diff options
Diffstat (limited to 'drivers/net/ethernet/intel')
82 files changed, 5574 insertions, 3443 deletions
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index c0e17433f623..1349b45f014d 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -58,7 +58,7 @@ config E1000E tristate "Intel(R) PRO/1000 PCI-Express Gigabit Ethernet support" depends on PCI && (!SPARC32 || BROKEN) select CRC32 - select PTP_1588_CLOCK + imply PTP_1588_CLOCK ---help--- This driver supports the PCI-Express Intel(R) PRO/1000 gigabit ethernet family of adapters. For PCI or PCI-X e1000 adapters, @@ -83,7 +83,7 @@ config E1000E_HWTS config IGB tristate "Intel(R) 82575/82576 PCI-Express Gigabit Ethernet support" depends on PCI - select PTP_1588_CLOCK + imply PTP_1588_CLOCK select I2C select I2C_ALGOBIT ---help--- @@ -156,7 +156,7 @@ config IXGBE tristate "Intel(R) 10GbE PCI Express adapters support" depends on PCI select MDIO - select PTP_1588_CLOCK + imply PTP_1588_CLOCK ---help--- This driver supports Intel(R) 10GbE PCI Express family of adapters. For more information on how to identify your adapter, go @@ -213,7 +213,7 @@ config IXGBEVF config I40E tristate "Intel(R) Ethernet Controller XL710 Family support" - select PTP_1588_CLOCK + imply PTP_1588_CLOCK depends on PCI ---help--- This driver supports Intel(R) Ethernet Controller XL710 Family of @@ -264,7 +264,7 @@ config FM10K tristate "Intel(R) FM10000 Ethernet Switch Host Interface Support" default n depends on PCI_MSI - select PTP_1588_CLOCK + imply PTP_1588_CLOCK ---help--- This driver supports Intel(R) FM10000 Ethernet Switch Host Interface. For more information on how to identify your adapter, diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index 068789e694c9..2b7323d392dc 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -2253,7 +2253,7 @@ static int e100_poll(struct napi_struct *napi, int budget) /* If budget not fully consumed, exit the polling mode */ if (work_done < budget) { - napi_complete(napi); + napi_complete_done(napi, work_done); e100_enable_irq(nic); } @@ -2286,14 +2286,6 @@ static int e100_set_mac_address(struct net_device *netdev, void *p) return 0; } -static int e100_change_mtu(struct net_device *netdev, int new_mtu) -{ - if (new_mtu < ETH_ZLEN || new_mtu > ETH_DATA_LEN) - return -EINVAL; - netdev->mtu = new_mtu; - return 0; -} - static int e100_asf(struct nic *nic) { /* ASF can be enabled from eeprom */ @@ -2434,19 +2426,21 @@ err_clean_rx: #define E100_82552_LED_ON 0x000F /* LEDTX and LED_RX both on */ #define E100_82552_LED_OFF 0x000A /* LEDTX and LED_RX both off */ -static int e100_get_settings(struct net_device *netdev, struct ethtool_cmd *cmd) +static int e100_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) { struct nic *nic = netdev_priv(netdev); - return mii_ethtool_gset(&nic->mii, cmd); + return mii_ethtool_get_link_ksettings(&nic->mii, cmd); } -static int e100_set_settings(struct net_device *netdev, struct ethtool_cmd *cmd) +static int e100_set_link_ksettings(struct net_device *netdev, + const struct ethtool_link_ksettings *cmd) { struct nic *nic = netdev_priv(netdev); int err; mdio_write(netdev, nic->mii.phy_id, MII_BMCR, BMCR_RESET); - err = mii_ethtool_sset(&nic->mii, cmd); + err = mii_ethtool_set_link_ksettings(&nic->mii, cmd); e100_exec_cb(nic, NULL, e100_configure); return err; @@ -2749,8 +2743,6 @@ static void e100_get_strings(struct net_device *netdev, u32 stringset, u8 *data) } static const struct ethtool_ops e100_ethtool_ops = { - .get_settings = e100_get_settings, - .set_settings = e100_set_settings, .get_drvinfo = e100_get_drvinfo, .get_regs_len = e100_get_regs_len, .get_regs = e100_get_regs, @@ -2771,6 +2763,8 @@ static const struct ethtool_ops e100_ethtool_ops = { .get_ethtool_stats = e100_get_ethtool_stats, .get_sset_count = e100_get_sset_count, .get_ts_info = ethtool_op_get_ts_info, + .get_link_ksettings = e100_get_link_ksettings, + .set_link_ksettings = e100_set_link_ksettings, }; static int e100_do_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) @@ -2834,7 +2828,6 @@ static const struct net_device_ops e100_netdev_ops = { .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = e100_set_multicast_list, .ndo_set_mac_address = e100_set_mac_address, - .ndo_change_mtu = e100_change_mtu, .ndo_do_ioctl = e100_do_ioctl, .ndo_tx_timeout = e100_tx_timeout, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index f42129d09e2c..93fc6c67306b 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -1085,6 +1085,10 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw->subsystem_vendor_id != PCI_VENDOR_ID_VMWARE) netdev->priv_flags |= IFF_UNICAST_FLT; + /* MTU range: 46 - 16110 */ + netdev->min_mtu = ETH_ZLEN - ETH_HLEN; + netdev->max_mtu = MAX_JUMBO_FRAME_SIZE - (ETH_HLEN + ETH_FCS_LEN); + adapter->en_mng_pt = e1000_enable_mng_pass_thru(hw); /* initialize eeprom parameters */ @@ -3549,13 +3553,7 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu) { struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; - int max_frame = new_mtu + ENET_HEADER_SIZE + ETHERNET_FCS_SIZE; - - if ((max_frame < MINIMUM_ETHERNET_FRAME_SIZE) || - (max_frame > MAX_JUMBO_FRAME_SIZE)) { - e_err(probe, "Invalid MTU setting\n"); - return -EINVAL; - } + int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN; /* Adapter-specific max frame size limits. */ switch (hw->mac_type) { @@ -5257,8 +5255,8 @@ static void e1000_netpoll(struct net_device *netdev) { struct e1000_adapter *adapter = netdev_priv(netdev); - disable_irq(adapter->pdev->irq); - e1000_intr(adapter->pdev->irq, netdev); + if (disable_hardirq(adapter->pdev->irq)) + e1000_intr(adapter->pdev->irq, netdev); enable_irq(adapter->pdev->irq); } #endif diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index 879cca47b021..a29b12e80855 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -493,8 +493,8 @@ int e1000e_setup_rx_resources(struct e1000_ring *ring); int e1000e_setup_tx_resources(struct e1000_ring *ring); void e1000e_free_rx_resources(struct e1000_ring *ring); void e1000e_free_tx_resources(struct e1000_ring *ring); -struct rtnl_link_stats64 *e1000e_get_stats64(struct net_device *netdev, - struct rtnl_link_stats64 *stats); +void e1000e_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *stats); void e1000e_set_interrupt_capability(struct e1000_adapter *adapter); void e1000e_reset_interrupt_capability(struct e1000_adapter *adapter); void e1000e_get_hw_control(struct e1000_adapter *adapter); diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 7017281ba2dc..2175cced402f 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -240,9 +240,9 @@ static void e1000e_dump(struct e1000_adapter *adapter) /* Print netdevice Info */ if (netdev) { dev_info(&adapter->pdev->dev, "Net device Info\n"); - pr_info("Device Name state trans_start last_rx\n"); - pr_info("%-15s %016lX %016lX %016lX\n", netdev->name, - netdev->state, dev_trans_start(netdev), netdev->last_rx); + pr_info("Device Name state trans_start\n"); + pr_info("%-15s %016lX %016lX\n", netdev->name, + netdev->state, dev_trans_start(netdev)); } /* Print Registers */ @@ -4305,24 +4305,24 @@ void e1000e_reinit_locked(struct e1000_adapter *adapter) /** * e1000e_sanitize_systim - sanitize raw cycle counter reads * @hw: pointer to the HW structure - * @systim: cycle_t value read, sanitized and returned + * @systim: time value read, sanitized and returned * * Errata for 82574/82583 possible bad bits read from SYSTIMH/L: * check to see that the time is incrementing at a reasonable * rate and is a multiple of incvalue. **/ -static cycle_t e1000e_sanitize_systim(struct e1000_hw *hw, cycle_t systim) +static u64 e1000e_sanitize_systim(struct e1000_hw *hw, u64 systim) { u64 time_delta, rem, temp; - cycle_t systim_next; + u64 systim_next; u32 incvalue; int i; incvalue = er32(TIMINCA) & E1000_TIMINCA_INCVALUE_MASK; for (i = 0; i < E1000_MAX_82574_SYSTIM_REREADS; i++) { /* latch SYSTIMH on read of SYSTIML */ - systim_next = (cycle_t)er32(SYSTIML); - systim_next |= (cycle_t)er32(SYSTIMH) << 32; + systim_next = (u64)er32(SYSTIML); + systim_next |= (u64)er32(SYSTIMH) << 32; time_delta = systim_next - systim; temp = time_delta; @@ -4342,13 +4342,13 @@ static cycle_t e1000e_sanitize_systim(struct e1000_hw *hw, cycle_t systim) * e1000e_cyclecounter_read - read raw cycle counter (used by time counter) * @cc: cyclecounter structure **/ -static cycle_t e1000e_cyclecounter_read(const struct cyclecounter *cc) +static u64 e1000e_cyclecounter_read(const struct cyclecounter *cc) { struct e1000_adapter *adapter = container_of(cc, struct e1000_adapter, cc); struct e1000_hw *hw = &adapter->hw; u32 systimel, systimeh; - cycle_t systim; + u64 systim; /* SYSTIMH latching upon SYSTIML read does not work well. * This means that if SYSTIML overflows after we read it but before * we read SYSTIMH, the value of SYSTIMH has been incremented and we @@ -4368,8 +4368,8 @@ static cycle_t e1000e_cyclecounter_read(const struct cyclecounter *cc) systimel = systimel_2; } } - systim = (cycle_t)systimel; - systim |= (cycle_t)systimeh << 32; + systim = (u64)systimel; + systim |= (u64)systimeh << 32; if (adapter->flags2 & FLAG2_CHECK_SYSTIM_OVERFLOW) systim = e1000e_sanitize_systim(hw, systim); @@ -5920,12 +5920,11 @@ static void e1000_reset_task(struct work_struct *work) * * Returns the address of the device statistics structure. **/ -struct rtnl_link_stats64 *e1000e_get_stats64(struct net_device *netdev, - struct rtnl_link_stats64 *stats) +void e1000e_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *stats) { struct e1000_adapter *adapter = netdev_priv(netdev); - memset(stats, 0, sizeof(struct rtnl_link_stats64)); spin_lock(&adapter->stats64_lock); e1000e_update_stats(adapter); /* Fill out the OS statistics structure */ @@ -5958,7 +5957,6 @@ struct rtnl_link_stats64 *e1000e_get_stats64(struct net_device *netdev, /* Tx Dropped needs to be maintained elsewhere */ spin_unlock(&adapter->stats64_lock); - return stats; } /** @@ -5974,19 +5972,12 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu) int max_frame = new_mtu + VLAN_ETH_HLEN + ETH_FCS_LEN; /* Jumbo frame support */ - if ((max_frame > (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN)) && + if ((new_mtu > ETH_DATA_LEN) && !(adapter->flags & FLAG_HAS_JUMBO_FRAMES)) { e_err("Jumbo Frames not supported.\n"); return -EINVAL; } - /* Supported frame sizes */ - if ((new_mtu < (VLAN_ETH_ZLEN + ETH_FCS_LEN)) || - (max_frame > adapter->max_hw_frame_size)) { - e_err("Unsupported MTU setting\n"); - return -EINVAL; - } - /* Jumbo frame workaround on 82579 and newer requires CRC be stripped */ if ((adapter->hw.mac.type >= e1000_pch2lan) && !(adapter->flags2 & FLAG2_CRC_STRIPPING) && @@ -6283,8 +6274,8 @@ static int e1000e_pm_freeze(struct device *dev) /* Quiesce the device without resetting the hardware */ e1000e_down(adapter, false); e1000_free_irq(adapter); + e1000e_reset_interrupt_capability(adapter); } - e1000e_reset_interrupt_capability(adapter); /* Allow time for pending master requests to run */ e1000e_disable_pcie_master(&adapter->hw); @@ -6762,13 +6753,13 @@ static void e1000_netpoll(struct net_device *netdev) e1000_intr_msix(adapter->pdev->irq, netdev); break; case E1000E_INT_MODE_MSI: - disable_irq(adapter->pdev->irq); - e1000_intr_msi(adapter->pdev->irq, netdev); + if (disable_hardirq(adapter->pdev->irq)) + e1000_intr_msi(adapter->pdev->irq, netdev); enable_irq(adapter->pdev->irq); break; default: /* E1000E_INT_MODE_LEGACY */ - disable_irq(adapter->pdev->irq); - e1000_intr(adapter->pdev->irq, netdev); + if (disable_hardirq(adapter->pdev->irq)) + e1000_intr(adapter->pdev->irq, netdev); enable_irq(adapter->pdev->irq); break; } @@ -7187,6 +7178,11 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->vlan_features |= NETIF_F_HIGHDMA; } + /* MTU range: 68 - max_hw_frame_size */ + netdev->min_mtu = ETH_MIN_MTU; + netdev->max_mtu = adapter->max_hw_frame_size - + (VLAN_ETH_HLEN + ETH_FCS_LEN); + if (e1000e_enable_mng_pass_thru(&adapter->hw)) adapter->flags |= FLAG_MNG_PT_ENABLED; diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c index ad03763e009a..34cc3be0df8e 100644 --- a/drivers/net/ethernet/intel/e1000e/ptp.c +++ b/drivers/net/ethernet/intel/e1000e/ptp.c @@ -127,8 +127,8 @@ static int e1000e_phc_get_syncdevicetime(ktime_t *device, unsigned long flags; int i; u32 tsync_ctrl; - cycle_t dev_cycles; - cycle_t sys_cycles; + u64 dev_cycles; + u64 sys_cycles; tsync_ctrl = er32(TSYNCTXCTL); tsync_ctrl |= E1000_TSYNCTXCTL_START_SYNC | diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h index 4d19e46f7c55..52b979443cde 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k.h @@ -260,9 +260,7 @@ struct fm10k_intfc { #define FM10K_FLAG_RESET_REQUESTED (u32)(BIT(0)) #define FM10K_FLAG_RSS_FIELD_IPV4_UDP (u32)(BIT(1)) #define FM10K_FLAG_RSS_FIELD_IPV6_UDP (u32)(BIT(2)) -#define FM10K_FLAG_RX_TS_ENABLED (u32)(BIT(3)) -#define FM10K_FLAG_SWPRI_CONFIG (u32)(BIT(4)) -#define FM10K_FLAG_DEBUG_STATS (u32)(BIT(5)) +#define FM10K_FLAG_SWPRI_CONFIG (u32)(BIT(3)) int xcast_mode; /* Tx fast path data */ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_common.c b/drivers/net/ethernet/intel/fm10k/fm10k_common.c index dd95ac4f4c64..62a6ad9b3eed 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_common.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_common.c @@ -506,7 +506,7 @@ s32 fm10k_get_host_state_generic(struct fm10k_hw *hw, bool *host_ready) goto out; /* if we somehow dropped the Tx enable we should reset */ - if (hw->mac.tx_ready && !(txdctl & FM10K_TXDCTL_ENABLE)) { + if (mac->tx_ready && !(txdctl & FM10K_TXDCTL_ENABLE)) { ret_val = FM10K_ERR_RESET_REQUESTED; goto out; } @@ -523,8 +523,8 @@ s32 fm10k_get_host_state_generic(struct fm10k_hw *hw, bool *host_ready) /* interface cannot receive traffic without logical ports */ if (mac->dglort_map == FM10K_DGLORTMAP_NONE) { - if (hw->mac.ops.request_lport_map) - ret_val = hw->mac.ops.request_lport_map(hw); + if (mac->ops.request_lport_map) + ret_val = mac->ops.request_lport_map(hw); goto out; } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c index 5241e0873397..0c84fef750f4 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c @@ -148,7 +148,7 @@ enum { static const char fm10k_prv_flags[FM10K_PRV_FLAG_LEN][ETH_GSTRING_LEN] = { }; -static void fm10k_add_stat_strings(char **p, const char *prefix, +static void fm10k_add_stat_strings(u8 **p, const char *prefix, const struct fm10k_stats stats[], const unsigned int size) { @@ -164,32 +164,31 @@ static void fm10k_add_stat_strings(char **p, const char *prefix, static void fm10k_get_stat_strings(struct net_device *dev, u8 *data) { struct fm10k_intfc *interface = netdev_priv(dev); - char *p = (char *)data; unsigned int i; - fm10k_add_stat_strings(&p, "", fm10k_gstrings_net_stats, + fm10k_add_stat_strings(&data, "", fm10k_gstrings_net_stats, FM10K_NETDEV_STATS_LEN); - fm10k_add_stat_strings(&p, "", fm10k_gstrings_global_stats, + fm10k_add_stat_strings(&data, "", fm10k_gstrings_global_stats, FM10K_GLOBAL_STATS_LEN); - fm10k_add_stat_strings(&p, "", fm10k_gstrings_mbx_stats, + fm10k_add_stat_strings(&data, "", fm10k_gstrings_mbx_stats, FM10K_MBX_STATS_LEN); if (interface->hw.mac.type != fm10k_mac_vf) - fm10k_add_stat_strings(&p, "", fm10k_gstrings_pf_stats, + fm10k_add_stat_strings(&data, "", fm10k_gstrings_pf_stats, FM10K_PF_STATS_LEN); for (i = 0; i < interface->hw.mac.max_queues; i++) { char prefix[ETH_GSTRING_LEN]; snprintf(prefix, ETH_GSTRING_LEN, "tx_queue_%u_", i); - fm10k_add_stat_strings(&p, prefix, + fm10k_add_stat_strings(&data, prefix, fm10k_gstrings_queue_stats, FM10K_QUEUE_STATS_LEN); snprintf(prefix, ETH_GSTRING_LEN, "rx_queue_%u_", i); - fm10k_add_stat_strings(&p, prefix, + fm10k_add_stat_strings(&data, prefix, fm10k_gstrings_queue_stats, FM10K_QUEUE_STATS_LEN); } @@ -198,18 +197,16 @@ static void fm10k_get_stat_strings(struct net_device *dev, u8 *data) static void fm10k_get_strings(struct net_device *dev, u32 stringset, u8 *data) { - char *p = (char *)data; - switch (stringset) { case ETH_SS_TEST: - memcpy(data, *fm10k_gstrings_test, + memcpy(data, fm10k_gstrings_test, FM10K_TEST_LEN * ETH_GSTRING_LEN); break; case ETH_SS_STATS: fm10k_get_stat_strings(dev, data); break; case ETH_SS_PRIV_FLAGS: - memcpy(p, fm10k_prv_flags, + memcpy(data, fm10k_prv_flags, FM10K_PRV_FLAG_LEN * ETH_GSTRING_LEN); break; } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 5de937852436..5bb233a9614c 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -28,7 +28,7 @@ #include "fm10k.h" -#define DRV_VERSION "0.21.2-k" +#define DRV_VERSION "0.21.7-k" #define DRV_SUMMARY "Intel(R) Ethernet Switch Host Interface Driver" const char fm10k_driver_version[] = DRV_VERSION; char fm10k_driver_name[] = "fm10k"; @@ -251,6 +251,7 @@ static bool fm10k_can_reuse_rx_page(struct fm10k_rx_buffer *rx_buffer, /** * fm10k_add_rx_frag - Add contents of Rx buffer to sk_buff * @rx_buffer: buffer containing page to add + * @size: packet size from rx_desc * @rx_desc: descriptor containing length of buffer written by hardware * @skb: sk_buff to place the data into * @@ -263,12 +264,12 @@ static bool fm10k_can_reuse_rx_page(struct fm10k_rx_buffer *rx_buffer, * true if the buffer can be reused by the interface. **/ static bool fm10k_add_rx_frag(struct fm10k_rx_buffer *rx_buffer, + unsigned int size, union fm10k_rx_desc *rx_desc, struct sk_buff *skb) { struct page *page = rx_buffer->page; unsigned char *va = page_address(page) + rx_buffer->page_offset; - unsigned int size = le16_to_cpu(rx_desc->w.length); #if (PAGE_SIZE < 8192) unsigned int truesize = FM10K_RX_BUFSZ; #else @@ -314,6 +315,7 @@ static struct sk_buff *fm10k_fetch_rx_buffer(struct fm10k_ring *rx_ring, union fm10k_rx_desc *rx_desc, struct sk_buff *skb) { + unsigned int size = le16_to_cpu(rx_desc->w.length); struct fm10k_rx_buffer *rx_buffer; struct page *page; @@ -350,11 +352,11 @@ static struct sk_buff *fm10k_fetch_rx_buffer(struct fm10k_ring *rx_ring, dma_sync_single_range_for_cpu(rx_ring->dev, rx_buffer->dma, rx_buffer->page_offset, - FM10K_RX_BUFSZ, + size, DMA_FROM_DEVICE); /* pull page into skb */ - if (fm10k_add_rx_frag(rx_buffer, rx_desc, skb)) { + if (fm10k_add_rx_frag(rx_buffer, size, rx_desc, skb)) { /* hand second half of page back to the ring */ fm10k_reuse_rx_page(rx_ring, rx_buffer); } else { @@ -473,6 +475,8 @@ static unsigned int fm10k_process_skb_fields(struct fm10k_ring *rx_ring, fm10k_rx_checksum(rx_ring, rx_desc, skb); + FM10K_CB(skb)->tstamp = rx_desc->q.timestamp; + FM10K_CB(skb)->fi.w.vlan = rx_desc->w.vlan; skb_record_rx_queue(skb, rx_ring->queue_index); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c index c9dfa6564fcf..334088a101c3 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c @@ -2011,9 +2011,10 @@ static void fm10k_sm_mbx_create_reply(struct fm10k_hw *hw, * function can also be used to respond to an error as the connection * resetting would also be a means of dealing with errors. **/ -static void fm10k_sm_mbx_process_reset(struct fm10k_hw *hw, - struct fm10k_mbx_info *mbx) +static s32 fm10k_sm_mbx_process_reset(struct fm10k_hw *hw, + struct fm10k_mbx_info *mbx) { + s32 err = 0; const enum fm10k_mbx_state state = mbx->state; switch (state) { @@ -2026,6 +2027,7 @@ static void fm10k_sm_mbx_process_reset(struct fm10k_hw *hw, case FM10K_STATE_OPEN: /* flush any incomplete work */ fm10k_sm_mbx_connect_reset(mbx); + err = FM10K_ERR_RESET_REQUESTED; break; case FM10K_STATE_CONNECT: /* Update remote value to match local value */ @@ -2035,6 +2037,8 @@ static void fm10k_sm_mbx_process_reset(struct fm10k_hw *hw, } fm10k_sm_mbx_create_reply(hw, mbx, mbx->tail); + + return err; } /** @@ -2115,7 +2119,7 @@ static s32 fm10k_sm_mbx_process(struct fm10k_hw *hw, switch (FM10K_MSG_HDR_FIELD_GET(mbx->mbx_hdr, SM_VER)) { case 0: - fm10k_sm_mbx_process_reset(hw, mbx); + err = fm10k_sm_mbx_process_reset(hw, mbx); break; case FM10K_SM_MBX_VERSION: err = fm10k_sm_mbx_process_version_1(hw, mbx); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c index 05629381be6b..01db688cf539 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c @@ -706,16 +706,6 @@ static netdev_tx_t fm10k_xmit_frame(struct sk_buff *skb, struct net_device *dev) return err; } -static int fm10k_change_mtu(struct net_device *dev, int new_mtu) -{ - if (new_mtu < 68 || new_mtu > FM10K_MAX_JUMBO_FRAME_SIZE) - return -EINVAL; - - dev->mtu = new_mtu; - - return 0; -} - /** * fm10k_tx_timeout - Respond to a Tx Hang * @netdev: network interface device structure @@ -1128,8 +1118,8 @@ void fm10k_reset_rx_state(struct fm10k_intfc *interface) * Returns 64bit statistics, for use in the ndo_get_stats64 callback. This * function replaces fm10k_get_stats for kernels which support it. */ -static struct rtnl_link_stats64 *fm10k_get_stats64(struct net_device *netdev, - struct rtnl_link_stats64 *stats) +static void fm10k_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *stats) { struct fm10k_intfc *interface = netdev_priv(netdev); struct fm10k_ring *ring; @@ -1174,8 +1164,6 @@ static struct rtnl_link_stats64 *fm10k_get_stats64(struct net_device *netdev, /* following stats updated by fm10k_service_task() */ stats->rx_missed_errors = netdev->stats.rx_missed_errors; - - return stats; } int fm10k_setup_tc(struct net_device *dev, u8 tc) @@ -1405,7 +1393,6 @@ static const struct net_device_ops fm10k_netdev_ops = { .ndo_validate_addr = eth_validate_addr, .ndo_start_xmit = fm10k_xmit_frame, .ndo_set_mac_address = fm10k_set_mac, - .ndo_change_mtu = fm10k_change_mtu, .ndo_tx_timeout = fm10k_tx_timeout, .ndo_vlan_rx_add_vid = fm10k_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = fm10k_vlan_rx_kill_vid, @@ -1490,5 +1477,9 @@ struct net_device *fm10k_alloc_netdev(const struct fm10k_info *info) dev->hw_features |= hw_features; + /* MTU range: 68 - 15342 */ + dev->min_mtu = ETH_MIN_MTU; + dev->max_mtu = FM10K_MAX_JUMBO_FRAME_SIZE; + return dev; } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index b1a2f8437d59..e372a5823480 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -1144,6 +1144,7 @@ static irqreturn_t fm10k_msix_mbx_pf(int __always_unused irq, void *data) struct fm10k_hw *hw = &interface->hw; struct fm10k_mbx_info *mbx = &hw->mbx; u32 eicr; + s32 err = 0; /* unmask any set bits related to this interrupt */ eicr = fm10k_read_reg(hw, FM10K_EICR); @@ -1159,12 +1160,15 @@ static irqreturn_t fm10k_msix_mbx_pf(int __always_unused irq, void *data) /* service mailboxes */ if (fm10k_mbx_trylock(interface)) { - mbx->ops.process(hw, mbx); + err = mbx->ops.process(hw, mbx); /* handle VFLRE events */ fm10k_iov_event(interface); fm10k_mbx_unlock(interface); } + if (err == FM10K_ERR_RESET_REQUESTED) + interface->flags |= FM10K_FLAG_RESET_REQUESTED; + /* if switch toggled state we should reset GLORTs */ if (eicr & FM10K_EICR_SWITCHNOTREADY) { /* force link down for at least 4 seconds */ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c index 23fb319fd2a0..40ee0242a80a 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c @@ -72,10 +72,6 @@ force_reset: fm10k_write_flush(hw); udelay(FM10K_RESET_TIMEOUT); - /* Reset mailbox global interrupts */ - reg = FM10K_MBX_GLOBAL_REQ_INTERRUPT | FM10K_MBX_GLOBAL_ACK_INTERRUPT; - fm10k_write_reg(hw, FM10K_GMBX, reg); - /* Verify we made it out of reset */ reg = fm10k_read_reg(hw, FM10K_IP); if (!(reg & FM10K_IP_NOTINRESET)) diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 6d61e443bdf8..82d8040fa418 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -39,6 +39,7 @@ #include <linux/iommu.h> #include <linux/slab.h> #include <linux/list.h> +#include <linux/hashtable.h> #include <linux/string.h> #include <linux/in.h> #include <linux/ip.h> @@ -133,19 +134,6 @@ /* default to trying for four seconds */ #define I40E_TRY_LINK_TIMEOUT (4 * HZ) -/** - * i40e_is_mac_710 - Return true if MAC is X710/XL710 - * @hw: ptr to the hardware info - **/ -static inline bool i40e_is_mac_710(struct i40e_hw *hw) -{ - if ((hw->mac.type == I40E_MAC_X710) || - (hw->mac.type == I40E_MAC_XL710)) - return true; - - return false; -} - /* driver state flags */ enum i40e_state_t { __I40E_TESTING, @@ -355,9 +343,13 @@ struct i40e_pf { #define I40E_FLAG_NO_DCB_SUPPORT BIT_ULL(45) #define I40E_FLAG_USE_SET_LLDP_MIB BIT_ULL(46) #define I40E_FLAG_STOP_FW_LLDP BIT_ULL(47) -#define I40E_FLAG_HAVE_10GBASET_PHY BIT_ULL(48) +#define I40E_FLAG_PHY_CONTROLS_LEDS BIT_ULL(48) #define I40E_FLAG_PF_MAC BIT_ULL(50) #define I40E_FLAG_TRUE_PROMISC_SUPPORT BIT_ULL(51) +#define I40E_FLAG_HAVE_CRT_RETIMER BIT_ULL(52) +#define I40E_FLAG_PTP_L4_CAPABLE BIT_ULL(53) +#define I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE BIT_ULL(54) +#define I40E_FLAG_TEMP_LINK_POLLING BIT_ULL(55) /* tracks features that get auto disabled by errors */ u64 auto_disable_flags; @@ -428,11 +420,13 @@ struct i40e_pf { struct ptp_clock_info ptp_caps; struct sk_buff *ptp_tx_skb; struct hwtstamp_config tstamp_config; - unsigned long last_rx_ptp_check; - spinlock_t tmreg_lock; /* Used to protect the device time registers. */ + struct mutex tmreg_lock; /* Used to protect the SYSTIME registers. */ u64 ptp_base_adj; u32 tx_hwtstamp_timeouts; u32 rx_hwtstamp_cleared; + u32 latch_event_flags; + spinlock_t ptp_rx_lock; /* Used to protect Rx timestamp registers. */ + unsigned long latch_events[4]; bool ptp_tx; bool ptp_rx; u16 rss_table_size; /* HW RSS table size */ @@ -445,6 +439,20 @@ struct i40e_pf { u16 phy_led_val; }; +/** + * i40e_mac_to_hkey - Convert a 6-byte MAC Address to a u64 hash key + * @macaddr: the MAC Address as the base key + * + * Simply copies the address and returns it as a u64 for hashing + **/ +static inline u64 i40e_addr_to_hkey(const u8 *macaddr) +{ + u64 key = 0; + + ether_addr_copy((u8 *)&key, macaddr); + return key; +} + enum i40e_filter_state { I40E_FILTER_INVALID = 0, /* Invalid state */ I40E_FILTER_NEW, /* New, not sent to FW yet */ @@ -454,13 +462,26 @@ enum i40e_filter_state { /* There is no 'removed' state; the filter struct is freed */ }; struct i40e_mac_filter { - struct list_head list; + struct hlist_node hlist; u8 macaddr[ETH_ALEN]; #define I40E_VLAN_ANY -1 s16 vlan; - u8 counter; /* number of instances of this filter */ - bool is_vf; /* filter belongs to a VF */ - bool is_netdev; /* filter belongs to a netdev */ + enum i40e_filter_state state; +}; + +/* Wrapper structure to keep track of filters while we are preparing to send + * firmware commands. We cannot send firmware commands while holding a + * spinlock, since it might sleep. To avoid this, we wrap the added filters in + * a separate structure, which will track the state change and update the real + * filter while under lock. We can't simply hold the filters in a separate + * list, as this opens a window for a race condition when adding new MAC + * addresses to all VLANs, or when adding new VLANs to all MAC addresses. + */ +struct i40e_new_mac_filter { + struct hlist_node hlist; + struct i40e_mac_filter *f; + + /* Track future changes to state separately */ enum i40e_filter_state state; }; @@ -501,9 +522,11 @@ struct i40e_vsi { #define I40E_VSI_FLAG_VEB_OWNER BIT(1) unsigned long flags; - /* Per VSI lock to protect elements/list (MAC filter) */ - spinlock_t mac_filter_list_lock; - struct list_head mac_filter_list; + /* Per VSI lock to protect elements/hash (MAC filter) */ + spinlock_t mac_filter_hash_lock; + /* Fixed size hash table with 2^8 buckets for MAC filters */ + DECLARE_HASHTABLE(mac_filter_hash, 8); + bool has_vlan_filter; /* VSI stats */ struct rtnl_link_stats64 net_stats; @@ -579,6 +602,7 @@ struct i40e_vsi { u16 veb_idx; /* index of VEB parent */ struct kobject *kobj; /* sysfs object */ bool current_isup; /* Sync 'link up' logging */ + enum i40e_aq_link_speed current_speed; /* Sync link speed logging */ void *priv; /* client driver data reference. */ @@ -608,6 +632,8 @@ struct i40e_q_vector { unsigned long hung_detected; /* Set/Reset for hung_detection logic */ cpumask_t affinity_mask; + struct irq_affinity_notify affinity_notify; + struct rcu_head rcu; /* to avoid race with update stats on free */ char name[I40E_INT_NAME_STR_LEN]; bool arm_wb_state; @@ -705,6 +731,25 @@ int i40e_get_rss(struct i40e_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size); void i40e_fill_rss_lut(struct i40e_pf *pf, u8 *lut, u16 rss_table_size, u16 rss_size); struct i40e_vsi *i40e_find_vsi_from_id(struct i40e_pf *pf, u16 id); +/** + * i40e_find_vsi_by_type - Find and return Flow Director VSI + * @pf: PF to search for VSI + * @type: Value indicating type of VSI we are looking for + **/ +static inline struct i40e_vsi * +i40e_find_vsi_by_type(struct i40e_pf *pf, u16 type) +{ + int i; + + for (i = 0; i < pf->num_alloc_vsi; i++) { + struct i40e_vsi *vsi = pf->vsi[i]; + + if (vsi && vsi->type == type) + return vsi; + } + + return NULL; +} void i40e_update_stats(struct i40e_vsi *vsi); void i40e_update_eth_stats(struct i40e_vsi *vsi); struct rtnl_link_stats64 *i40e_get_vsi_stats_struct(struct i40e_vsi *vsi); @@ -721,16 +766,13 @@ u32 i40e_get_global_fd_count(struct i40e_pf *pf); bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features); void i40e_set_ethtool_ops(struct net_device *netdev); struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi, - u8 *macaddr, s16 vlan, - bool is_vf, bool is_netdev); -void i40e_del_filter(struct i40e_vsi *vsi, u8 *macaddr, s16 vlan, - bool is_vf, bool is_netdev); + const u8 *macaddr, s16 vlan); +void __i40e_del_filter(struct i40e_vsi *vsi, struct i40e_mac_filter *f); +void i40e_del_filter(struct i40e_vsi *vsi, const u8 *macaddr, s16 vlan); int i40e_sync_vsi_filters(struct i40e_vsi *vsi); struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type, u16 uplink, u32 param1); int i40e_vsi_release(struct i40e_vsi *vsi); -struct i40e_vsi *i40e_vsi_lookup(struct i40e_pf *pf, enum i40e_vsi_type type, - struct i40e_vsi *start_vsi); #ifdef I40E_FCOE void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, struct i40e_vsi_context *ctxt, @@ -740,7 +782,8 @@ void i40e_service_event_schedule(struct i40e_pf *pf); void i40e_notify_client_of_vf_msg(struct i40e_vsi *vsi, u32 vf_id, u8 *msg, u16 len); -int i40e_vsi_control_rings(struct i40e_vsi *vsi, bool enable); +int i40e_vsi_start_rings(struct i40e_vsi *vsi); +void i40e_vsi_stop_rings(struct i40e_vsi *vsi); int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count); struct i40e_veb *i40e_veb_setup(struct i40e_pf *pf, u16 flags, u16 uplink_seid, u16 downlink_seid, u8 enabled_tc); @@ -767,7 +810,6 @@ int i40e_lan_add_device(struct i40e_pf *pf); int i40e_lan_del_device(struct i40e_pf *pf); void i40e_client_subtask(struct i40e_pf *pf); void i40e_notify_client_of_l2_param_changes(struct i40e_vsi *vsi); -void i40e_notify_client_of_netdev_open(struct i40e_vsi *vsi); void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset); void i40e_notify_client_of_vf_enable(struct i40e_pf *pf, u32 num_vfs); void i40e_notify_client_of_vf_reset(struct i40e_pf *pf, u32 vf_id); @@ -797,9 +839,8 @@ static inline void i40e_irq_dynamic_enable(struct i40e_vsi *vsi, int vector) void i40e_irq_dynamic_disable_icr0(struct i40e_pf *pf); void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf, bool clearpba); #ifdef I40E_FCOE -struct rtnl_link_stats64 *i40e_get_netdev_stats_struct( - struct net_device *netdev, - struct rtnl_link_stats64 *storage); +void i40e_get_netdev_stats_struct(struct net_device *netdev, + struct rtnl_link_stats64 *storage); int i40e_set_mac(struct net_device *netdev, void *p); void i40e_set_rx_mode(struct net_device *netdev); #endif @@ -815,15 +856,15 @@ int i40e_open(struct net_device *netdev); int i40e_close(struct net_device *netdev); int i40e_vsi_open(struct i40e_vsi *vsi); void i40e_vlan_stripping_disable(struct i40e_vsi *vsi); -int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid); -int i40e_vsi_kill_vlan(struct i40e_vsi *vsi, s16 vid); -struct i40e_mac_filter *i40e_put_mac_in_vlan(struct i40e_vsi *vsi, u8 *macaddr, - bool is_vf, bool is_netdev); -int i40e_del_mac_all_vlan(struct i40e_vsi *vsi, u8 *macaddr, - bool is_vf, bool is_netdev); +int i40e_add_vlan_all_mac(struct i40e_vsi *vsi, s16 vid); +int i40e_vsi_add_vlan(struct i40e_vsi *vsi, u16 vid); +void i40e_rm_vlan_all_mac(struct i40e_vsi *vsi, s16 vid); +void i40e_vsi_kill_vlan(struct i40e_vsi *vsi, u16 vid); +struct i40e_mac_filter *i40e_add_mac_filter(struct i40e_vsi *vsi, + const u8 *macaddr); +int i40e_del_mac_filter(struct i40e_vsi *vsi, const u8 *macaddr); bool i40e_is_vsi_in_vlan(struct i40e_vsi *vsi); -struct i40e_mac_filter *i40e_find_mac(struct i40e_vsi *vsi, u8 *macaddr, - bool is_vf, bool is_netdev); +struct i40e_mac_filter *i40e_find_mac(struct i40e_vsi *vsi, const u8 *macaddr); #ifdef I40E_FCOE int __i40e_setup_tc(struct net_device *netdev, u32 handle, __be16 proto, struct tc_to_netdev *tc); diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c index 738b42a44f20..56fb27298936 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c @@ -964,11 +964,11 @@ i40e_status i40e_clean_arq_element(struct i40e_hw *hw, desc = I40E_ADMINQ_DESC(hw->aq.arq, ntc); desc_idx = ntc; + hw->aq.arq_last_status = + (enum i40e_admin_queue_err)le16_to_cpu(desc->retval); flags = le16_to_cpu(desc->flags); if (flags & I40E_AQ_FLAG_ERR) { ret_code = I40E_ERR_ADMIN_QUEUE_ERROR; - hw->aq.arq_last_status = - (enum i40e_admin_queue_err)le16_to_cpu(desc->retval); i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQRX: Event received with error 0x%X.\n", diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index 67e396b2b347..451f48b7540a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -538,6 +538,8 @@ I40E_CHECK_STRUCT_LEN(24, i40e_aqc_mac_address_read_data); /* Manage MAC Address Write Command (0x0108) */ struct i40e_aqc_mac_address_write { __le16 command_flags; +#define I40E_AQC_MC_MAG_EN 0x0100 +#define I40E_AQC_WOL_PRESERVE_ON_PFR 0x0200 #define I40E_AQC_WRITE_TYPE_LAA_ONLY 0x0000 #define I40E_AQC_WRITE_TYPE_LAA_WOL 0x4000 #define I40E_AQC_WRITE_TYPE_PORT 0x8000 @@ -1642,6 +1644,10 @@ enum i40e_aq_phy_type { I40E_PHY_TYPE_1000BASE_LX = 0x1C, I40E_PHY_TYPE_1000BASE_T_OPTICAL = 0x1D, I40E_PHY_TYPE_20GBASE_KR2 = 0x1E, + I40E_PHY_TYPE_25GBASE_KR = 0x1F, + I40E_PHY_TYPE_25GBASE_CR = 0x20, + I40E_PHY_TYPE_25GBASE_SR = 0x21, + I40E_PHY_TYPE_25GBASE_LR = 0x22, I40E_PHY_TYPE_MAX }; @@ -1650,6 +1656,7 @@ enum i40e_aq_phy_type { #define I40E_LINK_SPEED_10GB_SHIFT 0x3 #define I40E_LINK_SPEED_40GB_SHIFT 0x4 #define I40E_LINK_SPEED_20GB_SHIFT 0x5 +#define I40E_LINK_SPEED_25GB_SHIFT 0x6 enum i40e_aq_link_speed { I40E_LINK_SPEED_UNKNOWN = 0, @@ -1657,7 +1664,8 @@ enum i40e_aq_link_speed { I40E_LINK_SPEED_1GB = BIT(I40E_LINK_SPEED_1000MB_SHIFT), I40E_LINK_SPEED_10GB = BIT(I40E_LINK_SPEED_10GB_SHIFT), I40E_LINK_SPEED_40GB = BIT(I40E_LINK_SPEED_40GB_SHIFT), - I40E_LINK_SPEED_20GB = BIT(I40E_LINK_SPEED_20GB_SHIFT) + I40E_LINK_SPEED_20GB = BIT(I40E_LINK_SPEED_20GB_SHIFT), + I40E_LINK_SPEED_25GB = BIT(I40E_LINK_SPEED_25GB_SHIFT), }; struct i40e_aqc_module_desc { @@ -1680,6 +1688,8 @@ struct i40e_aq_get_phy_abilities_resp { #define I40E_AQ_PHY_LINK_ENABLED 0x08 #define I40E_AQ_PHY_AN_ENABLED 0x10 #define I40E_AQ_PHY_FLAG_MODULE_QUAL 0x20 +#define I40E_AQ_PHY_FEC_ABILITY_KR 0x40 +#define I40E_AQ_PHY_FEC_ABILITY_RS 0x80 __le16 eee_capability; #define I40E_AQ_EEE_100BASE_TX 0x0002 #define I40E_AQ_EEE_1000BASE_T 0x0004 @@ -1690,7 +1700,22 @@ struct i40e_aq_get_phy_abilities_resp { __le32 eeer_val; u8 d3_lpan; #define I40E_AQ_SET_PHY_D3_LPAN_ENA 0x01 - u8 reserved[3]; + u8 phy_type_ext; +#define I40E_AQ_PHY_TYPE_EXT_25G_KR 0X01 +#define I40E_AQ_PHY_TYPE_EXT_25G_CR 0X02 +#define I40E_AQ_PHY_TYPE_EXT_25G_SR 0x04 +#define I40E_AQ_PHY_TYPE_EXT_25G_LR 0x08 + u8 fec_cfg_curr_mod_ext_info; +#define I40E_AQ_ENABLE_FEC_KR 0x01 +#define I40E_AQ_ENABLE_FEC_RS 0x02 +#define I40E_AQ_REQUEST_FEC_KR 0x04 +#define I40E_AQ_REQUEST_FEC_RS 0x08 +#define I40E_AQ_ENABLE_FEC_AUTO 0x10 +#define I40E_AQ_FEC +#define I40E_AQ_MODULE_TYPE_EXT_MASK 0xE0 +#define I40E_AQ_MODULE_TYPE_EXT_SHIFT 5 + + u8 ext_comp_code; u8 phy_id[4]; u8 module_type[3]; u8 qualified_module_count; @@ -1712,7 +1737,20 @@ struct i40e_aq_set_phy_config { /* same bits as above in all */ __le16 eee_capability; __le32 eeer; u8 low_power_ctrl; - u8 reserved[3]; + u8 phy_type_ext; +#define I40E_AQ_PHY_TYPE_EXT_25G_KR 0X01 +#define I40E_AQ_PHY_TYPE_EXT_25G_CR 0X02 +#define I40E_AQ_PHY_TYPE_EXT_25G_SR 0x04 +#define I40E_AQ_PHY_TYPE_EXT_25G_LR 0x08 + u8 fec_config; +#define I40E_AQ_SET_FEC_ABILITY_KR BIT(0) +#define I40E_AQ_SET_FEC_ABILITY_RS BIT(1) +#define I40E_AQ_SET_FEC_REQUEST_KR BIT(2) +#define I40E_AQ_SET_FEC_REQUEST_RS BIT(3) +#define I40E_AQ_SET_FEC_AUTO BIT(4) +#define I40E_AQ_PHY_FEC_CONFIG_SHIFT 0x0 +#define I40E_AQ_PHY_FEC_CONFIG_MASK (0x1F << I40E_AQ_PHY_FEC_CONFIG_SHIFT) + u8 reserved; }; I40E_CHECK_CMD_LENGTH(i40e_aq_set_phy_config); @@ -1792,9 +1830,18 @@ struct i40e_aqc_get_link_status { #define I40E_AQ_LINK_TX_DRAINED 0x01 #define I40E_AQ_LINK_TX_FLUSHED 0x03 #define I40E_AQ_LINK_FORCED_40G 0x10 +/* 25G Error Codes */ +#define I40E_AQ_25G_NO_ERR 0X00 +#define I40E_AQ_25G_NOT_PRESENT 0X01 +#define I40E_AQ_25G_NVM_CRC_ERR 0X02 +#define I40E_AQ_25G_SBUS_UCODE_ERR 0X03 +#define I40E_AQ_25G_SERDES_UCODE_ERR 0X04 +#define I40E_AQ_25G_NIMB_UCODE_ERR 0X05 u8 loopback; /* use defines from i40e_aqc_set_lb_mode */ __le16 max_frame_size; u8 config; +#define I40E_AQ_CONFIG_FEC_KR_ENA 0x01 +#define I40E_AQ_CONFIG_FEC_RS_ENA 0x02 #define I40E_AQ_CONFIG_CRC_ENA 0x04 #define I40E_AQ_CONFIG_PACING_MASK 0x78 u8 external_power_ability; diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c index 250db0b244b7..d570219efd9f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_client.c +++ b/drivers/net/ethernet/intel/i40e/i40e_client.c @@ -174,8 +174,6 @@ void i40e_notify_client_of_l2_param_changes(struct i40e_vsi *vsi) if (!vsi) return; - memset(¶ms, 0, sizeof(params)); - i40e_client_get_params(vsi, ¶ms); mutex_lock(&i40e_client_instance_mutex); list_for_each_entry(cdev, &i40e_client_instances, list) { if (cdev->lan_info.pf == vsi->back) { @@ -186,6 +184,8 @@ void i40e_notify_client_of_l2_param_changes(struct i40e_vsi *vsi) "Cannot locate client instance l2_param_change routine\n"); continue; } + memset(¶ms, 0, sizeof(params)); + i40e_client_get_params(vsi, ¶ms); if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) { dev_dbg(&vsi->back->pdev->dev, "Client is not open, abort l2 param change\n"); @@ -201,41 +201,6 @@ void i40e_notify_client_of_l2_param_changes(struct i40e_vsi *vsi) } /** - * i40e_notify_client_of_netdev_open - call the client open callback - * @vsi: the VSI with netdev opened - * - * If there is a client to this netdev, call the client with open - **/ -void i40e_notify_client_of_netdev_open(struct i40e_vsi *vsi) -{ - struct i40e_client_instance *cdev; - int ret = 0; - - if (!vsi) - return; - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry(cdev, &i40e_client_instances, list) { - if (cdev->lan_info.netdev == vsi->netdev) { - if (!cdev->client || - !cdev->client->ops || !cdev->client->ops->open) { - dev_dbg(&vsi->back->pdev->dev, - "Cannot locate client instance open routine\n"); - continue; - } - if (!(test_bit(__I40E_CLIENT_INSTANCE_OPENED, - &cdev->state))) { - ret = cdev->client->ops->open(&cdev->lan_info, - cdev->client); - if (!ret) - set_bit(__I40E_CLIENT_INSTANCE_OPENED, - &cdev->state); - } - } - } - mutex_unlock(&i40e_client_instance_mutex); -} - -/** * i40e_client_release_qvlist * @ldev: pointer to L2 context. * @@ -287,6 +252,7 @@ void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset) } cdev->client->ops->close(&cdev->lan_info, cdev->client, reset); + clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state); i40e_client_release_qvlist(&cdev->lan_info); } } @@ -406,37 +372,6 @@ int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id, } /** - * i40e_vsi_lookup - finds a matching VSI from the PF list starting at start_vsi - * @pf: board private structure - * @type: vsi type - * @start_vsi: a VSI pointer from where to start the search - * - * Returns non NULL on success or NULL for failure - **/ -struct i40e_vsi *i40e_vsi_lookup(struct i40e_pf *pf, - enum i40e_vsi_type type, - struct i40e_vsi *start_vsi) -{ - struct i40e_vsi *vsi; - int i = 0; - - if (start_vsi) { - for (i = 0; i < pf->num_alloc_vsi; i++) { - vsi = pf->vsi[i]; - if (vsi == start_vsi) - break; - } - } - for (; i < pf->num_alloc_vsi; i++) { - vsi = pf->vsi[i]; - if (vsi && vsi->type == type) - return vsi; - } - - return NULL; -} - -/** * i40e_client_add_instance - add a client instance struct to the instance list * @pf: pointer to the board struct * @client: pointer to a client struct in the client list. @@ -565,7 +500,7 @@ void i40e_client_subtask(struct i40e_pf *pf) if (test_bit(__I40E_DOWN, &pf->vsi[pf->lan_vsi]->state)) continue; } else { - dev_warn(&pf->pdev->dev, "This client %s is being instanciated at probe\n", + dev_warn(&pf->pdev->dev, "This client %s is being instantiated at probe\n", client->name); } @@ -575,29 +510,26 @@ void i40e_client_subtask(struct i40e_pf *pf) continue; if (!existing) { - /* Also up the ref_cnt for no. of instances of this - * client. - */ - atomic_inc(&client->ref_cnt); - dev_info(&pf->pdev->dev, "Added instance of Client %s to PF%d bus=0x%02x func=0x%02x\n", + dev_info(&pf->pdev->dev, "Added instance of Client %s to PF%d bus=0x%02x dev=0x%02x func=0x%02x\n", client->name, pf->hw.pf_id, - pf->hw.bus.device, pf->hw.bus.func); + pf->hw.bus.bus_id, pf->hw.bus.device, + pf->hw.bus.func); } mutex_lock(&i40e_client_instance_mutex); - /* Send an Open request to the client */ - atomic_inc(&cdev->ref_cnt); - if (client->ops && client->ops->open) - ret = client->ops->open(&cdev->lan_info, client); - atomic_dec(&cdev->ref_cnt); - if (!ret) { - set_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state); - } else { - /* remove client instance */ - mutex_unlock(&i40e_client_instance_mutex); - i40e_client_del_instance(pf, client); - atomic_dec(&client->ref_cnt); - continue; + if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, + &cdev->state)) { + /* Send an Open request to the client */ + if (client->ops && client->ops->open) + ret = client->ops->open(&cdev->lan_info, + client); + if (!ret) { + set_bit(__I40E_CLIENT_INSTANCE_OPENED, + &cdev->state); + } else { + /* remove client instance */ + i40e_client_del_instance(pf, client); + } } mutex_unlock(&i40e_client_instance_mutex); } @@ -630,8 +562,9 @@ int i40e_lan_add_device(struct i40e_pf *pf) ldev->pf = pf; INIT_LIST_HEAD(&ldev->list); list_add(&ldev->list, &i40e_devices); - dev_info(&pf->pdev->dev, "Added LAN device PF%d bus=0x%02x func=0x%02x\n", - pf->hw.pf_id, pf->hw.bus.device, pf->hw.bus.func); + dev_info(&pf->pdev->dev, "Added LAN device PF%d bus=0x%02x dev=0x%02x func=0x%02x\n", + pf->hw.pf_id, pf->hw.bus.bus_id, + pf->hw.bus.device, pf->hw.bus.func); /* Since in some cases register may have happened before a device gets * added, we can schedule a subtask to go initiate the clients if @@ -659,9 +592,9 @@ int i40e_lan_del_device(struct i40e_pf *pf) mutex_lock(&i40e_device_mutex); list_for_each_entry_safe(ldev, tmp, &i40e_devices, list) { if (ldev->pf == pf) { - dev_info(&pf->pdev->dev, "Deleted LAN device PF%d bus=0x%02x func=0x%02x\n", - pf->hw.pf_id, pf->hw.bus.device, - pf->hw.bus.func); + dev_info(&pf->pdev->dev, "Deleted LAN device PF%d bus=0x%02x dev=0x%02x func=0x%02x\n", + pf->hw.pf_id, pf->hw.bus.bus_id, + pf->hw.bus.device, pf->hw.bus.func); list_del(&ldev->list); kfree(ldev); ret = 0; @@ -694,10 +627,6 @@ static int i40e_client_release(struct i40e_client *client) continue; pf = (struct i40e_pf *)cdev->lan_info.pf; if (test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) { - if (atomic_read(&cdev->ref_cnt) > 0) { - ret = I40E_ERR_NOT_READY; - goto out; - } if (client->ops && client->ops->close) client->ops->close(&cdev->lan_info, client, false); @@ -710,11 +639,9 @@ static int i40e_client_release(struct i40e_client *client) } /* delete the client instance from the list */ list_move(&cdev->list, &cdevs_tmp); - atomic_dec(&client->ref_cnt); dev_info(&pf->pdev->dev, "Deleted client instance of Client %s\n", client->name); } -out: mutex_unlock(&i40e_client_instance_mutex); /* free the client device and release its vsi */ @@ -728,13 +655,11 @@ out: * i40e_client_prepare - prepare client specific resources * @client: pointer to the registered client * - * Return 0 on success or < 0 on error **/ -static int i40e_client_prepare(struct i40e_client *client) +static void i40e_client_prepare(struct i40e_client *client) { struct i40e_device *ldev; struct i40e_pf *pf; - int ret = 0; mutex_lock(&i40e_device_mutex); list_for_each_entry(ldev, &i40e_devices, list) { @@ -744,7 +669,6 @@ static int i40e_client_prepare(struct i40e_client *client) i40e_service_event_schedule(pf); } mutex_unlock(&i40e_device_mutex); - return ret; } /** @@ -1001,13 +925,9 @@ int i40e_register_client(struct i40e_client *client) set_bit(__I40E_CLIENT_REGISTERED, &client->state); mutex_unlock(&i40e_client_mutex); - if (i40e_client_prepare(client)) { - ret = -EIO; - goto out; - } + i40e_client_prepare(client); - pr_info("i40e: Registered client %s with return code %d\n", - client->name, ret); + pr_info("i40e: Registered client %s\n", client->name); out: return ret; } @@ -1040,17 +960,10 @@ int i40e_unregister_client(struct i40e_client *client) ret = -ENODEV; goto out; } - if (atomic_read(&client->ref_cnt) == 0) { - clear_bit(__I40E_CLIENT_REGISTERED, &client->state); - list_del(&client->list); - pr_info("i40e: Unregistered client %s with return code %d\n", - client->name, ret); - } else { - ret = I40E_ERR_NOT_READY; - pr_err("i40e: Client %s failed unregister - client has open instances\n", - client->name); - } - + clear_bit(__I40E_CLIENT_REGISTERED, &client->state); + list_del(&client->list); + pr_info("i40e: Unregistered client %s with return code %d\n", + client->name, ret); out: mutex_unlock(&i40e_client_mutex); return ret; diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.h b/drivers/net/ethernet/intel/i40e/i40e_client.h index 38a6c36a6a0e..528bd79b05fe 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_client.h +++ b/drivers/net/ethernet/intel/i40e/i40e_client.h @@ -203,8 +203,6 @@ struct i40e_client_instance { struct i40e_info lan_info; struct i40e_client *client; unsigned long state; - /* A count of all the in-progress calls to the client */ - atomic_t ref_cnt; }; struct i40e_client { diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 2154a34c1dd8..ece57d6a6e23 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -53,6 +53,8 @@ static i40e_status i40e_set_mac_type(struct i40e_hw *hw) case I40E_DEV_ID_10G_BASE_T4: case I40E_DEV_ID_20G_KR2: case I40E_DEV_ID_20G_KR2_A: + case I40E_DEV_ID_25G_B: + case I40E_DEV_ID_25G_SFP28: hw->mac.type = I40E_MAC_XL710; break; case I40E_DEV_ID_KX_X722: @@ -298,7 +300,6 @@ void i40e_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, void *desc, struct i40e_aq_desc *aq_desc = (struct i40e_aq_desc *)desc; u16 len; u8 *buf = (u8 *)buffer; - u16 i = 0; if ((!(mask & hw->debug_mask)) || (desc == NULL)) return; @@ -326,12 +327,18 @@ void i40e_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, void *desc, if (buf_len < len) len = buf_len; /* write the full 16-byte chunks */ - for (i = 0; i < (len - 16); i += 16) - i40e_debug(hw, mask, "\t0x%04X %16ph\n", i, buf + i); - /* write whatever's left over without overrunning the buffer */ - if (i < len) - i40e_debug(hw, mask, "\t0x%04X %*ph\n", - i, len - i, buf + i); + if (hw->debug_mask & mask) { + char prefix[20]; + + snprintf(prefix, 20, + "i40e %02x:%02x.%x: \t0x", + hw->bus.bus_id, + hw->bus.device, + hw->bus.func); + + print_hex_dump(KERN_INFO, prefix, DUMP_PREFIX_OFFSET, + 16, 1, buf, len, false); + } } } @@ -1183,6 +1190,8 @@ static enum i40e_media_type i40e_get_media_type(struct i40e_hw *hw) case I40E_PHY_TYPE_1000BASE_LX: case I40E_PHY_TYPE_40GBASE_SR4: case I40E_PHY_TYPE_40GBASE_LR4: + case I40E_PHY_TYPE_25GBASE_LR: + case I40E_PHY_TYPE_25GBASE_SR: media = I40E_MEDIA_TYPE_FIBER; break; case I40E_PHY_TYPE_100BASE_TX: @@ -1197,6 +1206,7 @@ static enum i40e_media_type i40e_get_media_type(struct i40e_hw *hw) case I40E_PHY_TYPE_10GBASE_SFPP_CU: case I40E_PHY_TYPE_40GBASE_AOC: case I40E_PHY_TYPE_10GBASE_AOC: + case I40E_PHY_TYPE_25GBASE_CR: media = I40E_MEDIA_TYPE_DA; break; case I40E_PHY_TYPE_1000BASE_KX: @@ -1204,6 +1214,7 @@ static enum i40e_media_type i40e_get_media_type(struct i40e_hw *hw) case I40E_PHY_TYPE_10GBASE_KR: case I40E_PHY_TYPE_40GBASE_KR4: case I40E_PHY_TYPE_20GBASE_KR2: + case I40E_PHY_TYPE_25GBASE_KR: media = I40E_MEDIA_TYPE_BACKPLANE; break; case I40E_PHY_TYPE_SGMII: @@ -1608,8 +1619,10 @@ i40e_status i40e_aq_get_phy_capabilities(struct i40e_hw *hw, if (hw->aq.asq_last_status == I40E_AQ_RC_EIO) status = I40E_ERR_UNKNOWN_PHY; - if (report_init) + if (report_init) { hw->phy.phy_types = le32_to_cpu(abilities->phy_type); + hw->phy.phy_types |= ((u64)abilities->phy_type_ext << 32); + } return status; } @@ -1701,10 +1714,13 @@ enum i40e_status_code i40e_set_fc(struct i40e_hw *hw, u8 *aq_failures, config.abilities |= I40E_AQ_PHY_ENABLE_ATOMIC_LINK; /* Copy over all the old settings */ config.phy_type = abilities.phy_type; + config.phy_type_ext = abilities.phy_type_ext; config.link_speed = abilities.link_speed; config.eee_capability = abilities.eee_capability; config.eeer = abilities.eeer_val; config.low_power_ctrl = abilities.d3_lpan; + config.fec_config = abilities.fec_cfg_curr_mod_ext_info & + I40E_AQ_PHY_FEC_CONFIG_MASK; status = i40e_aq_set_phy_config(hw, &config, NULL); if (status) @@ -1827,6 +1843,8 @@ i40e_status i40e_aq_get_link_info(struct i40e_hw *hw, hw_link_info->link_speed = (enum i40e_aq_link_speed)resp->link_speed; hw_link_info->link_info = resp->link_info; hw_link_info->an_info = resp->an_info; + hw_link_info->fec_info = resp->config & (I40E_AQ_CONFIG_FEC_KR_ENA | + I40E_AQ_CONFIG_FEC_RS_ENA); hw_link_info->ext_info = resp->ext_info; hw_link_info->loopback = resp->loopback; hw_link_info->max_frame_size = le16_to_cpu(resp->max_frame_size); @@ -1849,12 +1867,13 @@ i40e_status i40e_aq_get_link_info(struct i40e_hw *hw, else hw_link_info->crc_enable = false; - if (resp->command_flags & cpu_to_le16(I40E_AQ_LSE_ENABLE)) + if (resp->command_flags & cpu_to_le16(I40E_AQ_LSE_IS_ENABLED)) hw_link_info->lse_enable = true; else hw_link_info->lse_enable = false; - if ((hw->aq.fw_maj_ver < 4 || (hw->aq.fw_maj_ver == 4 && + if ((hw->mac.type == I40E_MAC_XL710) && + (hw->aq.fw_maj_ver < 4 || (hw->aq.fw_maj_ver == 4 && hw->aq.fw_min_ver < 40)) && hw_link_info->phy_type == 0xE) hw_link_info->phy_type = I40E_PHY_TYPE_10GBASE_SFPP_CU; @@ -2169,6 +2188,40 @@ enum i40e_status_code i40e_aq_set_vsi_uc_promisc_on_vlan(struct i40e_hw *hw, } /** + * i40e_aq_set_vsi_bc_promisc_on_vlan + * @hw: pointer to the hw struct + * @seid: vsi number + * @enable: set broadcast promiscuous enable/disable for a given VLAN + * @vid: The VLAN tag filter - capture any broadcast packet with this VLAN tag + * @cmd_details: pointer to command details structure or NULL + **/ +i40e_status i40e_aq_set_vsi_bc_promisc_on_vlan(struct i40e_hw *hw, + u16 seid, bool enable, u16 vid, + struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_set_vsi_promiscuous_modes *cmd = + (struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw; + i40e_status status; + u16 flags = 0; + + i40e_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_set_vsi_promiscuous_modes); + + if (enable) + flags |= I40E_AQC_SET_VSI_PROMISC_BROADCAST; + + cmd->promiscuous_flags = cpu_to_le16(flags); + cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_BROADCAST); + cmd->seid = cpu_to_le16(seid); + cmd->vlan_tag = cpu_to_le16(vid | I40E_AQC_SET_VSI_VLAN_VALID); + + status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details); + + return status; +} + +/** * i40e_aq_set_vsi_broadcast * @hw: pointer to the hw struct * @seid: vsi number @@ -2494,7 +2547,10 @@ i40e_status i40e_update_link_info(struct i40e_hw *hw) if (status) return status; - if (hw->phy.link_info.link_info & I40E_AQ_MEDIA_AVAILABLE) { + /* extra checking needed to ensure link info to user is timely */ + if ((hw->phy.link_info.link_info & I40E_AQ_MEDIA_AVAILABLE) && + ((hw->phy.link_info.link_info & I40E_AQ_LINK_UP) || + !(hw->phy.link_info_old.link_info & I40E_AQ_LINK_UP))) { status = i40e_aq_get_phy_capabilities(hw, false, false, &abilities, NULL); if (status) @@ -3144,6 +3200,14 @@ static void i40e_parse_discover_capabilities(struct i40e_hw *hw, void *buff, break; case I40E_AQ_CAP_ID_MNG_MODE: p->management_mode = number; + if (major_rev > 1) { + p->mng_protocols_over_mctp = logical_id; + i40e_debug(hw, I40E_DEBUG_INIT, + "HW Capability: Protocols over MCTP = %d\n", + p->mng_protocols_over_mctp); + } else { + p->mng_protocols_over_mctp = 0; + } break; case I40E_AQ_CAP_ID_NPAR_ACTIVE: p->npar_enable = number; @@ -3310,8 +3374,10 @@ static void i40e_parse_discover_capabilities(struct i40e_hw *hw, void *buff, /* partition id is 1-based, and functions are evenly spread * across the ports as partitions */ - hw->partition_id = (hw->pf_id / hw->num_ports) + 1; - hw->num_partitions = num_functions / hw->num_ports; + if (hw->num_ports != 0) { + hw->partition_id = (hw->pf_id / hw->num_ports) + 1; + hw->num_partitions = num_functions / hw->num_ports; + } /* additional HW specific goodies that might * someday be HW version specific @@ -4391,7 +4457,92 @@ i40e_status i40e_aq_configure_partition_bw(struct i40e_hw *hw, } /** - * i40e_read_phy_register + * i40e_read_phy_register_clause22 + * @hw: pointer to the HW structure + * @reg: register address in the page + * @phy_adr: PHY address on MDIO interface + * @value: PHY register value + * + * Reads specified PHY register value + **/ +i40e_status i40e_read_phy_register_clause22(struct i40e_hw *hw, + u16 reg, u8 phy_addr, u16 *value) +{ + i40e_status status = I40E_ERR_TIMEOUT; + u8 port_num = (u8)hw->func_caps.mdio_port_num; + u32 command = 0; + u16 retry = 1000; + + command = (reg << I40E_GLGEN_MSCA_DEVADD_SHIFT) | + (phy_addr << I40E_GLGEN_MSCA_PHYADD_SHIFT) | + (I40E_MDIO_CLAUSE22_OPCODE_READ_MASK) | + (I40E_MDIO_CLAUSE22_STCODE_MASK) | + (I40E_GLGEN_MSCA_MDICMD_MASK); + wr32(hw, I40E_GLGEN_MSCA(port_num), command); + do { + command = rd32(hw, I40E_GLGEN_MSCA(port_num)); + if (!(command & I40E_GLGEN_MSCA_MDICMD_MASK)) { + status = 0; + break; + } + udelay(10); + retry--; + } while (retry); + + if (status) { + i40e_debug(hw, I40E_DEBUG_PHY, + "PHY: Can't write command to external PHY.\n"); + } else { + command = rd32(hw, I40E_GLGEN_MSRWD(port_num)); + *value = (command & I40E_GLGEN_MSRWD_MDIRDDATA_MASK) >> + I40E_GLGEN_MSRWD_MDIRDDATA_SHIFT; + } + + return status; +} + +/** + * i40e_write_phy_register_clause22 + * @hw: pointer to the HW structure + * @reg: register address in the page + * @phy_adr: PHY address on MDIO interface + * @value: PHY register value + * + * Writes specified PHY register value + **/ +i40e_status i40e_write_phy_register_clause22(struct i40e_hw *hw, + u16 reg, u8 phy_addr, u16 value) +{ + i40e_status status = I40E_ERR_TIMEOUT; + u8 port_num = (u8)hw->func_caps.mdio_port_num; + u32 command = 0; + u16 retry = 1000; + + command = value << I40E_GLGEN_MSRWD_MDIWRDATA_SHIFT; + wr32(hw, I40E_GLGEN_MSRWD(port_num), command); + + command = (reg << I40E_GLGEN_MSCA_DEVADD_SHIFT) | + (phy_addr << I40E_GLGEN_MSCA_PHYADD_SHIFT) | + (I40E_MDIO_CLAUSE22_OPCODE_WRITE_MASK) | + (I40E_MDIO_CLAUSE22_STCODE_MASK) | + (I40E_GLGEN_MSCA_MDICMD_MASK); + + wr32(hw, I40E_GLGEN_MSCA(port_num), command); + do { + command = rd32(hw, I40E_GLGEN_MSCA(port_num)); + if (!(command & I40E_GLGEN_MSCA_MDICMD_MASK)) { + status = 0; + break; + } + udelay(10); + retry--; + } while (retry); + + return status; +} + +/** + * i40e_read_phy_register_clause45 * @hw: pointer to the HW structure * @page: registers page number * @reg: register address in the page @@ -4400,9 +4551,8 @@ i40e_status i40e_aq_configure_partition_bw(struct i40e_hw *hw, * * Reads specified PHY register value **/ -i40e_status i40e_read_phy_register(struct i40e_hw *hw, - u8 page, u16 reg, u8 phy_addr, - u16 *value) +i40e_status i40e_read_phy_register_clause45(struct i40e_hw *hw, + u8 page, u16 reg, u8 phy_addr, u16 *value) { i40e_status status = I40E_ERR_TIMEOUT; u32 command = 0; @@ -4412,8 +4562,8 @@ i40e_status i40e_read_phy_register(struct i40e_hw *hw, command = (reg << I40E_GLGEN_MSCA_MDIADD_SHIFT) | (page << I40E_GLGEN_MSCA_DEVADD_SHIFT) | (phy_addr << I40E_GLGEN_MSCA_PHYADD_SHIFT) | - (I40E_MDIO_OPCODE_ADDRESS) | - (I40E_MDIO_STCODE) | + (I40E_MDIO_CLAUSE45_OPCODE_ADDRESS_MASK) | + (I40E_MDIO_CLAUSE45_STCODE_MASK) | (I40E_GLGEN_MSCA_MDICMD_MASK) | (I40E_GLGEN_MSCA_MDIINPROGEN_MASK); wr32(hw, I40E_GLGEN_MSCA(port_num), command); @@ -4435,8 +4585,8 @@ i40e_status i40e_read_phy_register(struct i40e_hw *hw, command = (page << I40E_GLGEN_MSCA_DEVADD_SHIFT) | (phy_addr << I40E_GLGEN_MSCA_PHYADD_SHIFT) | - (I40E_MDIO_OPCODE_READ) | - (I40E_MDIO_STCODE) | + (I40E_MDIO_CLAUSE45_OPCODE_READ_MASK) | + (I40E_MDIO_CLAUSE45_STCODE_MASK) | (I40E_GLGEN_MSCA_MDICMD_MASK) | (I40E_GLGEN_MSCA_MDIINPROGEN_MASK); status = I40E_ERR_TIMEOUT; @@ -4466,7 +4616,7 @@ phy_read_end: } /** - * i40e_write_phy_register + * i40e_write_phy_register_clause45 * @hw: pointer to the HW structure * @page: registers page number * @reg: register address in the page @@ -4475,9 +4625,8 @@ phy_read_end: * * Writes value to specified PHY register **/ -i40e_status i40e_write_phy_register(struct i40e_hw *hw, - u8 page, u16 reg, u8 phy_addr, - u16 value) +i40e_status i40e_write_phy_register_clause45(struct i40e_hw *hw, + u8 page, u16 reg, u8 phy_addr, u16 value) { i40e_status status = I40E_ERR_TIMEOUT; u32 command = 0; @@ -4487,8 +4636,8 @@ i40e_status i40e_write_phy_register(struct i40e_hw *hw, command = (reg << I40E_GLGEN_MSCA_MDIADD_SHIFT) | (page << I40E_GLGEN_MSCA_DEVADD_SHIFT) | (phy_addr << I40E_GLGEN_MSCA_PHYADD_SHIFT) | - (I40E_MDIO_OPCODE_ADDRESS) | - (I40E_MDIO_STCODE) | + (I40E_MDIO_CLAUSE45_OPCODE_ADDRESS_MASK) | + (I40E_MDIO_CLAUSE45_STCODE_MASK) | (I40E_GLGEN_MSCA_MDICMD_MASK) | (I40E_GLGEN_MSCA_MDIINPROGEN_MASK); wr32(hw, I40E_GLGEN_MSCA(port_num), command); @@ -4512,8 +4661,8 @@ i40e_status i40e_write_phy_register(struct i40e_hw *hw, command = (page << I40E_GLGEN_MSCA_DEVADD_SHIFT) | (phy_addr << I40E_GLGEN_MSCA_PHYADD_SHIFT) | - (I40E_MDIO_OPCODE_WRITE) | - (I40E_MDIO_STCODE) | + (I40E_MDIO_CLAUSE45_OPCODE_WRITE_MASK) | + (I40E_MDIO_CLAUSE45_STCODE_MASK) | (I40E_GLGEN_MSCA_MDICMD_MASK) | (I40E_GLGEN_MSCA_MDIINPROGEN_MASK); status = I40E_ERR_TIMEOUT; @@ -4534,6 +4683,78 @@ phy_write_end: } /** + * i40e_write_phy_register + * @hw: pointer to the HW structure + * @page: registers page number + * @reg: register address in the page + * @phy_adr: PHY address on MDIO interface + * @value: PHY register value + * + * Writes value to specified PHY register + **/ +i40e_status i40e_write_phy_register(struct i40e_hw *hw, + u8 page, u16 reg, u8 phy_addr, u16 value) +{ + i40e_status status; + + switch (hw->device_id) { + case I40E_DEV_ID_1G_BASE_T_X722: + status = i40e_write_phy_register_clause22(hw, reg, phy_addr, + value); + break; + case I40E_DEV_ID_10G_BASE_T: + case I40E_DEV_ID_10G_BASE_T4: + case I40E_DEV_ID_10G_BASE_T_X722: + case I40E_DEV_ID_25G_B: + case I40E_DEV_ID_25G_SFP28: + status = i40e_write_phy_register_clause45(hw, page, reg, + phy_addr, value); + break; + default: + status = I40E_ERR_UNKNOWN_PHY; + break; + } + + return status; +} + +/** + * i40e_read_phy_register + * @hw: pointer to the HW structure + * @page: registers page number + * @reg: register address in the page + * @phy_adr: PHY address on MDIO interface + * @value: PHY register value + * + * Reads specified PHY register value + **/ +i40e_status i40e_read_phy_register(struct i40e_hw *hw, + u8 page, u16 reg, u8 phy_addr, u16 *value) +{ + i40e_status status; + + switch (hw->device_id) { + case I40E_DEV_ID_1G_BASE_T_X722: + status = i40e_read_phy_register_clause22(hw, reg, phy_addr, + value); + break; + case I40E_DEV_ID_10G_BASE_T: + case I40E_DEV_ID_10G_BASE_T4: + case I40E_DEV_ID_10G_BASE_T_X722: + case I40E_DEV_ID_25G_B: + case I40E_DEV_ID_25G_SFP28: + status = i40e_read_phy_register_clause45(hw, page, reg, + phy_addr, value); + break; + default: + status = I40E_ERR_UNKNOWN_PHY; + break; + } + + return status; +} + +/** * i40e_get_phy_address * @hw: pointer to the HW structure * @dev_num: PHY port num that address we want @@ -4575,14 +4796,16 @@ i40e_status i40e_blink_phy_link_led(struct i40e_hw *hw, for (gpio_led_port = 0; gpio_led_port < 3; gpio_led_port++, led_addr++) { - status = i40e_read_phy_register(hw, I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, &led_reg); + status = i40e_read_phy_register_clause45(hw, + I40E_PHY_COM_REG_PAGE, + led_addr, phy_addr, + &led_reg); if (status) goto phy_blinking_end; led_ctl = led_reg; if (led_reg & I40E_PHY_LED_LINK_MODE_MASK) { led_reg = 0; - status = i40e_write_phy_register(hw, + status = i40e_write_phy_register_clause45(hw, I40E_PHY_COM_REG_PAGE, led_addr, phy_addr, led_reg); @@ -4594,20 +4817,18 @@ i40e_status i40e_blink_phy_link_led(struct i40e_hw *hw, if (time > 0 && interval > 0) { for (i = 0; i < time * 1000; i += interval) { - status = i40e_read_phy_register(hw, - I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, - &led_reg); + status = i40e_read_phy_register_clause45(hw, + I40E_PHY_COM_REG_PAGE, + led_addr, phy_addr, &led_reg); if (status) goto restore_config; if (led_reg & I40E_PHY_LED_MANUAL_ON) led_reg = 0; else led_reg = I40E_PHY_LED_MANUAL_ON; - status = i40e_write_phy_register(hw, - I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, - led_reg); + status = i40e_write_phy_register_clause45(hw, + I40E_PHY_COM_REG_PAGE, + led_addr, phy_addr, led_reg); if (status) goto restore_config; msleep(interval); @@ -4615,8 +4836,9 @@ i40e_status i40e_blink_phy_link_led(struct i40e_hw *hw, } restore_config: - status = i40e_write_phy_register(hw, I40E_PHY_COM_REG_PAGE, led_addr, - phy_addr, led_ctl); + status = i40e_write_phy_register_clause45(hw, + I40E_PHY_COM_REG_PAGE, + led_addr, phy_addr, led_ctl); phy_blinking_end: return status; @@ -4647,8 +4869,10 @@ i40e_status i40e_led_get_phy(struct i40e_hw *hw, u16 *led_addr, for (gpio_led_port = 0; gpio_led_port < 3; gpio_led_port++, temp_addr++) { - status = i40e_read_phy_register(hw, I40E_PHY_COM_REG_PAGE, - temp_addr, phy_addr, ®_val); + status = i40e_read_phy_register_clause45(hw, + I40E_PHY_COM_REG_PAGE, + temp_addr, phy_addr, + ®_val); if (status) return status; *val = reg_val; @@ -4681,41 +4905,42 @@ i40e_status i40e_led_set_phy(struct i40e_hw *hw, bool on, i = rd32(hw, I40E_PFGEN_PORTNUM); port_num = (u8)(i & I40E_PFGEN_PORTNUM_PORT_NUM_MASK); phy_addr = i40e_get_phy_address(hw, port_num); - - status = i40e_read_phy_register(hw, I40E_PHY_COM_REG_PAGE, led_addr, - phy_addr, &led_reg); + status = i40e_read_phy_register_clause45(hw, I40E_PHY_COM_REG_PAGE, + led_addr, phy_addr, &led_reg); if (status) return status; led_ctl = led_reg; if (led_reg & I40E_PHY_LED_LINK_MODE_MASK) { led_reg = 0; - status = i40e_write_phy_register(hw, I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, led_reg); + status = i40e_write_phy_register_clause45(hw, + I40E_PHY_COM_REG_PAGE, + led_addr, phy_addr, + led_reg); if (status) return status; } - status = i40e_read_phy_register(hw, I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, &led_reg); + status = i40e_read_phy_register_clause45(hw, I40E_PHY_COM_REG_PAGE, + led_addr, phy_addr, &led_reg); if (status) goto restore_config; if (on) led_reg = I40E_PHY_LED_MANUAL_ON; else led_reg = 0; - status = i40e_write_phy_register(hw, I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, led_reg); + status = i40e_write_phy_register_clause45(hw, I40E_PHY_COM_REG_PAGE, + led_addr, phy_addr, led_reg); if (status) goto restore_config; if (mode & I40E_PHY_LED_MODE_ORIG) { led_ctl = (mode & I40E_PHY_LED_MODE_MASK); - status = i40e_write_phy_register(hw, + status = i40e_write_phy_register_clause45(hw, I40E_PHY_COM_REG_PAGE, led_addr, phy_addr, led_ctl); } return status; restore_config: - status = i40e_write_phy_register(hw, I40E_PHY_COM_REG_PAGE, led_addr, - phy_addr, led_ctl); + status = i40e_write_phy_register_clause45(hw, I40E_PHY_COM_REG_PAGE, + led_addr, phy_addr, led_ctl); return status; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 0c1875b5b16d..267ad2588255 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -134,7 +134,7 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) struct rtnl_link_stats64 *nstat; struct i40e_mac_filter *f; struct i40e_vsi *vsi; - int i; + int i, bkt; vsi = i40e_dbg_find_vsi(pf, seid); if (!vsi) { @@ -166,13 +166,13 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) pf->hw.mac.addr, pf->hw.mac.san_addr, pf->hw.mac.port_addr); - list_for_each_entry(f, &vsi->mac_filter_list, list) { + hash_for_each(vsi->mac_filter_hash, bkt, f, hlist) { dev_info(&pf->pdev->dev, - " mac_filter_list: %pM vid=%d, is_netdev=%d is_vf=%d counter=%d, state %s\n", - f->macaddr, f->vlan, f->is_netdev, f->is_vf, - f->counter, i40e_filter_state_string[f->state]); + " mac_filter_hash: %pM vid=%d, state %s\n", + f->macaddr, f->vlan, + i40e_filter_state_string[f->state]); } - dev_info(&pf->pdev->dev, " active_filters %d, promisc_threshold %d, overflow promisc %s\n", + dev_info(&pf->pdev->dev, " active_filters %u, promisc_threshold %u, overflow promisc %s\n", vsi->active_filters, vsi->promisc_threshold, (test_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state) ? "ON" : "OFF")); @@ -867,86 +867,6 @@ static ssize_t i40e_dbg_command_write(struct file *filp, dev_info(&pf->pdev->dev, "deleting relay %d\n", veb_seid); i40e_veb_release(pf->veb[i]); - - } else if (strncmp(cmd_buf, "add macaddr", 11) == 0) { - struct i40e_mac_filter *f; - int vlan = 0; - u8 ma[6]; - int ret; - - cnt = sscanf(&cmd_buf[11], - "%i %hhx:%hhx:%hhx:%hhx:%hhx:%hhx %i", - &vsi_seid, - &ma[0], &ma[1], &ma[2], &ma[3], &ma[4], &ma[5], - &vlan); - if (cnt == 7) { - vlan = 0; - } else if (cnt != 8) { - dev_info(&pf->pdev->dev, - "add macaddr: bad command string, cnt=%d\n", - cnt); - goto command_write_done; - } - - vsi = i40e_dbg_find_vsi(pf, vsi_seid); - if (!vsi) { - dev_info(&pf->pdev->dev, - "add macaddr: VSI %d not found\n", vsi_seid); - goto command_write_done; - } - - spin_lock_bh(&vsi->mac_filter_list_lock); - f = i40e_add_filter(vsi, ma, vlan, false, false); - spin_unlock_bh(&vsi->mac_filter_list_lock); - ret = i40e_sync_vsi_filters(vsi); - if (f && !ret) - dev_info(&pf->pdev->dev, - "add macaddr: %pM vlan=%d added to VSI %d\n", - ma, vlan, vsi_seid); - else - dev_info(&pf->pdev->dev, - "add macaddr: %pM vlan=%d to VSI %d failed, f=%p ret=%d\n", - ma, vlan, vsi_seid, f, ret); - - } else if (strncmp(cmd_buf, "del macaddr", 11) == 0) { - int vlan = 0; - u8 ma[6]; - int ret; - - cnt = sscanf(&cmd_buf[11], - "%i %hhx:%hhx:%hhx:%hhx:%hhx:%hhx %i", - &vsi_seid, - &ma[0], &ma[1], &ma[2], &ma[3], &ma[4], &ma[5], - &vlan); - if (cnt == 7) { - vlan = 0; - } else if (cnt != 8) { - dev_info(&pf->pdev->dev, - "del macaddr: bad command string, cnt=%d\n", - cnt); - goto command_write_done; - } - - vsi = i40e_dbg_find_vsi(pf, vsi_seid); - if (!vsi) { - dev_info(&pf->pdev->dev, - "del macaddr: VSI %d not found\n", vsi_seid); - goto command_write_done; - } - - spin_lock_bh(&vsi->mac_filter_list_lock); - i40e_del_filter(vsi, ma, vlan, false, false); - spin_unlock_bh(&vsi->mac_filter_list_lock); - ret = i40e_sync_vsi_filters(vsi); - if (!ret) - dev_info(&pf->pdev->dev, - "del macaddr: %pM vlan=%d removed from VSI %d\n", - ma, vlan, vsi_seid); - else - dev_info(&pf->pdev->dev, - "del macaddr: %pM vlan=%d from VSI %d failed, ret=%d\n", - ma, vlan, vsi_seid, ret); - } else if (strncmp(cmd_buf, "add pvid", 8) == 0) { i40e_status ret; u16 vid; @@ -1054,7 +974,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp, struct i40e_dcbx_config *r_cfg = &pf->hw.remote_dcbx_config; int i, ret; - u32 switch_id; + u16 switch_id; bw_data = kzalloc(sizeof( struct i40e_aqc_query_port_ets_config_resp), @@ -1066,7 +986,8 @@ static ssize_t i40e_dbg_command_write(struct file *filp, vsi = pf->vsi[pf->lan_vsi]; switch_id = - vsi->info.switch_id & I40E_AQ_VSI_SW_ID_MASK; + le16_to_cpu(vsi->info.switch_id) & + I40E_AQ_VSI_SW_ID_MASK; ret = i40e_aq_query_port_ets_config(&pf->hw, switch_id, @@ -1210,24 +1131,6 @@ static ssize_t i40e_dbg_command_write(struct file *filp, dev_info(&pf->pdev->dev, "dump debug fwdata <cluster_id> <table_id> <index>\n"); } - - } else if (strncmp(cmd_buf, "msg_enable", 10) == 0) { - u32 level; - cnt = sscanf(&cmd_buf[10], "%i", &level); - if (cnt) { - if (I40E_DEBUG_USER & level) { - pf->hw.debug_mask = level; - dev_info(&pf->pdev->dev, - "set hw.debug_mask = 0x%08x\n", - pf->hw.debug_mask); - } - pf->msg_enable = level; - dev_info(&pf->pdev->dev, "set msg_enable = 0x%08x\n", - pf->msg_enable); - } else { - dev_info(&pf->pdev->dev, "msg_enable = 0x%08x\n", - pf->msg_enable); - } } else if (strncmp(cmd_buf, "pfr", 3) == 0) { dev_info(&pf->pdev->dev, "debugfs: forcing PFR\n"); i40e_do_reset_safe(pf, BIT(__I40E_PF_RESET_REQUESTED)); @@ -1633,8 +1536,6 @@ static ssize_t i40e_dbg_command_write(struct file *filp, dev_info(&pf->pdev->dev, " del vsi [vsi_seid]\n"); dev_info(&pf->pdev->dev, " add relay <uplink_seid> <vsi_seid>\n"); dev_info(&pf->pdev->dev, " del relay <relay_seid>\n"); - dev_info(&pf->pdev->dev, " add macaddr <vsi_seid> <aa:bb:cc:dd:ee:ff> [vlan]\n"); - dev_info(&pf->pdev->dev, " del macaddr <vsi_seid> <aa:bb:cc:dd:ee:ff> [vlan]\n"); dev_info(&pf->pdev->dev, " add pvid <vsi_seid> <vid>\n"); dev_info(&pf->pdev->dev, " del pvid <vsi_seid>\n"); dev_info(&pf->pdev->dev, " dump switch\n"); @@ -1644,7 +1545,6 @@ static ssize_t i40e_dbg_command_write(struct file *filp, dev_info(&pf->pdev->dev, " dump desc aq\n"); dev_info(&pf->pdev->dev, " dump reset stats\n"); dev_info(&pf->pdev->dev, " dump debug fwdata <cluster_id> <table_id> <index>\n"); - dev_info(&pf->pdev->dev, " msg_enable [level]\n"); dev_info(&pf->pdev->dev, " read <reg>\n"); dev_info(&pf->pdev->dev, " write <reg> <value>\n"); dev_info(&pf->pdev->dev, " clear_stats vsi [seid]\n"); diff --git a/drivers/net/ethernet/intel/i40e/i40e_devids.h b/drivers/net/ethernet/intel/i40e/i40e_devids.h index dd4457d29e98..8e46098bad57 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_devids.h +++ b/drivers/net/ethernet/intel/i40e/i40e_devids.h @@ -39,6 +39,8 @@ #define I40E_DEV_ID_20G_KR2 0x1587 #define I40E_DEV_ID_20G_KR2_A 0x1588 #define I40E_DEV_ID_10G_BASE_T4 0x1589 +#define I40E_DEV_ID_25G_B 0x158A +#define I40E_DEV_ID_25G_SFP28 0x158B #define I40E_DEV_ID_KX_X722 0x37CE #define I40E_DEV_ID_QSFP_X722 0x37CF #define I40E_DEV_ID_SFP_X722 0x37D0 diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 92bc8846f1ba..a22e26200bcc 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -104,7 +104,7 @@ static const struct i40e_stats i40e_gstrings_misc_stats[] = { * The PF_STATs are appended to the netdev stats only when ethtool -S * is queried on the base PF netdev, not on the VMDq or FCoE netdev. */ -static struct i40e_stats i40e_gstrings_stats[] = { +static const struct i40e_stats i40e_gstrings_stats[] = { I40E_PF_STAT("rx_bytes", stats.eth.rx_bytes), I40E_PF_STAT("tx_bytes", stats.eth.tx_bytes), I40E_PF_STAT("rx_unicast", stats.eth.rx_unicast), @@ -216,7 +216,6 @@ enum i40e_ethtool_test_id { I40E_ETH_TEST_REG = 0, I40E_ETH_TEST_EEPROM, I40E_ETH_TEST_INTR, - I40E_ETH_TEST_LOOPBACK, I40E_ETH_TEST_LINK, }; @@ -224,32 +223,27 @@ static const char i40e_gstrings_test[][ETH_GSTRING_LEN] = { "Register test (offline)", "Eeprom test (offline)", "Interrupt test (offline)", - "Loopback test (offline)", "Link test (on/offline)" }; #define I40E_TEST_LEN (sizeof(i40e_gstrings_test) / ETH_GSTRING_LEN) -static const char i40e_priv_flags_strings_gl[][ETH_GSTRING_LEN] = { +static const char i40e_priv_flags_strings[][ETH_GSTRING_LEN] = { "MFP", "LinkPolling", "flow-director-atr", "veb-stats", "hw-atr-eviction", - "vf-true-promisc-support", }; -#define I40E_PRIV_FLAGS_GL_STR_LEN ARRAY_SIZE(i40e_priv_flags_strings_gl) +#define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_priv_flags_strings) -static const char i40e_priv_flags_strings[][ETH_GSTRING_LEN] = { - "NPAR", - "LinkPolling", - "flow-director-atr", - "veb-stats", - "hw-atr-eviction", +/* Private flags with a global effect, restricted to PF 0 */ +static const char i40e_gl_priv_flags_strings[][ETH_GSTRING_LEN] = { + "vf-true-promisc-support", }; -#define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_priv_flags_strings) +#define I40E_GL_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gl_priv_flags_strings) /** * i40e_partition_setting_complaint - generic complaint for MFP restriction @@ -271,8 +265,9 @@ static void i40e_partition_setting_complaint(struct i40e_pf *pf) static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported, u32 *advertising) { - enum i40e_aq_capabilities_phy_type phy_types = pf->hw.phy.phy_types; struct i40e_link_status *hw_link_info = &pf->hw.phy.link_info; + u64 phy_types = pf->hw.phy.phy_types; + *supported = 0x0; *advertising = 0x0; @@ -351,11 +346,13 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported, *advertising |= ADVERTISED_20000baseKR2_Full; } if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_KR) { - *supported |= SUPPORTED_10000baseKR_Full | - SUPPORTED_Autoneg; + if (!(pf->flags & I40E_FLAG_HAVE_CRT_RETIMER)) + *supported |= SUPPORTED_10000baseKR_Full | + SUPPORTED_Autoneg; *advertising |= ADVERTISED_Autoneg; if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) - *advertising |= ADVERTISED_10000baseKR_Full; + if (!(pf->flags & I40E_FLAG_HAVE_CRT_RETIMER)) + *advertising |= ADVERTISED_10000baseKR_Full; } if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_KX4) { *supported |= SUPPORTED_10000baseKX4_Full | @@ -365,11 +362,20 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported, *advertising |= ADVERTISED_10000baseKX4_Full; } if (phy_types & I40E_CAP_PHY_TYPE_1000BASE_KX) { - *supported |= SUPPORTED_1000baseKX_Full | - SUPPORTED_Autoneg; + if (!(pf->flags & I40E_FLAG_HAVE_CRT_RETIMER)) + *supported |= SUPPORTED_1000baseKX_Full | + SUPPORTED_Autoneg; *advertising |= ADVERTISED_Autoneg; if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) - *advertising |= ADVERTISED_1000baseKX_Full; + if (!(pf->flags & I40E_FLAG_HAVE_CRT_RETIMER)) + *advertising |= ADVERTISED_1000baseKX_Full; + } + if (phy_types & I40E_CAP_PHY_TYPE_25GBASE_KR || + phy_types & I40E_CAP_PHY_TYPE_25GBASE_CR || + phy_types & I40E_CAP_PHY_TYPE_25GBASE_SR || + phy_types & I40E_CAP_PHY_TYPE_25GBASE_LR) { + *supported |= SUPPORTED_Autoneg; + *advertising |= ADVERTISED_Autoneg; } } @@ -493,6 +499,14 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, ADVERTISED_1000baseKX_Full | ADVERTISED_Autoneg; break; + case I40E_PHY_TYPE_25GBASE_KR: + case I40E_PHY_TYPE_25GBASE_CR: + case I40E_PHY_TYPE_25GBASE_SR: + case I40E_PHY_TYPE_25GBASE_LR: + ecmd->supported = SUPPORTED_Autoneg; + ecmd->advertising = ADVERTISED_Autoneg; + /* TODO: add speeds when ethtool is ready to support*/ + break; default: /* if we got here and link is up something bad is afoot */ netdev_info(netdev, "WARNING: Link is up but PHY type 0x%x is not recognized.\n", @@ -514,6 +528,14 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, case I40E_LINK_SPEED_40GB: ethtool_cmd_speed_set(ecmd, SPEED_40000); break; + case I40E_LINK_SPEED_25GB: +#ifdef SPEED_25000 + ethtool_cmd_speed_set(ecmd, SPEED_25000); +#else + netdev_info(netdev, + "Speed is 25G, display not supported by this version of ethtool.\n"); +#endif + break; case I40E_LINK_SPEED_20GB: ethtool_cmd_speed_set(ecmd, SPEED_20000); break; @@ -781,9 +803,12 @@ static int i40e_set_settings(struct net_device *netdev, if (change || (abilities.link_speed != config.link_speed)) { /* copy over the rest of the abilities */ config.phy_type = abilities.phy_type; + config.phy_type_ext = abilities.phy_type_ext; config.eee_capability = abilities.eee_capability; config.eeer = abilities.eeer_val; config.low_power_ctrl = abilities.d3_lpan; + config.fec_config = abilities.fec_cfg_curr_mod_ext_info & + I40E_AQ_PHY_FEC_CONFIG_MASK; /* save the requested speeds */ hw->phy.link_info.requested_speeds = config.link_speed; @@ -978,6 +1003,10 @@ static u32 i40e_get_msglevel(struct net_device *netdev) { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_pf *pf = np->vsi->back; + u32 debug_mask = pf->hw.debug_mask; + + if (debug_mask) + netdev_info(netdev, "i40e debug_mask: 0x%08X\n", debug_mask); return pf->msg_enable; } @@ -989,7 +1018,8 @@ static void i40e_set_msglevel(struct net_device *netdev, u32 data) if (I40E_DEBUG_USER & data) pf->hw.debug_mask = data; - pf->msg_enable = data; + else + pf->msg_enable = data; } static int i40e_get_regs_len(struct net_device *netdev) @@ -1191,10 +1221,9 @@ static void i40e_get_drvinfo(struct net_device *netdev, sizeof(drvinfo->fw_version)); strlcpy(drvinfo->bus_info, pci_name(pf->pdev), sizeof(drvinfo->bus_info)); + drvinfo->n_priv_flags = I40E_PRIV_FLAGS_STR_LEN; if (pf->hw.pf_id == 0) - drvinfo->n_priv_flags = I40E_PRIV_FLAGS_GL_STR_LEN; - else - drvinfo->n_priv_flags = I40E_PRIV_FLAGS_STR_LEN; + drvinfo->n_priv_flags += I40E_GL_PRIV_FLAGS_STR_LEN; } static void i40e_get_ringparam(struct net_device *netdev, @@ -1219,6 +1248,7 @@ static int i40e_set_ringparam(struct net_device *netdev, { struct i40e_ring *tx_rings = NULL, *rx_rings = NULL; struct i40e_netdev_priv *np = netdev_priv(netdev); + struct i40e_hw *hw = &np->vsi->back->hw; struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; u32 new_rx_count, new_tx_count; @@ -1311,10 +1341,6 @@ static int i40e_set_ringparam(struct net_device *netdev, } for (i = 0; i < vsi->num_queue_pairs; i++) { - /* this is to allow wr32 to have something to write to - * during early allocation of Rx buffers - */ - u32 __iomem faketail = 0; struct i40e_ring *ring; u16 unused; @@ -1326,7 +1352,10 @@ static int i40e_set_ringparam(struct net_device *netdev, */ rx_rings[i].desc = NULL; rx_rings[i].rx_bi = NULL; - rx_rings[i].tail = (u8 __iomem *)&faketail; + /* this is to allow wr32 to have something to write to + * during early allocation of Rx buffers + */ + rx_rings[i].tail = hw->hw_addr + I40E_PRTGEN_STATUS; err = i40e_setup_rx_descriptors(&rx_rings[i]); if (err) goto rx_unwind; @@ -1422,10 +1451,8 @@ static int i40e_get_sset_count(struct net_device *netdev, int sset) return I40E_VSI_STATS_LEN(netdev); } case ETH_SS_PRIV_FLAGS: - if (pf->hw.pf_id == 0) - return I40E_PRIV_FLAGS_GL_STR_LEN; - else - return I40E_PRIV_FLAGS_STR_LEN; + return I40E_PRIV_FLAGS_STR_LEN + + (pf->hw.pf_id == 0 ? I40E_GL_PRIV_FLAGS_STR_LEN : 0); default: return -EOPNOTSUPP; } @@ -1536,10 +1563,8 @@ static void i40e_get_strings(struct net_device *netdev, u32 stringset, switch (stringset) { case ETH_SS_TEST: - for (i = 0; i < I40E_TEST_LEN; i++) { - memcpy(data, i40e_gstrings_test[i], ETH_GSTRING_LEN); - data += ETH_GSTRING_LEN; - } + memcpy(data, i40e_gstrings_test, + I40E_TEST_LEN * ETH_GSTRING_LEN); break; case ETH_SS_STATS: for (i = 0; i < I40E_NETDEV_STATS_LEN; i++) { @@ -1623,19 +1648,12 @@ static void i40e_get_strings(struct net_device *netdev, u32 stringset, /* BUG_ON(p - data != I40E_STATS_LEN * ETH_GSTRING_LEN); */ break; case ETH_SS_PRIV_FLAGS: - if (pf->hw.pf_id == 0) { - for (i = 0; i < I40E_PRIV_FLAGS_GL_STR_LEN; i++) { - memcpy(data, i40e_priv_flags_strings_gl[i], - ETH_GSTRING_LEN); - data += ETH_GSTRING_LEN; - } - } else { - for (i = 0; i < I40E_PRIV_FLAGS_STR_LEN; i++) { - memcpy(data, i40e_priv_flags_strings[i], - ETH_GSTRING_LEN); - data += ETH_GSTRING_LEN; - } - } + memcpy(data, i40e_priv_flags_strings, + I40E_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN); + data += I40E_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN; + if (pf->hw.pf_id == 0) + memcpy(data, i40e_gl_priv_flags_strings, + I40E_GL_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN); break; default: break; @@ -1666,8 +1684,19 @@ static int i40e_get_ts_info(struct net_device *dev, info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON); info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | - BIT(HWTSTAMP_FILTER_PTP_V1_L4_EVENT) | - BIT(HWTSTAMP_FILTER_PTP_V2_EVENT); + BIT(HWTSTAMP_FILTER_PTP_V2_L2_EVENT) | + BIT(HWTSTAMP_FILTER_PTP_V2_L2_SYNC) | + BIT(HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ); + + if (pf->flags & I40E_FLAG_PTP_L4_CAPABLE) + info->rx_filters |= BIT(HWTSTAMP_FILTER_PTP_V1_L4_SYNC) | + BIT(HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) | + BIT(HWTSTAMP_FILTER_PTP_V2_EVENT) | + BIT(HWTSTAMP_FILTER_PTP_V2_L4_EVENT) | + BIT(HWTSTAMP_FILTER_PTP_V2_SYNC) | + BIT(HWTSTAMP_FILTER_PTP_V2_L4_SYNC) | + BIT(HWTSTAMP_FILTER_PTP_V2_DELAY_REQ) | + BIT(HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ); return 0; } @@ -1739,17 +1768,6 @@ static int i40e_intr_test(struct net_device *netdev, u64 *data) return *data; } -static int i40e_loopback_test(struct net_device *netdev, u64 *data) -{ - struct i40e_netdev_priv *np = netdev_priv(netdev); - struct i40e_pf *pf = np->vsi->back; - - netif_info(pf, hw, netdev, "loopback test not implemented\n"); - *data = 0; - - return *data; -} - static inline bool i40e_active_vfs(struct i40e_pf *pf) { struct i40e_vf *vfs = pf->vf; @@ -1763,17 +1781,7 @@ static inline bool i40e_active_vfs(struct i40e_pf *pf) static inline bool i40e_active_vmdqs(struct i40e_pf *pf) { - struct i40e_vsi **vsi = pf->vsi; - int i; - - for (i = 0; i < pf->num_alloc_vsi; i++) { - if (!vsi[i]) - continue; - if (vsi[i]->type == I40E_VSI_VMDQ2) - return true; - } - - return false; + return !!i40e_find_vsi_by_type(pf, I40E_VSI_VMDQ2); } static void i40e_diag_test(struct net_device *netdev, @@ -1795,7 +1803,6 @@ static void i40e_diag_test(struct net_device *netdev, data[I40E_ETH_TEST_REG] = 1; data[I40E_ETH_TEST_EEPROM] = 1; data[I40E_ETH_TEST_INTR] = 1; - data[I40E_ETH_TEST_LOOPBACK] = 1; data[I40E_ETH_TEST_LINK] = 1; eth_test->flags |= ETH_TEST_FL_FAILED; clear_bit(__I40E_TESTING, &pf->state); @@ -1823,9 +1830,6 @@ static void i40e_diag_test(struct net_device *netdev, if (i40e_intr_test(netdev, &data[I40E_ETH_TEST_INTR])) eth_test->flags |= ETH_TEST_FL_FAILED; - if (i40e_loopback_test(netdev, &data[I40E_ETH_TEST_LOOPBACK])) - eth_test->flags |= ETH_TEST_FL_FAILED; - /* run reg test last, a reset is required after it */ if (i40e_reg_test(netdev, &data[I40E_ETH_TEST_REG])) eth_test->flags |= ETH_TEST_FL_FAILED; @@ -1846,7 +1850,6 @@ static void i40e_diag_test(struct net_device *netdev, data[I40E_ETH_TEST_REG] = 0; data[I40E_ETH_TEST_EEPROM] = 0; data[I40E_ETH_TEST_INTR] = 0; - data[I40E_ETH_TEST_LOOPBACK] = 0; } skip_ol_tests: @@ -1925,7 +1928,7 @@ static int i40e_set_phys_id(struct net_device *netdev, switch (state) { case ETHTOOL_ID_ACTIVE: - if (!(pf->flags & I40E_FLAG_HAVE_10GBASET_PHY)) { + if (!(pf->flags & I40E_FLAG_PHY_CONTROLS_LEDS)) { pf->led_status = i40e_led_get(hw); } else { i40e_aq_set_phy_debug(hw, I40E_PHY_DEBUG_ALL, NULL); @@ -1935,20 +1938,20 @@ static int i40e_set_phys_id(struct net_device *netdev, } return blink_freq; case ETHTOOL_ID_ON: - if (!(pf->flags & I40E_FLAG_HAVE_10GBASET_PHY)) + if (!(pf->flags & I40E_FLAG_PHY_CONTROLS_LEDS)) i40e_led_set(hw, 0xf, false); else ret = i40e_led_set_phy(hw, true, pf->led_status, 0); break; case ETHTOOL_ID_OFF: - if (!(pf->flags & I40E_FLAG_HAVE_10GBASET_PHY)) + if (!(pf->flags & I40E_FLAG_PHY_CONTROLS_LEDS)) i40e_led_set(hw, 0x0, false); else ret = i40e_led_set_phy(hw, false, pf->led_status, 0); break; case ETHTOOL_ID_INACTIVE: - if (!(pf->flags & I40E_FLAG_HAVE_10GBASET_PHY)) { - i40e_led_set(hw, false, pf->led_status); + if (!(pf->flags & I40E_FLAG_PHY_CONTROLS_LEDS)) { + i40e_led_set(hw, pf->led_status, false); } else { ret = i40e_led_set_phy(hw, false, pf->led_status, (pf->phy_led_val | @@ -2072,7 +2075,7 @@ static void i40e_set_itr_per_queue(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector; u16 vector, intrl; - intrl = INTRL_USEC_TO_REG(vsi->int_rate_limit); + intrl = i40e_intrl_usec_to_reg(vsi->int_rate_limit); vsi->rx_rings[queue]->rx_itr_setting = ec->rx_coalesce_usecs; vsi->tx_rings[queue]->tx_itr_setting = ec->tx_coalesce_usecs; @@ -2116,6 +2119,7 @@ static int __i40e_set_coalesce(struct net_device *netdev, struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; + u16 intrl_reg; int i; if (ec->tx_max_coalesced_frames_irq || ec->rx_max_coalesced_frames_irq) @@ -2127,8 +2131,9 @@ static int __i40e_set_coalesce(struct net_device *netdev, return -EINVAL; } - if (ec->rx_coalesce_usecs_high >= INTRL_REG_TO_USEC(I40E_MAX_INTRL)) { - netif_info(pf, drv, netdev, "Invalid value, rx-usecs-high range is 0-235\n"); + if (ec->rx_coalesce_usecs_high > INTRL_REG_TO_USEC(I40E_MAX_INTRL)) { + netif_info(pf, drv, netdev, "Invalid value, rx-usecs-high range is 0-%lu\n", + INTRL_REG_TO_USEC(I40E_MAX_INTRL)); return -EINVAL; } @@ -2141,7 +2146,12 @@ static int __i40e_set_coalesce(struct net_device *netdev, return -EINVAL; } - vsi->int_rate_limit = ec->rx_coalesce_usecs_high; + intrl_reg = i40e_intrl_usec_to_reg(ec->rx_coalesce_usecs_high); + vsi->int_rate_limit = INTRL_REG_TO_USEC(intrl_reg); + if (vsi->int_rate_limit != ec->rx_coalesce_usecs_high) { + netif_info(pf, drv, netdev, "Interrupt rate limit rounded down to %d\n", + vsi->int_rate_limit); + } if (ec->tx_coalesce_usecs == 0) { if (ec->use_adaptive_tx_coalesce) diff --git a/drivers/net/ethernet/intel/i40e/i40e_fcoe.c b/drivers/net/ethernet/intel/i40e/i40e_fcoe.c index 58e6c1570335..b077ef8b00fa 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_fcoe.c +++ b/drivers/net/ethernet/intel/i40e/i40e_fcoe.c @@ -1522,12 +1522,12 @@ void i40e_fcoe_config_netdev(struct net_device *netdev, struct i40e_vsi *vsi) * same PCI function. */ netdev->dev_port = 1; - spin_lock_bh(&vsi->mac_filter_list_lock); - i40e_add_filter(vsi, hw->mac.san_addr, 0, false, false); - i40e_add_filter(vsi, (u8[6]) FC_FCOE_FLOGI_MAC, 0, false, false); - i40e_add_filter(vsi, FIP_ALL_FCOE_MACS, 0, false, false); - i40e_add_filter(vsi, FIP_ALL_ENODE_MACS, 0, false, false); - spin_unlock_bh(&vsi->mac_filter_list_lock); + spin_lock_bh(&vsi->mac_filter_hash_lock); + i40e_add_filter(vsi, hw->mac.san_addr, 0); + i40e_add_filter(vsi, (u8[6]) FC_FCOE_FLOGI_MAC, 0); + i40e_add_filter(vsi, FIP_ALL_FCOE_MACS, 0); + i40e_add_filter(vsi, FIP_ALL_ENODE_MACS, 0); + spin_unlock_bh(&vsi->mac_filter_hash_lock); /* use san mac */ ether_addr_copy(netdev->dev_addr, hw->mac.san_addr); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 31c97e3937a4..e8a8351c8ea9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -41,7 +41,7 @@ static const char i40e_driver_string[] = #define DRV_VERSION_MAJOR 1 #define DRV_VERSION_MINOR 6 -#define DRV_VERSION_BUILD 16 +#define DRV_VERSION_BUILD 27 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." \ __stringify(DRV_VERSION_BUILD) DRV_KERN @@ -77,7 +77,6 @@ static const struct pci_device_id i40e_pci_tbl[] = { {PCI_VDEVICE(INTEL, I40E_DEV_ID_QSFP_C), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T4), 0}, - {PCI_VDEVICE(INTEL, I40E_DEV_ID_20G_KR2), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_KX_X722), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_QSFP_X722), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_SFP_X722), 0}, @@ -86,6 +85,8 @@ static const struct pci_device_id i40e_pci_tbl[] = { {PCI_VDEVICE(INTEL, I40E_DEV_ID_SFP_I_X722), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_20G_KR2), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_20G_KR2_A), 0}, + {PCI_VDEVICE(INTEL, I40E_DEV_ID_25G_B), 0}, + {PCI_VDEVICE(INTEL, I40E_DEV_ID_25G_SFP28), 0}, /* required last entry */ {0, } }; @@ -93,8 +94,8 @@ MODULE_DEVICE_TABLE(pci, i40e_pci_tbl); #define I40E_MAX_VF_COUNT 128 static int debug = -1; -module_param(debug, int, 0); -MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); +module_param(debug, uint, 0); +MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all), Debug mask (0x8XXXXXXX)"); MODULE_AUTHOR("Intel Corporation, <e1000-devel@lists.sourceforge.net>"); MODULE_DESCRIPTION("Intel(R) Ethernet Connection XL710 Network Driver"); @@ -286,8 +287,7 @@ struct i40e_vsi *i40e_find_vsi_from_id(struct i40e_pf *pf, u16 id) void i40e_service_event_schedule(struct i40e_pf *pf) { if (!test_bit(__I40E_DOWN, &pf->state) && - !test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state) && - !test_and_set_bit(__I40E_SERVICE_SCHED, &pf->state)) + !test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state)) queue_work(i40e_wq, &pf->service_task); } @@ -408,15 +408,11 @@ struct rtnl_link_stats64 *i40e_get_vsi_stats_struct(struct i40e_vsi *vsi) * Returns the address of the device statistics structure. * The statistics are actually updated from the service task. **/ -#ifdef I40E_FCOE -struct rtnl_link_stats64 *i40e_get_netdev_stats_struct( - struct net_device *netdev, - struct rtnl_link_stats64 *stats) -#else -static struct rtnl_link_stats64 *i40e_get_netdev_stats_struct( - struct net_device *netdev, - struct rtnl_link_stats64 *stats) +#ifndef I40E_FCOE +static #endif +void i40e_get_netdev_stats_struct(struct net_device *netdev, + struct rtnl_link_stats64 *stats) { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_ring *tx_ring, *rx_ring; @@ -425,10 +421,10 @@ static struct rtnl_link_stats64 *i40e_get_netdev_stats_struct( int i; if (test_bit(__I40E_DOWN, &vsi->state)) - return stats; + return; if (!vsi->tx_rings) - return stats; + return; rcu_read_lock(); for (i = 0; i < vsi->num_queue_pairs; i++) { @@ -468,8 +464,6 @@ static struct rtnl_link_stats64 *i40e_get_netdev_stats_struct( stats->rx_dropped = vsi_stats->rx_dropped; stats->rx_crc_errors = vsi_stats->rx_crc_errors; stats->rx_length_errors = vsi_stats->rx_length_errors; - - return stats; } /** @@ -1145,25 +1139,22 @@ void i40e_update_stats(struct i40e_vsi *vsi) * @vsi: the VSI to be searched * @macaddr: the MAC address * @vlan: the vlan - * @is_vf: make sure its a VF filter, else doesn't matter - * @is_netdev: make sure its a netdev filter, else doesn't matter * * Returns ptr to the filter object or NULL **/ static struct i40e_mac_filter *i40e_find_filter(struct i40e_vsi *vsi, - u8 *macaddr, s16 vlan, - bool is_vf, bool is_netdev) + const u8 *macaddr, s16 vlan) { struct i40e_mac_filter *f; + u64 key; if (!vsi || !macaddr) return NULL; - list_for_each_entry(f, &vsi->mac_filter_list, list) { + key = i40e_addr_to_hkey(macaddr); + hash_for_each_possible(vsi->mac_filter_hash, f, hlist, key) { if ((ether_addr_equal(macaddr, f->macaddr)) && - (vlan == f->vlan) && - (!is_vf || f->is_vf) && - (!is_netdev || f->is_netdev)) + (vlan == f->vlan)) return f; } return NULL; @@ -1173,24 +1164,21 @@ static struct i40e_mac_filter *i40e_find_filter(struct i40e_vsi *vsi, * i40e_find_mac - Find a mac addr in the macvlan filters list * @vsi: the VSI to be searched * @macaddr: the MAC address we are searching for - * @is_vf: make sure its a VF filter, else doesn't matter - * @is_netdev: make sure its a netdev filter, else doesn't matter * * Returns the first filter with the provided MAC address or NULL if * MAC address was not found **/ -struct i40e_mac_filter *i40e_find_mac(struct i40e_vsi *vsi, u8 *macaddr, - bool is_vf, bool is_netdev) +struct i40e_mac_filter *i40e_find_mac(struct i40e_vsi *vsi, const u8 *macaddr) { struct i40e_mac_filter *f; + u64 key; if (!vsi || !macaddr) return NULL; - list_for_each_entry(f, &vsi->mac_filter_list, list) { - if ((ether_addr_equal(macaddr, f->macaddr)) && - (!is_vf || f->is_vf) && - (!is_netdev || f->is_netdev)) + key = i40e_addr_to_hkey(macaddr); + hash_for_each_possible(vsi->mac_filter_hash, f, hlist, key) { + if ((ether_addr_equal(macaddr, f->macaddr))) return f; } return NULL; @@ -1204,86 +1192,141 @@ struct i40e_mac_filter *i40e_find_mac(struct i40e_vsi *vsi, u8 *macaddr, **/ bool i40e_is_vsi_in_vlan(struct i40e_vsi *vsi) { - struct i40e_mac_filter *f; + /* If we have a PVID, always operate in VLAN mode */ + if (vsi->info.pvid) + return true; - /* Only -1 for all the filters denotes not in vlan mode - * so we have to go through all the list in order to make sure + /* We need to operate in VLAN mode whenever we have any filters with + * a VLAN other than I40E_VLAN_ALL. We could check the table each + * time, incurring search cost repeatedly. However, we can notice two + * things: + * + * 1) the only place where we can gain a VLAN filter is in + * i40e_add_filter. + * + * 2) the only place where filters are actually removed is in + * i40e_sync_filters_subtask. + * + * Thus, we can simply use a boolean value, has_vlan_filters which we + * will set to true when we add a VLAN filter in i40e_add_filter. Then + * we have to perform the full search after deleting filters in + * i40e_sync_filters_subtask, but we already have to search + * filters here and can perform the check at the same time. This + * results in avoiding embedding a loop for VLAN mode inside another + * loop over all the filters, and should maintain correctness as noted + * above. */ - list_for_each_entry(f, &vsi->mac_filter_list, list) { - if (f->vlan >= 0 || vsi->info.pvid) - return true; - } - - return false; + return vsi->has_vlan_filter; } /** - * i40e_put_mac_in_vlan - Make macvlan filters from macaddrs and vlans - * @vsi: the VSI to be searched - * @macaddr: the mac address to be filtered - * @is_vf: true if it is a VF - * @is_netdev: true if it is a netdev + * i40e_correct_mac_vlan_filters - Correct non-VLAN filters if necessary + * @vsi: the VSI to configure + * @tmp_add_list: list of filters ready to be added + * @tmp_del_list: list of filters ready to be deleted + * @vlan_filters: the number of active VLAN filters * - * Goes through all the macvlan filters and adds a - * macvlan filter for each unique vlan that already exists + * Update VLAN=0 and VLAN=-1 (I40E_VLAN_ANY) filters properly so that they + * behave as expected. If we have any active VLAN filters remaining or about + * to be added then we need to update non-VLAN filters to be marked as VLAN=0 + * so that they only match against untagged traffic. If we no longer have any + * active VLAN filters, we need to make all non-VLAN filters marked as VLAN=-1 + * so that they match against both tagged and untagged traffic. In this way, + * we ensure that we correctly receive the desired traffic. This ensures that + * when we have an active VLAN we will receive only untagged traffic and + * traffic matching active VLANs. If we have no active VLANs then we will + * operate in non-VLAN mode and receive all traffic, tagged or untagged. * - * Returns first filter found on success, else NULL - **/ -struct i40e_mac_filter *i40e_put_mac_in_vlan(struct i40e_vsi *vsi, u8 *macaddr, - bool is_vf, bool is_netdev) -{ - struct i40e_mac_filter *f; + * Finally, in a similar fashion, this function also corrects filters when + * there is an active PVID assigned to this VSI. + * + * In case of memory allocation failure return -ENOMEM. Otherwise, return 0. + * + * This function is only expected to be called from within + * i40e_sync_vsi_filters. + * + * NOTE: This function expects to be called while under the + * mac_filter_hash_lock + */ +static int i40e_correct_mac_vlan_filters(struct i40e_vsi *vsi, + struct hlist_head *tmp_add_list, + struct hlist_head *tmp_del_list, + int vlan_filters) +{ + s16 pvid = le16_to_cpu(vsi->info.pvid); + struct i40e_mac_filter *f, *add_head; + struct i40e_new_mac_filter *new; + struct hlist_node *h; + int bkt, new_vlan; + + /* To determine if a particular filter needs to be replaced we + * have the three following conditions: + * + * a) if we have a PVID assigned, then all filters which are + * not marked as VLAN=PVID must be replaced with filters that + * are. + * b) otherwise, if we have any active VLANS, all filters + * which are marked as VLAN=-1 must be replaced with + * filters marked as VLAN=0 + * c) finally, if we do not have any active VLANS, all filters + * which are marked as VLAN=0 must be replaced with filters + * marked as VLAN=-1 + */ - list_for_each_entry(f, &vsi->mac_filter_list, list) { - if (vsi->info.pvid) - f->vlan = le16_to_cpu(vsi->info.pvid); - if (!i40e_find_filter(vsi, macaddr, f->vlan, - is_vf, is_netdev)) { - if (!i40e_add_filter(vsi, macaddr, f->vlan, - is_vf, is_netdev)) - return NULL; - } - } + /* Update the filters about to be added in place */ + hlist_for_each_entry(new, tmp_add_list, hlist) { + if (pvid && new->f->vlan != pvid) + new->f->vlan = pvid; + else if (vlan_filters && new->f->vlan == I40E_VLAN_ANY) + new->f->vlan = 0; + else if (!vlan_filters && new->f->vlan == 0) + new->f->vlan = I40E_VLAN_ANY; + } + + /* Update the remaining active filters */ + hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { + /* Combine the checks for whether a filter needs to be changed + * and then determine the new VLAN inside the if block, in + * order to avoid duplicating code for adding the new filter + * then deleting the old filter. + */ + if ((pvid && f->vlan != pvid) || + (vlan_filters && f->vlan == I40E_VLAN_ANY) || + (!vlan_filters && f->vlan == 0)) { + /* Determine the new vlan we will be adding */ + if (pvid) + new_vlan = pvid; + else if (vlan_filters) + new_vlan = 0; + else + new_vlan = I40E_VLAN_ANY; - return list_first_entry_or_null(&vsi->mac_filter_list, - struct i40e_mac_filter, list); -} + /* Create the new filter */ + add_head = i40e_add_filter(vsi, f->macaddr, new_vlan); + if (!add_head) + return -ENOMEM; -/** - * i40e_del_mac_all_vlan - Remove a MAC filter from all VLANS - * @vsi: the VSI to be searched - * @macaddr: the mac address to be removed - * @is_vf: true if it is a VF - * @is_netdev: true if it is a netdev - * - * Removes a given MAC address from a VSI, regardless of VLAN - * - * Returns 0 for success, or error - **/ -int i40e_del_mac_all_vlan(struct i40e_vsi *vsi, u8 *macaddr, - bool is_vf, bool is_netdev) -{ - struct i40e_mac_filter *f = NULL; - int changed = 0; + /* Create a temporary i40e_new_mac_filter */ + new = kzalloc(sizeof(*new), GFP_ATOMIC); + if (!new) + return -ENOMEM; - WARN(!spin_is_locked(&vsi->mac_filter_list_lock), - "Missing mac_filter_list_lock\n"); - list_for_each_entry(f, &vsi->mac_filter_list, list) { - if ((ether_addr_equal(macaddr, f->macaddr)) && - (is_vf == f->is_vf) && - (is_netdev == f->is_netdev)) { - f->counter--; - changed = 1; - if (f->counter == 0) - f->state = I40E_FILTER_REMOVE; + new->f = add_head; + new->state = add_head->state; + + /* Add the new filter to the tmp list */ + hlist_add_head(&new->hlist, tmp_add_list); + + /* Put the original filter into the delete list */ + f->state = I40E_FILTER_REMOVE; + hash_del(&f->hlist); + hlist_add_head(&f->hlist, tmp_del_list); } } - if (changed) { - vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED; - vsi->back->flags |= I40E_FLAG_FILTER_SYNC; - return 0; - } - return -ENOENT; + + vsi->has_vlan_filter = !!vlan_filters; + + return 0; } /** @@ -1324,36 +1367,32 @@ static void i40e_rm_default_mac_filter(struct i40e_vsi *vsi, u8 *macaddr) * @vsi: the VSI to be searched * @macaddr: the MAC address * @vlan: the vlan - * @is_vf: make sure its a VF filter, else doesn't matter - * @is_netdev: make sure its a netdev filter, else doesn't matter * * Returns ptr to the filter object or NULL when no memory available. * - * NOTE: This function is expected to be called with mac_filter_list_lock + * NOTE: This function is expected to be called with mac_filter_hash_lock * being held. **/ struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi, - u8 *macaddr, s16 vlan, - bool is_vf, bool is_netdev) + const u8 *macaddr, s16 vlan) { struct i40e_mac_filter *f; - int changed = false; + u64 key; if (!vsi || !macaddr) return NULL; - /* Do not allow broadcast filter to be added since broadcast filter - * is added as part of add VSI for any newly created VSI except - * FDIR VSI - */ - if (is_broadcast_ether_addr(macaddr)) - return NULL; - - f = i40e_find_filter(vsi, macaddr, vlan, is_vf, is_netdev); + f = i40e_find_filter(vsi, macaddr, vlan); if (!f) { f = kzalloc(sizeof(*f), GFP_ATOMIC); if (!f) - goto add_filter_out; + return NULL; + + /* Update the boolean indicating if we need to function in + * VLAN mode. + */ + if (vlan >= 0) + vsi->has_vlan_filter = true; ether_addr_copy(f->macaddr, macaddr); f->vlan = vlan; @@ -1365,100 +1404,155 @@ struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi, f->state = I40E_FILTER_FAILED; else f->state = I40E_FILTER_NEW; - changed = true; - INIT_LIST_HEAD(&f->list); - list_add_tail(&f->list, &vsi->mac_filter_list); - } + INIT_HLIST_NODE(&f->hlist); - /* increment counter and add a new flag if needed */ - if (is_vf) { - if (!f->is_vf) { - f->is_vf = true; - f->counter++; - } - } else if (is_netdev) { - if (!f->is_netdev) { - f->is_netdev = true; - f->counter++; - } - } else { - f->counter++; - } + key = i40e_addr_to_hkey(macaddr); + hash_add(vsi->mac_filter_hash, &f->hlist, key); - if (changed) { vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED; vsi->back->flags |= I40E_FLAG_FILTER_SYNC; } -add_filter_out: + /* If we're asked to add a filter that has been marked for removal, it + * is safe to simply restore it to active state. __i40e_del_filter + * will have simply deleted any filters which were previously marked + * NEW or FAILED, so if it is currently marked REMOVE it must have + * previously been ACTIVE. Since we haven't yet run the sync filters + * task, just restore this filter to the ACTIVE state so that the + * sync task leaves it in place + */ + if (f->state == I40E_FILTER_REMOVE) + f->state = I40E_FILTER_ACTIVE; + return f; } /** - * i40e_del_filter - Remove a mac/vlan filter from the VSI + * __i40e_del_filter - Remove a specific filter from the VSI + * @vsi: VSI to remove from + * @f: the filter to remove from the list + * + * This function should be called instead of i40e_del_filter only if you know + * the exact filter you will remove already, such as via i40e_find_filter or + * i40e_find_mac. + * + * NOTE: This function is expected to be called with mac_filter_hash_lock + * being held. + * ANOTHER NOTE: This function MUST be called from within the context of + * the "safe" variants of any list iterators, e.g. list_for_each_entry_safe() + * instead of list_for_each_entry(). + **/ +void __i40e_del_filter(struct i40e_vsi *vsi, struct i40e_mac_filter *f) +{ + if (!f) + return; + + /* If the filter was never added to firmware then we can just delete it + * directly and we don't want to set the status to remove or else an + * admin queue command will unnecessarily fire. + */ + if ((f->state == I40E_FILTER_FAILED) || + (f->state == I40E_FILTER_NEW)) { + hash_del(&f->hlist); + kfree(f); + } else { + f->state = I40E_FILTER_REMOVE; + } + + vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED; + vsi->back->flags |= I40E_FLAG_FILTER_SYNC; +} + +/** + * i40e_del_filter - Remove a MAC/VLAN filter from the VSI * @vsi: the VSI to be searched * @macaddr: the MAC address - * @vlan: the vlan - * @is_vf: make sure it's a VF filter, else doesn't matter - * @is_netdev: make sure it's a netdev filter, else doesn't matter + * @vlan: the VLAN * - * NOTE: This function is expected to be called with mac_filter_list_lock + * NOTE: This function is expected to be called with mac_filter_hash_lock * being held. * ANOTHER NOTE: This function MUST be called from within the context of * the "safe" variants of any list iterators, e.g. list_for_each_entry_safe() * instead of list_for_each_entry(). **/ -void i40e_del_filter(struct i40e_vsi *vsi, - u8 *macaddr, s16 vlan, - bool is_vf, bool is_netdev) +void i40e_del_filter(struct i40e_vsi *vsi, const u8 *macaddr, s16 vlan) { struct i40e_mac_filter *f; if (!vsi || !macaddr) return; - f = i40e_find_filter(vsi, macaddr, vlan, is_vf, is_netdev); - if (!f || f->counter == 0) - return; + f = i40e_find_filter(vsi, macaddr, vlan); + __i40e_del_filter(vsi, f); +} - if (is_vf) { - if (f->is_vf) { - f->is_vf = false; - f->counter--; - } - } else if (is_netdev) { - if (f->is_netdev) { - f->is_netdev = false; - f->counter--; - } - } else { - /* make sure we don't remove a filter in use by VF or netdev */ - int min_f = 0; +/** + * i40e_add_mac_filter - Add a MAC filter for all active VLANs + * @vsi: the VSI to be searched + * @macaddr: the mac address to be filtered + * + * If we're not in VLAN mode, just add the filter to I40E_VLAN_ANY. Otherwise, + * go through all the macvlan filters and add a macvlan filter for each + * unique vlan that already exists. If a PVID has been assigned, instead only + * add the macaddr to that VLAN. + * + * Returns last filter added on success, else NULL + **/ +struct i40e_mac_filter *i40e_add_mac_filter(struct i40e_vsi *vsi, + const u8 *macaddr) +{ + struct i40e_mac_filter *f, *add = NULL; + struct hlist_node *h; + int bkt; - min_f += (f->is_vf ? 1 : 0); - min_f += (f->is_netdev ? 1 : 0); + if (vsi->info.pvid) + return i40e_add_filter(vsi, macaddr, + le16_to_cpu(vsi->info.pvid)); - if (f->counter > min_f) - f->counter--; + if (!i40e_is_vsi_in_vlan(vsi)) + return i40e_add_filter(vsi, macaddr, I40E_VLAN_ANY); + + hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { + if (f->state == I40E_FILTER_REMOVE) + continue; + add = i40e_add_filter(vsi, macaddr, f->vlan); + if (!add) + return NULL; } - /* counter == 0 tells sync_filters_subtask to - * remove the filter from the firmware's list - */ - if (f->counter == 0) { - if ((f->state == I40E_FILTER_FAILED) || - (f->state == I40E_FILTER_NEW)) { - /* this one never got added by the FW. Just remove it, - * no need to sync anything. - */ - list_del(&f->list); - kfree(f); - } else { - f->state = I40E_FILTER_REMOVE; - vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED; - vsi->back->flags |= I40E_FLAG_FILTER_SYNC; + return add; +} + +/** + * i40e_del_mac_filter - Remove a MAC filter from all VLANs + * @vsi: the VSI to be searched + * @macaddr: the mac address to be removed + * + * Removes a given MAC address from a VSI regardless of what VLAN it has been + * associated with. + * + * Returns 0 for success, or error + **/ +int i40e_del_mac_filter(struct i40e_vsi *vsi, const u8 *macaddr) +{ + struct i40e_mac_filter *f; + struct hlist_node *h; + bool found = false; + int bkt; + + WARN(!spin_is_locked(&vsi->mac_filter_hash_lock), + "Missing mac_filter_hash_lock\n"); + hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { + if (ether_addr_equal(macaddr, f->macaddr)) { + __i40e_del_filter(vsi, f); + found = true; } } + + if (found) + return 0; + else + return -ENOENT; } /** @@ -1499,10 +1593,10 @@ static int i40e_set_mac(struct net_device *netdev, void *p) else netdev_info(netdev, "set new mac address %pM\n", addr->sa_data); - spin_lock_bh(&vsi->mac_filter_list_lock); - i40e_del_mac_all_vlan(vsi, netdev->dev_addr, false, true); - i40e_put_mac_in_vlan(vsi, addr->sa_data, false, true); - spin_unlock_bh(&vsi->mac_filter_list_lock); + spin_lock_bh(&vsi->mac_filter_hash_lock); + i40e_del_mac_filter(vsi, netdev->dev_addr); + i40e_add_mac_filter(vsi, addr->sa_data); + spin_unlock_bh(&vsi->mac_filter_hash_lock); ether_addr_copy(netdev->dev_addr, addr->sa_data); if (vsi->type == I40E_VSI_MAIN) { i40e_status ret; @@ -1666,6 +1760,43 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, } /** + * i40e_addr_sync - Callback for dev_(mc|uc)_sync to add address + * @netdev: the netdevice + * @addr: address to add + * + * Called by __dev_(mc|uc)_sync when an address needs to be added. We call + * __dev_(uc|mc)_sync from .set_rx_mode and guarantee to hold the hash lock. + */ +static int i40e_addr_sync(struct net_device *netdev, const u8 *addr) +{ + struct i40e_netdev_priv *np = netdev_priv(netdev); + struct i40e_vsi *vsi = np->vsi; + + if (i40e_add_mac_filter(vsi, addr)) + return 0; + else + return -ENOMEM; +} + +/** + * i40e_addr_unsync - Callback for dev_(mc|uc)_sync to remove address + * @netdev: the netdevice + * @addr: address to add + * + * Called by __dev_(mc|uc)_sync when an address needs to be removed. We call + * __dev_(uc|mc)_sync from .set_rx_mode and guarantee to hold the hash lock. + */ +static int i40e_addr_unsync(struct net_device *netdev, const u8 *addr) +{ + struct i40e_netdev_priv *np = netdev_priv(netdev); + struct i40e_vsi *vsi = np->vsi; + + i40e_del_mac_filter(vsi, addr); + + return 0; +} + +/** * i40e_set_rx_mode - NDO callback to set the netdev filters * @netdev: network interface device structure **/ @@ -1676,62 +1807,14 @@ static void i40e_set_rx_mode(struct net_device *netdev) #endif { struct i40e_netdev_priv *np = netdev_priv(netdev); - struct i40e_mac_filter *f, *ftmp; struct i40e_vsi *vsi = np->vsi; - struct netdev_hw_addr *uca; - struct netdev_hw_addr *mca; - struct netdev_hw_addr *ha; - - spin_lock_bh(&vsi->mac_filter_list_lock); - - /* add addr if not already in the filter list */ - netdev_for_each_uc_addr(uca, netdev) { - if (!i40e_find_mac(vsi, uca->addr, false, true)) { - if (i40e_is_vsi_in_vlan(vsi)) - i40e_put_mac_in_vlan(vsi, uca->addr, - false, true); - else - i40e_add_filter(vsi, uca->addr, I40E_VLAN_ANY, - false, true); - } - } - - netdev_for_each_mc_addr(mca, netdev) { - if (!i40e_find_mac(vsi, mca->addr, false, true)) { - if (i40e_is_vsi_in_vlan(vsi)) - i40e_put_mac_in_vlan(vsi, mca->addr, - false, true); - else - i40e_add_filter(vsi, mca->addr, I40E_VLAN_ANY, - false, true); - } - } - - /* remove filter if not in netdev list */ - list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) { - - if (!f->is_netdev) - continue; - - netdev_for_each_mc_addr(mca, netdev) - if (ether_addr_equal(mca->addr, f->macaddr)) - goto bottom_of_search_loop; - netdev_for_each_uc_addr(uca, netdev) - if (ether_addr_equal(uca->addr, f->macaddr)) - goto bottom_of_search_loop; + spin_lock_bh(&vsi->mac_filter_hash_lock); - for_each_dev_addr(netdev, ha) - if (ether_addr_equal(ha->addr, f->macaddr)) - goto bottom_of_search_loop; + __dev_uc_sync(netdev, i40e_addr_sync, i40e_addr_unsync); + __dev_mc_sync(netdev, i40e_addr_sync, i40e_addr_unsync); - /* f->macaddr wasn't found in uc, mc, or ha list so delete it */ - i40e_del_filter(vsi, f->macaddr, I40E_VLAN_ANY, false, true); - -bottom_of_search_loop: - continue; - } - spin_unlock_bh(&vsi->mac_filter_list_lock); + spin_unlock_bh(&vsi->mac_filter_hash_lock); /* check for other flag changes */ if (vsi->current_netdev_flags != vsi->netdev->flags) { @@ -1747,30 +1830,80 @@ bottom_of_search_loop: /** * i40e_undo_del_filter_entries - Undo the changes made to MAC filter entries - * @vsi: pointer to vsi struct + * @vsi: Pointer to VSI struct * @from: Pointer to list which contains MAC filter entries - changes to * those entries needs to be undone. * - * MAC filter entries from list were slated to be removed from device. + * MAC filter entries from this list were slated for deletion. **/ static void i40e_undo_del_filter_entries(struct i40e_vsi *vsi, - struct list_head *from) + struct hlist_head *from) { - struct i40e_mac_filter *f, *ftmp; + struct i40e_mac_filter *f; + struct hlist_node *h; + + hlist_for_each_entry_safe(f, h, from, hlist) { + u64 key = i40e_addr_to_hkey(f->macaddr); - list_for_each_entry_safe(f, ftmp, from, list) { /* Move the element back into MAC filter list*/ - list_move_tail(&f->list, &vsi->mac_filter_list); + hlist_del(&f->hlist); + hash_add(vsi->mac_filter_hash, &f->hlist, key); + } +} + +/** + * i40e_undo_add_filter_entries - Undo the changes made to MAC filter entries + * @vsi: Pointer to vsi struct + * @from: Pointer to list which contains MAC filter entries - changes to + * those entries needs to be undone. + * + * MAC filter entries from this list were slated for addition. + **/ +static void i40e_undo_add_filter_entries(struct i40e_vsi *vsi, + struct hlist_head *from) +{ + struct i40e_new_mac_filter *new; + struct hlist_node *h; + + hlist_for_each_entry_safe(new, h, from, hlist) { + /* We can simply free the wrapper structure */ + hlist_del(&new->hlist); + kfree(new); } } /** + * i40e_next_entry - Get the next non-broadcast filter from a list + * @next: pointer to filter in list + * + * Returns the next non-broadcast filter in the list. Required so that we + * ignore broadcast filters within the list, since these are not handled via + * the normal firmware update path. + */ +static +struct i40e_new_mac_filter *i40e_next_filter(struct i40e_new_mac_filter *next) +{ + while (next) { + next = hlist_entry(next->hlist.next, + typeof(struct i40e_new_mac_filter), + hlist); + + /* keep going if we found a broadcast filter */ + if (next && is_broadcast_ether_addr(next->f->macaddr)) + continue; + + break; + } + + return next; +} + +/** * i40e_update_filter_state - Update filter state based on return data * from firmware * @count: Number of filters added * @add_list: return data from fw * @head: pointer to first filter in current batch - * @aq_err: status from fw * * MAC filter entries from list were slated to be added to device. Returns * number of successful filters. Note that 0 does NOT mean success! @@ -1778,45 +1911,146 @@ static void i40e_undo_del_filter_entries(struct i40e_vsi *vsi, static int i40e_update_filter_state(int count, struct i40e_aqc_add_macvlan_element_data *add_list, - struct i40e_mac_filter *add_head, int aq_err) + struct i40e_new_mac_filter *add_head) { int retval = 0; int i; - - if (!aq_err) { - retval = count; - /* Everything's good, mark all filters active. */ - for (i = 0; i < count ; i++) { - add_head->state = I40E_FILTER_ACTIVE; - add_head = list_next_entry(add_head, list); - } - } else if (aq_err == I40E_AQ_RC_ENOSPC) { - /* Device ran out of filter space. Check the return value - * for each filter to see which ones are active. + for (i = 0; i < count; i++) { + /* Always check status of each filter. We don't need to check + * the firmware return status because we pre-set the filter + * status to I40E_AQC_MM_ERR_NO_RES when sending the filter + * request to the adminq. Thus, if it no longer matches then + * we know the filter is active. */ - for (i = 0; i < count ; i++) { - if (add_list[i].match_method == - I40E_AQC_MM_ERR_NO_RES) { - add_head->state = I40E_FILTER_FAILED; - } else { - add_head->state = I40E_FILTER_ACTIVE; - retval++; - } - add_head = list_next_entry(add_head, list); - } - } else { - /* Some other horrible thing happened, fail all filters */ - retval = 0; - for (i = 0; i < count ; i++) { + if (add_list[i].match_method == I40E_AQC_MM_ERR_NO_RES) { add_head->state = I40E_FILTER_FAILED; - add_head = list_next_entry(add_head, list); + } else { + add_head->state = I40E_FILTER_ACTIVE; + retval++; } + + add_head = i40e_next_filter(add_head); + if (!add_head) + break; } + return retval; } /** + * i40e_aqc_del_filters - Request firmware to delete a set of filters + * @vsi: ptr to the VSI + * @vsi_name: name to display in messages + * @list: the list of filters to send to firmware + * @num_del: the number of filters to delete + * @retval: Set to -EIO on failure to delete + * + * Send a request to firmware via AdminQ to delete a set of filters. Uses + * *retval instead of a return value so that success does not force ret_val to + * be set to 0. This ensures that a sequence of calls to this function + * preserve the previous value of *retval on successful delete. + */ +static +void i40e_aqc_del_filters(struct i40e_vsi *vsi, const char *vsi_name, + struct i40e_aqc_remove_macvlan_element_data *list, + int num_del, int *retval) +{ + struct i40e_hw *hw = &vsi->back->hw; + i40e_status aq_ret; + int aq_err; + + aq_ret = i40e_aq_remove_macvlan(hw, vsi->seid, list, num_del, NULL); + aq_err = hw->aq.asq_last_status; + + /* Explicitly ignore and do not report when firmware returns ENOENT */ + if (aq_ret && !(aq_err == I40E_AQ_RC_ENOENT)) { + *retval = -EIO; + dev_info(&vsi->back->pdev->dev, + "ignoring delete macvlan error on %s, err %s, aq_err %s\n", + vsi_name, i40e_stat_str(hw, aq_ret), + i40e_aq_str(hw, aq_err)); + } +} + +/** + * i40e_aqc_add_filters - Request firmware to add a set of filters + * @vsi: ptr to the VSI + * @vsi_name: name to display in messages + * @list: the list of filters to send to firmware + * @add_head: Position in the add hlist + * @num_add: the number of filters to add + * @promisc_change: set to true on exit if promiscuous mode was forced on + * + * Send a request to firmware via AdminQ to add a chunk of filters. Will set + * promisc_changed to true if the firmware has run out of space for more + * filters. + */ +static +void i40e_aqc_add_filters(struct i40e_vsi *vsi, const char *vsi_name, + struct i40e_aqc_add_macvlan_element_data *list, + struct i40e_new_mac_filter *add_head, + int num_add, bool *promisc_changed) +{ + struct i40e_hw *hw = &vsi->back->hw; + int aq_err, fcnt; + + i40e_aq_add_macvlan(hw, vsi->seid, list, num_add, NULL); + aq_err = hw->aq.asq_last_status; + fcnt = i40e_update_filter_state(num_add, list, add_head); + + if (fcnt != num_add) { + *promisc_changed = true; + set_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state); + dev_warn(&vsi->back->pdev->dev, + "Error %s adding RX filters on %s, promiscuous mode forced on\n", + i40e_aq_str(hw, aq_err), + vsi_name); + } +} + +/** + * i40e_aqc_broadcast_filter - Set promiscuous broadcast flags + * @vsi: pointer to the VSI + * @f: filter data + * + * This function sets or clears the promiscuous broadcast flags for VLAN + * filters in order to properly receive broadcast frames. Assumes that only + * broadcast filters are passed. + * + * Returns status indicating success or failure; + **/ +static i40e_status +i40e_aqc_broadcast_filter(struct i40e_vsi *vsi, const char *vsi_name, + struct i40e_mac_filter *f) +{ + bool enable = f->state == I40E_FILTER_NEW; + struct i40e_hw *hw = &vsi->back->hw; + i40e_status aq_ret; + + if (f->vlan == I40E_VLAN_ANY) { + aq_ret = i40e_aq_set_vsi_broadcast(hw, + vsi->seid, + enable, + NULL); + } else { + aq_ret = i40e_aq_set_vsi_bc_promisc_on_vlan(hw, + vsi->seid, + enable, + f->vlan, + NULL); + } + + if (aq_ret) + dev_warn(&vsi->back->pdev->dev, + "Error %s setting broadcast promiscuous mode on %s\n", + i40e_aq_str(hw, hw->aq.asq_last_status), + vsi_name); + + return aq_ret; +} + +/** * i40e_sync_vsi_filters - Update the VSI filter list to the HW * @vsi: ptr to the VSI * @@ -1826,22 +2060,25 @@ i40e_update_filter_state(int count, **/ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) { - struct i40e_mac_filter *f, *ftmp, *add_head = NULL; - struct list_head tmp_add_list, tmp_del_list; + struct hlist_head tmp_add_list, tmp_del_list; + struct i40e_mac_filter *f; + struct i40e_new_mac_filter *new, *add_head = NULL; struct i40e_hw *hw = &vsi->back->hw; + unsigned int failed_filters = 0; + unsigned int vlan_filters = 0; bool promisc_changed = false; char vsi_name[16] = "PF"; int filter_list_len = 0; - u32 changed_flags = 0; i40e_status aq_ret = 0; - int retval = 0; + u32 changed_flags = 0; + struct hlist_node *h; struct i40e_pf *pf; int num_add = 0; int num_del = 0; - int aq_err = 0; + int retval = 0; u16 cmd_flags; int list_size; - int fcnt; + int bkt; /* empty array typed pointers, kcalloc later */ struct i40e_aqc_add_macvlan_element_data *add_list; @@ -1856,8 +2093,8 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) vsi->current_netdev_flags = vsi->netdev->flags; } - INIT_LIST_HEAD(&tmp_add_list); - INIT_LIST_HEAD(&tmp_del_list); + INIT_HLIST_HEAD(&tmp_add_list); + INIT_HLIST_HEAD(&tmp_del_list); if (vsi->type == I40E_VSI_SRIOV) snprintf(vsi_name, sizeof(vsi_name) - 1, "VF %d", vsi->vf_id); @@ -1867,43 +2104,73 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) if (vsi->flags & I40E_VSI_FLAG_FILTER_CHANGED) { vsi->flags &= ~I40E_VSI_FLAG_FILTER_CHANGED; - spin_lock_bh(&vsi->mac_filter_list_lock); + spin_lock_bh(&vsi->mac_filter_hash_lock); /* Create a list of filters to delete. */ - list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) { + hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { if (f->state == I40E_FILTER_REMOVE) { - WARN_ON(f->counter != 0); /* Move the element into temporary del_list */ - list_move_tail(&f->list, &tmp_del_list); - vsi->active_filters--; + hash_del(&f->hlist); + hlist_add_head(&f->hlist, &tmp_del_list); + + /* Avoid counting removed filters */ + continue; } if (f->state == I40E_FILTER_NEW) { - WARN_ON(f->counter == 0); - /* Move the element into temporary add_list */ - list_move_tail(&f->list, &tmp_add_list); + /* Create a temporary i40e_new_mac_filter */ + new = kzalloc(sizeof(*new), GFP_ATOMIC); + if (!new) + goto err_no_memory_locked; + + /* Store pointer to the real filter */ + new->f = f; + new->state = f->state; + + /* Add it to the hash list */ + hlist_add_head(&new->hlist, &tmp_add_list); } + + /* Count the number of active (current and new) VLAN + * filters we have now. Does not count filters which + * are marked for deletion. + */ + if (f->vlan > 0) + vlan_filters++; } - spin_unlock_bh(&vsi->mac_filter_list_lock); + + retval = i40e_correct_mac_vlan_filters(vsi, + &tmp_add_list, + &tmp_del_list, + vlan_filters); + if (retval) + goto err_no_memory_locked; + + spin_unlock_bh(&vsi->mac_filter_hash_lock); } /* Now process 'del_list' outside the lock */ - if (!list_empty(&tmp_del_list)) { + if (!hlist_empty(&tmp_del_list)) { filter_list_len = hw->aq.asq_buf_size / sizeof(struct i40e_aqc_remove_macvlan_element_data); list_size = filter_list_len * sizeof(struct i40e_aqc_remove_macvlan_element_data); del_list = kzalloc(list_size, GFP_ATOMIC); - if (!del_list) { - /* Undo VSI's MAC filter entry element updates */ - spin_lock_bh(&vsi->mac_filter_list_lock); - i40e_undo_del_filter_entries(vsi, &tmp_del_list); - spin_unlock_bh(&vsi->mac_filter_list_lock); - retval = -ENOMEM; - goto out; - } + if (!del_list) + goto err_no_memory; - list_for_each_entry_safe(f, ftmp, &tmp_del_list, list) { + hlist_for_each_entry_safe(f, h, &tmp_del_list, hlist) { cmd_flags = 0; + /* handle broadcast filters by updating the broadcast + * promiscuous flag and release filter list. + */ + if (is_broadcast_ether_addr(f->macaddr)) { + i40e_aqc_broadcast_filter(vsi, vsi_name, f); + + hlist_del(&f->hlist); + kfree(f); + continue; + } + /* add to delete list */ ether_addr_copy(del_list[num_del].mac_addr, f->macaddr); if (f->vlan == I40E_VLAN_ANY) { @@ -1920,168 +2187,136 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) /* flush a full buffer */ if (num_del == filter_list_len) { - aq_ret = i40e_aq_remove_macvlan(hw, vsi->seid, - del_list, - num_del, NULL); - aq_err = hw->aq.asq_last_status; - num_del = 0; + i40e_aqc_del_filters(vsi, vsi_name, del_list, + num_del, &retval); memset(del_list, 0, list_size); - - /* Explicitly ignore and do not report when - * firmware returns ENOENT. - */ - if (aq_ret && !(aq_err == I40E_AQ_RC_ENOENT)) { - retval = -EIO; - dev_info(&pf->pdev->dev, - "ignoring delete macvlan error on %s, err %s, aq_err %s\n", - vsi_name, - i40e_stat_str(hw, aq_ret), - i40e_aq_str(hw, aq_err)); - } + num_del = 0; } /* Release memory for MAC filter entries which were * synced up with HW. */ - list_del(&f->list); + hlist_del(&f->hlist); kfree(f); } if (num_del) { - aq_ret = i40e_aq_remove_macvlan(hw, vsi->seid, del_list, - num_del, NULL); - aq_err = hw->aq.asq_last_status; - num_del = 0; - - /* Explicitly ignore and do not report when firmware - * returns ENOENT. - */ - if (aq_ret && !(aq_err == I40E_AQ_RC_ENOENT)) { - retval = -EIO; - dev_info(&pf->pdev->dev, - "ignoring delete macvlan error on %s, err %s aq_err %s\n", - vsi_name, - i40e_stat_str(hw, aq_ret), - i40e_aq_str(hw, aq_err)); - } + i40e_aqc_del_filters(vsi, vsi_name, del_list, + num_del, &retval); } kfree(del_list); del_list = NULL; } - if (!list_empty(&tmp_add_list)) { + if (!hlist_empty(&tmp_add_list)) { /* Do all the adds now. */ filter_list_len = hw->aq.asq_buf_size / sizeof(struct i40e_aqc_add_macvlan_element_data); list_size = filter_list_len * sizeof(struct i40e_aqc_add_macvlan_element_data); add_list = kzalloc(list_size, GFP_ATOMIC); - if (!add_list) { - retval = -ENOMEM; - goto out; - } + if (!add_list) + goto err_no_memory; + num_add = 0; - list_for_each_entry(f, &tmp_add_list, list) { + hlist_for_each_entry_safe(new, h, &tmp_add_list, hlist) { if (test_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state)) { - f->state = I40E_FILTER_FAILED; + new->state = I40E_FILTER_FAILED; continue; } + + /* handle broadcast filters by updating the broadcast + * promiscuous flag instead of adding a MAC filter. + */ + if (is_broadcast_ether_addr(new->f->macaddr)) { + if (i40e_aqc_broadcast_filter(vsi, vsi_name, + new->f)) + new->state = I40E_FILTER_FAILED; + else + new->state = I40E_FILTER_ACTIVE; + continue; + } + /* add to add array */ if (num_add == 0) - add_head = f; + add_head = new; cmd_flags = 0; - ether_addr_copy(add_list[num_add].mac_addr, f->macaddr); - if (f->vlan == I40E_VLAN_ANY) { + ether_addr_copy(add_list[num_add].mac_addr, + new->f->macaddr); + if (new->f->vlan == I40E_VLAN_ANY) { add_list[num_add].vlan_tag = 0; cmd_flags |= I40E_AQC_MACVLAN_ADD_IGNORE_VLAN; } else { add_list[num_add].vlan_tag = - cpu_to_le16((u16)(f->vlan)); + cpu_to_le16((u16)(new->f->vlan)); } add_list[num_add].queue_number = 0; + /* set invalid match method for later detection */ + add_list[num_add].match_method = I40E_AQC_MM_ERR_NO_RES; cmd_flags |= I40E_AQC_MACVLAN_ADD_PERFECT_MATCH; add_list[num_add].flags = cpu_to_le16(cmd_flags); num_add++; /* flush a full buffer */ if (num_add == filter_list_len) { - aq_ret = i40e_aq_add_macvlan(hw, vsi->seid, - add_list, num_add, - NULL); - aq_err = hw->aq.asq_last_status; - fcnt = i40e_update_filter_state(num_add, - add_list, - add_head, - aq_ret); - vsi->active_filters += fcnt; - - if (fcnt != num_add) { - promisc_changed = true; - set_bit(__I40E_FILTER_OVERFLOW_PROMISC, - &vsi->state); - vsi->promisc_threshold = - (vsi->active_filters * 3) / 4; - dev_warn(&pf->pdev->dev, - "Error %s adding RX filters on %s, promiscuous mode forced on\n", - i40e_aq_str(hw, aq_err), - vsi_name); - } + i40e_aqc_add_filters(vsi, vsi_name, add_list, + add_head, num_add, + &promisc_changed); memset(add_list, 0, list_size); num_add = 0; } } if (num_add) { - aq_ret = i40e_aq_add_macvlan(hw, vsi->seid, - add_list, num_add, NULL); - aq_err = hw->aq.asq_last_status; - fcnt = i40e_update_filter_state(num_add, add_list, - add_head, aq_ret); - vsi->active_filters += fcnt; - if (fcnt != num_add) { - promisc_changed = true; - set_bit(__I40E_FILTER_OVERFLOW_PROMISC, - &vsi->state); - vsi->promisc_threshold = - (vsi->active_filters * 3) / 4; - dev_warn(&pf->pdev->dev, - "Error %s adding RX filters on %s, promiscuous mode forced on\n", - i40e_aq_str(hw, aq_err), vsi_name); - } + i40e_aqc_add_filters(vsi, vsi_name, add_list, add_head, + num_add, &promisc_changed); } /* Now move all of the filters from the temp add list back to * the VSI's list. */ - spin_lock_bh(&vsi->mac_filter_list_lock); - list_for_each_entry_safe(f, ftmp, &tmp_add_list, list) { - list_move_tail(&f->list, &vsi->mac_filter_list); - } - spin_unlock_bh(&vsi->mac_filter_list_lock); + spin_lock_bh(&vsi->mac_filter_hash_lock); + hlist_for_each_entry_safe(new, h, &tmp_add_list, hlist) { + /* Only update the state if we're still NEW */ + if (new->f->state == I40E_FILTER_NEW) + new->f->state = new->state; + hlist_del(&new->hlist); + kfree(new); + } + spin_unlock_bh(&vsi->mac_filter_hash_lock); kfree(add_list); add_list = NULL; } - /* Check to see if we can drop out of overflow promiscuous mode. */ + /* Determine the number of active and failed filters. */ + spin_lock_bh(&vsi->mac_filter_hash_lock); + vsi->active_filters = 0; + hash_for_each(vsi->mac_filter_hash, bkt, f, hlist) { + if (f->state == I40E_FILTER_ACTIVE) + vsi->active_filters++; + else if (f->state == I40E_FILTER_FAILED) + failed_filters++; + } + spin_unlock_bh(&vsi->mac_filter_hash_lock); + + /* If promiscuous mode has changed, we need to calculate a new + * threshold for when we are safe to exit + */ + if (promisc_changed) + vsi->promisc_threshold = (vsi->active_filters * 3) / 4; + + /* Check if we are able to exit overflow promiscuous mode. We can + * safely exit if we didn't just enter, we no longer have any failed + * filters, and we have reduced filters below the threshold value. + */ if (test_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state) && + !promisc_changed && !failed_filters && (vsi->active_filters < vsi->promisc_threshold)) { - int failed_count = 0; - /* See if we have any failed filters. We can't drop out of - * promiscuous until these have all been deleted. - */ - spin_lock_bh(&vsi->mac_filter_list_lock); - list_for_each_entry(f, &vsi->mac_filter_list, list) { - if (f->state == I40E_FILTER_FAILED) - failed_count++; - } - spin_unlock_bh(&vsi->mac_filter_list_lock); - if (!failed_count) { - dev_info(&pf->pdev->dev, - "filter logjam cleared on %s, leaving overflow promiscuous mode\n", - vsi_name); - clear_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state); - promisc_changed = true; - vsi->promisc_threshold = 0; - } + dev_info(&pf->pdev->dev, + "filter logjam cleared on %s, leaving overflow promiscuous mode\n", + vsi_name); + clear_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state); + promisc_changed = true; + vsi->promisc_threshold = 0; } /* if the VF is not trusted do not do promisc */ @@ -2201,6 +2436,18 @@ out: clear_bit(__I40E_CONFIG_BUSY, &vsi->state); return retval; + +err_no_memory: + /* Restore elements on the temporary add and delete lists */ + spin_lock_bh(&vsi->mac_filter_hash_lock); +err_no_memory_locked: + i40e_undo_del_filter_entries(vsi, &tmp_del_list); + i40e_undo_add_filter_entries(vsi, &tmp_add_list); + spin_unlock_bh(&vsi->mac_filter_hash_lock); + + vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED; + clear_bit(__I40E_CONFIG_BUSY, &vsi->state); + return -ENOMEM; } /** @@ -2239,13 +2486,8 @@ static void i40e_sync_filters_subtask(struct i40e_pf *pf) static int i40e_change_mtu(struct net_device *netdev, int new_mtu) { struct i40e_netdev_priv *np = netdev_priv(netdev); - int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; struct i40e_vsi *vsi = np->vsi; - /* MTU < 68 is an error and causes problems on some kernels */ - if ((new_mtu < 68) || (max_frame > I40E_MAX_RXBUFFER)) - return -EINVAL; - netdev_info(netdev, "changing MTU from %d to %d\n", netdev->mtu, new_mtu); netdev->mtu = new_mtu; @@ -2354,88 +2596,57 @@ static void i40e_vlan_rx_register(struct net_device *netdev, u32 features) } /** - * i40e_vsi_add_vlan - Add vsi membership for given vlan + * i40e_add_vlan_all_mac - Add a MAC/VLAN filter for each existing MAC address * @vsi: the vsi being configured * @vid: vlan id to be added (0 = untagged only , -1 = any) + * + * This is a helper function for adding a new MAC/VLAN filter with the + * specified VLAN for each existing MAC address already in the hash table. + * This function does *not* perform any accounting to update filters based on + * VLAN mode. + * + * NOTE: this function expects to be called while under the + * mac_filter_hash_lock **/ -int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid) +int i40e_add_vlan_all_mac(struct i40e_vsi *vsi, s16 vid) { - struct i40e_mac_filter *f, *ftmp, *add_f; - bool is_netdev, is_vf; - - is_vf = (vsi->type == I40E_VSI_SRIOV); - is_netdev = !!(vsi->netdev); - - /* Locked once because all functions invoked below iterates list*/ - spin_lock_bh(&vsi->mac_filter_list_lock); - - if (is_netdev) { - add_f = i40e_add_filter(vsi, vsi->netdev->dev_addr, vid, - is_vf, is_netdev); - if (!add_f) { - dev_info(&vsi->back->pdev->dev, - "Could not add vlan filter %d for %pM\n", - vid, vsi->netdev->dev_addr); - spin_unlock_bh(&vsi->mac_filter_list_lock); - return -ENOMEM; - } - } + struct i40e_mac_filter *f, *add_f; + struct hlist_node *h; + int bkt; - list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) { - add_f = i40e_add_filter(vsi, f->macaddr, vid, is_vf, is_netdev); + hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { + if (f->state == I40E_FILTER_REMOVE) + continue; + add_f = i40e_add_filter(vsi, f->macaddr, vid); if (!add_f) { dev_info(&vsi->back->pdev->dev, "Could not add vlan filter %d for %pM\n", vid, f->macaddr); - spin_unlock_bh(&vsi->mac_filter_list_lock); return -ENOMEM; } } - /* Now if we add a vlan tag, make sure to check if it is the first - * tag (i.e. a "tag" -1 does exist) and if so replace the -1 "tag" - * with 0, so we now accept untagged and specified tagged traffic - * (and not all tags along with untagged) - */ - if (vid > 0) { - if (is_netdev && i40e_find_filter(vsi, vsi->netdev->dev_addr, - I40E_VLAN_ANY, - is_vf, is_netdev)) { - i40e_del_filter(vsi, vsi->netdev->dev_addr, - I40E_VLAN_ANY, is_vf, is_netdev); - add_f = i40e_add_filter(vsi, vsi->netdev->dev_addr, 0, - is_vf, is_netdev); - if (!add_f) { - dev_info(&vsi->back->pdev->dev, - "Could not add filter 0 for %pM\n", - vsi->netdev->dev_addr); - spin_unlock_bh(&vsi->mac_filter_list_lock); - return -ENOMEM; - } - } - } + return 0; +} - /* Do not assume that I40E_VLAN_ANY should be reset to VLAN 0 */ - if (vid > 0 && !vsi->info.pvid) { - list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) { - if (!i40e_find_filter(vsi, f->macaddr, I40E_VLAN_ANY, - is_vf, is_netdev)) - continue; - i40e_del_filter(vsi, f->macaddr, I40E_VLAN_ANY, - is_vf, is_netdev); - add_f = i40e_add_filter(vsi, f->macaddr, - 0, is_vf, is_netdev); - if (!add_f) { - dev_info(&vsi->back->pdev->dev, - "Could not add filter 0 for %pM\n", - f->macaddr); - spin_unlock_bh(&vsi->mac_filter_list_lock); - return -ENOMEM; - } - } - } +/** + * i40e_vsi_add_vlan - Add VSI membership for given VLAN + * @vsi: the VSI being configured + * @vid: VLAN id to be added + **/ +int i40e_vsi_add_vlan(struct i40e_vsi *vsi, u16 vid) +{ + int err; - spin_unlock_bh(&vsi->mac_filter_list_lock); + if (!vid || vsi->info.pvid) + return -EINVAL; + + /* Locked once because all functions invoked below iterates list*/ + spin_lock_bh(&vsi->mac_filter_hash_lock); + err = i40e_add_vlan_all_mac(vsi, vid); + spin_unlock_bh(&vsi->mac_filter_hash_lock); + if (err) + return err; /* schedule our worker thread which will take care of * applying the new filter changes @@ -2445,82 +2656,48 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid) } /** - * i40e_vsi_kill_vlan - Remove vsi membership for given vlan + * i40e_rm_vlan_all_mac - Remove MAC/VLAN pair for all MAC with the given VLAN * @vsi: the vsi being configured * @vid: vlan id to be removed (0 = untagged only , -1 = any) * - * Return: 0 on success or negative otherwise - **/ -int i40e_vsi_kill_vlan(struct i40e_vsi *vsi, s16 vid) + * This function should be used to remove all VLAN filters which match the + * given VID. It does not schedule the service event and does not take the + * mac_filter_hash_lock so it may be combined with other operations under + * a single invocation of the mac_filter_hash_lock. + * + * NOTE: this function expects to be called while under the + * mac_filter_hash_lock + */ +void i40e_rm_vlan_all_mac(struct i40e_vsi *vsi, s16 vid) { - struct net_device *netdev = vsi->netdev; - struct i40e_mac_filter *f, *ftmp, *add_f; - bool is_vf, is_netdev; - int filter_count = 0; - - is_vf = (vsi->type == I40E_VSI_SRIOV); - is_netdev = !!(netdev); - - /* Locked once because all functions invoked below iterates list */ - spin_lock_bh(&vsi->mac_filter_list_lock); - - if (is_netdev) - i40e_del_filter(vsi, netdev->dev_addr, vid, is_vf, is_netdev); - - list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) - i40e_del_filter(vsi, f->macaddr, vid, is_vf, is_netdev); - - /* go through all the filters for this VSI and if there is only - * vid == 0 it means there are no other filters, so vid 0 must - * be replaced with -1. This signifies that we should from now - * on accept any traffic (with any tag present, or untagged) - */ - list_for_each_entry(f, &vsi->mac_filter_list, list) { - if (is_netdev) { - if (f->vlan && - ether_addr_equal(netdev->dev_addr, f->macaddr)) - filter_count++; - } - - if (f->vlan) - filter_count++; - } + struct i40e_mac_filter *f; + struct hlist_node *h; + int bkt; - if (!filter_count && is_netdev) { - i40e_del_filter(vsi, netdev->dev_addr, 0, is_vf, is_netdev); - f = i40e_add_filter(vsi, netdev->dev_addr, I40E_VLAN_ANY, - is_vf, is_netdev); - if (!f) { - dev_info(&vsi->back->pdev->dev, - "Could not add filter %d for %pM\n", - I40E_VLAN_ANY, netdev->dev_addr); - spin_unlock_bh(&vsi->mac_filter_list_lock); - return -ENOMEM; - } + hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { + if (f->vlan == vid) + __i40e_del_filter(vsi, f); } +} - if (!filter_count) { - list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) { - i40e_del_filter(vsi, f->macaddr, 0, is_vf, is_netdev); - add_f = i40e_add_filter(vsi, f->macaddr, I40E_VLAN_ANY, - is_vf, is_netdev); - if (!add_f) { - dev_info(&vsi->back->pdev->dev, - "Could not add filter %d for %pM\n", - I40E_VLAN_ANY, f->macaddr); - spin_unlock_bh(&vsi->mac_filter_list_lock); - return -ENOMEM; - } - } - } +/** + * i40e_vsi_kill_vlan - Remove VSI membership for given VLAN + * @vsi: the VSI being configured + * @vid: VLAN id to be removed + **/ +void i40e_vsi_kill_vlan(struct i40e_vsi *vsi, u16 vid) +{ + if (!vid || vsi->info.pvid) + return; - spin_unlock_bh(&vsi->mac_filter_list_lock); + spin_lock_bh(&vsi->mac_filter_hash_lock); + i40e_rm_vlan_all_mac(vsi, vid); + spin_unlock_bh(&vsi->mac_filter_hash_lock); /* schedule our worker thread which will take care of * applying the new filter changes */ i40e_service_event_schedule(vsi->back); - return 0; } /** @@ -2542,7 +2719,7 @@ static int i40e_vlan_rx_add_vid(struct net_device *netdev, struct i40e_vsi *vsi = np->vsi; int ret = 0; - if (vid > 4095) + if (vid >= VLAN_N_VID) return -EINVAL; /* If the network stack called us with vid = 0 then @@ -2554,7 +2731,7 @@ static int i40e_vlan_rx_add_vid(struct net_device *netdev, if (vid) ret = i40e_vsi_add_vlan(vsi, vid); - if (!ret && (vid < VLAN_N_VID)) + if (!ret) set_bit(vid, vsi->active_vlans); return ret; @@ -3159,7 +3336,7 @@ static void i40e_vsi_configure_msix(struct i40e_vsi *vsi) wr32(hw, I40E_PFINT_ITRN(I40E_TX_ITR, vector - 1), q_vector->tx.itr); wr32(hw, I40E_PFINT_RATEN(vector - 1), - INTRL_USEC_TO_REG(vsi->int_rate_limit)); + i40e_intrl_usec_to_reg(vsi->int_rate_limit)); /* Linked list for the queuepairs assigned to this vector */ wr32(hw, I40E_PFINT_LNKLSTN(vector - 1), qp); @@ -3322,6 +3499,33 @@ static irqreturn_t i40e_msix_clean_rings(int irq, void *data) } /** + * i40e_irq_affinity_notify - Callback for affinity changes + * @notify: context as to what irq was changed + * @mask: the new affinity mask + * + * This is a callback function used by the irq_set_affinity_notifier function + * so that we may register to receive changes to the irq affinity masks. + **/ +static void i40e_irq_affinity_notify(struct irq_affinity_notify *notify, + const cpumask_t *mask) +{ + struct i40e_q_vector *q_vector = + container_of(notify, struct i40e_q_vector, affinity_notify); + + q_vector->affinity_mask = *mask; +} + +/** + * i40e_irq_affinity_release - Callback for affinity notifier release + * @ref: internal core kernel usage + * + * This is a callback function used by the irq_set_affinity_notifier function + * to inform the current notification subscriber that they will no longer + * receive notifications. + **/ +static void i40e_irq_affinity_release(struct kref *ref) {} + +/** * i40e_vsi_request_irq_msix - Initialize MSI-X interrupts * @vsi: the VSI being configured * @basename: name for the vector @@ -3336,10 +3540,13 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename) int rx_int_idx = 0; int tx_int_idx = 0; int vector, err; + int irq_num; for (vector = 0; vector < q_vectors; vector++) { struct i40e_q_vector *q_vector = vsi->q_vectors[vector]; + irq_num = pf->msix_entries[base + vector].vector; + if (q_vector->tx.ring && q_vector->rx.ring) { snprintf(q_vector->name, sizeof(q_vector->name) - 1, "%s-%s-%d", basename, "TxRx", rx_int_idx++); @@ -3354,7 +3561,7 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename) /* skip this unused q_vector */ continue; } - err = request_irq(pf->msix_entries[base + vector].vector, + err = request_irq(irq_num, vsi->irq_handler, 0, q_vector->name, @@ -3364,9 +3571,13 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename) "MSIX request_irq failed, error: %d\n", err); goto free_queue_irqs; } + + /* register for affinity change notifications */ + q_vector->affinity_notify.notify = i40e_irq_affinity_notify; + q_vector->affinity_notify.release = i40e_irq_affinity_release; + irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify); /* assign the mask for this irq */ - irq_set_affinity_hint(pf->msix_entries[base + vector].vector, - &q_vector->affinity_mask); + irq_set_affinity_hint(irq_num, &q_vector->affinity_mask); } vsi->irqs_ready = true; @@ -3375,10 +3586,10 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename) free_queue_irqs: while (vector) { vector--; - irq_set_affinity_hint(pf->msix_entries[base + vector].vector, - NULL); - free_irq(pf->msix_entries[base + vector].vector, - &(vsi->q_vectors[vector])); + irq_num = pf->msix_entries[base + vector].vector; + irq_set_affinity_notifier(irq_num, NULL); + irq_set_affinity_hint(irq_num, NULL); + free_irq(irq_num, &vsi->q_vectors[vector]); } return err; } @@ -3480,7 +3691,7 @@ static irqreturn_t i40e_intr(int irq, void *data) (ena_mask & I40E_PFINT_ICR0_ENA_PE_CRITERR_MASK)) { ena_mask &= ~I40E_PFINT_ICR0_ENA_PE_CRITERR_MASK; icr0 &= ~I40E_PFINT_ICR0_ENA_PE_CRITERR_MASK; - dev_info(&pf->pdev->dev, "cleared PE_CRITERR\n"); + dev_dbg(&pf->pdev->dev, "cleared PE_CRITERR\n"); } /* only q0 is used in MSI/Legacy mode, and none are used in MSIX */ @@ -3973,30 +4184,36 @@ static int i40e_vsi_control_rx(struct i40e_vsi *vsi, bool enable) } /** - * i40e_vsi_control_rings - Start or stop a VSI's rings + * i40e_vsi_start_rings - Start a VSI's rings * @vsi: the VSI being configured - * @enable: start or stop the rings **/ -int i40e_vsi_control_rings(struct i40e_vsi *vsi, bool request) +int i40e_vsi_start_rings(struct i40e_vsi *vsi) { int ret = 0; /* do rx first for enable and last for disable */ - if (request) { - ret = i40e_vsi_control_rx(vsi, request); - if (ret) - return ret; - ret = i40e_vsi_control_tx(vsi, request); - } else { - /* Ignore return value, we need to shutdown whatever we can */ - i40e_vsi_control_tx(vsi, request); - i40e_vsi_control_rx(vsi, request); - } + ret = i40e_vsi_control_rx(vsi, true); + if (ret) + return ret; + ret = i40e_vsi_control_tx(vsi, true); return ret; } /** + * i40e_vsi_stop_rings - Stop a VSI's rings + * @vsi: the VSI being configured + **/ +void i40e_vsi_stop_rings(struct i40e_vsi *vsi) +{ + /* do rx first for enable and last for disable + * Ignore return value, we need to shutdown whatever we can + */ + i40e_vsi_control_tx(vsi, false); + i40e_vsi_control_rx(vsi, false); +} + +/** * i40e_vsi_free_irq - Free the irq association with the OS * @vsi: the VSI being configured **/ @@ -4017,19 +4234,23 @@ static void i40e_vsi_free_irq(struct i40e_vsi *vsi) vsi->irqs_ready = false; for (i = 0; i < vsi->num_q_vectors; i++) { - u16 vector = i + base; + int irq_num; + u16 vector; + + vector = i + base; + irq_num = pf->msix_entries[vector].vector; /* free only the irqs that were actually requested */ if (!vsi->q_vectors[i] || !vsi->q_vectors[i]->num_ringpairs) continue; + /* clear the affinity notifier in the IRQ descriptor */ + irq_set_affinity_notifier(irq_num, NULL); /* clear the affinity_mask in the IRQ descriptor */ - irq_set_affinity_hint(pf->msix_entries[vector].vector, - NULL); - synchronize_irq(pf->msix_entries[vector].vector); - free_irq(pf->msix_entries[vector].vector, - vsi->q_vectors[i]); + irq_set_affinity_hint(irq_num, NULL); + synchronize_irq(irq_num); + free_irq(irq_num, vsi->q_vectors[i]); /* Tear down the interrupt queue link list * @@ -4464,8 +4685,10 @@ static void i40e_detect_recover_hung_queue(int q_idx, struct i40e_vsi *vsi) */ if ((!tx_pending_hw) && i40e_get_tx_pending(tx_ring, true) && (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK))) { + local_bh_disable(); if (napi_reschedule(&tx_ring->q_vector->napi)) tx_ring->tx_stats.tx_lost_interrupt++; + local_bh_enable(); } } @@ -5116,12 +5339,18 @@ out: */ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup) { + enum i40e_aq_link_speed new_speed; char *speed = "Unknown"; char *fc = "Unknown"; + char *fec = ""; + char *an = ""; - if (vsi->current_isup == isup) + new_speed = vsi->back->hw.phy.link_info.link_speed; + + if ((vsi->current_isup == isup) && (vsi->current_speed == new_speed)) return; vsi->current_isup = isup; + vsi->current_speed = new_speed; if (!isup) { netdev_info(vsi->netdev, "NIC Link is Down\n"); return; @@ -5143,6 +5372,9 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup) case I40E_LINK_SPEED_20GB: speed = "20 G"; break; + case I40E_LINK_SPEED_25GB: + speed = "25 G"; + break; case I40E_LINK_SPEED_10GB: speed = "10 G"; break; @@ -5171,8 +5403,23 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup) break; } - netdev_info(vsi->netdev, "NIC Link is Up %sbps Full Duplex, Flow Control: %s\n", - speed, fc); + if (vsi->back->hw.phy.link_info.link_speed == I40E_LINK_SPEED_25GB) { + fec = ", FEC: None"; + an = ", Autoneg: False"; + + if (vsi->back->hw.phy.link_info.an_info & I40E_AQ_AN_COMPLETED) + an = ", Autoneg: True"; + + if (vsi->back->hw.phy.link_info.fec_info & + I40E_AQ_CONFIG_FEC_KR_ENA) + fec = ", FEC: CL74 FC-FEC/BASE-R"; + else if (vsi->back->hw.phy.link_info.fec_info & + I40E_AQ_CONFIG_FEC_RS_ENA) + fec = ", FEC: CL108 RS-FEC"; + } + + netdev_info(vsi->netdev, "NIC Link is Up, %sbps Full Duplex%s%s, Flow Control: %s\n", + speed, fec, an, fc); } /** @@ -5190,7 +5437,7 @@ static int i40e_up_complete(struct i40e_vsi *vsi) i40e_configure_msi_and_legacy(vsi); /* start rings */ - err = i40e_vsi_control_rings(vsi, true); + err = i40e_vsi_start_rings(vsi); if (err) return err; @@ -5287,7 +5534,7 @@ void i40e_down(struct i40e_vsi *vsi) netif_tx_disable(vsi->netdev); } i40e_vsi_disable_irq(vsi); - i40e_vsi_control_rings(vsi, false); + i40e_vsi_stop_rings(vsi); i40e_napi_disable_all(vsi); for (i = 0; i < vsi->num_queue_pairs; i++) { @@ -5833,19 +6080,6 @@ static void i40e_handle_lan_overflow_event(struct i40e_pf *pf, } /** - * i40e_service_event_complete - Finish up the service event - * @pf: board private structure - **/ -static void i40e_service_event_complete(struct i40e_pf *pf) -{ - WARN_ON(!test_bit(__I40E_SERVICE_SCHED, &pf->state)); - - /* flush memory to make sure state is correct before next watchog */ - smp_mb__before_atomic(); - clear_bit(__I40E_SERVICE_SCHED, &pf->state); -} - -/** * i40e_get_cur_guaranteed_fd_count - Get the consumed guaranteed FD filters * @pf: board private structure **/ @@ -6120,7 +6354,16 @@ static void i40e_link_event(struct i40e_pf *pf) old_link = (pf->hw.phy.link_info_old.link_info & I40E_AQ_LINK_UP); status = i40e_get_link_status(&pf->hw, &new_link); - if (status) { + + /* On success, disable temp link polling */ + if (status == I40E_SUCCESS) { + if (pf->flags & I40E_FLAG_TEMP_LINK_POLLING) + pf->flags &= ~I40E_FLAG_TEMP_LINK_POLLING; + } else { + /* Enable link polling temporarily until i40e_get_link_status + * returns I40E_SUCCESS + */ + pf->flags |= I40E_FLAG_TEMP_LINK_POLLING; dev_dbg(&pf->pdev->dev, "couldn't get link state, status: %d\n", status); return; @@ -6172,7 +6415,8 @@ static void i40e_watchdog_subtask(struct i40e_pf *pf) return; pf->service_timer_previous = jiffies; - if (pf->flags & I40E_FLAG_LINK_POLLING_ENABLED) + if ((pf->flags & I40E_FLAG_LINK_POLLING_ENABLED) || + (pf->flags & I40E_FLAG_TEMP_LINK_POLLING)) i40e_link_event(pf); /* Update the stats for active netdevs so the network stack @@ -6670,7 +6914,6 @@ static int i40e_vsi_clear(struct i40e_vsi *vsi); static void i40e_fdir_sb_setup(struct i40e_pf *pf) { struct i40e_vsi *vsi; - int i; /* quick workaround for an NVM issue that leaves a critical register * uninitialized @@ -6681,6 +6924,7 @@ static void i40e_fdir_sb_setup(struct i40e_pf *pf) 0xeacb7d61, 0xaa4f05b6, 0x9c5c89ed, 0xfc425ddb, 0xa4654832, 0xfc7461d4, 0x8f827619, 0xf5c63c21, 0x95b3a76d}; + int i; for (i = 0; i <= I40E_GLQF_HKEY_MAX_INDEX; i++) wr32(&pf->hw, I40E_GLQF_HKEY(i), hkey[i]); @@ -6690,13 +6934,7 @@ static void i40e_fdir_sb_setup(struct i40e_pf *pf) return; /* find existing VSI and see if it needs configuring */ - vsi = NULL; - for (i = 0; i < pf->num_alloc_vsi; i++) { - if (pf->vsi[i] && pf->vsi[i]->type == I40E_VSI_FDIR) { - vsi = pf->vsi[i]; - break; - } - } + vsi = i40e_find_vsi_by_type(pf, I40E_VSI_FDIR); /* create a new VSI if none exists */ if (!vsi) { @@ -6718,15 +6956,12 @@ static void i40e_fdir_sb_setup(struct i40e_pf *pf) **/ static void i40e_fdir_teardown(struct i40e_pf *pf) { - int i; + struct i40e_vsi *vsi; i40e_fdir_filter_exit(pf); - for (i = 0; i < pf->num_alloc_vsi; i++) { - if (pf->vsi[i] && pf->vsi[i]->type == I40E_VSI_FDIR) { - i40e_vsi_release(pf->vsi[i]); - break; - } - } + vsi = i40e_find_vsi_by_type(pf, I40E_VSI_FDIR); + if (vsi) + i40e_vsi_release(vsi); } /** @@ -7163,10 +7398,12 @@ static void i40e_service_task(struct work_struct *work) /* don't bother with service tasks if a reset is in progress */ if (test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state)) { - i40e_service_event_complete(pf); return; } + if (test_and_set_bit(__I40E_SERVICE_SCHED, &pf->state)) + return; + i40e_detect_recover_hung(pf); i40e_sync_filters_subtask(pf); i40e_reset_subtask(pf); @@ -7179,7 +7416,9 @@ static void i40e_service_task(struct work_struct *work) i40e_sync_udp_filters_subtask(pf); i40e_clean_adminq_subtask(pf); - i40e_service_event_complete(pf); + /* flush memory to make sure state is correct before next watchdog */ + smp_mb__before_atomic(); + clear_bit(__I40E_SERVICE_SCHED, &pf->state); /* If the tasks have taken longer than one timer cycle or there * is more work to be done, reschedule the service task now @@ -7354,7 +7593,7 @@ static int i40e_vsi_mem_alloc(struct i40e_pf *pf, enum i40e_vsi_type type) pf->rss_table_size : 64; vsi->netdev_registered = false; vsi->work_limit = I40E_DEFAULT_IRQ_WORK; - INIT_LIST_HEAD(&vsi->mac_filter_list); + hash_init(vsi->mac_filter_hash); vsi->irqs_ready = false; ret = i40e_set_num_rings_in_vsi(vsi); @@ -7369,7 +7608,7 @@ static int i40e_vsi_mem_alloc(struct i40e_pf *pf, enum i40e_vsi_type type) i40e_vsi_setup_irqhandler(vsi, i40e_msix_clean_rings); /* Initialize VSI lock */ - spin_lock_init(&vsi->mac_filter_list_lock); + spin_lock_init(&vsi->mac_filter_hash_lock); pf->vsi[vsi_idx] = vsi; ret = vsi_idx; goto unlock_pf; @@ -8345,8 +8584,8 @@ int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count) i40e_pf_config_rss(pf); } - dev_info(&pf->pdev->dev, "RSS count/HW max RSS count: %d/%d\n", - pf->alloc_rss_size, pf->rss_size_max); + dev_info(&pf->pdev->dev, "User requested queue count/HW max RSS count: %d/%d\n", + vsi->req_queue_pairs, pf->rss_size_max); return pf->alloc_rss_size; } @@ -8489,15 +8728,6 @@ static int i40e_sw_init(struct i40e_pf *pf) int err = 0; int size; - pf->msg_enable = netif_msg_init(I40E_DEFAULT_MSG_ENABLE, - (NETIF_MSG_DRV|NETIF_MSG_PROBE|NETIF_MSG_LINK)); - if (debug != -1 && debug != I40E_DEFAULT_MSG_ENABLE) { - if (I40E_DEBUG_USER & debug) - pf->hw.debug_mask = debug; - pf->msg_enable = netif_msg_init((debug & ~I40E_DEBUG_USER), - I40E_DEFAULT_MSG_ENABLE); - } - /* Set default capability flags */ pf->flags = I40E_FLAG_RX_CSUM_ENABLED | I40E_FLAG_MSI_ENABLED | @@ -8551,7 +8781,7 @@ static int i40e_sw_init(struct i40e_pf *pf) pf->hw.func_caps.fd_filters_best_effort; } - if (i40e_is_mac_710(&pf->hw) && + if ((pf->hw.mac.type == I40E_MAC_XL710) && (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver < 33)) || (pf->hw.aq.fw_maj_ver < 4))) { pf->flags |= I40E_FLAG_RESTART_AUTONEG; @@ -8560,13 +8790,13 @@ static int i40e_sw_init(struct i40e_pf *pf) } /* Disable FW LLDP if FW < v4.3 */ - if (i40e_is_mac_710(&pf->hw) && + if ((pf->hw.mac.type == I40E_MAC_XL710) && (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver < 3)) || (pf->hw.aq.fw_maj_ver < 4))) pf->flags |= I40E_FLAG_STOP_FW_LLDP; /* Use the FW Set LLDP MIB API if FW > v4.40 */ - if (i40e_is_mac_710(&pf->hw) && + if ((pf->hw.mac.type == I40E_MAC_XL710) && (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver >= 40)) || (pf->hw.aq.fw_maj_ver >= 5))) pf->flags |= I40E_FLAG_USE_SET_LLDP_MIB; @@ -8597,15 +8827,17 @@ static int i40e_sw_init(struct i40e_pf *pf) } #endif /* CONFIG_PCI_IOV */ if (pf->hw.mac.type == I40E_MAC_X722) { - pf->flags |= I40E_FLAG_RSS_AQ_CAPABLE | - I40E_FLAG_128_QP_RSS_CAPABLE | - I40E_FLAG_HW_ATR_EVICT_CAPABLE | - I40E_FLAG_OUTER_UDP_CSUM_CAPABLE | - I40E_FLAG_WB_ON_ITR_CAPABLE | - I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE | - I40E_FLAG_NO_PCI_LINK_CHECK | - I40E_FLAG_USE_SET_LLDP_MIB | - I40E_FLAG_GENEVE_OFFLOAD_CAPABLE; + pf->flags |= I40E_FLAG_RSS_AQ_CAPABLE + | I40E_FLAG_128_QP_RSS_CAPABLE + | I40E_FLAG_HW_ATR_EVICT_CAPABLE + | I40E_FLAG_OUTER_UDP_CSUM_CAPABLE + | I40E_FLAG_WB_ON_ITR_CAPABLE + | I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE + | I40E_FLAG_NO_PCI_LINK_CHECK + | I40E_FLAG_USE_SET_LLDP_MIB + | I40E_FLAG_GENEVE_OFFLOAD_CAPABLE + | I40E_FLAG_PTP_L4_CAPABLE + | I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE; } else if ((pf->hw.aq.api_maj_ver > 1) || ((pf->hw.aq.api_maj_ver == 1) && (pf->hw.aq.api_min_ver > 4))) { @@ -9037,10 +9269,6 @@ static int i40e_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, 0, 0, nlflags, filter_mask, NULL); } -/* Hardware supports L4 tunnel length of 128B (=2^7) which includes - * inner mac plus all inner ethertypes. - */ -#define I40E_MAX_TUNNEL_HDR_LEN 128 /** * i40e_features_check - Validate encapsulated packet conforms to limits * @skb: skb buff @@ -9051,12 +9279,52 @@ static netdev_features_t i40e_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features) { - if (skb->encapsulation && - ((skb_inner_network_header(skb) - skb_transport_header(skb)) > - I40E_MAX_TUNNEL_HDR_LEN)) - return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); + size_t len; + + /* No point in doing any of this if neither checksum nor GSO are + * being requested for this frame. We can rule out both by just + * checking for CHECKSUM_PARTIAL + */ + if (skb->ip_summed != CHECKSUM_PARTIAL) + return features; + + /* We cannot support GSO if the MSS is going to be less than + * 64 bytes. If it is then we need to drop support for GSO. + */ + if (skb_is_gso(skb) && (skb_shinfo(skb)->gso_size < 64)) + features &= ~NETIF_F_GSO_MASK; + + /* MACLEN can support at most 63 words */ + len = skb_network_header(skb) - skb->data; + if (len & ~(63 * 2)) + goto out_err; + + /* IPLEN and EIPLEN can support at most 127 dwords */ + len = skb_transport_header(skb) - skb_network_header(skb); + if (len & ~(127 * 4)) + goto out_err; + + if (skb->encapsulation) { + /* L4TUNLEN can support 127 words */ + len = skb_inner_network_header(skb) - skb_transport_header(skb); + if (len & ~(127 * 2)) + goto out_err; + + /* IPLEN can support at most 127 dwords */ + len = skb_inner_transport_header(skb) - + skb_inner_network_header(skb); + if (len & ~(127 * 4)) + goto out_err; + } + + /* No need to validate L4LEN as TCP is the only protocol with a + * a flexible value and we support all possible values supported + * by TCP, which is at most 15 dwords + */ return features; +out_err: + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); } static const struct net_device_ops i40e_netdev_ops = { @@ -9109,6 +9377,7 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) struct i40e_hw *hw = &pf->hw; struct i40e_netdev_priv *np; struct net_device *netdev; + u8 broadcast[ETH_ALEN]; u8 mac_addr[ETH_ALEN]; int etherdev_size; @@ -9169,20 +9438,38 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) * which must be replaced by a normal filter. */ i40e_rm_default_mac_filter(vsi, mac_addr); - spin_lock_bh(&vsi->mac_filter_list_lock); - i40e_add_filter(vsi, mac_addr, I40E_VLAN_ANY, false, true); - spin_unlock_bh(&vsi->mac_filter_list_lock); + spin_lock_bh(&vsi->mac_filter_hash_lock); + i40e_add_mac_filter(vsi, mac_addr); + spin_unlock_bh(&vsi->mac_filter_hash_lock); } else { /* relate the VSI_VMDQ name to the VSI_MAIN name */ snprintf(netdev->name, IFNAMSIZ, "%sv%%d", pf->vsi[pf->lan_vsi]->netdev->name); random_ether_addr(mac_addr); - spin_lock_bh(&vsi->mac_filter_list_lock); - i40e_add_filter(vsi, mac_addr, I40E_VLAN_ANY, false, false); - spin_unlock_bh(&vsi->mac_filter_list_lock); + spin_lock_bh(&vsi->mac_filter_hash_lock); + i40e_add_mac_filter(vsi, mac_addr); + spin_unlock_bh(&vsi->mac_filter_hash_lock); } + /* Add the broadcast filter so that we initially will receive + * broadcast packets. Note that when a new VLAN is first added the + * driver will convert all filters marked I40E_VLAN_ANY into VLAN + * specific filters as part of transitioning into "vlan" operation. + * When more VLANs are added, the driver will copy each existing MAC + * filter and add it for the new VLAN. + * + * Broadcast filters are handled specially by + * i40e_sync_filters_subtask, as the driver must to set the broadcast + * promiscuous bit instead of adding this directly as a MAC/VLAN + * filter. The subtask will update the correct broadcast promiscuous + * bits as VLANs become active or inactive. + */ + eth_broadcast_addr(broadcast); + spin_lock_bh(&vsi->mac_filter_hash_lock); + i40e_add_mac_filter(vsi, broadcast); + spin_unlock_bh(&vsi->mac_filter_hash_lock); + ether_addr_copy(netdev->dev_addr, mac_addr); ether_addr_copy(netdev->perm_addr, mac_addr); @@ -9198,6 +9485,11 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) i40e_fcoe_config_netdev(netdev, vsi); #endif + /* MTU range: 68 - 9706 */ + netdev->min_mtu = ETH_MIN_MTU; + netdev->max_mtu = I40E_MAX_RXBUFFER - + (ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN); + return 0; } @@ -9260,11 +9552,12 @@ int i40e_is_vsi_uplink_mode_veb(struct i40e_vsi *vsi) static int i40e_add_vsi(struct i40e_vsi *vsi) { int ret = -ENODEV; - i40e_status aq_ret = 0; struct i40e_pf *pf = vsi->back; struct i40e_hw *hw = &pf->hw; struct i40e_vsi_context ctxt; - struct i40e_mac_filter *f, *ftmp; + struct i40e_mac_filter *f; + struct hlist_node *h; + int bkt; u8 enabled_tc = 0x1; /* TC0 enabled */ int f_count = 0; @@ -9448,28 +9741,16 @@ static int i40e_add_vsi(struct i40e_vsi *vsi) vsi->seid = ctxt.seid; vsi->id = ctxt.vsi_number; } - /* Except FDIR VSI, for all othet VSI set the broadcast filter */ - if (vsi->type != I40E_VSI_FDIR) { - aq_ret = i40e_aq_set_vsi_broadcast(hw, vsi->seid, true, NULL); - if (aq_ret) { - ret = i40e_aq_rc_to_posix(aq_ret, - hw->aq.asq_last_status); - dev_info(&pf->pdev->dev, - "set brdcast promisc failed, err %s, aq_err %s\n", - i40e_stat_str(hw, aq_ret), - i40e_aq_str(hw, hw->aq.asq_last_status)); - } - } vsi->active_filters = 0; clear_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state); - spin_lock_bh(&vsi->mac_filter_list_lock); + spin_lock_bh(&vsi->mac_filter_hash_lock); /* If macvlan filters already exist, force them to get loaded */ - list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) { + hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { f->state = I40E_FILTER_NEW; f_count++; } - spin_unlock_bh(&vsi->mac_filter_list_lock); + spin_unlock_bh(&vsi->mac_filter_hash_lock); if (f_count) { vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED; @@ -9499,11 +9780,12 @@ err: **/ int i40e_vsi_release(struct i40e_vsi *vsi) { - struct i40e_mac_filter *f, *ftmp; + struct i40e_mac_filter *f; + struct hlist_node *h; struct i40e_veb *veb = NULL; struct i40e_pf *pf; u16 uplink_seid; - int i, n; + int i, n, bkt; pf = vsi->back; @@ -9533,11 +9815,19 @@ int i40e_vsi_release(struct i40e_vsi *vsi) i40e_vsi_disable_irq(vsi); } - spin_lock_bh(&vsi->mac_filter_list_lock); - list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) - i40e_del_filter(vsi, f->macaddr, f->vlan, - f->is_vf, f->is_netdev); - spin_unlock_bh(&vsi->mac_filter_list_lock); + spin_lock_bh(&vsi->mac_filter_hash_lock); + + /* clear the sync flag on all filters */ + if (vsi->netdev) { + __dev_uc_unsync(vsi->netdev, NULL); + __dev_mc_unsync(vsi->netdev, NULL); + } + + /* make sure any remaining filters are marked for deletion */ + hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) + __i40e_del_filter(vsi, f); + + spin_unlock_bh(&vsi->mac_filter_hash_lock); i40e_sync_vsi_filters(vsi); @@ -10483,7 +10773,6 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit) i40e_pf_config_rss(pf); /* fill in link information and enable LSE reporting */ - i40e_update_link_info(&pf->hw); i40e_link_event(pf); /* Initialize user-specific link properties */ @@ -10798,6 +11087,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw->subsystem_device_id = pdev->subsystem_device; hw->bus.device = PCI_SLOT(pdev->devfn); hw->bus.func = PCI_FUNC(pdev->devfn); + hw->bus.bus_id = pdev->bus->number; pf->instance = pfs_found; /* set up the locks for the AQ, do this only once in probe @@ -10806,10 +11096,12 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) mutex_init(&hw->aq.asq_mutex); mutex_init(&hw->aq.arq_mutex); - if (debug != -1) { - pf->msg_enable = pf->hw.debug_mask; - pf->msg_enable = debug; - } + pf->msg_enable = netif_msg_init(debug, + NETIF_MSG_DRV | + NETIF_MSG_PROBE | + NETIF_MSG_LINK); + if (debug < -1) + pf->hw.debug_mask = debug; /* do a special CORER for clearing PXE mode once at init */ if (hw->revision_id == 0 && @@ -10951,7 +11243,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = i40e_init_pf_dcb(pf); if (err) { dev_info(&pdev->dev, "DCB init failed %d, disabled\n", err); - pf->flags &= ~(I40E_FLAG_DCB_CAPABLE & I40E_FLAG_DCB_ENABLED); + pf->flags &= ~(I40E_FLAG_DCB_CAPABLE | I40E_FLAG_DCB_ENABLED); /* Continue without DCB enabled */ } #endif /* CONFIG_I40E_DCB */ @@ -11209,7 +11501,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) dev_dbg(&pf->pdev->dev, "get supported phy types ret = %s last_status = %s\n", i40e_stat_str(&pf->hw, err), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); - pf->hw.phy.phy_types = le32_to_cpu(abilities.phy_type); /* Add a filter to drop all Flow control frames from any VSI from being * transmitted. By doing so we stop a malicious VF from sending out @@ -11221,9 +11512,10 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pf->main_vsi_seid); if ((pf->hw.device_id == I40E_DEV_ID_10G_BASE_T) || - (pf->hw.device_id == I40E_DEV_ID_10G_BASE_T4)) - pf->flags |= I40E_FLAG_HAVE_10GBASET_PHY; - + (pf->hw.device_id == I40E_DEV_ID_10G_BASE_T4)) + pf->flags |= I40E_FLAG_PHY_CONTROLS_LEDS; + if (pf->hw.device_id == I40E_DEV_ID_SFP_I_X722) + pf->flags |= I40E_FLAG_HAVE_CRT_RETIMER; /* print a string summarizing features */ i40e_print_features(pf); @@ -11461,6 +11753,53 @@ static void i40e_pci_error_resume(struct pci_dev *pdev) } /** + * i40e_enable_mc_magic_wake - enable multicast magic packet wake up + * using the mac_address_write admin q function + * @pf: pointer to i40e_pf struct + **/ +static void i40e_enable_mc_magic_wake(struct i40e_pf *pf) +{ + struct i40e_hw *hw = &pf->hw; + i40e_status ret; + u8 mac_addr[6]; + u16 flags = 0; + + /* Get current MAC address in case it's an LAA */ + if (pf->vsi[pf->lan_vsi] && pf->vsi[pf->lan_vsi]->netdev) { + ether_addr_copy(mac_addr, + pf->vsi[pf->lan_vsi]->netdev->dev_addr); + } else { + dev_err(&pf->pdev->dev, + "Failed to retrieve MAC address; using default\n"); + ether_addr_copy(mac_addr, hw->mac.addr); + } + + /* The FW expects the mac address write cmd to first be called with + * one of these flags before calling it again with the multicast + * enable flags. + */ + flags = I40E_AQC_WRITE_TYPE_LAA_WOL; + + if (hw->func_caps.flex10_enable && hw->partition_id != 1) + flags = I40E_AQC_WRITE_TYPE_LAA_ONLY; + + ret = i40e_aq_mac_address_write(hw, flags, mac_addr, NULL); + if (ret) { + dev_err(&pf->pdev->dev, + "Failed to update MAC address registers; cannot enable Multicast Magic packet wake up"); + return; + } + + flags = I40E_AQC_MC_MAG_EN + | I40E_AQC_WOL_PRESERVE_ON_PFR + | I40E_AQC_WRITE_TYPE_UPDATE_MC_MAG; + ret = i40e_aq_mac_address_write(hw, flags, mac_addr, NULL); + if (ret) + dev_err(&pf->pdev->dev, + "Failed to enable Multicast Magic Packet wake up\n"); +} + +/** * i40e_shutdown - PCI callback for shutting down * @pdev: PCI device information struct **/ @@ -11482,6 +11821,9 @@ static void i40e_shutdown(struct pci_dev *pdev) cancel_work_sync(&pf->service_task); i40e_fdir_teardown(pf); + if (pf->wol_en && (pf->flags & I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE)) + i40e_enable_mc_magic_wake(pf); + rtnl_lock(); i40e_prep_for_reset(pf); rtnl_unlock(); @@ -11513,6 +11855,9 @@ static int i40e_suspend(struct pci_dev *pdev, pm_message_t state) set_bit(__I40E_SUSPENDED, &pf->state); set_bit(__I40E_DOWN, &pf->state); + if (pf->wol_en && (pf->flags & I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE)) + i40e_enable_mc_magic_wake(pf); + rtnl_lock(); i40e_prep_for_reset(pf); rtnl_unlock(); diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c index 954efe3118db..38ee18f11124 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c +++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c @@ -722,9 +722,20 @@ i40e_status i40e_nvmupd_command(struct i40e_hw *hw, *((u16 *)&bytes[2]) = hw->nvm_wait_opcode; } + /* Clear error status on read */ + if (hw->nvmupd_state == I40E_NVMUPD_STATE_ERROR) + hw->nvmupd_state = I40E_NVMUPD_STATE_INIT; + return 0; } + /* Clear status even it is not read and log */ + if (hw->nvmupd_state == I40E_NVMUPD_STATE_ERROR) { + i40e_debug(hw, I40E_DEBUG_NVM, + "Clearing I40E_NVMUPD_STATE_ERROR state without reading\n"); + hw->nvmupd_state = I40E_NVMUPD_STATE_INIT; + } + switch (hw->nvmupd_state) { case I40E_NVMUPD_STATE_INIT: status = i40e_nvmupd_state_init(hw, cmd, bytes, perrno); @@ -1074,6 +1085,11 @@ void i40e_nvmupd_check_wait_event(struct i40e_hw *hw, u16 opcode) } hw->nvm_wait_opcode = 0; + if (hw->aq.arq_last_status) { + hw->nvmupd_state = I40E_NVMUPD_STATE_ERROR; + return; + } + switch (hw->nvmupd_state) { case I40E_NVMUPD_STATE_INIT_WAIT: hw->nvmupd_state = I40E_NVMUPD_STATE_INIT; diff --git a/drivers/net/ethernet/intel/i40e/i40e_osdep.h b/drivers/net/ethernet/intel/i40e/i40e_osdep.h index 5b6feb7edeb1..fea81ed065db 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_osdep.h +++ b/drivers/net/ethernet/intel/i40e/i40e_osdep.h @@ -55,7 +55,7 @@ struct i40e_dma_mem { void *va; dma_addr_t pa; u32 size; -} __packed; +}; #define i40e_allocate_dma_mem(h, m, unused, s, a) \ i40e_allocate_dma_mem_d(h, m, s, a) @@ -64,17 +64,17 @@ struct i40e_dma_mem { struct i40e_virt_mem { void *va; u32 size; -} __packed; +}; #define i40e_allocate_virt_mem(h, m, s) i40e_allocate_virt_mem_d(h, m, s) #define i40e_free_virt_mem(h, m) i40e_free_virt_mem_d(h, m) -#define i40e_debug(h, m, s, ...) \ -do { \ - if (((m) & (h)->debug_mask)) \ - pr_info("i40e %02x.%x " s, \ - (h)->bus.device, (h)->bus.func, \ - ##__VA_ARGS__); \ +#define i40e_debug(h, m, s, ...) \ +do { \ + if (((m) & (h)->debug_mask)) \ + pr_info("i40e %02x:%02x.%x " s, \ + (h)->bus.bus_id, (h)->bus.device, \ + (h)->bus.func, ##__VA_ARGS__); \ } while (0) typedef enum i40e_status_code i40e_status; diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h index 4660c5abc855..2551fc827444 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h @@ -144,6 +144,9 @@ enum i40e_status_code i40e_aq_set_vsi_uc_promisc_on_vlan(struct i40e_hw *hw, u16 seid, bool enable, u16 vid, struct i40e_asq_cmd_details *cmd_details); +i40e_status i40e_aq_set_vsi_bc_promisc_on_vlan(struct i40e_hw *hw, + u16 seid, bool enable, u16 vid, + struct i40e_asq_cmd_details *cmd_details); i40e_status i40e_aq_set_vsi_vlan_promisc(struct i40e_hw *hw, u16 seid, bool enable, struct i40e_asq_cmd_details *cmd_details); @@ -362,10 +365,18 @@ i40e_status i40e_aq_rx_ctl_write_register(struct i40e_hw *hw, u32 reg_addr, u32 reg_val, struct i40e_asq_cmd_details *cmd_details); void i40e_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val); -i40e_status i40e_read_phy_register(struct i40e_hw *hw, u8 page, - u16 reg, u8 phy_addr, u16 *value); -i40e_status i40e_write_phy_register(struct i40e_hw *hw, u8 page, - u16 reg, u8 phy_addr, u16 value); +i40e_status i40e_read_phy_register_clause22(struct i40e_hw *hw, + u16 reg, u8 phy_addr, u16 *value); +i40e_status i40e_write_phy_register_clause22(struct i40e_hw *hw, + u16 reg, u8 phy_addr, u16 value); +i40e_status i40e_read_phy_register_clause45(struct i40e_hw *hw, + u8 page, u16 reg, u8 phy_addr, u16 *value); +i40e_status i40e_write_phy_register_clause45(struct i40e_hw *hw, + u8 page, u16 reg, u8 phy_addr, u16 value); +i40e_status i40e_read_phy_register(struct i40e_hw *hw, u8 page, u16 reg, + u8 phy_addr, u16 *value); +i40e_status i40e_write_phy_register(struct i40e_hw *hw, u8 page, u16 reg, + u8 phy_addr, u16 value); u8 i40e_get_phy_address(struct i40e_hw *hw, u8 dev_num); i40e_status i40e_blink_phy_link_led(struct i40e_hw *hw, u32 time, u32 interval); diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index f1feceab758a..2caee35528fa 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -159,16 +159,15 @@ static int i40e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) { struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps); struct timespec64 now, then; - unsigned long flags; then = ns_to_timespec64(delta); - spin_lock_irqsave(&pf->tmreg_lock, flags); + mutex_lock(&pf->tmreg_lock); i40e_ptp_read(pf, &now); now = timespec64_add(now, then); i40e_ptp_write(pf, (const struct timespec64 *)&now); - spin_unlock_irqrestore(&pf->tmreg_lock, flags); + mutex_unlock(&pf->tmreg_lock); return 0; } @@ -184,11 +183,10 @@ static int i40e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) static int i40e_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) { struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps); - unsigned long flags; - spin_lock_irqsave(&pf->tmreg_lock, flags); + mutex_lock(&pf->tmreg_lock); i40e_ptp_read(pf, ts); - spin_unlock_irqrestore(&pf->tmreg_lock, flags); + mutex_unlock(&pf->tmreg_lock); return 0; } @@ -205,11 +203,10 @@ static int i40e_ptp_settime(struct ptp_clock_info *ptp, const struct timespec64 *ts) { struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps); - unsigned long flags; - spin_lock_irqsave(&pf->tmreg_lock, flags); + mutex_lock(&pf->tmreg_lock); i40e_ptp_write(pf, ts); - spin_unlock_irqrestore(&pf->tmreg_lock, flags); + mutex_unlock(&pf->tmreg_lock); return 0; } @@ -230,6 +227,47 @@ static int i40e_ptp_feature_enable(struct ptp_clock_info *ptp, } /** + * i40e_ptp_update_latch_events - Read I40E_PRTTSYN_STAT_1 and latch events + * @pf: the PF data structure + * + * This function reads I40E_PRTTSYN_STAT_1 and updates the corresponding timers + * for noticed latch events. This allows the driver to keep track of the first + * time a latch event was noticed which will be used to help clear out Rx + * timestamps for packets that got dropped or lost. + * + * This function will return the current value of I40E_PRTTSYN_STAT_1 and is + * expected to be called only while under the ptp_rx_lock. + **/ +static u32 i40e_ptp_get_rx_events(struct i40e_pf *pf) +{ + struct i40e_hw *hw = &pf->hw; + u32 prttsyn_stat, new_latch_events; + int i; + + prttsyn_stat = rd32(hw, I40E_PRTTSYN_STAT_1); + new_latch_events = prttsyn_stat & ~pf->latch_event_flags; + + /* Update the jiffies time for any newly latched timestamp. This + * ensures that we store the time that we first discovered a timestamp + * was latched by the hardware. The service task will later determine + * if we should free the latch and drop that timestamp should too much + * time pass. This flow ensures that we only update jiffies for new + * events latched since the last time we checked, and not all events + * currently latched, so that the service task accounting remains + * accurate. + */ + for (i = 0; i < 4; i++) { + if (new_latch_events & BIT(i)) + pf->latch_events[i] = jiffies; + } + + /* Finally, we store the current status of the Rx timestamp latches */ + pf->latch_event_flags = prttsyn_stat; + + return prttsyn_stat; +} + +/** * i40e_ptp_rx_hang - Detect error case when Rx timestamp registers are hung * @vsi: The VSI with the rings relevant to 1588 * @@ -242,10 +280,7 @@ void i40e_ptp_rx_hang(struct i40e_vsi *vsi) { struct i40e_pf *pf = vsi->back; struct i40e_hw *hw = &pf->hw; - struct i40e_ring *rx_ring; - unsigned long rx_event; - u32 prttsyn_stat; - int n; + unsigned int i, cleared = 0; /* Since we cannot turn off the Rx timestamp logic if the device is * configured for Tx timestamping, we check if Rx timestamping is @@ -255,42 +290,41 @@ void i40e_ptp_rx_hang(struct i40e_vsi *vsi) if (!(pf->flags & I40E_FLAG_PTP) || !pf->ptp_rx) return; - prttsyn_stat = rd32(hw, I40E_PRTTSYN_STAT_1); + spin_lock_bh(&pf->ptp_rx_lock); + + /* Update current latch times for Rx events */ + i40e_ptp_get_rx_events(pf); - /* Unless all four receive timestamp registers are latched, we are not - * concerned about a possible PTP Rx hang, so just update the timeout - * counter and exit. + /* Check all the currently latched Rx events and see whether they have + * been latched for over a second. It is assumed that any timestamp + * should have been cleared within this time, or else it was captured + * for a dropped frame that the driver never received. Thus, we will + * clear any timestamp that has been latched for over 1 second. */ - if (!(prttsyn_stat & ((I40E_PRTTSYN_STAT_1_RXT0_MASK << - I40E_PRTTSYN_STAT_1_RXT0_SHIFT) | - (I40E_PRTTSYN_STAT_1_RXT1_MASK << - I40E_PRTTSYN_STAT_1_RXT1_SHIFT) | - (I40E_PRTTSYN_STAT_1_RXT2_MASK << - I40E_PRTTSYN_STAT_1_RXT2_SHIFT) | - (I40E_PRTTSYN_STAT_1_RXT3_MASK << - I40E_PRTTSYN_STAT_1_RXT3_SHIFT)))) { - pf->last_rx_ptp_check = jiffies; - return; + for (i = 0; i < 4; i++) { + if ((pf->latch_event_flags & BIT(i)) && + time_is_before_jiffies(pf->latch_events[i] + HZ)) { + rd32(hw, I40E_PRTTSYN_RXTIME_H(i)); + pf->latch_event_flags &= ~BIT(i); + cleared++; + } } - /* Determine the most recent watchdog or rx_timestamp event. */ - rx_event = pf->last_rx_ptp_check; - for (n = 0; n < vsi->num_queue_pairs; n++) { - rx_ring = vsi->rx_rings[n]; - if (time_after(rx_ring->last_rx_timestamp, rx_event)) - rx_event = rx_ring->last_rx_timestamp; - } + spin_unlock_bh(&pf->ptp_rx_lock); - /* Only need to read the high RXSTMP register to clear the lock */ - if (time_is_before_jiffies(rx_event + 5 * HZ)) { - rd32(hw, I40E_PRTTSYN_RXTIME_H(0)); - rd32(hw, I40E_PRTTSYN_RXTIME_H(1)); - rd32(hw, I40E_PRTTSYN_RXTIME_H(2)); - rd32(hw, I40E_PRTTSYN_RXTIME_H(3)); - pf->last_rx_ptp_check = jiffies; - pf->rx_hwtstamp_cleared++; - WARN_ONCE(1, "Detected Rx timestamp register hang\n"); - } + /* Log a warning if more than 2 timestamps got dropped in the same + * check. We don't want to warn about all drops because it can occur + * in normal scenarios such as PTP frames on multicast addresses we + * aren't listening to. However, administrator should know if this is + * the reason packets aren't receiving timestamps. + */ + if (cleared > 2) + dev_dbg(&pf->pdev->dev, + "Dropped %d missed RXTIME timestamp events\n", + cleared); + + /* Finally, update the rx_hwtstamp_cleared counter */ + pf->rx_hwtstamp_cleared += cleared; } /** @@ -353,14 +387,25 @@ void i40e_ptp_rx_hwtstamp(struct i40e_pf *pf, struct sk_buff *skb, u8 index) hw = &pf->hw; - prttsyn_stat = rd32(hw, I40E_PRTTSYN_STAT_1); + spin_lock_bh(&pf->ptp_rx_lock); - if (!(prttsyn_stat & BIT(index))) + /* Get current Rx events and update latch times */ + prttsyn_stat = i40e_ptp_get_rx_events(pf); + + /* TODO: Should we warn about missing Rx timestamp event? */ + if (!(prttsyn_stat & BIT(index))) { + spin_unlock_bh(&pf->ptp_rx_lock); return; + } + + /* Clear the latched event since we're about to read its register */ + pf->latch_event_flags &= ~BIT(index); lo = rd32(hw, I40E_PRTTSYN_RXTIME_L(index)); hi = rd32(hw, I40E_PRTTSYN_RXTIME_H(index)); + spin_unlock_bh(&pf->ptp_rx_lock); + ns = (((u64)hi) << 32) | lo; i40e_ptp_convert_to_hwtstamp(skb_hwtstamps(skb), ns); @@ -487,6 +532,8 @@ static int i40e_ptp_set_timestamp_mode(struct i40e_pf *pf, case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + if (!(pf->flags & I40E_FLAG_PTP_L4_CAPABLE)) + return -ERANGE; pf->ptp_rx = true; tsyntype = I40E_PRTTSYN_CTL1_V1MESSTYPE0_MASK | I40E_PRTTSYN_CTL1_TSYNTYPE_V1 | @@ -494,19 +541,26 @@ static int i40e_ptp_set_timestamp_mode(struct i40e_pf *pf, config->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT; break; case HWTSTAMP_FILTER_PTP_V2_EVENT: - case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: case HWTSTAMP_FILTER_PTP_V2_SYNC: - case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: - case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + if (!(pf->flags & I40E_FLAG_PTP_L4_CAPABLE)) + return -ERANGE; + /* fall through */ + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: pf->ptp_rx = true; tsyntype = I40E_PRTTSYN_CTL1_V2MESSTYPE0_MASK | - I40E_PRTTSYN_CTL1_TSYNTYPE_V2 | - I40E_PRTTSYN_CTL1_UDP_ENA_MASK; - config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + I40E_PRTTSYN_CTL1_TSYNTYPE_V2; + if (pf->flags & I40E_FLAG_PTP_L4_CAPABLE) { + tsyntype |= I40E_PRTTSYN_CTL1_UDP_ENA_MASK; + config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + } else { + config->rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT; + } break; case HWTSTAMP_FILTER_ALL: default: @@ -514,12 +568,15 @@ static int i40e_ptp_set_timestamp_mode(struct i40e_pf *pf, } /* Clear out all 1588-related registers to clear and unlatch them. */ + spin_lock_bh(&pf->ptp_rx_lock); rd32(hw, I40E_PRTTSYN_STAT_0); rd32(hw, I40E_PRTTSYN_TXTIME_H); rd32(hw, I40E_PRTTSYN_RXTIME_H(0)); rd32(hw, I40E_PRTTSYN_RXTIME_H(1)); rd32(hw, I40E_PRTTSYN_RXTIME_H(2)); rd32(hw, I40E_PRTTSYN_RXTIME_H(3)); + pf->latch_event_flags = 0; + spin_unlock_bh(&pf->ptp_rx_lock); /* Enable/disable the Tx timestamp interrupt based on user input. */ regval = rd32(hw, I40E_PRTTSYN_CTL0); @@ -658,10 +715,8 @@ void i40e_ptp_init(struct i40e_pf *pf) return; } - /* we have to initialize the lock first, since we can't control - * when the user will enter the PHC device entry points - */ - spin_lock_init(&pf->tmreg_lock); + mutex_init(&pf->tmreg_lock); + spin_lock_init(&pf->ptp_rx_lock); /* ensure we have a clock device */ err = i40e_ptp_create_clock(pf); diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 6287bf63c43c..97d46058d71d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -122,14 +122,10 @@ static int i40e_program_fdir_filter(struct i40e_fdir_filter *fdir_data, struct device *dev; dma_addr_t dma; u32 td_cmd = 0; - u16 delay = 0; u16 i; /* find existing FDIR VSI */ - vsi = NULL; - for (i = 0; i < pf->num_alloc_vsi; i++) - if (pf->vsi[i] && pf->vsi[i]->type == I40E_VSI_FDIR) - vsi = pf->vsi[i]; + vsi = i40e_find_vsi_by_type(pf, I40E_VSI_FDIR); if (!vsi) return -ENOENT; @@ -137,15 +133,11 @@ static int i40e_program_fdir_filter(struct i40e_fdir_filter *fdir_data, dev = tx_ring->dev; /* we need two descriptors to add/del a filter and we can wait */ - do { - if (I40E_DESC_UNUSED(tx_ring) > 1) - break; + for (i = I40E_FD_CLEAN_DELAY; I40E_DESC_UNUSED(tx_ring) < 2; i--) { + if (!i) + return -EAGAIN; msleep_interruptible(1); - delay++; - } while (delay < I40E_FD_CLEAN_DELAY); - - if (!(I40E_DESC_UNUSED(tx_ring) > 1)) - return -EAGAIN; + } dma = dma_map_single(dev, raw_packet, I40E_FDIR_MAX_RAW_PACKET_SIZE, DMA_TO_DEVICE); @@ -335,22 +327,6 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi, return err ? -EOPNOTSUPP : 0; } -/** - * i40e_add_del_fdir_sctpv4 - Add/Remove SCTPv4 Flow Director filters for - * a specific flow spec - * @vsi: pointer to the targeted VSI - * @fd_data: the flow director data required for the FDir descriptor - * @add: true adds a filter, false removes it - * - * Returns 0 if the filters were successfully added or removed - **/ -static int i40e_add_del_fdir_sctpv4(struct i40e_vsi *vsi, - struct i40e_fdir_filter *fd_data, - bool add) -{ - return -EOPNOTSUPP; -} - #define I40E_IP_DUMMY_PACKET_LEN 34 /** * i40e_add_del_fdir_ipv4 - Add/Remove IPv4 Flow Director filters for @@ -433,12 +409,6 @@ int i40e_add_del_fdir(struct i40e_vsi *vsi, case UDP_V4_FLOW: ret = i40e_add_del_fdir_udpv4(vsi, input, add); break; - case SCTP_V4_FLOW: - ret = i40e_add_del_fdir_sctpv4(vsi, input, add); - break; - case IPV4_FLOW: - ret = i40e_add_del_fdir_ipv4(vsi, input, add); - break; case IP_USER_FLOW: switch (input->ip4_proto) { case IPPROTO_TCP: @@ -447,21 +417,27 @@ int i40e_add_del_fdir(struct i40e_vsi *vsi, case IPPROTO_UDP: ret = i40e_add_del_fdir_udpv4(vsi, input, add); break; - case IPPROTO_SCTP: - ret = i40e_add_del_fdir_sctpv4(vsi, input, add); - break; - default: + case IPPROTO_IP: ret = i40e_add_del_fdir_ipv4(vsi, input, add); break; + default: + /* We cannot support masking based on protocol */ + goto unsupported_flow; } break; default: +unsupported_flow: dev_info(&pf->pdev->dev, "Could not specify spec type %d\n", input->flow_type); ret = -EINVAL; } - /* The buffer allocated here is freed by the i40e_clean_tx_ring() */ + /* The buffer allocated here will be normally be freed by + * i40e_clean_fdir_tx_irq() as it reclaims resources after transmit + * completion. In the event of an error adding the buffer to the FDIR + * ring, it will immediately be freed. It may also be freed by + * i40e_clean_tx_ring() when closing the VSI. + */ return ret; } @@ -645,7 +621,7 @@ u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw) return 0; } -#define WB_STRIDE 0x3 +#define WB_STRIDE 4 /** * i40e_clean_tx_irq - Reclaim resources after transmit completes @@ -761,7 +737,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, unsigned int j = i40e_get_tx_pending(tx_ring, false); if (budget && - ((j / (WB_STRIDE + 1)) == 0) && (j != 0) && + ((j / WB_STRIDE) == 0) && (j > 0) && !test_bit(__I40E_DOWN, &vsi->state) && (I40E_DESC_UNUSED(tx_ring) != tx_ring->count)) tx_ring->arm_wb = true; @@ -1042,14 +1018,15 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring) if (!rx_ring->rx_bi) return; + if (rx_ring->skb) { + dev_kfree_skb(rx_ring->skb); + rx_ring->skb = NULL; + } + /* Free all the Rx ring sk_buffs */ for (i = 0; i < rx_ring->count; i++) { struct i40e_rx_buffer *rx_bi = &rx_ring->rx_bi[i]; - if (rx_bi->skb) { - dev_kfree_skb(rx_bi->skb); - rx_bi->skb = NULL; - } if (!rx_bi->page) continue; @@ -1246,7 +1223,6 @@ bool i40e_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count) * because each write-back erases this info. */ rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset); - rx_desc->read.hdr_addr = 0; rx_desc++; bi++; @@ -1437,13 +1413,12 @@ void i40e_process_skb_fields(struct i40e_ring *rx_ring, u64 qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); u32 rx_status = (qword & I40E_RXD_QW1_STATUS_MASK) >> I40E_RXD_QW1_STATUS_SHIFT; - u32 rsyn = (rx_status & I40E_RXD_QW1_STATUS_TSYNINDX_MASK) >> + u32 tsynvalid = rx_status & I40E_RXD_QW1_STATUS_TSYNVALID_MASK; + u32 tsyn = (rx_status & I40E_RXD_QW1_STATUS_TSYNINDX_MASK) >> I40E_RXD_QW1_STATUS_TSYNINDX_SHIFT; - if (unlikely(rsyn)) { - i40e_ptp_rx_hwtstamp(rx_ring->vsi->back, skb, rsyn); - rx_ring->last_rx_timestamp = jiffies; - } + if (unlikely(tsynvalid)) + i40e_ptp_rx_hwtstamp(rx_ring->vsi->back, skb, tsyn); i40e_rx_hash(rx_ring, rx_desc, skb, rx_ptype); @@ -1456,45 +1431,6 @@ void i40e_process_skb_fields(struct i40e_ring *rx_ring, } /** - * i40e_pull_tail - i40e specific version of skb_pull_tail - * @rx_ring: rx descriptor ring packet is being transacted on - * @skb: pointer to current skb being adjusted - * - * This function is an i40e specific version of __pskb_pull_tail. The - * main difference between this version and the original function is that - * this function can make several assumptions about the state of things - * that allow for significant optimizations versus the standard function. - * As a result we can do things like drop a frag and maintain an accurate - * truesize for the skb. - */ -static void i40e_pull_tail(struct i40e_ring *rx_ring, struct sk_buff *skb) -{ - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; - unsigned char *va; - unsigned int pull_len; - - /* it is valid to use page_address instead of kmap since we are - * working with pages allocated out of the lomem pool per - * alloc_page(GFP_ATOMIC) - */ - va = skb_frag_address(frag); - - /* we need the header to contain the greater of either ETH_HLEN or - * 60 bytes if the skb->len is less than 60 for skb_pad. - */ - pull_len = eth_get_headlen(va, I40E_RX_HDR_SIZE); - - /* align pull length to size of long to optimize memcpy performance */ - skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long))); - - /* update all of the pointers */ - skb_frag_size_sub(frag, pull_len); - frag->page_offset += pull_len; - skb->data_len -= pull_len; - skb->tail += pull_len; -} - -/** * i40e_cleanup_headers - Correct empty headers * @rx_ring: rx descriptor ring packet is being transacted on * @skb: pointer to current skb being fixed @@ -1509,10 +1445,6 @@ static void i40e_pull_tail(struct i40e_ring *rx_ring, struct sk_buff *skb) **/ static bool i40e_cleanup_headers(struct i40e_ring *rx_ring, struct sk_buff *skb) { - /* place header in linear portion of buffer */ - if (skb_is_nonlinear(skb)) - i40e_pull_tail(rx_ring, skb); - /* if eth_skb_pad returns an error the skb was freed */ if (eth_skb_pad(skb)) return true; @@ -1544,19 +1476,85 @@ static void i40e_reuse_rx_page(struct i40e_ring *rx_ring, } /** - * i40e_page_is_reserved - check if reuse is possible + * i40e_page_is_reusable - check if any reuse is possible * @page: page struct to check + * + * A page is not reusable if it was allocated under low memory + * conditions, or it's not in the same NUMA node as this CPU. */ -static inline bool i40e_page_is_reserved(struct page *page) +static inline bool i40e_page_is_reusable(struct page *page) { - return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page); + return (page_to_nid(page) == numa_mem_id()) && + !page_is_pfmemalloc(page); +} + +/** + * i40e_can_reuse_rx_page - Determine if this page can be reused by + * the adapter for another receive + * + * @rx_buffer: buffer containing the page + * @page: page address from rx_buffer + * @truesize: actual size of the buffer in this page + * + * If page is reusable, rx_buffer->page_offset is adjusted to point to + * an unused region in the page. + * + * For small pages, @truesize will be a constant value, half the size + * of the memory at page. We'll attempt to alternate between high and + * low halves of the page, with one half ready for use by the hardware + * and the other half being consumed by the stack. We use the page + * ref count to determine whether the stack has finished consuming the + * portion of this page that was passed up with a previous packet. If + * the page ref count is >1, we'll assume the "other" half page is + * still busy, and this page cannot be reused. + * + * For larger pages, @truesize will be the actual space used by the + * received packet (adjusted upward to an even multiple of the cache + * line size). This will advance through the page by the amount + * actually consumed by the received packets while there is still + * space for a buffer. Each region of larger pages will be used at + * most once, after which the page will not be reused. + * + * In either case, if the page is reusable its refcount is increased. + **/ +static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer, + struct page *page, + const unsigned int truesize) +{ +#if (PAGE_SIZE >= 8192) + unsigned int last_offset = PAGE_SIZE - I40E_RXBUFFER_2048; +#endif + + /* Is any reuse possible? */ + if (unlikely(!i40e_page_is_reusable(page))) + return false; + +#if (PAGE_SIZE < 8192) + /* if we are only owner of page we can reuse it */ + if (unlikely(page_count(page) != 1)) + return false; + + /* flip page offset to other buffer */ + rx_buffer->page_offset ^= truesize; +#else + /* move offset up to the next cache line */ + rx_buffer->page_offset += truesize; + + if (rx_buffer->page_offset > last_offset) + return false; +#endif + + /* Inc ref count on page before passing it up to the stack */ + get_page(page); + + return true; } /** * i40e_add_rx_frag - Add contents of Rx buffer to sk_buff * @rx_ring: rx descriptor ring to transact packets on * @rx_buffer: buffer containing page to add - * @rx_desc: descriptor containing length of buffer written by hardware + * @size: packet length from rx_desc * @skb: sk_buff to place the data into * * This function will add the data contained in rx_buffer->page to the skb. @@ -1569,30 +1567,29 @@ static inline bool i40e_page_is_reserved(struct page *page) **/ static bool i40e_add_rx_frag(struct i40e_ring *rx_ring, struct i40e_rx_buffer *rx_buffer, - union i40e_rx_desc *rx_desc, + unsigned int size, struct sk_buff *skb) { struct page *page = rx_buffer->page; - u64 qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - unsigned int size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >> - I40E_RXD_QW1_LENGTH_PBUF_SHIFT; + unsigned char *va = page_address(page) + rx_buffer->page_offset; #if (PAGE_SIZE < 8192) unsigned int truesize = I40E_RXBUFFER_2048; #else unsigned int truesize = ALIGN(size, L1_CACHE_BYTES); - unsigned int last_offset = PAGE_SIZE - I40E_RXBUFFER_2048; #endif + unsigned int pull_len; + + if (unlikely(skb_is_nonlinear(skb))) + goto add_tail_frag; /* will the data fit in the skb we allocated? if so, just * copy it as it is pretty small anyway */ - if ((size <= I40E_RX_HDR_SIZE) && !skb_is_nonlinear(skb)) { - unsigned char *va = page_address(page) + rx_buffer->page_offset; - + if (size <= I40E_RX_HDR_SIZE) { memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long))); - /* page is not reserved, we can reuse buffer as-is */ - if (likely(!i40e_page_is_reserved(page))) + /* page is reusable, we can reuse buffer as-is */ + if (likely(i40e_page_is_reusable(page))) return true; /* this page cannot be reused so discard it */ @@ -1600,34 +1597,26 @@ static bool i40e_add_rx_frag(struct i40e_ring *rx_ring, return false; } - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, - rx_buffer->page_offset, size, truesize); - - /* avoid re-using remote pages */ - if (unlikely(i40e_page_is_reserved(page))) - return false; - -#if (PAGE_SIZE < 8192) - /* if we are only owner of page we can reuse it */ - if (unlikely(page_count(page) != 1)) - return false; + /* we need the header to contain the greater of either + * ETH_HLEN or 60 bytes if the skb->len is less than + * 60 for skb_pad. + */ + pull_len = eth_get_headlen(va, I40E_RX_HDR_SIZE); - /* flip page offset to other buffer */ - rx_buffer->page_offset ^= truesize; -#else - /* move offset up to the next cache line */ - rx_buffer->page_offset += truesize; + /* align pull length to size of long to optimize + * memcpy performance + */ + memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long))); - if (rx_buffer->page_offset > last_offset) - return false; -#endif + /* update all of the pointers */ + va += pull_len; + size -= pull_len; - /* Even if we own the page, we are not allowed to use atomic_set() - * This would break get_page_unless_zero() users. - */ - get_page(rx_buffer->page); +add_tail_frag: + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, + (unsigned long)va & ~PAGE_MASK, size, truesize); - return true; + return i40e_can_reuse_rx_page(rx_buffer, page, truesize); } /** @@ -1642,18 +1631,21 @@ static bool i40e_add_rx_frag(struct i40e_ring *rx_ring, */ static inline struct sk_buff *i40e_fetch_rx_buffer(struct i40e_ring *rx_ring, - union i40e_rx_desc *rx_desc) + union i40e_rx_desc *rx_desc, + struct sk_buff *skb) { + u64 local_status_error_len = + le64_to_cpu(rx_desc->wb.qword1.status_error_len); + unsigned int size = + (local_status_error_len & I40E_RXD_QW1_LENGTH_PBUF_MASK) >> + I40E_RXD_QW1_LENGTH_PBUF_SHIFT; struct i40e_rx_buffer *rx_buffer; - struct sk_buff *skb; struct page *page; rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean]; page = rx_buffer->page; prefetchw(page); - skb = rx_buffer->skb; - if (likely(!skb)) { void *page_addr = page_address(page) + rx_buffer->page_offset; @@ -1677,19 +1669,17 @@ struct sk_buff *i40e_fetch_rx_buffer(struct i40e_ring *rx_ring, * it now to avoid a possible cache miss */ prefetchw(skb->data); - } else { - rx_buffer->skb = NULL; } /* we are reusing so sync this buffer for CPU use */ dma_sync_single_range_for_cpu(rx_ring->dev, rx_buffer->dma, rx_buffer->page_offset, - I40E_RXBUFFER_2048, + size, DMA_FROM_DEVICE); /* pull page into skb */ - if (i40e_add_rx_frag(rx_ring, rx_buffer, rx_desc, skb)) { + if (i40e_add_rx_frag(rx_ring, rx_buffer, size, skb)) { /* hand second half of page back to the ring */ i40e_reuse_rx_page(rx_ring, rx_buffer); rx_ring->rx_stats.page_reuse_count++; @@ -1731,7 +1721,6 @@ static bool i40e_is_non_eop(struct i40e_ring *rx_ring, #define staterrlen rx_desc->wb.qword1.status_error_len if (unlikely(i40e_rx_is_programming_status(le64_to_cpu(staterrlen)))) { i40e_clean_programming_status(rx_ring, rx_desc); - rx_ring->rx_bi[ntc].skb = skb; return true; } /* if we are the last buffer then there is nothing else to do */ @@ -1739,8 +1728,6 @@ static bool i40e_is_non_eop(struct i40e_ring *rx_ring, if (likely(i40e_test_staterr(rx_desc, I40E_RXD_EOF))) return false; - /* place skb in next buffer to be received */ - rx_ring->rx_bi[ntc].skb = skb; rx_ring->rx_stats.non_eop_descs++; return true; @@ -1761,13 +1748,12 @@ static bool i40e_is_non_eop(struct i40e_ring *rx_ring, static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) { unsigned int total_rx_bytes = 0, total_rx_packets = 0; + struct sk_buff *skb = rx_ring->skb; u16 cleaned_count = I40E_DESC_UNUSED(rx_ring); bool failure = false; while (likely(total_rx_packets < budget)) { union i40e_rx_desc *rx_desc; - struct sk_buff *skb; - u32 rx_status; u16 vlan_tag; u8 rx_ptype; u64 qword; @@ -1781,21 +1767,13 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) rx_desc = I40E_RX_DESC(rx_ring, rx_ring->next_to_clean); - qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - rx_ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >> - I40E_RXD_QW1_PTYPE_SHIFT; - rx_status = (qword & I40E_RXD_QW1_STATUS_MASK) >> - I40E_RXD_QW1_STATUS_SHIFT; - - if (!(rx_status & BIT(I40E_RX_DESC_STATUS_DD_SHIFT))) - break; - /* status_error_len will always be zero for unused descriptors * because it's cleared in cleanup, and overlaps with hdr_addr * which is always zero because packet split isn't used, if the * hardware wrote DD then it will be non-zero */ - if (!rx_desc->wb.qword1.status_error_len) + if (!i40e_test_staterr(rx_desc, + BIT(I40E_RX_DESC_STATUS_DD_SHIFT))) break; /* This memory barrier is needed to keep us from reading @@ -1804,7 +1782,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) */ dma_rmb(); - skb = i40e_fetch_rx_buffer(rx_ring, rx_desc); + skb = i40e_fetch_rx_buffer(rx_ring, rx_desc, skb); if (!skb) break; @@ -1823,12 +1801,18 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) continue; } - if (i40e_cleanup_headers(rx_ring, skb)) + if (i40e_cleanup_headers(rx_ring, skb)) { + skb = NULL; continue; + } /* probably a little skewed due to removing CRC */ total_rx_bytes += skb->len; + qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); + rx_ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >> + I40E_RXD_QW1_PTYPE_SHIFT; + /* populate checksum, VLAN, and protocol */ i40e_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype); @@ -1845,11 +1829,14 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1) : 0; i40e_receive_skb(rx_ring, skb, vlan_tag); + skb = NULL; /* update budget accounting */ total_rx_packets++; } + rx_ring->skb = skb; + u64_stats_update_begin(&rx_ring->syncp); rx_ring->stats.packets += total_rx_packets; rx_ring->stats.bytes += total_rx_bytes; @@ -1877,14 +1864,14 @@ static u32 i40e_buildreg_itr(const int type, const u16 itr) /* a small macro to shorten up some long lines */ #define INTREG I40E_PFINT_DYN_CTLN -static inline int get_rx_itr_enabled(struct i40e_vsi *vsi, int idx) +static inline int get_rx_itr(struct i40e_vsi *vsi, int idx) { - return !!(vsi->rx_rings[idx]->rx_itr_setting); + return vsi->rx_rings[idx]->rx_itr_setting; } -static inline int get_tx_itr_enabled(struct i40e_vsi *vsi, int idx) +static inline int get_tx_itr(struct i40e_vsi *vsi, int idx) { - return !!(vsi->tx_rings[idx]->tx_itr_setting); + return vsi->tx_rings[idx]->tx_itr_setting; } /** @@ -1910,8 +1897,8 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, */ rxval = txval = i40e_buildreg_itr(I40E_ITR_NONE, 0); - rx_itr_setting = get_rx_itr_enabled(vsi, idx); - tx_itr_setting = get_tx_itr_enabled(vsi, idx); + rx_itr_setting = get_rx_itr(vsi, idx); + tx_itr_setting = get_tx_itr(vsi, idx); if (q_vector->itr_countdown > 0 || (!ITR_IS_DYNAMIC(rx_itr_setting) && @@ -2025,12 +2012,25 @@ int i40e_napi_poll(struct napi_struct *napi, int budget) /* If work not completed, return budget and polling will return */ if (!clean_complete) { + const cpumask_t *aff_mask = &q_vector->affinity_mask; + int cpu_id = smp_processor_id(); + + /* It is possible that the interrupt affinity has changed but, + * if the cpu is pegged at 100%, polling will never exit while + * traffic continues and the interrupt will be stuck on this + * cpu. We check to make sure affinity is correct before we + * continue to poll, otherwise we must stop polling so the + * interrupt can move to the correct cpu. + */ + if (likely(cpumask_test_cpu(cpu_id, aff_mask) || + !(vsi->back->flags & I40E_FLAG_MSIX_ENABLED))) { tx_only: - if (arm_wb) { - q_vector->tx.ring[0].tx_stats.tx_force_wb++; - i40e_enable_wb_on_itr(vsi, q_vector); + if (arm_wb) { + q_vector->tx.ring[0].tx_stats.tx_force_wb++; + i40e_enable_wb_on_itr(vsi, q_vector); + } + return budget; } - return budget; } if (vsi->back->flags & I40E_TXR_FLAGS_WB_ON_ITR) @@ -2038,12 +2038,19 @@ tx_only: /* Work is done so exit the polling mode and re-enable the interrupt */ napi_complete_done(napi, work_done); - if (vsi->back->flags & I40E_FLAG_MSIX_ENABLED) { - i40e_update_enable_itr(vsi, q_vector); - } else { /* Legacy mode */ + + /* If we're prematurely stopping polling to fix the interrupt + * affinity we want to make sure polling starts back up so we + * issue a call to i40e_force_wb which triggers a SW interrupt. + */ + if (!clean_complete) + i40e_force_wb(vsi, q_vector); + else if (!(vsi->back->flags & I40E_FLAG_MSIX_ENABLED)) i40e_irq_dynamic_enable_icr0(vsi->back, false); - } - return 0; + else + i40e_update_enable_itr(vsi, q_vector); + + return min(work_done, budget - 1); } /** @@ -2267,14 +2274,16 @@ out: /** * i40e_tso - set up the tso context descriptor - * @skb: ptr to the skb we're sending + * @first: pointer to first Tx buffer for xmit * @hdr_len: ptr to the size of the packet header * @cd_type_cmd_tso_mss: Quad Word 1 * * Returns 0 if no TSO can happen, 1 if tso is going, or error **/ -static int i40e_tso(struct sk_buff *skb, u8 *hdr_len, u64 *cd_type_cmd_tso_mss) +static int i40e_tso(struct i40e_tx_buffer *first, u8 *hdr_len, + u64 *cd_type_cmd_tso_mss) { + struct sk_buff *skb = first->skb; u64 cd_cmd, cd_tso_len, cd_mss; union { struct iphdr *v4; @@ -2287,6 +2296,7 @@ static int i40e_tso(struct sk_buff *skb, u8 *hdr_len, u64 *cd_type_cmd_tso_mss) unsigned char *hdr; } l4; u32 paylen, l4_offset; + u16 gso_segs, gso_size; int err; if (skb->ip_summed != CHECKSUM_PARTIAL) @@ -2325,7 +2335,8 @@ static int i40e_tso(struct sk_buff *skb, u8 *hdr_len, u64 *cd_type_cmd_tso_mss) /* remove payload length from outer checksum */ paylen = skb->len - l4_offset; - csum_replace_by_diff(&l4.udp->check, htonl(paylen)); + csum_replace_by_diff(&l4.udp->check, + (__force __wsum)htonl(paylen)); } /* reset pointers to inner headers */ @@ -2346,15 +2357,23 @@ static int i40e_tso(struct sk_buff *skb, u8 *hdr_len, u64 *cd_type_cmd_tso_mss) /* remove payload length from inner checksum */ paylen = skb->len - l4_offset; - csum_replace_by_diff(&l4.tcp->check, htonl(paylen)); + csum_replace_by_diff(&l4.tcp->check, (__force __wsum)htonl(paylen)); /* compute length of segmentation header */ *hdr_len = (l4.tcp->doff * 4) + l4_offset; + /* pull values out of skb_shinfo */ + gso_size = skb_shinfo(skb)->gso_size; + gso_segs = skb_shinfo(skb)->gso_segs; + + /* update GSO size and bytecount with header size */ + first->gso_segs = gso_segs; + first->bytecount += (first->gso_segs - 1) * *hdr_len; + /* find the field values */ cd_cmd = I40E_TX_CTX_DESC_TSO; cd_tso_len = skb->len - *hdr_len; - cd_mss = skb_shinfo(skb)->gso_size; + cd_mss = gso_size; *cd_type_cmd_tso_mss |= (cd_cmd << I40E_TXD_CTX_QW1_CMD_SHIFT) | (cd_tso_len << I40E_TXD_CTX_QW1_TSO_LEN_SHIFT) | (cd_mss << I40E_TXD_CTX_QW1_MSS_SHIFT); @@ -2715,10 +2734,7 @@ static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, u16 i = tx_ring->next_to_use; u32 td_tag = 0; dma_addr_t dma; - u16 gso_segs; - u16 desc_count = 0; - bool tail_bump = true; - bool do_rs = false; + u16 desc_count = 1; if (tx_flags & I40E_TX_FLAGS_HW_VLAN) { td_cmd |= I40E_TX_DESC_CMD_IL2TAG1; @@ -2726,15 +2742,6 @@ static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, I40E_TX_FLAGS_VLAN_SHIFT; } - if (tx_flags & (I40E_TX_FLAGS_TSO | I40E_TX_FLAGS_FSO)) - gso_segs = skb_shinfo(skb)->gso_segs; - else - gso_segs = 1; - - /* multiply data chunks by size of headers */ - first->bytecount = skb->len - hdr_len + (gso_segs * hdr_len); - first->gso_segs = gso_segs; - first->skb = skb; first->tx_flags = tx_flags; dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE); @@ -2801,8 +2808,7 @@ static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, tx_bi = &tx_ring->tx_bi[i]; } - /* set next_to_watch value indicating a packet is present */ - first->next_to_watch = tx_desc; + netdev_tx_sent_queue(txring_txq(tx_ring), first->bytecount); i++; if (i == tx_ring->count) @@ -2810,66 +2816,72 @@ static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, tx_ring->next_to_use = i; - netdev_tx_sent_queue(txring_txq(tx_ring), first->bytecount); i40e_maybe_stop_tx(tx_ring, DESC_NEEDED); + /* write last descriptor with EOP bit */ + td_cmd |= I40E_TX_DESC_CMD_EOP; + + /* We can OR these values together as they both are checked against + * 4 below and at this point desc_count will be used as a boolean value + * after this if/else block. + */ + desc_count |= ++tx_ring->packet_stride; + /* Algorithm to optimize tail and RS bit setting: - * if xmit_more is supported - * if xmit_more is true - * do not update tail and do not mark RS bit. - * if xmit_more is false and last xmit_more was false - * if every packet spanned less than 4 desc - * then set RS bit on 4th packet and update tail - * on every packet - * else - * update tail and set RS bit on every packet. - * if xmit_more is false and last_xmit_more was true - * update tail and set RS bit. + * if queue is stopped + * mark RS bit + * reset packet counter + * else if xmit_more is supported and is true + * advance packet counter to 4 + * reset desc_count to 0 * - * Optimization: wmb to be issued only in case of tail update. - * Also optimize the Descriptor WB path for RS bit with the same - * algorithm. + * if desc_count >= 4 + * mark RS bit + * reset packet counter + * if desc_count > 0 + * update tail * - * Note: If there are less than 4 packets + * Note: If there are less than 4 descriptors * pending and interrupts were disabled the service task will * trigger a force WB. */ - if (skb->xmit_more && - !netif_xmit_stopped(txring_txq(tx_ring))) { - tx_ring->flags |= I40E_TXR_FLAGS_LAST_XMIT_MORE_SET; - tail_bump = false; - } else if (!skb->xmit_more && - !netif_xmit_stopped(txring_txq(tx_ring)) && - (!(tx_ring->flags & I40E_TXR_FLAGS_LAST_XMIT_MORE_SET)) && - (tx_ring->packet_stride < WB_STRIDE) && - (desc_count < WB_STRIDE)) { - tx_ring->packet_stride++; - } else { + if (netif_xmit_stopped(txring_txq(tx_ring))) { + goto do_rs; + } else if (skb->xmit_more) { + /* set stride to arm on next packet and reset desc_count */ + tx_ring->packet_stride = WB_STRIDE; + desc_count = 0; + } else if (desc_count >= WB_STRIDE) { +do_rs: + /* write last descriptor with RS bit set */ + td_cmd |= I40E_TX_DESC_CMD_RS; tx_ring->packet_stride = 0; - tx_ring->flags &= ~I40E_TXR_FLAGS_LAST_XMIT_MORE_SET; - do_rs = true; } - if (do_rs) - tx_ring->packet_stride = 0; tx_desc->cmd_type_offset_bsz = - build_ctob(td_cmd, td_offset, size, td_tag) | - cpu_to_le64((u64)(do_rs ? I40E_TXD_CMD : - I40E_TX_DESC_CMD_EOP) << - I40E_TXD_QW1_CMD_SHIFT); + build_ctob(td_cmd, td_offset, size, td_tag); + + /* Force memory writes to complete before letting h/w know there + * are new descriptors to fetch. + * + * We also use this memory barrier to make certain all of the + * status bits have been updated before next_to_watch is written. + */ + wmb(); + + /* set next_to_watch value indicating a packet is present */ + first->next_to_watch = tx_desc; /* notify HW of packet */ - if (!tail_bump) { - prefetchw(tx_desc + 1); - } else { - /* Force memory writes to complete before letting h/w - * know there are new descriptors to fetch. (Only - * applicable for weak-ordered memory model archs, - * such as IA-64). - */ - wmb(); + if (desc_count) { writel(i, tx_ring->tail); + + /* we need this if more than one processor can write to our tail + * at a time, it synchronizes IO on IA64/Altix systems + */ + mmiowb(); } + return; dma_error: @@ -2915,8 +2927,10 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, count = i40e_xmit_descriptor_count(skb); if (i40e_chk_linearize(skb, count)) { - if (__skb_linearize(skb)) - goto out_drop; + if (__skb_linearize(skb)) { + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + } count = i40e_txd_use_count(skb->len); tx_ring->tx_stats.tx_linearize++; } @@ -2932,6 +2946,12 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, return NETDEV_TX_BUSY; } + /* record the location of the first descriptor for this packet */ + first = &tx_ring->tx_bi[tx_ring->next_to_use]; + first->skb = skb; + first->bytecount = skb->len; + first->gso_segs = 1; + /* prepare the xmit flags */ if (i40e_tx_prepare_vlan_flags(skb, tx_ring, &tx_flags)) goto out_drop; @@ -2939,16 +2959,13 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, /* obtain protocol of skb */ protocol = vlan_get_protocol(skb); - /* record the location of the first descriptor for this packet */ - first = &tx_ring->tx_bi[tx_ring->next_to_use]; - /* setup IPv4/IPv6 offloads */ if (protocol == htons(ETH_P_IP)) tx_flags |= I40E_TX_FLAGS_IPV4; else if (protocol == htons(ETH_P_IPV6)) tx_flags |= I40E_TX_FLAGS_IPV6; - tso = i40e_tso(skb, &hdr_len, &cd_type_cmd_tso_mss); + tso = i40e_tso(first, &hdr_len, &cd_type_cmd_tso_mss); if (tso < 0) goto out_drop; @@ -2986,7 +3003,8 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, return NETDEV_TX_OK; out_drop: - dev_kfree_skb_any(skb); + dev_kfree_skb_any(first->skb); + first->skb = NULL; return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 508840585645..f80979025c01 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -52,7 +52,20 @@ */ #define INTRL_ENA BIT(6) #define INTRL_REG_TO_USEC(intrl) ((intrl & ~INTRL_ENA) << 2) -#define INTRL_USEC_TO_REG(set) ((set) ? ((set) >> 2) | INTRL_ENA : 0) +/** + * i40e_intrl_usec_to_reg - convert interrupt rate limit to register + * @intrl: interrupt rate limit to convert + * + * This function converts a decimal interrupt rate limit to the appropriate + * register format expected by the firmware when setting interrupt rate limit. + */ +static inline u16 i40e_intrl_usec_to_reg(int intrl) +{ + if (intrl >> 2) + return ((intrl >> 2) | INTRL_ENA); + else + return 0; +} #define I40E_INTRL_8K 125 /* 8000 ints/sec */ #define I40E_INTRL_62K 16 /* 62500 ints/sec */ #define I40E_INTRL_83K 12 /* 83333 ints/sec */ @@ -173,26 +186,37 @@ static inline bool i40e_test_staterr(union i40e_rx_desc *rx_desc, #define I40E_MAX_DATA_PER_TXD_ALIGNED \ (I40E_MAX_DATA_PER_TXD & ~(I40E_MAX_READ_REQ_SIZE - 1)) -/* This ugly bit of math is equivalent to DIV_ROUNDUP(size, X) where X is - * the value I40E_MAX_DATA_PER_TXD_ALIGNED. It is needed due to the fact - * that 12K is not a power of 2 and division is expensive. It is used to - * approximate the number of descriptors used per linear buffer. Note - * that this will overestimate in some cases as it doesn't account for the - * fact that we will add up to 4K - 1 in aligning the 12K buffer, however - * the error should not impact things much as large buffers usually mean - * we will use fewer descriptors then there are frags in an skb. +/** + * i40e_txd_use_count - estimate the number of descriptors needed for Tx + * @size: transmit request size in bytes + * + * Due to hardware alignment restrictions (4K alignment), we need to + * assume that we can have no more than 12K of data per descriptor, even + * though each descriptor can take up to 16K - 1 bytes of aligned memory. + * Thus, we need to divide by 12K. But division is slow! Instead, + * we decompose the operation into shifts and one relatively cheap + * multiply operation. + * + * To divide by 12K, we first divide by 4K, then divide by 3: + * To divide by 4K, shift right by 12 bits + * To divide by 3, multiply by 85, then divide by 256 + * (Divide by 256 is done by shifting right by 8 bits) + * Finally, we add one to round up. Because 256 isn't an exact multiple of + * 3, we'll underestimate near each multiple of 12K. This is actually more + * accurate as we have 4K - 1 of wiggle room that we can fit into the last + * segment. For our purposes this is accurate out to 1M which is orders of + * magnitude greater than our largest possible GSO size. + * + * This would then be implemented as: + * return (((size >> 12) * 85) >> 8) + 1; + * + * Since multiplication and division are commutative, we can reorder + * operations into: + * return ((size * 85) >> 20) + 1; */ static inline unsigned int i40e_txd_use_count(unsigned int size) { - const unsigned int max = I40E_MAX_DATA_PER_TXD_ALIGNED; - const unsigned int reciprocal = ((1ull << 32) - 1 + (max / 2)) / max; - unsigned int adjust = ~(u32)0; - - /* if we rounded up on the reciprocal pull down the adjustment */ - if ((max * reciprocal) > adjust) - adjust = ~(u32)(reciprocal - 1); - - return (u32)((((u64)size * reciprocal) + adjust) >> 32); + return ((size * 85) >> 20) + 1; } /* Tx Descriptors needed, worst case */ @@ -229,7 +253,6 @@ struct i40e_tx_buffer { }; struct i40e_rx_buffer { - struct sk_buff *skb; dma_addr_t dma; struct page *page; unsigned int page_offset; @@ -307,15 +330,12 @@ struct i40e_ring { u8 atr_sample_rate; u8 atr_count; - unsigned long last_rx_timestamp; - bool ring_active; /* is ring online or not */ bool arm_wb; /* do something to arm write back */ u8 packet_stride; u16 flags; #define I40E_TXR_FLAGS_WB_ON_ITR BIT(0) -#define I40E_TXR_FLAGS_LAST_XMIT_MORE_SET BIT(2) /* stats structs */ struct i40e_queue_stats stats; @@ -333,6 +353,14 @@ struct i40e_ring { struct rcu_head rcu; /* to avoid race on free */ u16 next_to_alloc; + struct sk_buff *skb; /* When i40e_clean_rx_ring_irq() must + * return before it sees the EOP for + * the current packet, we save that skb + * here and resume receiving this + * packet the next time + * i40e_clean_rx_ring_irq() is called + * for this ring. + */ } ____cacheline_internodealigned_in_smp; enum i40e_latency_range { diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index bd5f13bef83c..939f9fdc8f85 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -90,14 +90,23 @@ enum i40e_debug_mask { I40E_DEBUG_ALL = 0xFFFFFFFF }; -#define I40E_MDIO_STCODE 0 -#define I40E_MDIO_OPCODE_ADDRESS 0 -#define I40E_MDIO_OPCODE_WRITE I40E_MASK(1, \ +#define I40E_MDIO_CLAUSE22_STCODE_MASK I40E_MASK(1, \ + I40E_GLGEN_MSCA_STCODE_SHIFT) +#define I40E_MDIO_CLAUSE22_OPCODE_WRITE_MASK I40E_MASK(1, \ I40E_GLGEN_MSCA_OPCODE_SHIFT) -#define I40E_MDIO_OPCODE_READ_INC_ADDR I40E_MASK(2, \ +#define I40E_MDIO_CLAUSE22_OPCODE_READ_MASK I40E_MASK(2, \ I40E_GLGEN_MSCA_OPCODE_SHIFT) -#define I40E_MDIO_OPCODE_READ I40E_MASK(3, \ + +#define I40E_MDIO_CLAUSE45_STCODE_MASK I40E_MASK(0, \ + I40E_GLGEN_MSCA_STCODE_SHIFT) +#define I40E_MDIO_CLAUSE45_OPCODE_ADDRESS_MASK I40E_MASK(0, \ + I40E_GLGEN_MSCA_OPCODE_SHIFT) +#define I40E_MDIO_CLAUSE45_OPCODE_WRITE_MASK I40E_MASK(1, \ I40E_GLGEN_MSCA_OPCODE_SHIFT) +#define I40E_MDIO_CLAUSE45_OPCODE_READ_INC_ADDR_MASK I40E_MASK(2, \ + I40E_GLGEN_MSCA_OPCODE_SHIFT) +#define I40E_MDIO_CLAUSE45_OPCODE_READ_MASK I40E_MASK(3, \ + I40E_GLGEN_MSCA_OPCODE_SHIFT) #define I40E_PHY_COM_REG_PAGE 0x1E #define I40E_PHY_LED_LINK_MODE_MASK 0xF0 @@ -116,7 +125,6 @@ enum i40e_debug_mask { */ enum i40e_mac_type { I40E_MAC_UNKNOWN = 0, - I40E_MAC_X710, I40E_MAC_XL710, I40E_MAC_VF, I40E_MAC_X722, @@ -176,6 +184,7 @@ struct i40e_link_status { enum i40e_aq_link_speed link_speed; u8 link_info; u8 an_info; + u8 fec_info; u8 ext_info; u8 loopback; /* is Link Status Event notification to SW enabled */ @@ -204,47 +213,59 @@ struct i40e_link_status { #define I40E_MODULE_TYPE_1000BASE_T 0x08 }; -enum i40e_aq_capabilities_phy_type { - I40E_CAP_PHY_TYPE_SGMII = BIT(I40E_PHY_TYPE_SGMII), - I40E_CAP_PHY_TYPE_1000BASE_KX = BIT(I40E_PHY_TYPE_1000BASE_KX), - I40E_CAP_PHY_TYPE_10GBASE_KX4 = BIT(I40E_PHY_TYPE_10GBASE_KX4), - I40E_CAP_PHY_TYPE_10GBASE_KR = BIT(I40E_PHY_TYPE_10GBASE_KR), - I40E_CAP_PHY_TYPE_40GBASE_KR4 = BIT(I40E_PHY_TYPE_40GBASE_KR4), - I40E_CAP_PHY_TYPE_XAUI = BIT(I40E_PHY_TYPE_XAUI), - I40E_CAP_PHY_TYPE_XFI = BIT(I40E_PHY_TYPE_XFI), - I40E_CAP_PHY_TYPE_SFI = BIT(I40E_PHY_TYPE_SFI), - I40E_CAP_PHY_TYPE_XLAUI = BIT(I40E_PHY_TYPE_XLAUI), - I40E_CAP_PHY_TYPE_XLPPI = BIT(I40E_PHY_TYPE_XLPPI), - I40E_CAP_PHY_TYPE_40GBASE_CR4_CU = BIT(I40E_PHY_TYPE_40GBASE_CR4_CU), - I40E_CAP_PHY_TYPE_10GBASE_CR1_CU = BIT(I40E_PHY_TYPE_10GBASE_CR1_CU), - I40E_CAP_PHY_TYPE_10GBASE_AOC = BIT(I40E_PHY_TYPE_10GBASE_AOC), - I40E_CAP_PHY_TYPE_40GBASE_AOC = BIT(I40E_PHY_TYPE_40GBASE_AOC), - I40E_CAP_PHY_TYPE_100BASE_TX = BIT(I40E_PHY_TYPE_100BASE_TX), - I40E_CAP_PHY_TYPE_1000BASE_T = BIT(I40E_PHY_TYPE_1000BASE_T), - I40E_CAP_PHY_TYPE_10GBASE_T = BIT(I40E_PHY_TYPE_10GBASE_T), - I40E_CAP_PHY_TYPE_10GBASE_SR = BIT(I40E_PHY_TYPE_10GBASE_SR), - I40E_CAP_PHY_TYPE_10GBASE_LR = BIT(I40E_PHY_TYPE_10GBASE_LR), - I40E_CAP_PHY_TYPE_10GBASE_SFPP_CU = BIT(I40E_PHY_TYPE_10GBASE_SFPP_CU), - I40E_CAP_PHY_TYPE_10GBASE_CR1 = BIT(I40E_PHY_TYPE_10GBASE_CR1), - I40E_CAP_PHY_TYPE_40GBASE_CR4 = BIT(I40E_PHY_TYPE_40GBASE_CR4), - I40E_CAP_PHY_TYPE_40GBASE_SR4 = BIT(I40E_PHY_TYPE_40GBASE_SR4), - I40E_CAP_PHY_TYPE_40GBASE_LR4 = BIT(I40E_PHY_TYPE_40GBASE_LR4), - I40E_CAP_PHY_TYPE_1000BASE_SX = BIT(I40E_PHY_TYPE_1000BASE_SX), - I40E_CAP_PHY_TYPE_1000BASE_LX = BIT(I40E_PHY_TYPE_1000BASE_LX), - I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL = - BIT(I40E_PHY_TYPE_1000BASE_T_OPTICAL), - I40E_CAP_PHY_TYPE_20GBASE_KR2 = BIT(I40E_PHY_TYPE_20GBASE_KR2) -}; - struct i40e_phy_info { struct i40e_link_status link_info; struct i40e_link_status link_info_old; bool get_link_info; enum i40e_media_type media_type; /* all the phy types the NVM is capable of */ - enum i40e_aq_capabilities_phy_type phy_types; -}; - + u64 phy_types; +}; + +#define I40E_CAP_PHY_TYPE_SGMII BIT_ULL(I40E_PHY_TYPE_SGMII) +#define I40E_CAP_PHY_TYPE_1000BASE_KX BIT_ULL(I40E_PHY_TYPE_1000BASE_KX) +#define I40E_CAP_PHY_TYPE_10GBASE_KX4 BIT_ULL(I40E_PHY_TYPE_10GBASE_KX4) +#define I40E_CAP_PHY_TYPE_10GBASE_KR BIT_ULL(I40E_PHY_TYPE_10GBASE_KR) +#define I40E_CAP_PHY_TYPE_40GBASE_KR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_KR4) +#define I40E_CAP_PHY_TYPE_XAUI BIT_ULL(I40E_PHY_TYPE_XAUI) +#define I40E_CAP_PHY_TYPE_XFI BIT_ULL(I40E_PHY_TYPE_XFI) +#define I40E_CAP_PHY_TYPE_SFI BIT_ULL(I40E_PHY_TYPE_SFI) +#define I40E_CAP_PHY_TYPE_XLAUI BIT_ULL(I40E_PHY_TYPE_XLAUI) +#define I40E_CAP_PHY_TYPE_XLPPI BIT_ULL(I40E_PHY_TYPE_XLPPI) +#define I40E_CAP_PHY_TYPE_40GBASE_CR4_CU BIT_ULL(I40E_PHY_TYPE_40GBASE_CR4_CU) +#define I40E_CAP_PHY_TYPE_10GBASE_CR1_CU BIT_ULL(I40E_PHY_TYPE_10GBASE_CR1_CU) +#define I40E_CAP_PHY_TYPE_10GBASE_AOC BIT_ULL(I40E_PHY_TYPE_10GBASE_AOC) +#define I40E_CAP_PHY_TYPE_40GBASE_AOC BIT_ULL(I40E_PHY_TYPE_40GBASE_AOC) +#define I40E_CAP_PHY_TYPE_100BASE_TX BIT_ULL(I40E_PHY_TYPE_100BASE_TX) +#define I40E_CAP_PHY_TYPE_1000BASE_T BIT_ULL(I40E_PHY_TYPE_1000BASE_T) +#define I40E_CAP_PHY_TYPE_10GBASE_T BIT_ULL(I40E_PHY_TYPE_10GBASE_T) +#define I40E_CAP_PHY_TYPE_10GBASE_SR BIT_ULL(I40E_PHY_TYPE_10GBASE_SR) +#define I40E_CAP_PHY_TYPE_10GBASE_LR BIT_ULL(I40E_PHY_TYPE_10GBASE_LR) +#define I40E_CAP_PHY_TYPE_10GBASE_SFPP_CU BIT_ULL(I40E_PHY_TYPE_10GBASE_SFPP_CU) +#define I40E_CAP_PHY_TYPE_10GBASE_CR1 BIT_ULL(I40E_PHY_TYPE_10GBASE_CR1) +#define I40E_CAP_PHY_TYPE_40GBASE_CR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_CR4) +#define I40E_CAP_PHY_TYPE_40GBASE_SR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_SR4) +#define I40E_CAP_PHY_TYPE_40GBASE_LR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_LR4) +#define I40E_CAP_PHY_TYPE_1000BASE_SX BIT_ULL(I40E_PHY_TYPE_1000BASE_SX) +#define I40E_CAP_PHY_TYPE_1000BASE_LX BIT_ULL(I40E_PHY_TYPE_1000BASE_LX) +#define I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL \ + BIT_ULL(I40E_PHY_TYPE_1000BASE_T_OPTICAL) +#define I40E_CAP_PHY_TYPE_20GBASE_KR2 BIT_ULL(I40E_PHY_TYPE_20GBASE_KR2) +/* Defining the macro I40E_TYPE_OFFSET to implement a bit shift for some + * PHY types. There is an unused bit (31) in the I40E_CAP_PHY_TYPE_* bit + * fields but no corresponding gap in the i40e_aq_phy_type enumeration. So, + * a shift is needed to adjust for this with values larger than 31. The + * only affected values are I40E_PHY_TYPE_25GBASE_*. + */ +#define I40E_PHY_TYPE_OFFSET 1 +#define I40E_CAP_PHY_TYPE_25GBASE_KR BIT_ULL(I40E_PHY_TYPE_25GBASE_KR + \ + I40E_PHY_TYPE_OFFSET) +#define I40E_CAP_PHY_TYPE_25GBASE_CR BIT_ULL(I40E_PHY_TYPE_25GBASE_CR + \ + I40E_PHY_TYPE_OFFSET) +#define I40E_CAP_PHY_TYPE_25GBASE_SR BIT_ULL(I40E_PHY_TYPE_25GBASE_SR + \ + I40E_PHY_TYPE_OFFSET) +#define I40E_CAP_PHY_TYPE_25GBASE_LR BIT_ULL(I40E_PHY_TYPE_25GBASE_LR + \ + I40E_PHY_TYPE_OFFSET) #define I40E_HW_CAP_MAX_GPIO 30 /* Capabilities of a PF or a VF or the whole device */ struct i40e_hw_capabilities { @@ -254,6 +275,10 @@ struct i40e_hw_capabilities { #define I40E_NVM_IMAGE_TYPE_UDP_CLOUD 0x3 u32 management_mode; + u32 mng_protocols_over_mctp; +#define I40E_MNG_PROTOCOL_PLDM 0x2 +#define I40E_MNG_PROTOCOL_OEM_COMMANDS 0x4 +#define I40E_MNG_PROTOCOL_NCSI 0x8 u32 npar_enable; u32 os2bmc; u32 valid_functions; @@ -366,6 +391,7 @@ enum i40e_nvmupd_state { I40E_NVMUPD_STATE_WRITING, I40E_NVMUPD_STATE_INIT_WAIT, I40E_NVMUPD_STATE_WRITE_WAIT, + I40E_NVMUPD_STATE_ERROR }; /* nvm_access definition and its masks/shifts need to be accessible to @@ -444,6 +470,7 @@ struct i40e_bus_info { u16 func; u16 device; u16 lan_id; + u16 bus_id; }; /* Flow control (FC) parameters */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h index f861d3109d1a..974ba2baf6ea 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h @@ -165,6 +165,10 @@ struct i40e_virtchnl_vsi_resource { #define I40E_VIRTCHNL_VF_OFFLOAD_RSS_PF 0X00080000 #define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM 0X00100000 +#define I40E_VF_BASE_MODE_OFFLOADS (I40E_VIRTCHNL_VF_OFFLOAD_L2 | \ + I40E_VIRTCHNL_VF_OFFLOAD_VLAN | \ + I40E_VIRTCHNL_VF_OFFLOAD_RSS_PF) + struct i40e_virtchnl_vf_resource { u16 num_vsis; u16 num_queue_pairs; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 54b8ee2583f1..78460c52b7c4 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -674,6 +674,7 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type) } if (type == I40E_VSI_SRIOV) { u64 hena = i40e_pf_get_default_rss_hena(pf); + u8 broadcast[ETH_ALEN]; vf->lan_vsi_idx = vsi->idx; vf->lan_vsi_id = vsi->id; @@ -686,17 +687,21 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type) if (vf->port_vlan_id) i40e_vsi_add_pvid(vsi, vf->port_vlan_id); - spin_lock_bh(&vsi->mac_filter_list_lock); + spin_lock_bh(&vsi->mac_filter_hash_lock); if (is_valid_ether_addr(vf->default_lan_addr.addr)) { - f = i40e_add_filter(vsi, vf->default_lan_addr.addr, - vf->port_vlan_id ? vf->port_vlan_id : -1, - true, false); + f = i40e_add_mac_filter(vsi, + vf->default_lan_addr.addr); if (!f) dev_info(&pf->pdev->dev, "Could not add MAC filter %pM for VF %d\n", vf->default_lan_addr.addr, vf->vf_id); } - spin_unlock_bh(&vsi->mac_filter_list_lock); + eth_broadcast_addr(broadcast); + f = i40e_add_mac_filter(vsi, broadcast); + if (!f) + dev_info(&pf->pdev->dev, + "Could not allocate VF broadcast filter\n"); + spin_unlock_bh(&vsi->mac_filter_hash_lock); i40e_write_rx_ctl(&pf->hw, I40E_VFQF_HENA1(0, vf->vf_id), (u32)hena); i40e_write_rx_ctl(&pf->hw, I40E_VFQF_HENA1(1, vf->vf_id), @@ -811,6 +816,7 @@ static void i40e_free_vf_res(struct i40e_vf *vf) i40e_vsi_release(pf->vsi[vf->lan_vsi_idx]); vf->lan_vsi_idx = 0; vf->lan_vsi_id = 0; + vf->num_mac = 0; } msix_vf = pf->hw.func_caps.num_msix_vectors_vf; @@ -841,9 +847,7 @@ static void i40e_free_vf_res(struct i40e_vf *vf) wr32(hw, reg_idx, reg); i40e_flush(hw); } - /* reset some of the state varibles keeping - * track of the resources - */ + /* reset some of the state variables keeping track of the resources */ vf->num_queue_pairs = 0; vf->vf_states = 0; clear_bit(I40E_VF_STAT_INIT, &vf->vf_states); @@ -990,7 +994,7 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr) if (vf->lan_vsi_idx == 0) goto complete_reset; - i40e_vsi_control_rings(pf->vsi[vf->lan_vsi_idx], false); + i40e_vsi_stop_rings(pf->vsi[vf->lan_vsi_idx]); complete_reset: /* reallocate VF resources to reset the VSI state */ i40e_free_vf_res(vf); @@ -1031,8 +1035,7 @@ void i40e_free_vfs(struct i40e_pf *pf) i40e_notify_client_of_vf_enable(pf, 0); for (i = 0; i < pf->num_alloc_vfs; i++) if (test_bit(I40E_VF_STAT_INIT, &pf->vf[i].vf_states)) - i40e_vsi_control_rings(pf->vsi[pf->vf[i].lan_vsi_idx], - false); + i40e_vsi_stop_rings(pf->vsi[pf->vf[i].lan_vsi_idx]); /* Disable IOV before freeing resources. This lets any VF drivers * running in the host get themselves cleaned up before we yank @@ -1449,9 +1452,9 @@ static void i40e_vc_reset_vf_msg(struct i40e_vf *vf) static inline int i40e_getnum_vf_vsi_vlan_filters(struct i40e_vsi *vsi) { struct i40e_mac_filter *f; - int num_vlans = 0; + int num_vlans = 0, bkt; - list_for_each_entry(f, &vsi->mac_filter_list, list) { + hash_for_each(vsi->mac_filter_hash, bkt, f, hlist) { if (f->vlan >= 0 && f->vlan <= I40E_MAX_VLANID) num_vlans++; } @@ -1481,6 +1484,7 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, struct i40e_vsi *vsi; bool alluni = false; int aq_err = 0; + int bkt; vsi = i40e_find_vsi_from_id(pf, info->vsi_id); if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states) || @@ -1507,7 +1511,7 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, vf->port_vlan_id, NULL); } else if (i40e_getnum_vf_vsi_vlan_filters(vsi)) { - list_for_each_entry(f, &vsi->mac_filter_list, list) { + hash_for_each(vsi->mac_filter_hash, bkt, f, hlist) { if (f->vlan < 0 || f->vlan > I40E_MAX_VLANID) continue; aq_ret = i40e_aq_set_vsi_mc_promisc_on_vlan(hw, @@ -1535,7 +1539,7 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, vf->vf_id, i40e_stat_str(&pf->hw, aq_ret), i40e_aq_str(&pf->hw, aq_err)); - goto error_param_int; + goto error_param; } } @@ -1557,7 +1561,7 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, vf->port_vlan_id, NULL); } else if (i40e_getnum_vf_vsi_vlan_filters(vsi)) { - list_for_each_entry(f, &vsi->mac_filter_list, list) { + hash_for_each(vsi->mac_filter_hash, bkt, f, hlist) { aq_ret = 0; if (f->vlan >= 0 && f->vlan <= I40E_MAX_VLANID) { aq_ret = @@ -1580,15 +1584,16 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, allmulti, NULL, true); aq_err = pf->hw.aq.asq_last_status; - if (aq_ret) + if (aq_ret) { dev_err(&pf->pdev->dev, "VF %d failed to set unicast promiscuous mode %8.8x err %s aq_err %s\n", vf->vf_id, info->flags, i40e_stat_str(&pf->hw, aq_ret), i40e_aq_str(&pf->hw, aq_err)); + goto error_param; + } } -error_param_int: if (!aq_ret) { dev_info(&pf->pdev->dev, "VF %d successfully set unicast promiscuous mode\n", @@ -1757,7 +1762,7 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) goto error_param; } - if (i40e_vsi_control_rings(pf->vsi[vf->lan_vsi_idx], true)) + if (i40e_vsi_start_rings(pf->vsi[vf->lan_vsi_idx])) aq_ret = I40E_ERR_TIMEOUT; error_param: /* send the response to the VF */ @@ -1796,8 +1801,7 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) goto error_param; } - if (i40e_vsi_control_rings(pf->vsi[vf->lan_vsi_idx], false)) - aq_ret = I40E_ERR_TIMEOUT; + i40e_vsi_stop_rings(pf->vsi[vf->lan_vsi_idx]); error_param: /* send the response to the VF */ @@ -1927,34 +1931,28 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) /* Lock once, because all function inside for loop accesses VSI's * MAC filter list which needs to be protected using same lock. */ - spin_lock_bh(&vsi->mac_filter_list_lock); + spin_lock_bh(&vsi->mac_filter_hash_lock); /* add new addresses to the list */ for (i = 0; i < al->num_elements; i++) { struct i40e_mac_filter *f; - f = i40e_find_mac(vsi, al->list[i].addr, true, false); - if (!f) { - if (i40e_is_vsi_in_vlan(vsi)) - f = i40e_put_mac_in_vlan(vsi, al->list[i].addr, - true, false); - else - f = i40e_add_filter(vsi, al->list[i].addr, -1, - true, false); - } + f = i40e_find_mac(vsi, al->list[i].addr); + if (!f) + f = i40e_add_mac_filter(vsi, al->list[i].addr); if (!f) { dev_err(&pf->pdev->dev, "Unable to add MAC filter %pM for VF %d\n", al->list[i].addr, vf->vf_id); ret = I40E_ERR_PARAM; - spin_unlock_bh(&vsi->mac_filter_list_lock); + spin_unlock_bh(&vsi->mac_filter_hash_lock); goto error_param; } else { vf->num_mac++; } } - spin_unlock_bh(&vsi->mac_filter_list_lock); + spin_unlock_bh(&vsi->mac_filter_hash_lock); /* program the updated filter list */ ret = i40e_sync_vsi_filters(vsi); @@ -2003,18 +2001,18 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) } vsi = pf->vsi[vf->lan_vsi_idx]; - spin_lock_bh(&vsi->mac_filter_list_lock); + spin_lock_bh(&vsi->mac_filter_hash_lock); /* delete addresses from the list */ for (i = 0; i < al->num_elements; i++) - if (i40e_del_mac_all_vlan(vsi, al->list[i].addr, true, false)) { + if (i40e_del_mac_filter(vsi, al->list[i].addr)) { ret = I40E_ERR_INVALID_MAC_ADDR; - spin_unlock_bh(&vsi->mac_filter_list_lock); + spin_unlock_bh(&vsi->mac_filter_hash_lock); goto error_param; } else { vf->num_mac--; } - spin_unlock_bh(&vsi->mac_filter_list_lock); + spin_unlock_bh(&vsi->mac_filter_hash_lock); /* program the updated filter list */ ret = i40e_sync_vsi_filters(vsi); @@ -2139,9 +2137,8 @@ static int i40e_vc_remove_vlan_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) } for (i = 0; i < vfl->num_elements; i++) { - int ret = i40e_vsi_kill_vlan(vsi, vfl->vlan_id[i]); - if (!ret) - vf->num_vlan--; + i40e_vsi_kill_vlan(vsi, vfl->vlan_id[i]); + vf->num_vlan--; if (test_bit(I40E_VF_STAT_UC_PROMISC, &vf->vf_states)) i40e_aq_set_vsi_uc_promisc_on_vlan(&pf->hw, vsi->seid, @@ -2153,11 +2150,6 @@ static int i40e_vc_remove_vlan_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) false, vfl->vlan_id[i], NULL); - - if (ret) - dev_err(&pf->pdev->dev, - "Unable to delete VLAN filter %d for VF %d, error %d\n", - vfl->vlan_id[i], vf->vf_id, ret); } error_param: @@ -2689,6 +2681,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) struct i40e_mac_filter *f; struct i40e_vf *vf; int ret = 0; + int bkt; /* validate the request */ if (vf_id >= pf->num_alloc_vfs) { @@ -2715,23 +2708,21 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) } /* Lock once because below invoked function add/del_filter requires - * mac_filter_list_lock to be held + * mac_filter_hash_lock to be held */ - spin_lock_bh(&vsi->mac_filter_list_lock); + spin_lock_bh(&vsi->mac_filter_hash_lock); /* delete the temporary mac address */ if (!is_zero_ether_addr(vf->default_lan_addr.addr)) - i40e_del_filter(vsi, vf->default_lan_addr.addr, - vf->port_vlan_id ? vf->port_vlan_id : -1, - true, false); + i40e_del_mac_filter(vsi, vf->default_lan_addr.addr); /* Delete all the filters for this VSI - we're going to kill it * anyway. */ - list_for_each_entry(f, &vsi->mac_filter_list, list) - i40e_del_filter(vsi, f->macaddr, f->vlan, true, false); + hash_for_each(vsi->mac_filter_hash, bkt, f, hlist) + __i40e_del_filter(vsi, f); - spin_unlock_bh(&vsi->mac_filter_list_lock); + spin_unlock_bh(&vsi->mac_filter_hash_lock); dev_info(&pf->pdev->dev, "Setting MAC %pM on VF %d\n", mac, vf_id); /* program mac filter */ @@ -2766,7 +2757,6 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlanprio = vlan_id | (qos << I40E_VLAN_PRIORITY_SHIFT); struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_pf *pf = np->vsi->back; - bool is_vsi_in_vlan = false; struct i40e_vsi *vsi; struct i40e_vf *vf; int ret = 0; @@ -2803,11 +2793,10 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, /* duplicate request, so just return success */ goto error_pvid; - spin_lock_bh(&vsi->mac_filter_list_lock); - is_vsi_in_vlan = i40e_is_vsi_in_vlan(vsi); - spin_unlock_bh(&vsi->mac_filter_list_lock); + /* Locked once because multiple functions below iterate list */ + spin_lock_bh(&vsi->mac_filter_hash_lock); - if (le16_to_cpu(vsi->info.pvid) == 0 && is_vsi_in_vlan) { + if (le16_to_cpu(vsi->info.pvid) == 0 && i40e_is_vsi_in_vlan(vsi)) { dev_err(&pf->pdev->dev, "VF %d has already configured VLAN filters and the administrator is requesting a port VLAN override.\nPlease unload and reload the VF driver for this change to take effect.\n", vf_id); @@ -2830,19 +2819,23 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, */ if ((!(vlan_id || qos) || vlanprio != le16_to_cpu(vsi->info.pvid)) && - vsi->info.pvid) - ret = i40e_vsi_add_vlan(vsi, I40E_VLAN_ANY); - - if (vsi->info.pvid) { - /* kill old VLAN */ - ret = i40e_vsi_kill_vlan(vsi, (le16_to_cpu(vsi->info.pvid) & - VLAN_VID_MASK)); + vsi->info.pvid) { + ret = i40e_add_vlan_all_mac(vsi, I40E_VLAN_ANY); if (ret) { dev_info(&vsi->back->pdev->dev, - "remove VLAN failed, ret=%d, aq_err=%d\n", - ret, pf->hw.aq.asq_last_status); + "add VF VLAN failed, ret=%d aq_err=%d\n", ret, + vsi->back->hw.aq.asq_last_status); + spin_unlock_bh(&vsi->mac_filter_hash_lock); + goto error_pvid; } } + + if (vsi->info.pvid) { + /* remove all filters on the old VLAN */ + i40e_rm_vlan_all_mac(vsi, (le16_to_cpu(vsi->info.pvid) & + VLAN_VID_MASK)); + } + if (vlan_id || qos) ret = i40e_vsi_add_pvid(vsi, vlanprio); else @@ -2852,24 +2845,30 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, dev_info(&pf->pdev->dev, "Setting VLAN %d, QOS 0x%x on VF %d\n", vlan_id, qos, vf_id); - /* add new VLAN filter */ - ret = i40e_vsi_add_vlan(vsi, vlan_id); + /* add new VLAN filter for each MAC */ + ret = i40e_add_vlan_all_mac(vsi, vlan_id); if (ret) { dev_info(&vsi->back->pdev->dev, "add VF VLAN failed, ret=%d aq_err=%d\n", ret, vsi->back->hw.aq.asq_last_status); + spin_unlock_bh(&vsi->mac_filter_hash_lock); goto error_pvid; } - /* Kill non-vlan MAC filters - ignore error return since - * there might not be any non-vlan MAC filters. - */ - i40e_vsi_kill_vlan(vsi, I40E_VLAN_ANY); + + /* remove the previously added non-VLAN MAC filters */ + i40e_rm_vlan_all_mac(vsi, I40E_VLAN_ANY); } + spin_unlock_bh(&vsi->mac_filter_hash_lock); + + /* Schedule the worker thread to take care of applying changes */ + i40e_service_event_schedule(vsi->back); + if (ret) { dev_err(&pf->pdev->dev, "Unable to update VF vsi context\n"); goto error_pvid; } + /* The Port VLAN needs to be saved across resets the same as the * default LAN MAC address. */ @@ -2926,6 +2925,9 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, case I40E_LINK_SPEED_40GB: speed = 40000; break; + case I40E_LINK_SPEED_25GB: + speed = 25000; + break; case I40E_LINK_SPEED_20GB: speed = 20000; break; @@ -2940,7 +2942,7 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, } if (max_tx_rate > speed) { - dev_err(&pf->pdev->dev, "Invalid max tx rate %d specified for VF %d.", + dev_err(&pf->pdev->dev, "Invalid max tx rate %d specified for VF %d.\n", max_tx_rate, vf->vf_id); ret = -EINVAL; goto error; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c index 44f7ed7583dd..96385156b824 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c @@ -912,11 +912,11 @@ i40e_status i40evf_clean_arq_element(struct i40e_hw *hw, desc = I40E_ADMINQ_DESC(hw->aq.arq, ntc); desc_idx = ntc; + hw->aq.arq_last_status = + (enum i40e_admin_queue_err)le16_to_cpu(desc->retval); flags = le16_to_cpu(desc->flags); if (flags & I40E_AQ_FLAG_ERR) { ret_code = I40E_ERR_ADMIN_QUEUE_ERROR; - hw->aq.arq_last_status = - (enum i40e_admin_queue_err)le16_to_cpu(desc->retval); i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQRX: Event received with error 0x%X.\n", diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h index 40b0eafd0c71..eeb9864bc5b1 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h @@ -1639,6 +1639,10 @@ enum i40e_aq_phy_type { I40E_PHY_TYPE_1000BASE_LX = 0x1C, I40E_PHY_TYPE_1000BASE_T_OPTICAL = 0x1D, I40E_PHY_TYPE_20GBASE_KR2 = 0x1E, + I40E_PHY_TYPE_25GBASE_KR = 0x1F, + I40E_PHY_TYPE_25GBASE_CR = 0x20, + I40E_PHY_TYPE_25GBASE_SR = 0x21, + I40E_PHY_TYPE_25GBASE_LR = 0x22, I40E_PHY_TYPE_MAX }; @@ -1647,6 +1651,7 @@ enum i40e_aq_phy_type { #define I40E_LINK_SPEED_10GB_SHIFT 0x3 #define I40E_LINK_SPEED_40GB_SHIFT 0x4 #define I40E_LINK_SPEED_20GB_SHIFT 0x5 +#define I40E_LINK_SPEED_25GB_SHIFT 0x6 enum i40e_aq_link_speed { I40E_LINK_SPEED_UNKNOWN = 0, @@ -1654,7 +1659,8 @@ enum i40e_aq_link_speed { I40E_LINK_SPEED_1GB = BIT(I40E_LINK_SPEED_1000MB_SHIFT), I40E_LINK_SPEED_10GB = BIT(I40E_LINK_SPEED_10GB_SHIFT), I40E_LINK_SPEED_40GB = BIT(I40E_LINK_SPEED_40GB_SHIFT), - I40E_LINK_SPEED_20GB = BIT(I40E_LINK_SPEED_20GB_SHIFT) + I40E_LINK_SPEED_20GB = BIT(I40E_LINK_SPEED_20GB_SHIFT), + I40E_LINK_SPEED_25GB = BIT(I40E_LINK_SPEED_25GB_SHIFT), }; struct i40e_aqc_module_desc { @@ -1677,6 +1683,8 @@ struct i40e_aq_get_phy_abilities_resp { #define I40E_AQ_PHY_LINK_ENABLED 0x08 #define I40E_AQ_PHY_AN_ENABLED 0x10 #define I40E_AQ_PHY_FLAG_MODULE_QUAL 0x20 +#define I40E_AQ_PHY_FEC_ABILITY_KR 0x40 +#define I40E_AQ_PHY_FEC_ABILITY_RS 0x80 __le16 eee_capability; #define I40E_AQ_EEE_100BASE_TX 0x0002 #define I40E_AQ_EEE_1000BASE_T 0x0004 @@ -1687,7 +1695,22 @@ struct i40e_aq_get_phy_abilities_resp { __le32 eeer_val; u8 d3_lpan; #define I40E_AQ_SET_PHY_D3_LPAN_ENA 0x01 - u8 reserved[3]; + u8 phy_type_ext; +#define I40E_AQ_PHY_TYPE_EXT_25G_KR 0X01 +#define I40E_AQ_PHY_TYPE_EXT_25G_CR 0X02 +#define I40E_AQ_PHY_TYPE_EXT_25G_SR 0x04 +#define I40E_AQ_PHY_TYPE_EXT_25G_LR 0x08 + u8 fec_cfg_curr_mod_ext_info; +#define I40E_AQ_ENABLE_FEC_KR 0x01 +#define I40E_AQ_ENABLE_FEC_RS 0x02 +#define I40E_AQ_REQUEST_FEC_KR 0x04 +#define I40E_AQ_REQUEST_FEC_RS 0x08 +#define I40E_AQ_ENABLE_FEC_AUTO 0x10 +#define I40E_AQ_FEC +#define I40E_AQ_MODULE_TYPE_EXT_MASK 0xE0 +#define I40E_AQ_MODULE_TYPE_EXT_SHIFT 5 + + u8 ext_comp_code; u8 phy_id[4]; u8 module_type[3]; u8 qualified_module_count; @@ -1709,7 +1732,20 @@ struct i40e_aq_set_phy_config { /* same bits as above in all */ __le16 eee_capability; __le32 eeer; u8 low_power_ctrl; - u8 reserved[3]; + u8 phy_type_ext; +#define I40E_AQ_PHY_TYPE_EXT_25G_KR 0X01 +#define I40E_AQ_PHY_TYPE_EXT_25G_CR 0X02 +#define I40E_AQ_PHY_TYPE_EXT_25G_SR 0x04 +#define I40E_AQ_PHY_TYPE_EXT_25G_LR 0x08 + u8 fec_config; +#define I40E_AQ_SET_FEC_ABILITY_KR BIT(0) +#define I40E_AQ_SET_FEC_ABILITY_RS BIT(1) +#define I40E_AQ_SET_FEC_REQUEST_KR BIT(2) +#define I40E_AQ_SET_FEC_REQUEST_RS BIT(3) +#define I40E_AQ_SET_FEC_AUTO BIT(4) +#define I40E_AQ_PHY_FEC_CONFIG_SHIFT 0x0 +#define I40E_AQ_PHY_FEC_CONFIG_MASK (0x1F << I40E_AQ_PHY_FEC_CONFIG_SHIFT) + u8 reserved; }; I40E_CHECK_CMD_LENGTH(i40e_aq_set_phy_config); @@ -1789,9 +1825,18 @@ struct i40e_aqc_get_link_status { #define I40E_AQ_LINK_TX_DRAINED 0x01 #define I40E_AQ_LINK_TX_FLUSHED 0x03 #define I40E_AQ_LINK_FORCED_40G 0x10 +/* 25G Error Codes */ +#define I40E_AQ_25G_NO_ERR 0X00 +#define I40E_AQ_25G_NOT_PRESENT 0X01 +#define I40E_AQ_25G_NVM_CRC_ERR 0X02 +#define I40E_AQ_25G_SBUS_UCODE_ERR 0X03 +#define I40E_AQ_25G_SERDES_UCODE_ERR 0X04 +#define I40E_AQ_25G_NIMB_UCODE_ERR 0X05 u8 loopback; /* use defines from i40e_aqc_set_lb_mode */ __le16 max_frame_size; u8 config; +#define I40E_AQ_CONFIG_FEC_KR_ENA 0x01 +#define I40E_AQ_CONFIG_FEC_RS_ENA 0x02 #define I40E_AQ_CONFIG_CRC_ENA 0x04 #define I40E_AQ_CONFIG_PACING_MASK 0x78 u8 external_power_ability; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c index 7953c13451b9..89dfdbca13db 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_common.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c @@ -53,6 +53,8 @@ i40e_status i40e_set_mac_type(struct i40e_hw *hw) case I40E_DEV_ID_10G_BASE_T4: case I40E_DEV_ID_20G_KR2: case I40E_DEV_ID_20G_KR2_A: + case I40E_DEV_ID_25G_B: + case I40E_DEV_ID_25G_SFP28: hw->mac.type = I40E_MAC_XL710; break; case I40E_DEV_ID_SFP_X722: @@ -62,7 +64,6 @@ i40e_status i40e_set_mac_type(struct i40e_hw *hw) hw->mac.type = I40E_MAC_X722; break; case I40E_DEV_ID_X722_VF: - case I40E_DEV_ID_X722_VF_HV: hw->mac.type = I40E_MAC_X722_VF; break; case I40E_DEV_ID_VF: @@ -303,7 +304,6 @@ void i40evf_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, void *desc, { struct i40e_aq_desc *aq_desc = (struct i40e_aq_desc *)desc; u8 *buf = (u8 *)buffer; - u16 i = 0; if ((!(mask & hw->debug_mask)) || (desc == NULL)) return; @@ -331,12 +331,18 @@ void i40evf_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, void *desc, if (buf_len < len) len = buf_len; /* write the full 16-byte chunks */ - for (i = 0; i < (len - 16); i += 16) - i40e_debug(hw, mask, "\t0x%04X %16ph\n", i, buf + i); - /* write whatever's left over without overrunning the buffer */ - if (i < len) - i40e_debug(hw, mask, "\t0x%04X %*ph\n", - i, len - i, buf + i); + if (hw->debug_mask & mask) { + char prefix[20]; + + snprintf(prefix, 20, + "i40evf %02x:%02x.%x: \t0x", + hw->bus.bus_id, + hw->bus.device, + hw->bus.func); + + print_hex_dump(KERN_INFO, prefix, DUMP_PREFIX_OFFSET, + 16, 1, buf, len, false); + } } } diff --git a/drivers/net/ethernet/intel/i40evf/i40e_devids.h b/drivers/net/ethernet/intel/i40evf/i40e_devids.h index 70235706915e..d76393c95056 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_devids.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_devids.h @@ -39,6 +39,8 @@ #define I40E_DEV_ID_20G_KR2 0x1587 #define I40E_DEV_ID_20G_KR2_A 0x1588 #define I40E_DEV_ID_10G_BASE_T4 0x1589 +#define I40E_DEV_ID_25G_B 0x158A +#define I40E_DEV_ID_25G_SFP28 0x158B #define I40E_DEV_ID_VF 0x154C #define I40E_DEV_ID_VF_HV 0x1571 #define I40E_DEV_ID_SFP_X722 0x37D0 @@ -46,7 +48,6 @@ #define I40E_DEV_ID_10G_BASE_T_X722 0x37D2 #define I40E_DEV_ID_SFP_I_X722 0x37D3 #define I40E_DEV_ID_X722_VF 0x37CD -#define I40E_DEV_ID_X722_VF_HV 0x37D9 #define i40e_is_40G_device(d) ((d) == I40E_DEV_ID_QSFP_A || \ (d) == I40E_DEV_ID_QSFP_B || \ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h index d89d52109efa..ba6c6bda0e22 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h @@ -115,6 +115,10 @@ i40e_status i40e_read_phy_register(struct i40e_hw *hw, u8 page, u16 reg, u8 phy_addr, u16 *value); i40e_status i40e_write_phy_register(struct i40e_hw *hw, u8 page, u16 reg, u8 phy_addr, u16 value); +i40e_status i40e_read_phy_register(struct i40e_hw *hw, u8 page, u16 reg, + u8 phy_addr, u16 *value); +i40e_status i40e_write_phy_register(struct i40e_hw *hw, u8 page, u16 reg, + u8 phy_addr, u16 value); u8 i40e_get_phy_address(struct i40e_hw *hw, u8 dev_num); i40e_status i40e_blink_phy_link_led(struct i40e_hw *hw, u32 time, u32 interval); diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index 75f2a2cdd738..c91fcf43ccbc 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -150,7 +150,7 @@ u32 i40evf_get_tx_pending(struct i40e_ring *ring, bool in_sw) return 0; } -#define WB_STRIDE 0x3 +#define WB_STRIDE 4 /** * i40e_clean_tx_irq - Reclaim resources after transmit completes @@ -266,7 +266,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, unsigned int j = i40evf_get_tx_pending(tx_ring, false); if (budget && - ((j / (WB_STRIDE + 1)) == 0) && (j > 0) && + ((j / WB_STRIDE) == 0) && (j > 0) && !test_bit(__I40E_DOWN, &vsi->state) && (I40E_DESC_UNUSED(tx_ring) != tx_ring->count)) tx_ring->arm_wb = true; @@ -501,14 +501,15 @@ void i40evf_clean_rx_ring(struct i40e_ring *rx_ring) if (!rx_ring->rx_bi) return; + if (rx_ring->skb) { + dev_kfree_skb(rx_ring->skb); + rx_ring->skb = NULL; + } + /* Free all the Rx ring sk_buffs */ for (i = 0; i < rx_ring->count; i++) { struct i40e_rx_buffer *rx_bi = &rx_ring->rx_bi[i]; - if (rx_bi->skb) { - dev_kfree_skb(rx_bi->skb); - rx_bi->skb = NULL; - } if (!rx_bi->page) continue; @@ -705,7 +706,6 @@ bool i40evf_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count) * because each write-back erases this info. */ rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset); - rx_desc->read.hdr_addr = 0; rx_desc++; bi++; @@ -904,45 +904,6 @@ void i40evf_process_skb_fields(struct i40e_ring *rx_ring, } /** - * i40e_pull_tail - i40e specific version of skb_pull_tail - * @rx_ring: rx descriptor ring packet is being transacted on - * @skb: pointer to current skb being adjusted - * - * This function is an i40e specific version of __pskb_pull_tail. The - * main difference between this version and the original function is that - * this function can make several assumptions about the state of things - * that allow for significant optimizations versus the standard function. - * As a result we can do things like drop a frag and maintain an accurate - * truesize for the skb. - */ -static void i40e_pull_tail(struct i40e_ring *rx_ring, struct sk_buff *skb) -{ - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; - unsigned char *va; - unsigned int pull_len; - - /* it is valid to use page_address instead of kmap since we are - * working with pages allocated out of the lomem pool per - * alloc_page(GFP_ATOMIC) - */ - va = skb_frag_address(frag); - - /* we need the header to contain the greater of either ETH_HLEN or - * 60 bytes if the skb->len is less than 60 for skb_pad. - */ - pull_len = eth_get_headlen(va, I40E_RX_HDR_SIZE); - - /* align pull length to size of long to optimize memcpy performance */ - skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long))); - - /* update all of the pointers */ - skb_frag_size_sub(frag, pull_len); - frag->page_offset += pull_len; - skb->data_len -= pull_len; - skb->tail += pull_len; -} - -/** * i40e_cleanup_headers - Correct empty headers * @rx_ring: rx descriptor ring packet is being transacted on * @skb: pointer to current skb being fixed @@ -957,10 +918,6 @@ static void i40e_pull_tail(struct i40e_ring *rx_ring, struct sk_buff *skb) **/ static bool i40e_cleanup_headers(struct i40e_ring *rx_ring, struct sk_buff *skb) { - /* place header in linear portion of buffer */ - if (skb_is_nonlinear(skb)) - i40e_pull_tail(rx_ring, skb); - /* if eth_skb_pad returns an error the skb was freed */ if (eth_skb_pad(skb)) return true; @@ -992,19 +949,85 @@ static void i40e_reuse_rx_page(struct i40e_ring *rx_ring, } /** - * i40e_page_is_reserved - check if reuse is possible + * i40e_page_is_reusable - check if any reuse is possible * @page: page struct to check + * + * A page is not reusable if it was allocated under low memory + * conditions, or it's not in the same NUMA node as this CPU. */ -static inline bool i40e_page_is_reserved(struct page *page) +static inline bool i40e_page_is_reusable(struct page *page) { - return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page); + return (page_to_nid(page) == numa_mem_id()) && + !page_is_pfmemalloc(page); +} + +/** + * i40e_can_reuse_rx_page - Determine if this page can be reused by + * the adapter for another receive + * + * @rx_buffer: buffer containing the page + * @page: page address from rx_buffer + * @truesize: actual size of the buffer in this page + * + * If page is reusable, rx_buffer->page_offset is adjusted to point to + * an unused region in the page. + * + * For small pages, @truesize will be a constant value, half the size + * of the memory at page. We'll attempt to alternate between high and + * low halves of the page, with one half ready for use by the hardware + * and the other half being consumed by the stack. We use the page + * ref count to determine whether the stack has finished consuming the + * portion of this page that was passed up with a previous packet. If + * the page ref count is >1, we'll assume the "other" half page is + * still busy, and this page cannot be reused. + * + * For larger pages, @truesize will be the actual space used by the + * received packet (adjusted upward to an even multiple of the cache + * line size). This will advance through the page by the amount + * actually consumed by the received packets while there is still + * space for a buffer. Each region of larger pages will be used at + * most once, after which the page will not be reused. + * + * In either case, if the page is reusable its refcount is increased. + **/ +static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer, + struct page *page, + const unsigned int truesize) +{ +#if (PAGE_SIZE >= 8192) + unsigned int last_offset = PAGE_SIZE - I40E_RXBUFFER_2048; +#endif + + /* Is any reuse possible? */ + if (unlikely(!i40e_page_is_reusable(page))) + return false; + +#if (PAGE_SIZE < 8192) + /* if we are only owner of page we can reuse it */ + if (unlikely(page_count(page) != 1)) + return false; + + /* flip page offset to other buffer */ + rx_buffer->page_offset ^= truesize; +#else + /* move offset up to the next cache line */ + rx_buffer->page_offset += truesize; + + if (rx_buffer->page_offset > last_offset) + return false; +#endif + + /* Inc ref count on page before passing it up to the stack */ + get_page(page); + + return true; } /** * i40e_add_rx_frag - Add contents of Rx buffer to sk_buff * @rx_ring: rx descriptor ring to transact packets on * @rx_buffer: buffer containing page to add - * @rx_desc: descriptor containing length of buffer written by hardware + * @size: packet length from rx_desc * @skb: sk_buff to place the data into * * This function will add the data contained in rx_buffer->page to the skb. @@ -1017,30 +1040,29 @@ static inline bool i40e_page_is_reserved(struct page *page) **/ static bool i40e_add_rx_frag(struct i40e_ring *rx_ring, struct i40e_rx_buffer *rx_buffer, - union i40e_rx_desc *rx_desc, + unsigned int size, struct sk_buff *skb) { struct page *page = rx_buffer->page; - u64 qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - unsigned int size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >> - I40E_RXD_QW1_LENGTH_PBUF_SHIFT; + unsigned char *va = page_address(page) + rx_buffer->page_offset; #if (PAGE_SIZE < 8192) unsigned int truesize = I40E_RXBUFFER_2048; #else unsigned int truesize = ALIGN(size, L1_CACHE_BYTES); - unsigned int last_offset = PAGE_SIZE - I40E_RXBUFFER_2048; #endif + unsigned int pull_len; + + if (unlikely(skb_is_nonlinear(skb))) + goto add_tail_frag; /* will the data fit in the skb we allocated? if so, just * copy it as it is pretty small anyway */ - if ((size <= I40E_RX_HDR_SIZE) && !skb_is_nonlinear(skb)) { - unsigned char *va = page_address(page) + rx_buffer->page_offset; - + if (size <= I40E_RX_HDR_SIZE) { memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long))); - /* page is not reserved, we can reuse buffer as-is */ - if (likely(!i40e_page_is_reserved(page))) + /* page is reusable, we can reuse buffer as-is */ + if (likely(i40e_page_is_reusable(page))) return true; /* this page cannot be reused so discard it */ @@ -1048,34 +1070,26 @@ static bool i40e_add_rx_frag(struct i40e_ring *rx_ring, return false; } - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, - rx_buffer->page_offset, size, truesize); - - /* avoid re-using remote pages */ - if (unlikely(i40e_page_is_reserved(page))) - return false; - -#if (PAGE_SIZE < 8192) - /* if we are only owner of page we can reuse it */ - if (unlikely(page_count(page) != 1)) - return false; + /* we need the header to contain the greater of either + * ETH_HLEN or 60 bytes if the skb->len is less than + * 60 for skb_pad. + */ + pull_len = eth_get_headlen(va, I40E_RX_HDR_SIZE); - /* flip page offset to other buffer */ - rx_buffer->page_offset ^= truesize; -#else - /* move offset up to the next cache line */ - rx_buffer->page_offset += truesize; + /* align pull length to size of long to optimize + * memcpy performance + */ + memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long))); - if (rx_buffer->page_offset > last_offset) - return false; -#endif + /* update all of the pointers */ + va += pull_len; + size -= pull_len; - /* Even if we own the page, we are not allowed to use atomic_set() - * This would break get_page_unless_zero() users. - */ - get_page(rx_buffer->page); +add_tail_frag: + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, + (unsigned long)va & ~PAGE_MASK, size, truesize); - return true; + return i40e_can_reuse_rx_page(rx_buffer, page, truesize); } /** @@ -1090,18 +1104,21 @@ static bool i40e_add_rx_frag(struct i40e_ring *rx_ring, */ static inline struct sk_buff *i40evf_fetch_rx_buffer(struct i40e_ring *rx_ring, - union i40e_rx_desc *rx_desc) + union i40e_rx_desc *rx_desc, + struct sk_buff *skb) { + u64 local_status_error_len = + le64_to_cpu(rx_desc->wb.qword1.status_error_len); + unsigned int size = + (local_status_error_len & I40E_RXD_QW1_LENGTH_PBUF_MASK) >> + I40E_RXD_QW1_LENGTH_PBUF_SHIFT; struct i40e_rx_buffer *rx_buffer; - struct sk_buff *skb; struct page *page; rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean]; page = rx_buffer->page; prefetchw(page); - skb = rx_buffer->skb; - if (likely(!skb)) { void *page_addr = page_address(page) + rx_buffer->page_offset; @@ -1125,19 +1142,17 @@ struct sk_buff *i40evf_fetch_rx_buffer(struct i40e_ring *rx_ring, * it now to avoid a possible cache miss */ prefetchw(skb->data); - } else { - rx_buffer->skb = NULL; } /* we are reusing so sync this buffer for CPU use */ dma_sync_single_range_for_cpu(rx_ring->dev, rx_buffer->dma, rx_buffer->page_offset, - I40E_RXBUFFER_2048, + size, DMA_FROM_DEVICE); /* pull page into skb */ - if (i40e_add_rx_frag(rx_ring, rx_buffer, rx_desc, skb)) { + if (i40e_add_rx_frag(rx_ring, rx_buffer, size, skb)) { /* hand second half of page back to the ring */ i40e_reuse_rx_page(rx_ring, rx_buffer); rx_ring->rx_stats.page_reuse_count++; @@ -1181,8 +1196,6 @@ static bool i40e_is_non_eop(struct i40e_ring *rx_ring, if (likely(i40e_test_staterr(rx_desc, I40E_RXD_EOF))) return false; - /* place skb in next buffer to be received */ - rx_ring->rx_bi[ntc].skb = skb; rx_ring->rx_stats.non_eop_descs++; return true; @@ -1203,13 +1216,12 @@ static bool i40e_is_non_eop(struct i40e_ring *rx_ring, static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) { unsigned int total_rx_bytes = 0, total_rx_packets = 0; + struct sk_buff *skb = rx_ring->skb; u16 cleaned_count = I40E_DESC_UNUSED(rx_ring); bool failure = false; while (likely(total_rx_packets < budget)) { union i40e_rx_desc *rx_desc; - struct sk_buff *skb; - u32 rx_status; u16 vlan_tag; u8 rx_ptype; u64 qword; @@ -1223,21 +1235,13 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) rx_desc = I40E_RX_DESC(rx_ring, rx_ring->next_to_clean); - qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - rx_ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >> - I40E_RXD_QW1_PTYPE_SHIFT; - rx_status = (qword & I40E_RXD_QW1_STATUS_MASK) >> - I40E_RXD_QW1_STATUS_SHIFT; - - if (!(rx_status & BIT(I40E_RX_DESC_STATUS_DD_SHIFT))) - break; - /* status_error_len will always be zero for unused descriptors * because it's cleared in cleanup, and overlaps with hdr_addr * which is always zero because packet split isn't used, if the * hardware wrote DD then it will be non-zero */ - if (!rx_desc->wb.qword1.status_error_len) + if (!i40e_test_staterr(rx_desc, + BIT(I40E_RX_DESC_STATUS_DD_SHIFT))) break; /* This memory barrier is needed to keep us from reading @@ -1246,7 +1250,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) */ dma_rmb(); - skb = i40evf_fetch_rx_buffer(rx_ring, rx_desc); + skb = i40evf_fetch_rx_buffer(rx_ring, rx_desc, skb); if (!skb) break; @@ -1265,12 +1269,18 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) continue; } - if (i40e_cleanup_headers(rx_ring, skb)) + if (i40e_cleanup_headers(rx_ring, skb)) { + skb = NULL; continue; + } /* probably a little skewed due to removing CRC */ total_rx_bytes += skb->len; + qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); + rx_ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >> + I40E_RXD_QW1_PTYPE_SHIFT; + /* populate checksum, VLAN, and protocol */ i40evf_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype); @@ -1279,11 +1289,14 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1) : 0; i40e_receive_skb(rx_ring, skb, vlan_tag); + skb = NULL; /* update budget accounting */ total_rx_packets++; } + rx_ring->skb = skb; + u64_stats_update_begin(&rx_ring->syncp); rx_ring->stats.packets += total_rx_packets; rx_ring->stats.bytes += total_rx_bytes; @@ -1311,18 +1324,18 @@ static u32 i40e_buildreg_itr(const int type, const u16 itr) /* a small macro to shorten up some long lines */ #define INTREG I40E_VFINT_DYN_CTLN1 -static inline int get_rx_itr_enabled(struct i40e_vsi *vsi, int idx) +static inline int get_rx_itr(struct i40e_vsi *vsi, int idx) { struct i40evf_adapter *adapter = vsi->back; - return !!(adapter->rx_rings[idx].rx_itr_setting); + return adapter->rx_rings[idx].rx_itr_setting; } -static inline int get_tx_itr_enabled(struct i40e_vsi *vsi, int idx) +static inline int get_tx_itr(struct i40e_vsi *vsi, int idx) { struct i40evf_adapter *adapter = vsi->back; - return !!(adapter->tx_rings[idx].tx_itr_setting); + return adapter->tx_rings[idx].tx_itr_setting; } /** @@ -1348,8 +1361,8 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, */ rxval = txval = i40e_buildreg_itr(I40E_ITR_NONE, 0); - rx_itr_setting = get_rx_itr_enabled(vsi, idx); - tx_itr_setting = get_tx_itr_enabled(vsi, idx); + rx_itr_setting = get_rx_itr(vsi, idx); + tx_itr_setting = get_tx_itr(vsi, idx); if (q_vector->itr_countdown > 0 || (!ITR_IS_DYNAMIC(rx_itr_setting) && @@ -1461,12 +1474,24 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget) /* If work not completed, return budget and polling will return */ if (!clean_complete) { + const cpumask_t *aff_mask = &q_vector->affinity_mask; + int cpu_id = smp_processor_id(); + + /* It is possible that the interrupt affinity has changed but, + * if the cpu is pegged at 100%, polling will never exit while + * traffic continues and the interrupt will be stuck on this + * cpu. We check to make sure affinity is correct before we + * continue to poll, otherwise we must stop polling so the + * interrupt can move to the correct cpu. + */ + if (likely(cpumask_test_cpu(cpu_id, aff_mask))) { tx_only: - if (arm_wb) { - q_vector->tx.ring[0].tx_stats.tx_force_wb++; - i40e_enable_wb_on_itr(vsi, q_vector); + if (arm_wb) { + q_vector->tx.ring[0].tx_stats.tx_force_wb++; + i40e_enable_wb_on_itr(vsi, q_vector); + } + return budget; } - return budget; } if (vsi->back->flags & I40E_TXR_FLAGS_WB_ON_ITR) @@ -1474,8 +1499,17 @@ tx_only: /* Work is done so exit the polling mode and re-enable the interrupt */ napi_complete_done(napi, work_done); - i40e_update_enable_itr(vsi, q_vector); - return 0; + + /* If we're prematurely stopping polling to fix the interrupt + * affinity we want to make sure polling starts back up so we + * issue a call to i40evf_force_wb which triggers a SW interrupt. + */ + if (!clean_complete) + i40evf_force_wb(vsi, q_vector); + else + i40e_update_enable_itr(vsi, q_vector); + + return min(work_done, budget - 1); } /** @@ -1534,14 +1568,16 @@ out: /** * i40e_tso - set up the tso context descriptor - * @skb: ptr to the skb we're sending + * @first: pointer to first Tx buffer for xmit * @hdr_len: ptr to the size of the packet header * @cd_type_cmd_tso_mss: Quad Word 1 * * Returns 0 if no TSO can happen, 1 if tso is going, or error **/ -static int i40e_tso(struct sk_buff *skb, u8 *hdr_len, u64 *cd_type_cmd_tso_mss) +static int i40e_tso(struct i40e_tx_buffer *first, u8 *hdr_len, + u64 *cd_type_cmd_tso_mss) { + struct sk_buff *skb = first->skb; u64 cd_cmd, cd_tso_len, cd_mss; union { struct iphdr *v4; @@ -1554,6 +1590,7 @@ static int i40e_tso(struct sk_buff *skb, u8 *hdr_len, u64 *cd_type_cmd_tso_mss) unsigned char *hdr; } l4; u32 paylen, l4_offset; + u16 gso_segs, gso_size; int err; if (skb->ip_summed != CHECKSUM_PARTIAL) @@ -1592,7 +1629,8 @@ static int i40e_tso(struct sk_buff *skb, u8 *hdr_len, u64 *cd_type_cmd_tso_mss) /* remove payload length from outer checksum */ paylen = skb->len - l4_offset; - csum_replace_by_diff(&l4.udp->check, htonl(paylen)); + csum_replace_by_diff(&l4.udp->check, + (__force __wsum)htonl(paylen)); } /* reset pointers to inner headers */ @@ -1613,15 +1651,23 @@ static int i40e_tso(struct sk_buff *skb, u8 *hdr_len, u64 *cd_type_cmd_tso_mss) /* remove payload length from inner checksum */ paylen = skb->len - l4_offset; - csum_replace_by_diff(&l4.tcp->check, htonl(paylen)); + csum_replace_by_diff(&l4.tcp->check, (__force __wsum)htonl(paylen)); /* compute length of segmentation header */ *hdr_len = (l4.tcp->doff * 4) + l4_offset; + /* pull values out of skb_shinfo */ + gso_size = skb_shinfo(skb)->gso_size; + gso_segs = skb_shinfo(skb)->gso_segs; + + /* update GSO size and bytecount with header size */ + first->gso_segs = gso_segs; + first->bytecount += (first->gso_segs - 1) * *hdr_len; + /* find the field values */ cd_cmd = I40E_TX_CTX_DESC_TSO; cd_tso_len = skb->len - *hdr_len; - cd_mss = skb_shinfo(skb)->gso_size; + cd_mss = gso_size; *cd_type_cmd_tso_mss |= (cd_cmd << I40E_TXD_CTX_QW1_CMD_SHIFT) | (cd_tso_len << I40E_TXD_CTX_QW1_TSO_LEN_SHIFT) | (cd_mss << I40E_TXD_CTX_QW1_MSS_SHIFT); @@ -1934,10 +1980,7 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, u16 i = tx_ring->next_to_use; u32 td_tag = 0; dma_addr_t dma; - u16 gso_segs; - u16 desc_count = 0; - bool tail_bump = true; - bool do_rs = false; + u16 desc_count = 1; if (tx_flags & I40E_TX_FLAGS_HW_VLAN) { td_cmd |= I40E_TX_DESC_CMD_IL2TAG1; @@ -1945,15 +1988,6 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, I40E_TX_FLAGS_VLAN_SHIFT; } - if (tx_flags & (I40E_TX_FLAGS_TSO | I40E_TX_FLAGS_FSO)) - gso_segs = skb_shinfo(skb)->gso_segs; - else - gso_segs = 1; - - /* multiply data chunks by size of headers */ - first->bytecount = skb->len - hdr_len + (gso_segs * hdr_len); - first->gso_segs = gso_segs; - first->skb = skb; first->tx_flags = tx_flags; dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE); @@ -2020,8 +2054,7 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, tx_bi = &tx_ring->tx_bi[i]; } - /* set next_to_watch value indicating a packet is present */ - first->next_to_watch = tx_desc; + netdev_tx_sent_queue(txring_txq(tx_ring), first->bytecount); i++; if (i == tx_ring->count) @@ -2029,66 +2062,72 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, tx_ring->next_to_use = i; - netdev_tx_sent_queue(txring_txq(tx_ring), first->bytecount); i40e_maybe_stop_tx(tx_ring, DESC_NEEDED); + /* write last descriptor with EOP bit */ + td_cmd |= I40E_TX_DESC_CMD_EOP; + + /* We can OR these values together as they both are checked against + * 4 below and at this point desc_count will be used as a boolean value + * after this if/else block. + */ + desc_count |= ++tx_ring->packet_stride; + /* Algorithm to optimize tail and RS bit setting: - * if xmit_more is supported - * if xmit_more is true - * do not update tail and do not mark RS bit. - * if xmit_more is false and last xmit_more was false - * if every packet spanned less than 4 desc - * then set RS bit on 4th packet and update tail - * on every packet - * else - * update tail and set RS bit on every packet. - * if xmit_more is false and last_xmit_more was true - * update tail and set RS bit. + * if queue is stopped + * mark RS bit + * reset packet counter + * else if xmit_more is supported and is true + * advance packet counter to 4 + * reset desc_count to 0 * - * Optimization: wmb to be issued only in case of tail update. - * Also optimize the Descriptor WB path for RS bit with the same - * algorithm. + * if desc_count >= 4 + * mark RS bit + * reset packet counter + * if desc_count > 0 + * update tail * - * Note: If there are less than 4 packets + * Note: If there are less than 4 descriptors * pending and interrupts were disabled the service task will * trigger a force WB. */ - if (skb->xmit_more && - !netif_xmit_stopped(txring_txq(tx_ring))) { - tx_ring->flags |= I40E_TXR_FLAGS_LAST_XMIT_MORE_SET; - tail_bump = false; - } else if (!skb->xmit_more && - !netif_xmit_stopped(txring_txq(tx_ring)) && - (!(tx_ring->flags & I40E_TXR_FLAGS_LAST_XMIT_MORE_SET)) && - (tx_ring->packet_stride < WB_STRIDE) && - (desc_count < WB_STRIDE)) { - tx_ring->packet_stride++; - } else { + if (netif_xmit_stopped(txring_txq(tx_ring))) { + goto do_rs; + } else if (skb->xmit_more) { + /* set stride to arm on next packet and reset desc_count */ + tx_ring->packet_stride = WB_STRIDE; + desc_count = 0; + } else if (desc_count >= WB_STRIDE) { +do_rs: + /* write last descriptor with RS bit set */ + td_cmd |= I40E_TX_DESC_CMD_RS; tx_ring->packet_stride = 0; - tx_ring->flags &= ~I40E_TXR_FLAGS_LAST_XMIT_MORE_SET; - do_rs = true; } - if (do_rs) - tx_ring->packet_stride = 0; tx_desc->cmd_type_offset_bsz = - build_ctob(td_cmd, td_offset, size, td_tag) | - cpu_to_le64((u64)(do_rs ? I40E_TXD_CMD : - I40E_TX_DESC_CMD_EOP) << - I40E_TXD_QW1_CMD_SHIFT); + build_ctob(td_cmd, td_offset, size, td_tag); + + /* Force memory writes to complete before letting h/w know there + * are new descriptors to fetch. + * + * We also use this memory barrier to make certain all of the + * status bits have been updated before next_to_watch is written. + */ + wmb(); + + /* set next_to_watch value indicating a packet is present */ + first->next_to_watch = tx_desc; /* notify HW of packet */ - if (!tail_bump) { - prefetchw(tx_desc + 1); - } else { - /* Force memory writes to complete before letting h/w - * know there are new descriptors to fetch. (Only - * applicable for weak-ordered memory model archs, - * such as IA-64). - */ - wmb(); + if (desc_count) { writel(i, tx_ring->tail); + + /* we need this if more than one processor can write to our tail + * at a time, it synchronizes IO on IA64/Altix systems + */ + mmiowb(); } + return; dma_error: @@ -2133,8 +2172,10 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, count = i40e_xmit_descriptor_count(skb); if (i40e_chk_linearize(skb, count)) { - if (__skb_linearize(skb)) - goto out_drop; + if (__skb_linearize(skb)) { + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + } count = i40e_txd_use_count(skb->len); tx_ring->tx_stats.tx_linearize++; } @@ -2150,6 +2191,12 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, return NETDEV_TX_BUSY; } + /* record the location of the first descriptor for this packet */ + first = &tx_ring->tx_bi[tx_ring->next_to_use]; + first->skb = skb; + first->bytecount = skb->len; + first->gso_segs = 1; + /* prepare the xmit flags */ if (i40evf_tx_prepare_vlan_flags(skb, tx_ring, &tx_flags)) goto out_drop; @@ -2157,16 +2204,13 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, /* obtain protocol of skb */ protocol = vlan_get_protocol(skb); - /* record the location of the first descriptor for this packet */ - first = &tx_ring->tx_bi[tx_ring->next_to_use]; - /* setup IPv4/IPv6 offloads */ if (protocol == htons(ETH_P_IP)) tx_flags |= I40E_TX_FLAGS_IPV4; else if (protocol == htons(ETH_P_IPV6)) tx_flags |= I40E_TX_FLAGS_IPV6; - tso = i40e_tso(skb, &hdr_len, &cd_type_cmd_tso_mss); + tso = i40e_tso(first, &hdr_len, &cd_type_cmd_tso_mss); if (tso < 0) goto out_drop; @@ -2193,7 +2237,8 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, return NETDEV_TX_OK; out_drop: - dev_kfree_skb_any(skb); + dev_kfree_skb_any(first->skb); + first->skb = NULL; return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h index abcdecabbc56..8274ba68bd32 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h @@ -173,26 +173,37 @@ static inline bool i40e_test_staterr(union i40e_rx_desc *rx_desc, #define I40E_MAX_DATA_PER_TXD_ALIGNED \ (I40E_MAX_DATA_PER_TXD & ~(I40E_MAX_READ_REQ_SIZE - 1)) -/* This ugly bit of math is equivalent to DIV_ROUNDUP(size, X) where X is - * the value I40E_MAX_DATA_PER_TXD_ALIGNED. It is needed due to the fact - * that 12K is not a power of 2 and division is expensive. It is used to - * approximate the number of descriptors used per linear buffer. Note - * that this will overestimate in some cases as it doesn't account for the - * fact that we will add up to 4K - 1 in aligning the 12K buffer, however - * the error should not impact things much as large buffers usually mean - * we will use fewer descriptors then there are frags in an skb. +/** + * i40e_txd_use_count - estimate the number of descriptors needed for Tx + * @size: transmit request size in bytes + * + * Due to hardware alignment restrictions (4K alignment), we need to + * assume that we can have no more than 12K of data per descriptor, even + * though each descriptor can take up to 16K - 1 bytes of aligned memory. + * Thus, we need to divide by 12K. But division is slow! Instead, + * we decompose the operation into shifts and one relatively cheap + * multiply operation. + * + * To divide by 12K, we first divide by 4K, then divide by 3: + * To divide by 4K, shift right by 12 bits + * To divide by 3, multiply by 85, then divide by 256 + * (Divide by 256 is done by shifting right by 8 bits) + * Finally, we add one to round up. Because 256 isn't an exact multiple of + * 3, we'll underestimate near each multiple of 12K. This is actually more + * accurate as we have 4K - 1 of wiggle room that we can fit into the last + * segment. For our purposes this is accurate out to 1M which is orders of + * magnitude greater than our largest possible GSO size. + * + * This would then be implemented as: + * return (((size >> 12) * 85) >> 8) + 1; + * + * Since multiplication and division are commutative, we can reorder + * operations into: + * return ((size * 85) >> 20) + 1; */ static inline unsigned int i40e_txd_use_count(unsigned int size) { - const unsigned int max = I40E_MAX_DATA_PER_TXD_ALIGNED; - const unsigned int reciprocal = ((1ull << 32) - 1 + (max / 2)) / max; - unsigned int adjust = ~(u32)0; - - /* if we rounded up on the reciprocal pull down the adjustment */ - if ((max * reciprocal) > adjust) - adjust = ~(u32)(reciprocal - 1); - - return (u32)((((u64)size * reciprocal) + adjust) >> 32); + return ((size * 85) >> 20) + 1; } /* Tx Descriptors needed, worst case */ @@ -228,7 +239,6 @@ struct i40e_tx_buffer { }; struct i40e_rx_buffer { - struct sk_buff *skb; dma_addr_t dma; struct page *page; unsigned int page_offset; @@ -309,7 +319,6 @@ struct i40e_ring { bool ring_active; /* is ring online or not */ bool arm_wb; /* do something to arm write back */ u8 packet_stride; -#define I40E_TXR_FLAGS_LAST_XMIT_MORE_SET BIT(2) u16 flags; #define I40E_TXR_FLAGS_WB_ON_ITR BIT(0) @@ -330,6 +339,14 @@ struct i40e_ring { struct rcu_head rcu; /* to avoid race on free */ u16 next_to_alloc; + struct sk_buff *skb; /* When i40evf_clean_rx_ring_irq() must + * return before it sees the EOP for + * the current packet, we save that skb + * here and resume receiving this + * packet the next time + * i40evf_clean_rx_ring_irq() is called + * for this ring. + */ } ____cacheline_internodealigned_in_smp; enum i40e_latency_range { diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h index 97f96e0d9c4c..16bb88084bb9 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_type.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h @@ -100,7 +100,6 @@ enum i40e_debug_mask { */ enum i40e_mac_type { I40E_MAC_UNKNOWN = 0, - I40E_MAC_X710, I40E_MAC_XL710, I40E_MAC_VF, I40E_MAC_X722, @@ -159,6 +158,7 @@ struct i40e_link_status { enum i40e_aq_link_speed link_speed; u8 link_info; u8 an_info; + u8 fec_info; u8 ext_info; u8 loopback; /* is Link Status Event notification to SW enabled */ @@ -187,47 +187,59 @@ struct i40e_link_status { #define I40E_MODULE_TYPE_1000BASE_T 0x08 }; -enum i40e_aq_capabilities_phy_type { - I40E_CAP_PHY_TYPE_SGMII = BIT(I40E_PHY_TYPE_SGMII), - I40E_CAP_PHY_TYPE_1000BASE_KX = BIT(I40E_PHY_TYPE_1000BASE_KX), - I40E_CAP_PHY_TYPE_10GBASE_KX4 = BIT(I40E_PHY_TYPE_10GBASE_KX4), - I40E_CAP_PHY_TYPE_10GBASE_KR = BIT(I40E_PHY_TYPE_10GBASE_KR), - I40E_CAP_PHY_TYPE_40GBASE_KR4 = BIT(I40E_PHY_TYPE_40GBASE_KR4), - I40E_CAP_PHY_TYPE_XAUI = BIT(I40E_PHY_TYPE_XAUI), - I40E_CAP_PHY_TYPE_XFI = BIT(I40E_PHY_TYPE_XFI), - I40E_CAP_PHY_TYPE_SFI = BIT(I40E_PHY_TYPE_SFI), - I40E_CAP_PHY_TYPE_XLAUI = BIT(I40E_PHY_TYPE_XLAUI), - I40E_CAP_PHY_TYPE_XLPPI = BIT(I40E_PHY_TYPE_XLPPI), - I40E_CAP_PHY_TYPE_40GBASE_CR4_CU = BIT(I40E_PHY_TYPE_40GBASE_CR4_CU), - I40E_CAP_PHY_TYPE_10GBASE_CR1_CU = BIT(I40E_PHY_TYPE_10GBASE_CR1_CU), - I40E_CAP_PHY_TYPE_10GBASE_AOC = BIT(I40E_PHY_TYPE_10GBASE_AOC), - I40E_CAP_PHY_TYPE_40GBASE_AOC = BIT(I40E_PHY_TYPE_40GBASE_AOC), - I40E_CAP_PHY_TYPE_100BASE_TX = BIT(I40E_PHY_TYPE_100BASE_TX), - I40E_CAP_PHY_TYPE_1000BASE_T = BIT(I40E_PHY_TYPE_1000BASE_T), - I40E_CAP_PHY_TYPE_10GBASE_T = BIT(I40E_PHY_TYPE_10GBASE_T), - I40E_CAP_PHY_TYPE_10GBASE_SR = BIT(I40E_PHY_TYPE_10GBASE_SR), - I40E_CAP_PHY_TYPE_10GBASE_LR = BIT(I40E_PHY_TYPE_10GBASE_LR), - I40E_CAP_PHY_TYPE_10GBASE_SFPP_CU = BIT(I40E_PHY_TYPE_10GBASE_SFPP_CU), - I40E_CAP_PHY_TYPE_10GBASE_CR1 = BIT(I40E_PHY_TYPE_10GBASE_CR1), - I40E_CAP_PHY_TYPE_40GBASE_CR4 = BIT(I40E_PHY_TYPE_40GBASE_CR4), - I40E_CAP_PHY_TYPE_40GBASE_SR4 = BIT(I40E_PHY_TYPE_40GBASE_SR4), - I40E_CAP_PHY_TYPE_40GBASE_LR4 = BIT(I40E_PHY_TYPE_40GBASE_LR4), - I40E_CAP_PHY_TYPE_1000BASE_SX = BIT(I40E_PHY_TYPE_1000BASE_SX), - I40E_CAP_PHY_TYPE_1000BASE_LX = BIT(I40E_PHY_TYPE_1000BASE_LX), - I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL = - BIT(I40E_PHY_TYPE_1000BASE_T_OPTICAL), - I40E_CAP_PHY_TYPE_20GBASE_KR2 = BIT(I40E_PHY_TYPE_20GBASE_KR2) -}; - struct i40e_phy_info { struct i40e_link_status link_info; struct i40e_link_status link_info_old; bool get_link_info; enum i40e_media_type media_type; /* all the phy types the NVM is capable of */ - enum i40e_aq_capabilities_phy_type phy_types; -}; - + u64 phy_types; +}; + +#define I40E_CAP_PHY_TYPE_SGMII BIT_ULL(I40E_PHY_TYPE_SGMII) +#define I40E_CAP_PHY_TYPE_1000BASE_KX BIT_ULL(I40E_PHY_TYPE_1000BASE_KX) +#define I40E_CAP_PHY_TYPE_10GBASE_KX4 BIT_ULL(I40E_PHY_TYPE_10GBASE_KX4) +#define I40E_CAP_PHY_TYPE_10GBASE_KR BIT_ULL(I40E_PHY_TYPE_10GBASE_KR) +#define I40E_CAP_PHY_TYPE_40GBASE_KR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_KR4) +#define I40E_CAP_PHY_TYPE_XAUI BIT_ULL(I40E_PHY_TYPE_XAUI) +#define I40E_CAP_PHY_TYPE_XFI BIT_ULL(I40E_PHY_TYPE_XFI) +#define I40E_CAP_PHY_TYPE_SFI BIT_ULL(I40E_PHY_TYPE_SFI) +#define I40E_CAP_PHY_TYPE_XLAUI BIT_ULL(I40E_PHY_TYPE_XLAUI) +#define I40E_CAP_PHY_TYPE_XLPPI BIT_ULL(I40E_PHY_TYPE_XLPPI) +#define I40E_CAP_PHY_TYPE_40GBASE_CR4_CU BIT_ULL(I40E_PHY_TYPE_40GBASE_CR4_CU) +#define I40E_CAP_PHY_TYPE_10GBASE_CR1_CU BIT_ULL(I40E_PHY_TYPE_10GBASE_CR1_CU) +#define I40E_CAP_PHY_TYPE_10GBASE_AOC BIT_ULL(I40E_PHY_TYPE_10GBASE_AOC) +#define I40E_CAP_PHY_TYPE_40GBASE_AOC BIT_ULL(I40E_PHY_TYPE_40GBASE_AOC) +#define I40E_CAP_PHY_TYPE_100BASE_TX BIT_ULL(I40E_PHY_TYPE_100BASE_TX) +#define I40E_CAP_PHY_TYPE_1000BASE_T BIT_ULL(I40E_PHY_TYPE_1000BASE_T) +#define I40E_CAP_PHY_TYPE_10GBASE_T BIT_ULL(I40E_PHY_TYPE_10GBASE_T) +#define I40E_CAP_PHY_TYPE_10GBASE_SR BIT_ULL(I40E_PHY_TYPE_10GBASE_SR) +#define I40E_CAP_PHY_TYPE_10GBASE_LR BIT_ULL(I40E_PHY_TYPE_10GBASE_LR) +#define I40E_CAP_PHY_TYPE_10GBASE_SFPP_CU BIT_ULL(I40E_PHY_TYPE_10GBASE_SFPP_CU) +#define I40E_CAP_PHY_TYPE_10GBASE_CR1 BIT_ULL(I40E_PHY_TYPE_10GBASE_CR1) +#define I40E_CAP_PHY_TYPE_40GBASE_CR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_CR4) +#define I40E_CAP_PHY_TYPE_40GBASE_SR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_SR4) +#define I40E_CAP_PHY_TYPE_40GBASE_LR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_LR4) +#define I40E_CAP_PHY_TYPE_1000BASE_SX BIT_ULL(I40E_PHY_TYPE_1000BASE_SX) +#define I40E_CAP_PHY_TYPE_1000BASE_LX BIT_ULL(I40E_PHY_TYPE_1000BASE_LX) +#define I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL \ + BIT_ULL(I40E_PHY_TYPE_1000BASE_T_OPTICAL) +#define I40E_CAP_PHY_TYPE_20GBASE_KR2 BIT_ULL(I40E_PHY_TYPE_20GBASE_KR2) +/* Defining the macro I40E_TYPE_OFFSET to implement a bit shift for some + * PHY types. There is an unused bit (31) in the I40E_CAP_PHY_TYPE_* bit + * fields but no corresponding gap in the i40e_aq_phy_type enumeration. So, + * a shift is needed to adjust for this with values larger than 31. The + * only affected values are I40E_PHY_TYPE_25GBASE_*. + */ +#define I40E_PHY_TYPE_OFFSET 1 +#define I40E_CAP_PHY_TYPE_25GBASE_KR BIT_ULL(I40E_PHY_TYPE_25GBASE_KR + \ + I40E_PHY_TYPE_OFFSET) +#define I40E_CAP_PHY_TYPE_25GBASE_CR BIT_ULL(I40E_PHY_TYPE_25GBASE_CR + \ + I40E_PHY_TYPE_OFFSET) +#define I40E_CAP_PHY_TYPE_25GBASE_SR BIT_ULL(I40E_PHY_TYPE_25GBASE_SR + \ + I40E_PHY_TYPE_OFFSET) +#define I40E_CAP_PHY_TYPE_25GBASE_LR BIT_ULL(I40E_PHY_TYPE_25GBASE_LR + \ + I40E_PHY_TYPE_OFFSET) #define I40E_HW_CAP_MAX_GPIO 30 /* Capabilities of a PF or a VF or the whole device */ struct i40e_hw_capabilities { @@ -237,6 +249,10 @@ struct i40e_hw_capabilities { #define I40E_NVM_IMAGE_TYPE_UDP_CLOUD 0x3 u32 management_mode; + u32 mng_protocols_over_mctp; +#define I40E_MNG_PROTOCOL_PLDM 0x2 +#define I40E_MNG_PROTOCOL_OEM_COMMANDS 0x4 +#define I40E_MNG_PROTOCOL_NCSI 0x8 u32 npar_enable; u32 os2bmc; u32 valid_functions; @@ -348,6 +364,7 @@ enum i40e_nvmupd_state { I40E_NVMUPD_STATE_WRITING, I40E_NVMUPD_STATE_INIT_WAIT, I40E_NVMUPD_STATE_WRITE_WAIT, + I40E_NVMUPD_STATE_ERROR }; /* nvm_access definition and its masks/shifts need to be accessible to @@ -426,6 +443,7 @@ struct i40e_bus_info { u16 func; u16 device; u16 lan_id; + u16 bus_id; }; /* Flow control (FC) parameters */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h b/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h index bd691ad86673..d38a2b2aea2b 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h @@ -81,6 +81,7 @@ enum i40e_virtchnl_ops { I40E_VIRTCHNL_OP_GET_STATS = 15, I40E_VIRTCHNL_OP_FCOE = 16, I40E_VIRTCHNL_OP_EVENT = 17, /* must ALWAYS be 17 */ + I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP = 21, I40E_VIRTCHNL_OP_CONFIG_RSS_KEY = 23, I40E_VIRTCHNL_OP_CONFIG_RSS_LUT = 24, I40E_VIRTCHNL_OP_GET_RSS_HENA_CAPS = 25, @@ -162,6 +163,10 @@ struct i40e_virtchnl_vsi_resource { #define I40E_VIRTCHNL_VF_OFFLOAD_RSS_PF 0X00080000 #define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM 0X00100000 +#define I40E_VF_BASE_MODE_OFFLOADS (I40E_VIRTCHNL_VF_OFFLOAD_L2 | \ + I40E_VIRTCHNL_VF_OFFLOAD_VLAN | \ + I40E_VIRTCHNL_VF_OFFLOAD_RSS_PF) + struct i40e_virtchnl_vf_resource { u16 num_vsis; u16 num_queue_pairs; diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h index c5fd724313c7..00c42d803276 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf.h +++ b/drivers/net/ethernet/intel/i40evf/i40evf.h @@ -107,7 +107,8 @@ struct i40e_q_vector { int v_idx; /* vector index in list */ char name[IFNAMSIZ + 9]; bool arm_wb_state; - cpumask_var_t affinity_mask; + cpumask_t affinity_mask; + struct irq_affinity_notify affinity_notify; }; /* Helper macros to switch between ints/sec and what the register uses. @@ -194,6 +195,7 @@ struct i40evf_adapter { u64 hw_csum_rx_error; u32 rx_desc_count; int num_msix_vectors; + u32 client_pending; struct msix_entry *msix_entries; u32 flags; diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c index a9940154eead..272d600c1ed0 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c @@ -85,6 +85,14 @@ static int i40evf_get_settings(struct net_device *netdev, case I40E_LINK_SPEED_40GB: ethtool_cmd_speed_set(ecmd, SPEED_40000); break; + case I40E_LINK_SPEED_25GB: +#ifdef SPEED_25000 + ethtool_cmd_speed_set(ecmd, SPEED_25000); +#else + netdev_info(netdev, + "Speed is 25G, display not supported by this version of ethtool.\n"); +#endif + break; case I40E_LINK_SPEED_20GB: ethtool_cmd_speed_set(ecmd, SPEED_20000); break; diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index 14372810fc27..f35dcaac5bb7 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -38,7 +38,7 @@ static const char i40evf_driver_string[] = #define DRV_VERSION_MAJOR 1 #define DRV_VERSION_MINOR 6 -#define DRV_VERSION_BUILD 16 +#define DRV_VERSION_BUILD 27 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." \ __stringify(DRV_VERSION_BUILD) \ @@ -59,7 +59,6 @@ static const struct pci_device_id i40evf_pci_tbl[] = { {PCI_VDEVICE(INTEL, I40E_DEV_ID_VF), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_VF_HV), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_X722_VF), 0}, - {PCI_VDEVICE(INTEL, I40E_DEV_ID_X722_VF_HV), 0}, /* required last entry */ {0, } }; @@ -207,6 +206,9 @@ static void i40evf_misc_irq_disable(struct i40evf_adapter *adapter) { struct i40e_hw *hw = &adapter->hw; + if (!adapter->msix_entries) + return; + wr32(hw, I40E_VFINT_DYN_CTL01, 0); /* read flush */ @@ -496,6 +498,33 @@ static void i40evf_netpoll(struct net_device *netdev) #endif /** + * i40evf_irq_affinity_notify - Callback for affinity changes + * @notify: context as to what irq was changed + * @mask: the new affinity mask + * + * This is a callback function used by the irq_set_affinity_notifier function + * so that we may register to receive changes to the irq affinity masks. + **/ +static void i40evf_irq_affinity_notify(struct irq_affinity_notify *notify, + const cpumask_t *mask) +{ + struct i40e_q_vector *q_vector = + container_of(notify, struct i40e_q_vector, affinity_notify); + + q_vector->affinity_mask = *mask; +} + +/** + * i40evf_irq_affinity_release - Callback for affinity notifier release + * @ref: internal core kernel usage + * + * This is a callback function used by the irq_set_affinity_notifier function + * to inform the current notification subscriber that they will no longer + * receive notifications. + **/ +static void i40evf_irq_affinity_release(struct kref *ref) {} + +/** * i40evf_request_traffic_irqs - Initialize MSI-X interrupts * @adapter: board private structure * @@ -507,6 +536,7 @@ i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename) { int vector, err, q_vectors; int rx_int_idx = 0, tx_int_idx = 0; + int irq_num; i40evf_irq_disable(adapter); /* Decrement for Other and TCP Timer vectors */ @@ -514,6 +544,7 @@ i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename) for (vector = 0; vector < q_vectors; vector++) { struct i40e_q_vector *q_vector = &adapter->q_vectors[vector]; + irq_num = adapter->msix_entries[vector + NONQ_VECS].vector; if (q_vector->tx.ring && q_vector->rx.ring) { snprintf(q_vector->name, sizeof(q_vector->name) - 1, @@ -532,21 +563,23 @@ i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename) /* skip this unused q_vector */ continue; } - err = request_irq( - adapter->msix_entries[vector + NONQ_VECS].vector, - i40evf_msix_clean_rings, - 0, - q_vector->name, - q_vector); + err = request_irq(irq_num, + i40evf_msix_clean_rings, + 0, + q_vector->name, + q_vector); if (err) { dev_info(&adapter->pdev->dev, "Request_irq failed, error: %d\n", err); goto free_queue_irqs; } + /* register for affinity change notifications */ + q_vector->affinity_notify.notify = i40evf_irq_affinity_notify; + q_vector->affinity_notify.release = + i40evf_irq_affinity_release; + irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify); /* assign the mask for this irq */ - irq_set_affinity_hint( - adapter->msix_entries[vector + NONQ_VECS].vector, - q_vector->affinity_mask); + irq_set_affinity_hint(irq_num, &q_vector->affinity_mask); } return 0; @@ -554,11 +587,10 @@ i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename) free_queue_irqs: while (vector) { vector--; - irq_set_affinity_hint( - adapter->msix_entries[vector + NONQ_VECS].vector, - NULL); - free_irq(adapter->msix_entries[vector + NONQ_VECS].vector, - &adapter->q_vectors[vector]); + irq_num = adapter->msix_entries[vector + NONQ_VECS].vector; + irq_set_affinity_notifier(irq_num, NULL); + irq_set_affinity_hint(irq_num, NULL); + free_irq(irq_num, &adapter->q_vectors[vector]); } return err; } @@ -599,16 +631,18 @@ static int i40evf_request_misc_irq(struct i40evf_adapter *adapter) **/ static void i40evf_free_traffic_irqs(struct i40evf_adapter *adapter) { - int i; - int q_vectors; + int vector, irq_num, q_vectors; + + if (!adapter->msix_entries) + return; q_vectors = adapter->num_msix_vectors - NONQ_VECS; - for (i = 0; i < q_vectors; i++) { - irq_set_affinity_hint(adapter->msix_entries[i+1].vector, - NULL); - free_irq(adapter->msix_entries[i+1].vector, - &adapter->q_vectors[i]); + for (vector = 0; vector < q_vectors; vector++) { + irq_num = adapter->msix_entries[vector + NONQ_VECS].vector; + irq_set_affinity_notifier(irq_num, NULL); + irq_set_affinity_hint(irq_num, NULL); + free_irq(irq_num, &adapter->q_vectors[vector]); } } @@ -622,6 +656,9 @@ static void i40evf_free_misc_irq(struct i40evf_adapter *adapter) { struct net_device *netdev = adapter->netdev; + if (!adapter->msix_entries) + return; + free_irq(adapter->msix_entries[0].vector, netdev); } @@ -1396,6 +1433,9 @@ static void i40evf_free_q_vectors(struct i40evf_adapter *adapter) int q_idx, num_q_vectors; int napi_vectors; + if (!adapter->q_vectors) + return; + num_q_vectors = adapter->num_msix_vectors - NONQ_VECS; napi_vectors = adapter->num_active_queues; @@ -1405,6 +1445,7 @@ static void i40evf_free_q_vectors(struct i40evf_adapter *adapter) netif_napi_del(&q_vector->napi); } kfree(adapter->q_vectors); + adapter->q_vectors = NULL; } /** @@ -1414,6 +1455,9 @@ static void i40evf_free_q_vectors(struct i40evf_adapter *adapter) **/ void i40evf_reset_interrupt_capability(struct i40evf_adapter *adapter) { + if (!adapter->msix_entries) + return; + pci_disable_msix(adapter->pdev); kfree(adapter->msix_entries); adapter->msix_entries = NULL; @@ -1664,6 +1708,49 @@ restart_watchdog: schedule_work(&adapter->adminq_task); } +static void i40evf_disable_vf(struct i40evf_adapter *adapter) +{ + struct i40evf_mac_filter *f, *ftmp; + struct i40evf_vlan_filter *fv, *fvtmp; + + adapter->flags |= I40EVF_FLAG_PF_COMMS_FAILED; + + if (netif_running(adapter->netdev)) { + set_bit(__I40E_DOWN, &adapter->vsi.state); + netif_carrier_off(adapter->netdev); + netif_tx_disable(adapter->netdev); + adapter->link_up = false; + i40evf_napi_disable_all(adapter); + i40evf_irq_disable(adapter); + i40evf_free_traffic_irqs(adapter); + i40evf_free_all_tx_resources(adapter); + i40evf_free_all_rx_resources(adapter); + } + + /* Delete all of the filters, both MAC and VLAN. */ + list_for_each_entry_safe(f, ftmp, &adapter->mac_filter_list, list) { + list_del(&f->list); + kfree(f); + } + + list_for_each_entry_safe(fv, fvtmp, &adapter->vlan_filter_list, list) { + list_del(&fv->list); + kfree(fv); + } + + i40evf_free_misc_irq(adapter); + i40evf_reset_interrupt_capability(adapter); + i40evf_free_queues(adapter); + i40evf_free_q_vectors(adapter); + kfree(adapter->vf_res); + i40evf_shutdown_adminq(&adapter->hw); + adapter->netdev->flags &= ~IFF_UP; + clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); + adapter->flags &= ~I40EVF_FLAG_RESET_PENDING; + adapter->state = __I40EVF_DOWN; + dev_info(&adapter->pdev->dev, "Reset task did not complete, VF disabled\n"); +} + #define I40EVF_RESET_WAIT_MS 10 #define I40EVF_RESET_WAIT_COUNT 500 /** @@ -1717,60 +1804,21 @@ static void i40evf_reset_task(struct work_struct *work) /* wait until the reset is complete and the PF is responding to us */ for (i = 0; i < I40EVF_RESET_WAIT_COUNT; i++) { + /* sleep first to make sure a minimum wait time is met */ + msleep(I40EVF_RESET_WAIT_MS); + reg_val = rd32(hw, I40E_VFGEN_RSTAT) & I40E_VFGEN_RSTAT_VFR_STATE_MASK; if (reg_val == I40E_VFR_VFACTIVE) break; - msleep(I40EVF_RESET_WAIT_MS); } + pci_set_master(adapter->pdev); - /* extra wait to make sure minimum wait is met */ - msleep(I40EVF_RESET_WAIT_MS); - if (i == I40EVF_RESET_WAIT_COUNT) { - struct i40evf_mac_filter *ftmp; - struct i40evf_vlan_filter *fv, *fvtmp; - /* reset never finished */ + if (i == I40EVF_RESET_WAIT_COUNT) { dev_err(&adapter->pdev->dev, "Reset never finished (%x)\n", reg_val); - adapter->flags |= I40EVF_FLAG_PF_COMMS_FAILED; - - if (netif_running(adapter->netdev)) { - set_bit(__I40E_DOWN, &adapter->vsi.state); - netif_carrier_off(netdev); - netif_tx_disable(netdev); - adapter->link_up = false; - i40evf_napi_disable_all(adapter); - i40evf_irq_disable(adapter); - i40evf_free_traffic_irqs(adapter); - i40evf_free_all_tx_resources(adapter); - i40evf_free_all_rx_resources(adapter); - } - - /* Delete all of the filters, both MAC and VLAN. */ - list_for_each_entry_safe(f, ftmp, &adapter->mac_filter_list, - list) { - list_del(&f->list); - kfree(f); - } - - list_for_each_entry_safe(fv, fvtmp, &adapter->vlan_filter_list, - list) { - list_del(&fv->list); - kfree(fv); - } - - i40evf_free_misc_irq(adapter); - i40evf_reset_interrupt_capability(adapter); - i40evf_free_queues(adapter); - i40evf_free_q_vectors(adapter); - kfree(adapter->vf_res); - i40evf_shutdown_adminq(hw); - adapter->netdev->flags &= ~IFF_UP; - clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); - adapter->flags &= ~I40EVF_FLAG_RESET_PENDING; - adapter->state = __I40EVF_DOWN; - dev_info(&adapter->pdev->dev, "Reset task did not complete, VF disabled\n"); + i40evf_disable_vf(adapter); return; /* Do not attempt to reinit. It's dead, Jim. */ } @@ -2105,6 +2153,11 @@ static int i40evf_close(struct net_device *netdev) adapter->state = __I40EVF_DOWN_PENDING; i40evf_free_traffic_irqs(adapter); + /* We explicitly don't free resources here because the hardware is + * still active and can DMA into memory. Resources are cleared in + * i40evf_virtchnl_completion() after we get confirmation from the PF + * driver that the rings have been stopped. + */ return 0; } @@ -2133,10 +2186,6 @@ static struct net_device_stats *i40evf_get_stats(struct net_device *netdev) static int i40evf_change_mtu(struct net_device *netdev, int new_mtu) { struct i40evf_adapter *adapter = netdev_priv(netdev); - int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN; - - if ((new_mtu < 68) || (max_frame > I40E_MAX_RXBUFFER)) - return -EINVAL; netdev->mtu = new_mtu; adapter->flags |= I40EVF_FLAG_RESET_NEEDED; @@ -2145,6 +2194,64 @@ static int i40evf_change_mtu(struct net_device *netdev, int new_mtu) return 0; } +/** + * i40evf_features_check - Validate encapsulated packet conforms to limits + * @skb: skb buff + * @netdev: This physical port's netdev + * @features: Offload features that the stack believes apply + **/ +static netdev_features_t i40evf_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features) +{ + size_t len; + + /* No point in doing any of this if neither checksum nor GSO are + * being requested for this frame. We can rule out both by just + * checking for CHECKSUM_PARTIAL + */ + if (skb->ip_summed != CHECKSUM_PARTIAL) + return features; + + /* We cannot support GSO if the MSS is going to be less than + * 64 bytes. If it is then we need to drop support for GSO. + */ + if (skb_is_gso(skb) && (skb_shinfo(skb)->gso_size < 64)) + features &= ~NETIF_F_GSO_MASK; + + /* MACLEN can support at most 63 words */ + len = skb_network_header(skb) - skb->data; + if (len & ~(63 * 2)) + goto out_err; + + /* IPLEN and EIPLEN can support at most 127 dwords */ + len = skb_transport_header(skb) - skb_network_header(skb); + if (len & ~(127 * 4)) + goto out_err; + + if (skb->encapsulation) { + /* L4TUNLEN can support 127 words */ + len = skb_inner_network_header(skb) - skb_transport_header(skb); + if (len & ~(127 * 2)) + goto out_err; + + /* IPLEN can support at most 127 dwords */ + len = skb_inner_transport_header(skb) - + skb_inner_network_header(skb); + if (len & ~(127 * 4)) + goto out_err; + } + + /* No need to validate L4LEN as TCP is the only protocol with a + * a flexible value and we support all possible values supported + * by TCP, which is at most 15 dwords + */ + + return features; +out_err: + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); +} + #define I40EVF_VLAN_FEATURES (NETIF_F_HW_VLAN_CTAG_TX |\ NETIF_F_HW_VLAN_CTAG_RX |\ NETIF_F_HW_VLAN_CTAG_FILTER) @@ -2179,6 +2286,7 @@ static const struct net_device_ops i40evf_netdev_ops = { .ndo_tx_timeout = i40evf_tx_timeout, .ndo_vlan_rx_add_vid = i40evf_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = i40evf_vlan_rx_kill_vid, + .ndo_features_check = i40evf_features_check, .ndo_fix_features = i40evf_fix_features, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = i40evf_netpoll, @@ -2424,6 +2532,10 @@ static void i40evf_init_task(struct work_struct *work) i40evf_set_ethtool_ops(netdev); netdev->watchdog_timeo = 5 * HZ; + /* MTU range: 68 - 9710 */ + netdev->min_mtu = ETH_MIN_MTU; + netdev->max_mtu = I40E_MAX_RXBUFFER - (ETH_HLEN + ETH_FCS_LEN); + if (!is_valid_ether_addr(adapter->hw.mac.addr)) { dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n", adapter->hw.mac.addr); @@ -2619,6 +2731,7 @@ static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw->subsystem_device_id = pdev->subsystem_device; hw->bus.device = PCI_SLOT(pdev->devfn); hw->bus.func = PCI_FUNC(pdev->devfn); + hw->bus.bus_id = pdev->bus->number; /* set up the locks for the AQ, do this only once in probe * and destroy them only once in remove @@ -2763,13 +2876,12 @@ static void i40evf_remove(struct pci_dev *pdev) i40evf_request_reset(adapter); msleep(50); } - - if (adapter->msix_entries) { - i40evf_misc_irq_disable(adapter); - i40evf_free_misc_irq(adapter); - i40evf_reset_interrupt_capability(adapter); - i40evf_free_q_vectors(adapter); - } + i40evf_free_all_tx_resources(adapter); + i40evf_free_all_rx_resources(adapter); + i40evf_misc_irq_disable(adapter); + i40evf_free_misc_irq(adapter); + i40evf_reset_interrupt_capability(adapter); + i40evf_free_q_vectors(adapter); if (adapter->watchdog_timer.function) del_timer_sync(&adapter->watchdog_timer); diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c index ddf478d6322b..bee58af390e1 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c @@ -836,6 +836,9 @@ static void i40evf_print_link_message(struct i40evf_adapter *adapter) case I40E_LINK_SPEED_40GB: speed = "40 G"; break; + case I40E_LINK_SPEED_25GB: + speed = "25 G"; + break; case I40E_LINK_SPEED_20GB: speed = "20 G"; break; @@ -996,6 +999,10 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, if (v_opcode != adapter->current_op) return; break; + case I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP: + adapter->client_pending &= + ~(BIT(I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP)); + break; case I40E_VIRTCHNL_OP_GET_RSS_HENA_CAPS: { struct i40e_virtchnl_rss_hena *vrh = (struct i40e_virtchnl_rss_hena *)msg; diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c index a61447fd778e..ee443985581f 100644 --- a/drivers/net/ethernet/intel/igb/e1000_82575.c +++ b/drivers/net/ethernet/intel/igb/e1000_82575.c @@ -245,6 +245,17 @@ static s32 igb_init_phy_params_82575(struct e1000_hw *hw) hw->bus.func = (rd32(E1000_STATUS) & E1000_STATUS_FUNC_MASK) >> E1000_STATUS_FUNC_SHIFT; + /* Make sure the PHY is in a good state. Several people have reported + * firmware leaving the PHY's page select register set to something + * other than the default of zero, which causes the PHY ID read to + * access something other than the intended register. + */ + ret_val = hw->phy.ops.reset(hw); + if (ret_val) { + hw_dbg("Error resetting the PHY.\n"); + goto out; + } + /* Set phy->phy_addr and phy->id. */ ret_val = igb_get_phy_id_82575(hw); if (ret_val) diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h index 2688180a7acd..8aee314332a8 100644 --- a/drivers/net/ethernet/intel/igb/e1000_defines.h +++ b/drivers/net/ethernet/intel/igb/e1000_defines.h @@ -357,7 +357,8 @@ #define ETHERNET_IEEE_VLAN_TYPE 0x8100 /* 802.3ac packet */ /* As per the EAS the maximum supported size is 9.5KB (9728 bytes) */ -#define MAX_JUMBO_FRAME_SIZE 0x2600 +#define MAX_JUMBO_FRAME_SIZE 0x2600 +#define MAX_STD_JUMBO_FRAME_SIZE 9216 /* PBA constants */ #define E1000_PBA_34K 0x0022 diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.c b/drivers/net/ethernet/intel/igb/e1000_i210.c index 8aa798737d4d..07d48f2e3369 100644 --- a/drivers/net/ethernet/intel/igb/e1000_i210.c +++ b/drivers/net/ethernet/intel/igb/e1000_i210.c @@ -699,9 +699,9 @@ static s32 igb_update_flash_i210(struct e1000_hw *hw) ret_val = igb_pool_flash_update_done_i210(hw); if (ret_val) - hw_dbg("Flash update complete\n"); - else hw_dbg("Flash update time out\n"); + else + hw_dbg("Flash update complete\n"); out: return ret_val; diff --git a/drivers/net/ethernet/intel/igb/e1000_mac.c b/drivers/net/ethernet/intel/igb/e1000_mac.c index 5010e2232c50..5eff82678f0b 100644 --- a/drivers/net/ethernet/intel/igb/e1000_mac.c +++ b/drivers/net/ethernet/intel/igb/e1000_mac.c @@ -792,15 +792,13 @@ static s32 igb_set_default_fc(struct e1000_hw *hw) * control setting, then the variable hw->fc will * be initialized based on a value in the EEPROM. */ - if (hw->mac.type == e1000_i350) { + if (hw->mac.type == e1000_i350) lan_offset = NVM_82580_LAN_FUNC_OFFSET(hw->bus.func); - ret_val = hw->nvm.ops.read(hw, NVM_INIT_CONTROL2_REG - + lan_offset, 1, &nvm_data); - } else { - ret_val = hw->nvm.ops.read(hw, NVM_INIT_CONTROL2_REG, - 1, &nvm_data); - } + else + lan_offset = 0; + ret_val = hw->nvm.ops.read(hw, NVM_INIT_CONTROL2_REG + lan_offset, + 1, &nvm_data); if (ret_val) { hw_dbg("NVM Read Error\n"); goto out; @@ -808,8 +806,7 @@ static s32 igb_set_default_fc(struct e1000_hw *hw) if ((nvm_data & NVM_WORD0F_PAUSE_MASK) == 0) hw->fc.requested_mode = e1000_fc_none; - else if ((nvm_data & NVM_WORD0F_PAUSE_MASK) == - NVM_WORD0F_ASM_DIR) + else if ((nvm_data & NVM_WORD0F_PAUSE_MASK) == NVM_WORD0F_ASM_DIR) hw->fc.requested_mode = e1000_fc_tx_pause; else hw->fc.requested_mode = e1000_fc_full; diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.c b/drivers/net/ethernet/intel/igb/e1000_phy.c index 5b54254aed4f..68812d783f33 100644 --- a/drivers/net/ethernet/intel/igb/e1000_phy.c +++ b/drivers/net/ethernet/intel/igb/e1000_phy.c @@ -77,6 +77,10 @@ s32 igb_get_phy_id(struct e1000_hw *hw) s32 ret_val = 0; u16 phy_id; + /* ensure PHY page selection to fix misconfigured i210 */ + if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211)) + phy->ops.write_reg(hw, I347AT4_PAGE_SELECT, 0); + ret_val = phy->ops.read_reg(hw, PHY_ID1, &phy_id); if (ret_val) goto out; @@ -290,7 +294,7 @@ s32 igb_write_phy_reg_i2c(struct e1000_hw *hw, u32 offset, u16 data) u32 i, i2ccmd = 0; u16 phy_data_swapped; - /* Prevent overwritting SFP I2C EEPROM which is at A0 address.*/ + /* Prevent overwriting SFP I2C EEPROM which is at A0 address.*/ if ((hw->phy.addr == 0) || (hw->phy.addr > 7)) { hw_dbg("PHY I2C Address %d is out of range.\n", hw->phy.addr); diff --git a/drivers/net/ethernet/intel/igb/e1000_regs.h b/drivers/net/ethernet/intel/igb/e1000_regs.h index d84afdd83e53..58adbf234e07 100644 --- a/drivers/net/ethernet/intel/igb/e1000_regs.h +++ b/drivers/net/ethernet/intel/igb/e1000_regs.h @@ -320,7 +320,7 @@ #define E1000_VT_CTL 0x0581C /* VMDq Control - RW */ #define E1000_WUC 0x05800 /* Wakeup Control - RW */ #define E1000_WUFC 0x05808 /* Wakeup Filter Control - RW */ -#define E1000_WUS 0x05810 /* Wakeup Status - RO */ +#define E1000_WUS 0x05810 /* Wakeup Status - R/W1C */ #define E1000_MANC 0x05820 /* Management Control - RW */ #define E1000_IPAV 0x05838 /* IP Address Valid - RW */ #define E1000_WUPL 0x05900 /* Wakeup Packet Length - RW */ diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index d11093dce1b9..acbc3abe2ddd 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -210,7 +210,12 @@ struct igb_tx_buffer { struct igb_rx_buffer { dma_addr_t dma; struct page *page; - unsigned int page_offset; +#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536) + __u32 page_offset; +#else + __u16 page_offset; +#endif + __u16 pagecnt_bias; }; struct igb_tx_queue_stats { diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 9affd7c198bd..be456bae8169 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -137,8 +137,8 @@ static void igb_update_phy_info(unsigned long); static void igb_watchdog(unsigned long); static void igb_watchdog_task(struct work_struct *); static netdev_tx_t igb_xmit_frame(struct sk_buff *skb, struct net_device *); -static struct rtnl_link_stats64 *igb_get_stats64(struct net_device *dev, - struct rtnl_link_stats64 *stats); +static void igb_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *stats); static int igb_change_mtu(struct net_device *, int); static int igb_set_mac(struct net_device *, void *); static void igb_set_uta(struct igb_adapter *adapter, bool set); @@ -383,9 +383,9 @@ static void igb_dump(struct igb_adapter *adapter) /* Print netdevice Info */ if (netdev) { dev_info(&adapter->pdev->dev, "Net device Info\n"); - pr_info("Device Name state trans_start last_rx\n"); - pr_info("%-15s %016lX %016lX %016lX\n", netdev->name, - netdev->state, dev_trans_start(netdev), netdev->last_rx); + pr_info("Device Name state trans_start\n"); + pr_info("%-15s %016lX %016lX\n", netdev->name, + netdev->state, dev_trans_start(netdev)); } /* Print Registers */ @@ -2468,6 +2468,10 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->priv_flags |= IFF_UNICAST_FLT; + /* MTU range: 68 - 9216 */ + netdev->min_mtu = ETH_MIN_MTU; + netdev->max_mtu = MAX_STD_JUMBO_FRAME_SIZE; + adapter->en_mng_pt = igb_enable_mng_pass_thru(hw); /* before reading the NVM, reset the controller to put the device in a @@ -3271,7 +3275,9 @@ static int __igb_close(struct net_device *netdev, bool suspending) int igb_close(struct net_device *netdev) { - return __igb_close(netdev, false); + if (netif_device_present(netdev)) + return __igb_close(netdev, false); + return 0; } /** @@ -3390,7 +3396,7 @@ void igb_configure_tx_ring(struct igb_adapter *adapter, tdba & 0x00000000ffffffffULL); wr32(E1000_TDBAH(reg_idx), tdba >> 32); - ring->tail = hw->hw_addr + E1000_TDT(reg_idx); + ring->tail = adapter->io_addr + E1000_TDT(reg_idx); wr32(E1000_TDH(reg_idx), 0); writel(0, ring->tail); @@ -3729,7 +3735,7 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, ring->count * sizeof(union e1000_adv_rx_desc)); /* initialize head and tail */ - ring->tail = hw->hw_addr + E1000_RDT(reg_idx); + ring->tail = adapter->io_addr + E1000_RDT(reg_idx); wr32(E1000_RDH(reg_idx), 0); writel(0, ring->tail); @@ -3943,11 +3949,23 @@ static void igb_clean_rx_ring(struct igb_ring *rx_ring) if (!buffer_info->page) continue; - dma_unmap_page(rx_ring->dev, - buffer_info->dma, - PAGE_SIZE, - DMA_FROM_DEVICE); - __free_page(buffer_info->page); + /* Invalidate cache lines that may have been written to by + * device so that we avoid corrupting memory. + */ + dma_sync_single_range_for_cpu(rx_ring->dev, + buffer_info->dma, + buffer_info->page_offset, + IGB_RX_BUFSZ, + DMA_FROM_DEVICE); + + /* free resources associated with mapping */ + dma_unmap_page_attrs(rx_ring->dev, + buffer_info->dma, + PAGE_SIZE, + DMA_FROM_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC); + __page_frag_cache_drain(buffer_info->page, + buffer_info->pagecnt_bias); buffer_info->page = NULL; } @@ -5386,8 +5404,8 @@ static void igb_reset_task(struct work_struct *work) * @netdev: network interface device structure * @stats: rtnl_link_stats64 pointer **/ -static struct rtnl_link_stats64 *igb_get_stats64(struct net_device *netdev, - struct rtnl_link_stats64 *stats) +static void igb_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *stats) { struct igb_adapter *adapter = netdev_priv(netdev); @@ -5395,8 +5413,6 @@ static struct rtnl_link_stats64 *igb_get_stats64(struct net_device *netdev, igb_update_stats(adapter, &adapter->stats64); memcpy(stats, &adapter->stats64, sizeof(*stats)); spin_unlock(&adapter->stats64_lock); - - return stats; } /** @@ -5412,17 +5428,6 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu) struct pci_dev *pdev = adapter->pdev; int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; - if ((new_mtu < 68) || (max_frame > MAX_JUMBO_FRAME_SIZE)) { - dev_err(&pdev->dev, "Invalid MTU setting\n"); - return -EINVAL; - } - -#define MAX_STD_JUMBO_FRAME_SIZE 9238 - if (max_frame > MAX_STD_JUMBO_FRAME_SIZE) { - dev_err(&pdev->dev, "MTU > 9216 not supported.\n"); - return -EINVAL; - } - /* adjust max frame to be at least the size of a standard frame */ if (max_frame < (ETH_FRAME_LEN + ETH_FCS_LEN)) max_frame = ETH_FRAME_LEN + ETH_FCS_LEN; @@ -6819,12 +6824,6 @@ static void igb_reuse_rx_page(struct igb_ring *rx_ring, /* transfer page from old buffer to new buffer */ *new_buff = *old_buff; - - /* sync the buffer for use by the device */ - dma_sync_single_range_for_device(rx_ring->dev, old_buff->dma, - old_buff->page_offset, - IGB_RX_BUFSZ, - DMA_FROM_DEVICE); } static inline bool igb_page_is_reserved(struct page *page) @@ -6836,13 +6835,15 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, struct page *page, unsigned int truesize) { + unsigned int pagecnt_bias = rx_buffer->pagecnt_bias--; + /* avoid re-using remote pages */ if (unlikely(igb_page_is_reserved(page))) return false; #if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ - if (unlikely(page_count(page) != 1)) + if (unlikely(page_ref_count(page) != pagecnt_bias)) return false; /* flip page offset to other buffer */ @@ -6855,10 +6856,14 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, return false; #endif - /* Even if we own the page, we are not allowed to use atomic_set() - * This would break get_page_unless_zero() users. + /* If we have drained the page fragment pool we need to update + * the pagecnt_bias and page count so that we fully restock the + * number of references the driver holds. */ - page_ref_inc(page); + if (unlikely(pagecnt_bias == 1)) { + page_ref_add(page, USHRT_MAX); + rx_buffer->pagecnt_bias = USHRT_MAX; + } return true; } @@ -6910,7 +6915,6 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring, return true; /* this page cannot be reused so discard it */ - __free_page(page); return false; } @@ -6945,6 +6949,13 @@ static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring, page = rx_buffer->page; prefetchw(page); + /* we are reusing so sync this buffer for CPU use */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + size, + DMA_FROM_DEVICE); + if (likely(!skb)) { void *page_addr = page_address(page) + rx_buffer->page_offset; @@ -6969,21 +6980,18 @@ static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring, prefetchw(skb->data); } - /* we are reusing so sync this buffer for CPU use */ - dma_sync_single_range_for_cpu(rx_ring->dev, - rx_buffer->dma, - rx_buffer->page_offset, - size, - DMA_FROM_DEVICE); - /* pull page into skb */ if (igb_add_rx_frag(rx_ring, rx_buffer, size, rx_desc, skb)) { /* hand second half of page back to the ring */ igb_reuse_rx_page(rx_ring, rx_buffer); } else { - /* we are not reusing the buffer so unmap it */ - dma_unmap_page(rx_ring->dev, rx_buffer->dma, - PAGE_SIZE, DMA_FROM_DEVICE); + /* We are not reusing the buffer so unmap it and free + * any references we are holding to it + */ + dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, + PAGE_SIZE, DMA_FROM_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC); + __page_frag_cache_drain(page, rx_buffer->pagecnt_bias); } /* clear contents of rx_buffer */ @@ -7241,7 +7249,8 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, } /* map page for use */ - dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE); + dma = dma_map_page_attrs(rx_ring->dev, page, 0, PAGE_SIZE, + DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC); /* if mapping failed free memory back to system since * there isn't much point in holding memory we can't use @@ -7256,6 +7265,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, bi->dma = dma; bi->page = page; bi->page_offset = 0; + bi->pagecnt_bias = 1; return true; } @@ -7282,6 +7292,12 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count) if (!igb_alloc_mapped_page(rx_ring, bi)) break; + /* sync the buffer for use by the device */ + dma_sync_single_range_for_device(rx_ring->dev, bi->dma, + bi->page_offset, + IGB_RX_BUFSZ, + DMA_FROM_DEVICE); + /* Refresh the desc even if buffer_addrs didn't change * because each write-back erases this info. */ @@ -7548,6 +7564,7 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake, int retval = 0; #endif + rtnl_lock(); netif_device_detach(netdev); if (netif_running(netdev)) @@ -7556,6 +7573,7 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake, igb_ptp_suspend(adapter); igb_clear_interrupt_scheme(adapter); + rtnl_unlock(); #ifdef CONFIG_PM retval = pci_save_state(pdev); @@ -7674,16 +7692,15 @@ static int igb_resume(struct device *dev) wr32(E1000_WUS, ~0); - if (netdev->flags & IFF_UP) { - rtnl_lock(); + rtnl_lock(); + if (!err && netif_running(netdev)) err = __igb_open(netdev, true); - rtnl_unlock(); - if (err) - return err; - } - netif_device_attach(netdev); - return 0; + if (!err) + netif_device_attach(netdev); + rtnl_unlock(); + + return err; } static int igb_runtime_idle(struct device *dev) @@ -7882,6 +7899,11 @@ static pci_ers_result_t igb_io_slot_reset(struct pci_dev *pdev) pci_enable_wake(pdev, PCI_D3hot, 0); pci_enable_wake(pdev, PCI_D3cold, 0); + /* In case of PCI error, adapter lose its HW address + * so we should re-assign it here. + */ + hw->hw_addr = adapter->io_addr; + igb_reset(adapter); wr32(E1000_WUS, ~0); result = PCI_ERS_RESULT_RECOVERED; diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index a7895c4cbcc3..c4477552ce9e 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -77,7 +77,7 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter); /* SYSTIM read access for the 82576 */ -static cycle_t igb_ptp_read_82576(const struct cyclecounter *cc) +static u64 igb_ptp_read_82576(const struct cyclecounter *cc) { struct igb_adapter *igb = container_of(cc, struct igb_adapter, cc); struct e1000_hw *hw = &igb->hw; @@ -94,7 +94,7 @@ static cycle_t igb_ptp_read_82576(const struct cyclecounter *cc) } /* SYSTIM read access for the 82580 */ -static cycle_t igb_ptp_read_82580(const struct cyclecounter *cc) +static u64 igb_ptp_read_82580(const struct cyclecounter *cc) { struct igb_adapter *igb = container_of(cc, struct igb_adapter, cc); struct e1000_hw *hw = &igb->hw; @@ -226,7 +226,7 @@ static int igb_ptp_adjfreq_82576(struct ptp_clock_info *ptp, s32 ppb) return 0; } -static int igb_ptp_adjfreq_82580(struct ptp_clock_info *ptp, s32 ppb) +static int igb_ptp_adjfine_82580(struct ptp_clock_info *ptp, long scaled_ppm) { struct igb_adapter *igb = container_of(ptp, struct igb_adapter, ptp_caps); @@ -235,13 +235,13 @@ static int igb_ptp_adjfreq_82580(struct ptp_clock_info *ptp, s32 ppb) u64 rate; u32 inca; - if (ppb < 0) { + if (scaled_ppm < 0) { neg_adj = 1; - ppb = -ppb; + scaled_ppm = -scaled_ppm; } - rate = ppb; - rate <<= 26; - rate = div_u64(rate, 1953125); + rate = scaled_ppm; + rate <<= 13; + rate = div_u64(rate, 15625); inca = rate & INCVALUE_MASK; if (neg_adj) @@ -1103,7 +1103,7 @@ void igb_ptp_init(struct igb_adapter *adapter) adapter->ptp_caps.max_adj = 62499999; adapter->ptp_caps.n_ext_ts = 0; adapter->ptp_caps.pps = 0; - adapter->ptp_caps.adjfreq = igb_ptp_adjfreq_82580; + adapter->ptp_caps.adjfine = igb_ptp_adjfine_82580; adapter->ptp_caps.adjtime = igb_ptp_adjtime_82576; adapter->ptp_caps.gettime64 = igb_ptp_gettime_82576; adapter->ptp_caps.settime64 = igb_ptp_settime_82576; @@ -1131,7 +1131,7 @@ void igb_ptp_init(struct igb_adapter *adapter) adapter->ptp_caps.n_pins = IGB_N_SDP; adapter->ptp_caps.pps = 1; adapter->ptp_caps.pin_config = adapter->sdp_config; - adapter->ptp_caps.adjfreq = igb_ptp_adjfreq_82580; + adapter->ptp_caps.adjfine = igb_ptp_adjfine_82580; adapter->ptp_caps.adjtime = igb_ptp_adjtime_i210; adapter->ptp_caps.gettime64 = igb_ptp_gettime_i210; adapter->ptp_caps.settime64 = igb_ptp_settime_i210; diff --git a/drivers/net/ethernet/intel/igbvf/defines.h b/drivers/net/ethernet/intel/igbvf/defines.h index ee1ef08d7fc4..f1789d192e24 100644 --- a/drivers/net/ethernet/intel/igbvf/defines.h +++ b/drivers/net/ethernet/intel/igbvf/defines.h @@ -85,7 +85,8 @@ #define E1000_TXD_CMD_DEXT 0x20000000 /* Desc extension (0 = legacy) */ #define E1000_TXD_STAT_DD 0x00000001 /* Desc Done */ -#define MAX_JUMBO_FRAME_SIZE 0x3F00 +#define MAX_JUMBO_FRAME_SIZE 0x3F00 +#define MAX_STD_JUMBO_FRAME_SIZE 9216 /* 802.1q VLAN Packet Size */ #define VLAN_TAG_SIZE 4 /* 802.3ac tag (not DMA'd) */ diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 7dff7f6239cd..839ba110f7fb 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -2360,16 +2360,6 @@ static int igbvf_change_mtu(struct net_device *netdev, int new_mtu) struct igbvf_adapter *adapter = netdev_priv(netdev); int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN; - if (new_mtu < 68 || new_mtu > INT_MAX - ETH_HLEN - ETH_FCS_LEN || - max_frame > MAX_JUMBO_FRAME_SIZE) - return -EINVAL; - -#define MAX_STD_JUMBO_FRAME_SIZE 9234 - if (max_frame > MAX_STD_JUMBO_FRAME_SIZE) { - dev_err(&adapter->pdev->dev, "MTU > 9216 not supported.\n"); - return -EINVAL; - } - while (test_and_set_bit(__IGBVF_RESETTING, &adapter->state)) usleep_range(1000, 2000); /* igbvf_down has a dependency on max_frame_size */ @@ -2790,6 +2780,10 @@ static int igbvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_TX; + /* MTU range: 68 - 9216 */ + netdev->min_mtu = ETH_MIN_MTU; + netdev->max_mtu = MAX_STD_JUMBO_FRAME_SIZE; + /*reset the controller to put the device in a known good state */ err = hw->mac.ops.reset_hw(hw); if (err) { diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c index d2b29b490ae0..e5d72559cca9 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c @@ -30,7 +30,7 @@ #include "ixgb.h" -#include <asm/uaccess.h> +#include <linux/uaccess.h> #define IXGB_ALL_RAR_ENTRIES 16 diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c index 31f91459312f..fbd220d137b3 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c @@ -487,6 +487,10 @@ ixgb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->vlan_features |= NETIF_F_HIGHDMA; } + /* MTU range: 68 - 16114 */ + netdev->min_mtu = ETH_MIN_MTU; + netdev->max_mtu = IXGB_MAX_JUMBO_FRAME_SIZE - ETH_HLEN; + /* make sure the EEPROM is good */ if (!ixgb_validate_eeprom_checksum(&adapter->hw)) { @@ -1619,18 +1623,6 @@ ixgb_change_mtu(struct net_device *netdev, int new_mtu) { struct ixgb_adapter *adapter = netdev_priv(netdev); int max_frame = new_mtu + ENET_HEADER_SIZE + ENET_FCS_LENGTH; - int old_max_frame = netdev->mtu + ENET_HEADER_SIZE + ENET_FCS_LENGTH; - - /* MTU < 68 is an error for IPv4 traffic, just don't allow it */ - if ((new_mtu < 68) || - (max_frame > IXGB_MAX_JUMBO_FRAME_SIZE + ENET_FCS_LENGTH)) { - netif_err(adapter, probe, adapter->netdev, - "Invalid MTU setting %d\n", new_mtu); - return -EINVAL; - } - - if (old_max_frame == max_frame) - return 0; if (netif_running(netdev)) ixgb_down(adapter, true); @@ -1825,7 +1817,7 @@ ixgb_clean(struct napi_struct *napi, int budget) /* If budget not fully consumed, exit the polling mode */ if (work_done < budget) { - napi_complete(napi); + napi_complete_done(napi, work_done); if (!test_bit(__IXGB_DOWN, &adapter->flags)) ixgb_irq_enable(adapter); } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index b06e32d0d22a..b1ecc2627a5a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -55,9 +55,6 @@ #include <net/busy_poll.h> -#ifdef CONFIG_NET_RX_BUSY_POLL -#define BP_EXTENDED_STATS -#endif /* common prefix used by pr_<> macros */ #undef pr_fmt #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -94,6 +91,14 @@ #define IXGBE_RXBUFFER_4K 4096 #define IXGBE_MAX_RXBUFFER 16384 /* largest size for a single descriptor */ +#define IXGBE_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) +#if (PAGE_SIZE < 8192) +#define IXGBE_MAX_FRAME_BUILD_SKB \ + (SKB_WITH_OVERHEAD(IXGBE_RXBUFFER_2K) - IXGBE_SKB_PAD) +#else +#define IXGBE_MAX_FRAME_BUILD_SKB IXGBE_RXBUFFER_2K +#endif + /* * NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN means we * reserve 64 more, and skb_shared_info adds an additional 320 bytes more, @@ -107,6 +112,9 @@ /* How many Rx Buffers do we bundle into one write to the hardware ? */ #define IXGBE_RX_BUFFER_WRITE 16 /* Must be power of 2 */ +#define IXGBE_RX_DMA_ATTR \ + (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) + enum ixgbe_tx_flags { /* cmd_type flags */ IXGBE_TX_FLAGS_HW_VLAN = 0x01, @@ -159,6 +167,7 @@ enum ixgbevf_xcast_modes { IXGBEVF_XCAST_MODE_NONE = 0, IXGBEVF_XCAST_MODE_MULTI, IXGBEVF_XCAST_MODE_ALLMULTI, + IXGBEVF_XCAST_MODE_PROMISC, }; struct vf_macvlans { @@ -194,17 +203,17 @@ struct ixgbe_rx_buffer { struct sk_buff *skb; dma_addr_t dma; struct page *page; - unsigned int page_offset; +#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536) + __u32 page_offset; +#else + __u16 page_offset; +#endif + __u16 pagecnt_bias; }; struct ixgbe_queue_stats { u64 packets; u64 bytes; -#ifdef BP_EXTENDED_STATS - u64 yields; - u64 misses; - u64 cleaned; -#endif /* BP_EXTENDED_STATS */ }; struct ixgbe_tx_queue_stats { @@ -225,15 +234,20 @@ struct ixgbe_rx_queue_stats { #define IXGBE_TS_HDR_LEN 8 enum ixgbe_ring_state_t { + __IXGBE_RX_3K_BUFFER, + __IXGBE_RX_BUILD_SKB_ENABLED, + __IXGBE_RX_RSC_ENABLED, + __IXGBE_RX_CSUM_UDP_ZERO_ERR, + __IXGBE_RX_FCOE, __IXGBE_TX_FDIR_INIT_DONE, __IXGBE_TX_XPS_INIT_DONE, __IXGBE_TX_DETECT_HANG, __IXGBE_HANG_CHECK_ARMED, - __IXGBE_RX_RSC_ENABLED, - __IXGBE_RX_CSUM_UDP_ZERO_ERR, - __IXGBE_RX_FCOE, }; +#define ring_uses_build_skb(ring) \ + test_bit(__IXGBE_RX_BUILD_SKB_ENABLED, &(ring)->state) + struct ixgbe_fwd_adapter { unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; struct net_device *netdev; @@ -343,19 +357,20 @@ struct ixgbe_ring_feature { */ static inline unsigned int ixgbe_rx_bufsz(struct ixgbe_ring *ring) { -#ifdef IXGBE_FCOE - if (test_bit(__IXGBE_RX_FCOE, &ring->state)) - return (PAGE_SIZE < 8192) ? IXGBE_RXBUFFER_4K : - IXGBE_RXBUFFER_3K; + if (test_bit(__IXGBE_RX_3K_BUFFER, &ring->state)) + return IXGBE_RXBUFFER_3K; +#if (PAGE_SIZE < 8192) + if (ring_uses_build_skb(ring)) + return IXGBE_MAX_FRAME_BUILD_SKB; #endif return IXGBE_RXBUFFER_2K; } static inline unsigned int ixgbe_rx_pg_order(struct ixgbe_ring *ring) { -#ifdef IXGBE_FCOE - if (test_bit(__IXGBE_RX_FCOE, &ring->state)) - return (PAGE_SIZE < 8192) ? 1 : 0; +#if (PAGE_SIZE < 8192) + if (test_bit(__IXGBE_RX_3K_BUFFER, &ring->state)) + return 1; #endif return 0; } @@ -398,127 +413,10 @@ struct ixgbe_q_vector { struct rcu_head rcu; /* to avoid race with update stats on free */ char name[IFNAMSIZ + 9]; -#ifdef CONFIG_NET_RX_BUSY_POLL - atomic_t state; -#endif /* CONFIG_NET_RX_BUSY_POLL */ - /* for dynamic allocation of rings associated with this q_vector */ struct ixgbe_ring ring[0] ____cacheline_internodealigned_in_smp; }; -#ifdef CONFIG_NET_RX_BUSY_POLL -enum ixgbe_qv_state_t { - IXGBE_QV_STATE_IDLE = 0, - IXGBE_QV_STATE_NAPI, - IXGBE_QV_STATE_POLL, - IXGBE_QV_STATE_DISABLE -}; - -static inline void ixgbe_qv_init_lock(struct ixgbe_q_vector *q_vector) -{ - /* reset state to idle */ - atomic_set(&q_vector->state, IXGBE_QV_STATE_IDLE); -} - -/* called from the device poll routine to get ownership of a q_vector */ -static inline bool ixgbe_qv_lock_napi(struct ixgbe_q_vector *q_vector) -{ - int rc = atomic_cmpxchg(&q_vector->state, IXGBE_QV_STATE_IDLE, - IXGBE_QV_STATE_NAPI); -#ifdef BP_EXTENDED_STATS - if (rc != IXGBE_QV_STATE_IDLE) - q_vector->tx.ring->stats.yields++; -#endif - - return rc == IXGBE_QV_STATE_IDLE; -} - -/* returns true is someone tried to get the qv while napi had it */ -static inline void ixgbe_qv_unlock_napi(struct ixgbe_q_vector *q_vector) -{ - WARN_ON(atomic_read(&q_vector->state) != IXGBE_QV_STATE_NAPI); - - /* flush any outstanding Rx frames */ - if (q_vector->napi.gro_list) - napi_gro_flush(&q_vector->napi, false); - - /* reset state to idle */ - atomic_set(&q_vector->state, IXGBE_QV_STATE_IDLE); -} - -/* called from ixgbe_low_latency_poll() */ -static inline bool ixgbe_qv_lock_poll(struct ixgbe_q_vector *q_vector) -{ - int rc = atomic_cmpxchg(&q_vector->state, IXGBE_QV_STATE_IDLE, - IXGBE_QV_STATE_POLL); -#ifdef BP_EXTENDED_STATS - if (rc != IXGBE_QV_STATE_IDLE) - q_vector->rx.ring->stats.yields++; -#endif - return rc == IXGBE_QV_STATE_IDLE; -} - -/* returns true if someone tried to get the qv while it was locked */ -static inline void ixgbe_qv_unlock_poll(struct ixgbe_q_vector *q_vector) -{ - WARN_ON(atomic_read(&q_vector->state) != IXGBE_QV_STATE_POLL); - - /* reset state to idle */ - atomic_set(&q_vector->state, IXGBE_QV_STATE_IDLE); -} - -/* true if a socket is polling, even if it did not get the lock */ -static inline bool ixgbe_qv_busy_polling(struct ixgbe_q_vector *q_vector) -{ - return atomic_read(&q_vector->state) == IXGBE_QV_STATE_POLL; -} - -/* false if QV is currently owned */ -static inline bool ixgbe_qv_disable(struct ixgbe_q_vector *q_vector) -{ - int rc = atomic_cmpxchg(&q_vector->state, IXGBE_QV_STATE_IDLE, - IXGBE_QV_STATE_DISABLE); - - return rc == IXGBE_QV_STATE_IDLE; -} - -#else /* CONFIG_NET_RX_BUSY_POLL */ -static inline void ixgbe_qv_init_lock(struct ixgbe_q_vector *q_vector) -{ -} - -static inline bool ixgbe_qv_lock_napi(struct ixgbe_q_vector *q_vector) -{ - return true; -} - -static inline bool ixgbe_qv_unlock_napi(struct ixgbe_q_vector *q_vector) -{ - return false; -} - -static inline bool ixgbe_qv_lock_poll(struct ixgbe_q_vector *q_vector) -{ - return false; -} - -static inline bool ixgbe_qv_unlock_poll(struct ixgbe_q_vector *q_vector) -{ - return false; -} - -static inline bool ixgbe_qv_busy_polling(struct ixgbe_q_vector *q_vector) -{ - return false; -} - -static inline bool ixgbe_qv_disable(struct ixgbe_q_vector *q_vector) -{ - return true; -} - -#endif /* CONFIG_NET_RX_BUSY_POLL */ - #ifdef CONFIG_IXGBE_HWMON #define IXGBE_HWMON_TYPE_LOC 0 @@ -661,6 +559,9 @@ struct ixgbe_adapter { #define IXGBE_FLAG2_PHY_INTERRUPT BIT(11) #define IXGBE_FLAG2_UDP_TUN_REREG_NEEDED BIT(12) #define IXGBE_FLAG2_VLAN_PROMISC BIT(13) +#define IXGBE_FLAG2_EEE_CAPABLE BIT(14) +#define IXGBE_FLAG2_EEE_ENABLED BIT(15) +#define IXGBE_FLAG2_RX_LEGACY BIT(16) /* Tx fast path data */ int num_tx_queues; @@ -862,6 +763,7 @@ enum ixgbe_boards { board_X550, board_X550EM_x, board_x550em_a, + board_x550em_a_fw, }; extern const struct ixgbe_info ixgbe_82598_info; @@ -870,8 +772,9 @@ extern const struct ixgbe_info ixgbe_X540_info; extern const struct ixgbe_info ixgbe_X550_info; extern const struct ixgbe_info ixgbe_X550EM_x_info; extern const struct ixgbe_info ixgbe_x550em_a_info; +extern const struct ixgbe_info ixgbe_x550em_a_fw_info; #ifdef CONFIG_IXGBE_DCB -extern const struct dcbnl_rtnl_ops dcbnl_ops; +extern const struct dcbnl_rtnl_ops ixgbe_dcbnl_ops; #endif extern char ixgbe_driver_name[]; @@ -1026,5 +929,8 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, struct ixgbe_adapter *adapter, struct ixgbe_ring *tx_ring); u32 ixgbe_rss_indir_tbl_entries(struct ixgbe_adapter *adapter); +void ixgbe_store_key(struct ixgbe_adapter *adapter); void ixgbe_store_reta(struct ixgbe_adapter *adapter); +s32 ixgbe_negotiate_fc(struct ixgbe_hw *hw, u32 adv_reg, u32 lp_reg, + u32 adv_sym, u32 adv_asm, u32 lp_sym, u32 lp_asm); #endif /* _IXGBE_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c index fb51be74dd4c..523f9d05a810 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c @@ -139,8 +139,6 @@ static s32 ixgbe_init_phy_ops_82598(struct ixgbe_hw *hw) case ixgbe_phy_tn: phy->ops.setup_link = &ixgbe_setup_phy_link_tnx; phy->ops.check_link = &ixgbe_check_phy_link_tnx; - phy->ops.get_firmware_version = - &ixgbe_get_phy_firmware_version_tnx; break; case ixgbe_phy_nl: phy->ops.reset = &ixgbe_reset_phy_nl; @@ -367,7 +365,7 @@ static s32 ixgbe_fc_enable_82598(struct ixgbe_hw *hw) } /* Negotiate the fc mode to use */ - ixgbe_fc_autoneg(hw); + hw->mac.ops.fc_autoneg(hw); /* Disable any previous flow control settings */ fctrl_reg = IXGBE_READ_REG(hw, IXGBE_FCTRL); @@ -1179,6 +1177,7 @@ static const struct ixgbe_mac_operations mac_ops_82598 = { .get_link_capabilities = &ixgbe_get_link_capabilities_82598, .led_on = &ixgbe_led_on_generic, .led_off = &ixgbe_led_off_generic, + .init_led_link_act = ixgbe_init_led_link_act_generic, .blink_led_start = &ixgbe_blink_led_start_generic, .blink_led_stop = &ixgbe_blink_led_stop_generic, .set_rar = &ixgbe_set_rar_generic, @@ -1193,6 +1192,7 @@ static const struct ixgbe_mac_operations mac_ops_82598 = { .set_vfta = &ixgbe_set_vfta_82598, .fc_enable = &ixgbe_fc_enable_82598, .setup_fc = ixgbe_setup_fc_generic, + .fc_autoneg = ixgbe_fc_autoneg, .set_fw_drv_ver = NULL, .acquire_swfw_sync = &ixgbe_acquire_swfw_sync, .release_swfw_sync = &ixgbe_release_swfw_sync, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c index 63b25006ac90..c8ac46049f34 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c @@ -331,8 +331,6 @@ static s32 ixgbe_init_phy_ops_82599(struct ixgbe_hw *hw) case ixgbe_phy_tn: phy->ops.check_link = &ixgbe_check_phy_link_tnx; phy->ops.setup_link = &ixgbe_setup_phy_link_tnx; - phy->ops.get_firmware_version = - &ixgbe_get_phy_firmware_version_tnx; break; default: break; @@ -1451,7 +1449,7 @@ do { \ * @atr_input: input bitstream to compute the hash on * @input_mask: mask for the input bitstream * - * This function serves two main purposes. First it applys the input_mask + * This function serves two main purposes. First it applies the input_mask * to the atr_input resulting in a cleaned up atr_input data stream. * Secondly it computes the hash and stores it in the bkt_hash field at * the end of the input byte stream. This way it will be available for @@ -2204,6 +2202,7 @@ static const struct ixgbe_mac_operations mac_ops_82599 = { .get_link_capabilities = &ixgbe_get_link_capabilities_82599, .led_on = &ixgbe_led_on_generic, .led_off = &ixgbe_led_off_generic, + .init_led_link_act = ixgbe_init_led_link_act_generic, .blink_led_start = &ixgbe_blink_led_start_generic, .blink_led_stop = &ixgbe_blink_led_stop_generic, .set_rar = &ixgbe_set_rar_generic, @@ -2219,6 +2218,7 @@ static const struct ixgbe_mac_operations mac_ops_82599 = { .set_vfta = &ixgbe_set_vfta_generic, .fc_enable = &ixgbe_fc_enable_generic, .setup_fc = ixgbe_setup_fc_generic, + .fc_autoneg = ixgbe_fc_autoneg, .set_fw_drv_ver = &ixgbe_set_fw_drv_ver_generic, .init_uta_tables = &ixgbe_init_uta_tables_generic, .setup_sfp = &ixgbe_setup_sfp_modules_82599, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 77d3039283f6..c38d50c1fcf7 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -100,6 +100,8 @@ bool ixgbe_device_supports_autoneg_fc(struct ixgbe_hw *hw) case IXGBE_DEV_ID_X550T1: case IXGBE_DEV_ID_X550EM_X_10G_T: case IXGBE_DEV_ID_X550EM_A_10G_T: + case IXGBE_DEV_ID_X550EM_A_1G_T: + case IXGBE_DEV_ID_X550EM_A_1G_T_L: supported = true; break; default: @@ -298,10 +300,12 @@ s32 ixgbe_start_hw_generic(struct ixgbe_hw *hw) IXGBE_WRITE_REG(hw, IXGBE_CTRL_EXT, ctrl_ext); IXGBE_WRITE_FLUSH(hw); - /* Setup flow control */ - ret_val = hw->mac.ops.setup_fc(hw); - if (ret_val) - return ret_val; + /* Setup flow control if method for doing so */ + if (hw->mac.ops.setup_fc) { + ret_val = hw->mac.ops.setup_fc(hw); + if (ret_val) + return ret_val; + } /* Cashe bit indicating need for crosstalk fix */ switch (hw->mac.type) { @@ -346,7 +350,7 @@ s32 ixgbe_start_hw_gen2(struct ixgbe_hw *hw) } IXGBE_WRITE_FLUSH(hw); -#ifndef CONFIG_SPARC +#ifndef CONFIG_ARCH_WANT_RELAX_ORDER /* Disable relaxed ordering */ for (i = 0; i < hw->mac.max_tx_queues; i++) { u32 regval; @@ -390,6 +394,9 @@ s32 ixgbe_init_hw_generic(struct ixgbe_hw *hw) status = hw->mac.ops.start_hw(hw); } + /* Initialize the LED link active for LED blink support */ + hw->mac.ops.init_led_link_act(hw); + return status; } @@ -773,6 +780,49 @@ s32 ixgbe_stop_adapter_generic(struct ixgbe_hw *hw) } /** + * ixgbe_init_led_link_act_generic - Store the LED index link/activity. + * @hw: pointer to hardware structure + * + * Store the index for the link active LED. This will be used to support + * blinking the LED. + **/ +s32 ixgbe_init_led_link_act_generic(struct ixgbe_hw *hw) +{ + struct ixgbe_mac_info *mac = &hw->mac; + u32 led_reg, led_mode; + u16 i; + + led_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL); + + /* Get LED link active from the LEDCTL register */ + for (i = 0; i < 4; i++) { + led_mode = led_reg >> IXGBE_LED_MODE_SHIFT(i); + + if ((led_mode & IXGBE_LED_MODE_MASK_BASE) == + IXGBE_LED_LINK_ACTIVE) { + mac->led_link_act = i; + return 0; + } + } + + /* If LEDCTL register does not have the LED link active set, then use + * known MAC defaults. + */ + switch (hw->mac.type) { + case ixgbe_mac_x550em_a: + mac->led_link_act = 0; + break; + case ixgbe_mac_X550EM_x: + mac->led_link_act = 1; + break; + default: + mac->led_link_act = 2; + } + + return 0; +} + +/** * ixgbe_led_on_generic - Turns on the software controllable LEDs. * @hw: pointer to hardware structure * @index: led number to turn on @@ -2127,7 +2177,7 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw) } /* Negotiate the fc mode to use */ - ixgbe_fc_autoneg(hw); + hw->mac.ops.fc_autoneg(hw); /* Disable any previous flow control settings */ mflcn_reg = IXGBE_READ_REG(hw, IXGBE_MFLCN); @@ -2231,8 +2281,8 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw) * Find the intersection between advertised settings and link partner's * advertised settings **/ -static s32 ixgbe_negotiate_fc(struct ixgbe_hw *hw, u32 adv_reg, u32 lp_reg, - u32 adv_sym, u32 adv_asm, u32 lp_sym, u32 lp_asm) +s32 ixgbe_negotiate_fc(struct ixgbe_hw *hw, u32 adv_reg, u32 lp_reg, + u32 adv_sym, u32 adv_asm, u32 lp_sym, u32 lp_asm) { if ((!(adv_reg)) || (!(lp_reg))) return IXGBE_ERR_FC_NOT_NEGOTIATED; @@ -3334,6 +3384,13 @@ s32 ixgbe_check_mac_link_generic(struct ixgbe_hw *hw, ixgbe_link_speed *speed, else *speed = IXGBE_LINK_SPEED_100_FULL; break; + case IXGBE_LINKS_SPEED_10_X550EM_A: + *speed = IXGBE_LINK_SPEED_UNKNOWN; + if (hw->device_id == IXGBE_DEV_ID_X550EM_A_1G_T || + hw->device_id == IXGBE_DEV_ID_X550EM_A_1G_T_L) { + *speed = IXGBE_LINK_SPEED_10_FULL; + } + break; default: *speed = IXGBE_LINK_SPEED_UNKNOWN; } @@ -3530,7 +3587,7 @@ void ixgbe_set_rxpba_generic(struct ixgbe_hw *hw, * Calculates the checksum for some buffer on a specified length. The * checksum calculated is returned. **/ -static u8 ixgbe_calculate_checksum(u8 *buffer, u32 length) +u8 ixgbe_calculate_checksum(u8 *buffer, u32 length) { u32 i; u8 sum = 0; @@ -3545,43 +3602,29 @@ static u8 ixgbe_calculate_checksum(u8 *buffer, u32 length) } /** - * ixgbe_host_interface_command - Issue command to manageability block + * ixgbe_hic_unlocked - Issue command to manageability block unlocked * @hw: pointer to the HW structure - * @buffer: contains the command to write and where the return status will - * be placed + * @buffer: command to write and where the return status will be placed * @length: length of buffer, must be multiple of 4 bytes * @timeout: time in ms to wait for command completion - * @return_data: read and return data from the buffer (true) or not (false) - * Needed because FW structures are big endian and decoding of - * these fields can be 8 bit or 16 bit based on command. Decoding - * is not easily understood without making a table of commands. - * So we will leave this up to the caller to read back the data - * in these cases. * - * Communicates with the manageability block. On success return 0 - * else return IXGBE_ERR_HOST_INTERFACE_COMMAND. + * Communicates with the manageability block. On success return 0 + * else returns semaphore error when encountering an error acquiring + * semaphore or IXGBE_ERR_HOST_INTERFACE_COMMAND when command fails. + * + * This function assumes that the IXGBE_GSSR_SW_MNG_SM semaphore is held + * by the caller. **/ -s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer, - u32 length, u32 timeout, - bool return_data) +s32 ixgbe_hic_unlocked(struct ixgbe_hw *hw, u32 *buffer, u32 length, + u32 timeout) { - u32 hdr_size = sizeof(struct ixgbe_hic_hdr); - u32 hicr, i, bi, fwsts; - u16 buf_len, dword_len; - union { - struct ixgbe_hic_hdr hdr; - u32 u32arr[1]; - } *bp = buffer; - s32 status; + u32 hicr, i, fwsts; + u16 dword_len; if (!length || length > IXGBE_HI_MAX_BLOCK_BYTE_LENGTH) { hw_dbg(hw, "Buffer length failure buffersize-%d.\n", length); return IXGBE_ERR_HOST_INTERFACE_COMMAND; } - /* Take management host interface semaphore */ - status = hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_SW_MNG_SM); - if (status) - return status; /* Set bit 9 of FWSTS clearing FW reset indication */ fwsts = IXGBE_READ_REG(hw, IXGBE_FWSTS); @@ -3591,15 +3634,13 @@ s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer, hicr = IXGBE_READ_REG(hw, IXGBE_HICR); if (!(hicr & IXGBE_HICR_EN)) { hw_dbg(hw, "IXGBE_HOST_EN bit disabled.\n"); - status = IXGBE_ERR_HOST_INTERFACE_COMMAND; - goto rel_out; + return IXGBE_ERR_HOST_INTERFACE_COMMAND; } /* Calculate length in DWORDs. We must be DWORD aligned */ if (length % sizeof(u32)) { hw_dbg(hw, "Buffer length failure, not aligned to dword"); - status = IXGBE_ERR_INVALID_ARGUMENT; - goto rel_out; + return IXGBE_ERR_INVALID_ARGUMENT; } dword_len = length >> 2; @@ -3609,7 +3650,7 @@ s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer, */ for (i = 0; i < dword_len; i++) IXGBE_WRITE_REG_ARRAY(hw, IXGBE_FLEX_MNG, - i, cpu_to_le32(bp->u32arr[i])); + i, cpu_to_le32(buffer[i])); /* Setting this bit tells the ARC that a new command is pending. */ IXGBE_WRITE_REG(hw, IXGBE_HICR, hicr | IXGBE_HICR_C); @@ -3623,11 +3664,54 @@ s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer, /* Check command successful completion. */ if ((timeout && i == timeout) || - !(IXGBE_READ_REG(hw, IXGBE_HICR) & IXGBE_HICR_SV)) { - hw_dbg(hw, "Command has failed with no status valid.\n"); - status = IXGBE_ERR_HOST_INTERFACE_COMMAND; - goto rel_out; + !(IXGBE_READ_REG(hw, IXGBE_HICR) & IXGBE_HICR_SV)) + return IXGBE_ERR_HOST_INTERFACE_COMMAND; + + return 0; +} + +/** + * ixgbe_host_interface_command - Issue command to manageability block + * @hw: pointer to the HW structure + * @buffer: contains the command to write and where the return status will + * be placed + * @length: length of buffer, must be multiple of 4 bytes + * @timeout: time in ms to wait for command completion + * @return_data: read and return data from the buffer (true) or not (false) + * Needed because FW structures are big endian and decoding of + * these fields can be 8 bit or 16 bit based on command. Decoding + * is not easily understood without making a table of commands. + * So we will leave this up to the caller to read back the data + * in these cases. + * + * Communicates with the manageability block. On success return 0 + * else return IXGBE_ERR_HOST_INTERFACE_COMMAND. + **/ +s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer, + u32 length, u32 timeout, + bool return_data) +{ + u32 hdr_size = sizeof(struct ixgbe_hic_hdr); + union { + struct ixgbe_hic_hdr hdr; + u32 u32arr[1]; + } *bp = buffer; + u16 buf_len, dword_len; + s32 status; + u32 bi; + + if (!length || length > IXGBE_HI_MAX_BLOCK_BYTE_LENGTH) { + hw_dbg(hw, "Buffer length failure buffersize-%d.\n", length); + return IXGBE_ERR_HOST_INTERFACE_COMMAND; } + /* Take management host interface semaphore */ + status = hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_SW_MNG_SM); + if (status) + return status; + + status = ixgbe_hic_unlocked(hw, buffer, length, timeout); + if (status) + goto rel_out; if (!return_data) goto rel_out; @@ -3674,6 +3758,8 @@ rel_out: * @min: driver version minor number * @build: driver version build number * @sub: driver version sub build number + * @len: length of driver_ver string + * @driver_ver: driver string * * Sends driver version number to firmware through the manageability * block. On success return 0 @@ -3681,7 +3767,8 @@ rel_out: * semaphore or IXGBE_ERR_HOST_INTERFACE_COMMAND when command fails. **/ s32 ixgbe_set_fw_drv_ver_generic(struct ixgbe_hw *hw, u8 maj, u8 min, - u8 build, u8 sub) + u8 build, u8 sub, __always_unused u16 len, + __always_unused const char *driver_ver) { struct ixgbe_hic_drv_info fw_cmd; int i; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h index 6d4c260d0cbd..e083732adf64 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h @@ -49,6 +49,7 @@ s32 ixgbe_stop_adapter_generic(struct ixgbe_hw *hw); s32 ixgbe_led_on_generic(struct ixgbe_hw *hw, u32 index); s32 ixgbe_led_off_generic(struct ixgbe_hw *hw, u32 index); +s32 ixgbe_init_led_link_act_generic(struct ixgbe_hw *hw); s32 ixgbe_init_eeprom_params_generic(struct ixgbe_hw *hw); s32 ixgbe_write_eeprom_generic(struct ixgbe_hw *hw, u16 offset, u16 data); @@ -110,9 +111,13 @@ void ixgbe_set_mac_anti_spoofing(struct ixgbe_hw *hw, bool enable, int vf); void ixgbe_set_vlan_anti_spoofing(struct ixgbe_hw *hw, bool enable, int vf); s32 ixgbe_get_device_caps_generic(struct ixgbe_hw *hw, u16 *device_caps); s32 ixgbe_set_fw_drv_ver_generic(struct ixgbe_hw *hw, u8 maj, u8 min, - u8 build, u8 ver); + u8 build, u8 ver, u16 len, const char *str); +u8 ixgbe_calculate_checksum(u8 *buffer, u32 length); s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *, u32 length, u32 timeout, bool return_data); +s32 ixgbe_hic_unlocked(struct ixgbe_hw *hw, u32 *buffer, u32 len, u32 timeout); +s32 ixgbe_fw_phy_activity(struct ixgbe_hw *hw, u16 activity, + u32 (*data)[FW_PHY_ACT_DATA_COUNT]); void ixgbe_clear_tx_pending(struct ixgbe_hw *hw); bool ixgbe_mng_present(struct ixgbe_hw *hw); bool ixgbe_mng_enabled(struct ixgbe_hw *hw); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c index b8fc3cfec831..78c52375acc6 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c @@ -777,7 +777,7 @@ static u8 ixgbe_dcbnl_setdcbx(struct net_device *dev, u8 mode) return err ? 1 : 0; } -const struct dcbnl_rtnl_ops dcbnl_ops = { +const struct dcbnl_rtnl_ops ixgbe_dcbnl_ops = { .ieee_getets = ixgbe_dcbnl_ieee_getets, .ieee_setets = ixgbe_dcbnl_ieee_setets, .ieee_getpfc = ixgbe_dcbnl_ieee_getpfc, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index f49f80380aa5..90fa5bf23d1b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -151,6 +151,13 @@ static const char ixgbe_gstrings_test[][ETH_GSTRING_LEN] = { }; #define IXGBE_TEST_LEN sizeof(ixgbe_gstrings_test) / ETH_GSTRING_LEN +static const char ixgbe_priv_flags_strings[][ETH_GSTRING_LEN] = { +#define IXGBE_PRIV_FLAGS_LEGACY_RX BIT(0) + "legacy-rx", +}; + +#define IXGBE_PRIV_FLAGS_STR_LEN ARRAY_SIZE(ixgbe_priv_flags_strings) + /* currently supported speeds for 10G */ #define ADVRTSD_MSK_10G (SUPPORTED_10000baseT_Full | \ SUPPORTED_10000baseKX4_Full | \ @@ -197,15 +204,17 @@ static int ixgbe_get_settings(struct net_device *netdev, SUPPORTED_1000baseKX_Full : SUPPORTED_1000baseT_Full; if (supported_link & IXGBE_LINK_SPEED_100_FULL) - ecmd->supported |= ixgbe_isbackplane(hw->phy.media_type) ? - SUPPORTED_1000baseKX_Full : - SUPPORTED_1000baseT_Full; + ecmd->supported |= SUPPORTED_100baseT_Full; + if (supported_link & IXGBE_LINK_SPEED_10_FULL) + ecmd->supported |= SUPPORTED_10baseT_Full; /* default advertised speed if phy.autoneg_advertised isn't set */ ecmd->advertising = ecmd->supported; /* set the advertised speeds */ if (hw->phy.autoneg_advertised) { ecmd->advertising = 0; + if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10_FULL) + ecmd->advertising |= ADVERTISED_10baseT_Full; if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_100_FULL) ecmd->advertising |= ADVERTISED_100baseT_Full; if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10GB_FULL) @@ -237,6 +246,7 @@ static int ixgbe_get_settings(struct net_device *netdev, case ixgbe_phy_tn: case ixgbe_phy_aq: case ixgbe_phy_x550em_ext_t: + case ixgbe_phy_fw: case ixgbe_phy_cu_unknown: ecmd->supported |= SUPPORTED_TP; ecmd->advertising |= ADVERTISED_TP; @@ -337,6 +347,9 @@ static int ixgbe_get_settings(struct net_device *netdev, case IXGBE_LINK_SPEED_10GB_FULL: ethtool_cmd_speed_set(ecmd, SPEED_10000); break; + case IXGBE_LINK_SPEED_5GB_FULL: + ethtool_cmd_speed_set(ecmd, SPEED_5000); + break; case IXGBE_LINK_SPEED_2_5GB_FULL: ethtool_cmd_speed_set(ecmd, SPEED_2500); break; @@ -346,6 +359,9 @@ static int ixgbe_get_settings(struct net_device *netdev, case IXGBE_LINK_SPEED_100_FULL: ethtool_cmd_speed_set(ecmd, SPEED_100); break; + case IXGBE_LINK_SPEED_10_FULL: + ethtool_cmd_speed_set(ecmd, SPEED_10); + break; default: break; } @@ -394,6 +410,9 @@ static int ixgbe_set_settings(struct net_device *netdev, if (ecmd->advertising & ADVERTISED_100baseT_Full) advertised |= IXGBE_LINK_SPEED_100_FULL; + if (ecmd->advertising & ADVERTISED_10baseT_Full) + advertised |= IXGBE_LINK_SPEED_10_FULL; + if (old == advertised) return err; /* this sets the link speed and restarts auto-neg */ @@ -989,6 +1008,8 @@ static void ixgbe_get_drvinfo(struct net_device *netdev, strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); + + drvinfo->n_priv_flags = IXGBE_PRIV_FLAGS_STR_LEN; } static void ixgbe_get_ringparam(struct net_device *netdev, @@ -1128,6 +1149,8 @@ static int ixgbe_get_sset_count(struct net_device *netdev, int sset) return IXGBE_TEST_LEN; case ETH_SS_STATS: return IXGBE_STATS_LEN; + case ETH_SS_PRIV_FLAGS: + return IXGBE_PRIV_FLAGS_STR_LEN; default: return -EOPNOTSUPP; } @@ -1170,12 +1193,6 @@ static void ixgbe_get_ethtool_stats(struct net_device *netdev, data[i] = 0; data[i+1] = 0; i += 2; -#ifdef BP_EXTENDED_STATS - data[i] = 0; - data[i+1] = 0; - data[i+2] = 0; - i += 3; -#endif continue; } @@ -1185,12 +1202,6 @@ static void ixgbe_get_ethtool_stats(struct net_device *netdev, data[i+1] = ring->stats.bytes; } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); i += 2; -#ifdef BP_EXTENDED_STATS - data[i] = ring->stats.yields; - data[i+1] = ring->stats.misses; - data[i+2] = ring->stats.cleaned; - i += 3; -#endif } for (j = 0; j < IXGBE_NUM_RX_QUEUES; j++) { ring = adapter->rx_ring[j]; @@ -1198,12 +1209,6 @@ static void ixgbe_get_ethtool_stats(struct net_device *netdev, data[i] = 0; data[i+1] = 0; i += 2; -#ifdef BP_EXTENDED_STATS - data[i] = 0; - data[i+1] = 0; - data[i+2] = 0; - i += 3; -#endif continue; } @@ -1213,12 +1218,6 @@ static void ixgbe_get_ethtool_stats(struct net_device *netdev, data[i+1] = ring->stats.bytes; } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); i += 2; -#ifdef BP_EXTENDED_STATS - data[i] = ring->stats.yields; - data[i+1] = ring->stats.misses; - data[i+2] = ring->stats.cleaned; - i += 3; -#endif } for (j = 0; j < IXGBE_MAX_PACKET_BUFFERS; j++) { @@ -1255,28 +1254,12 @@ static void ixgbe_get_strings(struct net_device *netdev, u32 stringset, p += ETH_GSTRING_LEN; sprintf(p, "tx_queue_%u_bytes", i); p += ETH_GSTRING_LEN; -#ifdef BP_EXTENDED_STATS - sprintf(p, "tx_queue_%u_bp_napi_yield", i); - p += ETH_GSTRING_LEN; - sprintf(p, "tx_queue_%u_bp_misses", i); - p += ETH_GSTRING_LEN; - sprintf(p, "tx_queue_%u_bp_cleaned", i); - p += ETH_GSTRING_LEN; -#endif /* BP_EXTENDED_STATS */ } for (i = 0; i < IXGBE_NUM_RX_QUEUES; i++) { sprintf(p, "rx_queue_%u_packets", i); p += ETH_GSTRING_LEN; sprintf(p, "rx_queue_%u_bytes", i); p += ETH_GSTRING_LEN; -#ifdef BP_EXTENDED_STATS - sprintf(p, "rx_queue_%u_bp_poll_yield", i); - p += ETH_GSTRING_LEN; - sprintf(p, "rx_queue_%u_bp_misses", i); - p += ETH_GSTRING_LEN; - sprintf(p, "rx_queue_%u_bp_cleaned", i); - p += ETH_GSTRING_LEN; -#endif /* BP_EXTENDED_STATS */ } for (i = 0; i < IXGBE_MAX_PACKET_BUFFERS; i++) { sprintf(p, "tx_pb_%u_pxon", i); @@ -1292,6 +1275,9 @@ static void ixgbe_get_strings(struct net_device *netdev, u32 stringset, } /* BUG_ON(p - data != IXGBE_STATS_LEN * ETH_GSTRING_LEN); */ break; + case ETH_SS_PRIV_FLAGS: + memcpy(data, ixgbe_priv_flags_strings, + IXGBE_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN); } } @@ -1896,7 +1882,7 @@ static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring, tx_ntc = tx_ring->next_to_clean; rx_desc = IXGBE_RX_DESC(rx_ring, rx_ntc); - while (ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_DD)) { + while (rx_desc->wb.upper.length) { /* check Rx buffer */ rx_buffer = &rx_ring->rx_buffer_info[rx_ntc]; @@ -1918,7 +1904,16 @@ static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring, /* unmap buffer on Tx side */ tx_buffer = &tx_ring->tx_buffer_info[tx_ntc]; - ixgbe_unmap_and_free_tx_resource(tx_ring, tx_buffer); + + /* Free all the Tx ring sk_buffs */ + dev_kfree_skb_any(tx_buffer->skb); + + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); /* increment Rx/Tx next to clean counters */ rx_ntc++; @@ -2225,11 +2220,11 @@ static int ixgbe_set_phys_id(struct net_device *netdev, return 2; case ETHTOOL_ID_ON: - hw->mac.ops.led_on(hw, hw->bus.func); + hw->mac.ops.led_on(hw, hw->mac.led_link_act); break; case ETHTOOL_ID_OFF: - hw->mac.ops.led_off(hw, hw->bus.func); + hw->mac.ops.led_off(hw, hw->mac.led_link_act); break; case ETHTOOL_ID_INACTIVE: @@ -3003,8 +2998,10 @@ static int ixgbe_set_rxfh(struct net_device *netdev, const u32 *indir, } /* Fill out the rss hash key */ - if (key) + if (key) { memcpy(adapter->rss_key, key, ixgbe_get_rxfh_key_size(netdev)); + ixgbe_store_key(adapter); + } ixgbe_store_reta(adapter); @@ -3173,6 +3170,9 @@ static int ixgbe_get_module_info(struct net_device *dev, u8 sff8472_rev, addr_mode; bool page_swap = false; + if (hw->phy.type == ixgbe_phy_fw) + return -ENXIO; + /* Check whether we support SFF-8472 or not */ status = hw->phy.ops.read_i2c_eeprom(hw, IXGBE_SFF_SFF_8472_COMP, @@ -3218,6 +3218,9 @@ static int ixgbe_get_module_eeprom(struct net_device *dev, if (ee->len == 0) return -EINVAL; + if (hw->phy.type == ixgbe_phy_fw) + return -ENXIO; + for (i = ee->offset; i < ee->offset + ee->len; i++) { /* I2C reads can take long time */ if (test_bit(__IXGBE_IN_SFP_INIT, &adapter->state)) @@ -3237,6 +3240,167 @@ static int ixgbe_get_module_eeprom(struct net_device *dev, return 0; } +static const struct { + ixgbe_link_speed mac_speed; + u32 supported; +} ixgbe_ls_map[] = { + { IXGBE_LINK_SPEED_10_FULL, SUPPORTED_10baseT_Full }, + { IXGBE_LINK_SPEED_100_FULL, SUPPORTED_100baseT_Full }, + { IXGBE_LINK_SPEED_1GB_FULL, SUPPORTED_1000baseT_Full }, + { IXGBE_LINK_SPEED_2_5GB_FULL, SUPPORTED_2500baseX_Full }, + { IXGBE_LINK_SPEED_10GB_FULL, SUPPORTED_10000baseT_Full }, +}; + +static const struct { + u32 lp_advertised; + u32 mac_speed; +} ixgbe_lp_map[] = { + { FW_PHY_ACT_UD_2_100M_TX_EEE, SUPPORTED_100baseT_Full }, + { FW_PHY_ACT_UD_2_1G_T_EEE, SUPPORTED_1000baseT_Full }, + { FW_PHY_ACT_UD_2_10G_T_EEE, SUPPORTED_10000baseT_Full }, + { FW_PHY_ACT_UD_2_1G_KX_EEE, SUPPORTED_1000baseKX_Full }, + { FW_PHY_ACT_UD_2_10G_KX4_EEE, SUPPORTED_10000baseKX4_Full }, + { FW_PHY_ACT_UD_2_10G_KR_EEE, SUPPORTED_10000baseKR_Full}, +}; + +static int +ixgbe_get_eee_fw(struct ixgbe_adapter *adapter, struct ethtool_eee *edata) +{ + u32 info[FW_PHY_ACT_DATA_COUNT] = { 0 }; + struct ixgbe_hw *hw = &adapter->hw; + s32 rc; + u16 i; + + rc = ixgbe_fw_phy_activity(hw, FW_PHY_ACT_UD_2, &info); + if (rc) + return rc; + + edata->lp_advertised = 0; + for (i = 0; i < ARRAY_SIZE(ixgbe_lp_map); ++i) { + if (info[0] & ixgbe_lp_map[i].lp_advertised) + edata->lp_advertised |= ixgbe_lp_map[i].mac_speed; + } + + edata->supported = 0; + for (i = 0; i < ARRAY_SIZE(ixgbe_ls_map); ++i) { + if (hw->phy.eee_speeds_supported & ixgbe_ls_map[i].mac_speed) + edata->supported |= ixgbe_ls_map[i].supported; + } + + edata->advertised = 0; + for (i = 0; i < ARRAY_SIZE(ixgbe_ls_map); ++i) { + if (hw->phy.eee_speeds_advertised & ixgbe_ls_map[i].mac_speed) + edata->advertised |= ixgbe_ls_map[i].supported; + } + + edata->eee_enabled = !!edata->advertised; + edata->tx_lpi_enabled = edata->eee_enabled; + if (edata->advertised & edata->lp_advertised) + edata->eee_active = true; + + return 0; +} + +static int ixgbe_get_eee(struct net_device *netdev, struct ethtool_eee *edata) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + + if (!(adapter->flags2 & IXGBE_FLAG2_EEE_CAPABLE)) + return -EOPNOTSUPP; + + if (hw->phy.eee_speeds_supported && hw->phy.type == ixgbe_phy_fw) + return ixgbe_get_eee_fw(adapter, edata); + + return -EOPNOTSUPP; +} + +static int ixgbe_set_eee(struct net_device *netdev, struct ethtool_eee *edata) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + struct ethtool_eee eee_data; + s32 ret_val; + + if (!(adapter->flags2 & IXGBE_FLAG2_EEE_CAPABLE)) + return -EOPNOTSUPP; + + memset(&eee_data, 0, sizeof(struct ethtool_eee)); + + ret_val = ixgbe_get_eee(netdev, &eee_data); + if (ret_val) + return ret_val; + + if (eee_data.eee_enabled && !edata->eee_enabled) { + if (eee_data.tx_lpi_enabled != edata->tx_lpi_enabled) { + e_err(drv, "Setting EEE tx-lpi is not supported\n"); + return -EINVAL; + } + + if (eee_data.tx_lpi_timer != edata->tx_lpi_timer) { + e_err(drv, + "Setting EEE Tx LPI timer is not supported\n"); + return -EINVAL; + } + + if (eee_data.advertised != edata->advertised) { + e_err(drv, + "Setting EEE advertised speeds is not supported\n"); + return -EINVAL; + } + } + + if (eee_data.eee_enabled != edata->eee_enabled) { + if (edata->eee_enabled) { + adapter->flags2 |= IXGBE_FLAG2_EEE_ENABLED; + hw->phy.eee_speeds_advertised = + hw->phy.eee_speeds_supported; + } else { + adapter->flags2 &= ~IXGBE_FLAG2_EEE_ENABLED; + hw->phy.eee_speeds_advertised = 0; + } + + /* reset link */ + if (netif_running(netdev)) + ixgbe_reinit_locked(adapter); + else + ixgbe_reset(adapter); + } + + return 0; +} + +static u32 ixgbe_get_priv_flags(struct net_device *netdev) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + u32 priv_flags = 0; + + if (adapter->flags2 & IXGBE_FLAG2_RX_LEGACY) + priv_flags |= IXGBE_PRIV_FLAGS_LEGACY_RX; + + return priv_flags; +} + +static int ixgbe_set_priv_flags(struct net_device *netdev, u32 priv_flags) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + unsigned int flags2 = adapter->flags2; + + flags2 &= ~IXGBE_FLAG2_RX_LEGACY; + if (priv_flags & IXGBE_PRIV_FLAGS_LEGACY_RX) + flags2 |= IXGBE_FLAG2_RX_LEGACY; + + if (flags2 != adapter->flags2) { + adapter->flags2 = flags2; + + /* reset interface to repopulate queues */ + if (netif_running(netdev)) + ixgbe_reinit_locked(adapter); + } + + return 0; +} + static const struct ethtool_ops ixgbe_ethtool_ops = { .get_settings = ixgbe_get_settings, .set_settings = ixgbe_set_settings, @@ -3269,8 +3433,12 @@ static const struct ethtool_ops ixgbe_ethtool_ops = { .get_rxfh_key_size = ixgbe_get_rxfh_key_size, .get_rxfh = ixgbe_get_rxfh, .set_rxfh = ixgbe_set_rxfh, + .get_eee = ixgbe_get_eee, + .set_eee = ixgbe_set_eee, .get_channels = ixgbe_get_channels, .set_channels = ixgbe_set_channels, + .get_priv_flags = ixgbe_get_priv_flags, + .set_priv_flags = ixgbe_set_priv_flags, .get_ts_info = ixgbe_get_ts_info, .get_module_info = ixgbe_get_module_info, .get_module_eeprom = ixgbe_get_module_eeprom, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c index 15ab337fd7ad..1b8be7d813bd 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -308,6 +308,7 @@ static void ixgbe_cache_ring_register(struct ixgbe_adapter *adapter) ixgbe_cache_ring_rss(adapter); } +#define IXGBE_RSS_64Q_MASK 0x3F #define IXGBE_RSS_16Q_MASK 0xF #define IXGBE_RSS_8Q_MASK 0x7 #define IXGBE_RSS_4Q_MASK 0x3 @@ -604,6 +605,7 @@ static bool ixgbe_set_sriov_queues(struct ixgbe_adapter *adapter) **/ static bool ixgbe_set_rss_queues(struct ixgbe_adapter *adapter) { + struct ixgbe_hw *hw = &adapter->hw; struct ixgbe_ring_feature *f; u16 rss_i; @@ -612,7 +614,11 @@ static bool ixgbe_set_rss_queues(struct ixgbe_adapter *adapter) rss_i = f->limit; f->indices = rss_i; - f->mask = IXGBE_RSS_16Q_MASK; + + if (hw->mac.type < ixgbe_mac_X550) + f->mask = IXGBE_RSS_16Q_MASK; + else + f->mask = IXGBE_RSS_64Q_MASK; /* disable ATR by default, it will be configured below */ adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE; @@ -847,11 +853,6 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter, netif_napi_add(adapter->netdev, &q_vector->napi, ixgbe_poll, 64); -#ifdef CONFIG_NET_RX_BUSY_POLL - /* initialize busy poll */ - atomic_set(&q_vector->state, IXGBE_QV_STATE_DISABLE); - -#endif /* tie q_vector and adapter together */ adapter->q_vector[v_idx] = q_vector; q_vector->adapter = adapter; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index fee1f2918ead..a7a430a7be2c 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -54,6 +54,7 @@ #include <net/pkt_cls.h> #include <net/tc_act/tc_gact.h> #include <net/tc_act/tc_mirred.h> +#include <net/vxlan.h> #include "ixgbe.h" #include "ixgbe_common.h" @@ -71,7 +72,7 @@ char ixgbe_default_device_descr[] = static char ixgbe_default_device_descr[] = "Intel(R) 10 Gigabit Network Connection"; #endif -#define DRV_VERSION "4.4.0-k" +#define DRV_VERSION "5.0.0-k" const char ixgbe_driver_version[] = DRV_VERSION; static const char ixgbe_copyright[] = "Copyright (c) 1999-2016 Intel Corporation."; @@ -85,6 +86,7 @@ static const struct ixgbe_info *ixgbe_info_tbl[] = { [board_X550] = &ixgbe_X550_info, [board_X550EM_x] = &ixgbe_X550EM_x_info, [board_x550em_a] = &ixgbe_x550em_a_info, + [board_x550em_a_fw] = &ixgbe_x550em_a_fw_info, }; /* ixgbe_pci_tbl - PCI Device ID Table @@ -139,6 +141,8 @@ static const struct pci_device_id ixgbe_pci_tbl[] = { {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_SGMII_L), board_x550em_a }, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_10G_T), board_x550em_a}, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_SFP), board_x550em_a }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_1G_T), board_x550em_a_fw }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_1G_T_L), board_x550em_a_fw }, /* required last entry */ {0, } }; @@ -179,6 +183,7 @@ MODULE_VERSION(DRV_VERSION); static struct workqueue_struct *ixgbe_wq; static bool ixgbe_check_cfg_remove(struct ixgbe_hw *hw, struct pci_dev *pdev); +static void ixgbe_watchdog_link_is_down(struct ixgbe_adapter *); static int ixgbe_read_pci_cfg_word_parent(struct ixgbe_adapter *adapter, u32 reg, u16 *value) @@ -606,12 +611,11 @@ static void ixgbe_dump(struct ixgbe_adapter *adapter) if (netdev) { dev_info(&adapter->pdev->dev, "Net device Info\n"); pr_info("Device Name state " - "trans_start last_rx\n"); - pr_info("%-15s %016lX %016lX %016lX\n", + "trans_start\n"); + pr_info("%-15s %016lX %016lX\n", netdev->name, netdev->state, - dev_trans_start(netdev), - netdev->last_rx); + dev_trans_start(netdev)); } /* Print Registers */ @@ -941,28 +945,6 @@ static inline void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter, } } -void ixgbe_unmap_and_free_tx_resource(struct ixgbe_ring *ring, - struct ixgbe_tx_buffer *tx_buffer) -{ - if (tx_buffer->skb) { - dev_kfree_skb_any(tx_buffer->skb); - if (dma_unmap_len(tx_buffer, len)) - dma_unmap_single(ring->dev, - dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - DMA_TO_DEVICE); - } else if (dma_unmap_len(tx_buffer, len)) { - dma_unmap_page(ring->dev, - dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - DMA_TO_DEVICE); - } - tx_buffer->next_to_watch = NULL; - tx_buffer->skb = NULL; - dma_unmap_len_set(tx_buffer, len, 0); - /* tx_buffer must be completely set up in the transmit path */ -} - static void ixgbe_update_xoff_rx_lfc(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; @@ -1194,7 +1176,6 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, DMA_TO_DEVICE); /* clear tx_buffer data */ - tx_buffer->skb = NULL; dma_unmap_len_set(tx_buffer, len, 0); /* unmap remaining buffers */ @@ -1548,6 +1529,11 @@ static inline void ixgbe_rx_checksum(struct ixgbe_ring *ring, } } +static inline unsigned int ixgbe_rx_offset(struct ixgbe_ring *rx_ring) +{ + return ring_uses_build_skb(rx_ring) ? IXGBE_SKB_PAD : 0; +} + static bool ixgbe_alloc_mapped_page(struct ixgbe_ring *rx_ring, struct ixgbe_rx_buffer *bi) { @@ -1566,8 +1552,10 @@ static bool ixgbe_alloc_mapped_page(struct ixgbe_ring *rx_ring, } /* map page for use */ - dma = dma_map_page(rx_ring->dev, page, 0, - ixgbe_rx_pg_size(rx_ring), DMA_FROM_DEVICE); + dma = dma_map_page_attrs(rx_ring->dev, page, 0, + ixgbe_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + IXGBE_RX_DMA_ATTR); /* * if mapping failed free memory back to system since @@ -1582,7 +1570,8 @@ static bool ixgbe_alloc_mapped_page(struct ixgbe_ring *rx_ring, bi->dma = dma; bi->page = page; - bi->page_offset = 0; + bi->page_offset = ixgbe_rx_offset(rx_ring); + bi->pagecnt_bias = 1; return true; } @@ -1597,6 +1586,7 @@ void ixgbe_alloc_rx_buffers(struct ixgbe_ring *rx_ring, u16 cleaned_count) union ixgbe_adv_rx_desc *rx_desc; struct ixgbe_rx_buffer *bi; u16 i = rx_ring->next_to_use; + u16 bufsz; /* nothing to do */ if (!cleaned_count) @@ -1606,10 +1596,17 @@ void ixgbe_alloc_rx_buffers(struct ixgbe_ring *rx_ring, u16 cleaned_count) bi = &rx_ring->rx_buffer_info[i]; i -= rx_ring->count; + bufsz = ixgbe_rx_bufsz(rx_ring); + do { if (!ixgbe_alloc_mapped_page(rx_ring, bi)) break; + /* sync the buffer for use by the device */ + dma_sync_single_range_for_device(rx_ring->dev, bi->dma, + bi->page_offset, bufsz, + DMA_FROM_DEVICE); + /* * Refresh the desc even if buffer_addrs didn't change * because each write-back erases this info. @@ -1625,8 +1622,8 @@ void ixgbe_alloc_rx_buffers(struct ixgbe_ring *rx_ring, u16 cleaned_count) i -= rx_ring->count; } - /* clear the status bits for the next_to_use descriptor */ - rx_desc->wb.upper.status_error = 0; + /* clear the length for the next_to_use descriptor */ + rx_desc->wb.upper.length = 0; cleaned_count--; } while (cleaned_count); @@ -1716,11 +1713,7 @@ static void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring, static void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector, struct sk_buff *skb) { - skb_mark_napi_id(skb, &q_vector->napi); - if (ixgbe_qv_busy_polling(q_vector)) - netif_receive_skb(skb); - else - napi_gro_receive(&q_vector->napi, skb); + napi_gro_receive(&q_vector->napi, skb); } /** @@ -1832,19 +1825,19 @@ static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring, { /* if the page was released unmap it, else just sync our portion */ if (unlikely(IXGBE_CB(skb)->page_released)) { - dma_unmap_page(rx_ring->dev, IXGBE_CB(skb)->dma, - ixgbe_rx_pg_size(rx_ring), DMA_FROM_DEVICE); - IXGBE_CB(skb)->page_released = false; + dma_unmap_page_attrs(rx_ring->dev, IXGBE_CB(skb)->dma, + ixgbe_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + IXGBE_RX_DMA_ATTR); } else { struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; dma_sync_single_range_for_cpu(rx_ring->dev, IXGBE_CB(skb)->dma, frag->page_offset, - ixgbe_rx_bufsz(rx_ring), + skb_frag_size(frag), DMA_FROM_DEVICE); } - IXGBE_CB(skb)->dma = 0; } /** @@ -1880,7 +1873,7 @@ static bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring, } /* place header in linear portion of buffer */ - if (skb_is_nonlinear(skb)) + if (!skb_headlen(skb)) ixgbe_pull_tail(rx_ring, skb); #ifdef IXGBE_FCOE @@ -1915,14 +1908,14 @@ static void ixgbe_reuse_rx_page(struct ixgbe_ring *rx_ring, nta++; rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; - /* transfer page from old buffer to new buffer */ - *new_buff = *old_buff; - - /* sync the buffer for use by the device */ - dma_sync_single_range_for_device(rx_ring->dev, new_buff->dma, - new_buff->page_offset, - ixgbe_rx_bufsz(rx_ring), - DMA_FROM_DEVICE); + /* Transfer page from old buffer to new buffer. + * Move each member individually to avoid possible store + * forwarding stalls and unnecessary copy of skb. + */ + new_buff->dma = old_buff->dma; + new_buff->page = old_buff->page; + new_buff->page_offset = old_buff->page_offset; + new_buff->pagecnt_bias = old_buff->pagecnt_bias; } static inline bool ixgbe_page_is_reserved(struct page *page) @@ -1930,6 +1923,43 @@ static inline bool ixgbe_page_is_reserved(struct page *page) return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page); } +static bool ixgbe_can_reuse_rx_page(struct ixgbe_rx_buffer *rx_buffer) +{ + unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; + struct page *page = rx_buffer->page; + + /* avoid re-using remote pages */ + if (unlikely(ixgbe_page_is_reserved(page))) + return false; + +#if (PAGE_SIZE < 8192) + /* if we are only owner of page we can reuse it */ + if (unlikely((page_ref_count(page) - pagecnt_bias) > 1)) + return false; +#else + /* The last offset is a bit aggressive in that we assume the + * worst case of FCoE being enabled and using a 3K buffer. + * However this should have minimal impact as the 1K extra is + * still less than one buffer in size. + */ +#define IXGBE_LAST_OFFSET \ + (SKB_WITH_OVERHEAD(PAGE_SIZE) - IXGBE_RXBUFFER_3K) + if (rx_buffer->page_offset > IXGBE_LAST_OFFSET) + return false; +#endif + + /* If we have drained the page fragment pool we need to update + * the pagecnt_bias and page count so that we fully restock the + * number of references the driver holds. + */ + if (unlikely(!pagecnt_bias)) { + page_ref_add(page, USHRT_MAX); + rx_buffer->pagecnt_bias = USHRT_MAX; + } + + return true; +} + /** * ixgbe_add_rx_frag - Add contents of Rx buffer to sk_buff * @rx_ring: rx descriptor ring to transact packets on @@ -1945,144 +1975,172 @@ static inline bool ixgbe_page_is_reserved(struct page *page) * The function will then update the page offset if necessary and return * true if the buffer can be reused by the adapter. **/ -static bool ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring, +static void ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring, struct ixgbe_rx_buffer *rx_buffer, - union ixgbe_adv_rx_desc *rx_desc, - struct sk_buff *skb) + struct sk_buff *skb, + unsigned int size) { - struct page *page = rx_buffer->page; - unsigned int size = le16_to_cpu(rx_desc->wb.upper.length); #if (PAGE_SIZE < 8192) - unsigned int truesize = ixgbe_rx_bufsz(rx_ring); + unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2; #else - unsigned int truesize = ALIGN(size, L1_CACHE_BYTES); - unsigned int last_offset = ixgbe_rx_pg_size(rx_ring) - - ixgbe_rx_bufsz(rx_ring); + unsigned int truesize = ring_uses_build_skb(rx_ring) ? + SKB_DATA_ALIGN(IXGBE_SKB_PAD + size) : + SKB_DATA_ALIGN(size); #endif - - if ((size <= IXGBE_RX_HDR_SIZE) && !skb_is_nonlinear(skb)) { - unsigned char *va = page_address(page) + rx_buffer->page_offset; - - memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long))); - - /* page is not reserved, we can reuse buffer as-is */ - if (likely(!ixgbe_page_is_reserved(page))) - return true; - - /* this page cannot be reused so discard it */ - __free_pages(page, ixgbe_rx_pg_order(rx_ring)); - return false; - } - - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page, rx_buffer->page_offset, size, truesize); - - /* avoid re-using remote pages */ - if (unlikely(ixgbe_page_is_reserved(page))) - return false; - #if (PAGE_SIZE < 8192) - /* if we are only owner of page we can reuse it */ - if (unlikely(page_count(page) != 1)) - return false; - - /* flip page offset to other buffer */ rx_buffer->page_offset ^= truesize; #else - /* move offset up to the next cache line */ rx_buffer->page_offset += truesize; - - if (rx_buffer->page_offset > last_offset) - return false; #endif - - /* Even if we own the page, we are not allowed to use atomic_set() - * This would break get_page_unless_zero() users. - */ - page_ref_inc(page); - - return true; } -static struct sk_buff *ixgbe_fetch_rx_buffer(struct ixgbe_ring *rx_ring, - union ixgbe_adv_rx_desc *rx_desc) +static struct ixgbe_rx_buffer *ixgbe_get_rx_buffer(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff **skb, + const unsigned int size) { struct ixgbe_rx_buffer *rx_buffer; - struct sk_buff *skb; - struct page *page; rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; - page = rx_buffer->page; - prefetchw(page); + prefetchw(rx_buffer->page); + *skb = rx_buffer->skb; - skb = rx_buffer->skb; + /* Delay unmapping of the first packet. It carries the header + * information, HW may still access the header after the writeback. + * Only unmap it when EOP is reached + */ + if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)) { + if (!*skb) + goto skip_sync; + } else { + if (*skb) + ixgbe_dma_sync_frag(rx_ring, *skb); + } - if (likely(!skb)) { - void *page_addr = page_address(page) + - rx_buffer->page_offset; + /* we are reusing so sync this buffer for CPU use */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + size, + DMA_FROM_DEVICE); +skip_sync: + rx_buffer->pagecnt_bias--; - /* prefetch first cache line of first page */ - prefetch(page_addr); -#if L1_CACHE_BYTES < 128 - prefetch(page_addr + L1_CACHE_BYTES); -#endif + return rx_buffer; +} - /* allocate a skb to store the frags */ - skb = napi_alloc_skb(&rx_ring->q_vector->napi, - IXGBE_RX_HDR_SIZE); - if (unlikely(!skb)) { - rx_ring->rx_stats.alloc_rx_buff_failed++; - return NULL; +static void ixgbe_put_rx_buffer(struct ixgbe_ring *rx_ring, + struct ixgbe_rx_buffer *rx_buffer, + struct sk_buff *skb) +{ + if (ixgbe_can_reuse_rx_page(rx_buffer)) { + /* hand second half of page back to the ring */ + ixgbe_reuse_rx_page(rx_ring, rx_buffer); + } else { + if (IXGBE_CB(skb)->dma == rx_buffer->dma) { + /* the page has been released from the ring */ + IXGBE_CB(skb)->page_released = true; + } else { + /* we are not reusing the buffer so unmap it */ + dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, + ixgbe_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + IXGBE_RX_DMA_ATTR); } + __page_frag_cache_drain(rx_buffer->page, + rx_buffer->pagecnt_bias); + } - /* - * we will be copying header into skb->data in - * pskb_may_pull so it is in our interest to prefetch - * it now to avoid a possible cache miss - */ - prefetchw(skb->data); + /* clear contents of rx_buffer */ + rx_buffer->page = NULL; + rx_buffer->skb = NULL; +} - /* - * Delay unmapping of the first packet. It carries the - * header information, HW may still access the header - * after the writeback. Only unmap it when EOP is - * reached - */ - if (likely(ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP))) - goto dma_sync; +static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring, + struct ixgbe_rx_buffer *rx_buffer, + union ixgbe_adv_rx_desc *rx_desc, + unsigned int size) +{ + void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; +#if (PAGE_SIZE < 8192) + unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = SKB_DATA_ALIGN(size); +#endif + struct sk_buff *skb; - IXGBE_CB(skb)->dma = rx_buffer->dma; - } else { - if (ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)) - ixgbe_dma_sync_frag(rx_ring, skb); + /* prefetch first cache line of first page */ + prefetch(va); +#if L1_CACHE_BYTES < 128 + prefetch(va + L1_CACHE_BYTES); +#endif -dma_sync: - /* we are reusing so sync this buffer for CPU use */ - dma_sync_single_range_for_cpu(rx_ring->dev, - rx_buffer->dma, - rx_buffer->page_offset, - ixgbe_rx_bufsz(rx_ring), - DMA_FROM_DEVICE); + /* allocate a skb to store the frags */ + skb = napi_alloc_skb(&rx_ring->q_vector->napi, IXGBE_RX_HDR_SIZE); + if (unlikely(!skb)) + return NULL; - rx_buffer->skb = NULL; - } + if (size > IXGBE_RX_HDR_SIZE) { + if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)) + IXGBE_CB(skb)->dma = rx_buffer->dma; - /* pull page into skb */ - if (ixgbe_add_rx_frag(rx_ring, rx_buffer, rx_desc, skb)) { - /* hand second half of page back to the ring */ - ixgbe_reuse_rx_page(rx_ring, rx_buffer); - } else if (IXGBE_CB(skb)->dma == rx_buffer->dma) { - /* the page has been released from the ring */ - IXGBE_CB(skb)->page_released = true; + skb_add_rx_frag(skb, 0, rx_buffer->page, + rx_buffer->page_offset, + size, truesize); +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif } else { - /* we are not reusing the buffer so unmap it */ - dma_unmap_page(rx_ring->dev, rx_buffer->dma, - ixgbe_rx_pg_size(rx_ring), - DMA_FROM_DEVICE); + memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long))); + rx_buffer->pagecnt_bias++; } - /* clear contents of buffer_info */ - rx_buffer->page = NULL; + return skb; +} + +static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, + struct ixgbe_rx_buffer *rx_buffer, + union ixgbe_adv_rx_desc *rx_desc, + unsigned int size) +{ + void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; +#if (PAGE_SIZE < 8192) + unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) + + SKB_DATA_ALIGN(IXGBE_SKB_PAD + size); +#endif + struct sk_buff *skb; + + /* prefetch first cache line of first page */ + prefetch(va); +#if L1_CACHE_BYTES < 128 + prefetch(va + L1_CACHE_BYTES); +#endif + + /* build an skb to around the page buffer */ + skb = build_skb(va - IXGBE_SKB_PAD, truesize); + if (unlikely(!skb)) + return NULL; + + /* update pointers within the skb to store the data */ + skb_reserve(skb, IXGBE_SKB_PAD); + __skb_put(skb, size); + + /* record DMA address if this is the start of a chain of buffers */ + if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)) + IXGBE_CB(skb)->dma = rx_buffer->dma; + + /* update buffer offset */ +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif return skb; } @@ -2114,7 +2172,9 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, while (likely(total_rx_packets < budget)) { union ixgbe_adv_rx_desc *rx_desc; + struct ixgbe_rx_buffer *rx_buffer; struct sk_buff *skb; + unsigned int size; /* return some buffers to hardware, one at a time is too slow */ if (cleaned_count >= IXGBE_RX_BUFFER_WRITE) { @@ -2123,8 +2183,8 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, } rx_desc = IXGBE_RX_DESC(rx_ring, rx_ring->next_to_clean); - - if (!rx_desc->wb.upper.status_error) + size = le16_to_cpu(rx_desc->wb.upper.length); + if (!size) break; /* This memory barrier is needed to keep us from reading @@ -2133,13 +2193,26 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, */ dma_rmb(); + rx_buffer = ixgbe_get_rx_buffer(rx_ring, rx_desc, &skb, size); + /* retrieve a buffer from the ring */ - skb = ixgbe_fetch_rx_buffer(rx_ring, rx_desc); + if (skb) + ixgbe_add_rx_frag(rx_ring, rx_buffer, skb, size); + else if (ring_uses_build_skb(rx_ring)) + skb = ixgbe_build_skb(rx_ring, rx_buffer, + rx_desc, size); + else + skb = ixgbe_construct_skb(rx_ring, rx_buffer, + rx_desc, size); /* exit if we failed to retrieve a buffer */ - if (!skb) + if (!skb) { + rx_ring->rx_stats.alloc_rx_buff_failed++; + rx_buffer->pagecnt_bias++; break; + } + ixgbe_put_rx_buffer(rx_ring, rx_buffer, skb); cleaned_count++; /* place incomplete frames back on ring for completion */ @@ -2197,40 +2270,6 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, return total_rx_packets; } -#ifdef CONFIG_NET_RX_BUSY_POLL -/* must be called with local_bh_disable()d */ -static int ixgbe_low_latency_recv(struct napi_struct *napi) -{ - struct ixgbe_q_vector *q_vector = - container_of(napi, struct ixgbe_q_vector, napi); - struct ixgbe_adapter *adapter = q_vector->adapter; - struct ixgbe_ring *ring; - int found = 0; - - if (test_bit(__IXGBE_DOWN, &adapter->state)) - return LL_FLUSH_FAILED; - - if (!ixgbe_qv_lock_poll(q_vector)) - return LL_FLUSH_BUSY; - - ixgbe_for_each_ring(ring, q_vector->rx) { - found = ixgbe_clean_rx_irq(q_vector, ring, 4); -#ifdef BP_EXTENDED_STATS - if (found) - ring->stats.cleaned += found; - else - ring->stats.misses++; -#endif - if (found) - break; - } - - ixgbe_qv_unlock_poll(q_vector); - - return found; -} -#endif /* CONFIG_NET_RX_BUSY_POLL */ - /** * ixgbe_configure_msix - Configure MSI-X hardware * @adapter: board private structure @@ -2446,6 +2485,7 @@ static void ixgbe_check_overtemp_subtask(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; u32 eicr = adapter->interrupt_event; + s32 rc; if (test_bit(__IXGBE_DOWN, &adapter->state)) return; @@ -2484,6 +2524,12 @@ static void ixgbe_check_overtemp_subtask(struct ixgbe_adapter *adapter) return; break; + case IXGBE_DEV_ID_X550EM_A_1G_T: + case IXGBE_DEV_ID_X550EM_A_1G_T_L: + rc = hw->phy.ops.check_overtemp(hw); + if (rc != IXGBE_ERR_OVERTEMP) + return; + break; default: if (adapter->hw.mac.type >= ixgbe_mac_X540) return; @@ -2530,6 +2576,18 @@ static void ixgbe_check_overtemp_event(struct ixgbe_adapter *adapter, u32 eicr) return; } return; + case ixgbe_mac_x550em_a: + if (eicr & IXGBE_EICR_GPI_SDP0_X550EM_a) { + adapter->interrupt_event = eicr; + adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_EVENT; + ixgbe_service_event_schedule(adapter); + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, + IXGBE_EICR_GPI_SDP0_X550EM_a); + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICR, + IXGBE_EICR_GPI_SDP0_X550EM_a); + } + return; + case ixgbe_mac_X550: case ixgbe_mac_X540: if (!(eicr & IXGBE_EICR_TS)) return; @@ -2855,8 +2913,8 @@ int ixgbe_poll(struct napi_struct *napi, int budget) clean_complete = false; } - /* Exit if we are called by netpoll or busy polling is active */ - if ((budget <= 0) || !ixgbe_qv_lock_napi(q_vector)) + /* Exit if we are called by netpoll */ + if (budget <= 0) return budget; /* attempt to distribute budget to each queue fairly, but don't allow @@ -2875,7 +2933,6 @@ int ixgbe_poll(struct napi_struct *napi, int budget) clean_complete = false; } - ixgbe_qv_unlock_napi(q_vector); /* If all work not completed, return budget and keep polling */ if (!clean_complete) return budget; @@ -3070,6 +3127,9 @@ static void ixgbe_free_irq(struct ixgbe_adapter *adapter) return; } + if (!adapter->msix_entries) + return; + for (vector = 0; vector < adapter->num_q_vectors; vector++) { struct ixgbe_q_vector *q_vector = adapter->q_vector[vector]; struct msix_entry *entry = &adapter->msix_entries[vector]; @@ -3210,6 +3270,10 @@ void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter, clear_bit(__IXGBE_HANG_CHECK_ARMED, &ring->state); + /* reinitialize tx_buffer_info */ + memset(ring->tx_buffer_info, 0, + sizeof(struct ixgbe_tx_buffer) * ring->count); + /* enable queue */ IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), txdctl); @@ -3380,7 +3444,10 @@ static void ixgbe_configure_srrctl(struct ixgbe_adapter *adapter, srrctl = IXGBE_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT; /* configure the packet buffer length */ - srrctl |= ixgbe_rx_bufsz(rx_ring) >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; + if (test_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state)) + srrctl |= IXGBE_RXBUFFER_3K >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; + else + srrctl |= IXGBE_RXBUFFER_2K >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; /* configure descriptor type */ srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF; @@ -3407,6 +3474,21 @@ u32 ixgbe_rss_indir_tbl_entries(struct ixgbe_adapter *adapter) } /** + * ixgbe_store_key - Write the RSS key to HW + * @adapter: device handle + * + * Write the RSS key stored in adapter.rss_key to HW. + */ +void ixgbe_store_key(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + int i; + + for (i = 0; i < 10; i++) + IXGBE_WRITE_REG(hw, IXGBE_RSSRK(i), adapter->rss_key[i]); +} + +/** * ixgbe_store_reta - Write the RETA table to HW * @adapter: device handle * @@ -3471,7 +3553,6 @@ static void ixgbe_store_vfreta(struct ixgbe_adapter *adapter) static void ixgbe_setup_reta(struct ixgbe_adapter *adapter) { - struct ixgbe_hw *hw = &adapter->hw; u32 i, j; u32 reta_entries = ixgbe_rss_indir_tbl_entries(adapter); u16 rss_i = adapter->ring_feature[RING_F_RSS].indices; @@ -3484,8 +3565,7 @@ static void ixgbe_setup_reta(struct ixgbe_adapter *adapter) rss_i = 4; /* Fill out hash function seeds */ - for (i = 0; i < 10; i++) - IXGBE_WRITE_REG(hw, IXGBE_RSSRK(i), adapter->rss_key[i]); + ixgbe_store_key(adapter); /* Fill out redirection table */ memset(adapter->rss_indir_tbl, 0, sizeof(adapter->rss_indir_tbl)); @@ -3681,6 +3761,7 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, struct ixgbe_ring *ring) { struct ixgbe_hw *hw = &adapter->hw; + union ixgbe_adv_rx_desc *rx_desc; u64 rdba = ring->dma; u32 rxdctl; u8 reg_idx = ring->reg_idx; @@ -3713,8 +3794,27 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, */ rxdctl &= ~0x3FFFFF; rxdctl |= 0x080420; +#if (PAGE_SIZE < 8192) + } else { + rxdctl &= ~(IXGBE_RXDCTL_RLPMLMASK | + IXGBE_RXDCTL_RLPML_EN); + + /* Limit the maximum frame size so we don't overrun the skb */ + if (ring_uses_build_skb(ring) && + !test_bit(__IXGBE_RX_3K_BUFFER, &ring->state)) + rxdctl |= IXGBE_MAX_FRAME_BUILD_SKB | + IXGBE_RXDCTL_RLPML_EN; +#endif } + /* initialize rx_buffer_info */ + memset(ring->rx_buffer_info, 0, + sizeof(struct ixgbe_rx_buffer) * ring->count); + + /* initialize Rx descriptor 0 */ + rx_desc = IXGBE_RX_DESC(ring, 0); + rx_desc->wb.upper.length = 0; + /* enable receive descriptor ring */ rxdctl |= IXGBE_RXDCTL_ENABLE; IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl); @@ -3851,10 +3951,31 @@ static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter) */ for (i = 0; i < adapter->num_rx_queues; i++) { rx_ring = adapter->rx_ring[i]; + + clear_ring_rsc_enabled(rx_ring); + clear_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state); + clear_bit(__IXGBE_RX_BUILD_SKB_ENABLED, &rx_ring->state); + if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) set_ring_rsc_enabled(rx_ring); - else - clear_ring_rsc_enabled(rx_ring); + + if (test_bit(__IXGBE_RX_FCOE, &rx_ring->state)) + set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state); + + clear_bit(__IXGBE_RX_BUILD_SKB_ENABLED, &rx_ring->state); + if (adapter->flags2 & IXGBE_FLAG2_RX_LEGACY) + continue; + + set_bit(__IXGBE_RX_BUILD_SKB_ENABLED, &rx_ring->state); + +#if (PAGE_SIZE < 8192) + if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) + set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state); + + if ((max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN)) || + (max_frame > IXGBE_MAX_FRAME_BUILD_SKB)) + set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state); +#endif } } @@ -4555,23 +4676,16 @@ static void ixgbe_napi_enable_all(struct ixgbe_adapter *adapter) { int q_idx; - for (q_idx = 0; q_idx < adapter->num_q_vectors; q_idx++) { - ixgbe_qv_init_lock(adapter->q_vector[q_idx]); + for (q_idx = 0; q_idx < adapter->num_q_vectors; q_idx++) napi_enable(&adapter->q_vector[q_idx]->napi); - } } static void ixgbe_napi_disable_all(struct ixgbe_adapter *adapter) { int q_idx; - for (q_idx = 0; q_idx < adapter->num_q_vectors; q_idx++) { + for (q_idx = 0; q_idx < adapter->num_q_vectors; q_idx++) napi_disable(&adapter->q_vector[q_idx]->napi); - while (!ixgbe_qv_disable(adapter->q_vector[q_idx])) { - pr_info("QV %d locked\n", q_idx); - usleep_range(1000, 20000); - } - } } static void ixgbe_clear_udp_tunnel_port(struct ixgbe_adapter *adapter, u32 mask) @@ -4875,45 +4989,47 @@ static void ixgbe_fwd_psrtype(struct ixgbe_fwd_adapter *vadapter) **/ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring) { - struct device *dev = rx_ring->dev; - unsigned long size; - u16 i; - - /* ring already cleared, nothing to do */ - if (!rx_ring->rx_buffer_info) - return; + u16 i = rx_ring->next_to_clean; + struct ixgbe_rx_buffer *rx_buffer = &rx_ring->rx_buffer_info[i]; /* Free all the Rx ring sk_buffs */ - for (i = 0; i < rx_ring->count; i++) { - struct ixgbe_rx_buffer *rx_buffer = &rx_ring->rx_buffer_info[i]; - + while (i != rx_ring->next_to_alloc) { if (rx_buffer->skb) { struct sk_buff *skb = rx_buffer->skb; if (IXGBE_CB(skb)->page_released) - dma_unmap_page(dev, - IXGBE_CB(skb)->dma, - ixgbe_rx_bufsz(rx_ring), - DMA_FROM_DEVICE); + dma_unmap_page_attrs(rx_ring->dev, + IXGBE_CB(skb)->dma, + ixgbe_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + IXGBE_RX_DMA_ATTR); dev_kfree_skb(skb); - rx_buffer->skb = NULL; } - if (!rx_buffer->page) - continue; + /* Invalidate cache lines that may have been written to by + * device so that we avoid corrupting memory. + */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + ixgbe_rx_bufsz(rx_ring), + DMA_FROM_DEVICE); - dma_unmap_page(dev, rx_buffer->dma, - ixgbe_rx_pg_size(rx_ring), DMA_FROM_DEVICE); - __free_pages(rx_buffer->page, ixgbe_rx_pg_order(rx_ring)); + /* free resources associated with mapping */ + dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, + ixgbe_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + IXGBE_RX_DMA_ATTR); + __page_frag_cache_drain(rx_buffer->page, + rx_buffer->pagecnt_bias); - rx_buffer->page = NULL; + i++; + rx_buffer++; + if (i == rx_ring->count) { + i = 0; + rx_buffer = rx_ring->rx_buffer_info; + } } - size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count; - memset(rx_ring->rx_buffer_info, 0, size); - - /* Zero out the descriptor ring */ - memset(rx_ring->desc, 0, rx_ring->size); - rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; @@ -5012,24 +5128,23 @@ fwd_queue_err: return err; } -static void ixgbe_configure_dfwd(struct ixgbe_adapter *adapter) +static int ixgbe_upper_dev_walk(struct net_device *upper, void *data) { - struct net_device *upper; - struct list_head *iter; - int err; - - netdev_for_each_all_upper_dev_rcu(adapter->netdev, upper, iter) { - if (netif_is_macvlan(upper)) { - struct macvlan_dev *dfwd = netdev_priv(upper); - struct ixgbe_fwd_adapter *vadapter = dfwd->fwd_priv; + if (netif_is_macvlan(upper)) { + struct macvlan_dev *dfwd = netdev_priv(upper); + struct ixgbe_fwd_adapter *vadapter = dfwd->fwd_priv; - if (dfwd->fwd_priv) { - err = ixgbe_fwd_ring_up(upper, vadapter); - if (err) - continue; - } - } + if (dfwd->fwd_priv) + ixgbe_fwd_ring_up(upper, vadapter); } + + return 0; +} + +static void ixgbe_configure_dfwd(struct ixgbe_adapter *adapter) +{ + netdev_walk_all_upper_dev_rcu(adapter->netdev, + ixgbe_upper_dev_walk, NULL); } static void ixgbe_configure(struct ixgbe_adapter *adapter) @@ -5291,6 +5406,8 @@ void ixgbe_reinit_locked(struct ixgbe_adapter *adapter) while (test_and_set_bit(__IXGBE_RESETTING, &adapter->state)) usleep_range(1000, 2000); + if (adapter->hw.phy.type == ixgbe_phy_fw) + ixgbe_watchdog_link_is_down(adapter); ixgbe_down(adapter); /* * If SR-IOV enabled then wait a bit before bringing the adapter @@ -5381,28 +5498,57 @@ void ixgbe_reset(struct ixgbe_adapter *adapter) **/ static void ixgbe_clean_tx_ring(struct ixgbe_ring *tx_ring) { - struct ixgbe_tx_buffer *tx_buffer_info; - unsigned long size; - u16 i; + u16 i = tx_ring->next_to_clean; + struct ixgbe_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i]; - /* ring already cleared, nothing to do */ - if (!tx_ring->tx_buffer_info) - return; + while (i != tx_ring->next_to_use) { + union ixgbe_adv_tx_desc *eop_desc, *tx_desc; - /* Free all the Tx ring sk_buffs */ - for (i = 0; i < tx_ring->count; i++) { - tx_buffer_info = &tx_ring->tx_buffer_info[i]; - ixgbe_unmap_and_free_tx_resource(tx_ring, tx_buffer_info); - } + /* Free all the Tx ring sk_buffs */ + dev_kfree_skb_any(tx_buffer->skb); - netdev_tx_reset_queue(txring_txq(tx_ring)); + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); - size = sizeof(struct ixgbe_tx_buffer) * tx_ring->count; - memset(tx_ring->tx_buffer_info, 0, size); + /* check for eop_desc to determine the end of the packet */ + eop_desc = tx_buffer->next_to_watch; + tx_desc = IXGBE_TX_DESC(tx_ring, i); + + /* unmap remaining buffers */ + while (tx_desc != eop_desc) { + tx_buffer++; + tx_desc++; + i++; + if (unlikely(i == tx_ring->count)) { + i = 0; + tx_buffer = tx_ring->tx_buffer_info; + tx_desc = IXGBE_TX_DESC(tx_ring, 0); + } - /* Zero out the descriptor ring */ - memset(tx_ring->desc, 0, tx_ring->size); + /* unmap any remaining paged data */ + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + } + /* move us one more past the eop_desc for start of next pkt */ + tx_buffer++; + i++; + if (unlikely(i == tx_ring->count)) { + i = 0; + tx_buffer = tx_ring->tx_buffer_info; + } + } + + /* reset BQL for queue */ + netdev_tx_reset_queue(txring_txq(tx_ring)); + + /* reset next_to_use and next_to_clean */ tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; } @@ -5448,12 +5594,25 @@ static void ixgbe_fdir_filter_exit(struct ixgbe_adapter *adapter) spin_unlock(&adapter->fdir_perfect_lock); } +static int ixgbe_disable_macvlan(struct net_device *upper, void *data) +{ + if (netif_is_macvlan(upper)) { + struct macvlan_dev *vlan = netdev_priv(upper); + + if (vlan->fwd_priv) { + netif_tx_stop_all_queues(upper); + netif_carrier_off(upper); + netif_tx_disable(upper); + } + } + + return 0; +} + void ixgbe_down(struct ixgbe_adapter *adapter) { struct net_device *netdev = adapter->netdev; struct ixgbe_hw *hw = &adapter->hw; - struct net_device *upper; - struct list_head *iter; int i; /* signal that we are down to the interrupt handler */ @@ -5477,17 +5636,8 @@ void ixgbe_down(struct ixgbe_adapter *adapter) netif_tx_disable(netdev); /* disable any upper devices */ - netdev_for_each_all_upper_dev_rcu(adapter->netdev, upper, iter) { - if (netif_is_macvlan(upper)) { - struct macvlan_dev *vlan = netdev_priv(upper); - - if (vlan->fwd_priv) { - netif_tx_stop_all_queues(upper); - netif_carrier_off(upper); - netif_tx_disable(upper); - } - } - } + netdev_walk_all_upper_dev_rcu(adapter->netdev, + ixgbe_disable_macvlan, NULL); ixgbe_irq_disable(adapter); @@ -5547,6 +5697,31 @@ void ixgbe_down(struct ixgbe_adapter *adapter) } /** + * ixgbe_eee_capable - helper function to determine EEE support on X550 + * @adapter: board private structure + */ +static void ixgbe_set_eee_capable(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + + switch (hw->device_id) { + case IXGBE_DEV_ID_X550EM_A_1G_T: + case IXGBE_DEV_ID_X550EM_A_1G_T_L: + if (!hw->phy.eee_speeds_supported) + break; + adapter->flags2 |= IXGBE_FLAG2_EEE_CAPABLE; + if (!hw->phy.eee_speeds_advertised) + break; + adapter->flags2 |= IXGBE_FLAG2_EEE_ENABLED; + break; + default: + adapter->flags2 &= ~IXGBE_FLAG2_EEE_CAPABLE; + adapter->flags2 &= ~IXGBE_FLAG2_EEE_ENABLED; + break; + } +} + +/** * ixgbe_tx_timeout - Respond to a Tx Hang * @netdev: network interface device structure **/ @@ -5618,7 +5793,8 @@ static void ixgbe_init_dcb(struct ixgbe_adapter *adapter) * Fields are initialized based on PCI device information and * OS network device settings (MTU size). **/ -static int ixgbe_sw_init(struct ixgbe_adapter *adapter) +static int ixgbe_sw_init(struct ixgbe_adapter *adapter, + const struct ixgbe_info *ii) { struct ixgbe_hw *hw = &adapter->hw; struct pci_dev *pdev = adapter->pdev; @@ -5634,6 +5810,9 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter) hw->subsystem_vendor_id = pdev->subsystem_vendor; hw->subsystem_device_id = pdev->subsystem_device; + /* get_invariants needs the device IDs */ + ii->get_invariants(hw); + /* Set common capability flags and settings */ rss = min_t(int, ixgbe_max_rss_indices(adapter), num_online_cpus()); adapter->ring_feature[RING_F_RSS].limit = rss; @@ -5706,6 +5885,14 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter) break; case ixgbe_mac_x550em_a: adapter->flags |= IXGBE_FLAG_GENEVE_OFFLOAD_CAPABLE; + switch (hw->device_id) { + case IXGBE_DEV_ID_X550EM_A_1G_T: + case IXGBE_DEV_ID_X550EM_A_1G_T_L: + adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE; + break; + default: + break; + } /* fall through */ case ixgbe_mac_X550EM_x: #ifdef CONFIG_IXGBE_DCB @@ -5719,6 +5906,8 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter) #endif /* IXGBE_FCOE */ /* Fall Through */ case ixgbe_mac_X550: + if (hw->mac.type == ixgbe_mac_X550) + adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE; #ifdef CONFIG_IXGBE_DCA adapter->flags &= ~IXGBE_FLAG_DCA_CAPABLE; #endif @@ -5805,9 +5994,9 @@ int ixgbe_setup_tx_resources(struct ixgbe_ring *tx_ring) if (tx_ring->q_vector) ring_node = tx_ring->q_vector->numa_node; - tx_ring->tx_buffer_info = vzalloc_node(size, ring_node); + tx_ring->tx_buffer_info = vmalloc_node(size, ring_node); if (!tx_ring->tx_buffer_info) - tx_ring->tx_buffer_info = vzalloc(size); + tx_ring->tx_buffer_info = vmalloc(size); if (!tx_ring->tx_buffer_info) goto err; @@ -5889,9 +6078,9 @@ int ixgbe_setup_rx_resources(struct ixgbe_ring *rx_ring) if (rx_ring->q_vector) ring_node = rx_ring->q_vector->numa_node; - rx_ring->rx_buffer_info = vzalloc_node(size, ring_node); + rx_ring->rx_buffer_info = vmalloc_node(size, ring_node); if (!rx_ring->rx_buffer_info) - rx_ring->rx_buffer_info = vzalloc(size); + rx_ring->rx_buffer_info = vmalloc(size); if (!rx_ring->rx_buffer_info) goto err; @@ -6049,11 +6238,6 @@ static void ixgbe_free_all_rx_resources(struct ixgbe_adapter *adapter) static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu) { struct ixgbe_adapter *adapter = netdev_priv(netdev); - int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN; - - /* MTU < 68 is an error and causes problems on some kernels */ - if ((new_mtu < 68) || (max_frame > IXGBE_MAX_JUMBO_FRAME_SIZE)) - return -EINVAL; /* * For 82599EB we cannot allow legacy VFs to enable their receive @@ -6062,7 +6246,7 @@ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu) */ if ((adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) && (adapter->hw.mac.type == ixgbe_mac_82599EB) && - (max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN))) + (new_mtu > ETH_DATA_LEN)) e_warn(probe, "Setting MTU > 1500 will disable legacy VFs\n"); e_info(probe, "changing MTU from %d to %d\n", netdev->mtu, new_mtu); @@ -6194,7 +6378,8 @@ int ixgbe_close(struct net_device *netdev) ixgbe_ptp_stop(adapter); - ixgbe_close_suspend(adapter); + if (netif_device_present(netdev)) + ixgbe_close_suspend(adapter); ixgbe_fdir_filter_exit(adapter); @@ -6239,14 +6424,12 @@ static int ixgbe_resume(struct pci_dev *pdev) if (!err && netif_running(netdev)) err = ixgbe_open(netdev); - rtnl_unlock(); - - if (err) - return err; - netif_device_attach(netdev); + if (!err) + netif_device_attach(netdev); + rtnl_unlock(); - return 0; + return err; } #endif /* CONFIG_PM */ @@ -6261,14 +6444,14 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake) int retval = 0; #endif + rtnl_lock(); netif_device_detach(netdev); - rtnl_lock(); if (netif_running(netdev)) ixgbe_close_suspend(adapter); - rtnl_unlock(); ixgbe_clear_interrupt_scheme(adapter); + rtnl_unlock(); #ifdef CONFIG_PM retval = pci_save_state(pdev); @@ -6728,6 +6911,18 @@ static void ixgbe_update_default_up(struct ixgbe_adapter *adapter) #endif } +static int ixgbe_enable_macvlan(struct net_device *upper, void *data) +{ + if (netif_is_macvlan(upper)) { + struct macvlan_dev *vlan = netdev_priv(upper); + + if (vlan->fwd_priv) + netif_tx_wake_all_queues(upper); + } + + return 0; +} + /** * ixgbe_watchdog_link_is_up - update netif_carrier status and * print link up message @@ -6737,8 +6932,6 @@ static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *adapter) { struct net_device *netdev = adapter->netdev; struct ixgbe_hw *hw = &adapter->hw; - struct net_device *upper; - struct list_head *iter; u32 link_speed = adapter->link_speed; const char *speed_str; bool flow_rx, flow_tx; @@ -6792,6 +6985,9 @@ static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *adapter) case IXGBE_LINK_SPEED_100_FULL: speed_str = "100 Mbps"; break; + case IXGBE_LINK_SPEED_10_FULL: + speed_str = "10 Mbps"; + break; default: speed_str = "unknown speed"; break; @@ -6809,14 +7005,8 @@ static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *adapter) /* enable any upper devices */ rtnl_lock(); - netdev_for_each_all_upper_dev_rcu(adapter->netdev, upper, iter) { - if (netif_is_macvlan(upper)) { - struct macvlan_dev *vlan = netdev_priv(upper); - - if (vlan->fwd_priv) - netif_tx_wake_all_queues(upper); - } - } + netdev_walk_all_upper_dev_rcu(adapter->netdev, + ixgbe_enable_macvlan, NULL); rtnl_unlock(); /* update the default user priority for VFs */ @@ -7605,18 +7795,32 @@ static void ixgbe_tx_map(struct ixgbe_ring *tx_ring, return; dma_error: dev_err(tx_ring->dev, "TX DMA map failed\n"); + tx_buffer = &tx_ring->tx_buffer_info[i]; /* clear dma mappings for failed tx_buffer_info map */ - for (;;) { + while (tx_buffer != first) { + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + + if (i--) + i += tx_ring->count; tx_buffer = &tx_ring->tx_buffer_info[i]; - ixgbe_unmap_and_free_tx_resource(tx_ring, tx_buffer); - if (tx_buffer == first) - break; - if (i == 0) - i = tx_ring->count; - i--; } + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + + dev_kfree_skb_any(first->skb); + first->skb = NULL; + tx_ring->next_to_use = i; } @@ -7655,11 +7859,17 @@ static void ixgbe_atr(struct ixgbe_ring *ring, /* snag network header to get L4 type and address */ skb = first->skb; hdr.network = skb_network_header(skb); + if (unlikely(hdr.network <= skb->data)) + return; if (skb->encapsulation && first->protocol == htons(ETH_P_IP) && - hdr.ipv4->protocol != IPPROTO_UDP) { + hdr.ipv4->protocol == IPPROTO_UDP) { struct ixgbe_adapter *adapter = q_vector->adapter; + if (unlikely(skb_tail_pointer(skb) < hdr.network + + VXLAN_HEADROOM)) + return; + /* verify the port is recognized as VXLAN */ if (adapter->vxlan_port && udp_hdr(skb)->dest == adapter->vxlan_port) @@ -7670,6 +7880,12 @@ static void ixgbe_atr(struct ixgbe_ring *ring, hdr.network = skb_inner_network_header(skb); } + /* Make sure we have at least [minimum IPv4 header + TCP] + * or [IPv6 header] bytes + */ + if (unlikely(skb_tail_pointer(skb) < hdr.network + 40)) + return; + /* Currently only IPv4/IPv6 with TCP is supported */ switch (hdr.ipv4->version) { case IPVERSION: @@ -7689,6 +7905,10 @@ static void ixgbe_atr(struct ixgbe_ring *ring, if (l4_proto != IPPROTO_TCP) return; + if (unlikely(skb_tail_pointer(skb) < hdr.network + + hlen + sizeof(struct tcphdr))) + return; + th = (struct tcphdr *)(hdr.network + hlen); /* skip this packet since the socket is closing */ @@ -8085,8 +8305,9 @@ static void ixgbe_netpoll(struct net_device *netdev) } #endif -static struct rtnl_link_stats64 *ixgbe_get_stats64(struct net_device *netdev, - struct rtnl_link_stats64 *stats) + +static void ixgbe_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *stats) { struct ixgbe_adapter *adapter = netdev_priv(netdev); int i; @@ -8124,13 +8345,13 @@ static struct rtnl_link_stats64 *ixgbe_get_stats64(struct net_device *netdev, } } rcu_read_unlock(); + /* following stats updated by ixgbe_watchdog_task() */ stats->multicast = netdev->stats.multicast; stats->rx_errors = netdev->stats.rx_errors; stats->rx_length_errors = netdev->stats.rx_length_errors; stats->rx_crc_errors = netdev->stats.rx_crc_errors; stats->rx_missed_errors = netdev->stats.rx_missed_errors; - return stats; } #ifdef CONFIG_IXGBE_DCB @@ -8354,12 +8575,38 @@ static int ixgbe_configure_clsu32_del_hnode(struct ixgbe_adapter *adapter, } #ifdef CONFIG_NET_CLS_ACT +struct upper_walk_data { + struct ixgbe_adapter *adapter; + u64 action; + int ifindex; + u8 queue; +}; + +static int get_macvlan_queue(struct net_device *upper, void *_data) +{ + if (netif_is_macvlan(upper)) { + struct macvlan_dev *dfwd = netdev_priv(upper); + struct ixgbe_fwd_adapter *vadapter = dfwd->fwd_priv; + struct upper_walk_data *data = _data; + struct ixgbe_adapter *adapter = data->adapter; + int ifindex = data->ifindex; + + if (vadapter && vadapter->netdev->ifindex == ifindex) { + data->queue = adapter->rx_ring[vadapter->rx_base_queue]->reg_idx; + data->action = data->queue; + return 1; + } + } + + return 0; +} + static int handle_redirect_action(struct ixgbe_adapter *adapter, int ifindex, u8 *queue, u64 *action) { unsigned int num_vfs = adapter->num_vfs, vf; + struct upper_walk_data data; struct net_device *upper; - struct list_head *iter; /* redirect to a SRIOV VF */ for (vf = 0; vf < num_vfs; ++vf) { @@ -8377,17 +8624,16 @@ static int handle_redirect_action(struct ixgbe_adapter *adapter, int ifindex, } /* redirect to a offloaded macvlan netdev */ - netdev_for_each_all_upper_dev_rcu(adapter->netdev, upper, iter) { - if (netif_is_macvlan(upper)) { - struct macvlan_dev *dfwd = netdev_priv(upper); - struct ixgbe_fwd_adapter *vadapter = dfwd->fwd_priv; - - if (vadapter && vadapter->netdev->ifindex == ifindex) { - *queue = adapter->rx_ring[vadapter->rx_base_queue]->reg_idx; - *action = *queue; - return 0; - } - } + data.adapter = adapter; + data.ifindex = ifindex; + data.action = 0; + data.queue = 0; + if (netdev_walk_all_upper_dev_rcu(adapter->netdev, + get_macvlan_queue, &data)) { + *action = data.action; + *queue = data.queue; + + return 0; } return -EINVAL; @@ -8414,7 +8660,7 @@ static int parse_tc_actions(struct ixgbe_adapter *adapter, } /* Redirect to a VF or a offloaded macvlan */ - if (is_tcf_mirred_redirect(a)) { + if (is_tcf_mirred_egress_redirect(a)) { int ifindex = tcf_mirred_ifindex(a); err = handle_redirect_action(adapter, ifindex, queue, @@ -9239,9 +9485,6 @@ static const struct net_device_ops ixgbe_netdev_ops = { #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = ixgbe_netpoll, #endif -#ifdef CONFIG_NET_RX_BUSY_POLL - .ndo_busy_poll = ixgbe_low_latency_recv, -#endif #ifdef IXGBE_FCOE .ndo_fcoe_ddp_setup = ixgbe_fcoe_ddp_get, .ndo_fcoe_ddp_target = ixgbe_fcoe_ddp_target, @@ -9481,6 +9724,8 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw->mac.ops = *ii->mac_ops; hw->mac.type = ii->mac; hw->mvals = ii->mvals; + if (ii->link_ops) + hw->link.ops = *ii->link_ops; /* EEPROM */ hw->eeprom.ops = *ii->eeprom_ops; @@ -9504,10 +9749,8 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw->phy.mdio.mdio_read = ixgbe_mdio_read; hw->phy.mdio.mdio_write = ixgbe_mdio_write; - ii->get_invariants(hw); - /* setup the private structure */ - err = ixgbe_sw_init(adapter); + err = ixgbe_sw_init(adapter, ii); if (err) goto err_sw_init; @@ -9545,6 +9788,7 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw->phy.reset_if_overtemp = true; err = hw->mac.ops.reset_hw(hw); hw->phy.reset_if_overtemp = false; + ixgbe_set_eee_capable(adapter); if (err == IXGBE_ERR_SFP_NOT_PRESENT) { err = 0; } else if (err == IXGBE_ERR_SFP_NOT_SUPPORTED) { @@ -9616,9 +9860,13 @@ skip_sriov: netdev->priv_flags |= IFF_UNICAST_FLT; netdev->priv_flags |= IFF_SUPP_NOFCS; + /* MTU range: 68 - 9710 */ + netdev->min_mtu = ETH_MIN_MTU; + netdev->max_mtu = IXGBE_MAX_JUMBO_FRAME_SIZE - (ETH_HLEN + ETH_FCS_LEN); + #ifdef CONFIG_IXGBE_DCB if (adapter->flags & IXGBE_FLAG_DCB_CAPABLE) - netdev->dcbnl_ops = &dcbnl_ops; + netdev->dcbnl_ops = &ixgbe_dcbnl_ops; #endif #ifdef IXGBE_FCOE @@ -9778,8 +10026,9 @@ skip_sriov: * since os does not support feature */ if (hw->mac.ops.set_fw_drv_ver) - hw->mac.ops.set_fw_drv_ver(hw, 0xFF, 0xFF, 0xFF, - 0xFF); + hw->mac.ops.set_fw_drv_ver(hw, 0xFF, 0xFF, 0xFF, 0xFF, + sizeof(ixgbe_driver_version) - 1, + ixgbe_driver_version); /* add san mac addr to netdev */ ixgbe_add_sanmac_netdev(netdev); @@ -10027,7 +10276,7 @@ skip_bad_vf_detection: } if (netif_running(netdev)) - ixgbe_down(adapter); + ixgbe_close_suspend(adapter); if (!test_and_set_bit(__IXGBE_DISABLED, &adapter->state)) pci_disable_device(pdev); @@ -10097,10 +10346,12 @@ static void ixgbe_io_resume(struct pci_dev *pdev) } #endif + rtnl_lock(); if (netif_running(netdev)) - ixgbe_up(adapter); + ixgbe_open(netdev); netif_device_attach(netdev); + rtnl_unlock(); } static const struct pci_error_handlers ixgbe_err_handler = { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h index 01c2667c0f92..811cb4f64a5b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h @@ -74,6 +74,7 @@ enum ixgbe_pfvf_api_rev { ixgbe_mbox_api_20, /* API version 2.0, solaris Phase1 VF driver */ ixgbe_mbox_api_11, /* API version 1.1, linux/freebsd VF driver */ ixgbe_mbox_api_12, /* API version 1.2, linux/freebsd VF driver */ + ixgbe_mbox_api_13, /* API version 1.3, linux/freebsd VF driver */ /* This value should always be last */ ixgbe_mbox_api_unknown, /* indicates that API version is not known */ }; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c index 021ab9b89c71..e55b2602f371 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c @@ -109,11 +109,11 @@ static u8 ixgbe_ones_comp_byte_add(u8 add1, u8 add2) * * Returns an error code on error. */ -static s32 ixgbe_read_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr, - u16 reg, u16 *val, bool lock) +s32 ixgbe_read_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr, + u16 reg, u16 *val, bool lock) { u32 swfw_mask = hw->phy.phy_semaphore_mask; - int max_retry = 10; + int max_retry = 3; int retry = 0; u8 csum_byte; u8 high_bits; @@ -178,36 +178,6 @@ fail: } /** - * ixgbe_read_i2c_combined_generic - Perform I2C read combined operation - * @hw: pointer to the hardware structure - * @addr: I2C bus address to read from - * @reg: I2C device register to read from - * @val: pointer to location to receive read value - * - * Returns an error code on error. - */ -s32 ixgbe_read_i2c_combined_generic(struct ixgbe_hw *hw, u8 addr, - u16 reg, u16 *val) -{ - return ixgbe_read_i2c_combined_generic_int(hw, addr, reg, val, true); -} - -/** - * ixgbe_read_i2c_combined_generic_unlocked - Unlocked I2C read combined - * @hw: pointer to the hardware structure - * @addr: I2C bus address to read from - * @reg: I2C device register to read from - * @val: pointer to location to receive read value - * - * Returns an error code on error. - */ -s32 ixgbe_read_i2c_combined_generic_unlocked(struct ixgbe_hw *hw, u8 addr, - u16 reg, u16 *val) -{ - return ixgbe_read_i2c_combined_generic_int(hw, addr, reg, val, false); -} - -/** * ixgbe_write_i2c_combined_generic_int - Perform I2C write combined operation * @hw: pointer to the hardware structure * @addr: I2C bus address to write to @@ -217,8 +187,8 @@ s32 ixgbe_read_i2c_combined_generic_unlocked(struct ixgbe_hw *hw, u8 addr, * * Returns an error code on error. */ -static s32 ixgbe_write_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr, - u16 reg, u16 val, bool lock) +s32 ixgbe_write_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr, + u16 reg, u16 val, bool lock) { u32 swfw_mask = hw->phy.phy_semaphore_mask; int max_retry = 1; @@ -273,33 +243,39 @@ fail: } /** - * ixgbe_write_i2c_combined_generic - Perform I2C write combined operation - * @hw: pointer to the hardware structure - * @addr: I2C bus address to write to - * @reg: I2C device register to write to - * @val: value to write + * ixgbe_probe_phy - Probe a single address for a PHY + * @hw: pointer to hardware structure + * @phy_addr: PHY address to probe * - * Returns an error code on error. - */ -s32 ixgbe_write_i2c_combined_generic(struct ixgbe_hw *hw, - u8 addr, u16 reg, u16 val) + * Returns true if PHY found + **/ +static bool ixgbe_probe_phy(struct ixgbe_hw *hw, u16 phy_addr) { - return ixgbe_write_i2c_combined_generic_int(hw, addr, reg, val, true); -} + u16 ext_ability = 0; -/** - * ixgbe_write_i2c_combined_generic_unlocked - Unlocked I2C write combined - * @hw: pointer to the hardware structure - * @addr: I2C bus address to write to - * @reg: I2C device register to write to - * @val: value to write - * - * Returns an error code on error. - */ -s32 ixgbe_write_i2c_combined_generic_unlocked(struct ixgbe_hw *hw, - u8 addr, u16 reg, u16 val) -{ - return ixgbe_write_i2c_combined_generic_int(hw, addr, reg, val, false); + hw->phy.mdio.prtad = phy_addr; + if (mdio45_probe(&hw->phy.mdio, phy_addr) != 0) + return false; + + if (ixgbe_get_phy_id(hw)) + return false; + + hw->phy.type = ixgbe_get_phy_type_from_id(hw->phy.id); + + if (hw->phy.type == ixgbe_phy_unknown) { + hw->phy.ops.read_reg(hw, + MDIO_PMA_EXTABLE, + MDIO_MMD_PMAPMD, + &ext_ability); + if (ext_ability & + (MDIO_PMA_EXTABLE_10GBT | + MDIO_PMA_EXTABLE_1000BT)) + hw->phy.type = ixgbe_phy_cu_unknown; + else + hw->phy.type = ixgbe_phy_generic; + } + + return true; } /** @@ -311,7 +287,7 @@ s32 ixgbe_write_i2c_combined_generic_unlocked(struct ixgbe_hw *hw, s32 ixgbe_identify_phy_generic(struct ixgbe_hw *hw) { u32 phy_addr; - u16 ext_ability = 0; + u32 status = IXGBE_ERR_PHY_ADDR_INVALID; if (!hw->phy.phy_semaphore_mask) { if (hw->bus.lan_id) @@ -320,37 +296,34 @@ s32 ixgbe_identify_phy_generic(struct ixgbe_hw *hw) hw->phy.phy_semaphore_mask = IXGBE_GSSR_PHY0_SM; } - if (hw->phy.type == ixgbe_phy_unknown) { - for (phy_addr = 0; phy_addr < IXGBE_MAX_PHY_ADDR; phy_addr++) { - hw->phy.mdio.prtad = phy_addr; - if (mdio45_probe(&hw->phy.mdio, phy_addr) == 0) { - ixgbe_get_phy_id(hw); - hw->phy.type = - ixgbe_get_phy_type_from_id(hw->phy.id); - - if (hw->phy.type == ixgbe_phy_unknown) { - hw->phy.ops.read_reg(hw, - MDIO_PMA_EXTABLE, - MDIO_MMD_PMAPMD, - &ext_ability); - if (ext_ability & - (MDIO_PMA_EXTABLE_10GBT | - MDIO_PMA_EXTABLE_1000BT)) - hw->phy.type = - ixgbe_phy_cu_unknown; - else - hw->phy.type = - ixgbe_phy_generic; - } + if (hw->phy.type != ixgbe_phy_unknown) + return 0; - return 0; - } + if (hw->phy.nw_mng_if_sel) { + phy_addr = (hw->phy.nw_mng_if_sel & + IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD) >> + IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD_SHIFT; + if (ixgbe_probe_phy(hw, phy_addr)) + return 0; + else + return IXGBE_ERR_PHY_ADDR_INVALID; + } + + for (phy_addr = 0; phy_addr < IXGBE_MAX_PHY_ADDR; phy_addr++) { + if (ixgbe_probe_phy(hw, phy_addr)) { + status = 0; + break; } - /* indicate no PHY found */ - hw->phy.mdio.prtad = MDIO_PRTAD_NONE; - return IXGBE_ERR_PHY_ADDR_INVALID; } - return 0; + + /* Certain media types do not have a phy so an address will not + * be found and the code will take this path. Caller has to + * decide if it is an error or not. + */ + if (status) + hw->phy.mdio.prtad = MDIO_PRTAD_NONE; + + return status; } /** @@ -416,7 +389,8 @@ static enum ixgbe_phy_type ixgbe_get_phy_type_from_id(u32 phy_id) case TN1010_PHY_ID: phy_type = ixgbe_phy_tn; break; - case X550_PHY_ID: + case X550_PHY_ID2: + case X550_PHY_ID3: case X540_PHY_ID: phy_type = ixgbe_phy_aq; break; @@ -427,6 +401,7 @@ static enum ixgbe_phy_type ixgbe_get_phy_type_from_id(u32 phy_id) phy_type = ixgbe_phy_nl; break; case X557_PHY_ID: + case X557_PHY_ID2: phy_type = ixgbe_phy_x550em_ext_t; break; default: @@ -477,11 +452,27 @@ s32 ixgbe_reset_phy_generic(struct ixgbe_hw *hw) */ for (i = 0; i < 30; i++) { msleep(100); - hw->phy.ops.read_reg(hw, MDIO_CTRL1, - MDIO_MMD_PHYXS, &ctrl); - if (!(ctrl & MDIO_CTRL1_RESET)) { - udelay(2); - break; + if (hw->phy.type == ixgbe_phy_x550em_ext_t) { + status = hw->phy.ops.read_reg(hw, + IXGBE_MDIO_TX_VENDOR_ALARMS_3, + MDIO_MMD_PMAPMD, &ctrl); + if (status) + return status; + + if (ctrl & IXGBE_MDIO_TX_VENDOR_ALARMS_3_RST_MASK) { + udelay(2); + break; + } + } else { + status = hw->phy.ops.read_reg(hw, MDIO_CTRL1, + MDIO_MMD_PHYXS, &ctrl); + if (status) + return status; + + if (!(ctrl & MDIO_CTRL1_RESET)) { + udelay(2); + break; + } } } @@ -705,53 +696,52 @@ s32 ixgbe_setup_phy_link_generic(struct ixgbe_hw *hw) ixgbe_get_copper_link_capabilities_generic(hw, &speed, &autoneg); - if (speed & IXGBE_LINK_SPEED_10GB_FULL) { - /* Set or unset auto-negotiation 10G advertisement */ - hw->phy.ops.read_reg(hw, MDIO_AN_10GBT_CTRL, - MDIO_MMD_AN, - &autoneg_reg); + /* Set or unset auto-negotiation 10G advertisement */ + hw->phy.ops.read_reg(hw, MDIO_AN_10GBT_CTRL, MDIO_MMD_AN, &autoneg_reg); - autoneg_reg &= ~MDIO_AN_10GBT_CTRL_ADV10G; - if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10GB_FULL) - autoneg_reg |= MDIO_AN_10GBT_CTRL_ADV10G; + autoneg_reg &= ~MDIO_AN_10GBT_CTRL_ADV10G; + if ((hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10GB_FULL) && + (speed & IXGBE_LINK_SPEED_10GB_FULL)) + autoneg_reg |= MDIO_AN_10GBT_CTRL_ADV10G; - hw->phy.ops.write_reg(hw, MDIO_AN_10GBT_CTRL, - MDIO_MMD_AN, - autoneg_reg); - } + hw->phy.ops.write_reg(hw, MDIO_AN_10GBT_CTRL, MDIO_MMD_AN, autoneg_reg); - if (speed & IXGBE_LINK_SPEED_1GB_FULL) { - /* Set or unset auto-negotiation 1G advertisement */ - hw->phy.ops.read_reg(hw, - IXGBE_MII_AUTONEG_VENDOR_PROVISION_1_REG, - MDIO_MMD_AN, - &autoneg_reg); - - autoneg_reg &= ~IXGBE_MII_1GBASE_T_ADVERTISE; - if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_1GB_FULL) - autoneg_reg |= IXGBE_MII_1GBASE_T_ADVERTISE; + hw->phy.ops.read_reg(hw, IXGBE_MII_AUTONEG_VENDOR_PROVISION_1_REG, + MDIO_MMD_AN, &autoneg_reg); - hw->phy.ops.write_reg(hw, - IXGBE_MII_AUTONEG_VENDOR_PROVISION_1_REG, - MDIO_MMD_AN, - autoneg_reg); + if (hw->mac.type == ixgbe_mac_X550) { + /* Set or unset auto-negotiation 5G advertisement */ + autoneg_reg &= ~IXGBE_MII_5GBASE_T_ADVERTISE; + if ((hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_5GB_FULL) && + (speed & IXGBE_LINK_SPEED_5GB_FULL)) + autoneg_reg |= IXGBE_MII_5GBASE_T_ADVERTISE; + + /* Set or unset auto-negotiation 2.5G advertisement */ + autoneg_reg &= ~IXGBE_MII_2_5GBASE_T_ADVERTISE; + if ((hw->phy.autoneg_advertised & + IXGBE_LINK_SPEED_2_5GB_FULL) && + (speed & IXGBE_LINK_SPEED_2_5GB_FULL)) + autoneg_reg |= IXGBE_MII_2_5GBASE_T_ADVERTISE; } - if (speed & IXGBE_LINK_SPEED_100_FULL) { - /* Set or unset auto-negotiation 100M advertisement */ - hw->phy.ops.read_reg(hw, MDIO_AN_ADVERTISE, - MDIO_MMD_AN, - &autoneg_reg); + /* Set or unset auto-negotiation 1G advertisement */ + autoneg_reg &= ~IXGBE_MII_1GBASE_T_ADVERTISE; + if ((hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_1GB_FULL) && + (speed & IXGBE_LINK_SPEED_1GB_FULL)) + autoneg_reg |= IXGBE_MII_1GBASE_T_ADVERTISE; - autoneg_reg &= ~(ADVERTISE_100FULL | - ADVERTISE_100HALF); - if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_100_FULL) - autoneg_reg |= ADVERTISE_100FULL; + hw->phy.ops.write_reg(hw, IXGBE_MII_AUTONEG_VENDOR_PROVISION_1_REG, + MDIO_MMD_AN, autoneg_reg); - hw->phy.ops.write_reg(hw, MDIO_AN_ADVERTISE, - MDIO_MMD_AN, - autoneg_reg); - } + /* Set or unset auto-negotiation 100M advertisement */ + hw->phy.ops.read_reg(hw, MDIO_AN_ADVERTISE, MDIO_MMD_AN, &autoneg_reg); + + autoneg_reg &= ~(ADVERTISE_100FULL | ADVERTISE_100HALF); + if ((hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_100_FULL) && + (speed & IXGBE_LINK_SPEED_100_FULL)) + autoneg_reg |= ADVERTISE_100FULL; + + hw->phy.ops.write_reg(hw, MDIO_AN_ADVERTISE, MDIO_MMD_AN, autoneg_reg); /* Blocked by MNG FW so don't reset PHY */ if (ixgbe_check_reset_blocked(hw)) @@ -778,9 +768,7 @@ s32 ixgbe_setup_phy_link_speed_generic(struct ixgbe_hw *hw, ixgbe_link_speed speed, bool autoneg_wait_to_complete) { - - /* - * Clear autoneg_advertised and set new values based on input link + /* Clear autoneg_advertised and set new values based on input link * speed. */ hw->phy.autoneg_advertised = 0; @@ -788,12 +776,21 @@ s32 ixgbe_setup_phy_link_speed_generic(struct ixgbe_hw *hw, if (speed & IXGBE_LINK_SPEED_10GB_FULL) hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_10GB_FULL; + if (speed & IXGBE_LINK_SPEED_5GB_FULL) + hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_5GB_FULL; + + if (speed & IXGBE_LINK_SPEED_2_5GB_FULL) + hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_2_5GB_FULL; + if (speed & IXGBE_LINK_SPEED_1GB_FULL) hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_1GB_FULL; if (speed & IXGBE_LINK_SPEED_100_FULL) hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_100_FULL; + if (speed & IXGBE_LINK_SPEED_10_FULL) + hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_10_FULL; + /* Setup link based on the new speed settings */ hw->phy.ops.setup_link(hw); @@ -830,6 +827,7 @@ static s32 ixgbe_get_copper_speeds_supported(struct ixgbe_hw *hw) hw->phy.speeds_supported |= IXGBE_LINK_SPEED_5GB_FULL; break; case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: hw->phy.speeds_supported &= ~IXGBE_LINK_SPEED_100_FULL; break; default: @@ -986,40 +984,6 @@ s32 ixgbe_setup_phy_link_tnx(struct ixgbe_hw *hw) } /** - * ixgbe_get_phy_firmware_version_tnx - Gets the PHY Firmware Version - * @hw: pointer to hardware structure - * @firmware_version: pointer to the PHY Firmware Version - **/ -s32 ixgbe_get_phy_firmware_version_tnx(struct ixgbe_hw *hw, - u16 *firmware_version) -{ - s32 status; - - status = hw->phy.ops.read_reg(hw, TNX_FW_REV, - MDIO_MMD_VEND1, - firmware_version); - - return status; -} - -/** - * ixgbe_get_phy_firmware_version_generic - Gets the PHY Firmware Version - * @hw: pointer to hardware structure - * @firmware_version: pointer to the PHY Firmware Version - **/ -s32 ixgbe_get_phy_firmware_version_generic(struct ixgbe_hw *hw, - u16 *firmware_version) -{ - s32 status; - - status = hw->phy.ops.read_reg(hw, AQ_FW_REV, - MDIO_MMD_VEND1, - firmware_version); - - return status; -} - -/** * ixgbe_reset_phy_nl - Performs a PHY reset * @hw: pointer to hardware structure **/ @@ -1764,6 +1728,8 @@ static s32 ixgbe_read_i2c_byte_generic_int(struct ixgbe_hw *hw, u8 byte_offset, u32 swfw_mask = hw->phy.phy_semaphore_mask; bool nack = true; + if (hw->mac.type >= ixgbe_mac_X550) + max_retry = 3; if (ixgbe_is_sfp_probe(hw, byte_offset, dev_addr)) max_retry = IXGBE_SFP_DETECT_RETRIES; @@ -2396,9 +2362,7 @@ s32 ixgbe_set_copper_phy_power(struct ixgbe_hw *hw, bool on) if (!on && ixgbe_mng_present(hw)) return 0; - status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_VENDOR_SPECIFIC_1_CONTROL, - IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE, - ®); + status = hw->phy.ops.read_reg(hw, MDIO_CTRL1, MDIO_MMD_VEND1, ®); if (status) return status; @@ -2410,8 +2374,6 @@ s32 ixgbe_set_copper_phy_power(struct ixgbe_hw *hw, bool on) reg |= IXGBE_MDIO_PHY_SET_LOW_POWER_MODE; } - status = hw->phy.ops.write_reg(hw, IXGBE_MDIO_VENDOR_SPECIFIC_1_CONTROL, - IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE, - reg); + status = hw->phy.ops.write_reg(hw, MDIO_CTRL1, MDIO_MMD_VEND1, reg); return status; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h index cc735ec3e045..5aa2c3cf7aec 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h @@ -168,10 +168,6 @@ s32 ixgbe_check_phy_link_tnx(struct ixgbe_hw *hw, ixgbe_link_speed *speed, bool *link_up); s32 ixgbe_setup_phy_link_tnx(struct ixgbe_hw *hw); -s32 ixgbe_get_phy_firmware_version_tnx(struct ixgbe_hw *hw, - u16 *firmware_version); -s32 ixgbe_get_phy_firmware_version_generic(struct ixgbe_hw *hw, - u16 *firmware_version); s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw); s32 ixgbe_set_copper_phy_power(struct ixgbe_hw *hw, bool on); @@ -195,12 +191,8 @@ s32 ixgbe_read_i2c_sff8472_generic(struct ixgbe_hw *hw, u8 byte_offset, u8 *sff8472_data); s32 ixgbe_write_i2c_eeprom_generic(struct ixgbe_hw *hw, u8 byte_offset, u8 eeprom_data); -s32 ixgbe_read_i2c_combined_generic(struct ixgbe_hw *hw, u8 addr, - u16 reg, u16 *val); -s32 ixgbe_read_i2c_combined_generic_unlocked(struct ixgbe_hw *hw, u8 addr, - u16 reg, u16 *val); -s32 ixgbe_write_i2c_combined_generic(struct ixgbe_hw *hw, u8 addr, - u16 reg, u16 val); -s32 ixgbe_write_i2c_combined_generic_unlocked(struct ixgbe_hw *hw, u8 addr, - u16 reg, u16 val); +s32 ixgbe_read_i2c_combined_generic_int(struct ixgbe_hw *, u8 addr, u16 reg, + u16 *val, bool lock); +s32 ixgbe_write_i2c_combined_generic_int(struct ixgbe_hw *, u8 addr, u16 reg, + u16 val, bool lock); #endif /* _IXGBE_PHY_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index a92277683a64..ef0635e0918c 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -245,7 +245,7 @@ static void ixgbe_ptp_setup_sdp_x540(struct ixgbe_adapter *adapter) * result of SYSTIME is 32bits of "billions of cycles" and 32 bits of * "cycles", rather than seconds and nanoseconds. */ -static cycle_t ixgbe_ptp_read_X550(const struct cyclecounter *hw_cc) +static u64 ixgbe_ptp_read_X550(const struct cyclecounter *hw_cc) { struct ixgbe_adapter *adapter = container_of(hw_cc, struct ixgbe_adapter, hw_cc); @@ -282,7 +282,7 @@ static cycle_t ixgbe_ptp_read_X550(const struct cyclecounter *hw_cc) * cyclecounter structure used to construct a ns counter from the * arbitrary fixed point registers */ -static cycle_t ixgbe_ptp_read_82599(const struct cyclecounter *cc) +static u64 ixgbe_ptp_read_82599(const struct cyclecounter *cc) { struct ixgbe_adapter *adapter = container_of(cc, struct ixgbe_adapter, hw_cc); @@ -858,14 +858,14 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter, case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_L4_V1; tsync_rx_mtrl |= IXGBE_RXMTRL_V1_SYNC_MSG; - adapter->flags &= ~(IXGBE_FLAG_RX_HWTSTAMP_ENABLED | - IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); + adapter->flags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED | + IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); break; case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_L4_V1; tsync_rx_mtrl |= IXGBE_RXMTRL_V1_DELAY_REQ_MSG; - adapter->flags &= ~(IXGBE_FLAG_RX_HWTSTAMP_ENABLED | - IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); + adapter->flags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED | + IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); break; case HWTSTAMP_FILTER_PTP_V2_EVENT: case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: @@ -879,8 +879,8 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter, tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_EVENT_V2; is_l2 = true; config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; - adapter->flags &= ~(IXGBE_FLAG_RX_HWTSTAMP_ENABLED | - IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); + adapter->flags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED | + IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); break; case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: case HWTSTAMP_FILTER_ALL: diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index 7e5d9850e4b2..044cb44747cf 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -512,6 +512,7 @@ static s32 ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) switch (adapter->vfinfo[vf].vf_api) { case ixgbe_mbox_api_11: case ixgbe_mbox_api_12: + case ixgbe_mbox_api_13: /* * Version 1.1 supports jumbo frames on VFs if PF has * jumbo frames enabled which means legacy VFs are @@ -934,7 +935,8 @@ static int ixgbe_set_vf_macvlan_msg(struct ixgbe_adapter *adapter, IXGBE_VT_MSGINFO_SHIFT; int err; - if (adapter->vfinfo[vf].pf_set_mac && index > 0) { + if (adapter->vfinfo[vf].pf_set_mac && !adapter->vfinfo[vf].trusted && + index > 0) { e_warn(drv, "VF %d requested MACVLAN filter but is administratively denied\n", vf); @@ -978,6 +980,7 @@ static int ixgbe_negotiate_vf_api(struct ixgbe_adapter *adapter, case ixgbe_mbox_api_10: case ixgbe_mbox_api_11: case ixgbe_mbox_api_12: + case ixgbe_mbox_api_13: adapter->vfinfo[vf].vf_api = api; return 0; default: @@ -1002,6 +1005,7 @@ static int ixgbe_get_vf_queues(struct ixgbe_adapter *adapter, case ixgbe_mbox_api_20: case ixgbe_mbox_api_11: case ixgbe_mbox_api_12: + case ixgbe_mbox_api_13: break; default: return -1; @@ -1041,8 +1045,13 @@ static int ixgbe_get_vf_reta(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) return -EPERM; /* verify the PF is supporting the correct API */ - if (adapter->vfinfo[vf].vf_api != ixgbe_mbox_api_12) + switch (adapter->vfinfo[vf].vf_api) { + case ixgbe_mbox_api_13: + case ixgbe_mbox_api_12: + break; + default: return -EOPNOTSUPP; + } /* This mailbox command is supported (required) only for 82599 and x540 * VFs which support up to 4 RSS queues. Therefore we will compress the @@ -1068,8 +1077,13 @@ static int ixgbe_get_vf_rss_key(struct ixgbe_adapter *adapter, return -EPERM; /* verify the PF is supporting the correct API */ - if (adapter->vfinfo[vf].vf_api != ixgbe_mbox_api_12) + switch (adapter->vfinfo[vf].vf_api) { + case ixgbe_mbox_api_13: + case ixgbe_mbox_api_12: + break; + default: return -EOPNOTSUPP; + } memcpy(rss_key, adapter->rss_key, sizeof(adapter->rss_key)); @@ -1081,11 +1095,16 @@ static int ixgbe_update_vf_xcast_mode(struct ixgbe_adapter *adapter, { struct ixgbe_hw *hw = &adapter->hw; int xcast_mode = msgbuf[1]; - u32 vmolr, disable, enable; + u32 vmolr, fctrl, disable, enable; /* verify the PF is supporting the correct APIs */ switch (adapter->vfinfo[vf].vf_api) { case ixgbe_mbox_api_12: + /* promisc introduced in 1.3 version */ + if (xcast_mode == IXGBEVF_XCAST_MODE_PROMISC) + return -EOPNOTSUPP; + /* Fall threw */ + case ixgbe_mbox_api_13: break; default: return -EOPNOTSUPP; @@ -1101,17 +1120,34 @@ static int ixgbe_update_vf_xcast_mode(struct ixgbe_adapter *adapter, switch (xcast_mode) { case IXGBEVF_XCAST_MODE_NONE: - disable = IXGBE_VMOLR_BAM | IXGBE_VMOLR_ROMPE | IXGBE_VMOLR_MPE; + disable = IXGBE_VMOLR_BAM | IXGBE_VMOLR_ROMPE | + IXGBE_VMOLR_MPE | IXGBE_VMOLR_UPE | IXGBE_VMOLR_VPE; enable = 0; break; case IXGBEVF_XCAST_MODE_MULTI: - disable = IXGBE_VMOLR_MPE; + disable = IXGBE_VMOLR_MPE | IXGBE_VMOLR_UPE | IXGBE_VMOLR_VPE; enable = IXGBE_VMOLR_BAM | IXGBE_VMOLR_ROMPE; break; case IXGBEVF_XCAST_MODE_ALLMULTI: - disable = 0; + disable = IXGBE_VMOLR_UPE | IXGBE_VMOLR_VPE; enable = IXGBE_VMOLR_BAM | IXGBE_VMOLR_ROMPE | IXGBE_VMOLR_MPE; break; + case IXGBEVF_XCAST_MODE_PROMISC: + if (hw->mac.type <= ixgbe_mac_82599EB) + return -EOPNOTSUPP; + + fctrl = IXGBE_READ_REG(hw, IXGBE_FCTRL); + if (!(fctrl & IXGBE_FCTRL_UPE)) { + /* VF promisc requires PF in promisc */ + e_warn(drv, + "Enabling VF promisc requires PF in promisc\n"); + return -EPERM; + } + + disable = 0; + enable = IXGBE_VMOLR_BAM | IXGBE_VMOLR_ROMPE | + IXGBE_VMOLR_MPE | IXGBE_VMOLR_UPE | IXGBE_VMOLR_VPE; + break; default: return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h index 31d82e3abac8..1d07f2ead914 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h @@ -92,6 +92,8 @@ #define IXGBE_DEV_ID_X550EM_A_SGMII_L 0x15C7 #define IXGBE_DEV_ID_X550EM_A_10G_T 0x15C8 #define IXGBE_DEV_ID_X550EM_A_SFP 0x15CE +#define IXGBE_DEV_ID_X550EM_A_1G_T 0x15E4 +#define IXGBE_DEV_ID_X550EM_A_1G_T_L 0x15E5 /* VF Device IDs */ #define IXGBE_DEV_ID_82599_VF 0x10ED @@ -874,19 +876,13 @@ struct ixgbe_thermal_sensor_data { #define IXGBE_MDIO_AUTO_NEG_VENDOR_STATUS_1GB 0x4 /* 1Gb/s */ #define IXGBE_MDIO_AUTO_NEG_VENDOR_STATUS_10GB 0x6 /* 10Gb/s */ -#define IXGBE_MII_10GBASE_T_AUTONEG_CTRL_REG 0x20 /* 10G Control Reg */ #define IXGBE_MII_AUTONEG_VENDOR_PROVISION_1_REG 0xC400 /* 1G Provisioning 1 */ #define IXGBE_MII_AUTONEG_XNP_TX_REG 0x17 /* 1G XNP Transmit */ -#define IXGBE_MII_AUTONEG_ADVERTISE_REG 0x10 /* 100M Advertisement */ -#define IXGBE_MII_10GBASE_T_ADVERTISE 0x1000 /* full duplex, bit:12*/ #define IXGBE_MII_1GBASE_T_ADVERTISE_XNP_TX 0x4000 /* full duplex, bit:14*/ #define IXGBE_MII_1GBASE_T_ADVERTISE 0x8000 /* full duplex, bit:15*/ #define IXGBE_MII_2_5GBASE_T_ADVERTISE 0x0400 #define IXGBE_MII_5GBASE_T_ADVERTISE 0x0800 -#define IXGBE_MII_100BASE_T_ADVERTISE 0x0100 /* full duplex, bit:8 */ -#define IXGBE_MII_100BASE_T_ADVERTISE_HALF 0x0080 /* half duplex, bit:7 */ #define IXGBE_MII_RESTART 0x200 -#define IXGBE_MII_AUTONEG_COMPLETE 0x20 #define IXGBE_MII_AUTONEG_LINK_UP 0x04 #define IXGBE_MII_AUTONEG_REG 0x0 @@ -1320,30 +1316,20 @@ struct ixgbe_thermal_sensor_data { /* MDIO definitions */ #define IXGBE_MDIO_ZERO_DEV_TYPE 0x0 -#define IXGBE_MDIO_PMA_PMD_DEV_TYPE 0x1 #define IXGBE_MDIO_PCS_DEV_TYPE 0x3 -#define IXGBE_MDIO_PHY_XS_DEV_TYPE 0x4 -#define IXGBE_MDIO_AUTO_NEG_DEV_TYPE 0x7 -#define IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE 0x1E /* Device 30 */ #define IXGBE_TWINAX_DEV 1 #define IXGBE_MDIO_COMMAND_TIMEOUT 100 /* PHY Timeout for 1 GB mode */ -#define IXGBE_MDIO_VENDOR_SPECIFIC_1_CONTROL 0x0 /* VS1 Control Reg */ -#define IXGBE_MDIO_VENDOR_SPECIFIC_1_STATUS 0x1 /* VS1 Status Reg */ #define IXGBE_MDIO_VENDOR_SPECIFIC_1_LINK_STATUS 0x0008 /* 1 = Link Up */ #define IXGBE_MDIO_VENDOR_SPECIFIC_1_SPEED_STATUS 0x0010 /* 0 - 10G, 1 - 1G */ #define IXGBE_MDIO_VENDOR_SPECIFIC_1_10G_SPEED 0x0018 #define IXGBE_MDIO_VENDOR_SPECIFIC_1_1G_SPEED 0x0010 -#define IXGBE_MDIO_AUTO_NEG_CONTROL 0x0 /* AUTO_NEG Control Reg */ -#define IXGBE_MDIO_AUTO_NEG_STATUS 0x1 /* AUTO_NEG Status Reg */ #define IXGBE_MDIO_AUTO_NEG_VENDOR_STAT 0xC800 /* AUTO_NEG Vendor Status Reg */ #define IXGBE_MDIO_AUTO_NEG_VENDOR_TX_ALARM 0xCC00 /* AUTO_NEG Vendor TX Reg */ #define IXGBE_MDIO_AUTO_NEG_VENDOR_TX_ALARM2 0xCC01 /* AUTO_NEG Vendor Tx Reg */ #define IXGBE_MDIO_AUTO_NEG_VEN_LSC 0x1 /* AUTO_NEG Vendor Tx LSC */ -#define IXGBE_MDIO_AUTO_NEG_ADVT 0x10 /* AUTO_NEG Advt Reg */ -#define IXGBE_MDIO_AUTO_NEG_LP 0x13 /* AUTO_NEG LP Status Reg */ #define IXGBE_MDIO_AUTO_NEG_EEE_ADVT 0x3C /* AUTO_NEG EEE Advt Reg */ #define IXGBE_MDIO_PHY_SET_LOW_POWER_MODE 0x0800 /* Set low power mode */ @@ -1393,8 +1379,10 @@ struct ixgbe_thermal_sensor_data { #define TN1010_PHY_ID 0x00A19410 #define TNX_FW_REV 0xB #define X540_PHY_ID 0x01540200 -#define X550_PHY_ID 0x01540220 +#define X550_PHY_ID2 0x01540223 +#define X550_PHY_ID3 0x01540221 #define X557_PHY_ID 0x01540240 +#define X557_PHY_ID2 0x01540250 #define QT2022_PHY_ID 0x0043A400 #define ATH_PHY_ID 0x03429050 #define AQ_FW_REV 0x20 @@ -1513,6 +1501,8 @@ enum { #define IXGBE_VT_CTL_POOL_MASK (0x3F << IXGBE_VT_CTL_POOL_SHIFT) /* VMOLR bitmasks */ +#define IXGBE_VMOLR_UPE 0x00400000 /* unicast promiscuous */ +#define IXGBE_VMOLR_VPE 0x00800000 /* VLAN promiscuous */ #define IXGBE_VMOLR_AUPE 0x01000000 /* accept untagged packets */ #define IXGBE_VMOLR_ROMPE 0x02000000 /* accept packets in MTA tbl */ #define IXGBE_VMOLR_ROPE 0x04000000 /* accept packets in UC tbl */ @@ -1928,6 +1918,7 @@ enum { #define IXGBE_LINKS_SPEED_10G_82599 0x30000000 #define IXGBE_LINKS_SPEED_1G_82599 0x20000000 #define IXGBE_LINKS_SPEED_100_82599 0x10000000 +#define IXGBE_LINKS_SPEED_10_X550EM_A 0 #define IXGBE_LINK_UP_TIME 90 /* 9.0 Seconds */ #define IXGBE_AUTO_NEG_TIME 45 /* 4.5 Seconds */ @@ -2633,6 +2624,7 @@ enum ixgbe_fdir_pballoc_type { #define FW_CEM_UNUSED_VER 0x0 #define FW_CEM_MAX_RETRIES 3 #define FW_CEM_RESP_STATUS_SUCCESS 0x1 +#define FW_CEM_DRIVER_VERSION_SIZE 39 /* +9 would send 48 bytes to fw */ #define FW_READ_SHADOW_RAM_CMD 0x31 #define FW_READ_SHADOW_RAM_LEN 0x6 #define FW_WRITE_SHADOW_RAM_CMD 0x33 @@ -2658,6 +2650,59 @@ enum ixgbe_fdir_pballoc_type { #define FW_INT_PHY_REQ_LEN 10 #define FW_INT_PHY_REQ_READ 0 #define FW_INT_PHY_REQ_WRITE 1 +#define FW_PHY_ACT_REQ_CMD 5 +#define FW_PHY_ACT_DATA_COUNT 4 +#define FW_PHY_ACT_REQ_LEN (4 + 4 * FW_PHY_ACT_DATA_COUNT) +#define FW_PHY_ACT_INIT_PHY 1 +#define FW_PHY_ACT_SETUP_LINK 2 +#define FW_PHY_ACT_LINK_SPEED_10 BIT(0) +#define FW_PHY_ACT_LINK_SPEED_100 BIT(1) +#define FW_PHY_ACT_LINK_SPEED_1G BIT(2) +#define FW_PHY_ACT_LINK_SPEED_2_5G BIT(3) +#define FW_PHY_ACT_LINK_SPEED_5G BIT(4) +#define FW_PHY_ACT_LINK_SPEED_10G BIT(5) +#define FW_PHY_ACT_LINK_SPEED_20G BIT(6) +#define FW_PHY_ACT_LINK_SPEED_25G BIT(7) +#define FW_PHY_ACT_LINK_SPEED_40G BIT(8) +#define FW_PHY_ACT_LINK_SPEED_50G BIT(9) +#define FW_PHY_ACT_LINK_SPEED_100G BIT(10) +#define FW_PHY_ACT_SETUP_LINK_PAUSE_SHIFT 16 +#define FW_PHY_ACT_SETUP_LINK_PAUSE_MASK (3 << \ + HW_PHY_ACT_SETUP_LINK_PAUSE_SHIFT) +#define FW_PHY_ACT_SETUP_LINK_PAUSE_NONE 0u +#define FW_PHY_ACT_SETUP_LINK_PAUSE_TX 1u +#define FW_PHY_ACT_SETUP_LINK_PAUSE_RX 2u +#define FW_PHY_ACT_SETUP_LINK_PAUSE_RXTX 3u +#define FW_PHY_ACT_SETUP_LINK_LP BIT(18) +#define FW_PHY_ACT_SETUP_LINK_HP BIT(19) +#define FW_PHY_ACT_SETUP_LINK_EEE BIT(20) +#define FW_PHY_ACT_SETUP_LINK_AN BIT(22) +#define FW_PHY_ACT_SETUP_LINK_RSP_DOWN BIT(0) +#define FW_PHY_ACT_GET_LINK_INFO 3 +#define FW_PHY_ACT_GET_LINK_INFO_EEE BIT(19) +#define FW_PHY_ACT_GET_LINK_INFO_FC_TX BIT(20) +#define FW_PHY_ACT_GET_LINK_INFO_FC_RX BIT(21) +#define FW_PHY_ACT_GET_LINK_INFO_POWER BIT(22) +#define FW_PHY_ACT_GET_LINK_INFO_AN_COMPLETE BIT(24) +#define FW_PHY_ACT_GET_LINK_INFO_TEMP BIT(25) +#define FW_PHY_ACT_GET_LINK_INFO_LP_FC_TX BIT(28) +#define FW_PHY_ACT_GET_LINK_INFO_LP_FC_RX BIT(29) +#define FW_PHY_ACT_FORCE_LINK_DOWN 4 +#define FW_PHY_ACT_FORCE_LINK_DOWN_OFF BIT(0) +#define FW_PHY_ACT_PHY_SW_RESET 5 +#define FW_PHY_ACT_PHY_HW_RESET 6 +#define FW_PHY_ACT_GET_PHY_INFO 7 +#define FW_PHY_ACT_UD_2 0x1002 +#define FW_PHY_ACT_UD_2_10G_KR_EEE BIT(6) +#define FW_PHY_ACT_UD_2_10G_KX4_EEE BIT(5) +#define FW_PHY_ACT_UD_2_1G_KX_EEE BIT(4) +#define FW_PHY_ACT_UD_2_10G_T_EEE BIT(3) +#define FW_PHY_ACT_UD_2_1G_T_EEE BIT(2) +#define FW_PHY_ACT_UD_2_100M_TX_EEE BIT(1) +#define FW_PHY_ACT_RETRIES 50 +#define FW_PHY_INFO_SPEED_MASK 0xFFFu +#define FW_PHY_INFO_ID_HI_MASK 0xFFFF0000u +#define FW_PHY_INFO_ID_LO_MASK 0x0000FFFFu /* Host Interface Command Structures */ struct ixgbe_hic_hdr { @@ -2700,6 +2745,16 @@ struct ixgbe_hic_drv_info { u16 pad2; /* end spacing to ensure length is mult. of dword2 */ }; +struct ixgbe_hic_drv_info2 { + struct ixgbe_hic_hdr hdr; + u8 port_num; + u8 ver_sub; + u8 ver_build; + u8 ver_min; + u8 ver_maj; + char driver_string[FW_CEM_DRIVER_VERSION_SIZE]; +}; + /* These need to be dword aligned */ struct ixgbe_hic_read_shadow_ram { union ixgbe_hic_hdr2 hdr; @@ -2748,6 +2803,19 @@ struct ixgbe_hic_internal_phy_resp { __be32 read_data; }; +struct ixgbe_hic_phy_activity_req { + struct ixgbe_hic_hdr hdr; + u8 port_number; + u8 pad; + __le16 activity_id; + __be32 data[FW_PHY_ACT_DATA_COUNT]; +}; + +struct ixgbe_hic_phy_activity_resp { + struct ixgbe_hic_hdr hdr; + __be32 data[FW_PHY_ACT_DATA_COUNT]; +}; + /* Transmit Descriptor - Advanced */ union ixgbe_adv_tx_desc { struct { @@ -2863,6 +2931,7 @@ typedef u32 ixgbe_autoneg_advertised; /* Link speed */ typedef u32 ixgbe_link_speed; #define IXGBE_LINK_SPEED_UNKNOWN 0 +#define IXGBE_LINK_SPEED_10_FULL 0x0002 #define IXGBE_LINK_SPEED_100_FULL 0x0008 #define IXGBE_LINK_SPEED_1GB_FULL 0x0020 #define IXGBE_LINK_SPEED_2_5GB_FULL 0x0400 @@ -3078,6 +3147,7 @@ enum ixgbe_phy_type { ixgbe_phy_qsfp_unknown, ixgbe_phy_sfp_unsupported, ixgbe_phy_sgmii, + ixgbe_phy_fw, ixgbe_phy_generic }; @@ -3352,6 +3422,7 @@ struct ixgbe_mac_operations { s32 (*led_off)(struct ixgbe_hw *, u32); s32 (*blink_led_start)(struct ixgbe_hw *, u32); s32 (*blink_led_stop)(struct ixgbe_hw *, u32); + s32 (*init_led_link_act)(struct ixgbe_hw *); /* RAR, Multicast, VLAN */ s32 (*set_rar)(struct ixgbe_hw *, u32, u8 *, u32, u32); @@ -3372,9 +3443,11 @@ struct ixgbe_mac_operations { /* Flow Control */ s32 (*fc_enable)(struct ixgbe_hw *); s32 (*setup_fc)(struct ixgbe_hw *); + void (*fc_autoneg)(struct ixgbe_hw *); /* Manageability interface */ - s32 (*set_fw_drv_ver)(struct ixgbe_hw *, u8, u8, u8, u8); + s32 (*set_fw_drv_ver)(struct ixgbe_hw *, u8, u8, u8, u8, u16, + const char *); s32 (*get_thermal_sensor_data)(struct ixgbe_hw *); s32 (*init_thermal_sensor_thresh)(struct ixgbe_hw *hw); void (*disable_rx)(struct ixgbe_hw *hw); @@ -3404,22 +3477,33 @@ struct ixgbe_phy_operations { s32 (*setup_internal_link)(struct ixgbe_hw *); s32 (*setup_link_speed)(struct ixgbe_hw *, ixgbe_link_speed, bool); s32 (*check_link)(struct ixgbe_hw *, ixgbe_link_speed *, bool *); - s32 (*get_firmware_version)(struct ixgbe_hw *, u16 *); s32 (*read_i2c_byte)(struct ixgbe_hw *, u8, u8, u8 *); s32 (*write_i2c_byte)(struct ixgbe_hw *, u8, u8, u8); s32 (*read_i2c_sff8472)(struct ixgbe_hw *, u8 , u8 *); s32 (*read_i2c_eeprom)(struct ixgbe_hw *, u8 , u8 *); s32 (*write_i2c_eeprom)(struct ixgbe_hw *, u8, u8); - s32 (*read_i2c_combined)(struct ixgbe_hw *, u8 addr, u16 reg, u16 *val); - s32 (*write_i2c_combined)(struct ixgbe_hw *, u8 addr, u16 reg, u16 val); s32 (*check_overtemp)(struct ixgbe_hw *); s32 (*set_phy_power)(struct ixgbe_hw *, bool on); s32 (*enter_lplu)(struct ixgbe_hw *); s32 (*handle_lasi)(struct ixgbe_hw *hw); - s32 (*read_i2c_combined_unlocked)(struct ixgbe_hw *, u8 addr, u16 reg, - u16 *value); - s32 (*write_i2c_combined_unlocked)(struct ixgbe_hw *, u8 addr, u16 reg, - u16 value); + s32 (*read_i2c_byte_unlocked)(struct ixgbe_hw *, u8 offset, u8 addr, + u8 *value); + s32 (*write_i2c_byte_unlocked)(struct ixgbe_hw *, u8 offset, u8 addr, + u8 value); +}; + +struct ixgbe_link_operations { + s32 (*read_link)(struct ixgbe_hw *, u8 addr, u16 reg, u16 *val); + s32 (*read_link_unlocked)(struct ixgbe_hw *, u8 addr, u16 reg, + u16 *val); + s32 (*write_link)(struct ixgbe_hw *, u8 addr, u16 reg, u16 val); + s32 (*write_link_unlocked)(struct ixgbe_hw *, u8 addr, u16 reg, + u16 val); +}; + +struct ixgbe_link_info { + struct ixgbe_link_operations ops; + u8 addr; }; struct ixgbe_eeprom_info { @@ -3462,6 +3546,7 @@ struct ixgbe_mac_info { u8 san_mac_rar_index; struct ixgbe_thermal_sensor_data thermal_sensor_data; bool set_lben; + u8 led_link_act; }; struct ixgbe_phy_info { @@ -3477,6 +3562,8 @@ struct ixgbe_phy_info { bool reset_disable; ixgbe_autoneg_advertised autoneg_advertised; ixgbe_link_speed speeds_supported; + ixgbe_link_speed eee_speeds_supported; + ixgbe_link_speed eee_speeds_advertised; enum ixgbe_smart_speed smart_speed; bool smart_speed_active; bool multispeed_fiber; @@ -3523,6 +3610,7 @@ struct ixgbe_hw { struct ixgbe_addr_filter_info addr_ctrl; struct ixgbe_fc_info fc; struct ixgbe_phy_info phy; + struct ixgbe_link_info link; struct ixgbe_eeprom_info eeprom; struct ixgbe_bus_info bus; struct ixgbe_mbx_info mbx; @@ -3546,6 +3634,7 @@ struct ixgbe_info { const struct ixgbe_eeprom_operations *eeprom_ops; const struct ixgbe_phy_operations *phy_ops; const struct ixgbe_mbx_operations *mbx_ops; + const struct ixgbe_link_operations *link_ops; const u32 *mvals; }; @@ -3593,17 +3682,35 @@ struct ixgbe_info { #define IXGBE_FUSES0_REV_MASK (3u << 6) #define IXGBE_KRM_PORT_CAR_GEN_CTRL(P) ((P) ? 0x8010 : 0x4010) +#define IXGBE_KRM_LINK_S1(P) ((P) ? 0x8200 : 0x4200) #define IXGBE_KRM_LINK_CTRL_1(P) ((P) ? 0x820C : 0x420C) #define IXGBE_KRM_AN_CNTL_1(P) ((P) ? 0x822C : 0x422C) #define IXGBE_KRM_AN_CNTL_8(P) ((P) ? 0x8248 : 0x4248) #define IXGBE_KRM_SGMII_CTRL(P) ((P) ? 0x82A0 : 0x42A0) +#define IXGBE_KRM_LP_BASE_PAGE_HIGH(P) ((P) ? 0x836C : 0x436C) #define IXGBE_KRM_DSP_TXFFE_STATE_4(P) ((P) ? 0x8634 : 0x4634) #define IXGBE_KRM_DSP_TXFFE_STATE_5(P) ((P) ? 0x8638 : 0x4638) #define IXGBE_KRM_RX_TRN_LINKUP_CTRL(P) ((P) ? 0x8B00 : 0x4B00) #define IXGBE_KRM_PMD_DFX_BURNIN(P) ((P) ? 0x8E00 : 0x4E00) +#define IXGBE_KRM_PMD_FLX_MASK_ST20(P) ((P) ? 0x9054 : 0x5054) #define IXGBE_KRM_TX_COEFF_CTRL_1(P) ((P) ? 0x9520 : 0x5520) #define IXGBE_KRM_RX_ANA_CTL(P) ((P) ? 0x9A00 : 0x5A00) +#define IXGBE_KRM_PMD_FLX_MASK_ST20_SFI_10G_DA ~(0x3 << 20) +#define IXGBE_KRM_PMD_FLX_MASK_ST20_SFI_10G_SR BIT(20) +#define IXGBE_KRM_PMD_FLX_MASK_ST20_SFI_10G_LR (0x2 << 20) +#define IXGBE_KRM_PMD_FLX_MASK_ST20_SGMII_EN BIT(25) +#define IXGBE_KRM_PMD_FLX_MASK_ST20_AN37_EN BIT(26) +#define IXGBE_KRM_PMD_FLX_MASK_ST20_AN_EN BIT(27) +#define IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_10M ~(0x7 << 28) +#define IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_100M BIT(28) +#define IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_1G (0x2 << 28) +#define IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_10G (0x3 << 28) +#define IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_AN (0x4 << 28) +#define IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_2_5G (0x7 << 28) +#define IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_MASK (0x7 << 28) +#define IXGBE_KRM_PMD_FLX_MASK_ST20_FW_AN_RESTART BIT(31) + #define IXGBE_KRM_PORT_CAR_GEN_CTRL_NELB_32B BIT(9) #define IXGBE_KRM_PORT_CAR_GEN_CTRL_NELB_KRPCS BIT(11) @@ -3618,6 +3725,7 @@ struct ixgbe_info { #define IXGBE_KRM_LINK_CTRL_1_TETH_AN_CAP_KR BIT(18) #define IXGBE_KRM_LINK_CTRL_1_TETH_EEE_CAP_KX BIT(24) #define IXGBE_KRM_LINK_CTRL_1_TETH_EEE_CAP_KR BIT(26) +#define IXGBE_KRM_LINK_S1_MAC_AN_COMPLETE BIT(28) #define IXGBE_KRM_LINK_CTRL_1_TETH_AN_ENABLE BIT(29) #define IXGBE_KRM_LINK_CTRL_1_TETH_AN_RESTART BIT(31) @@ -3627,6 +3735,8 @@ struct ixgbe_info { #define IXGBE_KRM_AN_CNTL_8_LINEAR BIT(0) #define IXGBE_KRM_AN_CNTL_8_LIMITING BIT(1) +#define IXGBE_KRM_LP_BASE_PAGE_HIGH_SYM_PAUSE BIT(10) +#define IXGBE_KRM_LP_BASE_PAGE_HIGH_ASM_PAUSE BIT(11) #define IXGBE_KRM_SGMII_CTRL_MAC_TAR_FORCE_100_D BIT(12) #define IXGBE_KRM_SGMII_CTRL_MAC_TAR_FORCE_10_D BIT(19) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c index f2b1d48a16c3..84a467a8ed3d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c @@ -780,8 +780,10 @@ s32 ixgbe_blink_led_start_X540(struct ixgbe_hw *hw, u32 index) ixgbe_link_speed speed; bool link_up; - /* - * Link should be up in order for the blink bit in the LED control + if (index > 3) + return IXGBE_ERR_PARAM; + + /* Link should be up in order for the blink bit in the LED control * register to work. Force link and speed in the MAC if link is down. * This will be reversed when we stop the blinking. */ @@ -814,6 +816,9 @@ s32 ixgbe_blink_led_stop_X540(struct ixgbe_hw *hw, u32 index) u32 macc_reg; u32 ledctl_reg; + if (index > 3) + return IXGBE_ERR_PARAM; + /* Restore the LED to its default value. */ ledctl_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL); ledctl_reg &= ~IXGBE_LED_MODE_MASK(index); @@ -851,6 +856,7 @@ static const struct ixgbe_mac_operations mac_ops_X540 = { .get_link_capabilities = &ixgbe_get_copper_link_capabilities_generic, .led_on = &ixgbe_led_on_generic, .led_off = &ixgbe_led_off_generic, + .init_led_link_act = ixgbe_init_led_link_act_generic, .blink_led_start = &ixgbe_blink_led_start_X540, .blink_led_stop = &ixgbe_blink_led_stop_X540, .set_rar = &ixgbe_set_rar_generic, @@ -866,6 +872,7 @@ static const struct ixgbe_mac_operations mac_ops_X540 = { .set_vfta = &ixgbe_set_vfta_generic, .fc_enable = &ixgbe_fc_enable_generic, .setup_fc = ixgbe_setup_fc_generic, + .fc_autoneg = ixgbe_fc_autoneg, .set_fw_drv_ver = &ixgbe_set_fw_drv_ver_generic, .init_uta_tables = &ixgbe_init_uta_tables_generic, .setup_sfp = NULL, @@ -911,7 +918,6 @@ static const struct ixgbe_phy_operations phy_ops_X540 = { .write_i2c_eeprom = &ixgbe_write_i2c_eeprom_generic, .check_overtemp = &ixgbe_tn_check_overtemp, .set_phy_power = &ixgbe_set_copper_phy_power, - .get_firmware_version = &ixgbe_get_phy_firmware_version_generic, }; static const u32 ixgbe_mvals_X540[IXGBE_MVALS_IDX_LIMIT] = { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index 7e6b9267ca9d..200f847fd8f3 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -28,11 +28,31 @@ static s32 ixgbe_setup_kr_speed_x550em(struct ixgbe_hw *, ixgbe_link_speed); static s32 ixgbe_setup_fc_x550em(struct ixgbe_hw *); +static void ixgbe_fc_autoneg_fiber_x550em_a(struct ixgbe_hw *); +static void ixgbe_fc_autoneg_backplane_x550em_a(struct ixgbe_hw *); +static s32 ixgbe_setup_fc_backplane_x550em_a(struct ixgbe_hw *); static s32 ixgbe_get_invariants_X550_x(struct ixgbe_hw *hw) { struct ixgbe_mac_info *mac = &hw->mac; struct ixgbe_phy_info *phy = &hw->phy; + struct ixgbe_link_info *link = &hw->link; + + /* Start with X540 invariants, since so simular */ + ixgbe_get_invariants_X540(hw); + + if (mac->ops.get_media_type(hw) != ixgbe_media_type_copper) + phy->ops.set_phy_power = NULL; + + link->addr = IXGBE_CS4227; + + return 0; +} + +static s32 ixgbe_get_invariants_X550_a(struct ixgbe_hw *hw) +{ + struct ixgbe_mac_info *mac = &hw->mac; + struct ixgbe_phy_info *phy = &hw->phy; /* Start with X540 invariants, since so simular */ ixgbe_get_invariants_X540(hw); @@ -43,6 +63,18 @@ static s32 ixgbe_get_invariants_X550_x(struct ixgbe_hw *hw) return 0; } +static s32 ixgbe_get_invariants_X550_a_fw(struct ixgbe_hw *hw) +{ + struct ixgbe_phy_info *phy = &hw->phy; + + /* Start with X540 invariants, since so similar */ + ixgbe_get_invariants_X540(hw); + + phy->ops.set_phy_power = NULL; + + return 0; +} + /** ixgbe_setup_mux_ctl - Setup ESDP register for I2C mux control * @hw: pointer to hardware structure **/ @@ -69,8 +101,7 @@ static void ixgbe_setup_mux_ctl(struct ixgbe_hw *hw) */ static s32 ixgbe_read_cs4227(struct ixgbe_hw *hw, u16 reg, u16 *value) { - return hw->phy.ops.read_i2c_combined_unlocked(hw, IXGBE_CS4227, reg, - value); + return hw->link.ops.read_link_unlocked(hw, hw->link.addr, reg, value); } /** @@ -83,8 +114,7 @@ static s32 ixgbe_read_cs4227(struct ixgbe_hw *hw, u16 reg, u16 *value) */ static s32 ixgbe_write_cs4227(struct ixgbe_hw *hw, u16 reg, u16 value) { - return hw->phy.ops.write_i2c_combined_unlocked(hw, IXGBE_CS4227, reg, - value); + return hw->link.ops.write_link_unlocked(hw, hw->link.addr, reg, value); } /** @@ -322,6 +352,266 @@ static s32 ixgbe_write_phy_reg_x550em(struct ixgbe_hw *hw, u32 reg_addr, return IXGBE_NOT_IMPLEMENTED; } +/** + * ixgbe_read_i2c_combined_generic - Perform I2C read combined operation + * @hw: pointer to the hardware structure + * @addr: I2C bus address to read from + * @reg: I2C device register to read from + * @val: pointer to location to receive read value + * + * Returns an error code on error. + **/ +static s32 ixgbe_read_i2c_combined_generic(struct ixgbe_hw *hw, u8 addr, + u16 reg, u16 *val) +{ + return ixgbe_read_i2c_combined_generic_int(hw, addr, reg, val, true); +} + +/** + * ixgbe_read_i2c_combined_generic_unlocked - Do I2C read combined operation + * @hw: pointer to the hardware structure + * @addr: I2C bus address to read from + * @reg: I2C device register to read from + * @val: pointer to location to receive read value + * + * Returns an error code on error. + **/ +static s32 +ixgbe_read_i2c_combined_generic_unlocked(struct ixgbe_hw *hw, u8 addr, + u16 reg, u16 *val) +{ + return ixgbe_read_i2c_combined_generic_int(hw, addr, reg, val, false); +} + +/** + * ixgbe_write_i2c_combined_generic - Perform I2C write combined operation + * @hw: pointer to the hardware structure + * @addr: I2C bus address to write to + * @reg: I2C device register to write to + * @val: value to write + * + * Returns an error code on error. + **/ +static s32 ixgbe_write_i2c_combined_generic(struct ixgbe_hw *hw, + u8 addr, u16 reg, u16 val) +{ + return ixgbe_write_i2c_combined_generic_int(hw, addr, reg, val, true); +} + +/** + * ixgbe_write_i2c_combined_generic_unlocked - Do I2C write combined operation + * @hw: pointer to the hardware structure + * @addr: I2C bus address to write to + * @reg: I2C device register to write to + * @val: value to write + * + * Returns an error code on error. + **/ +static s32 +ixgbe_write_i2c_combined_generic_unlocked(struct ixgbe_hw *hw, + u8 addr, u16 reg, u16 val) +{ + return ixgbe_write_i2c_combined_generic_int(hw, addr, reg, val, false); +} + +/** + * ixgbe_fw_phy_activity - Perform an activity on a PHY + * @hw: pointer to hardware structure + * @activity: activity to perform + * @data: Pointer to 4 32-bit words of data + */ +s32 ixgbe_fw_phy_activity(struct ixgbe_hw *hw, u16 activity, + u32 (*data)[FW_PHY_ACT_DATA_COUNT]) +{ + union { + struct ixgbe_hic_phy_activity_req cmd; + struct ixgbe_hic_phy_activity_resp rsp; + } hic; + u16 retries = FW_PHY_ACT_RETRIES; + s32 rc; + u32 i; + + do { + memset(&hic, 0, sizeof(hic)); + hic.cmd.hdr.cmd = FW_PHY_ACT_REQ_CMD; + hic.cmd.hdr.buf_len = FW_PHY_ACT_REQ_LEN; + hic.cmd.hdr.checksum = FW_DEFAULT_CHECKSUM; + hic.cmd.port_number = hw->bus.lan_id; + hic.cmd.activity_id = cpu_to_le16(activity); + for (i = 0; i < ARRAY_SIZE(hic.cmd.data); ++i) + hic.cmd.data[i] = cpu_to_be32((*data)[i]); + + rc = ixgbe_host_interface_command(hw, &hic.cmd, sizeof(hic.cmd), + IXGBE_HI_COMMAND_TIMEOUT, + true); + if (rc) + return rc; + if (hic.rsp.hdr.cmd_or_resp.ret_status == + FW_CEM_RESP_STATUS_SUCCESS) { + for (i = 0; i < FW_PHY_ACT_DATA_COUNT; ++i) + (*data)[i] = be32_to_cpu(hic.rsp.data[i]); + return 0; + } + usleep_range(20, 30); + --retries; + } while (retries > 0); + + return IXGBE_ERR_HOST_INTERFACE_COMMAND; +} + +static const struct { + u16 fw_speed; + ixgbe_link_speed phy_speed; +} ixgbe_fw_map[] = { + { FW_PHY_ACT_LINK_SPEED_10, IXGBE_LINK_SPEED_10_FULL }, + { FW_PHY_ACT_LINK_SPEED_100, IXGBE_LINK_SPEED_100_FULL }, + { FW_PHY_ACT_LINK_SPEED_1G, IXGBE_LINK_SPEED_1GB_FULL }, + { FW_PHY_ACT_LINK_SPEED_2_5G, IXGBE_LINK_SPEED_2_5GB_FULL }, + { FW_PHY_ACT_LINK_SPEED_5G, IXGBE_LINK_SPEED_5GB_FULL }, + { FW_PHY_ACT_LINK_SPEED_10G, IXGBE_LINK_SPEED_10GB_FULL }, +}; + +/** + * ixgbe_get_phy_id_fw - Get the phy ID via firmware command + * @hw: pointer to hardware structure + * + * Returns error code + */ +static s32 ixgbe_get_phy_id_fw(struct ixgbe_hw *hw) +{ + u32 info[FW_PHY_ACT_DATA_COUNT] = { 0 }; + u16 phy_speeds; + u16 phy_id_lo; + s32 rc; + u16 i; + + if (hw->phy.id) + return 0; + + rc = ixgbe_fw_phy_activity(hw, FW_PHY_ACT_GET_PHY_INFO, &info); + if (rc) + return rc; + + hw->phy.speeds_supported = 0; + phy_speeds = info[0] & FW_PHY_INFO_SPEED_MASK; + for (i = 0; i < ARRAY_SIZE(ixgbe_fw_map); ++i) { + if (phy_speeds & ixgbe_fw_map[i].fw_speed) + hw->phy.speeds_supported |= ixgbe_fw_map[i].phy_speed; + } + + hw->phy.id = info[0] & FW_PHY_INFO_ID_HI_MASK; + phy_id_lo = info[1] & FW_PHY_INFO_ID_LO_MASK; + hw->phy.id |= phy_id_lo & IXGBE_PHY_REVISION_MASK; + hw->phy.revision = phy_id_lo & ~IXGBE_PHY_REVISION_MASK; + if (!hw->phy.id || hw->phy.id == IXGBE_PHY_REVISION_MASK) + return IXGBE_ERR_PHY_ADDR_INVALID; + + hw->phy.autoneg_advertised = hw->phy.speeds_supported; + hw->phy.eee_speeds_supported = IXGBE_LINK_SPEED_100_FULL | + IXGBE_LINK_SPEED_1GB_FULL; + hw->phy.eee_speeds_advertised = hw->phy.eee_speeds_supported; + return 0; +} + +/** + * ixgbe_identify_phy_fw - Get PHY type based on firmware command + * @hw: pointer to hardware structure + * + * Returns error code + */ +static s32 ixgbe_identify_phy_fw(struct ixgbe_hw *hw) +{ + if (hw->bus.lan_id) + hw->phy.phy_semaphore_mask = IXGBE_GSSR_PHY1_SM; + else + hw->phy.phy_semaphore_mask = IXGBE_GSSR_PHY0_SM; + + hw->phy.type = ixgbe_phy_fw; + hw->phy.ops.read_reg = NULL; + hw->phy.ops.write_reg = NULL; + return ixgbe_get_phy_id_fw(hw); +} + +/** + * ixgbe_shutdown_fw_phy - Shutdown a firmware-controlled PHY + * @hw: pointer to hardware structure + * + * Returns error code + */ +static s32 ixgbe_shutdown_fw_phy(struct ixgbe_hw *hw) +{ + u32 setup[FW_PHY_ACT_DATA_COUNT] = { 0 }; + + setup[0] = FW_PHY_ACT_FORCE_LINK_DOWN_OFF; + return ixgbe_fw_phy_activity(hw, FW_PHY_ACT_FORCE_LINK_DOWN, &setup); +} + +/** + * ixgbe_setup_fw_link - Setup firmware-controlled PHYs + * @hw: pointer to hardware structure + */ +static s32 ixgbe_setup_fw_link(struct ixgbe_hw *hw) +{ + u32 setup[FW_PHY_ACT_DATA_COUNT] = { 0 }; + s32 rc; + u16 i; + + if (hw->phy.reset_disable || ixgbe_check_reset_blocked(hw)) + return 0; + + if (hw->fc.strict_ieee && hw->fc.requested_mode == ixgbe_fc_rx_pause) { + hw_err(hw, "rx_pause not valid in strict IEEE mode\n"); + return IXGBE_ERR_INVALID_LINK_SETTINGS; + } + + switch (hw->fc.requested_mode) { + case ixgbe_fc_full: + setup[0] |= FW_PHY_ACT_SETUP_LINK_PAUSE_RXTX << + FW_PHY_ACT_SETUP_LINK_PAUSE_SHIFT; + break; + case ixgbe_fc_rx_pause: + setup[0] |= FW_PHY_ACT_SETUP_LINK_PAUSE_RX << + FW_PHY_ACT_SETUP_LINK_PAUSE_SHIFT; + break; + case ixgbe_fc_tx_pause: + setup[0] |= FW_PHY_ACT_SETUP_LINK_PAUSE_TX << + FW_PHY_ACT_SETUP_LINK_PAUSE_SHIFT; + break; + default: + break; + } + + for (i = 0; i < ARRAY_SIZE(ixgbe_fw_map); ++i) { + if (hw->phy.autoneg_advertised & ixgbe_fw_map[i].phy_speed) + setup[0] |= ixgbe_fw_map[i].fw_speed; + } + setup[0] |= FW_PHY_ACT_SETUP_LINK_HP | FW_PHY_ACT_SETUP_LINK_AN; + + if (hw->phy.eee_speeds_advertised) + setup[0] |= FW_PHY_ACT_SETUP_LINK_EEE; + + rc = ixgbe_fw_phy_activity(hw, FW_PHY_ACT_SETUP_LINK, &setup); + if (rc) + return rc; + if (setup[0] == FW_PHY_ACT_SETUP_LINK_RSP_DOWN) + return IXGBE_ERR_OVERTEMP; + return 0; +} + +/** + * ixgbe_fc_autoneg_fw - Set up flow control for FW-controlled PHYs + * @hw: pointer to hardware structure + * + * Called at init time to set up flow control. + */ +static s32 ixgbe_fc_autoneg_fw(struct ixgbe_hw *hw) +{ + if (hw->fc.requested_mode == ixgbe_fc_default) + hw->fc.requested_mode = ixgbe_fc_full; + + return ixgbe_setup_fw_link(hw); +} + /** ixgbe_init_eeprom_params_X550 - Initialize EEPROM params * @hw: pointer to hardware structure * @@ -544,41 +834,6 @@ static s32 ixgbe_read_iosf_sb_reg_x550a(struct ixgbe_hw *hw, u32 reg_addr, return status; } -/** ixgbe_read_ee_hostif_data_X550 - Read EEPROM word using a host interface - * command assuming that the semaphore is already obtained. - * @hw: pointer to hardware structure - * @offset: offset of word in the EEPROM to read - * @data: word read from the EEPROM - * - * Reads a 16 bit word from the EEPROM using the hostif. - **/ -static s32 ixgbe_read_ee_hostif_data_X550(struct ixgbe_hw *hw, u16 offset, - u16 *data) -{ - s32 status; - struct ixgbe_hic_read_shadow_ram buffer; - - buffer.hdr.req.cmd = FW_READ_SHADOW_RAM_CMD; - buffer.hdr.req.buf_lenh = 0; - buffer.hdr.req.buf_lenl = FW_READ_SHADOW_RAM_LEN; - buffer.hdr.req.checksum = FW_DEFAULT_CHECKSUM; - - /* convert offset from words to bytes */ - buffer.address = cpu_to_be32(offset * 2); - /* one word */ - buffer.length = cpu_to_be16(sizeof(u16)); - - status = ixgbe_host_interface_command(hw, &buffer, sizeof(buffer), - IXGBE_HI_COMMAND_TIMEOUT, false); - if (status) - return status; - - *data = (u16)IXGBE_READ_REG_ARRAY(hw, IXGBE_FLEX_MNG, - FW_NVM_DATA_OFFSET); - - return 0; -} - /** ixgbe_read_ee_hostif_buffer_X550- Read EEPROM word(s) using hostif * @hw: pointer to hardware structure * @offset: offset of word in the EEPROM to read @@ -590,6 +845,7 @@ static s32 ixgbe_read_ee_hostif_data_X550(struct ixgbe_hw *hw, u16 offset, static s32 ixgbe_read_ee_hostif_buffer_X550(struct ixgbe_hw *hw, u16 offset, u16 words, u16 *data) { + const u32 mask = IXGBE_GSSR_SW_MNG_SM | IXGBE_GSSR_EEP_SM; struct ixgbe_hic_read_shadow_ram buffer; u32 current_word = 0; u16 words_to_read; @@ -597,7 +853,7 @@ static s32 ixgbe_read_ee_hostif_buffer_X550(struct ixgbe_hw *hw, u32 i; /* Take semaphore for the entire operation. */ - status = hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM); + status = hw->mac.ops.acquire_swfw_sync(hw, mask); if (status) { hw_dbg(hw, "EEPROM read buffer - semaphore failed\n"); return status; @@ -618,10 +874,8 @@ static s32 ixgbe_read_ee_hostif_buffer_X550(struct ixgbe_hw *hw, buffer.address = cpu_to_be32((offset + current_word) * 2); buffer.length = cpu_to_be16(words_to_read * 2); - status = ixgbe_host_interface_command(hw, &buffer, - sizeof(buffer), - IXGBE_HI_COMMAND_TIMEOUT, - false); + status = ixgbe_hic_unlocked(hw, (u32 *)&buffer, sizeof(buffer), + IXGBE_HI_COMMAND_TIMEOUT); if (status) { hw_dbg(hw, "Host interface command failed\n"); goto out; @@ -645,7 +899,7 @@ static s32 ixgbe_read_ee_hostif_buffer_X550(struct ixgbe_hw *hw, } out: - hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_EEP_SM); + hw->mac.ops.release_swfw_sync(hw, mask); return status; } @@ -816,15 +1070,32 @@ static s32 ixgbe_calc_eeprom_checksum_X550(struct ixgbe_hw *hw) **/ static s32 ixgbe_read_ee_hostif_X550(struct ixgbe_hw *hw, u16 offset, u16 *data) { - s32 status = 0; + const u32 mask = IXGBE_GSSR_SW_MNG_SM | IXGBE_GSSR_EEP_SM; + struct ixgbe_hic_read_shadow_ram buffer; + s32 status; - if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM) == 0) { - status = ixgbe_read_ee_hostif_data_X550(hw, offset, data); - hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_EEP_SM); - } else { - status = IXGBE_ERR_SWFW_SYNC; + buffer.hdr.req.cmd = FW_READ_SHADOW_RAM_CMD; + buffer.hdr.req.buf_lenh = 0; + buffer.hdr.req.buf_lenl = FW_READ_SHADOW_RAM_LEN; + buffer.hdr.req.checksum = FW_DEFAULT_CHECKSUM; + + /* convert offset from words to bytes */ + buffer.address = cpu_to_be32(offset * 2); + /* one word */ + buffer.length = cpu_to_be16(sizeof(u16)); + + status = hw->mac.ops.acquire_swfw_sync(hw, mask); + if (status) + return status; + + status = ixgbe_hic_unlocked(hw, (u32 *)&buffer, sizeof(buffer), + IXGBE_HI_COMMAND_TIMEOUT); + if (!status) { + *data = (u16)IXGBE_READ_REG_ARRAY(hw, IXGBE_FLEX_MNG, + FW_NVM_DATA_OFFSET); } + hw->mac.ops.release_swfw_sync(hw, mask); return status; } @@ -1128,47 +1399,17 @@ out: return ret; } -/** ixgbe_setup_ixfi_x550em - Configure the KR PHY for iXFI mode. +/** + * ixgbe_setup_ixfi_x550em_x - MAC specific iXFI configuration * @hw: pointer to hardware structure - * @speed: the link speed to force * - * Configures the integrated KR PHY to use iXFI mode. Used to connect an - * internal and external PHY at a specific speed, without autonegotiation. + * iXfI configuration needed for ixgbe_mac_X550EM_x devices. **/ -static s32 ixgbe_setup_ixfi_x550em(struct ixgbe_hw *hw, ixgbe_link_speed *speed) +static s32 ixgbe_setup_ixfi_x550em_x(struct ixgbe_hw *hw) { s32 status; u32 reg_val; - /* Disable AN and force speed to 10G Serial. */ - status = ixgbe_read_iosf_sb_reg_x550(hw, - IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val); - if (status) - return status; - - reg_val &= ~IXGBE_KRM_LINK_CTRL_1_TETH_AN_ENABLE; - reg_val &= ~IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_MASK; - - /* Select forced link speed for internal PHY. */ - switch (*speed) { - case IXGBE_LINK_SPEED_10GB_FULL: - reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_10G; - break; - case IXGBE_LINK_SPEED_1GB_FULL: - reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_1G; - break; - default: - /* Other link speeds are not supported by internal KR PHY. */ - return IXGBE_ERR_LINK_SETUP; - } - - status = ixgbe_write_iosf_sb_reg_x550(hw, - IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); - if (status) - return status; - /* Disable training protocol FSM. */ status = ixgbe_read_iosf_sb_reg_x550(hw, IXGBE_KRM_RX_TRN_LINKUP_CTRL(hw->bus.lan_id), @@ -1228,20 +1469,106 @@ static s32 ixgbe_setup_ixfi_x550em(struct ixgbe_hw *hw, ixgbe_link_speed *speed) status = ixgbe_write_iosf_sb_reg_x550(hw, IXGBE_KRM_TX_COEFF_CTRL_1(hw->bus.lan_id), IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); - if (status) + return status; +} + +/** + * ixgbe_restart_an_internal_phy_x550em - restart autonegotiation for the + * internal PHY + * @hw: pointer to hardware structure + **/ +static s32 ixgbe_restart_an_internal_phy_x550em(struct ixgbe_hw *hw) +{ + s32 status; + u32 link_ctrl; + + /* Restart auto-negotiation. */ + status = hw->mac.ops.read_iosf_sb_reg(hw, + IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, &link_ctrl); + + if (status) { + hw_dbg(hw, "Auto-negotiation did not complete\n"); return status; + } - /* Toggle port SW reset by AN reset. */ - status = ixgbe_read_iosf_sb_reg_x550(hw, + link_ctrl |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_RESTART; + status = hw->mac.ops.write_iosf_sb_reg(hw, IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val); + IXGBE_SB_IOSF_TARGET_KR_PHY, link_ctrl); + + if (hw->mac.type == ixgbe_mac_x550em_a) { + u32 flx_mask_st20; + + /* Indicate to FW that AN restart has been asserted */ + status = hw->mac.ops.read_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, &flx_mask_st20); + + if (status) { + hw_dbg(hw, "Auto-negotiation did not complete\n"); + return status; + } + + flx_mask_st20 |= IXGBE_KRM_PMD_FLX_MASK_ST20_FW_AN_RESTART; + status = hw->mac.ops.write_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, flx_mask_st20); + } + + return status; +} + +/** ixgbe_setup_ixfi_x550em - Configure the KR PHY for iXFI mode. + * @hw: pointer to hardware structure + * @speed: the link speed to force + * + * Configures the integrated KR PHY to use iXFI mode. Used to connect an + * internal and external PHY at a specific speed, without autonegotiation. + **/ +static s32 ixgbe_setup_ixfi_x550em(struct ixgbe_hw *hw, ixgbe_link_speed *speed) +{ + s32 status; + u32 reg_val; + + /* Disable AN and force speed to 10G Serial. */ + status = ixgbe_read_iosf_sb_reg_x550(hw, + IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val); if (status) return status; - reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_RESTART; + reg_val &= ~IXGBE_KRM_LINK_CTRL_1_TETH_AN_ENABLE; + reg_val &= ~IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_MASK; + + /* Select forced link speed for internal PHY. */ + switch (*speed) { + case IXGBE_LINK_SPEED_10GB_FULL: + reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_10G; + break; + case IXGBE_LINK_SPEED_1GB_FULL: + reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_1G; + break; + default: + /* Other link speeds are not supported by internal KR PHY. */ + return IXGBE_ERR_LINK_SETUP; + } + status = ixgbe_write_iosf_sb_reg_x550(hw, IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); + if (status) + return status; + + /* Additional configuration needed for x550em_x */ + if (hw->mac.type == ixgbe_mac_X550EM_x) { + status = ixgbe_setup_ixfi_x550em_x(hw); + if (status) + return status; + } + + /* Toggle port SW reset by AN reset. */ + status = ixgbe_restart_an_internal_phy_x550em(hw); return status; } @@ -1292,7 +1619,7 @@ ixgbe_setup_mac_link_sfp_x550em(struct ixgbe_hw *hw, __always_unused bool autoneg_wait_to_complete) { s32 status; - u16 slice, value; + u16 reg_slice, reg_val; bool setup_linear = false; /* Check if SFP module is supported and linear */ @@ -1308,71 +1635,68 @@ ixgbe_setup_mac_link_sfp_x550em(struct ixgbe_hw *hw, if (status) return status; - if (!(hw->phy.nw_mng_if_sel & IXGBE_NW_MNG_IF_SEL_INT_PHY_MODE)) { - /* Configure CS4227 LINE side to 10G SR. */ - slice = IXGBE_CS4227_LINE_SPARE22_MSB + (hw->bus.lan_id << 12); - value = IXGBE_CS4227_SPEED_10G; - status = ixgbe_write_i2c_combined_generic(hw, IXGBE_CS4227, - slice, value); - if (status) - goto i2c_err; + /* Configure internal PHY for KR/KX. */ + ixgbe_setup_kr_speed_x550em(hw, speed); - slice = IXGBE_CS4227_LINE_SPARE24_LSB + (hw->bus.lan_id << 12); - value = (IXGBE_CS4227_EDC_MODE_SR << 1) | 1; - status = ixgbe_write_i2c_combined_generic(hw, IXGBE_CS4227, - slice, value); - if (status) - goto i2c_err; - - /* Configure CS4227 for HOST connection rate then type. */ - slice = IXGBE_CS4227_HOST_SPARE22_MSB + (hw->bus.lan_id << 12); - value = speed & IXGBE_LINK_SPEED_10GB_FULL ? - IXGBE_CS4227_SPEED_10G : IXGBE_CS4227_SPEED_1G; - status = ixgbe_write_i2c_combined_generic(hw, IXGBE_CS4227, - slice, value); - if (status) - goto i2c_err; + /* Configure CS4227 LINE side to proper mode. */ + reg_slice = IXGBE_CS4227_LINE_SPARE24_LSB + (hw->bus.lan_id << 12); + if (setup_linear) + reg_val = (IXGBE_CS4227_EDC_MODE_CX1 << 1) | 0x1; + else + reg_val = (IXGBE_CS4227_EDC_MODE_SR << 1) | 0x1; - slice = IXGBE_CS4227_HOST_SPARE24_LSB + (hw->bus.lan_id << 12); - if (setup_linear) - value = (IXGBE_CS4227_EDC_MODE_CX1 << 1) | 1; - else - value = (IXGBE_CS4227_EDC_MODE_SR << 1) | 1; - status = ixgbe_write_i2c_combined_generic(hw, IXGBE_CS4227, - slice, value); - if (status) - goto i2c_err; + status = hw->link.ops.write_link(hw, hw->link.addr, reg_slice, + reg_val); - /* Setup XFI internal link. */ - status = ixgbe_setup_ixfi_x550em(hw, &speed); - if (status) { - hw_dbg(hw, "setup_ixfi failed with %d\n", status); - return status; - } - } else { - /* Configure internal PHY for KR/KX. */ - status = ixgbe_setup_kr_speed_x550em(hw, speed); - if (status) { - hw_dbg(hw, "setup_kr_speed failed with %d\n", status); - return status; - } + return status; +} - /* Configure CS4227 LINE side to proper mode. */ - slice = IXGBE_CS4227_LINE_SPARE24_LSB + (hw->bus.lan_id << 12); - if (setup_linear) - value = (IXGBE_CS4227_EDC_MODE_CX1 << 1) | 1; - else - value = (IXGBE_CS4227_EDC_MODE_SR << 1) | 1; - status = ixgbe_write_i2c_combined_generic(hw, IXGBE_CS4227, - slice, value); - if (status) - goto i2c_err; +/** + * ixgbe_setup_sfi_x550a - Configure the internal PHY for native SFI mode + * @hw: pointer to hardware structure + * @speed: the link speed to force + * + * Configures the integrated PHY for native SFI mode. Used to connect the + * internal PHY directly to an SFP cage, without autonegotiation. + **/ +static s32 ixgbe_setup_sfi_x550a(struct ixgbe_hw *hw, ixgbe_link_speed *speed) +{ + struct ixgbe_mac_info *mac = &hw->mac; + s32 status; + u32 reg_val; + + /* Disable all AN and force speed to 10G Serial. */ + status = mac->ops.read_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val); + if (status) + return status; + + reg_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_AN_EN; + reg_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_AN37_EN; + reg_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_SGMII_EN; + reg_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_MASK; + + /* Select forced link speed for internal PHY. */ + switch (*speed) { + case IXGBE_LINK_SPEED_10GB_FULL: + reg_val |= IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_10G; + break; + case IXGBE_LINK_SPEED_1GB_FULL: + reg_val |= IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_1G; + break; + default: + /* Other link speeds are not supported by internal PHY. */ + return IXGBE_ERR_LINK_SETUP; } - return 0; + status = mac->ops.write_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); + + /* Toggle port SW reset by AN reset. */ + status = ixgbe_restart_an_internal_phy_x550em(hw); -i2c_err: - hw_dbg(hw, "combined i2c access failed with %d\n", status); return status; } @@ -1388,45 +1712,39 @@ ixgbe_setup_mac_link_sfp_n(struct ixgbe_hw *hw, ixgbe_link_speed speed, { bool setup_linear = false; u32 reg_phy_int; - s32 rc; + s32 ret_val; /* Check if SFP module is supported and linear */ - rc = ixgbe_supported_sfp_modules_X550em(hw, &setup_linear); + ret_val = ixgbe_supported_sfp_modules_X550em(hw, &setup_linear); /* If no SFP module present, then return success. Return success since * SFP not present error is not excepted in the setup MAC link flow. */ - if (rc == IXGBE_ERR_SFP_NOT_PRESENT) + if (ret_val == IXGBE_ERR_SFP_NOT_PRESENT) return 0; - if (!rc) - return rc; + if (!ret_val) + return ret_val; - /* Configure internal PHY for native SFI */ - rc = hw->mac.ops.read_iosf_sb_reg(hw, - IXGBE_KRM_AN_CNTL_8(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, - ®_phy_int); - if (rc) - return rc; + /* Configure internal PHY for native SFI based on module type */ + ret_val = hw->mac.ops.read_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, ®_phy_int); + if (!ret_val) + return ret_val; - if (setup_linear) { - reg_phy_int &= ~IXGBE_KRM_AN_CNTL_8_LIMITING; - reg_phy_int |= IXGBE_KRM_AN_CNTL_8_LINEAR; - } else { - reg_phy_int |= IXGBE_KRM_AN_CNTL_8_LIMITING; - reg_phy_int &= ~IXGBE_KRM_AN_CNTL_8_LINEAR; - } + reg_phy_int &= IXGBE_KRM_PMD_FLX_MASK_ST20_SFI_10G_DA; + if (!setup_linear) + reg_phy_int |= IXGBE_KRM_PMD_FLX_MASK_ST20_SFI_10G_SR; - rc = hw->mac.ops.write_iosf_sb_reg(hw, - IXGBE_KRM_AN_CNTL_8(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, - reg_phy_int); - if (rc) - return rc; + ret_val = hw->mac.ops.write_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, reg_phy_int); + if (!ret_val) + return ret_val; - /* Setup XFI/SFI internal link */ - return ixgbe_setup_ixfi_x550em(hw, &speed); + /* Setup SFI internal link. */ + return ixgbe_setup_sfi_x550a(hw, &speed); } /** @@ -1442,19 +1760,19 @@ ixgbe_setup_mac_link_sfp_x550a(struct ixgbe_hw *hw, ixgbe_link_speed speed, u32 reg_slice, slice_offset; bool setup_linear = false; u16 reg_phy_ext; - s32 rc; + s32 ret_val; /* Check if SFP module is supported and linear */ - rc = ixgbe_supported_sfp_modules_X550em(hw, &setup_linear); + ret_val = ixgbe_supported_sfp_modules_X550em(hw, &setup_linear); /* If no SFP module present, then return success. Return success since * SFP not present error is not excepted in the setup MAC link flow. */ - if (rc == IXGBE_ERR_SFP_NOT_PRESENT) + if (ret_val == IXGBE_ERR_SFP_NOT_PRESENT) return 0; - if (!rc) - return rc; + if (!ret_val) + return ret_val; /* Configure internal PHY for KR/KX. */ ixgbe_setup_kr_speed_x550em(hw, speed); @@ -1463,10 +1781,10 @@ ixgbe_setup_mac_link_sfp_x550a(struct ixgbe_hw *hw, ixgbe_link_speed speed, return IXGBE_ERR_PHY_ADDR_INVALID; /* Get external PHY device id */ - rc = hw->phy.ops.read_reg(hw, IXGBE_CS4227_GLOBAL_ID_MSB, + ret_val = hw->phy.ops.read_reg(hw, IXGBE_CS4227_GLOBAL_ID_MSB, IXGBE_MDIO_ZERO_DEV_TYPE, ®_phy_ext); - if (rc) - return rc; + if (ret_val) + return ret_val; /* When configuring quad port CS4223, the MAC instance is part * of the slice offset. @@ -1538,7 +1856,7 @@ static s32 ixgbe_check_link_t_X550em(struct ixgbe_hw *hw, bool link_up_wait_to_complete) { u32 status; - u16 autoneg_status; + u16 i, autoneg_status; if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_copper) return IXGBE_ERR_CONFIG; @@ -1550,14 +1868,18 @@ static s32 ixgbe_check_link_t_X550em(struct ixgbe_hw *hw, if (status || !(*link_up)) return status; - /* MAC link is up, so check external PHY link. - * Read this twice back to back to indicate current status. - */ - status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_AUTO_NEG_STATUS, - IXGBE_MDIO_AUTO_NEG_DEV_TYPE, - &autoneg_status); - if (status) - return status; + /* MAC link is up, so check external PHY link. + * Link status is latching low, and can only be used to detect link + * drop, and not the current status of the link without performing + * back-to-back reads. + */ + for (i = 0; i < 2; i++) { + status = hw->phy.ops.read_reg(hw, MDIO_STAT1, MDIO_MMD_AN, + &autoneg_status); + + if (status) + return status; + } /* If external PHY link is not up, then indicate link not up */ if (!(autoneg_status & IXGBE_MDIO_AUTO_NEG_LINK_STATUS)) @@ -1575,7 +1897,7 @@ ixgbe_setup_sgmii(struct ixgbe_hw *hw, __always_unused ixgbe_link_speed speed, __always_unused bool autoneg_wait_to_complete) { struct ixgbe_mac_info *mac = &hw->mac; - u32 lval, sval; + u32 lval, sval, flx_val; s32 rc; rc = mac->ops.read_iosf_sb_reg(hw, @@ -1609,12 +1931,183 @@ ixgbe_setup_sgmii(struct ixgbe_hw *hw, __always_unused ixgbe_link_speed speed, if (rc) return rc; - lval |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_RESTART; + rc = mac->ops.read_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, &flx_val); + if (rc) + return rc; + + rc = mac->ops.read_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, &flx_val); + if (rc) + return rc; + + flx_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_MASK; + flx_val |= IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_1G; + flx_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_AN_EN; + flx_val |= IXGBE_KRM_PMD_FLX_MASK_ST20_SGMII_EN; + flx_val |= IXGBE_KRM_PMD_FLX_MASK_ST20_AN37_EN; + + rc = mac->ops.write_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, flx_val); + if (rc) + return rc; + + rc = ixgbe_restart_an_internal_phy_x550em(hw); + return rc; +} + +/** + * ixgbe_setup_sgmii_fw - Set up link for sgmii with firmware-controlled PHYs + * @hw: pointer to hardware structure + */ +static s32 ixgbe_setup_sgmii_fw(struct ixgbe_hw *hw, ixgbe_link_speed speed, + bool autoneg_wait) +{ + struct ixgbe_mac_info *mac = &hw->mac; + u32 lval, sval, flx_val; + s32 rc; + + rc = mac->ops.read_iosf_sb_reg(hw, + IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, &lval); + if (rc) + return rc; + + lval &= ~IXGBE_KRM_LINK_CTRL_1_TETH_AN_ENABLE; + lval &= ~IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_MASK; + lval |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_SGMII_EN; + lval |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_CLAUSE_37_EN; + lval &= ~IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_1G; rc = mac->ops.write_iosf_sb_reg(hw, IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), IXGBE_SB_IOSF_TARGET_KR_PHY, lval); + if (rc) + return rc; - return rc; + rc = mac->ops.read_iosf_sb_reg(hw, + IXGBE_KRM_SGMII_CTRL(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, &sval); + if (rc) + return rc; + + sval &= ~IXGBE_KRM_SGMII_CTRL_MAC_TAR_FORCE_10_D; + sval &= ~IXGBE_KRM_SGMII_CTRL_MAC_TAR_FORCE_100_D; + rc = mac->ops.write_iosf_sb_reg(hw, + IXGBE_KRM_SGMII_CTRL(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, sval); + if (rc) + return rc; + + rc = mac->ops.write_iosf_sb_reg(hw, + IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, lval); + if (rc) + return rc; + + rc = mac->ops.read_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, &flx_val); + if (rc) + return rc; + + flx_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_MASK; + flx_val |= IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_AN; + flx_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_AN_EN; + flx_val |= IXGBE_KRM_PMD_FLX_MASK_ST20_SGMII_EN; + flx_val |= IXGBE_KRM_PMD_FLX_MASK_ST20_AN37_EN; + + rc = mac->ops.write_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, flx_val); + if (rc) + return rc; + + ixgbe_restart_an_internal_phy_x550em(hw); + + return hw->phy.ops.setup_link_speed(hw, speed, autoneg_wait); +} + +/** + * ixgbe_fc_autoneg_sgmii_x550em_a - Enable flow control IEEE clause 37 + * @hw: pointer to hardware structure + * + * Enable flow control according to IEEE clause 37. + */ +static void ixgbe_fc_autoneg_sgmii_x550em_a(struct ixgbe_hw *hw) +{ + s32 status = IXGBE_ERR_FC_NOT_NEGOTIATED; + u32 info[FW_PHY_ACT_DATA_COUNT] = { 0 }; + ixgbe_link_speed speed; + bool link_up; + + /* AN should have completed when the cable was plugged in. + * Look for reasons to bail out. Bail out if: + * - FC autoneg is disabled, or if + * - link is not up. + */ + if (hw->fc.disable_fc_autoneg) + goto out; + + hw->mac.ops.check_link(hw, &speed, &link_up, false); + if (!link_up) + goto out; + + /* Check if auto-negotiation has completed */ + status = ixgbe_fw_phy_activity(hw, FW_PHY_ACT_GET_LINK_INFO, &info); + if (status || !(info[0] & FW_PHY_ACT_GET_LINK_INFO_AN_COMPLETE)) { + status = IXGBE_ERR_FC_NOT_NEGOTIATED; + goto out; + } + + /* Negotiate the flow control */ + status = ixgbe_negotiate_fc(hw, info[0], info[0], + FW_PHY_ACT_GET_LINK_INFO_FC_RX, + FW_PHY_ACT_GET_LINK_INFO_FC_TX, + FW_PHY_ACT_GET_LINK_INFO_LP_FC_RX, + FW_PHY_ACT_GET_LINK_INFO_LP_FC_TX); + +out: + if (!status) { + hw->fc.fc_was_autonegged = true; + } else { + hw->fc.fc_was_autonegged = false; + hw->fc.current_mode = hw->fc.requested_mode; + } +} + +/** ixgbe_init_mac_link_ops_X550em_a - Init mac link function pointers + * @hw: pointer to hardware structure + **/ +static void ixgbe_init_mac_link_ops_X550em_a(struct ixgbe_hw *hw) +{ + struct ixgbe_mac_info *mac = &hw->mac; + + switch (mac->ops.get_media_type(hw)) { + case ixgbe_media_type_fiber: + mac->ops.setup_fc = NULL; + mac->ops.fc_autoneg = ixgbe_fc_autoneg_fiber_x550em_a; + break; + case ixgbe_media_type_copper: + if (hw->device_id != IXGBE_DEV_ID_X550EM_A_1G_T && + hw->device_id != IXGBE_DEV_ID_X550EM_A_1G_T_L) { + mac->ops.setup_link = ixgbe_setup_mac_link_t_X550em; + break; + } + mac->ops.fc_autoneg = ixgbe_fc_autoneg_sgmii_x550em_a; + mac->ops.setup_fc = ixgbe_fc_autoneg_fw; + mac->ops.setup_link = ixgbe_setup_sgmii_fw; + mac->ops.check_link = ixgbe_check_mac_link_generic; + break; + case ixgbe_media_type_backplane: + mac->ops.fc_autoneg = ixgbe_fc_autoneg_backplane_x550em_a; + mac->ops.setup_fc = ixgbe_setup_fc_backplane_x550em_a; + break; + default: + break; + } } /** ixgbe_init_mac_link_ops_X550em - init mac link function pointers @@ -1655,7 +2148,7 @@ static void ixgbe_init_mac_link_ops_X550em(struct ixgbe_hw *hw) mac->ops.setup_link = ixgbe_setup_mac_link_t_X550em; mac->ops.setup_fc = ixgbe_setup_fc_generic; mac->ops.check_link = ixgbe_check_link_t_X550em; - return; + break; case ixgbe_media_type_backplane: if (hw->device_id == IXGBE_DEV_ID_X550EM_A_SGMII || hw->device_id == IXGBE_DEV_ID_X550EM_A_SGMII_L) @@ -1664,6 +2157,10 @@ static void ixgbe_init_mac_link_ops_X550em(struct ixgbe_hw *hw) default: break; } + + /* Additional modification for X550em_a devices */ + if (hw->mac.type == ixgbe_mac_x550em_a) + ixgbe_init_mac_link_ops_X550em_a(hw); } /** ixgbe_setup_sfp_modules_X550em - Setup SFP module @@ -1694,6 +2191,12 @@ static s32 ixgbe_get_link_capabilities_X550em(struct ixgbe_hw *hw, ixgbe_link_speed *speed, bool *autoneg) { + if (hw->phy.type == ixgbe_phy_fw) { + *autoneg = true; + *speed = hw->phy.speeds_supported; + return 0; + } + /* SFP */ if (hw->phy.media_type == ixgbe_media_type_fiber) { /* CS4227 SFP must not enable auto-negotiation */ @@ -1740,7 +2243,7 @@ static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc) /* Vendor alarm triggered */ status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_CHIP_STD_INT_FLAG, - IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE, + MDIO_MMD_VEND1, ®); if (status || !(reg & IXGBE_MDIO_GLOBAL_VEN_ALM_INT_EN)) @@ -1748,7 +2251,7 @@ static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc) /* Vendor Auto-Neg alarm triggered or Global alarm 1 triggered */ status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_INT_CHIP_VEN_FLAG, - IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE, + MDIO_MMD_VEND1, ®); if (status || !(reg & (IXGBE_MDIO_GLOBAL_AN_VEN_ALM_INT_EN | @@ -1757,7 +2260,7 @@ static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc) /* Global alarm triggered */ status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_ALARM_1, - IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE, + MDIO_MMD_VEND1, ®); if (status) @@ -1772,7 +2275,7 @@ static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc) if (reg & IXGBE_MDIO_GLOBAL_ALM_1_DEV_FAULT) { /* device fault alarm triggered */ status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_FAULT_MSG, - IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE, + MDIO_MMD_VEND1, ®); if (status) return status; @@ -1787,14 +2290,14 @@ static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc) /* Vendor alarm 2 triggered */ status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_CHIP_STD_INT_FLAG, - IXGBE_MDIO_AUTO_NEG_DEV_TYPE, ®); + MDIO_MMD_AN, ®); if (status || !(reg & IXGBE_MDIO_GLOBAL_STD_ALM2_INT)) return status; /* link connect/disconnect event occurred */ status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_AUTO_NEG_VENDOR_TX_ALARM2, - IXGBE_MDIO_AUTO_NEG_DEV_TYPE, ®); + MDIO_MMD_AN, ®); if (status) return status; @@ -1826,20 +2329,20 @@ static s32 ixgbe_enable_lasi_ext_t_x550em(struct ixgbe_hw *hw) /* Enable link status change alarm */ status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_PMA_TX_VEN_LASI_INT_MASK, - IXGBE_MDIO_AUTO_NEG_DEV_TYPE, ®); + MDIO_MMD_AN, ®); if (status) return status; reg |= IXGBE_MDIO_PMA_TX_VEN_LASI_INT_EN; status = hw->phy.ops.write_reg(hw, IXGBE_MDIO_PMA_TX_VEN_LASI_INT_MASK, - IXGBE_MDIO_AUTO_NEG_DEV_TYPE, reg); + MDIO_MMD_AN, reg); if (status) return status; /* Enable high temperature failure and global fault alarms */ status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_INT_MASK, - IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE, + MDIO_MMD_VEND1, ®); if (status) return status; @@ -1848,14 +2351,14 @@ static s32 ixgbe_enable_lasi_ext_t_x550em(struct ixgbe_hw *hw) IXGBE_MDIO_GLOBAL_INT_DEV_FAULT_EN); status = hw->phy.ops.write_reg(hw, IXGBE_MDIO_GLOBAL_INT_MASK, - IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE, + MDIO_MMD_VEND1, reg); if (status) return status; /* Enable vendor Auto-Neg alarm and Global Interrupt Mask 1 alarm */ status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_INT_CHIP_VEN_MASK, - IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE, + MDIO_MMD_VEND1, ®); if (status) return status; @@ -1864,14 +2367,14 @@ static s32 ixgbe_enable_lasi_ext_t_x550em(struct ixgbe_hw *hw) IXGBE_MDIO_GLOBAL_ALARM_1_INT); status = hw->phy.ops.write_reg(hw, IXGBE_MDIO_GLOBAL_INT_CHIP_VEN_MASK, - IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE, + MDIO_MMD_VEND1, reg); if (status) return status; /* Enable chip-wide vendor alarm */ status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_INT_CHIP_STD_MASK, - IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE, + MDIO_MMD_VEND1, ®); if (status) return status; @@ -1879,7 +2382,7 @@ static s32 ixgbe_enable_lasi_ext_t_x550em(struct ixgbe_hw *hw) reg |= IXGBE_MDIO_GLOBAL_VEN_ALM_INT_EN; status = hw->phy.ops.write_reg(hw, IXGBE_MDIO_GLOBAL_INT_CHIP_STD_MASK, - IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE, + MDIO_MMD_VEND1, reg); return status; @@ -1932,8 +2435,6 @@ static s32 ixgbe_setup_kr_speed_x550em(struct ixgbe_hw *hw, return status; reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_ENABLE; - reg_val &= ~(IXGBE_KRM_LINK_CTRL_1_TETH_AN_FEC_REQ | - IXGBE_KRM_LINK_CTRL_1_TETH_AN_CAP_FEC); reg_val &= ~(IXGBE_KRM_LINK_CTRL_1_TETH_AN_CAP_KR | IXGBE_KRM_LINK_CTRL_1_TETH_AN_CAP_KX); @@ -1945,13 +2446,31 @@ static s32 ixgbe_setup_kr_speed_x550em(struct ixgbe_hw *hw, if (speed & IXGBE_LINK_SPEED_1GB_FULL) reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_CAP_KX; - /* Restart auto-negotiation. */ - reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_RESTART; status = hw->mac.ops.write_iosf_sb_reg(hw, IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); - return status; + if (hw->mac.type == ixgbe_mac_x550em_a) { + /* Set lane mode to KR auto negotiation */ + status = hw->mac.ops.read_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val); + + if (status) + return status; + + reg_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_MASK; + reg_val |= IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_AN; + reg_val |= IXGBE_KRM_PMD_FLX_MASK_ST20_AN_EN; + reg_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_AN37_EN; + reg_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_SGMII_EN; + + status = hw->mac.ops.write_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); + } + + return ixgbe_restart_an_internal_phy_x550em(hw); } /** ixgbe_setup_kx4_x550em - Configure the KX4 PHY. @@ -1995,12 +2514,11 @@ static s32 ixgbe_setup_kx4_x550em(struct ixgbe_hw *hw) /** * ixgbe_setup_kr_x550em - Configure the KR PHY * @hw: pointer to hardware structure - * - * Configures the integrated KR PHY for X550EM_x. **/ static s32 ixgbe_setup_kr_x550em(struct ixgbe_hw *hw) { - if (hw->mac.type != ixgbe_mac_X550EM_x) + /* leave link alone for 2.5G */ + if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_2_5GB_FULL) return 0; return ixgbe_setup_kr_speed_x550em(hw, hw->phy.autoneg_advertised); @@ -2020,14 +2538,12 @@ static s32 ixgbe_ext_phy_t_x550em_get_link(struct ixgbe_hw *hw, bool *link_up) *link_up = false; /* read this twice back to back to indicate current status */ - ret = hw->phy.ops.read_reg(hw, IXGBE_MDIO_AUTO_NEG_STATUS, - IXGBE_MDIO_AUTO_NEG_DEV_TYPE, + ret = hw->phy.ops.read_reg(hw, MDIO_STAT1, MDIO_MMD_AN, &autoneg_status); if (ret) return ret; - ret = hw->phy.ops.read_reg(hw, IXGBE_MDIO_AUTO_NEG_STATUS, - IXGBE_MDIO_AUTO_NEG_DEV_TYPE, + ret = hw->phy.ops.read_reg(hw, MDIO_STAT1, MDIO_MMD_AN, &autoneg_status); if (ret) return ret; @@ -2073,7 +2589,7 @@ static s32 ixgbe_setup_internal_phy_t_x550em(struct ixgbe_hw *hw) return 0; status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_AUTO_NEG_VENDOR_STAT, - IXGBE_MDIO_AUTO_NEG_DEV_TYPE, + MDIO_MMD_AN, &speed); if (status) return status; @@ -2134,10 +2650,10 @@ static s32 ixgbe_led_on_t_x550em(struct ixgbe_hw *hw, u32 led_idx) /* To turn on the LED, set mode to ON. */ hw->phy.ops.read_reg(hw, IXGBE_X557_LED_PROVISIONING + led_idx, - IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE, &phy_data); + MDIO_MMD_VEND1, &phy_data); phy_data |= IXGBE_X557_LED_MANUAL_SET_MASK; hw->phy.ops.write_reg(hw, IXGBE_X557_LED_PROVISIONING + led_idx, - IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE, phy_data); + MDIO_MMD_VEND1, phy_data); return 0; } @@ -2156,14 +2672,70 @@ static s32 ixgbe_led_off_t_x550em(struct ixgbe_hw *hw, u32 led_idx) /* To turn on the LED, set mode to ON. */ hw->phy.ops.read_reg(hw, IXGBE_X557_LED_PROVISIONING + led_idx, - IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE, &phy_data); + MDIO_MMD_VEND1, &phy_data); phy_data &= ~IXGBE_X557_LED_MANUAL_SET_MASK; hw->phy.ops.write_reg(hw, IXGBE_X557_LED_PROVISIONING + led_idx, - IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE, phy_data); + MDIO_MMD_VEND1, phy_data); return 0; } +/** + * ixgbe_set_fw_drv_ver_x550 - Sends driver version to firmware + * @hw: pointer to the HW structure + * @maj: driver version major number + * @min: driver version minor number + * @build: driver version build number + * @sub: driver version sub build number + * @len: length of driver_ver string + * @driver_ver: driver string + * + * Sends driver version number to firmware through the manageability + * block. On success return 0 + * else returns IXGBE_ERR_SWFW_SYNC when encountering an error acquiring + * semaphore or IXGBE_ERR_HOST_INTERFACE_COMMAND when command fails. + **/ +static s32 ixgbe_set_fw_drv_ver_x550(struct ixgbe_hw *hw, u8 maj, u8 min, + u8 build, u8 sub, u16 len, + const char *driver_ver) +{ + struct ixgbe_hic_drv_info2 fw_cmd; + s32 ret_val; + int i; + + if (!len || !driver_ver || (len > sizeof(fw_cmd.driver_string))) + return IXGBE_ERR_INVALID_ARGUMENT; + + fw_cmd.hdr.cmd = FW_CEM_CMD_DRIVER_INFO; + fw_cmd.hdr.buf_len = FW_CEM_CMD_DRIVER_INFO_LEN + len; + fw_cmd.hdr.cmd_or_resp.cmd_resv = FW_CEM_CMD_RESERVED; + fw_cmd.port_num = (u8)hw->bus.func; + fw_cmd.ver_maj = maj; + fw_cmd.ver_min = min; + fw_cmd.ver_build = build; + fw_cmd.ver_sub = sub; + fw_cmd.hdr.checksum = 0; + memcpy(fw_cmd.driver_string, driver_ver, len); + fw_cmd.hdr.checksum = ixgbe_calculate_checksum((u8 *)&fw_cmd, + (FW_CEM_HDR_LEN + fw_cmd.hdr.buf_len)); + + for (i = 0; i <= FW_CEM_MAX_RETRIES; i++) { + ret_val = ixgbe_host_interface_command(hw, (u32 *)&fw_cmd, + sizeof(fw_cmd), + IXGBE_HI_COMMAND_TIMEOUT, + true); + if (ret_val) + continue; + + if (fw_cmd.hdr.cmd_or_resp.ret_status != + FW_CEM_RESP_STATUS_SUCCESS) + return IXGBE_ERR_HOST_INTERFACE_COMMAND; + return 0; + } + + return ret_val; +} + /** ixgbe_get_lcd_x550em - Determine lowest common denominator * @hw: pointer to hardware structure * @lcd_speed: pointer to lowest common link speed @@ -2180,7 +2752,7 @@ static s32 ixgbe_get_lcd_t_x550em(struct ixgbe_hw *hw, *lcd_speed = IXGBE_LINK_SPEED_UNKNOWN; status = hw->phy.ops.read_reg(hw, IXGBE_AUTO_NEG_LP_STATUS, - IXGBE_MDIO_AUTO_NEG_DEV_TYPE, + MDIO_MMD_AN, &an_lp_status); if (status) return status; @@ -2281,6 +2853,90 @@ static s32 ixgbe_setup_fc_x550em(struct ixgbe_hw *hw) return rc; } +/** + * ixgbe_fc_autoneg_backplane_x550em_a - Enable flow control IEEE clause 37 + * @hw: pointer to hardware structure + **/ +static void ixgbe_fc_autoneg_backplane_x550em_a(struct ixgbe_hw *hw) +{ + u32 link_s1, lp_an_page_low, an_cntl_1; + s32 status = IXGBE_ERR_FC_NOT_NEGOTIATED; + ixgbe_link_speed speed; + bool link_up; + + /* AN should have completed when the cable was plugged in. + * Look for reasons to bail out. Bail out if: + * - FC autoneg is disabled, or if + * - link is not up. + */ + if (hw->fc.disable_fc_autoneg) { + hw_err(hw, "Flow control autoneg is disabled"); + goto out; + } + + hw->mac.ops.check_link(hw, &speed, &link_up, false); + if (!link_up) { + hw_err(hw, "The link is down"); + goto out; + } + + /* Check at auto-negotiation has completed */ + status = hw->mac.ops.read_iosf_sb_reg(hw, + IXGBE_KRM_LINK_S1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, &link_s1); + + if (status || (link_s1 & IXGBE_KRM_LINK_S1_MAC_AN_COMPLETE) == 0) { + hw_dbg(hw, "Auto-Negotiation did not complete\n"); + status = IXGBE_ERR_FC_NOT_NEGOTIATED; + goto out; + } + + /* Read the 10g AN autoc and LP ability registers and resolve + * local flow control settings accordingly + */ + status = hw->mac.ops.read_iosf_sb_reg(hw, + IXGBE_KRM_AN_CNTL_1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, &an_cntl_1); + + if (status) { + hw_dbg(hw, "Auto-Negotiation did not complete\n"); + goto out; + } + + status = hw->mac.ops.read_iosf_sb_reg(hw, + IXGBE_KRM_LP_BASE_PAGE_HIGH(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, &lp_an_page_low); + + if (status) { + hw_dbg(hw, "Auto-Negotiation did not complete\n"); + goto out; + } + + status = ixgbe_negotiate_fc(hw, an_cntl_1, lp_an_page_low, + IXGBE_KRM_AN_CNTL_1_SYM_PAUSE, + IXGBE_KRM_AN_CNTL_1_ASM_PAUSE, + IXGBE_KRM_LP_BASE_PAGE_HIGH_SYM_PAUSE, + IXGBE_KRM_LP_BASE_PAGE_HIGH_ASM_PAUSE); + +out: + if (!status) { + hw->fc.fc_was_autonegged = true; + } else { + hw->fc.fc_was_autonegged = false; + hw->fc.current_mode = hw->fc.requested_mode; + } +} + +/** + * ixgbe_fc_autoneg_fiber_x550em_a - passthrough FC settings + * @hw: pointer to hardware structure + **/ +static void ixgbe_fc_autoneg_fiber_x550em_a(struct ixgbe_hw *hw) +{ + hw->fc.fc_was_autonegged = false; + hw->fc.current_mode = hw->fc.requested_mode; +} + /** ixgbe_enter_lplu_x550em - Transition to low power states * @hw: pointer to hardware structure * @@ -2327,7 +2983,7 @@ static s32 ixgbe_enter_lplu_t_x550em(struct ixgbe_hw *hw) return ixgbe_set_copper_phy_power(hw, false); status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_AUTO_NEG_VENDOR_STAT, - IXGBE_MDIO_AUTO_NEG_DEV_TYPE, + MDIO_MMD_AN, &speed); if (status) return status; @@ -2349,20 +3005,20 @@ static s32 ixgbe_enter_lplu_t_x550em(struct ixgbe_hw *hw) /* Clear AN completed indication */ status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_AUTO_NEG_VENDOR_TX_ALARM, - IXGBE_MDIO_AUTO_NEG_DEV_TYPE, + MDIO_MMD_AN, &autoneg_reg); if (status) return status; - status = hw->phy.ops.read_reg(hw, IXGBE_MII_10GBASE_T_AUTONEG_CTRL_REG, - IXGBE_MDIO_AUTO_NEG_DEV_TYPE, + status = hw->phy.ops.read_reg(hw, MDIO_AN_10GBT_CTRL, + MDIO_MMD_AN, &an_10g_cntl_reg); if (status) return status; status = hw->phy.ops.read_reg(hw, IXGBE_MII_AUTONEG_VENDOR_PROVISION_1_REG, - IXGBE_MDIO_AUTO_NEG_DEV_TYPE, + MDIO_MMD_AN, &autoneg_reg); if (status) return status; @@ -2379,6 +3035,50 @@ static s32 ixgbe_enter_lplu_t_x550em(struct ixgbe_hw *hw) } /** + * ixgbe_reset_phy_fw - Reset firmware-controlled PHYs + * @hw: pointer to hardware structure + */ +static s32 ixgbe_reset_phy_fw(struct ixgbe_hw *hw) +{ + u32 store[FW_PHY_ACT_DATA_COUNT] = { 0 }; + s32 rc; + + if (hw->phy.reset_disable || ixgbe_check_reset_blocked(hw)) + return 0; + + rc = ixgbe_fw_phy_activity(hw, FW_PHY_ACT_PHY_SW_RESET, &store); + if (rc) + return rc; + memset(store, 0, sizeof(store)); + + rc = ixgbe_fw_phy_activity(hw, FW_PHY_ACT_INIT_PHY, &store); + if (rc) + return rc; + + return ixgbe_setup_fw_link(hw); +} + +/** + * ixgbe_check_overtemp_fw - Check firmware-controlled PHYs for overtemp + * @hw: pointer to hardware structure + */ +static s32 ixgbe_check_overtemp_fw(struct ixgbe_hw *hw) +{ + u32 store[FW_PHY_ACT_DATA_COUNT] = { 0 }; + s32 rc; + + rc = ixgbe_fw_phy_activity(hw, FW_PHY_ACT_GET_LINK_INFO, &store); + if (rc) + return rc; + + if (store[0] & FW_PHY_ACT_GET_LINK_INFO_TEMP) { + ixgbe_shutdown_fw_phy(hw); + return IXGBE_ERR_OVERTEMP; + } + return 0; +} + +/** * ixgbe_read_mng_if_sel_x550em - Read NW_MNG_IF_SEL register * @hw: pointer to hardware structure * @@ -2464,6 +3164,10 @@ static s32 ixgbe_init_phy_ops_X550em(struct ixgbe_hw *hw) phy->ops.handle_lasi = ixgbe_handle_lasi_ext_t_x550em; phy->ops.reset = ixgbe_reset_phy_t_X550em; break; + case ixgbe_phy_fw: + phy->ops.setup_link = ixgbe_setup_fw_link; + phy->ops.reset = ixgbe_reset_phy_fw; + break; default: break; } @@ -2501,6 +3205,8 @@ static enum ixgbe_media_type ixgbe_get_media_type_X550em(struct ixgbe_hw *hw) case IXGBE_DEV_ID_X550EM_X_1G_T: case IXGBE_DEV_ID_X550EM_X_10G_T: case IXGBE_DEV_ID_X550EM_A_10G_T: + case IXGBE_DEV_ID_X550EM_A_1G_T: + case IXGBE_DEV_ID_X550EM_A_1G_T_L: media_type = ixgbe_media_type_copper; break; default: @@ -2520,7 +3226,7 @@ static s32 ixgbe_init_ext_t_x550em(struct ixgbe_hw *hw) status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_TX_VENDOR_ALARMS_3, - IXGBE_MDIO_PMA_PMD_DEV_TYPE, + MDIO_MMD_PMAPMD, ®); if (status) return status; @@ -2531,7 +3237,7 @@ static s32 ixgbe_init_ext_t_x550em(struct ixgbe_hw *hw) if (reg & IXGBE_MDIO_TX_VENDOR_ALARMS_3_RST_MASK) { status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_RES_PR_10, - IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE, + MDIO_MMD_VEND1, ®); if (status) return status; @@ -2540,7 +3246,7 @@ static s32 ixgbe_init_ext_t_x550em(struct ixgbe_hw *hw) status = hw->phy.ops.write_reg(hw, IXGBE_MDIO_GLOBAL_RES_PR_10, - IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE, + MDIO_MMD_VEND1, reg); if (status) return status; @@ -2568,6 +3274,13 @@ static void ixgbe_set_mdio_speed(struct ixgbe_hw *hw) hlreg0 &= ~IXGBE_HLREG0_MDCSPD; IXGBE_WRITE_REG(hw, IXGBE_HLREG0, hlreg0); break; + case IXGBE_DEV_ID_X550EM_A_1G_T: + case IXGBE_DEV_ID_X550EM_A_1G_T_L: + /* Select fast MDIO clock speed for these devices */ + hlreg0 = IXGBE_READ_REG(hw, IXGBE_HLREG0); + hlreg0 |= IXGBE_HLREG0_MDCSPD; + IXGBE_WRITE_REG(hw, IXGBE_HLREG0, hlreg0); + break; default: break; } @@ -2729,6 +3442,90 @@ static void ixgbe_set_source_address_pruning_X550(struct ixgbe_hw *hw, } /** + * ixgbe_setup_fc_backplane_x550em_a - Set up flow control + * @hw: pointer to hardware structure + * + * Called at init time to set up flow control. + **/ +static s32 ixgbe_setup_fc_backplane_x550em_a(struct ixgbe_hw *hw) +{ + s32 status = 0; + u32 an_cntl = 0; + + /* Validate the requested mode */ + if (hw->fc.strict_ieee && hw->fc.requested_mode == ixgbe_fc_rx_pause) { + hw_err(hw, "ixgbe_fc_rx_pause not valid in strict IEEE mode\n"); + return IXGBE_ERR_INVALID_LINK_SETTINGS; + } + + if (hw->fc.requested_mode == ixgbe_fc_default) + hw->fc.requested_mode = ixgbe_fc_full; + + /* Set up the 1G and 10G flow control advertisement registers so the + * HW will be able to do FC autoneg once the cable is plugged in. If + * we link at 10G, the 1G advertisement is harmless and vice versa. + */ + status = hw->mac.ops.read_iosf_sb_reg(hw, + IXGBE_KRM_AN_CNTL_1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, &an_cntl); + + if (status) { + hw_dbg(hw, "Auto-Negotiation did not complete\n"); + return status; + } + + /* The possible values of fc.requested_mode are: + * 0: Flow control is completely disabled + * 1: Rx flow control is enabled (we can receive pause frames, + * but not send pause frames). + * 2: Tx flow control is enabled (we can send pause frames but + * we do not support receiving pause frames). + * 3: Both Rx and Tx flow control (symmetric) are enabled. + * other: Invalid. + */ + switch (hw->fc.requested_mode) { + case ixgbe_fc_none: + /* Flow control completely disabled by software override. */ + an_cntl &= ~(IXGBE_KRM_AN_CNTL_1_SYM_PAUSE | + IXGBE_KRM_AN_CNTL_1_ASM_PAUSE); + break; + case ixgbe_fc_tx_pause: + /* Tx Flow control is enabled, and Rx Flow control is + * disabled by software override. + */ + an_cntl |= IXGBE_KRM_AN_CNTL_1_ASM_PAUSE; + an_cntl &= ~IXGBE_KRM_AN_CNTL_1_SYM_PAUSE; + break; + case ixgbe_fc_rx_pause: + /* Rx Flow control is enabled and Tx Flow control is + * disabled by software override. Since there really + * isn't a way to advertise that we are capable of RX + * Pause ONLY, we will advertise that we support both + * symmetric and asymmetric Rx PAUSE, as such we fall + * through to the fc_full statement. Later, we will + * disable the adapter's ability to send PAUSE frames. + */ + case ixgbe_fc_full: + /* Flow control (both Rx and Tx) is enabled by SW override. */ + an_cntl |= IXGBE_KRM_AN_CNTL_1_SYM_PAUSE | + IXGBE_KRM_AN_CNTL_1_ASM_PAUSE; + break; + default: + hw_err(hw, "Flow control param set incorrectly\n"); + return IXGBE_ERR_CONFIG; + } + + status = hw->mac.ops.write_iosf_sb_reg(hw, + IXGBE_KRM_AN_CNTL_1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, an_cntl); + + /* Restart auto-negotiation. */ + status = ixgbe_restart_an_internal_phy_x550em(hw); + + return status; +} + +/** * ixgbe_set_mux - Set mux for port 1 access with CS4227 * @hw: pointer to hardware structure * @state: set mux if 1, clear if 0 @@ -2915,7 +3712,7 @@ static s32 ixgbe_write_phy_reg_x550a(struct ixgbe_hw *hw, u32 reg_addr, .clear_vfta = &ixgbe_clear_vfta_generic, \ .set_vfta = &ixgbe_set_vfta_generic, \ .fc_enable = &ixgbe_fc_enable_generic, \ - .set_fw_drv_ver = &ixgbe_set_fw_drv_ver_generic, \ + .set_fw_drv_ver = &ixgbe_set_fw_drv_ver_x550, \ .init_uta_tables = &ixgbe_init_uta_tables_generic, \ .set_mac_anti_spoofing = &ixgbe_set_mac_anti_spoofing, \ .set_vlan_anti_spoofing = &ixgbe_set_vlan_anti_spoofing, \ @@ -2934,6 +3731,7 @@ static const struct ixgbe_mac_operations mac_ops_X550 = { X550_COMMON_MAC .led_on = ixgbe_led_on_generic, .led_off = ixgbe_led_off_generic, + .init_led_link_act = ixgbe_init_led_link_act_generic, .reset_hw = &ixgbe_reset_hw_X540, .get_media_type = &ixgbe_get_media_type_X540, .get_san_mac_addr = &ixgbe_get_san_mac_addr_generic, @@ -2948,12 +3746,14 @@ static const struct ixgbe_mac_operations mac_ops_X550 = { .prot_autoc_read = prot_autoc_read_generic, .prot_autoc_write = prot_autoc_write_generic, .setup_fc = ixgbe_setup_fc_generic, + .fc_autoneg = ixgbe_fc_autoneg, }; static const struct ixgbe_mac_operations mac_ops_X550EM_x = { X550_COMMON_MAC .led_on = ixgbe_led_on_t_x550em, .led_off = ixgbe_led_off_t_x550em, + .init_led_link_act = ixgbe_init_led_link_act_generic, .reset_hw = &ixgbe_reset_hw_X550em, .get_media_type = &ixgbe_get_media_type_X550em, .get_san_mac_addr = NULL, @@ -2966,6 +3766,7 @@ static const struct ixgbe_mac_operations mac_ops_X550EM_x = { .release_swfw_sync = &ixgbe_release_swfw_sync_X550em, .init_swfw_sync = &ixgbe_init_swfw_sync_X540, .setup_fc = NULL, /* defined later */ + .fc_autoneg = ixgbe_fc_autoneg, .read_iosf_sb_reg = ixgbe_read_iosf_sb_reg_x550, .write_iosf_sb_reg = ixgbe_write_iosf_sb_reg_x550, }; @@ -2974,6 +3775,28 @@ static struct ixgbe_mac_operations mac_ops_x550em_a = { X550_COMMON_MAC .led_on = ixgbe_led_on_t_x550em, .led_off = ixgbe_led_off_t_x550em, + .init_led_link_act = ixgbe_init_led_link_act_generic, + .reset_hw = ixgbe_reset_hw_X550em, + .get_media_type = ixgbe_get_media_type_X550em, + .get_san_mac_addr = NULL, + .get_wwn_prefix = NULL, + .setup_link = NULL, /* defined later */ + .get_link_capabilities = ixgbe_get_link_capabilities_X550em, + .get_bus_info = ixgbe_get_bus_info_X550em, + .setup_sfp = ixgbe_setup_sfp_modules_X550em, + .acquire_swfw_sync = ixgbe_acquire_swfw_sync_x550em_a, + .release_swfw_sync = ixgbe_release_swfw_sync_x550em_a, + .setup_fc = ixgbe_setup_fc_x550em, + .fc_autoneg = ixgbe_fc_autoneg, + .read_iosf_sb_reg = ixgbe_read_iosf_sb_reg_x550a, + .write_iosf_sb_reg = ixgbe_write_iosf_sb_reg_x550a, +}; + +static struct ixgbe_mac_operations mac_ops_x550em_a_fw = { + X550_COMMON_MAC + .led_on = ixgbe_led_on_generic, + .led_off = ixgbe_led_off_generic, + .init_led_link_act = ixgbe_init_led_link_act_generic, .reset_hw = ixgbe_reset_hw_X550em, .get_media_type = ixgbe_get_media_type_X550em, .get_san_mac_addr = NULL, @@ -2985,6 +3808,7 @@ static struct ixgbe_mac_operations mac_ops_x550em_a = { .acquire_swfw_sync = ixgbe_acquire_swfw_sync_x550em_a, .release_swfw_sync = ixgbe_release_swfw_sync_x550em_a, .setup_fc = ixgbe_setup_fc_x550em, + .fc_autoneg = ixgbe_fc_autoneg, .read_iosf_sb_reg = ixgbe_read_iosf_sb_reg_x550a, .write_iosf_sb_reg = ixgbe_write_iosf_sb_reg_x550a, }; @@ -3018,12 +3842,11 @@ static const struct ixgbe_eeprom_operations eeprom_ops_X550EM_x = { .read_i2c_eeprom = &ixgbe_read_i2c_eeprom_generic, \ .write_i2c_eeprom = &ixgbe_write_i2c_eeprom_generic, \ .setup_link = &ixgbe_setup_phy_link_generic, \ - .set_phy_power = NULL, \ - .check_overtemp = &ixgbe_tn_check_overtemp, \ - .get_firmware_version = &ixgbe_get_phy_firmware_version_generic, + .set_phy_power = NULL, static const struct ixgbe_phy_operations phy_ops_X550 = { X550_COMMON_PHY + .check_overtemp = &ixgbe_tn_check_overtemp, .init = NULL, .identify = &ixgbe_identify_phy_generic, .read_reg = &ixgbe_read_phy_reg_generic, @@ -3032,19 +3855,16 @@ static const struct ixgbe_phy_operations phy_ops_X550 = { static const struct ixgbe_phy_operations phy_ops_X550EM_x = { X550_COMMON_PHY + .check_overtemp = &ixgbe_tn_check_overtemp, .init = &ixgbe_init_phy_ops_X550em, .identify = &ixgbe_identify_phy_x550em, .read_reg = &ixgbe_read_phy_reg_generic, .write_reg = &ixgbe_write_phy_reg_generic, - .read_i2c_combined = &ixgbe_read_i2c_combined_generic, - .write_i2c_combined = &ixgbe_write_i2c_combined_generic, - .read_i2c_combined_unlocked = &ixgbe_read_i2c_combined_generic_unlocked, - .write_i2c_combined_unlocked = - &ixgbe_write_i2c_combined_generic_unlocked, }; static const struct ixgbe_phy_operations phy_ops_x550em_a = { X550_COMMON_PHY + .check_overtemp = &ixgbe_tn_check_overtemp, .init = &ixgbe_init_phy_ops_X550em, .identify = &ixgbe_identify_phy_x550em, .read_reg = &ixgbe_read_phy_reg_x550a, @@ -3053,6 +3873,24 @@ static const struct ixgbe_phy_operations phy_ops_x550em_a = { .write_reg_mdi = &ixgbe_write_phy_reg_mdi, }; +static const struct ixgbe_phy_operations phy_ops_x550em_a_fw = { + X550_COMMON_PHY + .check_overtemp = ixgbe_check_overtemp_fw, + .init = ixgbe_init_phy_ops_X550em, + .identify = ixgbe_identify_phy_fw, + .read_reg = NULL, + .write_reg = NULL, + .read_reg_mdi = NULL, + .write_reg_mdi = NULL, +}; + +static const struct ixgbe_link_operations link_ops_x550em_x = { + .read_link = &ixgbe_read_i2c_combined_generic, + .read_link_unlocked = &ixgbe_read_i2c_combined_generic_unlocked, + .write_link = &ixgbe_write_i2c_combined_generic, + .write_link_unlocked = &ixgbe_write_i2c_combined_generic_unlocked, +}; + static const u32 ixgbe_mvals_X550[IXGBE_MVALS_IDX_LIMIT] = { IXGBE_MVALS_INIT(X550) }; @@ -3083,14 +3921,25 @@ const struct ixgbe_info ixgbe_X550EM_x_info = { .phy_ops = &phy_ops_X550EM_x, .mbx_ops = &mbx_ops_generic, .mvals = ixgbe_mvals_X550EM_x, + .link_ops = &link_ops_x550em_x, }; const struct ixgbe_info ixgbe_x550em_a_info = { .mac = ixgbe_mac_x550em_a, - .get_invariants = &ixgbe_get_invariants_X550_x, + .get_invariants = &ixgbe_get_invariants_X550_a, .mac_ops = &mac_ops_x550em_a, .eeprom_ops = &eeprom_ops_X550EM_x, .phy_ops = &phy_ops_x550em_a, .mbx_ops = &mbx_ops_generic, .mvals = ixgbe_mvals_x550em_a, }; + +const struct ixgbe_info ixgbe_x550em_a_fw_info = { + .mac = ixgbe_mac_x550em_a, + .get_invariants = ixgbe_get_invariants_X550_a_fw, + .mac_ops = &mac_ops_x550em_a_fw, + .eeprom_ops = &eeprom_ops_X550EM_x, + .phy_ops = &phy_ops_x550em_a_fw, + .mbx_ops = &mbx_ops_generic, + .mvals = ixgbe_mvals_x550em_a, +}; diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c index 508e72c5f1c2..1f6c0ecd50bb 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c +++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c @@ -432,11 +432,6 @@ static void ixgbevf_get_ethtool_stats(struct net_device *netdev, if (!ring) { data[i++] = 0; data[i++] = 0; -#ifdef BP_EXTENDED_STATS - data[i++] = 0; - data[i++] = 0; - data[i++] = 0; -#endif continue; } @@ -446,12 +441,6 @@ static void ixgbevf_get_ethtool_stats(struct net_device *netdev, data[i + 1] = ring->stats.bytes; } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); i += 2; -#ifdef BP_EXTENDED_STATS - data[i] = ring->stats.yields; - data[i + 1] = ring->stats.misses; - data[i + 2] = ring->stats.cleaned; - i += 3; -#endif } /* populate Rx queue data */ @@ -460,11 +449,6 @@ static void ixgbevf_get_ethtool_stats(struct net_device *netdev, if (!ring) { data[i++] = 0; data[i++] = 0; -#ifdef BP_EXTENDED_STATS - data[i++] = 0; - data[i++] = 0; - data[i++] = 0; -#endif continue; } @@ -474,12 +458,6 @@ static void ixgbevf_get_ethtool_stats(struct net_device *netdev, data[i + 1] = ring->stats.bytes; } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); i += 2; -#ifdef BP_EXTENDED_STATS - data[i] = ring->stats.yields; - data[i + 1] = ring->stats.misses; - data[i + 2] = ring->stats.cleaned; - i += 3; -#endif } } @@ -507,28 +485,12 @@ static void ixgbevf_get_strings(struct net_device *netdev, u32 stringset, p += ETH_GSTRING_LEN; sprintf(p, "tx_queue_%u_bytes", i); p += ETH_GSTRING_LEN; -#ifdef BP_EXTENDED_STATS - sprintf(p, "tx_queue_%u_bp_napi_yield", i); - p += ETH_GSTRING_LEN; - sprintf(p, "tx_queue_%u_bp_misses", i); - p += ETH_GSTRING_LEN; - sprintf(p, "tx_queue_%u_bp_cleaned", i); - p += ETH_GSTRING_LEN; -#endif /* BP_EXTENDED_STATS */ } for (i = 0; i < adapter->num_rx_queues; i++) { sprintf(p, "rx_queue_%u_packets", i); p += ETH_GSTRING_LEN; sprintf(p, "rx_queue_%u_bytes", i); p += ETH_GSTRING_LEN; -#ifdef BP_EXTENDED_STATS - sprintf(p, "rx_queue_%u_bp_poll_yield", i); - p += ETH_GSTRING_LEN; - sprintf(p, "rx_queue_%u_bp_misses", i); - p += ETH_GSTRING_LEN; - sprintf(p, "rx_queue_%u_bp_cleaned", i); - p += ETH_GSTRING_LEN; -#endif /* BP_EXTENDED_STATS */ } break; } diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h index 5639fbe294d0..a8cbc2dda0dd 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h @@ -37,11 +37,6 @@ #include "vf.h" -#ifdef CONFIG_NET_RX_BUSY_POLL -#include <net/busy_poll.h> -#define BP_EXTENDED_STATS -#endif - #define IXGBE_MAX_TXD_PWR 14 #define IXGBE_MAX_DATA_PER_TXD BIT(IXGBE_MAX_TXD_PWR) @@ -73,11 +68,6 @@ struct ixgbevf_rx_buffer { struct ixgbevf_stats { u64 packets; u64 bytes; -#ifdef BP_EXTENDED_STATS - u64 yields; - u64 misses; - u64 cleaned; -#endif }; struct ixgbevf_tx_queue_stats { @@ -217,109 +207,6 @@ struct ixgbevf_q_vector { #endif /* CONFIG_NET_RX_BUSY_POLL */ }; -#ifdef CONFIG_NET_RX_BUSY_POLL -static inline void ixgbevf_qv_init_lock(struct ixgbevf_q_vector *q_vector) -{ - spin_lock_init(&q_vector->lock); - q_vector->state = IXGBEVF_QV_STATE_IDLE; -} - -/* called from the device poll routine to get ownership of a q_vector */ -static inline bool ixgbevf_qv_lock_napi(struct ixgbevf_q_vector *q_vector) -{ - int rc = true; - - spin_lock_bh(&q_vector->lock); - if (q_vector->state & IXGBEVF_QV_LOCKED) { - WARN_ON(q_vector->state & IXGBEVF_QV_STATE_NAPI); - q_vector->state |= IXGBEVF_QV_STATE_NAPI_YIELD; - rc = false; -#ifdef BP_EXTENDED_STATS - q_vector->tx.ring->stats.yields++; -#endif - } else { - /* we don't care if someone yielded */ - q_vector->state = IXGBEVF_QV_STATE_NAPI; - } - spin_unlock_bh(&q_vector->lock); - return rc; -} - -/* returns true is someone tried to get the qv while napi had it */ -static inline bool ixgbevf_qv_unlock_napi(struct ixgbevf_q_vector *q_vector) -{ - int rc = false; - - spin_lock_bh(&q_vector->lock); - WARN_ON(q_vector->state & (IXGBEVF_QV_STATE_POLL | - IXGBEVF_QV_STATE_NAPI_YIELD)); - - if (q_vector->state & IXGBEVF_QV_STATE_POLL_YIELD) - rc = true; - /* reset state to idle, unless QV is disabled */ - q_vector->state &= IXGBEVF_QV_STATE_DISABLED; - spin_unlock_bh(&q_vector->lock); - return rc; -} - -/* called from ixgbevf_low_latency_poll() */ -static inline bool ixgbevf_qv_lock_poll(struct ixgbevf_q_vector *q_vector) -{ - int rc = true; - - spin_lock_bh(&q_vector->lock); - if ((q_vector->state & IXGBEVF_QV_LOCKED)) { - q_vector->state |= IXGBEVF_QV_STATE_POLL_YIELD; - rc = false; -#ifdef BP_EXTENDED_STATS - q_vector->rx.ring->stats.yields++; -#endif - } else { - /* preserve yield marks */ - q_vector->state |= IXGBEVF_QV_STATE_POLL; - } - spin_unlock_bh(&q_vector->lock); - return rc; -} - -/* returns true if someone tried to get the qv while it was locked */ -static inline bool ixgbevf_qv_unlock_poll(struct ixgbevf_q_vector *q_vector) -{ - int rc = false; - - spin_lock_bh(&q_vector->lock); - WARN_ON(q_vector->state & (IXGBEVF_QV_STATE_NAPI)); - - if (q_vector->state & IXGBEVF_QV_STATE_POLL_YIELD) - rc = true; - /* reset state to idle, unless QV is disabled */ - q_vector->state &= IXGBEVF_QV_STATE_DISABLED; - spin_unlock_bh(&q_vector->lock); - return rc; -} - -/* true if a socket is polling, even if it did not get the lock */ -static inline bool ixgbevf_qv_busy_polling(struct ixgbevf_q_vector *q_vector) -{ - WARN_ON(!(q_vector->state & IXGBEVF_QV_OWNED)); - return q_vector->state & IXGBEVF_QV_USER_PEND; -} - -/* false if QV is currently owned */ -static inline bool ixgbevf_qv_disable(struct ixgbevf_q_vector *q_vector) -{ - int rc = true; - - spin_lock_bh(&q_vector->lock); - if (q_vector->state & IXGBEVF_QV_OWNED) - rc = false; - q_vector->state |= IXGBEVF_QV_STATE_DISABLED; - spin_unlock_bh(&q_vector->lock); - return rc; -} - -#endif /* CONFIG_NET_RX_BUSY_POLL */ - /* microsecond values for various ITR rates shifted by 2 to fit itr register * with the first 3 bits reserved 0 */ @@ -464,6 +351,7 @@ enum ixgbevf_xcast_modes { IXGBEVF_XCAST_MODE_NONE = 0, IXGBEVF_XCAST_MODE_MULTI, IXGBEVF_XCAST_MODE_ALLMULTI, + IXGBEVF_XCAST_MODE_PROMISC, }; extern const struct ixgbevf_info ixgbevf_82599_vf_info; diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index cbf70fe4028a..80bab261a0ec 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -457,16 +457,6 @@ static bool ixgbevf_clean_tx_irq(struct ixgbevf_q_vector *q_vector, static void ixgbevf_rx_skb(struct ixgbevf_q_vector *q_vector, struct sk_buff *skb) { -#ifdef CONFIG_NET_RX_BUSY_POLL - skb_mark_napi_id(skb, &q_vector->napi); - - if (ixgbevf_qv_busy_polling(q_vector)) { - netif_receive_skb(skb); - /* exit early if we busy polled */ - return; - } -#endif /* CONFIG_NET_RX_BUSY_POLL */ - napi_gro_receive(&q_vector->napi, skb); } @@ -1031,10 +1021,6 @@ static int ixgbevf_poll(struct napi_struct *napi, int budget) if (budget <= 0) return budget; -#ifdef CONFIG_NET_RX_BUSY_POLL - if (!ixgbevf_qv_lock_napi(q_vector)) - return budget; -#endif /* attempt to distribute budget to each queue fairly, but don't allow * the budget to go below 1 because we'll exit polling @@ -1052,10 +1038,6 @@ static int ixgbevf_poll(struct napi_struct *napi, int budget) clean_complete = false; } -#ifdef CONFIG_NET_RX_BUSY_POLL - ixgbevf_qv_unlock_napi(q_vector); -#endif - /* If all work not completed, return budget and keep polling */ if (!clean_complete) return budget; @@ -1090,40 +1072,6 @@ void ixgbevf_write_eitr(struct ixgbevf_q_vector *q_vector) IXGBE_WRITE_REG(hw, IXGBE_VTEITR(v_idx), itr_reg); } -#ifdef CONFIG_NET_RX_BUSY_POLL -/* must be called with local_bh_disable()d */ -static int ixgbevf_busy_poll_recv(struct napi_struct *napi) -{ - struct ixgbevf_q_vector *q_vector = - container_of(napi, struct ixgbevf_q_vector, napi); - struct ixgbevf_adapter *adapter = q_vector->adapter; - struct ixgbevf_ring *ring; - int found = 0; - - if (test_bit(__IXGBEVF_DOWN, &adapter->state)) - return LL_FLUSH_FAILED; - - if (!ixgbevf_qv_lock_poll(q_vector)) - return LL_FLUSH_BUSY; - - ixgbevf_for_each_ring(ring, q_vector->rx) { - found = ixgbevf_clean_rx_irq(q_vector, ring, 4); -#ifdef BP_EXTENDED_STATS - if (found) - ring->stats.cleaned += found; - else - ring->stats.misses++; -#endif - if (found) - break; - } - - ixgbevf_qv_unlock_poll(q_vector); - - return found; -} -#endif /* CONFIG_NET_RX_BUSY_POLL */ - /** * ixgbevf_configure_msix - Configure MSI-X hardware * @adapter: board private structure @@ -1498,6 +1446,9 @@ static void ixgbevf_free_irq(struct ixgbevf_adapter *adapter) { int i, q_vectors; + if (!adapter->msix_entries) + return; + q_vectors = adapter->num_msix_vectors; i = q_vectors - 1; @@ -1927,6 +1878,16 @@ static void ixgbevf_set_rx_mode(struct net_device *netdev) (flags & (IFF_BROADCAST | IFF_MULTICAST)) ? IXGBEVF_XCAST_MODE_MULTI : IXGBEVF_XCAST_MODE_NONE; + /* request the most inclusive mode we need */ + if (flags & IFF_PROMISC) + xcast_mode = IXGBEVF_XCAST_MODE_PROMISC; + else if (flags & IFF_ALLMULTI) + xcast_mode = IXGBEVF_XCAST_MODE_ALLMULTI; + else if (flags & (IFF_BROADCAST | IFF_MULTICAST)) + xcast_mode = IXGBEVF_XCAST_MODE_MULTI; + else + xcast_mode = IXGBEVF_XCAST_MODE_NONE; + spin_lock_bh(&adapter->mbx_lock); hw->mac.ops.update_xcast_mode(hw, xcast_mode); @@ -1947,9 +1908,6 @@ static void ixgbevf_napi_enable_all(struct ixgbevf_adapter *adapter) for (q_idx = 0; q_idx < q_vectors; q_idx++) { q_vector = adapter->q_vector[q_idx]; -#ifdef CONFIG_NET_RX_BUSY_POLL - ixgbevf_qv_init_lock(adapter->q_vector[q_idx]); -#endif napi_enable(&q_vector->napi); } } @@ -1963,12 +1921,6 @@ static void ixgbevf_napi_disable_all(struct ixgbevf_adapter *adapter) for (q_idx = 0; q_idx < q_vectors; q_idx++) { q_vector = adapter->q_vector[q_idx]; napi_disable(&q_vector->napi); -#ifdef CONFIG_NET_RX_BUSY_POLL - while (!ixgbevf_qv_disable(adapter->q_vector[q_idx])) { - pr_info("QV %d locked\n", q_idx); - usleep_range(1000, 20000); - } -#endif /* CONFIG_NET_RX_BUSY_POLL */ } } @@ -2068,7 +2020,8 @@ static void ixgbevf_init_last_counter_stats(struct ixgbevf_adapter *adapter) static void ixgbevf_negotiate_api(struct ixgbevf_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; - int api[] = { ixgbe_mbox_api_12, + int api[] = { ixgbe_mbox_api_13, + ixgbe_mbox_api_12, ixgbe_mbox_api_11, ixgbe_mbox_api_10, ixgbe_mbox_api_unknown }; @@ -2370,6 +2323,7 @@ static void ixgbevf_set_num_queues(struct ixgbevf_adapter *adapter) switch (hw->api_version) { case ixgbe_mbox_api_11: case ixgbe_mbox_api_12: + case ixgbe_mbox_api_13: adapter->num_rx_queues = rss; adapter->num_tx_queues = rss; default: @@ -2552,6 +2506,9 @@ static void ixgbevf_free_q_vectors(struct ixgbevf_adapter *adapter) **/ static void ixgbevf_reset_interrupt_capability(struct ixgbevf_adapter *adapter) { + if (!adapter->msix_entries) + return; + pci_disable_msix(adapter->pdev); kfree(adapter->msix_entries); adapter->msix_entries = NULL; @@ -3222,6 +3179,21 @@ err_setup_reset: } /** + * ixgbevf_close_suspend - actions necessary to both suspend and close flows + * @adapter: the private adapter struct + * + * This function should contain the necessary work common to both suspending + * and closing of the device. + */ +static void ixgbevf_close_suspend(struct ixgbevf_adapter *adapter) +{ + ixgbevf_down(adapter); + ixgbevf_free_irq(adapter); + ixgbevf_free_all_tx_resources(adapter); + ixgbevf_free_all_rx_resources(adapter); +} + +/** * ixgbevf_close - Disables a network interface * @netdev: network interface device structure * @@ -3236,11 +3208,8 @@ int ixgbevf_close(struct net_device *netdev) { struct ixgbevf_adapter *adapter = netdev_priv(netdev); - ixgbevf_down(adapter); - ixgbevf_free_irq(adapter); - - ixgbevf_free_all_tx_resources(adapter); - ixgbevf_free_all_rx_resources(adapter); + if (netif_device_present(netdev)) + ixgbevf_close_suspend(adapter); return 0; } @@ -3262,6 +3231,8 @@ static void ixgbevf_queue_reset_subtask(struct ixgbevf_adapter *adapter) * match packet buffer alignment. Unfortunately, the * hardware is not flexible enough to do this dynamically. */ + rtnl_lock(); + if (netif_running(dev)) ixgbevf_close(dev); @@ -3270,6 +3241,8 @@ static void ixgbevf_queue_reset_subtask(struct ixgbevf_adapter *adapter) if (netif_running(dev)) ixgbevf_open(dev); + + rtnl_unlock(); } static void ixgbevf_tx_ctxtdesc(struct ixgbevf_ring *tx_ring, @@ -3746,24 +3719,8 @@ static int ixgbevf_change_mtu(struct net_device *netdev, int new_mtu) struct ixgbevf_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN; - int max_possible_frame = MAXIMUM_ETHERNET_VLAN_SIZE; int ret; - switch (adapter->hw.api_version) { - case ixgbe_mbox_api_11: - case ixgbe_mbox_api_12: - max_possible_frame = IXGBE_MAX_JUMBO_FRAME_SIZE; - break; - default: - if (adapter->hw.mac.type != ixgbe_mac_82599_vf) - max_possible_frame = IXGBE_MAX_JUMBO_FRAME_SIZE; - break; - } - - /* MTU < 68 is an error and causes problems on some kernels */ - if ((new_mtu < 68) || (max_frame > max_possible_frame)) - return -EINVAL; - spin_lock_bh(&adapter->mbx_lock); /* notify the PF of our intent to use this size of frame */ ret = hw->mac.ops.set_rlpml(hw, max_frame); @@ -3806,18 +3763,14 @@ static int ixgbevf_suspend(struct pci_dev *pdev, pm_message_t state) int retval = 0; #endif + rtnl_lock(); netif_device_detach(netdev); - if (netif_running(netdev)) { - rtnl_lock(); - ixgbevf_down(adapter); - ixgbevf_free_irq(adapter); - ixgbevf_free_all_tx_resources(adapter); - ixgbevf_free_all_rx_resources(adapter); - rtnl_unlock(); - } + if (netif_running(netdev)) + ixgbevf_close_suspend(adapter); ixgbevf_clear_interrupt_scheme(adapter); + rtnl_unlock(); #ifdef CONFIG_PM retval = pci_save_state(pdev); @@ -3849,6 +3802,8 @@ static int ixgbevf_resume(struct pci_dev *pdev) dev_err(&pdev->dev, "Cannot enable PCI device from suspend\n"); return err; } + + adapter->hw.hw_addr = adapter->io_addr; smp_mb__before_atomic(); clear_bit(__IXGBEVF_DISABLED, &adapter->state); pci_set_master(pdev); @@ -3880,8 +3835,8 @@ static void ixgbevf_shutdown(struct pci_dev *pdev) ixgbevf_suspend(pdev, PMSG_SUSPEND); } -static struct rtnl_link_stats64 *ixgbevf_get_stats(struct net_device *netdev, - struct rtnl_link_stats64 *stats) +static void ixgbevf_get_stats(struct net_device *netdev, + struct rtnl_link_stats64 *stats) { struct ixgbevf_adapter *adapter = netdev_priv(netdev); unsigned int start; @@ -3914,8 +3869,6 @@ static struct rtnl_link_stats64 *ixgbevf_get_stats(struct net_device *netdev, stats->tx_bytes += bytes; stats->tx_packets += packets; } - - return stats; } #define IXGBEVF_MAX_MAC_HDR_LEN 127 @@ -3964,9 +3917,6 @@ static const struct net_device_ops ixgbevf_netdev_ops = { .ndo_tx_timeout = ixgbevf_tx_timeout, .ndo_vlan_rx_add_vid = ixgbevf_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = ixgbevf_vlan_rx_kill_vid, -#ifdef CONFIG_NET_RX_BUSY_POLL - .ndo_busy_poll = ixgbevf_busy_poll_recv, -#endif #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = ixgbevf_netpoll, #endif @@ -4108,6 +4058,24 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->priv_flags |= IFF_UNICAST_FLT; + /* MTU range: 68 - 1504 or 9710 */ + netdev->min_mtu = ETH_MIN_MTU; + switch (adapter->hw.api_version) { + case ixgbe_mbox_api_11: + case ixgbe_mbox_api_12: + case ixgbe_mbox_api_13: + netdev->max_mtu = IXGBE_MAX_JUMBO_FRAME_SIZE - + (ETH_HLEN + ETH_FCS_LEN); + break; + default: + if (adapter->hw.mac.type != ixgbe_mac_82599_vf) + netdev->max_mtu = IXGBE_MAX_JUMBO_FRAME_SIZE - + (ETH_HLEN + ETH_FCS_LEN); + else + netdev->max_mtu = ETH_DATA_LEN + ETH_FCS_LEN; + break; + } + if (IXGBE_REMOVED(hw->hw_addr)) { err = -EIO; goto err_sw_init; @@ -4238,7 +4206,7 @@ static pci_ers_result_t ixgbevf_io_error_detected(struct pci_dev *pdev, } if (netif_running(netdev)) - ixgbevf_down(adapter); + ixgbevf_close_suspend(adapter); if (!test_and_set_bit(__IXGBEVF_DISABLED, &adapter->state)) pci_disable_device(pdev); @@ -4266,6 +4234,7 @@ static pci_ers_result_t ixgbevf_io_slot_reset(struct pci_dev *pdev) return PCI_ERS_RESULT_DISCONNECT; } + adapter->hw.hw_addr = adapter->io_addr; smp_mb__before_atomic(); clear_bit(__IXGBEVF_DISABLED, &adapter->state); pci_set_master(pdev); @@ -4286,12 +4255,13 @@ static pci_ers_result_t ixgbevf_io_slot_reset(struct pci_dev *pdev) static void ixgbevf_io_resume(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); - struct ixgbevf_adapter *adapter = netdev_priv(netdev); + rtnl_lock(); if (netif_running(netdev)) - ixgbevf_up(adapter); + ixgbevf_open(netdev); netif_device_attach(netdev); + rtnl_unlock(); } /* PCI Error Recovery (ERS) */ diff --git a/drivers/net/ethernet/intel/ixgbevf/mbx.h b/drivers/net/ethernet/intel/ixgbevf/mbx.h index 340cdd469455..bc0442acae78 100644 --- a/drivers/net/ethernet/intel/ixgbevf/mbx.h +++ b/drivers/net/ethernet/intel/ixgbevf/mbx.h @@ -84,6 +84,7 @@ enum ixgbe_pfvf_api_rev { ixgbe_mbox_api_20, /* API version 2.0, solaris Phase1 VF driver */ ixgbe_mbox_api_11, /* API version 1.1, linux/freebsd VF driver */ ixgbe_mbox_api_12, /* API version 1.2, linux/freebsd VF driver */ + ixgbe_mbox_api_13, /* API version 1.3, linux/freebsd VF driver */ /* This value should always be last */ ixgbe_mbox_api_unknown, /* indicates that API version is not known */ }; diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c index d46ba1dabcb7..8a5db9d7219d 100644 --- a/drivers/net/ethernet/intel/ixgbevf/vf.c +++ b/drivers/net/ethernet/intel/ixgbevf/vf.c @@ -330,9 +330,14 @@ int ixgbevf_get_reta_locked(struct ixgbe_hw *hw, u32 *reta, int num_rx_queues) * Thus return an error if API doesn't support RETA querying or querying * is not supported for this device type. */ - if (hw->api_version != ixgbe_mbox_api_12 || - hw->mac.type >= ixgbe_mac_X550_vf) + switch (hw->api_version) { + case ixgbe_mbox_api_13: + case ixgbe_mbox_api_12: + if (hw->mac.type >= ixgbe_mac_X550_vf) + break; + default: return -EOPNOTSUPP; + } msgbuf[0] = IXGBE_VF_GET_RETA; @@ -391,9 +396,14 @@ int ixgbevf_get_rss_key_locked(struct ixgbe_hw *hw, u8 *rss_key) * Thus return an error if API doesn't support RSS Random Key retrieval * or if the operation is not supported for this device type. */ - if (hw->api_version != ixgbe_mbox_api_12 || - hw->mac.type >= ixgbe_mac_X550_vf) + switch (hw->api_version) { + case ixgbe_mbox_api_13: + case ixgbe_mbox_api_12: + if (hw->mac.type >= ixgbe_mac_X550_vf) + break; + default: return -EOPNOTSUPP; + } msgbuf[0] = IXGBE_VF_GET_RSS_KEY; err = hw->mbx.ops.write_posted(hw, msgbuf, 1); @@ -545,6 +555,11 @@ static s32 ixgbevf_update_xcast_mode(struct ixgbe_hw *hw, int xcast_mode) switch (hw->api_version) { case ixgbe_mbox_api_12: + /* promisc introduced in 1.3 version */ + if (xcast_mode == IXGBEVF_XCAST_MODE_PROMISC) + return -EOPNOTSUPP; + /* Fall threw */ + case ixgbe_mbox_api_13: break; default: return -EOPNOTSUPP; @@ -884,6 +899,7 @@ int ixgbevf_get_queues(struct ixgbe_hw *hw, unsigned int *num_tcs, switch (hw->api_version) { case ixgbe_mbox_api_11: case ixgbe_mbox_api_12: + case ixgbe_mbox_api_13: break; default: return 0; |