diff options
Diffstat (limited to 'drivers/net/ethernet/intel')
46 files changed, 2812 insertions, 2452 deletions
diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index ada720b42ff6..535f94fac4a1 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -1249,20 +1249,35 @@ static const struct firmware *e100_request_firmware(struct nic *nic) const struct firmware *fw = nic->fw; u8 timer, bundle, min_size; int err = 0; + bool required = false; /* do not load u-code for ICH devices */ if (nic->flags & ich) return NULL; - /* Search for ucode match against h/w revision */ - if (nic->mac == mac_82559_D101M) + /* Search for ucode match against h/w revision + * + * Based on comments in the source code for the FreeBSD fxp + * driver, the FIRMWARE_D102E ucode includes both CPUSaver and + * + * "fixes for bugs in the B-step hardware (specifically, bugs + * with Inline Receive)." + * + * So we must fail if it cannot be loaded. + * + * The other microcode files are only required for the optional + * CPUSaver feature. Nice to have, but no reason to fail. + */ + if (nic->mac == mac_82559_D101M) { fw_name = FIRMWARE_D101M; - else if (nic->mac == mac_82559_D101S) + } else if (nic->mac == mac_82559_D101S) { fw_name = FIRMWARE_D101S; - else if (nic->mac == mac_82551_F || nic->mac == mac_82551_10) + } else if (nic->mac == mac_82551_F || nic->mac == mac_82551_10) { fw_name = FIRMWARE_D102E; - else /* No ucode on other devices */ + required = true; + } else { /* No ucode on other devices */ return NULL; + } /* If the firmware has not previously been loaded, request a pointer * to it. If it was previously loaded, we are reinitializing the @@ -1273,10 +1288,17 @@ static const struct firmware *e100_request_firmware(struct nic *nic) err = request_firmware(&fw, fw_name, &nic->pdev->dev); if (err) { - netif_err(nic, probe, nic->netdev, - "Failed to load firmware \"%s\": %d\n", - fw_name, err); - return ERR_PTR(err); + if (required) { + netif_err(nic, probe, nic->netdev, + "Failed to load firmware \"%s\": %d\n", + fw_name, err); + return ERR_PTR(err); + } else { + netif_info(nic, probe, nic->netdev, + "CPUSaver disabled. Needs \"%s\": %d\n", + fw_name, err); + return NULL; + } } /* Firmware should be precisely UCODE_SIZE (words) plus three bytes diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c index 3103f0b6bf5e..736a7d987db5 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c +++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c @@ -1851,6 +1851,7 @@ static const struct ethtool_ops e1000_ethtool_ops = { .get_sset_count = e1000_get_sset_count, .get_coalesce = e1000_get_coalesce, .set_coalesce = e1000_set_coalesce, + .get_ts_info = ethtool_op_get_ts_info, }; void e1000_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/intel/e1000/e1000_hw.c b/drivers/net/ethernet/intel/e1000/e1000_hw.c index c526279e4927..3d6839528761 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_hw.c +++ b/drivers/net/ethernet/intel/e1000/e1000_hw.c @@ -399,7 +399,7 @@ void e1000_set_media_type(struct e1000_hw *hw) } /** - * e1000_reset_hw: reset the hardware completely + * e1000_reset_hw - reset the hardware completely * @hw: Struct containing variables accessed by shared code * * Reset the transmit and receive units; mask and clear all interrupts. @@ -546,7 +546,7 @@ s32 e1000_reset_hw(struct e1000_hw *hw) } /** - * e1000_init_hw: Performs basic configuration of the adapter. + * e1000_init_hw - Performs basic configuration of the adapter. * @hw: Struct containing variables accessed by shared code * * Assumes that the controller has previously been reset and is in a @@ -2591,7 +2591,7 @@ s32 e1000_check_for_link(struct e1000_hw *hw) * @hw: Struct containing variables accessed by shared code * @speed: Speed of the connection * @duplex: Duplex setting of the connection - + * * Detects the current speed and duplex settings of the hardware. */ s32 e1000_get_speed_and_duplex(struct e1000_hw *hw, u16 *speed, u16 *duplex) @@ -2959,7 +2959,7 @@ static s32 e1000_read_phy_reg_ex(struct e1000_hw *hw, u32 reg_addr, * @hw: Struct containing variables accessed by shared code * @reg_addr: address of the PHY register to write * @data: data to write to the PHY - + * * Writes a value to a PHY register */ s32 e1000_write_phy_reg(struct e1000_hw *hw, u32 reg_addr, u16 phy_data) diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 7483ca0a6282..3bfbb8df8989 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -721,9 +721,7 @@ void e1000_reset(struct e1000_adapter *adapter) e1000_release_manageability(adapter); } -/** - * Dump the eeprom for users having checksum issues - **/ +/* Dump the eeprom for users having checksum issues */ static void e1000_dump_eeprom(struct e1000_adapter *adapter) { struct net_device *netdev = adapter->netdev; @@ -1078,18 +1076,18 @@ static int __devinit e1000_probe(struct pci_dev *pdev, netdev->priv_flags |= IFF_SUPP_NOFCS; netdev->features |= netdev->hw_features; - netdev->hw_features |= NETIF_F_RXCSUM; - netdev->hw_features |= NETIF_F_RXALL; - netdev->hw_features |= NETIF_F_RXFCS; + netdev->hw_features |= (NETIF_F_RXCSUM | + NETIF_F_RXALL | + NETIF_F_RXFCS); if (pci_using_dac) { netdev->features |= NETIF_F_HIGHDMA; netdev->vlan_features |= NETIF_F_HIGHDMA; } - netdev->vlan_features |= NETIF_F_TSO; - netdev->vlan_features |= NETIF_F_HW_CSUM; - netdev->vlan_features |= NETIF_F_SG; + netdev->vlan_features |= (NETIF_F_TSO | + NETIF_F_HW_CSUM | + NETIF_F_SG); netdev->priv_flags |= IFF_UNICAST_FLT; @@ -3056,14 +3054,13 @@ static void e1000_tx_queue(struct e1000_adapter *adapter, mmiowb(); } -/** - * 82547 workaround to avoid controller hang in half-duplex environment. +/* 82547 workaround to avoid controller hang in half-duplex environment. * The workaround is to avoid queuing a large packet that would span * the internal Tx FIFO ring boundary by notifying the stack to resend * the packet at a later time. This gives the Tx FIFO an opportunity to * flush all packets. When that occurs, we reset the Tx FIFO pointers * to the beginning of the Tx FIFO. - **/ + */ #define E1000_FIFO_HDR 0x10 #define E1000_82547_PAD_LEN 0x3E0 diff --git a/drivers/net/ethernet/intel/e1000e/82571.c b/drivers/net/ethernet/intel/e1000e/82571.c index 36db4df09aed..0b3bade957fd 100644 --- a/drivers/net/ethernet/intel/e1000e/82571.c +++ b/drivers/net/ethernet/intel/e1000e/82571.c @@ -1572,6 +1572,9 @@ static s32 e1000_check_for_serdes_link_82571(struct e1000_hw *hw) ctrl = er32(CTRL); status = er32(STATUS); rxcw = er32(RXCW); + /* SYNCH bit and IV bit are sticky */ + udelay(10); + rxcw = er32(RXCW); if ((rxcw & E1000_RXCW_SYNCH) && !(rxcw & E1000_RXCW_IV)) { @@ -1677,16 +1680,18 @@ static s32 e1000_check_for_serdes_link_82571(struct e1000_hw *hw) e_dbg("ANYSTATE -> DOWN\n"); } else { /* - * Check several times, if Sync and Config - * both are consistently 1 then simply ignore - * the Invalid bit and restart Autoneg + * Check several times, if SYNCH bit and CONFIG + * bit both are consistently 1 then simply ignore + * the IV bit and restart Autoneg */ for (i = 0; i < AN_RETRY_COUNT; i++) { udelay(10); rxcw = er32(RXCW); - if ((rxcw & E1000_RXCW_IV) && - !((rxcw & E1000_RXCW_SYNCH) && - (rxcw & E1000_RXCW_C))) { + if ((rxcw & E1000_RXCW_SYNCH) && + (rxcw & E1000_RXCW_C)) + continue; + + if (rxcw & E1000_RXCW_IV) { mac->serdes_has_link = false; mac->serdes_link_state = e1000_serdes_link_down; diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h index 351a4097b2ba..76edbc1be33b 100644 --- a/drivers/net/ethernet/intel/e1000e/defines.h +++ b/drivers/net/ethernet/intel/e1000e/defines.h @@ -103,6 +103,7 @@ #define E1000_RXD_ERR_SEQ 0x04 /* Sequence Error */ #define E1000_RXD_ERR_CXE 0x10 /* Carrier Extension Error */ #define E1000_RXD_ERR_TCPE 0x20 /* TCP/UDP Checksum Error */ +#define E1000_RXD_ERR_IPE 0x40 /* IP Checksum Error */ #define E1000_RXD_ERR_RXE 0x80 /* Rx Data Error */ #define E1000_RXD_SPC_VLAN_MASK 0x0FFF /* VLAN ID is in lower 12 bits */ diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index 6e6fffb34581..cd153326c3cf 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -514,6 +514,7 @@ extern void e1000e_set_interrupt_capability(struct e1000_adapter *adapter); extern void e1000e_reset_interrupt_capability(struct e1000_adapter *adapter); extern void e1000e_get_hw_control(struct e1000_adapter *adapter); extern void e1000e_release_hw_control(struct e1000_adapter *adapter); +extern void e1000e_write_itr(struct e1000_adapter *adapter, u32 itr); extern unsigned int copybreak; diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index 905e2147d918..0349e2478df8 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -1897,7 +1897,6 @@ static int e1000_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec) { struct e1000_adapter *adapter = netdev_priv(netdev); - struct e1000_hw *hw = &adapter->hw; if ((ec->rx_coalesce_usecs > E1000_MAX_ITR_USECS) || ((ec->rx_coalesce_usecs > 4) && @@ -1916,9 +1915,9 @@ static int e1000_set_coalesce(struct net_device *netdev, } if (adapter->itr_setting != 0) - ew32(ITR, 1000000000 / (adapter->itr * 256)); + e1000e_write_itr(adapter, adapter->itr); else - ew32(ITR, 0); + e1000e_write_itr(adapter, 0); return 0; } @@ -2062,6 +2061,7 @@ static const struct ethtool_ops e1000_ethtool_ops = { .get_coalesce = e1000_get_coalesce, .set_coalesce = e1000_set_coalesce, .get_rxnfc = e1000_get_rxnfc, + .get_ts_info = ethtool_op_get_ts_info, }; void e1000e_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 238ab2f8a5e7..e3a7b07df629 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -325,24 +325,46 @@ static inline void __ew32flash(struct e1000_hw *hw, unsigned long reg, u32 val) **/ static bool e1000_phy_is_accessible_pchlan(struct e1000_hw *hw) { - u16 phy_reg; - u32 phy_id; + u16 phy_reg = 0; + u32 phy_id = 0; + s32 ret_val; + u16 retry_count; + + for (retry_count = 0; retry_count < 2; retry_count++) { + ret_val = e1e_rphy_locked(hw, PHY_ID1, &phy_reg); + if (ret_val || (phy_reg == 0xFFFF)) + continue; + phy_id = (u32)(phy_reg << 16); - e1e_rphy_locked(hw, PHY_ID1, &phy_reg); - phy_id = (u32)(phy_reg << 16); - e1e_rphy_locked(hw, PHY_ID2, &phy_reg); - phy_id |= (u32)(phy_reg & PHY_REVISION_MASK); + ret_val = e1e_rphy_locked(hw, PHY_ID2, &phy_reg); + if (ret_val || (phy_reg == 0xFFFF)) { + phy_id = 0; + continue; + } + phy_id |= (u32)(phy_reg & PHY_REVISION_MASK); + break; + } if (hw->phy.id) { if (hw->phy.id == phy_id) return true; - } else { - if ((phy_id != 0) && (phy_id != PHY_REVISION_MASK)) - hw->phy.id = phy_id; + } else if (phy_id) { + hw->phy.id = phy_id; + hw->phy.revision = (u32)(phy_reg & ~PHY_REVISION_MASK); return true; } - return false; + /* + * In case the PHY needs to be in mdio slow mode, + * set slow mode and try to get the PHY id again. + */ + hw->phy.ops.release(hw); + ret_val = e1000_set_mdio_slow_mode_hv(hw); + if (!ret_val) + ret_val = e1000e_get_phy_id(hw); + hw->phy.ops.acquire(hw); + + return !ret_val; } /** diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 31d37a2b5ba8..95b245310f17 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -496,7 +496,7 @@ static void e1000_receive_skb(struct e1000_adapter *adapter, * @sk_buff: socket buffer with received data **/ static void e1000_rx_checksum(struct e1000_adapter *adapter, u32 status_err, - __le16 csum, struct sk_buff *skb) + struct sk_buff *skb) { u16 status = (u16)status_err; u8 errors = (u8)(status_err >> 24); @@ -511,8 +511,8 @@ static void e1000_rx_checksum(struct e1000_adapter *adapter, u32 status_err, if (status & E1000_RXD_STAT_IXSM) return; - /* TCP/UDP checksum error bit is set */ - if (errors & E1000_RXD_ERR_TCPE) { + /* TCP/UDP checksum error bit or IP checksum error bit is set */ + if (errors & (E1000_RXD_ERR_TCPE | E1000_RXD_ERR_IPE)) { /* let the stack verify checksum errors */ adapter->hw_csum_err++; return; @@ -523,19 +523,7 @@ static void e1000_rx_checksum(struct e1000_adapter *adapter, u32 status_err, return; /* It must be a TCP or UDP packet with a valid checksum */ - if (status & E1000_RXD_STAT_TCPCS) { - /* TCP checksum is good */ - skb->ip_summed = CHECKSUM_UNNECESSARY; - } else { - /* - * IP fragment with UDP payload - * Hardware complements the payload checksum, so we undo it - * and then put the value in host order for further stack use. - */ - __sum16 sum = (__force __sum16)swab16((__force u16)csum); - skb->csum = csum_unfold(~sum); - skb->ip_summed = CHECKSUM_COMPLETE; - } + skb->ip_summed = CHECKSUM_UNNECESSARY; adapter->hw_csum_good++; } @@ -954,8 +942,7 @@ static bool e1000_clean_rx_irq(struct e1000_ring *rx_ring, int *work_done, skb_put(skb, length); /* Receive Checksum Offload */ - e1000_rx_checksum(adapter, staterr, - rx_desc->wb.lower.hi_dword.csum_ip.csum, skb); + e1000_rx_checksum(adapter, staterr, skb); e1000_rx_hash(netdev, rx_desc->wb.lower.hi_dword.rss, skb); @@ -1341,8 +1328,7 @@ copydone: total_rx_bytes += skb->len; total_rx_packets++; - e1000_rx_checksum(adapter, staterr, - rx_desc->wb.lower.hi_dword.csum_ip.csum, skb); + e1000_rx_checksum(adapter, staterr, skb); e1000_rx_hash(netdev, rx_desc->wb.lower.hi_dword.rss, skb); @@ -1512,9 +1498,8 @@ static bool e1000_clean_jumbo_rx_irq(struct e1000_ring *rx_ring, int *work_done, } } - /* Receive Checksum Offload XXX recompute due to CRC strip? */ - e1000_rx_checksum(adapter, staterr, - rx_desc->wb.lower.hi_dword.csum_ip.csum, skb); + /* Receive Checksum Offload */ + e1000_rx_checksum(adapter, staterr, skb); e1000_rx_hash(netdev, rx_desc->wb.lower.hi_dword.rss, skb); @@ -2174,7 +2159,7 @@ void e1000e_release_hw_control(struct e1000_adapter *adapter) } /** - * @e1000_alloc_ring - allocate memory for a ring structure + * e1000_alloc_ring_dma - allocate memory for a ring structure **/ static int e1000_alloc_ring_dma(struct e1000_adapter *adapter, struct e1000_ring *ring) @@ -2489,6 +2474,30 @@ set_itr_now: } /** + * e1000e_write_itr - write the ITR value to the appropriate registers + * @adapter: address of board private structure + * @itr: new ITR value to program + * + * e1000e_write_itr determines if the adapter is in MSI-X mode + * and, if so, writes the EITR registers with the ITR value. + * Otherwise, it writes the ITR value into the ITR register. + **/ +void e1000e_write_itr(struct e1000_adapter *adapter, u32 itr) +{ + struct e1000_hw *hw = &adapter->hw; + u32 new_itr = itr ? 1000000000 / (itr * 256) : 0; + + if (adapter->msix_entries) { + int vector; + + for (vector = 0; vector < adapter->num_vectors; vector++) + writel(new_itr, hw->hw_addr + E1000_EITR_82574(vector)); + } else { + ew32(ITR, new_itr); + } +} + +/** * e1000_alloc_queues - Allocate memory for all rings * @adapter: board private structure to initialize **/ @@ -3074,7 +3083,7 @@ static void e1000_configure_rx(struct e1000_adapter *adapter) /* irq moderation */ ew32(RADV, adapter->rx_abs_int_delay); if ((adapter->itr_setting != 0) && (adapter->itr != 0)) - ew32(ITR, 1000000000 / (adapter->itr * 256)); + e1000e_write_itr(adapter, adapter->itr); ctrl_ext = er32(CTRL_EXT); /* Auto-Mask interrupts upon ICR access */ @@ -3098,19 +3107,10 @@ static void e1000_configure_rx(struct e1000_adapter *adapter) /* Enable Receive Checksum Offload for TCP and UDP */ rxcsum = er32(RXCSUM); - if (adapter->netdev->features & NETIF_F_RXCSUM) { + if (adapter->netdev->features & NETIF_F_RXCSUM) rxcsum |= E1000_RXCSUM_TUOFL; - - /* - * IPv4 payload checksum for UDP fragments must be - * used in conjunction with packet-split. - */ - if (adapter->rx_ps_pages) - rxcsum |= E1000_RXCSUM_IPPCSE; - } else { + else rxcsum &= ~E1000_RXCSUM_TUOFL; - /* no need to clear IPPCSE as it defaults to 0 */ - } ew32(RXCSUM, rxcsum); if (adapter->hw.mac.type == e1000_pch2lan) { @@ -3510,14 +3510,14 @@ void e1000e_reset(struct e1000_adapter *adapter) dev_info(&adapter->pdev->dev, "Interrupt Throttle Rate turned off\n"); adapter->flags2 |= FLAG2_DISABLE_AIM; - ew32(ITR, 0); + e1000e_write_itr(adapter, 0); } } else if (adapter->flags2 & FLAG2_DISABLE_AIM) { dev_info(&adapter->pdev->dev, "Interrupt Throttle Rate turned on\n"); adapter->flags2 &= ~FLAG2_DISABLE_AIM; adapter->itr = 20000; - ew32(ITR, 1000000000 / (adapter->itr * 256)); + e1000e_write_itr(adapter, adapter->itr); } } @@ -4600,7 +4600,7 @@ link_up: adapter->gorc - adapter->gotc) / 10000; u32 itr = goc > 0 ? (dif * 6000 / goc + 2000) : 8000; - ew32(ITR, 1000000000 / (itr * 256)); + e1000e_write_itr(adapter, itr); } /* Cause software interrupt to ensure Rx ring is cleaned */ @@ -5241,22 +5241,10 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu) int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN; /* Jumbo frame support */ - if (max_frame > ETH_FRAME_LEN + ETH_FCS_LEN) { - if (!(adapter->flags & FLAG_HAS_JUMBO_FRAMES)) { - e_err("Jumbo Frames not supported.\n"); - return -EINVAL; - } - - /* - * IP payload checksum (enabled with jumbos/packet-split when - * Rx checksum is enabled) and generation of RSS hash is - * mutually exclusive in the hardware. - */ - if ((netdev->features & NETIF_F_RXCSUM) && - (netdev->features & NETIF_F_RXHASH)) { - e_err("Jumbo frames cannot be enabled when both receive checksum offload and receive hashing are enabled. Disable one of the receive offload features before enabling jumbos.\n"); - return -EINVAL; - } + if ((max_frame > ETH_FRAME_LEN + ETH_FCS_LEN) && + !(adapter->flags & FLAG_HAS_JUMBO_FRAMES)) { + e_err("Jumbo Frames not supported.\n"); + return -EINVAL; } /* Supported frame sizes */ @@ -6030,17 +6018,6 @@ static int e1000_set_features(struct net_device *netdev, NETIF_F_RXALL))) return 0; - /* - * IP payload checksum (enabled with jumbos/packet-split when Rx - * checksum is enabled) and generation of RSS hash is mutually - * exclusive in the hardware. - */ - if (adapter->rx_ps_pages && - (features & NETIF_F_RXCSUM) && (features & NETIF_F_RXHASH)) { - e_err("Enabling both receive checksum offload and receive hashing is not possible with jumbo frames. Disable jumbos or enable only one of the receive offload features.\n"); - return -EINVAL; - } - if (changed & NETIF_F_RXFCS) { if (features & NETIF_F_RXFCS) { adapter->flags2 &= ~FLAG2_CRC_STRIPPING; @@ -6238,7 +6215,8 @@ static int __devinit e1000_probe(struct pci_dev *pdev, } if (hw->phy.ops.check_reset_block && hw->phy.ops.check_reset_block(hw)) - e_info("PHY reset is blocked due to SOL/IDER session.\n"); + dev_info(&pdev->dev, + "PHY reset is blocked due to SOL/IDER session.\n"); /* Set initial default active device features */ netdev->features = (NETIF_F_SG | @@ -6288,7 +6266,7 @@ static int __devinit e1000_probe(struct pci_dev *pdev, if (e1000_validate_nvm_checksum(&adapter->hw) >= 0) break; if (i == 2) { - e_err("The NVM Checksum Is Not Valid\n"); + dev_err(&pdev->dev, "The NVM Checksum Is Not Valid\n"); err = -EIO; goto err_eeprom; } @@ -6298,13 +6276,15 @@ static int __devinit e1000_probe(struct pci_dev *pdev, /* copy the MAC address */ if (e1000e_read_mac_addr(&adapter->hw)) - e_err("NVM Read Error while reading MAC address\n"); + dev_err(&pdev->dev, + "NVM Read Error while reading MAC address\n"); memcpy(netdev->dev_addr, adapter->hw.mac.addr, netdev->addr_len); memcpy(netdev->perm_addr, adapter->hw.mac.addr, netdev->addr_len); if (!is_valid_ether_addr(netdev->perm_addr)) { - e_err("Invalid MAC Address: %pM\n", netdev->perm_addr); + dev_err(&pdev->dev, "Invalid MAC Address: %pM\n", + netdev->perm_addr); err = -EIO; goto err_eeprom; } diff --git a/drivers/net/ethernet/intel/e1000e/param.c b/drivers/net/ethernet/intel/e1000e/param.c index 55cc1565bc2f..dfbfa7fd98c3 100644 --- a/drivers/net/ethernet/intel/e1000e/param.c +++ b/drivers/net/ethernet/intel/e1000e/param.c @@ -199,16 +199,19 @@ static int __devinit e1000_validate_option(unsigned int *value, case enable_option: switch (*value) { case OPTION_ENABLED: - e_info("%s Enabled\n", opt->name); + dev_info(&adapter->pdev->dev, "%s Enabled\n", + opt->name); return 0; case OPTION_DISABLED: - e_info("%s Disabled\n", opt->name); + dev_info(&adapter->pdev->dev, "%s Disabled\n", + opt->name); return 0; } break; case range_option: if (*value >= opt->arg.r.min && *value <= opt->arg.r.max) { - e_info("%s set to %i\n", opt->name, *value); + dev_info(&adapter->pdev->dev, "%s set to %i\n", + opt->name, *value); return 0; } break; @@ -220,7 +223,8 @@ static int __devinit e1000_validate_option(unsigned int *value, ent = &opt->arg.l.p[i]; if (*value == ent->i) { if (ent->str[0] != '\0') - e_info("%s\n", ent->str); + dev_info(&adapter->pdev->dev, "%s\n", + ent->str); return 0; } } @@ -230,8 +234,8 @@ static int __devinit e1000_validate_option(unsigned int *value, BUG(); } - e_info("Invalid %s value specified (%i) %s\n", opt->name, *value, - opt->err); + dev_info(&adapter->pdev->dev, "Invalid %s value specified (%i) %s\n", + opt->name, *value, opt->err); *value = opt->def; return -1; } @@ -251,8 +255,10 @@ void __devinit e1000e_check_options(struct e1000_adapter *adapter) int bd = adapter->bd_number; if (bd >= E1000_MAX_NIC) { - e_notice("Warning: no configuration for board #%i\n", bd); - e_notice("Using defaults for all values\n"); + dev_notice(&adapter->pdev->dev, + "Warning: no configuration for board #%i\n", bd); + dev_notice(&adapter->pdev->dev, + "Using defaults for all values\n"); } { /* Transmit Interrupt Delay */ @@ -366,27 +372,32 @@ void __devinit e1000e_check_options(struct e1000_adapter *adapter) * default values */ if (adapter->itr > 4) - e_info("%s set to default %d\n", opt.name, - adapter->itr); + dev_info(&adapter->pdev->dev, + "%s set to default %d\n", opt.name, + adapter->itr); } adapter->itr_setting = adapter->itr; switch (adapter->itr) { case 0: - e_info("%s turned off\n", opt.name); + dev_info(&adapter->pdev->dev, "%s turned off\n", + opt.name); break; case 1: - e_info("%s set to dynamic mode\n", opt.name); + dev_info(&adapter->pdev->dev, + "%s set to dynamic mode\n", opt.name); adapter->itr = 20000; break; case 3: - e_info("%s set to dynamic conservative mode\n", - opt.name); + dev_info(&adapter->pdev->dev, + "%s set to dynamic conservative mode\n", + opt.name); adapter->itr = 20000; break; case 4: - e_info("%s set to simplified (2000-8000 ints) mode\n", - opt.name); + dev_info(&adapter->pdev->dev, + "%s set to simplified (2000-8000 ints) mode\n", + opt.name); break; default: /* diff --git a/drivers/net/ethernet/intel/igb/e1000_regs.h b/drivers/net/ethernet/intel/igb/e1000_regs.h index 35d1e4f2c92c..10efcd88dca0 100644 --- a/drivers/net/ethernet/intel/igb/e1000_regs.h +++ b/drivers/net/ethernet/intel/igb/e1000_regs.h @@ -117,6 +117,7 @@ /* TX Rate Limit Registers */ #define E1000_RTTDQSEL 0x3604 /* Tx Desc Plane Queue Select - WO */ +#define E1000_RTTBCNRM 0x3690 /* Tx BCN Rate-scheduler MMW */ #define E1000_RTTBCNRC 0x36B0 /* Tx BCN Rate-Scheduler Config - WO */ /* Split and Replication RX Control - RW */ diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index ae6d3f393a54..9e572dd29ab2 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -65,19 +65,30 @@ struct igb_adapter; #define MAX_Q_VECTORS 8 /* Transmit and receive queues */ -#define IGB_MAX_RX_QUEUES ((adapter->vfs_allocated_count ? 2 : \ - (hw->mac.type > e1000_82575 ? 8 : 4))) -#define IGB_MAX_RX_QUEUES_I210 4 +#define IGB_MAX_RX_QUEUES 8 +#define IGB_MAX_RX_QUEUES_82575 4 #define IGB_MAX_RX_QUEUES_I211 2 -#define IGB_MAX_TX_QUEUES 16 -#define IGB_MAX_TX_QUEUES_I210 4 -#define IGB_MAX_TX_QUEUES_I211 2 +#define IGB_MAX_TX_QUEUES 8 #define IGB_MAX_VF_MC_ENTRIES 30 #define IGB_MAX_VF_FUNCTIONS 8 #define IGB_MAX_VFTA_ENTRIES 128 #define IGB_82576_VF_DEV_ID 0x10CA #define IGB_I350_VF_DEV_ID 0x1520 +/* NVM version defines */ +#define IGB_MAJOR_MASK 0xF000 +#define IGB_MINOR_MASK 0x0FF0 +#define IGB_BUILD_MASK 0x000F +#define IGB_COMB_VER_MASK 0x00FF +#define IGB_MAJOR_SHIFT 12 +#define IGB_MINOR_SHIFT 4 +#define IGB_COMB_VER_SHFT 8 +#define IGB_NVM_VER_INVALID 0xFFFF +#define IGB_ETRACK_SHIFT 16 +#define NVM_ETRACK_WORD 0x0042 +#define NVM_COMB_VER_OFF 0x0083 +#define NVM_COMB_VER_PTR 0x003d + struct vf_data_storage { unsigned char vf_mac_addresses[ETH_ALEN]; u16 vf_mc_hashes[IGB_MAX_VF_MC_ENTRIES]; @@ -371,6 +382,7 @@ struct igb_adapter { spinlock_t tmreg_lock; struct cyclecounter cc; struct timecounter tc; + char fw_version[32]; }; #define IGB_FLAG_HAS_MSI (1 << 0) @@ -420,6 +432,7 @@ extern void igb_update_stats(struct igb_adapter *, struct rtnl_link_stats64 *); extern bool igb_has_link(struct igb_adapter *adapter); extern void igb_set_ethtool_ops(struct net_device *); extern void igb_power_up_link(struct igb_adapter *); +extern void igb_set_fw_version(struct igb_adapter *); #ifdef CONFIG_IGB_PTP extern void igb_ptp_init(struct igb_adapter *adapter); extern void igb_ptp_remove(struct igb_adapter *adapter); diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 812d4f963bd1..a19c84cad0e9 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -710,6 +710,7 @@ static int igb_set_eeprom(struct net_device *netdev, if ((ret_val == 0) && ((first_word <= NVM_CHECKSUM_REG))) hw->nvm.ops.update(hw); + igb_set_fw_version(adapter); kfree(eeprom_buff); return ret_val; } @@ -718,20 +719,16 @@ static void igb_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) { struct igb_adapter *adapter = netdev_priv(netdev); - u16 eeprom_data; strlcpy(drvinfo->driver, igb_driver_name, sizeof(drvinfo->driver)); strlcpy(drvinfo->version, igb_driver_version, sizeof(drvinfo->version)); - /* EEPROM image version # is reported as firmware version # for - * 82575 controllers */ - adapter->hw.nvm.ops.read(&adapter->hw, 5, 1, &eeprom_data); - snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), - "%d.%d-%d", - (eeprom_data & 0xF000) >> 12, - (eeprom_data & 0x0FF0) >> 4, - eeprom_data & 0x000F); - + /* + * EEPROM image version # is reported as firmware version # for + * 82575 controllers + */ + strlcpy(drvinfo->fw_version, adapter->fw_version, + sizeof(drvinfo->fw_version)); strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); drvinfo->n_stats = IGB_STATS_LEN; @@ -2271,6 +2268,38 @@ static void igb_ethtool_complete(struct net_device *netdev) pm_runtime_put(&adapter->pdev->dev); } +#ifdef CONFIG_IGB_PTP +static int igb_ethtool_get_ts_info(struct net_device *dev, + struct ethtool_ts_info *info) +{ + struct igb_adapter *adapter = netdev_priv(dev); + + info->so_timestamping = + SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + + if (adapter->ptp_clock) + info->phc_index = ptp_clock_index(adapter->ptp_clock); + else + info->phc_index = -1; + + info->tx_types = + (1 << HWTSTAMP_TX_OFF) | + (1 << HWTSTAMP_TX_ON); + + info->rx_filters = + (1 << HWTSTAMP_FILTER_NONE) | + (1 << HWTSTAMP_FILTER_ALL) | + (1 << HWTSTAMP_FILTER_SOME) | + (1 << HWTSTAMP_FILTER_PTP_V1_L4_SYNC) | + (1 << HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) | + (1 << HWTSTAMP_FILTER_PTP_V2_EVENT); + + return 0; +} + +#endif static const struct ethtool_ops igb_ethtool_ops = { .get_settings = igb_get_settings, .set_settings = igb_set_settings, @@ -2299,6 +2328,9 @@ static const struct ethtool_ops igb_ethtool_ops = { .set_coalesce = igb_set_coalesce, .begin = igb_ethtool_begin, .complete = igb_ethtool_complete, +#ifdef CONFIG_IGB_PTP + .get_ts_info = igb_ethtool_get_ts_info, +#endif }; void igb_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index dd3bfe8cd36c..b7c2d5050572 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -59,9 +59,9 @@ #endif #include "igb.h" -#define MAJ 3 -#define MIN 4 -#define BUILD 7 +#define MAJ 4 +#define MIN 0 +#define BUILD 1 #define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) "." \ __stringify(BUILD) "-k" char igb_driver_name[] = "igb"; @@ -1048,11 +1048,6 @@ static int igb_set_interrupt_capability(struct igb_adapter *adapter) if (!(adapter->flags & IGB_FLAG_QUEUE_PAIRS)) numvecs += adapter->num_tx_queues; - /* i210 and i211 can only have 4 MSIX vectors for rx/tx queues. */ - if ((adapter->hw.mac.type == e1000_i210) - || (adapter->hw.mac.type == e1000_i211)) - numvecs = 4; - /* store the number of vectors reserved for queues */ adapter->num_q_vectors = numvecs; @@ -1505,11 +1500,12 @@ static void igb_configure(struct igb_adapter *adapter) **/ void igb_power_up_link(struct igb_adapter *adapter) { + igb_reset_phy(&adapter->hw); + if (adapter->hw.phy.media_type == e1000_media_type_copper) igb_power_up_phy_copper(&adapter->hw); else igb_power_up_serdes_link_82575(&adapter->hw); - igb_reset_phy(&adapter->hw); } /** @@ -1821,6 +1817,69 @@ static const struct net_device_ops igb_netdev_ops = { }; /** + * igb_set_fw_version - Configure version string for ethtool + * @adapter: adapter struct + * + **/ +void igb_set_fw_version(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u16 eeprom_verh, eeprom_verl, comb_verh, comb_verl, comb_offset; + u16 major, build, patch, fw_version; + u32 etrack_id; + + hw->nvm.ops.read(hw, 5, 1, &fw_version); + if (adapter->hw.mac.type != e1000_i211) { + hw->nvm.ops.read(hw, NVM_ETRACK_WORD, 1, &eeprom_verh); + hw->nvm.ops.read(hw, (NVM_ETRACK_WORD + 1), 1, &eeprom_verl); + etrack_id = (eeprom_verh << IGB_ETRACK_SHIFT) | eeprom_verl; + + /* combo image version needs to be found */ + hw->nvm.ops.read(hw, NVM_COMB_VER_PTR, 1, &comb_offset); + if ((comb_offset != 0x0) && + (comb_offset != IGB_NVM_VER_INVALID)) { + hw->nvm.ops.read(hw, (NVM_COMB_VER_OFF + comb_offset + + 1), 1, &comb_verh); + hw->nvm.ops.read(hw, (NVM_COMB_VER_OFF + comb_offset), + 1, &comb_verl); + + /* Only display Option Rom if it exists and is valid */ + if ((comb_verh && comb_verl) && + ((comb_verh != IGB_NVM_VER_INVALID) && + (comb_verl != IGB_NVM_VER_INVALID))) { + major = comb_verl >> IGB_COMB_VER_SHFT; + build = (comb_verl << IGB_COMB_VER_SHFT) | + (comb_verh >> IGB_COMB_VER_SHFT); + patch = comb_verh & IGB_COMB_VER_MASK; + snprintf(adapter->fw_version, + sizeof(adapter->fw_version), + "%d.%d%d, 0x%08x, %d.%d.%d", + (fw_version & IGB_MAJOR_MASK) >> + IGB_MAJOR_SHIFT, + (fw_version & IGB_MINOR_MASK) >> + IGB_MINOR_SHIFT, + (fw_version & IGB_BUILD_MASK), + etrack_id, major, build, patch); + goto out; + } + } + snprintf(adapter->fw_version, sizeof(adapter->fw_version), + "%d.%d%d, 0x%08x", + (fw_version & IGB_MAJOR_MASK) >> IGB_MAJOR_SHIFT, + (fw_version & IGB_MINOR_MASK) >> IGB_MINOR_SHIFT, + (fw_version & IGB_BUILD_MASK), etrack_id); + } else { + snprintf(adapter->fw_version, sizeof(adapter->fw_version), + "%d.%d%d", + (fw_version & IGB_MAJOR_MASK) >> IGB_MAJOR_SHIFT, + (fw_version & IGB_MINOR_MASK) >> IGB_MINOR_SHIFT, + (fw_version & IGB_BUILD_MASK)); + } +out: + return; +} + +/** * igb_probe - Device Initialization Routine * @pdev: PCI device information struct * @ent: entry in igb_pci_tbl @@ -2030,6 +2089,9 @@ static int __devinit igb_probe(struct pci_dev *pdev, goto err_eeprom; } + /* get firmware version for ethtool -i */ + igb_set_fw_version(adapter); + setup_timer(&adapter->watchdog_timer, igb_watchdog, (unsigned long) adapter); setup_timer(&adapter->phy_info_timer, igb_update_phy_info, @@ -2338,6 +2400,7 @@ static int __devinit igb_sw_init(struct igb_adapter *adapter) struct e1000_hw *hw = &adapter->hw; struct net_device *netdev = adapter->netdev; struct pci_dev *pdev = adapter->pdev; + u32 max_rss_queues; pci_read_config_word(pdev, PCI_COMMAND, &hw->bus.pci_cmd_word); @@ -2370,40 +2433,69 @@ static int __devinit igb_sw_init(struct igb_adapter *adapter) } else adapter->vfs_allocated_count = max_vfs; break; - case e1000_i210: - case e1000_i211: - adapter->vfs_allocated_count = 0; - break; default: break; } #endif /* CONFIG_PCI_IOV */ + + /* Determine the maximum number of RSS queues supported. */ switch (hw->mac.type) { + case e1000_i211: + max_rss_queues = IGB_MAX_RX_QUEUES_I211; + break; + case e1000_82575: case e1000_i210: - adapter->rss_queues = min_t(u32, IGB_MAX_RX_QUEUES_I210, - num_online_cpus()); + max_rss_queues = IGB_MAX_RX_QUEUES_82575; + break; + case e1000_i350: + /* I350 cannot do RSS and SR-IOV at the same time */ + if (!!adapter->vfs_allocated_count) { + max_rss_queues = 1; + break; + } + /* fall through */ + case e1000_82576: + if (!!adapter->vfs_allocated_count) { + max_rss_queues = 2; + break; + } + /* fall through */ + case e1000_82580: + default: + max_rss_queues = IGB_MAX_RX_QUEUES; break; + } + + adapter->rss_queues = min_t(u32, max_rss_queues, num_online_cpus()); + + /* Determine if we need to pair queues. */ + switch (hw->mac.type) { + case e1000_82575: case e1000_i211: - adapter->rss_queues = min_t(u32, IGB_MAX_RX_QUEUES_I211, - num_online_cpus()); + /* Device supports enough interrupts without queue pairing. */ break; + case e1000_82576: + /* + * If VFs are going to be allocated with RSS queues then we + * should pair the queues in order to conserve interrupts due + * to limited supply. + */ + if ((adapter->rss_queues > 1) && + (adapter->vfs_allocated_count > 6)) + adapter->flags |= IGB_FLAG_QUEUE_PAIRS; + /* fall through */ + case e1000_82580: + case e1000_i350: + case e1000_i210: default: - adapter->rss_queues = min_t(u32, IGB_MAX_RX_QUEUES, - num_online_cpus()); + /* + * If rss_queues > half of max_rss_queues, pair the queues in + * order to conserve interrupts due to limited supply. + */ + if (adapter->rss_queues > (max_rss_queues / 2)) + adapter->flags |= IGB_FLAG_QUEUE_PAIRS; break; } - /* i350 cannot do RSS and SR-IOV at the same time */ - if (hw->mac.type == e1000_i350 && adapter->vfs_allocated_count) - adapter->rss_queues = 1; - - /* - * if rss_queues > 4 or vfs are going to be allocated with rss_queues - * then we should combine the queues into a queue pair in order to - * conserve interrupts due to limited supply - */ - if ((adapter->rss_queues > 4) || - ((adapter->rss_queues > 1) && (adapter->vfs_allocated_count > 6))) - adapter->flags |= IGB_FLAG_QUEUE_PAIRS; /* Setup and initialize a copy of the hw vlan table array */ adapter->shadow_vfta = kzalloc(sizeof(u32) * @@ -4917,7 +5009,7 @@ static int igb_vf_configure(struct igb_adapter *adapter, int vf) unsigned int device_id; u16 thisvf_devfn; - random_ether_addr(mac_addr); + eth_random_addr(mac_addr); igb_set_vf_mac(adapter, vf, mac_addr); switch (adapter->hw.mac.type) { @@ -5326,7 +5418,7 @@ static void igb_vf_reset_event(struct igb_adapter *adapter, u32 vf) /* generate a new mac address as we were hotplug removed/added */ if (!(adapter->vf_data[vf].flags & IGB_VF_FLAG_PF_SET_MAC)) - random_ether_addr(vf_mac); + eth_random_addr(vf_mac); /* process remaining reset events */ igb_vf_reset(adapter, vf); @@ -5686,6 +5778,7 @@ static void igb_tx_hwtstamp(struct igb_q_vector *q_vector, /** * igb_clean_tx_irq - Reclaim resources after transmit completes * @q_vector: pointer to q_vector containing needed info + * * returns true if ring is completely cleaned **/ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector) @@ -6142,7 +6235,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, return true; if (!page) { - page = alloc_page(GFP_ATOMIC | __GFP_COLD); + page = __skb_alloc_page(GFP_ATOMIC, bi->skb); bi->page = page; if (unlikely(!page)) { rx_ring->rx_stats.alloc_failed++; @@ -6997,6 +7090,11 @@ static void igb_set_vf_rate_limit(struct e1000_hw *hw, int vf, int tx_rate, } wr32(E1000_RTTDQSEL, vf); /* vf X uses queue X */ + /* + * Set global transmit compensation time to the MMW_SIZE in RTTBCNRM + * register. MMW_SIZE=0x014 if 9728-byte jumbo is supported. + */ + wr32(E1000_RTTBCNRM, 0x14); wr32(E1000_RTTBCNRC, bcnrc_val); } diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index d5ee7fa50723..c846ea9131a3 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -330,7 +330,17 @@ void igb_ptp_init(struct igb_adapter *adapter) void igb_ptp_remove(struct igb_adapter *adapter) { - cancel_delayed_work_sync(&adapter->overflow_work); + switch (adapter->hw.mac.type) { + case e1000_i211: + case e1000_i210: + case e1000_i350: + case e1000_82580: + case e1000_82576: + cancel_delayed_work_sync(&adapter->overflow_work); + break; + default: + return; + } if (adapter->ptp_clock) { ptp_clock_unregister(adapter->ptp_clock); diff --git a/drivers/net/ethernet/intel/igbvf/ethtool.c b/drivers/net/ethernet/intel/igbvf/ethtool.c index 8ce67064b9c5..90eef07943f4 100644 --- a/drivers/net/ethernet/intel/igbvf/ethtool.c +++ b/drivers/net/ethernet/intel/igbvf/ethtool.c @@ -357,21 +357,28 @@ static int igbvf_set_coalesce(struct net_device *netdev, struct igbvf_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; - if ((ec->rx_coalesce_usecs > IGBVF_MAX_ITR_USECS) || - ((ec->rx_coalesce_usecs > 3) && - (ec->rx_coalesce_usecs < IGBVF_MIN_ITR_USECS)) || - (ec->rx_coalesce_usecs == 2)) - return -EINVAL; - - /* convert to rate of irq's per second */ - if (ec->rx_coalesce_usecs && ec->rx_coalesce_usecs <= 3) { + if ((ec->rx_coalesce_usecs >= IGBVF_MIN_ITR_USECS) && + (ec->rx_coalesce_usecs <= IGBVF_MAX_ITR_USECS)) { + adapter->current_itr = ec->rx_coalesce_usecs << 2; + adapter->requested_itr = 1000000000 / + (adapter->current_itr * 256); + } else if ((ec->rx_coalesce_usecs == 3) || + (ec->rx_coalesce_usecs == 2)) { adapter->current_itr = IGBVF_START_ITR; adapter->requested_itr = ec->rx_coalesce_usecs; - } else { - adapter->current_itr = ec->rx_coalesce_usecs << 2; + } else if (ec->rx_coalesce_usecs == 0) { + /* + * The user's desire is to turn off interrupt throttling + * altogether, but due to HW limitations, we can't do that. + * Instead we set a very small value in EITR, which would + * allow ~967k interrupts per second, but allow the adapter's + * internal clocking to still function properly. + */ + adapter->current_itr = 4; adapter->requested_itr = 1000000000 / (adapter->current_itr * 256); - } + } else + return -EINVAL; writel(adapter->current_itr, hw->hw_addr + adapter->rx_ring->itr_register); diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 8ec74b07f940..0696abfe9944 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -766,6 +766,7 @@ static void igbvf_set_itr(struct igbvf_adapter *adapter) /** * igbvf_clean_tx_irq - Reclaim resources after transmit completes * @adapter: board private structure + * * returns true if ring is completely cleaned **/ static bool igbvf_clean_tx_irq(struct igbvf_ring *tx_ring) diff --git a/drivers/net/ethernet/intel/igbvf/vf.c b/drivers/net/ethernet/intel/igbvf/vf.c index 30a6cc426037..eea0e10ce12f 100644 --- a/drivers/net/ethernet/intel/igbvf/vf.c +++ b/drivers/net/ethernet/intel/igbvf/vf.c @@ -283,7 +283,8 @@ static s32 e1000_set_vfta_vf(struct e1000_hw *hw, u16 vid, bool set) return err; } -/** e1000_rlpml_set_vf - Set the maximum receive packet length +/** + * e1000_rlpml_set_vf - Set the maximum receive packet length * @hw: pointer to the HW structure * @max_size: value to assign to max frame size **/ @@ -302,7 +303,7 @@ void e1000_rlpml_set_vf(struct e1000_hw *hw, u16 max_size) * e1000_rar_set_vf - set device MAC address * @hw: pointer to the HW structure * @addr: pointer to the receive address - * @index receive address array register + * @index: receive address array register **/ static void e1000_rar_set_vf(struct e1000_hw *hw, u8 * addr, u32 index) { diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_hw.c b/drivers/net/ethernet/intel/ixgb/ixgb_hw.c index 99b69adb4a0f..bf9a220f71fb 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_hw.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_hw.c @@ -32,6 +32,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/pci_ids.h> #include "ixgb_hw.h" #include "ixgb_ids.h" @@ -96,7 +97,7 @@ static u32 ixgb_mac_reset(struct ixgb_hw *hw) ASSERT(!(ctrl_reg & IXGB_CTRL0_RST)); #endif - if (hw->subsystem_vendor_id == SUN_SUBVENDOR_ID) { + if (hw->subsystem_vendor_id == PCI_VENDOR_ID_SUN) { ctrl_reg = /* Enable interrupt from XFP and SerDes */ IXGB_CTRL1_GPI0_EN | IXGB_CTRL1_SDP6_DIR | @@ -271,7 +272,7 @@ ixgb_identify_phy(struct ixgb_hw *hw) } /* update phy type for sun specific board */ - if (hw->subsystem_vendor_id == SUN_SUBVENDOR_ID) + if (hw->subsystem_vendor_id == PCI_VENDOR_ID_SUN) phy_type = ixgb_phy_type_bcm; return phy_type; diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_ids.h b/drivers/net/ethernet/intel/ixgb/ixgb_ids.h index 2a58847f46e8..32c1b302d791 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_ids.h +++ b/drivers/net/ethernet/intel/ixgb/ixgb_ids.h @@ -33,11 +33,6 @@ ** The Device and Vendor IDs for 10 Gigabit MACs **********************************************************************/ -#define INTEL_VENDOR_ID 0x8086 -#define INTEL_SUBVENDOR_ID 0x8086 -#define SUN_VENDOR_ID 0x108E -#define SUN_SUBVENDOR_ID 0x108E - #define IXGB_DEVICE_ID_82597EX 0x1048 #define IXGB_DEVICE_ID_82597EX_SR 0x1A48 #define IXGB_DEVICE_ID_82597EX_LR 0x1B48 diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c index 5fce363d810a..d05fc95befc5 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c @@ -54,13 +54,13 @@ MODULE_PARM_DESC(copybreak, * Class, Class Mask, private data (not used) } */ static DEFINE_PCI_DEVICE_TABLE(ixgb_pci_tbl) = { - {INTEL_VENDOR_ID, IXGB_DEVICE_ID_82597EX, + {PCI_VENDOR_ID_INTEL, IXGB_DEVICE_ID_82597EX, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, - {INTEL_VENDOR_ID, IXGB_DEVICE_ID_82597EX_CX4, + {PCI_VENDOR_ID_INTEL, IXGB_DEVICE_ID_82597EX_CX4, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, - {INTEL_VENDOR_ID, IXGB_DEVICE_ID_82597EX_SR, + {PCI_VENDOR_ID_INTEL, IXGB_DEVICE_ID_82597EX_SR, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, - {INTEL_VENDOR_ID, IXGB_DEVICE_ID_82597EX_LR, + {PCI_VENDOR_ID_INTEL, IXGB_DEVICE_ID_82597EX_LR, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, /* required last entry */ @@ -195,7 +195,7 @@ ixgb_irq_enable(struct ixgb_adapter *adapter) { u32 val = IXGB_INT_RXT0 | IXGB_INT_RXDMT0 | IXGB_INT_TXDW | IXGB_INT_LSC; - if (adapter->hw.subsystem_vendor_id == SUN_SUBVENDOR_ID) + if (adapter->hw.subsystem_vendor_id == PCI_VENDOR_ID_SUN) val |= IXGB_INT_GPI0; IXGB_WRITE_REG(&adapter->hw, IMS, val); IXGB_WRITE_FLUSH(&adapter->hw); @@ -2276,9 +2276,9 @@ static void ixgb_netpoll(struct net_device *dev) #endif /** - * ixgb_io_error_detected() - called when PCI error is detected - * @pdev pointer to pci device with error - * @state pci channel state after error + * ixgb_io_error_detected - called when PCI error is detected + * @pdev: pointer to pci device with error + * @state: pci channel state after error * * This callback is called by the PCI subsystem whenever * a PCI bus error is detected. diff --git a/drivers/net/ethernet/intel/ixgbe/Makefile b/drivers/net/ethernet/intel/ixgbe/Makefile index 0bdf06bc5c49..5fd5d04c26c9 100644 --- a/drivers/net/ethernet/intel/ixgbe/Makefile +++ b/drivers/net/ethernet/intel/ixgbe/Makefile @@ -34,11 +34,11 @@ obj-$(CONFIG_IXGBE) += ixgbe.o ixgbe-objs := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o \ ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o ixgbe_sriov.o \ - ixgbe_mbx.o ixgbe_x540.o ixgbe_sysfs.o ixgbe_lib.o + ixgbe_mbx.o ixgbe_x540.o ixgbe_lib.o ixgbe-$(CONFIG_IXGBE_DCB) += ixgbe_dcb.o ixgbe_dcb_82598.o \ ixgbe_dcb_82599.o ixgbe_dcb_nl.o ixgbe-$(CONFIG_IXGBE_PTP) += ixgbe_ptp.o - +ixgbe-$(CONFIG_IXGBE_HWMON) += ixgbe_sysfs.o ixgbe-$(CONFIG_FCOE:m=y) += ixgbe_fcoe.o diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 7af291e236bf..b9623e9ea895 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -77,17 +77,18 @@ #define IXGBE_MAX_FCPAUSE 0xFFFF /* Supported Rx Buffer Sizes */ -#define IXGBE_RXBUFFER_512 512 /* Used for packet split */ +#define IXGBE_RXBUFFER_256 256 /* Used for skb receive header */ #define IXGBE_MAX_RXBUFFER 16384 /* largest size for a single descriptor */ /* - * NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN mans we - * reserve 2 more, and skb_shared_info adds an additional 384 bytes more, - * this adds up to 512 bytes of extra data meaning the smallest allocation - * we could have is 1K. - * i.e. RXBUFFER_512 --> size-1024 slab + * 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, + * this adds up to 448 bytes of extra data. + * + * Since netdev_alloc_skb now allocates a page fragment we can use a value + * of 256 and the resultant skb will have a truesize of 960 or less. */ -#define IXGBE_RX_HDR_SIZE IXGBE_RXBUFFER_512 +#define IXGBE_RX_HDR_SIZE IXGBE_RXBUFFER_256 #define MAXIMUM_ETHERNET_VLAN_SIZE (ETH_FRAME_LEN + ETH_FCS_LEN + VLAN_HLEN) @@ -113,7 +114,7 @@ #define IXGBE_MAX_VFTA_ENTRIES 128 #define MAX_EMULATION_MAC_ADDRS 16 #define IXGBE_MAX_PF_MACVLANS 15 -#define VMDQ_P(p) ((p) + adapter->num_vfs) +#define VMDQ_P(p) ((p) + adapter->ring_feature[RING_F_VMDQ].offset) #define IXGBE_82599_VF_DEVICE_ID 0x10ED #define IXGBE_X540_VF_DEVICE_ID 0x1515 @@ -130,7 +131,6 @@ struct vf_data_storage { u16 tx_rate; u16 vlan_count; u8 spoofchk_enabled; - struct pci_dev *vfdev; }; struct vf_macvlans { @@ -278,10 +278,16 @@ enum ixgbe_ring_f_enum { #define MAX_TX_QUEUES IXGBE_MAX_FDIR_INDICES #endif /* IXGBE_FCOE */ struct ixgbe_ring_feature { - int indices; - int mask; + u16 limit; /* upper limit on feature indices */ + u16 indices; /* current value of indices */ + u16 mask; /* Mask used for feature to ring mapping */ + u16 offset; /* offset to start of feature */ } ____cacheline_internodealigned_in_smp; +#define IXGBE_82599_VMDQ_8Q_MASK 0x78 +#define IXGBE_82599_VMDQ_4Q_MASK 0x7C +#define IXGBE_82599_VMDQ_2Q_MASK 0x7E + /* * FCoE requires that all Rx buffers be over 2200 bytes in length. Since * this is twice the size of a half page we need to double the page order @@ -315,7 +321,7 @@ struct ixgbe_ring_container { ? 8 : 1) #define MAX_TX_PACKET_BUFFERS MAX_RX_PACKET_BUFFERS -/* MAX_MSIX_Q_VECTORS of these are allocated, +/* MAX_Q_VECTORS of these are allocated, * but we only use one per queue-specific vector. */ struct ixgbe_q_vector { @@ -401,11 +407,11 @@ static inline u16 ixgbe_desc_unused(struct ixgbe_ring *ring) #define NON_Q_VECTORS (OTHER_VECTOR) #define MAX_MSIX_VECTORS_82599 64 -#define MAX_MSIX_Q_VECTORS_82599 64 +#define MAX_Q_VECTORS_82599 64 #define MAX_MSIX_VECTORS_82598 18 -#define MAX_MSIX_Q_VECTORS_82598 16 +#define MAX_Q_VECTORS_82598 16 -#define MAX_MSIX_Q_VECTORS MAX_MSIX_Q_VECTORS_82599 +#define MAX_Q_VECTORS MAX_Q_VECTORS_82599 #define MAX_MSIX_COUNT MAX_MSIX_VECTORS_82599 #define MIN_MSIX_Q_VECTORS 1 @@ -427,35 +433,33 @@ struct ixgbe_adapter { * thus the additional *_CAPABLE flags. */ u32 flags; -#define IXGBE_FLAG_MSI_CAPABLE (u32)(1 << 1) -#define IXGBE_FLAG_MSI_ENABLED (u32)(1 << 2) -#define IXGBE_FLAG_MSIX_CAPABLE (u32)(1 << 3) -#define IXGBE_FLAG_MSIX_ENABLED (u32)(1 << 4) -#define IXGBE_FLAG_RX_1BUF_CAPABLE (u32)(1 << 6) -#define IXGBE_FLAG_RX_PS_CAPABLE (u32)(1 << 7) -#define IXGBE_FLAG_RX_PS_ENABLED (u32)(1 << 8) -#define IXGBE_FLAG_IN_NETPOLL (u32)(1 << 9) -#define IXGBE_FLAG_DCA_ENABLED (u32)(1 << 10) -#define IXGBE_FLAG_DCA_CAPABLE (u32)(1 << 11) -#define IXGBE_FLAG_IMIR_ENABLED (u32)(1 << 12) -#define IXGBE_FLAG_MQ_CAPABLE (u32)(1 << 13) -#define IXGBE_FLAG_DCB_ENABLED (u32)(1 << 14) -#define IXGBE_FLAG_RSS_ENABLED (u32)(1 << 16) -#define IXGBE_FLAG_RSS_CAPABLE (u32)(1 << 17) -#define IXGBE_FLAG_VMDQ_CAPABLE (u32)(1 << 18) -#define IXGBE_FLAG_VMDQ_ENABLED (u32)(1 << 19) -#define IXGBE_FLAG_FAN_FAIL_CAPABLE (u32)(1 << 20) -#define IXGBE_FLAG_NEED_LINK_UPDATE (u32)(1 << 22) -#define IXGBE_FLAG_NEED_LINK_CONFIG (u32)(1 << 23) -#define IXGBE_FLAG_FDIR_HASH_CAPABLE (u32)(1 << 24) -#define IXGBE_FLAG_FDIR_PERFECT_CAPABLE (u32)(1 << 25) -#define IXGBE_FLAG_FCOE_CAPABLE (u32)(1 << 26) -#define IXGBE_FLAG_FCOE_ENABLED (u32)(1 << 27) -#define IXGBE_FLAG_SRIOV_CAPABLE (u32)(1 << 28) -#define IXGBE_FLAG_SRIOV_ENABLED (u32)(1 << 29) +#define IXGBE_FLAG_MSI_CAPABLE (u32)(1 << 0) +#define IXGBE_FLAG_MSI_ENABLED (u32)(1 << 1) +#define IXGBE_FLAG_MSIX_CAPABLE (u32)(1 << 2) +#define IXGBE_FLAG_MSIX_ENABLED (u32)(1 << 3) +#define IXGBE_FLAG_RX_1BUF_CAPABLE (u32)(1 << 4) +#define IXGBE_FLAG_RX_PS_CAPABLE (u32)(1 << 5) +#define IXGBE_FLAG_RX_PS_ENABLED (u32)(1 << 6) +#define IXGBE_FLAG_IN_NETPOLL (u32)(1 << 7) +#define IXGBE_FLAG_DCA_ENABLED (u32)(1 << 8) +#define IXGBE_FLAG_DCA_CAPABLE (u32)(1 << 9) +#define IXGBE_FLAG_IMIR_ENABLED (u32)(1 << 10) +#define IXGBE_FLAG_MQ_CAPABLE (u32)(1 << 11) +#define IXGBE_FLAG_DCB_ENABLED (u32)(1 << 12) +#define IXGBE_FLAG_VMDQ_CAPABLE (u32)(1 << 13) +#define IXGBE_FLAG_VMDQ_ENABLED (u32)(1 << 14) +#define IXGBE_FLAG_FAN_FAIL_CAPABLE (u32)(1 << 15) +#define IXGBE_FLAG_NEED_LINK_UPDATE (u32)(1 << 16) +#define IXGBE_FLAG_NEED_LINK_CONFIG (u32)(1 << 17) +#define IXGBE_FLAG_FDIR_HASH_CAPABLE (u32)(1 << 18) +#define IXGBE_FLAG_FDIR_PERFECT_CAPABLE (u32)(1 << 19) +#define IXGBE_FLAG_FCOE_CAPABLE (u32)(1 << 20) +#define IXGBE_FLAG_FCOE_ENABLED (u32)(1 << 21) +#define IXGBE_FLAG_SRIOV_CAPABLE (u32)(1 << 22) +#define IXGBE_FLAG_SRIOV_ENABLED (u32)(1 << 23) u32 flags2; -#define IXGBE_FLAG2_RSC_CAPABLE (u32)(1) +#define IXGBE_FLAG2_RSC_CAPABLE (u32)(1 << 0) #define IXGBE_FLAG2_RSC_ENABLED (u32)(1 << 1) #define IXGBE_FLAG2_TEMP_SENSOR_CAPABLE (u32)(1 << 2) #define IXGBE_FLAG2_TEMP_SENSOR_EVENT (u32)(1 << 3) @@ -496,7 +500,7 @@ struct ixgbe_adapter { u32 alloc_rx_page_failed; u32 alloc_rx_buff_failed; - struct ixgbe_q_vector *q_vector[MAX_MSIX_Q_VECTORS]; + struct ixgbe_q_vector *q_vector[MAX_Q_VECTORS]; /* DCB parameters */ struct ieee_pfc *ixgbe_ieee_pfc; @@ -507,8 +511,8 @@ struct ixgbe_adapter { u8 dcbx_cap; enum ixgbe_fc_mode last_lfc_mode; - int num_msix_vectors; - int max_msix_q_vectors; /* true count of q_vectors for device */ + int num_q_vectors; /* current number of q_vectors for device */ + int max_q_vectors; /* true count of q_vectors for device */ struct ixgbe_ring_feature ring_feature[RING_F_ARRAY_SIZE]; struct msix_entry *msix_entries; @@ -561,6 +565,7 @@ struct ixgbe_adapter { spinlock_t tmreg_lock; struct cyclecounter cc; struct timecounter tc; + int rx_hwtstamp_filter; u32 base_incval; u32 cycle_speed; #endif /* CONFIG_IXGBE_PTP */ @@ -686,7 +691,6 @@ extern void ixgbe_configure_fcoe(struct ixgbe_adapter *adapter); extern int ixgbe_fso(struct ixgbe_ring *tx_ring, struct ixgbe_tx_buffer *first, u8 *hdr_len); -extern void ixgbe_cleanup_fcoe(struct ixgbe_adapter *adapter); extern int ixgbe_fcoe_ddp(struct ixgbe_adapter *adapter, union ixgbe_adv_rx_desc *rx_desc, struct sk_buff *skb); @@ -695,6 +699,8 @@ extern int ixgbe_fcoe_ddp_get(struct net_device *netdev, u16 xid, extern int ixgbe_fcoe_ddp_target(struct net_device *netdev, u16 xid, struct scatterlist *sgl, unsigned int sgc); extern int ixgbe_fcoe_ddp_put(struct net_device *netdev, u16 xid); +extern int ixgbe_setup_fcoe_ddp_resources(struct ixgbe_adapter *adapter); +extern void ixgbe_free_fcoe_ddp_resources(struct ixgbe_adapter *adapter); extern int ixgbe_fcoe_enable(struct net_device *netdev); extern int ixgbe_fcoe_disable(struct net_device *netdev); #ifdef CONFIG_IXGBE_DCB @@ -704,6 +710,7 @@ extern u8 ixgbe_fcoe_setapp(struct ixgbe_adapter *adapter, u8 up); extern int ixgbe_fcoe_get_wwn(struct net_device *netdev, u64 *wwn, int type); extern int ixgbe_fcoe_get_hbainfo(struct net_device *netdev, struct netdev_fcoe_hbainfo *info); +extern u8 ixgbe_fcoe_get_tc(struct ixgbe_adapter *adapter); #endif /* IXGBE_FCOE */ static inline struct netdev_queue *txring_txq(const struct ixgbe_ring *ring) @@ -718,6 +725,7 @@ extern void ixgbe_ptp_overflow_check(struct ixgbe_adapter *adapter); extern void ixgbe_ptp_tx_hwtstamp(struct ixgbe_q_vector *q_vector, struct sk_buff *skb); extern void ixgbe_ptp_rx_hwtstamp(struct ixgbe_q_vector *q_vector, + union ixgbe_adv_rx_desc *rx_desc, struct sk_buff *skb); extern int ixgbe_ptp_hwtstamp_ioctl(struct ixgbe_adapter *adapter, struct ifreq *ifr, int cmd); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c index dee64d2703f0..50fc137501da 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c @@ -241,7 +241,9 @@ static s32 ixgbe_get_link_capabilities_82599(struct ixgbe_hw *hw, /* Determine 1G link capabilities off of SFP+ type */ if (hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core0 || - hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core1) { + hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core1 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1) { *speed = IXGBE_LINK_SPEED_1GB_FULL; *negotiation = true; goto out; @@ -1023,6 +1025,9 @@ mac_reset_top: hw->mac.ops.set_rar(hw, hw->mac.num_rar_entries - 1, hw->mac.san_addr, 0, IXGBE_RAH_AV); + /* Save the SAN MAC RAR index */ + hw->mac.san_mac_rar_index = hw->mac.num_rar_entries - 1; + /* Reserve the last RAR for the SAN MAC address */ hw->mac.num_rar_entries--; } @@ -2104,6 +2109,7 @@ static struct ixgbe_mac_operations mac_ops_82599 = { .set_rar = &ixgbe_set_rar_generic, .clear_rar = &ixgbe_clear_rar_generic, .set_vmdq = &ixgbe_set_vmdq_generic, + .set_vmdq_san_mac = &ixgbe_set_vmdq_san_mac_generic, .clear_vmdq = &ixgbe_clear_vmdq_generic, .init_rx_addrs = &ixgbe_init_rx_addrs_generic, .update_mc_addr_list = &ixgbe_update_mc_addr_list_generic, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 77ac41feb0fe..90e41db3cb69 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -2848,6 +2848,31 @@ s32 ixgbe_set_vmdq_generic(struct ixgbe_hw *hw, u32 rar, u32 vmdq) } /** + * This function should only be involved in the IOV mode. + * In IOV mode, Default pool is next pool after the number of + * VFs advertized and not 0. + * MPSAR table needs to be updated for SAN_MAC RAR [hw->mac.san_mac_rar_index] + * + * ixgbe_set_vmdq_san_mac - Associate default VMDq pool index with a rx address + * @hw: pointer to hardware struct + * @vmdq: VMDq pool index + **/ +s32 ixgbe_set_vmdq_san_mac_generic(struct ixgbe_hw *hw, u32 vmdq) +{ + u32 rar = hw->mac.san_mac_rar_index; + + if (vmdq < 32) { + IXGBE_WRITE_REG(hw, IXGBE_MPSAR_LO(rar), 1 << vmdq); + IXGBE_WRITE_REG(hw, IXGBE_MPSAR_HI(rar), 0); + } else { + IXGBE_WRITE_REG(hw, IXGBE_MPSAR_LO(rar), 0); + IXGBE_WRITE_REG(hw, IXGBE_MPSAR_HI(rar), 1 << (vmdq - 32)); + } + + return 0; +} + +/** * ixgbe_init_uta_tables_generic - Initialize the Unicast Table Array * @hw: pointer to hardware structure **/ @@ -3132,7 +3157,7 @@ s32 ixgbe_check_mac_link_generic(struct ixgbe_hw *hw, ixgbe_link_speed *speed, } /** - * ixgbe_get_wwn_prefix_generic Get alternative WWNN/WWPN prefix from + * ixgbe_get_wwn_prefix_generic - Get alternative WWNN/WWPN prefix from * the EEPROM * @hw: pointer to hardware structure * @wwnn_prefix: the alternative WWNN prefix @@ -3200,20 +3225,22 @@ void ixgbe_set_mac_anti_spoofing(struct ixgbe_hw *hw, bool enable, int pf) * PFVFSPOOF register array is size 8 with 8 bits assigned to * MAC anti-spoof enables in each register array element. */ - for (j = 0; j < IXGBE_PFVFSPOOF_REG_COUNT; j++) + for (j = 0; j < pf_target_reg; j++) IXGBE_WRITE_REG(hw, IXGBE_PFVFSPOOF(j), pfvfspoof); - /* If not enabling anti-spoofing then done */ - if (!enable) - return; - /* * The PF should be allowed to spoof so that it can support - * emulation mode NICs. Reset the bit assigned to the PF + * emulation mode NICs. Do not set the bits assigned to the PF */ - pfvfspoof = IXGBE_READ_REG(hw, IXGBE_PFVFSPOOF(pf_target_reg)); - pfvfspoof ^= (1 << pf_target_shift); - IXGBE_WRITE_REG(hw, IXGBE_PFVFSPOOF(pf_target_reg), pfvfspoof); + pfvfspoof &= (1 << pf_target_shift) - 1; + IXGBE_WRITE_REG(hw, IXGBE_PFVFSPOOF(j), pfvfspoof); + + /* + * Remaining pools belong to the PF so they do not need to have + * anti-spoofing enabled. + */ + for (j++; j < IXGBE_PFVFSPOOF_REG_COUNT; j++) + IXGBE_WRITE_REG(hw, IXGBE_PFVFSPOOF(j), 0); } /** @@ -3325,6 +3352,7 @@ void ixgbe_set_rxpba_generic(struct ixgbe_hw *hw, * ixgbe_calculate_checksum - Calculate checksum for buffer * @buffer: pointer to EEPROM * @length: size of EEPROM to calculate a checksum for + * * Calculates the checksum for some buffer on a specified length. The * checksum calculated is returned. **/ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h index 6222fdb3d3f1..d813d1188c36 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h @@ -85,6 +85,7 @@ s32 ixgbe_acquire_swfw_sync(struct ixgbe_hw *hw, u16 mask); void ixgbe_release_swfw_sync(struct ixgbe_hw *hw, u16 mask); s32 ixgbe_get_san_mac_addr_generic(struct ixgbe_hw *hw, u8 *san_mac_addr); s32 ixgbe_set_vmdq_generic(struct ixgbe_hw *hw, u32 rar, u32 vmdq); +s32 ixgbe_set_vmdq_san_mac_generic(struct ixgbe_hw *hw, u32 vmdq); s32 ixgbe_clear_vmdq_generic(struct ixgbe_hw *hw, u32 rar, u32 vmdq); s32 ixgbe_init_uta_tables_generic(struct ixgbe_hw *hw); s32 ixgbe_set_vfta_generic(struct ixgbe_hw *hw, u32 vlan, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.c index 8bfaaee5ac5b..9bc17c0cb972 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.c @@ -180,67 +180,83 @@ out: void ixgbe_dcb_unpack_pfc(struct ixgbe_dcb_config *cfg, u8 *pfc_en) { - int i; + struct tc_configuration *tc_config = &cfg->tc_config[0]; + int tc; - *pfc_en = 0; - for (i = 0; i < MAX_TRAFFIC_CLASS; i++) - *pfc_en |= !!(cfg->tc_config[i].dcb_pfc & 0xF) << i; + for (*pfc_en = 0, tc = 0; tc < MAX_TRAFFIC_CLASS; tc++) { + if (tc_config[tc].dcb_pfc != pfc_disabled) + *pfc_en |= 1 << tc; + } } void ixgbe_dcb_unpack_refill(struct ixgbe_dcb_config *cfg, int direction, u16 *refill) { - struct tc_bw_alloc *p; - int i; + struct tc_configuration *tc_config = &cfg->tc_config[0]; + int tc; - for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { - p = &cfg->tc_config[i].path[direction]; - refill[i] = p->data_credits_refill; - } + for (tc = 0; tc < MAX_TRAFFIC_CLASS; tc++) + refill[tc] = tc_config[tc].path[direction].data_credits_refill; } void ixgbe_dcb_unpack_max(struct ixgbe_dcb_config *cfg, u16 *max) { - int i; + struct tc_configuration *tc_config = &cfg->tc_config[0]; + int tc; - for (i = 0; i < MAX_TRAFFIC_CLASS; i++) - max[i] = cfg->tc_config[i].desc_credits_max; + for (tc = 0; tc < MAX_TRAFFIC_CLASS; tc++) + max[tc] = tc_config[tc].desc_credits_max; } void ixgbe_dcb_unpack_bwgid(struct ixgbe_dcb_config *cfg, int direction, u8 *bwgid) { - struct tc_bw_alloc *p; - int i; + struct tc_configuration *tc_config = &cfg->tc_config[0]; + int tc; - for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { - p = &cfg->tc_config[i].path[direction]; - bwgid[i] = p->bwg_id; - } + for (tc = 0; tc < MAX_TRAFFIC_CLASS; tc++) + bwgid[tc] = tc_config[tc].path[direction].bwg_id; } void ixgbe_dcb_unpack_prio(struct ixgbe_dcb_config *cfg, int direction, u8 *ptype) { - struct tc_bw_alloc *p; - int i; + struct tc_configuration *tc_config = &cfg->tc_config[0]; + int tc; - for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { - p = &cfg->tc_config[i].path[direction]; - ptype[i] = p->prio_type; + for (tc = 0; tc < MAX_TRAFFIC_CLASS; tc++) + ptype[tc] = tc_config[tc].path[direction].prio_type; +} + +u8 ixgbe_dcb_get_tc_from_up(struct ixgbe_dcb_config *cfg, int direction, u8 up) +{ + struct tc_configuration *tc_config = &cfg->tc_config[0]; + u8 prio_mask = 1 << up; + u8 tc = cfg->num_tcs.pg_tcs; + + /* If tc is 0 then DCB is likely not enabled or supported */ + if (!tc) + goto out; + + /* + * Test from maximum TC to 1 and report the first match we find. If + * we find no match we can assume that the TC is 0 since the TC must + * be set for all user priorities + */ + for (tc--; tc; tc--) { + if (prio_mask & tc_config[tc].path[direction].up_to_tc_bitmap) + break; } +out: + return tc; } void ixgbe_dcb_unpack_map(struct ixgbe_dcb_config *cfg, int direction, u8 *map) { - int i, up; - unsigned long bitmap; + u8 up; - for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { - bitmap = cfg->tc_config[i].path[direction].up_to_tc_bitmap; - for_each_set_bit(up, &bitmap, MAX_USER_PRIORITY) - map[up] = i; - } + for (up = 0; up < MAX_USER_PRIORITY; up++) + map[up] = ixgbe_dcb_get_tc_from_up(cfg, direction, up); } /** diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.h index 24333b718166..1f4108ee154b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.h @@ -146,6 +146,7 @@ void ixgbe_dcb_unpack_max(struct ixgbe_dcb_config *, u16 *); void ixgbe_dcb_unpack_bwgid(struct ixgbe_dcb_config *, int, u8 *); void ixgbe_dcb_unpack_prio(struct ixgbe_dcb_config *, int, u8 *); void ixgbe_dcb_unpack_map(struct ixgbe_dcb_config *, int, u8 *); +u8 ixgbe_dcb_get_tc_from_up(struct ixgbe_dcb_config *, int, u8); /* DCB credits calculation */ s32 ixgbe_dcb_calculate_tc_credits(struct ixgbe_hw *, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c index 5164a21b13ca..f1e002d5fa8f 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c @@ -151,34 +151,21 @@ static u8 ixgbe_dcbnl_get_state(struct net_device *netdev) static u8 ixgbe_dcbnl_set_state(struct net_device *netdev, u8 state) { - int err = 0; - u8 prio_tc[MAX_USER_PRIORITY] = {0}; - int i; struct ixgbe_adapter *adapter = netdev_priv(netdev); + int err = 0; /* Fail command if not in CEE mode */ if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_CEE)) return 1; /* verify there is something to do, if not then exit */ - if (!!state != !(adapter->flags & IXGBE_FLAG_DCB_ENABLED)) - goto out; - - if (state > 0) { - err = ixgbe_setup_tc(netdev, adapter->dcb_cfg.num_tcs.pg_tcs); - ixgbe_dcb_unpack_map(&adapter->dcb_cfg, DCB_TX_CONFIG, prio_tc); - } else { - err = ixgbe_setup_tc(netdev, 0); - } - - if (err) + if (!state == !(adapter->flags & IXGBE_FLAG_DCB_ENABLED)) goto out; - for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) - netdev_set_prio_tc_map(netdev, i, prio_tc[i]); - + err = ixgbe_setup_tc(netdev, + state ? adapter->dcb_cfg.num_tcs.pg_tcs : 0); out: - return err ? 1 : 0; + return !!err; } static void ixgbe_dcbnl_get_perm_hw_addr(struct net_device *netdev, @@ -584,9 +571,6 @@ static int ixgbe_dcbnl_ieee_setets(struct net_device *dev, if (err) goto err_out; - for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) - netdev_set_prio_tc_map(dev, i, ets->prio_tc[i]); - err = ixgbe_dcb_hw_ets(&adapter->hw, ets, max_frame); err_out: return err; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 3178f1ec3711..4104ea25d818 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -154,100 +154,60 @@ static int ixgbe_get_settings(struct net_device *netdev, { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; + ixgbe_link_speed supported_link; u32 link_speed = 0; + bool autoneg; bool link_up; - ecmd->supported = SUPPORTED_10000baseT_Full; - ecmd->autoneg = AUTONEG_ENABLE; - ecmd->transceiver = XCVR_EXTERNAL; - if ((hw->phy.media_type == ixgbe_media_type_copper) || - (hw->phy.multispeed_fiber)) { - ecmd->supported |= (SUPPORTED_1000baseT_Full | - SUPPORTED_Autoneg); - - switch (hw->mac.type) { - case ixgbe_mac_X540: - ecmd->supported |= SUPPORTED_100baseT_Full; - break; - default: - break; - } - - ecmd->advertising = ADVERTISED_Autoneg; - if (hw->phy.autoneg_advertised) { - 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) - ecmd->advertising |= ADVERTISED_10000baseT_Full; - if (hw->phy.autoneg_advertised & - IXGBE_LINK_SPEED_1GB_FULL) - ecmd->advertising |= ADVERTISED_1000baseT_Full; - } else { - /* - * Default advertised modes in case - * phy.autoneg_advertised isn't set. - */ - ecmd->advertising |= (ADVERTISED_10000baseT_Full | - ADVERTISED_1000baseT_Full); - if (hw->mac.type == ixgbe_mac_X540) - ecmd->advertising |= ADVERTISED_100baseT_Full; - } - - if (hw->phy.media_type == ixgbe_media_type_copper) { - ecmd->supported |= SUPPORTED_TP; - ecmd->advertising |= ADVERTISED_TP; - ecmd->port = PORT_TP; - } else { - ecmd->supported |= SUPPORTED_FIBRE; - ecmd->advertising |= ADVERTISED_FIBRE; - ecmd->port = PORT_FIBRE; - } - } else if (hw->phy.media_type == ixgbe_media_type_backplane) { - /* Set as FIBRE until SERDES defined in kernel */ - if (hw->device_id == IXGBE_DEV_ID_82598_BX) { - ecmd->supported = (SUPPORTED_1000baseT_Full | - SUPPORTED_FIBRE); - ecmd->advertising = (ADVERTISED_1000baseT_Full | - ADVERTISED_FIBRE); - ecmd->port = PORT_FIBRE; - ecmd->autoneg = AUTONEG_DISABLE; - } else if ((hw->device_id == IXGBE_DEV_ID_82599_COMBO_BACKPLANE) || - (hw->device_id == IXGBE_DEV_ID_82599_KX4_MEZZ)) { - ecmd->supported |= (SUPPORTED_1000baseT_Full | - SUPPORTED_Autoneg | - SUPPORTED_FIBRE); - ecmd->advertising = (ADVERTISED_10000baseT_Full | - ADVERTISED_1000baseT_Full | - ADVERTISED_Autoneg | - ADVERTISED_FIBRE); - ecmd->port = PORT_FIBRE; - } else { - ecmd->supported |= (SUPPORTED_1000baseT_Full | - SUPPORTED_FIBRE); - ecmd->advertising = (ADVERTISED_10000baseT_Full | - ADVERTISED_1000baseT_Full | - ADVERTISED_FIBRE); - ecmd->port = PORT_FIBRE; - } + hw->mac.ops.get_link_capabilities(hw, &supported_link, &autoneg); + + /* set the supported link speeds */ + if (supported_link & IXGBE_LINK_SPEED_10GB_FULL) + ecmd->supported |= SUPPORTED_10000baseT_Full; + if (supported_link & IXGBE_LINK_SPEED_1GB_FULL) + ecmd->supported |= SUPPORTED_1000baseT_Full; + if (supported_link & IXGBE_LINK_SPEED_100_FULL) + ecmd->supported |= SUPPORTED_100baseT_Full; + + /* set the advertised speeds */ + if (hw->phy.autoneg_advertised) { + 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) + ecmd->advertising |= ADVERTISED_10000baseT_Full; + if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_1GB_FULL) + ecmd->advertising |= ADVERTISED_1000baseT_Full; } else { - ecmd->supported |= SUPPORTED_FIBRE; - ecmd->advertising = (ADVERTISED_10000baseT_Full | - ADVERTISED_FIBRE); - ecmd->port = PORT_FIBRE; - ecmd->autoneg = AUTONEG_DISABLE; + /* default modes in case phy.autoneg_advertised isn't set */ + if (supported_link & IXGBE_LINK_SPEED_10GB_FULL) + ecmd->advertising |= ADVERTISED_10000baseT_Full; + if (supported_link & IXGBE_LINK_SPEED_1GB_FULL) + ecmd->advertising |= ADVERTISED_1000baseT_Full; + if (supported_link & IXGBE_LINK_SPEED_100_FULL) + ecmd->advertising |= ADVERTISED_100baseT_Full; } - /* Get PHY type */ + if (autoneg) { + ecmd->supported |= SUPPORTED_Autoneg; + ecmd->advertising |= ADVERTISED_Autoneg; + ecmd->autoneg = AUTONEG_ENABLE; + } else + ecmd->autoneg = AUTONEG_DISABLE; + + ecmd->transceiver = XCVR_EXTERNAL; + + /* Determine the remaining settings based on the PHY type. */ switch (adapter->hw.phy.type) { case ixgbe_phy_tn: case ixgbe_phy_aq: case ixgbe_phy_cu_unknown: - /* Copper 10G-BASET */ + ecmd->supported |= SUPPORTED_TP; + ecmd->advertising |= ADVERTISED_TP; ecmd->port = PORT_TP; break; case ixgbe_phy_qt: + ecmd->supported |= SUPPORTED_FIBRE; + ecmd->advertising |= ADVERTISED_FIBRE; ecmd->port = PORT_FIBRE; break; case ixgbe_phy_nl: @@ -257,42 +217,59 @@ static int ixgbe_get_settings(struct net_device *netdev, case ixgbe_phy_sfp_avago: case ixgbe_phy_sfp_intel: case ixgbe_phy_sfp_unknown: - switch (adapter->hw.phy.sfp_type) { /* SFP+ devices, further checking needed */ + switch (adapter->hw.phy.sfp_type) { case ixgbe_sfp_type_da_cu: case ixgbe_sfp_type_da_cu_core0: case ixgbe_sfp_type_da_cu_core1: + ecmd->supported |= SUPPORTED_FIBRE; + ecmd->advertising |= ADVERTISED_FIBRE; ecmd->port = PORT_DA; break; case ixgbe_sfp_type_sr: case ixgbe_sfp_type_lr: case ixgbe_sfp_type_srlr_core0: case ixgbe_sfp_type_srlr_core1: + ecmd->supported |= SUPPORTED_FIBRE; + ecmd->advertising |= ADVERTISED_FIBRE; ecmd->port = PORT_FIBRE; break; case ixgbe_sfp_type_not_present: + ecmd->supported |= SUPPORTED_FIBRE; + ecmd->advertising |= ADVERTISED_FIBRE; ecmd->port = PORT_NONE; break; case ixgbe_sfp_type_1g_cu_core0: case ixgbe_sfp_type_1g_cu_core1: + ecmd->supported |= SUPPORTED_TP; + ecmd->advertising |= ADVERTISED_TP; ecmd->port = PORT_TP; - ecmd->supported = SUPPORTED_TP; - ecmd->advertising = (ADVERTISED_1000baseT_Full | - ADVERTISED_TP); + break; + case ixgbe_sfp_type_1g_sx_core0: + case ixgbe_sfp_type_1g_sx_core1: + ecmd->supported |= SUPPORTED_FIBRE; + ecmd->advertising |= ADVERTISED_FIBRE; + ecmd->port = PORT_FIBRE; break; case ixgbe_sfp_type_unknown: default: + ecmd->supported |= SUPPORTED_FIBRE; + ecmd->advertising |= ADVERTISED_FIBRE; ecmd->port = PORT_OTHER; break; } break; case ixgbe_phy_xaui: + ecmd->supported |= SUPPORTED_FIBRE; + ecmd->advertising |= ADVERTISED_FIBRE; ecmd->port = PORT_NONE; break; case ixgbe_phy_unknown: case ixgbe_phy_generic: case ixgbe_phy_sfp_unsupported: default: + ecmd->supported |= SUPPORTED_FIBRE; + ecmd->advertising |= ADVERTISED_FIBRE; ecmd->port = PORT_OTHER; break; } @@ -2113,7 +2090,6 @@ static int ixgbe_set_coalesce(struct net_device *netdev, struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_q_vector *q_vector; int i; - int num_vectors; u16 tx_itr_param, rx_itr_param; bool need_reset = false; @@ -2149,12 +2125,7 @@ static int ixgbe_set_coalesce(struct net_device *netdev, /* check the old value and enable RSC if necessary */ need_reset = ixgbe_update_rsc(adapter); - if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) - num_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - else - num_vectors = 1; - - for (i = 0; i < num_vectors; i++) { + for (i = 0; i < adapter->num_q_vectors; i++) { q_vector = adapter->q_vector[i]; if (q_vector->tx.count && !q_vector->rx.count) /* tx only */ @@ -2274,10 +2245,6 @@ static int ixgbe_get_rss_hash_opts(struct ixgbe_adapter *adapter, { cmd->data = 0; - /* if RSS is disabled then report no hashing */ - if (!(adapter->flags & IXGBE_FLAG_RSS_ENABLED)) - return 0; - /* Report default options for RSS on ixgbe */ switch (cmd->flow_type) { case TCP_V4_FLOW: diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c index bc07933d67da..ae73ef14fdf3 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c @@ -38,7 +38,7 @@ /** * ixgbe_fcoe_clear_ddp - clear the given ddp context - * @ddp - ptr to the ixgbe_fcoe_ddp + * @ddp: ptr to the ixgbe_fcoe_ddp * * Returns : none * @@ -104,10 +104,10 @@ int ixgbe_fcoe_ddp_put(struct net_device *netdev, u16 xid) udelay(100); } if (ddp->sgl) - pci_unmap_sg(adapter->pdev, ddp->sgl, ddp->sgc, + dma_unmap_sg(&adapter->pdev->dev, ddp->sgl, ddp->sgc, DMA_FROM_DEVICE); if (ddp->pool) { - pci_pool_free(ddp->pool, ddp->udl, ddp->udp); + dma_pool_free(ddp->pool, ddp->udl, ddp->udp); ddp->pool = NULL; } @@ -134,6 +134,7 @@ static int ixgbe_fcoe_ddp_setup(struct net_device *netdev, u16 xid, struct ixgbe_hw *hw; struct ixgbe_fcoe *fcoe; struct ixgbe_fcoe_ddp *ddp; + struct ixgbe_fcoe_ddp_pool *ddp_pool; struct scatterlist *sg; unsigned int i, j, dmacount; unsigned int len; @@ -144,8 +145,6 @@ static int ixgbe_fcoe_ddp_setup(struct net_device *netdev, u16 xid, unsigned int thislen = 0; u32 fcbuff, fcdmarw, fcfltrw, fcrxctl; dma_addr_t addr = 0; - struct pci_pool *pool; - unsigned int cpu; if (!netdev || !sgl) return 0; @@ -162,11 +161,6 @@ static int ixgbe_fcoe_ddp_setup(struct net_device *netdev, u16 xid, return 0; fcoe = &adapter->fcoe; - if (!fcoe->pool) { - e_warn(drv, "xid=0x%x no ddp pool for fcoe\n", xid); - return 0; - } - ddp = &fcoe->ddp[xid]; if (ddp->sgl) { e_err(drv, "xid 0x%x w/ non-null sgl=%p nents=%d\n", @@ -175,22 +169,32 @@ static int ixgbe_fcoe_ddp_setup(struct net_device *netdev, u16 xid, } ixgbe_fcoe_clear_ddp(ddp); + + if (!fcoe->ddp_pool) { + e_warn(drv, "No ddp_pool resources allocated\n"); + return 0; + } + + ddp_pool = per_cpu_ptr(fcoe->ddp_pool, get_cpu()); + if (!ddp_pool->pool) { + e_warn(drv, "xid=0x%x no ddp pool for fcoe\n", xid); + goto out_noddp; + } + /* setup dma from scsi command sgl */ - dmacount = pci_map_sg(adapter->pdev, sgl, sgc, DMA_FROM_DEVICE); + dmacount = dma_map_sg(&adapter->pdev->dev, sgl, sgc, DMA_FROM_DEVICE); if (dmacount == 0) { e_err(drv, "xid 0x%x DMA map error\n", xid); - return 0; + goto out_noddp; } /* alloc the udl from per cpu ddp pool */ - cpu = get_cpu(); - pool = *per_cpu_ptr(fcoe->pool, cpu); - ddp->udl = pci_pool_alloc(pool, GFP_ATOMIC, &ddp->udp); + ddp->udl = dma_pool_alloc(ddp_pool->pool, GFP_ATOMIC, &ddp->udp); if (!ddp->udl) { e_err(drv, "failed allocated ddp context\n"); goto out_noddp_unmap; } - ddp->pool = pool; + ddp->pool = ddp_pool->pool; ddp->sgl = sgl; ddp->sgc = sgc; @@ -201,7 +205,7 @@ static int ixgbe_fcoe_ddp_setup(struct net_device *netdev, u16 xid, while (len) { /* max number of buffers allowed in one DDP context */ if (j >= IXGBE_BUFFCNT_MAX) { - *per_cpu_ptr(fcoe->pcpu_noddp, cpu) += 1; + ddp_pool->noddp++; goto out_noddp_free; } @@ -241,7 +245,7 @@ static int ixgbe_fcoe_ddp_setup(struct net_device *netdev, u16 xid, */ if (lastsize == bufflen) { if (j >= IXGBE_BUFFCNT_MAX) { - *per_cpu_ptr(fcoe->pcpu_noddp_ext_buff, cpu) += 1; + ddp_pool->noddp_ext_buff++; goto out_noddp_free; } @@ -293,11 +297,12 @@ static int ixgbe_fcoe_ddp_setup(struct net_device *netdev, u16 xid, return 1; out_noddp_free: - pci_pool_free(pool, ddp->udl, ddp->udp); + dma_pool_free(ddp->pool, ddp->udl, ddp->udp); ixgbe_fcoe_clear_ddp(ddp); out_noddp_unmap: - pci_unmap_sg(adapter->pdev, sgl, sgc, DMA_FROM_DEVICE); + dma_unmap_sg(&adapter->pdev->dev, sgl, sgc, DMA_FROM_DEVICE); +out_noddp: put_cpu(); return 0; } @@ -409,7 +414,7 @@ int ixgbe_fcoe_ddp(struct ixgbe_adapter *adapter, break; /* unmap the sg list when FCPRSP is received */ case __constant_cpu_to_le32(IXGBE_RXDADV_STAT_FCSTAT_FCPRSP): - pci_unmap_sg(adapter->pdev, ddp->sgl, + dma_unmap_sg(&adapter->pdev->dev, ddp->sgl, ddp->sgc, DMA_FROM_DEVICE); ddp->err = ddp_err; ddp->sgl = NULL; @@ -563,44 +568,37 @@ int ixgbe_fso(struct ixgbe_ring *tx_ring, return 0; } -static void ixgbe_fcoe_ddp_pools_free(struct ixgbe_fcoe *fcoe) +static void ixgbe_fcoe_dma_pool_free(struct ixgbe_fcoe *fcoe, unsigned int cpu) { - unsigned int cpu; - struct pci_pool **pool; + struct ixgbe_fcoe_ddp_pool *ddp_pool; - for_each_possible_cpu(cpu) { - pool = per_cpu_ptr(fcoe->pool, cpu); - if (*pool) - pci_pool_destroy(*pool); - } - free_percpu(fcoe->pool); - fcoe->pool = NULL; + ddp_pool = per_cpu_ptr(fcoe->ddp_pool, cpu); + if (ddp_pool->pool) + dma_pool_destroy(ddp_pool->pool); + ddp_pool->pool = NULL; } -static void ixgbe_fcoe_ddp_pools_alloc(struct ixgbe_adapter *adapter) +static int ixgbe_fcoe_dma_pool_alloc(struct ixgbe_fcoe *fcoe, + struct device *dev, + unsigned int cpu) { - struct ixgbe_fcoe *fcoe = &adapter->fcoe; - unsigned int cpu; - struct pci_pool **pool; + struct ixgbe_fcoe_ddp_pool *ddp_pool; + struct dma_pool *pool; char pool_name[32]; - fcoe->pool = alloc_percpu(struct pci_pool *); - if (!fcoe->pool) - return; + snprintf(pool_name, 32, "ixgbe_fcoe_ddp_%d", cpu); - /* allocate pci pool for each cpu */ - for_each_possible_cpu(cpu) { - snprintf(pool_name, 32, "ixgbe_fcoe_ddp_%d", cpu); - pool = per_cpu_ptr(fcoe->pool, cpu); - *pool = pci_pool_create(pool_name, - adapter->pdev, IXGBE_FCPTR_MAX, - IXGBE_FCPTR_ALIGN, PAGE_SIZE); - if (!*pool) { - e_err(drv, "failed to alloc DDP pool on cpu:%d\n", cpu); - ixgbe_fcoe_ddp_pools_free(fcoe); - return; - } - } + pool = dma_pool_create(pool_name, dev, IXGBE_FCPTR_MAX, + IXGBE_FCPTR_ALIGN, PAGE_SIZE); + if (!pool) + return -ENOMEM; + + ddp_pool = per_cpu_ptr(fcoe->ddp_pool, cpu); + ddp_pool->pool = pool; + ddp_pool->noddp = 0; + ddp_pool->noddp_ext_buff = 0; + + return 0; } /** @@ -613,132 +611,171 @@ static void ixgbe_fcoe_ddp_pools_alloc(struct ixgbe_adapter *adapter) */ void ixgbe_configure_fcoe(struct ixgbe_adapter *adapter) { - int i, fcoe_q, fcoe_i; + struct ixgbe_ring_feature *fcoe = &adapter->ring_feature[RING_F_FCOE]; struct ixgbe_hw *hw = &adapter->hw; - struct ixgbe_fcoe *fcoe = &adapter->fcoe; - struct ixgbe_ring_feature *f = &adapter->ring_feature[RING_F_FCOE]; - unsigned int cpu; - - if (!fcoe->pool) { - spin_lock_init(&fcoe->lock); - - ixgbe_fcoe_ddp_pools_alloc(adapter); - if (!fcoe->pool) { - e_err(drv, "failed to alloc percpu fcoe DDP pools\n"); - return; - } - - /* Extra buffer to be shared by all DDPs for HW work around */ - fcoe->extra_ddp_buffer = kmalloc(IXGBE_FCBUFF_MIN, GFP_ATOMIC); - if (fcoe->extra_ddp_buffer == NULL) { - e_err(drv, "failed to allocated extra DDP buffer\n"); - goto out_ddp_pools; - } + int i, fcoe_q, fcoe_i; + u32 etqf; - fcoe->extra_ddp_buffer_dma = - dma_map_single(&adapter->pdev->dev, - fcoe->extra_ddp_buffer, - IXGBE_FCBUFF_MIN, - DMA_FROM_DEVICE); - if (dma_mapping_error(&adapter->pdev->dev, - fcoe->extra_ddp_buffer_dma)) { - e_err(drv, "failed to map extra DDP buffer\n"); - goto out_extra_ddp_buffer; - } + /* Minimal functionality for FCoE requires at least CRC offloads */ + if (!(adapter->netdev->features & NETIF_F_FCOE_CRC)) + return; - /* Alloc per cpu mem to count the ddp alloc failure number */ - fcoe->pcpu_noddp = alloc_percpu(u64); - if (!fcoe->pcpu_noddp) { - e_err(drv, "failed to alloc noddp counter\n"); - goto out_pcpu_noddp_alloc_fail; - } + /* Enable L2 EtherType filter for FCoE, needed for FCoE CRC and DDP */ + etqf = ETH_P_FCOE | IXGBE_ETQF_FCOE | IXGBE_ETQF_FILTER_EN; + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) { + etqf |= IXGBE_ETQF_POOL_ENABLE; + etqf |= VMDQ_P(0) << IXGBE_ETQF_POOL_SHIFT; + } + IXGBE_WRITE_REG(hw, IXGBE_ETQF(IXGBE_ETQF_FILTER_FCOE), etqf); + IXGBE_WRITE_REG(hw, IXGBE_ETQS(IXGBE_ETQF_FILTER_FCOE), 0); - fcoe->pcpu_noddp_ext_buff = alloc_percpu(u64); - if (!fcoe->pcpu_noddp_ext_buff) { - e_err(drv, "failed to alloc noddp extra buff cnt\n"); - goto out_pcpu_noddp_extra_buff_alloc_fail; - } + /* leave registers un-configured if FCoE is disabled */ + if (!(adapter->flags & IXGBE_FLAG_FCOE_ENABLED)) + return; - for_each_possible_cpu(cpu) { - *per_cpu_ptr(fcoe->pcpu_noddp, cpu) = 0; - *per_cpu_ptr(fcoe->pcpu_noddp_ext_buff, cpu) = 0; - } + /* Use one or more Rx queues for FCoE by redirection table */ + for (i = 0; i < IXGBE_FCRETA_SIZE; i++) { + fcoe_i = fcoe->offset + (i % fcoe->indices); + fcoe_i &= IXGBE_FCRETA_ENTRY_MASK; + fcoe_q = adapter->rx_ring[fcoe_i]->reg_idx; + IXGBE_WRITE_REG(hw, IXGBE_FCRETA(i), fcoe_q); } + IXGBE_WRITE_REG(hw, IXGBE_FCRECTL, IXGBE_FCRECTL_ENA); - /* Enable L2 eth type filter for FCoE */ - IXGBE_WRITE_REG(hw, IXGBE_ETQF(IXGBE_ETQF_FILTER_FCOE), - (ETH_P_FCOE | IXGBE_ETQF_FCOE | IXGBE_ETQF_FILTER_EN)); - /* Enable L2 eth type filter for FIP */ - IXGBE_WRITE_REG(hw, IXGBE_ETQF(IXGBE_ETQF_FILTER_FIP), - (ETH_P_FIP | IXGBE_ETQF_FILTER_EN)); - if (adapter->ring_feature[RING_F_FCOE].indices) { - /* Use multiple rx queues for FCoE by redirection table */ - for (i = 0; i < IXGBE_FCRETA_SIZE; i++) { - fcoe_i = f->mask + i % f->indices; - fcoe_i &= IXGBE_FCRETA_ENTRY_MASK; - fcoe_q = adapter->rx_ring[fcoe_i]->reg_idx; - IXGBE_WRITE_REG(hw, IXGBE_FCRETA(i), fcoe_q); - } - IXGBE_WRITE_REG(hw, IXGBE_FCRECTL, IXGBE_FCRECTL_ENA); - IXGBE_WRITE_REG(hw, IXGBE_ETQS(IXGBE_ETQF_FILTER_FCOE), 0); - } else { - /* Use single rx queue for FCoE */ - fcoe_i = f->mask; - fcoe_q = adapter->rx_ring[fcoe_i]->reg_idx; - IXGBE_WRITE_REG(hw, IXGBE_FCRECTL, 0); - IXGBE_WRITE_REG(hw, IXGBE_ETQS(IXGBE_ETQF_FILTER_FCOE), - IXGBE_ETQS_QUEUE_EN | - (fcoe_q << IXGBE_ETQS_RX_QUEUE_SHIFT)); + /* Enable L2 EtherType filter for FIP */ + etqf = ETH_P_FIP | IXGBE_ETQF_FILTER_EN; + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) { + etqf |= IXGBE_ETQF_POOL_ENABLE; + etqf |= VMDQ_P(0) << IXGBE_ETQF_POOL_SHIFT; } - /* send FIP frames to the first FCoE queue */ - fcoe_i = f->mask; - fcoe_q = adapter->rx_ring[fcoe_i]->reg_idx; + IXGBE_WRITE_REG(hw, IXGBE_ETQF(IXGBE_ETQF_FILTER_FIP), etqf); + + /* Send FIP frames to the first FCoE queue */ + fcoe_q = adapter->rx_ring[fcoe->offset]->reg_idx; IXGBE_WRITE_REG(hw, IXGBE_ETQS(IXGBE_ETQF_FILTER_FIP), IXGBE_ETQS_QUEUE_EN | (fcoe_q << IXGBE_ETQS_RX_QUEUE_SHIFT)); - IXGBE_WRITE_REG(hw, IXGBE_FCRXCTRL, IXGBE_FCRXCTRL_FCCRCBO | + /* Configure FCoE Rx control */ + IXGBE_WRITE_REG(hw, IXGBE_FCRXCTRL, + IXGBE_FCRXCTRL_FCCRCBO | (FC_FCOE_VER << IXGBE_FCRXCTRL_FCOEVER_SHIFT)); - return; -out_pcpu_noddp_extra_buff_alloc_fail: - free_percpu(fcoe->pcpu_noddp); -out_pcpu_noddp_alloc_fail: - dma_unmap_single(&adapter->pdev->dev, - fcoe->extra_ddp_buffer_dma, - IXGBE_FCBUFF_MIN, - DMA_FROM_DEVICE); -out_extra_ddp_buffer: - kfree(fcoe->extra_ddp_buffer); -out_ddp_pools: - ixgbe_fcoe_ddp_pools_free(fcoe); } /** - * ixgbe_cleanup_fcoe - release all fcoe ddp context resources + * ixgbe_free_fcoe_ddp_resources - release all fcoe ddp context resources * @adapter : ixgbe adapter * * Cleans up outstanding ddp context resources * * Returns : none */ -void ixgbe_cleanup_fcoe(struct ixgbe_adapter *adapter) +void ixgbe_free_fcoe_ddp_resources(struct ixgbe_adapter *adapter) { - int i; struct ixgbe_fcoe *fcoe = &adapter->fcoe; + int cpu, i; - if (!fcoe->pool) + /* do nothing if no DDP pools were allocated */ + if (!fcoe->ddp_pool) return; for (i = 0; i < IXGBE_FCOE_DDP_MAX; i++) ixgbe_fcoe_ddp_put(adapter->netdev, i); + + for_each_possible_cpu(cpu) + ixgbe_fcoe_dma_pool_free(fcoe, cpu); + dma_unmap_single(&adapter->pdev->dev, fcoe->extra_ddp_buffer_dma, IXGBE_FCBUFF_MIN, DMA_FROM_DEVICE); - free_percpu(fcoe->pcpu_noddp); - free_percpu(fcoe->pcpu_noddp_ext_buff); kfree(fcoe->extra_ddp_buffer); - ixgbe_fcoe_ddp_pools_free(fcoe); + + fcoe->extra_ddp_buffer = NULL; + fcoe->extra_ddp_buffer_dma = 0; +} + +/** + * ixgbe_setup_fcoe_ddp_resources - setup all fcoe ddp context resources + * @adapter: ixgbe adapter + * + * Sets up ddp context resouces + * + * Returns : 0 indicates success or -EINVAL on failure + */ +int ixgbe_setup_fcoe_ddp_resources(struct ixgbe_adapter *adapter) +{ + struct ixgbe_fcoe *fcoe = &adapter->fcoe; + struct device *dev = &adapter->pdev->dev; + void *buffer; + dma_addr_t dma; + unsigned int cpu; + + /* do nothing if no DDP pools were allocated */ + if (!fcoe->ddp_pool) + return 0; + + /* Extra buffer to be shared by all DDPs for HW work around */ + buffer = kmalloc(IXGBE_FCBUFF_MIN, GFP_ATOMIC); + if (!buffer) { + e_err(drv, "failed to allocate extra DDP buffer\n"); + return -ENOMEM; + } + + dma = dma_map_single(dev, buffer, IXGBE_FCBUFF_MIN, DMA_FROM_DEVICE); + if (dma_mapping_error(dev, dma)) { + e_err(drv, "failed to map extra DDP buffer\n"); + kfree(buffer); + return -ENOMEM; + } + + fcoe->extra_ddp_buffer = buffer; + fcoe->extra_ddp_buffer_dma = dma; + + /* allocate pci pool for each cpu */ + for_each_possible_cpu(cpu) { + int err = ixgbe_fcoe_dma_pool_alloc(fcoe, dev, cpu); + if (!err) + continue; + + e_err(drv, "failed to alloc DDP pool on cpu:%d\n", cpu); + ixgbe_free_fcoe_ddp_resources(adapter); + return -ENOMEM; + } + + return 0; +} + +static int ixgbe_fcoe_ddp_enable(struct ixgbe_adapter *adapter) +{ + struct ixgbe_fcoe *fcoe = &adapter->fcoe; + + if (!(adapter->flags & IXGBE_FLAG_FCOE_CAPABLE)) + return -EINVAL; + + fcoe->ddp_pool = alloc_percpu(struct ixgbe_fcoe_ddp_pool); + + if (!fcoe->ddp_pool) { + e_err(drv, "failed to allocate percpu DDP resources\n"); + return -ENOMEM; + } + + adapter->netdev->fcoe_ddp_xid = IXGBE_FCOE_DDP_MAX - 1; + + return 0; +} + +static void ixgbe_fcoe_ddp_disable(struct ixgbe_adapter *adapter) +{ + struct ixgbe_fcoe *fcoe = &adapter->fcoe; + + adapter->netdev->fcoe_ddp_xid = 0; + + if (!fcoe->ddp_pool) + return; + + free_percpu(fcoe->ddp_pool); + fcoe->ddp_pool = NULL; } /** @@ -751,40 +788,37 @@ void ixgbe_cleanup_fcoe(struct ixgbe_adapter *adapter) */ int ixgbe_fcoe_enable(struct net_device *netdev) { - int rc = -EINVAL; struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_fcoe *fcoe = &adapter->fcoe; + atomic_inc(&fcoe->refcnt); if (!(adapter->flags & IXGBE_FLAG_FCOE_CAPABLE)) - goto out_enable; + return -EINVAL; - atomic_inc(&fcoe->refcnt); if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) - goto out_enable; + return -EINVAL; e_info(drv, "Enabling FCoE offload features.\n"); if (netif_running(netdev)) netdev->netdev_ops->ndo_stop(netdev); - ixgbe_clear_interrupt_scheme(adapter); + /* Allocate per CPU memory to track DDP pools */ + ixgbe_fcoe_ddp_enable(adapter); + /* enable FCoE and notify stack */ adapter->flags |= IXGBE_FLAG_FCOE_ENABLED; - adapter->ring_feature[RING_F_FCOE].indices = IXGBE_FCRETA_SIZE; - netdev->features |= NETIF_F_FCOE_CRC; - netdev->features |= NETIF_F_FSO; netdev->features |= NETIF_F_FCOE_MTU; - netdev->fcoe_ddp_xid = IXGBE_FCOE_DDP_MAX - 1; + netdev_features_change(netdev); + /* release existing queues and reallocate them */ + ixgbe_clear_interrupt_scheme(adapter); ixgbe_init_interrupt_scheme(adapter); - netdev_features_change(netdev); if (netif_running(netdev)) netdev->netdev_ops->ndo_open(netdev); - rc = 0; -out_enable: - return rc; + return 0; } /** @@ -797,41 +831,35 @@ out_enable: */ int ixgbe_fcoe_disable(struct net_device *netdev) { - int rc = -EINVAL; struct ixgbe_adapter *adapter = netdev_priv(netdev); - struct ixgbe_fcoe *fcoe = &adapter->fcoe; - if (!(adapter->flags & IXGBE_FLAG_FCOE_CAPABLE)) - goto out_disable; + if (!atomic_dec_and_test(&adapter->fcoe.refcnt)) + return -EINVAL; if (!(adapter->flags & IXGBE_FLAG_FCOE_ENABLED)) - goto out_disable; - - if (!atomic_dec_and_test(&fcoe->refcnt)) - goto out_disable; + return -EINVAL; e_info(drv, "Disabling FCoE offload features.\n"); - netdev->features &= ~NETIF_F_FCOE_CRC; - netdev->features &= ~NETIF_F_FSO; - netdev->features &= ~NETIF_F_FCOE_MTU; - netdev->fcoe_ddp_xid = 0; - netdev_features_change(netdev); - if (netif_running(netdev)) netdev->netdev_ops->ndo_stop(netdev); - ixgbe_clear_interrupt_scheme(adapter); + /* Free per CPU memory to track DDP pools */ + ixgbe_fcoe_ddp_disable(adapter); + + /* disable FCoE and notify stack */ adapter->flags &= ~IXGBE_FLAG_FCOE_ENABLED; - adapter->ring_feature[RING_F_FCOE].indices = 0; - ixgbe_cleanup_fcoe(adapter); + netdev->features &= ~NETIF_F_FCOE_MTU; + + netdev_features_change(netdev); + + /* release existing queues and reallocate them */ + ixgbe_clear_interrupt_scheme(adapter); ixgbe_init_interrupt_scheme(adapter); if (netif_running(netdev)) netdev->netdev_ops->ndo_open(netdev); - rc = 0; -out_disable: - return rc; + return 0; } /** @@ -960,3 +988,18 @@ int ixgbe_fcoe_get_hbainfo(struct net_device *netdev, return 0; } + +/** + * ixgbe_fcoe_get_tc - get the current TC that fcoe is mapped to + * @adapter - pointer to the device adapter structure + * + * Return : TC that FCoE is mapped to + */ +u8 ixgbe_fcoe_get_tc(struct ixgbe_adapter *adapter) +{ +#ifdef CONFIG_IXGBE_DCB + return netdev_get_prio_tc_map(adapter->netdev, adapter->fcoe.up); +#else + return 0; +#endif +} diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.h index 1dbed17c8107..bf724da99375 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.h @@ -62,19 +62,24 @@ struct ixgbe_fcoe_ddp { struct scatterlist *sgl; dma_addr_t udp; u64 *udl; - struct pci_pool *pool; + struct dma_pool *pool; +}; + +/* per cpu variables */ +struct ixgbe_fcoe_ddp_pool { + struct dma_pool *pool; + u64 noddp; + u64 noddp_ext_buff; }; struct ixgbe_fcoe { - struct pci_pool **pool; + struct ixgbe_fcoe_ddp_pool __percpu *ddp_pool; atomic_t refcnt; spinlock_t lock; struct ixgbe_fcoe_ddp ddp[IXGBE_FCOE_DDP_MAX]; - unsigned char *extra_ddp_buffer; + void *extra_ddp_buffer; dma_addr_t extra_ddp_buffer_dma; unsigned long mode; - u64 __percpu *pcpu_noddp; - u64 __percpu *pcpu_noddp_ext_buff; #ifdef CONFIG_IXGBE_DCB u8 up; #endif diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c index c377706e81a8..17ecbcedd548 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -28,28 +28,83 @@ #include "ixgbe.h" #include "ixgbe_sriov.h" +#ifdef CONFIG_IXGBE_DCB /** - * ixgbe_cache_ring_rss - Descriptor ring to register mapping for RSS + * ixgbe_cache_ring_dcb_sriov - Descriptor ring to register mapping for SR-IOV * @adapter: board private structure to initialize * - * Cache the descriptor ring offsets for RSS to the assigned rings. + * Cache the descriptor ring offsets for SR-IOV to the assigned rings. It + * will also try to cache the proper offsets if RSS/FCoE are enabled along + * with VMDq. * **/ -static inline bool ixgbe_cache_ring_rss(struct ixgbe_adapter *adapter) +static bool ixgbe_cache_ring_dcb_sriov(struct ixgbe_adapter *adapter) { +#ifdef IXGBE_FCOE + struct ixgbe_ring_feature *fcoe = &adapter->ring_feature[RING_F_FCOE]; +#endif /* IXGBE_FCOE */ + struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ]; int i; + u16 reg_idx; + u8 tcs = netdev_get_num_tc(adapter->netdev); - if (!(adapter->flags & IXGBE_FLAG_RSS_ENABLED)) + /* verify we have DCB queueing enabled before proceeding */ + if (tcs <= 1) return false; - for (i = 0; i < adapter->num_rx_queues; i++) - adapter->rx_ring[i]->reg_idx = i; - for (i = 0; i < adapter->num_tx_queues; i++) - adapter->tx_ring[i]->reg_idx = i; + /* verify we have VMDq enabled before proceeding */ + if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) + return false; + + /* start at VMDq register offset for SR-IOV enabled setups */ + reg_idx = vmdq->offset * __ALIGN_MASK(1, ~vmdq->mask); + for (i = 0; i < adapter->num_rx_queues; i++, reg_idx++) { + /* If we are greater than indices move to next pool */ + if ((reg_idx & ~vmdq->mask) >= tcs) + reg_idx = __ALIGN_MASK(reg_idx, ~vmdq->mask); + adapter->rx_ring[i]->reg_idx = reg_idx; + } + + reg_idx = vmdq->offset * __ALIGN_MASK(1, ~vmdq->mask); + for (i = 0; i < adapter->num_tx_queues; i++, reg_idx++) { + /* If we are greater than indices move to next pool */ + if ((reg_idx & ~vmdq->mask) >= tcs) + reg_idx = __ALIGN_MASK(reg_idx, ~vmdq->mask); + adapter->tx_ring[i]->reg_idx = reg_idx; + } + +#ifdef IXGBE_FCOE + /* nothing to do if FCoE is disabled */ + if (!(adapter->flags & IXGBE_FLAG_FCOE_ENABLED)) + return true; + + /* The work is already done if the FCoE ring is shared */ + if (fcoe->offset < tcs) + return true; + + /* The FCoE rings exist separately, we need to move their reg_idx */ + if (fcoe->indices) { + u16 queues_per_pool = __ALIGN_MASK(1, ~vmdq->mask); + u8 fcoe_tc = ixgbe_fcoe_get_tc(adapter); + + reg_idx = (vmdq->offset + vmdq->indices) * queues_per_pool; + for (i = fcoe->offset; i < adapter->num_rx_queues; i++) { + reg_idx = __ALIGN_MASK(reg_idx, ~vmdq->mask) + fcoe_tc; + adapter->rx_ring[i]->reg_idx = reg_idx; + reg_idx++; + } + + reg_idx = (vmdq->offset + vmdq->indices) * queues_per_pool; + for (i = fcoe->offset; i < adapter->num_tx_queues; i++) { + reg_idx = __ALIGN_MASK(reg_idx, ~vmdq->mask) + fcoe_tc; + adapter->tx_ring[i]->reg_idx = reg_idx; + reg_idx++; + } + } +#endif /* IXGBE_FCOE */ return true; } -#ifdef CONFIG_IXGBE_DCB /* ixgbe_get_first_reg_idx - Return first register index associated with ring */ static void ixgbe_get_first_reg_idx(struct ixgbe_adapter *adapter, u8 tc, @@ -64,42 +119,37 @@ static void ixgbe_get_first_reg_idx(struct ixgbe_adapter *adapter, u8 tc, switch (hw->mac.type) { case ixgbe_mac_82598EB: - *tx = tc << 2; - *rx = tc << 3; + /* TxQs/TC: 4 RxQs/TC: 8 */ + *tx = tc << 2; /* 0, 4, 8, 12, 16, 20, 24, 28 */ + *rx = tc << 3; /* 0, 8, 16, 24, 32, 40, 48, 56 */ break; case ixgbe_mac_82599EB: case ixgbe_mac_X540: if (num_tcs > 4) { - if (tc < 3) { - *tx = tc << 5; - *rx = tc << 4; - } else if (tc < 5) { - *tx = ((tc + 2) << 4); - *rx = tc << 4; - } else if (tc < num_tcs) { - *tx = ((tc + 8) << 3); - *rx = tc << 4; - } + /* + * TCs : TC0/1 TC2/3 TC4-7 + * TxQs/TC: 32 16 8 + * RxQs/TC: 16 16 16 + */ + *rx = tc << 4; + if (tc < 3) + *tx = tc << 5; /* 0, 32, 64 */ + else if (tc < 5) + *tx = (tc + 2) << 4; /* 80, 96 */ + else + *tx = (tc + 8) << 3; /* 104, 112, 120 */ } else { - *rx = tc << 5; - switch (tc) { - case 0: - *tx = 0; - break; - case 1: - *tx = 64; - break; - case 2: - *tx = 96; - break; - case 3: - *tx = 112; - break; - default: - break; - } + /* + * TCs : TC0 TC1 TC2/3 + * TxQs/TC: 64 32 16 + * RxQs/TC: 32 32 32 + */ + *rx = tc << 5; + if (tc < 2) + *tx = tc << 6; /* 0, 64 */ + else + *tx = (tc + 4) << 4; /* 96, 112 */ } - break; default: break; } @@ -112,106 +162,115 @@ static void ixgbe_get_first_reg_idx(struct ixgbe_adapter *adapter, u8 tc, * Cache the descriptor ring offsets for DCB to the assigned rings. * **/ -static inline bool ixgbe_cache_ring_dcb(struct ixgbe_adapter *adapter) +static bool ixgbe_cache_ring_dcb(struct ixgbe_adapter *adapter) { struct net_device *dev = adapter->netdev; - int i, j, k; + unsigned int tx_idx, rx_idx; + int tc, offset, rss_i, i; u8 num_tcs = netdev_get_num_tc(dev); - if (!num_tcs) + /* verify we have DCB queueing enabled before proceeding */ + if (num_tcs <= 1) return false; - for (i = 0, k = 0; i < num_tcs; i++) { - unsigned int tx_s, rx_s; - u16 count = dev->tc_to_txq[i].count; + rss_i = adapter->ring_feature[RING_F_RSS].indices; - ixgbe_get_first_reg_idx(adapter, i, &tx_s, &rx_s); - for (j = 0; j < count; j++, k++) { - adapter->tx_ring[k]->reg_idx = tx_s + j; - adapter->rx_ring[k]->reg_idx = rx_s + j; - adapter->tx_ring[k]->dcb_tc = i; - adapter->rx_ring[k]->dcb_tc = i; + for (tc = 0, offset = 0; tc < num_tcs; tc++, offset += rss_i) { + ixgbe_get_first_reg_idx(adapter, tc, &tx_idx, &rx_idx); + for (i = 0; i < rss_i; i++, tx_idx++, rx_idx++) { + adapter->tx_ring[offset + i]->reg_idx = tx_idx; + adapter->rx_ring[offset + i]->reg_idx = rx_idx; + adapter->tx_ring[offset + i]->dcb_tc = tc; + adapter->rx_ring[offset + i]->dcb_tc = tc; } } return true; } -#endif +#endif /** - * ixgbe_cache_ring_fdir - Descriptor ring to register mapping for Flow Director + * ixgbe_cache_ring_sriov - Descriptor ring to register mapping for sriov * @adapter: board private structure to initialize * - * Cache the descriptor ring offsets for Flow Director to the assigned rings. + * SR-IOV doesn't use any descriptor rings but changes the default if + * no other mapping is used. * - **/ -static inline bool ixgbe_cache_ring_fdir(struct ixgbe_adapter *adapter) + */ +static bool ixgbe_cache_ring_sriov(struct ixgbe_adapter *adapter) { +#ifdef IXGBE_FCOE + struct ixgbe_ring_feature *fcoe = &adapter->ring_feature[RING_F_FCOE]; +#endif /* IXGBE_FCOE */ + struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ]; + struct ixgbe_ring_feature *rss = &adapter->ring_feature[RING_F_RSS]; int i; - bool ret = false; - - if ((adapter->flags & IXGBE_FLAG_RSS_ENABLED) && - (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE)) { - for (i = 0; i < adapter->num_rx_queues; i++) - adapter->rx_ring[i]->reg_idx = i; - for (i = 0; i < adapter->num_tx_queues; i++) - adapter->tx_ring[i]->reg_idx = i; - ret = true; + u16 reg_idx; + + /* only proceed if VMDq is enabled */ + if (!(adapter->flags & IXGBE_FLAG_VMDQ_ENABLED)) + return false; + + /* start at VMDq register offset for SR-IOV enabled setups */ + reg_idx = vmdq->offset * __ALIGN_MASK(1, ~vmdq->mask); + for (i = 0; i < adapter->num_rx_queues; i++, reg_idx++) { +#ifdef IXGBE_FCOE + /* Allow first FCoE queue to be mapped as RSS */ + if (fcoe->offset && (i > fcoe->offset)) + break; +#endif + /* If we are greater than indices move to next pool */ + if ((reg_idx & ~vmdq->mask) >= rss->indices) + reg_idx = __ALIGN_MASK(reg_idx, ~vmdq->mask); + adapter->rx_ring[i]->reg_idx = reg_idx; } - return ret; -} +#ifdef IXGBE_FCOE + /* FCoE uses a linear block of queues so just assigning 1:1 */ + for (; i < adapter->num_rx_queues; i++, reg_idx++) + adapter->rx_ring[i]->reg_idx = reg_idx; +#endif + reg_idx = vmdq->offset * __ALIGN_MASK(1, ~vmdq->mask); + for (i = 0; i < adapter->num_tx_queues; i++, reg_idx++) { #ifdef IXGBE_FCOE -/** - * ixgbe_cache_ring_fcoe - Descriptor ring to register mapping for the FCoE - * @adapter: board private structure to initialize - * - * Cache the descriptor ring offsets for FCoE mode to the assigned rings. - * - */ -static inline bool ixgbe_cache_ring_fcoe(struct ixgbe_adapter *adapter) -{ - struct ixgbe_ring_feature *f = &adapter->ring_feature[RING_F_FCOE]; - int i; - u8 fcoe_rx_i = 0, fcoe_tx_i = 0; + /* Allow first FCoE queue to be mapped as RSS */ + if (fcoe->offset && (i > fcoe->offset)) + break; +#endif + /* If we are greater than indices move to next pool */ + if ((reg_idx & rss->mask) >= rss->indices) + reg_idx = __ALIGN_MASK(reg_idx, ~vmdq->mask); + adapter->tx_ring[i]->reg_idx = reg_idx; + } - if (!(adapter->flags & IXGBE_FLAG_FCOE_ENABLED)) - return false; +#ifdef IXGBE_FCOE + /* FCoE uses a linear block of queues so just assigning 1:1 */ + for (; i < adapter->num_tx_queues; i++, reg_idx++) + adapter->tx_ring[i]->reg_idx = reg_idx; - if (adapter->flags & IXGBE_FLAG_RSS_ENABLED) { - if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) - ixgbe_cache_ring_fdir(adapter); - else - ixgbe_cache_ring_rss(adapter); +#endif - fcoe_rx_i = f->mask; - fcoe_tx_i = f->mask; - } - for (i = 0; i < f->indices; i++, fcoe_rx_i++, fcoe_tx_i++) { - adapter->rx_ring[f->mask + i]->reg_idx = fcoe_rx_i; - adapter->tx_ring[f->mask + i]->reg_idx = fcoe_tx_i; - } return true; } -#endif /* IXGBE_FCOE */ /** - * ixgbe_cache_ring_sriov - Descriptor ring to register mapping for sriov + * ixgbe_cache_ring_rss - Descriptor ring to register mapping for RSS * @adapter: board private structure to initialize * - * SR-IOV doesn't use any descriptor rings but changes the default if - * no other mapping is used. + * Cache the descriptor ring offsets for RSS to the assigned rings. * - */ -static inline bool ixgbe_cache_ring_sriov(struct ixgbe_adapter *adapter) + **/ +static bool ixgbe_cache_ring_rss(struct ixgbe_adapter *adapter) { - adapter->rx_ring[0]->reg_idx = adapter->num_vfs * 2; - adapter->tx_ring[0]->reg_idx = adapter->num_vfs * 2; - if (adapter->num_vfs) - return true; - else - return false; + int i; + + for (i = 0; i < adapter->num_rx_queues; i++) + adapter->rx_ring[i]->reg_idx = i; + for (i = 0; i < adapter->num_tx_queues; i++) + adapter->tx_ring[i]->reg_idx = i; + + return true; } /** @@ -231,186 +290,384 @@ static void ixgbe_cache_ring_register(struct ixgbe_adapter *adapter) adapter->rx_ring[0]->reg_idx = 0; adapter->tx_ring[0]->reg_idx = 0; - if (ixgbe_cache_ring_sriov(adapter)) - return; - #ifdef CONFIG_IXGBE_DCB - if (ixgbe_cache_ring_dcb(adapter)) + if (ixgbe_cache_ring_dcb_sriov(adapter)) return; -#endif -#ifdef IXGBE_FCOE - if (ixgbe_cache_ring_fcoe(adapter)) + if (ixgbe_cache_ring_dcb(adapter)) return; -#endif /* IXGBE_FCOE */ - if (ixgbe_cache_ring_fdir(adapter)) +#endif + if (ixgbe_cache_ring_sriov(adapter)) return; - if (ixgbe_cache_ring_rss(adapter)) - return; + ixgbe_cache_ring_rss(adapter); } -/** - * ixgbe_set_sriov_queues: Allocate queues for IOV use - * @adapter: board private structure to initialize - * - * IOV doesn't actually use anything, so just NAK the - * request for now and let the other queue routines - * figure out what to do. - */ -static inline bool ixgbe_set_sriov_queues(struct ixgbe_adapter *adapter) -{ - return false; -} +#define IXGBE_RSS_16Q_MASK 0xF +#define IXGBE_RSS_8Q_MASK 0x7 +#define IXGBE_RSS_4Q_MASK 0x3 +#define IXGBE_RSS_2Q_MASK 0x1 +#define IXGBE_RSS_DISABLED_MASK 0x0 +#ifdef CONFIG_IXGBE_DCB /** - * ixgbe_set_rss_queues: Allocate queues for RSS + * ixgbe_set_dcb_sriov_queues: Allocate queues for SR-IOV devices w/ DCB * @adapter: board private structure to initialize * - * This is our "base" multiqueue mode. RSS (Receive Side Scaling) will try - * to allocate one Rx queue per CPU, and if available, one Tx queue per CPU. + * When SR-IOV (Single Root IO Virtualiztion) is enabled, allocate queues + * and VM pools where appropriate. Also assign queues based on DCB + * priorities and map accordingly.. * **/ -static inline bool ixgbe_set_rss_queues(struct ixgbe_adapter *adapter) +static bool ixgbe_set_dcb_sriov_queues(struct ixgbe_adapter *adapter) { - bool ret = false; - struct ixgbe_ring_feature *f = &adapter->ring_feature[RING_F_RSS]; - - if (adapter->flags & IXGBE_FLAG_RSS_ENABLED) { - f->mask = 0xF; - adapter->num_rx_queues = f->indices; - adapter->num_tx_queues = f->indices; - ret = true; + int i; + u16 vmdq_i = adapter->ring_feature[RING_F_VMDQ].limit; + u16 vmdq_m = 0; +#ifdef IXGBE_FCOE + u16 fcoe_i = 0; +#endif + u8 tcs = netdev_get_num_tc(adapter->netdev); + + /* verify we have DCB queueing enabled before proceeding */ + if (tcs <= 1) + return false; + + /* verify we have VMDq enabled before proceeding */ + if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) + return false; + + /* Add starting offset to total pool count */ + vmdq_i += adapter->ring_feature[RING_F_VMDQ].offset; + + /* 16 pools w/ 8 TC per pool */ + if (tcs > 4) { + vmdq_i = min_t(u16, vmdq_i, 16); + vmdq_m = IXGBE_82599_VMDQ_8Q_MASK; + /* 32 pools w/ 4 TC per pool */ + } else { + vmdq_i = min_t(u16, vmdq_i, 32); + vmdq_m = IXGBE_82599_VMDQ_4Q_MASK; } - return ret; -} +#ifdef IXGBE_FCOE + /* queues in the remaining pools are available for FCoE */ + fcoe_i = (128 / __ALIGN_MASK(1, ~vmdq_m)) - vmdq_i; -/** - * ixgbe_set_fdir_queues: Allocate queues for Flow Director - * @adapter: board private structure to initialize - * - * Flow Director is an advanced Rx filter, attempting to get Rx flows back - * to the original CPU that initiated the Tx session. This runs in addition - * to RSS, so if a packet doesn't match an FDIR filter, we can still spread the - * Rx load across CPUs using RSS. - * - **/ -static inline bool ixgbe_set_fdir_queues(struct ixgbe_adapter *adapter) -{ - bool ret = false; - struct ixgbe_ring_feature *f_fdir = &adapter->ring_feature[RING_F_FDIR]; +#endif + /* remove the starting offset from the pool count */ + vmdq_i -= adapter->ring_feature[RING_F_VMDQ].offset; - f_fdir->indices = min_t(int, num_online_cpus(), f_fdir->indices); - f_fdir->mask = 0; + /* save features for later use */ + adapter->ring_feature[RING_F_VMDQ].indices = vmdq_i; + adapter->ring_feature[RING_F_VMDQ].mask = vmdq_m; /* - * Use RSS in addition to Flow Director to ensure the best - * distribution of flows across cores, even when an FDIR flow - * isn't matched. + * We do not support DCB, VMDq, and RSS all simultaneously + * so we will disable RSS since it is the lowest priority */ - if ((adapter->flags & IXGBE_FLAG_RSS_ENABLED) && - (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE)) { - adapter->num_tx_queues = f_fdir->indices; - adapter->num_rx_queues = f_fdir->indices; - ret = true; - } else { - adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE; + adapter->ring_feature[RING_F_RSS].indices = 1; + adapter->ring_feature[RING_F_RSS].mask = IXGBE_RSS_DISABLED_MASK; + + /* disable ATR as it is not supported when VMDq is enabled */ + adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE; + + adapter->num_rx_pools = vmdq_i; + adapter->num_rx_queues_per_pool = tcs; + + adapter->num_tx_queues = vmdq_i * tcs; + adapter->num_rx_queues = vmdq_i * tcs; + +#ifdef IXGBE_FCOE + if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) { + struct ixgbe_ring_feature *fcoe; + + fcoe = &adapter->ring_feature[RING_F_FCOE]; + + /* limit ourselves based on feature limits */ + fcoe_i = min_t(u16, fcoe_i, num_online_cpus()); + fcoe_i = min_t(u16, fcoe_i, fcoe->limit); + + if (fcoe_i) { + /* alloc queues for FCoE separately */ + fcoe->indices = fcoe_i; + fcoe->offset = vmdq_i * tcs; + + /* add queues to adapter */ + adapter->num_tx_queues += fcoe_i; + adapter->num_rx_queues += fcoe_i; + } else if (tcs > 1) { + /* use queue belonging to FcoE TC */ + fcoe->indices = 1; + fcoe->offset = ixgbe_fcoe_get_tc(adapter); + } else { + adapter->flags &= ~IXGBE_FLAG_FCOE_ENABLED; + + fcoe->indices = 0; + fcoe->offset = 0; + } } - return ret; + +#endif /* IXGBE_FCOE */ + /* configure TC to queue mapping */ + for (i = 0; i < tcs; i++) + netdev_set_tc_queue(adapter->netdev, i, 1, i); + + return true; } +static bool ixgbe_set_dcb_queues(struct ixgbe_adapter *adapter) +{ + struct net_device *dev = adapter->netdev; + struct ixgbe_ring_feature *f; + int rss_i, rss_m, i; + int tcs; + + /* Map queue offset and counts onto allocated tx queues */ + tcs = netdev_get_num_tc(dev); + + /* verify we have DCB queueing enabled before proceeding */ + if (tcs <= 1) + return false; + + /* determine the upper limit for our current DCB mode */ + rss_i = dev->num_tx_queues / tcs; + if (adapter->hw.mac.type == ixgbe_mac_82598EB) { + /* 8 TC w/ 4 queues per TC */ + rss_i = min_t(u16, rss_i, 4); + rss_m = IXGBE_RSS_4Q_MASK; + } else if (tcs > 4) { + /* 8 TC w/ 8 queues per TC */ + rss_i = min_t(u16, rss_i, 8); + rss_m = IXGBE_RSS_8Q_MASK; + } else { + /* 4 TC w/ 16 queues per TC */ + rss_i = min_t(u16, rss_i, 16); + rss_m = IXGBE_RSS_16Q_MASK; + } + + /* set RSS mask and indices */ + f = &adapter->ring_feature[RING_F_RSS]; + rss_i = min_t(int, rss_i, f->limit); + f->indices = rss_i; + f->mask = rss_m; + + /* disable ATR as it is not supported when multiple TCs are enabled */ + adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE; + #ifdef IXGBE_FCOE + /* FCoE enabled queues require special configuration indexed + * by feature specific indices and offset. Here we map FCoE + * indices onto the DCB queue pairs allowing FCoE to own + * configuration later. + */ + if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) { + u8 tc = ixgbe_fcoe_get_tc(adapter); + + f = &adapter->ring_feature[RING_F_FCOE]; + f->indices = min_t(u16, rss_i, f->limit); + f->offset = rss_i * tc; + } + +#endif /* IXGBE_FCOE */ + for (i = 0; i < tcs; i++) + netdev_set_tc_queue(dev, i, rss_i, rss_i * i); + + adapter->num_tx_queues = rss_i * tcs; + adapter->num_rx_queues = rss_i * tcs; + + return true; +} + +#endif /** - * ixgbe_set_fcoe_queues: Allocate queues for Fiber Channel over Ethernet (FCoE) + * ixgbe_set_sriov_queues - Allocate queues for SR-IOV devices * @adapter: board private structure to initialize * - * FCoE RX FCRETA can use up to 8 rx queues for up to 8 different exchanges. - * The ring feature mask is not used as a mask for FCoE, as it can take any 8 - * rx queues out of the max number of rx queues, instead, it is used as the - * index of the first rx queue used by FCoE. + * When SR-IOV (Single Root IO Virtualiztion) is enabled, allocate queues + * and VM pools where appropriate. If RSS is available, then also try and + * enable RSS and map accordingly. * **/ -static inline bool ixgbe_set_fcoe_queues(struct ixgbe_adapter *adapter) +static bool ixgbe_set_sriov_queues(struct ixgbe_adapter *adapter) { - struct ixgbe_ring_feature *f = &adapter->ring_feature[RING_F_FCOE]; + u16 vmdq_i = adapter->ring_feature[RING_F_VMDQ].limit; + u16 vmdq_m = 0; + u16 rss_i = adapter->ring_feature[RING_F_RSS].limit; + u16 rss_m = IXGBE_RSS_DISABLED_MASK; +#ifdef IXGBE_FCOE + u16 fcoe_i = 0; +#endif - if (!(adapter->flags & IXGBE_FLAG_FCOE_ENABLED)) + /* only proceed if SR-IOV is enabled */ + if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) return false; - f->indices = min_t(int, num_online_cpus(), f->indices); + /* Add starting offset to total pool count */ + vmdq_i += adapter->ring_feature[RING_F_VMDQ].offset; - adapter->num_rx_queues = 1; - adapter->num_tx_queues = 1; + /* double check we are limited to maximum pools */ + vmdq_i = min_t(u16, IXGBE_MAX_VMDQ_INDICES, vmdq_i); - if (adapter->flags & IXGBE_FLAG_RSS_ENABLED) { - e_info(probe, "FCoE enabled with RSS\n"); - if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) - ixgbe_set_fdir_queues(adapter); - else - ixgbe_set_rss_queues(adapter); + /* 64 pool mode with 2 queues per pool */ + if ((vmdq_i > 32) || (rss_i < 4)) { + vmdq_m = IXGBE_82599_VMDQ_2Q_MASK; + rss_m = IXGBE_RSS_2Q_MASK; + rss_i = min_t(u16, rss_i, 2); + /* 32 pool mode with 4 queues per pool */ + } else { + vmdq_m = IXGBE_82599_VMDQ_4Q_MASK; + rss_m = IXGBE_RSS_4Q_MASK; + rss_i = 4; } - /* adding FCoE rx rings to the end */ - f->mask = adapter->num_rx_queues; - adapter->num_rx_queues += f->indices; - adapter->num_tx_queues += f->indices; +#ifdef IXGBE_FCOE + /* queues in the remaining pools are available for FCoE */ + fcoe_i = 128 - (vmdq_i * __ALIGN_MASK(1, ~vmdq_m)); + +#endif + /* remove the starting offset from the pool count */ + vmdq_i -= adapter->ring_feature[RING_F_VMDQ].offset; + + /* save features for later use */ + adapter->ring_feature[RING_F_VMDQ].indices = vmdq_i; + adapter->ring_feature[RING_F_VMDQ].mask = vmdq_m; + + /* limit RSS based on user input and save for later use */ + adapter->ring_feature[RING_F_RSS].indices = rss_i; + adapter->ring_feature[RING_F_RSS].mask = rss_m; + adapter->num_rx_pools = vmdq_i; + adapter->num_rx_queues_per_pool = rss_i; + + adapter->num_rx_queues = vmdq_i * rss_i; + adapter->num_tx_queues = vmdq_i * rss_i; + + /* disable ATR as it is not supported when VMDq is enabled */ + adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE; + +#ifdef IXGBE_FCOE + /* + * FCoE can use rings from adjacent buffers to allow RSS + * like behavior. To account for this we need to add the + * FCoE indices to the total ring count. + */ + if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) { + struct ixgbe_ring_feature *fcoe; + + fcoe = &adapter->ring_feature[RING_F_FCOE]; + + /* limit ourselves based on feature limits */ + fcoe_i = min_t(u16, fcoe_i, fcoe->limit); + + if (vmdq_i > 1 && fcoe_i) { + /* reserve no more than number of CPUs */ + fcoe_i = min_t(u16, fcoe_i, num_online_cpus()); + + /* alloc queues for FCoE separately */ + fcoe->indices = fcoe_i; + fcoe->offset = vmdq_i * rss_i; + } else { + /* merge FCoE queues with RSS queues */ + fcoe_i = min_t(u16, fcoe_i + rss_i, num_online_cpus()); + + /* limit indices to rss_i if MSI-X is disabled */ + if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) + fcoe_i = rss_i; + + /* attempt to reserve some queues for just FCoE */ + fcoe->indices = min_t(u16, fcoe_i, fcoe->limit); + fcoe->offset = fcoe_i - fcoe->indices; + + fcoe_i -= rss_i; + } + + /* add queues to adapter */ + adapter->num_tx_queues += fcoe_i; + adapter->num_rx_queues += fcoe_i; + } + +#endif return true; } -#endif /* IXGBE_FCOE */ -/* Artificial max queue cap per traffic class in DCB mode */ -#define DCB_QUEUE_CAP 8 - -#ifdef CONFIG_IXGBE_DCB -static inline bool ixgbe_set_dcb_queues(struct ixgbe_adapter *adapter) +/** + * ixgbe_set_rss_queues - Allocate queues for RSS + * @adapter: board private structure to initialize + * + * This is our "base" multiqueue mode. RSS (Receive Side Scaling) will try + * to allocate one Rx queue per CPU, and if available, one Tx queue per CPU. + * + **/ +static bool ixgbe_set_rss_queues(struct ixgbe_adapter *adapter) { - int per_tc_q, q, i, offset = 0; - struct net_device *dev = adapter->netdev; - int tcs = netdev_get_num_tc(dev); + struct ixgbe_ring_feature *f; + u16 rss_i; - if (!tcs) - return false; + /* set mask for 16 queue limit of RSS */ + f = &adapter->ring_feature[RING_F_RSS]; + rss_i = f->limit; - /* Map queue offset and counts onto allocated tx queues */ - per_tc_q = min_t(unsigned int, dev->num_tx_queues / tcs, DCB_QUEUE_CAP); - q = min_t(int, num_online_cpus(), per_tc_q); + f->indices = rss_i; + f->mask = IXGBE_RSS_16Q_MASK; - for (i = 0; i < tcs; i++) { - netdev_set_tc_queue(dev, i, q, offset); - offset += q; - } + /* disable ATR by default, it will be configured below */ + adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE; + + /* + * Use Flow Director in addition to RSS to ensure the best + * distribution of flows across cores, even when an FDIR flow + * isn't matched. + */ + if (rss_i > 1 && adapter->atr_sample_rate) { + f = &adapter->ring_feature[RING_F_FDIR]; - adapter->num_tx_queues = q * tcs; - adapter->num_rx_queues = q * tcs; + f->indices = min_t(u16, num_online_cpus(), f->limit); + rss_i = max_t(u16, rss_i, f->indices); + + if (!(adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE)) + adapter->flags |= IXGBE_FLAG_FDIR_HASH_CAPABLE; + } #ifdef IXGBE_FCOE - /* FCoE enabled queues require special configuration indexed - * by feature specific indices and mask. Here we map FCoE - * indices onto the DCB queue pairs allowing FCoE to own - * configuration later. + /* + * FCoE can exist on the same rings as standard network traffic + * however it is preferred to avoid that if possible. In order + * to get the best performance we allocate as many FCoE queues + * as we can and we place them at the end of the ring array to + * avoid sharing queues with standard RSS on systems with 24 or + * more CPUs. */ if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) { - u8 prio_tc[MAX_USER_PRIORITY] = {0}; - int tc; - struct ixgbe_ring_feature *f = - &adapter->ring_feature[RING_F_FCOE]; - - ixgbe_dcb_unpack_map(&adapter->dcb_cfg, DCB_TX_CONFIG, prio_tc); - tc = prio_tc[adapter->fcoe.up]; - f->indices = dev->tc_to_txq[tc].count; - f->mask = dev->tc_to_txq[tc].offset; + struct net_device *dev = adapter->netdev; + u16 fcoe_i; + + f = &adapter->ring_feature[RING_F_FCOE]; + + /* merge FCoE queues with RSS queues */ + fcoe_i = min_t(u16, f->limit + rss_i, num_online_cpus()); + fcoe_i = min_t(u16, fcoe_i, dev->num_tx_queues); + + /* limit indices to rss_i if MSI-X is disabled */ + if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) + fcoe_i = rss_i; + + /* attempt to reserve some queues for just FCoE */ + f->indices = min_t(u16, fcoe_i, f->limit); + f->offset = fcoe_i - f->indices; + rss_i = max_t(u16, fcoe_i, rss_i); } -#endif + +#endif /* IXGBE_FCOE */ + adapter->num_rx_queues = rss_i; + adapter->num_tx_queues = rss_i; return true; } -#endif /** - * ixgbe_set_num_queues: Allocate queues for device, feature dependent + * ixgbe_set_num_queues - Allocate queues for device, feature dependent * @adapter: board private structure to initialize * * This is the top level queue allocation routine. The order here is very @@ -420,7 +677,7 @@ static inline bool ixgbe_set_dcb_queues(struct ixgbe_adapter *adapter) * fallthrough conditions. * **/ -static int ixgbe_set_num_queues(struct ixgbe_adapter *adapter) +static void ixgbe_set_num_queues(struct ixgbe_adapter *adapter) { /* Start with base case */ adapter->num_rx_queues = 1; @@ -428,38 +685,18 @@ static int ixgbe_set_num_queues(struct ixgbe_adapter *adapter) adapter->num_rx_pools = adapter->num_rx_queues; adapter->num_rx_queues_per_pool = 1; - if (ixgbe_set_sriov_queues(adapter)) - goto done; - #ifdef CONFIG_IXGBE_DCB + if (ixgbe_set_dcb_sriov_queues(adapter)) + return; + if (ixgbe_set_dcb_queues(adapter)) - goto done; + return; #endif -#ifdef IXGBE_FCOE - if (ixgbe_set_fcoe_queues(adapter)) - goto done; - -#endif /* IXGBE_FCOE */ - if (ixgbe_set_fdir_queues(adapter)) - goto done; - - if (ixgbe_set_rss_queues(adapter)) - goto done; - - /* fallback to base case */ - adapter->num_rx_queues = 1; - adapter->num_tx_queues = 1; - -done: - if ((adapter->netdev->reg_state == NETREG_UNREGISTERED) || - (adapter->netdev->reg_state == NETREG_UNREGISTERING)) - return 0; + if (ixgbe_set_sriov_queues(adapter)) + return; - /* Notify the stack of the (possibly) reduced queue counts. */ - netif_set_real_num_tx_queues(adapter->netdev, adapter->num_tx_queues); - return netif_set_real_num_rx_queues(adapter->netdev, - adapter->num_rx_queues); + ixgbe_set_rss_queues(adapter); } static void ixgbe_acquire_msix_vectors(struct ixgbe_adapter *adapter, @@ -507,8 +744,8 @@ static void ixgbe_acquire_msix_vectors(struct ixgbe_adapter *adapter, * of max_msix_q_vectors + NON_Q_VECTORS, or the number of * vectors we were allocated. */ - adapter->num_msix_vectors = min(vectors, - adapter->max_msix_q_vectors + NON_Q_VECTORS); + vectors -= NON_Q_VECTORS; + adapter->num_q_vectors = min(vectors, adapter->max_q_vectors); } } @@ -632,8 +869,8 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter, if (adapter->netdev->features & NETIF_F_FCOE_MTU) { struct ixgbe_ring_feature *f; f = &adapter->ring_feature[RING_F_FCOE]; - if ((rxr_idx >= f->mask) && - (rxr_idx < f->mask + f->indices)) + if ((rxr_idx >= f->offset) && + (rxr_idx < f->offset + f->indices)) set_bit(__IXGBE_RX_FCOE, &ring->state); } @@ -695,7 +932,7 @@ static void ixgbe_free_q_vector(struct ixgbe_adapter *adapter, int v_idx) **/ static int ixgbe_alloc_q_vectors(struct ixgbe_adapter *adapter) { - int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; + int q_vectors = adapter->num_q_vectors; int rxr_remaining = adapter->num_rx_queues; int txr_remaining = adapter->num_tx_queues; int rxr_idx = 0, txr_idx = 0, v_idx = 0; @@ -739,10 +976,12 @@ static int ixgbe_alloc_q_vectors(struct ixgbe_adapter *adapter) return 0; err_out: - while (v_idx) { - v_idx--; + adapter->num_tx_queues = 0; + adapter->num_rx_queues = 0; + adapter->num_q_vectors = 0; + + while (v_idx--) ixgbe_free_q_vector(adapter, v_idx); - } return -ENOMEM; } @@ -757,14 +996,13 @@ err_out: **/ static void ixgbe_free_q_vectors(struct ixgbe_adapter *adapter) { - int v_idx, q_vectors; + int v_idx = adapter->num_q_vectors; - if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) - q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - else - q_vectors = 1; + adapter->num_tx_queues = 0; + adapter->num_rx_queues = 0; + adapter->num_q_vectors = 0; - for (v_idx = 0; v_idx < q_vectors; v_idx++) + while (v_idx--) ixgbe_free_q_vector(adapter, v_idx); } @@ -788,11 +1026,10 @@ static void ixgbe_reset_interrupt_capability(struct ixgbe_adapter *adapter) * Attempt to configure the interrupts using the best available * capabilities of the hardware and the kernel. **/ -static int ixgbe_set_interrupt_capability(struct ixgbe_adapter *adapter) +static void ixgbe_set_interrupt_capability(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; - int err = 0; - int vector, v_budget; + int vector, v_budget, err; /* * It's easy to be greedy for MSI-X vectors, but it really @@ -825,38 +1062,41 @@ static int ixgbe_set_interrupt_capability(struct ixgbe_adapter *adapter) ixgbe_acquire_msix_vectors(adapter, v_budget); if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) - goto out; + return; } - adapter->flags &= ~IXGBE_FLAG_DCB_ENABLED; - adapter->flags &= ~IXGBE_FLAG_RSS_ENABLED; - if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) { - e_err(probe, - "ATR is not supported while multiple " - "queues are disabled. Disabling Flow Director\n"); + /* disable DCB if number of TCs exceeds 1 */ + if (netdev_get_num_tc(adapter->netdev) > 1) { + e_err(probe, "num TCs exceeds number of queues - disabling DCB\n"); + netdev_reset_tc(adapter->netdev); + + if (adapter->hw.mac.type == ixgbe_mac_82598EB) + adapter->hw.fc.requested_mode = adapter->last_lfc_mode; + + adapter->flags &= ~IXGBE_FLAG_DCB_ENABLED; + adapter->temp_dcb_cfg.pfc_mode_enable = false; + adapter->dcb_cfg.pfc_mode_enable = false; } - adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE; - adapter->atr_sample_rate = 0; - if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) - ixgbe_disable_sriov(adapter); + adapter->dcb_cfg.num_tcs.pg_tcs = 1; + adapter->dcb_cfg.num_tcs.pfc_tcs = 1; + + /* disable SR-IOV */ + ixgbe_disable_sriov(adapter); - err = ixgbe_set_num_queues(adapter); - if (err) - return err; + /* disable RSS */ + adapter->ring_feature[RING_F_RSS].limit = 1; + + ixgbe_set_num_queues(adapter); + adapter->num_q_vectors = 1; err = pci_enable_msi(adapter->pdev); - if (!err) { - adapter->flags |= IXGBE_FLAG_MSI_ENABLED; - } else { + if (err) { netif_printk(adapter, hw, KERN_DEBUG, adapter->netdev, "Unable to allocate MSI interrupt, " "falling back to legacy. Error: %d\n", err); - /* reset err */ - err = 0; + return; } - -out: - return err; + adapter->flags |= IXGBE_FLAG_MSI_ENABLED; } /** @@ -874,15 +1114,10 @@ int ixgbe_init_interrupt_scheme(struct ixgbe_adapter *adapter) int err; /* Number of supported queues */ - err = ixgbe_set_num_queues(adapter); - if (err) - return err; + ixgbe_set_num_queues(adapter); - err = ixgbe_set_interrupt_capability(adapter); - if (err) { - e_dev_err("Unable to setup interrupt capabilities\n"); - goto err_set_interrupt; - } + /* Set interrupt mode */ + ixgbe_set_interrupt_capability(adapter); err = ixgbe_alloc_q_vectors(adapter); if (err) { @@ -902,7 +1137,6 @@ int ixgbe_init_interrupt_scheme(struct ixgbe_adapter *adapter) err_alloc_q_vectors: ixgbe_reset_interrupt_capability(adapter); -err_set_interrupt: return err; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 18ca3bcadf0c..4326f74f7137 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -396,11 +396,10 @@ static void ixgbe_dump(struct ixgbe_adapter *adapter) pr_cont("\n"); if (netif_msg_pktdata(adapter) && - dma_unmap_len(tx_buffer, len) != 0) + tx_buffer->skb) print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS, 16, 1, - phys_to_virt(dma_unmap_addr(tx_buffer, - dma)), + tx_buffer->skb->data, dma_unmap_len(tx_buffer, len), true); } @@ -474,10 +473,12 @@ rx_ring_summary: (u64)rx_buffer_info->dma, rx_buffer_info->skb); - if (netif_msg_pktdata(adapter)) { + if (netif_msg_pktdata(adapter) && + rx_buffer_info->dma) { print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS, 16, 1, - phys_to_virt(rx_buffer_info->dma), + page_address(rx_buffer_info->page) + + rx_buffer_info->page_offset, ixgbe_rx_bufsz(rx_ring), true); } } @@ -516,7 +517,7 @@ static void ixgbe_get_hw_control(struct ixgbe_adapter *adapter) ctrl_ext | IXGBE_CTRL_EXT_DRV_LOAD); } -/* +/** * ixgbe_set_ivar - set the IVAR registers, mapping interrupt causes to vectors * @adapter: pointer to adapter struct * @direction: 0 for Rx, 1 for Tx, -1 for other causes @@ -790,12 +791,10 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, total_packets += tx_buffer->gso_segs; #ifdef CONFIG_IXGBE_PTP - if (unlikely(tx_buffer->tx_flags & - IXGBE_TX_FLAGS_TSTAMP)) - ixgbe_ptp_tx_hwtstamp(q_vector, - tx_buffer->skb); - + if (unlikely(tx_buffer->tx_flags & IXGBE_TX_FLAGS_TSTAMP)) + ixgbe_ptp_tx_hwtstamp(q_vector, tx_buffer->skb); #endif + /* free the skb */ dev_kfree_skb_any(tx_buffer->skb); @@ -995,7 +994,6 @@ out_no_update: static void ixgbe_setup_dca(struct ixgbe_adapter *adapter) { - int num_q_vectors; int i; if (!(adapter->flags & IXGBE_FLAG_DCA_ENABLED)) @@ -1004,12 +1002,7 @@ static void ixgbe_setup_dca(struct ixgbe_adapter *adapter) /* always use CB2 mode, difference is masked in the CB driver */ IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_CTRL, 2); - if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) - num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - else - num_q_vectors = 1; - - for (i = 0; i < num_q_vectors; i++) { + for (i = 0; i < adapter->num_q_vectors; i++) { adapter->q_vector[i]->cpu = -1; ixgbe_update_dca(adapter->q_vector[i]); } @@ -1148,8 +1141,8 @@ static bool ixgbe_alloc_mapped_page(struct ixgbe_ring *rx_ring, /* alloc new page for storage */ if (likely(!page)) { - page = alloc_pages(GFP_ATOMIC | __GFP_COLD | __GFP_COMP, - ixgbe_rx_pg_order(rx_ring)); + page = __skb_alloc_pages(GFP_ATOMIC | __GFP_COLD | __GFP_COMP, + bi->skb, ixgbe_rx_pg_order(rx_ring)); if (unlikely(!page)) { rx_ring->rx_stats.alloc_rx_page_failed++; return false; @@ -1399,8 +1392,7 @@ static void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring, ixgbe_rx_checksum(rx_ring, rx_desc, skb); #ifdef CONFIG_IXGBE_PTP - if (ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_STAT_TS)) - ixgbe_ptp_rx_hwtstamp(rx_ring->q_vector, skb); + ixgbe_ptp_rx_hwtstamp(rx_ring->q_vector, rx_desc, skb); #endif if ((dev->features & NETIF_F_HW_VLAN_RX) && @@ -1526,8 +1518,8 @@ static bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring, * 60 bytes if the skb->len is less than 60 for skb_pad. */ pull_len = skb_frag_size(frag); - if (pull_len > 256) - pull_len = ixgbe_get_headlen(va, pull_len); + if (pull_len > IXGBE_RX_HDR_SIZE) + pull_len = ixgbe_get_headlen(va, IXGBE_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))); @@ -1834,11 +1826,9 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, static void ixgbe_configure_msix(struct ixgbe_adapter *adapter) { struct ixgbe_q_vector *q_vector; - int q_vectors, v_idx; + int v_idx; u32 mask; - q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - /* Populate MSIX to EITR Select */ if (adapter->num_vfs > 32) { u32 eitrsel = (1 << (adapter->num_vfs - 32)) - 1; @@ -1849,7 +1839,7 @@ static void ixgbe_configure_msix(struct ixgbe_adapter *adapter) * Populate the IVAR table and set the ITR values to the * corresponding register. */ - for (v_idx = 0; v_idx < q_vectors; v_idx++) { + for (v_idx = 0; v_idx < adapter->num_q_vectors; v_idx++) { struct ixgbe_ring *ring; q_vector = adapter->q_vector[v_idx]; @@ -2413,11 +2403,10 @@ int ixgbe_poll(struct napi_struct *napi, int budget) static int ixgbe_request_msix_irqs(struct ixgbe_adapter *adapter) { struct net_device *netdev = adapter->netdev; - int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; int vector, err; int ri = 0, ti = 0; - for (vector = 0; vector < q_vectors; vector++) { + 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]; @@ -2572,30 +2561,28 @@ static int ixgbe_request_irq(struct ixgbe_adapter *adapter) static void ixgbe_free_irq(struct ixgbe_adapter *adapter) { - if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) { - int i, q_vectors; + int vector; - q_vectors = adapter->num_msix_vectors; - i = q_vectors - 1; - free_irq(adapter->msix_entries[i].vector, adapter); - i--; + if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) { + free_irq(adapter->pdev->irq, adapter); + return; + } - for (; i >= 0; i--) { - /* free only the irqs that were actually requested */ - if (!adapter->q_vector[i]->rx.ring && - !adapter->q_vector[i]->tx.ring) - continue; + 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]; - /* clear the affinity_mask in the IRQ descriptor */ - irq_set_affinity_hint(adapter->msix_entries[i].vector, - NULL); + /* free only the irqs that were actually requested */ + if (!q_vector->rx.ring && !q_vector->tx.ring) + continue; - free_irq(adapter->msix_entries[i].vector, - adapter->q_vector[i]); - } - } else { - free_irq(adapter->pdev->irq, adapter); + /* clear the affinity_mask in the IRQ descriptor */ + irq_set_affinity_hint(entry->vector, NULL); + + free_irq(entry->vector, q_vector); } + + free_irq(adapter->msix_entries[vector++].vector, adapter); } /** @@ -2619,9 +2606,12 @@ static inline void ixgbe_irq_disable(struct ixgbe_adapter *adapter) } IXGBE_WRITE_FLUSH(&adapter->hw); if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) { - int i; - for (i = 0; i < adapter->num_msix_vectors; i++) - synchronize_irq(adapter->msix_entries[i].vector); + int vector; + + for (vector = 0; vector < adapter->num_q_vectors; vector++) + synchronize_irq(adapter->msix_entries[vector].vector); + + synchronize_irq(adapter->msix_entries[vector++].vector); } else { synchronize_irq(adapter->pdev->irq); } @@ -2699,8 +2689,7 @@ void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter, 32; /* PTHRESH = 32 */ /* reinitialize flowdirector state */ - if ((adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) && - adapter->atr_sample_rate) { + if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) { ring->atr_sample_rate = adapter->atr_sample_rate; ring->atr_count = 0; set_bit(__IXGBE_TX_FDIR_INIT_DONE, &ring->state); @@ -2730,8 +2719,7 @@ void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter, static void ixgbe_setup_mtqc(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; - u32 rttdcs; - u32 reg; + u32 rttdcs, mtqc; u8 tcs = netdev_get_num_tc(adapter->netdev); if (hw->mac.type == ixgbe_mac_82598EB) @@ -2743,28 +2731,32 @@ static void ixgbe_setup_mtqc(struct ixgbe_adapter *adapter) IXGBE_WRITE_REG(hw, IXGBE_RTTDCS, rttdcs); /* set transmit pool layout */ - switch (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) { - case (IXGBE_FLAG_SRIOV_ENABLED): - IXGBE_WRITE_REG(hw, IXGBE_MTQC, - (IXGBE_MTQC_VT_ENA | IXGBE_MTQC_64VF)); - break; - default: - if (!tcs) - reg = IXGBE_MTQC_64Q_1PB; - else if (tcs <= 4) - reg = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_4TC_4TQ; + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) { + mtqc = IXGBE_MTQC_VT_ENA; + if (tcs > 4) + mtqc |= IXGBE_MTQC_RT_ENA | IXGBE_MTQC_8TC_8TQ; + else if (tcs > 1) + mtqc |= IXGBE_MTQC_RT_ENA | IXGBE_MTQC_4TC_4TQ; + else if (adapter->ring_feature[RING_F_RSS].indices == 4) + mtqc |= IXGBE_MTQC_32VF; else - reg = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_8TC_8TQ; + mtqc |= IXGBE_MTQC_64VF; + } else { + if (tcs > 4) + mtqc = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_8TC_8TQ; + else if (tcs > 1) + mtqc = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_4TC_4TQ; + else + mtqc = IXGBE_MTQC_64Q_1PB; + } - IXGBE_WRITE_REG(hw, IXGBE_MTQC, reg); + IXGBE_WRITE_REG(hw, IXGBE_MTQC, mtqc); - /* Enable Security TX Buffer IFG for multiple pb */ - if (tcs) { - reg = IXGBE_READ_REG(hw, IXGBE_SECTXMINIFG); - reg |= IXGBE_SECTX_DCB; - IXGBE_WRITE_REG(hw, IXGBE_SECTXMINIFG, reg); - } - break; + /* Enable Security TX Buffer IFG for multiple pb */ + if (tcs) { + u32 sectx = IXGBE_READ_REG(hw, IXGBE_SECTXMINIFG); + sectx |= IXGBE_SECTX_DCB; + IXGBE_WRITE_REG(hw, IXGBE_SECTXMINIFG, sectx); } /* re-enable the arbiter */ @@ -2858,40 +2850,34 @@ static void ixgbe_set_rx_drop_en(struct ixgbe_adapter *adapter) static void ixgbe_configure_srrctl(struct ixgbe_adapter *adapter, struct ixgbe_ring *rx_ring) { + struct ixgbe_hw *hw = &adapter->hw; u32 srrctl; u8 reg_idx = rx_ring->reg_idx; - switch (adapter->hw.mac.type) { - case ixgbe_mac_82598EB: { - struct ixgbe_ring_feature *feature = adapter->ring_feature; - const int mask = feature[RING_F_RSS].mask; - reg_idx = reg_idx & mask; - } - break; - case ixgbe_mac_82599EB: - case ixgbe_mac_X540: - default: - break; - } - - srrctl = IXGBE_READ_REG(&adapter->hw, IXGBE_SRRCTL(reg_idx)); + if (hw->mac.type == ixgbe_mac_82598EB) { + u16 mask = adapter->ring_feature[RING_F_RSS].mask; - srrctl &= ~IXGBE_SRRCTL_BSIZEHDR_MASK; - srrctl &= ~IXGBE_SRRCTL_BSIZEPKT_MASK; - if (adapter->num_vfs) - srrctl |= IXGBE_SRRCTL_DROP_EN; + /* + * if VMDq is not active we must program one srrctl register + * per RSS queue since we have enabled RDRXCTL.MVMEN + */ + reg_idx &= mask; + } - srrctl |= (IXGBE_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT) & - IXGBE_SRRCTL_BSIZEHDR_MASK; + /* configure header buffer length, needed for RSC */ + srrctl = IXGBE_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT; + /* configure the packet buffer length */ #if PAGE_SIZE > IXGBE_MAX_RXBUFFER srrctl |= IXGBE_MAX_RXBUFFER >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; #else srrctl |= ixgbe_rx_bufsz(rx_ring) >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; #endif + + /* configure descriptor type */ srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF; - IXGBE_WRITE_REG(&adapter->hw, IXGBE_SRRCTL(reg_idx), srrctl); + IXGBE_WRITE_REG(hw, IXGBE_SRRCTL(reg_idx), srrctl); } static void ixgbe_setup_mrqc(struct ixgbe_adapter *adapter) @@ -2903,11 +2889,15 @@ static void ixgbe_setup_mrqc(struct ixgbe_adapter *adapter) u32 mrqc = 0, reta = 0; u32 rxcsum; int i, j; - u8 tcs = netdev_get_num_tc(adapter->netdev); - int maxq = adapter->ring_feature[RING_F_RSS].indices; + u16 rss_i = adapter->ring_feature[RING_F_RSS].indices; - if (tcs) - maxq = min(maxq, adapter->num_tx_queues / tcs); + /* + * Program table for at least 2 queues w/ SR-IOV so that VFs can + * make full use of any rings they may have. We will use the + * PSRTYPE register to control how many rings we use within the PF. + */ + if ((adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) && (rss_i < 2)) + rss_i = 2; /* Fill out hash function seeds */ for (i = 0; i < 10; i++) @@ -2915,7 +2905,7 @@ static void ixgbe_setup_mrqc(struct ixgbe_adapter *adapter) /* Fill out redirection table */ for (i = 0, j = 0; i < 128; i++, j++) { - if (j == maxq) + if (j == rss_i) j = 0; /* reta = 4-byte sliding window of * 0x00..(indices-1)(indices-1)00..etc. */ @@ -2929,35 +2919,36 @@ static void ixgbe_setup_mrqc(struct ixgbe_adapter *adapter) rxcsum |= IXGBE_RXCSUM_PCSD; IXGBE_WRITE_REG(hw, IXGBE_RXCSUM, rxcsum); - if (adapter->hw.mac.type == ixgbe_mac_82598EB && - (adapter->flags & IXGBE_FLAG_RSS_ENABLED)) { - mrqc = IXGBE_MRQC_RSSEN; + if (adapter->hw.mac.type == ixgbe_mac_82598EB) { + if (adapter->ring_feature[RING_F_RSS].mask) + mrqc = IXGBE_MRQC_RSSEN; } else { - int mask = adapter->flags & (IXGBE_FLAG_RSS_ENABLED - | IXGBE_FLAG_SRIOV_ENABLED); - - switch (mask) { - case (IXGBE_FLAG_RSS_ENABLED): - if (!tcs) - mrqc = IXGBE_MRQC_RSSEN; - else if (tcs <= 4) - mrqc = IXGBE_MRQC_RTRSS4TCEN; + u8 tcs = netdev_get_num_tc(adapter->netdev); + + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) { + if (tcs > 4) + mrqc = IXGBE_MRQC_VMDQRT8TCEN; /* 8 TCs */ + else if (tcs > 1) + mrqc = IXGBE_MRQC_VMDQRT4TCEN; /* 4 TCs */ + else if (adapter->ring_feature[RING_F_RSS].indices == 4) + mrqc = IXGBE_MRQC_VMDQRSS32EN; else + mrqc = IXGBE_MRQC_VMDQRSS64EN; + } else { + if (tcs > 4) mrqc = IXGBE_MRQC_RTRSS8TCEN; - break; - case (IXGBE_FLAG_SRIOV_ENABLED): - mrqc = IXGBE_MRQC_VMDQEN; - break; - default: - break; + else if (tcs > 1) + mrqc = IXGBE_MRQC_RTRSS4TCEN; + else + mrqc = IXGBE_MRQC_RSSEN; } } /* Perform hash on these packet types */ - mrqc |= IXGBE_MRQC_RSS_FIELD_IPV4 - | IXGBE_MRQC_RSS_FIELD_IPV4_TCP - | IXGBE_MRQC_RSS_FIELD_IPV6 - | IXGBE_MRQC_RSS_FIELD_IPV6_TCP; + mrqc |= IXGBE_MRQC_RSS_FIELD_IPV4 | + IXGBE_MRQC_RSS_FIELD_IPV4_TCP | + IXGBE_MRQC_RSS_FIELD_IPV6 | + IXGBE_MRQC_RSS_FIELD_IPV6_TCP; if (adapter->flags2 & IXGBE_FLAG2_RSS_FIELD_IPV4_UDP) mrqc |= IXGBE_MRQC_RSS_FIELD_IPV4_UDP; @@ -3108,6 +3099,7 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, static void ixgbe_setup_psrtype(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; + int rss_i = adapter->ring_feature[RING_F_RSS].indices; int p; /* PSRTYPE must be initialized in non 82598 adapters */ @@ -3120,58 +3112,69 @@ static void ixgbe_setup_psrtype(struct ixgbe_adapter *adapter) if (hw->mac.type == ixgbe_mac_82598EB) return; - if (adapter->flags & IXGBE_FLAG_RSS_ENABLED) - psrtype |= (adapter->num_rx_queues_per_pool << 29); + if (rss_i > 3) + psrtype |= 2 << 29; + else if (rss_i > 1) + psrtype |= 1 << 29; for (p = 0; p < adapter->num_rx_pools; p++) - IXGBE_WRITE_REG(hw, IXGBE_PSRTYPE(adapter->num_vfs + p), + IXGBE_WRITE_REG(hw, IXGBE_PSRTYPE(VMDQ_P(p)), psrtype); } static void ixgbe_configure_virtualization(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; - u32 gcr_ext; - u32 vt_reg_bits; u32 reg_offset, vf_shift; - u32 vmdctl; + u32 gcr_ext, vmdctl; int i; if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) return; vmdctl = IXGBE_READ_REG(hw, IXGBE_VT_CTL); - vt_reg_bits = IXGBE_VMD_CTL_VMDQ_EN | IXGBE_VT_CTL_REPLEN; - vt_reg_bits |= (adapter->num_vfs << IXGBE_VT_CTL_POOL_SHIFT); - IXGBE_WRITE_REG(hw, IXGBE_VT_CTL, vmdctl | vt_reg_bits); + vmdctl |= IXGBE_VMD_CTL_VMDQ_EN; + vmdctl &= ~IXGBE_VT_CTL_POOL_MASK; + vmdctl |= VMDQ_P(0) << IXGBE_VT_CTL_POOL_SHIFT; + vmdctl |= IXGBE_VT_CTL_REPLEN; + IXGBE_WRITE_REG(hw, IXGBE_VT_CTL, vmdctl); - vf_shift = adapter->num_vfs % 32; - reg_offset = (adapter->num_vfs >= 32) ? 1 : 0; + vf_shift = VMDQ_P(0) % 32; + reg_offset = (VMDQ_P(0) >= 32) ? 1 : 0; /* Enable only the PF's pool for Tx/Rx */ - IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset), (1 << vf_shift)); - IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset ^ 1), 0); - IXGBE_WRITE_REG(hw, IXGBE_VFTE(reg_offset), (1 << vf_shift)); - IXGBE_WRITE_REG(hw, IXGBE_VFTE(reg_offset ^ 1), 0); + IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset), (~0) << vf_shift); + IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset ^ 1), reg_offset - 1); + IXGBE_WRITE_REG(hw, IXGBE_VFTE(reg_offset), (~0) << vf_shift); + IXGBE_WRITE_REG(hw, IXGBE_VFTE(reg_offset ^ 1), reg_offset - 1); IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, IXGBE_PFDTXGSWC_VT_LBEN); /* Map PF MAC address in RAR Entry 0 to first pool following VFs */ - hw->mac.ops.set_vmdq(hw, 0, adapter->num_vfs); + hw->mac.ops.set_vmdq(hw, 0, VMDQ_P(0)); /* * Set up VF register offsets for selected VT Mode, * i.e. 32 or 64 VFs for SR-IOV */ - gcr_ext = IXGBE_READ_REG(hw, IXGBE_GCR_EXT); - gcr_ext |= IXGBE_GCR_EXT_MSIX_EN; - gcr_ext |= IXGBE_GCR_EXT_VT_MODE_64; + switch (adapter->ring_feature[RING_F_VMDQ].mask) { + case IXGBE_82599_VMDQ_8Q_MASK: + gcr_ext = IXGBE_GCR_EXT_VT_MODE_16; + break; + case IXGBE_82599_VMDQ_4Q_MASK: + gcr_ext = IXGBE_GCR_EXT_VT_MODE_32; + break; + default: + gcr_ext = IXGBE_GCR_EXT_VT_MODE_64; + break; + } + IXGBE_WRITE_REG(hw, IXGBE_GCR_EXT, gcr_ext); /* enable Tx loopback for VF/PF communication */ IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, IXGBE_PFDTXGSWC_VT_LBEN); + /* Enable MAC Anti-Spoofing */ - hw->mac.ops.set_mac_anti_spoofing(hw, - (adapter->num_vfs != 0), + hw->mac.ops.set_mac_anti_spoofing(hw, (adapter->num_vfs != 0), adapter->num_vfs); /* For VFs that have spoof checking turned off */ for (i = 0; i < adapter->num_vfs; i++) { @@ -3307,10 +3310,9 @@ static int ixgbe_vlan_rx_add_vid(struct net_device *netdev, u16 vid) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; - int pool_ndx = adapter->num_vfs; /* add VID to filter table */ - hw->mac.ops.set_vfta(&adapter->hw, vid, pool_ndx, true); + hw->mac.ops.set_vfta(&adapter->hw, vid, VMDQ_P(0), true); set_bit(vid, adapter->active_vlans); return 0; @@ -3320,10 +3322,9 @@ static int ixgbe_vlan_rx_kill_vid(struct net_device *netdev, u16 vid) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; - int pool_ndx = adapter->num_vfs; /* remove VID from filter table */ - hw->mac.ops.set_vfta(&adapter->hw, vid, pool_ndx, false); + hw->mac.ops.set_vfta(&adapter->hw, vid, VMDQ_P(0), false); clear_bit(vid, adapter->active_vlans); return 0; @@ -3441,15 +3442,18 @@ static int ixgbe_write_uc_addr_list(struct net_device *netdev) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; - unsigned int vfn = adapter->num_vfs; - unsigned int rar_entries = IXGBE_MAX_PF_MACVLANS; + unsigned int rar_entries = hw->mac.num_rar_entries - 1; int count = 0; + /* In SR-IOV mode significantly less RAR entries are available */ + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) + rar_entries = IXGBE_MAX_PF_MACVLANS - 1; + /* return ENOMEM indicating insufficient memory for addresses */ if (netdev_uc_count(netdev) > rar_entries) return -ENOMEM; - if (!netdev_uc_empty(netdev) && rar_entries) { + if (!netdev_uc_empty(netdev)) { struct netdev_hw_addr *ha; /* return error if we do not support writing to RAR table */ if (!hw->mac.ops.set_rar) @@ -3459,7 +3463,7 @@ static int ixgbe_write_uc_addr_list(struct net_device *netdev) if (!rar_entries) break; hw->mac.ops.set_rar(hw, rar_entries--, ha->addr, - vfn, IXGBE_RAH_AV); + VMDQ_P(0), IXGBE_RAH_AV); count++; } } @@ -3533,12 +3537,14 @@ void ixgbe_set_rx_mode(struct net_device *netdev) vmolr |= IXGBE_VMOLR_ROPE; } - if (adapter->num_vfs) { + if (adapter->num_vfs) ixgbe_restore_vf_multicasts(adapter); - vmolr |= IXGBE_READ_REG(hw, IXGBE_VMOLR(adapter->num_vfs)) & + + if (hw->mac.type != ixgbe_mac_82598EB) { + vmolr |= IXGBE_READ_REG(hw, IXGBE_VMOLR(VMDQ_P(0))) & ~(IXGBE_VMOLR_MPE | IXGBE_VMOLR_ROMPE | IXGBE_VMOLR_ROPE); - IXGBE_WRITE_REG(hw, IXGBE_VMOLR(adapter->num_vfs), vmolr); + IXGBE_WRITE_REG(hw, IXGBE_VMOLR(VMDQ_P(0)), vmolr); } /* This is useful for sniffing bad packets. */ @@ -3564,37 +3570,21 @@ void ixgbe_set_rx_mode(struct net_device *netdev) static void ixgbe_napi_enable_all(struct ixgbe_adapter *adapter) { int q_idx; - struct ixgbe_q_vector *q_vector; - int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - - /* legacy and MSI only use one vector */ - if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) - q_vectors = 1; - for (q_idx = 0; q_idx < q_vectors; q_idx++) { - q_vector = adapter->q_vector[q_idx]; - napi_enable(&q_vector->napi); - } + 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; - struct ixgbe_q_vector *q_vector; - int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - /* legacy and MSI only use one vector */ - if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) - q_vectors = 1; - - for (q_idx = 0; q_idx < q_vectors; q_idx++) { - q_vector = adapter->q_vector[q_idx]; - napi_disable(&q_vector->napi); - } + for (q_idx = 0; q_idx < adapter->num_q_vectors; q_idx++) + napi_disable(&adapter->q_vector[q_idx]->napi); } #ifdef CONFIG_IXGBE_DCB -/* +/** * ixgbe_configure_dcb - Configure DCB hardware * @adapter: ixgbe adapter struct * @@ -3641,19 +3631,16 @@ static void ixgbe_configure_dcb(struct ixgbe_adapter *adapter) /* Enable RSS Hash per TC */ if (hw->mac.type != ixgbe_mac_82598EB) { - int i; - u32 reg = 0; - - for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { - u8 msb = 0; - u8 cnt = adapter->netdev->tc_to_txq[i].count; + u32 msb = 0; + u16 rss_i = adapter->ring_feature[RING_F_RSS].indices - 1; - while (cnt >>= 1) - msb++; - - reg |= msb << IXGBE_RQTC_SHIFT_TC(i); + while (rss_i) { + msb++; + rss_i >>= 1; } - IXGBE_WRITE_REG(hw, IXGBE_RQTC, reg); + + /* write msb to all 8 TCs in one write */ + IXGBE_WRITE_REG(hw, IXGBE_RQTC, msb * 0x11111111); } } #endif @@ -3661,11 +3648,11 @@ static void ixgbe_configure_dcb(struct ixgbe_adapter *adapter) /* Additional bittime to account for IXGBE framing */ #define IXGBE_ETH_FRAMING 20 -/* +/** * ixgbe_hpbthresh - calculate high water mark for flow control * * @adapter: board private structure to calculate for - * @pb - packet buffer to calculate + * @pb: packet buffer to calculate */ static int ixgbe_hpbthresh(struct ixgbe_adapter *adapter, int pb) { @@ -3679,18 +3666,12 @@ static int ixgbe_hpbthresh(struct ixgbe_adapter *adapter, int pb) #ifdef IXGBE_FCOE /* FCoE traffic class uses FCOE jumbo frames */ - if (dev->features & NETIF_F_FCOE_MTU) { - int fcoe_pb = 0; + if ((dev->features & NETIF_F_FCOE_MTU) && + (tc < IXGBE_FCOE_JUMBO_FRAME_SIZE) && + (pb == ixgbe_fcoe_get_tc(adapter))) + tc = IXGBE_FCOE_JUMBO_FRAME_SIZE; -#ifdef CONFIG_IXGBE_DCB - fcoe_pb = netdev_get_prio_tc_map(dev, adapter->fcoe.up); - -#endif - if (fcoe_pb == pb && tc < IXGBE_FCOE_JUMBO_FRAME_SIZE) - tc = IXGBE_FCOE_JUMBO_FRAME_SIZE; - } #endif - /* Calculate delay value for device */ switch (hw->mac.type) { case ixgbe_mac_X540: @@ -3725,11 +3706,11 @@ static int ixgbe_hpbthresh(struct ixgbe_adapter *adapter, int pb) return marker; } -/* +/** * ixgbe_lpbthresh - calculate low water mark for for flow control * * @adapter: board private structure to calculate for - * @pb - packet buffer to calculate + * @pb: packet buffer to calculate */ static int ixgbe_lpbthresh(struct ixgbe_adapter *adapter) { @@ -3830,12 +3811,6 @@ static void ixgbe_configure(struct ixgbe_adapter *adapter) ixgbe_set_rx_mode(adapter->netdev); ixgbe_restore_vlan(adapter); -#ifdef IXGBE_FCOE - if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) - ixgbe_configure_fcoe(adapter); - -#endif /* IXGBE_FCOE */ - switch (hw->mac.type) { case ixgbe_mac_82599EB: case ixgbe_mac_X540: @@ -3865,6 +3840,11 @@ static void ixgbe_configure(struct ixgbe_adapter *adapter) ixgbe_configure_virtualization(adapter); +#ifdef IXGBE_FCOE + /* configure FCoE L2 filters, redirection table, and Rx control */ + ixgbe_configure_fcoe(adapter); + +#endif /* IXGBE_FCOE */ ixgbe_configure_tx(adapter); ixgbe_configure_rx(adapter); } @@ -3973,7 +3953,18 @@ static void ixgbe_setup_gpie(struct ixgbe_adapter *adapter) if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) { gpie &= ~IXGBE_GPIE_VTMODE_MASK; - gpie |= IXGBE_GPIE_VTMODE_64; + + switch (adapter->ring_feature[RING_F_VMDQ].mask) { + case IXGBE_82599_VMDQ_8Q_MASK: + gpie |= IXGBE_GPIE_VTMODE_16; + break; + case IXGBE_82599_VMDQ_4Q_MASK: + gpie |= IXGBE_GPIE_VTMODE_32; + break; + default: + gpie |= IXGBE_GPIE_VTMODE_64; + break; + } } /* Enable Thermal over heat sensor interrupt */ @@ -4131,8 +4122,11 @@ void ixgbe_reset(struct ixgbe_adapter *adapter) clear_bit(__IXGBE_IN_SFP_INIT, &adapter->state); /* reprogram the RAR[0] in case user changed it. */ - hw->mac.ops.set_rar(hw, 0, hw->mac.addr, adapter->num_vfs, - IXGBE_RAH_AV); + hw->mac.ops.set_rar(hw, 0, hw->mac.addr, VMDQ_P(0), IXGBE_RAH_AV); + + /* update SAN MAC vmdq pool selection */ + if (hw->mac.san_mac_rar_index) + hw->mac.ops.set_vmdq_san_mac(hw, VMDQ_P(0)); } /** @@ -4413,32 +4407,29 @@ static int __devinit ixgbe_sw_init(struct ixgbe_adapter *adapter) /* Set capability flags */ rss = min_t(int, IXGBE_MAX_RSS_INDICES, num_online_cpus()); - adapter->ring_feature[RING_F_RSS].indices = rss; - adapter->flags |= IXGBE_FLAG_RSS_ENABLED; + adapter->ring_feature[RING_F_RSS].limit = rss; switch (hw->mac.type) { case ixgbe_mac_82598EB: if (hw->device_id == IXGBE_DEV_ID_82598AT) adapter->flags |= IXGBE_FLAG_FAN_FAIL_CAPABLE; - adapter->max_msix_q_vectors = MAX_MSIX_Q_VECTORS_82598; + adapter->max_q_vectors = MAX_Q_VECTORS_82598; break; case ixgbe_mac_X540: adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE; case ixgbe_mac_82599EB: - adapter->max_msix_q_vectors = MAX_MSIX_Q_VECTORS_82599; + adapter->max_q_vectors = MAX_Q_VECTORS_82599; adapter->flags2 |= IXGBE_FLAG2_RSC_CAPABLE; adapter->flags2 |= IXGBE_FLAG2_RSC_ENABLED; if (hw->device_id == IXGBE_DEV_ID_82599_T3_LOM) adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE; /* Flow Director hash filters enabled */ - adapter->flags |= IXGBE_FLAG_FDIR_HASH_CAPABLE; adapter->atr_sample_rate = 20; - adapter->ring_feature[RING_F_FDIR].indices = + adapter->ring_feature[RING_F_FDIR].limit = IXGBE_MAX_FDIR_INDICES; adapter->fdir_pballoc = IXGBE_FDIR_PBALLOC_64K; #ifdef IXGBE_FCOE adapter->flags |= IXGBE_FLAG_FCOE_CAPABLE; adapter->flags &= ~IXGBE_FLAG_FCOE_ENABLED; - adapter->ring_feature[RING_F_FCOE].indices = 0; #ifdef CONFIG_IXGBE_DCB /* Default traffic class to use for FCoE */ adapter->fcoe.up = IXGBE_FCOE_DEFTC; @@ -4449,6 +4440,11 @@ static int __devinit ixgbe_sw_init(struct ixgbe_adapter *adapter) break; } +#ifdef IXGBE_FCOE + /* FCoE support exists, always init the FCoE lock */ + spin_lock_init(&adapter->fcoe.lock); + +#endif /* n-tuple support exists, always init our spinlock */ spin_lock_init(&adapter->fdir_perfect_lock); @@ -4497,6 +4493,12 @@ static int __devinit ixgbe_sw_init(struct ixgbe_adapter *adapter) hw->fc.send_xon = true; hw->fc.disable_fc_autoneg = false; +#ifdef CONFIG_PCI_IOV + /* assign number of SR-IOV VFs */ + if (hw->mac.type != ixgbe_mac_82598EB) + adapter->num_vfs = (max_vfs > 63) ? 0 : max_vfs; + +#endif /* enable itr by default in dynamic mode */ adapter->rx_itr_setting = 1; adapter->tx_itr_setting = 1; @@ -4588,10 +4590,16 @@ static int ixgbe_setup_all_tx_resources(struct ixgbe_adapter *adapter) err = ixgbe_setup_tx_resources(adapter->tx_ring[i]); if (!err) continue; + e_err(probe, "Allocation for Tx Queue %u failed\n", i); - break; + goto err_setup_tx; } + return 0; +err_setup_tx: + /* rewind the index freeing the rings as we go */ + while (i--) + ixgbe_free_tx_resources(adapter->tx_ring[i]); return err; } @@ -4666,10 +4674,20 @@ static int ixgbe_setup_all_rx_resources(struct ixgbe_adapter *adapter) err = ixgbe_setup_rx_resources(adapter->rx_ring[i]); if (!err) continue; + e_err(probe, "Allocation for Rx Queue %u failed\n", i); - break; + goto err_setup_rx; } +#ifdef IXGBE_FCOE + err = ixgbe_setup_fcoe_ddp_resources(adapter); + if (!err) +#endif + return 0; +err_setup_rx: + /* rewind the index freeing the rings as we go */ + while (i--) + ixgbe_free_rx_resources(adapter->rx_ring[i]); return err; } @@ -4744,6 +4762,10 @@ static void ixgbe_free_all_rx_resources(struct ixgbe_adapter *adapter) { int i; +#ifdef IXGBE_FCOE + ixgbe_free_fcoe_ddp_resources(adapter); + +#endif for (i = 0; i < adapter->num_rx_queues; i++) if (adapter->rx_ring[i]->desc) ixgbe_free_rx_resources(adapter->rx_ring[i]); @@ -4825,15 +4847,31 @@ static int ixgbe_open(struct net_device *netdev) if (err) goto err_req_irq; + /* Notify the stack of the actual queue counts. */ + err = netif_set_real_num_tx_queues(netdev, + adapter->num_rx_pools > 1 ? 1 : + adapter->num_tx_queues); + if (err) + goto err_set_queues; + + + err = netif_set_real_num_rx_queues(netdev, + adapter->num_rx_pools > 1 ? 1 : + adapter->num_rx_queues); + if (err) + goto err_set_queues; + ixgbe_up_complete(adapter); return 0; +err_set_queues: + ixgbe_free_irq(adapter); err_req_irq: -err_setup_rx: ixgbe_free_all_rx_resources(adapter); -err_setup_tx: +err_setup_rx: ixgbe_free_all_tx_resources(adapter); +err_setup_tx: ixgbe_reset(adapter); return err; @@ -4891,23 +4929,19 @@ static int ixgbe_resume(struct pci_dev *pdev) pci_wake_from_d3(pdev, false); - rtnl_lock(); - err = ixgbe_init_interrupt_scheme(adapter); - rtnl_unlock(); - if (err) { - e_dev_err("Cannot initialize interrupts for device\n"); - return err; - } - ixgbe_reset(adapter); IXGBE_WRITE_REG(&adapter->hw, IXGBE_WUS, ~0); - if (netif_running(netdev)) { + rtnl_lock(); + err = ixgbe_init_interrupt_scheme(adapter); + if (!err && netif_running(netdev)) err = ixgbe_open(netdev); - if (err) - return err; - } + + rtnl_unlock(); + + if (err) + return err; netif_device_attach(netdev); @@ -5043,11 +5077,6 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) u64 non_eop_descs = 0, restart_queue = 0, tx_busy = 0; u64 alloc_rx_page_failed = 0, alloc_rx_buff_failed = 0; u64 bytes = 0, packets = 0, hw_csum_rx_error = 0; -#ifdef IXGBE_FCOE - struct ixgbe_fcoe *fcoe = &adapter->fcoe; - unsigned int cpu; - u64 fcoe_noddp_counts_sum = 0, fcoe_noddp_ext_buff_counts_sum = 0; -#endif /* IXGBE_FCOE */ if (test_bit(__IXGBE_DOWN, &adapter->state) || test_bit(__IXGBE_RESETTING, &adapter->state)) @@ -5178,17 +5207,19 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) hwstats->fcoedwrc += IXGBE_READ_REG(hw, IXGBE_FCOEDWRC); hwstats->fcoedwtc += IXGBE_READ_REG(hw, IXGBE_FCOEDWTC); /* Add up per cpu counters for total ddp aloc fail */ - if (fcoe->pcpu_noddp && fcoe->pcpu_noddp_ext_buff) { + if (adapter->fcoe.ddp_pool) { + struct ixgbe_fcoe *fcoe = &adapter->fcoe; + struct ixgbe_fcoe_ddp_pool *ddp_pool; + unsigned int cpu; + u64 noddp = 0, noddp_ext_buff = 0; for_each_possible_cpu(cpu) { - fcoe_noddp_counts_sum += - *per_cpu_ptr(fcoe->pcpu_noddp, cpu); - fcoe_noddp_ext_buff_counts_sum += - *per_cpu_ptr(fcoe-> - pcpu_noddp_ext_buff, cpu); + ddp_pool = per_cpu_ptr(fcoe->ddp_pool, cpu); + noddp += ddp_pool->noddp; + noddp_ext_buff += ddp_pool->noddp_ext_buff; } + hwstats->fcoe_noddp = noddp; + hwstats->fcoe_noddp_ext_buff = noddp_ext_buff; } - hwstats->fcoe_noddp = fcoe_noddp_counts_sum; - hwstats->fcoe_noddp_ext_buff = fcoe_noddp_ext_buff_counts_sum; #endif /* IXGBE_FCOE */ break; default: @@ -5246,7 +5277,7 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) /** * ixgbe_fdir_reinit_subtask - worker thread to reinit FDIR filter table - * @adapter - pointer to the device adapter structure + * @adapter: pointer to the device adapter structure **/ static void ixgbe_fdir_reinit_subtask(struct ixgbe_adapter *adapter) { @@ -5282,7 +5313,7 @@ static void ixgbe_fdir_reinit_subtask(struct ixgbe_adapter *adapter) /** * ixgbe_check_hang_subtask - check for hung queues and dropped interrupts - * @adapter - pointer to the device adapter structure + * @adapter: pointer to the device adapter structure * * This function serves two purposes. First it strobes the interrupt lines * in order to make certain interrupts are occurring. Secondly it sets the @@ -5316,7 +5347,7 @@ static void ixgbe_check_hang_subtask(struct ixgbe_adapter *adapter) (IXGBE_EICS_TCP_TIMER | IXGBE_EICS_OTHER)); } else { /* get one bit for every active tx/rx interrupt vector */ - for (i = 0; i < adapter->num_msix_vectors - NON_Q_VECTORS; i++) { + for (i = 0; i < adapter->num_q_vectors; i++) { struct ixgbe_q_vector *qv = adapter->q_vector[i]; if (qv->rx.ring || qv->tx.ring) eics |= ((u64)1 << i); @@ -5330,8 +5361,8 @@ static void ixgbe_check_hang_subtask(struct ixgbe_adapter *adapter) /** * ixgbe_watchdog_update_link - update the link status - * @adapter - pointer to the device adapter structure - * @link_speed - pointer to a u32 to store the link_speed + * @adapter: pointer to the device adapter structure + * @link_speed: pointer to a u32 to store the link_speed **/ static void ixgbe_watchdog_update_link(struct ixgbe_adapter *adapter) { @@ -5374,7 +5405,7 @@ static void ixgbe_watchdog_update_link(struct ixgbe_adapter *adapter) /** * ixgbe_watchdog_link_is_up - update netif_carrier status and * print link up message - * @adapter - pointer to the device adapter structure + * @adapter: pointer to the device adapter structure **/ static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *adapter) { @@ -5429,12 +5460,15 @@ static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *adapter) netif_carrier_on(netdev); ixgbe_check_vf_rate_limit(adapter); + + /* ping all the active vfs to let them know link has changed */ + ixgbe_ping_all_vfs(adapter); } /** * ixgbe_watchdog_link_is_down - update netif_carrier status and * print link down message - * @adapter - pointer to the adapter structure + * @adapter: pointer to the adapter structure **/ static void ixgbe_watchdog_link_is_down(struct ixgbe_adapter *adapter) { @@ -5458,11 +5492,14 @@ static void ixgbe_watchdog_link_is_down(struct ixgbe_adapter *adapter) e_info(drv, "NIC Link is Down\n"); netif_carrier_off(netdev); + + /* ping all the active vfs to let them know link has changed */ + ixgbe_ping_all_vfs(adapter); } /** * ixgbe_watchdog_flush_tx - flush queues on link down - * @adapter - pointer to the device adapter structure + * @adapter: pointer to the device adapter structure **/ static void ixgbe_watchdog_flush_tx(struct ixgbe_adapter *adapter) { @@ -5511,7 +5548,7 @@ static void ixgbe_spoof_check(struct ixgbe_adapter *adapter) /** * ixgbe_watchdog_subtask - check and bring link up - * @adapter - pointer to the device adapter structure + * @adapter: pointer to the device adapter structure **/ static void ixgbe_watchdog_subtask(struct ixgbe_adapter *adapter) { @@ -5535,7 +5572,7 @@ static void ixgbe_watchdog_subtask(struct ixgbe_adapter *adapter) /** * ixgbe_sfp_detection_subtask - poll for SFP+ cable - * @adapter - the ixgbe adapter structure + * @adapter: the ixgbe adapter structure **/ static void ixgbe_sfp_detection_subtask(struct ixgbe_adapter *adapter) { @@ -5602,7 +5639,7 @@ sfp_out: /** * ixgbe_sfp_link_config_subtask - set up link SFP after module install - * @adapter - the ixgbe adapter structure + * @adapter: the ixgbe adapter structure **/ static void ixgbe_sfp_link_config_subtask(struct ixgbe_adapter *adapter) { @@ -6233,8 +6270,14 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb) if (((protocol == htons(ETH_P_FCOE)) || (protocol == htons(ETH_P_FIP))) && (adapter->flags & IXGBE_FLAG_FCOE_ENABLED)) { - txq &= (adapter->ring_feature[RING_F_FCOE].indices - 1); - txq += adapter->ring_feature[RING_F_FCOE].mask; + struct ixgbe_ring_feature *f; + + f = &adapter->ring_feature[RING_F_FCOE]; + + while (txq >= f->indices) + txq -= f->indices; + txq += adapter->ring_feature[RING_F_FCOE].offset; + return txq; } #endif @@ -6348,7 +6391,7 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, #ifdef IXGBE_FCOE /* setup tx offload for FCoE */ if ((protocol == __constant_htons(ETH_P_FCOE)) && - (adapter->flags & IXGBE_FLAG_FCOE_ENABLED)) { + (tx_ring->netdev->features & (NETIF_F_FSO | NETIF_F_FCOE_CRC))) { tso = ixgbe_fso(tx_ring, first, &hdr_len); if (tso < 0) goto out_drop; @@ -6389,17 +6432,12 @@ static netdev_tx_t ixgbe_xmit_frame(struct sk_buff *skb, struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_ring *tx_ring; - if (skb->len <= 0) { - dev_kfree_skb_any(skb); - return NETDEV_TX_OK; - } - /* * The minimum packet size for olinfo paylen is 17 so pad the skb * in order to meet this minimum size requirement. */ - if (skb->len < 17) { - if (skb_padto(skb, 17)) + if (unlikely(skb->len < 17)) { + if (skb_pad(skb, 17 - skb->len)) return NETDEV_TX_OK; skb->len = 17; } @@ -6427,8 +6465,7 @@ static int ixgbe_set_mac(struct net_device *netdev, void *p) memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len); memcpy(hw->mac.addr, addr->sa_data, netdev->addr_len); - hw->mac.ops.set_rar(hw, 0, hw->mac.addr, adapter->num_vfs, - IXGBE_RAH_AV); + hw->mac.ops.set_rar(hw, 0, hw->mac.addr, VMDQ_P(0), IXGBE_RAH_AV); return 0; } @@ -6485,12 +6522,15 @@ static int ixgbe_add_sanmac_netdev(struct net_device *dev) { int err = 0; struct ixgbe_adapter *adapter = netdev_priv(dev); - struct ixgbe_mac_info *mac = &adapter->hw.mac; + struct ixgbe_hw *hw = &adapter->hw; - if (is_valid_ether_addr(mac->san_addr)) { + if (is_valid_ether_addr(hw->mac.san_addr)) { rtnl_lock(); - err = dev_addr_add(dev, mac->san_addr, NETDEV_HW_ADDR_T_SAN); + err = dev_addr_add(dev, hw->mac.san_addr, NETDEV_HW_ADDR_T_SAN); rtnl_unlock(); + + /* update SAN MAC vmdq pool selection */ + hw->mac.ops.set_vmdq_san_mac(hw, VMDQ_P(0)); } return err; } @@ -6533,11 +6573,8 @@ static void ixgbe_netpoll(struct net_device *netdev) adapter->flags |= IXGBE_FLAG_IN_NETPOLL; if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) { - int num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - for (i = 0; i < num_q_vectors; i++) { - struct ixgbe_q_vector *q_vector = adapter->q_vector[i]; - ixgbe_msix_clean_rings(0, q_vector); - } + for (i = 0; i < adapter->num_q_vectors; i++) + ixgbe_msix_clean_rings(0, adapter->q_vector[i]); } else { ixgbe_intr(adapter->pdev->irq, netdev); } @@ -6594,8 +6631,9 @@ static struct rtnl_link_stats64 *ixgbe_get_stats64(struct net_device *netdev, } #ifdef CONFIG_IXGBE_DCB -/* ixgbe_validate_rtr - verify 802.1Qp to Rx packet buffer mapping is valid. - * #adapter: pointer to ixgbe_adapter +/** + * ixgbe_validate_rtr - verify 802.1Qp to Rx packet buffer mapping is valid. + * @adapter: pointer to ixgbe_adapter * @tc: number of traffic classes currently enabled * * Configure a valid 802.1Qp to Rx packet buffer mapping ie confirm @@ -6630,8 +6668,33 @@ static void ixgbe_validate_rtr(struct ixgbe_adapter *adapter, u8 tc) return; } -/* ixgbe_setup_tc - routine to configure net_device for multiple traffic - * classes. +/** + * ixgbe_set_prio_tc_map - Configure netdev prio tc map + * @adapter: Pointer to adapter struct + * + * Populate the netdev user priority to tc map + */ +static void ixgbe_set_prio_tc_map(struct ixgbe_adapter *adapter) +{ + struct net_device *dev = adapter->netdev; + struct ixgbe_dcb_config *dcb_cfg = &adapter->dcb_cfg; + struct ieee_ets *ets = adapter->ixgbe_ieee_ets; + u8 prio; + + for (prio = 0; prio < MAX_USER_PRIORITY; prio++) { + u8 tc = 0; + + if (adapter->dcbx_cap & DCB_CAP_DCBX_VER_CEE) + tc = ixgbe_dcb_get_tc_from_up(dcb_cfg, 0, prio); + else if (ets) + tc = ets->prio_tc[prio]; + + netdev_set_prio_tc_map(dev, prio, tc); + } +} + +/** + * ixgbe_setup_tc - configure net_device for multiple traffic classes * * @netdev: net device to configure * @tc: number of traffic classes to enable @@ -6641,12 +6704,6 @@ int ixgbe_setup_tc(struct net_device *dev, u8 tc) struct ixgbe_adapter *adapter = netdev_priv(dev); struct ixgbe_hw *hw = &adapter->hw; - /* Multiple traffic classes requires multiple queues */ - if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) { - e_err(drv, "Enable failed, needs MSI-X\n"); - return -EINVAL; - } - /* Hardware supports up to 8 traffic classes */ if (tc > adapter->dcb_cfg.num_tcs.pg_tcs || (hw->mac.type == ixgbe_mac_82598EB && @@ -6663,8 +6720,9 @@ int ixgbe_setup_tc(struct net_device *dev, u8 tc) if (tc) { netdev_set_num_tc(dev, tc); + ixgbe_set_prio_tc_map(adapter); + adapter->flags |= IXGBE_FLAG_DCB_ENABLED; - adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE; if (adapter->hw.mac.type == ixgbe_mac_82598EB) { adapter->last_lfc_mode = adapter->hw.fc.requested_mode; @@ -6672,11 +6730,11 @@ int ixgbe_setup_tc(struct net_device *dev, u8 tc) } } else { netdev_reset_tc(dev); + if (adapter->hw.mac.type == ixgbe_mac_82598EB) adapter->hw.fc.requested_mode = adapter->last_lfc_mode; adapter->flags &= ~IXGBE_FLAG_DCB_ENABLED; - adapter->flags |= IXGBE_FLAG_FDIR_HASH_CAPABLE; adapter->temp_dcb_cfg.pfc_mode_enable = false; adapter->dcb_cfg.pfc_mode_enable = false; @@ -6706,10 +6764,6 @@ static netdev_features_t ixgbe_fix_features(struct net_device *netdev, { struct ixgbe_adapter *adapter = netdev_priv(netdev); - /* return error if RXHASH is being enabled when RSS is not supported */ - if (!(adapter->flags & IXGBE_FLAG_RSS_ENABLED)) - features &= ~NETIF_F_RXHASH; - /* If Rx checksum is disabled, then RSC/LRO should also be disabled */ if (!(features & NETIF_F_RXCSUM)) features &= ~NETIF_F_LRO; @@ -6749,20 +6803,40 @@ static int ixgbe_set_features(struct net_device *netdev, * Check if Flow Director n-tuple support was enabled or disabled. If * the state changed, we need to reset. */ - if (!(features & NETIF_F_NTUPLE)) { - if (adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE) { - /* turn off Flow Director, set ATR and reset */ - if ((adapter->flags & IXGBE_FLAG_RSS_ENABLED) && - !(adapter->flags & IXGBE_FLAG_DCB_ENABLED)) - adapter->flags |= IXGBE_FLAG_FDIR_HASH_CAPABLE; - need_reset = true; - } - adapter->flags &= ~IXGBE_FLAG_FDIR_PERFECT_CAPABLE; - } else if (!(adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE)) { + switch (features & NETIF_F_NTUPLE) { + case NETIF_F_NTUPLE: /* turn off ATR, enable perfect filters and reset */ + if (!(adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE)) + need_reset = true; + adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE; adapter->flags |= IXGBE_FLAG_FDIR_PERFECT_CAPABLE; - need_reset = true; + break; + default: + /* turn off perfect filters, enable ATR and reset */ + if (adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE) + need_reset = true; + + adapter->flags &= ~IXGBE_FLAG_FDIR_PERFECT_CAPABLE; + + /* We cannot enable ATR if SR-IOV is enabled */ + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) + break; + + /* We cannot enable ATR if we have 2 or more traffic classes */ + if (netdev_get_num_tc(netdev) > 1) + break; + + /* We cannot enable ATR if RSS is disabled */ + if (adapter->ring_feature[RING_F_RSS].limit <= 1) + break; + + /* A sample rate of 0 indicates ATR disabled */ + if (!adapter->atr_sample_rate) + break; + + adapter->flags |= IXGBE_FLAG_FDIR_HASH_CAPABLE; + break; } if (features & NETIF_F_HW_VLAN_RX) @@ -6786,7 +6860,10 @@ static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, u16 flags) { struct ixgbe_adapter *adapter = netdev_priv(dev); - int err = -EOPNOTSUPP; + int err; + + if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) + return -EOPNOTSUPP; if (ndm->ndm_state & NUD_PERMANENT) { pr_info("%s: FDB only supports static addresses\n", @@ -6794,13 +6871,17 @@ static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, return -EINVAL; } - if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) { - if (is_unicast_ether_addr(addr)) + if (is_unicast_ether_addr(addr)) { + u32 rar_uc_entries = IXGBE_MAX_PF_MACVLANS; + + if (netdev_uc_count(dev) < rar_uc_entries) err = dev_uc_add_excl(dev, addr); - else if (is_multicast_ether_addr(addr)) - err = dev_mc_add_excl(dev, addr); else - err = -EINVAL; + err = -ENOMEM; + } else if (is_multicast_ether_addr(addr)) { + err = dev_mc_add_excl(dev, addr); + } else { + err = -EINVAL; } /* Only return duplicate errors if NLM_F_EXCL is set */ @@ -6889,26 +6970,6 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_fdb_dump = ixgbe_ndo_fdb_dump, }; -static void __devinit ixgbe_probe_vf(struct ixgbe_adapter *adapter, - const struct ixgbe_info *ii) -{ -#ifdef CONFIG_PCI_IOV - struct ixgbe_hw *hw = &adapter->hw; - - if (hw->mac.type == ixgbe_mac_82598EB) - return; - - /* The 82599 supports up to 64 VFs per physical function - * but this implementation limits allocation to 63 so that - * basic networking resources are still available to the - * physical function. If the user requests greater thn - * 63 VFs then it is an error - reset to default of zero. - */ - adapter->num_vfs = (max_vfs > 63) ? 0 : max_vfs; - ixgbe_enable_sriov(adapter, ii); -#endif /* CONFIG_PCI_IOV */ -} - /** * ixgbe_wol_supported - Check whether device supports WoL * @hw: hw specific details @@ -6935,6 +6996,7 @@ int ixgbe_wol_supported(struct ixgbe_adapter *adapter, u16 device_id, if (hw->bus.func != 0) break; case IXGBE_SUBDEV_ID_82599_SFP: + case IXGBE_SUBDEV_ID_82599_RNDC: is_wol_supported = 1; break; } @@ -6982,6 +7044,7 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev, int i, err, pci_using_dac; u8 part_str[IXGBE_PBANUM_LENGTH]; unsigned int indices = num_possible_cpus(); + unsigned int dcb_max = 0; #ifdef IXGBE_FCOE u16 device_caps; #endif @@ -7031,7 +7094,12 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev, pci_save_state(pdev); #ifdef CONFIG_IXGBE_DCB - indices *= MAX_TRAFFIC_CLASS; + if (ii->mac == ixgbe_mac_82598EB) + dcb_max = min_t(unsigned int, indices * MAX_TRAFFIC_CLASS, + IXGBE_MAX_RSS_INDICES); + else + dcb_max = min_t(unsigned int, indices * MAX_TRAFFIC_CLASS, + IXGBE_MAX_FDIR_INDICES); #endif if (ii->mac == ixgbe_mac_82598EB) @@ -7043,6 +7111,7 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev, indices += min_t(unsigned int, num_possible_cpus(), IXGBE_MAX_FCOE_INDICES); #endif + indices = max_t(unsigned int, dcb_max, indices); netdev = alloc_etherdev_mq(sizeof(struct ixgbe_adapter), indices); if (!netdev) { err = -ENOMEM; @@ -7149,8 +7218,10 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev, goto err_sw_init; } - ixgbe_probe_vf(adapter, ii); +#ifdef CONFIG_PCI_IOV + ixgbe_enable_sriov(adapter, ii); +#endif netdev->features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | @@ -7186,10 +7257,6 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev, netdev->priv_flags |= IFF_UNICAST_FLT; netdev->priv_flags |= IFF_SUPP_NOFCS; - if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) - adapter->flags &= ~(IXGBE_FLAG_RSS_ENABLED | - IXGBE_FLAG_DCB_ENABLED); - #ifdef CONFIG_IXGBE_DCB netdev->dcbnl_ops = &dcbnl_ops; #endif @@ -7201,11 +7268,15 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev, if (device_caps & IXGBE_DEVICE_CAPS_FCOE_OFFLOADS) adapter->flags &= ~IXGBE_FLAG_FCOE_CAPABLE; } - } - if (adapter->flags & IXGBE_FLAG_FCOE_CAPABLE) { - netdev->vlan_features |= NETIF_F_FCOE_CRC; - netdev->vlan_features |= NETIF_F_FSO; - netdev->vlan_features |= NETIF_F_FCOE_MTU; + + adapter->ring_feature[RING_F_FCOE].limit = IXGBE_FCRETA_SIZE; + + netdev->features |= NETIF_F_FSO | + NETIF_F_FCOE_CRC; + + netdev->vlan_features |= NETIF_F_FSO | + NETIF_F_FCOE_CRC | + NETIF_F_FCOE_MTU; } #endif /* IXGBE_FCOE */ if (pci_using_dac) { @@ -7244,11 +7315,6 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev, if (err) goto err_sw_init; - if (!(adapter->flags & IXGBE_FLAG_RSS_ENABLED)) { - netdev->hw_features &= ~NETIF_F_RXHASH; - netdev->features &= ~NETIF_F_RXHASH; - } - /* WOL not supported for all devices */ adapter->wol = 0; hw->eeprom.ops.read(hw, 0x2c, &adapter->eeprom_cap); @@ -7359,8 +7425,7 @@ err_register: ixgbe_release_hw_control(adapter); ixgbe_clear_interrupt_scheme(adapter); err_sw_init: - if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) - ixgbe_disable_sriov(adapter); + ixgbe_disable_sriov(adapter); adapter->flags2 &= ~IXGBE_FLAG2_SEARCH_FOR_SFP; iounmap(hw->hw_addr); err_ioremap: @@ -7407,25 +7472,13 @@ static void __devexit ixgbe_remove(struct pci_dev *pdev) ixgbe_sysfs_exit(adapter); #endif /* CONFIG_IXGBE_HWMON */ -#ifdef IXGBE_FCOE - if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) - ixgbe_cleanup_fcoe(adapter); - -#endif /* IXGBE_FCOE */ - /* remove the added san mac */ ixgbe_del_sanmac_netdev(netdev); if (netdev->reg_state == NETREG_REGISTERED) unregister_netdev(netdev); - if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) { - if (!(ixgbe_check_vf_assignment(adapter))) - ixgbe_disable_sriov(adapter); - else - e_dev_warn("Unloading driver while VFs are assigned " - "- VFs will not be deallocated\n"); - } + ixgbe_disable_sriov(adapter); ixgbe_clear_interrupt_scheme(adapter); @@ -7516,11 +7569,11 @@ static pci_ers_result_t ixgbe_io_error_detected(struct pci_dev *pdev, } /* Find the pci device of the offending VF */ - vfdev = pci_get_device(IXGBE_INTEL_VENDOR_ID, device_id, NULL); + vfdev = pci_get_device(PCI_VENDOR_ID_INTEL, device_id, NULL); while (vfdev) { if (vfdev->devfn == (req_id & 0xFF)) break; - vfdev = pci_get_device(IXGBE_INTEL_VENDOR_ID, + vfdev = pci_get_device(PCI_VENDOR_ID_INTEL, device_id, vfdev); } /* diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c index 24117709d6a2..71659edf81aa 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c @@ -907,6 +907,8 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) * 8 SFP_act_lmt_DA_CORE1 - 82599-specific * 9 SFP_1g_cu_CORE0 - 82599-specific * 10 SFP_1g_cu_CORE1 - 82599-specific + * 11 SFP_1g_sx_CORE0 - 82599-specific + * 12 SFP_1g_sx_CORE1 - 82599-specific */ if (hw->mac.type == ixgbe_mac_82598EB) { if (cable_tech & IXGBE_SFF_DA_PASSIVE_CABLE) @@ -957,6 +959,13 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) else hw->phy.sfp_type = ixgbe_sfp_type_1g_cu_core1; + } else if (comp_codes_1g & IXGBE_SFF_1GBASESX_CAPABLE) { + if (hw->bus.lan_id == 0) + hw->phy.sfp_type = + ixgbe_sfp_type_1g_sx_core0; + else + hw->phy.sfp_type = + ixgbe_sfp_type_1g_sx_core1; } else { hw->phy.sfp_type = ixgbe_sfp_type_unknown; } @@ -1049,7 +1058,9 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) /* Verify supported 1G SFP modules */ if (comp_codes_10g == 0 && !(hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core1 || - hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core0)) { + hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1)) { hw->phy.type = ixgbe_phy_sfp_unsupported; status = IXGBE_ERR_SFP_NOT_SUPPORTED; goto out; @@ -1064,7 +1075,9 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) hw->mac.ops.get_device_caps(hw, &enforce_sfp); if (!(enforce_sfp & IXGBE_DEVICE_CAPS_ALLOW_ANY_SFP) && !((hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core0) || - (hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core1))) { + (hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core1) || + (hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core0) || + (hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1))) { /* Make sure we're a supported PHY type */ if (hw->phy.type == ixgbe_phy_sfp_intel) { status = 0; @@ -1128,10 +1141,12 @@ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, * SR modules */ if (sfp_type == ixgbe_sfp_type_da_act_lmt_core0 || - sfp_type == ixgbe_sfp_type_1g_cu_core0) + sfp_type == ixgbe_sfp_type_1g_cu_core0 || + sfp_type == ixgbe_sfp_type_1g_sx_core0) sfp_type = ixgbe_sfp_type_srlr_core0; else if (sfp_type == ixgbe_sfp_type_da_act_lmt_core1 || - sfp_type == ixgbe_sfp_type_1g_cu_core1) + sfp_type == ixgbe_sfp_type_1g_cu_core1 || + sfp_type == ixgbe_sfp_type_1g_sx_core1) sfp_type = ixgbe_sfp_type_srlr_core1; /* Read offset to PHY init contents */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index dcebd128becf..3456d5617143 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -26,6 +26,7 @@ *******************************************************************************/ #include "ixgbe.h" #include <linux/export.h> +#include <linux/ptp_classify.h> /* * The 82599 and the X540 do not have true 64bit nanosecond scale @@ -100,9 +101,13 @@ #define NSECS_PER_SEC 1000000000ULL #endif +static struct sock_filter ptp_filter[] = { + PTP_FILTER +}; + /** * ixgbe_ptp_read - read raw cycle counter (to be used by time counter) - * @cc - the cyclecounter structure + * @cc: the cyclecounter structure * * this function reads the cyclecounter registers and is called by the * cyclecounter structure used to construct a ns counter from the @@ -123,8 +128,8 @@ static cycle_t ixgbe_ptp_read(const struct cyclecounter *cc) /** * ixgbe_ptp_adjfreq - * @ptp - the ptp clock structure - * @ppb - parts per billion adjustment from base + * @ptp: the ptp clock structure + * @ppb: parts per billion adjustment from base * * adjust the frequency of the ptp cycle counter by the * indicated ppb from the base frequency. @@ -170,8 +175,8 @@ static int ixgbe_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) /** * ixgbe_ptp_adjtime - * @ptp - the ptp clock structure - * @delta - offset to adjust the cycle counter by + * @ptp: the ptp clock structure + * @delta: offset to adjust the cycle counter by * * adjust the timer by resetting the timecounter structure. */ @@ -198,8 +203,8 @@ static int ixgbe_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) /** * ixgbe_ptp_gettime - * @ptp - the ptp clock structure - * @ts - timespec structure to hold the current time value + * @ptp: the ptp clock structure + * @ts: timespec structure to hold the current time value * * read the timecounter and return the correct value on ns, * after converting it into a struct timespec. @@ -224,8 +229,8 @@ static int ixgbe_ptp_gettime(struct ptp_clock_info *ptp, struct timespec *ts) /** * ixgbe_ptp_settime - * @ptp - the ptp clock structure - * @ts - the timespec containing the new time for the cycle counter + * @ptp: the ptp clock structure + * @ts: the timespec containing the new time for the cycle counter * * reset the timecounter to use a new base value instead of the kernel * wall timer value. @@ -251,9 +256,9 @@ static int ixgbe_ptp_settime(struct ptp_clock_info *ptp, /** * ixgbe_ptp_enable - * @ptp - the ptp clock structure - * @rq - the requested feature to change - * @on - whether to enable or disable the feature + * @ptp: the ptp clock structure + * @rq: the requested feature to change + * @on: whether to enable or disable the feature * * enable (or disable) ancillary features of the phc subsystem. * our driver only supports the PPS feature on the X540 @@ -289,8 +294,8 @@ static int ixgbe_ptp_enable(struct ptp_clock_info *ptp, /** * ixgbe_ptp_check_pps_event - * @adapter - the private adapter structure - * @eicr - the interrupt cause register value + * @adapter: the private adapter structure + * @eicr: the interrupt cause register value * * This function is called by the interrupt routine when checking for * interrupts. It will check and handle a pps event. @@ -307,20 +312,21 @@ void ixgbe_ptp_check_pps_event(struct ixgbe_adapter *adapter, u32 eicr) !(adapter->flags2 & IXGBE_FLAG2_PTP_PPS_ENABLED)) return; - switch (hw->mac.type) { - case ixgbe_mac_X540: - if (eicr & IXGBE_EICR_TIMESYNC) + if (unlikely(eicr & IXGBE_EICR_TIMESYNC)) { + switch (hw->mac.type) { + case ixgbe_mac_X540: ptp_clock_event(adapter->ptp_clock, &event); - break; - default: - break; + break; + default: + break; + } } } /** * ixgbe_ptp_enable_sdp - * @hw - the hardware private structure - * @shift - the clock shift for calculating nanoseconds + * @hw: the hardware private structure + * @shift: the clock shift for calculating nanoseconds * * this function enables the clock out feature on the sdp0 for the * X540 device. It will create a 1second periodic output that can be @@ -393,7 +399,7 @@ static void ixgbe_ptp_enable_sdp(struct ixgbe_hw *hw, int shift) /** * ixgbe_ptp_disable_sdp - * @hw - the private hardware structure + * @hw: the private hardware structure * * this function disables the auxiliary SDP clock out feature */ @@ -425,6 +431,68 @@ void ixgbe_ptp_overflow_check(struct ixgbe_adapter *adapter) } /** + * ixgbe_ptp_match - determine if this skb matches a ptp packet + * @skb: pointer to the skb + * @hwtstamp: pointer to the hwtstamp_config to check + * + * Determine whether the skb should have been timestamped, assuming the + * hwtstamp was set via the hwtstamp ioctl. Returns non-zero when the packet + * should have a timestamp waiting in the registers, and 0 otherwise. + * + * V1 packets have to check the version type to determine whether they are + * correct. However, we can't directly access the data because it might be + * fragmented in the SKB, in paged memory. In order to work around this, we + * use skb_copy_bits which will properly copy the data whether it is in the + * paged memory fragments or not. We have to copy the IP header as well as the + * message type. + */ +static int ixgbe_ptp_match(struct sk_buff *skb, int rx_filter) +{ + struct iphdr iph; + u8 msgtype; + unsigned int type, offset; + + if (rx_filter == HWTSTAMP_FILTER_NONE) + return 0; + + type = sk_run_filter(skb, ptp_filter); + + if (likely(rx_filter == HWTSTAMP_FILTER_PTP_V2_EVENT)) + return type & PTP_CLASS_V2; + + /* For the remaining cases actually check message type */ + switch (type) { + case PTP_CLASS_V1_IPV4: + skb_copy_bits(skb, OFF_IHL, &iph, sizeof(iph)); + offset = ETH_HLEN + (iph.ihl << 2) + UDP_HLEN + OFF_PTP_CONTROL; + break; + case PTP_CLASS_V1_IPV6: + offset = OFF_PTP6 + OFF_PTP_CONTROL; + break; + default: + /* other cases invalid or handled above */ + return 0; + } + + /* Make sure our buffer is long enough */ + if (skb->len < offset) + return 0; + + skb_copy_bits(skb, offset, &msgtype, sizeof(msgtype)); + + switch (rx_filter) { + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + return (msgtype == IXGBE_RXMTRL_V1_SYNC_MSG); + break; + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + return (msgtype == IXGBE_RXMTRL_V1_DELAY_REQ_MSG); + break; + default: + return 0; + } +} + +/** * ixgbe_ptp_tx_hwtstamp - utility function which checks for TX time stamp * @q_vector: structure containing interrupt and ring information * @skb: particular skb to send timestamp with @@ -473,6 +541,7 @@ void ixgbe_ptp_tx_hwtstamp(struct ixgbe_q_vector *q_vector, /** * ixgbe_ptp_rx_hwtstamp - utility function which checks for RX time stamp * @q_vector: structure containing interrupt and ring information + * @rx_desc: the rx descriptor * @skb: particular skb to send timestamp with * * if the timestamp is valid, we convert it into the timecounter ns @@ -480,6 +549,7 @@ void ixgbe_ptp_tx_hwtstamp(struct ixgbe_q_vector *q_vector, * is passed up the network stack */ void ixgbe_ptp_rx_hwtstamp(struct ixgbe_q_vector *q_vector, + union ixgbe_adv_rx_desc *rx_desc, struct sk_buff *skb) { struct ixgbe_adapter *adapter; @@ -497,21 +567,33 @@ void ixgbe_ptp_rx_hwtstamp(struct ixgbe_q_vector *q_vector, hw = &adapter->hw; tsyncrxctl = IXGBE_READ_REG(hw, IXGBE_TSYNCRXCTL); + + /* Check if we have a valid timestamp and make sure the skb should + * have been timestamped */ + if (likely(!(tsyncrxctl & IXGBE_TSYNCRXCTL_VALID) || + !ixgbe_ptp_match(skb, adapter->rx_hwtstamp_filter))) + return; + + /* + * Always read the registers, in order to clear a possible fault + * because of stagnant RX timestamp values for a packet that never + * reached the queue. + */ regval |= (u64)IXGBE_READ_REG(hw, IXGBE_RXSTMPL); regval |= (u64)IXGBE_READ_REG(hw, IXGBE_RXSTMPH) << 32; /* - * If this bit is set, then the RX registers contain the time stamp. No - * other packet will be time stamped until we read these registers, so - * read the registers to make them available again. Because only one - * packet can be time stamped at a time, we know that the register - * values must belong to this one here and therefore we don't need to - * compare any of the additional attributes stored for it. + * If the timestamp bit is set in the packet's descriptor, we know the + * timestamp belongs to this packet. No other packet can be + * timestamped until the registers for timestamping have been read. + * Therefor only one packet with this bit can be in the queue at a + * time, and the rx timestamp values that were in the registers belong + * to this packet. * * If nothing went wrong, then it should have a skb_shared_tx that we * can turn into a skb_shared_hwtstamps. */ - if (!(tsyncrxctl & IXGBE_TSYNCRXCTL_VALID)) + if (unlikely(!ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_STAT_TS))) return; spin_lock_irqsave(&adapter->tmreg_lock, flags); @@ -539,6 +621,11 @@ void ixgbe_ptp_rx_hwtstamp(struct ixgbe_q_vector *q_vector, * type has to be specified. Matching the kind of event packet is * not supported, with the exception of "all V2 events regardless of * level 2 or 4". + * + * Since hardware always timestamps Path delay packets when timestamping V2 + * packets, regardless of the type specified in the register, only use V2 + * Event mode. This more accurately tells the user what the hardware is going + * to do anyways. */ int ixgbe_ptp_hwtstamp_ioctl(struct ixgbe_adapter *adapter, struct ifreq *ifr, int cmd) @@ -582,41 +669,30 @@ int ixgbe_ptp_hwtstamp_ioctl(struct ixgbe_adapter *adapter, tsync_rx_mtrl = IXGBE_RXMTRL_V1_DELAY_REQ_MSG; is_l4 = true; 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: - tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_L2_L4_V2; - tsync_rx_mtrl = IXGBE_RXMTRL_V2_SYNC_MSG; - is_l2 = true; - is_l4 = true; - config.rx_filter = HWTSTAMP_FILTER_SOME; - break; case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: - tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_L2_L4_V2; - tsync_rx_mtrl = IXGBE_RXMTRL_V2_DELAY_REQ_MSG; - is_l2 = true; - is_l4 = true; - config.rx_filter = HWTSTAMP_FILTER_SOME; - break; - case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: - case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: - case HWTSTAMP_FILTER_PTP_V2_EVENT: tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_EVENT_V2; - config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; is_l2 = true; is_l4 = true; + config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; break; case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: case HWTSTAMP_FILTER_ALL: default: /* - * register RXMTRL must be set, therefore it is not - * possible to time stamp both V1 Sync and Delay_Req messages - * and hardware does not support timestamping all packets - * => return error + * register RXMTRL must be set in order to do V1 packets, + * therefore it is not possible to time stamp both V1 Sync and + * Delay_Req messages and hardware does not support + * timestamping all packets => return error */ + config.rx_filter = HWTSTAMP_FILTER_NONE; return -ERANGE; } @@ -626,6 +702,9 @@ int ixgbe_ptp_hwtstamp_ioctl(struct ixgbe_adapter *adapter, return 0; } + /* Store filter value for later use */ + adapter->rx_hwtstamp_filter = config.rx_filter; + /* define ethertype filter for timestamped packets */ if (is_l2) IXGBE_WRITE_REG(hw, IXGBE_ETQF(3), @@ -690,7 +769,7 @@ int ixgbe_ptp_hwtstamp_ioctl(struct ixgbe_adapter *adapter, /** * ixgbe_ptp_start_cyclecounter - create the cycle counter from hw - * @adapter - pointer to the adapter structure + * @adapter: pointer to the adapter structure * * this function initializes the timecounter and cyclecounter * structures for use in generated a ns counter from the arbitrary @@ -826,7 +905,7 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter) /** * ixgbe_ptp_init - * @adapter - the ixgbe private adapter structure + * @adapter: the ixgbe private adapter structure * * This function performs the required steps for enabling ptp * support. If ptp support has already been loaded it simply calls the @@ -870,6 +949,10 @@ void ixgbe_ptp_init(struct ixgbe_adapter *adapter) return; } + /* initialize the ptp filter */ + if (ptp_filter_init(ptp_filter, ARRAY_SIZE(ptp_filter))) + e_dev_warn("ptp_filter_init failed\n"); + spin_lock_init(&adapter->tmreg_lock); ixgbe_ptp_start_cyclecounter(adapter); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index 2d971d18696e..4fea8716ab64 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -44,50 +44,15 @@ #include "ixgbe_sriov.h" #ifdef CONFIG_PCI_IOV -static int ixgbe_find_enabled_vfs(struct ixgbe_adapter *adapter) -{ - struct pci_dev *pdev = adapter->pdev; - struct pci_dev *pvfdev; - u16 vf_devfn = 0; - int device_id; - int vfs_found = 0; - - switch (adapter->hw.mac.type) { - case ixgbe_mac_82599EB: - device_id = IXGBE_DEV_ID_82599_VF; - break; - case ixgbe_mac_X540: - device_id = IXGBE_DEV_ID_X540_VF; - break; - default: - device_id = 0; - break; - } - - vf_devfn = pdev->devfn + 0x80; - pvfdev = pci_get_device(IXGBE_INTEL_VENDOR_ID, device_id, NULL); - while (pvfdev) { - if (pvfdev->devfn == vf_devfn && - (pvfdev->bus->number >= pdev->bus->number)) - vfs_found++; - vf_devfn += 2; - pvfdev = pci_get_device(IXGBE_INTEL_VENDOR_ID, - device_id, pvfdev); - } - - return vfs_found; -} - void ixgbe_enable_sriov(struct ixgbe_adapter *adapter, const struct ixgbe_info *ii) { struct ixgbe_hw *hw = &adapter->hw; - int err = 0; int num_vf_macvlans, i; struct vf_macvlans *mv_list; int pre_existing_vfs = 0; - pre_existing_vfs = ixgbe_find_enabled_vfs(adapter); + pre_existing_vfs = pci_num_vf(adapter->pdev); if (!pre_existing_vfs && !adapter->num_vfs) return; @@ -106,16 +71,33 @@ void ixgbe_enable_sriov(struct ixgbe_adapter *adapter, "enabled for this device - Please reload all " "VF drivers to avoid spoofed packet errors\n"); } else { + int err; + /* + * The 82599 supports up to 64 VFs per physical function + * but this implementation limits allocation to 63 so that + * basic networking resources are still available to the + * physical function. If the user requests greater thn + * 63 VFs then it is an error - reset to default of zero. + */ + adapter->num_vfs = min_t(unsigned int, adapter->num_vfs, 63); + err = pci_enable_sriov(adapter->pdev, adapter->num_vfs); + if (err) { + e_err(probe, "Failed to enable PCI sriov: %d\n", err); + adapter->num_vfs = 0; + return; + } } - if (err) { - e_err(probe, "Failed to enable PCI sriov: %d\n", err); - goto err_novfs; - } - adapter->flags |= IXGBE_FLAG_SRIOV_ENABLED; + adapter->flags |= IXGBE_FLAG_SRIOV_ENABLED; e_info(probe, "SR-IOV enabled with %d VFs\n", adapter->num_vfs); + /* Enable VMDq flag so device will be set in VM mode */ + adapter->flags |= IXGBE_FLAG_VMDQ_ENABLED; + if (!adapter->ring_feature[RING_F_VMDQ].limit) + adapter->ring_feature[RING_F_VMDQ].limit = 1; + adapter->ring_feature[RING_F_VMDQ].offset = adapter->num_vfs; + num_vf_macvlans = hw->mac.num_rar_entries - (IXGBE_MAX_PF_MACVLANS + 1 + adapter->num_vfs); @@ -146,12 +128,39 @@ void ixgbe_enable_sriov(struct ixgbe_adapter *adapter, * and memory allocated set up the mailbox parameters */ ixgbe_init_mbx_params_pf(hw); - memcpy(&hw->mbx.ops, ii->mbx_ops, - sizeof(hw->mbx.ops)); + memcpy(&hw->mbx.ops, ii->mbx_ops, sizeof(hw->mbx.ops)); + + /* limit trafffic classes based on VFs enabled */ + if ((adapter->hw.mac.type == ixgbe_mac_82599EB) && + (adapter->num_vfs < 16)) { + adapter->dcb_cfg.num_tcs.pg_tcs = MAX_TRAFFIC_CLASS; + adapter->dcb_cfg.num_tcs.pfc_tcs = MAX_TRAFFIC_CLASS; + } else if (adapter->num_vfs < 32) { + adapter->dcb_cfg.num_tcs.pg_tcs = 4; + adapter->dcb_cfg.num_tcs.pfc_tcs = 4; + } else { + adapter->dcb_cfg.num_tcs.pg_tcs = 1; + adapter->dcb_cfg.num_tcs.pfc_tcs = 1; + } + + /* We do not support RSS w/ SR-IOV */ + adapter->ring_feature[RING_F_RSS].limit = 1; /* Disable RSC when in SR-IOV mode */ adapter->flags2 &= ~(IXGBE_FLAG2_RSC_CAPABLE | IXGBE_FLAG2_RSC_ENABLED); + +#ifdef IXGBE_FCOE + /* + * When SR-IOV is enabled 82599 cannot support jumbo frames + * so we must disable FCoE because we cannot support FCoE MTU. + */ + if (adapter->hw.mac.type == ixgbe_mac_82599EB) + adapter->flags &= ~(IXGBE_FLAG_FCOE_ENABLED | + IXGBE_FLAG_FCOE_CAPABLE); +#endif + + /* enable spoof checking for all VFs */ for (i = 0; i < adapter->num_vfs; i++) adapter->vfinfo[i].spoofchk_enabled = true; return; @@ -160,31 +169,80 @@ void ixgbe_enable_sriov(struct ixgbe_adapter *adapter, /* Oh oh */ e_err(probe, "Unable to allocate memory for VF Data Storage - " "SRIOV disabled\n"); - pci_disable_sriov(adapter->pdev); + ixgbe_disable_sriov(adapter); +} -err_novfs: - adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED; - adapter->num_vfs = 0; +static bool ixgbe_vfs_are_assigned(struct ixgbe_adapter *adapter) +{ + struct pci_dev *pdev = adapter->pdev; + struct pci_dev *vfdev; + int dev_id; + + switch (adapter->hw.mac.type) { + case ixgbe_mac_82599EB: + dev_id = IXGBE_DEV_ID_82599_VF; + break; + case ixgbe_mac_X540: + dev_id = IXGBE_DEV_ID_X540_VF; + break; + default: + return false; + } + + /* loop through all the VFs to see if we own any that are assigned */ + vfdev = pci_get_device(PCI_VENDOR_ID_INTEL, dev_id, NULL); + while (vfdev) { + /* if we don't own it we don't care */ + if (vfdev->is_virtfn && vfdev->physfn == pdev) { + /* if it is assigned we cannot release it */ + if (vfdev->dev_flags & PCI_DEV_FLAGS_ASSIGNED) + return true; + } + + vfdev = pci_get_device(PCI_VENDOR_ID_INTEL, dev_id, vfdev); + } + + return false; } -#endif /* #ifdef CONFIG_PCI_IOV */ +#endif /* #ifdef CONFIG_PCI_IOV */ void ixgbe_disable_sriov(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; - u32 gcr; u32 gpie; u32 vmdctl; - int i; + + /* set num VFs to 0 to prevent access to vfinfo */ + adapter->num_vfs = 0; + + /* free VF control structures */ + kfree(adapter->vfinfo); + adapter->vfinfo = NULL; + + /* free macvlan list */ + kfree(adapter->mv_list); + adapter->mv_list = NULL; + + /* if SR-IOV is already disabled then there is nothing to do */ + if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) + return; #ifdef CONFIG_PCI_IOV + /* + * If our VFs are assigned we cannot shut down SR-IOV + * without causing issues, so just leave the hardware + * available but disabled + */ + if (ixgbe_vfs_are_assigned(adapter)) { + e_dev_warn("Unloading driver while VFs are assigned - VFs will not be deallocated\n"); + return; + } /* disable iov and allow time for transactions to clear */ pci_disable_sriov(adapter->pdev); #endif /* turn off device IOV mode */ - gcr = IXGBE_READ_REG(hw, IXGBE_GCR_EXT); - gcr &= ~(IXGBE_GCR_EXT_SRIOV); - IXGBE_WRITE_REG(hw, IXGBE_GCR_EXT, gcr); + IXGBE_WRITE_REG(hw, IXGBE_GCR_EXT, 0); gpie = IXGBE_READ_REG(hw, IXGBE_GPIE); gpie &= ~IXGBE_GPIE_VTMODE_MASK; IXGBE_WRITE_REG(hw, IXGBE_GPIE, gpie); @@ -195,19 +253,14 @@ void ixgbe_disable_sriov(struct ixgbe_adapter *adapter) IXGBE_WRITE_REG(hw, IXGBE_VT_CTL, vmdctl); IXGBE_WRITE_FLUSH(hw); + /* Disable VMDq flag so device will be set in VM mode */ + if (adapter->ring_feature[RING_F_VMDQ].limit == 1) + adapter->flags &= ~IXGBE_FLAG_VMDQ_ENABLED; + adapter->ring_feature[RING_F_VMDQ].offset = 0; + /* take a breather then clean up driver data */ msleep(100); - /* Release reference to VF devices */ - for (i = 0; i < adapter->num_vfs; i++) { - if (adapter->vfinfo[i].vfdev) - pci_dev_put(adapter->vfinfo[i].vfdev); - } - kfree(adapter->vfinfo); - kfree(adapter->mv_list); - adapter->vfinfo = NULL; - - adapter->num_vfs = 0; adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED; } @@ -441,33 +494,16 @@ static int ixgbe_set_vf_macvlan(struct ixgbe_adapter *adapter, return 0; } -int ixgbe_check_vf_assignment(struct ixgbe_adapter *adapter) -{ -#ifdef CONFIG_PCI_IOV - int i; - for (i = 0; i < adapter->num_vfs; i++) { - if (adapter->vfinfo[i].vfdev->dev_flags & - PCI_DEV_FLAGS_ASSIGNED) - return true; - } -#endif - return false; -} - int ixgbe_vf_configuration(struct pci_dev *pdev, unsigned int event_mask) { unsigned char vf_mac_addr[6]; struct ixgbe_adapter *adapter = pci_get_drvdata(pdev); unsigned int vfn = (event_mask & 0x3f); - struct pci_dev *pvfdev; - unsigned int device_id; - u16 thisvf_devfn = (pdev->devfn + 0x80 + (vfn << 1)) | - (pdev->devfn & 1); bool enable = ((event_mask & 0x10000000U) != 0); if (enable) { - random_ether_addr(vf_mac_addr); + eth_random_addr(vf_mac_addr); e_info(probe, "IOV: VF %d is enabled MAC %pM\n", vfn, vf_mac_addr); /* @@ -475,31 +511,6 @@ int ixgbe_vf_configuration(struct pci_dev *pdev, unsigned int event_mask) * for it later. */ memcpy(adapter->vfinfo[vfn].vf_mac_addresses, vf_mac_addr, 6); - - switch (adapter->hw.mac.type) { - case ixgbe_mac_82599EB: - device_id = IXGBE_DEV_ID_82599_VF; - break; - case ixgbe_mac_X540: - device_id = IXGBE_DEV_ID_X540_VF; - break; - default: - device_id = 0; - break; - } - - pvfdev = pci_get_device(IXGBE_INTEL_VENDOR_ID, device_id, NULL); - while (pvfdev) { - if (pvfdev->devfn == thisvf_devfn) - break; - pvfdev = pci_get_device(IXGBE_INTEL_VENDOR_ID, - device_id, pvfdev); - } - if (pvfdev) - adapter->vfinfo[vfn].vfdev = pvfdev; - else - e_err(drv, "Couldn't find pci dev ptr for VF %4.4x\n", - thisvf_devfn); } return 0; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h index 2ab38d5fda92..1be1d30e4e78 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h @@ -42,7 +42,6 @@ int ixgbe_ndo_get_vf_config(struct net_device *netdev, int vf, struct ifla_vf_info *ivi); void ixgbe_check_vf_rate_limit(struct ixgbe_adapter *adapter); void ixgbe_disable_sriov(struct ixgbe_adapter *adapter); -int ixgbe_check_vf_assignment(struct ixgbe_adapter *adapter); #ifdef CONFIG_PCI_IOV void ixgbe_enable_sriov(struct ixgbe_adapter *adapter, const struct ixgbe_info *ii); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sysfs.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sysfs.c index 1d80b1cefa6a..16ddf14e8ba4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sysfs.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sysfs.c @@ -37,7 +37,6 @@ #include <linux/netdevice.h> #include <linux/hwmon.h> -#ifdef CONFIG_IXGBE_HWMON /* hwmon callback functions */ static ssize_t ixgbe_hwmon_show_location(struct device *dev, struct device_attribute *attr, @@ -96,11 +95,11 @@ static ssize_t ixgbe_hwmon_show_maxopthresh(struct device *dev, return sprintf(buf, "%u\n", value); } -/* +/** * ixgbe_add_hwmon_attr - Create hwmon attr table for a hwmon sysfs file. - * @ adapter: pointer to the adapter structure - * @ offset: offset in the eeprom sensor data table - * @ type: type of sensor data to display + * @adapter: pointer to the adapter structure + * @offset: offset in the eeprom sensor data table + * @type: type of sensor data to display * * For each file we want in hwmon's sysfs interface we need a device_attribute * This is included in our hwmon_attr struct that contains the references to @@ -241,5 +240,4 @@ err: exit: return rc; } -#endif /* CONFIG_IXGBE_HWMON */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h index 204848d2448c..400f86a31174 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h @@ -32,9 +32,6 @@ #include <linux/mdio.h> #include <linux/netdevice.h> -/* Vendor ID */ -#define IXGBE_INTEL_VENDOR_ID 0x8086 - /* Device IDs */ #define IXGBE_DEV_ID_82598 0x10B6 #define IXGBE_DEV_ID_82598_BX 0x1508 @@ -57,6 +54,7 @@ #define IXGBE_DEV_ID_82599_BACKPLANE_FCOE 0x152a #define IXGBE_DEV_ID_82599_SFP_FCOE 0x1529 #define IXGBE_SUBDEV_ID_82599_SFP 0x11A9 +#define IXGBE_SUBDEV_ID_82599_RNDC 0x1F72 #define IXGBE_SUBDEV_ID_82599_560FLR 0x17D0 #define IXGBE_DEV_ID_82599_SFP_EM 0x1507 #define IXGBE_DEV_ID_82599_SFP_SF2 0x154D @@ -1452,6 +1450,7 @@ enum { #define IXGBE_ETQF_1588 0x40000000 /* bit 30 */ #define IXGBE_ETQF_FILTER_EN 0x80000000 /* bit 31 */ #define IXGBE_ETQF_POOL_ENABLE (1 << 26) /* bit 26 */ +#define IXGBE_ETQF_POOL_SHIFT 20 #define IXGBE_ETQS_RX_QUEUE 0x007F0000 /* bits 22:16 */ #define IXGBE_ETQS_RX_QUEUE_SHIFT 16 @@ -2419,7 +2418,7 @@ typedef u32 ixgbe_physical_layer; */ /* BitTimes (BT) conversion */ -#define IXGBE_BT2KB(BT) ((BT + 1023) / (8 * 1024)) +#define IXGBE_BT2KB(BT) ((BT + (8 * 1024 - 1)) / (8 * 1024)) #define IXGBE_B2BT(BT) (BT * 8) /* Calculate Delay to respond to PFC */ @@ -2450,24 +2449,31 @@ typedef u32 ixgbe_physical_layer; #define IXGBE_PCI_DELAY 10000 /* Calculate X540 delay value in bit times */ -#define IXGBE_FILL_RATE (36 / 25) - -#define IXGBE_DV_X540(LINK, TC) (IXGBE_FILL_RATE * \ - (IXGBE_B2BT(LINK) + IXGBE_PFC_D + \ - (2 * IXGBE_CABLE_DC) + \ - (2 * IXGBE_ID_X540) + \ - IXGBE_HD + IXGBE_B2BT(TC))) +#define IXGBE_DV_X540(_max_frame_link, _max_frame_tc) \ + ((36 * \ + (IXGBE_B2BT(_max_frame_link) + \ + IXGBE_PFC_D + \ + (2 * IXGBE_CABLE_DC) + \ + (2 * IXGBE_ID_X540) + \ + IXGBE_HD) / 25 + 1) + \ + 2 * IXGBE_B2BT(_max_frame_tc)) /* Calculate 82599, 82598 delay value in bit times */ -#define IXGBE_DV(LINK, TC) (IXGBE_FILL_RATE * \ - (IXGBE_B2BT(LINK) + IXGBE_PFC_D + \ - (2 * IXGBE_CABLE_DC) + (2 * IXGBE_ID) + \ - IXGBE_HD + IXGBE_B2BT(TC))) +#define IXGBE_DV(_max_frame_link, _max_frame_tc) \ + ((36 * \ + (IXGBE_B2BT(_max_frame_link) + \ + IXGBE_PFC_D + \ + (2 * IXGBE_CABLE_DC) + \ + (2 * IXGBE_ID) + \ + IXGBE_HD) / 25 + 1) + \ + 2 * IXGBE_B2BT(_max_frame_tc)) /* Calculate low threshold delay values */ -#define IXGBE_LOW_DV_X540(TC) (2 * IXGBE_B2BT(TC) + \ - (IXGBE_FILL_RATE * IXGBE_PCI_DELAY)) -#define IXGBE_LOW_DV(TC) (2 * IXGBE_LOW_DV_X540(TC)) +#define IXGBE_LOW_DV_X540(_max_frame_tc) \ + (2 * IXGBE_B2BT(_max_frame_tc) + \ + (36 * IXGBE_PCI_DELAY / 25) + 1) +#define IXGBE_LOW_DV(_max_frame_tc) \ + (2 * IXGBE_LOW_DV_X540(_max_frame_tc)) /* Software ATR hash keys */ #define IXGBE_ATR_BUCKET_HASH_KEY 0x3DAD14E2 @@ -2597,6 +2603,8 @@ enum ixgbe_sfp_type { ixgbe_sfp_type_da_act_lmt_core1 = 8, ixgbe_sfp_type_1g_cu_core0 = 9, ixgbe_sfp_type_1g_cu_core1 = 10, + ixgbe_sfp_type_1g_sx_core0 = 11, + ixgbe_sfp_type_1g_sx_core1 = 12, ixgbe_sfp_type_not_present = 0xFFFE, ixgbe_sfp_type_unknown = 0xFFFF }; @@ -2837,6 +2845,7 @@ struct ixgbe_mac_operations { s32 (*set_rar)(struct ixgbe_hw *, u32, u8 *, u32, u32); s32 (*clear_rar)(struct ixgbe_hw *, u32); s32 (*set_vmdq)(struct ixgbe_hw *, u32, u32); + s32 (*set_vmdq_san_mac)(struct ixgbe_hw *, u32); s32 (*clear_vmdq)(struct ixgbe_hw *, u32, u32); s32 (*init_rx_addrs)(struct ixgbe_hw *); s32 (*update_mc_addr_list)(struct ixgbe_hw *, struct net_device *); @@ -2912,6 +2921,7 @@ struct ixgbe_mac_info { bool orig_link_settings_stored; bool autotry_restart; u8 flags; + u8 san_mac_rar_index; struct ixgbe_thermal_sensor_data thermal_sensor_data; }; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c index f90ec078ece2..de4da5219b71 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c @@ -156,6 +156,9 @@ mac_reset_top: hw->mac.ops.set_rar(hw, hw->mac.num_rar_entries - 1, hw->mac.san_addr, 0, IXGBE_RAH_AV); + /* Save the SAN MAC RAR index */ + hw->mac.san_mac_rar_index = hw->mac.num_rar_entries - 1; + /* Reserve the last RAR for the SAN MAC address */ hw->mac.num_rar_entries--; } @@ -832,6 +835,7 @@ static struct ixgbe_mac_operations mac_ops_X540 = { .set_rar = &ixgbe_set_rar_generic, .clear_rar = &ixgbe_clear_rar_generic, .set_vmdq = &ixgbe_set_vmdq_generic, + .set_vmdq_san_mac = &ixgbe_set_vmdq_san_mac_generic, .clear_vmdq = &ixgbe_clear_vmdq_generic, .init_rx_addrs = &ixgbe_init_rx_addrs_generic, .update_mc_addr_list = &ixgbe_update_mc_addr_list_generic, diff --git a/drivers/net/ethernet/intel/ixgbevf/defines.h b/drivers/net/ethernet/intel/ixgbevf/defines.h index e09a6cc633bb..418af827b230 100644 --- a/drivers/net/ethernet/intel/ixgbevf/defines.h +++ b/drivers/net/ethernet/intel/ixgbevf/defines.h @@ -251,6 +251,7 @@ struct ixgbe_adv_tx_context_desc { #define IXGBE_ADVTXD_TUCMD_L4T_TCP 0x00000800 /* L4 Packet TYPE of TCP */ #define IXGBE_ADVTXD_TUCMD_L4T_SCTP 0x00001000 /* L4 Packet TYPE of SCTP */ #define IXGBE_ADVTXD_IDX_SHIFT 4 /* Adv desc Index shift */ +#define IXGBE_ADVTXD_CC 0x00000080 /* Check Context */ #define IXGBE_ADVTXD_POPTS_SHIFT 8 /* Adv desc POPTS shift */ #define IXGBE_ADVTXD_POPTS_IXSM (IXGBE_TXD_POPTS_IXSM << \ IXGBE_ADVTXD_POPTS_SHIFT) @@ -264,32 +265,9 @@ struct ixgbe_adv_tx_context_desc { /* Interrupt register bitmasks */ -/* Extended Interrupt Cause Read */ -#define IXGBE_EICR_RTX_QUEUE 0x0000FFFF /* RTx Queue Interrupt */ -#define IXGBE_EICR_MAILBOX 0x00080000 /* VF to PF Mailbox Interrupt */ -#define IXGBE_EICR_OTHER 0x80000000 /* Interrupt Cause Active */ - -/* Extended Interrupt Cause Set */ -#define IXGBE_EICS_RTX_QUEUE IXGBE_EICR_RTX_QUEUE /* RTx Queue Interrupt */ -#define IXGBE_EICS_MAILBOX IXGBE_EICR_MAILBOX /* VF to PF Mailbox Int */ -#define IXGBE_EICS_OTHER IXGBE_EICR_OTHER /* INT Cause Active */ - -/* Extended Interrupt Mask Set */ -#define IXGBE_EIMS_RTX_QUEUE IXGBE_EICR_RTX_QUEUE /* RTx Queue Interrupt */ -#define IXGBE_EIMS_MAILBOX IXGBE_EICR_MAILBOX /* VF to PF Mailbox Int */ -#define IXGBE_EIMS_OTHER IXGBE_EICR_OTHER /* INT Cause Active */ - -/* Extended Interrupt Mask Clear */ -#define IXGBE_EIMC_RTX_QUEUE IXGBE_EICR_RTX_QUEUE /* RTx Queue Interrupt */ -#define IXGBE_EIMC_MAILBOX IXGBE_EICR_MAILBOX /* VF to PF Mailbox Int */ -#define IXGBE_EIMC_OTHER IXGBE_EICR_OTHER /* INT Cause Active */ - -#define IXGBE_EIMS_ENABLE_MASK ( \ - IXGBE_EIMS_RTX_QUEUE | \ - IXGBE_EIMS_MAILBOX | \ - IXGBE_EIMS_OTHER) - #define IXGBE_EITR_CNT_WDIS 0x80000000 +#define IXGBE_MAX_EITR 0x00000FF8 +#define IXGBE_MIN_EITR 8 /* Error Codes */ #define IXGBE_ERR_INVALID_MAC_ADDR -1 diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c index e8dddf572d38..8f2070439b59 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c +++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c @@ -43,7 +43,6 @@ #define IXGBE_ALL_RAR_ENTRIES 16 -#ifdef ETHTOOL_GSTATS struct ixgbe_stats { char stat_string[ETH_GSTRING_LEN]; int sizeof_stat; @@ -75,21 +74,17 @@ static const struct ixgbe_stats ixgbe_gstrings_stats[] = { zero_base)}, {"tx_csum_offload_ctxt", IXGBEVF_STAT(hw_csum_tx_good, zero_base, zero_base)}, - {"rx_header_split", IXGBEVF_STAT(rx_hdr_split, zero_base, zero_base)}, }; #define IXGBE_QUEUE_STATS_LEN 0 #define IXGBE_GLOBAL_STATS_LEN ARRAY_SIZE(ixgbe_gstrings_stats) #define IXGBEVF_STATS_LEN (IXGBE_GLOBAL_STATS_LEN + IXGBE_QUEUE_STATS_LEN) -#endif /* ETHTOOL_GSTATS */ -#ifdef ETHTOOL_TEST static const char ixgbe_gstrings_test[][ETH_GSTRING_LEN] = { "Register test (offline)", "Link test (on/offline)" }; #define IXGBE_TEST_LEN (sizeof(ixgbe_gstrings_test) / ETH_GSTRING_LEN) -#endif /* ETHTOOL_TEST */ static int ixgbevf_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) @@ -289,13 +284,11 @@ static void ixgbevf_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) { struct ixgbevf_adapter *adapter = netdev_priv(netdev); - struct ixgbevf_ring *tx_ring = adapter->tx_ring; - struct ixgbevf_ring *rx_ring = adapter->rx_ring; ring->rx_max_pending = IXGBEVF_MAX_RXD; ring->tx_max_pending = IXGBEVF_MAX_TXD; - ring->rx_pending = rx_ring->count; - ring->tx_pending = tx_ring->count; + ring->rx_pending = adapter->rx_ring_count; + ring->tx_pending = adapter->tx_ring_count; } static int ixgbevf_set_ringparam(struct net_device *netdev, @@ -303,33 +296,28 @@ static int ixgbevf_set_ringparam(struct net_device *netdev, { struct ixgbevf_adapter *adapter = netdev_priv(netdev); struct ixgbevf_ring *tx_ring = NULL, *rx_ring = NULL; - int i, err = 0; u32 new_rx_count, new_tx_count; + int i, err = 0; if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending)) return -EINVAL; - new_rx_count = max(ring->rx_pending, (u32)IXGBEVF_MIN_RXD); - new_rx_count = min(new_rx_count, (u32)IXGBEVF_MAX_RXD); - new_rx_count = ALIGN(new_rx_count, IXGBE_REQ_RX_DESCRIPTOR_MULTIPLE); - - new_tx_count = max(ring->tx_pending, (u32)IXGBEVF_MIN_TXD); - new_tx_count = min(new_tx_count, (u32)IXGBEVF_MAX_TXD); + new_tx_count = max_t(u32, ring->tx_pending, IXGBEVF_MIN_TXD); + new_tx_count = min_t(u32, new_tx_count, IXGBEVF_MAX_TXD); new_tx_count = ALIGN(new_tx_count, IXGBE_REQ_TX_DESCRIPTOR_MULTIPLE); - if ((new_tx_count == adapter->tx_ring->count) && - (new_rx_count == adapter->rx_ring->count)) { - /* nothing to do */ + new_rx_count = max_t(u32, ring->rx_pending, IXGBEVF_MIN_RXD); + new_rx_count = min_t(u32, new_rx_count, IXGBEVF_MAX_RXD); + new_rx_count = ALIGN(new_rx_count, IXGBE_REQ_RX_DESCRIPTOR_MULTIPLE); + + /* if nothing to do return success */ + if ((new_tx_count == adapter->tx_ring_count) && + (new_rx_count == adapter->rx_ring_count)) return 0; - } while (test_and_set_bit(__IXGBEVF_RESETTING, &adapter->state)) - msleep(1); + usleep_range(1000, 2000); - /* - * If the adapter isn't up and running then just set the - * new parameters and scurry for the exits. - */ if (!netif_running(adapter->netdev)) { for (i = 0; i < adapter->num_tx_queues; i++) adapter->tx_ring[i].count = new_tx_count; @@ -340,82 +328,98 @@ static int ixgbevf_set_ringparam(struct net_device *netdev, goto clear_reset; } - tx_ring = kcalloc(adapter->num_tx_queues, - sizeof(struct ixgbevf_ring), GFP_KERNEL); - if (!tx_ring) { - err = -ENOMEM; - goto clear_reset; - } - - rx_ring = kcalloc(adapter->num_rx_queues, - sizeof(struct ixgbevf_ring), GFP_KERNEL); - if (!rx_ring) { - err = -ENOMEM; - goto err_rx_setup; - } - - ixgbevf_down(adapter); + if (new_tx_count != adapter->tx_ring_count) { + tx_ring = vmalloc(adapter->num_tx_queues * sizeof(*tx_ring)); + if (!tx_ring) { + err = -ENOMEM; + goto clear_reset; + } - memcpy(tx_ring, adapter->tx_ring, - adapter->num_tx_queues * sizeof(struct ixgbevf_ring)); - for (i = 0; i < adapter->num_tx_queues; i++) { - tx_ring[i].count = new_tx_count; - err = ixgbevf_setup_tx_resources(adapter, &tx_ring[i]); - if (err) { + for (i = 0; i < adapter->num_tx_queues; i++) { + /* clone ring and setup updated count */ + tx_ring[i] = adapter->tx_ring[i]; + tx_ring[i].count = new_tx_count; + err = ixgbevf_setup_tx_resources(adapter, &tx_ring[i]); + if (!err) + continue; while (i) { i--; - ixgbevf_free_tx_resources(adapter, - &tx_ring[i]); + ixgbevf_free_tx_resources(adapter, &tx_ring[i]); } - goto err_tx_ring_setup; + + vfree(tx_ring); + tx_ring = NULL; + + goto clear_reset; } - tx_ring[i].v_idx = adapter->tx_ring[i].v_idx; } - memcpy(rx_ring, adapter->rx_ring, - adapter->num_rx_queues * sizeof(struct ixgbevf_ring)); - for (i = 0; i < adapter->num_rx_queues; i++) { - rx_ring[i].count = new_rx_count; - err = ixgbevf_setup_rx_resources(adapter, &rx_ring[i]); - if (err) { + if (new_rx_count != adapter->rx_ring_count) { + rx_ring = vmalloc(adapter->num_rx_queues * sizeof(*rx_ring)); + if (!rx_ring) { + err = -ENOMEM; + goto clear_reset; + } + + for (i = 0; i < adapter->num_rx_queues; i++) { + /* clone ring and setup updated count */ + rx_ring[i] = adapter->rx_ring[i]; + rx_ring[i].count = new_rx_count; + err = ixgbevf_setup_rx_resources(adapter, &rx_ring[i]); + if (!err) + continue; while (i) { i--; - ixgbevf_free_rx_resources(adapter, - &rx_ring[i]); + ixgbevf_free_rx_resources(adapter, &rx_ring[i]); } - goto err_rx_ring_setup; + + vfree(rx_ring); + rx_ring = NULL; + + goto clear_reset; } - rx_ring[i].v_idx = adapter->rx_ring[i].v_idx; } - /* - * Only switch to new rings if all the prior allocations - * and ring setups have succeeded. - */ - kfree(adapter->tx_ring); - adapter->tx_ring = tx_ring; - adapter->tx_ring_count = new_tx_count; - - kfree(adapter->rx_ring); - adapter->rx_ring = rx_ring; - adapter->rx_ring_count = new_rx_count; + /* bring interface down to prepare for update */ + ixgbevf_down(adapter); - /* success! */ - ixgbevf_up(adapter); + /* Tx */ + if (tx_ring) { + for (i = 0; i < adapter->num_tx_queues; i++) { + ixgbevf_free_tx_resources(adapter, + &adapter->tx_ring[i]); + adapter->tx_ring[i] = tx_ring[i]; + } + adapter->tx_ring_count = new_tx_count; - goto clear_reset; + vfree(tx_ring); + tx_ring = NULL; + } -err_rx_ring_setup: - for(i = 0; i < adapter->num_tx_queues; i++) - ixgbevf_free_tx_resources(adapter, &tx_ring[i]); + /* Rx */ + if (rx_ring) { + for (i = 0; i < adapter->num_rx_queues; i++) { + ixgbevf_free_rx_resources(adapter, + &adapter->rx_ring[i]); + adapter->rx_ring[i] = rx_ring[i]; + } + adapter->rx_ring_count = new_rx_count; -err_tx_ring_setup: - kfree(rx_ring); + vfree(rx_ring); + rx_ring = NULL; + } -err_rx_setup: - kfree(tx_ring); + /* restore interface using new values */ + ixgbevf_up(adapter); clear_reset: + /* free Tx resources if Rx error is encountered */ + if (tx_ring) { + for (i = 0; i < adapter->num_tx_queues; i++) + ixgbevf_free_tx_resources(adapter, &tx_ring[i]); + vfree(tx_ring); + } + clear_bit(__IXGBEVF_RESETTING, &adapter->state); return err; } @@ -674,10 +678,8 @@ static int ixgbevf_nway_reset(struct net_device *netdev) { struct ixgbevf_adapter *adapter = netdev_priv(netdev); - if (netif_running(netdev)) { - if (!adapter->dev_closed) - ixgbevf_reinit_locked(adapter); - } + if (netif_running(netdev)) + ixgbevf_reinit_locked(adapter); return 0; } diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h index 0a1b99240d43..98cadb0c4dab 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h @@ -52,12 +52,12 @@ struct ixgbevf_tx_buffer { struct ixgbevf_rx_buffer { struct sk_buff *skb; dma_addr_t dma; - struct page *page; - dma_addr_t page_dma; - unsigned int page_offset; }; struct ixgbevf_ring { + struct ixgbevf_ring *next; + struct net_device *netdev; + struct device *dev; struct ixgbevf_adapter *adapter; /* backlink */ void *desc; /* descriptor ring memory */ dma_addr_t dma; /* phys. address of descriptor ring */ @@ -83,29 +83,9 @@ struct ixgbevf_ring { * offset associated with this ring, which is different * for DCB and RSS modes */ -#if defined(CONFIG_DCA) || defined(CONFIG_DCA_MODULE) - /* cpu for tx queue */ - int cpu; -#endif - - u64 v_idx; /* maps directly to the index for this ring in the hardware - * vector array, can also be used for finding the bit in EICR - * and friends that represents the vector for this ring */ - - u16 work_limit; /* max work per interrupt */ u16 rx_buf_len; }; -enum ixgbevf_ring_f_enum { - RING_F_NONE = 0, - RING_F_ARRAY_SIZE /* must be last in enum set */ -}; - -struct ixgbevf_ring_feature { - int indices; - int mask; -}; - /* How many Rx Buffers do we bundle into one write to the hardware ? */ #define IXGBEVF_RX_BUFFER_WRITE 16 /* Must be power of 2 */ @@ -120,8 +100,6 @@ struct ixgbevf_ring_feature { #define IXGBEVF_MIN_RXD 64 /* Supported Rx Buffer Sizes */ -#define IXGBEVF_RXBUFFER_64 64 /* Used for packet split */ -#define IXGBEVF_RXBUFFER_128 128 /* Used for packet split */ #define IXGBEVF_RXBUFFER_256 256 /* Used for packet split */ #define IXGBEVF_RXBUFFER_2048 2048 #define IXGBEVF_MAX_RXBUFFER 16384 /* largest size for single descriptor */ @@ -140,22 +118,42 @@ struct ixgbevf_ring_feature { #define IXGBE_TX_FLAGS_VLAN_PRIO_MASK 0x0000e000 #define IXGBE_TX_FLAGS_VLAN_SHIFT 16 +struct ixgbevf_ring_container { + struct ixgbevf_ring *ring; /* pointer to linked list of rings */ + unsigned int total_bytes; /* total bytes processed this int */ + unsigned int total_packets; /* total packets processed this int */ + u8 count; /* total number of rings in vector */ + u8 itr; /* current ITR setting for ring */ +}; + +/* iterator for handling rings in ring container */ +#define ixgbevf_for_each_ring(pos, head) \ + for (pos = (head).ring; pos != NULL; pos = pos->next) + /* MAX_MSIX_Q_VECTORS of these are allocated, * but we only use one per queue-specific vector. */ struct ixgbevf_q_vector { struct ixgbevf_adapter *adapter; + u16 v_idx; /* index of q_vector within array, also used for + * finding the bit in EICR and friends that + * represents the vector for this ring */ + u16 itr; /* Interrupt throttle rate written to EITR */ struct napi_struct napi; - DECLARE_BITMAP(rxr_idx, MAX_RX_QUEUES); /* Rx ring indices */ - DECLARE_BITMAP(txr_idx, MAX_TX_QUEUES); /* Tx ring indices */ - u8 rxr_count; /* Rx ring count assigned to this vector */ - u8 txr_count; /* Tx ring count assigned to this vector */ - u8 tx_itr; - u8 rx_itr; - u32 eitr; - int v_idx; /* vector index in list */ + struct ixgbevf_ring_container rx, tx; + char name[IFNAMSIZ + 9]; }; +/* + * microsecond values for various ITR rates shifted by 2 to fit itr register + * with the first 3 bits reserved 0 + */ +#define IXGBE_MIN_RSC_ITR 24 +#define IXGBE_100K_ITR 40 +#define IXGBE_20K_ITR 200 +#define IXGBE_10K_ITR 400 +#define IXGBE_8K_ITR 500 + /* Helper macros to switch between ints/sec and what the register uses. * And yes, it's the same math going both ways. The lowest value * supported by all of the ixgbe hardware is 8. @@ -168,12 +166,12 @@ struct ixgbevf_q_vector { ((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \ (R)->next_to_clean - (R)->next_to_use - 1) -#define IXGBE_RX_DESC_ADV(R, i) \ - (&(((union ixgbe_adv_rx_desc *)((R).desc))[i])) -#define IXGBE_TX_DESC_ADV(R, i) \ - (&(((union ixgbe_adv_tx_desc *)((R).desc))[i])) -#define IXGBE_TX_CTXTDESC_ADV(R, i) \ - (&(((struct ixgbe_adv_tx_context_desc *)((R).desc))[i])) +#define IXGBEVF_RX_DESC(R, i) \ + (&(((union ixgbe_adv_rx_desc *)((R)->desc))[i])) +#define IXGBEVF_TX_DESC(R, i) \ + (&(((union ixgbe_adv_tx_desc *)((R)->desc))[i])) +#define IXGBEVF_TX_CTXTDESC(R, i) \ + (&(((struct ixgbe_adv_tx_context_desc *)((R)->desc))[i])) #define IXGBE_MAX_JUMBO_FRAME_SIZE 16128 @@ -181,9 +179,8 @@ struct ixgbevf_q_vector { #define NON_Q_VECTORS (OTHER_VECTOR) #define MAX_MSIX_Q_VECTORS 2 -#define MAX_MSIX_COUNT 2 -#define MIN_MSIX_Q_VECTORS 2 +#define MIN_MSIX_Q_VECTORS 1 #define MIN_MSIX_COUNT (MIN_MSIX_Q_VECTORS + NON_Q_VECTORS) /* board specific private data structure */ @@ -193,12 +190,14 @@ struct ixgbevf_adapter { u16 bd_number; struct work_struct reset_task; struct ixgbevf_q_vector *q_vector[MAX_MSIX_Q_VECTORS]; - char name[MAX_MSIX_COUNT][IFNAMSIZ + 9]; /* Interrupt Throttle Rate */ - u32 itr_setting; - u16 eitr_low; - u16 eitr_high; + u16 rx_itr_setting; + u16 tx_itr_setting; + + /* interrupt masks */ + u32 eims_enable_mask; + u32 eims_other; /* TX */ struct ixgbevf_ring *tx_ring; /* One per active queue */ @@ -213,18 +212,13 @@ struct ixgbevf_adapter { /* RX */ struct ixgbevf_ring *rx_ring; /* One per active queue */ int num_rx_queues; - int num_rx_pools; /* == num_rx_queues in 82598 */ - int num_rx_queues_per_pool; /* 1 if 82598, can be many if 82599 */ u64 hw_csum_rx_error; u64 hw_rx_no_dma_resources; u64 hw_csum_rx_good; u64 non_eop_descs; int num_msix_vectors; - int max_msix_q_vectors; /* true count of q_vectors for device */ - struct ixgbevf_ring_feature ring_feature[RING_F_ARRAY_SIZE]; struct msix_entry *msix_entries; - u64 rx_hdr_split; u32 alloc_rx_page_failed; u32 alloc_rx_buff_failed; @@ -232,15 +226,8 @@ struct ixgbevf_adapter { * thus the additional *_CAPABLE flags. */ u32 flags; -#define IXGBE_FLAG_RX_CSUM_ENABLED (u32)(1) -#define IXGBE_FLAG_RX_1BUF_CAPABLE (u32)(1 << 1) -#define IXGBE_FLAG_RX_PS_CAPABLE (u32)(1 << 2) -#define IXGBE_FLAG_RX_PS_ENABLED (u32)(1 << 3) -#define IXGBE_FLAG_IN_NETPOLL (u32)(1 << 4) -#define IXGBE_FLAG_IMIR_ENABLED (u32)(1 << 5) -#define IXGBE_FLAG_MQ_CAPABLE (u32)(1 << 6) -#define IXGBE_FLAG_NEED_LINK_UPDATE (u32)(1 << 7) -#define IXGBE_FLAG_IN_WATCHDOG_TASK (u32)(1 << 8) +#define IXGBE_FLAG_IN_WATCHDOG_TASK (u32)(1) + /* OS defined structs */ struct net_device *netdev; struct pci_dev *pdev; @@ -254,18 +241,16 @@ struct ixgbevf_adapter { u32 eitr_param; unsigned long state; - u32 *config_space; u64 tx_busy; unsigned int tx_ring_count; unsigned int rx_ring_count; u32 link_speed; bool link_up; - unsigned long link_check_timeout; struct work_struct watchdog_task; - bool netdev_registered; - bool dev_closed; + + spinlock_t mbx_lock; }; enum ixbgevf_state_t { @@ -301,11 +286,8 @@ extern void ixgbevf_free_rx_resources(struct ixgbevf_adapter *, extern void ixgbevf_free_tx_resources(struct ixgbevf_adapter *, struct ixgbevf_ring *); extern void ixgbevf_update_stats(struct ixgbevf_adapter *adapter); - -#ifdef ETHTOOL_OPS_COMPAT extern int ethtool_ioctl(struct ifreq *ifr); -#endif extern void ixgbe_napi_add_all(struct ixgbevf_adapter *adapter); extern void ixgbe_napi_del_all(struct ixgbevf_adapter *adapter); diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index f69ec4288b10..60ef64587412 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -42,6 +42,7 @@ #include <linux/in.h> #include <linux/ip.h> #include <linux/tcp.h> +#include <linux/sctp.h> #include <linux/ipv6.h> #include <linux/slab.h> #include <net/checksum.h> @@ -97,9 +98,7 @@ module_param(debug, int, 0); MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); /* forward decls */ -static void ixgbevf_set_itr_msix(struct ixgbevf_q_vector *q_vector); -static void ixgbevf_write_eitr(struct ixgbevf_adapter *adapter, int v_idx, - u32 itr_reg); +static void ixgbevf_set_itr(struct ixgbevf_q_vector *q_vector); static inline void ixgbevf_release_rx_desc(struct ixgbe_hw *hw, struct ixgbevf_ring *rx_ring, @@ -115,7 +114,7 @@ static inline void ixgbevf_release_rx_desc(struct ixgbe_hw *hw, IXGBE_WRITE_REG(hw, IXGBE_VFRDT(rx_ring->reg_idx), val); } -/* +/** * ixgbevf_set_ivar - set IVAR registers - maps interrupt causes to vectors * @adapter: pointer to adapter struct * @direction: 0 for Rx, 1 for Tx, -1 for other causes @@ -146,18 +145,18 @@ static void ixgbevf_set_ivar(struct ixgbevf_adapter *adapter, s8 direction, } } -static void ixgbevf_unmap_and_free_tx_resource(struct ixgbevf_adapter *adapter, +static void ixgbevf_unmap_and_free_tx_resource(struct ixgbevf_ring *tx_ring, struct ixgbevf_tx_buffer *tx_buffer_info) { if (tx_buffer_info->dma) { if (tx_buffer_info->mapped_as_page) - dma_unmap_page(&adapter->pdev->dev, + dma_unmap_page(tx_ring->dev, tx_buffer_info->dma, tx_buffer_info->length, DMA_TO_DEVICE); else - dma_unmap_single(&adapter->pdev->dev, + dma_unmap_single(tx_ring->dev, tx_buffer_info->dma, tx_buffer_info->length, DMA_TO_DEVICE); @@ -175,38 +174,34 @@ static void ixgbevf_unmap_and_free_tx_resource(struct ixgbevf_adapter *adapter, #define IXGBE_MAX_DATA_PER_TXD (1 << IXGBE_MAX_TXD_PWR) /* Tx Descriptors needed, worst case */ -#define TXD_USE_COUNT(S) (((S) >> IXGBE_MAX_TXD_PWR) + \ - (((S) & (IXGBE_MAX_DATA_PER_TXD - 1)) ? 1 : 0)) -#ifdef MAX_SKB_FRAGS -#define DESC_NEEDED (TXD_USE_COUNT(IXGBE_MAX_DATA_PER_TXD) /* skb->data */ + \ - MAX_SKB_FRAGS * TXD_USE_COUNT(PAGE_SIZE) + 1) /* for context */ -#else -#define DESC_NEEDED TXD_USE_COUNT(IXGBE_MAX_DATA_PER_TXD) -#endif +#define TXD_USE_COUNT(S) DIV_ROUND_UP((S), IXGBE_MAX_DATA_PER_TXD) +#define DESC_NEEDED (MAX_SKB_FRAGS + 4) static void ixgbevf_tx_timeout(struct net_device *netdev); /** * ixgbevf_clean_tx_irq - Reclaim resources after transmit completes - * @adapter: board private structure + * @q_vector: board private structure * @tx_ring: tx ring to clean **/ -static bool ixgbevf_clean_tx_irq(struct ixgbevf_adapter *adapter, +static bool ixgbevf_clean_tx_irq(struct ixgbevf_q_vector *q_vector, struct ixgbevf_ring *tx_ring) { - struct net_device *netdev = adapter->netdev; - struct ixgbe_hw *hw = &adapter->hw; + struct ixgbevf_adapter *adapter = q_vector->adapter; union ixgbe_adv_tx_desc *tx_desc, *eop_desc; struct ixgbevf_tx_buffer *tx_buffer_info; unsigned int i, eop, count = 0; unsigned int total_bytes = 0, total_packets = 0; + if (test_bit(__IXGBEVF_DOWN, &adapter->state)) + return true; + i = tx_ring->next_to_clean; eop = tx_ring->tx_buffer_info[i].next_to_watch; - eop_desc = IXGBE_TX_DESC_ADV(*tx_ring, eop); + eop_desc = IXGBEVF_TX_DESC(tx_ring, eop); while ((eop_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD)) && - (count < tx_ring->work_limit)) { + (count < tx_ring->count)) { bool cleaned = false; rmb(); /* read buffer_info after eop_desc */ /* eop could change between read and DD-check */ @@ -214,7 +209,7 @@ static bool ixgbevf_clean_tx_irq(struct ixgbevf_adapter *adapter, goto cont_loop; for ( ; !cleaned; count++) { struct sk_buff *skb; - tx_desc = IXGBE_TX_DESC_ADV(*tx_ring, i); + tx_desc = IXGBEVF_TX_DESC(tx_ring, i); tx_buffer_info = &tx_ring->tx_buffer_info[i]; cleaned = (i == eop); skb = tx_buffer_info->skb; @@ -231,7 +226,7 @@ static bool ixgbevf_clean_tx_irq(struct ixgbevf_adapter *adapter, total_bytes += bytecount; } - ixgbevf_unmap_and_free_tx_resource(adapter, + ixgbevf_unmap_and_free_tx_resource(tx_ring, tx_buffer_info); tx_desc->wb.status = 0; @@ -243,37 +238,25 @@ static bool ixgbevf_clean_tx_irq(struct ixgbevf_adapter *adapter, cont_loop: eop = tx_ring->tx_buffer_info[i].next_to_watch; - eop_desc = IXGBE_TX_DESC_ADV(*tx_ring, eop); + eop_desc = IXGBEVF_TX_DESC(tx_ring, eop); } tx_ring->next_to_clean = i; #define TX_WAKE_THRESHOLD (DESC_NEEDED * 2) - if (unlikely(count && netif_carrier_ok(netdev) && + if (unlikely(count && netif_carrier_ok(tx_ring->netdev) && (IXGBE_DESC_UNUSED(tx_ring) >= TX_WAKE_THRESHOLD))) { /* Make sure that anybody stopping the queue after this * sees the new next_to_clean. */ smp_mb(); -#ifdef HAVE_TX_MQ - if (__netif_subqueue_stopped(netdev, tx_ring->queue_index) && - !test_bit(__IXGBEVF_DOWN, &adapter->state)) { - netif_wake_subqueue(netdev, tx_ring->queue_index); - ++adapter->restart_queue; - } -#else - if (netif_queue_stopped(netdev) && + if (__netif_subqueue_stopped(tx_ring->netdev, + tx_ring->queue_index) && !test_bit(__IXGBEVF_DOWN, &adapter->state)) { - netif_wake_queue(netdev); + netif_wake_subqueue(tx_ring->netdev, + tx_ring->queue_index); ++adapter->restart_queue; } -#endif - } - - /* re-arm the interrupt */ - if ((count >= tx_ring->work_limit) && - (!test_bit(__IXGBEVF_DOWN, &adapter->state))) { - IXGBE_WRITE_REG(hw, IXGBE_VTEICS, tx_ring->v_idx); } u64_stats_update_begin(&tx_ring->syncp); @@ -281,7 +264,7 @@ cont_loop: tx_ring->total_packets += total_packets; u64_stats_update_end(&tx_ring->syncp); - return count < tx_ring->work_limit; + return count < tx_ring->count; } /** @@ -301,13 +284,10 @@ static void ixgbevf_receive_skb(struct ixgbevf_q_vector *q_vector, bool is_vlan = (status & IXGBE_RXD_STAT_VP); u16 tag = le16_to_cpu(rx_desc->wb.upper.vlan); - if (is_vlan && test_bit(tag, adapter->active_vlans)) + if (is_vlan && test_bit(tag & VLAN_VID_MASK, adapter->active_vlans)) __vlan_hwaccel_put_tag(skb, tag); - if (!(adapter->flags & IXGBE_FLAG_IN_NETPOLL)) - napi_gro_receive(&q_vector->napi, skb); - else - netif_rx(skb); + napi_gro_receive(&q_vector->napi, skb); } /** @@ -317,12 +297,13 @@ static void ixgbevf_receive_skb(struct ixgbevf_q_vector *q_vector, * @skb: skb currently being received and modified **/ static inline void ixgbevf_rx_checksum(struct ixgbevf_adapter *adapter, + struct ixgbevf_ring *ring, u32 status_err, struct sk_buff *skb) { skb_checksum_none_assert(skb); /* Rx csum disabled */ - if (!(adapter->flags & IXGBE_FLAG_RX_CSUM_ENABLED)) + if (!(ring->netdev->features & NETIF_F_RXCSUM)) return; /* if IP and error */ @@ -357,52 +338,20 @@ static void ixgbevf_alloc_rx_buffers(struct ixgbevf_adapter *adapter, union ixgbe_adv_rx_desc *rx_desc; struct ixgbevf_rx_buffer *bi; struct sk_buff *skb; - unsigned int i; - unsigned int bufsz = rx_ring->rx_buf_len + NET_IP_ALIGN; + unsigned int i = rx_ring->next_to_use; - i = rx_ring->next_to_use; bi = &rx_ring->rx_buffer_info[i]; while (cleaned_count--) { - rx_desc = IXGBE_RX_DESC_ADV(*rx_ring, i); - - if (!bi->page_dma && - (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED)) { - if (!bi->page) { - bi->page = alloc_page(GFP_ATOMIC | __GFP_COLD); - if (!bi->page) { - adapter->alloc_rx_page_failed++; - goto no_buffers; - } - bi->page_offset = 0; - } else { - /* use a half page if we're re-using */ - bi->page_offset ^= (PAGE_SIZE / 2); - } - - bi->page_dma = dma_map_page(&pdev->dev, bi->page, - bi->page_offset, - (PAGE_SIZE / 2), - DMA_FROM_DEVICE); - } - + rx_desc = IXGBEVF_RX_DESC(rx_ring, i); skb = bi->skb; if (!skb) { - skb = netdev_alloc_skb(adapter->netdev, - bufsz); - + skb = netdev_alloc_skb_ip_align(rx_ring->netdev, + rx_ring->rx_buf_len); if (!skb) { adapter->alloc_rx_buff_failed++; goto no_buffers; } - - /* - * Make buffer alignment 2 beyond a 16 byte boundary - * this will result in a 16 byte aligned IP header after - * the 14 byte MAC header is removed - */ - skb_reserve(skb, NET_IP_ALIGN); - bi->skb = skb; } if (!bi->dma) { @@ -410,14 +359,7 @@ static void ixgbevf_alloc_rx_buffers(struct ixgbevf_adapter *adapter, rx_ring->rx_buf_len, DMA_FROM_DEVICE); } - /* Refresh the desc even if buffer_addrs didn't change because - * each write-back erases this info. */ - if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) { - rx_desc->read.pkt_addr = cpu_to_le64(bi->page_dma); - rx_desc->read.hdr_addr = cpu_to_le64(bi->dma); - } else { - rx_desc->read.pkt_addr = cpu_to_le64(bi->dma); - } + rx_desc->read.pkt_addr = cpu_to_le64(bi->dma); i++; if (i == rx_ring->count) @@ -428,36 +370,22 @@ static void ixgbevf_alloc_rx_buffers(struct ixgbevf_adapter *adapter, no_buffers: if (rx_ring->next_to_use != i) { rx_ring->next_to_use = i; - if (i-- == 0) - i = (rx_ring->count - 1); ixgbevf_release_rx_desc(&adapter->hw, rx_ring, i); } } static inline void ixgbevf_irq_enable_queues(struct ixgbevf_adapter *adapter, - u64 qmask) + u32 qmask) { - u32 mask; struct ixgbe_hw *hw = &adapter->hw; - mask = (qmask & 0xFFFFFFFF); - IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, mask); -} - -static inline u16 ixgbevf_get_hdr_info(union ixgbe_adv_rx_desc *rx_desc) -{ - return rx_desc->wb.lower.lo_dword.hs_rss.hdr_info; -} - -static inline u16 ixgbevf_get_pkt_info(union ixgbe_adv_rx_desc *rx_desc) -{ - return rx_desc->wb.lower.lo_dword.hs_rss.pkt_info; + IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, qmask); } static bool ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, struct ixgbevf_ring *rx_ring, - int *work_done, int work_to_do) + int budget) { struct ixgbevf_adapter *adapter = q_vector->adapter; struct pci_dev *pdev = adapter->pdev; @@ -466,36 +394,21 @@ static bool ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, struct sk_buff *skb; unsigned int i; u32 len, staterr; - u16 hdr_info; - bool cleaned = false; int cleaned_count = 0; unsigned int total_rx_bytes = 0, total_rx_packets = 0; i = rx_ring->next_to_clean; - rx_desc = IXGBE_RX_DESC_ADV(*rx_ring, i); + rx_desc = IXGBEVF_RX_DESC(rx_ring, i); staterr = le32_to_cpu(rx_desc->wb.upper.status_error); rx_buffer_info = &rx_ring->rx_buffer_info[i]; while (staterr & IXGBE_RXD_STAT_DD) { - u32 upper_len = 0; - if (*work_done >= work_to_do) + if (!budget) break; - (*work_done)++; + budget--; rmb(); /* read descriptor and rx_buffer_info after status DD */ - if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) { - hdr_info = le16_to_cpu(ixgbevf_get_hdr_info(rx_desc)); - len = (hdr_info & IXGBE_RXDADV_HDRBUFLEN_MASK) >> - IXGBE_RXDADV_HDRBUFLEN_SHIFT; - if (hdr_info & IXGBE_RXDADV_SPH) - adapter->rx_hdr_split++; - if (len > IXGBEVF_RX_HDR_SIZE) - len = IXGBEVF_RX_HDR_SIZE; - upper_len = le16_to_cpu(rx_desc->wb.upper.length); - } else { - len = le16_to_cpu(rx_desc->wb.upper.length); - } - cleaned = true; + len = le16_to_cpu(rx_desc->wb.upper.length); skb = rx_buffer_info->skb; prefetch(skb->data - NET_IP_ALIGN); rx_buffer_info->skb = NULL; @@ -508,46 +421,19 @@ static bool ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, skb_put(skb, len); } - if (upper_len) { - dma_unmap_page(&pdev->dev, rx_buffer_info->page_dma, - PAGE_SIZE / 2, DMA_FROM_DEVICE); - rx_buffer_info->page_dma = 0; - skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags, - rx_buffer_info->page, - rx_buffer_info->page_offset, - upper_len); - - if ((rx_ring->rx_buf_len > (PAGE_SIZE / 2)) || - (page_count(rx_buffer_info->page) != 1)) - rx_buffer_info->page = NULL; - else - get_page(rx_buffer_info->page); - - skb->len += upper_len; - skb->data_len += upper_len; - skb->truesize += upper_len; - } - i++; if (i == rx_ring->count) i = 0; - next_rxd = IXGBE_RX_DESC_ADV(*rx_ring, i); + next_rxd = IXGBEVF_RX_DESC(rx_ring, i); prefetch(next_rxd); cleaned_count++; next_buffer = &rx_ring->rx_buffer_info[i]; if (!(staterr & IXGBE_RXD_STAT_EOP)) { - if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) { - rx_buffer_info->skb = next_buffer->skb; - rx_buffer_info->dma = next_buffer->dma; - next_buffer->skb = skb; - next_buffer->dma = 0; - } else { - skb->next = next_buffer->skb; - skb->next->prev = skb; - } + skb->next = next_buffer->skb; + skb->next->prev = skb; adapter->non_eop_descs++; goto next_desc; } @@ -558,7 +444,7 @@ static bool ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, goto next_desc; } - ixgbevf_rx_checksum(adapter, staterr, skb); + ixgbevf_rx_checksum(adapter, rx_ring, staterr, skb); /* probably a little skewed due to removing CRC */ total_rx_bytes += skb->len; @@ -573,7 +459,7 @@ static bool ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, if (header_fixup_len < 14) skb_push(skb, header_fixup_len); } - skb->protocol = eth_type_trans(skb, adapter->netdev); + skb->protocol = eth_type_trans(skb, rx_ring->netdev); ixgbevf_receive_skb(q_vector, skb, staterr, rx_ring, rx_desc); @@ -605,95 +491,74 @@ next_desc: rx_ring->total_bytes += total_rx_bytes; u64_stats_update_end(&rx_ring->syncp); - return cleaned; + return !!budget; } /** - * ixgbevf_clean_rxonly - msix (aka one shot) rx clean routine + * ixgbevf_poll - NAPI polling calback * @napi: napi struct with our devices info in it * @budget: amount of work driver is allowed to do this pass, in packets * - * This function is optimized for cleaning one queue only on a single - * q_vector!!! + * This function will clean more than one or more rings associated with a + * q_vector. **/ -static int ixgbevf_clean_rxonly(struct napi_struct *napi, int budget) +static int ixgbevf_poll(struct napi_struct *napi, int budget) { struct ixgbevf_q_vector *q_vector = container_of(napi, struct ixgbevf_q_vector, napi); struct ixgbevf_adapter *adapter = q_vector->adapter; - struct ixgbevf_ring *rx_ring = NULL; - int work_done = 0; - long r_idx; - - r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues); - rx_ring = &(adapter->rx_ring[r_idx]); + struct ixgbevf_ring *ring; + int per_ring_budget; + bool clean_complete = true; - ixgbevf_clean_rx_irq(q_vector, rx_ring, &work_done, budget); + ixgbevf_for_each_ring(ring, q_vector->tx) + clean_complete &= ixgbevf_clean_tx_irq(q_vector, ring); - /* If all Rx work done, exit the polling mode */ - if (work_done < budget) { - napi_complete(napi); - if (adapter->itr_setting & 1) - ixgbevf_set_itr_msix(q_vector); - if (!test_bit(__IXGBEVF_DOWN, &adapter->state)) - ixgbevf_irq_enable_queues(adapter, rx_ring->v_idx); - } + /* attempt to distribute budget to each queue fairly, but don't allow + * the budget to go below 1 because we'll exit polling */ + if (q_vector->rx.count > 1) + per_ring_budget = max(budget/q_vector->rx.count, 1); + else + per_ring_budget = budget; + + ixgbevf_for_each_ring(ring, q_vector->rx) + clean_complete &= ixgbevf_clean_rx_irq(q_vector, ring, + per_ring_budget); + + /* If all work not completed, return budget and keep polling */ + if (!clean_complete) + return budget; + /* all work done, exit the polling mode */ + napi_complete(napi); + if (adapter->rx_itr_setting & 1) + ixgbevf_set_itr(q_vector); + if (!test_bit(__IXGBEVF_DOWN, &adapter->state)) + ixgbevf_irq_enable_queues(adapter, + 1 << q_vector->v_idx); - return work_done; + return 0; } /** - * ixgbevf_clean_rxonly_many - msix (aka one shot) rx clean routine - * @napi: napi struct with our devices info in it - * @budget: amount of work driver is allowed to do this pass, in packets - * - * This function will clean more than one rx queue associated with a - * q_vector. - **/ -static int ixgbevf_clean_rxonly_many(struct napi_struct *napi, int budget) + * ixgbevf_write_eitr - write VTEITR register in hardware specific way + * @q_vector: structure containing interrupt and ring information + */ +static void ixgbevf_write_eitr(struct ixgbevf_q_vector *q_vector) { - struct ixgbevf_q_vector *q_vector = - container_of(napi, struct ixgbevf_q_vector, napi); struct ixgbevf_adapter *adapter = q_vector->adapter; - struct ixgbevf_ring *rx_ring = NULL; - int work_done = 0, i; - long r_idx; - u64 enable_mask = 0; - - /* attempt to distribute budget to each queue fairly, but don't allow - * the budget to go below 1 because we'll exit polling */ - budget /= (q_vector->rxr_count ?: 1); - budget = max(budget, 1); - r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues); - for (i = 0; i < q_vector->rxr_count; i++) { - rx_ring = &(adapter->rx_ring[r_idx]); - ixgbevf_clean_rx_irq(q_vector, rx_ring, &work_done, budget); - enable_mask |= rx_ring->v_idx; - r_idx = find_next_bit(q_vector->rxr_idx, adapter->num_rx_queues, - r_idx + 1); - } - -#ifndef HAVE_NETDEV_NAPI_LIST - if (!netif_running(adapter->netdev)) - work_done = 0; - -#endif - r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues); - rx_ring = &(adapter->rx_ring[r_idx]); + struct ixgbe_hw *hw = &adapter->hw; + int v_idx = q_vector->v_idx; + u32 itr_reg = q_vector->itr & IXGBE_MAX_EITR; - /* If all Rx work done, exit the polling mode */ - if (work_done < budget) { - napi_complete(napi); - if (adapter->itr_setting & 1) - ixgbevf_set_itr_msix(q_vector); - if (!test_bit(__IXGBEVF_DOWN, &adapter->state)) - ixgbevf_irq_enable_queues(adapter, enable_mask); - } + /* + * set the WDIS bit to not clear the timer bits and cause an + * immediate assertion of the interrupt + */ + itr_reg |= IXGBE_EITR_CNT_WDIS; - return work_done; + IXGBE_WRITE_REG(hw, IXGBE_VTEITR(v_idx), itr_reg); } - /** * ixgbevf_configure_msix - Configure MSI-X hardware * @adapter: board private structure @@ -704,56 +569,49 @@ static int ixgbevf_clean_rxonly_many(struct napi_struct *napi, int budget) static void ixgbevf_configure_msix(struct ixgbevf_adapter *adapter) { struct ixgbevf_q_vector *q_vector; - struct ixgbe_hw *hw = &adapter->hw; - int i, j, q_vectors, v_idx, r_idx; - u32 mask; + int q_vectors, v_idx; q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; + adapter->eims_enable_mask = 0; /* * Populate the IVAR table and set the ITR values to the * corresponding register. */ for (v_idx = 0; v_idx < q_vectors; v_idx++) { + struct ixgbevf_ring *ring; q_vector = adapter->q_vector[v_idx]; - /* XXX for_each_set_bit(...) */ - r_idx = find_first_bit(q_vector->rxr_idx, - adapter->num_rx_queues); - - for (i = 0; i < q_vector->rxr_count; i++) { - j = adapter->rx_ring[r_idx].reg_idx; - ixgbevf_set_ivar(adapter, 0, j, v_idx); - r_idx = find_next_bit(q_vector->rxr_idx, - adapter->num_rx_queues, - r_idx + 1); - } - r_idx = find_first_bit(q_vector->txr_idx, - adapter->num_tx_queues); - - for (i = 0; i < q_vector->txr_count; i++) { - j = adapter->tx_ring[r_idx].reg_idx; - ixgbevf_set_ivar(adapter, 1, j, v_idx); - r_idx = find_next_bit(q_vector->txr_idx, - adapter->num_tx_queues, - r_idx + 1); + + ixgbevf_for_each_ring(ring, q_vector->rx) + ixgbevf_set_ivar(adapter, 0, ring->reg_idx, v_idx); + + ixgbevf_for_each_ring(ring, q_vector->tx) + ixgbevf_set_ivar(adapter, 1, ring->reg_idx, v_idx); + + if (q_vector->tx.ring && !q_vector->rx.ring) { + /* tx only vector */ + if (adapter->tx_itr_setting == 1) + q_vector->itr = IXGBE_10K_ITR; + else + q_vector->itr = adapter->tx_itr_setting; + } else { + /* rx or rx/tx vector */ + if (adapter->rx_itr_setting == 1) + q_vector->itr = IXGBE_20K_ITR; + else + q_vector->itr = adapter->rx_itr_setting; } - /* if this is a tx only vector halve the interrupt rate */ - if (q_vector->txr_count && !q_vector->rxr_count) - q_vector->eitr = (adapter->eitr_param >> 1); - else if (q_vector->rxr_count) - /* rx only */ - q_vector->eitr = adapter->eitr_param; + /* add q_vector eims value to global eims_enable_mask */ + adapter->eims_enable_mask |= 1 << v_idx; - ixgbevf_write_eitr(adapter, v_idx, q_vector->eitr); + ixgbevf_write_eitr(q_vector); } ixgbevf_set_ivar(adapter, -1, 1, v_idx); - - /* set up to autoclear timer, and the vectors */ - mask = IXGBE_EIMS_ENABLE_MASK; - mask &= ~IXGBE_EIMS_OTHER; - IXGBE_WRITE_REG(hw, IXGBE_VTEIAC, mask); + /* setup eims_other and add value to global eims_enable_mask */ + adapter->eims_other = 1 << v_idx; + adapter->eims_enable_mask |= adapter->eims_other; } enum latency_range { @@ -765,11 +623,8 @@ enum latency_range { /** * ixgbevf_update_itr - update the dynamic ITR value based on statistics - * @adapter: pointer to adapter - * @eitr: eitr setting (ints per sec) to give last timeslice - * @itr_setting: current throttle rate in ints/second - * @packets: the number of packets during this measurement interval - * @bytes: the number of bytes during this measurement interval + * @q_vector: structure containing interrupt and ring information + * @ring_container: structure containing ring performance data * * Stores a new ITR value based on packets and byte * counts during the last interrupt. The advantage of per interrupt @@ -779,17 +634,17 @@ enum latency_range { * on testing data as well as attempting to minimize response time * while increasing bulk throughput. **/ -static u8 ixgbevf_update_itr(struct ixgbevf_adapter *adapter, - u32 eitr, u8 itr_setting, - int packets, int bytes) +static void ixgbevf_update_itr(struct ixgbevf_q_vector *q_vector, + struct ixgbevf_ring_container *ring_container) { - unsigned int retval = itr_setting; + int bytes = ring_container->total_bytes; + int packets = ring_container->total_packets; u32 timepassed_us; u64 bytes_perint; + u8 itr_setting = ring_container->itr; if (packets == 0) - goto update_itr_done; - + return; /* simple throttlerate management * 0-20MB/s lowest (100000 ints/s) @@ -797,134 +652,77 @@ static u8 ixgbevf_update_itr(struct ixgbevf_adapter *adapter, * 100-1249MB/s bulk (8000 ints/s) */ /* what was last interrupt timeslice? */ - timepassed_us = 1000000/eitr; + timepassed_us = q_vector->itr >> 2; bytes_perint = bytes / timepassed_us; /* bytes/usec */ switch (itr_setting) { case lowest_latency: - if (bytes_perint > adapter->eitr_low) - retval = low_latency; + if (bytes_perint > 10) + itr_setting = low_latency; break; case low_latency: - if (bytes_perint > adapter->eitr_high) - retval = bulk_latency; - else if (bytes_perint <= adapter->eitr_low) - retval = lowest_latency; + if (bytes_perint > 20) + itr_setting = bulk_latency; + else if (bytes_perint <= 10) + itr_setting = lowest_latency; break; case bulk_latency: - if (bytes_perint <= adapter->eitr_high) - retval = low_latency; + if (bytes_perint <= 20) + itr_setting = low_latency; break; } -update_itr_done: - return retval; + /* clear work counters since we have the values we need */ + ring_container->total_bytes = 0; + ring_container->total_packets = 0; + + /* write updated itr to ring container */ + ring_container->itr = itr_setting; } -/** - * ixgbevf_write_eitr - write VTEITR register in hardware specific way - * @adapter: pointer to adapter struct - * @v_idx: vector index into q_vector array - * @itr_reg: new value to be written in *register* format, not ints/s - * - * This function is made to be called by ethtool and by the driver - * when it needs to update VTEITR registers at runtime. Hardware - * specific quirks/differences are taken care of here. - */ -static void ixgbevf_write_eitr(struct ixgbevf_adapter *adapter, int v_idx, - u32 itr_reg) +static void ixgbevf_set_itr(struct ixgbevf_q_vector *q_vector) { - struct ixgbe_hw *hw = &adapter->hw; - - itr_reg = EITR_INTS_PER_SEC_TO_REG(itr_reg); - - /* - * set the WDIS bit to not clear the timer bits and cause an - * immediate assertion of the interrupt - */ - itr_reg |= IXGBE_EITR_CNT_WDIS; + u32 new_itr = q_vector->itr; + u8 current_itr; - IXGBE_WRITE_REG(hw, IXGBE_VTEITR(v_idx), itr_reg); -} + ixgbevf_update_itr(q_vector, &q_vector->tx); + ixgbevf_update_itr(q_vector, &q_vector->rx); -static void ixgbevf_set_itr_msix(struct ixgbevf_q_vector *q_vector) -{ - struct ixgbevf_adapter *adapter = q_vector->adapter; - u32 new_itr; - u8 current_itr, ret_itr; - int i, r_idx, v_idx = q_vector->v_idx; - struct ixgbevf_ring *rx_ring, *tx_ring; - - r_idx = find_first_bit(q_vector->txr_idx, adapter->num_tx_queues); - for (i = 0; i < q_vector->txr_count; i++) { - tx_ring = &(adapter->tx_ring[r_idx]); - ret_itr = ixgbevf_update_itr(adapter, q_vector->eitr, - q_vector->tx_itr, - tx_ring->total_packets, - tx_ring->total_bytes); - /* if the result for this queue would decrease interrupt - * rate for this vector then use that result */ - q_vector->tx_itr = ((q_vector->tx_itr > ret_itr) ? - q_vector->tx_itr - 1 : ret_itr); - r_idx = find_next_bit(q_vector->txr_idx, adapter->num_tx_queues, - r_idx + 1); - } - - r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues); - for (i = 0; i < q_vector->rxr_count; i++) { - rx_ring = &(adapter->rx_ring[r_idx]); - ret_itr = ixgbevf_update_itr(adapter, q_vector->eitr, - q_vector->rx_itr, - rx_ring->total_packets, - rx_ring->total_bytes); - /* if the result for this queue would decrease interrupt - * rate for this vector then use that result */ - q_vector->rx_itr = ((q_vector->rx_itr > ret_itr) ? - q_vector->rx_itr - 1 : ret_itr); - r_idx = find_next_bit(q_vector->rxr_idx, adapter->num_rx_queues, - r_idx + 1); - } - - current_itr = max(q_vector->rx_itr, q_vector->tx_itr); + current_itr = max(q_vector->rx.itr, q_vector->tx.itr); switch (current_itr) { /* counts and packets in update_itr are dependent on these numbers */ case lowest_latency: - new_itr = 100000; + new_itr = IXGBE_100K_ITR; break; case low_latency: - new_itr = 20000; /* aka hwitr = ~200 */ + new_itr = IXGBE_20K_ITR; break; case bulk_latency: default: - new_itr = 8000; + new_itr = IXGBE_8K_ITR; break; } - if (new_itr != q_vector->eitr) { - u32 itr_reg; - - /* save the algorithm value here, not the smoothed one */ - q_vector->eitr = new_itr; + if (new_itr != q_vector->itr) { /* do an exponential smoothing */ - new_itr = ((q_vector->eitr * 90)/100) + ((new_itr * 10)/100); - itr_reg = EITR_INTS_PER_SEC_TO_REG(new_itr); - ixgbevf_write_eitr(adapter, v_idx, itr_reg); + new_itr = (10 * new_itr * q_vector->itr) / + ((9 * new_itr) + q_vector->itr); + + /* save the algorithm value here */ + q_vector->itr = new_itr; + + ixgbevf_write_eitr(q_vector); } } static irqreturn_t ixgbevf_msix_mbx(int irq, void *data) { - struct net_device *netdev = data; - struct ixgbevf_adapter *adapter = netdev_priv(netdev); + struct ixgbevf_adapter *adapter = data; struct ixgbe_hw *hw = &adapter->hw; - u32 eicr; u32 msg; bool got_ack = false; - eicr = IXGBE_READ_REG(hw, IXGBE_VTEICS); - IXGBE_WRITE_REG(hw, IXGBE_VTEICR, eicr); - if (!hw->mbx.ops.check_for_ack(hw)) got_ack = true; @@ -953,75 +751,24 @@ static irqreturn_t ixgbevf_msix_mbx(int irq, void *data) if (got_ack) hw->mbx.v2p_mailbox |= IXGBE_VFMAILBOX_PFACK; - return IRQ_HANDLED; -} - -static irqreturn_t ixgbevf_msix_clean_tx(int irq, void *data) -{ - struct ixgbevf_q_vector *q_vector = data; - struct ixgbevf_adapter *adapter = q_vector->adapter; - struct ixgbevf_ring *tx_ring; - int i, r_idx; - - if (!q_vector->txr_count) - return IRQ_HANDLED; - - r_idx = find_first_bit(q_vector->txr_idx, adapter->num_tx_queues); - for (i = 0; i < q_vector->txr_count; i++) { - tx_ring = &(adapter->tx_ring[r_idx]); - tx_ring->total_bytes = 0; - tx_ring->total_packets = 0; - ixgbevf_clean_tx_irq(adapter, tx_ring); - r_idx = find_next_bit(q_vector->txr_idx, adapter->num_tx_queues, - r_idx + 1); - } - - if (adapter->itr_setting & 1) - ixgbevf_set_itr_msix(q_vector); + IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, adapter->eims_other); return IRQ_HANDLED; } + /** - * ixgbevf_msix_clean_rx - single unshared vector rx clean (all queues) + * ixgbevf_msix_clean_rings - single unshared vector rx clean (all queues) * @irq: unused * @data: pointer to our q_vector struct for this interrupt vector **/ -static irqreturn_t ixgbevf_msix_clean_rx(int irq, void *data) +static irqreturn_t ixgbevf_msix_clean_rings(int irq, void *data) { struct ixgbevf_q_vector *q_vector = data; - struct ixgbevf_adapter *adapter = q_vector->adapter; - struct ixgbe_hw *hw = &adapter->hw; - struct ixgbevf_ring *rx_ring; - int r_idx; - int i; - - r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues); - for (i = 0; i < q_vector->rxr_count; i++) { - rx_ring = &(adapter->rx_ring[r_idx]); - rx_ring->total_bytes = 0; - rx_ring->total_packets = 0; - r_idx = find_next_bit(q_vector->rxr_idx, adapter->num_rx_queues, - r_idx + 1); - } - - if (!q_vector->rxr_count) - return IRQ_HANDLED; - - r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues); - rx_ring = &(adapter->rx_ring[r_idx]); - /* disable interrupts on this vector only */ - IXGBE_WRITE_REG(hw, IXGBE_VTEIMC, rx_ring->v_idx); - napi_schedule(&q_vector->napi); - - return IRQ_HANDLED; -} - -static irqreturn_t ixgbevf_msix_clean_many(int irq, void *data) -{ - ixgbevf_msix_clean_rx(irq, data); - ixgbevf_msix_clean_tx(irq, data); + /* EIAM disabled interrupts (on this vector) for us */ + if (q_vector->rx.ring || q_vector->tx.ring) + napi_schedule(&q_vector->napi); return IRQ_HANDLED; } @@ -1031,9 +778,9 @@ static inline void map_vector_to_rxq(struct ixgbevf_adapter *a, int v_idx, { struct ixgbevf_q_vector *q_vector = a->q_vector[v_idx]; - set_bit(r_idx, q_vector->rxr_idx); - q_vector->rxr_count++; - a->rx_ring[r_idx].v_idx = 1 << v_idx; + a->rx_ring[r_idx].next = q_vector->rx.ring; + q_vector->rx.ring = &a->rx_ring[r_idx]; + q_vector->rx.count++; } static inline void map_vector_to_txq(struct ixgbevf_adapter *a, int v_idx, @@ -1041,9 +788,9 @@ static inline void map_vector_to_txq(struct ixgbevf_adapter *a, int v_idx, { struct ixgbevf_q_vector *q_vector = a->q_vector[v_idx]; - set_bit(t_idx, q_vector->txr_idx); - q_vector->txr_count++; - a->tx_ring[t_idx].v_idx = 1 << v_idx; + a->tx_ring[t_idx].next = q_vector->tx.ring; + q_vector->tx.ring = &a->tx_ring[t_idx]; + q_vector->tx.count++; } /** @@ -1119,37 +866,30 @@ out: static int ixgbevf_request_msix_irqs(struct ixgbevf_adapter *adapter) { struct net_device *netdev = adapter->netdev; - irqreturn_t (*handler)(int, void *); - int i, vector, q_vectors, err; + int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; + int vector, err; int ri = 0, ti = 0; - /* Decrement for Other and TCP Timer vectors */ - q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - -#define SET_HANDLER(_v) (((_v)->rxr_count && (_v)->txr_count) \ - ? &ixgbevf_msix_clean_many : \ - (_v)->rxr_count ? &ixgbevf_msix_clean_rx : \ - (_v)->txr_count ? &ixgbevf_msix_clean_tx : \ - NULL) for (vector = 0; vector < q_vectors; vector++) { - handler = SET_HANDLER(adapter->q_vector[vector]); - - if (handler == &ixgbevf_msix_clean_rx) { - sprintf(adapter->name[vector], "%s-%s-%d", - netdev->name, "rx", ri++); - } else if (handler == &ixgbevf_msix_clean_tx) { - sprintf(adapter->name[vector], "%s-%s-%d", - netdev->name, "tx", ti++); - } else if (handler == &ixgbevf_msix_clean_many) { - sprintf(adapter->name[vector], "%s-%s-%d", - netdev->name, "TxRx", vector); + struct ixgbevf_q_vector *q_vector = adapter->q_vector[vector]; + struct msix_entry *entry = &adapter->msix_entries[vector]; + + if (q_vector->tx.ring && q_vector->rx.ring) { + snprintf(q_vector->name, sizeof(q_vector->name) - 1, + "%s-%s-%d", netdev->name, "TxRx", ri++); + ti++; + } else if (q_vector->rx.ring) { + snprintf(q_vector->name, sizeof(q_vector->name) - 1, + "%s-%s-%d", netdev->name, "rx", ri++); + } else if (q_vector->tx.ring) { + snprintf(q_vector->name, sizeof(q_vector->name) - 1, + "%s-%s-%d", netdev->name, "tx", ti++); } else { /* skip this unused q_vector */ continue; } - err = request_irq(adapter->msix_entries[vector].vector, - handler, 0, adapter->name[vector], - adapter->q_vector[vector]); + err = request_irq(entry->vector, &ixgbevf_msix_clean_rings, 0, + q_vector->name, q_vector); if (err) { hw_dbg(&adapter->hw, "request_irq failed for MSIX interrupt " @@ -1158,9 +898,8 @@ static int ixgbevf_request_msix_irqs(struct ixgbevf_adapter *adapter) } } - sprintf(adapter->name[vector], "%s:mbx", netdev->name); err = request_irq(adapter->msix_entries[vector].vector, - &ixgbevf_msix_mbx, 0, adapter->name[vector], netdev); + &ixgbevf_msix_mbx, 0, netdev->name, adapter); if (err) { hw_dbg(&adapter->hw, "request_irq for msix_mbx failed: %d\n", err); @@ -1170,9 +909,11 @@ static int ixgbevf_request_msix_irqs(struct ixgbevf_adapter *adapter) return 0; free_queue_irqs: - for (i = vector - 1; i >= 0; i--) - free_irq(adapter->msix_entries[--vector].vector, - &(adapter->q_vector[i])); + while (vector) { + vector--; + free_irq(adapter->msix_entries[vector].vector, + adapter->q_vector[vector]); + } pci_disable_msix(adapter->pdev); kfree(adapter->msix_entries); adapter->msix_entries = NULL; @@ -1185,11 +926,10 @@ static inline void ixgbevf_reset_q_vectors(struct ixgbevf_adapter *adapter) for (i = 0; i < q_vectors; i++) { struct ixgbevf_q_vector *q_vector = adapter->q_vector[i]; - bitmap_zero(q_vector->rxr_idx, MAX_RX_QUEUES); - bitmap_zero(q_vector->txr_idx, MAX_TX_QUEUES); - q_vector->rxr_count = 0; - q_vector->txr_count = 0; - q_vector->eitr = adapter->eitr_param; + q_vector->rx.ring = NULL; + q_vector->tx.ring = NULL; + q_vector->rx.count = 0; + q_vector->tx.count = 0; } } @@ -1215,17 +955,20 @@ static int ixgbevf_request_irq(struct ixgbevf_adapter *adapter) static void ixgbevf_free_irq(struct ixgbevf_adapter *adapter) { - struct net_device *netdev = adapter->netdev; int i, q_vectors; q_vectors = adapter->num_msix_vectors; - i = q_vectors - 1; - free_irq(adapter->msix_entries[i].vector, netdev); + free_irq(adapter->msix_entries[i].vector, adapter); i--; for (; i >= 0; i--) { + /* free only the irqs that were actually requested */ + if (!adapter->q_vector[i]->rx.ring && + !adapter->q_vector[i]->tx.ring) + continue; + free_irq(adapter->msix_entries[i].vector, adapter->q_vector[i]); } @@ -1239,10 +982,12 @@ static void ixgbevf_free_irq(struct ixgbevf_adapter *adapter) **/ static inline void ixgbevf_irq_disable(struct ixgbevf_adapter *adapter) { - int i; struct ixgbe_hw *hw = &adapter->hw; + int i; + IXGBE_WRITE_REG(hw, IXGBE_VTEIAM, 0); IXGBE_WRITE_REG(hw, IXGBE_VTEIMC, ~0); + IXGBE_WRITE_REG(hw, IXGBE_VTEIAC, 0); IXGBE_WRITE_FLUSH(hw); @@ -1254,23 +999,13 @@ static inline void ixgbevf_irq_disable(struct ixgbevf_adapter *adapter) * ixgbevf_irq_enable - Enable default interrupt generation settings * @adapter: board private structure **/ -static inline void ixgbevf_irq_enable(struct ixgbevf_adapter *adapter, - bool queues, bool flush) +static inline void ixgbevf_irq_enable(struct ixgbevf_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; - u32 mask; - u64 qmask; - - mask = (IXGBE_EIMS_ENABLE_MASK & ~IXGBE_EIMS_RTX_QUEUE); - qmask = ~0; - - IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, mask); - if (queues) - ixgbevf_irq_enable_queues(adapter, qmask); - - if (flush) - IXGBE_WRITE_FLUSH(hw); + IXGBE_WRITE_REG(hw, IXGBE_VTEIAM, adapter->eims_enable_mask); + IXGBE_WRITE_REG(hw, IXGBE_VTEIAC, adapter->eims_enable_mask); + IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, adapter->eims_enable_mask); } /** @@ -1320,29 +1055,14 @@ static void ixgbevf_configure_srrctl(struct ixgbevf_adapter *adapter, int index) srrctl = IXGBE_SRRCTL_DROP_EN; - if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) { - u16 bufsz = IXGBEVF_RXBUFFER_2048; - /* grow the amount we can receive on large page machines */ - if (bufsz < (PAGE_SIZE / 2)) - bufsz = (PAGE_SIZE / 2); - /* cap the bufsz at our largest descriptor size */ - bufsz = min((u16)IXGBEVF_MAX_RXBUFFER, bufsz); - - srrctl |= bufsz >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; - srrctl |= IXGBE_SRRCTL_DESCTYPE_HDR_SPLIT_ALWAYS; - srrctl |= ((IXGBEVF_RX_HDR_SIZE << - IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT) & - IXGBE_SRRCTL_BSIZEHDR_MASK); - } else { - srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF; + srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF; - if (rx_ring->rx_buf_len == MAXIMUM_ETHERNET_VLAN_SIZE) - srrctl |= IXGBEVF_RXBUFFER_2048 >> - IXGBE_SRRCTL_BSIZEPKT_SHIFT; - else - srrctl |= rx_ring->rx_buf_len >> - IXGBE_SRRCTL_BSIZEPKT_SHIFT; - } + if (rx_ring->rx_buf_len == MAXIMUM_ETHERNET_VLAN_SIZE) + srrctl |= IXGBEVF_RXBUFFER_2048 >> + IXGBE_SRRCTL_BSIZEPKT_SHIFT; + else + srrctl |= rx_ring->rx_buf_len >> + IXGBE_SRRCTL_BSIZEPKT_SHIFT; IXGBE_WRITE_REG(hw, IXGBE_VFSRRCTL(index), srrctl); } @@ -1362,36 +1082,12 @@ static void ixgbevf_configure_rx(struct ixgbevf_adapter *adapter) u32 rdlen; int rx_buf_len; - /* Decide whether to use packet split mode or not */ - if (netdev->mtu > ETH_DATA_LEN) { - if (adapter->flags & IXGBE_FLAG_RX_PS_CAPABLE) - adapter->flags |= IXGBE_FLAG_RX_PS_ENABLED; - else - adapter->flags &= ~IXGBE_FLAG_RX_PS_ENABLED; - } else { - if (adapter->flags & IXGBE_FLAG_RX_1BUF_CAPABLE) - adapter->flags &= ~IXGBE_FLAG_RX_PS_ENABLED; - else - adapter->flags |= IXGBE_FLAG_RX_PS_ENABLED; - } - - /* Set the RX buffer length according to the mode */ - if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) { - /* PSRTYPE must be initialized in 82599 */ - u32 psrtype = IXGBE_PSRTYPE_TCPHDR | - IXGBE_PSRTYPE_UDPHDR | - IXGBE_PSRTYPE_IPV4HDR | - IXGBE_PSRTYPE_IPV6HDR | - IXGBE_PSRTYPE_L2HDR; - IXGBE_WRITE_REG(hw, IXGBE_VFPSRTYPE, psrtype); - rx_buf_len = IXGBEVF_RX_HDR_SIZE; - } else { - IXGBE_WRITE_REG(hw, IXGBE_VFPSRTYPE, 0); - if (netdev->mtu <= ETH_DATA_LEN) - rx_buf_len = MAXIMUM_ETHERNET_VLAN_SIZE; - else - rx_buf_len = ALIGN(max_frame, 1024); - } + /* PSRTYPE must be initialized in 82599 */ + IXGBE_WRITE_REG(hw, IXGBE_VFPSRTYPE, 0); + if (netdev->mtu <= ETH_DATA_LEN) + rx_buf_len = MAXIMUM_ETHERNET_VLAN_SIZE; + else + rx_buf_len = ALIGN(max_frame, 1024); rdlen = adapter->rx_ring[0].count * sizeof(union ixgbe_adv_rx_desc); /* Setup the HW Rx Head and Tail Descriptor Pointers and @@ -1418,9 +1114,14 @@ static int ixgbevf_vlan_rx_add_vid(struct net_device *netdev, u16 vid) struct ixgbevf_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; + spin_lock(&adapter->mbx_lock); + /* add VID to filter table */ if (hw->mac.ops.set_vfta) hw->mac.ops.set_vfta(hw, vid, 0, true); + + spin_unlock(&adapter->mbx_lock); + set_bit(vid, adapter->active_vlans); return 0; @@ -1431,9 +1132,14 @@ static int ixgbevf_vlan_rx_kill_vid(struct net_device *netdev, u16 vid) struct ixgbevf_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; + spin_lock(&adapter->mbx_lock); + /* remove VID from filter table */ if (hw->mac.ops.set_vfta) hw->mac.ops.set_vfta(hw, vid, 0, false); + + spin_unlock(&adapter->mbx_lock); + clear_bit(vid, adapter->active_vlans); return 0; @@ -1488,11 +1194,15 @@ static void ixgbevf_set_rx_mode(struct net_device *netdev) struct ixgbevf_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; + spin_lock(&adapter->mbx_lock); + /* reprogram multicast list */ if (hw->mac.ops.update_mc_addr_list) hw->mac.ops.update_mc_addr_list(hw, netdev); ixgbevf_write_uc_addr_list(netdev); + + spin_unlock(&adapter->mbx_lock); } static void ixgbevf_napi_enable_all(struct ixgbevf_adapter *adapter) @@ -1502,15 +1212,8 @@ static void ixgbevf_napi_enable_all(struct ixgbevf_adapter *adapter) int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; for (q_idx = 0; q_idx < q_vectors; q_idx++) { - struct napi_struct *napi; q_vector = adapter->q_vector[q_idx]; - if (!q_vector->rxr_count) - continue; - napi = &q_vector->napi; - if (q_vector->rxr_count > 1) - napi->poll = &ixgbevf_clean_rxonly_many; - - napi_enable(napi); + napi_enable(&q_vector->napi); } } @@ -1522,8 +1225,6 @@ 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]; - if (!q_vector->rxr_count) - continue; napi_disable(&q_vector->napi); } } @@ -1541,9 +1242,8 @@ static void ixgbevf_configure(struct ixgbevf_adapter *adapter) ixgbevf_configure_rx(adapter); for (i = 0; i < adapter->num_rx_queues; i++) { struct ixgbevf_ring *ring = &adapter->rx_ring[i]; - ixgbevf_alloc_rx_buffers(adapter, ring, ring->count); - ring->next_to_use = ring->count - 1; - writel(ring->next_to_use, adapter->hw.hw_addr + ring->tail); + ixgbevf_alloc_rx_buffers(adapter, ring, + IXGBE_DESC_UNUSED(ring)); } } @@ -1647,6 +1347,8 @@ static void ixgbevf_up_complete(struct ixgbevf_adapter *adapter) ixgbevf_configure_msix(adapter); + spin_lock(&adapter->mbx_lock); + if (hw->mac.ops.set_rar) { if (is_valid_ether_addr(hw->mac.addr)) hw->mac.ops.set_rar(hw, 0, hw->mac.addr, 0); @@ -1658,6 +1360,8 @@ static void ixgbevf_up_complete(struct ixgbevf_adapter *adapter) msg[1] = netdev->mtu + ETH_HLEN + ETH_FCS_LEN; hw->mbx.ops.write_posted(hw, msg, 2); + spin_unlock(&adapter->mbx_lock); + clear_bit(__IXGBEVF_DOWN, &adapter->state); ixgbevf_napi_enable_all(adapter); @@ -1667,10 +1371,6 @@ static void ixgbevf_up_complete(struct ixgbevf_adapter *adapter) ixgbevf_save_reset_stats(adapter); ixgbevf_init_last_counter_stats(adapter); - /* bring the link up in the watchdog, this could race with our first - * link up interrupt but shouldn't be a problem */ - adapter->flags |= IXGBE_FLAG_NEED_LINK_UPDATE; - adapter->link_check_timeout = jiffies; mod_timer(&adapter->watchdog_timer, jiffies); } @@ -1685,7 +1385,7 @@ void ixgbevf_up(struct ixgbevf_adapter *adapter) /* clear any pending interrupts, may auto mask */ IXGBE_READ_REG(hw, IXGBE_VTEICR); - ixgbevf_irq_enable(adapter, true, true); + ixgbevf_irq_enable(adapter); } /** @@ -1723,14 +1423,6 @@ static void ixgbevf_clean_rx_ring(struct ixgbevf_adapter *adapter, dev_kfree_skb(this); } while (skb); } - if (!rx_buffer_info->page) - continue; - dma_unmap_page(&pdev->dev, rx_buffer_info->page_dma, - PAGE_SIZE / 2, DMA_FROM_DEVICE); - rx_buffer_info->page_dma = 0; - put_page(rx_buffer_info->page); - rx_buffer_info->page = NULL; - rx_buffer_info->page_offset = 0; } size = sizeof(struct ixgbevf_rx_buffer) * rx_ring->count; @@ -1767,7 +1459,7 @@ static void ixgbevf_clean_tx_ring(struct ixgbevf_adapter *adapter, for (i = 0; i < tx_ring->count; i++) { tx_buffer_info = &tx_ring->tx_buffer_info[i]; - ixgbevf_unmap_and_free_tx_resource(adapter, tx_buffer_info); + ixgbevf_unmap_and_free_tx_resource(tx_ring, tx_buffer_info); } size = sizeof(struct ixgbevf_tx_buffer) * tx_ring->count; @@ -1882,11 +1574,15 @@ void ixgbevf_reset(struct ixgbevf_adapter *adapter) struct ixgbe_hw *hw = &adapter->hw; struct net_device *netdev = adapter->netdev; + spin_lock(&adapter->mbx_lock); + if (hw->mac.ops.reset_hw(hw)) hw_dbg(hw, "PF still resetting\n"); else hw->mac.ops.init_hw(hw); + spin_unlock(&adapter->mbx_lock); + if (is_valid_ether_addr(adapter->hw.mac.addr)) { memcpy(netdev->dev_addr, adapter->hw.mac.addr, netdev->addr_len); @@ -1900,10 +1596,9 @@ static void ixgbevf_acquire_msix_vectors(struct ixgbevf_adapter *adapter, { int err, vector_threshold; - /* We'll want at least 3 (vector_threshold): - * 1) TxQ[0] Cleanup - * 2) RxQ[0] Cleanup - * 3) Other (Link Status Change, etc.) + /* We'll want at least 2 (vector_threshold): + * 1) TxQ[0] + RxQ[0] handler + * 2) Other (Link Status Change, etc.) */ vector_threshold = MIN_MSIX_COUNT; @@ -1942,8 +1637,8 @@ static void ixgbevf_acquire_msix_vectors(struct ixgbevf_adapter *adapter, } } -/* - * ixgbevf_set_num_queues: Allocate queues for device, feature dependent +/** + * ixgbevf_set_num_queues - Allocate queues for device, feature dependent * @adapter: board private structure to initialize * * This is the top level queue allocation routine. The order here is very @@ -1958,8 +1653,6 @@ static void ixgbevf_set_num_queues(struct ixgbevf_adapter *adapter) /* Start with base case */ adapter->num_rx_queues = 1; adapter->num_tx_queues = 1; - adapter->num_rx_pools = adapter->num_rx_queues; - adapter->num_rx_queues_per_pool = 1; } /** @@ -1988,12 +1681,16 @@ static int ixgbevf_alloc_queues(struct ixgbevf_adapter *adapter) adapter->tx_ring[i].count = adapter->tx_ring_count; adapter->tx_ring[i].queue_index = i; adapter->tx_ring[i].reg_idx = i; + adapter->tx_ring[i].dev = &adapter->pdev->dev; + adapter->tx_ring[i].netdev = adapter->netdev; } for (i = 0; i < adapter->num_rx_queues; i++) { adapter->rx_ring[i].count = adapter->rx_ring_count; adapter->rx_ring[i].queue_index = i; adapter->rx_ring[i].reg_idx = i; + adapter->rx_ring[i].dev = &adapter->pdev->dev; + adapter->rx_ring[i].netdev = adapter->netdev; } return 0; @@ -2020,10 +1717,12 @@ static int ixgbevf_set_interrupt_capability(struct ixgbevf_adapter *adapter) * It's easy to be greedy for MSI-X vectors, but it really * doesn't do us much good if we have a lot more vectors * than CPU's. So let's be conservative and only ask for - * (roughly) twice the number of vectors as there are CPU's. + * (roughly) the same number of vectors as there are CPU's. + * The default is to use pairs of vectors. */ - v_budget = min(adapter->num_rx_queues + adapter->num_tx_queues, - (int)(num_online_cpus() * 2)) + NON_Q_VECTORS; + v_budget = max(adapter->num_rx_queues, adapter->num_tx_queues); + v_budget = min_t(int, v_budget, num_online_cpus()); + v_budget += NON_Q_VECTORS; /* A failure in MSI-X entry allocation isn't fatal, but it does * mean we disable MSI-X capabilities of the adapter. */ @@ -2054,12 +1753,8 @@ static int ixgbevf_alloc_q_vectors(struct ixgbevf_adapter *adapter) { int q_idx, num_q_vectors; struct ixgbevf_q_vector *q_vector; - int napi_vectors; - int (*poll)(struct napi_struct *, int); num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - napi_vectors = adapter->num_rx_queues; - poll = &ixgbevf_clean_rxonly; for (q_idx = 0; q_idx < num_q_vectors; q_idx++) { q_vector = kzalloc(sizeof(struct ixgbevf_q_vector), GFP_KERNEL); @@ -2067,10 +1762,8 @@ static int ixgbevf_alloc_q_vectors(struct ixgbevf_adapter *adapter) goto err_out; q_vector->adapter = adapter; q_vector->v_idx = q_idx; - q_vector->eitr = adapter->eitr_param; - if (q_idx < napi_vectors) - netif_napi_add(adapter->netdev, &q_vector->napi, - (*poll), 64); + netif_napi_add(adapter->netdev, &q_vector->napi, + ixgbevf_poll, 64); adapter->q_vector[q_idx] = q_vector; } @@ -2216,21 +1909,17 @@ static int __devinit ixgbevf_sw_init(struct ixgbevf_adapter *adapter) adapter->netdev->addr_len); } - /* Enable dynamic interrupt throttling rates */ - adapter->eitr_param = 20000; - adapter->itr_setting = 1; + /* lock to protect mailbox accesses */ + spin_lock_init(&adapter->mbx_lock); - /* set defaults for eitr in MegaBytes */ - adapter->eitr_low = 10; - adapter->eitr_high = 20; + /* Enable dynamic interrupt throttling rates */ + adapter->rx_itr_setting = 1; + adapter->tx_itr_setting = 1; /* set default ring sizes */ adapter->tx_ring_count = IXGBEVF_DEFAULT_TXD; adapter->rx_ring_count = IXGBEVF_DEFAULT_RXD; - /* enable rx csum by default */ - adapter->flags |= IXGBE_FLAG_RX_CSUM_ENABLED; - set_bit(__IXGBEVF_DOWN, &adapter->state); return 0; @@ -2290,7 +1979,7 @@ static void ixgbevf_watchdog(unsigned long data) { struct ixgbevf_adapter *adapter = (struct ixgbevf_adapter *)data; struct ixgbe_hw *hw = &adapter->hw; - u64 eics = 0; + u32 eics = 0; int i; /* @@ -2304,11 +1993,11 @@ static void ixgbevf_watchdog(unsigned long data) /* get one bit for every active tx/rx interrupt vector */ for (i = 0; i < adapter->num_msix_vectors - NON_Q_VECTORS; i++) { struct ixgbevf_q_vector *qv = adapter->q_vector[i]; - if (qv->rxr_count || qv->txr_count) - eics |= (1 << i); + if (qv->rx.ring || qv->tx.ring) + eics |= 1 << i; } - IXGBE_WRITE_REG(hw, IXGBE_VTEICS, (u32)eics); + IXGBE_WRITE_REG(hw, IXGBE_VTEICS, eics); watchdog_short_circuit: schedule_work(&adapter->watchdog_task); @@ -2362,8 +2051,16 @@ static void ixgbevf_watchdog_task(struct work_struct *work) * no LSC interrupt */ if (hw->mac.ops.check_link) { - if ((hw->mac.ops.check_link(hw, &link_speed, - &link_up, false)) != 0) { + s32 need_reset; + + spin_lock(&adapter->mbx_lock); + + need_reset = hw->mac.ops.check_link(hw, &link_speed, + &link_up, false); + + spin_unlock(&adapter->mbx_lock); + + if (need_reset) { adapter->link_up = link_up; adapter->link_speed = link_speed; netif_carrier_off(netdev); @@ -2478,7 +2175,6 @@ int ixgbevf_setup_tx_resources(struct ixgbevf_adapter *adapter, tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; - tx_ring->work_limit = tx_ring->count; return 0; err: @@ -2682,7 +2378,7 @@ static int ixgbevf_open(struct net_device *netdev) if (err) goto err_req_irq; - ixgbevf_irq_enable(adapter, true, true); + ixgbevf_irq_enable(adapter); return 0; @@ -2724,172 +2420,153 @@ static int ixgbevf_close(struct net_device *netdev) return 0; } -static int ixgbevf_tso(struct ixgbevf_adapter *adapter, - struct ixgbevf_ring *tx_ring, - struct sk_buff *skb, u32 tx_flags, u8 *hdr_len) +static void ixgbevf_tx_ctxtdesc(struct ixgbevf_ring *tx_ring, + u32 vlan_macip_lens, u32 type_tucmd, + u32 mss_l4len_idx) { struct ixgbe_adv_tx_context_desc *context_desc; - unsigned int i; - int err; - struct ixgbevf_tx_buffer *tx_buffer_info; - u32 vlan_macip_lens = 0, type_tucmd_mlhl; - u32 mss_l4len_idx, l4len; + u16 i = tx_ring->next_to_use; - if (skb_is_gso(skb)) { - if (skb_header_cloned(skb)) { - err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); - if (err) - return err; - } - l4len = tcp_hdrlen(skb); - *hdr_len += l4len; - - if (skb->protocol == htons(ETH_P_IP)) { - struct iphdr *iph = ip_hdr(skb); - iph->tot_len = 0; - iph->check = 0; - tcp_hdr(skb)->check = ~csum_tcpudp_magic(iph->saddr, - iph->daddr, 0, - IPPROTO_TCP, - 0); - adapter->hw_tso_ctxt++; - } else if (skb_is_gso_v6(skb)) { - ipv6_hdr(skb)->payload_len = 0; - tcp_hdr(skb)->check = - ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - 0, IPPROTO_TCP, 0); - adapter->hw_tso6_ctxt++; - } + context_desc = IXGBEVF_TX_CTXTDESC(tx_ring, i); - i = tx_ring->next_to_use; + i++; + tx_ring->next_to_use = (i < tx_ring->count) ? i : 0; - tx_buffer_info = &tx_ring->tx_buffer_info[i]; - context_desc = IXGBE_TX_CTXTDESC_ADV(*tx_ring, i); - - /* VLAN MACLEN IPLEN */ - if (tx_flags & IXGBE_TX_FLAGS_VLAN) - vlan_macip_lens |= - (tx_flags & IXGBE_TX_FLAGS_VLAN_MASK); - vlan_macip_lens |= ((skb_network_offset(skb)) << - IXGBE_ADVTXD_MACLEN_SHIFT); - *hdr_len += skb_network_offset(skb); - vlan_macip_lens |= - (skb_transport_header(skb) - skb_network_header(skb)); - *hdr_len += - (skb_transport_header(skb) - skb_network_header(skb)); - context_desc->vlan_macip_lens = cpu_to_le32(vlan_macip_lens); - context_desc->seqnum_seed = 0; - - /* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */ - type_tucmd_mlhl = (IXGBE_TXD_CMD_DEXT | - IXGBE_ADVTXD_DTYP_CTXT); - - if (skb->protocol == htons(ETH_P_IP)) - type_tucmd_mlhl |= IXGBE_ADVTXD_TUCMD_IPV4; - type_tucmd_mlhl |= IXGBE_ADVTXD_TUCMD_L4T_TCP; - context_desc->type_tucmd_mlhl = cpu_to_le32(type_tucmd_mlhl); - - /* MSS L4LEN IDX */ - mss_l4len_idx = - (skb_shinfo(skb)->gso_size << IXGBE_ADVTXD_MSS_SHIFT); - mss_l4len_idx |= (l4len << IXGBE_ADVTXD_L4LEN_SHIFT); - /* use index 1 for TSO */ - mss_l4len_idx |= (1 << IXGBE_ADVTXD_IDX_SHIFT); - context_desc->mss_l4len_idx = cpu_to_le32(mss_l4len_idx); - - tx_buffer_info->time_stamp = jiffies; - tx_buffer_info->next_to_watch = i; + /* set bits to identify this as an advanced context descriptor */ + type_tucmd |= IXGBE_TXD_CMD_DEXT | IXGBE_ADVTXD_DTYP_CTXT; - i++; - if (i == tx_ring->count) - i = 0; - tx_ring->next_to_use = i; + context_desc->vlan_macip_lens = cpu_to_le32(vlan_macip_lens); + context_desc->seqnum_seed = 0; + context_desc->type_tucmd_mlhl = cpu_to_le32(type_tucmd); + context_desc->mss_l4len_idx = cpu_to_le32(mss_l4len_idx); +} - return true; +static int ixgbevf_tso(struct ixgbevf_ring *tx_ring, + struct sk_buff *skb, u32 tx_flags, u8 *hdr_len) +{ + u32 vlan_macip_lens, type_tucmd; + u32 mss_l4len_idx, l4len; + + if (!skb_is_gso(skb)) + return 0; + + if (skb_header_cloned(skb)) { + int err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); + if (err) + return err; } - return false; + /* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */ + type_tucmd = IXGBE_ADVTXD_TUCMD_L4T_TCP; + + if (skb->protocol == htons(ETH_P_IP)) { + struct iphdr *iph = ip_hdr(skb); + iph->tot_len = 0; + iph->check = 0; + tcp_hdr(skb)->check = ~csum_tcpudp_magic(iph->saddr, + iph->daddr, 0, + IPPROTO_TCP, + 0); + type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4; + } else if (skb_is_gso_v6(skb)) { + ipv6_hdr(skb)->payload_len = 0; + tcp_hdr(skb)->check = + ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + 0, IPPROTO_TCP, 0); + } + + /* compute header lengths */ + l4len = tcp_hdrlen(skb); + *hdr_len += l4len; + *hdr_len = skb_transport_offset(skb) + l4len; + + /* mss_l4len_id: use 1 as index for TSO */ + mss_l4len_idx = l4len << IXGBE_ADVTXD_L4LEN_SHIFT; + mss_l4len_idx |= skb_shinfo(skb)->gso_size << IXGBE_ADVTXD_MSS_SHIFT; + mss_l4len_idx |= 1 << IXGBE_ADVTXD_IDX_SHIFT; + + /* vlan_macip_lens: HEADLEN, MACLEN, VLAN tag */ + vlan_macip_lens = skb_network_header_len(skb); + vlan_macip_lens |= skb_network_offset(skb) << IXGBE_ADVTXD_MACLEN_SHIFT; + vlan_macip_lens |= tx_flags & IXGBE_TX_FLAGS_VLAN_MASK; + + ixgbevf_tx_ctxtdesc(tx_ring, vlan_macip_lens, + type_tucmd, mss_l4len_idx); + + return 1; } -static bool ixgbevf_tx_csum(struct ixgbevf_adapter *adapter, - struct ixgbevf_ring *tx_ring, +static bool ixgbevf_tx_csum(struct ixgbevf_ring *tx_ring, struct sk_buff *skb, u32 tx_flags) { - struct ixgbe_adv_tx_context_desc *context_desc; - unsigned int i; - struct ixgbevf_tx_buffer *tx_buffer_info; - u32 vlan_macip_lens = 0, type_tucmd_mlhl = 0; - if (skb->ip_summed == CHECKSUM_PARTIAL || - (tx_flags & IXGBE_TX_FLAGS_VLAN)) { - i = tx_ring->next_to_use; - tx_buffer_info = &tx_ring->tx_buffer_info[i]; - context_desc = IXGBE_TX_CTXTDESC_ADV(*tx_ring, i); - - if (tx_flags & IXGBE_TX_FLAGS_VLAN) - vlan_macip_lens |= (tx_flags & - IXGBE_TX_FLAGS_VLAN_MASK); - vlan_macip_lens |= (skb_network_offset(skb) << - IXGBE_ADVTXD_MACLEN_SHIFT); - if (skb->ip_summed == CHECKSUM_PARTIAL) - vlan_macip_lens |= (skb_transport_header(skb) - - skb_network_header(skb)); - - context_desc->vlan_macip_lens = cpu_to_le32(vlan_macip_lens); - context_desc->seqnum_seed = 0; - - type_tucmd_mlhl |= (IXGBE_TXD_CMD_DEXT | - IXGBE_ADVTXD_DTYP_CTXT); - - if (skb->ip_summed == CHECKSUM_PARTIAL) { - switch (skb->protocol) { - case __constant_htons(ETH_P_IP): - type_tucmd_mlhl |= IXGBE_ADVTXD_TUCMD_IPV4; - if (ip_hdr(skb)->protocol == IPPROTO_TCP) - type_tucmd_mlhl |= - IXGBE_ADVTXD_TUCMD_L4T_TCP; - break; - case __constant_htons(ETH_P_IPV6): - /* XXX what about other V6 headers?? */ - if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP) - type_tucmd_mlhl |= - IXGBE_ADVTXD_TUCMD_L4T_TCP; - break; - default: - if (unlikely(net_ratelimit())) { - pr_warn("partial checksum but " - "proto=%x!\n", skb->protocol); - } - break; - } - } - context_desc->type_tucmd_mlhl = cpu_to_le32(type_tucmd_mlhl); - /* use index zero for tx checksum offload */ - context_desc->mss_l4len_idx = 0; - tx_buffer_info->time_stamp = jiffies; - tx_buffer_info->next_to_watch = i; + u32 vlan_macip_lens = 0; + u32 mss_l4len_idx = 0; + u32 type_tucmd = 0; - adapter->hw_csum_tx_good++; - i++; - if (i == tx_ring->count) - i = 0; - tx_ring->next_to_use = i; + if (skb->ip_summed == CHECKSUM_PARTIAL) { + u8 l4_hdr = 0; + switch (skb->protocol) { + case __constant_htons(ETH_P_IP): + vlan_macip_lens |= skb_network_header_len(skb); + type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4; + l4_hdr = ip_hdr(skb)->protocol; + break; + case __constant_htons(ETH_P_IPV6): + vlan_macip_lens |= skb_network_header_len(skb); + l4_hdr = ipv6_hdr(skb)->nexthdr; + break; + default: + if (unlikely(net_ratelimit())) { + dev_warn(tx_ring->dev, + "partial checksum but proto=%x!\n", + skb->protocol); + } + break; + } - return true; + switch (l4_hdr) { + case IPPROTO_TCP: + type_tucmd |= IXGBE_ADVTXD_TUCMD_L4T_TCP; + mss_l4len_idx = tcp_hdrlen(skb) << + IXGBE_ADVTXD_L4LEN_SHIFT; + break; + case IPPROTO_SCTP: + type_tucmd |= IXGBE_ADVTXD_TUCMD_L4T_SCTP; + mss_l4len_idx = sizeof(struct sctphdr) << + IXGBE_ADVTXD_L4LEN_SHIFT; + break; + case IPPROTO_UDP: + mss_l4len_idx = sizeof(struct udphdr) << + IXGBE_ADVTXD_L4LEN_SHIFT; + break; + default: + if (unlikely(net_ratelimit())) { + dev_warn(tx_ring->dev, + "partial checksum but l4 proto=%x!\n", + l4_hdr); + } + break; + } } - return false; + /* vlan_macip_lens: MACLEN, VLAN tag */ + vlan_macip_lens |= skb_network_offset(skb) << IXGBE_ADVTXD_MACLEN_SHIFT; + vlan_macip_lens |= tx_flags & IXGBE_TX_FLAGS_VLAN_MASK; + + ixgbevf_tx_ctxtdesc(tx_ring, vlan_macip_lens, + type_tucmd, mss_l4len_idx); + + return (skb->ip_summed == CHECKSUM_PARTIAL); } -static int ixgbevf_tx_map(struct ixgbevf_adapter *adapter, - struct ixgbevf_ring *tx_ring, +static int ixgbevf_tx_map(struct ixgbevf_ring *tx_ring, struct sk_buff *skb, u32 tx_flags, unsigned int first) { - struct pci_dev *pdev = adapter->pdev; struct ixgbevf_tx_buffer *tx_buffer_info; unsigned int len; unsigned int total = skb->len; @@ -2908,12 +2585,11 @@ static int ixgbevf_tx_map(struct ixgbevf_adapter *adapter, tx_buffer_info->length = size; tx_buffer_info->mapped_as_page = false; - tx_buffer_info->dma = dma_map_single(&adapter->pdev->dev, + tx_buffer_info->dma = dma_map_single(tx_ring->dev, skb->data + offset, size, DMA_TO_DEVICE); - if (dma_mapping_error(&pdev->dev, tx_buffer_info->dma)) + if (dma_mapping_error(tx_ring->dev, tx_buffer_info->dma)) goto dma_error; - tx_buffer_info->time_stamp = jiffies; tx_buffer_info->next_to_watch = i; len -= size; @@ -2938,12 +2614,12 @@ static int ixgbevf_tx_map(struct ixgbevf_adapter *adapter, tx_buffer_info->length = size; tx_buffer_info->dma = - skb_frag_dma_map(&adapter->pdev->dev, frag, + skb_frag_dma_map(tx_ring->dev, frag, offset, size, DMA_TO_DEVICE); tx_buffer_info->mapped_as_page = true; - if (dma_mapping_error(&pdev->dev, tx_buffer_info->dma)) + if (dma_mapping_error(tx_ring->dev, + tx_buffer_info->dma)) goto dma_error; - tx_buffer_info->time_stamp = jiffies; tx_buffer_info->next_to_watch = i; len -= size; @@ -2964,15 +2640,15 @@ static int ixgbevf_tx_map(struct ixgbevf_adapter *adapter, i = i - 1; tx_ring->tx_buffer_info[i].skb = skb; tx_ring->tx_buffer_info[first].next_to_watch = i; + tx_ring->tx_buffer_info[first].time_stamp = jiffies; return count; dma_error: - dev_err(&pdev->dev, "TX DMA map failed\n"); + dev_err(tx_ring->dev, "TX DMA map failed\n"); /* clear timestamp and dma mappings for failed tx_buffer_info map */ tx_buffer_info->dma = 0; - tx_buffer_info->time_stamp = 0; tx_buffer_info->next_to_watch = 0; count--; @@ -2983,14 +2659,13 @@ dma_error: if (i < 0) i += tx_ring->count; tx_buffer_info = &tx_ring->tx_buffer_info[i]; - ixgbevf_unmap_and_free_tx_resource(adapter, tx_buffer_info); + ixgbevf_unmap_and_free_tx_resource(tx_ring, tx_buffer_info); } return count; } -static void ixgbevf_tx_queue(struct ixgbevf_adapter *adapter, - struct ixgbevf_ring *tx_ring, int tx_flags, +static void ixgbevf_tx_queue(struct ixgbevf_ring *tx_ring, int tx_flags, int count, u32 paylen, u8 hdr_len) { union ixgbe_adv_tx_desc *tx_desc = NULL; @@ -3007,28 +2682,31 @@ static void ixgbevf_tx_queue(struct ixgbevf_adapter *adapter, if (tx_flags & IXGBE_TX_FLAGS_VLAN) cmd_type_len |= IXGBE_ADVTXD_DCMD_VLE; + if (tx_flags & IXGBE_TX_FLAGS_CSUM) + olinfo_status |= IXGBE_ADVTXD_POPTS_TXSM; + if (tx_flags & IXGBE_TX_FLAGS_TSO) { cmd_type_len |= IXGBE_ADVTXD_DCMD_TSE; - olinfo_status |= IXGBE_TXD_POPTS_TXSM << - IXGBE_ADVTXD_POPTS_SHIFT; - /* use index 1 context for tso */ olinfo_status |= (1 << IXGBE_ADVTXD_IDX_SHIFT); if (tx_flags & IXGBE_TX_FLAGS_IPV4) - olinfo_status |= IXGBE_TXD_POPTS_IXSM << - IXGBE_ADVTXD_POPTS_SHIFT; + olinfo_status |= IXGBE_ADVTXD_POPTS_IXSM; + + } - } else if (tx_flags & IXGBE_TX_FLAGS_CSUM) - olinfo_status |= IXGBE_TXD_POPTS_TXSM << - IXGBE_ADVTXD_POPTS_SHIFT; + /* + * Check Context must be set if Tx switch is enabled, which it + * always is for case where virtual functions are running + */ + olinfo_status |= IXGBE_ADVTXD_CC; olinfo_status |= ((paylen - hdr_len) << IXGBE_ADVTXD_PAYLEN_SHIFT); i = tx_ring->next_to_use; while (count--) { tx_buffer_info = &tx_ring->tx_buffer_info[i]; - tx_desc = IXGBE_TX_DESC_ADV(*tx_ring, i); + tx_desc = IXGBEVF_TX_DESC(tx_ring, i); tx_desc->read.buffer_addr = cpu_to_le64(tx_buffer_info->dma); tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type_len | tx_buffer_info->length); @@ -3040,24 +2718,14 @@ static void ixgbevf_tx_queue(struct ixgbevf_adapter *adapter, tx_desc->read.cmd_type_len |= cpu_to_le32(txd_cmd); - /* - * 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(); - tx_ring->next_to_use = i; - writel(i, adapter->hw.hw_addr + tx_ring->tail); } -static int __ixgbevf_maybe_stop_tx(struct net_device *netdev, - struct ixgbevf_ring *tx_ring, int size) +static int __ixgbevf_maybe_stop_tx(struct ixgbevf_ring *tx_ring, int size) { - struct ixgbevf_adapter *adapter = netdev_priv(netdev); + struct ixgbevf_adapter *adapter = netdev_priv(tx_ring->netdev); - netif_stop_subqueue(netdev, tx_ring->queue_index); + netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index); /* Herbert's original patch had: * smp_mb__after_netif_stop_queue(); * but since that doesn't exist yet, just open code it. */ @@ -3069,17 +2737,16 @@ static int __ixgbevf_maybe_stop_tx(struct net_device *netdev, return -EBUSY; /* A reprieve! - use start_queue because it doesn't call schedule */ - netif_start_subqueue(netdev, tx_ring->queue_index); + netif_start_subqueue(tx_ring->netdev, tx_ring->queue_index); ++adapter->restart_queue; return 0; } -static int ixgbevf_maybe_stop_tx(struct net_device *netdev, - struct ixgbevf_ring *tx_ring, int size) +static int ixgbevf_maybe_stop_tx(struct ixgbevf_ring *tx_ring, int size) { if (likely(IXGBE_DESC_UNUSED(tx_ring) >= size)) return 0; - return __ixgbevf_maybe_stop_tx(netdev, tx_ring, size); + return __ixgbevf_maybe_stop_tx(tx_ring, size); } static int ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev) @@ -3090,54 +2757,66 @@ static int ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev) unsigned int tx_flags = 0; u8 hdr_len = 0; int r_idx = 0, tso; - int count = 0; - - unsigned int f; + u16 count = TXD_USE_COUNT(skb_headlen(skb)); +#if PAGE_SIZE > IXGBE_MAX_DATA_PER_TXD + unsigned short f; +#endif tx_ring = &adapter->tx_ring[r_idx]; + /* + * need: 1 descriptor per page * PAGE_SIZE/IXGBE_MAX_DATA_PER_TXD, + * + 1 desc for skb_headlen/IXGBE_MAX_DATA_PER_TXD, + * + 2 desc gap to keep tail from touching head, + * + 1 desc for context descriptor, + * otherwise try next time + */ +#if PAGE_SIZE > IXGBE_MAX_DATA_PER_TXD + for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) + count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size); +#else + count += skb_shinfo(skb)->nr_frags; +#endif + if (ixgbevf_maybe_stop_tx(tx_ring, count + 3)) { + adapter->tx_busy++; + return NETDEV_TX_BUSY; + } + if (vlan_tx_tag_present(skb)) { tx_flags |= vlan_tx_tag_get(skb); tx_flags <<= IXGBE_TX_FLAGS_VLAN_SHIFT; tx_flags |= IXGBE_TX_FLAGS_VLAN; } - /* four things can cause us to need a context descriptor */ - if (skb_is_gso(skb) || - (skb->ip_summed == CHECKSUM_PARTIAL) || - (tx_flags & IXGBE_TX_FLAGS_VLAN)) - count++; - - count += TXD_USE_COUNT(skb_headlen(skb)); - for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) - count += TXD_USE_COUNT(skb_frag_size(&skb_shinfo(skb)->frags[f])); - - if (ixgbevf_maybe_stop_tx(netdev, tx_ring, count)) { - adapter->tx_busy++; - return NETDEV_TX_BUSY; - } - first = tx_ring->next_to_use; if (skb->protocol == htons(ETH_P_IP)) tx_flags |= IXGBE_TX_FLAGS_IPV4; - tso = ixgbevf_tso(adapter, tx_ring, skb, tx_flags, &hdr_len); + tso = ixgbevf_tso(tx_ring, skb, tx_flags, &hdr_len); if (tso < 0) { dev_kfree_skb_any(skb); return NETDEV_TX_OK; } if (tso) - tx_flags |= IXGBE_TX_FLAGS_TSO; - else if (ixgbevf_tx_csum(adapter, tx_ring, skb, tx_flags) && - (skb->ip_summed == CHECKSUM_PARTIAL)) + tx_flags |= IXGBE_TX_FLAGS_TSO | IXGBE_TX_FLAGS_CSUM; + else if (ixgbevf_tx_csum(tx_ring, skb, tx_flags)) tx_flags |= IXGBE_TX_FLAGS_CSUM; - ixgbevf_tx_queue(adapter, tx_ring, tx_flags, - ixgbevf_tx_map(adapter, tx_ring, skb, tx_flags, first), + ixgbevf_tx_queue(tx_ring, tx_flags, + ixgbevf_tx_map(tx_ring, skb, tx_flags, first), skb->len, hdr_len); + /* + * 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(); + + writel(tx_ring->next_to_use, adapter->hw.hw_addr + tx_ring->tail); - ixgbevf_maybe_stop_tx(netdev, tx_ring, DESC_NEEDED); + ixgbevf_maybe_stop_tx(tx_ring, DESC_NEEDED); return NETDEV_TX_OK; } @@ -3161,9 +2840,13 @@ static int ixgbevf_set_mac(struct net_device *netdev, void *p) memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len); memcpy(hw->mac.addr, addr->sa_data, netdev->addr_len); + spin_lock(&adapter->mbx_lock); + if (hw->mac.ops.set_rar) hw->mac.ops.set_rar(hw, 0, hw->mac.addr, 0); + spin_unlock(&adapter->mbx_lock); + return 0; } @@ -3220,9 +2903,7 @@ static void ixgbevf_shutdown(struct pci_dev *pdev) ixgbevf_free_all_rx_resources(adapter); } -#ifdef CONFIG_PM pci_save_state(pdev); -#endif pci_disable_device(pdev); } @@ -3265,19 +2946,6 @@ static struct rtnl_link_stats64 *ixgbevf_get_stats(struct net_device *netdev, return stats; } -static int ixgbevf_set_features(struct net_device *netdev, - netdev_features_t features) -{ - struct ixgbevf_adapter *adapter = netdev_priv(netdev); - - if (features & NETIF_F_RXCSUM) - adapter->flags |= IXGBE_FLAG_RX_CSUM_ENABLED; - else - adapter->flags &= ~IXGBE_FLAG_RX_CSUM_ENABLED; - - return 0; -} - static const struct net_device_ops ixgbe_netdev_ops = { .ndo_open = ixgbevf_open, .ndo_stop = ixgbevf_close, @@ -3290,7 +2958,6 @@ static const struct net_device_ops ixgbe_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, - .ndo_set_features = ixgbevf_set_features, }; static void ixgbevf_assign_netdev_ops(struct net_device *dev) @@ -3350,12 +3017,8 @@ static int __devinit ixgbevf_probe(struct pci_dev *pdev, pci_set_master(pdev); -#ifdef HAVE_TX_MQ netdev = alloc_etherdev_mq(sizeof(struct ixgbevf_adapter), MAX_TX_QUEUES); -#else - netdev = alloc_etherdev(sizeof(struct ixgbevf_adapter)); -#endif if (!netdev) { err = -ENOMEM; goto err_alloc_etherdev; @@ -3396,10 +3059,6 @@ static int __devinit ixgbevf_probe(struct pci_dev *pdev, memcpy(&hw->mbx.ops, &ixgbevf_mbx_ops, sizeof(struct ixgbe_mbx_operations)); - adapter->flags &= ~IXGBE_FLAG_RX_PS_CAPABLE; - adapter->flags &= ~IXGBE_FLAG_RX_PS_ENABLED; - adapter->flags |= IXGBE_FLAG_RX_1BUF_CAPABLE; - /* setup the private structure */ err = ixgbevf_sw_init(adapter); if (err) @@ -3458,8 +3117,6 @@ static int __devinit ixgbevf_probe(struct pci_dev *pdev, if (err) goto err_register; - adapter->netdev_registered = true; - netif_carrier_off(netdev); ixgbevf_init_last_counter_stats(adapter); @@ -3469,8 +3126,6 @@ static int __devinit ixgbevf_probe(struct pci_dev *pdev, hw_dbg(hw, "MAC: %d\n", hw->mac.type); - hw_dbg(hw, "LRO is disabled\n"); - hw_dbg(hw, "Intel(R) 82599 Virtual Function\n"); cards_found++; return 0; @@ -3510,10 +3165,8 @@ static void __devexit ixgbevf_remove(struct pci_dev *pdev) cancel_work_sync(&adapter->reset_task); cancel_work_sync(&adapter->watchdog_task); - if (adapter->netdev_registered) { + if (netdev->reg_state == NETREG_REGISTERED) unregister_netdev(netdev); - adapter->netdev_registered = false; - } ixgbevf_reset_interrupt_capability(adapter); @@ -3530,12 +3183,92 @@ static void __devexit ixgbevf_remove(struct pci_dev *pdev) pci_disable_device(pdev); } +/** + * ixgbevf_io_error_detected - called when PCI error is detected + * @pdev: Pointer to PCI device + * @state: The current pci connection state + * + * This function is called after a PCI bus error affecting + * this device has been detected. + */ +static pci_ers_result_t ixgbevf_io_error_detected(struct pci_dev *pdev, + pci_channel_state_t state) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + + netif_device_detach(netdev); + + if (state == pci_channel_io_perm_failure) + return PCI_ERS_RESULT_DISCONNECT; + + if (netif_running(netdev)) + ixgbevf_down(adapter); + + pci_disable_device(pdev); + + /* Request a slot slot reset. */ + return PCI_ERS_RESULT_NEED_RESET; +} + +/** + * ixgbevf_io_slot_reset - called after the pci bus has been reset. + * @pdev: Pointer to PCI device + * + * Restart the card from scratch, as if from a cold-boot. Implementation + * resembles the first-half of the ixgbevf_resume routine. + */ +static pci_ers_result_t ixgbevf_io_slot_reset(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + + if (pci_enable_device_mem(pdev)) { + dev_err(&pdev->dev, + "Cannot re-enable PCI device after reset.\n"); + return PCI_ERS_RESULT_DISCONNECT; + } + + pci_set_master(pdev); + + ixgbevf_reset(adapter); + + return PCI_ERS_RESULT_RECOVERED; +} + +/** + * ixgbevf_io_resume - called when traffic can start flowing again. + * @pdev: Pointer to PCI device + * + * This callback is called when the error recovery driver tells us that + * its OK to resume normal operation. Implementation resembles the + * second-half of the ixgbevf_resume routine. + */ +static void ixgbevf_io_resume(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + + if (netif_running(netdev)) + ixgbevf_up(adapter); + + netif_device_attach(netdev); +} + +/* PCI Error Recovery (ERS) */ +static struct pci_error_handlers ixgbevf_err_handler = { + .error_detected = ixgbevf_io_error_detected, + .slot_reset = ixgbevf_io_slot_reset, + .resume = ixgbevf_io_resume, +}; + static struct pci_driver ixgbevf_driver = { .name = ixgbevf_driver_name, .id_table = ixgbevf_pci_tbl, .probe = ixgbevf_probe, .remove = __devexit_p(ixgbevf_remove), .shutdown = ixgbevf_shutdown, + .err_handler = &ixgbevf_err_handler }; /** |