IFF_PROMISC)) { - __dev_uc_sync(dev, cxgb4vf_mac_sync, cxgb4vf_mac_unsync); - if (!(dev->flags & IFF_ALLMULTI)) - __dev_mc_sync(dev, cxgb4vf_mac_sync, - cxgb4vf_mac_unsync); - } + __dev_uc_sync(dev, cxgb4vf_mac_sync, cxgb4vf_mac_unsync); + __dev_mc_sync(dev, cxgb4vf_mac_sync, cxgb4vf_mac_unsync); return t4vf_set_rxmode(pi->adapter, pi->viid, -1, (dev->flags & IFF_PROMISC) != 0, (dev->flags & IFF_ALLMULTI) != 0, @@ -1205,105 +1201,187 @@ static void cxgb4vf_poll_controller(struct net_device *dev) * state of the port to which we're linked. */ -static unsigned int t4vf_from_fw_linkcaps(enum fw_port_type type, - unsigned int caps) -{ - unsigned int v = 0; - - if (type == FW_PORT_TYPE_BT_SGMII || type == FW_PORT_TYPE_BT_XFI || - type == FW_PORT_TYPE_BT_XAUI) { - v |= SUPPORTED_TP; - if (caps & FW_PORT_CAP_SPEED_100M) - v |= SUPPORTED_100baseT_Full; - if (caps & FW_PORT_CAP_SPEED_1G) - v |= SUPPORTED_1000baseT_Full; - if (caps & FW_PORT_CAP_SPEED_10G) - v |= SUPPORTED_10000baseT_Full; - } else if (type == FW_PORT_TYPE_KX4 || type == FW_PORT_TYPE_KX) { - v |= SUPPORTED_Backplane; - if (caps & FW_PORT_CAP_SPEED_1G) - v |= SUPPORTED_1000baseKX_Full; - if (caps & FW_PORT_CAP_SPEED_10G) - v |= SUPPORTED_10000baseKX4_Full; - } else if (type == FW_PORT_TYPE_KR) - v |= SUPPORTED_Backplane | SUPPORTED_10000baseKR_Full; - else if (type == FW_PORT_TYPE_BP_AP) - v |= SUPPORTED_Backplane | SUPPORTED_10000baseR_FEC | - SUPPORTED_10000baseKR_Full | SUPPORTED_1000baseKX_Full; - else if (type == FW_PORT_TYPE_BP4_AP) - v |= SUPPORTED_Backplane | SUPPORTED_10000baseR_FEC | - SUPPORTED_10000baseKR_Full | SUPPORTED_1000baseKX_Full | - SUPPORTED_10000baseKX4_Full; - else if (type == FW_PORT_TYPE_FIBER_XFI || - type == FW_PORT_TYPE_FIBER_XAUI || - type == FW_PORT_TYPE_SFP || - type == FW_PORT_TYPE_QSFP_10G || - type == FW_PORT_TYPE_QSA) { - v |= SUPPORTED_FIBRE; - if (caps & FW_PORT_CAP_SPEED_1G) - v |= SUPPORTED_1000baseT_Full; - if (caps & FW_PORT_CAP_SPEED_10G) - v |= SUPPORTED_10000baseT_Full; - } else if (type == FW_PORT_TYPE_BP40_BA || - type == FW_PORT_TYPE_QSFP) { - v |= SUPPORTED_40000baseSR4_Full; - v |= SUPPORTED_FIBRE; - } - - if (caps & FW_PORT_CAP_ANEG) - v |= SUPPORTED_Autoneg; - return v; -} - -static int cxgb4vf_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) -{ - const struct port_info *p = netdev_priv(dev); - - if (p->port_type == FW_PORT_TYPE_BT_SGMII || - p->port_type == FW_PORT_TYPE_BT_XFI || - p->port_type == FW_PORT_TYPE_BT_XAUI) - cmd->port = PORT_TP; - else if (p->port_type == FW_PORT_TYPE_FIBER_XFI || - p->port_type == FW_PORT_TYPE_FIBER_XAUI) - cmd->port = PORT_FIBRE; - else if (p->port_type == FW_PORT_TYPE_SFP || - p->port_type == FW_PORT_TYPE_QSFP_10G || - p->port_type == FW_PORT_TYPE_QSA || - p->port_type == FW_PORT_TYPE_QSFP) { - if (p->mod_type == FW_PORT_MOD_TYPE_LR || - p->mod_type == FW_PORT_MOD_TYPE_SR || - p->mod_type == FW_PORT_MOD_TYPE_ER || - p->mod_type == FW_PORT_MOD_TYPE_LRM) - cmd->port = PORT_FIBRE; - else if (p->mod_type == FW_PORT_MOD_TYPE_TWINAX_PASSIVE || - p->mod_type == FW_PORT_MOD_TYPE_TWINAX_ACTIVE) - cmd->port = PORT_DA; +/** + * from_fw_port_mod_type - translate Firmware Port/Module type to Ethtool + * @port_type: Firmware Port Type + * @mod_type: Firmware Module Type + * + * Translate Firmware Port/Module type to Ethtool Port Type. + */ +static int from_fw_port_mod_type(enum fw_port_type port_type, + enum fw_port_module_type mod_type) +{ + if (port_type == FW_PORT_TYPE_BT_SGMII || + port_type == FW_PORT_TYPE_BT_XFI || + port_type == FW_PORT_TYPE_BT_XAUI) { + return PORT_TP; + } else if (port_type == FW_PORT_TYPE_FIBER_XFI || + port_type == FW_PORT_TYPE_FIBER_XAUI) { + return PORT_FIBRE; + } else if (port_type == FW_PORT_TYPE_SFP || + port_type == FW_PORT_TYPE_QSFP_10G || + port_type == FW_PORT_TYPE_QSA || + port_type == FW_PORT_TYPE_QSFP) { + if (mod_type == FW_PORT_MOD_TYPE_LR || + mod_type == FW_PORT_MOD_TYPE_SR || + mod_type == FW_PORT_MOD_TYPE_ER || + mod_type == FW_PORT_MOD_TYPE_LRM) + return PORT_FIBRE; + else if (mod_type == FW_PORT_MOD_TYPE_TWINAX_PASSIVE || + mod_type == FW_PORT_MOD_TYPE_TWINAX_ACTIVE) + return PORT_DA; else - cmd->port = PORT_OTHER; - } else - cmd->port = PORT_OTHER; + return PORT_OTHER; + } + + return PORT_OTHER; +} + +/** + * fw_caps_to_lmm - translate Firmware to ethtool Link Mode Mask + * @port_type: Firmware Port Type + * @fw_caps: Firmware Port Capabilities + * @link_mode_mask: ethtool Link Mode Mask + * + * Translate a Firmware Port Capabilities specification to an ethtool + * Link Mode Mask. + */ +static void fw_caps_to_lmm(enum fw_port_type port_type, + unsigned int fw_caps, + unsigned long *link_mode_mask) +{ + #define SET_LMM(__lmm_name) __set_bit(ETHTOOL_LINK_MODE_ ## __lmm_name\ + ## _BIT, link_mode_mask) + + #define FW_CAPS_TO_LMM(__fw_name, __lmm_name) \ + do { \ + if (fw_caps & FW_PORT_CAP_ ## __fw_name) \ + SET_LMM(__lmm_name); \ + } while (0) + + switch (port_type) { + case FW_PORT_TYPE_BT_SGMII: + case FW_PORT_TYPE_BT_XFI: + case FW_PORT_TYPE_BT_XAUI: + SET_LMM(TP); + FW_CAPS_TO_LMM(SPEED_100M, 100baseT_Full); + FW_CAPS_TO_LMM(SPEED_1G, 1000baseT_Full); + FW_CAPS_TO_LMM(SPEED_10G, 10000baseT_Full); + break; + + case FW_PORT_TYPE_KX4: + case FW_PORT_TYPE_KX: + SET_LMM(Backplane); + FW_CAPS_TO_LMM(SPEED_1G, 1000baseKX_Full); + FW_CAPS_TO_LMM(SPEED_10G, 10000baseKX4_Full); + break; + + case FW_PORT_TYPE_KR: + SET_LMM(Backplane); + SET_LMM(10000baseKR_Full); + break; + + case FW_PORT_TYPE_BP_AP: + SET_LMM(Backplane); + SET_LMM(10000baseR_FEC); + SET_LMM(10000baseKR_Full); + SET_LMM(1000baseKX_Full); + break; + + case FW_PORT_TYPE_BP4_AP: + SET_LMM(Backplane); + SET_LMM(10000baseR_FEC); + SET_LMM(10000baseKR_Full); + SET_LMM(1000baseKX_Full); + SET_LMM(10000baseKX4_Full); + break; + + case FW_PORT_TYPE_FIBER_XFI: + case FW_PORT_TYPE_FIBER_XAUI: + case FW_PORT_TYPE_SFP: + case FW_PORT_TYPE_QSFP_10G: + case FW_PORT_TYPE_QSA: + SET_LMM(FIBRE); + FW_CAPS_TO_LMM(SPEED_1G, 1000baseT_Full); + FW_CAPS_TO_LMM(SPEED_10G, 10000baseT_Full); + break; + + case FW_PORT_TYPE_BP40_BA: + case FW_PORT_TYPE_QSFP: + SET_LMM(FIBRE); + SET_LMM(40000baseSR4_Full); + break; + + case FW_PORT_TYPE_CR_QSFP: + case FW_PORT_TYPE_SFP28: + SET_LMM(FIBRE); + SET_LMM(25000baseCR_Full); + break; + + case FW_PORT_TYPE_KR4_100G: + case FW_PORT_TYPE_CR4_QSFP: + SET_LMM(FIBRE); + SET_LMM(100000baseCR4_Full); + break; + + default: + break; + } + + FW_CAPS_TO_LMM(ANEG, Autoneg); + FW_CAPS_TO_LMM(802_3_PAUSE, Pause); + FW_CAPS_TO_LMM(802_3_ASM_DIR, Asym_Pause); + + #undef FW_CAPS_TO_LMM + #undef SET_LMM +} + +static int cxgb4vf_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings + *link_ksettings) +{ + const struct port_info *pi = netdev_priv(dev); + struct ethtool_link_settings *base = &link_ksettings->base; - if (p->mdio_addr >= 0) { - cmd->phy_address = p->mdio_addr; - cmd->transceiver = XCVR_EXTERNAL; - cmd->mdio_support = p->port_type == FW_PORT_TYPE_BT_SGMII ? - MDIO_SUPPORTS_C22 : MDIO_SUPPORTS_C45; + ethtool_link_ksettings_zero_link_mode(link_ksettings, supported); + ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising); + ethtool_link_ksettings_zero_link_mode(link_ksettings, lp_advertising); + + base->port = from_fw_port_mod_type(pi->port_type, pi->mod_type); + + if (pi->mdio_addr >= 0) { + base->phy_address = pi->mdio_addr; + base->mdio_support = (pi->port_type == FW_PORT_TYPE_BT_SGMII + ? ETH_MDIO_SUPPORTS_C22 + : ETH_MDIO_SUPPORTS_C45); } else { - cmd->phy_address = 0; /* not really, but no better option */ - cmd->transceiver = XCVR_INTERNAL; - cmd->mdio_support = 0; - } - - cmd->supported = t4vf_from_fw_linkcaps(p->port_type, - p->link_cfg.supported); - cmd->advertising = t4vf_from_fw_linkcaps(p->port_type, - p->link_cfg.advertising); - ethtool_cmd_speed_set(cmd, - netif_carrier_ok(dev) ? p->link_cfg.speed : 0); - cmd->duplex = DUPLEX_FULL; - cmd->autoneg = p->link_cfg.autoneg; - cmd->maxtxpkt = 0; - cmd->maxrxpkt = 0; + base->phy_address = 255; + base->mdio_support = 0; + } + + fw_caps_to_lmm(pi->port_type, pi->link_cfg.supported, + link_ksettings->link_modes.supported); + fw_caps_to_lmm(pi->port_type, pi->link_cfg.advertising, + link_ksettings->link_modes.advertising); + fw_caps_to_lmm(pi->port_type, pi->link_cfg.lp_advertising, + link_ksettings->link_modes.lp_advertising); + + if (netif_carrier_ok(dev)) { + base->speed = pi->link_cfg.speed; + base->duplex = DUPLEX_FULL; + } else { + base->speed = SPEED_UNKNOWN; + base->duplex = DUPLEX_UNKNOWN; + } + + base->autoneg = pi->link_cfg.autoneg; + if (pi->link_cfg.supported & FW_PORT_CAP_ANEG) + ethtool_link_ksettings_add_link_mode(link_ksettings, + supported, Autoneg); + if (pi->link_cfg.autoneg) + ethtool_link_ksettings_add_link_mode(link_ksettings, + advertising, Autoneg); + return 0; } @@ -1679,7 +1757,7 @@ static void cxgb4vf_get_wol(struct net_device *dev, #define TSO_FLAGS (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_TSO_ECN) static const struct ethtool_ops cxgb4vf_ethtool_ops = { - .get_settings = cxgb4vf_get_settings, + .get_link_ksettings = cxgb4vf_get_link_ksettings, .get_drvinfo = cxgb4vf_get_drvinfo, .get_msglevel = cxgb4vf_get_msglevel, .set_msglevel = cxgb4vf_set_msglevel, @@ -2778,6 +2856,8 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev, * Initialize SMP data synchronization resources. */ spin_lock_init(&adapter->stats_lock); + spin_lock_init(&adapter->mbox_lock); + INIT_LIST_HEAD(&adapter->mlist.list); /* * Map our I/O registers in BAR0. diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c index 1bb57d3fb..c8fd4f8fe 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c @@ -1188,7 +1188,7 @@ int t4vf_eth_xmit(struct sk_buff *skb, struct net_device *dev) /* Discard the packet if the length is greater than mtu */ max_pkt_len = ETH_HLEN + dev->mtu; - if (skb_vlan_tag_present(skb)) + if (skb_vlan_tagged(skb)) max_pkt_len += VLAN_HLEN; if (!skb_shinfo(skb)->gso_size && (unlikely(skb->len > max_pkt_len))) goto out_free; diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h index 438374a05..17a2bbcf9 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h +++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h @@ -107,8 +107,9 @@ struct t4vf_port_stats { struct link_config { unsigned int supported; /* link capabilities */ unsigned int advertising; /* advertised capabilities */ - unsigned short requested_speed; /* speed user has requested */ - unsigned short speed; /* actual link speed */ + unsigned short lp_advertising; /* peer advertised capabilities */ + unsigned int requested_speed; /* speed user has requested */ + unsigned int speed; /* actual link speed */ unsigned char requested_fc; /* flow control user has requested */ unsigned char fc; /* actual link flow control */ unsigned char autoneg; /* autonegotiating? */ @@ -270,10 +271,17 @@ static inline bool is_10g_port(const struct link_config *lc) return (lc->supported & FW_PORT_CAP_SPEED_10G) != 0; } +/* Return true if the Link Configuration supports "High Speeds" (those greater + * than 1Gb/s). + */ static inline bool is_x_10g_port(const struct link_config *lc) { - return (lc->supported & FW_PORT_CAP_SPEED_10G) != 0 || - (lc->supported & FW_PORT_CAP_SPEED_40G) != 0; + unsigned int speeds, high_speeds; + + speeds = FW_PORT_CAP_SPEED_V(FW_PORT_CAP_SPEED_G(lc->supported)); + high_speeds = speeds & ~(FW_PORT_CAP_SPEED_100M | FW_PORT_CAP_SPEED_1G); + + return high_speeds != 0; } static inline unsigned int core_ticks_per_usec(const struct adapter *adapter) diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c index 955ff7c61..b5622b168 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c @@ -139,6 +139,7 @@ int t4vf_wr_mbox_core(struct adapter *adapter, const void *cmd, int size, u32 mbox_ctl = T4VF_CIM_BASE_ADDR + CIM_VF_EXT_MAILBOX_CTRL; u32 cmd_op = FW_CMD_OP_G(be32_to_cpu(((struct fw_cmd_hdr *)cmd)->hi)); __be64 cmd_rpl[MBOX_LEN / 8]; + struct mbox_list entry; /* In T6, mailbox size is changed to 128 bytes to avoid * invalidating the entire prefetch buffer. @@ -156,6 +157,51 @@ int t4vf_wr_mbox_core(struct adapter *adapter, const void *cmd, int size, size > NUM_CIM_VF_MAILBOX_DATA_INSTANCES * 4) return -EINVAL; + /* Queue ourselves onto the mailbox access list. When our entry is at + * the front of the list, we have rights to access the mailbox. So we + * wait [for a while] till we're at the front [or bail out with an + * EBUSY] ... + */ + spin_lock(&adapter->mbox_lock); + list_add_tail(&entry.list, &adapter->mlist.list); + spin_unlock(&adapter->mbox_lock); + + delay_idx = 0; + ms = delay[0]; + + for (i = 0; ; i += ms) { + /* If we've waited too long, return a busy indication. This + * really ought to be based on our initial position in the + * mailbox access list but this is a start. We very rearely + * contend on access to the mailbox ... + */ + if (i > FW_CMD_MAX_TIMEOUT) { + spin_lock(&adapter->mbox_lock); + list_del(&entry.list); + spin_unlock(&adapter->mbox_lock); + ret = -EBUSY; + t4vf_record_mbox(adapter, cmd, size, access, ret); + return ret; + } + + /* If we're at the head, break out and start the mailbox + * protocol. + */ + if (list_first_entry(&adapter->mlist.list, struct mbox_list, + list) == &entry) + break; + + /* Delay for a bit before checking again ... */ + if (sleep_ok) { + ms = delay[delay_idx]; /* last element may repeat */ + if (delay_idx < ARRAY_SIZE(delay) - 1) + delay_idx++; + msleep(ms); + } else { + mdelay(ms); + } + } + /* * Loop trying to get ownership of the mailbox. Return an error * if we can't gain ownership. @@ -164,6 +210,9 @@ int t4vf_wr_mbox_core(struct adapter *adapter, const void *cmd, int size, for (i = 0; v == MBOX_OWNER_NONE && i < 3; i++) v = MBOWNER_G(t4_read_reg(adapter, mbox_ctl)); if (v != MBOX_OWNER_DRV) { + spin_lock(&adapter->mbox_lock); + list_del(&entry.list); + spin_unlock(&adapter->mbox_lock); ret = (v == MBOX_OWNER_FW) ? -EBUSY : -ETIMEDOUT; t4vf_record_mbox(adapter, cmd, size, access, ret); return ret; @@ -248,6 +297,9 @@ int t4vf_wr_mbox_core(struct adapter *adapter, const void *cmd, int size, if (cmd_op != FW_VI_STATS_CMD) t4vf_record_mbox(adapter, cmd_rpl, size, access, execute); + spin_lock(&adapter->mbox_lock); + list_del(&entry.list); + spin_unlock(&adapter->mbox_lock); return -FW_CMD_RETVAL_G(v); } } @@ -255,12 +307,16 @@ int t4vf_wr_mbox_core(struct adapter *adapter, const void *cmd, int size, /* We timed out. Return the error ... */ ret = -ETIMEDOUT; t4vf_record_mbox(adapter, cmd, size, access, ret); + spin_lock(&adapter->mbox_lock); + list_del(&entry.list); + spin_unlock(&adapter->mbox_lock); return ret; } #define ADVERT_MASK (FW_PORT_CAP_SPEED_100M | FW_PORT_CAP_SPEED_1G |\ - FW_PORT_CAP_SPEED_10G | FW_PORT_CAP_SPEED_40G | \ - FW_PORT_CAP_SPEED_100G | FW_PORT_CAP_ANEG) + FW_PORT_CAP_SPEED_10G | FW_PORT_CAP_SPEED_25G | \ + FW_PORT_CAP_SPEED_40G | FW_PORT_CAP_SPEED_100G | \ + FW_PORT_CAP_ANEG) /** * init_link_config - initialize a link's SW state @@ -273,6 +329,7 @@ int t4vf_wr_mbox_core(struct adapter *adapter, const void *cmd, int size, static void init_link_config(struct link_config *lc, unsigned int caps) { lc->supported = caps; + lc->lp_advertising = 0; lc->requested_speed = 0; lc->speed = 0; lc->requested_fc = lc->fc = PAUSE_RX | PAUSE_TX; @@ -1656,8 +1713,12 @@ int t4vf_handle_fw_rpl(struct adapter *adapter, const __be64 *rpl) speed = 1000; else if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_10G)) speed = 10000; + else if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_25G)) + speed = 25000; else if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_40G)) speed = 40000; + else if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_100G)) + speed = 100000; /* * Scan all of our "ports" (Virtual Interfaces) looking for @@ -1688,6 +1749,8 @@ int t4vf_handle_fw_rpl(struct adapter *adapter, const __be64 *rpl) lc->fc = fc; lc->supported = be16_to_cpu(port_cmd->u.info.pcap); + lc->lp_advertising = + be16_to_cpu(port_cmd->u.info.lpacap); t4vf_os_link_changed(adapter, pidx, link_ok); } } diff --git a/drivers/net/ethernet/chelsio/libcxgb/Makefile b/drivers/net/ethernet/chelsio/libcxgb/Makefile new file mode 100644 index 000000000..2362230ef --- /dev/null +++ b/drivers/net/ethernet/chelsio/libcxgb/Makefile @@ -0,0 +1,3 @@ +obj-$(CONFIG_CHELSIO_LIB) += libcxgb.o + +libcxgb-y := libcxgb_ppm.o diff --git a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c new file mode 100644 index 000000000..0ed161642 --- /dev/null +++ b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c @@ -0,0 +1,498 @@ +/* + * libcxgb_ppm.c: Chelsio common library for T3/T4/T5 iSCSI PagePod Manager + * + * Copyright (c) 2016 Chelsio Communications, Inc. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + * Written by: Karen Xie (kxie@chelsio.com) + */ + +#define DRV_NAME "libcxgb" +#define DRV_VERSION "1.0.0-ko" +#define pr_fmt(fmt) DRV_NAME ": " fmt + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/errno.h> +#include <linux/types.h> +#include <linux/debugfs.h> +#include <linux/export.h> +#include <linux/list.h> +#include <linux/skbuff.h> +#include <linux/pci.h> +#include <linux/scatterlist.h> + +#include "libcxgb_ppm.h" + +/* Direct Data Placement - + * Directly place the iSCSI Data-In or Data-Out PDU's payload into + * pre-posted final destination host-memory buffers based on the + * Initiator Task Tag (ITT) in Data-In or Target Task Tag (TTT) + * in Data-Out PDUs. The host memory address is programmed into + * h/w in the format of pagepod entries. The location of the + * pagepod entry is encoded into ddp tag which is used as the base + * for ITT/TTT. + */ + +/* Direct-Data Placement page size adjustment + */ +int cxgbi_ppm_find_page_index(struct cxgbi_ppm *ppm, unsigned long pgsz) +{ + struct cxgbi_tag_format *tformat = &ppm->tformat; + int i; + + for (i = 0; i < DDP_PGIDX_MAX; i++) { + if (pgsz == 1UL << (DDP_PGSZ_BASE_SHIFT + + tformat->pgsz_order[i])) { + pr_debug("%s: %s ppm, pgsz %lu -> idx %d.\n", + __func__, ppm->ndev->name, pgsz, i); + return i; + } + } + pr_info("ippm: ddp page size %lu not supported.\n", pgsz); + return DDP_PGIDX_MAX; +} + +/* DDP setup & teardown + */ +static int ppm_find_unused_entries(unsigned long *bmap, + unsigned int max_ppods, + unsigned int start, + unsigned int nr, + unsigned int align_mask) +{ + unsigned long i; + + i = bitmap_find_next_zero_area(bmap, max_ppods, start, nr, align_mask); + + if (unlikely(i >= max_ppods) && (start > nr)) + i = bitmap_find_next_zero_area(bmap, max_ppods, 0, start - 1, + align_mask); + if (unlikely(i >= max_ppods)) + return -ENOSPC; + + bitmap_set(bmap, i, nr); + return (int)i; +} + +static void ppm_mark_entries(struct cxgbi_ppm *ppm, int i, int count, + unsigned long caller_data) +{ + struct cxgbi_ppod_data *pdata = ppm->ppod_data + i; + + pdata->caller_data = caller_data; + pdata->npods = count; + + if (pdata->color == ((1 << PPOD_IDX_SHIFT) - 1)) + pdata->color = 0; + else + pdata->color++; +} + +static int ppm_get_cpu_entries(struct cxgbi_ppm *ppm, unsigned int count, + unsigned long caller_data) +{ + struct cxgbi_ppm_pool *pool; + unsigned int cpu; + int i; + + cpu = get_cpu(); + pool = per_cpu_ptr(ppm->pool, cpu); + spin_lock_bh(&pool->lock); + put_cpu(); + + i = ppm_find_unused_entries(pool->bmap, ppm->pool_index_max, + pool->next, count, 0); + if (i < 0) { + pool->next = 0; + spin_unlock_bh(&pool->lock); + return -ENOSPC; + } + + pool->next = i + count; + if (pool->next >= ppm->pool_index_max) + pool->next = 0; + + spin_unlock_bh(&pool->lock); + + pr_debug("%s: cpu %u, idx %d + %d (%d), next %u.\n", + __func__, cpu, i, count, i + cpu * ppm->pool_index_max, + pool->next); + + i += cpu * ppm->pool_index_max; + ppm_mark_entries(ppm, i, count, caller_data); + + return i; +} + +static int ppm_get_entries(struct cxgbi_ppm *ppm, unsigned int count, + unsigned long caller_data) +{ + int i; + + spin_lock_bh(&ppm->map_lock); + i = ppm_find_unused_entries(ppm->ppod_bmap, ppm->bmap_index_max, + ppm->next, count, 0); + if (i < 0) { + ppm->next = 0; + spin_unlock_bh(&ppm->map_lock); + pr_debug("ippm: NO suitable entries %u available.\n", + count); + return -ENOSPC; + } + + ppm->next = i + count; + if (ppm->next >= ppm->bmap_index_max) + ppm->next = 0; + + spin_unlock_bh(&ppm->map_lock); + + pr_debug("%s: idx %d + %d (%d), next %u, caller_data 0x%lx.\n", + __func__, i, count, i + ppm->pool_rsvd, ppm->next, + caller_data); + + i += ppm->pool_rsvd; + ppm_mark_entries(ppm, i, count, caller_data); + + return i; +} + +static void ppm_unmark_entries(struct cxgbi_ppm *ppm, int i, int count) +{ + pr_debug("%s: idx %d + %d.\n", __func__, i, count); + + if (i < ppm->pool_rsvd) { + unsigned int cpu; + struct cxgbi_ppm_pool *pool; + + cpu = i / ppm->pool_index_max; + i %= ppm->pool_index_max; + + pool = per_cpu_ptr(ppm->pool, cpu); + spin_lock_bh(&pool->lock); + bitmap_clear(pool->bmap, i, count); + + if (i < pool->next) + pool->next = i; + spin_unlock_bh(&pool->lock); + + pr_debug("%s: cpu %u, idx %d, next %u.\n", + __func__, cpu, i, pool->next); + } else { + spin_lock_bh(&ppm->map_lock); + + i -= ppm->pool_rsvd; + bitmap_clear(ppm->ppod_bmap, i, count); + + if (i < ppm->next) + ppm->next = i; + spin_unlock_bh(&ppm->map_lock); + + pr_debug("%s: idx %d, next %u.\n", __func__, i, ppm->next); + } +} + +void cxgbi_ppm_ppod_release(struct cxgbi_ppm *ppm, u32 idx) +{ + struct cxgbi_ppod_data *pdata; + + if (idx >= ppm->ppmax) { + pr_warn("ippm: idx too big %u > %u.\n", idx, ppm->ppmax); + return; + } + + pdata = ppm->ppod_data + idx; + if (!pdata->npods) { + pr_warn("ippm: idx %u, npods 0.\n", idx); + return; + } + + pr_debug("release idx %u, npods %u.\n", idx, pdata->npods); + ppm_unmark_entries(ppm, idx, pdata->npods); +} +EXPORT_SYMBOL(cxgbi_ppm_ppod_release); + +int cxgbi_ppm_ppods_reserve(struct cxgbi_ppm *ppm, unsigned short nr_pages, + u32 per_tag_pg_idx, u32 *ppod_idx, + u32 *ddp_tag, unsigned long caller_data) +{ + struct cxgbi_ppod_data *pdata; + unsigned int npods; + int idx = -1; + unsigned int hwidx; + u32 tag; + + npods = (nr_pages + PPOD_PAGES_MAX - 1) >> PPOD_PAGES_SHIFT; + if (!npods) { + pr_warn("%s: pages %u -> npods %u, full.\n", + __func__, nr_pages, npods); + return -EINVAL; + } + + /* grab from cpu pool first */ + idx = ppm_get_cpu_entries(ppm, npods, caller_data); + /* try the general pool */ + if (idx < 0) + idx = ppm_get_entries(ppm, npods, caller_data); + if (idx < 0) { + pr_debug("ippm: pages %u, nospc %u, nxt %u, 0x%lx.\n", + nr_pages, npods, ppm->next, caller_data); + return idx; + } + + pdata = ppm->ppod_data + idx; + hwidx = ppm->base_idx + idx; + + tag = cxgbi_ppm_make_ddp_tag(hwidx, pdata->color); + + if (per_tag_pg_idx) + tag |= (per_tag_pg_idx << 30) & 0xC0000000; + + *ppod_idx = idx; + *ddp_tag = tag; + + pr_debug("ippm: sg %u, tag 0x%x(%u,%u), data 0x%lx.\n", + nr_pages, tag, idx, npods, caller_data); + + return npods; +} +EXPORT_SYMBOL(cxgbi_ppm_ppods_reserve); + +void cxgbi_ppm_make_ppod_hdr(struct cxgbi_ppm *ppm, u32 tag, + unsigned int tid, unsigned int offset, + unsigned int length, + struct cxgbi_pagepod_hdr *hdr) +{ + /* The ddp tag in pagepod should be with bit 31:30 set to 0. + * The ddp Tag on the wire should be with non-zero 31:30 to the peer + */ + tag &= 0x3FFFFFFF; + + hdr->vld_tid = htonl(PPOD_VALID_FLAG | PPOD_TID(tid)); + + hdr->rsvd = 0; + hdr->pgsz_tag_clr = htonl(tag & ppm->tformat.idx_clr_mask); + hdr->max_offset = htonl(length); + hdr->page_offset = htonl(offset); + + pr_debug("ippm: tag 0x%x, tid 0x%x, xfer %u, off %u.\n", + tag, tid, length, offset); +} +EXPORT_SYMBOL(cxgbi_ppm_make_ppod_hdr); + +static void ppm_free(struct cxgbi_ppm *ppm) +{ + vfree(ppm); +} + +static void ppm_destroy(struct kref *kref) +{ + struct cxgbi_ppm *ppm = container_of(kref, + struct cxgbi_ppm, + refcnt); + pr_info("ippm: kref 0, destroy %s ppm 0x%p.\n", + ppm->ndev->name, ppm); + + *ppm->ppm_pp = NULL; + + free_percpu(ppm->pool); + ppm_free(ppm); +} + +int cxgbi_ppm_release(struct cxgbi_ppm *ppm) +{ + if (ppm) { + int rv; + + rv = kref_put(&ppm->refcnt, ppm_destroy); + return rv; + } + return 1; +} +EXPORT_SYMBOL(cxgbi_ppm_release); + +static struct cxgbi_ppm_pool *ppm_alloc_cpu_pool(unsigned int *total, + unsigned int *pcpu_ppmax) +{ + struct cxgbi_ppm_pool *pools; + unsigned int ppmax = (*total) / num_possible_cpus(); + unsigned int max = (PCPU_MIN_UNIT_SIZE - sizeof(*pools)) << 3; + unsigned int bmap; + unsigned int alloc_sz; + unsigned int count = 0; + unsigned int cpu; + + /* make sure per cpu pool fits into PCPU_MIN_UNIT_SIZE */ + if (ppmax > max) + ppmax = max; + + /* pool size must be multiple of unsigned long */ + bmap = BITS_TO_LONGS(ppmax); + ppmax = (bmap * sizeof(unsigned long)) << 3; + + alloc_sz = sizeof(*pools) + sizeof(unsigned long) * bmap; + pools = __alloc_percpu(alloc_sz, __alignof__(struct cxgbi_ppm_pool)); + + if (!pools) + return NULL; + + for_each_possible_cpu(cpu) { + struct cxgbi_ppm_pool *ppool = per_cpu_ptr(pools, cpu); + + memset(ppool, 0, alloc_sz); + spin_lock_init(&ppool->lock); + count += ppmax; + } + + *total = count; + *pcpu_ppmax = ppmax; + + return pools; +} + +int cxgbi_ppm_init(void **ppm_pp, struct net_device *ndev, + struct pci_dev *pdev, void *lldev, + struct cxgbi_tag_format *tformat, + unsigned int ppmax, + unsigned int llimit, + unsigned int start, + unsigned int reserve_factor) +{ + struct cxgbi_ppm *ppm = (struct cxgbi_ppm *)(*ppm_pp); + struct cxgbi_ppm_pool *pool = NULL; + unsigned int ppmax_pool = 0; + unsigned int pool_index_max = 0; + unsigned int alloc_sz; + unsigned int ppod_bmap_size; + + if (ppm) { + pr_info("ippm: %s, ppm 0x%p,0x%p already initialized, %u/%u.\n", + ndev->name, ppm_pp, ppm, ppm->ppmax, ppmax); + kref_get(&ppm->refcnt); + return 1; + } + + if (reserve_factor) { + ppmax_pool = ppmax / reserve_factor; + pool = ppm_alloc_cpu_pool(&ppmax_pool, &pool_index_max); + + pr_debug("%s: ppmax %u, cpu total %u, per cpu %u.\n", + ndev->name, ppmax, ppmax_pool, pool_index_max); + } + + ppod_bmap_size = BITS_TO_LONGS(ppmax - ppmax_pool); + alloc_sz = sizeof(struct cxgbi_ppm) + + ppmax * (sizeof(struct cxgbi_ppod_data)) + + ppod_bmap_size * sizeof(unsigned long); + + ppm = vmalloc(alloc_sz); + if (!ppm) + goto release_ppm_pool; + + memset(ppm, 0, alloc_sz); + + ppm->ppod_bmap = (unsigned long *)(&ppm->ppod_data[ppmax]); + + if ((ppod_bmap_size >> 3) > (ppmax - ppmax_pool)) { + unsigned int start = ppmax - ppmax_pool; + unsigned int end = ppod_bmap_size >> 3; + + bitmap_set(ppm->ppod_bmap, ppmax, end - start); + pr_info("%s: %u - %u < %u * 8, mask extra bits %u, %u.\n", + __func__, ppmax, ppmax_pool, ppod_bmap_size, start, + end); + } + + spin_lock_init(&ppm->map_lock); + kref_init(&ppm->refcnt); + + memcpy(&ppm->tformat, tformat, sizeof(struct cxgbi_tag_format)); + + ppm->ppm_pp = ppm_pp; + ppm->ndev = ndev; + ppm->pdev = pdev; + ppm->lldev = lldev; + ppm->ppmax = ppmax; + ppm->next = 0; + ppm->llimit = llimit; + ppm->base_idx = start > llimit ? + (start - llimit + 1) >> PPOD_SIZE_SHIFT : 0; + ppm->bmap_index_max = ppmax - ppmax_pool; + + ppm->pool = pool; + ppm->pool_rsvd = ppmax_pool; + ppm->pool_index_max = pool_index_max; + + /* check one more time */ + if (*ppm_pp) { + ppm_free(ppm); + ppm = (struct cxgbi_ppm *)(*ppm_pp); + + pr_info("ippm: %s, ppm 0x%p,0x%p already initialized, %u/%u.\n", + ndev->name, ppm_pp, *ppm_pp, ppm->ppmax, ppmax); + + kref_get(&ppm->refcnt); + return 1; + } + *ppm_pp = ppm; + + ppm->tformat.pgsz_idx_dflt = cxgbi_ppm_find_page_index(ppm, PAGE_SIZE); + + pr_info("ippm %s: ppm 0x%p, 0x%p, base %u/%u, pg %lu,%u, rsvd %u,%u.\n", + ndev->name, ppm_pp, ppm, ppm->base_idx, ppm->ppmax, PAGE_SIZE, + ppm->tformat.pgsz_idx_dflt, ppm->pool_rsvd, + ppm->pool_index_max); + + return 0; + +release_ppm_pool: + free_percpu(pool); + return -ENOMEM; +} +EXPORT_SYMBOL(cxgbi_ppm_init); + +unsigned int cxgbi_tagmask_set(unsigned int ppmax) +{ + unsigned int bits = fls(ppmax); + + if (bits > PPOD_IDX_MAX_SIZE) + bits = PPOD_IDX_MAX_SIZE; + + pr_info("ippm: ppmax %u/0x%x -> bits %u, tagmask 0x%x.\n", + ppmax, ppmax, bits, 1 << (bits + PPOD_IDX_SHIFT)); + + return 1 << (bits + PPOD_IDX_SHIFT); +} +EXPORT_SYMBOL(cxgbi_tagmask_set); + +MODULE_AUTHOR("Chelsio Communications"); +MODULE_DESCRIPTION("Chelsio common library"); +MODULE_VERSION(DRV_VERSION); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.h b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.h new file mode 100644 index 000000000..e995a1a38 --- /dev/null +++ b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.h @@ -0,0 +1,334 @@ +/* + * libcxgb_ppm.h: Chelsio common library for T3/T4/T5 iSCSI ddp operation + * + * Copyright (c) 2016 Chelsio Communications, Inc. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + * Written by: Karen Xie (kxie@chelsio.com) + */ + +#ifndef __LIBCXGB_PPM_H__ +#define __LIBCXGB_PPM_H__ + +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/types.h> +#include <linux/debugfs.h> +#include <linux/list.h> +#include <linux/netdevice.h> +#include <linux/scatterlist.h> +#include <linux/skbuff.h> +#include <linux/vmalloc.h> +#include <linux/bitmap.h> + +struct cxgbi_pagepod_hdr { + u32 vld_tid; + u32 pgsz_tag_clr; + u32 max_offset; + u32 page_offset; + u64 rsvd; +}; + +#define PPOD_PAGES_MAX 4 +struct cxgbi_pagepod { + struct cxgbi_pagepod_hdr hdr; + u64 addr[PPOD_PAGES_MAX + 1]; +}; + +/* ddp tag format + * for a 32-bit tag: + * bit # + * 31 ..... ..... 0 + * X Y...Y Z...Z, where + * ^ ^^^^^ ^^^^ + * | | |____ when ddp bit = 0: color bits + * | | + * | |____ when ddp bit = 0: idx into the ddp memory region + * | + * |____ ddp bit: 0 - ddp tag, 1 - non-ddp tag + * + * [page selector:2] [sw/free bits] [0] [idx] [color:6] + */ + +#define DDP_PGIDX_MAX 4 +#define DDP_PGSZ_BASE_SHIFT 12 /* base page 4K */ + +struct cxgbi_task_tag_info { + unsigned char flags; +#define CXGBI_PPOD_INFO_FLAG_VALID 0x1 +#define CXGBI_PPOD_INFO_FLAG_MAPPED 0x2 + unsigned char cid; + unsigned short pg_shift; + unsigned int npods; + unsigned int idx; + unsigned int tag; + struct cxgbi_pagepod_hdr hdr; + int nents; + int nr_pages; + struct scatterlist *sgl; +}; + +struct cxgbi_tag_format { + unsigned char pgsz_order[DDP_PGIDX_MAX]; + unsigned char pgsz_idx_dflt; + unsigned char free_bits:4; + unsigned char color_bits:4; + unsigned char idx_bits; + unsigned char rsvd_bits; + unsigned int no_ddp_mask; + unsigned int idx_mask; + unsigned int color_mask; + unsigned int idx_clr_mask; + unsigned int rsvd_mask; +}; + +struct cxgbi_ppod_data { + unsigned char pg_idx:2; + unsigned char color:6; + unsigned char chan_id; + unsigned short npods; + unsigned long caller_data; +}; + +/* per cpu ppm pool */ +struct cxgbi_ppm_pool { + unsigned int base; /* base index */ + unsigned int next; /* next possible free index */ + spinlock_t lock; /* ppm pool lock */ + unsigned long bmap[0]; +} ____cacheline_aligned_in_smp; + +struct cxgbi_ppm { + struct kref refcnt; + struct net_device *ndev; /* net_device, 1st port */ + struct pci_dev *pdev; + void *lldev; + void **ppm_pp; + struct cxgbi_tag_format tformat; + unsigned int ppmax; + unsigned int llimit; + unsigned int base_idx; + + unsigned int pool_rsvd; + unsigned int pool_index_max; + struct cxgbi_ppm_pool __percpu *pool; + /* map lock */ + spinlock_t map_lock; /* ppm map lock */ + unsigned int bmap_index_max; + unsigned int next; + unsigned long *ppod_bmap; + struct cxgbi_ppod_data ppod_data[0]; +}; + +#define DDP_THRESHOLD 512 + +#define PPOD_PAGES_SHIFT 2 /* 4 pages per pod */ + +#define IPPOD_SIZE sizeof(struct cxgbi_pagepod) /* 64 */ +#define PPOD_SIZE_SHIFT 6 + +/* page pods are allocated in groups of this size (must be power of 2) */ +#define PPOD_CLUSTER_SIZE 16U + +#define ULPMEM_DSGL_MAX_NPPODS 16 /* 1024/PPOD_SIZE */ +#define ULPMEM_IDATA_MAX_NPPODS 3 /* (PPOD_SIZE * 3 + ulptx hdr) < 256B */ +#define PCIE_MEMWIN_MAX_NPPODS 16 /* 1024/PPOD_SIZE */ + +#define PPOD_COLOR_SHIFT 0 +#define PPOD_COLOR(x) ((x) << PPOD_COLOR_SHIFT) + +#define PPOD_IDX_SHIFT 6 +#define PPOD_IDX_MAX_SIZE 24 + +#define PPOD_TID_SHIFT 0 +#define PPOD_TID(x) ((x) << PPOD_TID_SHIFT) + +#define PPOD_TAG_SHIFT 6 +#define PPOD_TAG(x) ((x) << PPOD_TAG_SHIFT) + +#define PPOD_VALID_SHIFT 24 +#define PPOD_VALID(x) ((x) << PPOD_VALID_SHIFT) +#define PPOD_VALID_FLAG PPOD_VALID(1U) + +#define PPOD_PI_EXTRACT_CTL_SHIFT 31 +#define PPOD_PI_EXTRACT_CTL(x) ((x) << PPOD_PI_EXTRACT_CTL_SHIFT) +#define PPOD_PI_EXTRACT_CTL_FLAG V_PPOD_PI_EXTRACT_CTL(1U) + +#define PPOD_PI_TYPE_SHIFT 29 +#define PPOD_PI_TYPE_MASK 0x3 +#define PPOD_PI_TYPE(x) ((x) << PPOD_PI_TYPE_SHIFT) + +#define PPOD_PI_CHECK_CTL_SHIFT 27 +#define PPOD_PI_CHECK_CTL_MASK 0x3 +#define PPOD_PI_CHECK_CTL(x) ((x) << PPOD_PI_CHECK_CTL_SHIFT) + +#define PPOD_PI_REPORT_CTL_SHIFT 25 +#define PPOD_PI_REPORT_CTL_MASK 0x3 +#define PPOD_PI_REPORT_CTL(x) ((x) << PPOD_PI_REPORT_CTL_SHIFT) + +static inline int cxgbi_ppm_is_ddp_tag(struct cxgbi_ppm *ppm, u32 tag) +{ + return !(tag & ppm->tformat.no_ddp_mask); +} + +static inline int cxgbi_ppm_sw_tag_is_usable(struct cxgbi_ppm *ppm, + u32 tag) +{ + /* the sw tag must be using <= 31 bits */ + return !(tag & 0x80000000U); +} + +static inline int cxgbi_ppm_make_non_ddp_tag(struct cxgbi_ppm *ppm, + u32 sw_tag, + u32 *final_tag) +{ + struct cxgbi_tag_format *tformat = &ppm->tformat; + + if (!cxgbi_ppm_sw_tag_is_usable(ppm, sw_tag)) { + pr_info("sw_tag 0x%x NOT usable.\n", sw_tag); + return -EINVAL; + } + + if (!sw_tag) { + *final_tag = tformat->no_ddp_mask; + } else { + unsigned int shift = tformat->idx_bits + tformat->color_bits; + u32 lower = sw_tag & tformat->idx_clr_mask; + u32 upper = (sw_tag >> shift) << (shift + 1); + + *final_tag = upper | tformat->no_ddp_mask | lower; + } + return 0; +} + +static inline u32 cxgbi_ppm_decode_non_ddp_tag(struct cxgbi_ppm *ppm, + u32 tag) +{ + struct cxgbi_tag_format *tformat = &ppm->tformat; + unsigned int shift = tformat->idx_bits + tformat->color_bits; + u32 lower = tag & tformat->idx_clr_mask; + u32 upper = (tag >> tformat->rsvd_bits) << shift; + + return upper | lower; +} + +static inline u32 cxgbi_ppm_ddp_tag_get_idx(struct cxgbi_ppm *ppm, + u32 ddp_tag) +{ + u32 hw_idx = (ddp_tag >> PPOD_IDX_SHIFT) & + ppm->tformat.idx_mask; + + return hw_idx - ppm->base_idx; +} + +static inline u32 cxgbi_ppm_make_ddp_tag(unsigned int hw_idx, + unsigned char color) +{ + return (hw_idx << PPOD_IDX_SHIFT) | ((u32)color); +} + +static inline unsigned long +cxgbi_ppm_get_tag_caller_data(struct cxgbi_ppm *ppm, + u32 ddp_tag) +{ + u32 idx = cxgbi_ppm_ddp_tag_get_idx(ppm, ddp_tag); + + return ppm->ppod_data[idx].caller_data; +} + +/* sw bits are the free bits */ +static inline int cxgbi_ppm_ddp_tag_update_sw_bits(struct cxgbi_ppm *ppm, + u32 val, u32 orig_tag, + u32 *final_tag) +{ + struct cxgbi_tag_format *tformat = &ppm->tformat; + u32 v = val >> tformat->free_bits; + + if (v) { + pr_info("sw_bits 0x%x too large, avail bits %u.\n", + val, tformat->free_bits); + return -EINVAL; + } + if (!cxgbi_ppm_is_ddp_tag(ppm, orig_tag)) + return -EINVAL; + + *final_tag = (val << tformat->rsvd_bits) | + (orig_tag & ppm->tformat.rsvd_mask); + return 0; +} + +static inline void cxgbi_ppm_ppod_clear(struct cxgbi_pagepod *ppod) +{ + ppod->hdr.vld_tid = 0U; +} + +static inline void cxgbi_tagmask_check(unsigned int tagmask, + struct cxgbi_tag_format *tformat) +{ + unsigned int bits = fls(tagmask); + + /* reserve top most 2 bits for page selector */ + tformat->free_bits = 32 - 2 - bits; + tformat->rsvd_bits = bits; + tformat->color_bits = PPOD_IDX_SHIFT; + tformat->idx_bits = bits - 1 - PPOD_IDX_SHIFT; + tformat->no_ddp_mask = 1 << (bits - 1); + tformat->idx_mask = (1 << tformat->idx_bits) - 1; + tformat->color_mask = (1 << PPOD_IDX_SHIFT) - 1; + tformat->idx_clr_mask = (1 << (bits - 1)) - 1; + tformat->rsvd_mask = (1 << bits) - 1; + + pr_info("ippm: tagmask 0x%x, rsvd %u=%u+%u+1, mask 0x%x,0x%x, " + "pg %u,%u,%u,%u.\n", + tagmask, tformat->rsvd_bits, tformat->idx_bits, + tformat->color_bits, tformat->no_ddp_mask, tformat->rsvd_mask, + tformat->pgsz_order[0], tformat->pgsz_order[1], + tformat->pgsz_order[2], tformat->pgsz_order[3]); +} + +int cxgbi_ppm_find_page_index(struct cxgbi_ppm *ppm, unsigned long pgsz); +void cxgbi_ppm_make_ppod_hdr(struct cxgbi_ppm *ppm, u32 tag, + unsigned int tid, unsigned int offset, + unsigned int length, + struct cxgbi_pagepod_hdr *hdr); +void cxgbi_ppm_ppod_release(struct cxgbi_ppm *, u32 idx); +int cxgbi_ppm_ppods_reserve(struct cxgbi_ppm *, unsigned short nr_pages, + u32 per_tag_pg_idx, u32 *ppod_idx, u32 *ddp_tag, + unsigned long caller_data); +int cxgbi_ppm_init(void **ppm_pp, struct net_device *, struct pci_dev *, + void *lldev, struct cxgbi_tag_format *, + unsigned int ppmax, unsigned int llimit, + unsigned int start, + unsigned int reserve_factor); +int cxgbi_ppm_release(struct cxgbi_ppm *ppm); +void cxgbi_tagmask_check(unsigned int tagmask, struct cxgbi_tag_format *); +unsigned int cxgbi_tagmask_set(unsigned int ppmax); + +#endif /*__LIBCXGB_PPM_H__*/ |