diff options
Diffstat (limited to 'drivers/net')
289 files changed, 8014 insertions, 3098 deletions
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index edb1c023a753..6210757772ed 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -145,13 +145,16 @@ config MACVTAP To compile this driver as a module, choose M here: the module will be called macvtap. +config IPVLAN_L3S + depends on NETFILTER + depends on IPVLAN + def_bool y + select NET_L3_MASTER_DEV config IPVLAN tristate "IP-VLAN support" depends on INET depends on IPV6 || !IPV6 - depends on NETFILTER - select NET_L3_MASTER_DEV ---help--- This allows one to create virtual devices off of a main interface and packets will be delivered based on the dest L3 (IPv6/IPv4 addr) @@ -197,9 +200,9 @@ config VXLAN config GENEVE tristate "Generic Network Virtualization Encapsulation" - depends on INET && NET_UDP_TUNNEL + depends on INET depends on IPV6 || !IPV6 - select NET_IP_TUNNEL + select NET_UDP_TUNNEL select GRO_CELLS ---help--- This allows one to create geneve virtual interfaces that provide diff --git a/drivers/net/appletalk/cops.c b/drivers/net/appletalk/cops.c index f90bb723985f..b3c63d2f16aa 100644 --- a/drivers/net/appletalk/cops.c +++ b/drivers/net/appletalk/cops.c @@ -301,7 +301,7 @@ static int __init cops_probe1(struct net_device *dev, int ioaddr) dev->irq = cops_irq(ioaddr, board); if (dev->irq) break; - /* No IRQ found on this port, fallthrough */ + /* fall through - Once no IRQ found on this port. */ case 1: retval = -EINVAL; goto err_out; diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 4d5d01cb8141..da1fc17295d9 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -1375,6 +1375,7 @@ static int bond_option_slaves_set(struct bonding *bond, sscanf(newval->string, "%16s", command); /* IFNAMSIZ*/ ifname = command + 1; if ((strlen(command) <= 1) || + (command[0] != '+' && command[0] != '-') || !dev_valid_name(ifname)) goto err_no_cmd; @@ -1398,6 +1399,7 @@ static int bond_option_slaves_set(struct bonding *bond, break; default: + /* should not run here. */ goto err_no_cmd; } diff --git a/drivers/net/caif/caif_spi.c b/drivers/net/caif/caif_spi.c index d28a1398c091..7608bc3e00df 100644 --- a/drivers/net/caif/caif_spi.c +++ b/drivers/net/caif/caif_spi.c @@ -73,35 +73,37 @@ MODULE_PARM_DESC(spi_down_tail_align, "SPI downlink tail alignment."); #define LOW_WATER_MARK 100 #define HIGH_WATER_MARK (LOW_WATER_MARK*5) -#ifdef CONFIG_UML +#ifndef CONFIG_HAS_DMA /* * We sometimes use UML for debugging, but it cannot handle * dma_alloc_coherent so we have to wrap it. */ -static inline void *dma_alloc(dma_addr_t *daddr) +static inline void *dma_alloc(struct cfspi *cfspi, dma_addr_t *daddr) { return kmalloc(SPI_DMA_BUF_LEN, GFP_KERNEL); } -static inline void dma_free(void *cpu_addr, dma_addr_t handle) +static inline void dma_free(struct cfspi *cfspi, void *cpu_addr, + dma_addr_t handle) { kfree(cpu_addr); } #else -static inline void *dma_alloc(dma_addr_t *daddr) +static inline void *dma_alloc(struct cfspi *cfspi, dma_addr_t *daddr) { - return dma_alloc_coherent(NULL, SPI_DMA_BUF_LEN, daddr, + return dma_alloc_coherent(&cfspi->pdev->dev, SPI_DMA_BUF_LEN, daddr, GFP_KERNEL); } -static inline void dma_free(void *cpu_addr, dma_addr_t handle) +static inline void dma_free(struct cfspi *cfspi, void *cpu_addr, + dma_addr_t handle) { - dma_free_coherent(NULL, SPI_DMA_BUF_LEN, cpu_addr, handle); + dma_free_coherent(&cfspi->pdev->dev, SPI_DMA_BUF_LEN, cpu_addr, handle); } -#endif /* CONFIG_UML */ +#endif /* CONFIG_HAS_DMA */ #ifdef CONFIG_DEBUG_FS @@ -610,13 +612,13 @@ static int cfspi_init(struct net_device *dev) } /* Allocate DMA buffers. */ - cfspi->xfer.va_tx[0] = dma_alloc(&cfspi->xfer.pa_tx[0]); + cfspi->xfer.va_tx[0] = dma_alloc(cfspi, &cfspi->xfer.pa_tx[0]); if (!cfspi->xfer.va_tx[0]) { res = -ENODEV; goto err_dma_alloc_tx_0; } - cfspi->xfer.va_rx = dma_alloc(&cfspi->xfer.pa_rx); + cfspi->xfer.va_rx = dma_alloc(cfspi, &cfspi->xfer.pa_rx); if (!cfspi->xfer.va_rx) { res = -ENODEV; @@ -665,9 +667,9 @@ static int cfspi_init(struct net_device *dev) return 0; err_create_wq: - dma_free(cfspi->xfer.va_rx, cfspi->xfer.pa_rx); + dma_free(cfspi, cfspi->xfer.va_rx, cfspi->xfer.pa_rx); err_dma_alloc_rx: - dma_free(cfspi->xfer.va_tx[0], cfspi->xfer.pa_tx[0]); + dma_free(cfspi, cfspi->xfer.va_tx[0], cfspi->xfer.pa_tx[0]); err_dma_alloc_tx_0: return res; } @@ -683,8 +685,8 @@ static void cfspi_uninit(struct net_device *dev) cfspi->ndev = NULL; /* Free DMA buffers. */ - dma_free(cfspi->xfer.va_rx, cfspi->xfer.pa_rx); - dma_free(cfspi->xfer.va_tx[0], cfspi->xfer.pa_tx[0]); + dma_free(cfspi, cfspi->xfer.va_rx, cfspi->xfer.pa_rx); + dma_free(cfspi, cfspi->xfer.va_tx[0], cfspi->xfer.pa_tx[0]); set_bit(SPI_TERMINATE, &cfspi->state); wake_up_interruptible(&cfspi->wait); destroy_workqueue(cfspi->wq); diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 0e4bbdcc614f..c76892ac4e69 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -344,7 +344,8 @@ static void b53_set_forwarding(struct b53_device *dev, int enable) b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_CTRL, mgmt); } -static void b53_enable_vlan(struct b53_device *dev, bool enable) +static void b53_enable_vlan(struct b53_device *dev, bool enable, + bool enable_filtering) { u8 mgmt, vc0, vc1, vc4 = 0, vc5; @@ -369,8 +370,13 @@ static void b53_enable_vlan(struct b53_device *dev, bool enable) vc0 |= VC0_VLAN_EN | VC0_VID_CHK_EN | VC0_VID_HASH_VID; vc1 |= VC1_RX_MCST_UNTAG_EN | VC1_RX_MCST_FWD_EN; vc4 &= ~VC4_ING_VID_CHECK_MASK; - vc4 |= VC4_ING_VID_VIO_DROP << VC4_ING_VID_CHECK_S; - vc5 |= VC5_DROP_VTABLE_MISS; + if (enable_filtering) { + vc4 |= VC4_ING_VID_VIO_DROP << VC4_ING_VID_CHECK_S; + vc5 |= VC5_DROP_VTABLE_MISS; + } else { + vc4 |= VC4_ING_VID_VIO_FWD << VC4_ING_VID_CHECK_S; + vc5 &= ~VC5_DROP_VTABLE_MISS; + } if (is5325(dev)) vc0 &= ~VC0_RESERVED_1; @@ -420,6 +426,9 @@ static void b53_enable_vlan(struct b53_device *dev, bool enable) } b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, mgmt); + + dev->vlan_enabled = enable; + dev->vlan_filtering_enabled = enable_filtering; } static int b53_set_jumbo(struct b53_device *dev, bool enable, bool allow_10_100) @@ -632,25 +641,35 @@ static void b53_enable_mib(struct b53_device *dev) b53_write8(dev, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, gc); } +static u16 b53_default_pvid(struct b53_device *dev) +{ + if (is5325(dev) || is5365(dev)) + return 1; + else + return 0; +} + int b53_configure_vlan(struct dsa_switch *ds) { struct b53_device *dev = ds->priv; struct b53_vlan vl = { 0 }; - int i; + int i, def_vid; + + def_vid = b53_default_pvid(dev); /* clear all vlan entries */ if (is5325(dev) || is5365(dev)) { - for (i = 1; i < dev->num_vlans; i++) + for (i = def_vid; i < dev->num_vlans; i++) b53_set_vlan_entry(dev, i, &vl); } else { b53_do_vlan_op(dev, VTA_CMD_CLEAR); } - b53_enable_vlan(dev, false); + b53_enable_vlan(dev, false, dev->vlan_filtering_enabled); b53_for_each_port(dev, i) b53_write16(dev, B53_VLAN_PAGE, - B53_VLAN_PORT_DEF_TAG(i), 1); + B53_VLAN_PORT_DEF_TAG(i), def_vid); if (!is5325(dev) && !is5365(dev)) b53_set_jumbo(dev, dev->enable_jumbo, false); @@ -1255,6 +1274,46 @@ EXPORT_SYMBOL(b53_phylink_mac_link_up); int b53_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering) { + struct b53_device *dev = ds->priv; + struct net_device *bridge_dev; + unsigned int i; + u16 pvid, new_pvid; + + /* Handle the case were multiple bridges span the same switch device + * and one of them has a different setting than what is being requested + * which would be breaking filtering semantics for any of the other + * bridge devices. + */ + b53_for_each_port(dev, i) { + bridge_dev = dsa_to_port(ds, i)->bridge_dev; + if (bridge_dev && + bridge_dev != dsa_to_port(ds, port)->bridge_dev && + br_vlan_enabled(bridge_dev) != vlan_filtering) { + netdev_err(bridge_dev, + "VLAN filtering is global to the switch!\n"); + return -EINVAL; + } + } + + b53_read16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), &pvid); + new_pvid = pvid; + if (dev->vlan_filtering_enabled && !vlan_filtering) { + /* Filtering is currently enabled, use the default PVID since + * the bridge does not expect tagging anymore + */ + dev->ports[port].pvid = pvid; + new_pvid = b53_default_pvid(dev); + } else if (!dev->vlan_filtering_enabled && vlan_filtering) { + /* Filtering is currently disabled, restore the previous PVID */ + new_pvid = dev->ports[port].pvid; + } + + if (pvid != new_pvid) + b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), + new_pvid); + + b53_enable_vlan(dev, dev->vlan_enabled, vlan_filtering); + return 0; } EXPORT_SYMBOL(b53_vlan_filtering); @@ -1270,7 +1329,7 @@ int b53_vlan_prepare(struct dsa_switch *ds, int port, if (vlan->vid_end > dev->num_vlans) return -ERANGE; - b53_enable_vlan(dev, true); + b53_enable_vlan(dev, true, dev->vlan_filtering_enabled); return 0; } @@ -1300,7 +1359,7 @@ void b53_vlan_add(struct dsa_switch *ds, int port, b53_fast_age_vlan(dev, vid); } - if (pvid) { + if (pvid && !dsa_is_cpu_port(ds, port)) { b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), vlan->vid_end); b53_fast_age_vlan(dev, vid); @@ -1326,12 +1385,8 @@ int b53_vlan_del(struct dsa_switch *ds, int port, vl->members &= ~BIT(port); - if (pvid == vid) { - if (is5325(dev) || is5365(dev)) - pvid = 1; - else - pvid = 0; - } + if (pvid == vid) + pvid = b53_default_pvid(dev); if (untagged && !dsa_is_cpu_port(ds, port)) vl->untag &= ~(BIT(port)); @@ -1644,10 +1699,7 @@ void b53_br_leave(struct dsa_switch *ds, int port, struct net_device *br) b53_write16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), pvlan); dev->ports[port].vlan_ctl_mask = pvlan; - if (is5325(dev) || is5365(dev)) - pvid = 1; - else - pvid = 0; + pvid = b53_default_pvid(dev); /* Make this port join all VLANs without VLAN entries */ if (is58xx(dev)) { diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index ec796482792d..4dc7ee38b258 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -91,6 +91,7 @@ enum { struct b53_port { u16 vlan_ctl_mask; struct ethtool_eee eee; + u16 pvid; }; struct b53_vlan { @@ -137,6 +138,8 @@ struct b53_device { unsigned int num_vlans; struct b53_vlan *vlans; + bool vlan_enabled; + bool vlan_filtering_enabled; unsigned int num_ports; struct b53_port *ports; }; diff --git a/drivers/net/dsa/b53/b53_srab.c b/drivers/net/dsa/b53/b53_srab.c index 90f514252987..d9c56a779c08 100644 --- a/drivers/net/dsa/b53/b53_srab.c +++ b/drivers/net/dsa/b53/b53_srab.c @@ -511,9 +511,6 @@ static void b53_srab_prepare_irq(struct platform_device *pdev) /* Clear all pending interrupts */ writel(0xffffffff, priv->regs + B53_SRAB_INTR); - if (dev->pdata && dev->pdata->chip_id != BCM58XX_DEVICE_ID) - return; - for (i = 0; i < B53_N_PORTS; i++) { port = &priv->port_intrs[i]; diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 361fbde76654..f91b8e77d543 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -690,7 +690,7 @@ static int bcm_sf2_sw_suspend(struct dsa_switch *ds) * port, the other ones have already been disabled during * bcm_sf2_sw_setup */ - for (port = 0; port < DSA_MAX_PORTS; port++) { + for (port = 0; port < ds->num_ports; port++) { if (dsa_is_user_port(ds, port) || dsa_is_cpu_port(ds, port)) bcm_sf2_port_disable(ds, port, NULL); } @@ -726,10 +726,11 @@ static void bcm_sf2_sw_get_wol(struct dsa_switch *ds, int port, { struct net_device *p = ds->ports[port].cpu_dp->master; struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); - struct ethtool_wolinfo pwol; + struct ethtool_wolinfo pwol = { }; /* Get the parent device WoL settings */ - p->ethtool_ops->get_wol(p, &pwol); + if (p->ethtool_ops->get_wol) + p->ethtool_ops->get_wol(p, &pwol); /* Advertise the parent device supported settings */ wol->supported = pwol.supported; @@ -750,9 +751,10 @@ static int bcm_sf2_sw_set_wol(struct dsa_switch *ds, int port, struct net_device *p = ds->ports[port].cpu_dp->master; struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); s8 cpu_port = ds->ports[port].cpu_dp->index; - struct ethtool_wolinfo pwol; + struct ethtool_wolinfo pwol = { }; - p->ethtool_ops->get_wol(p, &pwol); + if (p->ethtool_ops->get_wol) + p->ethtool_ops->get_wol(p, &pwol); if (wol->wolopts & ~pwol.supported) return -EINVAL; @@ -894,12 +896,44 @@ static const struct b53_io_ops bcm_sf2_io_ops = { .write64 = bcm_sf2_core_write64, }; +static void bcm_sf2_sw_get_strings(struct dsa_switch *ds, int port, + u32 stringset, uint8_t *data) +{ + int cnt = b53_get_sset_count(ds, port, stringset); + + b53_get_strings(ds, port, stringset, data); + bcm_sf2_cfp_get_strings(ds, port, stringset, + data + cnt * ETH_GSTRING_LEN); +} + +static void bcm_sf2_sw_get_ethtool_stats(struct dsa_switch *ds, int port, + uint64_t *data) +{ + int cnt = b53_get_sset_count(ds, port, ETH_SS_STATS); + + b53_get_ethtool_stats(ds, port, data); + bcm_sf2_cfp_get_ethtool_stats(ds, port, data + cnt); +} + +static int bcm_sf2_sw_get_sset_count(struct dsa_switch *ds, int port, + int sset) +{ + int cnt = b53_get_sset_count(ds, port, sset); + + if (cnt < 0) + return cnt; + + cnt += bcm_sf2_cfp_get_sset_count(ds, port, sset); + + return cnt; +} + static const struct dsa_switch_ops bcm_sf2_ops = { .get_tag_protocol = b53_get_tag_protocol, .setup = bcm_sf2_sw_setup, - .get_strings = b53_get_strings, - .get_ethtool_stats = b53_get_ethtool_stats, - .get_sset_count = b53_get_sset_count, + .get_strings = bcm_sf2_sw_get_strings, + .get_ethtool_stats = bcm_sf2_sw_get_ethtool_stats, + .get_sset_count = bcm_sf2_sw_get_sset_count, .get_ethtool_phy_stats = b53_get_ethtool_phy_stats, .get_phy_flags = bcm_sf2_sw_get_phy_flags, .phylink_validate = bcm_sf2_sw_validate, @@ -1062,7 +1096,6 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev) dev_set_drvdata(&pdev->dev, priv); spin_lock_init(&priv->indir_lock); - mutex_init(&priv->stats_mutex); mutex_init(&priv->cfp.lock); INIT_LIST_HEAD(&priv->cfp.rules_list); diff --git a/drivers/net/dsa/bcm_sf2.h b/drivers/net/dsa/bcm_sf2.h index faaef320ec48..eb3655bea467 100644 --- a/drivers/net/dsa/bcm_sf2.h +++ b/drivers/net/dsa/bcm_sf2.h @@ -87,9 +87,6 @@ struct bcm_sf2_priv { /* Backing b53_device */ struct b53_device *dev; - /* Mutex protecting access to the MIB counters */ - struct mutex stats_mutex; - struct bcm_sf2_hw_params hw_params; struct bcm_sf2_port_status port_sts[DSA_MAX_PORTS]; @@ -216,5 +213,10 @@ int bcm_sf2_set_rxnfc(struct dsa_switch *ds, int port, int bcm_sf2_cfp_rst(struct bcm_sf2_priv *priv); void bcm_sf2_cfp_exit(struct dsa_switch *ds); int bcm_sf2_cfp_resume(struct dsa_switch *ds); +void bcm_sf2_cfp_get_strings(struct dsa_switch *ds, int port, + u32 stringset, uint8_t *data); +void bcm_sf2_cfp_get_ethtool_stats(struct dsa_switch *ds, int port, + uint64_t *data); +int bcm_sf2_cfp_get_sset_count(struct dsa_switch *ds, int port, int sset); #endif /* __BCM_SF2_H */ diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c index 6d8059dc77b7..e6234d209787 100644 --- a/drivers/net/dsa/bcm_sf2_cfp.c +++ b/drivers/net/dsa/bcm_sf2_cfp.c @@ -213,6 +213,7 @@ static inline unsigned int bcm_sf2_cfp_rule_size(struct bcm_sf2_priv *priv) static int bcm_sf2_cfp_act_pol_set(struct bcm_sf2_priv *priv, unsigned int rule_index, + int src_port, unsigned int port_num, unsigned int queue_num, bool fwd_map_change) @@ -230,6 +231,10 @@ static int bcm_sf2_cfp_act_pol_set(struct bcm_sf2_priv *priv, else reg = 0; + /* Enable looping back to the original port */ + if (src_port == port_num) + reg |= LOOP_BK_EN; + core_writel(priv, reg, CORE_ACT_POL_DATA0); /* Set classification ID that needs to be put in Broadcom tag */ @@ -443,7 +448,7 @@ static int bcm_sf2_cfp_ipv4_rule_set(struct bcm_sf2_priv *priv, int port, } /* Insert into Action and policer RAMs now */ - ret = bcm_sf2_cfp_act_pol_set(priv, rule_index, port_num, + ret = bcm_sf2_cfp_act_pol_set(priv, rule_index, port, port_num, queue_num, true); if (ret) goto out_err_flow_rule; @@ -598,7 +603,6 @@ static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port, unsigned int queue_num, struct ethtool_rx_flow_spec *fs) { - struct ethtool_tcpip6_spec *v6_spec, *v6_m_spec; struct ethtool_rx_flow_spec_input input = {}; unsigned int slice_num, rule_index[2]; const struct cfp_udf_layout *layout; @@ -613,13 +617,9 @@ static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port, switch (fs->flow_type & ~FLOW_EXT) { case TCP_V6_FLOW: ip_proto = IPPROTO_TCP; - v6_spec = &fs->h_u.tcp_ip6_spec; - v6_m_spec = &fs->m_u.tcp_ip6_spec; break; case UDP_V6_FLOW: ip_proto = IPPROTO_UDP; - v6_spec = &fs->h_u.udp_ip6_spec; - v6_m_spec = &fs->m_u.udp_ip6_spec; break; default: return -EINVAL; @@ -733,7 +733,7 @@ static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port, } /* Insert into Action and policer RAMs now */ - ret = bcm_sf2_cfp_act_pol_set(priv, rule_index[0], port_num, + ret = bcm_sf2_cfp_act_pol_set(priv, rule_index[0], port, port_num, queue_num, false); if (ret) goto out_err_flow_rule; @@ -795,7 +795,7 @@ static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port, /* Insert into Action and policer RAMs now, set chain ID to * the one we are chained to */ - ret = bcm_sf2_cfp_act_pol_set(priv, rule_index[1], port_num, + ret = bcm_sf2_cfp_act_pol_set(priv, rule_index[1], port, port_num, queue_num, true); if (ret) goto out_err_flow_rule; @@ -1201,3 +1201,91 @@ int bcm_sf2_cfp_resume(struct dsa_switch *ds) return ret; } + +static const struct bcm_sf2_cfp_stat { + unsigned int offset; + unsigned int ram_loc; + const char *name; +} bcm_sf2_cfp_stats[] = { + { + .offset = CORE_STAT_GREEN_CNTR, + .ram_loc = GREEN_STAT_RAM, + .name = "Green" + }, + { + .offset = CORE_STAT_YELLOW_CNTR, + .ram_loc = YELLOW_STAT_RAM, + .name = "Yellow" + }, + { + .offset = CORE_STAT_RED_CNTR, + .ram_loc = RED_STAT_RAM, + .name = "Red" + }, +}; + +void bcm_sf2_cfp_get_strings(struct dsa_switch *ds, int port, + u32 stringset, uint8_t *data) +{ + struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); + unsigned int s = ARRAY_SIZE(bcm_sf2_cfp_stats); + char buf[ETH_GSTRING_LEN]; + unsigned int i, j, iter; + + if (stringset != ETH_SS_STATS) + return; + + for (i = 1; i < priv->num_cfp_rules; i++) { + for (j = 0; j < s; j++) { + snprintf(buf, sizeof(buf), + "CFP%03d_%sCntr", + i, bcm_sf2_cfp_stats[j].name); + iter = (i - 1) * s + j; + strlcpy(data + iter * ETH_GSTRING_LEN, + buf, ETH_GSTRING_LEN); + } + } +} + +void bcm_sf2_cfp_get_ethtool_stats(struct dsa_switch *ds, int port, + uint64_t *data) +{ + struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); + unsigned int s = ARRAY_SIZE(bcm_sf2_cfp_stats); + const struct bcm_sf2_cfp_stat *stat; + unsigned int i, j, iter; + struct cfp_rule *rule; + int ret; + + mutex_lock(&priv->cfp.lock); + for (i = 1; i < priv->num_cfp_rules; i++) { + rule = bcm_sf2_cfp_rule_find(priv, port, i); + if (!rule) + continue; + + for (j = 0; j < s; j++) { + stat = &bcm_sf2_cfp_stats[j]; + + bcm_sf2_cfp_rule_addr_set(priv, i); + ret = bcm_sf2_cfp_op(priv, stat->ram_loc | OP_SEL_READ); + if (ret) + continue; + + iter = (i - 1) * s + j; + data[iter] = core_readl(priv, stat->offset); + } + + } + mutex_unlock(&priv->cfp.lock); +} + +int bcm_sf2_cfp_get_sset_count(struct dsa_switch *ds, int port, int sset) +{ + struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); + + if (sset != ETH_SS_STATS) + return 0; + + /* 3 counters per CFP rules */ + return (priv->num_cfp_rules - 1) * ARRAY_SIZE(bcm_sf2_cfp_stats); +} diff --git a/drivers/net/dsa/bcm_sf2_regs.h b/drivers/net/dsa/bcm_sf2_regs.h index 0a1e530d52b7..67f056206f37 100644 --- a/drivers/net/dsa/bcm_sf2_regs.h +++ b/drivers/net/dsa/bcm_sf2_regs.h @@ -400,6 +400,10 @@ enum bcm_sf2_reg_offs { #define CORE_RATE_METER6 0x281e0 #define CIR_REF_CNT_MASK 0x7ffff +#define CORE_STAT_GREEN_CNTR 0x28200 +#define CORE_STAT_YELLOW_CNTR 0x28210 +#define CORE_STAT_RED_CNTR 0x28220 + #define CORE_CFP_CTL_REG 0x28400 #define CFP_EN_MAP_MASK 0x1ff diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index 89ed059bb576..674d77e1b029 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -397,6 +397,7 @@ static void ksz9477_port_stp_state_set(struct dsa_switch *ds, int port, struct ksz_port *p = &dev->ports[port]; u8 data; int member = -1; + int forward = dev->member; ksz_pread8(dev, port, P_STP_CTRL, &data); data &= ~(PORT_TX_ENABLE | PORT_RX_ENABLE | PORT_LEARN_DISABLE); @@ -464,10 +465,10 @@ static void ksz9477_port_stp_state_set(struct dsa_switch *ds, int port, } /* When topology has changed the function ksz_update_port_member - * should be called to modify port forwarding behavior. However - * as the offload_fwd_mark indication cannot be reported here - * the switch forwarding function is not enabled. + * should be called to modify port forwarding behavior. */ + if (forward != dev->member) + ksz_update_port_member(dev, port); } static void ksz9477_flush_dyn_mac_table(struct ksz_device *dev, int port) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 669a7f13fdce..cc7ce06b6d58 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -261,6 +261,7 @@ static irqreturn_t mv88e6xxx_g1_irq_thread_work(struct mv88e6xxx_chip *chip) unsigned int sub_irq; unsigned int n; u16 reg; + u16 ctl1; int err; mutex_lock(&chip->reg_lock); @@ -270,13 +271,28 @@ static irqreturn_t mv88e6xxx_g1_irq_thread_work(struct mv88e6xxx_chip *chip) if (err) goto out; - for (n = 0; n < chip->g1_irq.nirqs; ++n) { - if (reg & (1 << n)) { - sub_irq = irq_find_mapping(chip->g1_irq.domain, n); - handle_nested_irq(sub_irq); - ++nhandled; + do { + for (n = 0; n < chip->g1_irq.nirqs; ++n) { + if (reg & (1 << n)) { + sub_irq = irq_find_mapping(chip->g1_irq.domain, + n); + handle_nested_irq(sub_irq); + ++nhandled; + } } - } + + mutex_lock(&chip->reg_lock); + err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_CTL1, &ctl1); + if (err) + goto unlock; + err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_STS, ®); +unlock: + mutex_unlock(&chip->reg_lock); + if (err) + goto out; + ctl1 &= GENMASK(chip->g1_irq.nirqs, 0); + } while (reg & ctl1); + out: return (nhandled > 0 ? IRQ_HANDLED : IRQ_NONE); } @@ -647,8 +663,10 @@ static void mv88e6390_phylink_validate(struct mv88e6xxx_chip *chip, int port, unsigned long *mask, struct phylink_link_state *state) { - if (port >= 9) + if (port >= 9) { phylink_set(mask, 2500baseX_Full); + phylink_set(mask, 2500baseT_Full); + } /* No ethtool bits for 200Mbps */ phylink_set(mask, 1000baseT_Full); @@ -4674,6 +4692,22 @@ static int mv88e6xxx_port_mdb_del(struct dsa_switch *ds, int port, return err; } +static int mv88e6xxx_port_egress_floods(struct dsa_switch *ds, int port, + bool unicast, bool multicast) +{ + struct mv88e6xxx_chip *chip = ds->priv; + int err = -EOPNOTSUPP; + + mutex_lock(&chip->reg_lock); + if (chip->info->ops->port_set_egress_floods) + err = chip->info->ops->port_set_egress_floods(chip, port, + unicast, + multicast); + mutex_unlock(&chip->reg_lock); + + return err; +} + static const struct dsa_switch_ops mv88e6xxx_switch_ops = { #if IS_ENABLED(CONFIG_NET_DSA_LEGACY) .probe = mv88e6xxx_drv_probe, @@ -4701,6 +4735,7 @@ static const struct dsa_switch_ops mv88e6xxx_switch_ops = { .set_ageing_time = mv88e6xxx_set_ageing_time, .port_bridge_join = mv88e6xxx_port_bridge_join, .port_bridge_leave = mv88e6xxx_port_bridge_leave, + .port_egress_floods = mv88e6xxx_port_egress_floods, .port_stp_state_set = mv88e6xxx_port_stp_state_set, .port_fast_age = mv88e6xxx_port_fast_age, .port_vlan_filtering = mv88e6xxx_port_vlan_filtering, diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c index 5200e4bdce93..ea243840ee0f 100644 --- a/drivers/net/dsa/mv88e6xxx/global1_atu.c +++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c @@ -314,6 +314,7 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id) { struct mv88e6xxx_chip *chip = dev_id; struct mv88e6xxx_atu_entry entry; + int spid; int err; u16 val; @@ -336,6 +337,8 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id) if (err) goto out; + spid = entry.state; + if (val & MV88E6XXX_G1_ATU_OP_AGE_OUT_VIOLATION) { dev_err_ratelimited(chip->dev, "ATU age out violation for %pM\n", @@ -344,23 +347,23 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id) if (val & MV88E6XXX_G1_ATU_OP_MEMBER_VIOLATION) { dev_err_ratelimited(chip->dev, - "ATU member violation for %pM portvec %x\n", - entry.mac, entry.portvec); - chip->ports[entry.portvec].atu_member_violation++; + "ATU member violation for %pM portvec %x spid %d\n", + entry.mac, entry.portvec, spid); + chip->ports[spid].atu_member_violation++; } if (val & MV88E6XXX_G1_ATU_OP_MISS_VIOLATION) { dev_err_ratelimited(chip->dev, - "ATU miss violation for %pM portvec %x\n", - entry.mac, entry.portvec); - chip->ports[entry.portvec].atu_miss_violation++; + "ATU miss violation for %pM portvec %x spid %d\n", + entry.mac, entry.portvec, spid); + chip->ports[spid].atu_miss_violation++; } if (val & MV88E6XXX_G1_ATU_OP_FULL_VIOLATION) { dev_err_ratelimited(chip->dev, - "ATU full violation for %pM portvec %x\n", - entry.mac, entry.portvec); - chip->ports[entry.portvec].atu_full_violation++; + "ATU full violation for %pM portvec %x spid %d\n", + entry.mac, entry.portvec, spid); + chip->ports[spid].atu_full_violation++; } mutex_unlock(&chip->reg_lock); diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index a4b6cda38016..195a8a87b984 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -443,6 +443,18 @@ qca8k_set_pad_ctrl(struct qca8k_priv *priv, int port, int mode) val = QCA8K_PORT_PAD_RGMII_EN; qca8k_write(priv, reg, val); break; + case PHY_INTERFACE_MODE_RGMII_ID: + /* RGMII_ID needs internal delay. This is enabled through + * PORT5_PAD_CTRL for all ports, rather than individual port + * registers + */ + qca8k_write(priv, reg, + QCA8K_PORT_PAD_RGMII_EN | + QCA8K_PORT_PAD_RGMII_TX_DELAY(QCA8K_MAX_DELAY) | + QCA8K_PORT_PAD_RGMII_RX_DELAY(QCA8K_MAX_DELAY)); + qca8k_write(priv, QCA8K_REG_PORT5_PAD_CTRL, + QCA8K_PORT_PAD_RGMII_RX_DELAY_EN); + break; case PHY_INTERFACE_MODE_SGMII: qca8k_write(priv, reg, QCA8K_PORT_PAD_SGMII_EN); break; diff --git a/drivers/net/dsa/qca8k.h b/drivers/net/dsa/qca8k.h index 613fe5c50236..d146e54c8a6c 100644 --- a/drivers/net/dsa/qca8k.h +++ b/drivers/net/dsa/qca8k.h @@ -40,6 +40,7 @@ ((0x8 + (x & 0x3)) << 22) #define QCA8K_PORT_PAD_RGMII_RX_DELAY(x) \ ((0x10 + (x & 0x3)) << 20) +#define QCA8K_MAX_DELAY 3 #define QCA8K_PORT_PAD_RGMII_RX_DELAY_EN BIT(24) #define QCA8K_PORT_PAD_SGMII_EN BIT(7) #define QCA8K_REG_MODULE_EN 0x030 diff --git a/drivers/net/ethernet/3com/3c515.c b/drivers/net/ethernet/3com/3c515.c index b648e3f95c01..808abb6b3671 100644 --- a/drivers/net/ethernet/3com/3c515.c +++ b/drivers/net/ethernet/3com/3c515.c @@ -1177,7 +1177,7 @@ static irqreturn_t corkscrew_interrupt(int irq, void *dev_id) if (inl(ioaddr + DownListPtr) == isa_virt_to_bus(&lp->tx_ring[entry])) break; /* It still hasn't been processed. */ if (lp->tx_skbuff[entry]) { - dev_kfree_skb_irq(lp->tx_skbuff[entry]); + dev_consume_skb_irq(lp->tx_skbuff[entry]); lp->tx_skbuff[entry] = NULL; } dirty_tx++; @@ -1192,7 +1192,7 @@ static irqreturn_t corkscrew_interrupt(int irq, void *dev_id) #ifdef VORTEX_BUS_MASTER if (status & DMADone) { outw(0x1000, ioaddr + Wn7_MasterStatus); /* Ack the event. */ - dev_kfree_skb_irq(lp->tx_skb); /* Release the transferred buffer */ + dev_consume_skb_irq(lp->tx_skb); /* Release the transferred buffer */ netif_wake_queue(dev); } #endif diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c index 40f421dbdf57..147051404194 100644 --- a/drivers/net/ethernet/3com/3c59x.c +++ b/drivers/net/ethernet/3com/3c59x.c @@ -2307,7 +2307,7 @@ _vortex_interrupt(int irq, struct net_device *dev) dma_unmap_single(vp->gendev, vp->tx_skb_dma, (vp->tx_skb->len + 3) & ~3, DMA_TO_DEVICE); pkts_compl++; bytes_compl += vp->tx_skb->len; - dev_kfree_skb_irq(vp->tx_skb); /* Release the transferred buffer */ + dev_consume_skb_irq(vp->tx_skb); /* Release the transferred buffer */ if (ioread16(ioaddr + TxFree) > 1536) { /* * AKPM: FIXME: I don't think we need this. If the queue was stopped due to @@ -2449,7 +2449,7 @@ _boomerang_interrupt(int irq, struct net_device *dev) #endif pkts_compl++; bytes_compl += skb->len; - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); vp->tx_skbuff[entry] = NULL; } else { pr_debug("boomerang_interrupt: no skb!\n"); diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c index 097467f44b0d..816540e6beac 100644 --- a/drivers/net/ethernet/adaptec/starfire.c +++ b/drivers/net/ethernet/adaptec/starfire.c @@ -1390,7 +1390,7 @@ static irqreturn_t intr_handler(int irq, void *dev_instance) } } - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); } np->tx_done_q[np->tx_done].status = 0; np->tx_done = (np->tx_done + 1) % DONE_Q_SIZE; diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index a70bb1bb90e7..a6eacf2099c3 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -2663,11 +2663,6 @@ static int ena_restore_device(struct ena_adapter *adapter) goto err_device_destroy; } - clear_bit(ENA_FLAG_ONGOING_RESET, &adapter->flags); - /* Make sure we don't have a race with AENQ Links state handler */ - if (test_bit(ENA_FLAG_LINK_UP, &adapter->flags)) - netif_carrier_on(adapter->netdev); - rc = ena_enable_msix_and_set_admin_interrupts(adapter, adapter->num_queues); if (rc) { @@ -2684,6 +2679,11 @@ static int ena_restore_device(struct ena_adapter *adapter) } set_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags); + + clear_bit(ENA_FLAG_ONGOING_RESET, &adapter->flags); + if (test_bit(ENA_FLAG_LINK_UP, &adapter->flags)) + netif_carrier_on(adapter->netdev); + mod_timer(&adapter->timer_service, round_jiffies(jiffies + HZ)); dev_err(&pdev->dev, "Device reset completed successfully, Driver info: %s\n", diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h index dc8b6173d8d8..63870072cbbd 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.h +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h @@ -45,7 +45,7 @@ #define DRV_MODULE_VER_MAJOR 2 #define DRV_MODULE_VER_MINOR 0 -#define DRV_MODULE_VER_SUBMINOR 2 +#define DRV_MODULE_VER_SUBMINOR 3 #define DRV_MODULE_NAME "ena" #ifndef DRV_MODULE_VERSION diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c index e833d1b3fe18..e5073aeea06a 100644 --- a/drivers/net/ethernet/amd/au1000_eth.c +++ b/drivers/net/ethernet/amd/au1000_eth.c @@ -1167,7 +1167,7 @@ static int au1000_probe(struct platform_device *pdev) /* Allocate the data buffers * Snooping works fine with eth on all au1xxx */ - aup->vaddr = (u32)dma_alloc_attrs(NULL, MAX_BUF_SIZE * + aup->vaddr = (u32)dma_alloc_attrs(&pdev->dev, MAX_BUF_SIZE * (NUM_TX_BUFFS + NUM_RX_BUFFS), &aup->dma_addr, 0, DMA_ATTR_NON_CONSISTENT); @@ -1349,7 +1349,7 @@ err_remap3: err_remap2: iounmap(aup->mac); err_remap1: - dma_free_attrs(NULL, MAX_BUF_SIZE * (NUM_TX_BUFFS + NUM_RX_BUFFS), + dma_free_attrs(&pdev->dev, MAX_BUF_SIZE * (NUM_TX_BUFFS + NUM_RX_BUFFS), (void *)aup->vaddr, aup->dma_addr, DMA_ATTR_NON_CONSISTENT); err_vaddr: @@ -1383,7 +1383,7 @@ static int au1000_remove(struct platform_device *pdev) if (aup->tx_db_inuse[i]) au1000_ReleaseDB(aup, aup->tx_db_inuse[i]); - dma_free_attrs(NULL, MAX_BUF_SIZE * (NUM_TX_BUFFS + NUM_RX_BUFFS), + dma_free_attrs(&pdev->dev, MAX_BUF_SIZE * (NUM_TX_BUFFS + NUM_RX_BUFFS), (void *)aup->vaddr, aup->dma_addr, DMA_ATTR_NON_CONSISTENT); diff --git a/drivers/net/ethernet/amd/lance.c b/drivers/net/ethernet/amd/lance.c index b56d84c7df46..f90b454b1642 100644 --- a/drivers/net/ethernet/amd/lance.c +++ b/drivers/net/ethernet/amd/lance.c @@ -1084,7 +1084,7 @@ static irqreturn_t lance_interrupt(int irq, void *dev_id) /* We must free the original skb if it's not a data-only copy in the bounce buffer. */ if (lp->tx_skbuff[entry]) { - dev_kfree_skb_irq(lp->tx_skbuff[entry]); + dev_consume_skb_irq(lp->tx_skbuff[entry]); lp->tx_skbuff[entry] = NULL; } dirty_tx++; diff --git a/drivers/net/ethernet/amd/ni65.c b/drivers/net/ethernet/amd/ni65.c index 8931ce6bab7b..87ff5d6d1b22 100644 --- a/drivers/net/ethernet/amd/ni65.c +++ b/drivers/net/ethernet/amd/ni65.c @@ -1028,7 +1028,7 @@ static void ni65_xmit_intr(struct net_device *dev,int csr0) #ifdef XMT_VIA_SKB if(p->tmd_skb[p->tmdlast]) { - dev_kfree_skb_irq(p->tmd_skb[p->tmdlast]); + dev_consume_skb_irq(p->tmd_skb[p->tmdlast]); p->tmd_skb[p->tmdlast] = NULL; } #endif diff --git a/drivers/net/ethernet/apple/mace.c b/drivers/net/ethernet/apple/mace.c index 68b9ee489489..4d9819d2894d 100644 --- a/drivers/net/ethernet/apple/mace.c +++ b/drivers/net/ethernet/apple/mace.c @@ -764,7 +764,7 @@ static irqreturn_t mace_interrupt(int irq, void *dev_id) dev->stats.tx_bytes += mp->tx_bufs[i]->len; ++dev->stats.tx_packets; } - dev_kfree_skb_irq(mp->tx_bufs[i]); + dev_consume_skb_irq(mp->tx_bufs[i]); --mp->tx_active; if (++i >= N_TX_RING) i = 0; diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c index 4406325fdd9f..ff3d68532f5f 100644 --- a/drivers/net/ethernet/arc/emac_main.c +++ b/drivers/net/ethernet/arc/emac_main.c @@ -148,7 +148,7 @@ static void arc_emac_tx_clean(struct net_device *ndev) dma_unmap_len(tx_buff, len), DMA_TO_DEVICE); /* return the sk_buff to system */ - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); txbd->data = 0; txbd->info = 0; diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c index 3164aad29bcf..9dfe6a9431e6 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c +++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c @@ -1259,7 +1259,7 @@ static bool atl1e_clean_tx_irq(struct atl1e_adapter *adapter) } if (tx_buffer->skb) { - dev_kfree_skb_irq(tx_buffer->skb); + dev_consume_skb_irq(tx_buffer->skb); tx_buffer->skb = NULL; } diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c index 63edc5706c09..9e07b469066a 100644 --- a/drivers/net/ethernet/atheros/atlx/atl1.c +++ b/drivers/net/ethernet/atheros/atlx/atl1.c @@ -2088,7 +2088,7 @@ static int atl1_intr_tx(struct atl1_adapter *adapter) } if (buffer_info->skb) { - dev_kfree_skb_irq(buffer_info->skb); + dev_consume_skb_irq(buffer_info->skb); buffer_info->skb = NULL; } diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index f9521d0274b7..bc3ac369cbe3 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -134,6 +134,10 @@ static void bcm_sysport_set_rx_csum(struct net_device *dev, priv->rx_chk_en = !!(wanted & NETIF_F_RXCSUM); reg = rxchk_readl(priv, RXCHK_CONTROL); + /* Clear L2 header checks, which would prevent BPDUs + * from being received. + */ + reg &= ~RXCHK_L2_HDR_DIS; if (priv->rx_chk_en) reg |= RXCHK_EN; else @@ -520,7 +524,6 @@ static void bcm_sysport_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) { struct bcm_sysport_priv *priv = netdev_priv(dev); - u32 reg; wol->supported = WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER; wol->wolopts = priv->wolopts; @@ -528,11 +531,7 @@ static void bcm_sysport_get_wol(struct net_device *dev, if (!(priv->wolopts & WAKE_MAGICSECURE)) return; - /* Return the programmed SecureOn password */ - reg = umac_readl(priv, UMAC_PSW_MS); - put_unaligned_be16(reg, &wol->sopass[0]); - reg = umac_readl(priv, UMAC_PSW_LS); - put_unaligned_be32(reg, &wol->sopass[2]); + memcpy(wol->sopass, priv->sopass, sizeof(priv->sopass)); } static int bcm_sysport_set_wol(struct net_device *dev, @@ -548,13 +547,8 @@ static int bcm_sysport_set_wol(struct net_device *dev, if (wol->wolopts & ~supported) return -EINVAL; - /* Program the SecureOn password */ - if (wol->wolopts & WAKE_MAGICSECURE) { - umac_writel(priv, get_unaligned_be16(&wol->sopass[0]), - UMAC_PSW_MS); - umac_writel(priv, get_unaligned_be32(&wol->sopass[2]), - UMAC_PSW_LS); - } + if (wol->wolopts & WAKE_MAGICSECURE) + memcpy(priv->sopass, wol->sopass, sizeof(priv->sopass)); /* Flag the device and relevant IRQ as wakeup capable */ if (wol->wolopts) { @@ -2649,13 +2643,18 @@ static int bcm_sysport_suspend_to_wol(struct bcm_sysport_priv *priv) unsigned int index, i = 0; u32 reg; - /* Password has already been programmed */ reg = umac_readl(priv, UMAC_MPD_CTRL); if (priv->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE)) reg |= MPD_EN; reg &= ~PSW_EN; - if (priv->wolopts & WAKE_MAGICSECURE) + if (priv->wolopts & WAKE_MAGICSECURE) { + /* Program the SecureOn password */ + umac_writel(priv, get_unaligned_be16(&priv->sopass[0]), + UMAC_PSW_MS); + umac_writel(priv, get_unaligned_be32(&priv->sopass[2]), + UMAC_PSW_LS); reg |= PSW_EN; + } umac_writel(priv, reg, UMAC_MPD_CTRL); if (priv->wolopts & WAKE_FILTER) { diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h index 0887e6356649..0b192fea9c5d 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.h +++ b/drivers/net/ethernet/broadcom/bcmsysport.h @@ -12,6 +12,7 @@ #define __BCM_SYSPORT_H #include <linux/bitmap.h> +#include <linux/ethtool.h> #include <linux/if_vlan.h> #include <linux/net_dim.h> @@ -778,6 +779,7 @@ struct bcm_sysport_priv { unsigned int crc_fwd:1; u16 rev; u32 wolopts; + u8 sopass[SOPASS_MAX]; unsigned int wol_irq_disabled:1; /* MIB related fields */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 0cec82450e19..626b491f7674 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -11998,7 +11998,7 @@ static void validate_set_si_mode(struct bnx2x *bp) static int bnx2x_get_hwinfo(struct bnx2x *bp) { int /*abs*/func = BP_ABS_FUNC(bp); - int vn, mfw_vn; + int vn; u32 val = 0, val2 = 0; int rc = 0; @@ -12083,12 +12083,10 @@ static int bnx2x_get_hwinfo(struct bnx2x *bp) /* * Initialize MF configuration */ - bp->mf_ov = 0; bp->mf_mode = 0; bp->mf_sub_mode = 0; vn = BP_VN(bp); - mfw_vn = BP_FW_MB_IDX(bp); if (!CHIP_IS_E1(bp) && !BP_NOMCP(bp)) { BNX2X_DEV_INFO("shmem2base 0x%x, size %d, mfcfg offset %d\n", diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c index 8e0a317b31f7..a9bdc21873d3 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c @@ -1654,13 +1654,9 @@ static int bnx2x_vf_mbx_macvlan_list(struct bnx2x *bp, { int i, j; struct bnx2x_vf_mac_vlan_filters *fl = NULL; - size_t fsz; - fsz = tlv->n_mac_vlan_filters * - sizeof(struct bnx2x_vf_mac_vlan_filter) + - sizeof(struct bnx2x_vf_mac_vlan_filters); - - fl = kzalloc(fsz, GFP_KERNEL); + fl = kzalloc(struct_size(fl, filters, tlv->n_mac_vlan_filters), + GFP_KERNEL); if (!fl) return -ENOMEM; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 1c2987c3d708..a9edf946d3bf 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1,7 +1,7 @@ /* Broadcom NetXtreme-C/E network driver. * * Copyright (c) 2014-2016 Broadcom Corporation - * Copyright (c) 2016-2018 Broadcom Limited + * Copyright (c) 2016-2019 Broadcom Limited * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -31,6 +31,7 @@ #include <asm/page.h> #include <linux/time.h> #include <linux/mii.h> +#include <linux/mdio.h> #include <linux/if.h> #include <linux/if_vlan.h> #include <linux/if_bridge.h> @@ -112,6 +113,7 @@ enum board_idx { BCM57454, BCM5745x_NPAR, BCM57508, + BCM57504, BCM58802, BCM58804, BCM58808, @@ -155,6 +157,7 @@ static const struct { [BCM57454] = { "Broadcom BCM57454 NetXtreme-E 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" }, [BCM5745x_NPAR] = { "Broadcom BCM5745x NetXtreme-E Ethernet Partition" }, [BCM57508] = { "Broadcom BCM57508 NetXtreme-E 10Gb/25Gb/50Gb/100Gb/200Gb Ethernet" }, + [BCM57504] = { "Broadcom BCM57504 NetXtreme-E 10Gb/25Gb/50Gb/100Gb/200Gb Ethernet" }, [BCM58802] = { "Broadcom BCM58802 NetXtreme-S 10Gb/25Gb/40Gb/50Gb Ethernet" }, [BCM58804] = { "Broadcom BCM58804 NetXtreme-S 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" }, [BCM58808] = { "Broadcom BCM58808 NetXtreme-S 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" }, @@ -201,6 +204,7 @@ static const struct pci_device_id bnxt_pci_tbl[] = { { PCI_VDEVICE(BROADCOM, 0x16f0), .driver_data = BCM58808 }, { PCI_VDEVICE(BROADCOM, 0x16f1), .driver_data = BCM57452 }, { PCI_VDEVICE(BROADCOM, 0x1750), .driver_data = BCM57508 }, + { PCI_VDEVICE(BROADCOM, 0x1751), .driver_data = BCM57504 }, { PCI_VDEVICE(BROADCOM, 0xd802), .driver_data = BCM58802 }, { PCI_VDEVICE(BROADCOM, 0xd804), .driver_data = BCM58804 }, #ifdef CONFIG_BNXT_SRIOV @@ -4973,12 +4977,18 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp) struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring; struct bnxt_ring_struct *ring = &cpr->cp_ring_struct; u32 map_idx = ring->map_idx; + unsigned int vector; + vector = bp->irq_tbl[map_idx].vector; + disable_irq_nosync(vector); rc = hwrm_ring_alloc_send_msg(bp, ring, type, map_idx); - if (rc) + if (rc) { + enable_irq(vector); goto err_out; + } bnxt_set_db(bp, &cpr->cp_db, type, map_idx, ring->fw_ring_id); bnxt_db_nq(bp, &cpr->cp_db, cpr->cp_raw_cons); + enable_irq(vector); bp->grp_info[i].cp_fw_ring_id = ring->fw_ring_id; if (!i) { @@ -6674,6 +6684,10 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp) VER_GET_RESP_DEV_CAPS_CFG_FLOW_HANDLE_64BIT_SUPPORTED) bp->fw_cap |= BNXT_FW_CAP_OVS_64BIT_HANDLE; + if (dev_caps_cfg & + VER_GET_RESP_DEV_CAPS_CFG_TRUSTED_VF_SUPPORTED) + bp->fw_cap |= BNXT_FW_CAP_TRUSTED_VF; + hwrm_ver_get_exit: mutex_unlock(&bp->hwrm_cmd_lock); return rc; @@ -8608,24 +8622,88 @@ static int bnxt_close(struct net_device *dev) return 0; } +static int bnxt_hwrm_port_phy_read(struct bnxt *bp, u16 phy_addr, u16 reg, + u16 *val) +{ + struct hwrm_port_phy_mdio_read_output *resp = bp->hwrm_cmd_resp_addr; + struct hwrm_port_phy_mdio_read_input req = {0}; + int rc; + + if (bp->hwrm_spec_code < 0x10a00) + return -EOPNOTSUPP; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_MDIO_READ, -1, -1); + req.port_id = cpu_to_le16(bp->pf.port_id); + req.phy_addr = phy_addr; + req.reg_addr = cpu_to_le16(reg & 0x1f); + if (bp->link_info.support_speeds & BNXT_LINK_SPEED_MSK_10GB) { + req.cl45_mdio = 1; + req.phy_addr = mdio_phy_id_prtad(phy_addr); + req.dev_addr = mdio_phy_id_devad(phy_addr); + req.reg_addr = cpu_to_le16(reg); + } + + mutex_lock(&bp->hwrm_cmd_lock); + rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (!rc) + *val = le16_to_cpu(resp->reg_data); + mutex_unlock(&bp->hwrm_cmd_lock); + return rc; +} + +static int bnxt_hwrm_port_phy_write(struct bnxt *bp, u16 phy_addr, u16 reg, + u16 val) +{ + struct hwrm_port_phy_mdio_write_input req = {0}; + + if (bp->hwrm_spec_code < 0x10a00) + return -EOPNOTSUPP; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_MDIO_WRITE, -1, -1); + req.port_id = cpu_to_le16(bp->pf.port_id); + req.phy_addr = phy_addr; + req.reg_addr = cpu_to_le16(reg & 0x1f); + if (bp->link_info.support_speeds & BNXT_LINK_SPEED_MSK_10GB) { + req.cl45_mdio = 1; + req.phy_addr = mdio_phy_id_prtad(phy_addr); + req.dev_addr = mdio_phy_id_devad(phy_addr); + req.reg_addr = cpu_to_le16(reg); + } + req.reg_data = cpu_to_le16(val); + + return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); +} + /* rtnl_lock held */ static int bnxt_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { + struct mii_ioctl_data *mdio = if_mii(ifr); + struct bnxt *bp = netdev_priv(dev); + int rc; + switch (cmd) { case SIOCGMIIPHY: + mdio->phy_id = bp->link_info.phy_addr; + /* fallthru */ case SIOCGMIIREG: { + u16 mii_regval = 0; + if (!netif_running(dev)) return -EAGAIN; - return 0; + rc = bnxt_hwrm_port_phy_read(bp, mdio->phy_id, mdio->reg_num, + &mii_regval); + mdio->val_out = mii_regval; + return rc; } case SIOCSMIIREG: if (!netif_running(dev)) return -EAGAIN; - return 0; + return bnxt_hwrm_port_phy_write(bp, mdio->phy_id, mdio->reg_num, + mdio->val_in); default: /* do nothing */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 17554d4be651..ecbe7d28a723 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -945,6 +945,7 @@ struct bnxt_vf_info { * stored by PF. */ u16 vlan; + u16 func_qcfg_flags; u32 flags; #define BNXT_VF_QOS 0x1 #define BNXT_VF_SPOOFCHK 0x2 @@ -1478,6 +1479,7 @@ struct bnxt { #define BNXT_FW_CAP_IF_CHANGE 0x00000010 #define BNXT_FW_CAP_KONG_MB_CHNL 0x00000080 #define BNXT_FW_CAP_OVS_64BIT_HANDLE 0x00000400 + #define BNXT_FW_CAP_TRUSTED_VF 0x00000800 #define BNXT_NEW_RM(bp) ((bp)->fw_cap & BNXT_FW_CAP_NEW_RM) u32 hwrm_spec_code; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index a6abfa4fb168..e1feb97bcd81 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -37,8 +37,6 @@ static const struct bnxt_dl_nvm_param nvm_params[] = { NVM_OFF_MSIX_VEC_PER_PF_MIN, BNXT_NVM_SHARED_CFG, 7}, {BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK, NVM_OFF_DIS_GRE_VER_CHECK, BNXT_NVM_SHARED_CFG, 1}, - - {DEVLINK_PARAM_GENERIC_ID_WOL, NVM_OFF_WOL, BNXT_NVM_PORT_CFG, 1}, }; static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg, @@ -72,8 +70,7 @@ static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg, bytesize = roundup(nvm_param.num_bits, BITS_PER_BYTE) / BITS_PER_BYTE; switch (bytesize) { case 1: - if (nvm_param.num_bits == 1 && - nvm_param.id != DEVLINK_PARAM_GENERIC_ID_WOL) + if (nvm_param.num_bits == 1) buf = &val->vbool; else buf = &val->vu8; @@ -167,17 +164,6 @@ static int bnxt_dl_msix_validate(struct devlink *dl, u32 id, return 0; } -static int bnxt_dl_wol_validate(struct devlink *dl, u32 id, - union devlink_param_value val, - struct netlink_ext_ack *extack) -{ - if (val.vu8 && val.vu8 != DEVLINK_PARAM_WAKE_MAGIC) { - NL_SET_ERR_MSG_MOD(extack, "WOL type is not supported"); - return -EINVAL; - } - return 0; -} - static const struct devlink_param bnxt_dl_params[] = { DEVLINK_PARAM_GENERIC(ENABLE_SRIOV, BIT(DEVLINK_PARAM_CMODE_PERMANENT), @@ -203,9 +189,6 @@ static const struct devlink_param bnxt_dl_params[] = { }; static const struct devlink_param bnxt_dl_port_params[] = { - DEVLINK_PARAM_GENERIC(WOL, BIT(DEVLINK_PARAM_CMODE_PERMANENT), - bnxt_dl_nvm_param_get, bnxt_dl_nvm_param_set, - bnxt_dl_wol_validate), }; int bnxt_dl_register(struct bnxt *bp) @@ -258,6 +241,9 @@ int bnxt_dl_register(struct bnxt *bp) netdev_err(bp->dev, "devlink_port_params_register failed"); goto err_dl_port_unreg; } + + devlink_params_publish(dl); + return 0; err_dl_port_unreg: diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h index da065ca84cc7..5b6b2c7d97cf 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h @@ -35,7 +35,6 @@ static inline void bnxt_link_bp_to_dl(struct bnxt *bp, struct devlink *dl) #define NVM_OFF_MSIX_VEC_PER_PF_MAX 108 #define NVM_OFF_MSIX_VEC_PER_PF_MIN 114 -#define NVM_OFF_WOL 152 #define NVM_OFF_IGNORE_ARI 164 #define NVM_OFF_DIS_GRE_VER_CHECK 171 #define NVM_OFF_ENABLE_SRIOV 401 diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h index 0a0995894ddb..b6c610339501 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h @@ -1,7 +1,7 @@ /* Broadcom NetXtreme-C/E network driver. * * Copyright (c) 2014-2016 Broadcom Corporation - * Copyright (c) 2016-2018 Broadcom Limited + * Copyright (c) 2016-2019 Broadcom Limited * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -98,6 +98,7 @@ struct hwrm_short_input { struct cmd_nums { __le16 req_type; #define HWRM_VER_GET 0x0UL + #define HWRM_ERROR_RECOVERY_QCFG 0xcUL #define HWRM_FUNC_DRV_IF_CHANGE 0xdUL #define HWRM_FUNC_BUF_UNRGTR 0xeUL #define HWRM_FUNC_VF_CFG 0xfUL @@ -221,6 +222,7 @@ struct cmd_nums { #define HWRM_CFA_METER_PROFILE_CFG 0xf7UL #define HWRM_CFA_METER_INSTANCE_ALLOC 0xf8UL #define HWRM_CFA_METER_INSTANCE_FREE 0xf9UL + #define HWRM_CFA_METER_INSTANCE_CFG 0xfaUL #define HWRM_CFA_VFR_ALLOC 0xfdUL #define HWRM_CFA_VFR_FREE 0xfeUL #define HWRM_CFA_VF_PAIR_ALLOC 0x100UL @@ -269,6 +271,7 @@ struct cmd_nums { #define HWRM_ENGINE_CKV_FLUSH 0x133UL #define HWRM_ENGINE_CKV_RNG_GET 0x134UL #define HWRM_ENGINE_CKV_KEY_GEN 0x135UL + #define HWRM_ENGINE_CKV_KEY_LABEL_CFG 0x136UL #define HWRM_ENGINE_QG_CONFIG_QUERY 0x13cUL #define HWRM_ENGINE_QG_QUERY 0x13dUL #define HWRM_ENGINE_QG_METER_PROFILE_CONFIG_QUERY 0x13eUL @@ -296,6 +299,7 @@ struct cmd_nums { #define HWRM_ENGINE_NQ_ALLOC 0x162UL #define HWRM_ENGINE_NQ_FREE 0x163UL #define HWRM_ENGINE_ON_DIE_RQE_CREDITS 0x164UL + #define HWRM_ENGINE_FUNC_QCFG 0x165UL #define HWRM_FUNC_RESOURCE_QCAPS 0x190UL #define HWRM_FUNC_VF_RESOURCE_CFG 0x191UL #define HWRM_FUNC_BACKING_STORE_QCAPS 0x192UL @@ -379,15 +383,15 @@ struct hwrm_err_output { }; #define HWRM_NA_SIGNATURE ((__le32)(-1)) #define HWRM_MAX_REQ_LEN 128 -#define HWRM_MAX_RESP_LEN 280 +#define HWRM_MAX_RESP_LEN 704 #define HW_HASH_INDEX_SIZE 0x80 #define HW_HASH_KEY_SIZE 40 #define HWRM_RESP_VALID_KEY 1 #define HWRM_VERSION_MAJOR 1 #define HWRM_VERSION_MINOR 10 #define HWRM_VERSION_UPDATE 0 -#define HWRM_VERSION_RSVD 35 -#define HWRM_VERSION_STR "1.10.0.35" +#define HWRM_VERSION_RSVD 47 +#define HWRM_VERSION_STR "1.10.0.47" /* hwrm_ver_get_input (size:192b/24B) */ struct hwrm_ver_get_input { @@ -580,6 +584,7 @@ struct hwrm_async_event_cmpl { #define ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CFG_CHANGE 0x6UL #define ASYNC_EVENT_CMPL_EVENT_ID_PORT_PHY_CFG_CHANGE 0x7UL #define ASYNC_EVENT_CMPL_EVENT_ID_RESET_NOTIFY 0x8UL + #define ASYNC_EVENT_CMPL_EVENT_ID_ERROR_RECOVERY 0x9UL #define ASYNC_EVENT_CMPL_EVENT_ID_FUNC_DRVR_UNLOAD 0x10UL #define ASYNC_EVENT_CMPL_EVENT_ID_FUNC_DRVR_LOAD 0x11UL #define ASYNC_EVENT_CMPL_EVENT_ID_FUNC_FLR_PROC_CMPLT 0x12UL @@ -595,6 +600,9 @@ struct hwrm_async_event_cmpl { #define ASYNC_EVENT_CMPL_EVENT_ID_DEBUG_NOTIFICATION 0x37UL #define ASYNC_EVENT_CMPL_EVENT_ID_EEM_CACHE_FLUSH_REQ 0x38UL #define ASYNC_EVENT_CMPL_EVENT_ID_EEM_CACHE_FLUSH_DONE 0x39UL + #define ASYNC_EVENT_CMPL_EVENT_ID_TCP_FLAG_ACTION_CHANGE 0x3aUL + #define ASYNC_EVENT_CMPL_EVENT_ID_EEM_FLOW_ACTIVE 0x3bUL + #define ASYNC_EVENT_CMPL_EVENT_ID_EEM_CFG_CHANGE 0x3cUL #define ASYNC_EVENT_CMPL_EVENT_ID_FW_TRACE_MSG 0xfeUL #define ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR 0xffUL #define ASYNC_EVENT_CMPL_EVENT_ID_LAST ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR @@ -724,6 +732,30 @@ struct hwrm_async_event_cmpl_reset_notify { #define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DELAY_IN_100MS_TICKS_SFT 16 }; +/* hwrm_async_event_cmpl_error_recovery (size:128b/16B) */ +struct hwrm_async_event_cmpl_error_recovery { + __le16 type; + #define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_MASK 0x3fUL + #define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_SFT 0 + #define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_HWRM_ASYNC_EVENT 0x2eUL + #define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_HWRM_ASYNC_EVENT + __le16 event_id; + #define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_ID_ERROR_RECOVERY 0x9UL + #define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_ID_LAST ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_ID_ERROR_RECOVERY + __le32 event_data2; + u8 opaque_v; + #define ASYNC_EVENT_CMPL_ERROR_RECOVERY_V 0x1UL + #define ASYNC_EVENT_CMPL_ERROR_RECOVERY_OPAQUE_MASK 0xfeUL + #define ASYNC_EVENT_CMPL_ERROR_RECOVERY_OPAQUE_SFT 1 + u8 timestamp_lo; + __le16 timestamp_hi; + __le32 event_data1; + #define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_MASK 0xffUL + #define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_SFT 0 + #define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_MASTER_FUNC 0x1UL + #define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_RECOVERY_ENABLED 0x2UL +}; + /* hwrm_async_event_cmpl_vf_cfg_change (size:128b/16B) */ struct hwrm_async_event_cmpl_vf_cfg_change { __le16 type; @@ -1014,6 +1046,7 @@ struct hwrm_func_qcaps_output { #define FUNC_QCAPS_RESP_FLAGS_WCB_PUSH_MODE 0x100000UL #define FUNC_QCAPS_RESP_FLAGS_DYNAMIC_TX_RING_ALLOC 0x200000UL #define FUNC_QCAPS_RESP_FLAGS_HOT_RESET_CAPABLE 0x400000UL + #define FUNC_QCAPS_RESP_FLAGS_ERROR_RECOVERY_CAPABLE 0x800000UL u8 mac_address[6]; __le16 max_rsscos_ctx; __le16 max_cmpl_rings; @@ -1185,6 +1218,7 @@ struct hwrm_func_cfg_input { #define FUNC_CFG_REQ_FLAGS_TRUSTED_VF_ENABLE 0x200000UL #define FUNC_CFG_REQ_FLAGS_DYNAMIC_TX_RING_ALLOC 0x400000UL #define FUNC_CFG_REQ_FLAGS_NQ_ASSETS_TEST 0x800000UL + #define FUNC_CFG_REQ_FLAGS_TRUSTED_VF_DISABLE 0x1000000UL __le32 enables; #define FUNC_CFG_REQ_ENABLES_MTU 0x1UL #define FUNC_CFG_REQ_ENABLES_MRU 0x2UL @@ -1390,6 +1424,7 @@ struct hwrm_func_drv_rgtr_input { #define FUNC_DRV_RGTR_REQ_FLAGS_16BIT_VER_MODE 0x4UL #define FUNC_DRV_RGTR_REQ_FLAGS_FLOW_HANDLE_64BIT_MODE 0x8UL #define FUNC_DRV_RGTR_REQ_FLAGS_HOT_RESET_SUPPORT 0x10UL + #define FUNC_DRV_RGTR_REQ_FLAGS_ERROR_RECOVERY_SUPPORT 0x20UL __le32 enables; #define FUNC_DRV_RGTR_REQ_ENABLES_OS_TYPE 0x1UL #define FUNC_DRV_RGTR_REQ_ENABLES_VER 0x2UL @@ -2024,6 +2059,89 @@ struct hwrm_func_backing_store_cfg_output { u8 valid; }; +/* hwrm_error_recovery_qcfg_input (size:192b/24B) */ +struct hwrm_error_recovery_qcfg_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + u8 unused_0[8]; +}; + +/* hwrm_error_recovery_qcfg_output (size:1664b/208B) */ +struct hwrm_error_recovery_qcfg_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le32 flags; + #define ERROR_RECOVERY_QCFG_RESP_FLAGS_HOST 0x1UL + #define ERROR_RECOVERY_QCFG_RESP_FLAGS_CO_CPU 0x2UL + __le32 driver_polling_freq; + __le32 master_func_wait_period; + __le32 normal_func_wait_period; + __le32 master_func_wait_period_after_reset; + __le32 max_bailout_time_after_reset; + __le32 fw_health_status_reg; + #define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_MASK 0x3UL + #define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_SFT 0 + #define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_PCIE_CFG 0x0UL + #define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_GRC 0x1UL + #define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_BAR0 0x2UL + #define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_BAR1 0x3UL + #define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_LAST ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_BAR1 + #define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_MASK 0xfffffffcUL + #define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SFT 2 + __le32 fw_heartbeat_reg; + #define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_MASK 0x3UL + #define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_SFT 0 + #define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_PCIE_CFG 0x0UL + #define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_GRC 0x1UL + #define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_BAR0 0x2UL + #define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_BAR1 0x3UL + #define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_LAST ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_BAR1 + #define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_MASK 0xfffffffcUL + #define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SFT 2 + __le32 fw_reset_cnt_reg; + #define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_MASK 0x3UL + #define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_SFT 0 + #define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_PCIE_CFG 0x0UL + #define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_GRC 0x1UL + #define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_BAR0 0x2UL + #define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_BAR1 0x3UL + #define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_LAST ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_BAR1 + #define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_MASK 0xfffffffcUL + #define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SFT 2 + __le32 reset_inprogress_reg; + #define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_MASK 0x3UL + #define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_SFT 0 + #define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_PCIE_CFG 0x0UL + #define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_GRC 0x1UL + #define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_BAR0 0x2UL + #define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_BAR1 0x3UL + #define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_LAST ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_BAR1 + #define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_MASK 0xfffffffcUL + #define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SFT 2 + __le32 reset_inprogress_reg_mask; + u8 unused_0[3]; + u8 reg_array_cnt; + __le32 reset_reg[16]; + #define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_MASK 0x3UL + #define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_SFT 0 + #define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_PCIE_CFG 0x0UL + #define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_GRC 0x1UL + #define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_BAR0 0x2UL + #define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_BAR1 0x3UL + #define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_LAST ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_BAR1 + #define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_MASK 0xfffffffcUL + #define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SFT 2 + __le32 reset_reg_val[16]; + u8 delay_after_reset[16]; + u8 unused_1[7]; + u8 valid; +}; + /* hwrm_func_drv_if_change_input (size:192b/24B) */ struct hwrm_func_drv_if_change_input { __le16 req_type; @@ -2955,6 +3073,7 @@ struct hwrm_port_phy_qcaps_output { #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100GB 0x800UL #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_10MBHD 0x1000UL #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_10MB 0x2000UL + #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_200GB 0x4000UL __le16 supported_speeds_auto_mode; #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_100MBHD 0x1UL #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_100MB 0x2UL @@ -2970,6 +3089,7 @@ struct hwrm_port_phy_qcaps_output { #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_100GB 0x800UL #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_10MBHD 0x1000UL #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_10MB 0x2000UL + #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_200GB 0x4000UL __le16 supported_speeds_eee_mode; #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_RSVD1 0x1UL #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_100MB 0x2UL @@ -4919,6 +5039,35 @@ struct hwrm_ring_free_output { u8 valid; }; +/* hwrm_ring_reset_input (size:192b/24B) */ +struct hwrm_ring_reset_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + u8 ring_type; + #define RING_RESET_REQ_RING_TYPE_L2_CMPL 0x0UL + #define RING_RESET_REQ_RING_TYPE_TX 0x1UL + #define RING_RESET_REQ_RING_TYPE_RX 0x2UL + #define RING_RESET_REQ_RING_TYPE_ROCE_CMPL 0x3UL + #define RING_RESET_REQ_RING_TYPE_LAST RING_RESET_REQ_RING_TYPE_ROCE_CMPL + u8 unused_0; + __le16 ring_id; + u8 unused_1[4]; +}; + +/* hwrm_ring_reset_output (size:128b/16B) */ +struct hwrm_ring_reset_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 unused_0[4]; + u8 consumer_idx[3]; + u8 valid; +}; + /* hwrm_ring_aggint_qcaps_input (size:128b/16B) */ struct hwrm_ring_aggint_qcaps_input { __le16 req_type; @@ -5446,19 +5595,21 @@ struct hwrm_cfa_encap_record_alloc_input { __le64 resp_addr; __le32 flags; #define CFA_ENCAP_RECORD_ALLOC_REQ_FLAGS_LOOPBACK 0x1UL + #define CFA_ENCAP_RECORD_ALLOC_REQ_FLAGS_EXTERNAL 0x2UL u8 encap_type; - #define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN 0x1UL - #define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_NVGRE 0x2UL - #define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_L2GRE 0x3UL - #define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPIP 0x4UL - #define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_GENEVE 0x5UL - #define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_MPLS 0x6UL - #define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VLAN 0x7UL - #define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPGRE 0x8UL - #define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_V4 0x9UL - #define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPGRE_V1 0xaUL - #define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_L2_ETYPE 0xbUL - #define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_LAST CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_L2_ETYPE + #define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN 0x1UL + #define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_NVGRE 0x2UL + #define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_L2GRE 0x3UL + #define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPIP 0x4UL + #define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_GENEVE 0x5UL + #define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_MPLS 0x6UL + #define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VLAN 0x7UL + #define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPGRE 0x8UL + #define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_V4 0x9UL + #define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPGRE_V1 0xaUL + #define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_L2_ETYPE 0xbUL + #define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_GPE_V6 0xcUL + #define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_LAST CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_GPE_V6 u8 unused_0[3]; __le32 encap_data[20]; }; @@ -5506,6 +5657,7 @@ struct hwrm_cfa_ntuple_filter_alloc_input { #define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_LOOPBACK 0x1UL #define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_DROP 0x2UL #define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_METER 0x4UL + #define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_DEST_FID 0x8UL __le32 enables; #define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_L2_FILTER_ID 0x1UL #define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_ETHERTYPE 0x2UL @@ -5627,7 +5779,8 @@ struct hwrm_cfa_ntuple_filter_cfg_input { #define CFA_NTUPLE_FILTER_CFG_REQ_ENABLES_NEW_DST_ID 0x1UL #define CFA_NTUPLE_FILTER_CFG_REQ_ENABLES_NEW_MIRROR_VNIC_ID 0x2UL #define CFA_NTUPLE_FILTER_CFG_REQ_ENABLES_NEW_METER_INSTANCE_ID 0x4UL - u8 unused_0[4]; + __le32 flags; + #define CFA_NTUPLE_FILTER_CFG_REQ_FLAGS_DEST_FID 0x1UL __le64 ntuple_filter_id; __le32 new_dst_id; __le32 new_mirror_vnic_id; @@ -5892,13 +6045,15 @@ struct hwrm_cfa_flow_info_input { __le64 ext_flow_handle; }; -/* hwrm_cfa_flow_info_output (size:448b/56B) */ +/* hwrm_cfa_flow_info_output (size:5632b/704B) */ struct hwrm_cfa_flow_info_output { __le16 error_code; __le16 req_type; __le16 seq_id; __le16 resp_len; u8 flags; + #define CFA_FLOW_INFO_RESP_FLAGS_PATH_TX 0x1UL + #define CFA_FLOW_INFO_RESP_FLAGS_PATH_RX 0x2UL u8 profile; __le16 src_fid; __le16 dst_fid; @@ -5910,7 +6065,10 @@ struct hwrm_cfa_flow_info_output { __le16 flow_handle; __le32 tunnel_handle; __le16 flow_timer; - u8 unused_0[5]; + u8 unused_0[6]; + __le32 flow_key_data[130]; + __le32 flow_action_info[30]; + u8 unused_1[7]; u8 valid; }; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index d80f5c981d90..2b90a2bb1a1d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -121,6 +121,54 @@ int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting) return rc; } +static int bnxt_hwrm_func_qcfg_flags(struct bnxt *bp, struct bnxt_vf_info *vf) +{ + struct hwrm_func_qcfg_output *resp = bp->hwrm_cmd_resp_addr; + struct hwrm_func_qcfg_input req = {0}; + int rc; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_QCFG, -1, -1); + req.fid = cpu_to_le16(vf->fw_fid); + mutex_lock(&bp->hwrm_cmd_lock); + rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (rc) { + mutex_unlock(&bp->hwrm_cmd_lock); + return -EIO; + } + vf->func_qcfg_flags = le16_to_cpu(resp->flags); + mutex_unlock(&bp->hwrm_cmd_lock); + return 0; +} + +static bool bnxt_is_trusted_vf(struct bnxt *bp, struct bnxt_vf_info *vf) +{ + if (!(bp->fw_cap & BNXT_FW_CAP_TRUSTED_VF)) + return !!(vf->flags & BNXT_VF_TRUST); + + bnxt_hwrm_func_qcfg_flags(bp, vf); + return !!(vf->func_qcfg_flags & FUNC_QCFG_RESP_FLAGS_TRUSTED_VF); +} + +static int bnxt_hwrm_set_trusted_vf(struct bnxt *bp, struct bnxt_vf_info *vf) +{ + struct hwrm_func_cfg_input req = {0}; + int rc; + + if (!(bp->fw_cap & BNXT_FW_CAP_TRUSTED_VF)) + return 0; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); + req.fid = cpu_to_le16(vf->fw_fid); + if (vf->flags & BNXT_VF_TRUST) + req.flags = cpu_to_le32(FUNC_CFG_REQ_FLAGS_TRUSTED_VF_ENABLE); + else + req.flags = cpu_to_le32(FUNC_CFG_REQ_FLAGS_TRUSTED_VF_DISABLE); + rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (rc) + return -EIO; + return 0; +} + int bnxt_set_vf_trust(struct net_device *dev, int vf_id, bool trusted) { struct bnxt *bp = netdev_priv(dev); @@ -135,6 +183,7 @@ int bnxt_set_vf_trust(struct net_device *dev, int vf_id, bool trusted) else vf->flags &= ~BNXT_VF_TRUST; + bnxt_hwrm_set_trusted_vf(bp, vf); return 0; } @@ -164,7 +213,7 @@ int bnxt_get_vf_config(struct net_device *dev, int vf_id, else ivi->qos = 0; ivi->spoofchk = !!(vf->flags & BNXT_VF_SPOOFCHK); - ivi->trusted = !!(vf->flags & BNXT_VF_TRUST); + ivi->trusted = bnxt_is_trusted_vf(bp, vf); if (!(vf->flags & BNXT_VF_LINK_FORCED)) ivi->linkstate = IFLA_VF_LINK_STATE_AUTO; else if (vf->flags & BNXT_VF_LINK_UP) @@ -935,9 +984,10 @@ static int bnxt_vf_configure_mac(struct bnxt *bp, struct bnxt_vf_info *vf) * if the PF assigned MAC address is zero */ if (req->enables & cpu_to_le32(FUNC_VF_CFG_REQ_ENABLES_DFLT_MAC_ADDR)) { + bool trust = bnxt_is_trusted_vf(bp, vf); + if (is_valid_ether_addr(req->dflt_mac_addr) && - ((vf->flags & BNXT_VF_TRUST) || - !is_valid_ether_addr(vf->mac_addr) || + (trust || !is_valid_ether_addr(vf->mac_addr) || ether_addr_equal(req->dflt_mac_addr, vf->mac_addr))) { ether_addr_copy(vf->vf_mac_addr, req->dflt_mac_addr); return bnxt_hwrm_exec_fwd_resp(bp, vf, msg_size); @@ -962,7 +1012,7 @@ static int bnxt_vf_validate_set_mac(struct bnxt *bp, struct bnxt_vf_info *vf) * Otherwise, it must match the VF MAC address if firmware spec >= * 1.2.2 */ - if (vf->flags & BNXT_VF_TRUST) { + if (bnxt_is_trusted_vf(bp, vf)) { mac_ok = true; } else if (is_valid_ether_addr(vf->mac_addr)) { if (ether_addr_equal((const u8 *)req->l2_addr, vf->mac_addr)) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index 61a3457ed71b..44d6c5743fb9 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -1290,7 +1290,7 @@ static int bnxt_tc_add_flow(struct bnxt *bp, u16 src_fid, bnxt_tc_set_flow_dir(bp, flow, src_fid); if (!bnxt_tc_can_offload(bp, flow)) { - rc = -ENOSPC; + rc = -EOPNOTSUPP; goto free_node; } diff --git a/drivers/net/ethernet/broadcom/sb1250-mac.c b/drivers/net/ethernet/broadcom/sb1250-mac.c index 5db9f4158e62..134ae2862efa 100644 --- a/drivers/net/ethernet/broadcom/sb1250-mac.c +++ b/drivers/net/ethernet/broadcom/sb1250-mac.c @@ -1288,7 +1288,7 @@ static void sbdma_tx_process(struct sbmac_softc *sc, struct sbmacdma *d, * for transmits, we just free buffers. */ - dev_kfree_skb_irq(sb); + dev_consume_skb_irq(sb); /* * .. and advance to the next buffer. diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 2b2882615e8b..f2915f2fe21a 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1734,7 +1734,7 @@ static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev) if (!nskb) return -ENOMEM; - dev_kfree_skb_any(*skb); + dev_consume_skb_any(*skb); *skb = nskb; } @@ -3673,9 +3673,9 @@ static netdev_tx_t at91ether_start_xmit(struct sk_buff *skb, /* Store packet information (to free when Tx completed) */ lp->skb = skb; lp->skb_length = skb->len; - lp->skb_physaddr = dma_map_single(NULL, skb->data, skb->len, - DMA_TO_DEVICE); - if (dma_mapping_error(NULL, lp->skb_physaddr)) { + lp->skb_physaddr = dma_map_single(&lp->pdev->dev, skb->data, + skb->len, DMA_TO_DEVICE); + if (dma_mapping_error(&lp->pdev->dev, lp->skb_physaddr)) { dev_kfree_skb_any(skb); dev->stats.tx_dropped++; netdev_err(dev, "%s: DMA mapping error\n", __func__); @@ -3763,9 +3763,9 @@ static irqreturn_t at91ether_interrupt(int irq, void *dev_id) dev->stats.tx_errors++; if (lp->skb) { - dev_kfree_skb_irq(lp->skb); + dev_consume_skb_irq(lp->skb); lp->skb = NULL; - dma_unmap_single(NULL, lp->skb_physaddr, + dma_unmap_single(&lp->pdev->dev, lp->skb_physaddr, lp->skb_length, DMA_TO_DEVICE); dev->stats.tx_packets++; dev->stats.tx_bytes += lp->skb_length; @@ -3943,6 +3943,7 @@ static const struct of_device_id macb_dt_ids[] = { { .compatible = "cdns,np4-macb", .data = &np4_config }, { .compatible = "cdns,pc302-gem", .data = &pc302gem_config }, { .compatible = "cdns,gem", .data = &pc302gem_config }, + { .compatible = "cdns,sam9x60-macb", .data = &at91sam9260_config }, { .compatible = "atmel,sama5d2-gem", .data = &sama5d2_config }, { .compatible = "atmel,sama5d3-gem", .data = &sama5d3_config }, { .compatible = "atmel,sama5d3-macb", .data = &sama5d3macb_config }, diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig index 5f03199a3acf..05f4a3b21e29 100644 --- a/drivers/net/ethernet/cavium/Kconfig +++ b/drivers/net/ethernet/cavium/Kconfig @@ -54,7 +54,6 @@ config CAVIUM_PTP tristate "Cavium PTP coprocessor as PTP clock" depends on 64BIT && PCI imply PTP_1588_CLOCK - default y ---help--- This driver adds support for the Precision Time Protocol Clocks and Timestamping coprocessor (PTP) found on Cavium processors. diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c index 9f4f3c1d5043..43d11c38b38a 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c +++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c @@ -1450,7 +1450,7 @@ void cn23xx_tell_vf_its_macaddr_changed(struct octeon_device *oct, int vfidx, mbox_cmd.recv_len = 0; mbox_cmd.recv_status = 0; mbox_cmd.fn = NULL; - mbox_cmd.fn_arg = 0; + mbox_cmd.fn_arg = NULL; ether_addr_copy(mbox_cmd.msg.s.params, mac); mbox_cmd.q_no = vfidx * oct->sriov_info.rings_per_vf; octeon_mbox_write(oct, &mbox_cmd); diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index e97e6754ee09..9b7819fdc9de 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -2907,7 +2907,7 @@ static int liquidio_set_vf_spoofchk(struct net_device *netdev, int vfidx, nctrl.ncmd.s.param2 = enable; nctrl.ncmd.s.more = 0; nctrl.iq_no = lio->linfo.txpciq[0].s.q_no; - nctrl.cb_fn = 0; + nctrl.cb_fn = NULL; retval = octnet_send_nic_ctrl_pkt(oct, &nctrl); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 568715a13b5c..b7b0eb104430 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -617,6 +617,7 @@ enum { /* adapter flags */ FW_OFLD_CONN = (1 << 9), ROOT_NO_RELAXED_ORDERING = (1 << 10), SHUTTING_DOWN = (1 << 11), + SGE_DBQ_TIMER = (1 << 12), }; enum { @@ -756,6 +757,8 @@ struct sge_eth_txq { /* state for an SGE Ethernet Tx queue */ #ifdef CONFIG_CHELSIO_T4_DCB u8 dcb_prio; /* DCB Priority bound to queue */ #endif + u8 dbqt; /* SGE Doorbell Queue Timer in use */ + unsigned int dbqtimerix; /* SGE Doorbell Queue Timer Index */ unsigned long tso; /* # of TSO requests */ unsigned long tx_cso; /* # of Tx checksum offloads */ unsigned long vlan_ins; /* # of Tx VLAN insertions */ @@ -816,6 +819,8 @@ struct sge { u16 nqs_per_uld; /* # of Rx queues per ULD */ u16 timer_val[SGE_NTIMERS]; u8 counter_val[SGE_NCOUNTERS]; + u16 dbqtimer_tick; + u16 dbqtimer_val[SGE_NDBQTIMERS]; u32 fl_pg_order; /* large page allocation size */ u32 stat_len; /* length of status page at ring end */ u32 pktshift; /* padding between CPL & packet data */ @@ -1402,7 +1407,7 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq, rspq_flush_handler_t flush_handler, int cong); int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq, struct net_device *dev, struct netdev_queue *netdevq, - unsigned int iqid); + unsigned int iqid, u8 dbqt); int t4_sge_alloc_ctrl_txq(struct adapter *adap, struct sge_ctrl_txq *txq, struct net_device *dev, unsigned int iqid, unsigned int cmplqid); @@ -1415,6 +1420,8 @@ irqreturn_t t4_sge_intr_msix(int irq, void *cookie); int t4_sge_init(struct adapter *adap); void t4_sge_start(struct adapter *adap); void t4_sge_stop(struct adapter *adap); +int t4_sge_eth_txq_egress_update(struct adapter *adap, struct sge_eth_txq *q, + int maxreclaim); void cxgb4_set_ethtool_ops(struct net_device *netdev); int cxgb4_write_rss(const struct port_info *pi, const u16 *queues); enum cpl_tx_tnl_lso_type cxgb_encap_offload_supported(struct sk_buff *skb); @@ -1821,6 +1828,8 @@ int t4_ctrl_eq_free(struct adapter *adap, unsigned int mbox, unsigned int pf, int t4_ofld_eq_free(struct adapter *adap, unsigned int mbox, unsigned int pf, unsigned int vf, unsigned int eqid); int t4_sge_ctxt_flush(struct adapter *adap, unsigned int mbox, int ctxt_type); +int t4_read_sge_dbqtimers(struct adapter *adap, unsigned int ndbqtimers, + u16 *dbqtimers); void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl); int t4_update_port_info(struct port_info *pi); int t4_get_link_params(struct port_info *pi, unsigned int *link_okp, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index 796043544fc3..65b8dc706c1d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -932,11 +932,190 @@ static int get_adaptive_rx_setting(struct net_device *dev) return q->rspq.adaptive_rx; } -static int set_coalesce(struct net_device *dev, struct ethtool_coalesce *c) +/* Return the current global Adapter SGE Doorbell Queue Timer Tick for all + * Ethernet TX Queues. + */ +static int get_dbqtimer_tick(struct net_device *dev) +{ + struct port_info *pi = netdev_priv(dev); + struct adapter *adap = pi->adapter; + + if (!(adap->flags & SGE_DBQ_TIMER)) + return 0; + + return adap->sge.dbqtimer_tick; +} + +/* Return the SGE Doorbell Queue Timer Value for the Ethernet TX Queues + * associated with a Network Device. + */ +static int get_dbqtimer(struct net_device *dev) +{ + struct port_info *pi = netdev_priv(dev); + struct adapter *adap = pi->adapter; + struct sge_eth_txq *txq; + + txq = &adap->sge.ethtxq[pi->first_qset]; + + if (!(adap->flags & SGE_DBQ_TIMER)) + return 0; + + /* all of the TX Queues use the same Timer Index */ + return adap->sge.dbqtimer_val[txq->dbqtimerix]; +} + +/* Set the global Adapter SGE Doorbell Queue Timer Tick for all Ethernet TX + * Queues. This is the fundamental "Tick" that sets the scale of values which + * can be used. Individual Ethernet TX Queues index into a relatively small + * array of Tick Multipliers. Changing the base Tick will thus change all of + * the resulting Timer Values associated with those multipliers for all + * Ethernet TX Queues. + */ +static int set_dbqtimer_tick(struct net_device *dev, int usecs) +{ + struct port_info *pi = netdev_priv(dev); + struct adapter *adap = pi->adapter; + struct sge *s = &adap->sge; + u32 param, val; + int ret; + + if (!(adap->flags & SGE_DBQ_TIMER)) + return 0; + + /* return early if it's the same Timer Tick we're already using */ + if (s->dbqtimer_tick == usecs) + return 0; + + /* attempt to set the new Timer Tick value */ + param = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) | + FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_DBQ_TIMERTICK)); + val = usecs; + ret = t4_set_params(adap, adap->mbox, adap->pf, 0, 1, ¶m, &val); + if (ret) + return ret; + s->dbqtimer_tick = usecs; + + /* if successful, reread resulting dependent Timer values */ + ret = t4_read_sge_dbqtimers(adap, ARRAY_SIZE(s->dbqtimer_val), + s->dbqtimer_val); + return ret; +} + +/* Set the SGE Doorbell Queue Timer Value for the Ethernet TX Queues + * associated with a Network Device. There is a relatively small array of + * possible Timer Values so we need to pick the closest value available. + */ +static int set_dbqtimer(struct net_device *dev, int usecs) +{ + int qix, timerix, min_timerix, delta, min_delta; + struct port_info *pi = netdev_priv(dev); + struct adapter *adap = pi->adapter; + struct sge *s = &adap->sge; + struct sge_eth_txq *txq; + u32 param, val; + int ret; + + if (!(adap->flags & SGE_DBQ_TIMER)) + return 0; + + /* Find the SGE Doorbell Timer Value that's closest to the requested + * value. + */ + min_delta = INT_MAX; + min_timerix = 0; + for (timerix = 0; timerix < ARRAY_SIZE(s->dbqtimer_val); timerix++) { + delta = s->dbqtimer_val[timerix] - usecs; + if (delta < 0) + delta = -delta; + if (delta < min_delta) { + min_delta = delta; + min_timerix = timerix; + } + } + + /* Return early if it's the same Timer Index we're already using. + * We use the same Timer Index for all of the TX Queues for an + * interface so it's only necessary to check the first one. + */ + txq = &s->ethtxq[pi->first_qset]; + if (txq->dbqtimerix == min_timerix) + return 0; + + for (qix = 0; qix < pi->nqsets; qix++, txq++) { + if (adap->flags & FULL_INIT_DONE) { + param = + (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DMAQ) | + FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DMAQ_EQ_TIMERIX) | + FW_PARAMS_PARAM_YZ_V(txq->q.cntxt_id)); + val = min_timerix; + ret = t4_set_params(adap, adap->mbox, adap->pf, 0, + 1, ¶m, &val); + if (ret) + return ret; + } + txq->dbqtimerix = min_timerix; + } + return 0; +} + +/* Set the global Adapter SGE Doorbell Queue Timer Tick for all Ethernet TX + * Queues and the Timer Value for the Ethernet TX Queues associated with a + * Network Device. Since changing the global Tick changes all of the + * available Timer Values, we need to do this first before selecting the + * resulting closest Timer Value. Moreover, since the Tick is global, + * changing it affects the Timer Values for all Network Devices on the + * adapter. So, before changing the Tick, we grab all of the current Timer + * Values for other Network Devices on this Adapter and then attempt to select + * new Timer Values which are close to the old values ... + */ +static int set_dbqtimer_tickval(struct net_device *dev, + int tick_usecs, int timer_usecs) +{ + struct port_info *pi = netdev_priv(dev); + struct adapter *adap = pi->adapter; + int timer[MAX_NPORTS]; + unsigned int port; + int ret; + + /* Grab the other adapter Network Interface current timers and fill in + * the new one for this Network Interface. + */ + for_each_port(adap, port) + if (port == pi->port_id) + timer[port] = timer_usecs; + else + timer[port] = get_dbqtimer(adap->port[port]); + + /* Change the global Tick first ... */ + ret = set_dbqtimer_tick(dev, tick_usecs); + if (ret) + return ret; + + /* ... and then set all of the Network Interface Timer Values ... */ + for_each_port(adap, port) { + ret = set_dbqtimer(adap->port[port], timer[port]); + if (ret) + return ret; + } + + return 0; +} + +static int set_coalesce(struct net_device *dev, + struct ethtool_coalesce *coalesce) { - set_adaptive_rx_setting(dev, c->use_adaptive_rx_coalesce); - return set_rx_intr_params(dev, c->rx_coalesce_usecs, - c->rx_max_coalesced_frames); + int ret; + + set_adaptive_rx_setting(dev, coalesce->use_adaptive_rx_coalesce); + + ret = set_rx_intr_params(dev, coalesce->rx_coalesce_usecs, + coalesce->rx_max_coalesced_frames); + if (ret) + return ret; + + return set_dbqtimer_tickval(dev, + coalesce->tx_coalesce_usecs_irq, + coalesce->tx_coalesce_usecs); } static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c) @@ -949,6 +1128,8 @@ static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c) c->rx_max_coalesced_frames = (rq->intr_params & QINTR_CNT_EN_F) ? adap->sge.counter_val[rq->pktcnt_idx] : 0; c->use_adaptive_rx_coalesce = get_adaptive_rx_setting(dev); + c->tx_coalesce_usecs_irq = get_dbqtimer_tick(dev); + c->tx_coalesce_usecs = get_dbqtimer(dev); return 0; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index adf75d16e6d3..bcbac247a73d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -575,7 +575,7 @@ static int fwevtq_handler(struct sge_rspq *q, const __be64 *rsp, struct sge_eth_txq *eq; eq = container_of(txq, struct sge_eth_txq, q); - netif_tx_wake_queue(eq->txq); + t4_sge_eth_txq_egress_update(q->adap, eq, -1); } else { struct sge_uld_txq *oq; @@ -933,10 +933,13 @@ static int setup_sge_queues(struct adapter *adap) q->rspq.idx = j; memset(&q->stats, 0, sizeof(q->stats)); } - for (j = 0; j < pi->nqsets; j++, t++) { + + q = &s->ethrxq[pi->first_qset]; + for (j = 0; j < pi->nqsets; j++, t++, q++) { err = t4_sge_alloc_eth_txq(adap, t, dev, netdev_get_tx_queue(dev, j), - s->fw_evtq.cntxt_id); + q->rspq.cntxt_id, + !!(adap->flags & SGE_DBQ_TIMER)); if (err) goto freeout; } @@ -958,7 +961,7 @@ static int setup_sge_queues(struct adapter *adap) if (!is_t4(adap->params.chip)) { err = t4_sge_alloc_eth_txq(adap, &s->ptptxq, adap->port[0], netdev_get_tx_queue(adap->port[0], 0) - , s->fw_evtq.cntxt_id); + , s->fw_evtq.cntxt_id, false); if (err) goto freeout; } @@ -4325,6 +4328,24 @@ static int adap_init0(struct adapter *adap) if (ret < 0) goto bye; + /* Grab the SGE Doorbell Queue Timer values. If successful, that + * indicates that the Firmware and Hardware support this. + */ + params[0] = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) | + FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_DBQ_TIMERTICK)); + ret = t4_query_params(adap, adap->mbox, adap->pf, 0, + 1, params, val); + + if (!ret) { + adap->sge.dbqtimer_tick = val[0]; + ret = t4_read_sge_dbqtimers(adap, + ARRAY_SIZE(adap->sge.dbqtimer_val), + adap->sge.dbqtimer_val); + } + + if (!ret) + adap->flags |= SGE_DBQ_TIMER; + if (is_bypass_device(adap->pdev->device)) adap->params.bypass = 1; diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index fc0bc6458e84..f18493fb32aa 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -80,9 +80,10 @@ * Max number of Tx descriptors we clean up at a time. Should be modest as * freeing skbs isn't cheap and it happens while holding locks. We just need * to free packets faster than they arrive, we eventually catch up and keep - * the amortized cost reasonable. Must be >= 2 * TXQ_STOP_THRES. + * the amortized cost reasonable. Must be >= 2 * TXQ_STOP_THRES. It should + * also match the CIDX Flush Threshold. */ -#define MAX_TX_RECLAIM 16 +#define MAX_TX_RECLAIM 32 /* * Max number of Rx buffers we replenish at a time. Again keep this modest, @@ -401,31 +402,52 @@ static inline int reclaimable(const struct sge_txq *q) } /** - * cxgb4_reclaim_completed_tx - reclaims completed Tx descriptors + * reclaim_completed_tx - reclaims completed TX Descriptors * @adap: the adapter * @q: the Tx queue to reclaim completed descriptors from + * @maxreclaim: the maximum number of TX Descriptors to reclaim or -1 * @unmap: whether the buffers should be unmapped for DMA * - * Reclaims Tx descriptors that the SGE has indicated it has processed, - * and frees the associated buffers if possible. Called with the Tx - * queue locked. + * Reclaims Tx Descriptors that the SGE has indicated it has processed, + * and frees the associated buffers if possible. If @max == -1, then + * we'll use a defaiult maximum. Called with the TX Queue locked. */ -inline void cxgb4_reclaim_completed_tx(struct adapter *adap, struct sge_txq *q, - bool unmap) +static inline int reclaim_completed_tx(struct adapter *adap, struct sge_txq *q, + int maxreclaim, bool unmap) { - int avail = reclaimable(q); + int reclaim = reclaimable(q); - if (avail) { + if (reclaim) { /* * Limit the amount of clean up work we do at a time to keep * the Tx lock hold time O(1). */ - if (avail > MAX_TX_RECLAIM) - avail = MAX_TX_RECLAIM; + if (maxreclaim < 0) + maxreclaim = MAX_TX_RECLAIM; + if (reclaim > maxreclaim) + reclaim = maxreclaim; - free_tx_desc(adap, q, avail, unmap); - q->in_use -= avail; + free_tx_desc(adap, q, reclaim, unmap); + q->in_use -= reclaim; } + + return reclaim; +} + +/** + * cxgb4_reclaim_completed_tx - reclaims completed Tx descriptors + * @adap: the adapter + * @q: the Tx queue to reclaim completed descriptors from + * @unmap: whether the buffers should be unmapped for DMA + * + * Reclaims Tx descriptors that the SGE has indicated it has processed, + * and frees the associated buffers if possible. Called with the Tx + * queue locked. + */ +void cxgb4_reclaim_completed_tx(struct adapter *adap, struct sge_txq *q, + bool unmap) +{ + (void)reclaim_completed_tx(adap, q, -1, unmap); } EXPORT_SYMBOL(cxgb4_reclaim_completed_tx); @@ -1288,6 +1310,44 @@ static inline void t6_fill_tnl_lso(struct sk_buff *skb, } /** + * t4_sge_eth_txq_egress_update - handle Ethernet TX Queue update + * @adap: the adapter + * @eq: the Ethernet TX Queue + * @maxreclaim: the maximum number of TX Descriptors to reclaim or -1 + * + * We're typically called here to update the state of an Ethernet TX + * Queue with respect to the hardware's progress in consuming the TX + * Work Requests that we've put on that Egress Queue. This happens + * when we get Egress Queue Update messages and also prophylactically + * in regular timer-based Ethernet TX Queue maintenance. + */ +int t4_sge_eth_txq_egress_update(struct adapter *adap, struct sge_eth_txq *eq, + int maxreclaim) +{ + struct sge_txq *q = &eq->q; + unsigned int reclaimed; + + if (!q->in_use || !__netif_tx_trylock(eq->txq)) + return 0; + + /* Reclaim pending completed TX Descriptors. */ + reclaimed = reclaim_completed_tx(adap, &eq->q, maxreclaim, true); + + /* If the TX Queue is currently stopped and there's now more than half + * the queue available, restart it. Otherwise bail out since the rest + * of what we want do here is with the possibility of shipping any + * currently buffered Coalesced TX Work Request. + */ + if (netif_tx_queue_stopped(eq->txq) && txq_avail(q) > (q->size / 2)) { + netif_tx_wake_queue(eq->txq); + eq->q.restarts++; + } + + __netif_tx_unlock(eq->txq); + return reclaimed; +} + +/** * cxgb4_eth_xmit - add a packet to an Ethernet Tx queue * @skb: the packet * @dev: the egress net device @@ -1357,7 +1417,7 @@ out_free: dev_kfree_skb_any(skb); } skb_tx_timestamp(skb); - cxgb4_reclaim_completed_tx(adap, &q->q, true); + reclaim_completed_tx(adap, &q->q, -1, true); cntrl = TXPKT_L4CSUM_DIS_F | TXPKT_IPCSUM_DIS_F; #ifdef CONFIG_CHELSIO_T4_FCOE @@ -1400,8 +1460,25 @@ out_free: dev_kfree_skb_any(skb); wr_mid = FW_WR_LEN16_V(DIV_ROUND_UP(flits, 2)); if (unlikely(credits < ETHTXQ_STOP_THRES)) { + /* After we're done injecting the Work Request for this + * packet, we'll be below our "stop threshold" so stop the TX + * Queue now and schedule a request for an SGE Egress Queue + * Update message. The queue will get started later on when + * the firmware processes this Work Request and sends us an + * Egress Queue Status Update message indicating that space + * has opened up. + */ eth_txq_stop(q); - wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F; + + /* If we're using the SGE Doorbell Queue Timer facility, we + * don't need to ask the Firmware to send us Egress Queue CIDX + * Updates: the Hardware will do this automatically. And + * since we send the Ingress Queue CIDX Updates to the + * corresponding Ethernet Response Queue, we'll get them very + * quickly. + */ + if (!q->dbqt) + wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F; } wr = (void *)&q->q.desc[q->q.pidx]; @@ -1671,7 +1748,7 @@ static netdev_tx_t cxgb4_vf_eth_xmit(struct sk_buff *skb, /* Take this opportunity to reclaim any TX Descriptors whose DMA * transfers have completed. */ - cxgb4_reclaim_completed_tx(adapter, &txq->q, true); + reclaim_completed_tx(adapter, &txq->q, -1, true); /* Calculate the number of flits and TX Descriptors we're going to * need along with how many TX Descriptors will be left over after @@ -1715,7 +1792,16 @@ static netdev_tx_t cxgb4_vf_eth_xmit(struct sk_buff *skb, * has opened up. */ eth_txq_stop(txq); - wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F; + + /* If we're using the SGE Doorbell Queue Timer facility, we + * don't need to ask the Firmware to send us Egress Queue CIDX + * Updates: the Hardware will do this automatically. And + * since we send the Ingress Queue CIDX Updates to the + * corresponding Ethernet Response Queue, we'll get them very + * quickly. + */ + if (!txq->dbqt) + wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F; } /* Start filling in our Work Request. Note that we do _not_ handle @@ -2794,6 +2880,74 @@ static int t4_tx_hststamp(struct adapter *adapter, struct sk_buff *skb, } /** + * t4_tx_completion_handler - handle CPL_SGE_EGR_UPDATE messages + * @rspq: Ethernet RX Response Queue associated with Ethernet TX Queue + * @rsp: Response Entry pointer into Response Queue + * @gl: Gather List pointer + * + * For adapters which support the SGE Doorbell Queue Timer facility, + * we configure the Ethernet TX Queues to send CIDX Updates to the + * Associated Ethernet RX Response Queue with CPL_SGE_EGR_UPDATE + * messages. This adds a small load to PCIe Link RX bandwidth and, + * potentially, higher CPU Interrupt load, but allows us to respond + * much more quickly to the CIDX Updates. This is important for + * Upper Layer Software which isn't willing to have a large amount + * of TX Data outstanding before receiving DMA Completions. + */ +static void t4_tx_completion_handler(struct sge_rspq *rspq, + const __be64 *rsp, + const struct pkt_gl *gl) +{ + u8 opcode = ((const struct rss_header *)rsp)->opcode; + struct port_info *pi = netdev_priv(rspq->netdev); + struct adapter *adapter = rspq->adap; + struct sge *s = &adapter->sge; + struct sge_eth_txq *txq; + + /* skip RSS header */ + rsp++; + + /* FW can send EGR_UPDATEs encapsulated in a CPL_FW4_MSG. + */ + if (unlikely(opcode == CPL_FW4_MSG && + ((const struct cpl_fw4_msg *)rsp)->type == + FW_TYPE_RSSCPL)) { + rsp++; + opcode = ((const struct rss_header *)rsp)->opcode; + rsp++; + } + + if (unlikely(opcode != CPL_SGE_EGR_UPDATE)) { + pr_info("%s: unexpected FW4/CPL %#x on Rx queue\n", + __func__, opcode); + return; + } + + txq = &s->ethtxq[pi->first_qset + rspq->idx]; + + /* We've got the Hardware Consumer Index Update in the Egress Update + * message. If we're using the SGE Doorbell Queue Timer mechanism, + * these Egress Update messages will be our sole CIDX Updates we get + * since we don't want to chew up PCIe bandwidth for both Ingress + * Messages and Status Page writes. However, The code which manages + * reclaiming successfully DMA'ed TX Work Requests uses the CIDX value + * stored in the Status Page at the end of the TX Queue. It's easiest + * to simply copy the CIDX Update value from the Egress Update message + * to the Status Page. Also note that no Endian issues need to be + * considered here since both are Big Endian and we're just copying + * bytes consistently ... + */ + if (txq->dbqt) { + struct cpl_sge_egr_update *egr; + + egr = (struct cpl_sge_egr_update *)rsp; + WRITE_ONCE(txq->q.stat->cidx, egr->cidx); + } + + t4_sge_eth_txq_egress_update(adapter, txq, -1); +} + +/** * t4_ethrx_handler - process an ingress ethernet packet * @q: the response queue that received the packet * @rsp: the response queue descriptor holding the RX_PKT message @@ -2816,6 +2970,15 @@ int t4_ethrx_handler(struct sge_rspq *q, const __be64 *rsp, struct port_info *pi; int ret = 0; + /* If we're looking at TX Queue CIDX Update, handle that separately + * and return. + */ + if (unlikely((*(u8 *)rsp == CPL_FW4_MSG) || + (*(u8 *)rsp == CPL_SGE_EGR_UPDATE))) { + t4_tx_completion_handler(q, rsp, si); + return 0; + } + if (unlikely(*(u8 *)rsp == cpl_trace_pkt)) return handle_trace_pkt(q->adap, si); @@ -3289,10 +3452,10 @@ done: static void sge_tx_timer_cb(struct timer_list *t) { - unsigned long m; - unsigned int i, budget; struct adapter *adap = from_timer(adap, t, sge.tx_timer); struct sge *s = &adap->sge; + unsigned long m, period; + unsigned int i, budget; for (i = 0; i < BITS_TO_LONGS(s->egr_sz); i++) for (m = s->txq_maperr[i]; m; m &= m - 1) { @@ -3320,29 +3483,29 @@ static void sge_tx_timer_cb(struct timer_list *t) budget = MAX_TIMER_TX_RECLAIM; i = s->ethtxq_rover; do { - struct sge_eth_txq *q = &s->ethtxq[i]; - - if (q->q.in_use && - time_after_eq(jiffies, q->txq->trans_start + HZ / 100) && - __netif_tx_trylock(q->txq)) { - int avail = reclaimable(&q->q); - - if (avail) { - if (avail > budget) - avail = budget; - - free_tx_desc(adap, &q->q, avail, true); - q->q.in_use -= avail; - budget -= avail; - } - __netif_tx_unlock(q->txq); - } + budget -= t4_sge_eth_txq_egress_update(adap, &s->ethtxq[i], + budget); + if (!budget) + break; if (++i >= s->ethqsets) i = 0; - } while (budget && i != s->ethtxq_rover); + } while (i != s->ethtxq_rover); s->ethtxq_rover = i; - mod_timer(&s->tx_timer, jiffies + (budget ? TX_QCHECK_PERIOD : 2)); + + if (budget == 0) { + /* If we found too many reclaimable packets schedule a timer + * in the near future to continue where we left off. + */ + period = 2; + } else { + /* We reclaimed all reclaimable TX Descriptors, so reschedule + * at the normal period. + */ + period = TX_QCHECK_PERIOD; + } + + mod_timer(&s->tx_timer, jiffies + period); } /** @@ -3421,7 +3584,8 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq, : FW_IQ_IQTYPE_OFLD)); if (fl) { - enum chip_type chip = CHELSIO_CHIP_VERSION(adap->params.chip); + unsigned int chip_ver = + CHELSIO_CHIP_VERSION(adap->params.chip); /* Allocate the ring for the hardware free list (with space * for its status page) along with the associated software @@ -3459,10 +3623,10 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq, * the smaller 64-byte value there). */ c.fl0dcaen_to_fl0cidxfthresh = - htons(FW_IQ_CMD_FL0FBMIN_V(chip <= CHELSIO_T5 ? + htons(FW_IQ_CMD_FL0FBMIN_V(chip_ver <= CHELSIO_T5 ? FETCHBURSTMIN_128B_X : - FETCHBURSTMIN_64B_X) | - FW_IQ_CMD_FL0FBMAX_V((chip <= CHELSIO_T5) ? + FETCHBURSTMIN_64B_T6_X) | + FW_IQ_CMD_FL0FBMAX_V((chip_ver <= CHELSIO_T5) ? FETCHBURSTMAX_512B_X : FETCHBURSTMAX_256B_X)); c.fl0size = htons(flsz); @@ -3584,14 +3748,24 @@ static void init_txq(struct adapter *adap, struct sge_txq *q, unsigned int id) adap->sge.egr_map[id - adap->sge.egr_start] = q; } +/** + * t4_sge_alloc_eth_txq - allocate an Ethernet TX Queue + * @adap: the adapter + * @txq: the SGE Ethernet TX Queue to initialize + * @dev: the Linux Network Device + * @netdevq: the corresponding Linux TX Queue + * @iqid: the Ingress Queue to which to deliver CIDX Update messages + * @dbqt: whether this TX Queue will use the SGE Doorbell Queue Timers + */ int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq, struct net_device *dev, struct netdev_queue *netdevq, - unsigned int iqid) + unsigned int iqid, u8 dbqt) { - int ret, nentries; - struct fw_eq_eth_cmd c; - struct sge *s = &adap->sge; + unsigned int chip_ver = CHELSIO_CHIP_VERSION(adap->params.chip); struct port_info *pi = netdev_priv(dev); + struct sge *s = &adap->sge; + struct fw_eq_eth_cmd c; + int ret, nentries; /* Add status entries */ nentries = txq->q.size + s->stat_len / sizeof(struct tx_desc); @@ -3610,19 +3784,47 @@ int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq, FW_EQ_ETH_CMD_VFN_V(0)); c.alloc_to_len16 = htonl(FW_EQ_ETH_CMD_ALLOC_F | FW_EQ_ETH_CMD_EQSTART_F | FW_LEN16(c)); - c.viid_pkd = htonl(FW_EQ_ETH_CMD_AUTOEQUEQE_F | - FW_EQ_ETH_CMD_VIID_V(pi->viid)); + + /* For TX Ethernet Queues using the SGE Doorbell Queue Timer + * mechanism, we use Ingress Queue messages for Hardware Consumer + * Index Updates on the TX Queue. Otherwise we have the Hardware + * write the CIDX Updates into the Status Page at the end of the + * TX Queue. + */ + c.autoequiqe_to_viid = htonl((dbqt + ? FW_EQ_ETH_CMD_AUTOEQUIQE_F + : FW_EQ_ETH_CMD_AUTOEQUEQE_F) | + FW_EQ_ETH_CMD_VIID_V(pi->viid)); + c.fetchszm_to_iqid = - htonl(FW_EQ_ETH_CMD_HOSTFCMODE_V(HOSTFCMODE_STATUS_PAGE_X) | + htonl(FW_EQ_ETH_CMD_HOSTFCMODE_V(dbqt + ? HOSTFCMODE_INGRESS_QUEUE_X + : HOSTFCMODE_STATUS_PAGE_X) | FW_EQ_ETH_CMD_PCIECHN_V(pi->tx_chan) | FW_EQ_ETH_CMD_FETCHRO_F | FW_EQ_ETH_CMD_IQID_V(iqid)); + + /* Note that the CIDX Flush Threshold should match MAX_TX_RECLAIM. */ c.dcaen_to_eqsize = - htonl(FW_EQ_ETH_CMD_FBMIN_V(FETCHBURSTMIN_64B_X) | + htonl(FW_EQ_ETH_CMD_FBMIN_V(chip_ver <= CHELSIO_T5 + ? FETCHBURSTMIN_64B_X + : FETCHBURSTMIN_64B_T6_X) | FW_EQ_ETH_CMD_FBMAX_V(FETCHBURSTMAX_512B_X) | FW_EQ_ETH_CMD_CIDXFTHRESH_V(CIDXFLUSHTHRESH_32_X) | FW_EQ_ETH_CMD_EQSIZE_V(nentries)); + c.eqaddr = cpu_to_be64(txq->q.phys_addr); + /* If we're using the SGE Doorbell Queue Timer mechanism, pass in the + * currently configured Timer Index. THis can be changed later via an + * ethtool -C tx-usecs {Timer Val} command. Note that the SGE + * Doorbell Queue mode is currently automatically enabled in the + * Firmware by setting either AUTOEQUEQE or AUTOEQUIQE ... + */ + if (dbqt) + c.timeren_timerix = + cpu_to_be32(FW_EQ_ETH_CMD_TIMEREN_F | + FW_EQ_ETH_CMD_TIMERIX_V(txq->dbqtimerix)); + ret = t4_wr_mbox(adap, adap->mbox, &c, sizeof(c), &c); if (ret) { kfree(txq->q.sdesc); @@ -3639,6 +3841,8 @@ int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq, txq->txq = netdevq; txq->tso = txq->tx_cso = txq->vlan_ins = 0; txq->mapping_err = 0; + txq->dbqt = dbqt; + return 0; } @@ -3646,10 +3850,11 @@ int t4_sge_alloc_ctrl_txq(struct adapter *adap, struct sge_ctrl_txq *txq, struct net_device *dev, unsigned int iqid, unsigned int cmplqid) { - int ret, nentries; - struct fw_eq_ctrl_cmd c; - struct sge *s = &adap->sge; + unsigned int chip_ver = CHELSIO_CHIP_VERSION(adap->params.chip); struct port_info *pi = netdev_priv(dev); + struct sge *s = &adap->sge; + struct fw_eq_ctrl_cmd c; + int ret, nentries; /* Add status entries */ nentries = txq->q.size + s->stat_len / sizeof(struct tx_desc); @@ -3673,7 +3878,9 @@ int t4_sge_alloc_ctrl_txq(struct adapter *adap, struct sge_ctrl_txq *txq, FW_EQ_CTRL_CMD_PCIECHN_V(pi->tx_chan) | FW_EQ_CTRL_CMD_FETCHRO_F | FW_EQ_CTRL_CMD_IQID_V(iqid)); c.dcaen_to_eqsize = - htonl(FW_EQ_CTRL_CMD_FBMIN_V(FETCHBURSTMIN_64B_X) | + htonl(FW_EQ_CTRL_CMD_FBMIN_V(chip_ver <= CHELSIO_T5 + ? FETCHBURSTMIN_64B_X + : FETCHBURSTMIN_64B_T6_X) | FW_EQ_CTRL_CMD_FBMAX_V(FETCHBURSTMAX_512B_X) | FW_EQ_CTRL_CMD_CIDXFTHRESH_V(CIDXFLUSHTHRESH_32_X) | FW_EQ_CTRL_CMD_EQSIZE_V(nentries)); @@ -3713,6 +3920,7 @@ int t4_sge_alloc_uld_txq(struct adapter *adap, struct sge_uld_txq *txq, struct net_device *dev, unsigned int iqid, unsigned int uld_type) { + unsigned int chip_ver = CHELSIO_CHIP_VERSION(adap->params.chip); int ret, nentries; struct fw_eq_ofld_cmd c; struct sge *s = &adap->sge; @@ -3743,7 +3951,9 @@ int t4_sge_alloc_uld_txq(struct adapter *adap, struct sge_uld_txq *txq, FW_EQ_OFLD_CMD_PCIECHN_V(pi->tx_chan) | FW_EQ_OFLD_CMD_FETCHRO_F | FW_EQ_OFLD_CMD_IQID_V(iqid)); c.dcaen_to_eqsize = - htonl(FW_EQ_OFLD_CMD_FBMIN_V(FETCHBURSTMIN_64B_X) | + htonl(FW_EQ_OFLD_CMD_FBMIN_V(chip_ver <= CHELSIO_T5 + ? FETCHBURSTMIN_64B_X + : FETCHBURSTMIN_64B_T6_X) | FW_EQ_OFLD_CMD_FBMAX_V(FETCHBURSTMAX_512B_X) | FW_EQ_OFLD_CMD_CIDXFTHRESH_V(CIDXFLUSHTHRESH_32_X) | FW_EQ_OFLD_CMD_EQSIZE_V(nentries)); diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index c5e5466ee38b..49e4374d584c 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -4962,7 +4962,13 @@ static void pl_intr_handler(struct adapter *adap) */ int t4_slow_intr_handler(struct adapter *adapter) { - u32 cause = t4_read_reg(adapter, PL_INT_CAUSE_A); + /* There are rare cases where a PL_INT_CAUSE bit may end up getting + * set when the corresponding PL_INT_ENABLE bit isn't set. It's + * easiest just to mask that case here. + */ + u32 raw_cause = t4_read_reg(adapter, PL_INT_CAUSE_A); + u32 enable = t4_read_reg(adapter, PL_INT_ENABLE_A); + u32 cause = raw_cause & enable; if (!(cause & GLBL_INTR_MASK)) return 0; @@ -5014,7 +5020,7 @@ int t4_slow_intr_handler(struct adapter *adapter) ulptx_intr_handler(adapter); /* Clear the interrupts just processed for which we are the master. */ - t4_write_reg(adapter, PL_INT_CAUSE_A, cause & GLBL_INTR_MASK); + t4_write_reg(adapter, PL_INT_CAUSE_A, raw_cause & GLBL_INTR_MASK); (void)t4_read_reg(adapter, PL_INT_CAUSE_A); /* flush */ return 1; } @@ -6713,6 +6719,47 @@ int t4_sge_ctxt_flush(struct adapter *adap, unsigned int mbox, int ctxt_type) } /** + * t4_read_sge_dbqtimers - reag SGE Doorbell Queue Timer values + * @adap - the adapter + * @ndbqtimers: size of the provided SGE Doorbell Queue Timer table + * @dbqtimers: SGE Doorbell Queue Timer table + * + * Reads the SGE Doorbell Queue Timer values into the provided table. + * Returns 0 on success (Firmware and Hardware support this feature), + * an error on failure. + */ +int t4_read_sge_dbqtimers(struct adapter *adap, unsigned int ndbqtimers, + u16 *dbqtimers) +{ + int ret, dbqtimerix; + + ret = 0; + dbqtimerix = 0; + while (dbqtimerix < ndbqtimers) { + int nparams, param; + u32 params[7], vals[7]; + + nparams = ndbqtimers - dbqtimerix; + if (nparams > ARRAY_SIZE(params)) + nparams = ARRAY_SIZE(params); + + for (param = 0; param < nparams; param++) + params[param] = + (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) | + FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_DBQ_TIMER) | + FW_PARAMS_PARAM_Y_V(dbqtimerix + param)); + ret = t4_query_params(adap, adap->mbox, adap->pf, 0, + nparams, params, vals); + if (ret) + break; + + for (param = 0; param < nparams; param++) + dbqtimers[dbqtimerix++] = vals[param]; + } + return ret; +} + +/** * t4_fw_hello - establish communication with FW * @adap: the adapter * @mbox: mailbox to use for the FW command diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h index 361d5032c288..002fc62ea726 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h @@ -91,6 +91,7 @@ enum { SGE_CTXT_SIZE = 24, /* size of SGE context */ SGE_NTIMERS = 6, /* # of interrupt holdoff timer values */ SGE_NCOUNTERS = 4, /* # of interrupt packet counter values */ + SGE_NDBQTIMERS = 8, /* # of Doorbell Queue Timer values */ SGE_MAX_IQ_SIZE = 65520, SGE_TIMER_RSTRT_CNTR = 6, /* restart RX packet threshold counter */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_values.h b/drivers/net/ethernet/chelsio/cxgb4/t4_values.h index f6558cbfc54e..eb1aa82149db 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_values.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_values.h @@ -71,12 +71,18 @@ #define FETCHBURSTMIN_64B_X 2 #define FETCHBURSTMIN_128B_X 3 +/* T6 and later use a single-bit encoding for FetchBurstMin */ +#define FETCHBURSTMIN_64B_T6_X 0 +#define FETCHBURSTMIN_128B_T6_X 1 + #define FETCHBURSTMAX_256B_X 2 #define FETCHBURSTMAX_512B_X 3 +#define HOSTFCMODE_INGRESS_QUEUE_X 1 #define HOSTFCMODE_STATUS_PAGE_X 2 #define CIDXFLUSHTHRESH_32_X 5 +#define CIDXFLUSHTHRESH_128_X 7 #define UPDATEDELIVERY_INTERRUPT_X 1 diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h index 1d9b3e1e5f94..631f1663f4e0 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h @@ -1254,6 +1254,8 @@ enum fw_params_param_dev { FW_PARAMS_PARAM_DEV_RDMA_WRITE_WITH_IMM = 0x21, FW_PARAMS_PARAM_DEV_RI_WRITE_CMPL_WR = 0x24, FW_PARAMS_PARAM_DEV_OPAQUE_VIID_SMT_EXTN = 0x27, + FW_PARAMS_PARAM_DEV_DBQ_TIMER = 0x29, + FW_PARAMS_PARAM_DEV_DBQ_TIMERTICK = 0x2A, }; /* @@ -1322,6 +1324,7 @@ enum fw_params_param_dmaq { FW_PARAMS_PARAM_DMAQ_EQ_CMPLIQID_CTRL = 0x11, FW_PARAMS_PARAM_DMAQ_EQ_SCHEDCLASS_ETH = 0x12, FW_PARAMS_PARAM_DMAQ_EQ_DCBPRIO_ETH = 0x13, + FW_PARAMS_PARAM_DMAQ_EQ_TIMERIX = 0x15, FW_PARAMS_PARAM_DMAQ_CONM_CTXT = 0x20, }; @@ -1751,8 +1754,8 @@ struct fw_eq_eth_cmd { __be32 fetchszm_to_iqid; __be32 dcaen_to_eqsize; __be64 eqaddr; - __be32 viid_pkd; - __be32 r8_lo; + __be32 autoequiqe_to_viid; + __be32 timeren_timerix; __be64 r9; }; @@ -1847,6 +1850,10 @@ struct fw_eq_eth_cmd { #define FW_EQ_ETH_CMD_EQSIZE_S 0 #define FW_EQ_ETH_CMD_EQSIZE_V(x) ((x) << FW_EQ_ETH_CMD_EQSIZE_S) +#define FW_EQ_ETH_CMD_AUTOEQUIQE_S 31 +#define FW_EQ_ETH_CMD_AUTOEQUIQE_V(x) ((x) << FW_EQ_ETH_CMD_AUTOEQUIQE_S) +#define FW_EQ_ETH_CMD_AUTOEQUIQE_F FW_EQ_ETH_CMD_AUTOEQUIQE_V(1U) + #define FW_EQ_ETH_CMD_AUTOEQUEQE_S 30 #define FW_EQ_ETH_CMD_AUTOEQUEQE_V(x) ((x) << FW_EQ_ETH_CMD_AUTOEQUEQE_S) #define FW_EQ_ETH_CMD_AUTOEQUEQE_F FW_EQ_ETH_CMD_AUTOEQUEQE_V(1U) @@ -1854,6 +1861,19 @@ struct fw_eq_eth_cmd { #define FW_EQ_ETH_CMD_VIID_S 16 #define FW_EQ_ETH_CMD_VIID_V(x) ((x) << FW_EQ_ETH_CMD_VIID_S) +#define FW_EQ_ETH_CMD_TIMEREN_S 3 +#define FW_EQ_ETH_CMD_TIMEREN_M 0x1 +#define FW_EQ_ETH_CMD_TIMEREN_V(x) ((x) << FW_EQ_ETH_CMD_TIMEREN_S) +#define FW_EQ_ETH_CMD_TIMEREN_G(x) \ + (((x) >> FW_EQ_ETH_CMD_TIMEREN_S) & FW_EQ_ETH_CMD_TIMEREN_M) +#define FW_EQ_ETH_CMD_TIMEREN_F FW_EQ_ETH_CMD_TIMEREN_V(1U) + +#define FW_EQ_ETH_CMD_TIMERIX_S 0 +#define FW_EQ_ETH_CMD_TIMERIX_M 0x7 +#define FW_EQ_ETH_CMD_TIMERIX_V(x) ((x) << FW_EQ_ETH_CMD_TIMERIX_S) +#define FW_EQ_ETH_CMD_TIMERIX_G(x) \ + (((x) >> FW_EQ_ETH_CMD_TIMERIX_S) & FW_EQ_ETH_CMD_TIMERIX_M) + struct fw_eq_ctrl_cmd { __be32 op_to_vfn; __be32 alloc_to_len16; diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index 84be3313fede..3300b69a42b3 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -1408,7 +1408,7 @@ static void fw_caps_to_lmm(enum fw_port_type port_type, case FW_PORT_TYPE_CR4_QSFP: SET_LMM(FIBRE); FW_CAPS_TO_LMM(SPEED_1G, 1000baseT_Full); - FW_CAPS_TO_LMM(SPEED_10G, 10000baseSR_Full); + FW_CAPS_TO_LMM(SPEED_10G, 10000baseKR_Full); FW_CAPS_TO_LMM(SPEED_40G, 40000baseSR4_Full); FW_CAPS_TO_LMM(SPEED_25G, 25000baseCR_Full); FW_CAPS_TO_LMM(SPEED_50G, 50000baseCR2_Full); @@ -1419,6 +1419,13 @@ static void fw_caps_to_lmm(enum fw_port_type port_type, break; } + if (fw_caps & FW_PORT_CAP32_FEC_V(FW_PORT_CAP32_FEC_M)) { + FW_CAPS_TO_LMM(FEC_RS, FEC_RS); + FW_CAPS_TO_LMM(FEC_BASER_RS, FEC_BASER); + } else { + SET_LMM(FEC_NONE); + } + FW_CAPS_TO_LMM(ANEG, Autoneg); FW_CAPS_TO_LMM(802_3_PAUSE, Pause); FW_CAPS_TO_LMM(802_3_ASM_DIR, Asym_Pause); diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c index 1d534f0baa69..11d2ba0a2bf5 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c @@ -2268,7 +2268,7 @@ int t4vf_sge_alloc_rxq(struct adapter *adapter, struct sge_rspq *rspq, cmd.iqaddr = cpu_to_be64(rspq->phys_addr); if (fl) { - enum chip_type chip = + unsigned int chip_ver = CHELSIO_CHIP_VERSION(adapter->params.chip); /* * Allocate the ring for the hardware free list (with space @@ -2319,10 +2319,10 @@ int t4vf_sge_alloc_rxq(struct adapter *adapter, struct sge_rspq *rspq, */ cmd.fl0dcaen_to_fl0cidxfthresh = cpu_to_be16( - FW_IQ_CMD_FL0FBMIN_V(chip <= CHELSIO_T5 ? - FETCHBURSTMIN_128B_X : - FETCHBURSTMIN_64B_X) | - FW_IQ_CMD_FL0FBMAX_V((chip <= CHELSIO_T5) ? + FW_IQ_CMD_FL0FBMIN_V(chip_ver <= CHELSIO_T5 + ? FETCHBURSTMIN_128B_X + : FETCHBURSTMIN_64B_T6_X) | + FW_IQ_CMD_FL0FBMAX_V((chip_ver <= CHELSIO_T5) ? FETCHBURSTMAX_512B_X : FETCHBURSTMAX_256B_X)); cmd.fl0size = cpu_to_be16(flsz); @@ -2411,10 +2411,11 @@ int t4vf_sge_alloc_eth_txq(struct adapter *adapter, struct sge_eth_txq *txq, struct net_device *dev, struct netdev_queue *devq, unsigned int iqid) { + unsigned int chip_ver = CHELSIO_CHIP_VERSION(adapter->params.chip); + struct port_info *pi = netdev_priv(dev); + struct fw_eq_eth_cmd cmd, rpl; struct sge *s = &adapter->sge; int ret, nentries; - struct fw_eq_eth_cmd cmd, rpl; - struct port_info *pi = netdev_priv(dev); /* * Calculate the size of the hardware TX Queue (including the Status @@ -2448,17 +2449,19 @@ int t4vf_sge_alloc_eth_txq(struct adapter *adapter, struct sge_eth_txq *txq, cmd.alloc_to_len16 = cpu_to_be32(FW_EQ_ETH_CMD_ALLOC_F | FW_EQ_ETH_CMD_EQSTART_F | FW_LEN16(cmd)); - cmd.viid_pkd = cpu_to_be32(FW_EQ_ETH_CMD_AUTOEQUEQE_F | - FW_EQ_ETH_CMD_VIID_V(pi->viid)); + cmd.autoequiqe_to_viid = cpu_to_be32(FW_EQ_ETH_CMD_AUTOEQUEQE_F | + FW_EQ_ETH_CMD_VIID_V(pi->viid)); cmd.fetchszm_to_iqid = cpu_to_be32(FW_EQ_ETH_CMD_HOSTFCMODE_V(SGE_HOSTFCMODE_STPG) | FW_EQ_ETH_CMD_PCIECHN_V(pi->port_id) | FW_EQ_ETH_CMD_IQID_V(iqid)); cmd.dcaen_to_eqsize = - cpu_to_be32(FW_EQ_ETH_CMD_FBMIN_V(SGE_FETCHBURSTMIN_64B) | - FW_EQ_ETH_CMD_FBMAX_V(SGE_FETCHBURSTMAX_512B) | + cpu_to_be32(FW_EQ_ETH_CMD_FBMIN_V(chip_ver <= CHELSIO_T5 + ? FETCHBURSTMIN_64B_X + : FETCHBURSTMIN_64B_T6_X) | + FW_EQ_ETH_CMD_FBMAX_V(FETCHBURSTMAX_512B_X) | FW_EQ_ETH_CMD_CIDXFTHRESH_V( - SGE_CIDXFLUSHTHRESH_32) | + CIDXFLUSHTHRESH_32_X) | FW_EQ_ETH_CMD_EQSIZE_V(nentries)); cmd.eqaddr = cpu_to_be64(txq->q.phys_addr); diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index 60641e202534..9a7f70db20c7 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -1434,7 +1434,8 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq, * csum is correct or is zero. */ if ((netdev->features & NETIF_F_RXCSUM) && !csum_not_calc && - tcp_udp_csum_ok && ipv4_csum_ok && outer_csum_ok) { + tcp_udp_csum_ok && outer_csum_ok && + (ipv4_csum_ok || ipv6)) { skb->ip_summed = CHECKSUM_UNNECESSARY; skb->csum_level = encap; } diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c index 13430f75496c..f1a2da15dd0a 100644 --- a/drivers/net/ethernet/dec/tulip/de2104x.c +++ b/drivers/net/ethernet/dec/tulip/de2104x.c @@ -585,7 +585,7 @@ static void de_tx (struct de_private *de) netif_dbg(de, tx_done, de->dev, "tx done, slot %d\n", tx_tail); } - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); } next: diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c index d8d423f22c4f..cfcdfee718b0 100644 --- a/drivers/net/ethernet/dlink/dl2k.c +++ b/drivers/net/ethernet/dlink/dl2k.c @@ -843,9 +843,9 @@ rio_free_tx (struct net_device *dev, int irq) desc_to_dma(&np->tx_ring[entry]), skb->len, PCI_DMA_TODEVICE); if (irq) - dev_kfree_skb_irq (skb); + dev_consume_skb_irq(skb); else - dev_kfree_skb (skb); + dev_kfree_skb(skb); np->tx_skbuff[entry] = NULL; entry = (entry + 1) % TX_RING_SIZE; diff --git a/drivers/net/ethernet/dlink/sundance.c b/drivers/net/ethernet/dlink/sundance.c index 1a27176381fb..4a37a69764ce 100644 --- a/drivers/net/ethernet/dlink/sundance.c +++ b/drivers/net/ethernet/dlink/sundance.c @@ -1193,7 +1193,6 @@ static irqreturn_t intr_handler(int irq, void *dev_instance) int handled = 0; int i; - do { int intr_status = ioread16(ioaddr + IntrStatus); iowrite16(intr_status, ioaddr + IntrStatus); @@ -1286,7 +1285,7 @@ static irqreturn_t intr_handler(int irq, void *dev_instance) dma_unmap_single(&np->pci_dev->dev, le32_to_cpu(np->tx_ring[entry].frag[0].addr), skb->len, DMA_TO_DEVICE); - dev_kfree_skb_irq (np->tx_skbuff[entry]); + dev_consume_skb_irq(np->tx_skbuff[entry]); np->tx_skbuff[entry] = NULL; np->tx_ring[entry].frag[0].addr = 0; np->tx_ring[entry].frag[0].length = 0; @@ -1305,7 +1304,7 @@ static irqreturn_t intr_handler(int irq, void *dev_instance) dma_unmap_single(&np->pci_dev->dev, le32_to_cpu(np->tx_ring[entry].frag[0].addr), skb->len, DMA_TO_DEVICE); - dev_kfree_skb_irq (np->tx_skbuff[entry]); + dev_consume_skb_irq(np->tx_skbuff[entry]); np->tx_skbuff[entry] = NULL; np->tx_ring[entry].frag[0].addr = 0; np->tx_ring[entry].frag[0].length = 0; diff --git a/drivers/net/ethernet/fealnx.c b/drivers/net/ethernet/fealnx.c index ae55da60ed0e..c24fd56a2c71 100644 --- a/drivers/net/ethernet/fealnx.c +++ b/drivers/net/ethernet/fealnx.c @@ -1531,7 +1531,7 @@ static irqreturn_t intr_handler(int irq, void *dev_instance) /* Free the original skb. */ pci_unmap_single(np->pci_dev, np->cur_tx->buffer, np->cur_tx->skbuff->len, PCI_DMA_TODEVICE); - dev_kfree_skb_irq(np->cur_tx->skbuff); + dev_consume_skb_irq(np->cur_tx->skbuff); np->cur_tx->skbuff = NULL; --np->really_tx_count; if (np->cur_tx->control & TXLD) { diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c index 62497119c85f..bdee441bc3b7 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c @@ -501,7 +501,7 @@ static int dpaa_get_ts_info(struct net_device *net_dev, struct device_node *mac_node = dev->of_node; struct device_node *fman_node = NULL, *ptp_node = NULL; struct platform_device *ptp_dev = NULL; - struct qoriq_ptp *ptp = NULL; + struct ptp_qoriq *ptp = NULL; info->phc_index = -1; diff --git a/drivers/net/ethernet/freescale/enetc/Kconfig b/drivers/net/ethernet/freescale/enetc/Kconfig index f9dd26fbfc83..8429f5c1d810 100644 --- a/drivers/net/ethernet/freescale/enetc/Kconfig +++ b/drivers/net/ethernet/freescale/enetc/Kconfig @@ -17,3 +17,15 @@ config FSL_ENETC_VF virtual function (VF) devices enabled by the ENETC PF driver. If compiled as module (M), the module name is fsl-enetc-vf. + +config FSL_ENETC_PTP_CLOCK + tristate "ENETC PTP clock driver" + depends on PTP_1588_CLOCK_QORIQ && (FSL_ENETC || FSL_ENETC_VF) + default y + help + This driver adds support for using the ENETC 1588 timer + as a PTP clock. This clock is only useful if your PTP + programs are getting hardware time stamps on the PTP Ethernet + packets using the SO_TIMESTAMPING API. + + If compiled as module (M), the module name is fsl-enetc-ptp. diff --git a/drivers/net/ethernet/freescale/enetc/Makefile b/drivers/net/ethernet/freescale/enetc/Makefile index 9529b01872ca..697660294dbc 100644 --- a/drivers/net/ethernet/freescale/enetc/Makefile +++ b/drivers/net/ethernet/freescale/enetc/Makefile @@ -13,3 +13,6 @@ fsl-enetc-vf-$(CONFIG_FSL_ENETC_VF) += enetc.o enetc_cbdr.o \ enetc_ethtool.o fsl-enetc-vf-objs := enetc_vf.o $(fsl-enetc-vf-y) endif + +obj-$(CONFIG_FSL_ENETC_PTP_CLOCK) += fsl-enetc-ptp.o +fsl-enetc-ptp-$(CONFIG_FSL_ENETC_PTP_CLOCK) += enetc_ptp.o diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h index efa0b1a5ef4f..df8eb8882d92 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h @@ -4,8 +4,9 @@ #include <linux/bitops.h> /* ENETC device IDs */ -#define ENETC_DEV_ID_PF 0xe100 -#define ENETC_DEV_ID_VF 0xef00 +#define ENETC_DEV_ID_PF 0xe100 +#define ENETC_DEV_ID_VF 0xef00 +#define ENETC_DEV_ID_PTP 0xee02 /* ENETC register block BAR */ #define ENETC_BAR_REGS 0 diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ptp.c b/drivers/net/ethernet/freescale/enetc/enetc_ptp.c new file mode 100644 index 000000000000..8c1497e7d9c5 --- /dev/null +++ b/drivers/net/ethernet/freescale/enetc/enetc_ptp.c @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) +/* Copyright 2019 NXP */ + +#include <linux/module.h> +#include <linux/of.h> +#include <linux/fsl/ptp_qoriq.h> + +#include "enetc.h" + +static struct ptp_clock_info enetc_ptp_caps = { + .owner = THIS_MODULE, + .name = "ENETC PTP clock", + .max_adj = 512000, + .n_alarm = 0, + .n_ext_ts = 2, + .n_per_out = 0, + .n_pins = 0, + .pps = 1, + .adjfine = ptp_qoriq_adjfine, + .adjtime = ptp_qoriq_adjtime, + .gettime64 = ptp_qoriq_gettime, + .settime64 = ptp_qoriq_settime, + .enable = ptp_qoriq_enable, +}; + +static int enetc_ptp_probe(struct pci_dev *pdev, + const struct pci_device_id *ent) +{ + struct ptp_qoriq *ptp_qoriq; + void __iomem *base; + int err, len, n; + + if (pdev->dev.of_node && !of_device_is_available(pdev->dev.of_node)) { + dev_info(&pdev->dev, "device is disabled, skipping\n"); + return -ENODEV; + } + + err = pci_enable_device_mem(pdev); + if (err) { + dev_err(&pdev->dev, "device enable failed\n"); + return err; + } + + /* set up for high or low dma */ + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (err) { + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (err) { + dev_err(&pdev->dev, + "DMA configuration failed: 0x%x\n", err); + goto err_dma; + } + } + + err = pci_request_mem_regions(pdev, KBUILD_MODNAME); + if (err) { + dev_err(&pdev->dev, "pci_request_regions failed err=%d\n", err); + goto err_pci_mem_reg; + } + + pci_set_master(pdev); + + ptp_qoriq = kzalloc(sizeof(*ptp_qoriq), GFP_KERNEL); + if (!ptp_qoriq) { + err = -ENOMEM; + goto err_alloc_ptp; + } + + len = pci_resource_len(pdev, ENETC_BAR_REGS); + + base = ioremap(pci_resource_start(pdev, ENETC_BAR_REGS), len); + if (!base) { + err = -ENXIO; + dev_err(&pdev->dev, "ioremap() failed\n"); + goto err_ioremap; + } + + /* Allocate 1 interrupt */ + n = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSIX); + if (n != 1) { + err = -EPERM; + goto err_irq; + } + + ptp_qoriq->irq = pci_irq_vector(pdev, 0); + + err = request_irq(ptp_qoriq->irq, ptp_qoriq_isr, 0, DRIVER, ptp_qoriq); + if (err) { + dev_err(&pdev->dev, "request_irq() failed!\n"); + goto err_irq; + } + + ptp_qoriq->dev = &pdev->dev; + + err = ptp_qoriq_init(ptp_qoriq, base, &enetc_ptp_caps); + if (err) + goto err_no_clock; + + pci_set_drvdata(pdev, ptp_qoriq); + + return 0; + +err_no_clock: + free_irq(ptp_qoriq->irq, ptp_qoriq); +err_irq: + iounmap(base); +err_ioremap: + kfree(ptp_qoriq); +err_alloc_ptp: + pci_release_mem_regions(pdev); +err_pci_mem_reg: +err_dma: + pci_disable_device(pdev); + + return err; +} + +static void enetc_ptp_remove(struct pci_dev *pdev) +{ + struct ptp_qoriq *ptp_qoriq = pci_get_drvdata(pdev); + + ptp_qoriq_free(ptp_qoriq); + kfree(ptp_qoriq); + + pci_release_mem_regions(pdev); + pci_disable_device(pdev); +} + +static const struct pci_device_id enetc_ptp_id_table[] = { + { PCI_DEVICE(PCI_VENDOR_ID_FREESCALE, ENETC_DEV_ID_PTP) }, + { 0, } /* End of table. */ +}; +MODULE_DEVICE_TABLE(pci, enetc_ptp_id_table); + +static struct pci_driver enetc_ptp_driver = { + .name = KBUILD_MODNAME, + .id_table = enetc_ptp_id_table, + .probe = enetc_ptp_probe, + .remove = enetc_ptp_remove, +}; +module_pci_driver(enetc_ptp_driver); + +MODULE_DESCRIPTION("ENETC PTP clock driver"); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 2370dc204202..697c2427f2b7 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2098,6 +2098,7 @@ static int fec_enet_get_regs_len(struct net_device *ndev) #if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \ defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) || \ defined(CONFIG_ARM64) || defined(CONFIG_COMPILE_TEST) +static __u32 fec_enet_register_version = 2; static u32 fec_enet_register_offset[] = { FEC_IEVENT, FEC_IMASK, FEC_R_DES_ACTIVE_0, FEC_X_DES_ACTIVE_0, FEC_ECNTRL, FEC_MII_DATA, FEC_MII_SPEED, FEC_MIB_CTRLSTAT, FEC_R_CNTRL, @@ -2128,6 +2129,7 @@ static u32 fec_enet_register_offset[] = { IEEE_R_FDXFC, IEEE_R_OCTETS_OK }; #else +static __u32 fec_enet_register_version = 1; static u32 fec_enet_register_offset[] = { FEC_ECNTRL, FEC_IEVENT, FEC_IMASK, FEC_IVEC, FEC_R_DES_ACTIVE_0, FEC_R_DES_ACTIVE_1, FEC_R_DES_ACTIVE_2, FEC_X_DES_ACTIVE_0, @@ -2149,6 +2151,8 @@ static void fec_enet_get_regs(struct net_device *ndev, u32 *buf = (u32 *)regbuf; u32 i, off; + regs->version = fec_enet_register_version; + memset(buf, 0, regs->len); for (i = 0; i < ARRAY_SIZE(fec_enet_register_offset); i++) { diff --git a/drivers/net/ethernet/freescale/fec_mpc52xx.c b/drivers/net/ethernet/freescale/fec_mpc52xx.c index b90bab72efdb..c1968b3ecec8 100644 --- a/drivers/net/ethernet/freescale/fec_mpc52xx.c +++ b/drivers/net/ethernet/freescale/fec_mpc52xx.c @@ -369,7 +369,7 @@ static irqreturn_t mpc52xx_fec_tx_interrupt(int irq, void *dev_id) dma_unmap_single(dev->dev.parent, bd->skb_pa, skb->len, DMA_TO_DEVICE); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); } spin_unlock(&priv->lock); diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c index 241325c35cb4..27ed995f439a 100644 --- a/drivers/net/ethernet/freescale/gianfar_ethtool.c +++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c @@ -1492,7 +1492,7 @@ static int gfar_get_ts_info(struct net_device *dev, struct gfar_private *priv = netdev_priv(dev); struct platform_device *ptp_dev; struct device_node *ptp_node; - struct qoriq_ptp *ptp = NULL; + struct ptp_qoriq *ptp = NULL; info->phc_index = -1; diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index c3d539e209ed..eb3e65e8868f 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -1879,6 +1879,8 @@ static void ucc_geth_free_tx(struct ucc_geth_private *ugeth) u16 i, j; u8 __iomem *bd; + netdev_reset_queue(ugeth->ndev); + ug_info = ugeth->ug_info; uf_info = &ug_info->uf_info; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index 3b9e74be5fbd..ac55db065f16 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -3081,6 +3081,7 @@ int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset) dsaf_dev = dev_get_drvdata(&pdev->dev); if (!dsaf_dev) { dev_err(&pdev->dev, "dsaf_dev is NULL\n"); + put_device(&pdev->dev); return -ENODEV; } @@ -3088,6 +3089,7 @@ int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset) if (AE_IS_VER1(dsaf_dev->dsaf_ver)) { dev_err(dsaf_dev->dev, "%s v1 chip doesn't support RoCE!\n", dsaf_dev->ae_dev.name); + put_device(&pdev->dev); return -ENODEV; } @@ -3126,6 +3128,9 @@ int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset) dsaf_set_bit(credit, DSAF_SBM_ROCEE_CFG_CRD_EN_B, 1); dsaf_write_dev(dsaf_dev, DSAF_SBM_ROCEE_CFG_REG_REG, credit); } + + put_device(&pdev->dev); + return 0; } EXPORT_SYMBOL(hns_dsaf_roce_reset); diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h index 53089cd980d9..9b6b7b45dde3 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h +++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h @@ -42,6 +42,8 @@ enum HCLGE_MBX_OPCODE { HCLGE_MBX_GET_QID_IN_PF, /* (VF -> PF) get queue id in pf */ HCLGE_MBX_LINK_STAT_MODE, /* (PF -> VF) link mode has changed */ HCLGE_MBX_GET_LINK_MODE, /* (VF -> PF) get the link mode of pf */ + + HCLGE_MBX_GET_VF_FLR_STATUS = 200, /* (M7 -> PF) get vf reset status */ }; /* below are per-VF mac-vlan subcodes */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.c b/drivers/net/ethernet/hisilicon/hns3/hnae3.c index 50011aafbae4..17ab4f4af6ad 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.c +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.c @@ -32,6 +32,9 @@ static bool hnae3_client_match(enum hnae3_client_type client_type, void hnae3_set_client_init_flag(struct hnae3_client *client, struct hnae3_ae_dev *ae_dev, int inited) { + if (!client || !ae_dev) + return; + switch (client->type) { case HNAE3_CLIENT_KNIC: hnae3_set_bit(ae_dev->flag, HNAE3_KNIC_CLIENT_INITED_B, inited); @@ -109,6 +112,9 @@ int hnae3_register_client(struct hnae3_client *client) struct hnae3_ae_dev *ae_dev; int ret = 0; + if (!client) + return -ENODEV; + mutex_lock(&hnae3_common_lock); /* one system should only have one client for every type */ list_for_each_entry(client_tmp, &hnae3_client_list, node) { @@ -141,6 +147,9 @@ void hnae3_unregister_client(struct hnae3_client *client) { struct hnae3_ae_dev *ae_dev; + if (!client) + return; + mutex_lock(&hnae3_common_lock); /* un-initialize the client on every matched port */ list_for_each_entry(ae_dev, &hnae3_ae_dev_list, node) { @@ -163,6 +172,9 @@ void hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo) struct hnae3_client *client; int ret = 0; + if (!ae_algo) + return; + mutex_lock(&hnae3_common_lock); list_add_tail(&ae_algo->node, &hnae3_ae_algo_list); @@ -173,8 +185,12 @@ void hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo) if (!id) continue; - /* ae_dev init should set flag */ + if (!ae_algo->ops) { + dev_err(&ae_dev->pdev->dev, "ae_algo ops are null\n"); + continue; + } ae_dev->ops = ae_algo->ops; + ret = ae_algo->ops->init_ae_dev(ae_dev); if (ret) { dev_err(&ae_dev->pdev->dev, @@ -182,6 +198,7 @@ void hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo) continue; } + /* ae_dev init should set flag */ hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 1); /* check the client list for the match with this ae_dev type and @@ -209,6 +226,9 @@ void hnae3_unregister_ae_algo(struct hnae3_ae_algo *ae_algo) struct hnae3_ae_dev *ae_dev; struct hnae3_client *client; + if (!ae_algo) + return; + mutex_lock(&hnae3_common_lock); /* Check if there are matched ae_dev */ list_for_each_entry(ae_dev, &hnae3_ae_dev_list, node) { @@ -245,6 +265,9 @@ int hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev) struct hnae3_client *client; int ret = 0; + if (!ae_dev) + return -ENODEV; + mutex_lock(&hnae3_common_lock); list_add_tail(&ae_dev->node, &hnae3_ae_dev_list); @@ -255,15 +278,13 @@ int hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev) if (!id) continue; - ae_dev->ops = ae_algo->ops; - - if (!ae_dev->ops) { - dev_err(&ae_dev->pdev->dev, "ae_dev ops are null\n"); + if (!ae_algo->ops) { + dev_err(&ae_dev->pdev->dev, "ae_algo ops are null\n"); ret = -EOPNOTSUPP; goto out_err; } + ae_dev->ops = ae_algo->ops; - /* ae_dev init should set flag */ ret = ae_dev->ops->init_ae_dev(ae_dev); if (ret) { dev_err(&ae_dev->pdev->dev, @@ -271,6 +292,7 @@ int hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev) goto out_err; } + /* ae_dev init should set flag */ hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 1); break; } @@ -307,6 +329,9 @@ void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev) struct hnae3_ae_algo *ae_algo; struct hnae3_client *client; + if (!ae_dev) + return; + mutex_lock(&hnae3_common_lock); /* Check if there are matched ae_algo */ list_for_each_entry(ae_algo, &hnae3_ae_algo_list, node) { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index 63f5f56bda94..d94c90a38563 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -621,12 +621,11 @@ static int hns3_get_link_ksettings(struct net_device *netdev, hns3_get_ksettings(h, cmd); break; case HNAE3_MEDIA_TYPE_COPPER: - if (!netdev->phydev) - return -EOPNOTSUPP; - cmd->base.port = PORT_TP; - phy_ethtool_ksettings_get(netdev->phydev, cmd); - + if (!netdev->phydev) + hns3_get_ksettings(h, cmd); + else + phy_ethtool_ksettings_get(netdev->phydev, cmd); break; default: diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c index 1dddfcba41a9..3a093a92eac5 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c @@ -390,6 +390,20 @@ int hclge_cmd_init(struct hclge_dev *hdev) return 0; } +static void hclge_cmd_uninit_regs(struct hclge_hw *hw) +{ + hclge_write_dev(hw, HCLGE_NIC_CSQ_BASEADDR_L_REG, 0); + hclge_write_dev(hw, HCLGE_NIC_CSQ_BASEADDR_H_REG, 0); + hclge_write_dev(hw, HCLGE_NIC_CSQ_DEPTH_REG, 0); + hclge_write_dev(hw, HCLGE_NIC_CSQ_HEAD_REG, 0); + hclge_write_dev(hw, HCLGE_NIC_CSQ_TAIL_REG, 0); + hclge_write_dev(hw, HCLGE_NIC_CRQ_BASEADDR_L_REG, 0); + hclge_write_dev(hw, HCLGE_NIC_CRQ_BASEADDR_H_REG, 0); + hclge_write_dev(hw, HCLGE_NIC_CRQ_DEPTH_REG, 0); + hclge_write_dev(hw, HCLGE_NIC_CRQ_HEAD_REG, 0); + hclge_write_dev(hw, HCLGE_NIC_CRQ_TAIL_REG, 0); +} + static void hclge_destroy_queue(struct hclge_cmq_ring *ring) { spin_lock(&ring->lock); @@ -402,3 +416,15 @@ void hclge_destroy_cmd_queue(struct hclge_hw *hw) hclge_destroy_queue(&hw->cmq.csq); hclge_destroy_queue(&hw->cmq.crq); } + +void hclge_cmd_uninit(struct hclge_dev *hdev) +{ + spin_lock_bh(&hdev->hw.cmq.csq.lock); + spin_lock(&hdev->hw.cmq.crq.lock); + set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state); + hclge_cmd_uninit_regs(&hdev->hw); + spin_unlock(&hdev->hw.cmq.crq.lock); + spin_unlock_bh(&hdev->hw.cmq.csq.lock); + + hclge_destroy_cmd_queue(&hdev->hw); +} diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index ac2cd219a9fb..bad21c89f6b7 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -975,6 +975,6 @@ enum hclge_cmd_status hclge_cmd_mdio_write(struct hclge_hw *hw, enum hclge_cmd_status hclge_cmd_mdio_read(struct hclge_hw *hw, struct hclge_desc *desc); -void hclge_destroy_cmd_queue(struct hclge_hw *hw); +void hclge_cmd_uninit(struct hclge_dev *hdev); int hclge_cmd_queue_init(struct hclge_dev *hdev); #endif diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c index d0f654123b9b..b9d363fa595a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c @@ -80,7 +80,7 @@ static const struct hclge_hw_error hclge_ppp_mpf_abnormal_int_st1[] = { { .int_msk = BIT(3), .msg = "umv_key_mem1_ecc_mbit_err" }, { .int_msk = BIT(4), .msg = "umv_key_mem2_ecc_mbit_err" }, { .int_msk = BIT(5), .msg = "umv_key_mem3_ecc_mbit_err" }, - { .int_msk = BIT(6), .msg = "umv_ad_mem_ecc_mbit_erre" }, + { .int_msk = BIT(6), .msg = "umv_ad_mem_ecc_mbit_err" }, { .int_msk = BIT(7), .msg = "rss_tc_mode_mem_ecc_mbit_err" }, { .int_msk = BIT(8), .msg = "rss_idt_mem0_ecc_mbit_err" }, { .int_msk = BIT(9), .msg = "rss_idt_mem1_ecc_mbit_err" }, @@ -219,6 +219,12 @@ static const struct hclge_hw_error hclge_mac_afifo_tnl_int[] = { { .int_msk = BIT(5), .msg = "cge_igu_afifo_ecc_mbit_err" }, { .int_msk = BIT(6), .msg = "lge_igu_afifo_ecc_1bit_err" }, { .int_msk = BIT(7), .msg = "lge_igu_afifo_ecc_mbit_err" }, + { .int_msk = BIT(8), .msg = "cge_igu_afifo_overflow_err" }, + { .int_msk = BIT(9), .msg = "lge_igu_afifo_overflow_err" }, + { .int_msk = BIT(10), .msg = "egu_cge_afifo_underrun_err" }, + { .int_msk = BIT(11), .msg = "egu_lge_afifo_underrun_err" }, + { .int_msk = BIT(12), .msg = "egu_ge_afifo_underrun_err" }, + { .int_msk = BIT(13), .msg = "ge_igu_afifo_overflow_err" }, { /* sentinel */ } }; @@ -277,6 +283,45 @@ static const struct hclge_hw_error hclge_ssu_com_err_int[] = { { /* sentinel */ } }; +#define HCLGE_SSU_MEM_ECC_ERR(x) \ + { .int_msk = BIT(x), .msg = "ssu_mem" #x "_ecc_mbit_err" } + +static const struct hclge_hw_error hclge_ssu_mem_ecc_err_int[] = { + HCLGE_SSU_MEM_ECC_ERR(0), + HCLGE_SSU_MEM_ECC_ERR(1), + HCLGE_SSU_MEM_ECC_ERR(2), + HCLGE_SSU_MEM_ECC_ERR(3), + HCLGE_SSU_MEM_ECC_ERR(4), + HCLGE_SSU_MEM_ECC_ERR(5), + HCLGE_SSU_MEM_ECC_ERR(6), + HCLGE_SSU_MEM_ECC_ERR(7), + HCLGE_SSU_MEM_ECC_ERR(8), + HCLGE_SSU_MEM_ECC_ERR(9), + HCLGE_SSU_MEM_ECC_ERR(10), + HCLGE_SSU_MEM_ECC_ERR(11), + HCLGE_SSU_MEM_ECC_ERR(12), + HCLGE_SSU_MEM_ECC_ERR(13), + HCLGE_SSU_MEM_ECC_ERR(14), + HCLGE_SSU_MEM_ECC_ERR(15), + HCLGE_SSU_MEM_ECC_ERR(16), + HCLGE_SSU_MEM_ECC_ERR(17), + HCLGE_SSU_MEM_ECC_ERR(18), + HCLGE_SSU_MEM_ECC_ERR(19), + HCLGE_SSU_MEM_ECC_ERR(20), + HCLGE_SSU_MEM_ECC_ERR(21), + HCLGE_SSU_MEM_ECC_ERR(22), + HCLGE_SSU_MEM_ECC_ERR(23), + HCLGE_SSU_MEM_ECC_ERR(24), + HCLGE_SSU_MEM_ECC_ERR(25), + HCLGE_SSU_MEM_ECC_ERR(26), + HCLGE_SSU_MEM_ECC_ERR(27), + HCLGE_SSU_MEM_ECC_ERR(28), + HCLGE_SSU_MEM_ECC_ERR(29), + HCLGE_SSU_MEM_ECC_ERR(30), + HCLGE_SSU_MEM_ECC_ERR(31), + { /* sentinel */ } +}; + static const struct hclge_hw_error hclge_ssu_port_based_err_int[] = { { .int_msk = BIT(0), .msg = "roc_pkt_without_key_port" }, { .int_msk = BIT(1), .msg = "tpu_pkt_without_key_port" }, @@ -835,13 +880,15 @@ static int hclge_handle_mpf_ras_error(struct hclge_dev *hdev, desc_data = (__le32 *)&desc[2]; status = le32_to_cpu(*(desc_data + 2)); if (status) { - dev_warn(dev, "SSU_ECC_MULTI_BIT_INT_0 ssu_ecc_mbit_int[31:0]\n"); + hclge_log_error(dev, "SSU_ECC_MULTI_BIT_INT_0", + &hclge_ssu_mem_ecc_err_int[0], status); HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET); } status = le32_to_cpu(*(desc_data + 3)) & BIT(0); if (status) { - dev_warn(dev, "SSU_ECC_MULTI_BIT_INT_1 ssu_ecc_mbit_int[32]\n"); + dev_warn(dev, "SSU_ECC_MULTI_BIT_INT_1 ssu_mem32_ecc_mbit_err found [error status=0x%x]\n", + status); HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET); } @@ -997,6 +1044,13 @@ static int hclge_handle_pf_ras_error(struct hclge_dev *hdev, hclge_log_error(dev, "IGU_EGU_TNL_INT_STS", &hclge_igu_egu_tnl_int[0], status); + /* log PPU(RCB) errors */ + desc_data = (__le32 *)&desc[3]; + status = le32_to_cpu(*desc_data) & HCLGE_PPU_PF_INT_RAS_MASK; + if (status) + hclge_log_error(dev, "PPU_PF_ABNORMAL_INT_ST0", + &hclge_ppu_pf_abnormal_int[0], status); + /* clear all PF RAS errors */ hclge_cmd_reuse_desc(&desc[0], false); desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); @@ -1332,14 +1386,13 @@ int hclge_handle_hw_msix_error(struct hclge_dev *hdev, set_bit(HNAE3_GLOBAL_RESET, reset_requests); } - /* log PPU(RCB) errors */ + /* log PPU(RCB) MPF errors */ desc_data = (__le32 *)&desc[5]; status = le32_to_cpu(*(desc_data + 2)) & HCLGE_PPU_MPF_INT_ST2_MSIX_MASK; if (status) { - dev_warn(dev, - "PPU_MPF_ABNORMAL_INT_ST2[28:29], err_status(0x%x)\n", - status); + hclge_log_error(dev, "PPU_MPF_ABNORMAL_INT_ST2", + &hclge_ppu_mpf_abnormal_int_st2[0], status); set_bit(HNAE3_CORE_RESET, reset_requests); } @@ -1386,7 +1439,7 @@ int hclge_handle_hw_msix_error(struct hclge_dev *hdev, hclge_log_error(dev, "PPP_PF_ABNORMAL_INT_ST0", &hclge_ppp_pf_abnormal_int[0], status); - /* PPU(RCB) PF errors */ + /* log PPU(RCB) PF errors */ desc_data = (__le32 *)&desc[3]; status = le32_to_cpu(*desc_data) & HCLGE_PPU_PF_INT_MSIX_MASK; if (status) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h index 51a7d4eb066a..fc068280d391 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h @@ -45,8 +45,8 @@ #define HCLGE_TM_QCN_MEM_ERR_INT_EN 0xFFFFFF #define HCLGE_NCSI_ERR_INT_EN 0x3 #define HCLGE_NCSI_ERR_INT_TYPE 0x9 -#define HCLGE_MAC_COMMON_ERR_INT_EN GENMASK(7, 0) -#define HCLGE_MAC_COMMON_ERR_INT_EN_MASK GENMASK(7, 0) +#define HCLGE_MAC_COMMON_ERR_INT_EN 0x107FF +#define HCLGE_MAC_COMMON_ERR_INT_EN_MASK 0x107FF #define HCLGE_PPU_MPF_ABNORMAL_INT0_EN GENMASK(31, 0) #define HCLGE_PPU_MPF_ABNORMAL_INT0_EN_MASK GENMASK(31, 0) #define HCLGE_PPU_MPF_ABNORMAL_INT1_EN GENMASK(31, 0) @@ -79,6 +79,7 @@ #define HCLGE_PPP_MPF_INT_ST3_MASK GENMASK(5, 0) #define HCLGE_PPU_MPF_INT_ST3_MASK GENMASK(7, 0) #define HCLGE_PPU_MPF_INT_ST2_MSIX_MASK GENMASK(29, 28) +#define HCLGE_PPU_PF_INT_RAS_MASK 0x18 #define HCLGE_PPU_PF_INT_MSIX_MASK 0x27 #define HCLGE_QCN_FIFO_INT_MASK GENMASK(17, 0) #define HCLGE_QCN_ECC_INT_MASK GENMASK(21, 0) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 0a64c7f2dc6c..5c8f2e4d71c9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -839,37 +839,67 @@ static void hclge_parse_fiber_link_mode(struct hclge_dev *hdev, unsigned long *supported = hdev->hw.mac.supported; if (speed_ability & HCLGE_SUPPORT_1G_BIT) - set_bit(ETHTOOL_LINK_MODE_1000baseX_Full_BIT, - supported); + linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseX_Full_BIT, + supported); if (speed_ability & HCLGE_SUPPORT_10G_BIT) - set_bit(ETHTOOL_LINK_MODE_10000baseSR_Full_BIT, - supported); + linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseSR_Full_BIT, + supported); if (speed_ability & HCLGE_SUPPORT_25G_BIT) - set_bit(ETHTOOL_LINK_MODE_25000baseSR_Full_BIT, - supported); + linkmode_set_bit(ETHTOOL_LINK_MODE_25000baseSR_Full_BIT, + supported); if (speed_ability & HCLGE_SUPPORT_50G_BIT) - set_bit(ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT, - supported); + linkmode_set_bit(ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT, + supported); if (speed_ability & HCLGE_SUPPORT_100G_BIT) - set_bit(ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT, - supported); + linkmode_set_bit(ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT, + supported); - set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, supported); - set_bit(ETHTOOL_LINK_MODE_Pause_BIT, supported); + linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, supported); + linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, supported); +} + +static void hclge_parse_copper_link_mode(struct hclge_dev *hdev, + u8 speed_ability) +{ + unsigned long *supported = hdev->hw.mac.supported; + + /* default to support all speed for GE port */ + if (!speed_ability) + speed_ability = HCLGE_SUPPORT_GE; + + if (speed_ability & HCLGE_SUPPORT_1G_BIT) + linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + supported); + + if (speed_ability & HCLGE_SUPPORT_100M_BIT) { + linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, + supported); + linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, + supported); + } + + if (speed_ability & HCLGE_SUPPORT_10M_BIT) { + linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, supported); + linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, supported); + } + + linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, supported); + linkmode_set_bit(ETHTOOL_LINK_MODE_TP_BIT, supported); + linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, supported); } static void hclge_parse_link_mode(struct hclge_dev *hdev, u8 speed_ability) { u8 media_type = hdev->hw.mac.media_type; - if (media_type != HNAE3_MEDIA_TYPE_FIBER) - return; - - hclge_parse_fiber_link_mode(hdev, speed_ability); + if (media_type == HNAE3_MEDIA_TYPE_FIBER) + hclge_parse_fiber_link_mode(hdev, speed_ability); + else if (media_type == HNAE3_MEDIA_TYPE_COPPER) + hclge_parse_copper_link_mode(hdev, speed_ability); } static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc) @@ -1299,6 +1329,9 @@ static int hclge_alloc_vport(struct hclge_dev *hdev) vport->back = hdev; vport->vport_id = i; vport->mps = HCLGE_MAC_DEFAULT_FRAME; + INIT_LIST_HEAD(&vport->vlan_list); + INIT_LIST_HEAD(&vport->uc_mac_list); + INIT_LIST_HEAD(&vport->mc_mac_list); if (i == 0) ret = hclge_vport_setup(vport, tqp_main_vport); @@ -2599,7 +2632,7 @@ static int hclge_set_vf_rst(struct hclge_dev *hdev, int func_id, bool reset) return hclge_cmd_send(&hdev->hw, &desc, 1); } -int hclge_set_all_vf_rst(struct hclge_dev *hdev, bool reset) +static int hclge_set_all_vf_rst(struct hclge_dev *hdev, bool reset) { int i; @@ -6044,6 +6077,103 @@ int hclge_rm_mc_addr_common(struct hclge_vport *vport, return status; } +void hclge_add_vport_mac_table(struct hclge_vport *vport, const u8 *mac_addr, + enum HCLGE_MAC_ADDR_TYPE mac_type) +{ + struct hclge_vport_mac_addr_cfg *mac_cfg; + struct list_head *list; + + if (!vport->vport_id) + return; + + mac_cfg = kzalloc(sizeof(*mac_cfg), GFP_KERNEL); + if (!mac_cfg) + return; + + mac_cfg->hd_tbl_status = true; + memcpy(mac_cfg->mac_addr, mac_addr, ETH_ALEN); + + list = (mac_type == HCLGE_MAC_ADDR_UC) ? + &vport->uc_mac_list : &vport->mc_mac_list; + + list_add_tail(&mac_cfg->node, list); +} + +void hclge_rm_vport_mac_table(struct hclge_vport *vport, const u8 *mac_addr, + bool is_write_tbl, + enum HCLGE_MAC_ADDR_TYPE mac_type) +{ + struct hclge_vport_mac_addr_cfg *mac_cfg, *tmp; + struct list_head *list; + bool uc_flag, mc_flag; + + list = (mac_type == HCLGE_MAC_ADDR_UC) ? + &vport->uc_mac_list : &vport->mc_mac_list; + + uc_flag = is_write_tbl && mac_type == HCLGE_MAC_ADDR_UC; + mc_flag = is_write_tbl && mac_type == HCLGE_MAC_ADDR_MC; + + list_for_each_entry_safe(mac_cfg, tmp, list, node) { + if (strncmp(mac_cfg->mac_addr, mac_addr, ETH_ALEN) == 0) { + if (uc_flag && mac_cfg->hd_tbl_status) + hclge_rm_uc_addr_common(vport, mac_addr); + + if (mc_flag && mac_cfg->hd_tbl_status) + hclge_rm_mc_addr_common(vport, mac_addr); + + list_del(&mac_cfg->node); + kfree(mac_cfg); + break; + } + } +} + +void hclge_rm_vport_all_mac_table(struct hclge_vport *vport, bool is_del_list, + enum HCLGE_MAC_ADDR_TYPE mac_type) +{ + struct hclge_vport_mac_addr_cfg *mac_cfg, *tmp; + struct list_head *list; + + list = (mac_type == HCLGE_MAC_ADDR_UC) ? + &vport->uc_mac_list : &vport->mc_mac_list; + + list_for_each_entry_safe(mac_cfg, tmp, list, node) { + if (mac_type == HCLGE_MAC_ADDR_UC && mac_cfg->hd_tbl_status) + hclge_rm_uc_addr_common(vport, mac_cfg->mac_addr); + + if (mac_type == HCLGE_MAC_ADDR_MC && mac_cfg->hd_tbl_status) + hclge_rm_mc_addr_common(vport, mac_cfg->mac_addr); + + mac_cfg->hd_tbl_status = false; + if (is_del_list) { + list_del(&mac_cfg->node); + kfree(mac_cfg); + } + } +} + +void hclge_uninit_vport_mac_table(struct hclge_dev *hdev) +{ + struct hclge_vport_mac_addr_cfg *mac, *tmp; + struct hclge_vport *vport; + int i; + + mutex_lock(&hdev->vport_cfg_mutex); + for (i = 0; i < hdev->num_alloc_vport; i++) { + vport = &hdev->vport[i]; + list_for_each_entry_safe(mac, tmp, &vport->uc_mac_list, node) { + list_del(&mac->node); + kfree(mac); + } + + list_for_each_entry_safe(mac, tmp, &vport->mc_mac_list, node) { + list_del(&mac->node); + kfree(mac); + } + } + mutex_unlock(&hdev->vport_cfg_mutex); +} + static int hclge_get_mac_ethertype_cmd_status(struct hclge_dev *hdev, u16 cmdq_resp, u8 resp_code) { @@ -6617,6 +6747,84 @@ static int hclge_init_vlan_config(struct hclge_dev *hdev) return hclge_set_vlan_filter(handle, htons(ETH_P_8021Q), 0, false); } +void hclge_add_vport_vlan_table(struct hclge_vport *vport, u16 vlan_id) +{ + struct hclge_vport_vlan_cfg *vlan; + + /* vlan 0 is reserved */ + if (!vlan_id) + return; + + vlan = kzalloc(sizeof(*vlan), GFP_KERNEL); + if (!vlan) + return; + + vlan->hd_tbl_status = true; + vlan->vlan_id = vlan_id; + + list_add_tail(&vlan->node, &vport->vlan_list); +} + +void hclge_rm_vport_vlan_table(struct hclge_vport *vport, u16 vlan_id, + bool is_write_tbl) +{ + struct hclge_vport_vlan_cfg *vlan, *tmp; + struct hclge_dev *hdev = vport->back; + + list_for_each_entry_safe(vlan, tmp, &vport->vlan_list, node) { + if (vlan->vlan_id == vlan_id) { + if (is_write_tbl && vlan->hd_tbl_status) + hclge_set_vlan_filter_hw(hdev, + htons(ETH_P_8021Q), + vport->vport_id, + vlan_id, 0, + true); + + list_del(&vlan->node); + kfree(vlan); + break; + } + } +} + +void hclge_rm_vport_all_vlan_table(struct hclge_vport *vport, bool is_del_list) +{ + struct hclge_vport_vlan_cfg *vlan, *tmp; + struct hclge_dev *hdev = vport->back; + + list_for_each_entry_safe(vlan, tmp, &vport->vlan_list, node) { + if (vlan->hd_tbl_status) + hclge_set_vlan_filter_hw(hdev, + htons(ETH_P_8021Q), + vport->vport_id, + vlan->vlan_id, 0, + true); + + vlan->hd_tbl_status = false; + if (is_del_list) { + list_del(&vlan->node); + kfree(vlan); + } + } +} + +void hclge_uninit_vport_vlan_table(struct hclge_dev *hdev) +{ + struct hclge_vport_vlan_cfg *vlan, *tmp; + struct hclge_vport *vport; + int i; + + mutex_lock(&hdev->vport_cfg_mutex); + for (i = 0; i < hdev->num_alloc_vport; i++) { + vport = &hdev->vport[i]; + list_for_each_entry_safe(vlan, tmp, &vport->vlan_list, node) { + list_del(&vlan->node); + kfree(vlan); + } + } + mutex_unlock(&hdev->vport_cfg_mutex); +} + int hclge_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable) { struct hclge_vport *vport = hclge_get_vport(handle); @@ -7299,6 +7507,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) hdev->mps = ETH_FRAME_LEN + ETH_FCS_LEN + 2 * VLAN_HLEN; mutex_init(&hdev->vport_lock); + mutex_init(&hdev->vport_cfg_mutex); ret = hclge_pci_init(hdev); if (ret) { @@ -7460,7 +7669,7 @@ err_msi_irq_uninit: err_msi_uninit: pci_free_irq_vectors(pdev); err_cmd_uninit: - hclge_destroy_cmd_queue(&hdev->hw); + hclge_cmd_uninit(hdev); err_pci_uninit: pcim_iounmap(pdev, hdev->hw.io_base); pci_clear_master(pdev); @@ -7587,10 +7796,13 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev) synchronize_irq(hdev->misc_vector.vector_irq); hclge_hw_error_set_state(hdev, false); - hclge_destroy_cmd_queue(&hdev->hw); + hclge_cmd_uninit(hdev); hclge_misc_irq_uninit(hdev); hclge_pci_uninit(hdev); mutex_destroy(&hdev->vport_lock); + hclge_uninit_vport_mac_table(hdev); + hclge_uninit_vport_vlan_table(hdev); + mutex_destroy(&hdev->vport_cfg_mutex); ae_dev->priv = NULL; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index c939f4a7f5f0..abbc58ea4864 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -188,6 +188,10 @@ enum HLCGE_PORT_TYPE { #define HCLGE_SUPPORT_25G_BIT BIT(2) #define HCLGE_SUPPORT_50G_BIT BIT(3) #define HCLGE_SUPPORT_100G_BIT BIT(4) +#define HCLGE_SUPPORT_100M_BIT BIT(6) +#define HCLGE_SUPPORT_10M_BIT BIT(7) +#define HCLGE_SUPPORT_GE \ + (HCLGE_SUPPORT_1G_BIT | HCLGE_SUPPORT_100M_BIT | HCLGE_SUPPORT_10M_BIT) enum HCLGE_DEV_STATE { HCLGE_STATE_REINITING, @@ -628,6 +632,23 @@ struct hclge_fd_ad_data { u16 rule_id; }; +struct hclge_vport_mac_addr_cfg { + struct list_head node; + int hd_tbl_status; + u8 mac_addr[ETH_ALEN]; +}; + +enum HCLGE_MAC_ADDR_TYPE { + HCLGE_MAC_ADDR_UC, + HCLGE_MAC_ADDR_MC +}; + +struct hclge_vport_vlan_cfg { + struct list_head node; + int hd_tbl_status; + u16 vlan_id; +}; + /* For each bit of TCAM entry, it uses a pair of 'x' and * 'y' to indicate which value to match, like below: * ---------------------------------- @@ -767,6 +788,8 @@ struct hclge_dev { /* unicast mac vlan space shared by PF and its VFs */ u16 share_umv_size; struct mutex umv_mutex; /* protect share_umv_size */ + + struct mutex vport_cfg_mutex; /* Protect stored vf table */ }; /* VPort level vlan tag configuration for TX direction */ @@ -834,6 +857,10 @@ struct hclge_vport { unsigned long state; unsigned long last_active_jiffies; u32 mps; /* Max packet size */ + + struct list_head uc_mac_list; /* Store VF unicast table */ + struct list_head mc_mac_list; /* Store VF multicast table */ + struct list_head vlan_list; /* Store VF vlan table */ }; void hclge_promisc_param_init(struct hclge_promisc_param *param, bool en_uc, @@ -888,4 +915,17 @@ int hclge_dbg_run_cmd(struct hnae3_handle *handle, char *cmd_buf); u16 hclge_covert_handle_qid_global(struct hnae3_handle *handle, u16 queue_id); int hclge_notify_client(struct hclge_dev *hdev, enum hnae3_reset_notify_type type); +void hclge_add_vport_mac_table(struct hclge_vport *vport, const u8 *mac_addr, + enum HCLGE_MAC_ADDR_TYPE mac_type); +void hclge_rm_vport_mac_table(struct hclge_vport *vport, const u8 *mac_addr, + bool is_write_tbl, + enum HCLGE_MAC_ADDR_TYPE mac_type); +void hclge_rm_vport_all_mac_table(struct hclge_vport *vport, bool is_del_list, + enum HCLGE_MAC_ADDR_TYPE mac_type); +void hclge_uninit_vport_mac_table(struct hclge_dev *hdev); +void hclge_add_vport_vlan_table(struct hclge_vport *vport, u16 vlan_id); +void hclge_rm_vport_vlan_table(struct hclge_vport *vport, u16 vlan_id, + bool is_write_tbl); +void hclge_rm_vport_all_vlan_table(struct hclge_vport *vport, bool is_del_list); +void hclge_uninit_vport_vlan_table(struct hclge_dev *hdev); #endif diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index 7e4a104582d6..9e0952c329bb 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -224,12 +224,24 @@ static int hclge_set_vf_uc_mac_addr(struct hclge_vport *vport, hclge_rm_uc_addr_common(vport, old_addr); status = hclge_add_uc_addr_common(vport, mac_addr); - if (status) + if (status) { hclge_add_uc_addr_common(vport, old_addr); + } else { + hclge_rm_vport_mac_table(vport, mac_addr, + false, HCLGE_MAC_ADDR_UC); + hclge_add_vport_mac_table(vport, mac_addr, + HCLGE_MAC_ADDR_UC); + } } else if (mbx_req->msg[1] == HCLGE_MBX_MAC_VLAN_UC_ADD) { status = hclge_add_uc_addr_common(vport, mac_addr); + if (!status) + hclge_add_vport_mac_table(vport, mac_addr, + HCLGE_MAC_ADDR_UC); } else if (mbx_req->msg[1] == HCLGE_MBX_MAC_VLAN_UC_REMOVE) { status = hclge_rm_uc_addr_common(vport, mac_addr); + if (!status) + hclge_rm_vport_mac_table(vport, mac_addr, + false, HCLGE_MAC_ADDR_UC); } else { dev_err(&hdev->pdev->dev, "failed to set unicast mac addr, unknown subcode %d\n", @@ -255,8 +267,14 @@ static int hclge_set_vf_mc_mac_addr(struct hclge_vport *vport, if (mbx_req->msg[1] == HCLGE_MBX_MAC_VLAN_MC_ADD) { status = hclge_add_mc_addr_common(vport, mac_addr); + if (!status) + hclge_add_vport_mac_table(vport, mac_addr, + HCLGE_MAC_ADDR_MC); } else if (mbx_req->msg[1] == HCLGE_MBX_MAC_VLAN_MC_REMOVE) { status = hclge_rm_mc_addr_common(vport, mac_addr); + if (!status) + hclge_rm_vport_mac_table(vport, mac_addr, + false, HCLGE_MAC_ADDR_MC); } else { dev_err(&hdev->pdev->dev, "failed to set mcast mac addr, unknown subcode %d\n", @@ -287,6 +305,9 @@ static int hclge_set_vf_vlan_cfg(struct hclge_vport *vport, memcpy(&proto, &mbx_req->msg[5], sizeof(proto)); status = hclge_set_vlan_filter(handle, cpu_to_be16(proto), vlan, is_kill); + if (!status) + is_kill ? hclge_rm_vport_vlan_table(vport, vlan, false) + : hclge_add_vport_vlan_table(vport, vlan); } else if (mbx_req->msg[1] == HCLGE_MBX_VLAN_RX_OFF_CFG) { struct hnae3_handle *handle = &vport->nic; bool en = mbx_req->msg[2] ? true : false; @@ -585,6 +606,15 @@ void hclge_mbx_handler(struct hclge_dev *hdev) case HCLGE_MBX_GET_LINK_MODE: hclge_get_link_mode(vport, req); break; + case HCLGE_MBX_GET_VF_FLR_STATUS: + mutex_lock(&hdev->vport_cfg_mutex); + hclge_rm_vport_all_mac_table(vport, true, + HCLGE_MAC_ADDR_UC); + hclge_rm_vport_all_mac_table(vport, true, + HCLGE_MAC_ADDR_MC); + hclge_rm_vport_all_vlan_table(vport, true); + mutex_unlock(&hdev->vport_cfg_mutex); + break; default: dev_err(&hdev->pdev->dev, "un-supported mailbox message, code = %d\n", diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c index 84f28785ba28..48eda2c6fdae 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c @@ -8,12 +8,6 @@ #include "hclge_main.h" #include "hclge_mdio.h" -#define HCLGE_PHY_SUPPORTED_FEATURES (SUPPORTED_Autoneg | \ - SUPPORTED_TP | \ - PHY_10BT_FEATURES | \ - PHY_100BT_FEATURES | \ - SUPPORTED_1000baseT_Full) - enum hclge_mdio_c22_op_seq { HCLGE_MDIO_C22_WRITE = 1, HCLGE_MDIO_C22_READ = 2 @@ -217,16 +211,9 @@ int hclge_mac_connect_phy(struct hnae3_handle *handle) return ret; } - linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, mask); - linkmode_set_bit(ETHTOOL_LINK_MODE_TP_BIT, mask); - linkmode_set_bit_array(phy_10_100_features_array, - ARRAY_SIZE(phy_10_100_features_array), - mask); - linkmode_set_bit_array(phy_gbit_features_array, - ARRAY_SIZE(phy_gbit_features_array), - mask); + linkmode_copy(mask, hdev->hw.mac.supported); linkmode_and(phydev->supported, phydev->supported, mask); - phy_support_asym_pause(phydev); + linkmode_copy(phydev->advertising, phydev->supported); return 0; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c index 4e78e8812a04..9441b453d38d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c @@ -362,8 +362,28 @@ int hclgevf_cmd_init(struct hclgevf_dev *hdev) return 0; } +static void hclgevf_cmd_uninit_regs(struct hclgevf_hw *hw) +{ + hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_BASEADDR_L_REG, 0); + hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_BASEADDR_H_REG, 0); + hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_DEPTH_REG, 0); + hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_HEAD_REG, 0); + hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_TAIL_REG, 0); + hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_BASEADDR_L_REG, 0); + hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_BASEADDR_H_REG, 0); + hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_DEPTH_REG, 0); + hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_HEAD_REG, 0); + hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_TAIL_REG, 0); +} + void hclgevf_cmd_uninit(struct hclgevf_dev *hdev) { + spin_lock_bh(&hdev->hw.cmq.csq.lock); + spin_lock(&hdev->hw.cmq.crq.lock); + clear_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state); + hclgevf_cmd_uninit_regs(&hdev->hw); + spin_unlock(&hdev->hw.cmq.crq.lock); + spin_unlock_bh(&hdev->hw.cmq.csq.lock); hclgevf_free_cmd_desc(&hdev->hw.cmq.csq); hclgevf_free_cmd_desc(&hdev->hw.cmq.crq); } diff --git a/drivers/net/ethernet/i825xx/lib82596.c b/drivers/net/ethernet/i825xx/lib82596.c index 2f7ae118217f..1274ad24d6af 100644 --- a/drivers/net/ethernet/i825xx/lib82596.c +++ b/drivers/net/ethernet/i825xx/lib82596.c @@ -1194,7 +1194,7 @@ static irqreturn_t i596_interrupt(int irq, void *dev_id) dma_unmap_single(dev->dev.parent, tx_cmd->dma_addr, skb->len, DMA_TO_DEVICE); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); tx_cmd->cmd.command = 0; /* Mark free */ break; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 6fd15a734324..5a0419421511 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -1603,14 +1603,12 @@ static int fm10k_alloc_q_vector(struct fm10k_intfc *interface, { struct fm10k_q_vector *q_vector; struct fm10k_ring *ring; - int ring_count, size; + int ring_count; ring_count = txr_count + rxr_count; - size = sizeof(struct fm10k_q_vector) + - (sizeof(struct fm10k_ring) * ring_count); /* allocate q_vector and rings */ - q_vector = kzalloc(size, GFP_KERNEL); + q_vector = kzalloc(struct_size(q_vector, ring, ring_count), GFP_KERNEL); if (!q_vector) return -ENOMEM; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 44856a84738d..5e74a5127849 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -12128,9 +12128,6 @@ static int i40e_xdp(struct net_device *dev, case XDP_QUERY_PROG: xdp->prog_id = vsi->xdp_prog ? vsi->xdp_prog->aux->id : 0; return 0; - case XDP_QUERY_XSK_UMEM: - return i40e_xsk_umem_query(vsi, &xdp->xsk.umem, - xdp->xsk.queue_id); case XDP_SETUP_XSK_UMEM: return i40e_xsk_umem_setup(vsi, xdp->xsk.umem, xdp->xsk.queue_id); diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 96d849460d9b..e190a2c2b9ff 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -155,34 +155,6 @@ static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid) } /** - * i40e_xsk_umem_query - Queries a certain ring/qid for its UMEM - * @vsi: Current VSI - * @umem: UMEM associated to the ring, if any - * @qid: Rx ring to associate UMEM to - * - * This function will store, if any, the UMEM associated to certain ring. - * - * Returns 0 on success, <0 on failure - **/ -int i40e_xsk_umem_query(struct i40e_vsi *vsi, struct xdp_umem **umem, - u16 qid) -{ - struct net_device *netdev = vsi->netdev; - struct xdp_umem *queried_umem; - - if (vsi->type != I40E_VSI_MAIN) - return -EINVAL; - - queried_umem = xdp_get_umem_from_qid(netdev, qid); - - if (!queried_umem) - return -EINVAL; - - *umem = queried_umem; - return 0; -} - -/** * i40e_xsk_umem_setup - Enable/disassociate a UMEM to/from a ring/qid * @vsi: Current VSI * @umem: UMEM to enable/associate to a ring, or NULL to disable diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h index 9038c5d5cf08..8cc0a2e7d9a2 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h @@ -10,8 +10,6 @@ struct zero_copy_allocator; int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair); int i40e_queue_pair_enable(struct i40e_vsi *vsi, int queue_pair); -int i40e_xsk_umem_query(struct i40e_vsi *vsi, struct xdp_umem **umem, - u16 qid); int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem, u16 qid); void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 6d812e96572d..69b230c53fed 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -1189,15 +1189,15 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter, { struct igb_q_vector *q_vector; struct igb_ring *ring; - int ring_count, size; + int ring_count; + size_t size; /* igb only supports 1 Tx and/or 1 Rx queue per vector */ if (txr_count > 1 || rxr_count > 1) return -ENOMEM; ring_count = txr_count + rxr_count; - size = sizeof(struct igb_q_vector) + - (sizeof(struct igb_ring) * ring_count); + size = struct_size(q_vector, ring, ring_count); /* allocate q_vector and rings */ q_vector = adapter->q_vector[v_idx]; diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 11c75433fe22..87a11879bf2d 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -2958,22 +2958,21 @@ static int igc_alloc_q_vector(struct igc_adapter *adapter, { struct igc_q_vector *q_vector; struct igc_ring *ring; - int ring_count, size; + int ring_count; /* igc only supports 1 Tx and/or 1 Rx queue per vector */ if (txr_count > 1 || rxr_count > 1) return -ENOMEM; ring_count = txr_count + rxr_count; - size = sizeof(struct igc_q_vector) + - (sizeof(struct igc_ring) * ring_count); /* allocate q_vector and rings */ q_vector = adapter->q_vector[v_idx]; if (!q_vector) - q_vector = kzalloc(size, GFP_KERNEL); + q_vector = kzalloc(struct_size(q_vector, ring, ring_count), + GFP_KERNEL); else - memset(q_vector, 0, size); + memset(q_vector, 0, struct_size(q_vector, ring, ring_count)); if (!q_vector) return -ENOMEM; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c index 62e6499e4146..cc3196ae5aea 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -836,12 +836,10 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter, struct ixgbe_ring *ring; int node = NUMA_NO_NODE; int cpu = -1; - int ring_count, size; + int ring_count; u8 tcs = adapter->hw_tcs; ring_count = txr_count + rxr_count + xdp_count; - size = sizeof(struct ixgbe_q_vector) + - (sizeof(struct ixgbe_ring) * ring_count); /* customize cpu for Flow Director mapping */ if ((tcs <= 1) && !(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) { @@ -855,9 +853,11 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter, } /* allocate q_vector and rings */ - q_vector = kzalloc_node(size, GFP_KERNEL, node); + q_vector = kzalloc_node(struct_size(q_vector, ring, ring_count), + GFP_KERNEL, node); if (!q_vector) - q_vector = kzalloc(size, GFP_KERNEL); + q_vector = kzalloc(struct_size(q_vector, ring, ring_count), + GFP_KERNEL); if (!q_vector) return -ENOMEM; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index b53087a980ef..38c430b94ae3 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -10280,9 +10280,6 @@ static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp) xdp->prog_id = adapter->xdp_prog ? adapter->xdp_prog->aux->id : 0; return 0; - case XDP_QUERY_XSK_UMEM: - return ixgbe_xsk_umem_query(adapter, &xdp->xsk.umem, - xdp->xsk.queue_id); case XDP_SETUP_XSK_UMEM: return ixgbe_xsk_umem_setup(adapter, xdp->xsk.umem, xdp->xsk.queue_id); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h index 53d4089f5644..d93a690aff74 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h @@ -30,8 +30,6 @@ void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring); struct xdp_umem *ixgbe_xsk_umem(struct ixgbe_adapter *adapter, struct ixgbe_ring *ring); -int ixgbe_xsk_umem_query(struct ixgbe_adapter *adapter, struct xdp_umem **umem, - u16 qid); int ixgbe_xsk_umem_setup(struct ixgbe_adapter *adapter, struct xdp_umem *umem, u16 qid); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index 65c3e2c979d4..98870707b51a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -174,23 +174,6 @@ static int ixgbe_xsk_umem_disable(struct ixgbe_adapter *adapter, u16 qid) return 0; } -int ixgbe_xsk_umem_query(struct ixgbe_adapter *adapter, struct xdp_umem **umem, - u16 qid) -{ - if (qid >= adapter->num_rx_queues) - return -EINVAL; - - if (adapter->xsk_umems) { - if (qid >= adapter->num_xsk_umems) - return -EINVAL; - *umem = adapter->xsk_umems[qid]; - return 0; - } - - *umem = NULL; - return 0; -} - int ixgbe_xsk_umem_setup(struct ixgbe_adapter *adapter, struct xdp_umem *umem, u16 qid) { diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c index 32ac9045cdae..f9bb890733b5 100644 --- a/drivers/net/ethernet/lantiq_etop.c +++ b/drivers/net/ethernet/lantiq_etop.c @@ -112,10 +112,12 @@ struct ltq_etop_priv { static int ltq_etop_alloc_skb(struct ltq_etop_chan *ch) { + struct ltq_etop_priv *priv = netdev_priv(ch->netdev); + ch->skb[ch->dma.desc] = netdev_alloc_skb(ch->netdev, MAX_DMA_DATA_LEN); if (!ch->skb[ch->dma.desc]) return -ENOMEM; - ch->dma.desc_base[ch->dma.desc].addr = dma_map_single(NULL, + ch->dma.desc_base[ch->dma.desc].addr = dma_map_single(&priv->pdev->dev, ch->skb[ch->dma.desc]->data, MAX_DMA_DATA_LEN, DMA_FROM_DEVICE); ch->dma.desc_base[ch->dma.desc].addr = @@ -487,7 +489,7 @@ ltq_etop_tx(struct sk_buff *skb, struct net_device *dev) netif_trans_update(dev); spin_lock_irqsave(&priv->lock, flags); - desc->addr = ((unsigned int) dma_map_single(NULL, skb->data, len, + desc->addr = ((unsigned int) dma_map_single(&priv->pdev->dev, skb->data, len, DMA_TO_DEVICE)) - byte_offset; wmb(); desc->ctl = LTQ_DMA_OWN | LTQ_DMA_SOP | LTQ_DMA_EOP | diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 2f427271a793..292a668ce88e 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -2879,7 +2879,7 @@ static int mv643xx_eth_shared_probe(struct platform_device *pdev) ret = mv643xx_eth_shared_of_probe(pdev); if (ret) - return ret; + goto err_put_clk; pd = dev_get_platdata(&pdev->dev); msp->tx_csum_limit = (pd != NULL && pd->tx_csum_limit) ? @@ -2887,6 +2887,11 @@ static int mv643xx_eth_shared_probe(struct platform_device *pdev) infer_hw_params(msp); return 0; + +err_put_clk: + if (!IS_ERR(msp->clk)) + clk_disable_unprepare(msp->clk); + return ret; } static int mv643xx_eth_shared_remove(struct platform_device *pdev) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 9d4568eb2297..d134d3538f9b 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -27,6 +27,7 @@ #include <linux/of_irq.h> #include <linux/of_mdio.h> #include <linux/of_net.h> +#include <linux/phy/phy.h> #include <linux/phy.h> #include <linux/phylink.h> #include <linux/platform_device.h> @@ -436,6 +437,7 @@ struct mvneta_port { struct device_node *dn; unsigned int tx_csum_limit; struct phylink *phylink; + struct phy *comphy; struct mvneta_bm *bm_priv; struct mvneta_bm_pool *pool_long; @@ -3151,6 +3153,8 @@ static void mvneta_start_dev(struct mvneta_port *pp) { int cpu; + WARN_ON(phy_power_on(pp->comphy)); + mvneta_max_rx_size_set(pp, pp->pkt_size); mvneta_txq_max_tx_size_set(pp, pp->pkt_size); @@ -3213,6 +3217,8 @@ static void mvneta_stop_dev(struct mvneta_port *pp) mvneta_tx_reset(pp); mvneta_rx_reset(pp); + + WARN_ON(phy_power_off(pp->comphy)); } static void mvneta_percpu_enable(void *arg) @@ -3338,6 +3344,7 @@ static int mvneta_set_mac_addr(struct net_device *dev, void *addr) static void mvneta_validate(struct net_device *ndev, unsigned long *supported, struct phylink_link_state *state) { + struct mvneta_port *pp = netdev_priv(ndev); __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; /* We only support QSGMII, SGMII, 802.3z and RGMII modes */ @@ -3358,8 +3365,13 @@ static void mvneta_validate(struct net_device *ndev, unsigned long *supported, phylink_set(mask, Pause); /* Half-duplex at speeds higher than 100Mbit is unsupported */ - phylink_set(mask, 1000baseT_Full); - phylink_set(mask, 1000baseX_Full); + if (pp->comphy || state->interface != PHY_INTERFACE_MODE_2500BASEX) { + phylink_set(mask, 1000baseT_Full); + phylink_set(mask, 1000baseX_Full); + } + if (pp->comphy || state->interface == PHY_INTERFACE_MODE_2500BASEX) { + phylink_set(mask, 2500baseX_Full); + } if (!phy_interface_mode_is_8023z(state->interface)) { /* 10M and 100M are only supported in non-802.3z mode */ @@ -3373,6 +3385,11 @@ static void mvneta_validate(struct net_device *ndev, unsigned long *supported, __ETHTOOL_LINK_MODE_MASK_NBITS); bitmap_and(state->advertising, state->advertising, mask, __ETHTOOL_LINK_MODE_MASK_NBITS); + + /* We can only operate at 2500BaseX or 1000BaseX. If requested + * to advertise both, only report advertising at 2500BaseX. + */ + phylink_helper_basex_speed(state); } static int mvneta_mac_link_state(struct net_device *ndev, @@ -3384,7 +3401,9 @@ static int mvneta_mac_link_state(struct net_device *ndev, gmac_stat = mvreg_read(pp, MVNETA_GMAC_STATUS); if (gmac_stat & MVNETA_GMAC_SPEED_1000) - state->speed = SPEED_1000; + state->speed = + state->interface == PHY_INTERFACE_MODE_2500BASEX ? + SPEED_2500 : SPEED_1000; else if (gmac_stat & MVNETA_GMAC_SPEED_100) state->speed = SPEED_100; else @@ -3499,12 +3518,20 @@ static void mvneta_mac_config(struct net_device *ndev, unsigned int mode, MVNETA_GMAC_FORCE_LINK_DOWN); } + /* When at 2.5G, the link partner can send frames with shortened * preambles. */ if (state->speed == SPEED_2500) new_ctrl4 |= MVNETA_GMAC4_SHORT_PREAMBLE_ENABLE; + if (pp->comphy && + (state->interface == PHY_INTERFACE_MODE_SGMII || + state->interface == PHY_INTERFACE_MODE_1000BASEX || + state->interface == PHY_INTERFACE_MODE_2500BASEX)) + WARN_ON(phy_set_mode_ext(pp->comphy, PHY_MODE_ETHERNET, + state->interface)); + if (new_ctrl0 != gmac_ctrl0) mvreg_write(pp, MVNETA_GMAC_CTRL_0, new_ctrl0); if (new_ctrl2 != gmac_ctrl2) @@ -4404,7 +4431,7 @@ static int mvneta_port_power_up(struct mvneta_port *pp, int phy_mode) if (phy_mode == PHY_INTERFACE_MODE_QSGMII) mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_QSGMII_SERDES_PROTO); else if (phy_mode == PHY_INTERFACE_MODE_SGMII || - phy_mode == PHY_INTERFACE_MODE_1000BASEX) + phy_interface_mode_is_8023z(phy_mode)) mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_SGMII_SERDES_PROTO); else if (!phy_interface_mode_is_rgmii(phy_mode)) return -EINVAL; @@ -4421,6 +4448,7 @@ static int mvneta_probe(struct platform_device *pdev) struct mvneta_port *pp; struct net_device *dev; struct phylink *phylink; + struct phy *comphy; const char *dt_mac_addr; char hw_mac_addr[ETH_ALEN]; const char *mac_from; @@ -4446,6 +4474,14 @@ static int mvneta_probe(struct platform_device *pdev) goto err_free_irq; } + comphy = devm_of_phy_get(&pdev->dev, dn, NULL); + if (comphy == ERR_PTR(-EPROBE_DEFER)) { + err = -EPROBE_DEFER; + goto err_free_irq; + } else if (IS_ERR(comphy)) { + comphy = NULL; + } + phylink = phylink_create(dev, pdev->dev.fwnode, phy_mode, &mvneta_phylink_ops); if (IS_ERR(phylink)) { @@ -4462,6 +4498,7 @@ static int mvneta_probe(struct platform_device *pdev) pp = netdev_priv(dev); spin_lock_init(&pp->lock); pp->phylink = phylink; + pp->comphy = comphy; pp->phy_interface = phy_mode; pp->dn = dn; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h index 398328f10743..96e3f0669032 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h @@ -402,8 +402,8 @@ #define MVPP2_GMAC_STATUS0_GMII_SPEED BIT(1) #define MVPP2_GMAC_STATUS0_MII_SPEED BIT(2) #define MVPP2_GMAC_STATUS0_FULL_DUPLEX BIT(3) -#define MVPP2_GMAC_STATUS0_RX_PAUSE BIT(6) -#define MVPP2_GMAC_STATUS0_TX_PAUSE BIT(7) +#define MVPP2_GMAC_STATUS0_RX_PAUSE BIT(4) +#define MVPP2_GMAC_STATUS0_TX_PAUSE BIT(5) #define MVPP2_GMAC_STATUS0_AN_COMPLETE BIT(11) #define MVPP2_GMAC_PORT_FIFO_CFG_1_REG 0x1c #define MVPP2_GMAC_TX_FIFO_MIN_TH_OFFS 6 diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 5c0c26fd8363..191d9ce85b7e 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -965,6 +965,11 @@ mvpp2_shared_interrupt_mask_unmask(struct mvpp2_port *port, bool mask) } /* Port configuration routines */ +static bool mvpp2_is_xlg(phy_interface_t interface) +{ + return interface == PHY_INTERFACE_MODE_10GKR || + interface == PHY_INTERFACE_MODE_XAUI; +} static void mvpp22_gop_init_rgmii(struct mvpp2_port *port) { @@ -1101,7 +1106,7 @@ static void mvpp22_gop_unmask_irq(struct mvpp2_port *port) if (port->gop_id == 0) { /* Enable the XLG/GIG irqs for this port */ val = readl(port->base + MVPP22_XLG_EXT_INT_MASK); - if (port->phy_interface == PHY_INTERFACE_MODE_10GKR) + if (mvpp2_is_xlg(port->phy_interface)) val |= MVPP22_XLG_EXT_INT_MASK_XLG; else val |= MVPP22_XLG_EXT_INT_MASK_GIG; @@ -1181,9 +1186,7 @@ static void mvpp2_port_enable(struct mvpp2_port *port) u32 val; /* Only GOP port 0 has an XLG MAC */ - if (port->gop_id == 0 && - (port->phy_interface == PHY_INTERFACE_MODE_XAUI || - port->phy_interface == PHY_INTERFACE_MODE_10GKR)) { + if (port->gop_id == 0 && mvpp2_is_xlg(port->phy_interface)) { val = readl(port->base + MVPP22_XLG_CTRL0_REG); val |= MVPP22_XLG_CTRL0_PORT_EN | MVPP22_XLG_CTRL0_MAC_RESET_DIS; @@ -1202,9 +1205,7 @@ static void mvpp2_port_disable(struct mvpp2_port *port) u32 val; /* Only GOP port 0 has an XLG MAC */ - if (port->gop_id == 0 && - (port->phy_interface == PHY_INTERFACE_MODE_XAUI || - port->phy_interface == PHY_INTERFACE_MODE_10GKR)) { + if (port->gop_id == 0 && mvpp2_is_xlg(port->phy_interface)) { val = readl(port->base + MVPP22_XLG_CTRL0_REG); val &= ~MVPP22_XLG_CTRL0_PORT_EN; writel(val, port->base + MVPP22_XLG_CTRL0_REG); @@ -1377,13 +1378,9 @@ static void mvpp2_port_reset(struct mvpp2_port *port) for (i = 0; i < ARRAY_SIZE(mvpp2_ethtool_regs); i++) mvpp2_read_count(port, &mvpp2_ethtool_regs[i]); - val = readl(port->base + MVPP2_GMAC_CTRL_2_REG) & - ~MVPP2_GMAC_PORT_RESET_MASK; + val = readl(port->base + MVPP2_GMAC_CTRL_2_REG) | + MVPP2_GMAC_PORT_RESET_MASK; writel(val, port->base + MVPP2_GMAC_CTRL_2_REG); - - while (readl(port->base + MVPP2_GMAC_CTRL_2_REG) & - MVPP2_GMAC_PORT_RESET_MASK) - continue; } /* Change maximum receive size of the port */ @@ -2459,8 +2456,7 @@ static irqreturn_t mvpp2_link_status_isr(int irq, void *dev_id) mvpp22_gop_mask_irq(port); - if (port->gop_id == 0 && - port->phy_interface == PHY_INTERFACE_MODE_10GKR) { + if (port->gop_id == 0 && mvpp2_is_xlg(port->phy_interface)) { val = readl(port->base + MVPP22_XLG_INT_STAT); if (val & MVPP22_XLG_INT_STAT_LINK) { event = true; @@ -3150,8 +3146,7 @@ static void mvpp22_mode_reconfigure(struct mvpp2_port *port) ctrl3 = readl(port->base + MVPP22_XLG_CTRL3_REG); ctrl3 &= ~MVPP22_XLG_CTRL3_MACMODESELECT_MASK; - if (port->phy_interface == PHY_INTERFACE_MODE_XAUI || - port->phy_interface == PHY_INTERFACE_MODE_10GKR) + if (mvpp2_is_xlg(port->phy_interface)) ctrl3 |= MVPP22_XLG_CTRL3_MACMODESELECT_10G; else ctrl3 |= MVPP22_XLG_CTRL3_MACMODESELECT_GMAC; @@ -3159,9 +3154,7 @@ static void mvpp22_mode_reconfigure(struct mvpp2_port *port) writel(ctrl3, port->base + MVPP22_XLG_CTRL3_REG); } - if (port->gop_id == 0 && - (port->phy_interface == PHY_INTERFACE_MODE_XAUI || - port->phy_interface == PHY_INTERFACE_MODE_10GKR)) + if (port->gop_id == 0 && mvpp2_is_xlg(port->phy_interface)) mvpp2_xlg_max_rx_size_set(port); else mvpp2_gmac_max_rx_size_set(port); @@ -4501,17 +4494,12 @@ static int mvpp2_phylink_mac_link_state(struct net_device *dev, static void mvpp2_mac_an_restart(struct net_device *dev) { struct mvpp2_port *port = netdev_priv(dev); - u32 val; + u32 val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG); - if (port->phy_interface != PHY_INTERFACE_MODE_SGMII) - return; - - val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG); - /* The RESTART_AN bit is cleared by the h/w after restarting the AN - * process. - */ - val |= MVPP2_GMAC_IN_BAND_RESTART_AN | MVPP2_GMAC_IN_BAND_AUTONEG; - writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG); + writel(val | MVPP2_GMAC_IN_BAND_RESTART_AN, + port->base + MVPP2_GMAC_AUTONEG_CONFIG); + writel(val & ~MVPP2_GMAC_IN_BAND_RESTART_AN, + port->base + MVPP2_GMAC_AUTONEG_CONFIG); } static void mvpp2_xlg_config(struct mvpp2_port *port, unsigned int mode, @@ -4524,8 +4512,13 @@ static void mvpp2_xlg_config(struct mvpp2_port *port, unsigned int mode, if (state->pause & MLO_PAUSE_TX) ctrl0 |= MVPP22_XLG_CTRL0_TX_FLOW_CTRL_EN; + else + ctrl0 &= ~MVPP22_XLG_CTRL0_TX_FLOW_CTRL_EN; + if (state->pause & MLO_PAUSE_RX) ctrl0 |= MVPP22_XLG_CTRL0_RX_FLOW_CTRL_EN; + else + ctrl0 &= ~MVPP22_XLG_CTRL0_RX_FLOW_CTRL_EN; ctrl4 &= ~MVPP22_XLG_CTRL4_MACMODSELECT_GMAC; ctrl4 |= MVPP22_XLG_CTRL4_FWD_FC | MVPP22_XLG_CTRL4_FWD_PFC | @@ -4538,83 +4531,130 @@ static void mvpp2_xlg_config(struct mvpp2_port *port, unsigned int mode, static void mvpp2_gmac_config(struct mvpp2_port *port, unsigned int mode, const struct phylink_link_state *state) { - u32 an, ctrl0, ctrl2, ctrl4; - - an = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG); - ctrl0 = readl(port->base + MVPP2_GMAC_CTRL_0_REG); - ctrl2 = readl(port->base + MVPP2_GMAC_CTRL_2_REG); - ctrl4 = readl(port->base + MVPP22_GMAC_CTRL_4_REG); - - /* Force link down */ - an &= ~MVPP2_GMAC_FORCE_LINK_PASS; - an |= MVPP2_GMAC_FORCE_LINK_DOWN; - writel(an, port->base + MVPP2_GMAC_AUTONEG_CONFIG); + u32 old_an, an; + u32 old_ctrl0, ctrl0; + u32 old_ctrl2, ctrl2; + u32 old_ctrl4, ctrl4; - /* Set the GMAC in a reset state */ - ctrl2 |= MVPP2_GMAC_PORT_RESET_MASK; - writel(ctrl2, port->base + MVPP2_GMAC_CTRL_2_REG); + old_an = an = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG); + old_ctrl0 = ctrl0 = readl(port->base + MVPP2_GMAC_CTRL_0_REG); + old_ctrl2 = ctrl2 = readl(port->base + MVPP2_GMAC_CTRL_2_REG); + old_ctrl4 = ctrl4 = readl(port->base + MVPP22_GMAC_CTRL_4_REG); an &= ~(MVPP2_GMAC_CONFIG_MII_SPEED | MVPP2_GMAC_CONFIG_GMII_SPEED | MVPP2_GMAC_AN_SPEED_EN | MVPP2_GMAC_FC_ADV_EN | MVPP2_GMAC_FC_ADV_ASM_EN | MVPP2_GMAC_FLOW_CTRL_AUTONEG | MVPP2_GMAC_CONFIG_FULL_DUPLEX | MVPP2_GMAC_AN_DUPLEX_EN | - MVPP2_GMAC_FORCE_LINK_DOWN); + MVPP2_GMAC_IN_BAND_AUTONEG | MVPP2_GMAC_IN_BAND_AUTONEG_BYPASS); ctrl0 &= ~MVPP2_GMAC_PORT_TYPE_MASK; - ctrl2 &= ~(MVPP2_GMAC_PORT_RESET_MASK | MVPP2_GMAC_PCS_ENABLE_MASK); + ctrl2 &= ~(MVPP2_GMAC_INBAND_AN_MASK | MVPP2_GMAC_PORT_RESET_MASK | + MVPP2_GMAC_PCS_ENABLE_MASK); + ctrl4 &= ~(MVPP22_CTRL4_RX_FC_EN | MVPP22_CTRL4_TX_FC_EN); + /* Configure port type */ if (phy_interface_mode_is_8023z(state->interface)) { - /* 1000BaseX and 2500BaseX ports cannot negotiate speed nor can - * they negotiate duplex: they are always operating with a fixed - * speed of 1000/2500Mbps in full duplex, so force 1000/2500 - * speed and full duplex here. - */ - ctrl0 |= MVPP2_GMAC_PORT_TYPE_MASK; - an |= MVPP2_GMAC_CONFIG_GMII_SPEED | - MVPP2_GMAC_CONFIG_FULL_DUPLEX; - } else if (!phy_interface_mode_is_rgmii(state->interface)) { - an |= MVPP2_GMAC_AN_SPEED_EN | MVPP2_GMAC_FLOW_CTRL_AUTONEG; + ctrl2 |= MVPP2_GMAC_PCS_ENABLE_MASK; + ctrl4 &= ~MVPP22_CTRL4_EXT_PIN_GMII_SEL; + ctrl4 |= MVPP22_CTRL4_SYNC_BYPASS_DIS | + MVPP22_CTRL4_DP_CLK_SEL | + MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE; + } else if (state->interface == PHY_INTERFACE_MODE_SGMII) { + ctrl2 |= MVPP2_GMAC_PCS_ENABLE_MASK | MVPP2_GMAC_INBAND_AN_MASK; + ctrl4 &= ~MVPP22_CTRL4_EXT_PIN_GMII_SEL; + ctrl4 |= MVPP22_CTRL4_SYNC_BYPASS_DIS | + MVPP22_CTRL4_DP_CLK_SEL | + MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE; + } else if (phy_interface_mode_is_rgmii(state->interface)) { + ctrl4 &= ~MVPP22_CTRL4_DP_CLK_SEL; + ctrl4 |= MVPP22_CTRL4_EXT_PIN_GMII_SEL | + MVPP22_CTRL4_SYNC_BYPASS_DIS | + MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE; } - if (state->duplex) - an |= MVPP2_GMAC_CONFIG_FULL_DUPLEX; + /* Configure advertisement bits */ if (phylink_test(state->advertising, Pause)) an |= MVPP2_GMAC_FC_ADV_EN; if (phylink_test(state->advertising, Asym_Pause)) an |= MVPP2_GMAC_FC_ADV_ASM_EN; - if (phy_interface_mode_is_8023z(state->interface) || - state->interface == PHY_INTERFACE_MODE_SGMII) { - an |= MVPP2_GMAC_IN_BAND_AUTONEG; - ctrl2 |= MVPP2_GMAC_INBAND_AN_MASK | MVPP2_GMAC_PCS_ENABLE_MASK; + /* Configure negotiation style */ + if (!phylink_autoneg_inband(mode)) { + /* Phy or fixed speed - no in-band AN */ + if (state->duplex) + an |= MVPP2_GMAC_CONFIG_FULL_DUPLEX; - ctrl4 &= ~(MVPP22_CTRL4_EXT_PIN_GMII_SEL | - MVPP22_CTRL4_RX_FC_EN | MVPP22_CTRL4_TX_FC_EN); - ctrl4 |= MVPP22_CTRL4_SYNC_BYPASS_DIS | - MVPP22_CTRL4_DP_CLK_SEL | - MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE; + if (state->speed == SPEED_1000 || state->speed == SPEED_2500) + an |= MVPP2_GMAC_CONFIG_GMII_SPEED; + else if (state->speed == SPEED_100) + an |= MVPP2_GMAC_CONFIG_MII_SPEED; if (state->pause & MLO_PAUSE_TX) ctrl4 |= MVPP22_CTRL4_TX_FC_EN; if (state->pause & MLO_PAUSE_RX) ctrl4 |= MVPP22_CTRL4_RX_FC_EN; - } else if (phy_interface_mode_is_rgmii(state->interface)) { - an |= MVPP2_GMAC_IN_BAND_AUTONEG_BYPASS; + } else if (state->interface == PHY_INTERFACE_MODE_SGMII) { + /* SGMII in-band mode receives the speed and duplex from + * the PHY. Flow control information is not received. */ + an &= ~(MVPP2_GMAC_FORCE_LINK_DOWN | MVPP2_GMAC_FORCE_LINK_PASS); + an |= MVPP2_GMAC_IN_BAND_AUTONEG | + MVPP2_GMAC_AN_SPEED_EN | + MVPP2_GMAC_AN_DUPLEX_EN; - if (state->speed == SPEED_1000) - an |= MVPP2_GMAC_CONFIG_GMII_SPEED; - else if (state->speed == SPEED_100) - an |= MVPP2_GMAC_CONFIG_MII_SPEED; + if (state->pause & MLO_PAUSE_TX) + ctrl4 |= MVPP22_CTRL4_TX_FC_EN; + if (state->pause & MLO_PAUSE_RX) + ctrl4 |= MVPP22_CTRL4_RX_FC_EN; + } else if (phy_interface_mode_is_8023z(state->interface)) { + /* 1000BaseX and 2500BaseX ports cannot negotiate speed nor can + * they negotiate duplex: they are always operating with a fixed + * speed of 1000/2500Mbps in full duplex, so force 1000/2500 + * speed and full duplex here. + */ + ctrl0 |= MVPP2_GMAC_PORT_TYPE_MASK; + an &= ~(MVPP2_GMAC_FORCE_LINK_DOWN | MVPP2_GMAC_FORCE_LINK_PASS); + an |= MVPP2_GMAC_IN_BAND_AUTONEG | + MVPP2_GMAC_CONFIG_GMII_SPEED | + MVPP2_GMAC_CONFIG_FULL_DUPLEX; - ctrl4 &= ~MVPP22_CTRL4_DP_CLK_SEL; - ctrl4 |= MVPP22_CTRL4_EXT_PIN_GMII_SEL | - MVPP22_CTRL4_SYNC_BYPASS_DIS | - MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE; + if (state->pause & MLO_PAUSE_AN && state->an_enabled) { + an |= MVPP2_GMAC_FLOW_CTRL_AUTONEG; + } else { + if (state->pause & MLO_PAUSE_TX) + ctrl4 |= MVPP22_CTRL4_TX_FC_EN; + if (state->pause & MLO_PAUSE_RX) + ctrl4 |= MVPP22_CTRL4_RX_FC_EN; + } } - writel(ctrl0, port->base + MVPP2_GMAC_CTRL_0_REG); - writel(ctrl2, port->base + MVPP2_GMAC_CTRL_2_REG); - writel(ctrl4, port->base + MVPP22_GMAC_CTRL_4_REG); - writel(an, port->base + MVPP2_GMAC_AUTONEG_CONFIG); + if ((old_ctrl0 ^ ctrl0) & MVPP2_GMAC_PORT_TYPE_MASK || + (old_ctrl2 ^ ctrl2) & MVPP2_GMAC_INBAND_AN_MASK || + (old_an ^ an) & MVPP2_GMAC_IN_BAND_AUTONEG) { + /* Force link down */ + old_an &= ~MVPP2_GMAC_FORCE_LINK_PASS; + old_an |= MVPP2_GMAC_FORCE_LINK_DOWN; + writel(old_an, port->base + MVPP2_GMAC_AUTONEG_CONFIG); + + /* Set the GMAC in a reset state - do this in a way that + * ensures we clear it below. + */ + old_ctrl2 |= MVPP2_GMAC_PORT_RESET_MASK; + writel(old_ctrl2, port->base + MVPP2_GMAC_CTRL_2_REG); + } + + if (old_ctrl0 != ctrl0) + writel(ctrl0, port->base + MVPP2_GMAC_CTRL_0_REG); + if (old_ctrl2 != ctrl2) + writel(ctrl2, port->base + MVPP2_GMAC_CTRL_2_REG); + if (old_ctrl4 != ctrl4) + writel(ctrl4, port->base + MVPP22_GMAC_CTRL_4_REG); + if (old_an != an) + writel(an, port->base + MVPP2_GMAC_AUTONEG_CONFIG); + + if (old_ctrl2 & MVPP2_GMAC_PORT_RESET_MASK) { + while (readl(port->base + MVPP2_GMAC_CTRL_2_REG) & + MVPP2_GMAC_PORT_RESET_MASK) + continue; + } } static void mvpp2_mac_config(struct net_device *dev, unsigned int mode, @@ -4624,7 +4664,7 @@ static void mvpp2_mac_config(struct net_device *dev, unsigned int mode, bool change_interface = port->phy_interface != state->interface; /* Check for invalid configuration */ - if (state->interface == PHY_INTERFACE_MODE_10GKR && port->gop_id != 0) { + if (mvpp2_is_xlg(state->interface) && port->gop_id != 0) { netdev_err(dev, "Invalid mode on %s\n", dev->name); return; } @@ -4644,7 +4684,7 @@ static void mvpp2_mac_config(struct net_device *dev, unsigned int mode, } /* mac (re)configuration */ - if (state->interface == PHY_INTERFACE_MODE_10GKR) + if (mvpp2_is_xlg(state->interface)) mvpp2_xlg_config(port, mode, state); else if (phy_interface_mode_is_rgmii(state->interface) || phy_interface_mode_is_8023z(state->interface) || @@ -4666,12 +4706,10 @@ static void mvpp2_mac_link_up(struct net_device *dev, unsigned int mode, struct mvpp2_port *port = netdev_priv(dev); u32 val; - if (!phylink_autoneg_inband(mode) && - interface != PHY_INTERFACE_MODE_10GKR) { + if (!phylink_autoneg_inband(mode) && !mvpp2_is_xlg(interface)) { val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG); val &= ~MVPP2_GMAC_FORCE_LINK_DOWN; - if (phy_interface_mode_is_rgmii(interface)) - val |= MVPP2_GMAC_FORCE_LINK_PASS; + val |= MVPP2_GMAC_FORCE_LINK_PASS; writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG); } @@ -4688,8 +4726,7 @@ static void mvpp2_mac_link_down(struct net_device *dev, unsigned int mode, struct mvpp2_port *port = netdev_priv(dev); u32 val; - if (!phylink_autoneg_inband(mode) && - interface != PHY_INTERFACE_MODE_10GKR) { + if (!phylink_autoneg_inband(mode) && !mvpp2_is_xlg(interface)) { val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG); val &= ~MVPP2_GMAC_FORCE_LINK_PASS; val |= MVPP2_GMAC_FORCE_LINK_DOWN; diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c index f8a6d6e3cb7a..35f2142aac5e 100644 --- a/drivers/net/ethernet/marvell/pxa168_eth.c +++ b/drivers/net/ethernet/marvell/pxa168_eth.c @@ -201,6 +201,7 @@ struct tx_desc { }; struct pxa168_eth_private { + struct platform_device *pdev; int port_num; /* User Ethernet port number */ int phy_addr; int phy_speed; @@ -331,7 +332,7 @@ static void rxq_refill(struct net_device *dev) used_rx_desc = pep->rx_used_desc_q; p_used_rx_desc = &pep->p_rx_desc_area[used_rx_desc]; size = skb_end_pointer(skb) - skb->data; - p_used_rx_desc->buf_ptr = dma_map_single(NULL, + p_used_rx_desc->buf_ptr = dma_map_single(&pep->pdev->dev, skb->data, size, DMA_FROM_DEVICE); @@ -743,7 +744,7 @@ static int txq_reclaim(struct net_device *dev, int force) netdev_err(dev, "Error in TX\n"); dev->stats.tx_errors++; } - dma_unmap_single(NULL, addr, count, DMA_TO_DEVICE); + dma_unmap_single(&pep->pdev->dev, addr, count, DMA_TO_DEVICE); if (skb) dev_kfree_skb_irq(skb); released++; @@ -805,7 +806,7 @@ static int rxq_process(struct net_device *dev, int budget) if (rx_next_curr_desc == rx_used_desc) pep->rx_resource_err = 1; pep->rx_desc_count--; - dma_unmap_single(NULL, rx_desc->buf_ptr, + dma_unmap_single(&pep->pdev->dev, rx_desc->buf_ptr, rx_desc->buf_size, DMA_FROM_DEVICE); received_packets++; @@ -1274,7 +1275,8 @@ pxa168_eth_start_xmit(struct sk_buff *skb, struct net_device *dev) length = skb->len; pep->tx_skb[tx_index] = skb; desc->byte_cnt = length; - desc->buf_ptr = dma_map_single(NULL, skb->data, length, DMA_TO_DEVICE); + desc->buf_ptr = dma_map_single(&pep->pdev->dev, skb->data, length, + DMA_TO_DEVICE); skb_tx_timestamp(skb); @@ -1528,6 +1530,7 @@ static int pxa168_eth_probe(struct platform_device *pdev) if (err) goto err_free_mdio; + pep->pdev = pdev; SET_NETDEV_DEV(dev, &pdev->dev); pxa168_init_hw(pep); err = register_netdev(dev); diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c index 04fd1f135011..654ac534b10e 100644 --- a/drivers/net/ethernet/marvell/skge.c +++ b/drivers/net/ethernet/marvell/skge.c @@ -152,8 +152,10 @@ static void skge_get_regs(struct net_device *dev, struct ethtool_regs *regs, memset(p, 0, regs->len); memcpy_fromio(p, io, B3_RAM_ADDR); - memcpy_fromio(p + B3_RI_WTO_R1, io + B3_RI_WTO_R1, - regs->len - B3_RI_WTO_R1); + if (regs->len > B3_RI_WTO_R1) { + memcpy_fromio(p + B3_RI_WTO_R1, io + B3_RI_WTO_R1, + regs->len - B3_RI_WTO_R1); + } } /* Wake on Lan only supported on Yukon chips with rev 1 or above */ diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index f3a5fa84860f..57727fe1501e 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -5073,7 +5073,7 @@ static int sky2_probe(struct pci_dev *pdev, const struct pci_device_id *ent) INIT_WORK(&hw->restart_work, sky2_restart); pci_set_drvdata(pdev, hw); - pdev->d3_delay = 200; + pdev->d3_delay = 300; return 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 6b88881b8e35..c1438ae52a11 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -3360,7 +3360,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, dev->addr_len = ETH_ALEN; mlx4_en_u64_to_mac(dev->dev_addr, mdev->dev->caps.def_mac[priv->port]); if (!is_valid_ether_addr(dev->dev_addr)) { - en_err(priv, "Port: %d, invalid mac burned: %pM, quiting\n", + en_err(priv, "Port: %d, invalid mac burned: %pM, quitting\n", priv->port, dev->dev_addr); err = -EINVAL; goto out; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 9a0881cb7f51..6c01314e87b0 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -617,6 +617,8 @@ static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb, } #endif +#define short_frame(size) ((size) <= ETH_ZLEN + ETH_FCS_LEN) + /* We reach this function only after checking that any of * the (IPv4 | IPv6) bits are set in cqe->status. */ @@ -624,9 +626,20 @@ static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va, netdev_features_t dev_features) { __wsum hw_checksum = 0; + void *hdr; + + /* CQE csum doesn't cover padding octets in short ethernet + * frames. And the pad field is appended prior to calculating + * and appending the FCS field. + * + * Detecting these padded frames requires to verify and parse + * IP headers, so we simply force all those small frames to skip + * checksum complete. + */ + if (short_frame(skb->len)) + return -EINVAL; - void *hdr = (u8 *)va + sizeof(struct ethhdr); - + hdr = (u8 *)va + sizeof(struct ethhdr); hw_checksum = csum_unfold((__force __sum16)cqe->checksum); if (cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_CVLAN_PRESENT_MASK) && @@ -819,6 +832,11 @@ xdp_drop_no_cnt: skb_record_rx_queue(skb, cq_ring); if (likely(dev->features & NETIF_F_RXCSUM)) { + /* TODO: For IP non TCP/UDP packets when csum complete is + * not an option (not supported or any other reason) we can + * actually check cqe IPOK status bit and report + * CHECKSUM_UNNECESSARY rather than CHECKSUM_NONE + */ if ((cqe->status & cpu_to_be16(MLX4_CQE_STATUS_TCP | MLX4_CQE_STATUS_UDP)) && (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPOK)) && diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index bdb8dd161923..1f6e16d5ea6b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -3981,6 +3981,7 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) if (ret) goto err_params_unregister; + devlink_params_publish(devlink); pci_save_state(pdev); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 9de9abacf7f6..82d636baaa4e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -13,7 +13,7 @@ obj-$(CONFIG_MLX5_CORE) += mlx5_core.o # mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ health.o mcg.o cq.o alloc.o qp.o port.o mr.o pd.o \ - mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o \ + transobj.o vport.o sriov.o fs_cmd.o fs_core.o \ fs_counters.o rl.o lag.o dev.o events.o wq.o lib/gid.o \ lib/devcom.o diag/fs_tracepoint.o diag/fw_tracer.o @@ -22,7 +22,7 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ # mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \ en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \ - en_selftest.o en/port.o en/monitor_stats.o + en_selftest.o en/port.o en/monitor_stats.o en/reporter_tx.o # # Netdev extra @@ -35,7 +35,7 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH) += en_rep.o en_tc.o en/tc_tun.o # # Core extra # -mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o +mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o ecpf.o mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o mlx5_core-$(CONFIG_VXLAN) += lib/vxlan.o mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 3e0fa8a8077b..be48c6440251 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -316,6 +316,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_DESTROY_GENERAL_OBJECT: case MLX5_CMD_OP_DEALLOC_MEMIC: case MLX5_CMD_OP_PAGE_FAULT_RESUME: + case MLX5_CMD_OP_QUERY_HOST_PARAMS: return MLX5_CMD_STAT_OK; case MLX5_CMD_OP_QUERY_HCA_CAP: @@ -627,6 +628,7 @@ const char *mlx5_command_str(int command) MLX5_COMMAND_STR_CASE(QUERY_MODIFY_HEADER_CONTEXT); MLX5_COMMAND_STR_CASE(ALLOC_MEMIC); MLX5_COMMAND_STR_CASE(DEALLOC_MEMIC); + MLX5_COMMAND_STR_CASE(QUERY_HOST_PARAMS); default: return "unknown command opcode"; } } @@ -1583,6 +1585,24 @@ no_trig: spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags); } +void mlx5_cmd_flush(struct mlx5_core_dev *dev) +{ + struct mlx5_cmd *cmd = &dev->cmd; + int i; + + for (i = 0; i < cmd->max_reg_cmds; i++) + while (down_trylock(&cmd->sem)) + mlx5_cmd_trigger_completions(dev); + + while (down_trylock(&cmd->pages_sem)) + mlx5_cmd_trigger_completions(dev); + + /* Unlock cmdif */ + up(&cmd->pages_sem); + for (i = 0; i < cmd->max_reg_cmds; i++) + up(&cmd->sem); +} + static int status_to_err(u8 status) { return status ? -1 : 0; /* TBD more meaningful codes */ @@ -1711,12 +1731,57 @@ int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, } EXPORT_SYMBOL(mlx5_cmd_exec); -int mlx5_cmd_exec_cb(struct mlx5_core_dev *dev, void *in, int in_size, - void *out, int out_size, mlx5_cmd_cbk_t callback, - void *context) +void mlx5_cmd_init_async_ctx(struct mlx5_core_dev *dev, + struct mlx5_async_ctx *ctx) +{ + ctx->dev = dev; + /* Starts at 1 to avoid doing wake_up if we are not cleaning up */ + atomic_set(&ctx->num_inflight, 1); + init_waitqueue_head(&ctx->wait); +} +EXPORT_SYMBOL(mlx5_cmd_init_async_ctx); + +/** + * mlx5_cmd_cleanup_async_ctx - Clean up an async_ctx + * @ctx: The ctx to clean + * + * Upon return all callbacks given to mlx5_cmd_exec_cb() have been called. The + * caller must ensure that mlx5_cmd_exec_cb() is not called during or after + * the call mlx5_cleanup_async_ctx(). + */ +void mlx5_cmd_cleanup_async_ctx(struct mlx5_async_ctx *ctx) +{ + atomic_dec(&ctx->num_inflight); + wait_event(ctx->wait, atomic_read(&ctx->num_inflight) == 0); +} +EXPORT_SYMBOL(mlx5_cmd_cleanup_async_ctx); + +static void mlx5_cmd_exec_cb_handler(int status, void *_work) +{ + struct mlx5_async_work *work = _work; + struct mlx5_async_ctx *ctx = work->ctx; + + work->user_callback(status, work); + if (atomic_dec_and_test(&ctx->num_inflight)) + wake_up(&ctx->wait); +} + +int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size, + void *out, int out_size, mlx5_async_cbk_t callback, + struct mlx5_async_work *work) { - return cmd_exec(dev, in, in_size, out, out_size, callback, context, - false); + int ret; + + work->ctx = ctx; + work->user_callback = callback; + if (WARN_ON(!atomic_inc_not_zero(&ctx->num_inflight))) + return -EIO; + ret = cmd_exec(ctx->dev, in, in_size, out, out_size, + mlx5_cmd_exec_cb_handler, work, false); + if (ret && atomic_dec_and_test(&ctx->num_inflight)) + wake_up(&ctx->wait); + + return ret; } EXPORT_SYMBOL(mlx5_cmd_exec_cb); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c new file mode 100644 index 000000000000..4746f2d28fb6 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c @@ -0,0 +1,112 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include "ecpf.h" + +bool mlx5_read_embedded_cpu(struct mlx5_core_dev *dev) +{ + return (ioread32be(&dev->iseg->initializing) >> MLX5_ECPU_BIT_NUM) & 1; +} + +static int mlx5_peer_pf_enable_hca(struct mlx5_core_dev *dev) +{ + u32 out[MLX5_ST_SZ_DW(enable_hca_out)] = {}; + u32 in[MLX5_ST_SZ_DW(enable_hca_in)] = {}; + + MLX5_SET(enable_hca_in, in, opcode, MLX5_CMD_OP_ENABLE_HCA); + MLX5_SET(enable_hca_in, in, function_id, 0); + MLX5_SET(enable_hca_in, in, embedded_cpu_function, 0); + return mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out)); +} + +static int mlx5_peer_pf_disable_hca(struct mlx5_core_dev *dev) +{ + u32 out[MLX5_ST_SZ_DW(disable_hca_out)] = {}; + u32 in[MLX5_ST_SZ_DW(disable_hca_in)] = {}; + + MLX5_SET(disable_hca_in, in, opcode, MLX5_CMD_OP_DISABLE_HCA); + MLX5_SET(disable_hca_in, in, function_id, 0); + MLX5_SET(enable_hca_in, in, embedded_cpu_function, 0); + return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); +} + +static int mlx5_peer_pf_init(struct mlx5_core_dev *dev) +{ + int err; + + err = mlx5_peer_pf_enable_hca(dev); + if (err) + mlx5_core_err(dev, "Failed to enable peer PF HCA err(%d)\n", + err); + + return err; +} + +static void mlx5_peer_pf_cleanup(struct mlx5_core_dev *dev) +{ + int err; + + err = mlx5_peer_pf_disable_hca(dev); + if (err) { + mlx5_core_err(dev, "Failed to disable peer PF HCA err(%d)\n", + err); + return; + } + + err = mlx5_wait_for_pages(dev, &dev->priv.peer_pf_pages); + if (err) + mlx5_core_warn(dev, "Timeout reclaiming peer PF pages err(%d)\n", + err); +} + +int mlx5_ec_init(struct mlx5_core_dev *dev) +{ + int err = 0; + + if (!mlx5_core_is_ecpf(dev)) + return 0; + + /* ECPF shall enable HCA for peer PF in the same way a PF + * does this for its VFs. + */ + err = mlx5_peer_pf_init(dev); + if (err) + return err; + + return 0; +} + +void mlx5_ec_cleanup(struct mlx5_core_dev *dev) +{ + if (!mlx5_core_is_ecpf(dev)) + return; + + mlx5_peer_pf_cleanup(dev); +} + +static int mlx5_query_host_params_context(struct mlx5_core_dev *dev, + u32 *out, int outlen) +{ + u32 in[MLX5_ST_SZ_DW(query_host_params_in)] = {}; + + MLX5_SET(query_host_params_in, in, opcode, + MLX5_CMD_OP_QUERY_HOST_PARAMS); + + return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen); +} + +int mlx5_query_host_params_num_vfs(struct mlx5_core_dev *dev, int *num_vf) +{ + u32 out[MLX5_ST_SZ_DW(query_host_params_out)] = {}; + int err; + + err = mlx5_query_host_params_context(dev, out, sizeof(out)); + if (err) + return err; + + *num_vf = MLX5_GET(query_host_params_out, out, + host_params_context.host_num_of_vfs); + mlx5_core_dbg(dev, "host_num_of_vfs %d\n", *num_vf); + + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h new file mode 100644 index 000000000000..346372df218f --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2019 Mellanox Technologies. */ + +#ifndef __MLX5_ECPF_H__ +#define __MLX5_ECPF_H__ + +#include <linux/mlx5/driver.h> +#include "mlx5_core.h" + +#ifdef CONFIG_MLX5_ESWITCH + +enum { + MLX5_ECPU_BIT_NUM = 23, +}; + +bool mlx5_read_embedded_cpu(struct mlx5_core_dev *dev); +int mlx5_ec_init(struct mlx5_core_dev *dev); +void mlx5_ec_cleanup(struct mlx5_core_dev *dev); +int mlx5_query_host_params_num_vfs(struct mlx5_core_dev *dev, int *num_vf); + +#else /* CONFIG_MLX5_ESWITCH */ + +static inline bool +mlx5_read_embedded_cpu(struct mlx5_core_dev *dev) { return false; } +static inline int mlx5_ec_init(struct mlx5_core_dev *dev) { return 0; } +static inline void mlx5_ec_cleanup(struct mlx5_core_dev *dev) {} +static inline int +mlx5_query_host_params_num_vfs(struct mlx5_core_dev *dev, int *num_vf) +{ return -EOPNOTSUPP; } + +#endif /* CONFIG_MLX5_ESWITCH */ + +#endif /* __MLX5_ECPF_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 6dd74ef69389..71c65cc17904 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -387,10 +387,7 @@ struct mlx5e_txqsq { struct mlx5e_channel *channel; int txq_ix; u32 rate_limit; - struct mlx5e_txqsq_recover { - struct work_struct recover_work; - u64 last_recover; - } recover; + struct work_struct recover_work; } ____cacheline_aligned_in_smp; struct mlx5e_dma_info { @@ -658,6 +655,7 @@ struct mlx5e_channel_stats { enum { MLX5E_STATE_OPENED, MLX5E_STATE_DESTROYING, + MLX5E_STATE_XDP_TX_ENABLED, }; struct mlx5e_rqt { @@ -683,6 +681,13 @@ struct mlx5e_rss_params { u8 hfunc; }; +struct mlx5e_modify_sq_param { + int curr_state; + int next_state; + int rl_update; + int rl_index; +}; + struct mlx5e_priv { /* priv data path fields - start */ struct mlx5e_txqsq *txq2sq[MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC]; @@ -738,6 +743,7 @@ struct mlx5e_priv { #ifdef CONFIG_MLX5_EN_TLS struct mlx5e_tls *tls; #endif + struct devlink_health_reporter *tx_reporter; }; struct mlx5e_profile { @@ -852,9 +858,9 @@ void mlx5e_close_channels(struct mlx5e_channels *chs); * switching channels */ typedef int (*mlx5e_fp_hw_modify)(struct mlx5e_priv *priv); -void mlx5e_switch_priv_channels(struct mlx5e_priv *priv, - struct mlx5e_channels *new_chs, - mlx5e_fp_hw_modify hw_modify); +int mlx5e_safe_switch_channels(struct mlx5e_priv *priv, + struct mlx5e_channels *new_chs, + mlx5e_fp_hw_modify hw_modify); void mlx5e_activate_priv_channels(struct mlx5e_priv *priv); void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv); @@ -868,6 +874,11 @@ void mlx5e_set_rq_type(struct mlx5_core_dev *mdev, struct mlx5e_params *params); void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev, struct mlx5e_params *params); +int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn, + struct mlx5e_modify_sq_param *p); +void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq); +void mlx5e_tx_disable_queue(struct netdev_queue *txq); + static inline bool mlx5e_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev) { return (MLX5_CAP_ETH(mdev, tunnel_stateless_gre) && diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c index 2ce420851e77..7cd5b02e0f10 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c @@ -66,7 +66,7 @@ static int mlx5e_monitor_event_handler(struct notifier_block *nb, return NOTIFY_OK; } -void mlx5e_monitor_counter_start(struct mlx5e_priv *priv) +static void mlx5e_monitor_counter_start(struct mlx5e_priv *priv) { MLX5_NB_INIT(&priv->monitor_counters_nb, mlx5e_monitor_event_handler, MONITOR_COUNTER); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c index 4a37713023be..122927f3a600 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c @@ -63,66 +63,168 @@ static const u32 mlx5e_link_speed[MLX5E_LINK_MODES_NUMBER] = { [MLX5E_50GBASE_KR2] = 50000, }; -u32 mlx5e_port_ptys2speed(u32 eth_proto_oper) +static const u32 mlx5e_ext_link_speed[MLX5E_EXT_LINK_MODES_NUMBER] = { + [MLX5E_SGMII_100M] = 100, + [MLX5E_1000BASE_X_SGMII] = 1000, + [MLX5E_5GBASE_R] = 5000, + [MLX5E_10GBASE_XFI_XAUI_1] = 10000, + [MLX5E_40GBASE_XLAUI_4_XLPPI_4] = 40000, + [MLX5E_25GAUI_1_25GBASE_CR_KR] = 25000, + [MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2] = 50000, + [MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR] = 50000, + [MLX5E_CAUI_4_100GBASE_CR4_KR4] = 100000, + [MLX5E_200GAUI_4_200GBASE_CR4_KR4] = 200000, + [MLX5E_400GAUI_8] = 400000, +}; + +static void mlx5e_port_get_speed_arr(struct mlx5_core_dev *mdev, + const u32 **arr, u32 *size) +{ + bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); + + *size = ext ? ARRAY_SIZE(mlx5e_ext_link_speed) : + ARRAY_SIZE(mlx5e_link_speed); + *arr = ext ? mlx5e_ext_link_speed : mlx5e_link_speed; +} + +int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext, + struct mlx5e_port_eth_proto *eproto) +{ + u32 out[MLX5_ST_SZ_DW(ptys_reg)]; + int err; + + if (!eproto) + return -EINVAL; + + if (ext != MLX5_CAP_PCAM_FEATURE(dev, ptys_extended_ethernet)) + return -EOPNOTSUPP; + + err = mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_EN, port); + if (err) + return err; + + eproto->cap = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, + eth_proto_capability); + eproto->admin = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, eth_proto_admin); + eproto->oper = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, eth_proto_oper); + return 0; +} + +void mlx5_port_query_eth_autoneg(struct mlx5_core_dev *dev, u8 *an_status, + u8 *an_disable_cap, u8 *an_disable_admin) +{ + u32 out[MLX5_ST_SZ_DW(ptys_reg)]; + + *an_status = 0; + *an_disable_cap = 0; + *an_disable_admin = 0; + + if (mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_EN, 1)) + return; + + *an_status = MLX5_GET(ptys_reg, out, an_status); + *an_disable_cap = MLX5_GET(ptys_reg, out, an_disable_cap); + *an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin); +} + +int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable, + u32 proto_admin, bool ext) +{ + u32 out[MLX5_ST_SZ_DW(ptys_reg)]; + u32 in[MLX5_ST_SZ_DW(ptys_reg)]; + u8 an_disable_admin; + u8 an_disable_cap; + u8 an_status; + + mlx5_port_query_eth_autoneg(dev, &an_status, &an_disable_cap, + &an_disable_admin); + if (!an_disable_cap && an_disable) + return -EPERM; + + memset(in, 0, sizeof(in)); + + MLX5_SET(ptys_reg, in, local_port, 1); + MLX5_SET(ptys_reg, in, an_disable_admin, an_disable); + MLX5_SET(ptys_reg, in, proto_mask, MLX5_PTYS_EN); + if (ext) + MLX5_SET(ptys_reg, in, ext_eth_proto_admin, proto_admin); + else + MLX5_SET(ptys_reg, in, eth_proto_admin, proto_admin); + + return mlx5_core_access_reg(dev, in, sizeof(in), out, + sizeof(out), MLX5_REG_PTYS, 0, 1); +} + +u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper) { unsigned long temp = eth_proto_oper; + const u32 *table; u32 speed = 0; + u32 max_size; int i; - i = find_first_bit(&temp, MLX5E_LINK_MODES_NUMBER); - if (i < MLX5E_LINK_MODES_NUMBER) - speed = mlx5e_link_speed[i]; - + mlx5e_port_get_speed_arr(mdev, &table, &max_size); + i = find_first_bit(&temp, max_size); + if (i < max_size) + speed = table[i]; return speed; } int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed) { - u32 out[MLX5_ST_SZ_DW(ptys_reg)] = {}; - u32 eth_proto_oper; + struct mlx5e_port_eth_proto eproto; + bool ext; int err; - err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN, 1); + ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); + err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto); if (err) - return err; + goto out; - eth_proto_oper = MLX5_GET(ptys_reg, out, eth_proto_oper); - *speed = mlx5e_port_ptys2speed(eth_proto_oper); + *speed = mlx5e_port_ptys2speed(mdev, eproto.oper); if (!(*speed)) err = -EINVAL; +out: return err; } int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed) { + struct mlx5e_port_eth_proto eproto; u32 max_speed = 0; - u32 proto_cap; + const u32 *table; + u32 max_size; + bool ext; int err; int i; - err = mlx5_query_port_proto_cap(mdev, &proto_cap, MLX5_PTYS_EN); + ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); + err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto); if (err) return err; - for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) - if (proto_cap & MLX5E_PROT_MASK(i)) - max_speed = max(max_speed, mlx5e_link_speed[i]); + mlx5e_port_get_speed_arr(mdev, &table, &max_size); + for (i = 0; i < max_size; ++i) + if (eproto.cap & MLX5E_PROT_MASK(i)) + max_speed = max(max_speed, table[i]); *speed = max_speed; return 0; } -u32 mlx5e_port_speed2linkmodes(u32 speed) +u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed) { u32 link_modes = 0; + const u32 *table; + u32 max_size; int i; - for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) { - if (mlx5e_link_speed[i] == speed) + mlx5e_port_get_speed_arr(mdev, &table, &max_size); + for (i = 0; i < max_size; ++i) { + if (table[i] == speed) link_modes |= MLX5E_PROT_MASK(i); } - return link_modes; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h index cd2160b8c9bf..70f536ec51c4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h @@ -36,10 +36,22 @@ #include <linux/mlx5/driver.h> #include "en.h" -u32 mlx5e_port_ptys2speed(u32 eth_proto_oper); +struct mlx5e_port_eth_proto { + u32 cap; + u32 admin; + u32 oper; +}; + +int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext, + struct mlx5e_port_eth_proto *eproto); +void mlx5_port_query_eth_autoneg(struct mlx5_core_dev *dev, u8 *an_status, + u8 *an_disable_cap, u8 *an_disable_admin); +int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable, + u32 proto_admin, bool ext); +u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper); int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed); int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed); -u32 mlx5e_port_speed2linkmodes(u32 speed); +u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed); int mlx5e_port_query_pbmc(struct mlx5_core_dev *mdev, void *out); int mlx5e_port_set_pbmc(struct mlx5_core_dev *mdev, void *in); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h new file mode 100644 index 000000000000..e78e92753d73 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2019 Mellanox Technologies. */ + +#ifndef __MLX5E_EN_REPORTER_H +#define __MLX5E_EN_REPORTER_H + +#include <linux/mlx5/driver.h> +#include "en.h" + +int mlx5e_tx_reporter_create(struct mlx5e_priv *priv); +void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv); +void mlx5e_tx_reporter_err_cqe(struct mlx5e_txqsq *sq); +int mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq); + +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c new file mode 100644 index 000000000000..0aebfb377cf0 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -0,0 +1,297 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include <net/devlink.h> +#include "reporter.h" +#include "lib/eq.h" + +#define MLX5E_TX_REPORTER_PER_SQ_MAX_LEN 256 + +struct mlx5e_tx_err_ctx { + int (*recover)(struct mlx5e_txqsq *sq); + struct mlx5e_txqsq *sq; +}; + +static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq) +{ + unsigned long exp_time = jiffies + msecs_to_jiffies(2000); + + while (time_before(jiffies, exp_time)) { + if (sq->cc == sq->pc) + return 0; + + msleep(20); + } + + netdev_err(sq->channel->netdev, + "Wait for SQ 0x%x flush timeout (sq cc = 0x%x, sq pc = 0x%x)\n", + sq->sqn, sq->cc, sq->pc); + + return -ETIMEDOUT; +} + +static void mlx5e_reset_txqsq_cc_pc(struct mlx5e_txqsq *sq) +{ + WARN_ONCE(sq->cc != sq->pc, + "SQ 0x%x: cc (0x%x) != pc (0x%x)\n", + sq->sqn, sq->cc, sq->pc); + sq->cc = 0; + sq->dma_fifo_cc = 0; + sq->pc = 0; +} + +static int mlx5e_sq_to_ready(struct mlx5e_txqsq *sq, int curr_state) +{ + struct mlx5_core_dev *mdev = sq->channel->mdev; + struct net_device *dev = sq->channel->netdev; + struct mlx5e_modify_sq_param msp = {0}; + int err; + + msp.curr_state = curr_state; + msp.next_state = MLX5_SQC_STATE_RST; + + err = mlx5e_modify_sq(mdev, sq->sqn, &msp); + if (err) { + netdev_err(dev, "Failed to move sq 0x%x to reset\n", sq->sqn); + return err; + } + + memset(&msp, 0, sizeof(msp)); + msp.curr_state = MLX5_SQC_STATE_RST; + msp.next_state = MLX5_SQC_STATE_RDY; + + err = mlx5e_modify_sq(mdev, sq->sqn, &msp); + if (err) { + netdev_err(dev, "Failed to move sq 0x%x to ready\n", sq->sqn); + return err; + } + + return 0; +} + +static int mlx5e_tx_reporter_err_cqe_recover(struct mlx5e_txqsq *sq) +{ + struct mlx5_core_dev *mdev = sq->channel->mdev; + struct net_device *dev = sq->channel->netdev; + u8 state; + int err; + + if (!test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) + return 0; + + err = mlx5_core_query_sq_state(mdev, sq->sqn, &state); + if (err) { + netdev_err(dev, "Failed to query SQ 0x%x state. err = %d\n", + sq->sqn, err); + return err; + } + + if (state != MLX5_SQC_STATE_ERR) { + netdev_err(dev, "SQ 0x%x not in ERROR state\n", sq->sqn); + return -EINVAL; + } + + mlx5e_tx_disable_queue(sq->txq); + + err = mlx5e_wait_for_sq_flush(sq); + if (err) + return err; + + /* At this point, no new packets will arrive from the stack as TXQ is + * marked with QUEUE_STATE_DRV_XOFF. In addition, NAPI cleared all + * pending WQEs. SQ can safely reset the SQ. + */ + + err = mlx5e_sq_to_ready(sq, state); + if (err) + return err; + + mlx5e_reset_txqsq_cc_pc(sq); + sq->stats->recover++; + mlx5e_activate_txqsq(sq); + + return 0; +} + +void mlx5e_tx_reporter_err_cqe(struct mlx5e_txqsq *sq) +{ + char err_str[MLX5E_TX_REPORTER_PER_SQ_MAX_LEN]; + struct mlx5e_tx_err_ctx err_ctx = {0}; + + err_ctx.sq = sq; + err_ctx.recover = mlx5e_tx_reporter_err_cqe_recover; + sprintf(err_str, "ERR CQE on SQ: 0x%x", sq->sqn); + + devlink_health_report(sq->channel->priv->tx_reporter, err_str, + &err_ctx); +} + +static int mlx5e_tx_reporter_timeout_recover(struct mlx5e_txqsq *sq) +{ + struct mlx5_eq_comp *eq = sq->cq.mcq.eq; + u32 eqe_count; + int ret; + + netdev_err(sq->channel->netdev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n", + eq->core.eqn, eq->core.cons_index, eq->core.irqn); + + eqe_count = mlx5_eq_poll_irq_disabled(eq); + ret = eqe_count ? true : false; + if (!eqe_count) { + clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); + return ret; + } + + netdev_err(sq->channel->netdev, "Recover %d eqes on EQ 0x%x\n", + eqe_count, eq->core.eqn); + sq->channel->stats->eq_rearm++; + return ret; +} + +int mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq) +{ + char err_str[MLX5E_TX_REPORTER_PER_SQ_MAX_LEN]; + struct mlx5e_tx_err_ctx err_ctx; + + err_ctx.sq = sq; + err_ctx.recover = mlx5e_tx_reporter_timeout_recover; + sprintf(err_str, + "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u\n", + sq->channel->ix, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc, + jiffies_to_usecs(jiffies - sq->txq->trans_start)); + + return devlink_health_report(sq->channel->priv->tx_reporter, err_str, + &err_ctx); +} + +/* state lock cannot be grabbed within this function. + * It can cause a dead lock or a read-after-free. + */ +int mlx5e_tx_reporter_recover_from_ctx(struct mlx5e_tx_err_ctx *err_ctx) +{ + return err_ctx->recover(err_ctx->sq); +} + +static int mlx5e_tx_reporter_recover_all(struct mlx5e_priv *priv) +{ + int err; + + rtnl_lock(); + mutex_lock(&priv->state_lock); + mlx5e_close_locked(priv->netdev); + err = mlx5e_open_locked(priv->netdev); + mutex_unlock(&priv->state_lock); + rtnl_unlock(); + + return err; +} + +static int mlx5e_tx_reporter_recover(struct devlink_health_reporter *reporter, + void *context) +{ + struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); + struct mlx5e_tx_err_ctx *err_ctx = context; + + return err_ctx ? mlx5e_tx_reporter_recover_from_ctx(err_ctx) : + mlx5e_tx_reporter_recover_all(priv); +} + +static int +mlx5e_tx_reporter_build_diagnose_output(struct devlink_fmsg *fmsg, + u32 sqn, u8 state, bool stopped) +{ + int err; + + err = devlink_fmsg_obj_nest_start(fmsg); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "sqn", sqn); + if (err) + return err; + + err = devlink_fmsg_u8_pair_put(fmsg, "HW state", state); + if (err) + return err; + + err = devlink_fmsg_bool_pair_put(fmsg, "stopped", stopped); + if (err) + return err; + + err = devlink_fmsg_obj_nest_end(fmsg); + if (err) + return err; + + return 0; +} + +static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg) +{ + struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); + int i, err = 0; + + mutex_lock(&priv->state_lock); + + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) + goto unlock; + + err = devlink_fmsg_arr_pair_nest_start(fmsg, "SQs"); + if (err) + goto unlock; + + for (i = 0; i < priv->channels.num * priv->channels.params.num_tc; + i++) { + struct mlx5e_txqsq *sq = priv->txq2sq[i]; + u8 state; + + err = mlx5_core_query_sq_state(priv->mdev, sq->sqn, &state); + if (err) + break; + + err = mlx5e_tx_reporter_build_diagnose_output(fmsg, sq->sqn, + state, + netif_xmit_stopped(sq->txq)); + if (err) + break; + } + err = devlink_fmsg_arr_pair_nest_end(fmsg); + if (err) + goto unlock; + +unlock: + mutex_unlock(&priv->state_lock); + return err; +} + +static const struct devlink_health_reporter_ops mlx5_tx_reporter_ops = { + .name = "tx", + .recover = mlx5e_tx_reporter_recover, + .diagnose = mlx5e_tx_reporter_diagnose, +}; + +#define MLX5_REPORTER_TX_GRACEFUL_PERIOD 500 + +int mlx5e_tx_reporter_create(struct mlx5e_priv *priv) +{ + struct mlx5_core_dev *mdev = priv->mdev; + struct devlink *devlink = priv_to_devlink(mdev); + + priv->tx_reporter = + devlink_health_reporter_create(devlink, &mlx5_tx_reporter_ops, + MLX5_REPORTER_TX_GRACEFUL_PERIOD, + true, priv); + if (IS_ERR_OR_NULL(priv->tx_reporter)) + netdev_warn(priv->netdev, + "Failed to create tx reporter, err = %ld\n", + PTR_ERR(priv->tx_reporter)); + return PTR_ERR_OR_ZERO(priv->tx_reporter); +} + +void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv) +{ + if (IS_ERR_OR_NULL(priv->tx_reporter)) + return; + + devlink_health_reporter_destroy(priv->tx_reporter); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 9e71f4d41b82..bdcc5e79328d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -256,6 +256,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, e->m_neigh.family = n->ops->family; memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len); e->out_dev = out_dev; + e->route_dev = route_dev; /* It's important to add the neigh to the hash table before checking * the neigh validity state. So if we'll get a notification, in case the @@ -369,6 +370,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, e->m_neigh.family = n->ops->family; memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len); e->out_dev = out_dev; + e->route_dev = route_dev; /* It's importent to add the neigh to the hash table before checking * the neigh validity state. So if we'll get a notification, in case the @@ -602,16 +604,18 @@ int mlx5e_tc_tun_parse(struct net_device *filter_dev, struct mlx5_flow_spec *spec, struct tc_cls_flower_offload *f, void *headers_c, - void *headers_v) + void *headers_v, u8 *match_level) { int tunnel_type; int err = 0; tunnel_type = mlx5e_tc_tun_get_type(filter_dev); if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) { + *match_level = MLX5_MATCH_L4; err = mlx5e_tc_tun_parse_vxlan(priv, spec, f, headers_c, headers_v); } else if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_GRETAP) { + *match_level = MLX5_MATCH_L3; err = mlx5e_tc_tun_parse_gretap(priv, spec, f, headers_c, headers_v); } else { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h index 706ce7bf15e7..b63f15de899d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h @@ -39,6 +39,6 @@ int mlx5e_tc_tun_parse(struct net_device *filter_dev, struct mlx5_flow_spec *spec, struct tc_cls_flower_offload *f, void *headers_c, - void *headers_v); + void *headers_v, u8 *match_level); #endif //__MLX5_EN_TC_TUNNEL_H__ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 3740177eed09..03b2a9f9c589 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -365,7 +365,8 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, int sq_num; int i; - if (unlikely(!test_bit(MLX5E_STATE_OPENED, &priv->state))) + /* this flag is sufficient, no need to test internal sq state */ + if (unlikely(!mlx5e_xdp_tx_is_enabled(priv))) return -ENETDOWN; if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) @@ -378,9 +379,6 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, sq = &priv->channels.c[sq_num]->xdpsq; - if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))) - return -ENETDOWN; - for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; struct mlx5e_xdp_info xdpi; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h index 3a67cb3cd179..ee27a7c8cd87 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h @@ -50,6 +50,23 @@ void mlx5e_xdp_rx_poll_complete(struct mlx5e_rq *rq); int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags); +static inline void mlx5e_xdp_tx_enable(struct mlx5e_priv *priv) +{ + set_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state); +} + +static inline void mlx5e_xdp_tx_disable(struct mlx5e_priv *priv) +{ + clear_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state); + /* let other device's napi(s) see our new state */ + synchronize_rcu(); +} + +static inline bool mlx5e_xdp_tx_is_enabled(struct mlx5e_priv *priv) +{ + return test_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state); +} + static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq) { if (sq->doorbell_cseg) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 722998d68564..554672edf8c3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -1126,9 +1126,7 @@ static void mlx5e_trust_update_sq_inline_mode(struct mlx5e_priv *priv) priv->channels.params.tx_min_inline_mode) goto out; - if (mlx5e_open_channels(priv, &new_channels)) - goto out; - mlx5e_switch_priv_channels(priv, &new_channels, NULL); + mlx5e_safe_switch_channels(priv, &new_channels, NULL); out: mutex_unlock(&priv->state_lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 3bbccead2f63..0804b478ad19 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -63,76 +63,147 @@ struct ptys2ethtool_config { __ETHTOOL_DECLARE_LINK_MODE_MASK(advertised); }; -static struct ptys2ethtool_config ptys2ethtool_table[MLX5E_LINK_MODES_NUMBER]; +static +struct ptys2ethtool_config ptys2legacy_ethtool_table[MLX5E_LINK_MODES_NUMBER]; +static +struct ptys2ethtool_config ptys2ext_ethtool_table[MLX5E_EXT_LINK_MODES_NUMBER]; -#define MLX5_BUILD_PTYS2ETHTOOL_CONFIG(reg_, ...) \ +#define MLX5_BUILD_PTYS2ETHTOOL_CONFIG(reg_, table, ...) \ ({ \ struct ptys2ethtool_config *cfg; \ const unsigned int modes[] = { __VA_ARGS__ }; \ - unsigned int i; \ - cfg = &ptys2ethtool_table[reg_]; \ + unsigned int i, bit, idx; \ + cfg = &ptys2##table##_ethtool_table[reg_]; \ 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); \ + bit = modes[i] % 64; \ + idx = modes[i] / 64; \ + __set_bit(bit, &cfg->supported[idx]); \ + __set_bit(bit, &cfg->advertised[idx]); \ } \ }) void mlx5e_build_ptys2ethtool_map(void) { - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_1000BASE_CX_SGMII, + memset(ptys2legacy_ethtool_table, 0, sizeof(ptys2legacy_ethtool_table)); + memset(ptys2ext_ethtool_table, 0, sizeof(ptys2ext_ethtool_table)); + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_1000BASE_CX_SGMII, legacy, ETHTOOL_LINK_MODE_1000baseKX_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_1000BASE_KX, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_1000BASE_KX, legacy, ETHTOOL_LINK_MODE_1000baseKX_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_CX4, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_CX4, legacy, ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_KX4, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_KX4, legacy, ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_KR, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_KR, legacy, ETHTOOL_LINK_MODE_10000baseKR_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_20GBASE_KR2, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_20GBASE_KR2, legacy, ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_CR4, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_CR4, legacy, ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_KR4, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_KR4, legacy, ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_56GBASE_R4, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_56GBASE_R4, legacy, ETHTOOL_LINK_MODE_56000baseKR4_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_CR, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_CR, legacy, ETHTOOL_LINK_MODE_10000baseKR_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_SR, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_SR, legacy, ETHTOOL_LINK_MODE_10000baseKR_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_ER, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_ER, legacy, ETHTOOL_LINK_MODE_10000baseKR_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_SR4, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_SR4, legacy, ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_LR4, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_LR4, legacy, ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GBASE_SR2, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GBASE_SR2, legacy, ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_CR4, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_CR4, legacy, ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_SR4, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_SR4, legacy, ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_KR4, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_KR4, legacy, ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_LR4, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_LR4, legacy, ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_T, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_T, legacy, ETHTOOL_LINK_MODE_10000baseT_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_CR, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_CR, legacy, ETHTOOL_LINK_MODE_25000baseCR_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_KR, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_KR, legacy, ETHTOOL_LINK_MODE_25000baseKR_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_SR, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_SR, legacy, ETHTOOL_LINK_MODE_25000baseSR_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GBASE_CR2, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GBASE_CR2, legacy, ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GBASE_KR2, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GBASE_KR2, legacy, ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT); + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_SGMII_100M, ext, + ETHTOOL_LINK_MODE_100baseT_Full_BIT); + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_1000BASE_X_SGMII, ext, + ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, + ETHTOOL_LINK_MODE_1000baseX_Full_BIT); + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_5GBASE_R, ext, + ETHTOOL_LINK_MODE_5000baseT_Full_BIT); + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_XFI_XAUI_1, ext, + ETHTOOL_LINK_MODE_10000baseT_Full_BIT, + ETHTOOL_LINK_MODE_10000baseKR_Full_BIT, + ETHTOOL_LINK_MODE_10000baseR_FEC_BIT, + ETHTOOL_LINK_MODE_10000baseCR_Full_BIT, + ETHTOOL_LINK_MODE_10000baseSR_Full_BIT, + ETHTOOL_LINK_MODE_10000baseLR_Full_BIT, + ETHTOOL_LINK_MODE_10000baseER_Full_BIT); + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_XLAUI_4_XLPPI_4, ext, + ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT, + ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT, + ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT, + ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT); + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GAUI_1_25GBASE_CR_KR, ext, + ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, + ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, + ETHTOOL_LINK_MODE_25000baseSR_Full_BIT); + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2, + ext, + ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT, + ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT, + ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT); + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR, ext, + ETHTOOL_LINK_MODE_50000baseKR_Full_BIT, + ETHTOOL_LINK_MODE_50000baseSR_Full_BIT, + ETHTOOL_LINK_MODE_50000baseCR_Full_BIT, + ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, + ETHTOOL_LINK_MODE_50000baseDR_Full_BIT); + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_CAUI_4_100GBASE_CR4_KR4, ext, + ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, + ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT, + ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, + ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT); + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GAUI_2_100GBASE_CR2_KR2, ext, + ETHTOOL_LINK_MODE_100000baseKR2_Full_BIT, + ETHTOOL_LINK_MODE_100000baseSR2_Full_BIT, + ETHTOOL_LINK_MODE_100000baseCR2_Full_BIT, + ETHTOOL_LINK_MODE_100000baseLR2_ER2_FR2_Full_BIT, + ETHTOOL_LINK_MODE_100000baseDR2_Full_BIT); + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_200GAUI_4_200GBASE_CR4_KR4, ext, + ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT, + ETHTOOL_LINK_MODE_200000baseSR4_Full_BIT, + ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT, + ETHTOOL_LINK_MODE_200000baseDR4_Full_BIT, + ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT); +} + +static void mlx5e_ethtool_get_speed_arr(struct mlx5_core_dev *mdev, + struct ptys2ethtool_config **arr, + u32 *size) +{ + bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); + + *arr = ext ? ptys2ext_ethtool_table : ptys2legacy_ethtool_table; + *size = ext ? ARRAY_SIZE(ptys2ext_ethtool_table) : + ARRAY_SIZE(ptys2legacy_ethtool_table); } typedef int (*mlx5e_pflag_handler)(struct net_device *netdev, bool enable); @@ -298,11 +369,7 @@ int mlx5e_ethtool_set_ringparam(struct mlx5e_priv *priv, goto unlock; } - err = mlx5e_open_channels(priv, &new_channels); - if (err) - goto unlock; - - mlx5e_switch_priv_channels(priv, &new_channels, NULL); + err = mlx5e_safe_switch_channels(priv, &new_channels, NULL); unlock: mutex_unlock(&priv->state_lock); @@ -354,32 +421,29 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, new_channels.params = priv->channels.params; new_channels.params.num_channels = count; - if (!netif_is_rxfh_configured(priv->netdev)) - mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt, - MLX5E_INDIR_RQT_SIZE, count); if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { priv->channels.params = new_channels.params; goto out; } - /* Create fresh channels with new parameters */ - err = mlx5e_open_channels(priv, &new_channels); - if (err) - goto out; - arfs_enabled = priv->netdev->features & NETIF_F_NTUPLE; if (arfs_enabled) mlx5e_arfs_disable(priv); + if (!netif_is_rxfh_configured(priv->netdev)) + mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt, + MLX5E_INDIR_RQT_SIZE, count); + /* Switch to new channels, set new parameters and close old ones */ - mlx5e_switch_priv_channels(priv, &new_channels, NULL); + err = mlx5e_safe_switch_channels(priv, &new_channels, NULL); if (arfs_enabled) { - err = mlx5e_arfs_enable(priv); - if (err) + int err2 = mlx5e_arfs_enable(priv); + + if (err2) netdev_err(priv->netdev, "%s: mlx5e_arfs_enable failed: %d\n", - __func__, err); + __func__, err2); } out: @@ -505,12 +569,7 @@ int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv, goto out; } - /* open fresh channels with new coal parameters */ - err = mlx5e_open_channels(priv, &new_channels); - if (err) - goto out; - - mlx5e_switch_priv_channels(priv, &new_channels, NULL); + err = mlx5e_safe_switch_channels(priv, &new_channels, NULL); out: mutex_unlock(&priv->state_lock); @@ -525,27 +584,35 @@ static int mlx5e_set_coalesce(struct net_device *netdev, return mlx5e_ethtool_set_coalesce(priv, coal); } -static void ptys2ethtool_supported_link(unsigned long *supported_modes, +static void ptys2ethtool_supported_link(struct mlx5_core_dev *mdev, + unsigned long *supported_modes, u32 eth_proto_cap) { unsigned long proto_cap = eth_proto_cap; + struct ptys2ethtool_config *table; + u32 max_size; int proto; - for_each_set_bit(proto, &proto_cap, MLX5E_LINK_MODES_NUMBER) + mlx5e_ethtool_get_speed_arr(mdev, &table, &max_size); + for_each_set_bit(proto, &proto_cap, max_size) bitmap_or(supported_modes, supported_modes, - ptys2ethtool_table[proto].supported, + table[proto].supported, __ETHTOOL_LINK_MODE_MASK_NBITS); } -static void ptys2ethtool_adver_link(unsigned long *advertising_modes, +static void ptys2ethtool_adver_link(struct mlx5_core_dev *mdev, + unsigned long *advertising_modes, u32 eth_proto_cap) { unsigned long proto_cap = eth_proto_cap; + struct ptys2ethtool_config *table; + u32 max_size; int proto; - for_each_set_bit(proto, &proto_cap, MLX5E_LINK_MODES_NUMBER) + mlx5e_ethtool_get_speed_arr(mdev, &table, &max_size); + for_each_set_bit(proto, &proto_cap, max_size) bitmap_or(advertising_modes, advertising_modes, - ptys2ethtool_table[proto].advertised, + table[proto].advertised, __ETHTOOL_LINK_MODE_MASK_NBITS); } @@ -695,13 +762,14 @@ static void get_speed_duplex(struct net_device *netdev, u32 eth_proto_oper, struct ethtool_link_ksettings *link_ksettings) { + struct mlx5e_priv *priv = netdev_priv(netdev); u32 speed = SPEED_UNKNOWN; u8 duplex = DUPLEX_UNKNOWN; if (!netif_carrier_ok(netdev)) goto out; - speed = mlx5e_port_ptys2speed(eth_proto_oper); + speed = mlx5e_port_ptys2speed(priv->mdev, eth_proto_oper); if (!speed) { speed = SPEED_UNKNOWN; goto out; @@ -714,22 +782,22 @@ out: link_ksettings->base.duplex = duplex; } -static void get_supported(u32 eth_proto_cap, +static void get_supported(struct mlx5_core_dev *mdev, u32 eth_proto_cap, struct ethtool_link_ksettings *link_ksettings) { unsigned long *supported = link_ksettings->link_modes.supported; + ptys2ethtool_supported_link(mdev, supported, eth_proto_cap); - ptys2ethtool_supported_link(supported, eth_proto_cap); ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Pause); } -static void get_advertising(u32 eth_proto_cap, u8 tx_pause, - u8 rx_pause, +static void get_advertising(struct mlx5_core_dev *mdev, u32 eth_proto_cap, + u8 tx_pause, u8 rx_pause, struct ethtool_link_ksettings *link_ksettings) { unsigned long *advertising = link_ksettings->link_modes.advertising; + ptys2ethtool_adver_link(mdev, advertising, eth_proto_cap); - ptys2ethtool_adver_link(advertising, eth_proto_cap); if (rx_pause) ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Pause); if (tx_pause ^ rx_pause) @@ -779,12 +847,12 @@ static u8 get_connector_port(u32 eth_proto, u8 connector_type) return PORT_OTHER; } -static void get_lp_advertising(u32 eth_proto_lp, +static void get_lp_advertising(struct mlx5_core_dev *mdev, u32 eth_proto_lp, struct ethtool_link_ksettings *link_ksettings) { unsigned long *lp_advertising = link_ksettings->link_modes.lp_advertising; - ptys2ethtool_adver_link(lp_advertising, eth_proto_lp); + ptys2ethtool_adver_link(mdev, lp_advertising, eth_proto_lp); } int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv, @@ -801,6 +869,7 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv, u8 an_disable_admin; u8 an_status; u8 connector_type; + bool ext; int err; err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN, 1); @@ -809,22 +878,25 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv, __func__, err); goto err_query_regs; } - - eth_proto_cap = MLX5_GET(ptys_reg, out, eth_proto_capability); - eth_proto_admin = MLX5_GET(ptys_reg, out, eth_proto_admin); - eth_proto_oper = MLX5_GET(ptys_reg, out, eth_proto_oper); - eth_proto_lp = MLX5_GET(ptys_reg, out, eth_proto_lp_advertise); - an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin); - an_status = MLX5_GET(ptys_reg, out, an_status); - connector_type = MLX5_GET(ptys_reg, out, connector_type); + ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); + eth_proto_cap = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, + eth_proto_capability); + eth_proto_admin = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, + eth_proto_admin); + eth_proto_oper = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, + eth_proto_oper); + eth_proto_lp = MLX5_GET(ptys_reg, out, eth_proto_lp_advertise); + an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin); + an_status = MLX5_GET(ptys_reg, out, an_status); + connector_type = MLX5_GET(ptys_reg, out, connector_type); mlx5_query_port_pause(mdev, &rx_pause, &tx_pause); ethtool_link_ksettings_zero_link_mode(link_ksettings, supported); ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising); - get_supported(eth_proto_cap, link_ksettings); - get_advertising(eth_proto_admin, tx_pause, rx_pause, link_ksettings); + get_supported(mdev, eth_proto_cap, link_ksettings); + get_advertising(mdev, eth_proto_admin, tx_pause, rx_pause, link_ksettings); get_speed_duplex(priv->netdev, eth_proto_oper, link_ksettings); eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap; @@ -833,7 +905,7 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv, connector_type); ptys2ethtool_supported_advertised_port(link_ksettings, eth_proto_admin, connector_type); - get_lp_advertising(eth_proto_lp, link_ksettings); + get_lp_advertising(mdev, eth_proto_lp, link_ksettings); if (an_status == MLX5_AN_COMPLETE) ethtool_link_ksettings_add_link_mode(link_ksettings, @@ -872,7 +944,9 @@ static u32 mlx5e_ethtool2ptys_adver_link(const unsigned long *link_modes) u32 i, ptys_modes = 0; for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) { - if (bitmap_intersects(ptys2ethtool_table[i].advertised, + if (*ptys2legacy_ethtool_table[i].advertised == 0) + continue; + if (bitmap_intersects(ptys2legacy_ethtool_table[i].advertised, link_modes, __ETHTOOL_LINK_MODE_MASK_NBITS)) ptys_modes |= MLX5E_PROT_MASK(i); @@ -881,13 +955,34 @@ static u32 mlx5e_ethtool2ptys_adver_link(const unsigned long *link_modes) return ptys_modes; } +static u32 mlx5e_ethtool2ptys_ext_adver_link(const unsigned long *link_modes) +{ + u32 i, ptys_modes = 0; + unsigned long modes[2]; + + for (i = 0; i < MLX5E_EXT_LINK_MODES_NUMBER; ++i) { + if (*ptys2ext_ethtool_table[i].advertised == 0) + continue; + memset(modes, 0, sizeof(modes)); + bitmap_and(modes, ptys2ext_ethtool_table[i].advertised, + link_modes, __ETHTOOL_LINK_MODE_MASK_NBITS); + + if (modes[0] == ptys2ext_ethtool_table[i].advertised[0] && + modes[1] == ptys2ext_ethtool_table[i].advertised[1]) + ptys_modes |= MLX5E_PROT_MASK(i); + } + return ptys_modes; +} + int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, const struct ethtool_link_ksettings *link_ksettings) { struct mlx5_core_dev *mdev = priv->mdev; - u32 eth_proto_cap, eth_proto_admin; + struct mlx5e_port_eth_proto eproto; bool an_changes = false; u8 an_disable_admin; + bool ext_supported; + bool ext_requested; u8 an_disable_cap; bool an_disable; u32 link_modes; @@ -895,20 +990,33 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, u32 speed; int err; - speed = link_ksettings->base.speed; + u32 (*ethtool2ptys_adver_func)(const unsigned long *adver); - link_modes = link_ksettings->base.autoneg == AUTONEG_ENABLE ? - mlx5e_ethtool2ptys_adver_link(link_ksettings->link_modes.advertising) : - mlx5e_port_speed2linkmodes(speed); +#define MLX5E_PTYS_EXT ((1ULL << ETHTOOL_LINK_MODE_50000baseKR_Full_BIT) - 1) - err = mlx5_query_port_proto_cap(mdev, ð_proto_cap, MLX5_PTYS_EN); + ext_requested = (link_ksettings->link_modes.advertising[0] > + MLX5E_PTYS_EXT); + ext_supported = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); + + /*when ptys_extended_ethernet is set legacy link modes are deprecated */ + if (ext_requested != ext_supported) + return -EPROTONOSUPPORT; + + speed = link_ksettings->base.speed; + ethtool2ptys_adver_func = ext_requested ? + mlx5e_ethtool2ptys_ext_adver_link : + mlx5e_ethtool2ptys_adver_link; + err = mlx5_port_query_eth_proto(mdev, 1, ext_supported, &eproto); if (err) { - netdev_err(priv->netdev, "%s: query port eth proto cap failed: %d\n", + netdev_err(priv->netdev, "%s: query port eth proto failed: %d\n", __func__, err); goto out; } + link_modes = link_ksettings->base.autoneg == AUTONEG_ENABLE ? + ethtool2ptys_adver_func(link_ksettings->link_modes.advertising) : + mlx5e_port_speed2linkmodes(mdev, speed); - link_modes = link_modes & eth_proto_cap; + link_modes = link_modes & eproto.cap; if (!link_modes) { netdev_err(priv->netdev, "%s: Not supported link mode(s) requested", __func__); @@ -916,24 +1024,17 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, goto out; } - err = mlx5_query_port_proto_admin(mdev, ð_proto_admin, MLX5_PTYS_EN); - if (err) { - netdev_err(priv->netdev, "%s: query port eth proto admin failed: %d\n", - __func__, err); - goto out; - } - - mlx5_query_port_autoneg(mdev, MLX5_PTYS_EN, &an_status, - &an_disable_cap, &an_disable_admin); + mlx5_port_query_eth_autoneg(mdev, &an_status, &an_disable_cap, + &an_disable_admin); an_disable = link_ksettings->base.autoneg == AUTONEG_DISABLE; an_changes = ((!an_disable && an_disable_admin) || (an_disable && !an_disable_admin)); - if (!an_changes && link_modes == eth_proto_admin) + if (!an_changes && link_modes == eproto.admin) goto out; - mlx5_set_port_ptys(mdev, an_disable, link_modes, MLX5_PTYS_EN); + mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext_supported); mlx5_toggle_port_link(mdev); out: @@ -1521,7 +1622,6 @@ static int set_pflag_cqe_based_moder(struct net_device *netdev, bool enable, struct mlx5e_channels new_channels = {}; bool mode_changed; u8 cq_period_mode, current_cq_period_mode; - int err = 0; cq_period_mode = enable ? MLX5_CQ_PERIOD_MODE_START_FROM_CQE : @@ -1549,12 +1649,7 @@ static int set_pflag_cqe_based_moder(struct net_device *netdev, bool enable, return 0; } - err = mlx5e_open_channels(priv, &new_channels); - if (err) - return err; - - mlx5e_switch_priv_channels(priv, &new_channels, NULL); - return 0; + return mlx5e_safe_switch_channels(priv, &new_channels, NULL); } static int set_pflag_tx_cqe_based_moder(struct net_device *netdev, bool enable) @@ -1587,11 +1682,10 @@ int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val return 0; } - err = mlx5e_open_channels(priv, &new_channels); + err = mlx5e_safe_switch_channels(priv, &new_channels, NULL); if (err) return err; - mlx5e_switch_priv_channels(priv, &new_channels, NULL); mlx5e_dbg(DRV, priv, "MLX5E: RxCqeCmprss was turned %s\n", MLX5E_GET_PFLAG(&priv->channels.params, MLX5E_PFLAG_RX_CQE_COMPRESS) ? "ON" : "OFF"); @@ -1624,7 +1718,6 @@ static int set_pflag_rx_striding_rq(struct net_device *netdev, bool enable) struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = priv->mdev; struct mlx5e_channels new_channels = {}; - int err; if (enable) { if (!mlx5e_check_fragmented_striding_rq_cap(mdev)) @@ -1646,12 +1739,7 @@ static int set_pflag_rx_striding_rq(struct net_device *netdev, bool enable) return 0; } - err = mlx5e_open_channels(priv, &new_channels); - if (err) - return err; - - mlx5e_switch_priv_channels(priv, &new_channels, NULL); - return 0; + return mlx5e_safe_switch_channels(priv, &new_channels, NULL); } static int set_pflag_rx_no_csum_complete(struct net_device *netdev, bool enable) @@ -1694,12 +1782,8 @@ static int set_pflag_xdp_tx_mpwqe(struct net_device *netdev, bool enable) return 0; } - err = mlx5e_open_channels(priv, &new_channels); - if (err) - return err; - - mlx5e_switch_priv_channels(priv, &new_channels, NULL); - return 0; + err = mlx5e_safe_switch_channels(priv, &new_channels, NULL); + return err; } static const struct pflag_desc mlx5e_priv_flags[MLX5E_NUM_PFLAGS] = { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 099d307e6f25..878b3467e459 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -51,6 +51,7 @@ #include "en/xdp.h" #include "lib/eq.h" #include "en/monitor_stats.h" +#include "en/reporter.h" struct mlx5e_rq_param { u32 rqc[MLX5_ST_SZ_DW(rqc)]; @@ -1159,7 +1160,7 @@ static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa) return 0; } -static void mlx5e_sq_recover(struct work_struct *work); +static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work); static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, int txq_ix, struct mlx5e_params *params, @@ -1181,7 +1182,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, sq->uar_map = mdev->mlx5e_res.bfreg.map; sq->min_inline_mode = params->tx_min_inline_mode; sq->stats = &c->priv->channel_stats[c->ix].sq[tc]; - INIT_WORK(&sq->recover.recover_work, mlx5e_sq_recover); + INIT_WORK(&sq->recover_work, mlx5e_tx_err_cqe_work); if (MLX5_IPSEC_DEV(c->priv->mdev)) set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state); if (mlx5_accel_is_tls_device(c->priv->mdev)) @@ -1269,15 +1270,8 @@ static int mlx5e_create_sq(struct mlx5_core_dev *mdev, return err; } -struct mlx5e_modify_sq_param { - int curr_state; - int next_state; - bool rl_update; - int rl_index; -}; - -static int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn, - struct mlx5e_modify_sq_param *p) +int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn, + struct mlx5e_modify_sq_param *p) { void *in; void *sqc; @@ -1375,17 +1369,7 @@ err_free_txqsq: return err; } -static void mlx5e_reset_txqsq_cc_pc(struct mlx5e_txqsq *sq) -{ - WARN_ONCE(sq->cc != sq->pc, - "SQ 0x%x: cc (0x%x) != pc (0x%x)\n", - sq->sqn, sq->cc, sq->pc); - sq->cc = 0; - sq->dma_fifo_cc = 0; - sq->pc = 0; -} - -static void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq) +void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq) { sq->txq = netdev_get_tx_queue(sq->channel->netdev, sq->txq_ix); clear_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state); @@ -1394,7 +1378,7 @@ static void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq) netif_tx_start_queue(sq->txq); } -static inline void netif_tx_disable_queue(struct netdev_queue *txq) +void mlx5e_tx_disable_queue(struct netdev_queue *txq) { __netif_tx_lock_bh(txq); netif_tx_stop_queue(txq); @@ -1410,7 +1394,7 @@ static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq) /* prevent netif_tx_wake_queue */ napi_synchronize(&c->napi); - netif_tx_disable_queue(sq->txq); + mlx5e_tx_disable_queue(sq->txq); /* last doorbell out, godspeed .. */ if (mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1)) { @@ -1430,6 +1414,7 @@ static void mlx5e_close_txqsq(struct mlx5e_txqsq *sq) struct mlx5_rate_limit rl = {0}; cancel_work_sync(&sq->dim.work); + cancel_work_sync(&sq->recover_work); mlx5e_destroy_sq(mdev, sq->sqn); if (sq->rate_limit) { rl.rate = sq->rate_limit; @@ -1439,105 +1424,12 @@ static void mlx5e_close_txqsq(struct mlx5e_txqsq *sq) mlx5e_free_txqsq(sq); } -static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq) +static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work) { - unsigned long exp_time = jiffies + msecs_to_jiffies(2000); - - while (time_before(jiffies, exp_time)) { - if (sq->cc == sq->pc) - return 0; - - msleep(20); - } - - netdev_err(sq->channel->netdev, - "Wait for SQ 0x%x flush timeout (sq cc = 0x%x, sq pc = 0x%x)\n", - sq->sqn, sq->cc, sq->pc); + struct mlx5e_txqsq *sq = container_of(recover_work, struct mlx5e_txqsq, + recover_work); - return -ETIMEDOUT; -} - -static int mlx5e_sq_to_ready(struct mlx5e_txqsq *sq, int curr_state) -{ - struct mlx5_core_dev *mdev = sq->channel->mdev; - struct net_device *dev = sq->channel->netdev; - struct mlx5e_modify_sq_param msp = {0}; - int err; - - msp.curr_state = curr_state; - msp.next_state = MLX5_SQC_STATE_RST; - - err = mlx5e_modify_sq(mdev, sq->sqn, &msp); - if (err) { - netdev_err(dev, "Failed to move sq 0x%x to reset\n", sq->sqn); - return err; - } - - memset(&msp, 0, sizeof(msp)); - msp.curr_state = MLX5_SQC_STATE_RST; - msp.next_state = MLX5_SQC_STATE_RDY; - - err = mlx5e_modify_sq(mdev, sq->sqn, &msp); - if (err) { - netdev_err(dev, "Failed to move sq 0x%x to ready\n", sq->sqn); - return err; - } - - return 0; -} - -static void mlx5e_sq_recover(struct work_struct *work) -{ - struct mlx5e_txqsq_recover *recover = - container_of(work, struct mlx5e_txqsq_recover, - recover_work); - struct mlx5e_txqsq *sq = container_of(recover, struct mlx5e_txqsq, - recover); - struct mlx5_core_dev *mdev = sq->channel->mdev; - struct net_device *dev = sq->channel->netdev; - u8 state; - int err; - - err = mlx5_core_query_sq_state(mdev, sq->sqn, &state); - if (err) { - netdev_err(dev, "Failed to query SQ 0x%x state. err = %d\n", - sq->sqn, err); - return; - } - - if (state != MLX5_RQC_STATE_ERR) { - netdev_err(dev, "SQ 0x%x not in ERROR state\n", sq->sqn); - return; - } - - netif_tx_disable_queue(sq->txq); - - if (mlx5e_wait_for_sq_flush(sq)) - return; - - /* If the interval between two consecutive recovers per SQ is too - * short, don't recover to avoid infinite loop of ERR_CQE -> recover. - * If we reached this state, there is probably a bug that needs to be - * fixed. let's keep the queue close and let tx timeout cleanup. - */ - if (jiffies_to_msecs(jiffies - recover->last_recover) < - MLX5E_SQ_RECOVER_MIN_INTERVAL) { - netdev_err(dev, "Recover SQ 0x%x canceled, too many error CQEs\n", - sq->sqn); - return; - } - - /* At this point, no new packets will arrive from the stack as TXQ is - * marked with QUEUE_STATE_DRV_XOFF. In addition, NAPI cleared all - * pending WQEs. SQ can safely reset the SQ. - */ - if (mlx5e_sq_to_ready(sq, state)) - return; - - mlx5e_reset_txqsq_cc_pc(sq); - sq->stats->recover++; - recover->last_recover = jiffies; - mlx5e_activate_txqsq(sq); + mlx5e_tx_reporter_err_cqe(sq); } static int mlx5e_open_icosq(struct mlx5e_channel *c, @@ -2967,6 +2859,7 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) mlx5e_build_tx2sq_maps(priv); mlx5e_activate_channels(&priv->channels); + mlx5e_xdp_tx_enable(priv); netif_tx_start_all_queues(priv->netdev); if (mlx5e_is_vport_rep(priv)) @@ -2988,16 +2881,18 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv) */ netif_tx_stop_all_queues(priv->netdev); netif_tx_disable(priv->netdev); + mlx5e_xdp_tx_disable(priv); mlx5e_deactivate_channels(&priv->channels); } -void mlx5e_switch_priv_channels(struct mlx5e_priv *priv, - struct mlx5e_channels *new_chs, - mlx5e_fp_hw_modify hw_modify) +static void mlx5e_switch_priv_channels(struct mlx5e_priv *priv, + struct mlx5e_channels *new_chs, + mlx5e_fp_hw_modify hw_modify) { struct net_device *netdev = priv->netdev; int new_num_txqs; int carrier_ok; + new_num_txqs = new_chs->num * new_chs->params.num_tc; carrier_ok = netif_carrier_ok(netdev); @@ -3023,6 +2918,20 @@ void mlx5e_switch_priv_channels(struct mlx5e_priv *priv, netif_carrier_on(netdev); } +int mlx5e_safe_switch_channels(struct mlx5e_priv *priv, + struct mlx5e_channels *new_chs, + mlx5e_fp_hw_modify hw_modify) +{ + int err; + + err = mlx5e_open_channels(priv, new_chs); + if (err) + return err; + + mlx5e_switch_priv_channels(priv, new_chs, hw_modify); + return 0; +} + void mlx5e_timestamp_init(struct mlx5e_priv *priv) { priv->tstamp.tx_type = HWTSTAMP_TX_OFF; @@ -3236,6 +3145,7 @@ static void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv) { int tc; + mlx5e_tx_reporter_destroy(priv); for (tc = 0; tc < priv->profile->max_tc; tc++) mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]); } @@ -3438,13 +3348,12 @@ static int mlx5e_setup_tc_mqprio(struct net_device *netdev, goto out; } - err = mlx5e_open_channels(priv, &new_channels); + err = mlx5e_safe_switch_channels(priv, &new_channels, NULL); if (err) goto out; priv->max_opened_tc = max_t(u8, priv->max_opened_tc, new_channels.params.num_tc); - mlx5e_switch_priv_channels(priv, &new_channels, NULL); out: mutex_unlock(&priv->state_lock); return err; @@ -3654,11 +3563,7 @@ static int set_feature_lro(struct net_device *netdev, bool enable) goto out; } - err = mlx5e_open_channels(priv, &new_channels); - if (err) - goto out; - - mlx5e_switch_priv_channels(priv, &new_channels, mlx5e_modify_tirs_lro); + err = mlx5e_safe_switch_channels(priv, &new_channels, mlx5e_modify_tirs_lro); out: mutex_unlock(&priv->state_lock); return err; @@ -3876,11 +3781,10 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu, goto out; } - err = mlx5e_open_channels(priv, &new_channels); + err = mlx5e_safe_switch_channels(priv, &new_channels, set_mtu_cb); if (err) goto out; - mlx5e_switch_priv_channels(priv, &new_channels, set_mtu_cb); netdev->mtu = new_channels.params.sw_mtu; out: @@ -4223,31 +4127,13 @@ netdev_features_t mlx5e_features_check(struct sk_buff *skb, return features; } -static bool mlx5e_tx_timeout_eq_recover(struct net_device *dev, - struct mlx5e_txqsq *sq) -{ - struct mlx5_eq_comp *eq = sq->cq.mcq.eq; - u32 eqe_count; - - netdev_err(dev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n", - eq->core.eqn, eq->core.cons_index, eq->core.irqn); - - eqe_count = mlx5_eq_poll_irq_disabled(eq); - if (!eqe_count) - return false; - - netdev_err(dev, "Recover %d eqes on EQ 0x%x\n", eqe_count, eq->core.eqn); - sq->channel->stats->eq_rearm++; - return true; -} - static void mlx5e_tx_timeout_work(struct work_struct *work) { struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv, tx_timeout_work); - struct net_device *dev = priv->netdev; - bool reopen_channels = false; - int i, err; + bool report_failed = false; + int err; + int i; rtnl_lock(); mutex_lock(&priv->state_lock); @@ -4256,31 +4142,22 @@ static void mlx5e_tx_timeout_work(struct work_struct *work) goto unlock; for (i = 0; i < priv->channels.num * priv->channels.params.num_tc; i++) { - struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, i); + struct netdev_queue *dev_queue = + netdev_get_tx_queue(priv->netdev, i); struct mlx5e_txqsq *sq = priv->txq2sq[i]; if (!netif_xmit_stopped(dev_queue)) continue; - netdev_err(dev, - "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u\n", - i, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc, - jiffies_to_usecs(jiffies - dev_queue->trans_start)); - - /* If we recover a lost interrupt, most likely TX timeout will - * be resolved, skip reopening channels - */ - if (!mlx5e_tx_timeout_eq_recover(dev, sq)) { - clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); - reopen_channels = true; - } + if (mlx5e_tx_reporter_timeout(sq)) + report_failed = true; } - if (!reopen_channels) + if (!report_failed) goto unlock; - mlx5e_close_locked(dev); - err = mlx5e_open_locked(dev); + mlx5e_close_locked(priv->netdev); + err = mlx5e_open_locked(priv->netdev); if (err) netdev_err(priv->netdev, "mlx5e_open_locked failed recovering from a tx_timeout, err(%d).\n", @@ -4296,6 +4173,12 @@ static void mlx5e_tx_timeout(struct net_device *dev) struct mlx5e_priv *priv = netdev_priv(dev); netdev_err(dev, "TX timeout detected\n"); + + if (IS_ERR_OR_NULL(priv->tx_reporter)) { + netdev_err_once(priv->netdev, "tx timeout will not be handled, no valid tx reporter\n"); + return; + } + queue_work(priv->wq, &priv->tx_timeout_work); } @@ -4953,6 +4836,7 @@ static int mlx5e_init_nic_tx(struct mlx5e_priv *priv) #ifdef CONFIG_MLX5_CORE_EN_DCB mlx5e_dcbnl_initialize(priv); #endif + mlx5e_tx_reporter_create(priv); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 0b1988b330f3..287d48e5b073 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -153,7 +153,7 @@ static void mlx5e_rep_update_hw_counters(struct mlx5e_priv *priv) struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *rep = rpriv->rep; - if (rep->vport == FDB_UPLINK_VPORT) + if (rep->vport == MLX5_VPORT_UPLINK) mlx5e_uplink_rep_update_hw_counters(priv); else mlx5e_vf_rep_update_hw_counters(priv); @@ -579,6 +579,10 @@ static void mlx5e_rep_update_flows(struct mlx5e_priv *priv, if (neigh_connected && !(e->flags & MLX5_ENCAP_ENTRY_VALID)) { ether_addr_copy(e->h_dest, ha); ether_addr_copy(eth->h_dest, ha); + /* Update the encap source mac, in case that we delete + * the flows when encap source mac changed. + */ + ether_addr_copy(eth->h_source, e->route_dev->dev_addr); mlx5e_tc_encap_flows_add(priv, e); } @@ -1079,7 +1083,8 @@ static int mlx5e_vf_rep_open(struct net_device *dev) if (!mlx5_modify_vport_admin_state(priv->mdev, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, - rep->vport, MLX5_VPORT_ADMIN_STATE_UP)) + rep->vport, 1, + MLX5_VPORT_ADMIN_STATE_UP)) netif_carrier_on(dev); unlock: @@ -1097,7 +1102,8 @@ static int mlx5e_vf_rep_close(struct net_device *dev) mutex_lock(&priv->state_lock); mlx5_modify_vport_admin_state(priv->mdev, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, - rep->vport, MLX5_VPORT_ADMIN_STATE_DOWN); + rep->vport, 1, + MLX5_VPORT_ADMIN_STATE_DOWN); ret = mlx5e_close_locked(dev); mutex_unlock(&priv->state_lock); return ret; @@ -1115,7 +1121,7 @@ static int mlx5e_rep_get_phys_port_name(struct net_device *dev, if (ret) return ret; - if (rep->vport == FDB_UPLINK_VPORT) + if (rep->vport == MLX5_VPORT_UPLINK) ret = snprintf(buf, len, "p%d", pf_num); else ret = snprintf(buf, len, "pf%dvf%d", pf_num, rep->vport - 1); @@ -1202,7 +1208,7 @@ bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv) return false; rep = rpriv->rep; - return (rep->vport == FDB_UPLINK_VPORT); + return (rep->vport == MLX5_VPORT_UPLINK); } static bool mlx5e_rep_has_offload_stats(const struct net_device *dev, int attr_id) @@ -1340,7 +1346,7 @@ static void mlx5e_build_rep_params(struct net_device *netdev) params->sw_mtu = netdev->mtu; /* SQ */ - if (rep->vport == FDB_UPLINK_VPORT) + if (rep->vport == MLX5_VPORT_UPLINK) params->log_sq_size = MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE; else params->log_sq_size = MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE; @@ -1367,7 +1373,7 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev) struct mlx5_eswitch_rep *rep = rpriv->rep; struct mlx5_core_dev *mdev = priv->mdev; - if (rep->vport == FDB_UPLINK_VPORT) { + if (rep->vport == MLX5_VPORT_UPLINK) { SET_NETDEV_DEV(netdev, &priv->mdev->pdev->dev); netdev->netdev_ops = &mlx5e_netdev_ops_uplink_rep; /* we want a persistent mac for the uplink rep */ @@ -1397,7 +1403,7 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev) netdev->hw_features |= NETIF_F_TSO6; netdev->hw_features |= NETIF_F_RXCSUM; - if (rep->vport != FDB_UPLINK_VPORT) + if (rep->vport != MLX5_VPORT_UPLINK) netdev->features |= NETIF_F_VLAN_CHALLENGED; netdev->features |= netdev->hw_features; @@ -1550,7 +1556,7 @@ static int mlx5e_init_rep_tx(struct mlx5e_priv *priv) return err; } - if (rpriv->rep->vport == FDB_UPLINK_VPORT) { + if (rpriv->rep->vport == MLX5_VPORT_UPLINK) { uplink_priv = &rpriv->uplink_priv; /* init shared tc flow table */ @@ -1586,7 +1592,7 @@ static void mlx5e_cleanup_rep_tx(struct mlx5e_priv *priv) for (tc = 0; tc < priv->profile->max_tc; tc++) mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]); - if (rpriv->rep->vport == FDB_UPLINK_VPORT) { + if (rpriv->rep->vport == MLX5_VPORT_UPLINK) { /* clean indirect TC block notifications */ unregister_netdevice_notifier(&rpriv->uplink_priv.netdevice_nb); mlx5e_rep_indr_clean_block_privs(rpriv); @@ -1705,7 +1711,7 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) rpriv->rep = rep; nch = mlx5e_get_max_num_channels(dev); - profile = (rep->vport == FDB_UPLINK_VPORT) ? &mlx5e_uplink_rep_profile : &mlx5e_vf_rep_profile; + profile = (rep->vport == MLX5_VPORT_UPLINK) ? &mlx5e_uplink_rep_profile : &mlx5e_vf_rep_profile; netdev = mlx5e_create_netdev(dev, profile, nch, rpriv); if (!netdev) { pr_warn("Failed to create representor netdev for vport %d\n", @@ -1718,7 +1724,7 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) rep->rep_if[REP_ETH].priv = rpriv; INIT_LIST_HEAD(&rpriv->vport_sqs_list); - if (rep->vport == FDB_UPLINK_VPORT) { + if (rep->vport == MLX5_VPORT_UPLINK) { err = mlx5e_create_mdev_resources(dev); if (err) goto err_destroy_netdev; @@ -1754,7 +1760,7 @@ err_detach_netdev: mlx5e_detach_netdev(netdev_priv(netdev)); err_destroy_mdev_resources: - if (rep->vport == FDB_UPLINK_VPORT) + if (rep->vport == MLX5_VPORT_UPLINK) mlx5e_destroy_mdev_resources(dev); err_destroy_netdev: @@ -1774,7 +1780,7 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep) unregister_netdev(netdev); mlx5e_rep_neigh_cleanup(rpriv); mlx5e_detach_netdev(priv); - if (rep->vport == FDB_UPLINK_VPORT) + if (rep->vport == MLX5_VPORT_UPLINK) mlx5e_destroy_mdev_resources(priv->mdev); mlx5e_destroy_netdev(priv); kfree(ppriv); /* mlx5e_rep_priv */ @@ -1792,25 +1798,18 @@ static void *mlx5e_vport_rep_get_proto_dev(struct mlx5_eswitch_rep *rep) void mlx5e_rep_register_vport_reps(struct mlx5_core_dev *mdev) { struct mlx5_eswitch *esw = mdev->priv.eswitch; - int total_vfs = MLX5_TOTAL_VPORTS(mdev); - int vport; + struct mlx5_eswitch_rep_if rep_if = {}; - for (vport = 0; vport < total_vfs; vport++) { - struct mlx5_eswitch_rep_if rep_if = {}; + rep_if.load = mlx5e_vport_rep_load; + rep_if.unload = mlx5e_vport_rep_unload; + rep_if.get_proto_dev = mlx5e_vport_rep_get_proto_dev; - rep_if.load = mlx5e_vport_rep_load; - rep_if.unload = mlx5e_vport_rep_unload; - rep_if.get_proto_dev = mlx5e_vport_rep_get_proto_dev; - mlx5_eswitch_register_vport_rep(esw, vport, &rep_if, REP_ETH); - } + mlx5_eswitch_register_vport_reps(esw, &rep_if, REP_ETH); } void mlx5e_rep_unregister_vport_reps(struct mlx5_core_dev *mdev) { struct mlx5_eswitch *esw = mdev->priv.eswitch; - int total_vfs = MLX5_TOTAL_VPORTS(mdev); - int vport; - for (vport = total_vfs - 1; vport >= 0; vport--) - mlx5_eswitch_unregister_vport_rep(esw, vport, REP_ETH); + mlx5_eswitch_unregister_vport_reps(esw, REP_ETH); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index edd722824697..36eafc877e6b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -148,6 +148,7 @@ struct mlx5e_encap_entry { unsigned char h_dest[ETH_ALEN]; /* destination eth addr */ struct net_device *out_dev; + struct net_device *route_dev; int tunnel_type; int tunnel_hlen; int reformat_type; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 85c5dd7fc2c7..b38986e18dd7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -127,6 +127,7 @@ struct mlx5e_tc_flow_parse_attr { struct net_device *filter_dev; struct mlx5_flow_spec spec; int num_mod_hdr_actions; + int max_mod_hdr_actions; void *mod_hdr_actions; int mirred_ifindex[MLX5_MAX_FLOW_FWD_VPORTS]; }; @@ -928,13 +929,13 @@ mlx5e_tc_unoffload_from_slow_path(struct mlx5_eswitch *esw, static int mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, - struct mlx5e_tc_flow_parse_attr *parse_attr, struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; u32 max_chain = mlx5_eswitch_get_chain_range(esw); struct mlx5_esw_flow_attr *attr = flow->esw_attr; + struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr; u16 max_prio = mlx5_eswitch_get_prio_range(esw); struct net_device *out_dev, *encap_dev = NULL; struct mlx5_fc *counter = NULL; @@ -966,7 +967,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, if (!(attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)) continue; - mirred_ifindex = attr->parse_attr->mirred_ifindex[out_index]; + mirred_ifindex = parse_attr->mirred_ifindex[out_index]; out_dev = __dev_get_by_index(dev_net(priv->netdev), mirred_ifindex); err = mlx5e_attach_encap(priv, @@ -1301,7 +1302,7 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv, static int parse_tunnel_attr(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec, struct tc_cls_flower_offload *f, - struct net_device *filter_dev) + struct net_device *filter_dev, u8 *match_level) { struct netlink_ext_ack *extack = f->common.extack; void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, @@ -1313,7 +1314,7 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, int err; err = mlx5e_tc_tun_parse(filter_dev, priv, spec, f, - headers_c, headers_v); + headers_c, headers_v, match_level); if (err) { NL_SET_ERR_MSG_MOD(extack, "failed to parse tunnel attributes"); @@ -1413,7 +1414,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec, struct tc_cls_flower_offload *f, struct net_device *filter_dev, - u8 *match_level) + u8 *match_level, u8 *tunnel_match_level) { struct netlink_ext_ack *extack = f->common.extack; void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, @@ -1464,7 +1465,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, switch (match.key->addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: case FLOW_DISSECTOR_KEY_IPV6_ADDRS: - if (parse_tunnel_attr(priv, spec, f, filter_dev)) + if (parse_tunnel_attr(priv, spec, f, filter_dev, tunnel_match_level)) return -EOPNOTSUPP; break; default: @@ -1767,15 +1768,15 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_core_dev *dev = priv->mdev; struct mlx5_eswitch *esw = dev->priv.eswitch; struct mlx5e_rep_priv *rpriv = priv->ppriv; + u8 match_level, tunnel_match_level = MLX5_MATCH_NONE; struct mlx5_eswitch_rep *rep; - u8 match_level; int err; - err = __parse_cls_flower(priv, spec, f, filter_dev, &match_level); + err = __parse_cls_flower(priv, spec, f, filter_dev, &match_level, &tunnel_match_level); if (!err && (flow->flags & MLX5E_TC_FLOW_ESWITCH)) { rep = rpriv->rep; - if (rep->vport != FDB_UPLINK_VPORT && + if (rep->vport != MLX5_VPORT_UPLINK && (esw->offloads.inline_mode != MLX5_INLINE_MODE_NONE && esw->offloads.inline_mode < match_level)) { NL_SET_ERR_MSG_MOD(extack, @@ -1787,10 +1788,12 @@ static int parse_cls_flower(struct mlx5e_priv *priv, } } - if (flow->flags & MLX5E_TC_FLOW_ESWITCH) + if (flow->flags & MLX5E_TC_FLOW_ESWITCH) { flow->esw_attr->match_level = match_level; - else + flow->esw_attr->tunnel_match_level = tunnel_match_level; + } else { flow->nic_attr->match_level = match_level; + } return err; } @@ -1824,9 +1827,6 @@ static int set_pedit_val(u8 hdr_type, u32 mask, u32 val, u32 offset, { u32 *curr_pmask, *curr_pval; - if (hdr_type >= 2) - goto out_err; - curr_pmask = (u32 *)(pedit_header(&hdrs->masks, hdr_type) + offset); curr_pval = (u32 *)(pedit_header(&hdrs->vals, hdr_type) + offset); @@ -1880,9 +1880,9 @@ static struct mlx5_fields fields[] = { OFFLOAD(UDP_DPORT, 2, udp.dest, 0), }; -/* On input attr->num_mod_hdr_actions tells how many HW actions can be parsed at - * max from the SW pedit action. On success, it says how many HW actions were - * actually parsed. +/* On input attr->max_mod_hdr_actions tells how many HW actions can be parsed at + * max from the SW pedit action. On success, attr->num_mod_hdr_actions + * says how many HW actions were actually parsed. */ static int offload_pedit_fields(struct pedit_headers_action *hdrs, struct mlx5e_tc_flow_parse_attr *parse_attr, @@ -1905,9 +1905,11 @@ static int offload_pedit_fields(struct pedit_headers_action *hdrs, add_vals = &hdrs[1].vals; action_size = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto); - action = parse_attr->mod_hdr_actions; - max_actions = parse_attr->num_mod_hdr_actions; - nactions = 0; + action = parse_attr->mod_hdr_actions + + parse_attr->num_mod_hdr_actions * action_size; + + max_actions = parse_attr->max_mod_hdr_actions; + nactions = parse_attr->num_mod_hdr_actions; for (i = 0; i < ARRAY_SIZE(fields); i++) { f = &fields[i]; @@ -2020,7 +2022,7 @@ static int alloc_mod_hdr_actions(struct mlx5e_priv *priv, if (!parse_attr->mod_hdr_actions) return -ENOMEM; - parse_attr->num_mod_hdr_actions = max_actions; + parse_attr->max_mod_hdr_actions = max_actions; return 0; } @@ -2069,9 +2071,11 @@ static int alloc_tc_pedit_action(struct mlx5e_priv *priv, int namespace, int err; u8 cmd; - err = alloc_mod_hdr_actions(priv, hdrs, namespace, parse_attr); - if (err) - goto out_err; + if (!parse_attr->mod_hdr_actions) { + err = alloc_mod_hdr_actions(priv, hdrs, namespace, parse_attr); + if (err) + goto out_err; + } err = offload_pedit_fields(hdrs, parse_attr, extack); if (err < 0) @@ -2129,6 +2133,7 @@ static bool csum_offload_supported(struct mlx5e_priv *priv, static bool modify_header_match_supported(struct mlx5_flow_spec *spec, struct flow_action *flow_action, + u32 actions, struct netlink_ext_ack *extack) { const struct flow_action_entry *act; @@ -2138,7 +2143,11 @@ static bool modify_header_match_supported(struct mlx5_flow_spec *spec, u16 ethertype; int i; - headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers); + if (actions & MLX5_FLOW_CONTEXT_ACTION_DECAP) + headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, inner_headers); + else + headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers); + ethertype = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ethertype); /* for non-IP we only re-write MACs, so we're okay */ @@ -2191,7 +2200,7 @@ static bool actions_match_supported(struct mlx5e_priv *priv, if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) return modify_header_match_supported(&parse_attr->spec, - flow_action, + flow_action, actions, extack); return true; @@ -2681,7 +2690,7 @@ static struct rhashtable *get_tc_ht(struct mlx5e_priv *priv, int flags) static bool is_peer_flow_needed(struct mlx5e_tc_flow *flow) { struct mlx5_esw_flow_attr *attr = flow->esw_attr; - bool is_rep_ingress = attr->in_rep->vport != FDB_UPLINK_VPORT && + bool is_rep_ingress = attr->in_rep->vport != MLX5_VPORT_UPLINK && flow->flags & MLX5E_TC_FLOW_INGRESS; bool act_is_encap = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT); @@ -2724,6 +2733,30 @@ err_free: return err; } +static void +mlx5e_flow_esw_attr_init(struct mlx5_esw_flow_attr *esw_attr, + struct mlx5e_priv *priv, + struct mlx5e_tc_flow_parse_attr *parse_attr, + struct tc_cls_flower_offload *f, + struct mlx5_eswitch_rep *in_rep, + struct mlx5_core_dev *in_mdev) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + + esw_attr->parse_attr = parse_attr; + esw_attr->chain = f->common.chain_index; + esw_attr->prio = TC_H_MAJ(f->common.prio) >> 16; + + esw_attr->in_rep = in_rep; + esw_attr->in_mdev = in_mdev; + + if (MLX5_CAP_ESW(esw->dev, counter_eswitch_affinity) == + MLX5_COUNTER_SOURCE_ESWITCH) + esw_attr->counter_dev = in_mdev; + else + esw_attr->counter_dev = priv->mdev; +} + static struct mlx5e_tc_flow * __mlx5e_add_fdb_flow(struct mlx5e_priv *priv, struct tc_cls_flower_offload *f, @@ -2734,7 +2767,6 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv, { struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); struct netlink_ext_ack *extack = f->common.extack; - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5e_tc_flow *flow; int attr_size, err; @@ -2745,29 +2777,22 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv, &parse_attr, &flow); if (err) goto out; + parse_attr->filter_dev = filter_dev; - flow->esw_attr->parse_attr = parse_attr; + mlx5e_flow_esw_attr_init(flow->esw_attr, + priv, parse_attr, + f, in_rep, in_mdev); + err = parse_cls_flower(flow->priv, flow, &parse_attr->spec, f, filter_dev); if (err) goto err_free; - flow->esw_attr->chain = f->common.chain_index; - flow->esw_attr->prio = TC_H_MAJ(f->common.prio) >> 16; err = parse_tc_fdb_actions(priv, &rule->action, parse_attr, flow, extack); if (err) goto err_free; - flow->esw_attr->in_rep = in_rep; - flow->esw_attr->in_mdev = in_mdev; - - if (MLX5_CAP_ESW(esw->dev, counter_eswitch_affinity) == - MLX5_COUNTER_SOURCE_ESWITCH) - flow->esw_attr->counter_dev = in_mdev; - else - flow->esw_attr->counter_dev = priv->mdev; - - err = mlx5e_tc_add_fdb_flow(priv, parse_attr, flow, extack); + err = mlx5e_tc_add_fdb_flow(priv, flow, extack); if (err) goto err_free; @@ -2804,7 +2829,7 @@ static int mlx5e_tc_add_fdb_peer_flow(struct tc_cls_flower_offload *f, * original flow and packets redirected from uplink use the * peer mdev. */ - if (flow->esw_attr->in_rep->vport == FDB_UPLINK_VPORT) + if (flow->esw_attr->in_rep->vport == MLX5_VPORT_UPLINK) in_mdev = peer_priv->mdev; else in_mdev = priv->mdev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 598ad7e4d5c9..e7aae45a01f8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -148,12 +148,8 @@ static inline int mlx5e_skb_l2_header_offset(struct sk_buff *skb) static inline int mlx5e_skb_l3_header_offset(struct sk_buff *skb) { - struct flow_keys keys; - if (skb_transport_header_was_set(skb)) return skb_transport_offset(skb); - else if (skb_flow_dissect_flow_keys(skb, &keys, 0)) - return keys.control.thoff; else return mlx5e_skb_l2_header_offset(skb); } @@ -172,15 +168,8 @@ static inline u16 mlx5e_calc_min_inline(enum mlx5_inline_modes mode, hlen += VLAN_HLEN; break; case MLX5_INLINE_MODE_IP: - /* When transport header is set to zero, it means no transport - * header. When transport header is set to 0xff's, it means - * transport header wasn't set. - */ - if (skb_transport_offset(skb)) { - hlen = mlx5e_skb_l3_header_offset(skb); - break; - } - /* fall through */ + hlen = mlx5e_skb_l3_header_offset(skb); + break; case MLX5_INLINE_MODE_L2: default: hlen = mlx5e_skb_l2_header_offset(skb); @@ -387,8 +376,14 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS); contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi); if (unlikely(contig_wqebbs_room < num_wqebbs)) { +#ifdef CONFIG_MLX5_EN_IPSEC + struct mlx5_wqe_eth_seg cur_eth = wqe->eth; +#endif mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room); mlx5e_sq_fetch_wqe(sq, &wqe, &pi); +#ifdef CONFIG_MLX5_EN_IPSEC + wqe->eth = cur_eth; +#endif } /* fill wqe */ @@ -513,8 +508,9 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) &sq->state)) { mlx5e_dump_error_cqe(sq, (struct mlx5_err_cqe *)cqe); - queue_work(cq->channel->priv->wq, - &sq->recover.recover_work); + if (!IS_ERR_OR_NULL(cq->channel->priv->tx_reporter)) + queue_work(cq->channel->priv->wq, + &sq->recover_work); } stats->cqe_err++; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index ee04aab65a9f..bb6e5b5d9681 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -34,6 +34,7 @@ #include <linux/notifier.h> #include <linux/module.h> #include <linux/mlx5/driver.h> +#include <linux/mlx5/vport.h> #include <linux/mlx5/eq.h> #include <linux/mlx5/cmd.h> #ifdef CONFIG_RFS_ACCEL @@ -114,11 +115,11 @@ static struct mlx5_core_cq *mlx5_eq_cq_get(struct mlx5_eq *eq, u32 cqn) struct mlx5_cq_table *table = &eq->cq_table; struct mlx5_core_cq *cq = NULL; - spin_lock(&table->lock); + rcu_read_lock(); cq = radix_tree_lookup(&table->tree, cqn); if (likely(cq)) mlx5_cq_hold(cq); - spin_unlock(&table->lock); + rcu_read_unlock(); return cq; } @@ -371,9 +372,9 @@ int mlx5_eq_add_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq) struct mlx5_cq_table *table = &eq->cq_table; int err; - spin_lock_irq(&table->lock); + spin_lock(&table->lock); err = radix_tree_insert(&table->tree, cq->cqn, cq); - spin_unlock_irq(&table->lock); + spin_unlock(&table->lock); return err; } @@ -383,9 +384,9 @@ int mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq) struct mlx5_cq_table *table = &eq->cq_table; struct mlx5_core_cq *tmp; - spin_lock_irq(&table->lock); + spin_lock(&table->lock); tmp = radix_tree_delete(&table->tree, cq->cqn); - spin_unlock_irq(&table->lock); + spin_unlock(&table->lock); if (!tmp) { mlx5_core_warn(eq->dev, "cq 0x%x not found in eq 0x%x tree\n", eq->eqn, cq->cqn); @@ -530,6 +531,9 @@ static u64 gather_async_events_mask(struct mlx5_core_dev *dev) if (MLX5_CAP_GEN(dev, max_num_of_monitor_counters)) async_event_mask |= (1ull << MLX5_EVENT_TYPE_MONITOR_COUNTER); + if (mlx5_core_is_ecpf_esw_manager(dev)) + async_event_mask |= (1ull << MLX5_EVENT_TYPE_HOST_PARAMS_CHANGE); + return async_event_mask; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 5b492b67f4e1..6cb9710f76d5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -39,8 +39,7 @@ #include "lib/eq.h" #include "eswitch.h" #include "fs_core.h" - -#define UPLINK_VPORT 0xFFFF +#include "ecpf.h" enum { MLX5_ACTION_NONE = 0, @@ -52,7 +51,7 @@ enum { struct vport_addr { struct l2addr_node node; u8 action; - u32 vport; + u16 vport; struct mlx5_flow_handle *flow_rule; bool mpfs; /* UC MAC was added to MPFs */ /* A flag indicating that mac was added due to mc promiscuous vport */ @@ -70,6 +69,28 @@ enum { MC_ADDR_CHANGE | \ PROMISC_CHANGE) +/* The vport getter/iterator are only valid after esw->total_vports + * and vport->vport are initialized in mlx5_eswitch_init. + */ +#define mlx5_esw_for_all_vports(esw, i, vport) \ + for ((i) = MLX5_VPORT_PF; \ + (vport) = &(esw)->vports[i], \ + (i) < (esw)->total_vports; (i)++) + +#define mlx5_esw_for_each_vf_vport(esw, i, vport, nvfs) \ + for ((i) = MLX5_VPORT_FIRST_VF; \ + (vport) = &(esw)->vports[i], \ + (i) <= (nvfs); (i)++) + +static struct mlx5_vport *mlx5_eswitch_get_vport(struct mlx5_eswitch *esw, + u16 vport_num) +{ + u16 idx = mlx5_eswitch_vport_num_to_index(esw, vport_num); + + WARN_ON(idx > esw->total_vports - 1); + return &esw->vports[idx]; +} + static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport, u32 events_mask) { @@ -115,7 +136,7 @@ static int modify_esw_vport_context_cmd(struct mlx5_core_dev *dev, u16 vport, return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); } -static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u32 vport, +static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u16 vport, u16 vlan, u8 qos, u8 set_flags) { u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {0}; @@ -152,7 +173,7 @@ static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u32 vport, /* E-Switch FDB */ static struct mlx5_flow_handle * -__esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule, +__esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u16 vport, bool rx_rule, u8 mac_c[ETH_ALEN], u8 mac_v[ETH_ALEN]) { int match_header = (is_zero_ether_addr(mac_c) ? 0 : @@ -188,7 +209,7 @@ __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule, misc_parameters); mc_misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters); - MLX5_SET(fte_match_set_misc, mv_misc, source_port, UPLINK_VPORT); + MLX5_SET(fte_match_set_misc, mv_misc, source_port, MLX5_VPORT_UPLINK); MLX5_SET_TO_ONES(fte_match_set_misc, mc_misc, source_port); } @@ -215,7 +236,7 @@ __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule, } static struct mlx5_flow_handle * -esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u32 vport) +esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u16 vport) { u8 mac_c[ETH_ALEN]; @@ -224,7 +245,7 @@ esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u32 vport) } static struct mlx5_flow_handle * -esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u32 vport) +esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u16 vport) { u8 mac_c[ETH_ALEN]; u8 mac_v[ETH_ALEN]; @@ -237,7 +258,7 @@ esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u32 vport) } static struct mlx5_flow_handle * -esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u32 vport) +esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u16 vport) { u8 mac_c[ETH_ALEN]; u8 mac_v[ETH_ALEN]; @@ -377,19 +398,19 @@ typedef int (*vport_addr_action)(struct mlx5_eswitch *esw, static int esw_add_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) { u8 *mac = vaddr->node.addr; - u32 vport = vaddr->vport; + u16 vport = vaddr->vport; int err; - /* Skip mlx5_mpfs_add_mac for PFs, - * it is already done by the PF netdev in mlx5e_execute_l2_action + /* Skip mlx5_mpfs_add_mac for eswitch_managers, + * it is already done by its netdev in mlx5e_execute_l2_action */ - if (!vport) + if (esw->manager_vport == vport) goto fdb_add; err = mlx5_mpfs_add_mac(esw->dev, mac); if (err) { esw_warn(esw->dev, - "Failed to add L2 table mac(%pM) for vport(%d), err(%d)\n", + "Failed to add L2 table mac(%pM) for vport(0x%x), err(%d)\n", mac, vport, err); return err; } @@ -409,13 +430,13 @@ fdb_add: static int esw_del_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) { u8 *mac = vaddr->node.addr; - u32 vport = vaddr->vport; + u16 vport = vaddr->vport; int err = 0; - /* Skip mlx5_mpfs_del_mac for PFs, - * it is already done by the PF netdev in mlx5e_execute_l2_action + /* Skip mlx5_mpfs_del_mac for eswitch managerss, + * it is already done by its netdev in mlx5e_execute_l2_action */ - if (!vport || !vaddr->mpfs) + if (!vaddr->mpfs || esw->manager_vport == vport) goto fdb_del; err = mlx5_mpfs_del_mac(esw->dev, mac); @@ -438,17 +459,18 @@ static void update_allmulti_vports(struct mlx5_eswitch *esw, struct esw_mc_addr *esw_mc) { u8 *mac = vaddr->node.addr; - u32 vport_idx = 0; + struct mlx5_vport *vport; + u16 i, vport_num; - for (vport_idx = 0; vport_idx < esw->total_vports; vport_idx++) { - struct mlx5_vport *vport = &esw->vports[vport_idx]; + mlx5_esw_for_all_vports(esw, i, vport) { struct hlist_head *vport_hash = vport->mc_list; struct vport_addr *iter_vaddr = l2addr_hash_find(vport_hash, mac, struct vport_addr); + vport_num = vport->vport; if (IS_ERR_OR_NULL(vport->allmulti_rule) || - vaddr->vport == vport_idx) + vaddr->vport == vport_num) continue; switch (vaddr->action) { case MLX5_ACTION_ADD: @@ -460,14 +482,14 @@ static void update_allmulti_vports(struct mlx5_eswitch *esw, if (!iter_vaddr) { esw_warn(esw->dev, "ALL-MULTI: Failed to add MAC(%pM) to vport[%d] DB\n", - mac, vport_idx); + mac, vport_num); continue; } - iter_vaddr->vport = vport_idx; + iter_vaddr->vport = vport_num; iter_vaddr->flow_rule = esw_fdb_set_vport_rule(esw, mac, - vport_idx); + vport_num); iter_vaddr->mc_promisc = true; break; case MLX5_ACTION_DEL: @@ -485,7 +507,7 @@ static int esw_add_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) struct hlist_head *hash = esw->mc_table; struct esw_mc_addr *esw_mc; u8 *mac = vaddr->node.addr; - u32 vport = vaddr->vport; + u16 vport = vaddr->vport; if (!esw->fdb_table.legacy.fdb) return 0; @@ -499,7 +521,7 @@ static int esw_add_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) return -ENOMEM; esw_mc->uplink_rule = /* Forward MC MAC to Uplink */ - esw_fdb_set_vport_rule(esw, mac, UPLINK_VPORT); + esw_fdb_set_vport_rule(esw, mac, MLX5_VPORT_UPLINK); /* Add this multicast mac to all the mc promiscuous vports */ update_allmulti_vports(esw, vaddr, esw_mc); @@ -525,7 +547,7 @@ static int esw_del_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) struct hlist_head *hash = esw->mc_table; struct esw_mc_addr *esw_mc; u8 *mac = vaddr->node.addr; - u32 vport = vaddr->vport; + u16 vport = vaddr->vport; if (!esw->fdb_table.legacy.fdb) return 0; @@ -564,9 +586,9 @@ static int esw_del_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) /* Apply vport UC/MC list to HW l2 table and FDB table */ static void esw_apply_vport_addr_list(struct mlx5_eswitch *esw, - u32 vport_num, int list_type) + u16 vport_num, int list_type) { - struct mlx5_vport *vport = &esw->vports[vport_num]; + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); bool is_uc = list_type == MLX5_NVPRT_LIST_TYPE_UC; vport_addr_action vport_addr_add; vport_addr_action vport_addr_del; @@ -599,9 +621,9 @@ static void esw_apply_vport_addr_list(struct mlx5_eswitch *esw, /* Sync vport UC/MC list from vport context */ static void esw_update_vport_addr_list(struct mlx5_eswitch *esw, - u32 vport_num, int list_type) + u16 vport_num, int list_type) { - struct mlx5_vport *vport = &esw->vports[vport_num]; + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); bool is_uc = list_type == MLX5_NVPRT_LIST_TYPE_UC; u8 (*mac_list)[ETH_ALEN]; struct l2addr_node *node; @@ -686,9 +708,9 @@ out: /* Sync vport UC/MC list from vport context * Must be called after esw_update_vport_addr_list */ -static void esw_update_vport_mc_promisc(struct mlx5_eswitch *esw, u32 vport_num) +static void esw_update_vport_mc_promisc(struct mlx5_eswitch *esw, u16 vport_num) { - struct mlx5_vport *vport = &esw->vports[vport_num]; + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); struct l2addr_node *node; struct vport_addr *addr; struct hlist_head *hash; @@ -721,11 +743,11 @@ static void esw_update_vport_mc_promisc(struct mlx5_eswitch *esw, u32 vport_num) } /* Apply vport rx mode to HW FDB table */ -static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num, +static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u16 vport_num, bool promisc, bool mc_promisc) { + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); struct esw_mc_addr *allmulti_addr = &esw->mc_promisc; - struct mlx5_vport *vport = &esw->vports[vport_num]; if (IS_ERR_OR_NULL(vport->allmulti_rule) != mc_promisc) goto promisc; @@ -736,7 +758,7 @@ static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num, if (!allmulti_addr->uplink_rule) allmulti_addr->uplink_rule = esw_fdb_set_vport_allmulti_rule(esw, - UPLINK_VPORT); + MLX5_VPORT_UPLINK); allmulti_addr->refcnt++; } else if (vport->allmulti_rule) { mlx5_del_flow_rules(vport->allmulti_rule); @@ -764,9 +786,9 @@ promisc: } /* Sync vport rx mode from vport context */ -static void esw_update_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num) +static void esw_update_vport_rx_mode(struct mlx5_eswitch *esw, u16 vport_num) { - struct mlx5_vport *vport = &esw->vports[vport_num]; + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); int promisc_all = 0; int promisc_uc = 0; int promisc_mc = 0; @@ -1343,8 +1365,8 @@ static void esw_destroy_tsar(struct mlx5_eswitch *esw) static int esw_vport_enable_qos(struct mlx5_eswitch *esw, int vport_num, u32 initial_max_rate, u32 initial_bw_share) { + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0}; - struct mlx5_vport *vport = &esw->vports[vport_num]; struct mlx5_core_dev *dev = esw->dev; void *vport_elem; int err = 0; @@ -1383,7 +1405,7 @@ static int esw_vport_enable_qos(struct mlx5_eswitch *esw, int vport_num, static void esw_vport_disable_qos(struct mlx5_eswitch *esw, int vport_num) { - struct mlx5_vport *vport = &esw->vports[vport_num]; + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); int err = 0; if (!vport->qos.enabled) @@ -1402,8 +1424,8 @@ static void esw_vport_disable_qos(struct mlx5_eswitch *esw, int vport_num) static int esw_vport_qos_config(struct mlx5_eswitch *esw, int vport_num, u32 max_rate, u32 bw_share) { + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0}; - struct mlx5_vport *vport = &esw->vports[vport_num]; struct mlx5_core_dev *dev = esw->dev; void *vport_elem; u32 bitmask = 0; @@ -1459,15 +1481,22 @@ static void esw_apply_vport_conf(struct mlx5_eswitch *esw, { int vport_num = vport->vport; - if (!vport_num) + if (esw->manager_vport == vport_num) return; mlx5_modify_vport_admin_state(esw->dev, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, - vport_num, + vport_num, 1, vport->info.link_state); - mlx5_modify_nic_vport_mac_address(esw->dev, vport_num, vport->info.mac); - mlx5_modify_nic_vport_node_guid(esw->dev, vport_num, vport->info.node_guid); + + /* Host PF has its own mac/guid. */ + if (vport_num) { + mlx5_modify_nic_vport_mac_address(esw->dev, vport_num, + vport->info.mac); + mlx5_modify_nic_vport_node_guid(esw->dev, vport_num, + vport->info.node_guid); + } + modify_esw_vport_cvlan(esw->dev, vport_num, vport->info.vlan, vport->info.qos, (vport->info.vlan || vport->info.qos)); @@ -1513,10 +1542,10 @@ static void esw_vport_destroy_drop_counters(struct mlx5_vport *vport) mlx5_fc_destroy(dev, vport->egress.drop_counter); } -static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num, +static void esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport, int enable_events) { - struct mlx5_vport *vport = &esw->vports[vport_num]; + u16 vport_num = vport->vport; mutex_lock(&esw->state_lock); WARN_ON(vport->enabled); @@ -1539,8 +1568,11 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num, vport->enabled_events = enable_events; vport->enabled = true; - /* only PF is trusted by default */ - if (!vport_num) + /* Esw manager is trusted by default. Host PF (vport 0) is trusted as well + * in smartNIC as it's a vport group manager. + */ + if (esw->manager_vport == vport_num || + (!vport_num && mlx5_core_is_ecpf(esw->dev))) vport->info.trusted = true; esw_vport_change_handle_locked(vport); @@ -1550,9 +1582,10 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num, mutex_unlock(&esw->state_lock); } -static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num) +static void esw_disable_vport(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) { - struct mlx5_vport *vport = &esw->vports[vport_num]; + u16 vport_num = vport->vport; if (!vport->enabled) return; @@ -1573,10 +1606,11 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num) esw_vport_change_handle_locked(vport); vport->enabled_events = 0; esw_vport_disable_qos(esw, vport_num); - if (vport_num && esw->mode == SRIOV_LEGACY) { + if (esw->manager_vport != vport_num && + esw->mode == SRIOV_LEGACY) { mlx5_modify_vport_admin_state(esw->dev, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, - vport_num, + vport_num, 1, MLX5_VPORT_ADMIN_STATE_DOWN); esw_vport_disable_egress_acl(esw, vport); esw_vport_disable_ingress_acl(esw, vport); @@ -1595,7 +1629,7 @@ static int eswitch_vport_event(struct notifier_block *nb, u16 vport_num; vport_num = be16_to_cpu(eqe->data.vport_change.vport_num); - vport = &esw->vports[vport_num]; + vport = mlx5_eswitch_get_vport(esw, vport_num); if (vport->enabled) queue_work(esw->work_queue, &vport->vport_change_handler); @@ -1607,6 +1641,8 @@ static int eswitch_vport_event(struct notifier_block *nb, int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) { + int vf_nvports = 0, total_nvports = 0; + struct mlx5_vport *vport; int err; int i, enabled_events; @@ -1624,6 +1660,18 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) esw_info(esw->dev, "E-Switch enable SRIOV: nvfs(%d) mode (%d)\n", nvfs, mode); + if (mode == SRIOV_OFFLOADS) { + if (mlx5_core_is_ecpf_esw_manager(esw->dev)) { + err = mlx5_query_host_params_num_vfs(esw->dev, &vf_nvports); + if (err) + return err; + total_nvports = esw->total_vports; + } else { + vf_nvports = nvfs; + total_nvports = nvfs + MLX5_SPECIAL_VPORTS(esw->dev); + } + } + esw->mode = mode; mlx5_lag_update(esw->dev); @@ -1633,7 +1681,7 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) } else { mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH); mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); - err = esw_offloads_init(esw, nvfs + 1); + err = esw_offloads_init(esw, vf_nvports, total_nvports); } if (err) @@ -1648,8 +1696,20 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) * 2. FDB/Eswitch is programmed by user space tools */ enabled_events = (mode == SRIOV_LEGACY) ? SRIOV_VPORT_EVENTS : 0; - for (i = 0; i <= nvfs; i++) - esw_enable_vport(esw, i, enabled_events); + + /* Enable PF vport */ + vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF); + esw_enable_vport(esw, vport, enabled_events); + + /* Enable ECPF vports */ + if (mlx5_ecpf_vport_exists(esw->dev)) { + vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF); + esw_enable_vport(esw, vport, enabled_events); + } + + /* Enable VF vports */ + mlx5_esw_for_each_vf_vport(esw, i, vport, nvfs) + esw_enable_vport(esw, vport, enabled_events); if (mode == SRIOV_LEGACY) { MLX5_NB_INIT(&esw->nb, eswitch_vport_event, NIC_VPORT_CHANGE); @@ -1674,8 +1734,8 @@ abort: void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw) { struct esw_mc_addr *mc_promisc; + struct mlx5_vport *vport; int old_mode; - int nvports; int i; if (!ESW_ALLOWED(esw) || esw->mode == SRIOV_NONE) @@ -1685,13 +1745,12 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw) esw->enabled_vports, esw->mode); mc_promisc = &esw->mc_promisc; - nvports = esw->enabled_vports; if (esw->mode == SRIOV_LEGACY) mlx5_eq_notifier_unregister(esw->dev, &esw->nb); - for (i = 0; i < esw->total_vports; i++) - esw_disable_vport(esw, i); + mlx5_esw_for_all_vports(esw, i, vport) + esw_disable_vport(esw, vport); if (mc_promisc && mc_promisc->uplink_rule) mlx5_del_flow_rules(mc_promisc->uplink_rule); @@ -1701,7 +1760,7 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw) if (esw->mode == SRIOV_LEGACY) esw_destroy_legacy_fdb_table(esw); else if (esw->mode == SRIOV_OFFLOADS) - esw_offloads_cleanup(esw, nvports); + esw_offloads_cleanup(esw); old_mode = esw->mode; esw->mode = SRIOV_NONE; @@ -1718,8 +1777,8 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) { int total_vports = MLX5_TOTAL_VPORTS(dev); struct mlx5_eswitch *esw; - int vport_num; - int err; + struct mlx5_vport *vport; + int err, i; if (!MLX5_VPORT_MANAGER(dev)) return 0; @@ -1735,6 +1794,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) return -ENOMEM; esw->dev = dev; + esw->manager_vport = mlx5_eswitch_manager_vport(dev); esw->work_queue = create_singlethread_workqueue("mlx5_esw_wq"); if (!esw->work_queue) { @@ -1749,6 +1809,8 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) goto abort; } + esw->total_vports = total_vports; + err = esw_offloads_init_reps(esw); if (err) goto abort; @@ -1757,17 +1819,14 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) hash_init(esw->offloads.mod_hdr_tbl); mutex_init(&esw->state_lock); - for (vport_num = 0; vport_num < total_vports; vport_num++) { - struct mlx5_vport *vport = &esw->vports[vport_num]; - - vport->vport = vport_num; + mlx5_esw_for_all_vports(esw, i, vport) { + vport->vport = mlx5_eswitch_index_to_vport_num(esw, i); vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO; vport->dev = dev; INIT_WORK(&vport->vport_change_handler, esw_vport_change_handler); } - esw->total_vports = total_vports; esw->enabled_vports = 0; esw->mode = SRIOV_NONE; esw->offloads.inline_mode = MLX5_INLINE_MODE_NONE; @@ -1866,7 +1925,7 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, err = mlx5_modify_vport_admin_state(esw->dev, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, - vport, link_state); + vport, 1, link_state); if (err) { mlx5_core_warn(esw->dev, "Failed to set vport %d link state, err = %d", @@ -2009,8 +2068,7 @@ static u32 calculate_vports_min_rate_divider(struct mlx5_eswitch *esw) u32 max_guarantee = 0; int i; - for (i = 0; i < esw->total_vports; i++) { - evport = &esw->vports[i]; + mlx5_esw_for_all_vports(esw, i, evport) { if (!evport->enabled || evport->info.min_rate < max_guarantee) continue; max_guarantee = evport->info.min_rate; @@ -2029,8 +2087,7 @@ static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider) int err; int i; - for (i = 0; i < esw->total_vports; i++) { - evport = &esw->vports[i]; + mlx5_esw_for_all_vports(esw, i, evport) { if (!evport->enabled) continue; vport_min_rate = evport->info.min_rate; @@ -2045,7 +2102,7 @@ static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider) if (bw_share == evport->qos.bw_share) continue; - err = esw_vport_qos_config(esw, i, vport_max_rate, + err = esw_vport_qos_config(esw, evport->vport, vport_max_rate, bw_share); if (!err) evport->qos.bw_share = bw_share; @@ -2128,7 +2185,7 @@ static int mlx5_eswitch_query_vport_drop_stats(struct mlx5_core_dev *dev, !MLX5_CAP_GEN(dev, transmit_discard_vport_down)) return 0; - err = mlx5_query_vport_down_stats(dev, vport_idx, + err = mlx5_query_vport_down_stats(dev, vport_idx, 1, &rx_discard_vport_down, &tx_discard_vport_down); if (err) @@ -2165,8 +2222,7 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw, MLX5_CMD_OP_QUERY_VPORT_COUNTER); MLX5_SET(query_vport_counter_in, in, op_mod, 0); MLX5_SET(query_vport_counter_in, in, vport_number, vport); - if (vport) - MLX5_SET(query_vport_counter_in, in, other_vport, 1); + MLX5_SET(query_vport_counter_in, in, other_vport, 1); memset(out, 0, outlen); err = mlx5_cmd_exec(esw->dev, in, sizeof(in), out, outlen); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 9c89eea9b2c3..af5581a57e56 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -38,6 +38,7 @@ #include <net/devlink.h> #include <linux/mlx5/device.h> #include <linux/mlx5/eswitch.h> +#include <linux/mlx5/vport.h> #include <linux/mlx5/fs.h> #include "lib/mpfs.h" @@ -49,8 +50,6 @@ #define MLX5_MAX_MC_PER_VPORT(dev) \ (1 << MLX5_CAP_GEN(dev, log_max_current_mc_list)) -#define FDB_UPLINK_VPORT 0xffff - #define MLX5_MIN_BW_SHARE 1 #define MLX5_RATE_TO_BW_SHARE(rate, divider, limit) \ @@ -183,6 +182,16 @@ struct esw_mc_addr { /* SRIOV only */ u32 refcnt; }; +struct mlx5_host_work { + struct work_struct work; + struct mlx5_eswitch *esw; +}; + +struct mlx5_host_info { + struct mlx5_nb nb; + u16 num_vfs; +}; + struct mlx5_eswitch { struct mlx5_core_dev *dev; struct mlx5_nb nb; @@ -206,10 +215,13 @@ struct mlx5_eswitch { struct mlx5_esw_offload offloads; int mode; int nvports; + u16 manager_vport; + struct mlx5_host_info host_info; }; -void esw_offloads_cleanup(struct mlx5_eswitch *esw, int nvports); -int esw_offloads_init(struct mlx5_eswitch *esw, int nvports); +void esw_offloads_cleanup(struct mlx5_eswitch *esw); +int esw_offloads_init(struct mlx5_eswitch *esw, int vf_nvports, + int total_nvports); void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw); int esw_offloads_init_reps(struct mlx5_eswitch *esw); @@ -312,6 +324,7 @@ struct mlx5_esw_flow_attr { } dests[MLX5_MAX_FLOW_FWD_VPORTS]; u32 mod_hdr_id; u8 match_level; + u8 tunnel_match_level; struct mlx5_fc *counter; u32 chain; u16 prio; @@ -364,6 +377,53 @@ bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0, #define esw_debug(dev, format, ...) \ mlx5_core_dbg_mask(dev, MLX5_DEBUG_ESWITCH_MASK, format, ##__VA_ARGS__) + +/* The returned number is valid only when the dev is eswitch manager. */ +static inline u16 mlx5_eswitch_manager_vport(struct mlx5_core_dev *dev) +{ + return mlx5_core_is_ecpf_esw_manager(dev) ? + MLX5_VPORT_ECPF : MLX5_VPORT_PF; +} + +static inline int mlx5_eswitch_uplink_idx(struct mlx5_eswitch *esw) +{ + /* Uplink always locate at the last element of the array.*/ + return esw->total_vports - 1; +} + +static inline int mlx5_eswitch_ecpf_idx(struct mlx5_eswitch *esw) +{ + return esw->total_vports - 2; +} + +static inline int mlx5_eswitch_vport_num_to_index(struct mlx5_eswitch *esw, + u16 vport_num) +{ + if (vport_num == MLX5_VPORT_ECPF) { + if (!mlx5_ecpf_vport_exists(esw->dev)) + esw_warn(esw->dev, "ECPF vport doesn't exist!\n"); + return mlx5_eswitch_ecpf_idx(esw); + } + + if (vport_num == MLX5_VPORT_UPLINK) + return mlx5_eswitch_uplink_idx(esw); + + return vport_num; +} + +static inline int mlx5_eswitch_index_to_vport_num(struct mlx5_eswitch *esw, + int index) +{ + if (index == mlx5_eswitch_ecpf_idx(esw) && + mlx5_ecpf_vport_exists(esw->dev)) + return MLX5_VPORT_ECPF; + + if (index == mlx5_eswitch_uplink_idx(esw)) + return MLX5_VPORT_UPLINK; + + return index; +} + #else /* CONFIG_MLX5_ESWITCH */ /* eswitch API stubs */ static inline int mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 53065b6ae593..f2260391be5b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -40,15 +40,59 @@ #include "en.h" #include "fs_core.h" #include "lib/devcom.h" +#include "ecpf.h" +#include "lib/eq.h" enum { FDB_FAST_PATH = 0, FDB_SLOW_PATH }; +/* There are two match-all miss flows, one for unicast dst mac and + * one for multicast. + */ +#define MLX5_ESW_MISS_FLOWS (2) + #define fdb_prio_table(esw, chain, prio, level) \ (esw)->fdb_table.offloads.fdb_prio[(chain)][(prio)][(level)] +#define UPLINK_REP_INDEX 0 + +/* The rep getter/iterator are only valid after esw->total_vports + * and vport->vport are initialized in mlx5_eswitch_init. + */ +#define mlx5_esw_for_all_reps(esw, i, rep) \ + for ((i) = MLX5_VPORT_PF; \ + (rep) = &(esw)->offloads.vport_reps[i], \ + (i) < (esw)->total_vports; (i)++) + +#define mlx5_esw_for_each_vf_rep(esw, i, rep, nvfs) \ + for ((i) = MLX5_VPORT_FIRST_VF; \ + (rep) = &(esw)->offloads.vport_reps[i], \ + (i) <= (nvfs); (i)++) + +#define mlx5_esw_for_each_vf_rep_reverse(esw, i, rep, nvfs) \ + for ((i) = (nvfs); \ + (rep) = &(esw)->offloads.vport_reps[i], \ + (i) >= MLX5_VPORT_FIRST_VF; (i)--) + +#define mlx5_esw_for_each_vf_vport(esw, vport, nvfs) \ + for ((vport) = MLX5_VPORT_FIRST_VF; \ + (vport) <= (nvfs); (vport)++) + +#define mlx5_esw_for_each_vf_vport_reverse(esw, vport, nvfs) \ + for ((vport) = (nvfs); \ + (vport) >= MLX5_VPORT_FIRST_VF; (vport)--) + +static struct mlx5_eswitch_rep *mlx5_eswitch_get_rep(struct mlx5_eswitch *esw, + u16 vport_num) +{ + u16 idx = mlx5_eswitch_vport_num_to_index(esw, vport_num); + + WARN_ON(idx > esw->total_vports - 1); + return &esw->offloads.vport_reps[idx]; +} + static struct mlx5_flow_table * esw_get_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level); static void @@ -160,14 +204,15 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_eswitch_owner_vhca_id); - if (attr->match_level == MLX5_MATCH_NONE) - spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS; - else - spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS | - MLX5_MATCH_MISC_PARAMETERS; - - if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DECAP) - spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS; + spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS; + if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DECAP) { + if (attr->tunnel_match_level != MLX5_MATCH_NONE) + spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS; + if (attr->match_level != MLX5_MATCH_NONE) + spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS; + } else if (attr->match_level != MLX5_MATCH_NONE) { + spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS; + } if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) flow_act.modify_id = attr->mod_hdr_id; @@ -318,7 +363,7 @@ static int esw_set_global_vlan_pop(struct mlx5_eswitch *esw, u8 val) esw_debug(esw->dev, "%s applying global %s policy\n", __func__, val ? "pop" : "none"); for (vf_vport = 1; vf_vport < esw->enabled_vports; vf_vport++) { rep = &esw->offloads.vport_reps[vf_vport]; - if (!rep->rep_if[REP_ETH].valid) + if (rep->rep_if[REP_ETH].state != REP_LOADED) continue; err = __mlx5_eswitch_set_vport_vlan(esw, rep->vport, 0, 0, val); @@ -359,15 +404,15 @@ static int esw_add_vlan_action_check(struct mlx5_esw_flow_attr *attr, in_rep = attr->in_rep; out_rep = attr->dests[0].rep; - if (push && in_rep->vport == FDB_UPLINK_VPORT) + if (push && in_rep->vport == MLX5_VPORT_UPLINK) goto out_notsupp; - if (pop && out_rep->vport == FDB_UPLINK_VPORT) + if (pop && out_rep->vport == MLX5_VPORT_UPLINK) goto out_notsupp; /* vport has vlan push configured, can't offload VF --> wire rules w.o it */ if (!push && !pop && fwd) - if (in_rep->vlan && out_rep->vport == FDB_UPLINK_VPORT) + if (in_rep->vlan && out_rep->vport == MLX5_VPORT_UPLINK) goto out_notsupp; /* protects against (1) setting rules with different vlans to push and @@ -409,7 +454,7 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw, if (!push && !pop && fwd) { /* tracks VF --> wire rules without vlan push action */ - if (attr->dests[0].rep->vport == FDB_UPLINK_VPORT) { + if (attr->dests[0].rep->vport == MLX5_VPORT_UPLINK) { vport->vlan_refcount++; attr->vlan_handled = true; } @@ -469,7 +514,7 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw, if (!push && !pop && fwd) { /* tracks VF --> wire rules without vlan push action */ - if (attr->dests[0].rep->vport == FDB_UPLINK_VPORT) + if (attr->dests[0].rep->vport == MLX5_VPORT_UPLINK) vport->vlan_refcount--; return 0; @@ -516,7 +561,8 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, int vport, u32 sqn misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); MLX5_SET(fte_match_set_misc, misc, source_sqn, sqn); - MLX5_SET(fte_match_set_misc, misc, source_port, 0x0); /* source vport is 0 */ + /* source vport is the esw manager */ + MLX5_SET(fte_match_set_misc, misc, source_port, esw->manager_vport); misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters); MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_sqn); @@ -561,7 +607,7 @@ static void peer_miss_rules_setup(struct mlx5_core_dev *peer_dev, source_eswitch_owner_vhca_id); dest->type = MLX5_FLOW_DESTINATION_TYPE_VPORT; - dest->vport.num = 0; + dest->vport.num = peer_dev->priv.eswitch->manager_vport; dest->vport.vhca_id = MLX5_CAP_GEN(peer_dev, vhca_id); dest->vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID; } @@ -595,14 +641,35 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); - for (i = 1; i < nvports; i++) { + if (mlx5_core_is_ecpf_esw_manager(esw->dev)) { + MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_PF); + flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, + spec, &flow_act, &dest, 1); + if (IS_ERR(flow)) { + err = PTR_ERR(flow); + goto add_pf_flow_err; + } + flows[MLX5_VPORT_PF] = flow; + } + + if (mlx5_ecpf_vport_exists(esw->dev)) { + MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_ECPF); + flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, + spec, &flow_act, &dest, 1); + if (IS_ERR(flow)) { + err = PTR_ERR(flow); + goto add_ecpf_flow_err; + } + flows[mlx5_eswitch_ecpf_idx(esw)] = flow; + } + + mlx5_esw_for_each_vf_vport(esw, i, mlx5_core_max_vfs(esw->dev)) { MLX5_SET(fte_match_set_misc, misc, source_port, i); flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, spec, &flow_act, &dest, 1); if (IS_ERR(flow)) { err = PTR_ERR(flow); - esw_warn(esw->dev, "FDB: Failed to add peer miss flow rule err %d\n", err); - goto add_flow_err; + goto add_vf_flow_err; } flows[i] = flow; } @@ -612,9 +679,18 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, kvfree(spec); return 0; -add_flow_err: - for (i--; i > 0; i--) +add_vf_flow_err: + nvports = --i; + mlx5_esw_for_each_vf_vport_reverse(esw, i, nvports) mlx5_del_flow_rules(flows[i]); + + if (mlx5_ecpf_vport_exists(esw->dev)) + mlx5_del_flow_rules(flows[mlx5_eswitch_ecpf_idx(esw)]); +add_ecpf_flow_err: + if (mlx5_core_is_ecpf_esw_manager(esw->dev)) + mlx5_del_flow_rules(flows[MLX5_VPORT_PF]); +add_pf_flow_err: + esw_warn(esw->dev, "FDB: Failed to add peer miss flow rule err %d\n", err); kvfree(flows); alloc_flows_err: kvfree(spec); @@ -628,9 +704,15 @@ static void esw_del_fdb_peer_miss_rules(struct mlx5_eswitch *esw) flows = esw->fdb_table.offloads.peer_miss_rules; - for (i = 1; i < esw->total_vports; i++) + mlx5_esw_for_each_vf_vport_reverse(esw, i, mlx5_core_max_vfs(esw->dev)) mlx5_del_flow_rules(flows[i]); + if (mlx5_ecpf_vport_exists(esw->dev)) + mlx5_del_flow_rules(flows[mlx5_eswitch_ecpf_idx(esw)]); + + if (mlx5_core_is_ecpf_esw_manager(esw->dev)) + mlx5_del_flow_rules(flows[MLX5_VPORT_PF]); + kvfree(flows); } @@ -660,7 +742,7 @@ static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw) dmac_c[0] = 0x01; dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT; - dest.vport.num = 0; + dest.vport.num = esw->manager_vport; flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, spec, @@ -904,8 +986,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports) esw->fdb_table.offloads.fdb_left[i] = ESW_POOLS[i] <= fdb_max ? ESW_SIZE / ESW_POOLS[i] : 0; - table_size = nvports * MAX_SQ_NVPORTS + MAX_PF_SQ + 2 + - esw->total_vports; + table_size = nvports * MAX_SQ_NVPORTS + MAX_PF_SQ + + MLX5_ESW_MISS_FLOWS + esw->total_vports; /* create the slow path fdb with encap set, so further table instances * can be created at run time while VFs are probed if the FW allows that. @@ -999,7 +1081,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports) dmac[0] = 0x01; MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix); - MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ix + 2); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, + ix + MLX5_ESW_MISS_FLOWS); g = mlx5_create_flow_group(fdb, flow_group_in); if (IS_ERR(g)) { @@ -1048,7 +1131,7 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw) esw_destroy_offloads_fast_fdb_tables(esw); } -static int esw_create_offloads_table(struct mlx5_eswitch *esw) +static int esw_create_offloads_table(struct mlx5_eswitch *esw, int nvports) { struct mlx5_flow_table_attr ft_attr = {}; struct mlx5_core_dev *dev = esw->dev; @@ -1062,7 +1145,7 @@ static int esw_create_offloads_table(struct mlx5_eswitch *esw) return -EOPNOTSUPP; } - ft_attr.max_fte = dev->priv.sriov.num_vfs + 2; + ft_attr.max_fte = nvports + MLX5_ESW_MISS_FLOWS; ft_offloads = mlx5_create_flow_table(ns, &ft_attr); if (IS_ERR(ft_offloads)) { @@ -1082,16 +1165,15 @@ static void esw_destroy_offloads_table(struct mlx5_eswitch *esw) mlx5_destroy_flow_table(offloads->ft_offloads); } -static int esw_create_vport_rx_group(struct mlx5_eswitch *esw) +static int esw_create_vport_rx_group(struct mlx5_eswitch *esw, int nvports) { int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); struct mlx5_flow_group *g; - struct mlx5_priv *priv = &esw->dev->priv; u32 *flow_group_in; void *match_criteria, *misc; int err = 0; - int nvports = priv->sriov.num_vfs + 2; + nvports = nvports + MLX5_ESW_MISS_FLOWS; flow_group_in = kvzalloc(inlen, GFP_KERNEL); if (!flow_group_in) return -ENOMEM; @@ -1168,7 +1250,8 @@ static int esw_offloads_start(struct mlx5_eswitch *esw, { int err, err1, num_vfs = esw->dev->priv.sriov.num_vfs; - if (esw->mode != SRIOV_LEGACY) { + if (esw->mode != SRIOV_LEGACY && + !mlx5_core_is_ecpf_esw_manager(esw->dev)) { NL_SET_ERR_MSG_MOD(extack, "Can't set offloads mode, SRIOV legacy not enabled"); return -EINVAL; @@ -1206,9 +1289,8 @@ int esw_offloads_init_reps(struct mlx5_eswitch *esw) { int total_vfs = MLX5_TOTAL_VPORTS(esw->dev); struct mlx5_core_dev *dev = esw->dev; - struct mlx5_esw_offload *offloads; struct mlx5_eswitch_rep *rep; - u8 hw_id[ETH_ALEN]; + u8 hw_id[ETH_ALEN], rep_type; int vport; esw->offloads.vport_reps = kcalloc(total_vfs, @@ -1217,75 +1299,203 @@ int esw_offloads_init_reps(struct mlx5_eswitch *esw) if (!esw->offloads.vport_reps) return -ENOMEM; - offloads = &esw->offloads; mlx5_query_nic_vport_mac_address(dev, 0, hw_id); - for (vport = 0; vport < total_vfs; vport++) { - rep = &offloads->vport_reps[vport]; - - rep->vport = vport; + mlx5_esw_for_all_reps(esw, vport, rep) { + rep->vport = mlx5_eswitch_index_to_vport_num(esw, vport); ether_addr_copy(rep->hw_id, hw_id); - } - offloads->vport_reps[0].vport = FDB_UPLINK_VPORT; + for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) + rep->rep_if[rep_type].state = REP_UNREGISTERED; + } return 0; } -static void esw_offloads_unload_reps_type(struct mlx5_eswitch *esw, int nvports, - u8 rep_type) +static void __esw_offloads_unload_rep(struct mlx5_eswitch *esw, + struct mlx5_eswitch_rep *rep, u8 rep_type) +{ + if (rep->rep_if[rep_type].state != REP_LOADED) + return; + + rep->rep_if[rep_type].unload(rep); + rep->rep_if[rep_type].state = REP_REGISTERED; +} + +static void __unload_reps_special_vport(struct mlx5_eswitch *esw, u8 rep_type) { struct mlx5_eswitch_rep *rep; - int vport; - for (vport = nvports - 1; vport >= 0; vport--) { - rep = &esw->offloads.vport_reps[vport]; - if (!rep->rep_if[rep_type].valid) - continue; + if (mlx5_ecpf_vport_exists(esw->dev)) { + rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_ECPF); + __esw_offloads_unload_rep(esw, rep, rep_type); + } - rep->rep_if[rep_type].unload(rep); + if (mlx5_core_is_ecpf_esw_manager(esw->dev)) { + rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_PF); + __esw_offloads_unload_rep(esw, rep, rep_type); } + + rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK); + __esw_offloads_unload_rep(esw, rep, rep_type); } -static void esw_offloads_unload_reps(struct mlx5_eswitch *esw, int nvports) +static void __unload_reps_vf_vport(struct mlx5_eswitch *esw, int nvports, + u8 rep_type) +{ + struct mlx5_eswitch_rep *rep; + int i; + + mlx5_esw_for_each_vf_rep_reverse(esw, i, rep, nvports) + __esw_offloads_unload_rep(esw, rep, rep_type); +} + +static void esw_offloads_unload_vf_reps(struct mlx5_eswitch *esw, int nvports) +{ + u8 rep_type = NUM_REP_TYPES; + + while (rep_type-- > 0) + __unload_reps_vf_vport(esw, nvports, rep_type); +} + +static void __unload_reps_all_vport(struct mlx5_eswitch *esw, int nvports, + u8 rep_type) +{ + __unload_reps_vf_vport(esw, nvports, rep_type); + + /* Special vports must be the last to unload. */ + __unload_reps_special_vport(esw, rep_type); +} + +static void esw_offloads_unload_all_reps(struct mlx5_eswitch *esw, int nvports) { u8 rep_type = NUM_REP_TYPES; while (rep_type-- > 0) - esw_offloads_unload_reps_type(esw, nvports, rep_type); + __unload_reps_all_vport(esw, nvports, rep_type); +} + +static int __esw_offloads_load_rep(struct mlx5_eswitch *esw, + struct mlx5_eswitch_rep *rep, u8 rep_type) +{ + int err = 0; + + if (rep->rep_if[rep_type].state != REP_REGISTERED) + return 0; + + err = rep->rep_if[rep_type].load(esw->dev, rep); + if (err) + return err; + + rep->rep_if[rep_type].state = REP_LOADED; + + return 0; } -static int esw_offloads_load_reps_type(struct mlx5_eswitch *esw, int nvports, - u8 rep_type) +static int __load_reps_special_vport(struct mlx5_eswitch *esw, u8 rep_type) { struct mlx5_eswitch_rep *rep; - int vport; int err; - for (vport = 0; vport < nvports; vport++) { - rep = &esw->offloads.vport_reps[vport]; - if (!rep->rep_if[rep_type].valid) - continue; + rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK); + err = __esw_offloads_load_rep(esw, rep, rep_type); + if (err) + return err; - err = rep->rep_if[rep_type].load(esw->dev, rep); + if (mlx5_core_is_ecpf_esw_manager(esw->dev)) { + rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_PF); + err = __esw_offloads_load_rep(esw, rep, rep_type); if (err) - goto err_reps; + goto err_pf; + } + + if (mlx5_ecpf_vport_exists(esw->dev)) { + rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_ECPF); + err = __esw_offloads_load_rep(esw, rep, rep_type); + if (err) + goto err_ecpf; + } + + return 0; + +err_ecpf: + if (mlx5_core_is_ecpf_esw_manager(esw->dev)) { + rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_PF); + __esw_offloads_unload_rep(esw, rep, rep_type); + } + +err_pf: + rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK); + __esw_offloads_unload_rep(esw, rep, rep_type); + return err; +} + +static int __load_reps_vf_vport(struct mlx5_eswitch *esw, int nvports, + u8 rep_type) +{ + struct mlx5_eswitch_rep *rep; + int err, i; + + mlx5_esw_for_each_vf_rep(esw, i, rep, nvports) { + err = __esw_offloads_load_rep(esw, rep, rep_type); + if (err) + goto err_vf; } return 0; +err_vf: + __unload_reps_vf_vport(esw, --i, rep_type); + return err; +} + +static int esw_offloads_load_vf_reps(struct mlx5_eswitch *esw, int nvports) +{ + u8 rep_type = 0; + int err; + + for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) { + err = __load_reps_vf_vport(esw, nvports, rep_type); + if (err) + goto err_reps; + } + + return err; + err_reps: - esw_offloads_unload_reps_type(esw, vport, rep_type); + while (rep_type-- > 0) + __unload_reps_vf_vport(esw, nvports, rep_type); + return err; +} + +static int __load_reps_all_vport(struct mlx5_eswitch *esw, int nvports, + u8 rep_type) +{ + int err; + + /* Special vports must be loaded first. */ + err = __load_reps_special_vport(esw, rep_type); + if (err) + return err; + + err = __load_reps_vf_vport(esw, nvports, rep_type); + if (err) + goto err_vfs; + + return 0; + +err_vfs: + __unload_reps_special_vport(esw, rep_type); return err; } -static int esw_offloads_load_reps(struct mlx5_eswitch *esw, int nvports) +static int esw_offloads_load_all_reps(struct mlx5_eswitch *esw, int nvports) { u8 rep_type = 0; int err; for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) { - err = esw_offloads_load_reps_type(esw, nvports, rep_type); + err = __load_reps_all_vport(esw, nvports, rep_type); if (err) goto err_reps; } @@ -1294,7 +1504,7 @@ static int esw_offloads_load_reps(struct mlx5_eswitch *esw, int nvports) err_reps: while (rep_type-- > 0) - esw_offloads_unload_reps_type(esw, nvports, rep_type); + __unload_reps_all_vport(esw, nvports, rep_type); return err; } @@ -1397,7 +1607,7 @@ static void esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw) mlx5_devcom_unregister_component(devcom, MLX5_DEVCOM_ESW_OFFLOADS); } -int esw_offloads_init(struct mlx5_eswitch *esw, int nvports) +static int esw_offloads_steering_init(struct mlx5_eswitch *esw, int nvports) { int err; @@ -1407,24 +1617,16 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int nvports) if (err) return err; - err = esw_create_offloads_table(esw); + err = esw_create_offloads_table(esw, nvports); if (err) goto create_ft_err; - err = esw_create_vport_rx_group(esw); + err = esw_create_vport_rx_group(esw, nvports); if (err) goto create_fg_err; - err = esw_offloads_load_reps(esw, nvports); - if (err) - goto err_reps; - - esw_offloads_devcom_init(esw); return 0; -err_reps: - esw_destroy_vport_rx_group(esw); - create_fg_err: esw_destroy_offloads_table(esw); @@ -1434,6 +1636,95 @@ create_ft_err: return err; } +static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw) +{ + esw_destroy_vport_rx_group(esw); + esw_destroy_offloads_table(esw); + esw_destroy_offloads_fdb_tables(esw); +} + +static void esw_host_params_event_handler(struct work_struct *work) +{ + struct mlx5_host_work *host_work; + struct mlx5_eswitch *esw; + int err, num_vf = 0; + + host_work = container_of(work, struct mlx5_host_work, work); + esw = host_work->esw; + + err = mlx5_query_host_params_num_vfs(esw->dev, &num_vf); + if (err || num_vf == esw->host_info.num_vfs) + goto out; + + /* Number of VFs can only change from "0 to x" or "x to 0". */ + if (esw->host_info.num_vfs > 0) { + esw_offloads_unload_vf_reps(esw, esw->host_info.num_vfs); + } else { + err = esw_offloads_load_vf_reps(esw, num_vf); + + if (err) + goto out; + } + + esw->host_info.num_vfs = num_vf; + +out: + kfree(host_work); +} + +static int esw_host_params_event(struct notifier_block *nb, + unsigned long type, void *data) +{ + struct mlx5_host_work *host_work; + struct mlx5_host_info *host_info; + struct mlx5_eswitch *esw; + + host_work = kzalloc(sizeof(*host_work), GFP_ATOMIC); + if (!host_work) + return NOTIFY_DONE; + + host_info = mlx5_nb_cof(nb, struct mlx5_host_info, nb); + esw = container_of(host_info, struct mlx5_eswitch, host_info); + + host_work->esw = esw; + + INIT_WORK(&host_work->work, esw_host_params_event_handler); + queue_work(esw->work_queue, &host_work->work); + + return NOTIFY_OK; +} + +int esw_offloads_init(struct mlx5_eswitch *esw, int vf_nvports, + int total_nvports) +{ + int err; + + mutex_init(&esw->fdb_table.offloads.fdb_prio_lock); + + err = esw_offloads_steering_init(esw, total_nvports); + if (err) + return err; + + err = esw_offloads_load_all_reps(esw, vf_nvports); + if (err) + goto err_reps; + + esw_offloads_devcom_init(esw); + + if (mlx5_core_is_ecpf_esw_manager(esw->dev)) { + MLX5_NB_INIT(&esw->host_info.nb, esw_host_params_event, + HOST_PARAMS_CHANGE); + mlx5_eq_notifier_register(esw->dev, &esw->host_info.nb); + esw->host_info.num_vfs = vf_nvports; + } + + return 0; + +err_reps: + esw_offloads_steering_cleanup(esw); + return err; +} + static int esw_offloads_stop(struct mlx5_eswitch *esw, struct netlink_ext_ack *extack) { @@ -1453,13 +1744,21 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw, return err; } -void esw_offloads_cleanup(struct mlx5_eswitch *esw, int nvports) +void esw_offloads_cleanup(struct mlx5_eswitch *esw) { + u16 num_vfs; + + if (mlx5_core_is_ecpf_esw_manager(esw->dev)) { + mlx5_eq_notifier_unregister(esw->dev, &esw->host_info.nb); + flush_workqueue(esw->work_queue); + num_vfs = esw->host_info.num_vfs; + } else { + num_vfs = esw->dev->priv.sriov.num_vfs; + } + esw_offloads_devcom_cleanup(esw); - esw_offloads_unload_reps(esw, nvports); - esw_destroy_vport_rx_group(esw); - esw_destroy_offloads_table(esw); - esw_destroy_offloads_fdb_tables(esw); + esw_offloads_unload_all_reps(esw, num_vfs); + esw_offloads_steering_cleanup(esw); } static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode) @@ -1548,7 +1847,8 @@ static int mlx5_devlink_eswitch_check(struct devlink *devlink) if(!MLX5_ESWITCH_MANAGER(dev)) return -EPERM; - if (dev->priv.eswitch->mode == SRIOV_NONE) + if (dev->priv.eswitch->mode == SRIOV_NONE && + !mlx5_core_is_ecpf_esw_manager(dev)) return -EOPNOTSUPP; return 0; @@ -1760,47 +2060,45 @@ int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, u8 *encap) return 0; } -void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw, - int vport_index, - struct mlx5_eswitch_rep_if *__rep_if, - u8 rep_type) +void mlx5_eswitch_register_vport_reps(struct mlx5_eswitch *esw, + struct mlx5_eswitch_rep_if *__rep_if, + u8 rep_type) { - struct mlx5_esw_offload *offloads = &esw->offloads; struct mlx5_eswitch_rep_if *rep_if; + struct mlx5_eswitch_rep *rep; + int i; - rep_if = &offloads->vport_reps[vport_index].rep_if[rep_type]; - - rep_if->load = __rep_if->load; - rep_if->unload = __rep_if->unload; - rep_if->get_proto_dev = __rep_if->get_proto_dev; - rep_if->priv = __rep_if->priv; + mlx5_esw_for_all_reps(esw, i, rep) { + rep_if = &rep->rep_if[rep_type]; + rep_if->load = __rep_if->load; + rep_if->unload = __rep_if->unload; + rep_if->get_proto_dev = __rep_if->get_proto_dev; + rep_if->priv = __rep_if->priv; - rep_if->valid = true; + rep_if->state = REP_REGISTERED; + } } -EXPORT_SYMBOL(mlx5_eswitch_register_vport_rep); +EXPORT_SYMBOL(mlx5_eswitch_register_vport_reps); -void mlx5_eswitch_unregister_vport_rep(struct mlx5_eswitch *esw, - int vport_index, u8 rep_type) +void mlx5_eswitch_unregister_vport_reps(struct mlx5_eswitch *esw, u8 rep_type) { - struct mlx5_esw_offload *offloads = &esw->offloads; + u16 max_vf = mlx5_core_max_vfs(esw->dev); struct mlx5_eswitch_rep *rep; + int i; - rep = &offloads->vport_reps[vport_index]; - - if (esw->mode == SRIOV_OFFLOADS && esw->vports[vport_index].enabled) - rep->rep_if[rep_type].unload(rep); + if (esw->mode == SRIOV_OFFLOADS) + __unload_reps_all_vport(esw, max_vf, rep_type); - rep->rep_if[rep_type].valid = false; + mlx5_esw_for_all_reps(esw, i, rep) + rep->rep_if[rep_type].state = REP_UNREGISTERED; } -EXPORT_SYMBOL(mlx5_eswitch_unregister_vport_rep); +EXPORT_SYMBOL(mlx5_eswitch_unregister_vport_reps); void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type) { -#define UPLINK_REP_INDEX 0 - struct mlx5_esw_offload *offloads = &esw->offloads; struct mlx5_eswitch_rep *rep; - rep = &offloads->vport_reps[UPLINK_REP_INDEX]; + rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK); return rep->rep_if[rep_type].priv; } @@ -1808,15 +2106,11 @@ void *mlx5_eswitch_get_proto_dev(struct mlx5_eswitch *esw, int vport, u8 rep_type) { - struct mlx5_esw_offload *offloads = &esw->offloads; struct mlx5_eswitch_rep *rep; - if (vport == FDB_UPLINK_VPORT) - vport = UPLINK_REP_INDEX; - - rep = &offloads->vport_reps[vport]; + rep = mlx5_eswitch_get_rep(esw, vport); - if (rep->rep_if[rep_type].valid && + if (rep->rep_if[rep_type].state == REP_LOADED && rep->rep_if[rep_type].get_proto_dev) return rep->rep_if[rep_type].get_proto_dev(rep); return NULL; @@ -1825,13 +2119,13 @@ EXPORT_SYMBOL(mlx5_eswitch_get_proto_dev); void *mlx5_eswitch_uplink_get_proto_dev(struct mlx5_eswitch *esw, u8 rep_type) { - return mlx5_eswitch_get_proto_dev(esw, UPLINK_REP_INDEX, rep_type); + return mlx5_eswitch_get_proto_dev(esw, MLX5_VPORT_UPLINK, rep_type); } EXPORT_SYMBOL(mlx5_eswitch_uplink_get_proto_dev); struct mlx5_eswitch_rep *mlx5_eswitch_vport_rep(struct mlx5_eswitch *esw, int vport) { - return &esw->offloads.vport_reps[vport]; + return mlx5_eswitch_get_rep(esw, vport); } EXPORT_SYMBOL(mlx5_eswitch_vport_rep); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c index fbc42b7252a9..5d5864e8df3c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/events.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c @@ -103,6 +103,8 @@ static const char *eqe_type_str(u8 type) return "MLX5_EVENT_TYPE_STALL_EVENT"; case MLX5_EVENT_TYPE_CMD: return "MLX5_EVENT_TYPE_CMD"; + case MLX5_EVENT_TYPE_HOST_PARAMS_CHANGE: + return "MLX5_EVENT_TYPE_HOST_PARAMS_CHANGE"; case MLX5_EVENT_TYPE_PAGE_REQUEST: return "MLX5_EVENT_TYPE_PAGE_REQUEST"; case MLX5_EVENT_TYPE_PAGE_FAULT: @@ -211,11 +213,10 @@ static int port_module(struct notifier_block *nb, unsigned long type, void *data enum port_module_event_status_type module_status; enum port_module_event_error_type error_type; struct mlx5_eqe_port_module *module_event_eqe; - const char *status_str, *error_str; + const char *status_str; u8 module_num; module_event_eqe = &eqe->data.port_module; - module_num = module_event_eqe->module; module_status = module_event_eqe->module_status & PORT_MODULE_EVENT_MODULE_STATUS_MASK; error_type = module_event_eqe->error_type & @@ -223,25 +224,27 @@ static int port_module(struct notifier_block *nb, unsigned long type, void *data if (module_status < MLX5_MODULE_STATUS_NUM) events->pme_stats.status_counters[module_status]++; - status_str = mlx5_pme_status_to_string(module_status); - if (module_status == MLX5_MODULE_STATUS_ERROR) { + if (module_status == MLX5_MODULE_STATUS_ERROR) if (error_type < MLX5_MODULE_EVENT_ERROR_NUM) events->pme_stats.error_counters[error_type]++; - error_str = mlx5_pme_error_to_string(error_type); - } if (!printk_ratelimit()) return NOTIFY_OK; - if (module_status == MLX5_MODULE_STATUS_ERROR) + module_num = module_event_eqe->module; + status_str = mlx5_pme_status_to_string(module_status); + if (module_status == MLX5_MODULE_STATUS_ERROR) { + const char *error_str = mlx5_pme_error_to_string(error_type); + mlx5_core_err(events->dev, "Port module event[error]: module %u, %s, %s\n", module_num, status_str, error_str); - else + } else { mlx5_core_info(events->dev, "Port module event: module %u, %s\n", module_num, status_str); + } return NOTIFY_OK; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c index 27c5f6c7d36a..d046d1ec2a86 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c @@ -317,7 +317,6 @@ static int mlx5_fpga_event(struct mlx5_fpga_device *fdev, const char *event_name; bool teardown = false; unsigned long flags; - u32 fpga_qpn; u8 syndrome; switch (event) { @@ -328,7 +327,6 @@ static int mlx5_fpga_event(struct mlx5_fpga_device *fdev, case MLX5_EVENT_TYPE_FPGA_QP_ERROR: syndrome = MLX5_GET(fpga_qp_error_event, data, syndrome); event_name = mlx5_fpga_qp_syndrome_to_string(syndrome); - fpga_qpn = MLX5_GET(fpga_qp_error_event, data, fpga_qpn); break; default: return NOTIFY_DONE; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index b354f3ee94c5..f2cfa012315e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -32,6 +32,7 @@ #include <linux/mutex.h> #include <linux/mlx5/driver.h> +#include <linux/mlx5/vport.h> #include <linux/mlx5/eswitch.h> #include "mlx5_core.h" diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 196c07383082..cb9fa3430c53 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -103,7 +103,7 @@ void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force) mlx5_core_err(dev, "start\n"); if (pci_channel_offline(dev->pdev) || in_fatal(dev) || force) { dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR; - mlx5_cmd_trigger_completions(dev); + mlx5_cmd_flush(dev); } mlx5_notifier_call_chain(dev->priv.events, MLX5_DEV_EVENT_SYS_ERROR, (void *)1); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index bfc0f6581729..4eac42555c7d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -446,11 +446,11 @@ static int mlx5i_change_mtu(struct net_device *netdev, int new_mtu) new_channels.params = *params; new_channels.params.sw_mtu = new_mtu; - err = mlx5e_open_channels(priv, &new_channels); + + err = mlx5e_safe_switch_channels(priv, &new_channels, NULL); if (err) goto out; - mlx5e_switch_priv_channels(priv, &new_channels, NULL); netdev->mtu = new_channels.params.sw_mtu; out: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c index 2d223385dc81..04c5aca7f8c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c @@ -343,6 +343,11 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) roce_lag = !mlx5_sriov_is_enabled(dev0) && !mlx5_sriov_is_enabled(dev1); +#ifdef CONFIG_MLX5_ESWITCH + roce_lag &= dev0->priv.eswitch->mode == SRIOV_NONE && + dev1->priv.eswitch->mode == SRIOV_NONE; +#endif + if (roce_lag) mlx5_lag_remove_ib_devices(ldev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mad.c b/drivers/net/ethernet/mellanox/mlx5/core/mad.c deleted file mode 100644 index 3a3b0005fd2b..000000000000 --- a/drivers/net/ethernet/mellanox/mlx5/core/mad.c +++ /dev/null @@ -1,75 +0,0 @@ -/* - * Copyright (c) 2013-2015, Mellanox Technologies. 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. - */ - -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/mlx5/driver.h> -#include <linux/mlx5/cmd.h> -#include "mlx5_core.h" - -int mlx5_core_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb, - u16 opmod, u8 port) -{ - int outlen = MLX5_ST_SZ_BYTES(mad_ifc_out); - int inlen = MLX5_ST_SZ_BYTES(mad_ifc_in); - int err = -ENOMEM; - void *data; - void *resp; - u32 *out; - u32 *in; - - in = kzalloc(inlen, GFP_KERNEL); - out = kzalloc(outlen, GFP_KERNEL); - if (!in || !out) - goto out; - - MLX5_SET(mad_ifc_in, in, opcode, MLX5_CMD_OP_MAD_IFC); - MLX5_SET(mad_ifc_in, in, op_mod, opmod); - MLX5_SET(mad_ifc_in, in, port, port); - - data = MLX5_ADDR_OF(mad_ifc_in, in, mad); - memcpy(data, inb, MLX5_FLD_SZ_BYTES(mad_ifc_in, mad)); - - err = mlx5_cmd_exec(dev, in, inlen, out, outlen); - if (err) - goto out; - - resp = MLX5_ADDR_OF(mad_ifc_out, out, response_mad_packet); - memcpy(outb, resp, - MLX5_FLD_SZ_BYTES(mad_ifc_out, response_mad_packet)); - -out: - kfree(out); - kfree(in); - return err; -} -EXPORT_SYMBOL_GPL(mlx5_core_mad_ifc); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index be81b319b0dc..40d591c8e76c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -65,6 +65,7 @@ #include "lib/vxlan.h" #include "lib/devcom.h" #include "diag/fw_tracer.h" +#include "ecpf.h" MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>"); MODULE_DESCRIPTION("Mellanox 5th generation network adapters (ConnectX series) core driver"); @@ -459,6 +460,50 @@ static int handle_hca_cap_atomic(struct mlx5_core_dev *dev) return err; } +static int handle_hca_cap_odp(struct mlx5_core_dev *dev) +{ + void *set_hca_cap; + void *set_ctx; + int set_sz; + int err; + + if (!MLX5_CAP_GEN(dev, pg)) + return 0; + + err = mlx5_core_get_caps(dev, MLX5_CAP_ODP); + if (err) + return err; + + if (!(MLX5_CAP_ODP_MAX(dev, ud_odp_caps.srq_receive) || + MLX5_CAP_ODP_MAX(dev, rc_odp_caps.srq_receive) || + MLX5_CAP_ODP_MAX(dev, xrc_odp_caps.srq_receive))) + return 0; + + set_sz = MLX5_ST_SZ_BYTES(set_hca_cap_in); + set_ctx = kzalloc(set_sz, GFP_KERNEL); + if (!set_ctx) + return -ENOMEM; + + set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, capability); + memcpy(set_hca_cap, dev->caps.hca_cur[MLX5_CAP_ODP], + MLX5_ST_SZ_BYTES(odp_cap)); + + /* set ODP SRQ support for RC/UD and XRC transports */ + MLX5_SET(odp_cap, set_hca_cap, ud_odp_caps.srq_receive, + MLX5_CAP_ODP_MAX(dev, ud_odp_caps.srq_receive)); + + MLX5_SET(odp_cap, set_hca_cap, rc_odp_caps.srq_receive, + MLX5_CAP_ODP_MAX(dev, rc_odp_caps.srq_receive)); + + MLX5_SET(odp_cap, set_hca_cap, xrc_odp_caps.srq_receive, + MLX5_CAP_ODP_MAX(dev, xrc_odp_caps.srq_receive)); + + err = set_caps(dev, set_ctx, set_sz, MLX5_SET_HCA_CAP_OP_MOD_ODP); + + kfree(set_ctx); + return err; +} + static int handle_hca_cap(struct mlx5_core_dev *dev) { void *set_ctx = NULL; @@ -567,6 +612,8 @@ int mlx5_core_enable_hca(struct mlx5_core_dev *dev, u16 func_id) MLX5_SET(enable_hca_in, in, opcode, MLX5_CMD_OP_ENABLE_HCA); MLX5_SET(enable_hca_in, in, function_id, func_id); + MLX5_SET(enable_hca_in, in, embedded_cpu_function, + dev->caps.embedded_cpu); return mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out)); } @@ -577,6 +624,8 @@ int mlx5_core_disable_hca(struct mlx5_core_dev *dev, u16 func_id) MLX5_SET(disable_hca_in, in, opcode, MLX5_CMD_OP_DISABLE_HCA); MLX5_SET(disable_hca_in, in, function_id, func_id); + MLX5_SET(enable_hca_in, in, embedded_cpu_function, + dev->caps.embedded_cpu); return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } @@ -693,6 +742,11 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct mlx5_priv *priv) goto err_clr_master; } + if (pci_enable_atomic_ops_to_root(pdev, PCI_EXP_DEVCAP2_ATOMIC_COMP32) && + pci_enable_atomic_ops_to_root(pdev, PCI_EXP_DEVCAP2_ATOMIC_COMP64) && + pci_enable_atomic_ops_to_root(pdev, PCI_EXP_DEVCAP2_ATOMIC_COMP128)) + mlx5_core_dbg(dev, "Enabling pci atomics failed\n"); + dev->iseg_base = pci_resource_start(dev->pdev, 0); dev->iseg = ioremap(dev->iseg_base, sizeof(*dev->iseg)); if (!dev->iseg) { @@ -849,6 +903,7 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, struct pci_dev *pdev = dev->pdev; int err; + dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev); mutex_lock(&dev->intf_state_mutex); if (test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) { dev_warn(&dev->pdev->dev, "%s: interface is up, NOP\n", @@ -926,6 +981,12 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, goto reclaim_boot_pages; } + err = handle_hca_cap_odp(dev); + if (err) { + dev_err(&pdev->dev, "handle_hca_cap_odp failed\n"); + goto reclaim_boot_pages; + } + err = mlx5_satisfy_startup_pages(dev, 0); if (err) { dev_err(&pdev->dev, "failed to allocate init pages\n"); @@ -1014,6 +1075,12 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, goto err_sriov; } + err = mlx5_ec_init(dev); + if (err) { + dev_err(&pdev->dev, "Failed to init embedded CPU\n"); + goto err_ec; + } + if (mlx5_device_registered(dev)) { mlx5_attach_device(dev); } else { @@ -1031,6 +1098,9 @@ out: return 0; err_reg_dev: + mlx5_ec_cleanup(dev); + +err_ec: mlx5_sriov_detach(dev); err_sriov: @@ -1105,6 +1175,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, if (mlx5_device_registered(dev)) mlx5_detach_device(dev); + mlx5_ec_cleanup(dev); mlx5_sriov_detach(dev); mlx5_cleanup_fs(dev); mlx5_accel_ipsec_cleanup(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 5300b0b6d836..9529cf9623e3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -121,11 +121,12 @@ int mlx5_modify_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy, u32 modify_bitmask); int mlx5_destroy_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy, u32 element_id); -int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev); +int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages); u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev, struct ptp_system_timestamp *sts); void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev); +void mlx5_cmd_flush(struct mlx5_core_dev *dev); int mlx5_cq_debugfs_init(struct mlx5_core_dev *dev); void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c index 0670165afd5f..ea744d8466ea 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c @@ -51,9 +51,10 @@ void mlx5_cleanup_mkey_table(struct mlx5_core_dev *dev) int mlx5_core_create_mkey_cb(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey, - u32 *in, int inlen, - u32 *out, int outlen, - mlx5_cmd_cbk_t callback, void *context) + struct mlx5_async_ctx *async_ctx, u32 *in, + int inlen, u32 *out, int outlen, + mlx5_async_cbk_t callback, + struct mlx5_async_work *context) { struct mlx5_mkey_table *table = &dev->priv.mkey_table; u32 lout[MLX5_ST_SZ_DW(create_mkey_out)] = {0}; @@ -71,7 +72,7 @@ int mlx5_core_create_mkey_cb(struct mlx5_core_dev *dev, MLX5_SET(mkc, mkc, mkey_7_0, key); if (callback) - return mlx5_cmd_exec_cb(dev, in, inlen, out, outlen, + return mlx5_cmd_exec_cb(async_ctx, in, inlen, out, outlen, callback, context); err = mlx5_cmd_exec(dev, in, inlen, lout, sizeof(lout)); @@ -105,7 +106,7 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey, u32 *in, int inlen) { - return mlx5_core_create_mkey_cb(dev, mkey, in, inlen, + return mlx5_core_create_mkey_cb(dev, mkey, NULL, in, inlen, NULL, 0, NULL, NULL); } EXPORT_SYMBOL(mlx5_core_create_mkey); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index a83b517b0714..41025387ff2c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -48,6 +48,7 @@ enum { struct mlx5_pages_req { struct mlx5_core_dev *dev; u16 func_id; + u8 ec_function; s32 npages; struct work_struct work; }; @@ -143,6 +144,7 @@ static int mlx5_cmd_query_pages(struct mlx5_core_dev *dev, u16 *func_id, MLX5_SET(query_pages_in, in, op_mod, boot ? MLX5_QUERY_PAGES_IN_OP_MOD_BOOT_PAGES : MLX5_QUERY_PAGES_IN_OP_MOD_INIT_PAGES); + MLX5_SET(query_pages_in, in, embedded_cpu_function, mlx5_core_is_ecpf(dev)); err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); if (err) @@ -253,7 +255,8 @@ err_mapping: return err; } -static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id) +static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id, + bool ec_function) { u32 out[MLX5_ST_SZ_DW(manage_pages_out)] = {0}; u32 in[MLX5_ST_SZ_DW(manage_pages_in)] = {0}; @@ -262,6 +265,7 @@ static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id) MLX5_SET(manage_pages_in, in, opcode, MLX5_CMD_OP_MANAGE_PAGES); MLX5_SET(manage_pages_in, in, op_mod, MLX5_PAGES_CANT_GIVE); MLX5_SET(manage_pages_in, in, function_id, func_id); + MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function); err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); if (err) @@ -270,7 +274,7 @@ static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id) } static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, - int notify_fail) + int notify_fail, bool ec_function) { u32 out[MLX5_ST_SZ_DW(manage_pages_out)] = {0}; int inlen = MLX5_ST_SZ_BYTES(manage_pages_in); @@ -305,6 +309,7 @@ retry: MLX5_SET(manage_pages_in, in, op_mod, MLX5_PAGES_GIVE); MLX5_SET(manage_pages_in, in, function_id, func_id); MLX5_SET(manage_pages_in, in, input_num_entries, npages); + MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function); err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); if (err) { @@ -316,8 +321,11 @@ retry: dev->priv.fw_pages += npages; if (func_id) dev->priv.vfs_pages += npages; + else if (mlx5_core_is_ecpf(dev) && !ec_function) + dev->priv.peer_pf_pages += npages; - mlx5_core_dbg(dev, "err %d\n", err); + mlx5_core_dbg(dev, "npages %d, ec_function %d, func_id 0x%x, err %d\n", + npages, ec_function, func_id, err); kvfree(in); return 0; @@ -328,7 +336,7 @@ out_4k: out_free: kvfree(in); if (notify_fail) - page_notify_fail(dev, func_id); + page_notify_fail(dev, func_id, ec_function); return err; } @@ -364,7 +372,7 @@ static int reclaim_pages_cmd(struct mlx5_core_dev *dev, } static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages, - int *nclaimed) + int *nclaimed, bool ec_function) { int outlen = MLX5_ST_SZ_BYTES(manage_pages_out); u32 in[MLX5_ST_SZ_DW(manage_pages_in)] = {0}; @@ -385,6 +393,7 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages, MLX5_SET(manage_pages_in, in, op_mod, MLX5_PAGES_TAKE); MLX5_SET(manage_pages_in, in, function_id, func_id); MLX5_SET(manage_pages_in, in, input_num_entries, npages); + MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function); mlx5_core_dbg(dev, "npages %d, outlen %d\n", npages, outlen); err = reclaim_pages_cmd(dev, in, sizeof(in), out, outlen); @@ -410,6 +419,8 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages, dev->priv.fw_pages -= num_claimed; if (func_id) dev->priv.vfs_pages -= num_claimed; + else if (mlx5_core_is_ecpf(dev) && !ec_function) + dev->priv.peer_pf_pages -= num_claimed; out_free: kvfree(out); @@ -423,9 +434,10 @@ static void pages_work_handler(struct work_struct *work) int err = 0; if (req->npages < 0) - err = reclaim_pages(dev, req->func_id, -1 * req->npages, NULL); + err = reclaim_pages(dev, req->func_id, -1 * req->npages, NULL, + req->ec_function); else if (req->npages > 0) - err = give_pages(dev, req->func_id, req->npages, 1); + err = give_pages(dev, req->func_id, req->npages, 1, req->ec_function); if (err) mlx5_core_warn(dev, "%s fail %d\n", @@ -434,6 +446,10 @@ static void pages_work_handler(struct work_struct *work) kfree(req); } +enum { + EC_FUNCTION_MASK = 0x8000, +}; + static int req_pages_handler(struct notifier_block *nb, unsigned long type, void *data) { @@ -441,6 +457,7 @@ static int req_pages_handler(struct notifier_block *nb, struct mlx5_core_dev *dev; struct mlx5_priv *priv; struct mlx5_eqe *eqe; + bool ec_function; u16 func_id; s32 npages; @@ -450,6 +467,7 @@ static int req_pages_handler(struct notifier_block *nb, func_id = be16_to_cpu(eqe->data.req_pages.func_id); npages = be32_to_cpu(eqe->data.req_pages.num_pages); + ec_function = be16_to_cpu(eqe->data.req_pages.ec_function) & EC_FUNCTION_MASK; mlx5_core_dbg(dev, "page request for func 0x%x, npages %d\n", func_id, npages); req = kzalloc(sizeof(*req), GFP_ATOMIC); @@ -461,6 +479,7 @@ static int req_pages_handler(struct notifier_block *nb, req->dev = dev; req->func_id = func_id; req->npages = npages; + req->ec_function = ec_function; INIT_WORK(&req->work, pages_work_handler); queue_work(dev->priv.pg_wq, &req->work); return NOTIFY_OK; @@ -479,7 +498,7 @@ int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot) mlx5_core_dbg(dev, "requested %d %s pages for func_id 0x%x\n", npages, boot ? "boot" : "init", func_id); - return give_pages(dev, func_id, npages, 0); + return give_pages(dev, func_id, npages, 0, mlx5_core_is_ecpf(dev)); } enum { @@ -513,7 +532,7 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev) fwp = rb_entry(p, struct fw_page, rb_node); err = reclaim_pages(dev, fwp->func_id, optimal_reclaimed_pages(), - &nclaimed); + &nclaimed, mlx5_core_is_ecpf(dev)); if (err) { mlx5_core_warn(dev, "failed reclaiming pages (%d)\n", @@ -535,6 +554,9 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev) WARN(dev->priv.vfs_pages, "VFs FW pages counter is %d after reclaiming all pages\n", dev->priv.vfs_pages); + WARN(dev->priv.peer_pf_pages, + "Peer PF FW pages counter is %d after reclaiming all pages\n", + dev->priv.peer_pf_pages); return 0; } @@ -567,10 +589,10 @@ void mlx5_pagealloc_stop(struct mlx5_core_dev *dev) flush_workqueue(dev->priv.pg_wq); } -int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev) +int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages) { unsigned long end = jiffies + msecs_to_jiffies(MAX_RECLAIM_VFS_PAGES_TIME_MSECS); - int prev_vfs_pages = dev->priv.vfs_pages; + int prev_pages = *pages; /* In case of internal error we will free the pages manually later */ if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) { @@ -578,16 +600,16 @@ int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev) return 0; } - mlx5_core_dbg(dev, "Waiting for %d pages from %s\n", prev_vfs_pages, + mlx5_core_dbg(dev, "Waiting for %d pages from %s\n", prev_pages, dev->priv.name); - while (dev->priv.vfs_pages) { + while (*pages) { if (time_after(jiffies, end)) { - mlx5_core_warn(dev, "aborting while there are %d pending pages\n", dev->priv.vfs_pages); + mlx5_core_warn(dev, "aborting while there are %d pending pages\n", *pages); return -ETIMEDOUT; } - if (dev->priv.vfs_pages < prev_vfs_pages) { + if (*pages < prev_pages) { end = jiffies + msecs_to_jiffies(MAX_RECLAIM_VFS_PAGES_TIME_MSECS); - prev_vfs_pages = dev->priv.vfs_pages; + prev_pages = *pages; } msleep(50); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 2b82f35f4c35..b81542820528 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -30,10 +30,7 @@ * SOFTWARE. */ -#include <linux/module.h> -#include <linux/mlx5/driver.h> #include <linux/mlx5/port.h> -#include <linux/mlx5/cmd.h> #include "mlx5_core.h" int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in, @@ -157,44 +154,6 @@ int mlx5_set_port_beacon(struct mlx5_core_dev *dev, u16 beacon_duration) sizeof(out), MLX5_REG_MLCR, 0, 1); } -int mlx5_query_port_proto_cap(struct mlx5_core_dev *dev, - u32 *proto_cap, int proto_mask) -{ - u32 out[MLX5_ST_SZ_DW(ptys_reg)]; - int err; - - err = mlx5_query_port_ptys(dev, out, sizeof(out), proto_mask, 1); - if (err) - return err; - - if (proto_mask == MLX5_PTYS_EN) - *proto_cap = MLX5_GET(ptys_reg, out, eth_proto_capability); - else - *proto_cap = MLX5_GET(ptys_reg, out, ib_proto_capability); - - return 0; -} -EXPORT_SYMBOL_GPL(mlx5_query_port_proto_cap); - -int mlx5_query_port_proto_admin(struct mlx5_core_dev *dev, - u32 *proto_admin, int proto_mask) -{ - u32 out[MLX5_ST_SZ_DW(ptys_reg)]; - int err; - - err = mlx5_query_port_ptys(dev, out, sizeof(out), proto_mask, 1); - if (err) - return err; - - if (proto_mask == MLX5_PTYS_EN) - *proto_admin = MLX5_GET(ptys_reg, out, eth_proto_admin); - else - *proto_admin = MLX5_GET(ptys_reg, out, ib_proto_admin); - - return 0; -} -EXPORT_SYMBOL_GPL(mlx5_query_port_proto_admin); - int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev, u8 *link_width_oper, u8 local_port) { @@ -211,23 +170,6 @@ int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev, } EXPORT_SYMBOL_GPL(mlx5_query_port_link_width_oper); -int mlx5_query_port_eth_proto_oper(struct mlx5_core_dev *dev, - u32 *proto_oper, u8 local_port) -{ - u32 out[MLX5_ST_SZ_DW(ptys_reg)]; - int err; - - err = mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_EN, - local_port); - if (err) - return err; - - *proto_oper = MLX5_GET(ptys_reg, out, eth_proto_oper); - - return 0; -} -EXPORT_SYMBOL(mlx5_query_port_eth_proto_oper); - int mlx5_query_port_ib_proto_oper(struct mlx5_core_dev *dev, u8 *proto_oper, u8 local_port) { @@ -245,35 +187,6 @@ int mlx5_query_port_ib_proto_oper(struct mlx5_core_dev *dev, } EXPORT_SYMBOL(mlx5_query_port_ib_proto_oper); -int mlx5_set_port_ptys(struct mlx5_core_dev *dev, bool an_disable, - u32 proto_admin, int proto_mask) -{ - u32 out[MLX5_ST_SZ_DW(ptys_reg)]; - u32 in[MLX5_ST_SZ_DW(ptys_reg)]; - u8 an_disable_admin; - u8 an_disable_cap; - u8 an_status; - - mlx5_query_port_autoneg(dev, proto_mask, &an_status, - &an_disable_cap, &an_disable_admin); - if (!an_disable_cap && an_disable) - return -EPERM; - - memset(in, 0, sizeof(in)); - - MLX5_SET(ptys_reg, in, local_port, 1); - MLX5_SET(ptys_reg, in, an_disable_admin, an_disable); - MLX5_SET(ptys_reg, in, proto_mask, proto_mask); - if (proto_mask == MLX5_PTYS_EN) - MLX5_SET(ptys_reg, in, eth_proto_admin, proto_admin); - else - MLX5_SET(ptys_reg, in, ib_proto_admin, proto_admin); - - return mlx5_core_access_reg(dev, in, sizeof(in), out, - sizeof(out), MLX5_REG_PTYS, 0, 1); -} -EXPORT_SYMBOL_GPL(mlx5_set_port_ptys); - /* This function should be used after setting a port register only */ void mlx5_toggle_port_link(struct mlx5_core_dev *dev) { @@ -606,25 +519,6 @@ int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, u8 *pfc_en_rx) } EXPORT_SYMBOL_GPL(mlx5_query_port_pfc); -void mlx5_query_port_autoneg(struct mlx5_core_dev *dev, int proto_mask, - u8 *an_status, - u8 *an_disable_cap, u8 *an_disable_admin) -{ - u32 out[MLX5_ST_SZ_DW(ptys_reg)]; - - *an_status = 0; - *an_disable_cap = 0; - *an_disable_admin = 0; - - if (mlx5_query_port_ptys(dev, out, sizeof(out), proto_mask, 1)) - return; - - *an_status = MLX5_GET(ptys_reg, out, an_status); - *an_disable_cap = MLX5_GET(ptys_reg, out, an_disable_cap); - *an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin); -} -EXPORT_SYMBOL_GPL(mlx5_query_port_autoneg); - int mlx5_max_tc(struct mlx5_core_dev *mdev) { u8 num_tc = MLX5_CAP_GEN(mdev, max_tc) ? : 8; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index 6e178030d8fb..7b23fa8d2d60 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -147,7 +147,7 @@ out: if (MLX5_ESWITCH_MANAGER(dev)) mlx5_eswitch_disable_sriov(dev->priv.eswitch); - if (mlx5_wait_for_vf_pages(dev)) + if (mlx5_wait_for_pages(dev, &dev->priv.vfs_pages)) mlx5_core_warn(dev, "timeout reclaiming VFs pages\n"); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index 9b150ce9d315..ef95feca9961 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -64,7 +64,7 @@ u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport) } int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod, - u16 vport, u8 state) + u16 vport, u8 other_vport, u8 state) { u32 in[MLX5_ST_SZ_DW(modify_vport_state_in)] = {0}; u32 out[MLX5_ST_SZ_DW(modify_vport_state_out)] = {0}; @@ -73,8 +73,7 @@ int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod, MLX5_CMD_OP_MODIFY_VPORT_STATE); MLX5_SET(modify_vport_state_in, in, op_mod, opmod); MLX5_SET(modify_vport_state_in, in, vport_number, vport); - if (vport) - MLX5_SET(modify_vport_state_in, in, other_vport, 1); + MLX5_SET(modify_vport_state_in, in, other_vport, other_vport); MLX5_SET(modify_vport_state_in, in, admin_state, state); return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); @@ -255,7 +254,7 @@ int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu) EXPORT_SYMBOL_GPL(mlx5_modify_nic_vport_mtu); int mlx5_query_nic_vport_mac_list(struct mlx5_core_dev *dev, - u32 vport, + u16 vport, enum mlx5_list_type list_type, u8 addr_list[][ETH_ALEN], int *list_size) @@ -373,7 +372,7 @@ int mlx5_modify_nic_vport_mac_list(struct mlx5_core_dev *dev, EXPORT_SYMBOL_GPL(mlx5_modify_nic_vport_mac_list); int mlx5_query_nic_vport_vlans(struct mlx5_core_dev *dev, - u32 vport, + u16 vport, u16 vlans[], int *size) { @@ -526,7 +525,7 @@ int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid) EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_node_guid); int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev, - u32 vport, u64 node_guid) + u16 vport, u64 node_guid) { int inlen = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in); void *nic_vport_context; @@ -827,7 +826,7 @@ int mlx5_query_hca_vport_node_guid(struct mlx5_core_dev *dev, EXPORT_SYMBOL_GPL(mlx5_query_hca_vport_node_guid); int mlx5_query_nic_vport_promisc(struct mlx5_core_dev *mdev, - u32 vport, + u16 vport, int *promisc_uc, int *promisc_mc, int *promisc_all) @@ -1057,7 +1056,7 @@ free: EXPORT_SYMBOL_GPL(mlx5_core_query_vport_counter); int mlx5_query_vport_down_stats(struct mlx5_core_dev *mdev, u16 vport, - u64 *rx_discard_vport_down, + u8 other_vport, u64 *rx_discard_vport_down, u64 *tx_discard_vport_down) { u32 out[MLX5_ST_SZ_DW(query_vnic_env_out)] = {0}; @@ -1068,8 +1067,7 @@ int mlx5_query_vport_down_stats(struct mlx5_core_dev *mdev, u16 vport, MLX5_CMD_OP_QUERY_VNIC_ENV); MLX5_SET(query_vnic_env_in, in, op_mod, 0); MLX5_SET(query_vnic_env_in, in, vport_number, vport); - if (vport) - MLX5_SET(query_vnic_env_in, in, other_vport, 1); + MLX5_SET(query_vnic_env_in, in, other_vport, other_vport); err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); if (err) diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile index bbf45f10c208..a01d15546e37 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Makefile +++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_MLXSW_CORE) += mlxsw_core.o mlxsw_core-objs := core.o core_acl_flex_keys.o \ - core_acl_flex_actions.o + core_acl_flex_actions.o core_env.o mlxsw_core-$(CONFIG_MLXSW_CORE_HWMON) += core_hwmon.o mlxsw_core-$(CONFIG_MLXSW_CORE_THERMAL) += core_thermal.o obj-$(CONFIG_MLXSW_PCI) += mlxsw_pci.o diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 4f6fa515394e..b505d3858235 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -1062,6 +1062,9 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, goto err_driver_init; } + if (mlxsw_driver->params_register && !reload) + devlink_params_publish(devlink); + return 0; err_driver_init: @@ -1131,6 +1134,8 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, return; } + if (mlxsw_core->driver->params_unregister && !reload) + devlink_params_unpublish(devlink); if (mlxsw_core->driver->fini) mlxsw_core->driver->fini(mlxsw_core); mlxsw_thermal_fini(mlxsw_core->thermal); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index 4e114f35ee0d..cd0c6aa0dff9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -344,6 +344,7 @@ struct mlxsw_bus_info { struct mlxsw_fw_rev fw_rev; u8 vsd[MLXSW_CMD_BOARDINFO_VSD_LEN]; u8 psid[MLXSW_CMD_BOARDINFO_PSID_LEN]; + u8 low_frequency; }; struct mlxsw_hwmon; @@ -394,4 +395,9 @@ static inline void mlxsw_thermal_fini(struct mlxsw_thermal *thermal) #endif +enum mlxsw_devlink_param_id { + MLXSW_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, + MLXSW_DEVLINK_PARAM_ID_ACL_REGION_REHASH_INTERVAL, +}; + #endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.c b/drivers/net/ethernet/mellanox/mlxsw/core_env.c new file mode 100644 index 000000000000..160d6cd164f4 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.c @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 +/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */ + +#include <linux/kernel.h> +#include <linux/err.h> + +#include "core.h" +#include "core_env.h" +#include "item.h" +#include "reg.h" + +static int mlxsw_env_validate_cable_ident(struct mlxsw_core *core, int id, + bool *qsfp) +{ + char eeprom_tmp[MLXSW_REG_MCIA_EEPROM_SIZE]; + char mcia_pl[MLXSW_REG_MCIA_LEN]; + u8 ident; + int err; + + mlxsw_reg_mcia_pack(mcia_pl, id, 0, MLXSW_REG_MCIA_PAGE0_LO_OFF, 0, 1, + MLXSW_REG_MCIA_I2C_ADDR_LOW); + err = mlxsw_reg_query(core, MLXSW_REG(mcia), mcia_pl); + if (err) + return err; + mlxsw_reg_mcia_eeprom_memcpy_from(mcia_pl, eeprom_tmp); + ident = eeprom_tmp[0]; + switch (ident) { + case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_SFP: + *qsfp = false; + break; + case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP: /* fall-through */ + case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_PLUS: /* fall-through */ + case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28: /* fall-through */ + case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_DD: + *qsfp = true; + break; + default: + return -EINVAL; + } + + return 0; +} + +int mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, int module, + int off, int *temp) +{ + char eeprom_tmp[MLXSW_REG_MCIA_EEPROM_SIZE]; + union { + u8 buf[MLXSW_REG_MCIA_TH_ITEM_SIZE]; + u16 temp; + } temp_thresh; + char mcia_pl[MLXSW_REG_MCIA_LEN] = {0}; + char mtbr_pl[MLXSW_REG_MTBR_LEN] = {0}; + u16 module_temp; + bool qsfp; + int err; + + mlxsw_reg_mtbr_pack(mtbr_pl, MLXSW_REG_MTBR_BASE_MODULE_INDEX + module, + 1); + err = mlxsw_reg_query(core, MLXSW_REG(mtbr), mtbr_pl); + if (err) + return err; + + /* Don't read temperature thresholds for module with no valid info. */ + mlxsw_reg_mtbr_temp_unpack(mtbr_pl, 0, &module_temp, NULL); + switch (module_temp) { + case MLXSW_REG_MTBR_BAD_SENS_INFO: /* fall-through */ + case MLXSW_REG_MTBR_NO_CONN: /* fall-through */ + case MLXSW_REG_MTBR_NO_TEMP_SENS: /* fall-through */ + case MLXSW_REG_MTBR_INDEX_NA: + *temp = 0; + return 0; + default: + /* Do not consider thresholds for zero temperature. */ + if (!MLXSW_REG_MTMP_TEMP_TO_MC(module_temp)) { + *temp = 0; + return 0; + } + break; + } + + /* Read Free Side Device Temperature Thresholds from page 03h + * (MSB at lower byte address). + * Bytes: + * 128-129 - Temp High Alarm (SFP_TEMP_HIGH_ALARM); + * 130-131 - Temp Low Alarm (SFP_TEMP_LOW_ALARM); + * 132-133 - Temp High Warning (SFP_TEMP_HIGH_WARN); + * 134-135 - Temp Low Warning (SFP_TEMP_LOW_WARN); + */ + + /* Validate module identifier value. */ + err = mlxsw_env_validate_cable_ident(core, module, &qsfp); + if (err) + return err; + + if (qsfp) + mlxsw_reg_mcia_pack(mcia_pl, module, 0, + MLXSW_REG_MCIA_TH_PAGE_NUM, + MLXSW_REG_MCIA_TH_PAGE_OFF + off, + MLXSW_REG_MCIA_TH_ITEM_SIZE, + MLXSW_REG_MCIA_I2C_ADDR_LOW); + else + mlxsw_reg_mcia_pack(mcia_pl, module, 0, + MLXSW_REG_MCIA_PAGE0_LO, + off, MLXSW_REG_MCIA_TH_ITEM_SIZE, + MLXSW_REG_MCIA_I2C_ADDR_HIGH); + + err = mlxsw_reg_query(core, MLXSW_REG(mcia), mcia_pl); + if (err) + return err; + + mlxsw_reg_mcia_eeprom_memcpy_from(mcia_pl, eeprom_tmp); + memcpy(temp_thresh.buf, eeprom_tmp, MLXSW_REG_MCIA_TH_ITEM_SIZE); + *temp = temp_thresh.temp * 1000; + + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.h b/drivers/net/ethernet/mellanox/mlxsw/core_env.h new file mode 100644 index 000000000000..6dbdf63f3ee1 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */ +/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */ + +#ifndef _MLXSW_CORE_ENV_H +#define _MLXSW_CORE_ENV_H + +int mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, int module, + int off, int *temp); + +#endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c index e04e8162aa14..6956bbebe2f1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c @@ -7,8 +7,10 @@ #include <linux/sysfs.h> #include <linux/hwmon.h> #include <linux/err.h> +#include <linux/sfp.h> #include "core.h" +#include "core_env.h" #define MLXSW_HWMON_TEMP_SENSOR_MAX_COUNT 127 #define MLXSW_HWMON_ATTR_COUNT (MLXSW_HWMON_TEMP_SENSOR_MAX_COUNT * 4 + \ @@ -30,6 +32,7 @@ struct mlxsw_hwmon { struct attribute *attrs[MLXSW_HWMON_ATTR_COUNT + 1]; struct mlxsw_hwmon_attr hwmon_attrs[MLXSW_HWMON_ATTR_COUNT]; unsigned int attrs_count; + u8 sensor_count; }; static ssize_t mlxsw_hwmon_temp_show(struct device *dev, @@ -121,6 +124,27 @@ static ssize_t mlxsw_hwmon_fan_rpm_show(struct device *dev, return sprintf(buf, "%u\n", mlxsw_reg_mfsm_rpm_get(mfsm_pl)); } +static ssize_t mlxsw_hwmon_fan_fault_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct mlxsw_hwmon_attr *mlwsw_hwmon_attr = + container_of(attr, struct mlxsw_hwmon_attr, dev_attr); + struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon; + char fore_pl[MLXSW_REG_FORE_LEN]; + bool fault; + int err; + + err = mlxsw_reg_query(mlxsw_hwmon->core, MLXSW_REG(fore), fore_pl); + if (err) { + dev_err(mlxsw_hwmon->bus_info->dev, "Failed to query fan\n"); + return err; + } + mlxsw_reg_fore_unpack(fore_pl, mlwsw_hwmon_attr->type_index, &fault); + + return sprintf(buf, "%u\n", fault); +} + static ssize_t mlxsw_hwmon_pwm_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -167,12 +191,160 @@ static ssize_t mlxsw_hwmon_pwm_store(struct device *dev, return len; } +static ssize_t mlxsw_hwmon_module_temp_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct mlxsw_hwmon_attr *mlwsw_hwmon_attr = + container_of(attr, struct mlxsw_hwmon_attr, dev_attr); + struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon; + char mtbr_pl[MLXSW_REG_MTBR_LEN] = {0}; + u16 temp; + u8 module; + int err; + + module = mlwsw_hwmon_attr->type_index - mlxsw_hwmon->sensor_count; + mlxsw_reg_mtbr_pack(mtbr_pl, MLXSW_REG_MTBR_BASE_MODULE_INDEX + module, + 1); + err = mlxsw_reg_query(mlxsw_hwmon->core, MLXSW_REG(mtbr), mtbr_pl); + if (err) { + dev_err(dev, "Failed to query module temperature sensor\n"); + return err; + } + + mlxsw_reg_mtbr_temp_unpack(mtbr_pl, 0, &temp, NULL); + /* Update status and temperature cache. */ + switch (temp) { + case MLXSW_REG_MTBR_NO_CONN: /* fall-through */ + case MLXSW_REG_MTBR_NO_TEMP_SENS: /* fall-through */ + case MLXSW_REG_MTBR_INDEX_NA: + temp = 0; + break; + case MLXSW_REG_MTBR_BAD_SENS_INFO: + /* Untrusted cable is connected. Reading temperature from its + * sensor is faulty. + */ + temp = 0; + break; + default: + temp = MLXSW_REG_MTMP_TEMP_TO_MC(temp); + break; + } + + return sprintf(buf, "%u\n", temp); +} + +static ssize_t mlxsw_hwmon_module_temp_fault_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct mlxsw_hwmon_attr *mlwsw_hwmon_attr = + container_of(attr, struct mlxsw_hwmon_attr, dev_attr); + struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon; + char mtbr_pl[MLXSW_REG_MTBR_LEN] = {0}; + u8 module, fault; + u16 temp; + int err; + + module = mlwsw_hwmon_attr->type_index - mlxsw_hwmon->sensor_count; + mlxsw_reg_mtbr_pack(mtbr_pl, MLXSW_REG_MTBR_BASE_MODULE_INDEX + module, + 1); + err = mlxsw_reg_query(mlxsw_hwmon->core, MLXSW_REG(mtbr), mtbr_pl); + if (err) { + dev_err(dev, "Failed to query module temperature sensor\n"); + return err; + } + + mlxsw_reg_mtbr_temp_unpack(mtbr_pl, 0, &temp, NULL); + + /* Update status and temperature cache. */ + switch (temp) { + case MLXSW_REG_MTBR_BAD_SENS_INFO: + /* Untrusted cable is connected. Reading temperature from its + * sensor is faulty. + */ + fault = 1; + break; + case MLXSW_REG_MTBR_NO_CONN: /* fall-through */ + case MLXSW_REG_MTBR_NO_TEMP_SENS: /* fall-through */ + case MLXSW_REG_MTBR_INDEX_NA: + default: + fault = 0; + break; + } + + return sprintf(buf, "%u\n", fault); +} + +static ssize_t +mlxsw_hwmon_module_temp_critical_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct mlxsw_hwmon_attr *mlwsw_hwmon_attr = + container_of(attr, struct mlxsw_hwmon_attr, dev_attr); + struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon; + int temp; + u8 module; + int err; + + module = mlwsw_hwmon_attr->type_index - mlxsw_hwmon->sensor_count; + err = mlxsw_env_module_temp_thresholds_get(mlxsw_hwmon->core, module, + SFP_TEMP_HIGH_WARN, &temp); + if (err) { + dev_err(dev, "Failed to query module temperature thresholds\n"); + return err; + } + + return sprintf(buf, "%u\n", temp); +} + +static ssize_t +mlxsw_hwmon_module_temp_emergency_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct mlxsw_hwmon_attr *mlwsw_hwmon_attr = + container_of(attr, struct mlxsw_hwmon_attr, dev_attr); + struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon; + u8 module; + int temp; + int err; + + module = mlwsw_hwmon_attr->type_index - mlxsw_hwmon->sensor_count; + err = mlxsw_env_module_temp_thresholds_get(mlxsw_hwmon->core, module, + SFP_TEMP_HIGH_ALARM, &temp); + if (err) { + dev_err(dev, "Failed to query module temperature thresholds\n"); + return err; + } + + return sprintf(buf, "%u\n", temp); +} + +static ssize_t +mlxsw_hwmon_module_temp_label_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct mlxsw_hwmon_attr *mlwsw_hwmon_attr = + container_of(attr, struct mlxsw_hwmon_attr, dev_attr); + + return sprintf(buf, "front panel %03u\n", + mlwsw_hwmon_attr->type_index); +} + enum mlxsw_hwmon_attr_type { MLXSW_HWMON_ATTR_TYPE_TEMP, MLXSW_HWMON_ATTR_TYPE_TEMP_MAX, MLXSW_HWMON_ATTR_TYPE_TEMP_RST, MLXSW_HWMON_ATTR_TYPE_FAN_RPM, + MLXSW_HWMON_ATTR_TYPE_FAN_FAULT, MLXSW_HWMON_ATTR_TYPE_PWM, + MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE, + MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_FAULT, + MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_CRIT, + MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_EMERG, + MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_LABEL, }; static void mlxsw_hwmon_attr_add(struct mlxsw_hwmon *mlxsw_hwmon, @@ -209,6 +381,12 @@ static void mlxsw_hwmon_attr_add(struct mlxsw_hwmon *mlxsw_hwmon, snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name), "fan%u_input", num + 1); break; + case MLXSW_HWMON_ATTR_TYPE_FAN_FAULT: + mlxsw_hwmon_attr->dev_attr.show = mlxsw_hwmon_fan_fault_show; + mlxsw_hwmon_attr->dev_attr.attr.mode = 0444; + snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name), + "fan%u_fault", num + 1); + break; case MLXSW_HWMON_ATTR_TYPE_PWM: mlxsw_hwmon_attr->dev_attr.show = mlxsw_hwmon_pwm_show; mlxsw_hwmon_attr->dev_attr.store = mlxsw_hwmon_pwm_store; @@ -216,6 +394,40 @@ static void mlxsw_hwmon_attr_add(struct mlxsw_hwmon *mlxsw_hwmon, snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name), "pwm%u", num + 1); break; + case MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE: + mlxsw_hwmon_attr->dev_attr.show = mlxsw_hwmon_module_temp_show; + mlxsw_hwmon_attr->dev_attr.attr.mode = 0444; + snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name), + "temp%u_input", num + 1); + break; + case MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_FAULT: + mlxsw_hwmon_attr->dev_attr.show = + mlxsw_hwmon_module_temp_fault_show; + mlxsw_hwmon_attr->dev_attr.attr.mode = 0444; + snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name), + "temp%u_fault", num + 1); + break; + case MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_CRIT: + mlxsw_hwmon_attr->dev_attr.show = + mlxsw_hwmon_module_temp_critical_show; + mlxsw_hwmon_attr->dev_attr.attr.mode = 0444; + snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name), + "temp%u_crit", num + 1); + break; + case MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_EMERG: + mlxsw_hwmon_attr->dev_attr.show = + mlxsw_hwmon_module_temp_emergency_show; + mlxsw_hwmon_attr->dev_attr.attr.mode = 0444; + snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name), + "temp%u_emergency", num + 1); + break; + case MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_LABEL: + mlxsw_hwmon_attr->dev_attr.show = + mlxsw_hwmon_module_temp_label_show; + mlxsw_hwmon_attr->dev_attr.attr.mode = 0444; + snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name), + "temp%u_label", num + 1); + break; default: WARN_ON(1); } @@ -233,7 +445,6 @@ static int mlxsw_hwmon_temp_init(struct mlxsw_hwmon *mlxsw_hwmon) { char mtcap_pl[MLXSW_REG_MTCAP_LEN] = {0}; char mtmp_pl[MLXSW_REG_MTMP_LEN]; - u8 sensor_count; int i; int err; @@ -242,8 +453,8 @@ static int mlxsw_hwmon_temp_init(struct mlxsw_hwmon *mlxsw_hwmon) dev_err(mlxsw_hwmon->bus_info->dev, "Failed to get number of temp sensors\n"); return err; } - sensor_count = mlxsw_reg_mtcap_sensor_count_get(mtcap_pl); - for (i = 0; i < sensor_count; i++) { + mlxsw_hwmon->sensor_count = mlxsw_reg_mtcap_sensor_count_get(mtcap_pl); + for (i = 0; i < mlxsw_hwmon->sensor_count; i++) { mlxsw_reg_mtmp_pack(mtmp_pl, i, true, true); err = mlxsw_reg_write(mlxsw_hwmon->core, MLXSW_REG(mtmp), mtmp_pl); @@ -280,10 +491,14 @@ static int mlxsw_hwmon_fans_init(struct mlxsw_hwmon *mlxsw_hwmon) mlxsw_reg_mfcr_unpack(mfcr_pl, &freq, &tacho_active, &pwm_active); num = 0; for (type_index = 0; type_index < MLXSW_MFCR_TACHOS_MAX; type_index++) { - if (tacho_active & BIT(type_index)) + if (tacho_active & BIT(type_index)) { mlxsw_hwmon_attr_add(mlxsw_hwmon, MLXSW_HWMON_ATTR_TYPE_FAN_RPM, + type_index, num); + mlxsw_hwmon_attr_add(mlxsw_hwmon, + MLXSW_HWMON_ATTR_TYPE_FAN_FAULT, type_index, num++); + } } num = 0; for (type_index = 0; type_index < MLXSW_MFCR_PWMS_MAX; type_index++) { @@ -295,6 +510,53 @@ static int mlxsw_hwmon_fans_init(struct mlxsw_hwmon *mlxsw_hwmon) return 0; } +static int mlxsw_hwmon_module_init(struct mlxsw_hwmon *mlxsw_hwmon) +{ + unsigned int module_count = mlxsw_core_max_ports(mlxsw_hwmon->core); + char pmlp_pl[MLXSW_REG_PMLP_LEN] = {0}; + int i, index; + u8 width; + int err; + + /* Add extra attributes for module temperature. Sensor index is + * assigned to sensor_count value, while all indexed before + * sensor_count are already utilized by the sensors connected through + * mtmp register by mlxsw_hwmon_temp_init(). + */ + index = mlxsw_hwmon->sensor_count; + for (i = 1; i < module_count; i++) { + mlxsw_reg_pmlp_pack(pmlp_pl, i); + err = mlxsw_reg_query(mlxsw_hwmon->core, MLXSW_REG(pmlp), + pmlp_pl); + if (err) { + dev_err(mlxsw_hwmon->bus_info->dev, "Failed to read module index %d\n", + i); + return err; + } + width = mlxsw_reg_pmlp_width_get(pmlp_pl); + if (!width) + continue; + mlxsw_hwmon_attr_add(mlxsw_hwmon, + MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE, index, + index); + mlxsw_hwmon_attr_add(mlxsw_hwmon, + MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_FAULT, + index, index); + mlxsw_hwmon_attr_add(mlxsw_hwmon, + MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_CRIT, + index, index); + mlxsw_hwmon_attr_add(mlxsw_hwmon, + MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_EMERG, + index, index); + mlxsw_hwmon_attr_add(mlxsw_hwmon, + MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_LABEL, + index, index); + index++; + } + + return 0; +} + int mlxsw_hwmon_init(struct mlxsw_core *mlxsw_core, const struct mlxsw_bus_info *mlxsw_bus_info, struct mlxsw_hwmon **p_hwmon) @@ -317,6 +579,10 @@ int mlxsw_hwmon_init(struct mlxsw_core *mlxsw_core, if (err) goto err_fans_init; + err = mlxsw_hwmon_module_init(mlxsw_hwmon); + if (err) + goto err_temp_module_init; + mlxsw_hwmon->groups[0] = &mlxsw_hwmon->group; mlxsw_hwmon->group.attrs = mlxsw_hwmon->attrs; @@ -333,6 +599,7 @@ int mlxsw_hwmon_init(struct mlxsw_core *mlxsw_core, return 0; err_hwmon_register: +err_temp_module_init: err_fans_init: err_temp_init: kfree(mlxsw_hwmon); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c index 61f897b40f82..0b85c7252f9e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c @@ -9,11 +9,20 @@ #include <linux/sysfs.h> #include <linux/thermal.h> #include <linux/err.h> +#include <linux/sfp.h> #include "core.h" +#include "core_env.h" #define MLXSW_THERMAL_POLL_INT 1000 /* ms */ -#define MLXSW_THERMAL_MAX_TEMP 110000 /* 110C */ +#define MLXSW_THERMAL_SLOW_POLL_INT 20000 /* ms */ +#define MLXSW_THERMAL_ASIC_TEMP_NORM 75000 /* 75C */ +#define MLXSW_THERMAL_ASIC_TEMP_HIGH 85000 /* 85C */ +#define MLXSW_THERMAL_ASIC_TEMP_HOT 105000 /* 105C */ +#define MLXSW_THERMAL_ASIC_TEMP_CRIT 110000 /* 110C */ +#define MLXSW_THERMAL_HYSTERESIS_TEMP 5000 /* 5C */ +#define MLXSW_THERMAL_MODULE_TEMP_SHIFT (MLXSW_THERMAL_HYSTERESIS_TEMP * 2) +#define MLXSW_THERMAL_ZONE_MAX_NAME 16 #define MLXSW_THERMAL_MAX_STATE 10 #define MLXSW_THERMAL_MAX_DUTY 255 /* Minimum and maximum fan allowed speed in percent: from 20% to 100%. Values @@ -26,9 +35,22 @@ #define MLXSW_THERMAL_SPEED_MAX (MLXSW_THERMAL_MAX_STATE * 2) #define MLXSW_THERMAL_SPEED_MIN_LEVEL 2 /* 20% */ +/* External cooling devices, allowed for binding to mlxsw thermal zones. */ +static char * const mlxsw_thermal_external_allowed_cdev[] = { + "mlxreg_fan", +}; + +enum mlxsw_thermal_trips { + MLXSW_THERMAL_TEMP_TRIP_NORM, + MLXSW_THERMAL_TEMP_TRIP_HIGH, + MLXSW_THERMAL_TEMP_TRIP_HOT, + MLXSW_THERMAL_TEMP_TRIP_CRIT, +}; + struct mlxsw_thermal_trip { int type; int temp; + int hyst; int min_state; int max_state; }; @@ -36,32 +58,29 @@ struct mlxsw_thermal_trip { static const struct mlxsw_thermal_trip default_thermal_trips[] = { { /* In range - 0-40% PWM */ .type = THERMAL_TRIP_ACTIVE, - .temp = 75000, + .temp = MLXSW_THERMAL_ASIC_TEMP_NORM, + .hyst = MLXSW_THERMAL_HYSTERESIS_TEMP, .min_state = 0, .max_state = (4 * MLXSW_THERMAL_MAX_STATE) / 10, }, - { /* High - 40-100% PWM */ - .type = THERMAL_TRIP_ACTIVE, - .temp = 80000, - .min_state = (4 * MLXSW_THERMAL_MAX_STATE) / 10, - .max_state = MLXSW_THERMAL_MAX_STATE, - }, { - /* Very high - 100% PWM */ + /* In range - 40-100% PWM */ .type = THERMAL_TRIP_ACTIVE, - .temp = 85000, - .min_state = MLXSW_THERMAL_MAX_STATE, + .temp = MLXSW_THERMAL_ASIC_TEMP_HIGH, + .hyst = MLXSW_THERMAL_HYSTERESIS_TEMP, + .min_state = (4 * MLXSW_THERMAL_MAX_STATE) / 10, .max_state = MLXSW_THERMAL_MAX_STATE, }, { /* Warning */ .type = THERMAL_TRIP_HOT, - .temp = 105000, + .temp = MLXSW_THERMAL_ASIC_TEMP_HOT, + .hyst = MLXSW_THERMAL_HYSTERESIS_TEMP, .min_state = MLXSW_THERMAL_MAX_STATE, .max_state = MLXSW_THERMAL_MAX_STATE, }, { /* Critical - soft poweroff */ .type = THERMAL_TRIP_CRITICAL, - .temp = MLXSW_THERMAL_MAX_TEMP, + .temp = MLXSW_THERMAL_ASIC_TEMP_CRIT, .min_state = MLXSW_THERMAL_MAX_STATE, .max_state = MLXSW_THERMAL_MAX_STATE, } @@ -72,14 +91,27 @@ static const struct mlxsw_thermal_trip default_thermal_trips[] = { /* Make sure all trips are writable */ #define MLXSW_THERMAL_TRIP_MASK (BIT(MLXSW_THERMAL_NUM_TRIPS) - 1) +struct mlxsw_thermal; + +struct mlxsw_thermal_module { + struct mlxsw_thermal *parent; + struct thermal_zone_device *tzdev; + struct mlxsw_thermal_trip trips[MLXSW_THERMAL_NUM_TRIPS]; + enum thermal_device_mode mode; + int module; +}; + struct mlxsw_thermal { struct mlxsw_core *core; const struct mlxsw_bus_info *bus_info; struct thermal_zone_device *tzdev; + int polling_delay; struct thermal_cooling_device *cdevs[MLXSW_MFCR_PWMS_MAX]; u8 cooling_levels[MLXSW_THERMAL_MAX_STATE + 1]; struct mlxsw_thermal_trip trips[MLXSW_THERMAL_NUM_TRIPS]; enum thermal_device_mode mode; + struct mlxsw_thermal_module *tz_module_arr; + unsigned int tz_module_num; }; static inline u8 mlxsw_state_to_duty(int state) @@ -103,9 +135,67 @@ static int mlxsw_get_cooling_device_idx(struct mlxsw_thermal *thermal, if (thermal->cdevs[i] == cdev) return i; + /* Allow mlxsw thermal zone binding to an external cooling device */ + for (i = 0; i < ARRAY_SIZE(mlxsw_thermal_external_allowed_cdev); i++) { + if (strnstr(cdev->type, mlxsw_thermal_external_allowed_cdev[i], + sizeof(cdev->type))) + return 0; + } + return -ENODEV; } +static void +mlxsw_thermal_module_trips_reset(struct mlxsw_thermal_module *tz) +{ + tz->trips[MLXSW_THERMAL_TEMP_TRIP_NORM].temp = 0; + tz->trips[MLXSW_THERMAL_TEMP_TRIP_HIGH].temp = 0; + tz->trips[MLXSW_THERMAL_TEMP_TRIP_HOT].temp = 0; + tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = 0; +} + +static int +mlxsw_thermal_module_trips_update(struct device *dev, struct mlxsw_core *core, + struct mlxsw_thermal_module *tz) +{ + int crit_temp, emerg_temp; + int err; + + err = mlxsw_env_module_temp_thresholds_get(core, tz->module, + SFP_TEMP_HIGH_WARN, + &crit_temp); + if (err) + return err; + + err = mlxsw_env_module_temp_thresholds_get(core, tz->module, + SFP_TEMP_HIGH_ALARM, + &emerg_temp); + if (err) + return err; + + /* According to the system thermal requirements, the thermal zones are + * defined with four trip points. The critical and emergency + * temperature thresholds, provided by QSFP module are set as "active" + * and "hot" trip points, "normal" and "critical" trip points are + * derived from "active" and "hot" by subtracting or adding double + * hysteresis value. + */ + if (crit_temp >= MLXSW_THERMAL_MODULE_TEMP_SHIFT) + tz->trips[MLXSW_THERMAL_TEMP_TRIP_NORM].temp = crit_temp - + MLXSW_THERMAL_MODULE_TEMP_SHIFT; + else + tz->trips[MLXSW_THERMAL_TEMP_TRIP_NORM].temp = crit_temp; + tz->trips[MLXSW_THERMAL_TEMP_TRIP_HIGH].temp = crit_temp; + tz->trips[MLXSW_THERMAL_TEMP_TRIP_HOT].temp = emerg_temp; + if (emerg_temp > crit_temp) + tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = emerg_temp + + MLXSW_THERMAL_MODULE_TEMP_SHIFT; + else + tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = emerg_temp; + + return 0; +} + static int mlxsw_thermal_bind(struct thermal_zone_device *tzdev, struct thermal_cooling_device *cdev) { @@ -172,7 +262,7 @@ static int mlxsw_thermal_set_mode(struct thermal_zone_device *tzdev, mutex_lock(&tzdev->lock); if (mode == THERMAL_DEVICE_ENABLED) - tzdev->polling_delay = MLXSW_THERMAL_POLL_INT; + tzdev->polling_delay = thermal->polling_delay; else tzdev->polling_delay = 0; @@ -237,13 +327,31 @@ static int mlxsw_thermal_set_trip_temp(struct thermal_zone_device *tzdev, struct mlxsw_thermal *thermal = tzdev->devdata; if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS || - temp > MLXSW_THERMAL_MAX_TEMP) + temp > MLXSW_THERMAL_ASIC_TEMP_CRIT) return -EINVAL; thermal->trips[trip].temp = temp; return 0; } +static int mlxsw_thermal_get_trip_hyst(struct thermal_zone_device *tzdev, + int trip, int *p_hyst) +{ + struct mlxsw_thermal *thermal = tzdev->devdata; + + *p_hyst = thermal->trips[trip].hyst; + return 0; +} + +static int mlxsw_thermal_set_trip_hyst(struct thermal_zone_device *tzdev, + int trip, int hyst) +{ + struct mlxsw_thermal *thermal = tzdev->devdata; + + thermal->trips[trip].hyst = hyst; + return 0; +} + static struct thermal_zone_device_ops mlxsw_thermal_ops = { .bind = mlxsw_thermal_bind, .unbind = mlxsw_thermal_unbind, @@ -253,6 +361,206 @@ static struct thermal_zone_device_ops mlxsw_thermal_ops = { .get_trip_type = mlxsw_thermal_get_trip_type, .get_trip_temp = mlxsw_thermal_get_trip_temp, .set_trip_temp = mlxsw_thermal_set_trip_temp, + .get_trip_hyst = mlxsw_thermal_get_trip_hyst, + .set_trip_hyst = mlxsw_thermal_set_trip_hyst, +}; + +static int mlxsw_thermal_module_bind(struct thermal_zone_device *tzdev, + struct thermal_cooling_device *cdev) +{ + struct mlxsw_thermal_module *tz = tzdev->devdata; + struct mlxsw_thermal *thermal = tz->parent; + int i, j, err; + + /* If the cooling device is one of ours bind it */ + if (mlxsw_get_cooling_device_idx(thermal, cdev) < 0) + return 0; + + for (i = 0; i < MLXSW_THERMAL_NUM_TRIPS; i++) { + const struct mlxsw_thermal_trip *trip = &tz->trips[i]; + + err = thermal_zone_bind_cooling_device(tzdev, i, cdev, + trip->max_state, + trip->min_state, + THERMAL_WEIGHT_DEFAULT); + if (err < 0) + goto err_bind_cooling_device; + } + return 0; + +err_bind_cooling_device: + for (j = i - 1; j >= 0; j--) + thermal_zone_unbind_cooling_device(tzdev, j, cdev); + return err; +} + +static int mlxsw_thermal_module_unbind(struct thermal_zone_device *tzdev, + struct thermal_cooling_device *cdev) +{ + struct mlxsw_thermal_module *tz = tzdev->devdata; + struct mlxsw_thermal *thermal = tz->parent; + int i; + int err; + + /* If the cooling device is one of ours unbind it */ + if (mlxsw_get_cooling_device_idx(thermal, cdev) < 0) + return 0; + + for (i = 0; i < MLXSW_THERMAL_NUM_TRIPS; i++) { + err = thermal_zone_unbind_cooling_device(tzdev, i, cdev); + WARN_ON(err); + } + return err; +} + +static int mlxsw_thermal_module_mode_get(struct thermal_zone_device *tzdev, + enum thermal_device_mode *mode) +{ + struct mlxsw_thermal_module *tz = tzdev->devdata; + + *mode = tz->mode; + + return 0; +} + +static int mlxsw_thermal_module_mode_set(struct thermal_zone_device *tzdev, + enum thermal_device_mode mode) +{ + struct mlxsw_thermal_module *tz = tzdev->devdata; + struct mlxsw_thermal *thermal = tz->parent; + + mutex_lock(&tzdev->lock); + + if (mode == THERMAL_DEVICE_ENABLED) + tzdev->polling_delay = thermal->polling_delay; + else + tzdev->polling_delay = 0; + + mutex_unlock(&tzdev->lock); + + tz->mode = mode; + thermal_zone_device_update(tzdev, THERMAL_EVENT_UNSPECIFIED); + + return 0; +} + +static int mlxsw_thermal_module_temp_get(struct thermal_zone_device *tzdev, + int *p_temp) +{ + struct mlxsw_thermal_module *tz = tzdev->devdata; + struct mlxsw_thermal *thermal = tz->parent; + struct device *dev = thermal->bus_info->dev; + char mtbr_pl[MLXSW_REG_MTBR_LEN]; + u16 temp; + int err; + + /* Read module temperature. */ + mlxsw_reg_mtbr_pack(mtbr_pl, MLXSW_REG_MTBR_BASE_MODULE_INDEX + + tz->module, 1); + err = mlxsw_reg_query(thermal->core, MLXSW_REG(mtbr), mtbr_pl); + if (err) + return err; + + mlxsw_reg_mtbr_temp_unpack(mtbr_pl, 0, &temp, NULL); + /* Update temperature. */ + switch (temp) { + case MLXSW_REG_MTBR_NO_CONN: /* fall-through */ + case MLXSW_REG_MTBR_NO_TEMP_SENS: /* fall-through */ + case MLXSW_REG_MTBR_INDEX_NA: /* fall-through */ + case MLXSW_REG_MTBR_BAD_SENS_INFO: + temp = 0; + break; + default: + temp = MLXSW_REG_MTMP_TEMP_TO_MC(temp); + /* Reset all trip point. */ + mlxsw_thermal_module_trips_reset(tz); + /* Update trip points. */ + err = mlxsw_thermal_module_trips_update(dev, thermal->core, + tz); + if (err) + return err; + break; + } + + *p_temp = (int) temp; + return 0; +} + +static int +mlxsw_thermal_module_trip_type_get(struct thermal_zone_device *tzdev, int trip, + enum thermal_trip_type *p_type) +{ + struct mlxsw_thermal_module *tz = tzdev->devdata; + + if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS) + return -EINVAL; + + *p_type = tz->trips[trip].type; + return 0; +} + +static int +mlxsw_thermal_module_trip_temp_get(struct thermal_zone_device *tzdev, + int trip, int *p_temp) +{ + struct mlxsw_thermal_module *tz = tzdev->devdata; + + if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS) + return -EINVAL; + + *p_temp = tz->trips[trip].temp; + return 0; +} + +static int +mlxsw_thermal_module_trip_temp_set(struct thermal_zone_device *tzdev, + int trip, int temp) +{ + struct mlxsw_thermal_module *tz = tzdev->devdata; + + if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS || + temp > tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp) + return -EINVAL; + + tz->trips[trip].temp = temp; + return 0; +} + +static int +mlxsw_thermal_module_trip_hyst_get(struct thermal_zone_device *tzdev, int trip, + int *p_hyst) +{ + struct mlxsw_thermal_module *tz = tzdev->devdata; + + *p_hyst = tz->trips[trip].hyst; + return 0; +} + +static int +mlxsw_thermal_module_trip_hyst_set(struct thermal_zone_device *tzdev, int trip, + int hyst) +{ + struct mlxsw_thermal_module *tz = tzdev->devdata; + + tz->trips[trip].hyst = hyst; + return 0; +} + +static struct thermal_zone_params mlxsw_thermal_module_params = { + .governor_name = "user_space", +}; + +static struct thermal_zone_device_ops mlxsw_thermal_module_ops = { + .bind = mlxsw_thermal_module_bind, + .unbind = mlxsw_thermal_module_unbind, + .get_mode = mlxsw_thermal_module_mode_get, + .set_mode = mlxsw_thermal_module_mode_set, + .get_temp = mlxsw_thermal_module_temp_get, + .get_trip_type = mlxsw_thermal_module_trip_type_get, + .get_trip_temp = mlxsw_thermal_module_trip_temp_get, + .set_trip_temp = mlxsw_thermal_module_trip_temp_set, + .get_trip_hyst = mlxsw_thermal_module_trip_hyst_get, + .set_trip_hyst = mlxsw_thermal_module_trip_hyst_set, }; static int mlxsw_thermal_get_max_state(struct thermal_cooling_device *cdev, @@ -355,6 +663,123 @@ static const struct thermal_cooling_device_ops mlxsw_cooling_ops = { .set_cur_state = mlxsw_thermal_set_cur_state, }; +static int +mlxsw_thermal_module_tz_init(struct mlxsw_thermal_module *module_tz) +{ + char tz_name[MLXSW_THERMAL_ZONE_MAX_NAME]; + int err; + + snprintf(tz_name, sizeof(tz_name), "mlxsw-module%d", + module_tz->module + 1); + module_tz->tzdev = thermal_zone_device_register(tz_name, + MLXSW_THERMAL_NUM_TRIPS, + MLXSW_THERMAL_TRIP_MASK, + module_tz, + &mlxsw_thermal_module_ops, + &mlxsw_thermal_module_params, + 0, 0); + if (IS_ERR(module_tz->tzdev)) { + err = PTR_ERR(module_tz->tzdev); + return err; + } + + return 0; +} + +static void mlxsw_thermal_module_tz_fini(struct thermal_zone_device *tzdev) +{ + thermal_zone_device_unregister(tzdev); +} + +static int +mlxsw_thermal_module_init(struct device *dev, struct mlxsw_core *core, + struct mlxsw_thermal *thermal, u8 local_port) +{ + struct mlxsw_thermal_module *module_tz; + char pmlp_pl[MLXSW_REG_PMLP_LEN]; + u8 width, module; + int err; + + mlxsw_reg_pmlp_pack(pmlp_pl, local_port); + err = mlxsw_reg_query(core, MLXSW_REG(pmlp), pmlp_pl); + if (err) + return err; + + width = mlxsw_reg_pmlp_width_get(pmlp_pl); + if (!width) + return 0; + + module = mlxsw_reg_pmlp_module_get(pmlp_pl, 0); + module_tz = &thermal->tz_module_arr[module]; + module_tz->module = module; + module_tz->parent = thermal; + memcpy(module_tz->trips, default_thermal_trips, + sizeof(thermal->trips)); + /* Initialize all trip point. */ + mlxsw_thermal_module_trips_reset(module_tz); + /* Update trip point according to the module data. */ + err = mlxsw_thermal_module_trips_update(dev, core, module_tz); + if (err) + return err; + + thermal->tz_module_num++; + + return 0; +} + +static void mlxsw_thermal_module_fini(struct mlxsw_thermal_module *module_tz) +{ + if (module_tz && module_tz->tzdev) { + mlxsw_thermal_module_tz_fini(module_tz->tzdev); + module_tz->tzdev = NULL; + } +} + +static int +mlxsw_thermal_modules_init(struct device *dev, struct mlxsw_core *core, + struct mlxsw_thermal *thermal) +{ + unsigned int module_count = mlxsw_core_max_ports(core); + int i, err; + + thermal->tz_module_arr = kcalloc(module_count, + sizeof(*thermal->tz_module_arr), + GFP_KERNEL); + if (!thermal->tz_module_arr) + return -ENOMEM; + + for (i = 1; i < module_count; i++) { + err = mlxsw_thermal_module_init(dev, core, thermal, i); + if (err) + goto err_unreg_tz_module_arr; + } + + for (i = 0; i < thermal->tz_module_num; i++) { + err = mlxsw_thermal_module_tz_init(&thermal->tz_module_arr[i]); + if (err) + goto err_unreg_tz_module_arr; + } + + return 0; + +err_unreg_tz_module_arr: + for (i = module_count - 1; i >= 0; i--) + mlxsw_thermal_module_fini(&thermal->tz_module_arr[i]); + kfree(thermal->tz_module_arr); + return err; +} + +static void +mlxsw_thermal_modules_fini(struct mlxsw_thermal *thermal) +{ + unsigned int module_count = mlxsw_core_max_ports(thermal->core); + int i; + + for (i = module_count - 1; i >= 0; i--) + mlxsw_thermal_module_fini(&thermal->tz_module_arr[i]); + kfree(thermal->tz_module_arr); +} + int mlxsw_thermal_init(struct mlxsw_core *core, const struct mlxsw_bus_info *bus_info, struct mlxsw_thermal **p_thermal) @@ -407,8 +832,9 @@ int mlxsw_thermal_init(struct mlxsw_core *core, if (pwm_active & BIT(i)) { struct thermal_cooling_device *cdev; - cdev = thermal_cooling_device_register("Fan", thermal, - &mlxsw_cooling_ops); + cdev = thermal_cooling_device_register("mlxsw_fan", + thermal, + &mlxsw_cooling_ops); if (IS_ERR(cdev)) { err = PTR_ERR(cdev); dev_err(dev, "Failed to register cooling device\n"); @@ -423,22 +849,36 @@ int mlxsw_thermal_init(struct mlxsw_core *core, thermal->cooling_levels[i] = max(MLXSW_THERMAL_SPEED_MIN_LEVEL, i); + thermal->polling_delay = bus_info->low_frequency ? + MLXSW_THERMAL_SLOW_POLL_INT : + MLXSW_THERMAL_POLL_INT; + thermal->tzdev = thermal_zone_device_register("mlxsw", MLXSW_THERMAL_NUM_TRIPS, MLXSW_THERMAL_TRIP_MASK, thermal, &mlxsw_thermal_ops, NULL, 0, - MLXSW_THERMAL_POLL_INT); + thermal->polling_delay); if (IS_ERR(thermal->tzdev)) { err = PTR_ERR(thermal->tzdev); dev_err(dev, "Failed to register thermal zone\n"); goto err_unreg_cdevs; } + err = mlxsw_thermal_modules_init(dev, core, thermal); + if (err) + goto err_unreg_tzdev; + thermal->mode = THERMAL_DEVICE_ENABLED; *p_thermal = thermal; return 0; + +err_unreg_tzdev: + if (thermal->tzdev) { + thermal_zone_device_unregister(thermal->tzdev); + thermal->tzdev = NULL; + } err_unreg_cdevs: for (i = 0; i < MLXSW_MFCR_PWMS_MAX; i++) if (thermal->cdevs[i]) @@ -452,6 +892,7 @@ void mlxsw_thermal_fini(struct mlxsw_thermal *thermal) { int i; + mlxsw_thermal_modules_fini(thermal); if (thermal->tzdev) { thermal_zone_device_unregister(thermal->tzdev); thermal->tzdev = NULL; diff --git a/drivers/net/ethernet/mellanox/mlxsw/i2c.c b/drivers/net/ethernet/mellanox/mlxsw/i2c.c index 798bd5aca384..a87ca6b6580d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/i2c.c +++ b/drivers/net/ethernet/mellanox/mlxsw/i2c.c @@ -503,6 +503,7 @@ static int mlxsw_i2c_probe(struct i2c_client *client, mlxsw_i2c->bus_info.device_kind = id->name; mlxsw_i2c->bus_info.device_name = client->name; mlxsw_i2c->bus_info.dev = &client->dev; + mlxsw_i2c->bus_info.low_frequency = true; mlxsw_i2c->dev = &client->dev; err = mlxsw_core_bus_device_register(&mlxsw_i2c->bus_info, diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 5f8066ab7d40..cbd0193ec3f6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -2199,6 +2199,14 @@ MLXSW_ITEM32(reg, pagt, size, 0x00, 0, 8); */ MLXSW_ITEM32(reg, pagt, acl_group_id, 0x08, 0, 16); +/* reg_pagt_multi + * Multi-ACL + * 0 - This ACL is the last ACL in the multi-ACL + * 1 - This ACL is part of a multi-ACL + * Access: RW + */ +MLXSW_ITEM32_INDEXED(reg, pagt, multi, 0x30, 31, 1, 0x04, 0x00, false); + /* reg_pagt_acl_id * ACL identifier * Access: RW @@ -2212,12 +2220,13 @@ static inline void mlxsw_reg_pagt_pack(char *payload, u16 acl_group_id) } static inline void mlxsw_reg_pagt_acl_id_pack(char *payload, int index, - u16 acl_id) + u16 acl_id, bool multi) { u8 size = mlxsw_reg_pagt_size_get(payload); if (index >= size) mlxsw_reg_pagt_size_set(payload, index + 1); + mlxsw_reg_pagt_multi_set(payload, index, multi); mlxsw_reg_pagt_acl_id_set(payload, index, acl_id); } @@ -7866,6 +7875,35 @@ static inline void mlxsw_reg_mfsl_unpack(char *payload, u8 tacho, *p_tach_max = mlxsw_reg_mfsl_tach_max_get(payload); } +/* FORE - Fan Out of Range Event Register + * -------------------------------------- + * This register reports the status of the controlled fans compared to the + * range defined by the MFSL register. + */ +#define MLXSW_REG_FORE_ID 0x9007 +#define MLXSW_REG_FORE_LEN 0x0C + +MLXSW_REG_DEFINE(fore, MLXSW_REG_FORE_ID, MLXSW_REG_FORE_LEN); + +/* fan_under_limit + * Fan speed is below the low limit defined in MFSL register. Each bit relates + * to a single tachometer and indicates the specific tachometer reading is + * below the threshold. + * Access: RO + */ +MLXSW_ITEM32(reg, fore, fan_under_limit, 0x00, 16, 10); + +static inline void mlxsw_reg_fore_unpack(char *payload, u8 tacho, + bool *fault) +{ + u16 limit; + + if (fault) { + limit = mlxsw_reg_fore_fan_under_limit_get(payload); + *fault = limit & BIT(tacho); + } +} + /* MTCAP - Management Temperature Capabilities * ------------------------------------------- * This register exposes the capabilities of the device and @@ -7992,6 +8030,80 @@ static inline void mlxsw_reg_mtmp_unpack(char *payload, unsigned int *p_temp, mlxsw_reg_mtmp_sensor_name_memcpy_from(payload, sensor_name); } +/* MTBR - Management Temperature Bulk Register + * ------------------------------------------- + * This register is used for bulk temperature reading. + */ +#define MLXSW_REG_MTBR_ID 0x900F +#define MLXSW_REG_MTBR_BASE_LEN 0x10 /* base length, without records */ +#define MLXSW_REG_MTBR_REC_LEN 0x04 /* record length */ +#define MLXSW_REG_MTBR_REC_MAX_COUNT 47 /* firmware limitation */ +#define MLXSW_REG_MTBR_LEN (MLXSW_REG_MTBR_BASE_LEN + \ + MLXSW_REG_MTBR_REC_LEN * \ + MLXSW_REG_MTBR_REC_MAX_COUNT) + +MLXSW_REG_DEFINE(mtbr, MLXSW_REG_MTBR_ID, MLXSW_REG_MTBR_LEN); + +/* reg_mtbr_base_sensor_index + * Base sensors index to access (0 - ASIC sensor, 1-63 - ambient sensors, + * 64-127 are mapped to the SFP+/QSFP modules sequentially). + * Access: Index + */ +MLXSW_ITEM32(reg, mtbr, base_sensor_index, 0x00, 0, 7); + +/* reg_mtbr_num_rec + * Request: Number of records to read + * Response: Number of records read + * See above description for more details. + * Range 1..255 + * Access: RW + */ +MLXSW_ITEM32(reg, mtbr, num_rec, 0x04, 0, 8); + +/* reg_mtbr_rec_max_temp + * The highest measured temperature from the sensor. + * When the bit mte is cleared, the field max_temperature is reserved. + * Access: RO + */ +MLXSW_ITEM32_INDEXED(reg, mtbr, rec_max_temp, MLXSW_REG_MTBR_BASE_LEN, 16, + 16, MLXSW_REG_MTBR_REC_LEN, 0x00, false); + +/* reg_mtbr_rec_temp + * Temperature reading from the sensor. Reading is in 0..125 Celsius + * degrees units. + * Access: RO + */ +MLXSW_ITEM32_INDEXED(reg, mtbr, rec_temp, MLXSW_REG_MTBR_BASE_LEN, 0, 16, + MLXSW_REG_MTBR_REC_LEN, 0x00, false); + +static inline void mlxsw_reg_mtbr_pack(char *payload, u8 base_sensor_index, + u8 num_rec) +{ + MLXSW_REG_ZERO(mtbr, payload); + mlxsw_reg_mtbr_base_sensor_index_set(payload, base_sensor_index); + mlxsw_reg_mtbr_num_rec_set(payload, num_rec); +} + +/* Error codes from temperatute reading */ +enum mlxsw_reg_mtbr_temp_status { + MLXSW_REG_MTBR_NO_CONN = 0x8000, + MLXSW_REG_MTBR_NO_TEMP_SENS = 0x8001, + MLXSW_REG_MTBR_INDEX_NA = 0x8002, + MLXSW_REG_MTBR_BAD_SENS_INFO = 0x8003, +}; + +/* Base index for reading modules temperature */ +#define MLXSW_REG_MTBR_BASE_MODULE_INDEX 64 + +static inline void mlxsw_reg_mtbr_temp_unpack(char *payload, int rec_ind, + u16 *p_temp, u16 *p_max_temp) +{ + if (p_temp) + *p_temp = mlxsw_reg_mtbr_rec_temp_get(payload, rec_ind); + if (p_max_temp) + *p_max_temp = mlxsw_reg_mtbr_rec_max_temp_get(payload, rec_ind); +} + /* MCIA - Management Cable Info Access * ----------------------------------- * MCIA register is used to access the SFP+ and QSFP connector's EPROM. @@ -8046,13 +8158,41 @@ MLXSW_ITEM32(reg, mcia, device_address, 0x04, 0, 16); */ MLXSW_ITEM32(reg, mcia, size, 0x08, 0, 16); -#define MLXSW_SP_REG_MCIA_EEPROM_SIZE 48 +#define MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH 256 +#define MLXSW_REG_MCIA_EEPROM_SIZE 48 +#define MLXSW_REG_MCIA_I2C_ADDR_LOW 0x50 +#define MLXSW_REG_MCIA_I2C_ADDR_HIGH 0x51 +#define MLXSW_REG_MCIA_PAGE0_LO_OFF 0xa0 +#define MLXSW_REG_MCIA_TH_ITEM_SIZE 2 +#define MLXSW_REG_MCIA_TH_PAGE_NUM 3 +#define MLXSW_REG_MCIA_PAGE0_LO 0 +#define MLXSW_REG_MCIA_TH_PAGE_OFF 0x80 + +enum mlxsw_reg_mcia_eeprom_module_info_rev_id { + MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID_UNSPC = 0x00, + MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID_8436 = 0x01, + MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID_8636 = 0x03, +}; + +enum mlxsw_reg_mcia_eeprom_module_info_id { + MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_SFP = 0x03, + MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP = 0x0C, + MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_PLUS = 0x0D, + MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28 = 0x11, + MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_DD = 0x18, +}; + +enum mlxsw_reg_mcia_eeprom_module_info { + MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID, + MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID, + MLXSW_REG_MCIA_EEPROM_MODULE_INFO_SIZE, +}; /* reg_mcia_eeprom * Bytes to read/write. * Access: RW */ -MLXSW_ITEM_BUF(reg, mcia, eeprom, 0x10, MLXSW_SP_REG_MCIA_EEPROM_SIZE); +MLXSW_ITEM_BUF(reg, mcia, eeprom, 0x10, MLXSW_REG_MCIA_EEPROM_SIZE); static inline void mlxsw_reg_mcia_pack(char *payload, u8 module, u8 lock, u8 page_number, u16 device_addr, @@ -9740,8 +9880,10 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = { MLXSW_REG(mfsc), MLXSW_REG(mfsm), MLXSW_REG(mfsl), + MLXSW_REG(fore), MLXSW_REG(mtcap), MLXSW_REG(mtmp), + MLXSW_REG(mtbr), MLXSW_REG(mcia), MLXSW_REG(mpat), MLXSW_REG(mpar), diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h index b8b3a01c2a9e..773ef7fdb285 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/resources.h +++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h @@ -26,6 +26,7 @@ enum mlxsw_res_id { MLXSW_RES_ID_MAX_LAG_MEMBERS, MLXSW_RES_ID_MAX_BUFFER_SIZE, MLXSW_RES_ID_CELL_SIZE, + MLXSW_RES_ID_MAX_HEADROOM_SIZE, MLXSW_RES_ID_ACL_MAX_TCAM_REGIONS, MLXSW_RES_ID_ACL_MAX_TCAM_RULES, MLXSW_RES_ID_ACL_MAX_REGIONS, @@ -79,6 +80,7 @@ static u16 mlxsw_res_ids[] = { [MLXSW_RES_ID_MAX_LAG_MEMBERS] = 0x2521, [MLXSW_RES_ID_MAX_BUFFER_SIZE] = 0x2802, /* Bytes */ [MLXSW_RES_ID_CELL_SIZE] = 0x2803, /* Bytes */ + [MLXSW_RES_ID_MAX_HEADROOM_SIZE] = 0x2811, /* Bytes */ [MLXSW_RES_ID_ACL_MAX_TCAM_REGIONS] = 0x2901, [MLXSW_RES_ID_ACL_MAX_TCAM_RULES] = 0x2902, [MLXSW_RES_ID_ACL_MAX_REGIONS] = 0x2903, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 8dd808b7f931..f018b0607dac 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -852,8 +852,12 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu, u8 pfc_en = !!my_pfc ? my_pfc->pfc_en : 0; u16 delay = !!my_pfc ? my_pfc->delay : 0; char pbmc_pl[MLXSW_REG_PBMC_LEN]; + u32 taken_headroom_cells = 0; + u32 max_headroom_cells; int i, j, err; + max_headroom_cells = mlxsw_sp_sb_max_headroom_cells(mlxsw_sp); + mlxsw_reg_pbmc_pack(pbmc_pl, mlxsw_sp_port->local_port, 0, 0); err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(pbmc), pbmc_pl); if (err) @@ -862,8 +866,10 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu, for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { bool configure = false; bool pfc = false; + u16 thres_cells; + u16 delay_cells; + u16 total_cells; bool lossy; - u16 thres; for (j = 0; j < IEEE_8021QAZ_MAX_TCS; j++) { if (prio_tc[j] == i) { @@ -877,10 +883,17 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu, continue; lossy = !(pfc || pause_en); - thres = mlxsw_sp_pg_buf_threshold_get(mlxsw_sp, mtu); - delay = mlxsw_sp_pg_buf_delay_get(mlxsw_sp, mtu, delay, pfc, - pause_en); - mlxsw_sp_pg_buf_pack(pbmc_pl, i, thres + delay, thres, lossy); + thres_cells = mlxsw_sp_pg_buf_threshold_get(mlxsw_sp, mtu); + delay_cells = mlxsw_sp_pg_buf_delay_get(mlxsw_sp, mtu, delay, + pfc, pause_en); + total_cells = thres_cells + delay_cells; + + taken_headroom_cells += total_cells; + if (taken_headroom_cells > max_headroom_cells) + return -ENOBUFS; + + mlxsw_sp_pg_buf_pack(pbmc_pl, i, total_cells, + thres_cells, lossy); } return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pbmc), pbmc_pl); @@ -2723,23 +2736,23 @@ static int mlxsw_sp_query_module_eeprom(struct mlxsw_sp_port *mlxsw_sp_port, unsigned int *p_read_size) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; - char eeprom_tmp[MLXSW_SP_REG_MCIA_EEPROM_SIZE]; + char eeprom_tmp[MLXSW_REG_MCIA_EEPROM_SIZE]; char mcia_pl[MLXSW_REG_MCIA_LEN]; u16 i2c_addr; int status; int err; - size = min_t(u16, size, MLXSW_SP_REG_MCIA_EEPROM_SIZE); + size = min_t(u16, size, MLXSW_REG_MCIA_EEPROM_SIZE); - if (offset < MLXSW_SP_EEPROM_PAGE_LENGTH && - offset + size > MLXSW_SP_EEPROM_PAGE_LENGTH) + if (offset < MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH && + offset + size > MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH) /* Cross pages read, read until offset 256 in low page */ - size = MLXSW_SP_EEPROM_PAGE_LENGTH - offset; + size = MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH - offset; - i2c_addr = MLXSW_SP_I2C_ADDR_LOW; - if (offset >= MLXSW_SP_EEPROM_PAGE_LENGTH) { - i2c_addr = MLXSW_SP_I2C_ADDR_HIGH; - offset -= MLXSW_SP_EEPROM_PAGE_LENGTH; + i2c_addr = MLXSW_REG_MCIA_I2C_ADDR_LOW; + if (offset >= MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH) { + i2c_addr = MLXSW_REG_MCIA_I2C_ADDR_HIGH; + offset -= MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH; } mlxsw_reg_mcia_pack(mcia_pl, mlxsw_sp_port->mapping.module, @@ -2760,55 +2773,37 @@ static int mlxsw_sp_query_module_eeprom(struct mlxsw_sp_port *mlxsw_sp_port, return 0; } -enum mlxsw_sp_eeprom_module_info_rev_id { - MLXSW_SP_EEPROM_MODULE_INFO_REV_ID_UNSPC = 0x00, - MLXSW_SP_EEPROM_MODULE_INFO_REV_ID_8436 = 0x01, - MLXSW_SP_EEPROM_MODULE_INFO_REV_ID_8636 = 0x03, -}; - -enum mlxsw_sp_eeprom_module_info_id { - MLXSW_SP_EEPROM_MODULE_INFO_ID_SFP = 0x03, - MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP = 0x0C, - MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP_PLUS = 0x0D, - MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP28 = 0x11, -}; - -enum mlxsw_sp_eeprom_module_info { - MLXSW_SP_EEPROM_MODULE_INFO_ID, - MLXSW_SP_EEPROM_MODULE_INFO_REV_ID, - MLXSW_SP_EEPROM_MODULE_INFO_SIZE, -}; - static int mlxsw_sp_get_module_info(struct net_device *netdev, struct ethtool_modinfo *modinfo) { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(netdev); - u8 module_info[MLXSW_SP_EEPROM_MODULE_INFO_SIZE]; + u8 module_info[MLXSW_REG_MCIA_EEPROM_MODULE_INFO_SIZE]; + u16 offset = MLXSW_REG_MCIA_EEPROM_MODULE_INFO_SIZE; u8 module_rev_id, module_id; unsigned int read_size; int err; - err = mlxsw_sp_query_module_eeprom(mlxsw_sp_port, 0, - MLXSW_SP_EEPROM_MODULE_INFO_SIZE, + err = mlxsw_sp_query_module_eeprom(mlxsw_sp_port, 0, offset, module_info, &read_size); if (err) return err; - if (read_size < MLXSW_SP_EEPROM_MODULE_INFO_SIZE) + if (read_size < offset) return -EIO; - module_rev_id = module_info[MLXSW_SP_EEPROM_MODULE_INFO_REV_ID]; - module_id = module_info[MLXSW_SP_EEPROM_MODULE_INFO_ID]; + module_rev_id = module_info[MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID]; + module_id = module_info[MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID]; switch (module_id) { - case MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP: + case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP: modinfo->type = ETH_MODULE_SFF_8436; modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN; break; - case MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP_PLUS: - case MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP28: - if (module_id == MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP28 || - module_rev_id >= MLXSW_SP_EEPROM_MODULE_INFO_REV_ID_8636) { + case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_PLUS: /* fall-through */ + case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28: + if (module_id == MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28 || + module_rev_id >= + MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID_8636) { modinfo->type = ETH_MODULE_SFF_8636; modinfo->eeprom_len = ETH_MODULE_SFF_8636_LEN; } else { @@ -2816,7 +2811,7 @@ static int mlxsw_sp_get_module_info(struct net_device *netdev, modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN; } break; - case MLXSW_SP_EEPROM_MODULE_INFO_ID_SFP: + case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_SFP: modinfo->type = ETH_MODULE_SFF_8472; modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; break; @@ -3757,8 +3752,8 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core) burst_size = 7; break; case MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME: - rate = 4 * 1024; - burst_size = 4; + rate = 1024; + burst_size = 7; break; default: continue; @@ -4108,6 +4103,7 @@ static int mlxsw_sp1_init(struct mlxsw_core *mlxsw_core, mlxsw_sp->nve_ops_arr = mlxsw_sp1_nve_ops_arr; mlxsw_sp->mac_mask = mlxsw_sp1_mac_mask; mlxsw_sp->rif_ops_arr = mlxsw_sp1_rif_ops_arr; + mlxsw_sp->sb_vals = &mlxsw_sp1_sb_vals; return mlxsw_sp_init(mlxsw_core, mlxsw_bus_info); } @@ -4125,6 +4121,7 @@ static int mlxsw_sp2_init(struct mlxsw_core *mlxsw_core, mlxsw_sp->nve_ops_arr = mlxsw_sp2_nve_ops_arr; mlxsw_sp->mac_mask = mlxsw_sp2_mac_mask; mlxsw_sp->rif_ops_arr = mlxsw_sp2_rif_ops_arr; + mlxsw_sp->sb_vals = &mlxsw_sp2_sb_vals; return mlxsw_sp_init(mlxsw_core, mlxsw_bus_info); } @@ -4413,6 +4410,71 @@ static void mlxsw_sp_params_unregister(struct mlxsw_core *mlxsw_core) ARRAY_SIZE(mlxsw_sp_devlink_params)); } +static int +mlxsw_sp_params_acl_region_rehash_intrvl_get(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct mlxsw_core *mlxsw_core = devlink_priv(devlink); + struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); + + ctx->val.vu32 = mlxsw_sp_acl_region_rehash_intrvl_get(mlxsw_sp); + return 0; +} + +static int +mlxsw_sp_params_acl_region_rehash_intrvl_set(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct mlxsw_core *mlxsw_core = devlink_priv(devlink); + struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); + + return mlxsw_sp_acl_region_rehash_intrvl_set(mlxsw_sp, ctx->val.vu32); +} + +static const struct devlink_param mlxsw_sp2_devlink_params[] = { + DEVLINK_PARAM_DRIVER(MLXSW_DEVLINK_PARAM_ID_ACL_REGION_REHASH_INTERVAL, + "acl_region_rehash_interval", + DEVLINK_PARAM_TYPE_U32, + BIT(DEVLINK_PARAM_CMODE_RUNTIME), + mlxsw_sp_params_acl_region_rehash_intrvl_get, + mlxsw_sp_params_acl_region_rehash_intrvl_set, + NULL), +}; + +static int mlxsw_sp2_params_register(struct mlxsw_core *mlxsw_core) +{ + struct devlink *devlink = priv_to_devlink(mlxsw_core); + union devlink_param_value value; + int err; + + err = mlxsw_sp_params_register(mlxsw_core); + if (err) + return err; + + err = devlink_params_register(devlink, mlxsw_sp2_devlink_params, + ARRAY_SIZE(mlxsw_sp2_devlink_params)); + if (err) + goto err_devlink_params_register; + + value.vu32 = 0; + devlink_param_driverinit_value_set(devlink, + MLXSW_DEVLINK_PARAM_ID_ACL_REGION_REHASH_INTERVAL, + value); + return 0; + +err_devlink_params_register: + mlxsw_sp_params_unregister(mlxsw_core); + return err; +} + +static void mlxsw_sp2_params_unregister(struct mlxsw_core *mlxsw_core) +{ + devlink_params_unregister(priv_to_devlink(mlxsw_core), + mlxsw_sp2_devlink_params, + ARRAY_SIZE(mlxsw_sp2_devlink_params)); + mlxsw_sp_params_unregister(mlxsw_core); +} + static struct mlxsw_driver mlxsw_sp1_driver = { .kind = mlxsw_sp1_driver_name, .priv_size = sizeof(struct mlxsw_sp), @@ -4461,8 +4523,8 @@ static struct mlxsw_driver mlxsw_sp2_driver = { .sb_occ_tc_port_bind_get = mlxsw_sp_sb_occ_tc_port_bind_get, .txhdr_construct = mlxsw_sp_txhdr_construct, .resources_register = mlxsw_sp2_resources_register, - .params_register = mlxsw_sp_params_register, - .params_unregister = mlxsw_sp_params_unregister, + .params_register = mlxsw_sp2_params_register, + .params_unregister = mlxsw_sp2_params_unregister, .txhdr_len = MLXSW_TXHDR_LEN, .profile = &mlxsw_sp2_config_profile, .res_query_enabled = true, @@ -4706,9 +4768,6 @@ static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port, err = mlxsw_sp_lag_col_port_add(mlxsw_sp_port, lag_id, port_index); if (err) goto err_col_port_add; - err = mlxsw_sp_lag_col_port_enable(mlxsw_sp_port, lag_id); - if (err) - goto err_col_port_enable; mlxsw_core_lag_mapping_set(mlxsw_sp->core, lag_id, port_index, mlxsw_sp_port->local_port); @@ -4722,8 +4781,6 @@ static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port, return 0; -err_col_port_enable: - mlxsw_sp_lag_col_port_remove(mlxsw_sp_port, lag_id); err_col_port_add: if (!lag->ref_count) mlxsw_sp_lag_destroy(mlxsw_sp, lag_id); @@ -4742,7 +4799,6 @@ static void mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port, lag = mlxsw_sp_lag_get(mlxsw_sp, lag_id); WARN_ON(lag->ref_count == 0); - mlxsw_sp_lag_col_port_disable(mlxsw_sp_port, lag_id); mlxsw_sp_lag_col_port_remove(mlxsw_sp_port, lag_id); /* Any VLANs configured on the port are no longer valid */ @@ -4787,21 +4843,56 @@ static int mlxsw_sp_lag_dist_port_remove(struct mlxsw_sp_port *mlxsw_sp_port, return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sldr), sldr_pl); } -static int mlxsw_sp_port_lag_tx_en_set(struct mlxsw_sp_port *mlxsw_sp_port, - bool lag_tx_enabled) +static int +mlxsw_sp_port_lag_col_dist_enable(struct mlxsw_sp_port *mlxsw_sp_port) { - if (lag_tx_enabled) - return mlxsw_sp_lag_dist_port_add(mlxsw_sp_port, - mlxsw_sp_port->lag_id); - else - return mlxsw_sp_lag_dist_port_remove(mlxsw_sp_port, - mlxsw_sp_port->lag_id); + int err; + + err = mlxsw_sp_lag_col_port_enable(mlxsw_sp_port, + mlxsw_sp_port->lag_id); + if (err) + return err; + + err = mlxsw_sp_lag_dist_port_add(mlxsw_sp_port, mlxsw_sp_port->lag_id); + if (err) + goto err_dist_port_add; + + return 0; + +err_dist_port_add: + mlxsw_sp_lag_col_port_disable(mlxsw_sp_port, mlxsw_sp_port->lag_id); + return err; +} + +static int +mlxsw_sp_port_lag_col_dist_disable(struct mlxsw_sp_port *mlxsw_sp_port) +{ + int err; + + err = mlxsw_sp_lag_dist_port_remove(mlxsw_sp_port, + mlxsw_sp_port->lag_id); + if (err) + return err; + + err = mlxsw_sp_lag_col_port_disable(mlxsw_sp_port, + mlxsw_sp_port->lag_id); + if (err) + goto err_col_port_disable; + + return 0; + +err_col_port_disable: + mlxsw_sp_lag_dist_port_add(mlxsw_sp_port, mlxsw_sp_port->lag_id); + return err; } static int mlxsw_sp_port_lag_changed(struct mlxsw_sp_port *mlxsw_sp_port, struct netdev_lag_lower_state_info *info) { - return mlxsw_sp_port_lag_tx_en_set(mlxsw_sp_port, info->tx_enabled); + if (info->tx_enabled) + return mlxsw_sp_port_lag_col_dist_enable(mlxsw_sp_port); + else + return mlxsw_sp_port_lag_col_dist_disable(mlxsw_sp_port); } static int mlxsw_sp_port_stp_set(struct mlxsw_sp_port *mlxsw_sp_port, @@ -5024,8 +5115,7 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev, err = mlxsw_sp_port_lag_join(mlxsw_sp_port, upper_dev); } else { - mlxsw_sp_port_lag_tx_en_set(mlxsw_sp_port, - false); + mlxsw_sp_port_lag_col_dist_disable(mlxsw_sp_port); mlxsw_sp_port_lag_leave(mlxsw_sp_port, upper_dev); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 4fe0996c7cdd..8bb83d0facc2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -133,6 +133,7 @@ struct mlxsw_sp_kvdl_ops; struct mlxsw_sp_mr_tcam_ops; struct mlxsw_sp_acl_tcam_ops; struct mlxsw_sp_nve_ops; +struct mlxsw_sp_sb_vals; struct mlxsw_sp { struct mlxsw_sp_port **ports; @@ -167,6 +168,7 @@ struct mlxsw_sp { const struct mlxsw_sp_acl_tcam_ops *acl_tcam_ops; const struct mlxsw_sp_nve_ops **nve_ops_arr; const struct mlxsw_sp_rif_ops **rif_ops_arr; + const struct mlxsw_sp_sb_vals *sb_vals; }; static inline struct mlxsw_sp_upper * @@ -371,6 +373,10 @@ int mlxsw_sp_sb_occ_tc_port_bind_get(struct mlxsw_core_port *mlxsw_core_port, u32 *p_cur, u32 *p_max); u32 mlxsw_sp_cells_bytes(const struct mlxsw_sp *mlxsw_sp, u32 cells); u32 mlxsw_sp_bytes_cells(const struct mlxsw_sp *mlxsw_sp, u32 bytes); +u32 mlxsw_sp_sb_max_headroom_cells(const struct mlxsw_sp *mlxsw_sp); + +extern const struct mlxsw_sp_sb_vals mlxsw_sp1_sb_vals; +extern const struct mlxsw_sp_sb_vals mlxsw_sp2_sb_vals; /* spectrum_switchdev.c */ int mlxsw_sp_switchdev_init(struct mlxsw_sp *mlxsw_sp); @@ -690,6 +696,8 @@ struct mlxsw_sp_fid *mlxsw_sp_acl_dummy_fid(struct mlxsw_sp *mlxsw_sp); int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp); void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp); +u32 mlxsw_sp_acl_region_rehash_intrvl_get(struct mlxsw_sp *mlxsw_sp); +int mlxsw_sp_acl_region_rehash_intrvl_set(struct mlxsw_sp *mlxsw_sp, u32 val); /* spectrum_acl_tcam.c */ struct mlxsw_sp_acl_tcam; @@ -704,10 +712,13 @@ struct mlxsw_sp_acl_tcam_ops { size_t region_priv_size; int (*region_init)(struct mlxsw_sp *mlxsw_sp, void *region_priv, void *tcam_priv, - struct mlxsw_sp_acl_tcam_region *region); + struct mlxsw_sp_acl_tcam_region *region, + void *hints_priv); void (*region_fini)(struct mlxsw_sp *mlxsw_sp, void *region_priv); int (*region_associate)(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam_region *region); + void * (*region_rehash_hints_get)(void *region_priv); + void (*region_rehash_hints_put)(void *hints_priv); size_t chunk_priv_size; void (*chunk_init)(void *region_priv, void *chunk_priv, unsigned int priority); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c index 6e444525713f..3a636f753607 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c @@ -112,7 +112,8 @@ mlxsw_sp1_acl_ctcam_region_catchall_del(struct mlxsw_sp *mlxsw_sp, static int mlxsw_sp1_acl_tcam_region_init(struct mlxsw_sp *mlxsw_sp, void *region_priv, void *tcam_priv, - struct mlxsw_sp_acl_tcam_region *_region) + struct mlxsw_sp_acl_tcam_region *_region, + void *hints_priv) { struct mlxsw_sp1_acl_tcam_region *region = region_priv; int err; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c index d380b3403960..6c66a0f1b79e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c @@ -139,7 +139,8 @@ static void mlxsw_sp2_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, void *priv) static int mlxsw_sp2_acl_tcam_region_init(struct mlxsw_sp *mlxsw_sp, void *region_priv, void *tcam_priv, - struct mlxsw_sp_acl_tcam_region *_region) + struct mlxsw_sp_acl_tcam_region *_region, + void *hints_priv) { struct mlxsw_sp2_acl_tcam_region *region = region_priv; struct mlxsw_sp2_acl_tcam *tcam = tcam_priv; @@ -147,7 +148,8 @@ mlxsw_sp2_acl_tcam_region_init(struct mlxsw_sp *mlxsw_sp, void *region_priv, region->region = _region; return mlxsw_sp_acl_atcam_region_init(mlxsw_sp, &tcam->atcam, - ®ion->aregion, _region, + ®ion->aregion, + _region, hints_priv, &mlxsw_sp2_acl_ctcam_region_ops); } @@ -166,6 +168,18 @@ mlxsw_sp2_acl_tcam_region_associate(struct mlxsw_sp *mlxsw_sp, return mlxsw_sp_acl_atcam_region_associate(mlxsw_sp, region->id); } +static void *mlxsw_sp2_acl_tcam_region_rehash_hints_get(void *region_priv) +{ + struct mlxsw_sp2_acl_tcam_region *region = region_priv; + + return mlxsw_sp_acl_atcam_rehash_hints_get(®ion->aregion); +} + +static void mlxsw_sp2_acl_tcam_region_rehash_hints_put(void *hints_priv) +{ + mlxsw_sp_acl_atcam_rehash_hints_put(hints_priv); +} + static void mlxsw_sp2_acl_tcam_chunk_init(void *region_priv, void *chunk_priv, unsigned int priority) { @@ -243,6 +257,8 @@ const struct mlxsw_sp_acl_tcam_ops mlxsw_sp2_acl_tcam_ops = { .region_init = mlxsw_sp2_acl_tcam_region_init, .region_fini = mlxsw_sp2_acl_tcam_region_fini, .region_associate = mlxsw_sp2_acl_tcam_region_associate, + .region_rehash_hints_get = mlxsw_sp2_acl_tcam_region_rehash_hints_get, + .region_rehash_hints_put = mlxsw_sp2_acl_tcam_region_rehash_hints_put, .chunk_priv_size = sizeof(struct mlxsw_sp2_acl_tcam_chunk), .chunk_init = mlxsw_sp2_acl_tcam_chunk_init, .chunk_fini = mlxsw_sp2_acl_tcam_chunk_fini, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index 2649d128a57c..a146a44634e9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -640,7 +640,7 @@ mlxsw_sp_acl_rule_create(struct mlxsw_sp *mlxsw_sp, int err; mlxsw_sp_acl_ruleset_ref_inc(ruleset); - rule = kzalloc(sizeof(*rule) + ops->rule_priv_size(mlxsw_sp), + rule = kzalloc(sizeof(*rule) + ops->rule_priv_size, GFP_KERNEL); if (!rule) { err = -ENOMEM; @@ -912,3 +912,19 @@ void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp) mlxsw_afk_destroy(acl->afk); kfree(acl); } + +u32 mlxsw_sp_acl_region_rehash_intrvl_get(struct mlxsw_sp *mlxsw_sp) +{ + struct mlxsw_sp_acl *acl = mlxsw_sp->acl; + + return mlxsw_sp_acl_tcam_vregion_rehash_intrvl_get(mlxsw_sp, + &acl->tcam); +} + +int mlxsw_sp_acl_region_rehash_intrvl_set(struct mlxsw_sp *mlxsw_sp, u32 val) +{ + struct mlxsw_sp_acl *acl = mlxsw_sp->acl; + + return mlxsw_sp_acl_tcam_vregion_rehash_intrvl_set(mlxsw_sp, + &acl->tcam, val); +} diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c index a74a390901ac..ded4cf658680 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c @@ -318,6 +318,7 @@ mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_atcam *atcam, struct mlxsw_sp_acl_atcam_region *aregion, struct mlxsw_sp_acl_tcam_region *region, + void *hints_priv, const struct mlxsw_sp_acl_ctcam_region_ops *ops) { int err; @@ -334,7 +335,7 @@ mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp, err = aregion->ops->init(aregion); if (err) goto err_ops_init; - err = mlxsw_sp_acl_erp_region_init(aregion); + err = mlxsw_sp_acl_erp_region_init(aregion, hints_priv); if (err) goto err_erp_region_init; err = mlxsw_sp_acl_ctcam_region_init(mlxsw_sp, &aregion->cregion, @@ -634,3 +635,14 @@ void mlxsw_sp_acl_atcam_fini(struct mlxsw_sp *mlxsw_sp, { mlxsw_sp_acl_erps_fini(mlxsw_sp, atcam); } + +void * +mlxsw_sp_acl_atcam_rehash_hints_get(struct mlxsw_sp_acl_atcam_region *aregion) +{ + return mlxsw_sp_acl_erp_rehash_hints_get(aregion); +} + +void mlxsw_sp_acl_atcam_rehash_hints_put(void *hints_priv) +{ + mlxsw_sp_acl_erp_rehash_hints_put(hints_priv); +} diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c index 2941967e1cc5..e935c36638d9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c @@ -1200,6 +1200,32 @@ mlxsw_sp_acl_erp_delta_fill(const struct mlxsw_sp_acl_erp_key *parent_key, return 0; } +static bool mlxsw_sp_acl_erp_delta_check(void *priv, const void *parent_obj, + const void *obj) +{ + const struct mlxsw_sp_acl_erp_key *parent_key = parent_obj; + const struct mlxsw_sp_acl_erp_key *key = obj; + u16 delta_start; + u8 delta_mask; + int err; + + err = mlxsw_sp_acl_erp_delta_fill(parent_key, key, + &delta_start, &delta_mask); + return err ? false : true; +} + +static int mlxsw_sp_acl_erp_hints_obj_cmp(const void *obj1, const void *obj2) +{ + const struct mlxsw_sp_acl_erp_key *key1 = obj1; + const struct mlxsw_sp_acl_erp_key *key2 = obj2; + + /* For hints purposes, two objects are considered equal + * in case the masks are the same. Does not matter what + * the "ctcam" value is. + */ + return memcmp(key1->mask, key2->mask, sizeof(key1->mask)); +} + static void *mlxsw_sp_acl_erp_delta_create(void *priv, void *parent_obj, void *obj) { @@ -1254,12 +1280,17 @@ static void mlxsw_sp_acl_erp_delta_destroy(void *priv, void *delta_priv) kfree(delta); } -static void *mlxsw_sp_acl_erp_root_create(void *priv, void *obj) +static void *mlxsw_sp_acl_erp_root_create(void *priv, void *obj, + unsigned int root_id) { struct mlxsw_sp_acl_atcam_region *aregion = priv; struct mlxsw_sp_acl_erp_table *erp_table = aregion->erp_table; struct mlxsw_sp_acl_erp_key *key = obj; + if (!key->ctcam && + root_id != OBJAGG_OBJ_ROOT_ID_INVALID && + root_id >= MLXSW_SP_ACL_ERP_MAX_PER_REGION) + return ERR_PTR(-ENOBUFS); return erp_table->ops->erp_create(erp_table, key); } @@ -1273,6 +1304,8 @@ static void mlxsw_sp_acl_erp_root_destroy(void *priv, void *root_priv) static const struct objagg_ops mlxsw_sp_acl_erp_objagg_ops = { .obj_size = sizeof(struct mlxsw_sp_acl_erp_key), + .delta_check = mlxsw_sp_acl_erp_delta_check, + .hints_obj_cmp = mlxsw_sp_acl_erp_hints_obj_cmp, .delta_create = mlxsw_sp_acl_erp_delta_create, .delta_destroy = mlxsw_sp_acl_erp_delta_destroy, .root_create = mlxsw_sp_acl_erp_root_create, @@ -1280,7 +1313,8 @@ static const struct objagg_ops mlxsw_sp_acl_erp_objagg_ops = { }; static struct mlxsw_sp_acl_erp_table * -mlxsw_sp_acl_erp_table_create(struct mlxsw_sp_acl_atcam_region *aregion) +mlxsw_sp_acl_erp_table_create(struct mlxsw_sp_acl_atcam_region *aregion, + struct objagg_hints *hints) { struct mlxsw_sp_acl_erp_table *erp_table; int err; @@ -1290,7 +1324,7 @@ mlxsw_sp_acl_erp_table_create(struct mlxsw_sp_acl_atcam_region *aregion) return ERR_PTR(-ENOMEM); erp_table->objagg = objagg_create(&mlxsw_sp_acl_erp_objagg_ops, - aregion); + hints, aregion); if (IS_ERR(erp_table->objagg)) { err = PTR_ERR(erp_table->objagg); goto err_objagg_create; @@ -1337,12 +1371,88 @@ mlxsw_sp_acl_erp_region_param_init(struct mlxsw_sp_acl_atcam_region *aregion) return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pererp), pererp_pl); } -int mlxsw_sp_acl_erp_region_init(struct mlxsw_sp_acl_atcam_region *aregion) +static int +mlxsw_sp_acl_erp_hints_check(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_atcam_region *aregion, + struct objagg_hints *hints, bool *p_rehash_needed) +{ + struct objagg *objagg = aregion->erp_table->objagg; + const struct objagg_stats *ostats; + const struct objagg_stats *hstats; + int err; + + *p_rehash_needed = false; + + ostats = objagg_stats_get(objagg); + if (IS_ERR(ostats)) { + dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to get ERP stats\n"); + return PTR_ERR(ostats); + } + + hstats = objagg_hints_stats_get(hints); + if (IS_ERR(hstats)) { + dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to get ERP hints stats\n"); + err = PTR_ERR(hstats); + goto err_hints_stats_get; + } + + /* Very basic criterion for now. */ + if (hstats->root_count < ostats->root_count) + *p_rehash_needed = true; + + err = 0; + + objagg_stats_put(hstats); +err_hints_stats_get: + objagg_stats_put(ostats); + return err; +} + +void * +mlxsw_sp_acl_erp_rehash_hints_get(struct mlxsw_sp_acl_atcam_region *aregion) +{ + struct mlxsw_sp *mlxsw_sp = aregion->region->mlxsw_sp; + struct objagg_hints *hints; + bool rehash_needed; + int err; + + hints = objagg_hints_get(aregion->erp_table->objagg, + OBJAGG_OPT_ALGO_SIMPLE_GREEDY); + if (IS_ERR(hints)) { + dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to create ERP hints\n"); + return ERR_CAST(hints); + } + err = mlxsw_sp_acl_erp_hints_check(mlxsw_sp, aregion, hints, + &rehash_needed); + if (err) + goto errout; + + if (!rehash_needed) { + err = -EAGAIN; + goto errout; + } + return hints; + +errout: + objagg_hints_put(hints); + return ERR_PTR(err); +} + +void mlxsw_sp_acl_erp_rehash_hints_put(void *hints_priv) +{ + struct objagg_hints *hints = hints_priv; + + objagg_hints_put(hints); +} + +int mlxsw_sp_acl_erp_region_init(struct mlxsw_sp_acl_atcam_region *aregion, + void *hints_priv) { struct mlxsw_sp_acl_erp_table *erp_table; + struct objagg_hints *hints = hints_priv; int err; - erp_table = mlxsw_sp_acl_erp_table_create(aregion); + erp_table = mlxsw_sp_acl_erp_table_create(aregion, hints); if (IS_ERR(erp_table)) return PTR_ERR(erp_table); aregion->erp_table = erp_table; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c index 11456e1f236f..7e225a86e3a8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -8,6 +8,7 @@ #include <linux/list.h> #include <linux/rhashtable.h> #include <linux/netdevice.h> +#include <trace/events/mlxsw.h> #include "reg.h" #include "core.h" @@ -23,6 +24,9 @@ size_t mlxsw_sp_acl_tcam_priv_size(struct mlxsw_sp *mlxsw_sp) return ops->priv_size; } +#define MLXSW_SP_ACL_TCAM_VREGION_REHASH_INTRVL_DFLT 5000 /* ms */ +#define MLXSW_SP_ACL_TCAM_VREGION_REHASH_INTRVL_MIN 3000 /* ms */ + int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam *tcam) { @@ -33,6 +37,10 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, size_t alloc_size; int err; + tcam->vregion_rehash_intrvl = + MLXSW_SP_ACL_TCAM_VREGION_REHASH_INTRVL_DFLT; + INIT_LIST_HEAD(&tcam->vregion_list); + max_tcam_regions = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_TCAM_REGIONS); max_regions = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_REGIONS); @@ -153,9 +161,9 @@ struct mlxsw_sp_acl_tcam_pattern { struct mlxsw_sp_acl_tcam_group { struct mlxsw_sp_acl_tcam *tcam; u16 id; - struct list_head region_list; + struct list_head vregion_list; unsigned int region_count; - struct rhashtable chunk_ht; + struct rhashtable vchunk_ht; struct mlxsw_sp_acl_tcam_group_ops *ops; const struct mlxsw_sp_acl_tcam_pattern *patterns; unsigned int patterns_count; @@ -163,40 +171,77 @@ struct mlxsw_sp_acl_tcam_group { struct mlxsw_afk_element_usage tmplt_elusage; }; -struct mlxsw_sp_acl_tcam_chunk { - struct list_head list; /* Member of a TCAM region */ - struct rhash_head ht_node; /* Member of a chunk HT */ - unsigned int priority; /* Priority within the region and group */ +struct mlxsw_sp_acl_tcam_vregion { + struct mlxsw_sp_acl_tcam_region *region; + struct mlxsw_sp_acl_tcam_region *region2; /* Used during migration */ + struct list_head list; /* Member of a TCAM group */ + struct list_head tlist; /* Member of a TCAM */ + struct list_head vchunk_list; /* List of vchunks under this vregion */ struct mlxsw_sp_acl_tcam_group *group; + struct mlxsw_afk_key_info *key_info; + struct mlxsw_sp_acl_tcam *tcam; + struct delayed_work rehash_dw; + struct mlxsw_sp *mlxsw_sp; + bool failed_rollback; /* Indicates failed rollback during migration */ +}; + +struct mlxsw_sp_acl_tcam_vchunk; + +struct mlxsw_sp_acl_tcam_chunk { + struct mlxsw_sp_acl_tcam_vchunk *vchunk; struct mlxsw_sp_acl_tcam_region *region; - unsigned int ref_count; unsigned long priv[0]; /* priv has to be always the last item */ }; +struct mlxsw_sp_acl_tcam_vchunk { + struct mlxsw_sp_acl_tcam_chunk *chunk; + struct mlxsw_sp_acl_tcam_chunk *chunk2; /* Used during migration */ + struct list_head list; /* Member of a TCAM vregion */ + struct rhash_head ht_node; /* Member of a chunk HT */ + struct list_head ventry_list; + unsigned int priority; /* Priority within the vregion and group */ + struct mlxsw_sp_acl_tcam_group *group; + struct mlxsw_sp_acl_tcam_vregion *vregion; + unsigned int ref_count; +}; + struct mlxsw_sp_acl_tcam_entry { + struct mlxsw_sp_acl_tcam_ventry *ventry; struct mlxsw_sp_acl_tcam_chunk *chunk; unsigned long priv[0]; /* priv has to be always the last item */ }; -static const struct rhashtable_params mlxsw_sp_acl_tcam_chunk_ht_params = { +struct mlxsw_sp_acl_tcam_ventry { + struct mlxsw_sp_acl_tcam_entry *entry; + struct list_head list; /* Member of a TCAM vchunk */ + struct mlxsw_sp_acl_tcam_vchunk *vchunk; + struct mlxsw_sp_acl_rule_info *rulei; +}; + +static const struct rhashtable_params mlxsw_sp_acl_tcam_vchunk_ht_params = { .key_len = sizeof(unsigned int), - .key_offset = offsetof(struct mlxsw_sp_acl_tcam_chunk, priority), - .head_offset = offsetof(struct mlxsw_sp_acl_tcam_chunk, ht_node), + .key_offset = offsetof(struct mlxsw_sp_acl_tcam_vchunk, priority), + .head_offset = offsetof(struct mlxsw_sp_acl_tcam_vchunk, ht_node), .automatic_shrinking = true, }; static int mlxsw_sp_acl_tcam_group_update(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam_group *group) { - struct mlxsw_sp_acl_tcam_region *region; + struct mlxsw_sp_acl_tcam_vregion *vregion; char pagt_pl[MLXSW_REG_PAGT_LEN]; int acl_index = 0; mlxsw_reg_pagt_pack(pagt_pl, group->id); - list_for_each_entry(region, &group->region_list, list) - mlxsw_reg_pagt_acl_id_pack(pagt_pl, acl_index++, region->id); + list_for_each_entry(vregion, &group->vregion_list, list) { + if (vregion->region2) + mlxsw_reg_pagt_acl_id_pack(pagt_pl, acl_index++, + vregion->region2->id, true); + mlxsw_reg_pagt_acl_id_pack(pagt_pl, acl_index++, + vregion->region->id, false); + } mlxsw_reg_pagt_size_set(pagt_pl, acl_index); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pagt), pagt_pl); } @@ -219,13 +264,13 @@ mlxsw_sp_acl_tcam_group_add(struct mlxsw_sp *mlxsw_sp, memcpy(&group->tmplt_elusage, tmplt_elusage, sizeof(group->tmplt_elusage)); } - INIT_LIST_HEAD(&group->region_list); + INIT_LIST_HEAD(&group->vregion_list); err = mlxsw_sp_acl_tcam_group_id_get(tcam, &group->id); if (err) return err; - err = rhashtable_init(&group->chunk_ht, - &mlxsw_sp_acl_tcam_chunk_ht_params); + err = rhashtable_init(&group->vchunk_ht, + &mlxsw_sp_acl_tcam_vchunk_ht_params); if (err) goto err_rhashtable_init; @@ -241,9 +286,9 @@ static void mlxsw_sp_acl_tcam_group_del(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_acl_tcam *tcam = group->tcam; - rhashtable_destroy(&group->chunk_ht); + rhashtable_destroy(&group->vchunk_ht); mlxsw_sp_acl_tcam_group_id_put(tcam, group->id); - WARN_ON(!list_empty(&group->region_list)); + WARN_ON(!list_empty(&group->vregion_list)); } static int @@ -283,140 +328,153 @@ mlxsw_sp_acl_tcam_group_id(struct mlxsw_sp_acl_tcam_group *group) } static unsigned int -mlxsw_sp_acl_tcam_region_prio(struct mlxsw_sp_acl_tcam_region *region) +mlxsw_sp_acl_tcam_vregion_prio(struct mlxsw_sp_acl_tcam_vregion *vregion) { - struct mlxsw_sp_acl_tcam_chunk *chunk; + struct mlxsw_sp_acl_tcam_vchunk *vchunk; - if (list_empty(®ion->chunk_list)) + if (list_empty(&vregion->vchunk_list)) return 0; - /* As a priority of a region, return priority of the first chunk */ - chunk = list_first_entry(®ion->chunk_list, typeof(*chunk), list); - return chunk->priority; + /* As a priority of a vregion, return priority of the first vchunk */ + vchunk = list_first_entry(&vregion->vchunk_list, + typeof(*vchunk), list); + return vchunk->priority; } static unsigned int -mlxsw_sp_acl_tcam_region_max_prio(struct mlxsw_sp_acl_tcam_region *region) +mlxsw_sp_acl_tcam_vregion_max_prio(struct mlxsw_sp_acl_tcam_vregion *vregion) { - struct mlxsw_sp_acl_tcam_chunk *chunk; + struct mlxsw_sp_acl_tcam_vchunk *vchunk; - if (list_empty(®ion->chunk_list)) + if (list_empty(&vregion->vchunk_list)) return 0; - chunk = list_last_entry(®ion->chunk_list, typeof(*chunk), list); - return chunk->priority; + vchunk = list_last_entry(&vregion->vchunk_list, + typeof(*vchunk), list); + return vchunk->priority; } -static void -mlxsw_sp_acl_tcam_group_list_add(struct mlxsw_sp_acl_tcam_group *group, - struct mlxsw_sp_acl_tcam_region *region) +static int +mlxsw_sp_acl_tcam_group_region_attach(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_region *region) { - struct mlxsw_sp_acl_tcam_region *region2; - struct list_head *pos; + struct mlxsw_sp_acl_tcam_group *group = region->vregion->group; + int err; + + if (group->region_count == group->tcam->max_group_size) + return -ENOBUFS; + + err = mlxsw_sp_acl_tcam_group_update(mlxsw_sp, group); + if (err) + return err; - /* Position the region inside the list according to priority */ - list_for_each(pos, &group->region_list) { - region2 = list_entry(pos, typeof(*region2), list); - if (mlxsw_sp_acl_tcam_region_prio(region2) > - mlxsw_sp_acl_tcam_region_prio(region)) - break; - } - list_add_tail(®ion->list, pos); group->region_count++; + return 0; } static void -mlxsw_sp_acl_tcam_group_list_del(struct mlxsw_sp_acl_tcam_group *group, - struct mlxsw_sp_acl_tcam_region *region) +mlxsw_sp_acl_tcam_group_region_detach(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_region *region) { + struct mlxsw_sp_acl_tcam_group *group = region->vregion->group; + group->region_count--; - list_del(®ion->list); + mlxsw_sp_acl_tcam_group_update(mlxsw_sp, group); } static int -mlxsw_sp_acl_tcam_group_region_attach(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam_group *group, - struct mlxsw_sp_acl_tcam_region *region) +mlxsw_sp_acl_tcam_group_vregion_attach(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_group *group, + struct mlxsw_sp_acl_tcam_vregion *vregion) { + struct mlxsw_sp_acl_tcam_vregion *vregion2; + struct list_head *pos; int err; - if (group->region_count == group->tcam->max_group_size) - return -ENOBUFS; - - mlxsw_sp_acl_tcam_group_list_add(group, region); + /* Position the vregion inside the list according to priority */ + list_for_each(pos, &group->vregion_list) { + vregion2 = list_entry(pos, typeof(*vregion2), list); + if (mlxsw_sp_acl_tcam_vregion_prio(vregion2) > + mlxsw_sp_acl_tcam_vregion_prio(vregion)) + break; + } + list_add_tail(&vregion->list, pos); + vregion->group = group; - err = mlxsw_sp_acl_tcam_group_update(mlxsw_sp, group); + err = mlxsw_sp_acl_tcam_group_region_attach(mlxsw_sp, vregion->region); if (err) - goto err_group_update; - region->group = group; + goto err_region_attach; return 0; -err_group_update: - mlxsw_sp_acl_tcam_group_list_del(group, region); - mlxsw_sp_acl_tcam_group_update(mlxsw_sp, group); +err_region_attach: + list_del(&vregion->list); return err; } static void -mlxsw_sp_acl_tcam_group_region_detach(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam_region *region) +mlxsw_sp_acl_tcam_group_vregion_detach(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_vregion *vregion) { - struct mlxsw_sp_acl_tcam_group *group = region->group; - - mlxsw_sp_acl_tcam_group_list_del(group, region); - mlxsw_sp_acl_tcam_group_update(mlxsw_sp, group); + list_del(&vregion->list); + if (vregion->region2) + mlxsw_sp_acl_tcam_group_region_detach(mlxsw_sp, + vregion->region2); + mlxsw_sp_acl_tcam_group_region_detach(mlxsw_sp, vregion->region); } -static struct mlxsw_sp_acl_tcam_region * -mlxsw_sp_acl_tcam_group_region_find(struct mlxsw_sp_acl_tcam_group *group, - unsigned int priority, - struct mlxsw_afk_element_usage *elusage, - bool *p_need_split) +static struct mlxsw_sp_acl_tcam_vregion * +mlxsw_sp_acl_tcam_group_vregion_find(struct mlxsw_sp_acl_tcam_group *group, + unsigned int priority, + struct mlxsw_afk_element_usage *elusage, + bool *p_need_split) { - struct mlxsw_sp_acl_tcam_region *region, *region2; + struct mlxsw_sp_acl_tcam_vregion *vregion, *vregion2; struct list_head *pos; bool issubset; - list_for_each(pos, &group->region_list) { - region = list_entry(pos, typeof(*region), list); + list_for_each(pos, &group->vregion_list) { + vregion = list_entry(pos, typeof(*vregion), list); /* First, check if the requested priority does not rather belong - * under some of the next regions. + * under some of the next vregions. */ - if (pos->next != &group->region_list) { /* not last */ - region2 = list_entry(pos->next, typeof(*region2), list); - if (priority >= mlxsw_sp_acl_tcam_region_prio(region2)) + if (pos->next != &group->vregion_list) { /* not last */ + vregion2 = list_entry(pos->next, typeof(*vregion2), + list); + if (priority >= + mlxsw_sp_acl_tcam_vregion_prio(vregion2)) continue; } - issubset = mlxsw_afk_key_info_subset(region->key_info, elusage); + issubset = mlxsw_afk_key_info_subset(vregion->key_info, + elusage); /* If requested element usage would not fit and the priority - * is lower than the currently inspected region we cannot - * use this region, so return NULL to indicate new region has + * is lower than the currently inspected vregion we cannot + * use this region, so return NULL to indicate new vregion has * to be created. */ if (!issubset && - priority < mlxsw_sp_acl_tcam_region_prio(region)) + priority < mlxsw_sp_acl_tcam_vregion_prio(vregion)) return NULL; /* If requested element usage would not fit and the priority - * is higher than the currently inspected region we cannot - * use this region. There is still some hope that the next - * region would be the fit. So let it be processed and + * is higher than the currently inspected vregion we cannot + * use this vregion. There is still some hope that the next + * vregion would be the fit. So let it be processed and * eventually break at the check right above this. */ if (!issubset && - priority > mlxsw_sp_acl_tcam_region_max_prio(region)) + priority > mlxsw_sp_acl_tcam_vregion_max_prio(vregion)) continue; - /* Indicate if the region needs to be split in order to add + /* Indicate if the vregion needs to be split in order to add * the requested priority. Split is needed when requested - * element usage won't fit into the found region. + * element usage won't fit into the found vregion. */ *p_need_split = !issubset; - return region; + return vregion; } - return NULL; /* New region has to be created. */ + return NULL; /* New vregion has to be created. */ } static void @@ -511,24 +569,19 @@ mlxsw_sp_acl_tcam_region_disable(struct mlxsw_sp *mlxsw_sp, static struct mlxsw_sp_acl_tcam_region * mlxsw_sp_acl_tcam_region_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam *tcam, - struct mlxsw_afk_element_usage *elusage) + struct mlxsw_sp_acl_tcam_vregion *vregion, + void *hints_priv) { const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; - struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl); struct mlxsw_sp_acl_tcam_region *region; int err; region = kzalloc(sizeof(*region) + ops->region_priv_size, GFP_KERNEL); if (!region) return ERR_PTR(-ENOMEM); - INIT_LIST_HEAD(®ion->chunk_list); region->mlxsw_sp = mlxsw_sp; - - region->key_info = mlxsw_afk_key_info_get(afk, elusage); - if (IS_ERR(region->key_info)) { - err = PTR_ERR(region->key_info); - goto err_key_info_get; - } + region->vregion = vregion; + region->key_info = vregion->key_info; err = mlxsw_sp_acl_tcam_region_id_get(tcam, ®ion->id); if (err) @@ -547,7 +600,8 @@ mlxsw_sp_acl_tcam_region_create(struct mlxsw_sp *mlxsw_sp, if (err) goto err_tcam_region_enable; - err = ops->region_init(mlxsw_sp, region->priv, tcam->priv, region); + err = ops->region_init(mlxsw_sp, region->priv, tcam->priv, + region, hints_priv); if (err) goto err_tcam_region_init; @@ -561,8 +615,6 @@ err_tcam_region_alloc: err_tcam_region_associate: mlxsw_sp_acl_tcam_region_id_put(tcam, region->id); err_region_id_get: - mlxsw_afk_key_info_put(region->key_info); -err_key_info_get: kfree(region); return ERR_PTR(err); } @@ -576,217 +628,372 @@ mlxsw_sp_acl_tcam_region_destroy(struct mlxsw_sp *mlxsw_sp, ops->region_fini(mlxsw_sp, region->priv); mlxsw_sp_acl_tcam_region_disable(mlxsw_sp, region); mlxsw_sp_acl_tcam_region_free(mlxsw_sp, region); - mlxsw_sp_acl_tcam_region_id_put(region->group->tcam, region->id); - mlxsw_afk_key_info_put(region->key_info); + mlxsw_sp_acl_tcam_region_id_put(region->vregion->group->tcam, + region->id); kfree(region); } +static void +mlxsw_sp_acl_tcam_vregion_rehash_work_schedule(struct mlxsw_sp_acl_tcam_vregion *vregion) +{ + unsigned long interval = vregion->tcam->vregion_rehash_intrvl; + + if (!interval) + return; + mlxsw_core_schedule_dw(&vregion->rehash_dw, + msecs_to_jiffies(interval)); +} + static int -mlxsw_sp_acl_tcam_chunk_assoc(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam_group *group, - unsigned int priority, - struct mlxsw_afk_element_usage *elusage, - struct mlxsw_sp_acl_tcam_chunk *chunk) +mlxsw_sp_acl_tcam_vregion_rehash(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_vregion *vregion); + +static void mlxsw_sp_acl_tcam_vregion_rehash_work(struct work_struct *work) { - struct mlxsw_sp_acl_tcam_region *region; - bool region_created = false; + struct mlxsw_sp_acl_tcam_vregion *vregion = + container_of(work, struct mlxsw_sp_acl_tcam_vregion, + rehash_dw.work); + + /* TODO: Take rtnl lock here as the rest of the code counts on it + * now. Later, this should be replaced by per-vregion lock. + */ + rtnl_lock(); + mlxsw_sp_acl_tcam_vregion_rehash(vregion->mlxsw_sp, vregion); + rtnl_unlock(); + mlxsw_sp_acl_tcam_vregion_rehash_work_schedule(vregion); +} + +static struct mlxsw_sp_acl_tcam_vregion * +mlxsw_sp_acl_tcam_vregion_create(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam *tcam, + struct mlxsw_afk_element_usage *elusage) +{ + const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; + struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl); + struct mlxsw_sp_acl_tcam_vregion *vregion; + int err; + + vregion = kzalloc(sizeof(*vregion), GFP_KERNEL); + if (!vregion) + return ERR_PTR(-ENOMEM); + INIT_LIST_HEAD(&vregion->vchunk_list); + vregion->tcam = tcam; + vregion->mlxsw_sp = mlxsw_sp; + + vregion->key_info = mlxsw_afk_key_info_get(afk, elusage); + if (IS_ERR(vregion->key_info)) { + err = PTR_ERR(vregion->key_info); + goto err_key_info_get; + } + + vregion->region = mlxsw_sp_acl_tcam_region_create(mlxsw_sp, tcam, + vregion, NULL); + if (IS_ERR(vregion->region)) { + err = PTR_ERR(vregion->region); + goto err_region_create; + } + + list_add_tail(&vregion->tlist, &tcam->vregion_list); + + if (ops->region_rehash_hints_get) { + /* Create the delayed work for vregion periodic rehash */ + INIT_DELAYED_WORK(&vregion->rehash_dw, + mlxsw_sp_acl_tcam_vregion_rehash_work); + mlxsw_sp_acl_tcam_vregion_rehash_work_schedule(vregion); + } + + return vregion; + +err_region_create: + mlxsw_afk_key_info_put(vregion->key_info); +err_key_info_get: + kfree(vregion); + return ERR_PTR(err); +} + +static void +mlxsw_sp_acl_tcam_vregion_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_vregion *vregion) +{ + const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; + + if (ops->region_rehash_hints_get) + cancel_delayed_work_sync(&vregion->rehash_dw); + list_del(&vregion->tlist); + if (vregion->region2) + mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, vregion->region2); + mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, vregion->region); + mlxsw_afk_key_info_put(vregion->key_info); + kfree(vregion); +} + +u32 mlxsw_sp_acl_tcam_vregion_rehash_intrvl_get(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam *tcam) +{ + const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; + u32 vregion_rehash_intrvl; + + if (WARN_ON(!ops->region_rehash_hints_get)) + return 0; + vregion_rehash_intrvl = tcam->vregion_rehash_intrvl; + return vregion_rehash_intrvl; +} + +int mlxsw_sp_acl_tcam_vregion_rehash_intrvl_set(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam *tcam, + u32 val) +{ + const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; + struct mlxsw_sp_acl_tcam_vregion *vregion; + + if (val < MLXSW_SP_ACL_TCAM_VREGION_REHASH_INTRVL_MIN && val) + return -EINVAL; + if (WARN_ON(!ops->region_rehash_hints_get)) + return -EOPNOTSUPP; + tcam->vregion_rehash_intrvl = val; + rtnl_lock(); + list_for_each_entry(vregion, &tcam->vregion_list, tlist) { + if (val) + mlxsw_core_schedule_dw(&vregion->rehash_dw, 0); + else + cancel_delayed_work_sync(&vregion->rehash_dw); + } + rtnl_unlock(); + return 0; +} + +static int +mlxsw_sp_acl_tcam_vchunk_assoc(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_group *group, + unsigned int priority, + struct mlxsw_afk_element_usage *elusage, + struct mlxsw_sp_acl_tcam_vchunk *vchunk) +{ + struct mlxsw_sp_acl_tcam_vregion *vregion; + bool vregion_created = false; bool need_split; int err; - region = mlxsw_sp_acl_tcam_group_region_find(group, priority, elusage, - &need_split); - if (region && need_split) { - /* According to priority, the chunk should belong to an - * existing region. However, this chunk needs elements - * that region does not contain. We need to split the existing - * region into two and create a new region for this chunk + vregion = mlxsw_sp_acl_tcam_group_vregion_find(group, priority, elusage, + &need_split); + if (vregion && need_split) { + /* According to priority, the vchunk should belong to an + * existing vregion. However, this vchunk needs elements + * that vregion does not contain. We need to split the existing + * vregion into two and create a new vregion for this vchunk * in between. This is not supported now. */ return -EOPNOTSUPP; } - if (!region) { - struct mlxsw_afk_element_usage region_elusage; + if (!vregion) { + struct mlxsw_afk_element_usage vregion_elusage; mlxsw_sp_acl_tcam_group_use_patterns(group, elusage, - ®ion_elusage); - region = mlxsw_sp_acl_tcam_region_create(mlxsw_sp, group->tcam, - ®ion_elusage); - if (IS_ERR(region)) - return PTR_ERR(region); - region_created = true; + &vregion_elusage); + vregion = mlxsw_sp_acl_tcam_vregion_create(mlxsw_sp, + group->tcam, + &vregion_elusage); + if (IS_ERR(vregion)) + return PTR_ERR(vregion); + vregion_created = true; } - chunk->region = region; - list_add_tail(&chunk->list, ®ion->chunk_list); + vchunk->vregion = vregion; + list_add_tail(&vchunk->list, &vregion->vchunk_list); - if (!region_created) + if (!vregion_created) return 0; - err = mlxsw_sp_acl_tcam_group_region_attach(mlxsw_sp, group, region); + err = mlxsw_sp_acl_tcam_group_vregion_attach(mlxsw_sp, group, vregion); if (err) - goto err_group_region_attach; + goto err_group_vregion_attach; return 0; -err_group_region_attach: - mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, region); +err_group_vregion_attach: + mlxsw_sp_acl_tcam_vregion_destroy(mlxsw_sp, vregion); return err; } static void -mlxsw_sp_acl_tcam_chunk_deassoc(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam_chunk *chunk) +mlxsw_sp_acl_tcam_vchunk_deassoc(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_vchunk *vchunk) { - struct mlxsw_sp_acl_tcam_region *region = chunk->region; + struct mlxsw_sp_acl_tcam_vregion *vregion = vchunk->vregion; - list_del(&chunk->list); - if (list_empty(®ion->chunk_list)) { - mlxsw_sp_acl_tcam_group_region_detach(mlxsw_sp, region); - mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, region); + list_del(&vchunk->list); + if (list_empty(&vregion->vchunk_list)) { + mlxsw_sp_acl_tcam_group_vregion_detach(mlxsw_sp, vregion); + mlxsw_sp_acl_tcam_vregion_destroy(mlxsw_sp, vregion); } } static struct mlxsw_sp_acl_tcam_chunk * mlxsw_sp_acl_tcam_chunk_create(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam_group *group, - unsigned int priority, - struct mlxsw_afk_element_usage *elusage) + struct mlxsw_sp_acl_tcam_vchunk *vchunk, + struct mlxsw_sp_acl_tcam_region *region) { const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; struct mlxsw_sp_acl_tcam_chunk *chunk; + + chunk = kzalloc(sizeof(*chunk) + ops->chunk_priv_size, GFP_KERNEL); + if (!chunk) + return ERR_PTR(-ENOMEM); + chunk->vchunk = vchunk; + chunk->region = region; + + ops->chunk_init(region->priv, chunk->priv, vchunk->priority); + return chunk; +} + +static void +mlxsw_sp_acl_tcam_chunk_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_chunk *chunk) +{ + const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; + + ops->chunk_fini(chunk->priv); + kfree(chunk); +} + +static struct mlxsw_sp_acl_tcam_vchunk * +mlxsw_sp_acl_tcam_vchunk_create(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_group *group, + unsigned int priority, + struct mlxsw_afk_element_usage *elusage) +{ + struct mlxsw_sp_acl_tcam_vchunk *vchunk; int err; if (priority == MLXSW_SP_ACL_TCAM_CATCHALL_PRIO) return ERR_PTR(-EINVAL); - chunk = kzalloc(sizeof(*chunk) + ops->chunk_priv_size, GFP_KERNEL); - if (!chunk) + vchunk = kzalloc(sizeof(*vchunk), GFP_KERNEL); + if (!vchunk) return ERR_PTR(-ENOMEM); - chunk->priority = priority; - chunk->group = group; - chunk->ref_count = 1; + INIT_LIST_HEAD(&vchunk->ventry_list); + vchunk->priority = priority; + vchunk->group = group; + vchunk->ref_count = 1; - err = mlxsw_sp_acl_tcam_chunk_assoc(mlxsw_sp, group, priority, - elusage, chunk); + err = mlxsw_sp_acl_tcam_vchunk_assoc(mlxsw_sp, group, priority, + elusage, vchunk); if (err) - goto err_chunk_assoc; + goto err_vchunk_assoc; - ops->chunk_init(chunk->region->priv, chunk->priv, priority); - - err = rhashtable_insert_fast(&group->chunk_ht, &chunk->ht_node, - mlxsw_sp_acl_tcam_chunk_ht_params); + err = rhashtable_insert_fast(&group->vchunk_ht, &vchunk->ht_node, + mlxsw_sp_acl_tcam_vchunk_ht_params); if (err) goto err_rhashtable_insert; - return chunk; + vchunk->chunk = mlxsw_sp_acl_tcam_chunk_create(mlxsw_sp, vchunk, + vchunk->vregion->region); + if (IS_ERR(vchunk->chunk)) { + err = PTR_ERR(vchunk->chunk); + goto err_chunk_create; + } + + return vchunk; +err_chunk_create: + rhashtable_remove_fast(&group->vchunk_ht, &vchunk->ht_node, + mlxsw_sp_acl_tcam_vchunk_ht_params); err_rhashtable_insert: - ops->chunk_fini(chunk->priv); - mlxsw_sp_acl_tcam_chunk_deassoc(mlxsw_sp, chunk); -err_chunk_assoc: - kfree(chunk); + mlxsw_sp_acl_tcam_vchunk_deassoc(mlxsw_sp, vchunk); +err_vchunk_assoc: + kfree(vchunk); return ERR_PTR(err); } static void -mlxsw_sp_acl_tcam_chunk_destroy(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam_chunk *chunk) +mlxsw_sp_acl_tcam_vchunk_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_vchunk *vchunk) { - const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; - struct mlxsw_sp_acl_tcam_group *group = chunk->group; - - rhashtable_remove_fast(&group->chunk_ht, &chunk->ht_node, - mlxsw_sp_acl_tcam_chunk_ht_params); - ops->chunk_fini(chunk->priv); - mlxsw_sp_acl_tcam_chunk_deassoc(mlxsw_sp, chunk); - kfree(chunk); + struct mlxsw_sp_acl_tcam_group *group = vchunk->group; + + if (vchunk->chunk2) + mlxsw_sp_acl_tcam_chunk_destroy(mlxsw_sp, vchunk->chunk2); + mlxsw_sp_acl_tcam_chunk_destroy(mlxsw_sp, vchunk->chunk); + rhashtable_remove_fast(&group->vchunk_ht, &vchunk->ht_node, + mlxsw_sp_acl_tcam_vchunk_ht_params); + mlxsw_sp_acl_tcam_vchunk_deassoc(mlxsw_sp, vchunk); + kfree(vchunk); } -static struct mlxsw_sp_acl_tcam_chunk * -mlxsw_sp_acl_tcam_chunk_get(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam_group *group, - unsigned int priority, - struct mlxsw_afk_element_usage *elusage) +static struct mlxsw_sp_acl_tcam_vchunk * +mlxsw_sp_acl_tcam_vchunk_get(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_group *group, + unsigned int priority, + struct mlxsw_afk_element_usage *elusage) { - struct mlxsw_sp_acl_tcam_chunk *chunk; + struct mlxsw_sp_acl_tcam_vchunk *vchunk; - chunk = rhashtable_lookup_fast(&group->chunk_ht, &priority, - mlxsw_sp_acl_tcam_chunk_ht_params); - if (chunk) { - if (WARN_ON(!mlxsw_afk_key_info_subset(chunk->region->key_info, + vchunk = rhashtable_lookup_fast(&group->vchunk_ht, &priority, + mlxsw_sp_acl_tcam_vchunk_ht_params); + if (vchunk) { + if (WARN_ON(!mlxsw_afk_key_info_subset(vchunk->vregion->key_info, elusage))) return ERR_PTR(-EINVAL); - chunk->ref_count++; - return chunk; + vchunk->ref_count++; + return vchunk; } - return mlxsw_sp_acl_tcam_chunk_create(mlxsw_sp, group, - priority, elusage); + return mlxsw_sp_acl_tcam_vchunk_create(mlxsw_sp, group, + priority, elusage); } -static void mlxsw_sp_acl_tcam_chunk_put(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam_chunk *chunk) +static void +mlxsw_sp_acl_tcam_vchunk_put(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_vchunk *vchunk) { - if (--chunk->ref_count) + if (--vchunk->ref_count) return; - mlxsw_sp_acl_tcam_chunk_destroy(mlxsw_sp, chunk); + mlxsw_sp_acl_tcam_vchunk_destroy(mlxsw_sp, vchunk); } -static size_t mlxsw_sp_acl_tcam_entry_priv_size(struct mlxsw_sp *mlxsw_sp) -{ - const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; - - return ops->entry_priv_size; -} - -static int mlxsw_sp_acl_tcam_entry_add(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam_group *group, - struct mlxsw_sp_acl_tcam_entry *entry, - struct mlxsw_sp_acl_rule_info *rulei) +static struct mlxsw_sp_acl_tcam_entry * +mlxsw_sp_acl_tcam_entry_create(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_ventry *ventry, + struct mlxsw_sp_acl_tcam_chunk *chunk) { const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; - struct mlxsw_sp_acl_tcam_chunk *chunk; - struct mlxsw_sp_acl_tcam_region *region; + struct mlxsw_sp_acl_tcam_entry *entry; int err; - chunk = mlxsw_sp_acl_tcam_chunk_get(mlxsw_sp, group, rulei->priority, - &rulei->values.elusage); - if (IS_ERR(chunk)) - return PTR_ERR(chunk); - - region = chunk->region; + entry = kzalloc(sizeof(*entry) + ops->entry_priv_size, GFP_KERNEL); + if (!entry) + return ERR_PTR(-ENOMEM); + entry->ventry = ventry; + entry->chunk = chunk; - err = ops->entry_add(mlxsw_sp, region->priv, chunk->priv, - entry->priv, rulei); + err = ops->entry_add(mlxsw_sp, chunk->region->priv, chunk->priv, + entry->priv, ventry->rulei); if (err) goto err_entry_add; - entry->chunk = chunk; - return 0; + return entry; err_entry_add: - mlxsw_sp_acl_tcam_chunk_put(mlxsw_sp, chunk); - return err; + kfree(entry); + return ERR_PTR(err); } -static void mlxsw_sp_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam_entry *entry) +static void mlxsw_sp_acl_tcam_entry_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_entry *entry) { const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; - struct mlxsw_sp_acl_tcam_chunk *chunk = entry->chunk; - struct mlxsw_sp_acl_tcam_region *region = chunk->region; - ops->entry_del(mlxsw_sp, region->priv, chunk->priv, entry->priv); - mlxsw_sp_acl_tcam_chunk_put(mlxsw_sp, chunk); + ops->entry_del(mlxsw_sp, entry->chunk->region->priv, + entry->chunk->priv, entry->priv); + kfree(entry); } static int mlxsw_sp_acl_tcam_entry_action_replace(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_region *region, struct mlxsw_sp_acl_tcam_entry *entry, struct mlxsw_sp_acl_rule_info *rulei) { const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; - struct mlxsw_sp_acl_tcam_chunk *chunk = entry->chunk; - struct mlxsw_sp_acl_tcam_region *region = chunk->region; return ops->entry_action_replace(mlxsw_sp, region->priv, entry->priv, rulei); @@ -798,13 +1005,249 @@ mlxsw_sp_acl_tcam_entry_activity_get(struct mlxsw_sp *mlxsw_sp, bool *activity) { const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; - struct mlxsw_sp_acl_tcam_chunk *chunk = entry->chunk; - struct mlxsw_sp_acl_tcam_region *region = chunk->region; - return ops->entry_activity_get(mlxsw_sp, region->priv, + return ops->entry_activity_get(mlxsw_sp, entry->chunk->region->priv, entry->priv, activity); } +static int mlxsw_sp_acl_tcam_ventry_add(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_group *group, + struct mlxsw_sp_acl_tcam_ventry *ventry, + struct mlxsw_sp_acl_rule_info *rulei) +{ + struct mlxsw_sp_acl_tcam_vchunk *vchunk; + int err; + + vchunk = mlxsw_sp_acl_tcam_vchunk_get(mlxsw_sp, group, rulei->priority, + &rulei->values.elusage); + if (IS_ERR(vchunk)) + return PTR_ERR(vchunk); + + ventry->vchunk = vchunk; + ventry->rulei = rulei; + ventry->entry = mlxsw_sp_acl_tcam_entry_create(mlxsw_sp, ventry, + vchunk->chunk); + if (IS_ERR(ventry->entry)) { + err = PTR_ERR(ventry->entry); + goto err_entry_create; + } + + list_add_tail(&ventry->list, &vchunk->ventry_list); + + return 0; + +err_entry_create: + mlxsw_sp_acl_tcam_vchunk_put(mlxsw_sp, vchunk); + return err; +} + +static void mlxsw_sp_acl_tcam_ventry_del(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_ventry *ventry) +{ + struct mlxsw_sp_acl_tcam_vchunk *vchunk = ventry->vchunk; + + list_del(&ventry->list); + mlxsw_sp_acl_tcam_entry_destroy(mlxsw_sp, ventry->entry); + mlxsw_sp_acl_tcam_vchunk_put(mlxsw_sp, vchunk); +} + +static int +mlxsw_sp_acl_tcam_ventry_action_replace(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_ventry *ventry, + struct mlxsw_sp_acl_rule_info *rulei) +{ + struct mlxsw_sp_acl_tcam_vchunk *vchunk = ventry->vchunk; + + return mlxsw_sp_acl_tcam_entry_action_replace(mlxsw_sp, + vchunk->vregion->region, + ventry->entry, rulei); +} + +static int +mlxsw_sp_acl_tcam_ventry_activity_get(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_ventry *ventry, + bool *activity) +{ + return mlxsw_sp_acl_tcam_entry_activity_get(mlxsw_sp, + ventry->entry, activity); +} + +static int +mlxsw_sp_acl_tcam_ventry_migrate(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_ventry *ventry, + struct mlxsw_sp_acl_tcam_chunk *chunk2) +{ + struct mlxsw_sp_acl_tcam_entry *entry2; + + entry2 = mlxsw_sp_acl_tcam_entry_create(mlxsw_sp, ventry, chunk2); + if (IS_ERR(entry2)) + return PTR_ERR(entry2); + mlxsw_sp_acl_tcam_entry_destroy(mlxsw_sp, ventry->entry); + ventry->entry = entry2; + return 0; +} + +static int +mlxsw_sp_acl_tcam_vchunk_migrate_one(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_vchunk *vchunk, + struct mlxsw_sp_acl_tcam_region *region, + bool this_is_rollback) +{ + struct mlxsw_sp_acl_tcam_ventry *ventry; + struct mlxsw_sp_acl_tcam_chunk *chunk2; + int err; + int err2; + + chunk2 = mlxsw_sp_acl_tcam_chunk_create(mlxsw_sp, vchunk, region); + if (IS_ERR(chunk2)) { + if (this_is_rollback) + vchunk->vregion->failed_rollback = true; + return PTR_ERR(chunk2); + } + vchunk->chunk2 = chunk2; + list_for_each_entry(ventry, &vchunk->ventry_list, list) { + err = mlxsw_sp_acl_tcam_ventry_migrate(mlxsw_sp, ventry, + vchunk->chunk2); + if (err) { + if (this_is_rollback) { + vchunk->vregion->failed_rollback = true; + return err; + } + goto rollback; + } + } + mlxsw_sp_acl_tcam_chunk_destroy(mlxsw_sp, vchunk->chunk); + vchunk->chunk = chunk2; + vchunk->chunk2 = NULL; + return 0; + +rollback: + /* Migrate the entries back to the original chunk. If some entry + * migration fails, there's no good way how to proceed. Set the + * vregion with "failed_rollback" flag. + */ + list_for_each_entry_continue_reverse(ventry, &vchunk->ventry_list, + list) { + err2 = mlxsw_sp_acl_tcam_ventry_migrate(mlxsw_sp, ventry, + vchunk->chunk); + if (err2) { + vchunk->vregion->failed_rollback = true; + goto err_rollback; + } + } + + mlxsw_sp_acl_tcam_chunk_destroy(mlxsw_sp, vchunk->chunk2); + vchunk->chunk2 = NULL; + +err_rollback: + return err; +} + +static int +mlxsw_sp_acl_tcam_vchunk_migrate_all(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_vregion *vregion) +{ + struct mlxsw_sp_acl_tcam_vchunk *vchunk; + int err; + + list_for_each_entry(vchunk, &vregion->vchunk_list, list) { + err = mlxsw_sp_acl_tcam_vchunk_migrate_one(mlxsw_sp, vchunk, + vregion->region2, + false); + if (err) + goto rollback; + } + return 0; + +rollback: + list_for_each_entry_continue_reverse(vchunk, &vregion->vchunk_list, + list) { + mlxsw_sp_acl_tcam_vchunk_migrate_one(mlxsw_sp, vchunk, + vregion->region, true); + } + return err; +} + +static int +mlxsw_sp_acl_tcam_vregion_migrate(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_vregion *vregion, + void *hints_priv) +{ + struct mlxsw_sp_acl_tcam_region *region2, *unused_region; + int err; + + trace_mlxsw_sp_acl_tcam_vregion_migrate(mlxsw_sp, vregion); + + region2 = mlxsw_sp_acl_tcam_region_create(mlxsw_sp, vregion->tcam, + vregion, hints_priv); + if (IS_ERR(region2)) + return PTR_ERR(region2); + + vregion->region2 = region2; + err = mlxsw_sp_acl_tcam_group_region_attach(mlxsw_sp, region2); + if (err) + goto err_group_region_attach; + + err = mlxsw_sp_acl_tcam_vchunk_migrate_all(mlxsw_sp, vregion); + if (!vregion->failed_rollback) { + if (!err) { + /* In case of successful migration, region2 is used and + * the original is unused. + */ + unused_region = vregion->region; + vregion->region = vregion->region2; + } else { + /* In case of failure during migration, the original + * region is still used. + */ + unused_region = vregion->region2; + } + vregion->region2 = NULL; + mlxsw_sp_acl_tcam_group_region_detach(mlxsw_sp, unused_region); + mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, unused_region); + } + return err; + +err_group_region_attach: + vregion->region2 = NULL; + mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, region2); + return err; +} + +static int +mlxsw_sp_acl_tcam_vregion_rehash(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_vregion *vregion) +{ + const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; + void *hints_priv; + int err; + + trace_mlxsw_sp_acl_tcam_vregion_rehash(mlxsw_sp, vregion); + if (vregion->failed_rollback) + return -EBUSY; + + hints_priv = ops->region_rehash_hints_get(vregion->region->priv); + if (IS_ERR(hints_priv)) { + err = PTR_ERR(hints_priv); + if (err != -EAGAIN) + dev_err(mlxsw_sp->bus_info->dev, "Failed get rehash hints\n"); + return err; + } + + err = mlxsw_sp_acl_tcam_vregion_migrate(mlxsw_sp, vregion, hints_priv); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Failed to migrate vregion\n"); + if (vregion->failed_rollback) { + trace_mlxsw_sp_acl_tcam_vregion_rehash_dis(mlxsw_sp, + vregion); + dev_err(mlxsw_sp->bus_info->dev, "Failed to rollback during vregion migration fail\n"); + } + } + + ops->region_rehash_hints_put(hints_priv); + return err; +} + static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv4[] = { MLXSW_AFK_ELEMENT_SRC_SYS_PORT, MLXSW_AFK_ELEMENT_DMAC_32_47, @@ -859,7 +1302,7 @@ struct mlxsw_sp_acl_tcam_flower_ruleset { }; struct mlxsw_sp_acl_tcam_flower_rule { - struct mlxsw_sp_acl_tcam_entry entry; + struct mlxsw_sp_acl_tcam_ventry ventry; }; static int @@ -917,12 +1360,6 @@ mlxsw_sp_acl_tcam_flower_ruleset_group_id(void *ruleset_priv) return mlxsw_sp_acl_tcam_group_id(&ruleset->group); } -static size_t mlxsw_sp_acl_tcam_flower_rule_priv_size(struct mlxsw_sp *mlxsw_sp) -{ - return sizeof(struct mlxsw_sp_acl_tcam_flower_rule) + - mlxsw_sp_acl_tcam_entry_priv_size(mlxsw_sp); -} - static int mlxsw_sp_acl_tcam_flower_rule_add(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv, void *rule_priv, @@ -931,8 +1368,8 @@ mlxsw_sp_acl_tcam_flower_rule_add(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam_flower_ruleset *ruleset = ruleset_priv; struct mlxsw_sp_acl_tcam_flower_rule *rule = rule_priv; - return mlxsw_sp_acl_tcam_entry_add(mlxsw_sp, &ruleset->group, - &rule->entry, rulei); + return mlxsw_sp_acl_tcam_ventry_add(mlxsw_sp, &ruleset->group, + &rule->ventry, rulei); } static void @@ -940,7 +1377,7 @@ mlxsw_sp_acl_tcam_flower_rule_del(struct mlxsw_sp *mlxsw_sp, void *rule_priv) { struct mlxsw_sp_acl_tcam_flower_rule *rule = rule_priv; - mlxsw_sp_acl_tcam_entry_del(mlxsw_sp, &rule->entry); + mlxsw_sp_acl_tcam_ventry_del(mlxsw_sp, &rule->ventry); } static int @@ -957,8 +1394,8 @@ mlxsw_sp_acl_tcam_flower_rule_activity_get(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_acl_tcam_flower_rule *rule = rule_priv; - return mlxsw_sp_acl_tcam_entry_activity_get(mlxsw_sp, &rule->entry, - activity); + return mlxsw_sp_acl_tcam_ventry_activity_get(mlxsw_sp, &rule->ventry, + activity); } static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_flower_ops = { @@ -968,7 +1405,7 @@ static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_flower_ops = { .ruleset_bind = mlxsw_sp_acl_tcam_flower_ruleset_bind, .ruleset_unbind = mlxsw_sp_acl_tcam_flower_ruleset_unbind, .ruleset_group_id = mlxsw_sp_acl_tcam_flower_ruleset_group_id, - .rule_priv_size = mlxsw_sp_acl_tcam_flower_rule_priv_size, + .rule_priv_size = sizeof(struct mlxsw_sp_acl_tcam_flower_rule), .rule_add = mlxsw_sp_acl_tcam_flower_rule_add, .rule_del = mlxsw_sp_acl_tcam_flower_rule_del, .rule_action_replace = mlxsw_sp_acl_tcam_flower_rule_action_replace, @@ -976,12 +1413,12 @@ static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_flower_ops = { }; struct mlxsw_sp_acl_tcam_mr_ruleset { - struct mlxsw_sp_acl_tcam_chunk *chunk; + struct mlxsw_sp_acl_tcam_vchunk *vchunk; struct mlxsw_sp_acl_tcam_group group; }; struct mlxsw_sp_acl_tcam_mr_rule { - struct mlxsw_sp_acl_tcam_entry entry; + struct mlxsw_sp_acl_tcam_ventry ventry; }; static int @@ -1006,10 +1443,11 @@ mlxsw_sp_acl_tcam_mr_ruleset_add(struct mlxsw_sp *mlxsw_sp, * specific ACL Group ID which must exist in HW before multicast router * is initialized. */ - ruleset->chunk = mlxsw_sp_acl_tcam_chunk_get(mlxsw_sp, &ruleset->group, - 1, tmplt_elusage); - if (IS_ERR(ruleset->chunk)) { - err = PTR_ERR(ruleset->chunk); + ruleset->vchunk = mlxsw_sp_acl_tcam_vchunk_get(mlxsw_sp, + &ruleset->group, 1, + tmplt_elusage); + if (IS_ERR(ruleset->vchunk)) { + err = PTR_ERR(ruleset->vchunk); goto err_chunk_get; } @@ -1025,7 +1463,7 @@ mlxsw_sp_acl_tcam_mr_ruleset_del(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv) { struct mlxsw_sp_acl_tcam_mr_ruleset *ruleset = ruleset_priv; - mlxsw_sp_acl_tcam_chunk_put(mlxsw_sp, ruleset->chunk); + mlxsw_sp_acl_tcam_vchunk_put(mlxsw_sp, ruleset->vchunk); mlxsw_sp_acl_tcam_group_del(mlxsw_sp, &ruleset->group); } @@ -1054,12 +1492,6 @@ mlxsw_sp_acl_tcam_mr_ruleset_group_id(void *ruleset_priv) return mlxsw_sp_acl_tcam_group_id(&ruleset->group); } -static size_t mlxsw_sp_acl_tcam_mr_rule_priv_size(struct mlxsw_sp *mlxsw_sp) -{ - return sizeof(struct mlxsw_sp_acl_tcam_mr_rule) + - mlxsw_sp_acl_tcam_entry_priv_size(mlxsw_sp); -} - static int mlxsw_sp_acl_tcam_mr_rule_add(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv, void *rule_priv, @@ -1068,8 +1500,8 @@ mlxsw_sp_acl_tcam_mr_rule_add(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv, struct mlxsw_sp_acl_tcam_mr_ruleset *ruleset = ruleset_priv; struct mlxsw_sp_acl_tcam_mr_rule *rule = rule_priv; - return mlxsw_sp_acl_tcam_entry_add(mlxsw_sp, &ruleset->group, - &rule->entry, rulei); + return mlxsw_sp_acl_tcam_ventry_add(mlxsw_sp, &ruleset->group, + &rule->ventry, rulei); } static void @@ -1077,7 +1509,7 @@ mlxsw_sp_acl_tcam_mr_rule_del(struct mlxsw_sp *mlxsw_sp, void *rule_priv) { struct mlxsw_sp_acl_tcam_mr_rule *rule = rule_priv; - mlxsw_sp_acl_tcam_entry_del(mlxsw_sp, &rule->entry); + mlxsw_sp_acl_tcam_ventry_del(mlxsw_sp, &rule->ventry); } static int @@ -1087,8 +1519,8 @@ mlxsw_sp_acl_tcam_mr_rule_action_replace(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_acl_tcam_mr_rule *rule = rule_priv; - return mlxsw_sp_acl_tcam_entry_action_replace(mlxsw_sp, &rule->entry, - rulei); + return mlxsw_sp_acl_tcam_ventry_action_replace(mlxsw_sp, &rule->ventry, + rulei); } static int @@ -1097,8 +1529,8 @@ mlxsw_sp_acl_tcam_mr_rule_activity_get(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_acl_tcam_mr_rule *rule = rule_priv; - return mlxsw_sp_acl_tcam_entry_activity_get(mlxsw_sp, &rule->entry, - activity); + return mlxsw_sp_acl_tcam_ventry_activity_get(mlxsw_sp, &rule->ventry, + activity); } static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_mr_ops = { @@ -1108,7 +1540,7 @@ static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_mr_ops = { .ruleset_bind = mlxsw_sp_acl_tcam_mr_ruleset_bind, .ruleset_unbind = mlxsw_sp_acl_tcam_mr_ruleset_unbind, .ruleset_group_id = mlxsw_sp_acl_tcam_mr_ruleset_group_id, - .rule_priv_size = mlxsw_sp_acl_tcam_mr_rule_priv_size, + .rule_priv_size = sizeof(struct mlxsw_sp_acl_tcam_mr_rule), .rule_add = mlxsw_sp_acl_tcam_mr_rule_add, .rule_del = mlxsw_sp_acl_tcam_mr_rule_del, .rule_action_replace = mlxsw_sp_acl_tcam_mr_rule_action_replace, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h index 0858d5b06353..96bd42a9fbc3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h @@ -17,6 +17,8 @@ struct mlxsw_sp_acl_tcam { unsigned long *used_groups; /* bit array */ unsigned int max_groups; unsigned int max_group_size; + struct list_head vregion_list; + u32 vregion_rehash_intrvl; /* ms */ unsigned long priv[0]; /* priv has to be always the last item */ }; @@ -26,6 +28,11 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam *tcam); void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam *tcam); +u32 mlxsw_sp_acl_tcam_vregion_rehash_intrvl_get(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam *tcam); +int mlxsw_sp_acl_tcam_vregion_rehash_intrvl_set(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam *tcam, + u32 val); int mlxsw_sp_acl_tcam_priority_get(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_rule_info *rulei, u32 *priority, bool fillup_priority); @@ -43,7 +50,7 @@ struct mlxsw_sp_acl_profile_ops { struct mlxsw_sp_port *mlxsw_sp_port, bool ingress); u16 (*ruleset_group_id)(void *ruleset_priv); - size_t (*rule_priv_size)(struct mlxsw_sp *mlxsw_sp); + size_t rule_priv_size; int (*rule_add)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv, void *rule_priv, struct mlxsw_sp_acl_rule_info *rulei); @@ -67,11 +74,10 @@ mlxsw_sp_acl_tcam_profile_ops(struct mlxsw_sp *mlxsw_sp, (MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN * BITS_PER_BYTE) struct mlxsw_sp_acl_tcam_group; +struct mlxsw_sp_acl_tcam_vregion; struct mlxsw_sp_acl_tcam_region { - struct list_head list; /* Member of a TCAM group */ - struct list_head chunk_list; /* List of chunks under this region */ - struct mlxsw_sp_acl_tcam_group *group; + struct mlxsw_sp_acl_tcam_vregion *vregion; enum mlxsw_reg_ptar_key_type key_type; u16 id; /* ACL ID and region ID - they are same */ char tcam_region_info[MLXSW_REG_PXXX_TCAM_REGION_INFO_LEN]; @@ -207,6 +213,7 @@ mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_atcam *atcam, struct mlxsw_sp_acl_atcam_region *aregion, struct mlxsw_sp_acl_tcam_region *region, + void *hints_priv, const struct mlxsw_sp_acl_ctcam_region_ops *ops); void mlxsw_sp_acl_atcam_region_fini(struct mlxsw_sp_acl_atcam_region *aregion); void mlxsw_sp_acl_atcam_chunk_init(struct mlxsw_sp_acl_atcam_region *aregion, @@ -230,6 +237,9 @@ int mlxsw_sp_acl_atcam_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_atcam *atcam); void mlxsw_sp_acl_atcam_fini(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_atcam *atcam); +void * +mlxsw_sp_acl_atcam_rehash_hints_get(struct mlxsw_sp_acl_atcam_region *aregion); +void mlxsw_sp_acl_atcam_rehash_hints_put(void *hints_priv); struct mlxsw_sp_acl_erp_delta; @@ -260,7 +270,11 @@ void mlxsw_sp_acl_erp_bf_remove(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_atcam_region *aregion, struct mlxsw_sp_acl_erp_mask *erp_mask, struct mlxsw_sp_acl_atcam_entry *aentry); -int mlxsw_sp_acl_erp_region_init(struct mlxsw_sp_acl_atcam_region *aregion); +void * +mlxsw_sp_acl_erp_rehash_hints_get(struct mlxsw_sp_acl_atcam_region *aregion); +void mlxsw_sp_acl_erp_rehash_hints_put(void *hints_priv); +int mlxsw_sp_acl_erp_region_init(struct mlxsw_sp_acl_atcam_region *aregion, + void *hints_priv); void mlxsw_sp_acl_erp_region_fini(struct mlxsw_sp_acl_atcam_region *aregion); int mlxsw_sp_acl_erps_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_atcam *atcam); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index 80066f437a65..9a79b5e11597 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -37,13 +37,19 @@ struct mlxsw_sp_sb_pm { struct mlxsw_cp_sb_occ occ; }; +struct mlxsw_sp_sb_mm { + u32 min_buff; + u32 max_buff; + u16 pool_index; +}; + struct mlxsw_sp_sb_pool_des { enum mlxsw_reg_sbxx_dir dir; u8 pool; }; /* Order ingress pools before egress pools. */ -static const struct mlxsw_sp_sb_pool_des mlxsw_sp_sb_pool_dess[] = { +static const struct mlxsw_sp_sb_pool_des mlxsw_sp1_sb_pool_dess[] = { {MLXSW_REG_SBXX_DIR_INGRESS, 0}, {MLXSW_REG_SBXX_DIR_INGRESS, 1}, {MLXSW_REG_SBXX_DIR_INGRESS, 2}, @@ -55,7 +61,16 @@ static const struct mlxsw_sp_sb_pool_des mlxsw_sp_sb_pool_dess[] = { {MLXSW_REG_SBXX_DIR_EGRESS, 15}, }; -#define MLXSW_SP_SB_POOL_DESS_LEN ARRAY_SIZE(mlxsw_sp_sb_pool_dess) +static const struct mlxsw_sp_sb_pool_des mlxsw_sp2_sb_pool_dess[] = { + {MLXSW_REG_SBXX_DIR_INGRESS, 0}, + {MLXSW_REG_SBXX_DIR_INGRESS, 1}, + {MLXSW_REG_SBXX_DIR_INGRESS, 2}, + {MLXSW_REG_SBXX_DIR_INGRESS, 3}, + {MLXSW_REG_SBXX_DIR_EGRESS, 0}, + {MLXSW_REG_SBXX_DIR_EGRESS, 1}, + {MLXSW_REG_SBXX_DIR_EGRESS, 2}, + {MLXSW_REG_SBXX_DIR_EGRESS, 3}, +}; #define MLXSW_SP_SB_ING_TC_COUNT 8 #define MLXSW_SP_SB_EG_TC_COUNT 16 @@ -63,16 +78,32 @@ static const struct mlxsw_sp_sb_pool_des mlxsw_sp_sb_pool_dess[] = { struct mlxsw_sp_sb_port { struct mlxsw_sp_sb_cm ing_cms[MLXSW_SP_SB_ING_TC_COUNT]; struct mlxsw_sp_sb_cm eg_cms[MLXSW_SP_SB_EG_TC_COUNT]; - struct mlxsw_sp_sb_pm pms[MLXSW_SP_SB_POOL_DESS_LEN]; + struct mlxsw_sp_sb_pm *pms; }; struct mlxsw_sp_sb { - struct mlxsw_sp_sb_pr prs[MLXSW_SP_SB_POOL_DESS_LEN]; + struct mlxsw_sp_sb_pr *prs; struct mlxsw_sp_sb_port *ports; u32 cell_size; + u32 max_headroom_cells; u64 sb_size; }; +struct mlxsw_sp_sb_vals { + unsigned int pool_count; + const struct mlxsw_sp_sb_pool_des *pool_dess; + const struct mlxsw_sp_sb_pm *pms; + const struct mlxsw_sp_sb_pr *prs; + const struct mlxsw_sp_sb_mm *mms; + const struct mlxsw_sp_sb_cm *cms_ingress; + const struct mlxsw_sp_sb_cm *cms_egress; + const struct mlxsw_sp_sb_cm *cms_cpu; + unsigned int mms_count; + unsigned int cms_ingress_count; + unsigned int cms_egress_count; + unsigned int cms_cpu_count; +}; + u32 mlxsw_sp_cells_bytes(const struct mlxsw_sp *mlxsw_sp, u32 cells) { return mlxsw_sp->sb->cell_size * cells; @@ -83,6 +114,11 @@ u32 mlxsw_sp_bytes_cells(const struct mlxsw_sp *mlxsw_sp, u32 bytes) return DIV_ROUND_UP(bytes, mlxsw_sp->sb->cell_size); } +u32 mlxsw_sp_sb_max_headroom_cells(const struct mlxsw_sp *mlxsw_sp) +{ + return mlxsw_sp->sb->max_headroom_cells; +} + static struct mlxsw_sp_sb_pr *mlxsw_sp_sb_pr_get(struct mlxsw_sp *mlxsw_sp, u16 pool_index) { @@ -121,7 +157,7 @@ static int mlxsw_sp_sb_pr_write(struct mlxsw_sp *mlxsw_sp, u16 pool_index, u32 size, bool infi_size) { const struct mlxsw_sp_sb_pool_des *des = - &mlxsw_sp_sb_pool_dess[pool_index]; + &mlxsw_sp->sb_vals->pool_dess[pool_index]; char sbpr_pl[MLXSW_REG_SBPR_LEN]; struct mlxsw_sp_sb_pr *pr; int err; @@ -145,7 +181,7 @@ static int mlxsw_sp_sb_cm_write(struct mlxsw_sp *mlxsw_sp, u8 local_port, bool infi_max, u16 pool_index) { const struct mlxsw_sp_sb_pool_des *des = - &mlxsw_sp_sb_pool_dess[pool_index]; + &mlxsw_sp->sb_vals->pool_dess[pool_index]; char sbcm_pl[MLXSW_REG_SBCM_LEN]; struct mlxsw_sp_sb_cm *cm; int err; @@ -174,7 +210,7 @@ static int mlxsw_sp_sb_pm_write(struct mlxsw_sp *mlxsw_sp, u8 local_port, u16 pool_index, u32 min_buff, u32 max_buff) { const struct mlxsw_sp_sb_pool_des *des = - &mlxsw_sp_sb_pool_dess[pool_index]; + &mlxsw_sp->sb_vals->pool_dess[pool_index]; char sbpm_pl[MLXSW_REG_SBPM_LEN]; struct mlxsw_sp_sb_pm *pm; int err; @@ -195,7 +231,7 @@ static int mlxsw_sp_sb_pm_occ_clear(struct mlxsw_sp *mlxsw_sp, u8 local_port, u16 pool_index, struct list_head *bulk_list) { const struct mlxsw_sp_sb_pool_des *des = - &mlxsw_sp_sb_pool_dess[pool_index]; + &mlxsw_sp->sb_vals->pool_dess[pool_index]; char sbpm_pl[MLXSW_REG_SBPM_LEN]; mlxsw_reg_sbpm_pack(sbpm_pl, local_port, des->pool, des->dir, @@ -217,7 +253,7 @@ static int mlxsw_sp_sb_pm_occ_query(struct mlxsw_sp *mlxsw_sp, u8 local_port, u16 pool_index, struct list_head *bulk_list) { const struct mlxsw_sp_sb_pool_des *des = - &mlxsw_sp_sb_pool_dess[pool_index]; + &mlxsw_sp->sb_vals->pool_dess[pool_index]; char sbpm_pl[MLXSW_REG_SBPM_LEN]; struct mlxsw_sp_sb_pm *pm; @@ -230,24 +266,24 @@ static int mlxsw_sp_sb_pm_occ_query(struct mlxsw_sp *mlxsw_sp, u8 local_port, (unsigned long) pm); } -static const u16 mlxsw_sp_pbs[] = { - [0] = 2 * ETH_FRAME_LEN, - [9] = 2 * MLXSW_PORT_MAX_MTU, -}; - -#define MLXSW_SP_PBS_LEN ARRAY_SIZE(mlxsw_sp_pbs) +/* 1/4 of a headroom necessary for 100Gbps port and 100m cable. */ +#define MLXSW_SP_PB_HEADROOM 25632 #define MLXSW_SP_PB_UNUSED 8 static int mlxsw_sp_port_pb_init(struct mlxsw_sp_port *mlxsw_sp_port) { + const u32 pbs[] = { + [0] = MLXSW_SP_PB_HEADROOM * mlxsw_sp_port->mapping.width, + [9] = 2 * MLXSW_PORT_MAX_MTU, + }; struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; char pbmc_pl[MLXSW_REG_PBMC_LEN]; int i; mlxsw_reg_pbmc_pack(pbmc_pl, mlxsw_sp_port->local_port, 0xffff, 0xffff / 2); - for (i = 0; i < MLXSW_SP_PBS_LEN; i++) { - u16 size = mlxsw_sp_bytes_cells(mlxsw_sp, mlxsw_sp_pbs[i]); + for (i = 0; i < ARRAY_SIZE(pbs); i++) { + u16 size = mlxsw_sp_bytes_cells(mlxsw_sp, pbs[i]); if (i == MLXSW_SP_PB_UNUSED) continue; @@ -280,50 +316,119 @@ static int mlxsw_sp_port_headroom_init(struct mlxsw_sp_port *mlxsw_sp_port) return mlxsw_sp_port_pb_prio_init(mlxsw_sp_port); } +static int mlxsw_sp_sb_port_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_sb_port *sb_port) +{ + struct mlxsw_sp_sb_pm *pms; + + pms = kcalloc(mlxsw_sp->sb_vals->pool_count, sizeof(*pms), + GFP_KERNEL); + if (!pms) + return -ENOMEM; + sb_port->pms = pms; + return 0; +} + +static void mlxsw_sp_sb_port_fini(struct mlxsw_sp_sb_port *sb_port) +{ + kfree(sb_port->pms); +} + static int mlxsw_sp_sb_ports_init(struct mlxsw_sp *mlxsw_sp) { unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core); + struct mlxsw_sp_sb_pr *prs; + int i; + int err; mlxsw_sp->sb->ports = kcalloc(max_ports, sizeof(struct mlxsw_sp_sb_port), GFP_KERNEL); if (!mlxsw_sp->sb->ports) return -ENOMEM; + + prs = kcalloc(mlxsw_sp->sb_vals->pool_count, sizeof(*prs), + GFP_KERNEL); + if (!prs) { + err = -ENOMEM; + goto err_alloc_prs; + } + mlxsw_sp->sb->prs = prs; + + for (i = 0; i < max_ports; i++) { + err = mlxsw_sp_sb_port_init(mlxsw_sp, &mlxsw_sp->sb->ports[i]); + if (err) + goto err_sb_port_init; + } + return 0; + +err_sb_port_init: + for (i--; i >= 0; i--) + mlxsw_sp_sb_port_fini(&mlxsw_sp->sb->ports[i]); + kfree(mlxsw_sp->sb->prs); +err_alloc_prs: + kfree(mlxsw_sp->sb->ports); + return err; } static void mlxsw_sp_sb_ports_fini(struct mlxsw_sp *mlxsw_sp) { + int max_ports = mlxsw_core_max_ports(mlxsw_sp->core); + int i; + + for (i = max_ports - 1; i >= 0; i--) + mlxsw_sp_sb_port_fini(&mlxsw_sp->sb->ports[i]); + kfree(mlxsw_sp->sb->prs); kfree(mlxsw_sp->sb->ports); } -#define MLXSW_SP_SB_PR_INGRESS_SIZE 12440000 -#define MLXSW_SP_SB_PR_INGRESS_MNG_SIZE (200 * 1000) -#define MLXSW_SP_SB_PR_EGRESS_SIZE 13232000 - #define MLXSW_SP_SB_PR(_mode, _size) \ { \ .mode = _mode, \ .size = _size, \ } -static const struct mlxsw_sp_sb_pr mlxsw_sp_sb_prs[] = { +#define MLXSW_SP1_SB_PR_INGRESS_SIZE 12440000 +#define MLXSW_SP1_SB_PR_INGRESS_MNG_SIZE (200 * 1000) +#define MLXSW_SP1_SB_PR_EGRESS_SIZE 13232000 + +static const struct mlxsw_sp_sb_pr mlxsw_sp1_sb_prs[] = { /* Ingress pools. */ MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, - MLXSW_SP_SB_PR_INGRESS_SIZE), + MLXSW_SP1_SB_PR_INGRESS_SIZE), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, - MLXSW_SP_SB_PR_INGRESS_MNG_SIZE), + MLXSW_SP1_SB_PR_INGRESS_MNG_SIZE), /* Egress pools. */ - MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, MLXSW_SP_SB_PR_EGRESS_SIZE), + MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, + MLXSW_SP1_SB_PR_EGRESS_SIZE), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, MLXSW_SP_SB_INFI), }; -#define MLXSW_SP_SB_PRS_LEN ARRAY_SIZE(mlxsw_sp_sb_prs) +#define MLXSW_SP2_SB_PR_INGRESS_SIZE 40960000 +#define MLXSW_SP2_SB_PR_INGRESS_MNG_SIZE (200 * 1000) +#define MLXSW_SP2_SB_PR_EGRESS_SIZE 40960000 + +static const struct mlxsw_sp_sb_pr mlxsw_sp2_sb_prs[] = { + /* Ingress pools. */ + MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, + MLXSW_SP2_SB_PR_INGRESS_SIZE), + MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0), + MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0), + MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, + MLXSW_SP2_SB_PR_INGRESS_MNG_SIZE), + /* Egress pools. */ + MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, + MLXSW_SP2_SB_PR_EGRESS_SIZE), + MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0), + MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0), + MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0), +}; static int mlxsw_sp_sb_prs_init(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_sb_pr *prs, @@ -357,7 +462,7 @@ static int mlxsw_sp_sb_prs_init(struct mlxsw_sp *mlxsw_sp, .pool_index = _pool, \ } -static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_ingress[] = { +static const struct mlxsw_sp_sb_cm mlxsw_sp1_sb_cms_ingress[] = { MLXSW_SP_SB_CM(10000, 8, 0), MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0), MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0), @@ -370,9 +475,20 @@ static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_ingress[] = { MLXSW_SP_SB_CM(20000, 1, 3), }; -#define MLXSW_SP_SB_CMS_INGRESS_LEN ARRAY_SIZE(mlxsw_sp_sb_cms_ingress) +static const struct mlxsw_sp_sb_cm mlxsw_sp2_sb_cms_ingress[] = { + MLXSW_SP_SB_CM(0, 7, 0), + MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0), + MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0), + MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0), + MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0), + MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0), + MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0), + MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0), + MLXSW_SP_SB_CM(0, 0, 0), /* dummy, this PG does not exist */ + MLXSW_SP_SB_CM(20000, 1, 3), +}; -static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_egress[] = { +static const struct mlxsw_sp_sb_cm mlxsw_sp1_sb_cms_egress[] = { MLXSW_SP_SB_CM(1500, 9, 4), MLXSW_SP_SB_CM(1500, 9, 4), MLXSW_SP_SB_CM(1500, 9, 4), @@ -392,7 +508,25 @@ static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_egress[] = { MLXSW_SP_SB_CM(1, 0xff, 4), }; -#define MLXSW_SP_SB_CMS_EGRESS_LEN ARRAY_SIZE(mlxsw_sp_sb_cms_egress) +static const struct mlxsw_sp_sb_cm mlxsw_sp2_sb_cms_egress[] = { + MLXSW_SP_SB_CM(0, 7, 4), + MLXSW_SP_SB_CM(0, 7, 4), + MLXSW_SP_SB_CM(0, 7, 4), + MLXSW_SP_SB_CM(0, 7, 4), + MLXSW_SP_SB_CM(0, 7, 4), + MLXSW_SP_SB_CM(0, 7, 4), + MLXSW_SP_SB_CM(0, 7, 4), + MLXSW_SP_SB_CM(0, 7, 4), + MLXSW_SP_SB_CM(0, 7, 4), + MLXSW_SP_SB_CM(0, 7, 4), + MLXSW_SP_SB_CM(0, 7, 4), + MLXSW_SP_SB_CM(0, 7, 4), + MLXSW_SP_SB_CM(0, 7, 4), + MLXSW_SP_SB_CM(0, 7, 4), + MLXSW_SP_SB_CM(0, 7, 4), + MLXSW_SP_SB_CM(0, 7, 4), + MLXSW_SP_SB_CM(1, 0xff, 4), +}; #define MLXSW_SP_CPU_PORT_SB_CM MLXSW_SP_SB_CM(0, 0, 4) @@ -431,9 +565,6 @@ static const struct mlxsw_sp_sb_cm mlxsw_sp_cpu_port_sb_cms[] = { MLXSW_SP_CPU_PORT_SB_CM, }; -#define MLXSW_SP_CPU_PORT_SB_MCS_LEN \ - ARRAY_SIZE(mlxsw_sp_cpu_port_sb_cms) - static bool mlxsw_sp_sb_pool_is_static(struct mlxsw_sp *mlxsw_sp, u16 pool_index) { @@ -447,6 +578,7 @@ static int __mlxsw_sp_sb_cms_init(struct mlxsw_sp *mlxsw_sp, u8 local_port, const struct mlxsw_sp_sb_cm *cms, size_t cms_len) { + const struct mlxsw_sp_sb_vals *sb_vals = mlxsw_sp->sb_vals; int i; int err; @@ -458,7 +590,7 @@ static int __mlxsw_sp_sb_cms_init(struct mlxsw_sp *mlxsw_sp, u8 local_port, if (i == 8 && dir == MLXSW_REG_SBXX_DIR_INGRESS) continue; /* PG number 8 does not exist, skip it */ cm = &cms[i]; - if (WARN_ON(mlxsw_sp_sb_pool_dess[cm->pool_index].dir != dir)) + if (WARN_ON(sb_vals->pool_dess[cm->pool_index].dir != dir)) continue; min_buff = mlxsw_sp_bytes_cells(mlxsw_sp, cm->min_buff); @@ -484,27 +616,28 @@ static int __mlxsw_sp_sb_cms_init(struct mlxsw_sp *mlxsw_sp, u8 local_port, static int mlxsw_sp_port_sb_cms_init(struct mlxsw_sp_port *mlxsw_sp_port) { + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; int err; - err = __mlxsw_sp_sb_cms_init(mlxsw_sp_port->mlxsw_sp, + err = __mlxsw_sp_sb_cms_init(mlxsw_sp, mlxsw_sp_port->local_port, MLXSW_REG_SBXX_DIR_INGRESS, - mlxsw_sp_sb_cms_ingress, - MLXSW_SP_SB_CMS_INGRESS_LEN); + mlxsw_sp->sb_vals->cms_ingress, + mlxsw_sp->sb_vals->cms_ingress_count); if (err) return err; return __mlxsw_sp_sb_cms_init(mlxsw_sp_port->mlxsw_sp, mlxsw_sp_port->local_port, MLXSW_REG_SBXX_DIR_EGRESS, - mlxsw_sp_sb_cms_egress, - MLXSW_SP_SB_CMS_EGRESS_LEN); + mlxsw_sp->sb_vals->cms_egress, + mlxsw_sp->sb_vals->cms_egress_count); } static int mlxsw_sp_cpu_port_sb_cms_init(struct mlxsw_sp *mlxsw_sp) { return __mlxsw_sp_sb_cms_init(mlxsw_sp, 0, MLXSW_REG_SBXX_DIR_EGRESS, - mlxsw_sp_cpu_port_sb_cms, - MLXSW_SP_CPU_PORT_SB_MCS_LEN); + mlxsw_sp->sb_vals->cms_cpu, + mlxsw_sp->sb_vals->cms_cpu_count); } #define MLXSW_SP_SB_PM(_min_buff, _max_buff) \ @@ -513,7 +646,7 @@ static int mlxsw_sp_cpu_port_sb_cms_init(struct mlxsw_sp *mlxsw_sp) .max_buff = _max_buff, \ } -static const struct mlxsw_sp_sb_pm mlxsw_sp_sb_pms[] = { +static const struct mlxsw_sp_sb_pm mlxsw_sp1_sb_pms[] = { /* Ingress pools. */ MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MAX), MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN), @@ -527,7 +660,18 @@ static const struct mlxsw_sp_sb_pm mlxsw_sp_sb_pms[] = { MLXSW_SP_SB_PM(10000, 90000), }; -#define MLXSW_SP_SB_PMS_LEN ARRAY_SIZE(mlxsw_sp_sb_pms) +static const struct mlxsw_sp_sb_pm mlxsw_sp2_sb_pms[] = { + /* Ingress pools. */ + MLXSW_SP_SB_PM(0, 7), + MLXSW_SP_SB_PM(0, 0), + MLXSW_SP_SB_PM(0, 0), + MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MAX), + /* Egress pools. */ + MLXSW_SP_SB_PM(0, 7), + MLXSW_SP_SB_PM(0, 0), + MLXSW_SP_SB_PM(0, 0), + MLXSW_SP_SB_PM(0, 0), +}; static int mlxsw_sp_port_sb_pms_init(struct mlxsw_sp_port *mlxsw_sp_port) { @@ -535,8 +679,8 @@ static int mlxsw_sp_port_sb_pms_init(struct mlxsw_sp_port *mlxsw_sp_port) int i; int err; - for (i = 0; i < MLXSW_SP_SB_PMS_LEN; i++) { - const struct mlxsw_sp_sb_pm *pm = &mlxsw_sp_sb_pms[i]; + for (i = 0; i < mlxsw_sp->sb_vals->pool_count; i++) { + const struct mlxsw_sp_sb_pm *pm = &mlxsw_sp->sb_vals->pms[i]; u32 max_buff; u32 min_buff; @@ -552,12 +696,6 @@ static int mlxsw_sp_port_sb_pms_init(struct mlxsw_sp_port *mlxsw_sp_port) return 0; } -struct mlxsw_sp_sb_mm { - u32 min_buff; - u32 max_buff; - u16 pool_index; -}; - #define MLXSW_SP_SB_MM(_min_buff, _max_buff, _pool) \ { \ .min_buff = _min_buff, \ @@ -583,21 +721,19 @@ static const struct mlxsw_sp_sb_mm mlxsw_sp_sb_mms[] = { MLXSW_SP_SB_MM(0, 6, 4), }; -#define MLXSW_SP_SB_MMS_LEN ARRAY_SIZE(mlxsw_sp_sb_mms) - static int mlxsw_sp_sb_mms_init(struct mlxsw_sp *mlxsw_sp) { char sbmm_pl[MLXSW_REG_SBMM_LEN]; int i; int err; - for (i = 0; i < MLXSW_SP_SB_MMS_LEN; i++) { + for (i = 0; i < mlxsw_sp->sb_vals->mms_count; i++) { const struct mlxsw_sp_sb_pool_des *des; const struct mlxsw_sp_sb_mm *mc; u32 min_buff; - mc = &mlxsw_sp_sb_mms[i]; - des = &mlxsw_sp_sb_pool_dess[mc->pool_index]; + mc = &mlxsw_sp->sb_vals->mms[i]; + des = &mlxsw_sp->sb_vals->pool_dess[mc->pool_index]; /* All pools used by sb_mm's are initialized using dynamic * thresholds, therefore 'max_buff' isn't specified in cells. */ @@ -611,22 +747,55 @@ static int mlxsw_sp_sb_mms_init(struct mlxsw_sp *mlxsw_sp) return 0; } -static void mlxsw_sp_pool_count(u16 *p_ingress_len, u16 *p_egress_len) +static void mlxsw_sp_pool_count(struct mlxsw_sp *mlxsw_sp, + u16 *p_ingress_len, u16 *p_egress_len) { int i; - for (i = 0; i < MLXSW_SP_SB_POOL_DESS_LEN; ++i) - if (mlxsw_sp_sb_pool_dess[i].dir == MLXSW_REG_SBXX_DIR_EGRESS) + for (i = 0; i < mlxsw_sp->sb_vals->pool_count; ++i) + if (mlxsw_sp->sb_vals->pool_dess[i].dir == + MLXSW_REG_SBXX_DIR_EGRESS) goto out; WARN(1, "No egress pools\n"); out: *p_ingress_len = i; - *p_egress_len = MLXSW_SP_SB_POOL_DESS_LEN - i; + *p_egress_len = mlxsw_sp->sb_vals->pool_count - i; } +const struct mlxsw_sp_sb_vals mlxsw_sp1_sb_vals = { + .pool_count = ARRAY_SIZE(mlxsw_sp1_sb_pool_dess), + .pool_dess = mlxsw_sp1_sb_pool_dess, + .pms = mlxsw_sp1_sb_pms, + .prs = mlxsw_sp1_sb_prs, + .mms = mlxsw_sp_sb_mms, + .cms_ingress = mlxsw_sp1_sb_cms_ingress, + .cms_egress = mlxsw_sp1_sb_cms_egress, + .cms_cpu = mlxsw_sp_cpu_port_sb_cms, + .mms_count = ARRAY_SIZE(mlxsw_sp_sb_mms), + .cms_ingress_count = ARRAY_SIZE(mlxsw_sp1_sb_cms_ingress), + .cms_egress_count = ARRAY_SIZE(mlxsw_sp1_sb_cms_egress), + .cms_cpu_count = ARRAY_SIZE(mlxsw_sp_cpu_port_sb_cms), +}; + +const struct mlxsw_sp_sb_vals mlxsw_sp2_sb_vals = { + .pool_count = ARRAY_SIZE(mlxsw_sp2_sb_pool_dess), + .pool_dess = mlxsw_sp2_sb_pool_dess, + .pms = mlxsw_sp2_sb_pms, + .prs = mlxsw_sp2_sb_prs, + .mms = mlxsw_sp_sb_mms, + .cms_ingress = mlxsw_sp2_sb_cms_ingress, + .cms_egress = mlxsw_sp2_sb_cms_egress, + .cms_cpu = mlxsw_sp_cpu_port_sb_cms, + .mms_count = ARRAY_SIZE(mlxsw_sp_sb_mms), + .cms_ingress_count = ARRAY_SIZE(mlxsw_sp2_sb_cms_ingress), + .cms_egress_count = ARRAY_SIZE(mlxsw_sp2_sb_cms_egress), + .cms_cpu_count = ARRAY_SIZE(mlxsw_sp_cpu_port_sb_cms), +}; + int mlxsw_sp_buffers_init(struct mlxsw_sp *mlxsw_sp) { + u32 max_headroom_size; u16 ing_pool_count; u16 eg_pool_count; int err; @@ -637,18 +806,26 @@ int mlxsw_sp_buffers_init(struct mlxsw_sp *mlxsw_sp) if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_BUFFER_SIZE)) return -EIO; + if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_HEADROOM_SIZE)) + return -EIO; + mlxsw_sp->sb = kzalloc(sizeof(*mlxsw_sp->sb), GFP_KERNEL); if (!mlxsw_sp->sb) return -ENOMEM; mlxsw_sp->sb->cell_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, CELL_SIZE); mlxsw_sp->sb->sb_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_BUFFER_SIZE); + max_headroom_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, + MAX_HEADROOM_SIZE); + /* Round down, because this limit must not be overstepped. */ + mlxsw_sp->sb->max_headroom_cells = max_headroom_size / + mlxsw_sp->sb->cell_size; err = mlxsw_sp_sb_ports_init(mlxsw_sp); if (err) goto err_sb_ports_init; - err = mlxsw_sp_sb_prs_init(mlxsw_sp, mlxsw_sp_sb_prs, - MLXSW_SP_SB_PRS_LEN); + err = mlxsw_sp_sb_prs_init(mlxsw_sp, mlxsw_sp->sb_vals->prs, + mlxsw_sp->sb_vals->pool_count); if (err) goto err_sb_prs_init; err = mlxsw_sp_cpu_port_sb_cms_init(mlxsw_sp); @@ -657,7 +834,7 @@ int mlxsw_sp_buffers_init(struct mlxsw_sp *mlxsw_sp) err = mlxsw_sp_sb_mms_init(mlxsw_sp); if (err) goto err_sb_mms_init; - mlxsw_sp_pool_count(&ing_pool_count, &eg_pool_count); + mlxsw_sp_pool_count(mlxsw_sp, &ing_pool_count, &eg_pool_count); err = devlink_sb_register(priv_to_devlink(mlxsw_sp->core), 0, mlxsw_sp->sb->sb_size, ing_pool_count, @@ -705,10 +882,11 @@ int mlxsw_sp_sb_pool_get(struct mlxsw_core *mlxsw_core, unsigned int sb_index, u16 pool_index, struct devlink_sb_pool_info *pool_info) { - enum mlxsw_reg_sbxx_dir dir = mlxsw_sp_sb_pool_dess[pool_index].dir; struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); + enum mlxsw_reg_sbxx_dir dir; struct mlxsw_sp_sb_pr *pr; + dir = mlxsw_sp->sb_vals->pool_dess[pool_index].dir; pr = mlxsw_sp_sb_pr_get(mlxsw_sp, pool_index); pool_info->pool_type = (enum devlink_sb_pool_type) dir; pool_info->size = mlxsw_sp_cells_bytes(mlxsw_sp, pr->size); @@ -834,7 +1012,7 @@ int mlxsw_sp_sb_tc_pool_bind_set(struct mlxsw_core_port *mlxsw_core_port, u32 max_buff; int err; - if (dir != mlxsw_sp_sb_pool_dess[pool_index].dir) + if (dir != mlxsw_sp->sb_vals->pool_dess[pool_index].dir) return -EINVAL; err = mlxsw_sp_sb_threshold_in(mlxsw_sp, pool_index, @@ -932,7 +1110,7 @@ next_batch: continue; mlxsw_reg_sbsr_ingress_port_mask_set(sbsr_pl, local_port, 1); mlxsw_reg_sbsr_egress_port_mask_set(sbsr_pl, local_port, 1); - for (i = 0; i < MLXSW_SP_SB_POOL_DESS_LEN; i++) { + for (i = 0; i < mlxsw_sp->sb_vals->pool_count; i++) { err = mlxsw_sp_sb_pm_occ_query(mlxsw_sp, local_port, i, &bulk_list); if (err) @@ -991,7 +1169,7 @@ next_batch: continue; mlxsw_reg_sbsr_ingress_port_mask_set(sbsr_pl, local_port, 1); mlxsw_reg_sbsr_egress_port_mask_set(sbsr_pl, local_port, 1); - for (i = 0; i < MLXSW_SP_SB_POOL_DESS_LEN; i++) { + for (i = 0; i < mlxsw_sp->sb_vals->pool_count; i++) { err = mlxsw_sp_sb_pm_occ_clear(mlxsw_sp, local_port, i, &bulk_list); if (err) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index 9af9f5c1b25c..15f804453cd6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -102,8 +102,7 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, return err; } break; - case FLOW_ACTION_VLAN_PUSH: - case FLOW_ACTION_VLAN_POP: { + case FLOW_ACTION_VLAN_MANGLE: { u16 proto = be16_to_cpu(act->vlan.proto); u8 prio = act->vlan.prio; u16 vid = act->vlan.vid; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 6754061d9b72..52fed8c7bf1e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -3814,13 +3814,11 @@ mlxsw_sp_nexthop4_group_create(struct mlxsw_sp *mlxsw_sp, struct fib_info *fi) struct mlxsw_sp_nexthop_group *nh_grp; struct mlxsw_sp_nexthop *nh; struct fib_nh *fib_nh; - size_t alloc_size; int i; int err; - alloc_size = sizeof(*nh_grp) + - fi->fib_nhs * sizeof(struct mlxsw_sp_nexthop); - nh_grp = kzalloc(alloc_size, GFP_KERNEL); + nh_grp = kzalloc(struct_size(nh_grp, nexthops, fi->fib_nhs), + GFP_KERNEL); if (!nh_grp) return ERR_PTR(-ENOMEM); nh_grp->priv = fi; @@ -5066,13 +5064,11 @@ mlxsw_sp_nexthop6_group_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop_group *nh_grp; struct mlxsw_sp_rt6 *mlxsw_sp_rt6; struct mlxsw_sp_nexthop *nh; - size_t alloc_size; int i = 0; int err; - alloc_size = sizeof(*nh_grp) + - fib6_entry->nrt6 * sizeof(struct mlxsw_sp_nexthop); - nh_grp = kzalloc(alloc_size, GFP_KERNEL); + nh_grp = kzalloc(struct_size(nh_grp, nexthops, fib6_entry->nrt6), + GFP_KERNEL); if (!nh_grp) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&nh_grp->fib_list); @@ -6146,7 +6142,7 @@ static int mlxsw_sp_router_rif_disable(struct mlxsw_sp *mlxsw_sp, u16 rif) mlxsw_reg_ritr_rif_pack(ritr_pl, rif); err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); - if (WARN_ON_ONCE(err)) + if (err) return err; mlxsw_reg_ritr_enable_set(ritr_pl, false); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 95e37de3e48f..766f5b5f1cf5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -431,41 +431,6 @@ static void mlxsw_sp_bridge_vlan_put(struct mlxsw_sp_bridge_vlan *bridge_vlan) mlxsw_sp_bridge_vlan_destroy(bridge_vlan); } -static void mlxsw_sp_port_bridge_flags_get(struct mlxsw_sp_bridge *bridge, - struct net_device *dev, - unsigned long *brport_flags) -{ - struct mlxsw_sp_bridge_port *bridge_port; - - bridge_port = mlxsw_sp_bridge_port_find(bridge, dev); - if (WARN_ON(!bridge_port)) - return; - - memcpy(brport_flags, &bridge_port->flags, sizeof(*brport_flags)); -} - -static int mlxsw_sp_port_attr_get(struct net_device *dev, - struct switchdev_attr *attr) -{ - struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; - - switch (attr->id) { - case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: - mlxsw_sp_port_bridge_flags_get(mlxsw_sp->bridge, attr->orig_dev, - &attr->u.brport_flags); - break; - case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT: - attr->u.brport_flags_support = BR_LEARNING | BR_FLOOD | - BR_MCAST_FLOOD; - break; - default: - return -EOPNOTSUPP; - } - - return 0; -} - static int mlxsw_sp_port_bridge_vlan_stp_set(struct mlxsw_sp_port *mlxsw_sp_port, struct mlxsw_sp_bridge_vlan *bridge_vlan, @@ -615,6 +580,17 @@ err_port_bridge_vlan_learning_set: return err; } +static int mlxsw_sp_port_attr_br_pre_flags_set(struct mlxsw_sp_port + *mlxsw_sp_port, + struct switchdev_trans *trans, + unsigned long brport_flags) +{ + if (brport_flags & ~(BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD)) + return -EINVAL; + + return 0; +} + static int mlxsw_sp_port_attr_br_flags_set(struct mlxsw_sp_port *mlxsw_sp_port, struct switchdev_trans *trans, struct net_device *orig_dev, @@ -861,6 +837,11 @@ static int mlxsw_sp_port_attr_set(struct net_device *dev, attr->orig_dev, attr->u.stp_state); break; + case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS: + err = mlxsw_sp_port_attr_br_pre_flags_set(mlxsw_sp_port, + trans, + attr->u.brport_flags); + break; case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: err = mlxsw_sp_port_attr_br_flags_set(mlxsw_sp_port, trans, attr->orig_dev, @@ -1958,7 +1939,6 @@ static struct mlxsw_sp_port *mlxsw_sp_lag_rep_port(struct mlxsw_sp *mlxsw_sp, } static const struct switchdev_ops mlxsw_sp_port_switchdev_ops = { - .switchdev_port_attr_get = mlxsw_sp_port_attr_get, .switchdev_port_attr_set = mlxsw_sp_port_attr_set, }; diff --git a/drivers/net/ethernet/micrel/ks8695net.c b/drivers/net/ethernet/micrel/ks8695net.c index b881f5d4a7f9..6006d47707cb 100644 --- a/drivers/net/ethernet/micrel/ks8695net.c +++ b/drivers/net/ethernet/micrel/ks8695net.c @@ -391,7 +391,7 @@ ks8695_tx_irq(int irq, void *dev_id) ksp->tx_buffers[buff_n].dma_ptr, ksp->tx_buffers[buff_n].length, DMA_TO_DEVICE); - dev_kfree_skb_irq(ksp->tx_buffers[buff_n].skb); + dev_consume_skb_irq(ksp->tx_buffers[buff_n].skb); ksp->tx_buffers[buff_n].skb = NULL; ksp->tx_ring_used--; } diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index b34055ac476f..e1651756bf9d 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -81,11 +81,13 @@ static void moxart_mac_free_memory(struct net_device *ndev) priv->rx_buf_size, DMA_FROM_DEVICE); if (priv->tx_desc_base) - dma_free_coherent(NULL, TX_REG_DESC_SIZE * TX_DESC_NUM, + dma_free_coherent(&priv->pdev->dev, + TX_REG_DESC_SIZE * TX_DESC_NUM, priv->tx_desc_base, priv->tx_base); if (priv->rx_desc_base) - dma_free_coherent(NULL, RX_REG_DESC_SIZE * RX_DESC_NUM, + dma_free_coherent(&priv->pdev->dev, + RX_REG_DESC_SIZE * RX_DESC_NUM, priv->rx_desc_base, priv->rx_base); kfree(priv->tx_buf_base); @@ -298,7 +300,7 @@ static void moxart_tx_finished(struct net_device *ndev) ndev->stats.tx_packets++; ndev->stats.tx_bytes += priv->tx_skb[tx_tail]->len; - dev_kfree_skb_irq(priv->tx_skb[tx_tail]); + dev_consume_skb_irq(priv->tx_skb[tx_tail]); priv->tx_skb[tx_tail] = NULL; tx_tail = TX_NEXT(tx_tail); @@ -476,6 +478,7 @@ static int moxart_mac_probe(struct platform_device *pdev) priv = netdev_priv(ndev); priv->ndev = ndev; + priv->pdev = pdev; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); ndev->base_addr = res->start; @@ -491,7 +494,7 @@ static int moxart_mac_probe(struct platform_device *pdev) priv->tx_buf_size = TX_BUF_SIZE; priv->rx_buf_size = RX_BUF_SIZE; - priv->tx_desc_base = dma_alloc_coherent(NULL, TX_REG_DESC_SIZE * + priv->tx_desc_base = dma_alloc_coherent(&pdev->dev, TX_REG_DESC_SIZE * TX_DESC_NUM, &priv->tx_base, GFP_DMA | GFP_KERNEL); if (!priv->tx_desc_base) { @@ -499,7 +502,7 @@ static int moxart_mac_probe(struct platform_device *pdev) goto init_fail; } - priv->rx_desc_base = dma_alloc_coherent(NULL, RX_REG_DESC_SIZE * + priv->rx_desc_base = dma_alloc_coherent(&pdev->dev, RX_REG_DESC_SIZE * RX_DESC_NUM, &priv->rx_base, GFP_DMA | GFP_KERNEL); if (!priv->rx_desc_base) { diff --git a/drivers/net/ethernet/moxa/moxart_ether.h b/drivers/net/ethernet/moxa/moxart_ether.h index bee608b547d1..bf4c3029cd0c 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.h +++ b/drivers/net/ethernet/moxa/moxart_ether.h @@ -292,6 +292,7 @@ #define LINK_STATUS 0x4 struct moxart_mac_priv_t { + struct platform_device *pdev; void __iomem *base; unsigned int reg_maccr; unsigned int reg_imr; diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 19ce0e605096..e0340f778d8f 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -1408,7 +1408,7 @@ myri10ge_tx_done(struct myri10ge_slice_state *ss, int mcp_index) if (skb) { ss->stats.tx_bytes += skb->len; ss->stats.tx_packets++; - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); if (len) pci_unmap_single(pdev, dma_unmap_addr(&tx->info[idx], diff --git a/drivers/net/ethernet/natsemi/natsemi.c b/drivers/net/ethernet/natsemi/natsemi.c index b9a1a9f999ea..1a2634cbbb69 100644 --- a/drivers/net/ethernet/natsemi/natsemi.c +++ b/drivers/net/ethernet/natsemi/natsemi.c @@ -2173,7 +2173,7 @@ static void netdev_tx_done(struct net_device *dev) np->tx_skbuff[entry]->len, PCI_DMA_TODEVICE); /* Free the original skb. */ - dev_kfree_skb_irq(np->tx_skbuff[entry]); + dev_consume_skb_irq(np->tx_skbuff[entry]); np->tx_skbuff[entry] = NULL; } if (netif_queue_stopped(dev) && diff --git a/drivers/net/ethernet/natsemi/ns83820.c b/drivers/net/ethernet/natsemi/ns83820.c index 958fced4dacf..9098ee7fe0d1 100644 --- a/drivers/net/ethernet/natsemi/ns83820.c +++ b/drivers/net/ethernet/natsemi/ns83820.c @@ -1003,7 +1003,7 @@ static void do_tx_done(struct net_device *ndev) addr, len, PCI_DMA_TODEVICE); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); atomic_dec(&dev->nr_tx_skbs); } else pci_unmap_page(dev->pci_dev, @@ -1869,56 +1869,28 @@ static unsigned ns83820_mii_write_reg(struct ns83820 *dev, unsigned phy, unsigne static void ns83820_probe_phy(struct net_device *ndev) { struct ns83820 *dev = PRIV(ndev); - static int first; - int i; -#define MII_PHYIDR1 0x02 -#define MII_PHYIDR2 0x03 - -#if 0 - if (!first) { - unsigned tmp; - ns83820_mii_read_reg(dev, 1, 0x09); - ns83820_mii_write_reg(dev, 1, 0x10, 0x0d3e); - - tmp = ns83820_mii_read_reg(dev, 1, 0x00); - ns83820_mii_write_reg(dev, 1, 0x00, tmp | 0x8000); - udelay(1300); - ns83820_mii_read_reg(dev, 1, 0x09); - } -#endif - first = 1; - - for (i=1; i<2; i++) { - int j; - unsigned a, b; - a = ns83820_mii_read_reg(dev, i, MII_PHYIDR1); - b = ns83820_mii_read_reg(dev, i, MII_PHYIDR2); - - //printk("%s: phy %d: 0x%04x 0x%04x\n", - // ndev->name, i, a, b); - - for (j=0; j<0x16; j+=4) { - dprintk("%s: [0x%02x] %04x %04x %04x %04x\n", - ndev->name, j, - ns83820_mii_read_reg(dev, i, 0 + j), - ns83820_mii_read_reg(dev, i, 1 + j), - ns83820_mii_read_reg(dev, i, 2 + j), - ns83820_mii_read_reg(dev, i, 3 + j) - ); - } - } - { - unsigned a, b; - /* read firmware version: memory addr is 0x8402 and 0x8403 */ - ns83820_mii_write_reg(dev, 1, 0x16, 0x000d); - ns83820_mii_write_reg(dev, 1, 0x1e, 0x810e); - a = ns83820_mii_read_reg(dev, 1, 0x1d); - - ns83820_mii_write_reg(dev, 1, 0x16, 0x000d); - ns83820_mii_write_reg(dev, 1, 0x1e, 0x810e); - b = ns83820_mii_read_reg(dev, 1, 0x1d); - dprintk("version: 0x%04x 0x%04x\n", a, b); + int j; + unsigned a, b; + + for (j = 0; j < 0x16; j += 4) { + dprintk("%s: [0x%02x] %04x %04x %04x %04x\n", + ndev->name, j, + ns83820_mii_read_reg(dev, 1, 0 + j), + ns83820_mii_read_reg(dev, 1, 1 + j), + ns83820_mii_read_reg(dev, 1, 2 + j), + ns83820_mii_read_reg(dev, 1, 3 + j) + ); } + + /* read firmware version: memory addr is 0x8402 and 0x8403 */ + ns83820_mii_write_reg(dev, 1, 0x16, 0x000d); + ns83820_mii_write_reg(dev, 1, 0x1e, 0x810e); + a = ns83820_mii_read_reg(dev, 1, 0x1d); + + ns83820_mii_write_reg(dev, 1, 0x16, 0x000d); + ns83820_mii_write_reg(dev, 1, 0x1e, 0x810e); + b = ns83820_mii_read_reg(dev, 1, 0x1d); + dprintk("version: 0x%04x 0x%04x\n", a, b); } #endif diff --git a/drivers/net/ethernet/natsemi/sonic.c b/drivers/net/ethernet/natsemi/sonic.c index c805dcbebd02..aaec00912ea0 100644 --- a/drivers/net/ethernet/natsemi/sonic.c +++ b/drivers/net/ethernet/natsemi/sonic.c @@ -328,7 +328,7 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id) } /* We must free the original skb */ - dev_kfree_skb_irq(lp->tx_skb[entry]); + dev_consume_skb_irq(lp->tx_skb[entry]); lp->tx_skb[entry] = NULL; /* and unmap DMA buffer */ dma_unmap_single(lp->device, lp->tx_laddr[entry], lp->tx_len[entry], DMA_TO_DEVICE); diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index 82be90075695..feda9644289d 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -3055,7 +3055,7 @@ static void tx_intr_handler(struct fifo_info *fifo_data) /* Updating the statistics block */ swstats->mem_freed += skb->truesize; - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); get_info.offset++; if (get_info.offset == get_info.fifo_len + 1) diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c index 0da7393b2ef3..b877acec5cde 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-main.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c @@ -114,7 +114,7 @@ static inline void VXGE_COMPLETE_VPATH_TX(struct vxge_fifo *fifo) /* free SKBs */ for (temp = completed; temp != skb_ptr; temp++) - dev_kfree_skb_irq(*temp); + dev_consume_skb_irq(*temp); } while (more); } diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index dccae0319204..275de9f4c61c 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -465,7 +465,7 @@ static int nfp_bpf_init(struct nfp_app *app) app->ctrl_mtu = nfp_bpf_ctrl_cmsg_mtu(bpf); } - bpf->bpf_dev = bpf_offload_dev_create(&nfp_bpf_dev_ops); + bpf->bpf_dev = bpf_offload_dev_create(&nfp_bpf_dev_ops, bpf); err = PTR_ERR_OR_ZERO(bpf->bpf_dev); if (err) goto err_free_neutral_maps; diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c index 55c7dbf8b421..15dce97650a5 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c @@ -185,8 +185,6 @@ static void nfp_prog_free(struct nfp_prog *nfp_prog) static int nfp_bpf_verifier_prep(struct bpf_prog *prog) { - struct nfp_net *nn = netdev_priv(prog->aux->offload->netdev); - struct nfp_app *app = nn->app; struct nfp_prog *nfp_prog; int ret; @@ -197,7 +195,7 @@ static int nfp_bpf_verifier_prep(struct bpf_prog *prog) INIT_LIST_HEAD(&nfp_prog->insns); nfp_prog->type = prog->type; - nfp_prog->bpf = app->priv; + nfp_prog->bpf = bpf_offload_dev_priv(prog->aux->offload->offdev); ret = nfp_prog_prepare(nfp_prog, prog->insnsi, prog->len); if (ret) diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c index 583e97c99e68..eeda4ed98333 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/action.c +++ b/drivers/net/ethernet/netronome/nfp/flower/action.c @@ -345,7 +345,7 @@ static void nfp_fl_set_helper32(u32 value, u32 mask, u8 *p_exact, u8 *p_mask) } static int -nfp_fl_set_eth(const struct flow_action_entry *act, int idx, u32 off, +nfp_fl_set_eth(const struct flow_action_entry *act, u32 off, struct nfp_fl_set_eth *set_eth) { u32 exact, mask; @@ -376,7 +376,7 @@ struct ipv4_ttl_word { }; static int -nfp_fl_set_ip4(const struct flow_action_entry *act, int idx, u32 off, +nfp_fl_set_ip4(const struct flow_action_entry *act, u32 off, struct nfp_fl_set_ip4_addrs *set_ip_addr, struct nfp_fl_set_ip4_ttl_tos *set_ip_ttl_tos) { @@ -505,7 +505,7 @@ nfp_fl_set_ip6_hop_limit_flow_label(u32 off, __be32 exact, __be32 mask, } static int -nfp_fl_set_ip6(const struct flow_action_entry *act, int idx, u32 off, +nfp_fl_set_ip6(const struct flow_action_entry *act, u32 off, struct nfp_fl_set_ipv6_addr *ip_dst, struct nfp_fl_set_ipv6_addr *ip_src, struct nfp_fl_set_ipv6_tc_hl_fl *ip_hl_fl) @@ -541,7 +541,7 @@ nfp_fl_set_ip6(const struct flow_action_entry *act, int idx, u32 off, } static int -nfp_fl_set_tport(const struct flow_action_entry *act, int idx, u32 off, +nfp_fl_set_tport(const struct flow_action_entry *act, u32 off, struct nfp_fl_set_tport *set_tport, int opcode) { u32 exact, mask; @@ -598,8 +598,8 @@ nfp_fl_pedit(const struct flow_action_entry *act, struct nfp_fl_set_eth set_eth; size_t act_size = 0; u8 ip_proto = 0; - int idx, err; u32 offset; + int err; memset(&set_ip6_tc_hl_fl, 0, sizeof(set_ip6_tc_hl_fl)); memset(&set_ip_ttl_tos, 0, sizeof(set_ip_ttl_tos)); @@ -614,22 +614,22 @@ nfp_fl_pedit(const struct flow_action_entry *act, switch (htype) { case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH: - err = nfp_fl_set_eth(act, idx, offset, &set_eth); + err = nfp_fl_set_eth(act, offset, &set_eth); break; case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4: - err = nfp_fl_set_ip4(act, idx, offset, &set_ip_addr, + err = nfp_fl_set_ip4(act, offset, &set_ip_addr, &set_ip_ttl_tos); break; case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6: - err = nfp_fl_set_ip6(act, idx, offset, &set_ip6_dst, + err = nfp_fl_set_ip6(act, offset, &set_ip6_dst, &set_ip6_src, &set_ip6_tc_hl_fl); break; case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP: - err = nfp_fl_set_tport(act, idx, offset, &set_tport, + err = nfp_fl_set_tport(act, offset, &set_tport, NFP_FL_ACTION_OPCODE_SET_TCP); break; case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP: - err = nfp_fl_set_tport(act, idx, offset, &set_tport, + err = nfp_fl_set_tport(act, offset, &set_tport, NFP_FL_ACTION_OPCODE_SET_UDP); break; default: diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c index 56b22ea32474..cf9e1118ee8f 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c @@ -45,11 +45,9 @@ nfp_flower_cmsg_mac_repr_start(struct nfp_app *app, unsigned int num_ports) { struct nfp_flower_cmsg_mac_repr *msg; struct sk_buff *skb; - unsigned int size; - size = sizeof(*msg) + num_ports * sizeof(msg->ports[0]); - skb = nfp_flower_cmsg_alloc(app, size, NFP_FLOWER_CMSG_TYPE_MAC_REPR, - GFP_KERNEL); + skb = nfp_flower_cmsg_alloc(app, struct_size(msg, ports, num_ports), + NFP_FLOWER_CMSG_TYPE_MAC_REPR, GFP_KERNEL); if (!skb) return NULL; diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c index 1279fa5da9e1..e03c8ef2c28c 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/match.c +++ b/drivers/net/ethernet/netronome/nfp/flower/match.c @@ -172,46 +172,51 @@ nfp_flower_compile_ip_ext(struct nfp_flower_ip_ext *ext, } if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_TCP)) { + u16 tcp_flags, tcp_flags_mask; struct flow_match_tcp match; - u16 tcp_flags; flow_rule_match_tcp(rule, &match); tcp_flags = be16_to_cpu(match.key->flags); + tcp_flags_mask = be16_to_cpu(match.mask->flags); - if (tcp_flags & TCPHDR_FIN) { + if (tcp_flags & TCPHDR_FIN) ext->flags |= NFP_FL_TCP_FLAG_FIN; + if (tcp_flags_mask & TCPHDR_FIN) msk->flags |= NFP_FL_TCP_FLAG_FIN; - } - if (tcp_flags & TCPHDR_SYN) { + + if (tcp_flags & TCPHDR_SYN) ext->flags |= NFP_FL_TCP_FLAG_SYN; + if (tcp_flags_mask & TCPHDR_SYN) msk->flags |= NFP_FL_TCP_FLAG_SYN; - } - if (tcp_flags & TCPHDR_RST) { + + if (tcp_flags & TCPHDR_RST) ext->flags |= NFP_FL_TCP_FLAG_RST; + if (tcp_flags_mask & TCPHDR_RST) msk->flags |= NFP_FL_TCP_FLAG_RST; - } - if (tcp_flags & TCPHDR_PSH) { + + if (tcp_flags & TCPHDR_PSH) ext->flags |= NFP_FL_TCP_FLAG_PSH; + if (tcp_flags_mask & TCPHDR_PSH) msk->flags |= NFP_FL_TCP_FLAG_PSH; - } - if (tcp_flags & TCPHDR_URG) { + + if (tcp_flags & TCPHDR_URG) ext->flags |= NFP_FL_TCP_FLAG_URG; + if (tcp_flags_mask & TCPHDR_URG) msk->flags |= NFP_FL_TCP_FLAG_URG; - } } if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { struct flow_match_control match; flow_rule_match_control(rule, &match); - if (match.key->flags & FLOW_DIS_IS_FRAGMENT) { + if (match.key->flags & FLOW_DIS_IS_FRAGMENT) ext->flags |= NFP_FL_IP_FRAGMENTED; + if (match.mask->flags & FLOW_DIS_IS_FRAGMENT) msk->flags |= NFP_FL_IP_FRAGMENTED; - } - if (match.key->flags & FLOW_DIS_FIRST_FRAG) { + if (match.key->flags & FLOW_DIS_FIRST_FRAG) ext->flags |= NFP_FL_IP_FRAG_FIRST; + if (match.mask->flags & FLOW_DIS_FIRST_FRAG) msk->flags |= NFP_FL_IP_FRAG_FIRST; - } } } diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index fe1469d201af..450d7296fd57 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -187,7 +187,6 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, if (ipv4_addrs.mask->dst != cpu_to_be32(~0)) return -EOPNOTSUPP; - flow_rule_match_enc_ports(rule, &enc_ports); if (enc_ports.mask->dst != cpu_to_be16(~0)) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c index dddbb0575be9..db2da99f6aa7 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c @@ -178,7 +178,7 @@ static const struct nfp_devlink_versions_simple { } nfp_devlink_versions_hwinfo[] = { { DEVLINK_INFO_VERSION_GENERIC_BOARD_ID, "assembly.partno", }, { DEVLINK_INFO_VERSION_GENERIC_BOARD_REV, "assembly.revision", }, - { "board.vendor", /* fab */ "assembly.vendor", }, + { DEVLINK_INFO_VERSION_GENERIC_BOARD_MANUFACTURE, "assembly.vendor", }, { "board.model", /* code name */ "assembly.model", }, }; @@ -258,18 +258,33 @@ nfp_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req, struct netlink_ext_ack *extack) { struct nfp_pf *pf = devlink_priv(devlink); + const char *sn, *vendor, *part; struct nfp_nsp *nsp; char *buf = NULL; - const char *sn; int err; err = devlink_info_driver_name_put(req, "nfp"); if (err) return err; + vendor = nfp_hwinfo_lookup(pf->hwinfo, "assembly.vendor"); + part = nfp_hwinfo_lookup(pf->hwinfo, "assembly.partno"); sn = nfp_hwinfo_lookup(pf->hwinfo, "assembly.serial"); - if (sn) { - err = devlink_info_serial_number_put(req, sn); + if (vendor && part && sn) { + char *buf; + + buf = kmalloc(strlen(vendor) + strlen(part) + strlen(sn) + 1, + GFP_KERNEL); + if (!buf) + return -ENOMEM; + + buf[0] = '\0'; + strcat(buf, vendor); + strcat(buf, part); + strcat(buf, sn); + + err = devlink_info_serial_number_put(req, buf); + kfree(buf); if (err) return err; } @@ -315,6 +330,15 @@ err_close_nsp: return err; } +static int +nfp_devlink_flash_update(struct devlink *devlink, const char *path, + const char *component, struct netlink_ext_ack *extack) +{ + if (component) + return -EOPNOTSUPP; + return nfp_flash_update_common(devlink_priv(devlink), path, extack); +} + const struct devlink_ops nfp_devlink_ops = { .port_split = nfp_devlink_port_split, .port_unsplit = nfp_devlink_port_unsplit, @@ -323,6 +347,7 @@ const struct devlink_ops nfp_devlink_ops = { .eswitch_mode_get = nfp_devlink_eswitch_mode_get, .eswitch_mode_set = nfp_devlink_eswitch_mode_set, .info_get = nfp_devlink_info_get, + .flash_update = nfp_devlink_flash_update, }; int nfp_devlink_port_register(struct nfp_app *app, struct nfp_port *port) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c index 6c10e8d119e4..f4c8776e42b6 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c @@ -300,6 +300,47 @@ static int nfp_pcie_sriov_configure(struct pci_dev *pdev, int num_vfs) return nfp_pcie_sriov_enable(pdev, num_vfs); } +int nfp_flash_update_common(struct nfp_pf *pf, const char *path, + struct netlink_ext_ack *extack) +{ + struct device *dev = &pf->pdev->dev; + const struct firmware *fw; + struct nfp_nsp *nsp; + int err; + + nsp = nfp_nsp_open(pf->cpp); + if (IS_ERR(nsp)) { + err = PTR_ERR(nsp); + if (extack) + NL_SET_ERR_MSG_MOD(extack, "can't access NSP"); + else + dev_err(dev, "Failed to access the NSP: %d\n", err); + return err; + } + + err = request_firmware_direct(&fw, path, dev); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "unable to read flash file from disk"); + goto exit_close_nsp; + } + + dev_info(dev, "Please be patient while writing flash image: %s\n", + path); + + err = nfp_nsp_write_flash(nsp, fw); + if (err < 0) + goto exit_release_fw; + dev_info(dev, "Finished writing flash image\n"); + err = 0; + +exit_release_fw: + release_firmware(fw); +exit_close_nsp: + nfp_nsp_close(nsp); + return err; +} + static const struct firmware * nfp_net_fw_request(struct pci_dev *pdev, struct nfp_pf *pf, const char *name) { diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.h b/drivers/net/ethernet/netronome/nfp/nfp_main.h index a3613a2e0aa5..b7211f200d22 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_main.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_main.h @@ -164,6 +164,8 @@ nfp_pf_map_rtsym(struct nfp_pf *pf, const char *name, const char *sym_fmt, unsigned int min_size, struct nfp_cpp_area **area); int nfp_mbox_cmd(struct nfp_pf *pf, u32 cmd, void *in_data, u64 in_length, void *out_data, u64 out_length); +int nfp_flash_update_common(struct nfp_pf *pf, const char *path, + struct netlink_ext_ack *extack); enum nfp_dump_diag { NFP_DUMP_NSP_DIAG = 0, diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index cb9c512abc76..8f189149efc5 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -1237,11 +1237,8 @@ static int nfp_net_set_channels(struct net_device *netdev, static int nfp_net_flash_device(struct net_device *netdev, struct ethtool_flash *flash) { - const struct firmware *fw; struct nfp_app *app; - struct nfp_nsp *nsp; - struct device *dev; - int err; + int ret; if (flash->region != ETHTOOL_FLASH_ALL_REGIONS) return -EOPNOTSUPP; @@ -1250,39 +1247,13 @@ nfp_net_flash_device(struct net_device *netdev, struct ethtool_flash *flash) if (!app) return -EOPNOTSUPP; - dev = &app->pdev->dev; - - nsp = nfp_nsp_open(app->cpp); - if (IS_ERR(nsp)) { - err = PTR_ERR(nsp); - dev_err(dev, "Failed to access the NSP: %d\n", err); - return err; - } - - err = request_firmware_direct(&fw, flash->data, dev); - if (err) - goto exit_close_nsp; - - dev_info(dev, "Please be patient while writing flash image: %s\n", - flash->data); dev_hold(netdev); rtnl_unlock(); - - err = nfp_nsp_write_flash(nsp, fw); - if (err < 0) { - dev_err(dev, "Flash write failed: %d\n", err); - goto exit_rtnl_lock; - } - dev_info(dev, "Finished writing flash image\n"); - -exit_rtnl_lock: + ret = nfp_flash_update_common(app->pf, flash->data, NULL); rtnl_lock(); dev_put(netdev); - release_firmware(fw); -exit_close_nsp: - nfp_nsp_close(nsp); - return err; + return ret; } static const struct ethtool_ops nfp_net_ethtool_ops = { diff --git a/drivers/net/ethernet/nuvoton/w90p910_ether.c b/drivers/net/ethernet/nuvoton/w90p910_ether.c index c662c6f5bee3..67bf02b0763a 100644 --- a/drivers/net/ethernet/nuvoton/w90p910_ether.c +++ b/drivers/net/ethernet/nuvoton/w90p910_ether.c @@ -630,7 +630,7 @@ static int w90p910_ether_start_xmit(struct sk_buff *skb, struct net_device *dev) if (!(w90p910_send_frame(dev, skb->data, skb->len))) { ether->skb = skb; - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); return 0; } return -EAGAIN; diff --git a/drivers/net/ethernet/packetengines/hamachi.c b/drivers/net/ethernet/packetengines/hamachi.c index c9529c29a0a7..eee883a2aa8d 100644 --- a/drivers/net/ethernet/packetengines/hamachi.c +++ b/drivers/net/ethernet/packetengines/hamachi.c @@ -1337,7 +1337,7 @@ static irqreturn_t hamachi_interrupt(int irq, void *dev_instance) leXX_to_cpu(hmp->tx_ring[entry].addr), skb->len, PCI_DMA_TODEVICE); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); hmp->tx_skbuff[entry] = NULL; } hmp->tx_ring[entry].status_n_length = 0; diff --git a/drivers/net/ethernet/packetengines/yellowfin.c b/drivers/net/ethernet/packetengines/yellowfin.c index 54224d1822e3..6f8d6584f809 100644 --- a/drivers/net/ethernet/packetengines/yellowfin.c +++ b/drivers/net/ethernet/packetengines/yellowfin.c @@ -925,7 +925,7 @@ static irqreturn_t yellowfin_interrupt(int irq, void *dev_instance) /* Free the original skb. */ pci_unmap_single(yp->pci_dev, le32_to_cpu(yp->tx_ring[entry].addr), skb->len, PCI_DMA_TODEVICE); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); yp->tx_skbuff[entry] = NULL; } if (yp->tx_full && @@ -983,7 +983,7 @@ static irqreturn_t yellowfin_interrupt(int irq, void *dev_instance) pci_unmap_single(yp->pci_dev, yp->tx_ring[entry<<1].addr, skb->len, PCI_DMA_TODEVICE); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); yp->tx_skbuff[entry] = 0; /* Mark status as empty. */ yp->tx_status[entry].tx_errs = 0; diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index 3b0955d34716..43a57ec296fd 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -53,7 +53,7 @@ extern const struct qed_common_ops qed_common_ops_pass; #define QED_MAJOR_VERSION 8 -#define QED_MINOR_VERSION 33 +#define QED_MINOR_VERSION 37 #define QED_REVISION_VERSION 0 #define QED_ENGINEERING_VERSION 20 @@ -753,6 +753,7 @@ struct qed_dev { #define CHIP_BOND_ID_SHIFT 0 u8 num_engines; + u8 num_ports; u8 num_ports_in_engine; u8 num_funcs_in_port; @@ -892,7 +893,6 @@ void qed_configure_vp_wfq_on_link_change(struct qed_dev *cdev, void qed_clean_wfq_db(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); int qed_device_num_engines(struct qed_dev *cdev); -int qed_device_get_port_id(struct qed_dev *cdev); void qed_set_fw_mac_addr(__le16 *fw_msb, __le16 *fw_mid, __le16 *fw_lsb, u8 *mac); @@ -939,6 +939,10 @@ bool qed_edpm_enabled(struct qed_hwfn *p_hwfn); writel((u32)val, (void __iomem *)((u8 __iomem *)\ (cdev->doorbells) + (db_addr))) +#define MFW_PORT(_p_hwfn) ((_p_hwfn)->abs_pf_id % \ + qed_device_num_ports((_p_hwfn)->cdev)) +int qed_device_num_ports(struct qed_dev *cdev); + /* Prototypes */ int qed_fill_dev_info(struct qed_dev *cdev, struct qed_dev_info *dev_info); diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index 35c9f484eb9f..e61d1d905415 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -2135,12 +2135,12 @@ int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn, u32 rdma_tasks) struct qed_eth_pf_params *p_params = &p_hwfn->pf_params.eth_pf_params; - if (!p_params->num_vf_cons) - p_params->num_vf_cons = - ETH_PF_PARAMS_VF_CONS_DEFAULT; - qed_cxt_set_proto_cid_count(p_hwfn, PROTOCOLID_ETH, - p_params->num_cons, - p_params->num_vf_cons); + if (!p_params->num_vf_cons) + p_params->num_vf_cons = + ETH_PF_PARAMS_VF_CONS_DEFAULT; + qed_cxt_set_proto_cid_count(p_hwfn, PROTOCOLID_ETH, + p_params->num_cons, + p_params->num_vf_cons); p_hwfn->p_cxt_mngr->arfs_count = p_params->num_arfs_filters; break; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index e2cbd77646a2..9df8c4b3b54e 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -3269,55 +3269,43 @@ static void qed_get_num_funcs(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) p_hwfn->enabled_func_idx, p_hwfn->num_funcs_on_engine); } -static void qed_hw_info_port_num_bb(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt) -{ - u32 port_mode; - - port_mode = qed_rd(p_hwfn, p_ptt, CNIG_REG_NW_PORT_MODE_BB); - - if (port_mode < 3) { - p_hwfn->cdev->num_ports_in_engine = 1; - } else if (port_mode <= 5) { - p_hwfn->cdev->num_ports_in_engine = 2; - } else { - DP_NOTICE(p_hwfn, "PORT MODE: %d not supported\n", - p_hwfn->cdev->num_ports_in_engine); - - /* Default num_ports_in_engine to something */ - p_hwfn->cdev->num_ports_in_engine = 1; - } -} - -static void qed_hw_info_port_num_ah(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt) +static void qed_hw_info_port_num(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) { - u32 port; - int i; - - p_hwfn->cdev->num_ports_in_engine = 0; + u32 addr, global_offsize, global_addr, port_mode; + struct qed_dev *cdev = p_hwfn->cdev; - for (i = 0; i < MAX_NUM_PORTS_K2; i++) { - port = qed_rd(p_hwfn, p_ptt, - CNIG_REG_NIG_PORT0_CONF_K2 + (i * 4)); - if (port & 1) - p_hwfn->cdev->num_ports_in_engine++; + /* In CMT there is always only one port */ + if (cdev->num_hwfns > 1) { + cdev->num_ports_in_engine = 1; + cdev->num_ports = 1; + return; } - if (!p_hwfn->cdev->num_ports_in_engine) { - DP_NOTICE(p_hwfn, "All NIG ports are inactive\n"); - - /* Default num_ports_in_engine to something */ - p_hwfn->cdev->num_ports_in_engine = 1; + /* Determine the number of ports per engine */ + port_mode = qed_rd(p_hwfn, p_ptt, MISC_REG_PORT_MODE); + switch (port_mode) { + case 0x0: + cdev->num_ports_in_engine = 1; + break; + case 0x1: + cdev->num_ports_in_engine = 2; + break; + case 0x2: + cdev->num_ports_in_engine = 4; + break; + default: + DP_NOTICE(p_hwfn, "Unknown port mode 0x%08x\n", port_mode); + cdev->num_ports_in_engine = 1; /* Default to something */ + break; } -} -static void qed_hw_info_port_num(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) -{ - if (QED_IS_BB(p_hwfn->cdev)) - qed_hw_info_port_num_bb(p_hwfn, p_ptt); - else - qed_hw_info_port_num_ah(p_hwfn, p_ptt); + /* Get the total number of ports of the device */ + addr = SECTION_OFFSIZE_ADDR(p_hwfn->mcp_info->public_base, + PUBLIC_GLOBAL); + global_offsize = qed_rd(p_hwfn, p_ptt, addr); + global_addr = SECTION_ADDR(global_offsize, 0); + addr = global_addr + offsetof(struct public_global, max_ports); + cdev->num_ports = (u8)qed_rd(p_hwfn, p_ptt, addr); } static void qed_get_eee_caps(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) @@ -3355,7 +3343,8 @@ qed_get_hw_info(struct qed_hwfn *p_hwfn, return rc; } - qed_hw_info_port_num(p_hwfn, p_ptt); + if (IS_LEAD_HWFN(p_hwfn)) + qed_hw_info_port_num(p_hwfn, p_ptt); qed_mcp_get_capabilities(p_hwfn, p_ptt); @@ -4760,23 +4749,9 @@ void qed_clean_wfq_db(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) sizeof(*p_hwfn->qm_info.wfq_data) * p_hwfn->qm_info.num_vports); } -int qed_device_num_engines(struct qed_dev *cdev) -{ - return QED_IS_BB(cdev) ? 2 : 1; -} - -static int qed_device_num_ports(struct qed_dev *cdev) -{ - /* in CMT always only one port */ - if (cdev->num_hwfns > 1) - return 1; - - return cdev->num_ports_in_engine * qed_device_num_engines(cdev); -} - -int qed_device_get_port_id(struct qed_dev *cdev) +int qed_device_num_ports(struct qed_dev *cdev) { - return (QED_LEADING_HWFN(cdev)->abs_pf_id) % qed_device_num_ports(cdev); + return cdev->num_ports; } void qed_set_fw_mac_addr(__le16 *fw_msb, diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index 417121e74ee9..37edaa847512 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -12796,6 +12796,7 @@ struct public_drv_mb { #define FW_MB_PARAM_GET_PF_RDMA_BOTH 0x3 /* get MFW feature support response */ +#define FW_MB_PARAM_FEATURE_SUPPORT_SMARTLINQ 0x00000001 #define FW_MB_PARAM_FEATURE_SUPPORT_EEE 0x00000002 #define FW_MB_PARAM_FEATURE_SUPPORT_VLINK 0x00010000 diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c index beb8e5d6401a..ded556b7bab5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@ -1688,6 +1688,15 @@ qed_iwarp_parse_rx_pkt(struct qed_hwfn *p_hwfn, eth_hlen = ETH_HLEN + (vlan_valid ? sizeof(u32) : 0); + if (!ether_addr_equal(ethh->h_dest, + p_hwfn->p_rdma_info->iwarp.mac_addr)) { + DP_VERBOSE(p_hwfn, + QED_MSG_RDMA, + "Got unexpected mac %pM instead of %pM\n", + ethh->h_dest, p_hwfn->p_rdma_info->iwarp.mac_addr); + return -EINVAL; + } + ether_addr_copy(remote_mac_addr, ethh->h_source); ether_addr_copy(local_mac_addr, ethh->h_dest); @@ -2605,7 +2614,7 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, struct qed_iwarp_info *iwarp_info; struct qed_ll2_acquire_data data; struct qed_ll2_cbs cbs; - u32 mpa_buff_size; + u32 buff_size; u16 n_ooo_bufs; int rc = 0; int i; @@ -2632,7 +2641,7 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, memset(&data, 0, sizeof(data)); data.input.conn_type = QED_LL2_TYPE_IWARP; - data.input.mtu = QED_IWARP_MAX_SYN_PKT_SIZE; + data.input.mtu = params->max_mtu; data.input.rx_num_desc = QED_IWARP_LL2_SYN_RX_SIZE; data.input.tx_num_desc = QED_IWARP_LL2_SYN_TX_SIZE; data.input.tx_max_bds_per_packet = 1; /* will never be fragmented */ @@ -2654,9 +2663,10 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, goto err; } + buff_size = QED_IWARP_MAX_BUF_SIZE(params->max_mtu); rc = qed_iwarp_ll2_alloc_buffers(p_hwfn, QED_IWARP_LL2_SYN_RX_SIZE, - QED_IWARP_MAX_SYN_PKT_SIZE, + buff_size, iwarp_info->ll2_syn_handle); if (rc) goto err; @@ -2710,10 +2720,9 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, if (rc) goto err; - mpa_buff_size = QED_IWARP_MAX_BUF_SIZE(params->max_mtu); rc = qed_iwarp_ll2_alloc_buffers(p_hwfn, data.input.rx_num_desc, - mpa_buff_size, + buff_size, iwarp_info->ll2_mpa_handle); if (rc) goto err; @@ -2726,7 +2735,7 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, iwarp_info->max_num_partial_fpdus = (u16)p_hwfn->p_rdma_info->num_qps; - iwarp_info->mpa_intermediate_buf = kzalloc(mpa_buff_size, GFP_KERNEL); + iwarp_info->mpa_intermediate_buf = kzalloc(buff_size, GFP_KERNEL); if (!iwarp_info->mpa_intermediate_buf) goto err; diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h index b8f612d00241..7ac959038324 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h @@ -46,7 +46,6 @@ enum qed_iwarp_qp_state qed_roce2iwarp_state(enum qed_roce_qp_state state); #define QED_IWARP_LL2_SYN_TX_SIZE (128) #define QED_IWARP_LL2_SYN_RX_SIZE (256) -#define QED_IWARP_MAX_SYN_PKT_SIZE (128) #define QED_IWARP_LL2_OOO_DEF_TX_SIZE (256) #define QED_IWARP_MAX_OOO (16) diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index e68ca83ae915..57641728df69 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -1898,6 +1898,7 @@ static void _qed_get_vport_stats(struct qed_dev *cdev, struct qed_hwfn *p_hwfn = &cdev->hwfns[i]; struct qed_ptt *p_ptt = IS_PF(cdev) ? qed_ptt_acquire(p_hwfn) : NULL; + bool b_get_port_stats; if (IS_PF(cdev)) { /* The main vport index is relative first */ @@ -1912,8 +1913,9 @@ static void _qed_get_vport_stats(struct qed_dev *cdev, continue; } + b_get_port_stats = IS_PF(cdev) && IS_LEAD_HWFN(p_hwfn); __qed_get_vport_stats(p_hwfn, p_ptt, stats, fw_vport, - IS_PF(cdev) ? true : false); + b_get_port_stats); out: if (IS_PF(cdev) && p_ptt) @@ -2216,7 +2218,7 @@ static int qed_fill_eth_dev_info(struct qed_dev *cdev, u16 num_queues = 0; /* Since the feature controls only queue-zones, - * make sure we have the contexts [rx, tx, xdp] to + * make sure we have the contexts [rx, xdp, tcs] to * match. */ for_each_hwfn(cdev, i) { @@ -2226,7 +2228,8 @@ static int qed_fill_eth_dev_info(struct qed_dev *cdev, u16 cids; cids = hwfn->pf_params.eth_pf_params.num_cons; - num_queues += min_t(u16, l2_queues, cids / 3); + cids /= (2 + info->num_tc); + num_queues += min_t(u16, l2_queues, cids); } /* queues might theoretically be >256, but interrupts' @@ -2870,7 +2873,8 @@ static int qed_get_coalesce(struct qed_dev *cdev, u16 *coal, void *handle) p_hwfn = p_cid->p_owner; rc = qed_get_queue_coalesce(p_hwfn, coal, handle); if (rc) - DP_NOTICE(p_hwfn, "Unable to read queue coalescing\n"); + DP_VERBOSE(cdev, QED_MSG_DEBUG, + "Unable to read queue coalescing\n"); return rc; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index b47352643fb5..f164d4acebcb 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -281,6 +281,8 @@ int qed_fill_dev_info(struct qed_dev *cdev, if (hw_info->b_wol_support == QED_WOL_SUPPORT_PME) dev_info->wol_support = true; + dev_info->smart_an = qed_mcp_is_smart_an_supported(p_hwfn); + dev_info->abs_pf_id = QED_LEADING_HWFN(cdev)->abs_pf_id; } else { qed_vf_get_fw_version(&cdev->hwfns[0], &dev_info->fw_major, diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index bb8541847aa5..cc27fd60d689 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -3654,6 +3654,12 @@ void qed_mcp_resc_lock_default_init(struct qed_resc_lock_params *p_lock, } } +bool qed_mcp_is_smart_an_supported(struct qed_hwfn *p_hwfn) +{ + return !!(p_hwfn->mcp_info->capabilities & + FW_MB_PARAM_FEATURE_SUPPORT_SMARTLINQ); +} + int qed_mcp_get_capabilities(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) { u32 mcp_resp; diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h index 6e1d72a669ae..261c1a392e2c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h @@ -691,10 +691,6 @@ int qed_mfw_process_tlv_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); rel_pfid) #define MCP_PF_ID(p_hwfn) MCP_PF_ID_BY_REL(p_hwfn, (p_hwfn)->rel_pf_id) -#define MFW_PORT(_p_hwfn) ((_p_hwfn)->abs_pf_id % \ - ((_p_hwfn)->cdev->num_ports_in_engine * \ - qed_device_num_engines((_p_hwfn)->cdev))) - struct qed_mcp_info { /* List for mailbox commands which were sent and wait for a response */ struct list_head cmd_list; @@ -1148,6 +1144,16 @@ void qed_mcp_resc_lock_default_init(struct qed_resc_lock_params *p_lock, struct qed_resc_unlock_params *p_unlock, enum qed_resc_lock resource, bool b_is_permanent); + +/** + * @brief - Return whether management firmware support smart AN + * + * @param p_hwfn + * + * @return bool - true if feature is supported. + */ +bool qed_mcp_is_smart_an_supported(struct qed_hwfn *p_hwfn); + /** * @brief Learn of supported MFW features; To be done during early init * diff --git a/drivers/net/ethernet/qlogic/qed/qed_ptp.c b/drivers/net/ethernet/qlogic/qed/qed_ptp.c index 5a90d69dc2f8..1302b308bd87 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ptp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ptp.c @@ -47,7 +47,7 @@ static enum qed_resc_lock qed_ptcdev_to_resc(struct qed_hwfn *p_hwfn) { - switch (qed_device_get_port_id(p_hwfn->cdev)) { + switch (MFW_PORT(p_hwfn)) { case 0: return QED_RESC_LOCK_PTP_PORT0; case 1: diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h index 4179c9013fc6..96ab77ae6af5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h @@ -382,6 +382,7 @@ void qed_consq_setup(struct qed_hwfn *p_hwfn); * @param p_hwfn */ void qed_consq_free(struct qed_hwfn *p_hwfn); +int qed_spq_pend_post(struct qed_hwfn *p_hwfn); /** * @file diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c index 888274fa208b..5a495fda9e9d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c @@ -604,6 +604,9 @@ int qed_sp_pf_update_stag(struct qed_hwfn *p_hwfn) p_ent->ramrod.pf_update.update_mf_vlan_flag = true; p_ent->ramrod.pf_update.mf_vlan = cpu_to_le16(p_hwfn->hw_info.ovlan); + if (test_bit(QED_MF_UFP_SPECIFIC, &p_hwfn->cdev->mf_bits)) + p_ent->ramrod.pf_update.mf_vlan |= + cpu_to_le16(((u16)p_hwfn->ufp_info.tc << 13)); return qed_spq_post(p_hwfn, p_ent, NULL); } diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c index 3e0f7c46bb1b..79b311b86f66 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_spq.c +++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c @@ -397,6 +397,11 @@ int qed_eq_completion(struct qed_hwfn *p_hwfn, void *cookie) qed_eq_prod_update(p_hwfn, qed_chain_get_prod_idx(p_chain)); + /* Attempt to post pending requests */ + spin_lock_bh(&p_hwfn->p_spq->lock); + rc = qed_spq_pend_post(p_hwfn); + spin_unlock_bh(&p_hwfn->p_spq->lock); + return rc; } @@ -767,7 +772,7 @@ static int qed_spq_post_list(struct qed_hwfn *p_hwfn, return 0; } -static int qed_spq_pend_post(struct qed_hwfn *p_hwfn) +int qed_spq_pend_post(struct qed_hwfn *p_hwfn) { struct qed_spq *p_spq = p_hwfn->p_spq; struct qed_spq_entry *p_ent = NULL; @@ -927,7 +932,6 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn, struct qed_spq_entry *p_ent = NULL; struct qed_spq_entry *tmp; struct qed_spq_entry *found = NULL; - int rc; if (!p_hwfn) return -EINVAL; @@ -985,12 +989,7 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn, */ qed_spq_return_entry(p_hwfn, found); - /* Attempt to post pending requests */ - spin_lock_bh(&p_spq->lock); - rc = qed_spq_pend_post(p_hwfn); - spin_unlock_bh(&p_spq->lock); - - return rc; + return 0; } int qed_consq_alloc(struct qed_hwfn *p_hwfn) diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index 843416404aeb..63a78162cfaf 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -56,7 +56,7 @@ #include <net/tc_act/tc_gact.h> #define QEDE_MAJOR_VERSION 8 -#define QEDE_MINOR_VERSION 33 +#define QEDE_MINOR_VERSION 37 #define QEDE_REVISION_VERSION 0 #define QEDE_ENGINEERING_VERSION 20 #define DRV_MODULE_VERSION __stringify(QEDE_MAJOR_VERSION) "." \ @@ -497,6 +497,9 @@ struct qede_reload_args { /* Datapath functions definition */ netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev); +u16 qede_select_queue(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev, + select_queue_fallback_t fallback); netdev_features_t qede_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features); diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index 16331c6c6fa7..c6238083e898 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -186,11 +186,13 @@ static const struct { enum { QEDE_PRI_FLAG_CMT, + QEDE_PRI_FLAG_SMART_AN_SUPPORT, /* MFW supports SmartAN */ QEDE_PRI_FLAG_LEN, }; static const char qede_private_arr[QEDE_PRI_FLAG_LEN][ETH_GSTRING_LEN] = { "Coupled-Function", + "SmartAN capable", }; enum qede_ethtool_tests { @@ -404,8 +406,15 @@ static int qede_get_sset_count(struct net_device *dev, int stringset) static u32 qede_get_priv_flags(struct net_device *dev) { struct qede_dev *edev = netdev_priv(dev); + u32 flags = 0; - return (!!(edev->dev_info.common.num_hwfns > 1)) << QEDE_PRI_FLAG_CMT; + if (edev->dev_info.common.num_hwfns > 1) + flags |= BIT(QEDE_PRI_FLAG_CMT); + + if (edev->dev_info.common.smart_an) + flags |= BIT(QEDE_PRI_FLAG_SMART_AN_SUPPORT); + + return flags; } struct qede_link_mode_mapping { diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index bdf816fe5a16..31b046e24565 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -1695,6 +1695,19 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev) return NETDEV_TX_OK; } +u16 qede_select_queue(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev, + select_queue_fallback_t fallback) +{ + struct qede_dev *edev = netdev_priv(dev); + int total_txq; + + total_txq = QEDE_TSS_COUNT(edev) * edev->dev_info.num_tc; + + return QEDE_TSS_COUNT(edev) ? + fallback(dev, skb, NULL) % total_txq : 0; +} + /* 8B udp header + 8B base tunnel header + 32B option length */ #define QEDE_MAX_TUN_HDR_LEN 48 diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 6b4d96635238..02a97c659e29 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -621,6 +621,7 @@ static const struct net_device_ops qede_netdev_ops = { .ndo_open = qede_open, .ndo_stop = qede_close, .ndo_start_xmit = qede_start_xmit, + .ndo_select_queue = qede_select_queue, .ndo_set_rx_mode = qede_set_rx_mode, .ndo_set_mac_address = qede_set_mac_addr, .ndo_validate_addr = eth_validate_addr, @@ -656,6 +657,7 @@ static const struct net_device_ops qede_netdev_vf_ops = { .ndo_open = qede_open, .ndo_stop = qede_close, .ndo_start_xmit = qede_start_xmit, + .ndo_select_queue = qede_select_queue, .ndo_set_rx_mode = qede_set_rx_mode, .ndo_set_mac_address = qede_set_mac_addr, .ndo_validate_addr = eth_validate_addr, @@ -674,6 +676,7 @@ static const struct net_device_ops qede_netdev_vf_xdp_ops = { .ndo_open = qede_open, .ndo_stop = qede_close, .ndo_start_xmit = qede_start_xmit, + .ndo_select_queue = qede_select_queue, .ndo_set_rx_mode = qede_set_rx_mode, .ndo_set_mac_address = qede_set_mac_addr, .ndo_validate_addr = eth_validate_addr, diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c b/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c index 5edbd532127d..a6886cc5654c 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c @@ -249,8 +249,8 @@ static void ql_update_stats(struct ql_adapter *qdev) spin_lock(&qdev->stats_lock); if (ql_sem_spinlock(qdev, qdev->xg_sem_mask)) { - netif_err(qdev, drv, qdev->ndev, - "Couldn't get xgmac sem.\n"); + netif_err(qdev, drv, qdev->ndev, + "Couldn't get xgmac sem.\n"); goto quit; } /* diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c index 059ba9429e51..096515c27263 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c @@ -1159,10 +1159,10 @@ static void ql_update_lbq(struct ql_adapter *qdev, struct rx_ring *rx_ring) map = lbq_desc->p.pg_chunk.map + lbq_desc->p.pg_chunk.offset; - dma_unmap_addr_set(lbq_desc, mapaddr, map); + dma_unmap_addr_set(lbq_desc, mapaddr, map); dma_unmap_len_set(lbq_desc, maplen, rx_ring->lbq_buf_size); - *lbq_desc->addr = cpu_to_le64(map); + *lbq_desc->addr = cpu_to_le64(map); pci_dma_sync_single_for_device(qdev->pdev, map, rx_ring->lbq_buf_size, diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c index 8d790313ee3d..20d2400ad300 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c @@ -1204,7 +1204,7 @@ void emac_mac_tx_process(struct emac_adapter *adpt, struct emac_tx_queue *tx_q) if (tpbuf->skb) { pkts_compl++; bytes_compl += tpbuf->skb->len; - dev_kfree_skb_irq(tpbuf->skb); + dev_consume_skb_irq(tpbuf->skb); tpbuf->skb = NULL; } diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 1dd72137fd53..c29dde064078 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -6192,7 +6192,6 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, struct device *d = tp_to_dev(tp); dma_addr_t mapping; u32 opts[2], len; - bool stop_queue; int frags; if (unlikely(!rtl_tx_slots_avail(tp, skb_shinfo(skb)->nr_frags))) { @@ -6234,6 +6233,8 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, txd->opts2 = cpu_to_le32(opts[1]); + netdev_sent_queue(dev, skb->len); + skb_tx_timestamp(skb); /* Force memory writes to complete before releasing descriptor */ @@ -6246,14 +6247,14 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, tp->cur_tx += frags + 1; - stop_queue = !rtl_tx_slots_avail(tp, MAX_SKB_FRAGS); - if (unlikely(stop_queue)) - netif_stop_queue(dev); - - if (__netdev_sent_queue(dev, skb->len, skb->xmit_more)) - RTL_W8(tp, TxPoll, NPQ); + RTL_W8(tp, TxPoll, NPQ); - if (unlikely(stop_queue)) { + if (!rtl_tx_slots_avail(tp, MAX_SKB_FRAGS)) { + /* Avoid wrongly optimistic queue wake-up: rtl_tx thread must + * not miss a ring update when it notices a stopped queue. + */ + smp_wmb(); + netif_stop_queue(dev); /* Sync with rtl_tx: * - publish queue status and cur_tx ring index (write barrier) * - refresh dirty_tx ring index (read barrier). diff --git a/drivers/net/ethernet/rocker/rocker.h b/drivers/net/ethernet/rocker/rocker.h index 748fb12260a6..2b2e1c4f0dc3 100644 --- a/drivers/net/ethernet/rocker/rocker.h +++ b/drivers/net/ethernet/rocker/rocker.h @@ -109,8 +109,6 @@ struct rocker_world_ops { int (*port_attr_bridge_flags_set)(struct rocker_port *rocker_port, unsigned long brport_flags, struct switchdev_trans *trans); - int (*port_attr_bridge_flags_get)(const struct rocker_port *rocker_port, - unsigned long *p_brport_flags); int (*port_attr_bridge_flags_support_get)(const struct rocker_port * rocker_port, unsigned long * diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index 66f72f8c46e5..309a6bf9130c 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -1566,45 +1566,57 @@ static int rocker_world_port_attr_stp_state_set(struct rocker_port *rocker_port, } static int -rocker_world_port_attr_bridge_flags_set(struct rocker_port *rocker_port, - unsigned long brport_flags, - struct switchdev_trans *trans) +rocker_world_port_attr_bridge_flags_support_get(const struct rocker_port * + rocker_port, + unsigned long * + p_brport_flags_support) { struct rocker_world_ops *wops = rocker_port->rocker->wops; - if (!wops->port_attr_bridge_flags_set) + if (!wops->port_attr_bridge_flags_support_get) return -EOPNOTSUPP; - - if (switchdev_trans_ph_prepare(trans)) - return 0; - - return wops->port_attr_bridge_flags_set(rocker_port, brport_flags, - trans); + return wops->port_attr_bridge_flags_support_get(rocker_port, + p_brport_flags_support); } static int -rocker_world_port_attr_bridge_flags_get(const struct rocker_port *rocker_port, - unsigned long *p_brport_flags) +rocker_world_port_attr_pre_bridge_flags_set(struct rocker_port *rocker_port, + unsigned long brport_flags, + struct switchdev_trans *trans) { struct rocker_world_ops *wops = rocker_port->rocker->wops; + unsigned long brport_flags_s; + int err; - if (!wops->port_attr_bridge_flags_get) + if (!wops->port_attr_bridge_flags_set) return -EOPNOTSUPP; - return wops->port_attr_bridge_flags_get(rocker_port, p_brport_flags); + + err = rocker_world_port_attr_bridge_flags_support_get(rocker_port, + &brport_flags_s); + if (err) + return err; + + if (brport_flags & ~brport_flags_s) + return -EINVAL; + + return 0; } static int -rocker_world_port_attr_bridge_flags_support_get(const struct rocker_port * - rocker_port, - unsigned long * - p_brport_flags_support) +rocker_world_port_attr_bridge_flags_set(struct rocker_port *rocker_port, + unsigned long brport_flags, + struct switchdev_trans *trans) { struct rocker_world_ops *wops = rocker_port->rocker->wops; - if (!wops->port_attr_bridge_flags_support_get) + if (!wops->port_attr_bridge_flags_set) return -EOPNOTSUPP; - return wops->port_attr_bridge_flags_support_get(rocker_port, - p_brport_flags_support); + + if (switchdev_trans_ph_prepare(trans)) + return 0; + + return wops->port_attr_bridge_flags_set(rocker_port, brport_flags, + trans); } static int @@ -2054,28 +2066,6 @@ static const struct net_device_ops rocker_port_netdev_ops = { * swdev interface ********************/ -static int rocker_port_attr_get(struct net_device *dev, - struct switchdev_attr *attr) -{ - const struct rocker_port *rocker_port = netdev_priv(dev); - int err = 0; - - switch (attr->id) { - case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: - err = rocker_world_port_attr_bridge_flags_get(rocker_port, - &attr->u.brport_flags); - break; - case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT: - err = rocker_world_port_attr_bridge_flags_support_get(rocker_port, - &attr->u.brport_flags_support); - break; - default: - return -EOPNOTSUPP; - } - - return err; -} - static int rocker_port_attr_set(struct net_device *dev, const struct switchdev_attr *attr, struct switchdev_trans *trans) @@ -2089,6 +2079,11 @@ static int rocker_port_attr_set(struct net_device *dev, attr->u.stp_state, trans); break; + case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS: + err = rocker_world_port_attr_pre_bridge_flags_set(rocker_port, + attr->u.brport_flags, + trans); + break; case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: err = rocker_world_port_attr_bridge_flags_set(rocker_port, attr->u.brport_flags, @@ -2148,7 +2143,6 @@ static int rocker_port_obj_del(struct net_device *dev, } static const struct switchdev_ops rocker_port_switchdev_ops = { - .switchdev_port_attr_get = rocker_port_attr_get, .switchdev_port_attr_set = rocker_port_attr_set, }; diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c index bea7895930f6..fa296a7c255d 100644 --- a/drivers/net/ethernet/rocker/rocker_ofdpa.c +++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c @@ -2512,16 +2512,6 @@ static int ofdpa_port_attr_bridge_flags_set(struct rocker_port *rocker_port, } static int -ofdpa_port_attr_bridge_flags_get(const struct rocker_port *rocker_port, - unsigned long *p_brport_flags) -{ - const struct ofdpa_port *ofdpa_port = rocker_port->wpriv; - - *p_brport_flags = ofdpa_port->brport_flags; - return 0; -} - -static int ofdpa_port_attr_bridge_flags_support_get(const struct rocker_port * rocker_port, unsigned long * @@ -2823,7 +2813,6 @@ struct rocker_world_ops rocker_ofdpa_ops = { .port_stop = ofdpa_port_stop, .port_attr_stp_state_set = ofdpa_port_attr_stp_state_set, .port_attr_bridge_flags_set = ofdpa_port_attr_bridge_flags_set, - .port_attr_bridge_flags_get = ofdpa_port_attr_bridge_flags_get, .port_attr_bridge_flags_support_get = ofdpa_port_attr_bridge_flags_support_get, .port_attr_bridge_ageing_time_set = ofdpa_port_attr_bridge_ageing_time_set, .port_obj_vlan_add = ofdpa_port_obj_vlan_add, diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 6062e99fa69b..e888b479c596 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -6046,6 +6046,8 @@ static const struct efx_ef10_nvram_type_info efx_ef10_nvram_types[] = { { NVRAM_PARTITION_TYPE_DYNCONFIG_DEFAULTS, 0, 0, "sfc_dynamic_cfg_dflt" }, { NVRAM_PARTITION_TYPE_ROMCONFIG_DEFAULTS, 0, 0, "sfc_exp_rom_cfg_dflt" }, { NVRAM_PARTITION_TYPE_STATUS, 0, 0, "sfc_status" }, + { NVRAM_PARTITION_TYPE_BUNDLE, 0, 0, "sfc_bundle" }, + { NVRAM_PARTITION_TYPE_BUNDLE_METADATA, 0, 0, "sfc_bundle_metadata" }, }; #define EF10_NVRAM_PARTITION_COUNT ARRAY_SIZE(efx_ef10_nvram_types) @@ -6123,7 +6125,7 @@ static int efx_ef10_mtd_probe_partition(struct efx_nic *efx, static int efx_ef10_mtd_probe(struct efx_nic *efx) { MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_PARTITIONS_OUT_LENMAX); - DECLARE_BITMAP(found, EF10_NVRAM_PARTITION_COUNT); + DECLARE_BITMAP(found, EF10_NVRAM_PARTITION_COUNT) = { 0 }; struct efx_mcdi_mtd_partition *parts; size_t outlen, n_parts_total, i, n_parts; unsigned int type; diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 3643015a55cf..bc655ffc9e02 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -915,7 +915,7 @@ rollback: void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue) { - mod_timer(&rx_queue->slow_fill, jiffies + msecs_to_jiffies(100)); + mod_timer(&rx_queue->slow_fill, jiffies + msecs_to_jiffies(10)); } static bool efx_default_channel_want_txqs(struct efx_channel *channel) diff --git a/drivers/net/ethernet/sfc/mcdi_pcol.h b/drivers/net/ethernet/sfc/mcdi_pcol.h index 3839eec783ea..20a5523bf9f3 100644 --- a/drivers/net/ethernet/sfc/mcdi_pcol.h +++ b/drivers/net/ethernet/sfc/mcdi_pcol.h @@ -6784,6 +6784,14 @@ * subset of the information stored in this partition. */ #define NVRAM_PARTITION_TYPE_FRU_INFORMATION 0x1d00 +/* enum: Bundle image partition */ +#define NVRAM_PARTITION_TYPE_BUNDLE 0x1e00 +/* enum: Bundle metadata partition that holds additional information related to + * a bundle update in TLV format + */ +#define NVRAM_PARTITION_TYPE_BUNDLE_METADATA 0x1e01 +/* enum: Bundle update non-volatile log output partition */ +#define NVRAM_PARTITION_TYPE_BUNDLE_LOG 0x1e02 /* enum: Start of reserved value range (firmware may use for any purpose) */ #define NVRAM_PARTITION_TYPE_RESERVED_VALUES_MIN 0xff00 /* enum: End of reserved value range (firmware may use for any purpose) */ diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c index 396ff01298cd..8702ab44d80b 100644 --- a/drivers/net/ethernet/sfc/rx.c +++ b/drivers/net/ethernet/sfc/rx.c @@ -360,8 +360,7 @@ void efx_fast_push_rx_descriptors(struct efx_rx_queue *rx_queue, bool atomic) rc = efx_init_rx_buffers(rx_queue, atomic); if (unlikely(rc)) { /* Ensure that we don't leave the rx queue empty */ - if (rx_queue->added_count == rx_queue->removed_count) - efx_schedule_slow_fill(rx_queue); + efx_schedule_slow_fill(rx_queue); goto out; } } while ((space -= batch_size) >= batch_size); diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index 22eb059086f7..06c8f282263f 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -471,7 +471,7 @@ static int efx_tx_tso_fallback(struct efx_tx_queue *tx_queue, if (IS_ERR(segments)) return PTR_ERR(segments); - dev_kfree_skb_any(skb); + dev_consume_skb_any(skb); skb = segments; while (skb) { diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c index 3140999642ba..358e66b81926 100644 --- a/drivers/net/ethernet/sgi/ioc3-eth.c +++ b/drivers/net/ethernet/sgi/ioc3-eth.c @@ -666,7 +666,7 @@ static inline void ioc3_tx(struct net_device *dev) packets++; skb = ip->tx_skbs[o_entry]; bytes += skb->len; - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); ip->tx_skbs[o_entry] = NULL; o_entry = (o_entry + 1) & 127; /* Next */ diff --git a/drivers/net/ethernet/sgi/meth.c b/drivers/net/ethernet/sgi/meth.c index 0e1b7e960b98..f1271402ca21 100644 --- a/drivers/net/ethernet/sgi/meth.c +++ b/drivers/net/ethernet/sgi/meth.c @@ -68,6 +68,8 @@ module_param(timeout, int, 0); * packets in and out, so there is place for a packet */ struct meth_private { + struct platform_device *pdev; + /* in-memory copy of MAC Control register */ u64 mac_ctrl; @@ -211,8 +213,8 @@ static void meth_check_link(struct net_device *dev) static int meth_init_tx_ring(struct meth_private *priv) { /* Init TX ring */ - priv->tx_ring = dma_alloc_coherent(NULL, TX_RING_BUFFER_SIZE, - &priv->tx_ring_dma, GFP_ATOMIC); + priv->tx_ring = dma_alloc_coherent(&priv->pdev->dev, + TX_RING_BUFFER_SIZE, &priv->tx_ring_dma, GFP_ATOMIC); if (!priv->tx_ring) return -ENOMEM; @@ -236,7 +238,7 @@ static int meth_init_rx_ring(struct meth_private *priv) priv->rx_ring[i]=(rx_packet*)(priv->rx_skbs[i]->head); /* I'll need to re-sync it after each RX */ priv->rx_ring_dmas[i] = - dma_map_single(NULL, priv->rx_ring[i], + dma_map_single(&priv->pdev->dev, priv->rx_ring[i], METH_RX_BUFF_SIZE, DMA_FROM_DEVICE); mace->eth.rx_fifo = priv->rx_ring_dmas[i]; } @@ -253,7 +255,7 @@ static void meth_free_tx_ring(struct meth_private *priv) dev_kfree_skb(priv->tx_skbs[i]); priv->tx_skbs[i] = NULL; } - dma_free_coherent(NULL, TX_RING_BUFFER_SIZE, priv->tx_ring, + dma_free_coherent(&priv->pdev->dev, TX_RING_BUFFER_SIZE, priv->tx_ring, priv->tx_ring_dma); } @@ -263,7 +265,7 @@ static void meth_free_rx_ring(struct meth_private *priv) int i; for (i = 0; i < RX_RING_ENTRIES; i++) { - dma_unmap_single(NULL, priv->rx_ring_dmas[i], + dma_unmap_single(&priv->pdev->dev, priv->rx_ring_dmas[i], METH_RX_BUFF_SIZE, DMA_FROM_DEVICE); priv->rx_ring[i] = 0; priv->rx_ring_dmas[i] = 0; @@ -393,7 +395,8 @@ static void meth_rx(struct net_device* dev, unsigned long int_status) fifo_rptr = (fifo_rptr - 1) & 0x0f; } while (priv->rx_write != fifo_rptr) { - dma_unmap_single(NULL, priv->rx_ring_dmas[priv->rx_write], + dma_unmap_single(&priv->pdev->dev, + priv->rx_ring_dmas[priv->rx_write], METH_RX_BUFF_SIZE, DMA_FROM_DEVICE); status = priv->rx_ring[priv->rx_write]->status.raw; #if MFE_DEBUG @@ -454,7 +457,8 @@ static void meth_rx(struct net_device* dev, unsigned long int_status) priv->rx_ring[priv->rx_write] = (rx_packet*)skb->head; priv->rx_ring[priv->rx_write]->status.raw = 0; priv->rx_ring_dmas[priv->rx_write] = - dma_map_single(NULL, priv->rx_ring[priv->rx_write], + dma_map_single(&priv->pdev->dev, + priv->rx_ring[priv->rx_write], METH_RX_BUFF_SIZE, DMA_FROM_DEVICE); mace->eth.rx_fifo = priv->rx_ring_dmas[priv->rx_write]; ADVANCE_RX_PTR(priv->rx_write); @@ -521,7 +525,7 @@ static void meth_tx_cleanup(struct net_device* dev, unsigned long int_status) DPRINTK("RPTR points us here, but packet not done?\n"); break; } - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); priv->tx_skbs[priv->tx_read] = NULL; priv->tx_ring[priv->tx_read].header.raw = 0; priv->tx_read = (priv->tx_read+1)&(TX_RING_ENTRIES-1); @@ -637,7 +641,7 @@ static void meth_tx_1page_prepare(struct meth_private *priv, } /* first page */ - catbuf = dma_map_single(NULL, buffer_data, buffer_len, + catbuf = dma_map_single(&priv->pdev->dev, buffer_data, buffer_len, DMA_TO_DEVICE); desc->data.cat_buf[0].form.start_addr = catbuf >> 3; desc->data.cat_buf[0].form.len = buffer_len - 1; @@ -663,12 +667,12 @@ static void meth_tx_2page_prepare(struct meth_private *priv, } /* first page */ - catbuf1 = dma_map_single(NULL, buffer1_data, buffer1_len, + catbuf1 = dma_map_single(&priv->pdev->dev, buffer1_data, buffer1_len, DMA_TO_DEVICE); desc->data.cat_buf[0].form.start_addr = catbuf1 >> 3; desc->data.cat_buf[0].form.len = buffer1_len - 1; /* second page */ - catbuf2 = dma_map_single(NULL, buffer2_data, buffer2_len, + catbuf2 = dma_map_single(&priv->pdev->dev, buffer2_data, buffer2_len, DMA_TO_DEVICE); desc->data.cat_buf[1].form.start_addr = catbuf2 >> 3; desc->data.cat_buf[1].form.len = buffer2_len - 1; @@ -840,6 +844,7 @@ static int meth_probe(struct platform_device *pdev) memcpy(dev->dev_addr, o2meth_eaddr, ETH_ALEN); priv = netdev_priv(dev); + priv->pdev = pdev; spin_lock_init(&priv->meth_lock); SET_NETDEV_DEV(dev, &pdev->dev); diff --git a/drivers/net/ethernet/sis/sis190.c b/drivers/net/ethernet/sis/sis190.c index 808cf9816673..5b351beb78cb 100644 --- a/drivers/net/ethernet/sis/sis190.c +++ b/drivers/net/ethernet/sis/sis190.c @@ -714,7 +714,7 @@ static void sis190_tx_interrupt(struct net_device *dev, sis190_unmap_tx_skb(tp->pci_dev, skb, txd); tp->Tx_skbuff[entry] = NULL; - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); } if (tp->dirty_tx != dirty_tx) { diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c index 4bb89f74742c..6073387511f8 100644 --- a/drivers/net/ethernet/sis/sis900.c +++ b/drivers/net/ethernet/sis/sis900.c @@ -1927,7 +1927,7 @@ static void sis900_finish_xmit (struct net_device *net_dev) pci_unmap_single(sis_priv->pci_dev, sis_priv->tx_ring[entry].bufptr, skb->len, PCI_DMA_TODEVICE); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); sis_priv->tx_skbuff[entry] = NULL; sis_priv->tx_ring[entry].bufptr = 0; sis_priv->tx_ring[entry].cmdsts = 0; diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c index 15c62c160953..be47d864f8b9 100644 --- a/drivers/net/ethernet/smsc/epic100.c +++ b/drivers/net/ethernet/smsc/epic100.c @@ -1037,7 +1037,7 @@ static void epic_tx(struct net_device *dev, struct epic_private *ep) skb = ep->tx_skbuff[entry]; pci_unmap_single(ep->pci_dev, ep->tx_ring[entry].bufaddr, skb->len, PCI_DMA_TODEVICE); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); ep->tx_skbuff[entry] = NULL; } diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c index 8355dfbb8ec3..b550e624500d 100644 --- a/drivers/net/ethernet/smsc/smc911x.c +++ b/drivers/net/ethernet/smsc/smc911x.c @@ -1188,7 +1188,7 @@ smc911x_tx_dma_irq(void *data) DBG(SMC_DEBUG_TX | SMC_DEBUG_DMA, dev, "TX DMA irq handler\n"); BUG_ON(skb == NULL); - dma_unmap_single(NULL, tx_dmabuf, tx_dmalen, DMA_TO_DEVICE); + dma_unmap_single(lp->dev, tx_dmabuf, tx_dmalen, DMA_TO_DEVICE); netif_trans_update(dev); dev_kfree_skb_irq(skb); lp->current_tx_skb = NULL; @@ -1219,7 +1219,7 @@ smc911x_rx_dma_irq(void *data) DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); DBG(SMC_DEBUG_RX | SMC_DEBUG_DMA, dev, "RX DMA irq handler\n"); - dma_unmap_single(NULL, rx_dmabuf, rx_dmalen, DMA_FROM_DEVICE); + dma_unmap_single(lp->dev, rx_dmabuf, rx_dmalen, DMA_FROM_DEVICE); BUG_ON(skb == NULL); lp->current_rx_skb = NULL; PRINT_PKT(skb->data, skb->len); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c index 20299f6f65fc..7fbb6a4dbf51 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c @@ -241,15 +241,18 @@ static inline void dwmac4_get_timestamp(void *desc, u32 ats, u64 *ts) static int dwmac4_rx_check_timestamp(void *desc) { struct dma_desc *p = (struct dma_desc *)desc; + unsigned int rdes0 = le32_to_cpu(p->des0); + unsigned int rdes1 = le32_to_cpu(p->des1); + unsigned int rdes3 = le32_to_cpu(p->des3); u32 own, ctxt; int ret = 1; - own = p->des3 & RDES3_OWN; - ctxt = ((p->des3 & RDES3_CONTEXT_DESCRIPTOR) + own = rdes3 & RDES3_OWN; + ctxt = ((rdes3 & RDES3_CONTEXT_DESCRIPTOR) >> RDES3_CONTEXT_DESCRIPTOR_SHIFT); if (likely(!own && ctxt)) { - if ((p->des0 == 0xffffffff) && (p->des1 == 0xffffffff)) + if ((rdes0 == 0xffffffff) && (rdes1 == 0xffffffff)) /* Corrupted value */ ret = -EINVAL; else @@ -268,7 +271,7 @@ static int dwmac4_wrback_get_rx_timestamp_status(void *desc, void *next_desc, int ret = -EINVAL; /* Get the status from normal w/b descriptor */ - if (likely(p->des3 & TDES3_RS1V)) { + if (likely(le32_to_cpu(p->des3) & RDES3_RDES1_VALID)) { if (likely(le32_to_cpu(p->des1) & RDES1_TIMESTAMP_AVAILABLE)) { int i = 0; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c index 49f5687879df..545cb9c47433 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c @@ -124,9 +124,9 @@ void dwmac4_disable_dma_irq(void __iomem *ioaddr, u32 chan) int dwmac4_dma_interrupt(void __iomem *ioaddr, struct stmmac_extra_stats *x, u32 chan) { - int ret = 0; - u32 intr_status = readl(ioaddr + DMA_CHAN_STATUS(chan)); + u32 intr_en = readl(ioaddr + DMA_CHAN_INTR_ENA(chan)); + int ret = 0; /* ABNORMAL interrupts */ if (unlikely(intr_status & DMA_CHAN_STATUS_AIS)) { @@ -151,16 +151,11 @@ int dwmac4_dma_interrupt(void __iomem *ioaddr, if (likely(intr_status & DMA_CHAN_STATUS_NIS)) { x->normal_irq_n++; if (likely(intr_status & DMA_CHAN_STATUS_RI)) { - u32 value; - - value = readl(ioaddr + DMA_CHAN_INTR_ENA(chan)); - /* to schedule NAPI on real RIE event. */ - if (likely(value & DMA_CHAN_INTR_ENA_RIE)) { - x->rx_normal_irq_n++; - ret |= handle_rx; - } + x->rx_normal_irq_n++; + ret |= handle_rx; } - if (likely(intr_status & DMA_CHAN_STATUS_TI)) { + if (likely(intr_status & (DMA_CHAN_STATUS_TI | + DMA_CHAN_STATUS_TBU))) { x->tx_normal_irq_n++; ret |= handle_tx; } @@ -168,12 +163,7 @@ int dwmac4_dma_interrupt(void __iomem *ioaddr, x->rx_early_irq++; } - /* Clear the interrupt by writing a logic 1 to the chanX interrupt - * status [21-0] expect reserved bits [5-3] - */ - writel((intr_status & 0x3fffc7), - ioaddr + DMA_CHAN_STATUS(chan)); - + writel(intr_status & intr_en, ioaddr + DMA_CHAN_STATUS(chan)); return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h index d6bb953685fa..37d5e6fe7473 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h @@ -193,9 +193,10 @@ #define XGMAC_AIE BIT(14) #define XGMAC_RBUE BIT(7) #define XGMAC_RIE BIT(6) +#define XGMAC_TBUE BIT(2) #define XGMAC_TIE BIT(0) #define XGMAC_DMA_INT_DEFAULT_EN (XGMAC_NIE | XGMAC_AIE | XGMAC_RBUE | \ - XGMAC_RIE | XGMAC_TIE) + XGMAC_RIE | XGMAC_TBUE | XGMAC_TIE) #define XGMAC_DMA_CH_Rx_WATCHDOG(x) (0x0000313c + (0x80 * (x))) #define XGMAC_RWT GENMASK(7, 0) #define XGMAC_DMA_CH_STATUS(x) (0x00003160 + (0x80 * (x))) @@ -204,6 +205,7 @@ #define XGMAC_FBE BIT(12) #define XGMAC_RBU BIT(7) #define XGMAC_RI BIT(6) +#define XGMAC_TBU BIT(2) #define XGMAC_TPS BIT(1) #define XGMAC_TI BIT(0) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c index c5e25580a43f..2ba712b48a89 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c @@ -283,12 +283,10 @@ static int dwxgmac2_dma_interrupt(void __iomem *ioaddr, x->normal_irq_n++; if (likely(intr_status & XGMAC_RI)) { - if (likely(intr_en & XGMAC_RIE)) { - x->rx_normal_irq_n++; - ret |= handle_rx; - } + x->rx_normal_irq_n++; + ret |= handle_rx; } - if (likely(intr_status & XGMAC_TI)) { + if (likely(intr_status & (XGMAC_TI | XGMAC_TBU))) { x->tx_normal_irq_n++; ret |= handle_tx; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index f9b42b0c20f4..dd95d959c1ce 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -79,11 +79,10 @@ struct stmmac_rx_queue { }; struct stmmac_channel { - struct napi_struct napi ____cacheline_aligned_in_smp; + struct napi_struct rx_napi ____cacheline_aligned_in_smp; + struct napi_struct tx_napi ____cacheline_aligned_in_smp; struct stmmac_priv *priv_data; u32 index; - int has_rx; - int has_tx; }; struct stmmac_tc_entry { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index d1f61c25d82b..3c749c327cbd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -696,33 +696,38 @@ static int stmmac_ethtool_op_set_eee(struct net_device *dev, struct ethtool_eee *edata) { struct stmmac_priv *priv = netdev_priv(dev); + int ret; - priv->eee_enabled = edata->eee_enabled; - - if (!priv->eee_enabled) + if (!edata->eee_enabled) { stmmac_disable_eee_mode(priv); - else { + } else { /* We are asking for enabling the EEE but it is safe * to verify all by invoking the eee_init function. * In case of failure it will return an error. */ - priv->eee_enabled = stmmac_eee_init(priv); - if (!priv->eee_enabled) + edata->eee_enabled = stmmac_eee_init(priv); + if (!edata->eee_enabled) return -EOPNOTSUPP; - - /* Do not change tx_lpi_timer in case of failure */ - priv->tx_lpi_timer = edata->tx_lpi_timer; } - return phy_ethtool_set_eee(dev->phydev, edata); + ret = phy_ethtool_set_eee(dev->phydev, edata); + if (ret) + return ret; + + priv->eee_enabled = edata->eee_enabled; + priv->tx_lpi_timer = edata->tx_lpi_timer; + return 0; } static u32 stmmac_usec2riwt(u32 usec, struct stmmac_priv *priv) { unsigned long clk = clk_get_rate(priv->plat->stmmac_clk); - if (!clk) - return 0; + if (!clk) { + clk = priv->plat->clk_ref_rate; + if (!clk) + return 0; + } return (usec * (clk / 1000000)) / 256; } @@ -731,8 +736,11 @@ static u32 stmmac_riwt2usec(u32 riwt, struct stmmac_priv *priv) { unsigned long clk = clk_get_rate(priv->plat->stmmac_clk); - if (!clk) - return 0; + if (!clk) { + clk = priv->plat->clk_ref_rate; + if (!clk) + return 0; + } return (riwt * 256) / (clk / 1000000); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index effff171d250..e2a13ec2e30b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -155,7 +155,10 @@ static void stmmac_disable_all_queues(struct stmmac_priv *priv) for (queue = 0; queue < maxq; queue++) { struct stmmac_channel *ch = &priv->channel[queue]; - napi_disable(&ch->napi); + if (queue < rx_queues_cnt) + napi_disable(&ch->rx_napi); + if (queue < tx_queues_cnt) + napi_disable(&ch->tx_napi); } } @@ -173,7 +176,10 @@ static void stmmac_enable_all_queues(struct stmmac_priv *priv) for (queue = 0; queue < maxq; queue++) { struct stmmac_channel *ch = &priv->channel[queue]; - napi_enable(&ch->napi); + if (queue < rx_queues_cnt) + napi_enable(&ch->rx_napi); + if (queue < tx_queues_cnt) + napi_enable(&ch->tx_napi); } } @@ -1955,6 +1961,10 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue) mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(eee_timer)); } + /* We still have pending packets, let's call for a new scheduling */ + if (tx_q->dirty_tx != tx_q->cur_tx) + mod_timer(&tx_q->txtimer, STMMAC_COAL_TIMER(10)); + __netif_tx_unlock_bh(netdev_get_tx_queue(priv->dev, queue)); return count; @@ -2045,23 +2055,15 @@ static int stmmac_napi_check(struct stmmac_priv *priv, u32 chan) int status = stmmac_dma_interrupt_status(priv, priv->ioaddr, &priv->xstats, chan); struct stmmac_channel *ch = &priv->channel[chan]; - bool needs_work = false; - if ((status & handle_rx) && ch->has_rx) { - needs_work = true; - } else { - status &= ~handle_rx; - } - - if ((status & handle_tx) && ch->has_tx) { - needs_work = true; - } else { - status &= ~handle_tx; + if ((status & handle_rx) && (chan < priv->plat->rx_queues_to_use)) { + stmmac_disable_dma_irq(priv, priv->ioaddr, chan); + napi_schedule_irqoff(&ch->rx_napi); } - if (needs_work && napi_schedule_prep(&ch->napi)) { + if ((status & handle_tx) && (chan < priv->plat->tx_queues_to_use)) { stmmac_disable_dma_irq(priv, priv->ioaddr, chan); - __napi_schedule(&ch->napi); + napi_schedule_irqoff(&ch->tx_napi); } return status; @@ -2257,8 +2259,14 @@ static void stmmac_tx_timer(struct timer_list *t) ch = &priv->channel[tx_q->queue_index]; - if (likely(napi_schedule_prep(&ch->napi))) - __napi_schedule(&ch->napi); + /* + * If NAPI is already running we can miss some events. Let's rearm + * the timer and try again. + */ + if (likely(napi_schedule_prep(&ch->tx_napi))) + __napi_schedule(&ch->tx_napi); + else + mod_timer(&tx_q->txtimer, STMMAC_COAL_TIMER(10)); } /** @@ -3039,10 +3047,22 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) tx_q = &priv->tx_queue[queue]; + if (priv->tx_path_in_lpi_mode) + stmmac_disable_eee_mode(priv); + /* Manage oversized TCP frames for GMAC4 device */ if (skb_is_gso(skb) && priv->tso) { - if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) + if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) { + /* + * There is no way to determine the number of TSO + * capable Queues. Let's use always the Queue 0 + * because if TSO is supported then at least this + * one will be capable. + */ + skb_set_queue_mapping(skb, 0); + return stmmac_tso_xmit(skb, dev); + } } if (unlikely(stmmac_tx_avail(priv, queue) < nfrags + 1)) { @@ -3057,9 +3077,6 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_BUSY; } - if (priv->tx_path_in_lpi_mode) - stmmac_disable_eee_mode(priv); - entry = tx_q->cur_tx; first_entry = entry; WARN_ON(tx_q->tx_skbuff[first_entry]); @@ -3505,7 +3522,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) else skb->ip_summed = CHECKSUM_UNNECESSARY; - napi_gro_receive(&ch->napi, skb); + napi_gro_receive(&ch->rx_napi, skb); priv->dev->stats.rx_packets++; priv->dev->stats.rx_bytes += frame_len; @@ -3520,40 +3537,45 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) return count; } -/** - * stmmac_poll - stmmac poll method (NAPI) - * @napi : pointer to the napi structure. - * @budget : maximum number of packets that the current CPU can receive from - * all interfaces. - * Description : - * To look at the incoming frames and clear the tx resources. - */ -static int stmmac_napi_poll(struct napi_struct *napi, int budget) +static int stmmac_napi_poll_rx(struct napi_struct *napi, int budget) { struct stmmac_channel *ch = - container_of(napi, struct stmmac_channel, napi); + container_of(napi, struct stmmac_channel, rx_napi); struct stmmac_priv *priv = ch->priv_data; - int work_done, rx_done = 0, tx_done = 0; u32 chan = ch->index; + int work_done; priv->xstats.napi_poll++; - if (ch->has_tx) - tx_done = stmmac_tx_clean(priv, budget, chan); - if (ch->has_rx) - rx_done = stmmac_rx(priv, budget, chan); + work_done = stmmac_rx(priv, budget, chan); + if (work_done < budget && napi_complete_done(napi, work_done)) + stmmac_enable_dma_irq(priv, priv->ioaddr, chan); + return work_done; +} - work_done = max(rx_done, tx_done); - work_done = min(work_done, budget); +static int stmmac_napi_poll_tx(struct napi_struct *napi, int budget) +{ + struct stmmac_channel *ch = + container_of(napi, struct stmmac_channel, tx_napi); + struct stmmac_priv *priv = ch->priv_data; + struct stmmac_tx_queue *tx_q; + u32 chan = ch->index; + int work_done; + + priv->xstats.napi_poll++; - if (work_done < budget && napi_complete_done(napi, work_done)) { - int stat; + work_done = stmmac_tx_clean(priv, DMA_TX_SIZE, chan); + work_done = min(work_done, budget); + if (work_done < budget && napi_complete_done(napi, work_done)) stmmac_enable_dma_irq(priv, priv->ioaddr, chan); - stat = stmmac_dma_interrupt_status(priv, priv->ioaddr, - &priv->xstats, chan); - if (stat && napi_reschedule(napi)) - stmmac_disable_dma_irq(priv, priv->ioaddr, chan); + + /* Force transmission restart */ + tx_q = &priv->tx_queue[chan]; + if (tx_q->cur_tx != tx_q->dirty_tx) { + stmmac_enable_dma_transmission(priv, priv->ioaddr); + stmmac_set_tx_tail_ptr(priv, priv->ioaddr, tx_q->tx_tail_addr, + chan); } return work_done; @@ -4333,13 +4355,14 @@ int stmmac_dvr_probe(struct device *device, ch->priv_data = priv; ch->index = queue; - if (queue < priv->plat->rx_queues_to_use) - ch->has_rx = true; - if (queue < priv->plat->tx_queues_to_use) - ch->has_tx = true; - - netif_napi_add(ndev, &ch->napi, stmmac_napi_poll, - NAPI_POLL_WEIGHT); + if (queue < priv->plat->rx_queues_to_use) { + netif_napi_add(ndev, &ch->rx_napi, stmmac_napi_poll_rx, + NAPI_POLL_WEIGHT); + } + if (queue < priv->plat->tx_queues_to_use) { + netif_napi_add(ndev, &ch->tx_napi, stmmac_napi_poll_tx, + NAPI_POLL_WEIGHT); + } } mutex_init(&priv->lock); @@ -4395,7 +4418,10 @@ error_mdio_register: for (queue = 0; queue < maxq; queue++) { struct stmmac_channel *ch = &priv->channel[queue]; - netif_napi_del(&ch->napi); + if (queue < priv->plat->rx_queues_to_use) + netif_napi_del(&ch->rx_napi); + if (queue < priv->plat->tx_queues_to_use) + netif_napi_del(&ch->tx_napi); } error_hw_init: destroy_workqueue(priv->wq); diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index 7ec4eb74fe21..6fc05c106afc 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -1898,7 +1898,7 @@ static inline void cas_tx_ringN(struct cas *cp, int ring, int limit) cp->net_stats[ring].tx_packets++; cp->net_stats[ring].tx_bytes += skb->len; spin_unlock(&cp->stat_lock[ring]); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); } cp->tx_old[ring] = entry; diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c index 720b7ac77f3b..e9b757b03b56 100644 --- a/drivers/net/ethernet/sun/sunbmac.c +++ b/drivers/net/ethernet/sun/sunbmac.c @@ -781,7 +781,7 @@ static void bigmac_tx(struct bigmac *bp) DTX(("skb(%p) ", skb)); bp->tx_skbs[elem] = NULL; - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); elem = NEXT_TX(elem); } diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c index ff641cf30a4e..d007dfeba5c3 100644 --- a/drivers/net/ethernet/sun/sunhme.c +++ b/drivers/net/ethernet/sun/sunhme.c @@ -1962,7 +1962,7 @@ static void happy_meal_tx(struct happy_meal *hp) this = &txbase[elem]; } - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); dev->stats.tx_packets++; } hp->tx_old = elem; diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c index dc966ddb6d81..b24c11187017 100644 --- a/drivers/net/ethernet/tehuti/tehuti.c +++ b/drivers/net/ethernet/tehuti/tehuti.c @@ -1739,7 +1739,7 @@ static void bdx_tx_cleanup(struct bdx_priv *priv) tx_level -= db->rptr->len; /* '-' koz len is negative */ /* now should come skb pointer - free it */ - dev_kfree_skb_irq(db->rptr->addr.skb); + dev_consume_skb_irq(db->rptr->addr.skb); bdx_tx_db_inc_rptr(db); } diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index 1f612268c998..d847f672a705 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -259,7 +259,7 @@ static int netcp_module_probe(struct netcp_device *netcp_device, const char *name; char node_name[32]; - if (of_property_read_string(node, "label", &name) < 0) { + if (of_property_read_string(child, "label", &name) < 0) { snprintf(node_name, sizeof(node_name), "%pOFn", child); name = node_name; } diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c index 82412691ee66..27f6cf140845 100644 --- a/drivers/net/ethernet/via/via-velocity.c +++ b/drivers/net/ethernet/via/via-velocity.c @@ -1740,7 +1740,7 @@ static void velocity_free_tx_buf(struct velocity_info *vptr, dma_unmap_single(vptr->dev, tdinfo->skb_dma[i], le16_to_cpu(pktlen), DMA_TO_DEVICE); } - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); tdinfo->skb = NULL; } diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index 15bb058db392..44efffbe7970 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -630,7 +630,7 @@ static void temac_start_xmit_done(struct net_device *ndev) dma_unmap_single(ndev->dev.parent, cur_p->phys, cur_p->len, DMA_TO_DEVICE); if (cur_p->app4) - dev_kfree_skb_irq((struct sk_buff *)cur_p->app4); + dev_consume_skb_irq((struct sk_buff *)cur_p->app4); cur_p->app0 = 0; cur_p->app1 = 0; cur_p->app2 = 0; diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 0789d8af7d72..ec7e7ec24ff9 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -595,7 +595,7 @@ static void axienet_start_xmit_done(struct net_device *ndev) (cur_p->cntrl & XAXIDMA_BD_CTRL_LENGTH_MASK), DMA_TO_DEVICE); if (cur_p->app4) - dev_kfree_skb_irq((struct sk_buff *)cur_p->app4); + dev_consume_skb_irq((struct sk_buff *)cur_p->app4); /*cur_p->phys = 0;*/ cur_p->app0 = 0; cur_p->app1 = 0; diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c index 639e3e99af46..b03a417d0073 100644 --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c @@ -581,7 +581,7 @@ static void xemaclite_tx_handler(struct net_device *dev) return; dev->stats.tx_bytes += lp->deferred_skb->len; - dev_kfree_skb_irq(lp->deferred_skb); + dev_consume_skb_irq(lp->deferred_skb); lp->deferred_skb = NULL; netif_trans_update(dev); /* prevent tx timeout */ netif_wake_queue(dev); diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c index aee55c03def0..ed6623a9801e 100644 --- a/drivers/net/ethernet/xscale/ixp4xx_eth.c +++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c @@ -139,7 +139,7 @@ #ifdef __ARMEB__ typedef struct sk_buff buffer_t; #define free_buffer dev_kfree_skb -#define free_buffer_irq dev_kfree_skb_irq +#define free_buffer_irq dev_consume_skb_irq #else typedef void buffer_t; #define free_buffer kfree diff --git a/drivers/net/fddi/defxx.c b/drivers/net/fddi/defxx.c index 38ac8ef41f5f..56b7791911bf 100644 --- a/drivers/net/fddi/defxx.c +++ b/drivers/net/fddi/defxx.c @@ -3512,7 +3512,7 @@ static int dfx_xmt_done(DFX_board_t *bp) bp->descr_block_virt->xmt_data[comp].long_1, p_xmt_drv_descr->p_skb->len, DMA_TO_DEVICE); - dev_kfree_skb_irq(p_xmt_drv_descr->p_skb); + dev_consume_skb_irq(p_xmt_drv_descr->p_skb); /* * Move to start of next packet by updating completion index diff --git a/drivers/net/fddi/skfp/pcmplc.c b/drivers/net/fddi/skfp/pcmplc.c index 6ef44c480bd5..f29f5a6a45ab 100644 --- a/drivers/net/fddi/skfp/pcmplc.c +++ b/drivers/net/fddi/skfp/pcmplc.c @@ -851,6 +851,7 @@ static void pcm_fsm(struct s_smc *smc, struct s_phy *phy, int cmd) case ACTIONS(PC5_SIGNAL) : ACTIONS_DONE() ; + /* fall through */ case PC5_SIGNAL : if ((cmd != PC_SIGNAL) && (cmd != PC_TIMEOUT_LCT)) break ; diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 58bbba8582b0..3377ac66a347 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1512,9 +1512,13 @@ static void geneve_link_config(struct net_device *dev, } #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: { - struct rt6_info *rt = rt6_lookup(geneve->net, - &info->key.u.ipv6.dst, NULL, 0, - NULL, 0); + struct rt6_info *rt; + + if (!__in6_dev_get(dev)) + break; + + rt = rt6_lookup(geneve->net, &info->key.u.ipv6.dst, NULL, 0, + NULL, 0); if (rt && rt->dst.dev) ldev_mtu = rt->dst.dev->mtu - GENEVE_IPV6_HLEN; diff --git a/drivers/net/hamradio/baycom_ser_fdx.c b/drivers/net/hamradio/baycom_ser_fdx.c index 190f66c88479..ed0841630990 100644 --- a/drivers/net/hamradio/baycom_ser_fdx.c +++ b/drivers/net/hamradio/baycom_ser_fdx.c @@ -203,32 +203,6 @@ static inline void ser12_set_divisor(struct net_device *dev, */ } -/* --------------------------------------------------------------------- */ - -#if 0 -static inline unsigned int hweight16(unsigned int w) - __attribute__ ((unused)); -static inline unsigned int hweight8(unsigned int w) - __attribute__ ((unused)); - -static inline unsigned int hweight16(unsigned int w) -{ - unsigned short res = (w & 0x5555) + ((w >> 1) & 0x5555); - res = (res & 0x3333) + ((res >> 2) & 0x3333); - res = (res & 0x0F0F) + ((res >> 4) & 0x0F0F); - return (res & 0x00FF) + ((res >> 8) & 0x00FF); -} - -static inline unsigned int hweight8(unsigned int w) -{ - unsigned short res = (w & 0x55) + ((w >> 1) & 0x55); - res = (res & 0x33) + ((res >> 2) & 0x33); - return (res & 0x0F) + ((res >> 4) & 0x0F); -} -#endif - -/* --------------------------------------------------------------------- */ - static __inline__ void ser12_rx(struct net_device *dev, struct baycom_state *bc, struct timespec64 *ts, unsigned char curs) { int timediff; diff --git a/drivers/net/ieee802154/mcr20a.c b/drivers/net/ieee802154/mcr20a.c index 44de81e5f140..c589f5ae75bb 100644 --- a/drivers/net/ieee802154/mcr20a.c +++ b/drivers/net/ieee802154/mcr20a.c @@ -905,9 +905,9 @@ mcr20a_irq_clean_complete(void *context) } break; case (DAR_IRQSTS1_RXIRQ | DAR_IRQSTS1_SEQIRQ): - /* rx is starting */ - dev_dbg(printdev(lp), "RX is starting\n"); - mcr20a_handle_rx(lp); + /* rx is starting */ + dev_dbg(printdev(lp), "RX is starting\n"); + mcr20a_handle_rx(lp); break; case (DAR_IRQSTS1_RXIRQ | DAR_IRQSTS1_TXIRQ | DAR_IRQSTS1_SEQIRQ): if (lp->is_tx) { diff --git a/drivers/net/ipvlan/Makefile b/drivers/net/ipvlan/Makefile index 8a2c64dc9641..3ee95367a994 100644 --- a/drivers/net/ipvlan/Makefile +++ b/drivers/net/ipvlan/Makefile @@ -5,4 +5,5 @@ obj-$(CONFIG_IPVLAN) += ipvlan.o obj-$(CONFIG_IPVTAP) += ipvtap.o -ipvlan-objs := ipvlan_core.o ipvlan_main.o +ipvlan-objs-$(CONFIG_IPVLAN_L3S) += ipvlan_l3s.o +ipvlan-objs := ipvlan_core.o ipvlan_main.o $(ipvlan-objs-y) diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h index adb826f55e60..b906d2f6bd04 100644 --- a/drivers/net/ipvlan/ipvlan.h +++ b/drivers/net/ipvlan/ipvlan.h @@ -165,10 +165,9 @@ struct ipvl_addr *ipvlan_find_addr(const struct ipvl_dev *ipvlan, const void *iaddr, bool is_v6); bool ipvlan_addr_busy(struct ipvl_port *port, void *iaddr, bool is_v6); void ipvlan_ht_addr_del(struct ipvl_addr *addr); -struct sk_buff *ipvlan_l3_rcv(struct net_device *dev, struct sk_buff *skb, - u16 proto); -unsigned int ipvlan_nf_input(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state); +struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, void *lyr3h, + int addr_type, bool use_dest); +void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int *type); void ipvlan_count_rx(const struct ipvl_dev *ipvlan, unsigned int len, bool success, bool mcast); int ipvlan_link_new(struct net *src_net, struct net_device *dev, @@ -177,6 +176,36 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev, void ipvlan_link_delete(struct net_device *dev, struct list_head *head); void ipvlan_link_setup(struct net_device *dev); int ipvlan_link_register(struct rtnl_link_ops *ops); +#ifdef CONFIG_IPVLAN_L3S +int ipvlan_l3s_register(struct ipvl_port *port); +void ipvlan_l3s_unregister(struct ipvl_port *port); +void ipvlan_migrate_l3s_hook(struct net *oldnet, struct net *newnet); +int ipvlan_l3s_init(void); +void ipvlan_l3s_cleanup(void); +#else +static inline int ipvlan_l3s_register(struct ipvl_port *port) +{ + return -ENOTSUPP; +} + +static inline void ipvlan_l3s_unregister(struct ipvl_port *port) +{ +} + +static inline void ipvlan_migrate_l3s_hook(struct net *oldnet, + struct net *newnet) +{ +} + +static inline int ipvlan_l3s_init(void) +{ + return 0; +} + +static inline void ipvlan_l3s_cleanup(void) +{ +} +#endif /* CONFIG_IPVLAN_L3S */ static inline bool netif_is_ipvlan_port(const struct net_device *dev) { diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 1a8132eb2a3e..e0f5bc82b10c 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -138,7 +138,7 @@ bool ipvlan_addr_busy(struct ipvl_port *port, void *iaddr, bool is_v6) return ret; } -static void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int *type) +void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int *type) { void *lyr3h = NULL; @@ -355,9 +355,8 @@ out: return ret; } -static struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, - void *lyr3h, int addr_type, - bool use_dest) +struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, void *lyr3h, + int addr_type, bool use_dest) { struct ipvl_addr *addr = NULL; @@ -647,7 +646,9 @@ int ipvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev) case IPVLAN_MODE_L2: return ipvlan_xmit_mode_l2(skb, dev); case IPVLAN_MODE_L3: +#ifdef CONFIG_IPVLAN_L3S case IPVLAN_MODE_L3S: +#endif return ipvlan_xmit_mode_l3(skb, dev); } @@ -743,8 +744,10 @@ rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb) return ipvlan_handle_mode_l2(pskb, port); case IPVLAN_MODE_L3: return ipvlan_handle_mode_l3(pskb, port); +#ifdef CONFIG_IPVLAN_L3S case IPVLAN_MODE_L3S: return RX_HANDLER_PASS; +#endif } /* Should not reach here */ @@ -753,97 +756,3 @@ rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb) kfree_skb(skb); return RX_HANDLER_CONSUMED; } - -static struct ipvl_addr *ipvlan_skb_to_addr(struct sk_buff *skb, - struct net_device *dev) -{ - struct ipvl_addr *addr = NULL; - struct ipvl_port *port; - void *lyr3h; - int addr_type; - - if (!dev || !netif_is_ipvlan_port(dev)) - goto out; - - port = ipvlan_port_get_rcu(dev); - if (!port || port->mode != IPVLAN_MODE_L3S) - goto out; - - lyr3h = ipvlan_get_L3_hdr(port, skb, &addr_type); - if (!lyr3h) - goto out; - - addr = ipvlan_addr_lookup(port, lyr3h, addr_type, true); -out: - return addr; -} - -struct sk_buff *ipvlan_l3_rcv(struct net_device *dev, struct sk_buff *skb, - u16 proto) -{ - struct ipvl_addr *addr; - struct net_device *sdev; - - addr = ipvlan_skb_to_addr(skb, dev); - if (!addr) - goto out; - - sdev = addr->master->dev; - switch (proto) { - case AF_INET: - { - int err; - struct iphdr *ip4h = ip_hdr(skb); - - err = ip_route_input_noref(skb, ip4h->daddr, ip4h->saddr, - ip4h->tos, sdev); - if (unlikely(err)) - goto out; - break; - } -#if IS_ENABLED(CONFIG_IPV6) - case AF_INET6: - { - struct dst_entry *dst; - struct ipv6hdr *ip6h = ipv6_hdr(skb); - int flags = RT6_LOOKUP_F_HAS_SADDR; - struct flowi6 fl6 = { - .flowi6_iif = sdev->ifindex, - .daddr = ip6h->daddr, - .saddr = ip6h->saddr, - .flowlabel = ip6_flowinfo(ip6h), - .flowi6_mark = skb->mark, - .flowi6_proto = ip6h->nexthdr, - }; - - skb_dst_drop(skb); - dst = ip6_route_input_lookup(dev_net(sdev), sdev, &fl6, - skb, flags); - skb_dst_set(skb, dst); - break; - } -#endif - default: - break; - } - -out: - return skb; -} - -unsigned int ipvlan_nf_input(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - struct ipvl_addr *addr; - unsigned int len; - - addr = ipvlan_skb_to_addr(skb, skb->dev); - if (!addr) - goto out; - - skb->dev = addr->master->dev; - len = skb->len + ETH_HLEN; - ipvlan_count_rx(addr->master, len, true, false); -out: - return NF_ACCEPT; -} diff --git a/drivers/net/ipvlan/ipvlan_l3s.c b/drivers/net/ipvlan/ipvlan_l3s.c new file mode 100644 index 000000000000..d17480a911a3 --- /dev/null +++ b/drivers/net/ipvlan/ipvlan_l3s.c @@ -0,0 +1,227 @@ +/* Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of + * the License, or (at your option) any later version. + */ + +#include "ipvlan.h" + +static unsigned int ipvlan_netid __read_mostly; + +struct ipvlan_netns { + unsigned int ipvl_nf_hook_refcnt; +}; + +static struct ipvl_addr *ipvlan_skb_to_addr(struct sk_buff *skb, + struct net_device *dev) +{ + struct ipvl_addr *addr = NULL; + struct ipvl_port *port; + int addr_type; + void *lyr3h; + + if (!dev || !netif_is_ipvlan_port(dev)) + goto out; + + port = ipvlan_port_get_rcu(dev); + if (!port || port->mode != IPVLAN_MODE_L3S) + goto out; + + lyr3h = ipvlan_get_L3_hdr(port, skb, &addr_type); + if (!lyr3h) + goto out; + + addr = ipvlan_addr_lookup(port, lyr3h, addr_type, true); +out: + return addr; +} + +static struct sk_buff *ipvlan_l3_rcv(struct net_device *dev, + struct sk_buff *skb, u16 proto) +{ + struct ipvl_addr *addr; + struct net_device *sdev; + + addr = ipvlan_skb_to_addr(skb, dev); + if (!addr) + goto out; + + sdev = addr->master->dev; + switch (proto) { + case AF_INET: + { + struct iphdr *ip4h = ip_hdr(skb); + int err; + + err = ip_route_input_noref(skb, ip4h->daddr, ip4h->saddr, + ip4h->tos, sdev); + if (unlikely(err)) + goto out; + break; + } +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + { + struct dst_entry *dst; + struct ipv6hdr *ip6h = ipv6_hdr(skb); + int flags = RT6_LOOKUP_F_HAS_SADDR; + struct flowi6 fl6 = { + .flowi6_iif = sdev->ifindex, + .daddr = ip6h->daddr, + .saddr = ip6h->saddr, + .flowlabel = ip6_flowinfo(ip6h), + .flowi6_mark = skb->mark, + .flowi6_proto = ip6h->nexthdr, + }; + + skb_dst_drop(skb); + dst = ip6_route_input_lookup(dev_net(sdev), sdev, &fl6, + skb, flags); + skb_dst_set(skb, dst); + break; + } +#endif + default: + break; + } +out: + return skb; +} + +static const struct l3mdev_ops ipvl_l3mdev_ops = { + .l3mdev_l3_rcv = ipvlan_l3_rcv, +}; + +static unsigned int ipvlan_nf_input(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct ipvl_addr *addr; + unsigned int len; + + addr = ipvlan_skb_to_addr(skb, skb->dev); + if (!addr) + goto out; + + skb->dev = addr->master->dev; + len = skb->len + ETH_HLEN; + ipvlan_count_rx(addr->master, len, true, false); +out: + return NF_ACCEPT; +} + +static const struct nf_hook_ops ipvl_nfops[] = { + { + .hook = ipvlan_nf_input, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_LOCAL_IN, + .priority = INT_MAX, + }, +#if IS_ENABLED(CONFIG_IPV6) + { + .hook = ipvlan_nf_input, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_IN, + .priority = INT_MAX, + }, +#endif +}; + +static int ipvlan_register_nf_hook(struct net *net) +{ + struct ipvlan_netns *vnet = net_generic(net, ipvlan_netid); + int err = 0; + + if (!vnet->ipvl_nf_hook_refcnt) { + err = nf_register_net_hooks(net, ipvl_nfops, + ARRAY_SIZE(ipvl_nfops)); + if (!err) + vnet->ipvl_nf_hook_refcnt = 1; + } else { + vnet->ipvl_nf_hook_refcnt++; + } + + return err; +} + +static void ipvlan_unregister_nf_hook(struct net *net) +{ + struct ipvlan_netns *vnet = net_generic(net, ipvlan_netid); + + if (WARN_ON(!vnet->ipvl_nf_hook_refcnt)) + return; + + vnet->ipvl_nf_hook_refcnt--; + if (!vnet->ipvl_nf_hook_refcnt) + nf_unregister_net_hooks(net, ipvl_nfops, + ARRAY_SIZE(ipvl_nfops)); +} + +void ipvlan_migrate_l3s_hook(struct net *oldnet, struct net *newnet) +{ + struct ipvlan_netns *old_vnet; + + ASSERT_RTNL(); + + old_vnet = net_generic(oldnet, ipvlan_netid); + if (!old_vnet->ipvl_nf_hook_refcnt) + return; + + ipvlan_register_nf_hook(newnet); + ipvlan_unregister_nf_hook(oldnet); +} + +static void ipvlan_ns_exit(struct net *net) +{ + struct ipvlan_netns *vnet = net_generic(net, ipvlan_netid); + + if (WARN_ON_ONCE(vnet->ipvl_nf_hook_refcnt)) { + vnet->ipvl_nf_hook_refcnt = 0; + nf_unregister_net_hooks(net, ipvl_nfops, + ARRAY_SIZE(ipvl_nfops)); + } +} + +static struct pernet_operations ipvlan_net_ops = { + .id = &ipvlan_netid, + .size = sizeof(struct ipvlan_netns), + .exit = ipvlan_ns_exit, +}; + +int ipvlan_l3s_init(void) +{ + return register_pernet_subsys(&ipvlan_net_ops); +} + +void ipvlan_l3s_cleanup(void) +{ + unregister_pernet_subsys(&ipvlan_net_ops); +} + +int ipvlan_l3s_register(struct ipvl_port *port) +{ + struct net_device *dev = port->dev; + int ret; + + ASSERT_RTNL(); + + ret = ipvlan_register_nf_hook(read_pnet(&port->pnet)); + if (!ret) { + dev->l3mdev_ops = &ipvl_l3mdev_ops; + dev->priv_flags |= IFF_L3MDEV_RX_HANDLER; + } + + return ret; +} + +void ipvlan_l3s_unregister(struct ipvl_port *port) +{ + struct net_device *dev = port->dev; + + ASSERT_RTNL(); + + dev->priv_flags &= ~IFF_L3MDEV_RX_HANDLER; + ipvlan_unregister_nf_hook(read_pnet(&port->pnet)); + dev->l3mdev_ops = NULL; +} diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 19bdde60680c..8ec73d973079 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -9,73 +9,10 @@ #include "ipvlan.h" -static unsigned int ipvlan_netid __read_mostly; - -struct ipvlan_netns { - unsigned int ipvl_nf_hook_refcnt; -}; - -static const struct nf_hook_ops ipvl_nfops[] = { - { - .hook = ipvlan_nf_input, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_LOCAL_IN, - .priority = INT_MAX, - }, -#if IS_ENABLED(CONFIG_IPV6) - { - .hook = ipvlan_nf_input, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_LOCAL_IN, - .priority = INT_MAX, - }, -#endif -}; - -static const struct l3mdev_ops ipvl_l3mdev_ops = { - .l3mdev_l3_rcv = ipvlan_l3_rcv, -}; - -static void ipvlan_adjust_mtu(struct ipvl_dev *ipvlan, struct net_device *dev) -{ - ipvlan->dev->mtu = dev->mtu; -} - -static int ipvlan_register_nf_hook(struct net *net) -{ - struct ipvlan_netns *vnet = net_generic(net, ipvlan_netid); - int err = 0; - - if (!vnet->ipvl_nf_hook_refcnt) { - err = nf_register_net_hooks(net, ipvl_nfops, - ARRAY_SIZE(ipvl_nfops)); - if (!err) - vnet->ipvl_nf_hook_refcnt = 1; - } else { - vnet->ipvl_nf_hook_refcnt++; - } - - return err; -} - -static void ipvlan_unregister_nf_hook(struct net *net) -{ - struct ipvlan_netns *vnet = net_generic(net, ipvlan_netid); - - if (WARN_ON(!vnet->ipvl_nf_hook_refcnt)) - return; - - vnet->ipvl_nf_hook_refcnt--; - if (!vnet->ipvl_nf_hook_refcnt) - nf_unregister_net_hooks(net, ipvl_nfops, - ARRAY_SIZE(ipvl_nfops)); -} - static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval, struct netlink_ext_ack *extack) { struct ipvl_dev *ipvlan; - struct net_device *mdev = port->dev; unsigned int flags; int err; @@ -97,17 +34,12 @@ static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval, } if (nval == IPVLAN_MODE_L3S) { /* New mode is L3S */ - err = ipvlan_register_nf_hook(read_pnet(&port->pnet)); - if (!err) { - mdev->l3mdev_ops = &ipvl_l3mdev_ops; - mdev->priv_flags |= IFF_L3MDEV_MASTER; - } else + err = ipvlan_l3s_register(port); + if (err) goto fail; } else if (port->mode == IPVLAN_MODE_L3S) { /* Old mode was L3S */ - mdev->priv_flags &= ~IFF_L3MDEV_MASTER; - ipvlan_unregister_nf_hook(read_pnet(&port->pnet)); - mdev->l3mdev_ops = NULL; + ipvlan_l3s_unregister(port); } port->mode = nval; } @@ -166,11 +98,8 @@ static void ipvlan_port_destroy(struct net_device *dev) struct ipvl_port *port = ipvlan_port_get_rtnl(dev); struct sk_buff *skb; - if (port->mode == IPVLAN_MODE_L3S) { - dev->priv_flags &= ~IFF_L3MDEV_MASTER; - ipvlan_unregister_nf_hook(dev_net(dev)); - dev->l3mdev_ops = NULL; - } + if (port->mode == IPVLAN_MODE_L3S) + ipvlan_l3s_unregister(port); netdev_rx_handler_unregister(dev); cancel_work_sync(&port->wq); while ((skb = __skb_dequeue(&port->backlog)) != NULL) { @@ -446,6 +375,11 @@ static const struct header_ops ipvlan_header_ops = { .cache_update = eth_header_cache_update, }; +static void ipvlan_adjust_mtu(struct ipvl_dev *ipvlan, struct net_device *dev) +{ + ipvlan->dev->mtu = dev->mtu; +} + static bool netif_is_ipvlan(const struct net_device *dev) { /* both ipvlan and ipvtap devices use the same netdev_ops */ @@ -781,7 +715,6 @@ static int ipvlan_device_event(struct notifier_block *unused, case NETDEV_REGISTER: { struct net *oldnet, *newnet = dev_net(dev); - struct ipvlan_netns *old_vnet; oldnet = read_pnet(&port->pnet); if (net_eq(newnet, oldnet)) @@ -789,12 +722,7 @@ static int ipvlan_device_event(struct notifier_block *unused, write_pnet(&port->pnet, newnet); - old_vnet = net_generic(oldnet, ipvlan_netid); - if (!old_vnet->ipvl_nf_hook_refcnt) - break; - - ipvlan_register_nf_hook(newnet); - ipvlan_unregister_nf_hook(oldnet); + ipvlan_migrate_l3s_hook(oldnet, newnet); break; } case NETDEV_UNREGISTER: @@ -1068,23 +996,6 @@ static struct notifier_block ipvlan_addr6_vtor_notifier_block __read_mostly = { }; #endif -static void ipvlan_ns_exit(struct net *net) -{ - struct ipvlan_netns *vnet = net_generic(net, ipvlan_netid); - - if (WARN_ON_ONCE(vnet->ipvl_nf_hook_refcnt)) { - vnet->ipvl_nf_hook_refcnt = 0; - nf_unregister_net_hooks(net, ipvl_nfops, - ARRAY_SIZE(ipvl_nfops)); - } -} - -static struct pernet_operations ipvlan_net_ops = { - .id = &ipvlan_netid, - .size = sizeof(struct ipvlan_netns), - .exit = ipvlan_ns_exit, -}; - static int __init ipvlan_init_module(void) { int err; @@ -1099,13 +1010,13 @@ static int __init ipvlan_init_module(void) register_inetaddr_notifier(&ipvlan_addr4_notifier_block); register_inetaddr_validator_notifier(&ipvlan_addr4_vtor_notifier_block); - err = register_pernet_subsys(&ipvlan_net_ops); + err = ipvlan_l3s_init(); if (err < 0) goto error; err = ipvlan_link_register(&ipvlan_link_ops); if (err < 0) { - unregister_pernet_subsys(&ipvlan_net_ops); + ipvlan_l3s_cleanup(); goto error; } @@ -1126,7 +1037,7 @@ error: static void __exit ipvlan_cleanup_module(void) { rtnl_link_unregister(&ipvlan_link_ops); - unregister_pernet_subsys(&ipvlan_net_ops); + ipvlan_l3s_cleanup(); unregister_netdevice_notifier(&ipvlan_notifier_block); unregister_inetaddr_notifier(&ipvlan_addr4_notifier_block); unregister_inetaddr_validator_notifier( diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c index 172b271c8bd2..f92c43453ec6 100644 --- a/drivers/net/netdevsim/bpf.c +++ b/drivers/net/netdevsim/bpf.c @@ -248,7 +248,7 @@ static int nsim_bpf_create_prog(struct netdevsim *ns, struct bpf_prog *prog) static int nsim_bpf_verifier_prep(struct bpf_prog *prog) { - struct netdevsim *ns = netdev_priv(prog->aux->offload->netdev); + struct netdevsim *ns = bpf_offload_dev_priv(prog->aux->offload->offdev); if (!ns->bpf_bind_accept) return -EOPNOTSUPP; @@ -589,7 +589,8 @@ int nsim_bpf_init(struct netdevsim *ns) if (IS_ERR_OR_NULL(ns->sdev->ddir_bpf_bound_progs)) return -ENOMEM; - ns->sdev->bpf_dev = bpf_offload_dev_create(&nsim_bpf_dev_ops); + ns->sdev->bpf_dev = bpf_offload_dev_create(&nsim_bpf_dev_ops, + ns); err = PTR_ERR_OR_ZERO(ns->sdev->bpf_dev); if (err) return err; diff --git a/drivers/net/phy/aquantia.c b/drivers/net/phy/aquantia.c index 482004efa62d..34be44d00c19 100644 --- a/drivers/net/phy/aquantia.c +++ b/drivers/net/phy/aquantia.c @@ -17,6 +17,7 @@ #define PHY_ID_AQR105 0x03a1b4a2 #define PHY_ID_AQR106 0x03a1b4d0 #define PHY_ID_AQR107 0x03a1b4e0 +#define PHY_ID_AQCS109 0x03a1b5c2 #define PHY_ID_AQR405 0x03a1b4b0 #define MDIO_AN_TX_VEND_STATUS1 0xc800 @@ -155,8 +156,8 @@ static struct phy_driver aqr_driver[] = { { PHY_ID_MATCH_MODEL(PHY_ID_AQ1202), .name = "Aquantia AQ1202", - .features = PHY_10GBIT_FULL_FEATURES, .aneg_done = genphy_c45_aneg_done, + .get_features = genphy_c45_pma_read_abilities, .config_aneg = aqr_config_aneg, .config_intr = aqr_config_intr, .ack_interrupt = aqr_ack_interrupt, @@ -165,8 +166,8 @@ static struct phy_driver aqr_driver[] = { { PHY_ID_MATCH_MODEL(PHY_ID_AQ2104), .name = "Aquantia AQ2104", - .features = PHY_10GBIT_FULL_FEATURES, .aneg_done = genphy_c45_aneg_done, + .get_features = genphy_c45_pma_read_abilities, .config_aneg = aqr_config_aneg, .config_intr = aqr_config_intr, .ack_interrupt = aqr_ack_interrupt, @@ -175,8 +176,8 @@ static struct phy_driver aqr_driver[] = { { PHY_ID_MATCH_MODEL(PHY_ID_AQR105), .name = "Aquantia AQR105", - .features = PHY_10GBIT_FULL_FEATURES, .aneg_done = genphy_c45_aneg_done, + .get_features = genphy_c45_pma_read_abilities, .config_aneg = aqr_config_aneg, .config_intr = aqr_config_intr, .ack_interrupt = aqr_ack_interrupt, @@ -185,8 +186,8 @@ static struct phy_driver aqr_driver[] = { { PHY_ID_MATCH_MODEL(PHY_ID_AQR106), .name = "Aquantia AQR106", - .features = PHY_10GBIT_FULL_FEATURES, .aneg_done = genphy_c45_aneg_done, + .get_features = genphy_c45_pma_read_abilities, .config_aneg = aqr_config_aneg, .config_intr = aqr_config_intr, .ack_interrupt = aqr_ack_interrupt, @@ -195,8 +196,18 @@ static struct phy_driver aqr_driver[] = { { PHY_ID_MATCH_MODEL(PHY_ID_AQR107), .name = "Aquantia AQR107", - .features = PHY_10GBIT_FULL_FEATURES, .aneg_done = genphy_c45_aneg_done, + .get_features = genphy_c45_pma_read_abilities, + .config_aneg = aqr_config_aneg, + .config_intr = aqr_config_intr, + .ack_interrupt = aqr_ack_interrupt, + .read_status = aqr_read_status, +}, +{ + PHY_ID_MATCH_MODEL(PHY_ID_AQCS109), + .name = "Aquantia AQCS109", + .aneg_done = genphy_c45_aneg_done, + .get_features = genphy_c45_pma_read_abilities, .config_aneg = aqr_config_aneg, .config_intr = aqr_config_intr, .ack_interrupt = aqr_ack_interrupt, @@ -205,8 +216,8 @@ static struct phy_driver aqr_driver[] = { { PHY_ID_MATCH_MODEL(PHY_ID_AQR405), .name = "Aquantia AQR405", - .features = PHY_10GBIT_FULL_FEATURES, .aneg_done = genphy_c45_aneg_done, + .get_features = genphy_c45_pma_read_abilities, .config_aneg = aqr_config_aneg, .config_intr = aqr_config_intr, .ack_interrupt = aqr_ack_interrupt, @@ -222,6 +233,7 @@ static struct mdio_device_id __maybe_unused aqr_tbl[] = { { PHY_ID_MATCH_MODEL(PHY_ID_AQR105) }, { PHY_ID_MATCH_MODEL(PHY_ID_AQR106) }, { PHY_ID_MATCH_MODEL(PHY_ID_AQR107) }, + { PHY_ID_MATCH_MODEL(PHY_ID_AQCS109) }, { PHY_ID_MATCH_MODEL(PHY_ID_AQR405) }, { } }; diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 25ef483bcc24..2fe2ebaf62d1 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -885,14 +885,14 @@ static void decode_txts(struct dp83640_private *dp83640, struct phy_txts *phy_txts) { struct skb_shared_hwtstamps shhwtstamps; + struct dp83640_skb_info *skb_info; struct sk_buff *skb; - u64 ns; u8 overflow; + u64 ns; /* We must already have the skb that triggered this. */ - +again: skb = skb_dequeue(&dp83640->tx_queue); - if (!skb) { pr_debug("have timestamp but tx_queue empty\n"); return; @@ -907,6 +907,11 @@ static void decode_txts(struct dp83640_private *dp83640, } return; } + skb_info = (struct dp83640_skb_info *)skb->cb; + if (time_after(jiffies, skb_info->tmo)) { + kfree_skb(skb); + goto again; + } ns = phy2txts(phy_txts); memset(&shhwtstamps, 0, sizeof(shhwtstamps)); @@ -1459,6 +1464,7 @@ static bool dp83640_rxtstamp(struct phy_device *phydev, static void dp83640_txtstamp(struct phy_device *phydev, struct sk_buff *skb, int type) { + struct dp83640_skb_info *skb_info = (struct dp83640_skb_info *)skb->cb; struct dp83640_private *dp83640 = phydev->priv; switch (dp83640->hwts_tx_en) { @@ -1471,6 +1477,7 @@ static void dp83640_txtstamp(struct phy_device *phydev, /* fall through */ case HWTSTAMP_TX_ON: skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + skb_info->tmo = jiffies + SKB_TIMESTAMP_TIMEOUT; skb_queue_tail(&dp83640->tx_queue, skb); break; diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c index f136a23c1a35..b0d1368c3400 100644 --- a/drivers/net/phy/fixed_phy.c +++ b/drivers/net/phy/fixed_phy.c @@ -85,11 +85,11 @@ static int fixed_mdio_read(struct mii_bus *bus, int phy_addr, int reg_num) s = read_seqcount_begin(&fp->seqcount); fp->status.link = !fp->no_carrier; /* Issue callback if user registered it. */ - if (fp->link_update) { + if (fp->link_update) fp->link_update(fp->phydev->attached_dev, &fp->status); - fixed_phy_update(fp); - } + /* Check the GPIO for change in status */ + fixed_phy_update(fp); state = fp->status; } while (read_seqcount_retry(&fp->seqcount, s)); @@ -229,12 +229,12 @@ static struct gpio_desc *fixed_phy_get_gpiod(struct device_node *np) } #endif -struct phy_device *fixed_phy_register(unsigned int irq, - struct fixed_phy_status *status, - struct device_node *np) +static struct phy_device *__fixed_phy_register(unsigned int irq, + struct fixed_phy_status *status, + struct device_node *np, + struct gpio_desc *gpiod) { struct fixed_mdio_bus *fmb = &platform_fmb; - struct gpio_desc *gpiod = NULL; struct phy_device *phy; int phy_addr; int ret; @@ -243,9 +243,11 @@ struct phy_device *fixed_phy_register(unsigned int irq, return ERR_PTR(-EPROBE_DEFER); /* Check if we have a GPIO associated with this fixed phy */ - gpiod = fixed_phy_get_gpiod(np); - if (IS_ERR(gpiod)) - return ERR_CAST(gpiod); + if (!gpiod) { + gpiod = fixed_phy_get_gpiod(np); + if (IS_ERR(gpiod)) + return ERR_CAST(gpiod); + } /* Get the next available PHY address, up to PHY_MAX_ADDR */ phy_addr = ida_simple_get(&phy_fixed_ida, 0, PHY_MAX_ADDR, GFP_KERNEL); @@ -308,8 +310,24 @@ struct phy_device *fixed_phy_register(unsigned int irq, return phy; } + +struct phy_device *fixed_phy_register(unsigned int irq, + struct fixed_phy_status *status, + struct device_node *np) +{ + return __fixed_phy_register(irq, status, np, NULL); +} EXPORT_SYMBOL_GPL(fixed_phy_register); +struct phy_device * +fixed_phy_register_with_gpiod(unsigned int irq, + struct fixed_phy_status *status, + struct gpio_desc *gpiod) +{ + return __fixed_phy_register(irq, status, NULL, gpiod); +} +EXPORT_SYMBOL_GPL(fixed_phy_register_with_gpiod); + void fixed_phy_unregister(struct phy_device *phy) { phy_device_remove(phy); diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 90f44ba8aca7..3ccba37bd6dd 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -842,7 +842,6 @@ static int m88e1510_config_init(struct phy_device *phydev) /* SGMII-to-Copper mode initialization */ if (phydev->interface == PHY_INTERFACE_MODE_SGMII) { - /* Select page 18 */ err = marvell_set_page(phydev, 18); if (err < 0) @@ -865,21 +864,6 @@ static int m88e1510_config_init(struct phy_device *phydev) err = marvell_set_page(phydev, MII_MARVELL_COPPER_PAGE); if (err < 0) return err; - - /* There appears to be a bug in the 88e1512 when used in - * SGMII to copper mode, where the AN advertisement register - * clears the pause bits each time a negotiation occurs. - * This means we can never be truely sure what was advertised, - * so disable Pause support. - */ - linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, - phydev->supported); - linkmode_clear_bit(ETHTOOL_LINK_MODE_Pause_BIT, - phydev->supported); - linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, - phydev->advertising); - linkmode_clear_bit(ETHTOOL_LINK_MODE_Pause_BIT, - phydev->advertising); } return m88e1318_config_init(phydev); diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index 296a537cdfcb..586ae1bc5a50 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -141,10 +141,9 @@ static int mv3310_hwmon_config(struct phy_device *phydev, bool enable) return ret; val = enable ? MV_V2_TEMP_CTRL_SAMPLE : MV_V2_TEMP_CTRL_DISABLE; - ret = phy_modify_mmd(phydev, MDIO_MMD_VEND2, MV_V2_TEMP_CTRL, - MV_V2_TEMP_CTRL_MASK, val); - return ret < 0 ? ret : 0; + return phy_modify_mmd(phydev, MDIO_MMD_VEND2, MV_V2_TEMP_CTRL, + MV_V2_TEMP_CTRL_MASK, val); } static void mv3310_hwmon_disable(void *data) @@ -234,8 +233,7 @@ static int mv3310_resume(struct phy_device *phydev) static int mv3310_config_init(struct phy_device *phydev) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(supported) = { 0, }; - int val; + int ret, val; /* Check that the PHY interface type is compatible */ if (phydev->interface != PHY_INTERFACE_MODE_SGMII && @@ -244,83 +242,19 @@ static int mv3310_config_init(struct phy_device *phydev) phydev->interface != PHY_INTERFACE_MODE_10GKR) return -ENODEV; - __set_bit(ETHTOOL_LINK_MODE_Pause_BIT, supported); - __set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, supported); - if (phydev->c45_ids.devices_in_package & MDIO_DEVS_AN) { val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_STAT1); if (val < 0) return val; if (val & MDIO_AN_STAT1_ABLE) - __set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, supported); - } - - val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_STAT2); - if (val < 0) - return val; - - /* Ethtool does not support the WAN mode bits */ - if (val & (MDIO_PMA_STAT2_10GBSR | MDIO_PMA_STAT2_10GBLR | - MDIO_PMA_STAT2_10GBER | MDIO_PMA_STAT2_10GBLX4 | - MDIO_PMA_STAT2_10GBSW | MDIO_PMA_STAT2_10GBLW | - MDIO_PMA_STAT2_10GBEW)) - __set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, supported); - if (val & MDIO_PMA_STAT2_10GBSR) - __set_bit(ETHTOOL_LINK_MODE_10000baseSR_Full_BIT, supported); - if (val & MDIO_PMA_STAT2_10GBLR) - __set_bit(ETHTOOL_LINK_MODE_10000baseLR_Full_BIT, supported); - if (val & MDIO_PMA_STAT2_10GBER) - __set_bit(ETHTOOL_LINK_MODE_10000baseER_Full_BIT, supported); - - if (val & MDIO_PMA_STAT2_EXTABLE) { - val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_EXTABLE); - if (val < 0) - return val; - - if (val & (MDIO_PMA_EXTABLE_10GBT | MDIO_PMA_EXTABLE_1000BT | - MDIO_PMA_EXTABLE_100BTX | MDIO_PMA_EXTABLE_10BT)) - __set_bit(ETHTOOL_LINK_MODE_TP_BIT, supported); - if (val & MDIO_PMA_EXTABLE_10GBLRM) - __set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, supported); - if (val & (MDIO_PMA_EXTABLE_10GBKX4 | MDIO_PMA_EXTABLE_10GBKR | - MDIO_PMA_EXTABLE_1000BKX)) - __set_bit(ETHTOOL_LINK_MODE_Backplane_BIT, supported); - if (val & MDIO_PMA_EXTABLE_10GBLRM) - __set_bit(ETHTOOL_LINK_MODE_10000baseLRM_Full_BIT, - supported); - if (val & MDIO_PMA_EXTABLE_10GBT) - __set_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT, - supported); - if (val & MDIO_PMA_EXTABLE_10GBKX4) - __set_bit(ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, - supported); - if (val & MDIO_PMA_EXTABLE_10GBKR) - __set_bit(ETHTOOL_LINK_MODE_10000baseKR_Full_BIT, - supported); - if (val & MDIO_PMA_EXTABLE_1000BT) - __set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, - supported); - if (val & MDIO_PMA_EXTABLE_1000BKX) - __set_bit(ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, - supported); - if (val & MDIO_PMA_EXTABLE_100BTX) { - __set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, - supported); - __set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, - supported); - } - if (val & MDIO_PMA_EXTABLE_10BT) { - __set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, - supported); - __set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, - supported); - } + __set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + phydev->supported); } - linkmode_copy(phydev->supported, supported); - linkmode_and(phydev->advertising, phydev->advertising, - phydev->supported); + ret = genphy_c45_pma_read_abilities(phydev); + if (ret) + return ret; return 0; } @@ -334,52 +268,27 @@ static int mv3310_config_aneg(struct phy_device *phydev) /* We don't support manual MDI control */ phydev->mdix_ctrl = ETH_TP_MDI_AUTO; - if (phydev->autoneg == AUTONEG_DISABLE) { - ret = genphy_c45_pma_setup_forced(phydev); - if (ret < 0) - return ret; + if (phydev->autoneg == AUTONEG_DISABLE) + return genphy_c45_pma_setup_forced(phydev); - return genphy_c45_an_disable_aneg(phydev); - } - - linkmode_and(phydev->advertising, phydev->advertising, - phydev->supported); - - ret = phy_modify_mmd(phydev, MDIO_MMD_AN, MDIO_AN_ADVERTISE, - ADVERTISE_ALL | ADVERTISE_100BASE4 | - ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM, - linkmode_adv_to_mii_adv_t(phydev->advertising)); + ret = genphy_c45_an_config_aneg(phydev); if (ret < 0) return ret; if (ret > 0) changed = true; + /* Clause 45 has no standardized support for 1000BaseT, therefore + * use vendor registers for this mode. + */ reg = linkmode_adv_to_mii_ctrl1000_t(phydev->advertising); - ret = phy_modify_mmd(phydev, MDIO_MMD_AN, MV_AN_CTRL1000, + ret = phy_modify_mmd_changed(phydev, MDIO_MMD_AN, MV_AN_CTRL1000, ADVERTISE_1000FULL | ADVERTISE_1000HALF, reg); if (ret < 0) return ret; if (ret > 0) changed = true; - /* 10G control register */ - if (linkmode_test_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT, - phydev->advertising)) - reg = MDIO_AN_10GBT_CTRL_ADV10G; - else - reg = 0; - - ret = phy_modify_mmd(phydev, MDIO_MMD_AN, MDIO_AN_10GBT_CTRL, - MDIO_AN_10GBT_CTRL_ADV10G, reg); - if (ret < 0) - return ret; - if (ret > 0) - changed = true; - - if (changed) - ret = genphy_c45_restart_aneg(phydev); - - return ret; + return genphy_c45_check_and_restart_aneg(phydev, changed); } static int mv3310_aneg_done(struct phy_device *phydev) @@ -428,16 +337,8 @@ static int mv3310_read_10gbr_status(struct phy_device *phydev) static int mv3310_read_status(struct phy_device *phydev) { - u32 mmd_mask = phydev->c45_ids.devices_in_package; int val; - /* The vendor devads do not report link status. Avoid the PHYXS - * instance as there are three, and its status depends on the MAC - * being appropriately configured for the negotiated speed. - */ - mmd_mask &= ~(BIT(MDIO_MMD_VEND1) | BIT(MDIO_MMD_VEND2) | - BIT(MDIO_MMD_PHYXS)); - phydev->speed = SPEED_UNKNOWN; phydev->duplex = DUPLEX_UNKNOWN; linkmode_zero(phydev->lp_advertising); @@ -453,7 +354,7 @@ static int mv3310_read_status(struct phy_device *phydev) if (val & MDIO_STAT1_LSTATUS) return mv3310_read_10gbr_status(phydev); - val = genphy_c45_read_link(phydev, mmd_mask); + val = genphy_c45_read_link(phydev); if (val < 0) return val; diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 3d313585c9c1..debc74c90307 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -48,11 +48,12 @@ static int mdiobus_register_gpiod(struct mdio_device *mdiodev) gpiod = fwnode_get_named_gpiod(&mdiodev->dev.of_node->fwnode, "reset-gpios", 0, GPIOD_OUT_LOW, "PHY reset"); - if (PTR_ERR(gpiod) == -ENOENT || - PTR_ERR(gpiod) == -ENOSYS) - gpiod = NULL; - else if (IS_ERR(gpiod)) - return PTR_ERR(gpiod); + if (IS_ERR(gpiod)) { + if (PTR_ERR(gpiod) == -ENOENT || PTR_ERR(gpiod) == -ENOSYS) + gpiod = NULL; + else + return PTR_ERR(gpiod); + } mdiodev->reset = gpiod; diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index c92d0fb7ec4f..fc3173cc078b 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -47,6 +47,16 @@ int genphy_c45_pma_setup_forced(struct phy_device *phydev) /* Assume 1000base-T */ ctrl2 |= MDIO_PMA_CTRL2_1000BT; break; + case SPEED_2500: + ctrl1 |= MDIO_CTRL1_SPEED2_5G; + /* Assume 2.5Gbase-T */ + ctrl2 |= MDIO_PMA_CTRL2_2_5GBT; + break; + case SPEED_5000: + ctrl1 |= MDIO_CTRL1_SPEED5G; + /* Assume 5Gbase-T */ + ctrl2 |= MDIO_PMA_CTRL2_5GBT; + break; case SPEED_10000: ctrl1 |= MDIO_CTRL1_SPEED10G; /* Assume 10Gbase-T */ @@ -60,11 +70,61 @@ int genphy_c45_pma_setup_forced(struct phy_device *phydev) if (ret < 0) return ret; - return phy_write_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_CTRL2, ctrl2); + ret = phy_write_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_CTRL2, ctrl2); + if (ret < 0) + return ret; + + return genphy_c45_an_disable_aneg(phydev); } EXPORT_SYMBOL_GPL(genphy_c45_pma_setup_forced); /** + * genphy_c45_an_config_aneg - configure advertisement registers + * @phydev: target phy_device struct + * + * Configure advertisement registers based on modes set in phydev->advertising + * + * Returns negative errno code on failure, 0 if advertisement didn't change, + * or 1 if advertised modes changed. + */ +int genphy_c45_an_config_aneg(struct phy_device *phydev) +{ + int changed, ret; + u32 adv; + + linkmode_and(phydev->advertising, phydev->advertising, + phydev->supported); + + changed = genphy_config_eee_advert(phydev); + + adv = linkmode_adv_to_mii_adv_t(phydev->advertising); + + ret = phy_modify_mmd(phydev, MDIO_MMD_AN, MDIO_AN_ADVERTISE, + ADVERTISE_ALL | ADVERTISE_100BASE4 | + ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM, + adv); + if (ret < 0) + return ret; + if (ret > 0) + changed = 1; + + adv = linkmode_adv_to_mii_10gbt_adv_t(phydev->advertising); + + ret = phy_modify_mmd(phydev, MDIO_MMD_AN, MDIO_AN_10GBT_CTRL, + MDIO_AN_10GBT_CTRL_ADV10G | + MDIO_AN_10GBT_CTRL_ADV5G | + MDIO_AN_10GBT_CTRL_ADV2_5G, + adv); + if (ret < 0) + return ret; + if (ret > 0) + changed = 1; + + return changed; +} +EXPORT_SYMBOL_GPL(genphy_c45_an_config_aneg); + +/** * genphy_c45_an_disable_aneg - disable auto-negotiation * @phydev: target phy_device struct * @@ -97,6 +157,36 @@ int genphy_c45_restart_aneg(struct phy_device *phydev) EXPORT_SYMBOL_GPL(genphy_c45_restart_aneg); /** + * genphy_c45_check_and_restart_aneg - Enable and restart auto-negotiation + * @phydev: target phy_device struct + * @restart: whether aneg restart is requested + * + * This assumes that the auto-negotiation MMD is present. + * + * Check, and restart auto-negotiation if needed. + */ +int genphy_c45_check_and_restart_aneg(struct phy_device *phydev, bool restart) +{ + int ret = 0; + + if (!restart) { + /* Configure and restart aneg if it wasn't set before */ + ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_CTRL1); + if (ret < 0) + return ret; + + if (!(ret & MDIO_AN_CTRL1_ENABLE)) + restart = true; + } + + if (restart) + ret = genphy_c45_restart_aneg(phydev); + + return ret; +} +EXPORT_SYMBOL_GPL(genphy_c45_check_and_restart_aneg); + +/** * genphy_c45_aneg_done - return auto-negotiation complete status * @phydev: target phy_device struct * @@ -118,25 +208,40 @@ EXPORT_SYMBOL_GPL(genphy_c45_aneg_done); /** * genphy_c45_read_link - read the overall link status from the MMDs * @phydev: target phy_device struct - * @mmd_mask: MMDs to read status from * * Read the link status from the specified MMDs, and if they all indicate * that the link is up, set phydev->link to 1. If an error is encountered, * a negative errno will be returned, otherwise zero. */ -int genphy_c45_read_link(struct phy_device *phydev, u32 mmd_mask) +int genphy_c45_read_link(struct phy_device *phydev) { + u32 mmd_mask = phydev->c45_ids.devices_in_package; int val, devad; bool link = true; + /* The vendor devads and C22EXT do not report link status. Avoid the + * PHYXS instance as its status may depend on the MAC being + * appropriately configured for the negotiated speed. + */ + mmd_mask &= ~(MDIO_DEVS_VEND1 | MDIO_DEVS_VEND2 | MDIO_DEVS_C22EXT | + MDIO_DEVS_PHYXS); + while (mmd_mask && link) { devad = __ffs(mmd_mask); mmd_mask &= ~BIT(devad); /* The link state is latched low so that momentary link - * drops can be detected. Do not double-read the status - * register if the link is down. + * drops can be detected. Do not double-read the status + * in polling mode to detect such short link drops. */ + if (!phy_polling_mode(phydev)) { + val = phy_read_mmd(phydev, devad, MDIO_STAT1); + if (val < 0) + return val; + else if (val & MDIO_STAT1_LSTATUS) + continue; + } + val = phy_read_mmd(phydev, devad, MDIO_STAT1); if (val < 0) return val; @@ -179,9 +284,7 @@ int genphy_c45_read_lpa(struct phy_device *phydev) if (val < 0) return val; - if (val & MDIO_AN_10GBT_STAT_LP10G) - linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT, - phydev->lp_advertising); + mii_10gbt_stat_mod_linkmode_lpa_t(phydev->lp_advertising, val); return 0; } @@ -209,6 +312,12 @@ int genphy_c45_read_pma(struct phy_device *phydev) case MDIO_PMA_CTRL1_SPEED1000: phydev->speed = SPEED_1000; break; + case MDIO_CTRL1_SPEED2_5G: + phydev->speed = SPEED_2500; + break; + case MDIO_CTRL1_SPEED5G: + phydev->speed = SPEED_5000; + break; case MDIO_CTRL1_SPEED10G: phydev->speed = SPEED_10000; break; @@ -256,6 +365,95 @@ int genphy_c45_read_mdix(struct phy_device *phydev) } EXPORT_SYMBOL_GPL(genphy_c45_read_mdix); +/** + * genphy_c45_pma_read_abilities - read supported link modes from PMA + * @phydev: target phy_device struct + * + * Read the supported link modes from the PMA Status 2 (1.8) register. If bit + * 1.8.9 is set, the list of supported modes is build using the values in the + * PMA Extended Abilities (1.11) register, indicating 1000BASET an 10G related + * modes. If bit 1.11.14 is set, then the list is also extended with the modes + * in the 2.5G/5G PMA Extended register (1.21), indicating if 2.5GBASET and + * 5GBASET are supported. + */ +int genphy_c45_pma_read_abilities(struct phy_device *phydev) +{ + int val; + + val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_STAT2); + if (val < 0) + return val; + + linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseSR_Full_BIT, + phydev->supported, + val & MDIO_PMA_STAT2_10GBSR); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseLR_Full_BIT, + phydev->supported, + val & MDIO_PMA_STAT2_10GBLR); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseER_Full_BIT, + phydev->supported, + val & MDIO_PMA_STAT2_10GBER); + + if (val & MDIO_PMA_STAT2_EXTABLE) { + val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_EXTABLE); + if (val < 0) + return val; + + linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseLRM_Full_BIT, + phydev->supported, + val & MDIO_PMA_EXTABLE_10GBLRM); + linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT, + phydev->supported, + val & MDIO_PMA_EXTABLE_10GBT); + linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, + phydev->supported, + val & MDIO_PMA_EXTABLE_10GBKX4); + linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseKR_Full_BIT, + phydev->supported, + val & MDIO_PMA_EXTABLE_10GBKR); + linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + phydev->supported, + val & MDIO_PMA_EXTABLE_1000BT); + linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, + phydev->supported, + val & MDIO_PMA_EXTABLE_1000BKX); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, + phydev->supported, + val & MDIO_PMA_EXTABLE_100BTX); + linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, + phydev->supported, + val & MDIO_PMA_EXTABLE_100BTX); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, + phydev->supported, + val & MDIO_PMA_EXTABLE_10BT); + linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, + phydev->supported, + val & MDIO_PMA_EXTABLE_10BT); + + if (val & MDIO_PMA_EXTABLE_NBT) { + val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, + MDIO_PMA_NG_EXTABLE); + if (val < 0) + return val; + + linkmode_mod_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, + phydev->supported, + val & MDIO_PMA_NG_EXTABLE_2_5GBT); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_5000baseT_Full_BIT, + phydev->supported, + val & MDIO_PMA_NG_EXTABLE_5GBT); + } + } + + return 0; +} +EXPORT_SYMBOL_GPL(genphy_c45_pma_read_abilities); + /* The gen10g_* functions are the old Clause 45 stub */ int gen10g_config_aneg(struct phy_device *phydev) @@ -266,16 +464,11 @@ EXPORT_SYMBOL_GPL(gen10g_config_aneg); int gen10g_read_status(struct phy_device *phydev) { - u32 mmd_mask = phydev->c45_ids.devices_in_package; - /* For now just lie and say it's 10G all the time */ phydev->speed = SPEED_10000; phydev->duplex = DUPLEX_FULL; - /* Avoid reading the vendor MMDs */ - mmd_mask &= ~(BIT(MDIO_MMD_VEND1) | BIT(MDIO_MMD_VEND2)); - - return genphy_c45_read_link(phydev, mmd_mask); + return genphy_c45_read_link(phydev); } EXPORT_SYMBOL_GPL(gen10g_read_status); diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index 7d6aad287f84..5016cd5fd7c7 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -4,6 +4,7 @@ */ #include <linux/export.h> #include <linux/phy.h> +#include <linux/of.h> const char *phy_speed_to_str(int speed) { @@ -338,6 +339,77 @@ size_t phy_speeds(unsigned int *speeds, size_t size, return count; } +static int __set_phy_supported(struct phy_device *phydev, u32 max_speed) +{ + const struct phy_setting *p; + int i; + + for (i = 0, p = settings; i < ARRAY_SIZE(settings); i++, p++) { + if (p->speed > max_speed) + linkmode_clear_bit(p->bit, phydev->supported); + else + break; + } + + return 0; +} + +int phy_set_max_speed(struct phy_device *phydev, u32 max_speed) +{ + int err; + + err = __set_phy_supported(phydev, max_speed); + if (err) + return err; + + linkmode_copy(phydev->advertising, phydev->supported); + + return 0; +} +EXPORT_SYMBOL(phy_set_max_speed); + +void of_set_phy_supported(struct phy_device *phydev) +{ + struct device_node *node = phydev->mdio.dev.of_node; + u32 max_speed; + + if (!IS_ENABLED(CONFIG_OF_MDIO)) + return; + + if (!node) + return; + + if (!of_property_read_u32(node, "max-speed", &max_speed)) + __set_phy_supported(phydev, max_speed); +} + +void of_set_phy_eee_broken(struct phy_device *phydev) +{ + struct device_node *node = phydev->mdio.dev.of_node; + u32 broken = 0; + + if (!IS_ENABLED(CONFIG_OF_MDIO)) + return; + + if (!node) + return; + + if (of_property_read_bool(node, "eee-broken-100tx")) + broken |= MDIO_EEE_100TX; + if (of_property_read_bool(node, "eee-broken-1000t")) + broken |= MDIO_EEE_1000T; + if (of_property_read_bool(node, "eee-broken-10gt")) + broken |= MDIO_EEE_10GT; + if (of_property_read_bool(node, "eee-broken-1000kx")) + broken |= MDIO_EEE_1000KX; + if (of_property_read_bool(node, "eee-broken-10gkx4")) + broken |= MDIO_EEE_10GKX4; + if (of_property_read_bool(node, "eee-broken-10gkr")) + broken |= MDIO_EEE_10GKR; + + phydev->eee_broken_modes = broken; +} + /** * phy_resolve_aneg_linkmode - resolve the advertisements into phy settings * @phydev: The phy_device struct @@ -349,45 +421,16 @@ size_t phy_speeds(unsigned int *speeds, size_t size, void phy_resolve_aneg_linkmode(struct phy_device *phydev) { __ETHTOOL_DECLARE_LINK_MODE_MASK(common); + int i; linkmode_and(common, phydev->lp_advertising, phydev->advertising); - if (linkmode_test_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT, common)) { - phydev->speed = SPEED_10000; - phydev->duplex = DUPLEX_FULL; - } else if (linkmode_test_bit(ETHTOOL_LINK_MODE_5000baseT_Full_BIT, - common)) { - phydev->speed = SPEED_5000; - phydev->duplex = DUPLEX_FULL; - } else if (linkmode_test_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, - common)) { - phydev->speed = SPEED_2500; - phydev->duplex = DUPLEX_FULL; - } else if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, - common)) { - phydev->speed = SPEED_1000; - phydev->duplex = DUPLEX_FULL; - } else if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, - common)) { - phydev->speed = SPEED_1000; - phydev->duplex = DUPLEX_HALF; - } else if (linkmode_test_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, - common)) { - phydev->speed = SPEED_100; - phydev->duplex = DUPLEX_FULL; - } else if (linkmode_test_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, - common)) { - phydev->speed = SPEED_100; - phydev->duplex = DUPLEX_HALF; - } else if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, - common)) { - phydev->speed = SPEED_10; - phydev->duplex = DUPLEX_FULL; - } else if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, - common)) { - phydev->speed = SPEED_10; - phydev->duplex = DUPLEX_HALF; - } + for (i = 0; i < ARRAY_SIZE(settings); i++) + if (test_bit(settings[i].bit, common)) { + phydev->speed = settings[i].speed; + phydev->duplex = settings[i].duplex; + break; + } if (phydev->duplex == DUPLEX_FULL) { phydev->pause = linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, @@ -531,7 +574,7 @@ int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) EXPORT_SYMBOL(phy_write_mmd); /** - * __phy_modify() - Convenience function for modifying a PHY register + * __phy_modify_changed() - Convenience function for modifying a PHY register * @phydev: a pointer to a &struct phy_device * @regnum: register number * @mask: bit mask of bits to clear @@ -539,16 +582,69 @@ EXPORT_SYMBOL(phy_write_mmd); * * Unlocked helper function which allows a PHY register to be modified as * new register value = (old register value & ~mask) | set + * + * Returns negative errno, 0 if there was no change, and 1 in case of change */ -int __phy_modify(struct phy_device *phydev, u32 regnum, u16 mask, u16 set) +int __phy_modify_changed(struct phy_device *phydev, u32 regnum, u16 mask, + u16 set) { - int ret; + int new, ret; ret = __phy_read(phydev, regnum); if (ret < 0) return ret; - ret = __phy_write(phydev, regnum, (ret & ~mask) | set); + new = (ret & ~mask) | set; + if (new == ret) + return 0; + + ret = __phy_write(phydev, regnum, new); + + return ret < 0 ? ret : 1; +} +EXPORT_SYMBOL_GPL(__phy_modify_changed); + +/** + * phy_modify_changed - Function for modifying a PHY register + * @phydev: the phy_device struct + * @regnum: register number to modify + * @mask: bit mask of bits to clear + * @set: new value of bits set in mask to write to @regnum + * + * NOTE: MUST NOT be called from interrupt context, + * because the bus read/write functions may wait for an interrupt + * to conclude the operation. + * + * Returns negative errno, 0 if there was no change, and 1 in case of change + */ +int phy_modify_changed(struct phy_device *phydev, u32 regnum, u16 mask, u16 set) +{ + int ret; + + mutex_lock(&phydev->mdio.bus->mdio_lock); + ret = __phy_modify_changed(phydev, regnum, mask, set); + mutex_unlock(&phydev->mdio.bus->mdio_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(phy_modify_changed); + +/** + * __phy_modify - Convenience function for modifying a PHY register + * @phydev: the phy_device struct + * @regnum: register number to modify + * @mask: bit mask of bits to clear + * @set: new value of bits set in mask to write to @regnum + * + * NOTE: MUST NOT be called from interrupt context, + * because the bus read/write functions may wait for an interrupt + * to conclude the operation. + */ +int __phy_modify(struct phy_device *phydev, u32 regnum, u16 mask, u16 set) +{ + int ret; + + ret = __phy_modify_changed(phydev, regnum, mask, set); return ret < 0 ? ret : 0; } @@ -578,7 +674,7 @@ int phy_modify(struct phy_device *phydev, u32 regnum, u16 mask, u16 set) EXPORT_SYMBOL_GPL(phy_modify); /** - * __phy_modify_mmd - Convenience function for modifying a register on MMD + * __phy_modify_mmd_changed - Function for modifying a register on MMD * @phydev: the phy_device struct * @devad: the MMD containing register to modify * @regnum: register number to modify @@ -587,17 +683,73 @@ EXPORT_SYMBOL_GPL(phy_modify); * * Unlocked helper function which allows a MMD register to be modified as * new register value = (old register value & ~mask) | set + * + * Returns negative errno, 0 if there was no change, and 1 in case of change */ -int __phy_modify_mmd(struct phy_device *phydev, int devad, u32 regnum, - u16 mask, u16 set) +int __phy_modify_mmd_changed(struct phy_device *phydev, int devad, u32 regnum, + u16 mask, u16 set) { - int ret; + int new, ret; ret = __phy_read_mmd(phydev, devad, regnum); if (ret < 0) return ret; - ret = __phy_write_mmd(phydev, devad, regnum, (ret & ~mask) | set); + new = (ret & ~mask) | set; + if (new == ret) + return 0; + + ret = __phy_write_mmd(phydev, devad, regnum, new); + + return ret < 0 ? ret : 1; +} +EXPORT_SYMBOL_GPL(__phy_modify_mmd_changed); + +/** + * phy_modify_mmd_changed - Function for modifying a register on MMD + * @phydev: the phy_device struct + * @devad: the MMD containing register to modify + * @regnum: register number to modify + * @mask: bit mask of bits to clear + * @set: new value of bits set in mask to write to @regnum + * + * NOTE: MUST NOT be called from interrupt context, + * because the bus read/write functions may wait for an interrupt + * to conclude the operation. + * + * Returns negative errno, 0 if there was no change, and 1 in case of change + */ +int phy_modify_mmd_changed(struct phy_device *phydev, int devad, u32 regnum, + u16 mask, u16 set) +{ + int ret; + + mutex_lock(&phydev->mdio.bus->mdio_lock); + ret = __phy_modify_mmd_changed(phydev, devad, regnum, mask, set); + mutex_unlock(&phydev->mdio.bus->mdio_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(phy_modify_mmd_changed); + +/** + * __phy_modify_mmd - Convenience function for modifying a register on MMD + * @phydev: the phy_device struct + * @devad: the MMD containing register to modify + * @regnum: register number to modify + * @mask: bit mask of bits to clear + * @set: new value of bits set in mask to write to @regnum + * + * NOTE: MUST NOT be called from interrupt context, + * because the bus read/write functions may wait for an interrupt + * to conclude the operation. + */ +int __phy_modify_mmd(struct phy_device *phydev, int devad, u32 regnum, + u16 mask, u16 set) +{ + int ret; + + ret = __phy_modify_mmd_changed(phydev, devad, regnum, mask, set); return ret < 0 ? ret : 0; } diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 89ead29cec68..69dc64a4dbf8 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -543,7 +543,7 @@ int phy_start_aneg(struct phy_device *phydev) if (err < 0) goto out_unlock; - if (__phy_is_started(phydev)) { + if (phy_is_started(phydev)) { if (phydev->autoneg == AUTONEG_ENABLE) { err = phy_check_link_status(phydev); } else { @@ -699,7 +699,7 @@ void phy_stop_machine(struct phy_device *phydev) cancel_delayed_work_sync(&phydev->state_queue); mutex_lock(&phydev->lock); - if (__phy_is_started(phydev)) + if (phy_is_started(phydev)) phydev->state = PHY_UP; mutex_unlock(&phydev->lock); } @@ -752,9 +752,6 @@ static irqreturn_t phy_interrupt(int irq, void *phy_dat) { struct phy_device *phydev = phy_dat; - if (!phy_is_started(phydev)) - return IRQ_NONE; /* It can't be ours. */ - if (phydev->drv->did_interrupt && !phydev->drv->did_interrupt(phydev)) return IRQ_NONE; @@ -813,15 +810,14 @@ EXPORT_SYMBOL(phy_request_interrupt); */ void phy_stop(struct phy_device *phydev) { - mutex_lock(&phydev->lock); - - if (!__phy_is_started(phydev)) { + if (!phy_is_started(phydev)) { WARN(1, "called from state %s\n", phy_state_to_str(phydev->state)); - mutex_unlock(&phydev->lock); return; } + mutex_lock(&phydev->lock); + if (phy_interrupt_is_valid(phydev)) phy_disable_interrupts(phydev); @@ -961,8 +957,10 @@ void phy_state_machine(struct work_struct *work) * state machine would be pointless and possibly error prone when * called from phy_disconnect() synchronously. */ + mutex_lock(&phydev->lock); if (phy_polling_mode(phydev) && phy_is_started(phydev)) phy_queue_state_machine(phydev, PHY_STATE_TIME); + mutex_unlock(&phydev->lock); } /** diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 891e0178b97f..49fdd1ee798e 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -30,7 +30,6 @@ #include <linux/mdio.h> #include <linux/io.h> #include <linux/uaccess.h> -#include <linux/of.h> MODULE_DESCRIPTION("PHY library"); MODULE_AUTHOR("Andy Fleming"); @@ -676,13 +675,16 @@ static int get_phy_c45_devs_in_pkg(struct mii_bus *bus, int addr, int dev_addr, phy_reg = mdiobus_read(bus, addr, reg_addr); if (phy_reg < 0) return -EIO; - *devices_in_package = (phy_reg & 0xffff) << 16; + *devices_in_package = phy_reg << 16; reg_addr = MII_ADDR_C45 | dev_addr << 16 | MDIO_DEVS1; phy_reg = mdiobus_read(bus, addr, reg_addr); if (phy_reg < 0) return -EIO; - *devices_in_package |= (phy_reg & 0xffff); + *devices_in_package |= phy_reg; + + /* Bit 0 doesn't represent a device, it indicates c22 regs presence */ + *devices_in_package &= ~BIT(0); return 0; } @@ -743,13 +745,13 @@ static int get_phy_c45_ids(struct mii_bus *bus, int addr, u32 *phy_id, phy_reg = mdiobus_read(bus, addr, reg_addr); if (phy_reg < 0) return -EIO; - c45_ids->device_ids[i] = (phy_reg & 0xffff) << 16; + c45_ids->device_ids[i] = phy_reg << 16; reg_addr = MII_ADDR_C45 | i << 16 | MII_PHYSID2; phy_reg = mdiobus_read(bus, addr, reg_addr); if (phy_reg < 0) return -EIO; - c45_ids->device_ids[i] |= (phy_reg & 0xffff); + c45_ids->device_ids[i] |= phy_reg; } *phy_id = 0; return 0; @@ -786,14 +788,14 @@ static int get_phy_id(struct mii_bus *bus, int addr, u32 *phy_id, return (phy_reg == -EIO || phy_reg == -ENODEV) ? -ENODEV : -EIO; } - *phy_id = (phy_reg & 0xffff) << 16; + *phy_id = phy_reg << 16; /* Grab the bits from PHYIR2, and put them in the lower half */ phy_reg = mdiobus_read(bus, addr, MII_PHYSID2); if (phy_reg < 0) return -EIO; - *phy_id |= (phy_reg & 0xffff); + *phy_id |= phy_reg; return 0; } @@ -1513,7 +1515,7 @@ EXPORT_SYMBOL(phy_reset_after_clk_enable); static int genphy_config_advert(struct phy_device *phydev) { u32 advertise; - int oldadv, adv, bmsr; + int bmsr, adv; int err, changed = 0; /* Only allow advertising what this PHY supports */ @@ -1526,22 +1528,14 @@ static int genphy_config_advert(struct phy_device *phydev) phydev->advertising); /* Setup standard advertisement */ - adv = phy_read(phydev, MII_ADVERTISE); - if (adv < 0) - return adv; - - oldadv = adv; - adv &= ~(ADVERTISE_ALL | ADVERTISE_100BASE4 | ADVERTISE_PAUSE_CAP | - ADVERTISE_PAUSE_ASYM); - adv |= ethtool_adv_to_mii_adv_t(advertise); - - if (adv != oldadv) { - err = phy_write(phydev, MII_ADVERTISE, adv); - - if (err < 0) - return err; + err = phy_modify_changed(phydev, MII_ADVERTISE, + ADVERTISE_ALL | ADVERTISE_100BASE4 | + ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM, + ethtool_adv_to_mii_adv_t(advertise)); + if (err < 0) + return err; + if (err > 0) changed = 1; - } bmsr = phy_read(phydev, MII_BMSR); if (bmsr < 0) @@ -1555,25 +1549,20 @@ static int genphy_config_advert(struct phy_device *phydev) return changed; /* Configure gigabit if it's supported */ - adv = phy_read(phydev, MII_CTRL1000); - if (adv < 0) - return adv; - - oldadv = adv; - adv &= ~(ADVERTISE_1000FULL | ADVERTISE_1000HALF); - + adv = 0; if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, phydev->supported) || linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, phydev->supported)) - adv |= ethtool_adv_to_mii_ctrl1000_t(advertise); - - if (adv != oldadv) - changed = 1; + adv = ethtool_adv_to_mii_ctrl1000_t(advertise); - err = phy_write(phydev, MII_CTRL1000, adv); + err = phy_modify_changed(phydev, MII_CTRL1000, + ADVERTISE_1000FULL | ADVERTISE_1000HALF, + adv); if (err < 0) return err; + if (err > 0) + changed = 1; return changed; } @@ -1586,34 +1575,20 @@ static int genphy_config_advert(struct phy_device *phydev) * efficent ethernet modes. Returns 0 if the PHY's advertisement hasn't * changed, and 1 if it has changed. */ -static int genphy_config_eee_advert(struct phy_device *phydev) +int genphy_config_eee_advert(struct phy_device *phydev) { - int broken = phydev->eee_broken_modes; - int old_adv, adv; + int err; /* Nothing to disable */ - if (!broken) + if (!phydev->eee_broken_modes) return 0; - /* If the following call fails, we assume that EEE is not - * supported by the phy. If we read 0, EEE is not advertised - * In both case, we don't need to continue - */ - adv = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV); - if (adv <= 0) - return 0; - - old_adv = adv; - adv &= ~broken; - - /* Advertising remains unchanged with the broken mask */ - if (old_adv == adv) - return 0; - - phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, adv); - - return 1; + err = phy_modify_mmd_changed(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, + phydev->eee_broken_modes, 0); + /* If the call failed, we assume that EEE is not supported */ + return err < 0 ? 0 : err; } +EXPORT_SYMBOL(genphy_config_eee_advert); /** * genphy_setup_forced - configures/forces speed/duplex from @phydev @@ -1729,10 +1704,19 @@ int genphy_update_link(struct phy_device *phydev) { int status; - /* Do a fake read */ - status = phy_read(phydev, MII_BMSR); - if (status < 0) - return status; + /* The link state is latched low so that momentary link + * drops can be detected. Do not double-read the status + * in polling mode to detect such short link drops. + */ + if (!phy_polling_mode(phydev)) { + status = phy_read(phydev, MII_BMSR); + if (status < 0) { + return status; + } else if (status & BMSR_LSTATUS) { + phydev->link = 1; + return 0; + } + } /* Read link and autonegotiation status */ status = phy_read(phydev, MII_BMSR); @@ -1763,8 +1747,6 @@ int genphy_read_status(struct phy_device *phydev) int err; int lpa; int lpagb = 0; - int common_adv; - int common_adv_gb = 0; /* Update the link, but return if there was an error */ err = genphy_update_link(phydev); @@ -1796,7 +1778,6 @@ int genphy_read_status(struct phy_device *phydev) mii_stat1000_mod_linkmode_lpa_t(phydev->lp_advertising, lpagb); - common_adv_gb = lpagb & adv << 2; } lpa = phy_read(phydev, MII_LPA); @@ -1805,35 +1786,12 @@ int genphy_read_status(struct phy_device *phydev) mii_lpa_mod_linkmode_lpa_t(phydev->lp_advertising, lpa); - adv = phy_read(phydev, MII_ADVERTISE); - if (adv < 0) - return adv; - - common_adv = lpa & adv; - - phydev->speed = SPEED_10; - phydev->duplex = DUPLEX_HALF; + phydev->speed = SPEED_UNKNOWN; + phydev->duplex = DUPLEX_UNKNOWN; phydev->pause = 0; phydev->asym_pause = 0; - if (common_adv_gb & (LPA_1000FULL | LPA_1000HALF)) { - phydev->speed = SPEED_1000; - - if (common_adv_gb & LPA_1000FULL) - phydev->duplex = DUPLEX_FULL; - } else if (common_adv & (LPA_100FULL | LPA_100HALF)) { - phydev->speed = SPEED_100; - - if (common_adv & LPA_100FULL) - phydev->duplex = DUPLEX_FULL; - } else - if (common_adv & LPA_10FULL) - phydev->duplex = DUPLEX_FULL; - - if (phydev->duplex == DUPLEX_FULL) { - phydev->pause = lpa & LPA_PAUSE_CAP ? 1 : 0; - phydev->asym_pause = lpa & LPA_PAUSE_ASYM ? 1 : 0; - } + phy_resolve_aneg_linkmode(phydev); } else { int bmcr = phy_read(phydev, MII_BMCR); @@ -1965,44 +1923,6 @@ int genphy_loopback(struct phy_device *phydev, bool enable) } EXPORT_SYMBOL(genphy_loopback); -static int __set_phy_supported(struct phy_device *phydev, u32 max_speed) -{ - switch (max_speed) { - case SPEED_10: - linkmode_clear_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, - phydev->supported); - linkmode_clear_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, - phydev->supported); - /* fall through */ - case SPEED_100: - linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, - phydev->supported); - linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, - phydev->supported); - break; - case SPEED_1000: - break; - default: - return -ENOTSUPP; - } - - return 0; -} - -int phy_set_max_speed(struct phy_device *phydev, u32 max_speed) -{ - int err; - - err = __set_phy_supported(phydev, max_speed); - if (err) - return err; - - linkmode_copy(phydev->advertising, phydev->supported); - - return 0; -} -EXPORT_SYMBOL(phy_set_max_speed); - /** * phy_remove_link_mode - Remove a supported link mode * @phydev: phy_device structure to remove link mode from @@ -2133,48 +2053,6 @@ bool phy_validate_pause(struct phy_device *phydev, } EXPORT_SYMBOL(phy_validate_pause); -static void of_set_phy_supported(struct phy_device *phydev) -{ - struct device_node *node = phydev->mdio.dev.of_node; - u32 max_speed; - - if (!IS_ENABLED(CONFIG_OF_MDIO)) - return; - - if (!node) - return; - - if (!of_property_read_u32(node, "max-speed", &max_speed)) - __set_phy_supported(phydev, max_speed); -} - -static void of_set_phy_eee_broken(struct phy_device *phydev) -{ - struct device_node *node = phydev->mdio.dev.of_node; - u32 broken = 0; - - if (!IS_ENABLED(CONFIG_OF_MDIO)) - return; - - if (!node) - return; - - if (of_property_read_bool(node, "eee-broken-100tx")) - broken |= MDIO_EEE_100TX; - if (of_property_read_bool(node, "eee-broken-1000t")) - broken |= MDIO_EEE_1000T; - if (of_property_read_bool(node, "eee-broken-10gt")) - broken |= MDIO_EEE_10GT; - if (of_property_read_bool(node, "eee-broken-1000kx")) - broken |= MDIO_EEE_1000KX; - if (of_property_read_bool(node, "eee-broken-10gkx4")) - broken |= MDIO_EEE_10GKX4; - if (of_property_read_bool(node, "eee-broken-10gkr")) - broken |= MDIO_EEE_10GKR; - - phydev->eee_broken_modes = broken; -} - static bool phy_drv_supports_irq(struct phy_driver *phydrv) { return phydrv->config_intr && phydrv->ack_interrupt; @@ -2208,11 +2086,30 @@ static int phy_probe(struct device *dev) mutex_lock(&phydev->lock); + if (phydev->drv->probe) { + /* Deassert the reset signal */ + phy_device_reset(phydev, 0); + + err = phydev->drv->probe(phydev); + if (err) { + /* Assert the reset signal */ + phy_device_reset(phydev, 1); + goto out; + } + } + /* Start out supporting everything. Eventually, * a controller will attach, and may modify one * or both of these values */ - linkmode_copy(phydev->supported, phydrv->features); + if (phydrv->features) { + linkmode_copy(phydev->supported, phydrv->features); + } else { + err = phydrv->get_features(phydev); + if (err) + goto out; + } + of_set_phy_supported(phydev); linkmode_copy(phydev->advertising, phydev->supported); @@ -2232,20 +2129,8 @@ static int phy_probe(struct device *dev) * (e.g. hardware erratum) where the driver wants to set only one * of these bits. */ - if (test_bit(ETHTOOL_LINK_MODE_Pause_BIT, phydrv->features) || - test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, phydrv->features)) { - linkmode_clear_bit(ETHTOOL_LINK_MODE_Pause_BIT, - phydev->supported); - linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, - phydev->supported); - if (test_bit(ETHTOOL_LINK_MODE_Pause_BIT, phydrv->features)) - linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, - phydev->supported); - if (test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, - phydrv->features)) - linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, - phydev->supported); - } else { + if (!test_bit(ETHTOOL_LINK_MODE_Pause_BIT, phydev->supported) && + !test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, phydev->supported)) { linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, phydev->supported); linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, @@ -2255,17 +2140,7 @@ static int phy_probe(struct device *dev) /* Set the state to READY by default */ phydev->state = PHY_READY; - if (phydev->drv->probe) { - /* Deassert the reset signal */ - phy_device_reset(phydev, 0); - - err = phydev->drv->probe(phydev); - if (err) { - /* Assert the reset signal */ - phy_device_reset(phydev, 1); - } - } - +out: mutex_unlock(&phydev->lock); return err; @@ -2301,7 +2176,11 @@ int phy_driver_register(struct phy_driver *new_driver, struct module *owner) { int retval; - if (WARN_ON(!new_driver->features)) { + /* Either the features are hard coded, or dynamically + * determine. It cannot be both or neither + */ + if (WARN_ON((!new_driver->features && !new_driver->get_features) || + (new_driver->features && new_driver->get_features))) { pr_err("%s: Driver features are missing\n", new_driver->name); return -EINVAL; } diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 2e21ce42e388..59d175a5ba54 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -302,6 +302,13 @@ static void phylink_mac_config(struct phylink *pl, pl->ops->mac_config(pl->netdev, pl->link_an_mode, state); } +static void phylink_mac_config_up(struct phylink *pl, + const struct phylink_link_state *state) +{ + if (state->link) + phylink_mac_config(pl, state); +} + static void phylink_mac_an_restart(struct phylink *pl) { if (pl->link_config.an_enabled && @@ -401,12 +408,12 @@ static void phylink_resolve(struct work_struct *w) case MLO_AN_PHY: link_state = pl->phy_state; phylink_resolve_flow(pl, &link_state); - phylink_mac_config(pl, &link_state); + phylink_mac_config_up(pl, &link_state); break; case MLO_AN_FIXED: phylink_get_fixed_state(pl, &link_state); - phylink_mac_config(pl, &link_state); + phylink_mac_config_up(pl, &link_state); break; case MLO_AN_INBAND: @@ -471,6 +478,17 @@ static void phylink_run_resolve(struct phylink *pl) queue_work(system_power_efficient_wq, &pl->resolve); } +static void phylink_run_resolve_and_disable(struct phylink *pl, int bit) +{ + unsigned long state = pl->phylink_disable_state; + + set_bit(bit, &pl->phylink_disable_state); + if (state == 0) { + queue_work(system_power_efficient_wq, &pl->resolve); + flush_work(&pl->resolve); + } +} + static void phylink_fixed_poll(struct timer_list *t) { struct phylink *pl = container_of(t, struct phylink, link_poll); @@ -920,9 +938,7 @@ void phylink_stop(struct phylink *pl) if (pl->link_an_mode == MLO_AN_FIXED && !IS_ERR(pl->link_gpio)) del_timer_sync(&pl->link_poll); - set_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state); - queue_work(system_power_efficient_wq, &pl->resolve); - flush_work(&pl->resolve); + phylink_run_resolve_and_disable(pl, PHYLINK_DISABLE_STOPPED); } EXPORT_SYMBOL_GPL(phylink_stop); @@ -1265,6 +1281,24 @@ int phylink_get_eee_err(struct phylink *pl) EXPORT_SYMBOL_GPL(phylink_get_eee_err); /** + * phylink_init_eee() - init and check the EEE features + * @pl: a pointer to a &struct phylink returned from phylink_create() + * @clk_stop_enable: allow PHY to stop receive clock + * + * Must be called either with RTNL held or within mac_link_up() + */ +int phylink_init_eee(struct phylink *pl, bool clk_stop_enable) +{ + int ret = -EOPNOTSUPP; + + if (pl->phydev) + ret = phy_init_eee(pl->phydev, clk_stop_enable); + + return ret; +} +EXPORT_SYMBOL_GPL(phylink_init_eee); + +/** * phylink_ethtool_get_eee() - read the energy efficient ethernet parameters * @pl: a pointer to a &struct phylink returned from phylink_create() * @eee: a pointer to a &struct ethtool_eee for the read parameters @@ -1628,9 +1662,7 @@ static void phylink_sfp_link_down(void *upstream) ASSERT_RTNL(); - set_bit(PHYLINK_DISABLE_LINK, &pl->phylink_disable_state); - queue_work(system_power_efficient_wq, &pl->resolve); - flush_work(&pl->resolve); + phylink_run_resolve_and_disable(pl, PHYLINK_DISABLE_LINK); } static void phylink_sfp_link_up(void *upstream) diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index ad9db652874d..fef701bfad62 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -347,6 +347,7 @@ static int sfp_register_bus(struct sfp_bus *bus) return ret; } } + bus->socket_ops->attach(bus->sfp); if (bus->started) bus->socket_ops->start(bus->sfp); bus->netdev->sfp_bus = bus; @@ -362,6 +363,7 @@ static void sfp_unregister_bus(struct sfp_bus *bus) if (bus->registered) { if (bus->started) bus->socket_ops->stop(bus->sfp); + bus->socket_ops->detach(bus->sfp); if (bus->phydev && ops && ops->disconnect_phy) ops->disconnect_phy(bus->upstream); } diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 298ab7546929..d4635c2178d1 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -185,6 +185,7 @@ struct sfp { struct gpio_desc *gpio[GPIO_MAX]; + bool attached; unsigned int state; struct delayed_work poll; struct delayed_work timeout; @@ -1476,7 +1477,7 @@ static void sfp_sm_event(struct sfp *sfp, unsigned int event) */ switch (sfp->sm_mod_state) { default: - if (event == SFP_E_INSERT) { + if (event == SFP_E_INSERT && sfp->attached) { sfp_module_tx_disable(sfp); sfp_sm_ins_next(sfp, SFP_MOD_PROBE, T_PROBE_INIT); } @@ -1608,6 +1609,19 @@ static void sfp_sm_event(struct sfp *sfp, unsigned int event) mutex_unlock(&sfp->sm_mutex); } +static void sfp_attach(struct sfp *sfp) +{ + sfp->attached = true; + if (sfp->state & SFP_F_PRESENT) + sfp_sm_event(sfp, SFP_E_INSERT); +} + +static void sfp_detach(struct sfp *sfp) +{ + sfp->attached = false; + sfp_sm_event(sfp, SFP_E_REMOVE); +} + static void sfp_start(struct sfp *sfp) { sfp_sm_event(sfp, SFP_E_DEV_UP); @@ -1668,6 +1682,8 @@ static int sfp_module_eeprom(struct sfp *sfp, struct ethtool_eeprom *ee, } static const struct sfp_socket_ops sfp_module_ops = { + .attach = sfp_attach, + .detach = sfp_detach, .start = sfp_start, .stop = sfp_stop, .module_info = sfp_module_info, @@ -1835,10 +1851,6 @@ static int sfp_probe(struct platform_device *pdev) dev_info(sfp->dev, "Host maximum power %u.%uW\n", sfp->max_power_mW / 1000, (sfp->max_power_mW / 100) % 10); - sfp->sfp_bus = sfp_register_socket(sfp->dev, sfp, &sfp_module_ops); - if (!sfp->sfp_bus) - return -ENOMEM; - /* Get the initial state, and always signal TX disable, * since the network interface will not be up. */ @@ -1849,10 +1861,6 @@ static int sfp_probe(struct platform_device *pdev) sfp->state |= SFP_F_RATE_SELECT; sfp_set_state(sfp, sfp->state); sfp_module_tx_disable(sfp); - rtnl_lock(); - if (sfp->state & SFP_F_PRESENT) - sfp_sm_event(sfp, SFP_E_INSERT); - rtnl_unlock(); for (i = 0; i < GPIO_MAX; i++) { if (gpio_flags[i] != GPIOD_IN || !sfp->gpio[i]) @@ -1885,6 +1893,10 @@ static int sfp_probe(struct platform_device *pdev) dev_warn(sfp->dev, "No tx_disable pin: SFP modules will always be emitting.\n"); + sfp->sfp_bus = sfp_register_socket(sfp->dev, sfp, &sfp_module_ops); + if (!sfp->sfp_bus) + return -ENOMEM; + return 0; } diff --git a/drivers/net/phy/sfp.h b/drivers/net/phy/sfp.h index 31b0acf337e2..64f54b0bbd8c 100644 --- a/drivers/net/phy/sfp.h +++ b/drivers/net/phy/sfp.h @@ -7,6 +7,8 @@ struct sfp; struct sfp_socket_ops { + void (*attach)(struct sfp *sfp); + void (*detach)(struct sfp *sfp); void (*start)(struct sfp *sfp); void (*stop)(struct sfp *sfp); int (*module_info)(struct sfp *sfp, struct ethtool_modinfo *modinfo); diff --git a/drivers/net/phy/xilinx_gmii2rgmii.c b/drivers/net/phy/xilinx_gmii2rgmii.c index ebf419dc7307..2d1449345959 100644 --- a/drivers/net/phy/xilinx_gmii2rgmii.c +++ b/drivers/net/phy/xilinx_gmii2rgmii.c @@ -35,7 +35,10 @@ static int xgmiitorgmii_read_status(struct phy_device *phydev) u16 val = 0; int err; - err = priv->phy_drv->read_status(phydev); + if (priv->phy_drv->read_status) + err = priv->phy_drv->read_status(phydev); + else + err = genphy_read_status(phydev); if (err < 0) return err; diff --git a/drivers/net/tap.c b/drivers/net/tap.c index c0b52e48f0e6..2ea9b4976f4a 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -712,7 +712,7 @@ static ssize_t tap_get_user(struct tap_queue *q, void *msg_control, goto err_kfree; } - skb_probe_transport_header(skb, ETH_HLEN); + skb_probe_transport_header(skb); /* Move network header to the right position for VLAN tagged packets */ if ((skb->protocol == htons(ETH_P_8021Q) || @@ -1187,7 +1187,7 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp) tap = rcu_dereference(q->tap); if (tap) { skb->dev = tap->dev; - skb_probe_transport_header(skb, ETH_HLEN); + skb_probe_transport_header(skb); dev_queue_xmit(skb); } else { kfree_skb(skb); diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index afd9d25d1992..958f1cf67282 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -256,17 +256,6 @@ static void __team_option_inst_mark_removed_port(struct team *team, } } -static bool __team_option_inst_tmp_find(const struct list_head *opts, - const struct team_option_inst *needle) -{ - struct team_option_inst *opt_inst; - - list_for_each_entry(opt_inst, opts, tmp_list) - if (opt_inst == needle) - return true; - return false; -} - static int __team_options_register(struct team *team, const struct team_option *option, size_t option_count) @@ -2460,7 +2449,6 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info) int err = 0; int i; struct nlattr *nl_option; - LIST_HEAD(opt_inst_list); rtnl_lock(); @@ -2480,6 +2468,7 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info) struct nlattr *opt_attrs[TEAM_ATTR_OPTION_MAX + 1]; struct nlattr *attr; struct nlattr *attr_data; + LIST_HEAD(opt_inst_list); enum team_option_type opt_type; int opt_port_ifindex = 0; /* != 0 for per-port options */ u32 opt_array_index = 0; @@ -2584,23 +2573,17 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info) if (err) goto team_put; opt_inst->changed = true; - - /* dumb/evil user-space can send us duplicate opt, - * keep only the last one - */ - if (__team_option_inst_tmp_find(&opt_inst_list, - opt_inst)) - continue; - list_add(&opt_inst->tmp_list, &opt_inst_list); } if (!opt_found) { err = -ENOENT; goto team_put; } - } - err = team_nl_send_event_options_get(team, &opt_inst_list); + err = team_nl_send_event_options_get(team, &opt_inst_list); + if (err) + break; + } team_put: team_nl_team_put(team); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 18656c4094b3..80bff1b4ec17 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -866,8 +866,6 @@ static int tun_attach(struct tun_struct *tun, struct file *file, if (rtnl_dereference(tun->xdp_prog)) sock_set_flag(&tfile->sk, SOCK_XDP); - tun_set_real_num_queues(tun); - /* device is allowed to go away first, so no need to hold extra * refcnt. */ @@ -879,6 +877,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file, rcu_assign_pointer(tfile->tun, tun); rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile); tun->numqueues++; + tun_set_real_num_queues(tun); out: return err; } @@ -1930,7 +1929,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, } skb_reset_network_header(skb); - skb_probe_transport_header(skb, 0); + skb_probe_transport_header(skb); if (skb_xdp) { struct bpf_prog *xdp_prog; @@ -2483,7 +2482,7 @@ build: skb->protocol = eth_type_trans(skb, tun->dev); skb_reset_network_header(skb); - skb_probe_transport_header(skb, 0); + skb_probe_transport_header(skb); if (skb_xdp) { err = do_xdp_generic(xdp_prog, skb); diff --git a/drivers/net/usb/cdc-phonet.c b/drivers/net/usb/cdc-phonet.c index 78b16eb9e58c..63aaae487995 100644 --- a/drivers/net/usb/cdc-phonet.c +++ b/drivers/net/usb/cdc-phonet.c @@ -361,8 +361,8 @@ static int usbpn_probe(struct usb_interface *intf, const struct usb_device_id *i else return -EINVAL; - dev = alloc_netdev(sizeof(*pnd) + sizeof(pnd->urbs[0]) * rxq_size, - ifname, NET_NAME_UNKNOWN, usbpn_setup); + dev = alloc_netdev(struct_size(pnd, urbs, rxq_size), ifname, + NET_NAME_UNKNOWN, usbpn_setup); if (!dev) return -ENOMEM; diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c index f4247b275e09..63e44e746ccc 100644 --- a/drivers/net/usb/pegasus.c +++ b/drivers/net/usb/pegasus.c @@ -1011,6 +1011,7 @@ static int pegasus_ioctl(struct net_device *net, struct ifreq *rq, int cmd) switch (cmd) { case SIOCDEVPRIVATE: data[0] = pegasus->phy; + /* fall through */ case SIOCDEVPRIVATE + 1: read_mii_word(pegasus, data[0], data[1] & 0x1f, &data[3]); res = 0; diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 735ad838e2ba..18af2f8eee96 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1201,8 +1201,8 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x114f, 0x68a2, 8)}, /* Sierra Wireless MC7750 */ {QMI_FIXED_INTF(0x1199, 0x68a2, 8)}, /* Sierra Wireless MC7710 in QMI mode */ {QMI_FIXED_INTF(0x1199, 0x68a2, 19)}, /* Sierra Wireless MC7710 in QMI mode */ - {QMI_FIXED_INTF(0x1199, 0x68c0, 8)}, /* Sierra Wireless MC7304/MC7354 */ - {QMI_FIXED_INTF(0x1199, 0x68c0, 10)}, /* Sierra Wireless MC7304/MC7354 */ + {QMI_QUIRK_SET_DTR(0x1199, 0x68c0, 8)}, /* Sierra Wireless MC7304/MC7354, WP76xx */ + {QMI_QUIRK_SET_DTR(0x1199, 0x68c0, 10)},/* Sierra Wireless MC7304/MC7354 */ {QMI_FIXED_INTF(0x1199, 0x901c, 8)}, /* Sierra Wireless EM7700 */ {QMI_FIXED_INTF(0x1199, 0x901f, 8)}, /* Sierra Wireless EM7355 */ {QMI_FIXED_INTF(0x1199, 0x9041, 8)}, /* Sierra Wireless MC7305/MC7355 */ diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 60dd1ec1665f..ada6baf8847a 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -557,6 +557,7 @@ enum spd_duplex { /* MAC PASSTHRU */ #define AD_MASK 0xfee0 #define BND_MASK 0x0004 +#define BD_MASK 0x0001 #define EFUSE 0xcfdb #define PASS_THRU_MASK 0x1 @@ -1176,9 +1177,9 @@ static int vendor_mac_passthru_addr_read(struct r8152 *tp, struct sockaddr *sa) return -ENODEV; } } else { - /* test for RTL8153-BND */ + /* test for RTL8153-BND and RTL8153-BD */ ocp_data = ocp_read_byte(tp, MCU_TYPE_USB, USB_MISC_1); - if ((ocp_data & BND_MASK) == 0) { + if ((ocp_data & BND_MASK) == 0 && (ocp_data & BD_MASK)) { netif_dbg(tp, probe, tp->netdev, "Invalid variant for MAC pass through\n"); return -ENODEV; diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c index 3f145e4c6c08..59dbdbb5feff 100644 --- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -847,6 +847,7 @@ static int rtl8150_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) switch (cmd) { case SIOCDEVPRIVATE: data[0] = dev->phy; + /* fall through */ case SIOCDEVPRIVATE + 1: read_mii_word(dev, dev->phy, (data[1] & 0x1f), &data[3]); break; diff --git a/drivers/net/veth.c b/drivers/net/veth.c index f412ea1cef18..fbf890ebbeae 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -540,8 +540,10 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq, goto xdp_xmit; default: bpf_warn_invalid_xdp_action(act); + /* fall through */ case XDP_ABORTED: trace_xdp_exception(rq->dev, xdp_prog, act); + /* fall through */ case XDP_DROP: goto err_xdp; } @@ -661,8 +663,10 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq, struct sk_buff *skb, goto xdp_xmit; default: bpf_warn_invalid_xdp_action(act); + /* fall through */ case XDP_ABORTED: trace_xdp_exception(rq->dev, xdp_prog, act); + /* fall through */ case XDP_DROP: goto drop; } diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 2a0edd4653e3..7eb38ea9ba56 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -57,6 +57,8 @@ module_param(napi_tx, bool, 0644); #define VIRTIO_XDP_TX BIT(0) #define VIRTIO_XDP_REDIR BIT(1) +#define VIRTIO_XDP_FLAG BIT(0) + /* RX packet size EWMA. The average packet size is used to determine the packet * buffer size when refilling RX rings. As the entire RX ring may be refilled * at once, the weight is chosen so that the EWMA will be insensitive to short- @@ -252,6 +254,21 @@ struct padded_vnet_hdr { char padding[4]; }; +static bool is_xdp_frame(void *ptr) +{ + return (unsigned long)ptr & VIRTIO_XDP_FLAG; +} + +static void *xdp_to_ptr(struct xdp_frame *ptr) +{ + return (void *)((unsigned long)ptr | VIRTIO_XDP_FLAG); +} + +static struct xdp_frame *ptr_to_xdp(void *ptr) +{ + return (struct xdp_frame *)((unsigned long)ptr & ~VIRTIO_XDP_FLAG); +} + /* Converting between virtqueue no. and kernel tx/rx queue no. * 0:rx0 1:tx0 2:rx1 3:tx1 ... 2N:rxN 2N+1:txN 2N+2:cvq */ @@ -462,7 +479,8 @@ static int __virtnet_xdp_xmit_one(struct virtnet_info *vi, sg_init_one(sq->sg, xdpf->data, xdpf->len); - err = virtqueue_add_outbuf(sq->vq, sq->sg, 1, xdpf, GFP_ATOMIC); + err = virtqueue_add_outbuf(sq->vq, sq->sg, 1, xdp_to_ptr(xdpf), + GFP_ATOMIC); if (unlikely(err)) return -ENOSPC; /* Caller handle free/refcnt */ @@ -482,36 +500,47 @@ static int virtnet_xdp_xmit(struct net_device *dev, { struct virtnet_info *vi = netdev_priv(dev); struct receive_queue *rq = vi->rq; - struct xdp_frame *xdpf_sent; struct bpf_prog *xdp_prog; struct send_queue *sq; unsigned int len; + int packets = 0; + int bytes = 0; int drops = 0; int kicks = 0; int ret, err; + void *ptr; int i; - sq = virtnet_xdp_sq(vi); - - if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) { - ret = -EINVAL; - drops = n; - goto out; - } - /* Only allow ndo_xdp_xmit if XDP is loaded on dev, as this * indicate XDP resources have been successfully allocated. */ xdp_prog = rcu_dereference(rq->xdp_prog); - if (!xdp_prog) { - ret = -ENXIO; + if (!xdp_prog) + return -ENXIO; + + sq = virtnet_xdp_sq(vi); + + if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) { + ret = -EINVAL; drops = n; goto out; } /* Free up any pending old buffers before queueing new ones. */ - while ((xdpf_sent = virtqueue_get_buf(sq->vq, &len)) != NULL) - xdp_return_frame(xdpf_sent); + while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) { + if (likely(is_xdp_frame(ptr))) { + struct xdp_frame *frame = ptr_to_xdp(ptr); + + bytes += frame->len; + xdp_return_frame(frame); + } else { + struct sk_buff *skb = ptr; + + bytes += skb->len; + napi_consume_skb(skb, false); + } + packets++; + } for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; @@ -530,6 +559,8 @@ static int virtnet_xdp_xmit(struct net_device *dev, } out: u64_stats_update_begin(&sq->stats.syncp); + sq->stats.bytes += bytes; + sq->stats.packets += packets; sq->stats.xdp_tx += n; sq->stats.xdp_tx_drops += drops; sq->stats.kicks += kicks; @@ -1333,18 +1364,26 @@ static int virtnet_receive(struct receive_queue *rq, int budget, static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi) { - struct sk_buff *skb; unsigned int len; unsigned int packets = 0; unsigned int bytes = 0; + void *ptr; - while ((skb = virtqueue_get_buf(sq->vq, &len)) != NULL) { - pr_debug("Sent skb %p\n", skb); + while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) { + if (likely(!is_xdp_frame(ptr))) { + struct sk_buff *skb = ptr; - bytes += skb->len; - packets++; + pr_debug("Sent skb %p\n", skb); + + bytes += skb->len; + napi_consume_skb(skb, in_napi); + } else { + struct xdp_frame *frame = ptr_to_xdp(ptr); - napi_consume_skb(skb, in_napi); + bytes += frame->len; + xdp_return_frame(frame); + } + packets++; } /* Avoid overhead when no packets have been processed @@ -1359,6 +1398,16 @@ static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi) u64_stats_update_end(&sq->stats.syncp); } +static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q) +{ + if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs)) + return false; + else if (q < vi->curr_queue_pairs) + return true; + else + return false; +} + static void virtnet_poll_cleantx(struct receive_queue *rq) { struct virtnet_info *vi = rq->vq->vdev->priv; @@ -1366,7 +1415,7 @@ static void virtnet_poll_cleantx(struct receive_queue *rq) struct send_queue *sq = &vi->sq[index]; struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, index); - if (!sq->napi.weight) + if (!sq->napi.weight || is_xdp_raw_buffer_queue(vi, index)) return; if (__netif_tx_trylock(txq)) { @@ -1443,8 +1492,16 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget) { struct send_queue *sq = container_of(napi, struct send_queue, napi); struct virtnet_info *vi = sq->vq->vdev->priv; - struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, vq2txq(sq->vq)); + unsigned int index = vq2txq(sq->vq); + struct netdev_queue *txq; + if (unlikely(is_xdp_raw_buffer_queue(vi, index))) { + /* We don't need to enable cb for XDP */ + napi_complete_done(napi, 0); + return 0; + } + + txq = netdev_get_tx_queue(vi->dev, index); __netif_tx_lock(txq, raw_smp_processor_id()); free_old_xmit_skbs(sq, true); __netif_tx_unlock(txq); @@ -2396,6 +2453,10 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, return -ENOMEM; } + old_prog = rtnl_dereference(vi->rq[0].xdp_prog); + if (!prog && !old_prog) + return 0; + if (prog) { prog = bpf_prog_add(prog, vi->max_queue_pairs - 1); if (IS_ERR(prog)) @@ -2403,36 +2464,62 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, } /* Make sure NAPI is not using any XDP TX queues for RX. */ - if (netif_running(dev)) - for (i = 0; i < vi->max_queue_pairs; i++) + if (netif_running(dev)) { + for (i = 0; i < vi->max_queue_pairs; i++) { napi_disable(&vi->rq[i].napi); + virtnet_napi_tx_disable(&vi->sq[i].napi); + } + } + + if (!prog) { + for (i = 0; i < vi->max_queue_pairs; i++) { + rcu_assign_pointer(vi->rq[i].xdp_prog, prog); + if (i == 0) + virtnet_restore_guest_offloads(vi); + } + synchronize_net(); + } - netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp); err = _virtnet_set_queues(vi, curr_qp + xdp_qp); if (err) goto err; + netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp); vi->xdp_queue_pairs = xdp_qp; - for (i = 0; i < vi->max_queue_pairs; i++) { - old_prog = rtnl_dereference(vi->rq[i].xdp_prog); - rcu_assign_pointer(vi->rq[i].xdp_prog, prog); - if (i == 0) { - if (!old_prog) + if (prog) { + for (i = 0; i < vi->max_queue_pairs; i++) { + rcu_assign_pointer(vi->rq[i].xdp_prog, prog); + if (i == 0 && !old_prog) virtnet_clear_guest_offloads(vi); - if (!prog) - virtnet_restore_guest_offloads(vi); } + } + + for (i = 0; i < vi->max_queue_pairs; i++) { if (old_prog) bpf_prog_put(old_prog); - if (netif_running(dev)) + if (netif_running(dev)) { virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); + virtnet_napi_tx_enable(vi, vi->sq[i].vq, + &vi->sq[i].napi); + } } return 0; err: - for (i = 0; i < vi->max_queue_pairs; i++) - virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); + if (!prog) { + virtnet_clear_guest_offloads(vi); + for (i = 0; i < vi->max_queue_pairs; i++) + rcu_assign_pointer(vi->rq[i].xdp_prog, old_prog); + } + + if (netif_running(dev)) { + for (i = 0; i < vi->max_queue_pairs; i++) { + virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); + virtnet_napi_tx_enable(vi, vi->sq[i].vq, + &vi->sq[i].napi); + } + } if (prog) bpf_prog_sub(prog, vi->max_queue_pairs - 1); return err; @@ -2614,16 +2701,6 @@ static void free_receive_page_frags(struct virtnet_info *vi) put_page(vi->rq[i].alloc_frag.page); } -static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q) -{ - if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs)) - return false; - else if (q < vi->curr_queue_pairs) - return true; - else - return false; -} - static void free_unused_bufs(struct virtnet_info *vi) { void *buf; @@ -2632,10 +2709,10 @@ static void free_unused_bufs(struct virtnet_info *vi) for (i = 0; i < vi->max_queue_pairs; i++) { struct virtqueue *vq = vi->sq[i].vq; while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) { - if (!is_xdp_raw_buffer_queue(vi, i)) + if (!is_xdp_frame(buf)) dev_kfree_skb(buf); else - put_page(virt_to_head_page(buf)); + xdp_return_frame(ptr_to_xdp(buf)); } } diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index ef45c3c925be..33edc78e818d 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -869,6 +869,14 @@ static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f, call_rcu(&f->rcu, vxlan_fdb_free); } +static void vxlan_dst_free(struct rcu_head *head) +{ + struct vxlan_rdst *rd = container_of(head, struct vxlan_rdst, rcu); + + dst_cache_destroy(&rd->dst_cache); + kfree(rd); +} + static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan, union vxlan_addr *ip, __u16 state, __u16 flags, @@ -941,8 +949,10 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan, err_notify: if ((flags & NLM_F_REPLACE) && rc) *rd = oldrd; - else if ((flags & NLM_F_APPEND) && rc) + else if ((flags & NLM_F_APPEND) && rc) { list_del_rcu(&rd->list); + call_rcu(&rd->rcu, vxlan_dst_free); + } return err; } @@ -1013,14 +1023,6 @@ static int vxlan_fdb_update(struct vxlan_dev *vxlan, } } -static void vxlan_dst_free(struct rcu_head *head) -{ - struct vxlan_rdst *rd = container_of(head, struct vxlan_rdst, rcu); - - dst_cache_destroy(&rd->dst_cache); - kfree(rd); -} - static void vxlan_fdb_dst_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f, struct vxlan_rdst *rd, bool swdev_notify) { @@ -2291,7 +2293,7 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, struct pcpu_sw_netstats *tx_stats, *rx_stats; union vxlan_addr loopback; union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip; - struct net_device *dev = skb->dev; + struct net_device *dev; int len = skb->len; tx_stats = this_cpu_ptr(src_vxlan->dev->tstats); @@ -2311,9 +2313,15 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, #endif } + rcu_read_lock(); + dev = skb->dev; + if (unlikely(!(dev->flags & IFF_UP))) { + kfree_skb(skb); + goto drop; + } + if (dst_vxlan->cfg.flags & VXLAN_F_LEARN) - vxlan_snoop(skb->dev, &loopback, eth_hdr(skb)->h_source, 0, - vni); + vxlan_snoop(dev, &loopback, eth_hdr(skb)->h_source, 0, vni); u64_stats_update_begin(&tx_stats->syncp); tx_stats->tx_packets++; @@ -2326,8 +2334,10 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, rx_stats->rx_bytes += len; u64_stats_update_end(&rx_stats->syncp); } else { +drop: dev->stats.rx_dropped++; } + rcu_read_unlock(); } static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev, diff --git a/drivers/net/wan/dscc4.c b/drivers/net/wan/dscc4.c index d5dc823f781e..fa78d2b14136 100644 --- a/drivers/net/wan/dscc4.c +++ b/drivers/net/wan/dscc4.c @@ -1575,7 +1575,7 @@ try: dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; } - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); dpriv->tx_skbuff[cur] = NULL; ++dpriv->tx_dirty; } else { diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c index 66d889d54e58..a08f04c3f644 100644 --- a/drivers/net/wan/fsl_ucc_hdlc.c +++ b/drivers/net/wan/fsl_ucc_hdlc.c @@ -482,7 +482,7 @@ static int hdlc_tx_done(struct ucc_hdlc_private *priv) memset(priv->tx_buffer + (be32_to_cpu(bd->buf) - priv->dma_tx_addr), 0, skb->len); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); priv->tx_skbuff[priv->skb_dirtytx] = NULL; priv->skb_dirtytx = diff --git a/drivers/net/wan/wanxl.c b/drivers/net/wan/wanxl.c index d573a57bc301..459ce52a0a4d 100644 --- a/drivers/net/wan/wanxl.c +++ b/drivers/net/wan/wanxl.c @@ -565,7 +565,7 @@ static int wanxl_pci_init_one(struct pci_dev *pdev, u32 plx_phy; /* PLX PCI base address */ u32 mem_phy; /* memory PCI base addr */ u8 __iomem *mem; /* memory virtual base addr */ - int i, ports, alloc_size; + int i, ports; #ifndef MODULE pr_info_once("%s\n", version); @@ -601,8 +601,7 @@ static int wanxl_pci_init_one(struct pci_dev *pdev, default: ports = 4; } - alloc_size = sizeof(struct card) + ports * sizeof(struct port); - card = kzalloc(alloc_size, GFP_KERNEL); + card = kzalloc(struct_size(card, ports, ports), GFP_KERNEL); if (card == NULL) { pci_release_regions(pdev); pci_disable_device(pdev); diff --git a/drivers/net/wimax/i2400m/rx.c b/drivers/net/wimax/i2400m/rx.c index 0b602951ff6b..d28b96d06919 100644 --- a/drivers/net/wimax/i2400m/rx.c +++ b/drivers/net/wimax/i2400m/rx.c @@ -1260,8 +1260,8 @@ int i2400m_rx(struct i2400m *i2400m, struct sk_buff *skb) goto error_msg_hdr_check; result = -EIO; num_pls = le16_to_cpu(msg_hdr->num_pls); - pl_itr = sizeof(*msg_hdr) + /* Check payload descriptor(s) */ - num_pls * sizeof(msg_hdr->pld[0]); + /* Check payload descriptor(s) */ + pl_itr = struct_size(msg_hdr, pld, num_pls); pl_itr = ALIGN(pl_itr, I2400M_PL_ALIGN); if (pl_itr > skb_len) { /* got all the payload descriptors? */ dev_err(dev, "RX: HW BUG? message too short (%u bytes) for " diff --git a/drivers/net/wimax/i2400m/usb.c b/drivers/net/wimax/i2400m/usb.c index f8eb66ef2944..73842a830645 100644 --- a/drivers/net/wimax/i2400m/usb.c +++ b/drivers/net/wimax/i2400m/usb.c @@ -210,6 +210,7 @@ retry: msleep(10); /* give the device some time */ goto retry; } + /* fall through */ case -EINVAL: /* while removing driver */ case -ENODEV: /* dev disconnect ... */ case -ENOENT: /* just ignore it */ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h b/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h index 7a3f7b7e6358..941c50477003 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h @@ -7,7 +7,7 @@ * * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2017 Intel Deutschland GmbH - * Copyright(c) 2018 Intel Corporation + * Copyright(c) 2018 - 2019 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -29,7 +29,7 @@ * * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2017 Intel Deutschland GmbH - * Copyright(c) 2018 Intel Corporation + * Copyright(c) 2018 - 2019 Intel Corporation * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -433,6 +433,28 @@ struct iwl_he_backoff_conf { __le16 mu_time; } __packed; /* AC_QOS_DOT11AX_API_S */ +/** + * enum iwl_he_pkt_ext_constellations - PPE constellation indices + * @IWL_HE_PKT_EXT_BPSK: BPSK + * @IWL_HE_PKT_EXT_QPSK: QPSK + * @IWL_HE_PKT_EXT_16QAM: 16-QAM + * @IWL_HE_PKT_EXT_64QAM: 64-QAM + * @IWL_HE_PKT_EXT_256QAM: 256-QAM + * @IWL_HE_PKT_EXT_1024QAM: 1024-QAM + * @IWL_HE_PKT_EXT_RESERVED: reserved value + * @IWL_HE_PKT_EXT_NONE: not defined + */ +enum iwl_he_pkt_ext_constellations { + IWL_HE_PKT_EXT_BPSK = 0, + IWL_HE_PKT_EXT_QPSK, + IWL_HE_PKT_EXT_16QAM, + IWL_HE_PKT_EXT_64QAM, + IWL_HE_PKT_EXT_256QAM, + IWL_HE_PKT_EXT_1024QAM, + IWL_HE_PKT_EXT_RESERVED, + IWL_HE_PKT_EXT_NONE, +}; + #define MAX_HE_SUPP_NSS 2 #define MAX_HE_CHANNEL_BW_INDX 4 diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c index 65228a092bd6..87d6de7efdd2 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c @@ -482,7 +482,6 @@ static struct ieee80211_sband_iftype_data iwl_he_capa[] = { IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8, .mac_cap_info[2] = IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP | - IEEE80211_HE_MAC_CAP2_MU_CASCADING | IEEE80211_HE_MAC_CAP2_ACK_EN, .mac_cap_info[3] = IEEE80211_HE_MAC_CAP3_OMI_CONTROL | @@ -493,7 +492,9 @@ static struct ieee80211_sband_iftype_data iwl_he_capa[] = { .mac_cap_info[5] = IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B40 | IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B41 | - IEEE80211_HE_MAC_CAP5_UL_2x996_TONE_RU, + IEEE80211_HE_MAC_CAP5_UL_2x996_TONE_RU | + IEEE80211_HE_MAC_CAP5_HE_DYNAMIC_SM_PS | + IEEE80211_HE_MAC_CAP5_HT_VHT_TRIG_FRAME_RX, .phy_cap_info[0] = IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G | @@ -501,18 +502,13 @@ static struct ieee80211_sband_iftype_data iwl_he_capa[] = { .phy_cap_info[1] = IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK | IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A | - IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD | - IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS, + IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD, .phy_cap_info[2] = - IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US | - IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ | - IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ | - IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO | - IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO, + IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US, .phy_cap_info[3] = - IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_BPSK | + IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_NO_DCM | IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_1 | - IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_BPSK | + IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_NO_DCM | IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_1, .phy_cap_info[4] = IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE | @@ -520,16 +516,8 @@ static struct ieee80211_sband_iftype_data iwl_he_capa[] = { IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_8, .phy_cap_info[5] = IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_2 | - IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2 | - IEEE80211_HE_PHY_CAP5_NG16_SU_FEEDBACK | - IEEE80211_HE_PHY_CAP5_NG16_MU_FEEDBACK, + IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2, .phy_cap_info[6] = - IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_42_SU | - IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_75_MU | - IEEE80211_HE_PHY_CAP6_TRIG_SU_BEAMFORMER_FB | - IEEE80211_HE_PHY_CAP6_TRIG_MU_BEAMFORMER_FB | - IEEE80211_HE_PHY_CAP6_TRIG_CQI_FB | - IEEE80211_HE_PHY_CAP6_PARTIAL_BANDWIDTH_DL_MUMIMO | IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT, .phy_cap_info[7] = IEEE80211_HE_PHY_CAP7_POWER_BOOST_FACTOR_AR | @@ -540,11 +528,12 @@ static struct ieee80211_sband_iftype_data iwl_he_capa[] = { IEEE80211_HE_PHY_CAP8_20MHZ_IN_40MHZ_HE_PPDU_IN_2G | IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU | IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU | - IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_160_OR_80P80_MHZ, + IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_2x996, .phy_cap_info[9] = IEEE80211_HE_PHY_CAP9_NON_TRIGGERED_CQI_FEEDBACK | IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB | - IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB, + IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB | + IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_RESERVED, }, /* * Set default Tx/Rx HE MCS NSS Support field. @@ -578,28 +567,26 @@ static struct ieee80211_sband_iftype_data iwl_he_capa[] = { IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8, .mac_cap_info[2] = IEEE80211_HE_MAC_CAP2_BSR | - IEEE80211_HE_MAC_CAP2_MU_CASCADING | IEEE80211_HE_MAC_CAP2_ACK_EN, .mac_cap_info[3] = IEEE80211_HE_MAC_CAP3_OMI_CONTROL | IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_2, .mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMDSU_IN_AMPDU, + .mac_cap_info[5] = + IEEE80211_HE_MAC_CAP5_UL_2x996_TONE_RU, .phy_cap_info[0] = IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G, .phy_cap_info[1] = - IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD | - IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS, + IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD, .phy_cap_info[2] = - IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US | - IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ | - IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ, + IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US, .phy_cap_info[3] = - IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_BPSK | + IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_NO_DCM | IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_1 | - IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_BPSK | + IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_NO_DCM | IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_1, .phy_cap_info[4] = IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE | @@ -607,12 +594,8 @@ static struct ieee80211_sband_iftype_data iwl_he_capa[] = { IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_8, .phy_cap_info[5] = IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_2 | - IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2 | - IEEE80211_HE_PHY_CAP5_NG16_SU_FEEDBACK | - IEEE80211_HE_PHY_CAP5_NG16_MU_FEEDBACK, + IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2, .phy_cap_info[6] = - IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_42_SU | - IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_75_MU | IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT, .phy_cap_info[7] = IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI | @@ -622,10 +605,11 @@ static struct ieee80211_sband_iftype_data iwl_he_capa[] = { IEEE80211_HE_PHY_CAP8_20MHZ_IN_40MHZ_HE_PPDU_IN_2G | IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU | IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU | - IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_160_OR_80P80_MHZ, + IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_2x996, .phy_cap_info[9] = IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB | - IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB, + IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB | + IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_RESERVED, }, /* * Set default Tx/Rx HE MCS NSS Support field. diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index f8928ba1f338..3a92c09d4692 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -2229,6 +2229,46 @@ static void iwl_mvm_cfg_he_sta(struct iwl_mvm *mvm, } flags |= STA_CTXT_HE_PACKET_EXT; + } else if ((sta->he_cap.he_cap_elem.phy_cap_info[9] & + IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_MASK) != + IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_RESERVED) { + int low_th = -1; + int high_th = -1; + + /* Take the PPE thresholds from the nominal padding info */ + switch (sta->he_cap.he_cap_elem.phy_cap_info[9] & + IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_MASK) { + case IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_0US: + low_th = IWL_HE_PKT_EXT_NONE; + high_th = IWL_HE_PKT_EXT_NONE; + break; + case IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_8US: + low_th = IWL_HE_PKT_EXT_BPSK; + high_th = IWL_HE_PKT_EXT_NONE; + break; + case IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_16US: + low_th = IWL_HE_PKT_EXT_NONE; + high_th = IWL_HE_PKT_EXT_BPSK; + break; + } + + /* Set the PPE thresholds accordingly */ + if (low_th >= 0 && high_th >= 0) { + u8 ***pkt_ext_qam = + (void *)sta_ctxt_cmd.pkt_ext.pkt_ext_qam_th; + + for (i = 0; i < MAX_HE_SUPP_NSS; i++) { + u8 bw; + + for (bw = 0; bw < MAX_HE_CHANNEL_BW_INDX; + bw++) { + pkt_ext_qam[i][bw][0] = low_th; + pkt_ext_qam[i][bw][1] = high_th; + } + } + + flags |= STA_CTXT_HE_PACKET_EXT; + } } rcu_read_unlock(); diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 320edcac4699..e8e359c80ad0 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -1273,10 +1273,12 @@ static bool mac80211_hwsim_tx_frame_no_nl(struct ieee80211_hw *hw, * probably doesn't really matter. */ if (ieee80211_is_beacon(hdr->frame_control) || - ieee80211_is_probe_resp(hdr->frame_control)) + ieee80211_is_probe_resp(hdr->frame_control)) { + rx_status.boottime_ns = ktime_get_boot_ns(); now = data->abs_bcn_ts; - else + } else { now = mac80211_hwsim_get_tsf_raw(); + } /* Copy skb to all enabled radios that are on the current frequency */ spin_lock(&hwsim_radio_lock); @@ -2799,6 +2801,7 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, ieee80211_hw_set(hw, TDLS_WIDER_BW); if (rctbl) ieee80211_hw_set(hw, SUPPORTS_RC_TABLE); + ieee80211_hw_set(hw, SUPPORTS_MULTI_BSSID); hw->wiphy->flags |= WIPHY_FLAG_SUPPORTS_TDLS | WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL | diff --git a/drivers/net/wireless/virt_wifi.c b/drivers/net/wireless/virt_wifi.c index 71044c6cfd8c..606999f102eb 100644 --- a/drivers/net/wireless/virt_wifi.c +++ b/drivers/net/wireless/virt_wifi.c @@ -360,7 +360,6 @@ static struct wiphy *virt_wifi_make_wiphy(void) wiphy->bands[NL80211_BAND_5GHZ] = &band_5ghz; wiphy->bands[NL80211_BAND_60GHZ] = NULL; - wiphy->regulatory_flags = REGULATORY_WIPHY_SELF_MANAGED; wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION); priv = wiphy_priv(wiphy); diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 80aae3a32c2a..c801a832851c 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -1169,15 +1169,24 @@ static int xenvif_tx_submit(struct xenvif_queue *queue) continue; } - skb_probe_transport_header(skb, 0); + skb_probe_transport_header(skb); /* If the packet is GSO then we will have just set up the * transport header offset in checksum_setup so it's now * straightforward to calculate gso_segs. */ if (skb_is_gso(skb)) { - int mss = skb_shinfo(skb)->gso_size; - int hdrlen = skb_transport_header(skb) - + int mss, hdrlen; + + /* GSO implies having the L4 header. */ + WARN_ON_ONCE(!skb_transport_header_was_set(skb)); + if (unlikely(!skb_transport_header_was_set(skb))) { + kfree_skb(skb); + continue; + } + + mss = skb_shinfo(skb)->gso_size; + hdrlen = skb_transport_header(skb) - skb_mac_header(skb) + tcp_hdrlen(skb); diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index 2625740bdc4a..330ddb64930f 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -655,7 +655,7 @@ static void frontend_changed(struct xenbus_device *dev, set_backend_state(be, XenbusStateClosed); if (xenbus_dev_is_online(dev)) break; - /* fall through if not online */ + /* fall through - if not online */ case XenbusStateUnknown: set_backend_state(be, XenbusStateClosed); device_unregister(&dev->dev); |
