diff options
Diffstat (limited to 'drivers/net/ethernet/intel/igb/igb_main.c')
| -rw-r--r-- | drivers/net/ethernet/intel/igb/igb_main.c | 987 |
1 files changed, 759 insertions, 228 deletions
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index b46bff8fe056..f8e32833226c 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -30,6 +30,8 @@ #include <linux/if_ether.h> #include <linux/aer.h> #include <linux/prefetch.h> +#include <linux/bpf.h> +#include <linux/bpf_trace.h> #include <linux/pm_runtime.h> #include <linux/etherdevice.h> #ifdef CONFIG_IGB_DCA @@ -38,12 +40,6 @@ #include <linux/i2c.h> #include "igb.h" -#define MAJ 5 -#define MIN 6 -#define BUILD 0 -#define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) "." \ -__stringify(BUILD) "-k" - enum queue_mode { QUEUE_MODE_STRICT_PRIORITY, QUEUE_MODE_STREAM_RESERVATION, @@ -55,7 +51,6 @@ enum tx_queue_prio { }; char igb_driver_name[] = "igb"; -char igb_driver_version[] = DRV_VERSION; static const char igb_driver_string[] = "Intel(R) Gigabit Ethernet Network Driver"; static const char igb_copyright[] = @@ -240,7 +235,6 @@ static struct pci_driver igb_driver = { MODULE_AUTHOR("Intel Corporation, <e1000-devel@lists.sourceforge.net>"); MODULE_DESCRIPTION("Intel(R) Gigabit Ethernet Network Driver"); MODULE_LICENSE("GPL v2"); -MODULE_VERSION(DRV_VERSION); #define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV|NETIF_MSG_PROBE|NETIF_MSG_LINK) static int debug = -1; @@ -322,7 +316,7 @@ static void igb_regdump(struct e1000_hw *hw, struct igb_reg_info *reginfo) break; case E1000_TDBAL(0): for (n = 0; n < 4; n++) - regs[n] = rd32(E1000_RDBAL(n)); + regs[n] = rd32(E1000_TDBAL(n)); break; case E1000_TDBAH(0): for (n = 0; n < 4; n++) @@ -362,7 +356,7 @@ static void igb_dump(struct igb_adapter *adapter) struct igb_reg_info *reginfo; struct igb_ring *tx_ring; union e1000_adv_tx_desc *tx_desc; - struct my_u0 { u64 a; u64 b; } *u0; + struct my_u0 { __le64 a; __le64 b; } *u0; struct igb_ring *rx_ring; union e1000_adv_rx_desc *rx_desc; u32 staterr; @@ -557,8 +551,7 @@ exit: /** * igb_get_i2c_data - Reads the I2C SDA data bit - * @hw: pointer to hardware structure - * @i2cctl: Current value of I2CCTL register + * @data: opaque pointer to adapter struct * * Returns the I2C data bit value **/ @@ -584,16 +577,15 @@ static void igb_set_i2c_data(void *data, int state) struct e1000_hw *hw = &adapter->hw; s32 i2cctl = rd32(E1000_I2CPARAMS); - if (state) - i2cctl |= E1000_I2C_DATA_OUT; - else + if (state) { + i2cctl |= E1000_I2C_DATA_OUT | E1000_I2C_DATA_OE_N; + } else { + i2cctl &= ~E1000_I2C_DATA_OE_N; i2cctl &= ~E1000_I2C_DATA_OUT; + } - i2cctl &= ~E1000_I2C_DATA_OE_N; - i2cctl |= E1000_I2C_CLK_OE_N; wr32(E1000_I2CPARAMS, i2cctl); wrfl(); - } /** @@ -610,8 +602,7 @@ static void igb_set_i2c_clk(void *data, int state) s32 i2cctl = rd32(E1000_I2CPARAMS); if (state) { - i2cctl |= E1000_I2C_CLK_OUT; - i2cctl &= ~E1000_I2C_CLK_OE_N; + i2cctl |= E1000_I2C_CLK_OUT | E1000_I2C_CLK_OE_N; } else { i2cctl &= ~E1000_I2C_CLK_OUT; i2cctl &= ~E1000_I2C_CLK_OE_N; @@ -666,8 +657,7 @@ static int __init igb_init_module(void) { int ret; - pr_info("%s - version %s\n", - igb_driver_string, igb_driver_version); + pr_info("%s\n", igb_driver_string); pr_info("%s\n", igb_copyright); #ifdef CONFIG_IGB_DCA @@ -720,14 +710,13 @@ static void igb_cache_ring_register(struct igb_adapter *adapter) adapter->rx_ring[i]->reg_idx = rbase_offset + Q_IDX_82576(i); } - /* Fall through */ + fallthrough; case e1000_82575: case e1000_82580: case e1000_i350: case e1000_i354: case e1000_i210: case e1000_i211: - /* Fall through */ default: for (; i < adapter->num_rx_queues; i++) adapter->rx_ring[i]->reg_idx = rbase_offset + i; @@ -940,6 +929,7 @@ static void igb_configure_msix(struct igb_adapter *adapter) **/ static int igb_request_msix(struct igb_adapter *adapter) { + unsigned int num_q_vectors = adapter->num_q_vectors; struct net_device *netdev = adapter->netdev; int i, err = 0, vector = 0, free_vector = 0; @@ -948,7 +938,13 @@ static int igb_request_msix(struct igb_adapter *adapter) if (err) goto err_out; - for (i = 0; i < adapter->num_q_vectors; i++) { + if (num_q_vectors > MAX_Q_VECTORS) { + num_q_vectors = MAX_Q_VECTORS; + dev_warn(&adapter->pdev->dev, + "The number of queue vectors (%d) is higher than max allowed (%d)\n", + adapter->num_q_vectors, MAX_Q_VECTORS); + } + for (i = 0; i < num_q_vectors; i++) { struct igb_q_vector *q_vector = adapter->q_vector[i]; vector++; @@ -1215,8 +1211,7 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter, return -ENOMEM; /* initialize NAPI */ - netif_napi_add(adapter->netdev, &q_vector->napi, - igb_poll, 64); + netif_napi_add(adapter->netdev, &q_vector->napi, igb_poll); /* tie q_vector and adapter together */ adapter->q_vector[v_idx] = q_vector; @@ -1687,14 +1682,15 @@ static bool is_any_txtime_enabled(struct igb_adapter *adapter) **/ static void igb_config_tx_modes(struct igb_adapter *adapter, int queue) { - struct igb_ring *ring = adapter->tx_ring[queue]; struct net_device *netdev = adapter->netdev; struct e1000_hw *hw = &adapter->hw; + struct igb_ring *ring; u32 tqavcc, tqavctrl; u16 value; WARN_ON(hw->mac.type != e1000_i210); WARN_ON(queue < 0 || queue > 1); + ring = adapter->tx_ring[queue]; /* If any of the Qav features is enabled, configure queues as SR and * with HIGH PRIO. If none is, then configure them with LOW PRIO and @@ -1930,8 +1926,8 @@ static void igb_setup_tx_mode(struct igb_adapter *adapter) */ val = rd32(E1000_TXPBS); val &= ~I210_TXPBSIZE_MASK; - val |= I210_TXPBSIZE_PB0_8KB | I210_TXPBSIZE_PB1_8KB | - I210_TXPBSIZE_PB2_4KB | I210_TXPBSIZE_PB3_4KB; + val |= I210_TXPBSIZE_PB0_6KB | I210_TXPBSIZE_PB1_6KB | + I210_TXPBSIZE_PB2_6KB | I210_TXPBSIZE_PB3_6KB; wr32(E1000_TXPBS, val); val = rd32(E1000_RXPBS); @@ -1948,7 +1944,7 @@ static void igb_setup_tx_mode(struct igb_adapter *adapter) * However, when we do so, no frame from queue 2 and 3 are * transmitted. It seems the MAX_TPKT_SIZE should not be great * or _equal_ to the buffer size programmed in TXPBS. For this - * reason, we set set MAX_ TPKT_SIZE to (4kB - 1) / 64. + * reason, we set MAX_ TPKT_SIZE to (4kB - 1) / 64. */ val = (4096 - 1) / 64; wr32(E1000_I210_DTXMXPKTSZ, val); @@ -2046,7 +2042,7 @@ static void igb_power_down_link(struct igb_adapter *adapter) } /** - * Detect and switch function for Media Auto Sense + * igb_check_swap_media - Detect and switch function for Media Auto Sense * @adapter: address of the board private structure **/ static void igb_check_swap_media(struct igb_adapter *adapter) @@ -2230,7 +2226,6 @@ void igb_down(struct igb_adapter *adapter) void igb_reinit_locked(struct igb_adapter *adapter) { - WARN_ON(in_interrupt()); while (test_and_set_bit(__IGB_RESETTING, &adapter->state)) usleep_range(1000, 2000); igb_down(adapter); @@ -2653,7 +2648,8 @@ static int igb_parse_cls_flower(struct igb_adapter *adapter, } input->filter.match_flags |= IGB_FILTER_FLAG_VLAN_TCI; - input->filter.vlan_tci = match.key->vlan_priority; + input->filter.vlan_tci = + (__force __be16)match.key->vlan_priority; } } @@ -2834,6 +2830,156 @@ static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type, } } +static int igb_xdp_setup(struct net_device *dev, struct netdev_bpf *bpf) +{ + int i, frame_size = dev->mtu + IGB_ETH_PKT_HDR_PAD; + struct igb_adapter *adapter = netdev_priv(dev); + struct bpf_prog *prog = bpf->prog, *old_prog; + bool running = netif_running(dev); + bool need_reset; + + /* verify igb ring attributes are sufficient for XDP */ + for (i = 0; i < adapter->num_rx_queues; i++) { + struct igb_ring *ring = adapter->rx_ring[i]; + + if (frame_size > igb_rx_bufsz(ring)) { + NL_SET_ERR_MSG_MOD(bpf->extack, + "The RX buffer size is too small for the frame size"); + netdev_warn(dev, "XDP RX buffer size %d is too small for the frame size %d\n", + igb_rx_bufsz(ring), frame_size); + return -EINVAL; + } + } + + old_prog = xchg(&adapter->xdp_prog, prog); + need_reset = (!!prog != !!old_prog); + + /* device is up and bpf is added/removed, must setup the RX queues */ + if (need_reset && running) { + igb_close(dev); + } else { + for (i = 0; i < adapter->num_rx_queues; i++) + (void)xchg(&adapter->rx_ring[i]->xdp_prog, + adapter->xdp_prog); + } + + if (old_prog) + bpf_prog_put(old_prog); + + /* bpf is just replaced, RXQ and MTU are already setup */ + if (!need_reset) + return 0; + + if (running) + igb_open(dev); + + return 0; +} + +static int igb_xdp(struct net_device *dev, struct netdev_bpf *xdp) +{ + switch (xdp->command) { + case XDP_SETUP_PROG: + return igb_xdp_setup(dev, xdp); + default: + return -EINVAL; + } +} + +static void igb_xdp_ring_update_tail(struct igb_ring *ring) +{ + /* Force memory writes to complete before letting h/w know there + * are new descriptors to fetch. + */ + wmb(); + writel(ring->next_to_use, ring->tail); +} + +static struct igb_ring *igb_xdp_tx_queue_mapping(struct igb_adapter *adapter) +{ + unsigned int r_idx = smp_processor_id(); + + if (r_idx >= adapter->num_tx_queues) + r_idx = r_idx % adapter->num_tx_queues; + + return adapter->tx_ring[r_idx]; +} + +static int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp) +{ + struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp); + int cpu = smp_processor_id(); + struct igb_ring *tx_ring; + struct netdev_queue *nq; + u32 ret; + + if (unlikely(!xdpf)) + return IGB_XDP_CONSUMED; + + /* During program transitions its possible adapter->xdp_prog is assigned + * but ring has not been configured yet. In this case simply abort xmit. + */ + tx_ring = adapter->xdp_prog ? igb_xdp_tx_queue_mapping(adapter) : NULL; + if (unlikely(!tx_ring)) + return IGB_XDP_CONSUMED; + + nq = txring_txq(tx_ring); + __netif_tx_lock(nq, cpu); + /* Avoid transmit queue timeout since we share it with the slow path */ + txq_trans_cond_update(nq); + ret = igb_xmit_xdp_ring(adapter, tx_ring, xdpf); + __netif_tx_unlock(nq); + + return ret; +} + +static int igb_xdp_xmit(struct net_device *dev, int n, + struct xdp_frame **frames, u32 flags) +{ + struct igb_adapter *adapter = netdev_priv(dev); + int cpu = smp_processor_id(); + struct igb_ring *tx_ring; + struct netdev_queue *nq; + int nxmit = 0; + int i; + + if (unlikely(test_bit(__IGB_DOWN, &adapter->state))) + return -ENETDOWN; + + if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) + return -EINVAL; + + /* During program transitions its possible adapter->xdp_prog is assigned + * but ring has not been configured yet. In this case simply abort xmit. + */ + tx_ring = adapter->xdp_prog ? igb_xdp_tx_queue_mapping(adapter) : NULL; + if (unlikely(!tx_ring)) + return -ENXIO; + + nq = txring_txq(tx_ring); + __netif_tx_lock(nq, cpu); + + /* Avoid transmit queue timeout since we share it with the slow path */ + txq_trans_cond_update(nq); + + for (i = 0; i < n; i++) { + struct xdp_frame *xdpf = frames[i]; + int err; + + err = igb_xmit_xdp_ring(adapter, tx_ring, xdpf); + if (err != IGB_XDP_TX) + break; + nxmit++; + } + + __netif_tx_unlock(nq); + + if (unlikely(flags & XDP_XMIT_FLUSH)) + igb_xdp_ring_update_tail(tx_ring); + + return nxmit; +} + static const struct net_device_ops igb_netdev_ops = { .ndo_open = igb_open, .ndo_stop = igb_close, @@ -2842,7 +2988,7 @@ static const struct net_device_ops igb_netdev_ops = { .ndo_set_rx_mode = igb_set_rx_mode, .ndo_set_mac_address = igb_set_mac, .ndo_change_mtu = igb_change_mtu, - .ndo_do_ioctl = igb_ioctl, + .ndo_eth_ioctl = igb_ioctl, .ndo_tx_timeout = igb_tx_timeout, .ndo_validate_addr = eth_validate_addr, .ndo_vlan_rx_add_vid = igb_vlan_rx_add_vid, @@ -2858,6 +3004,8 @@ static const struct net_device_ops igb_netdev_ops = { .ndo_fdb_add = igb_ndo_fdb_add, .ndo_features_check = igb_features_check, .ndo_setup_tc = igb_setup_tc, + .ndo_bpf = igb_xdp, + .ndo_xdp_xmit = igb_xdp_xmit, }; /** @@ -2882,7 +3030,7 @@ void igb_set_fw_version(struct igb_adapter *adapter) fw.invm_img_type); break; } - /* fall through */ + fallthrough; default: /* if option is rom valid, display its version too */ if (fw.or_valid) { @@ -2965,14 +3113,23 @@ static void igb_init_mas(struct igb_adapter *adapter) **/ static s32 igb_init_i2c(struct igb_adapter *adapter) { + struct e1000_hw *hw = &adapter->hw; s32 status = 0; + s32 i2cctl; /* I2C interface supported on i350 devices */ if (adapter->hw.mac.type != e1000_i350) return 0; + i2cctl = rd32(E1000_I2CPARAMS); + i2cctl |= E1000_I2CBB_EN + | E1000_I2C_CLK_OUT | E1000_I2C_CLK_OE_N + | E1000_I2C_DATA_OUT | E1000_I2C_DATA_OE_N; + wr32(E1000_I2CPARAMS, i2cctl); + wrfl(); + /* Initialize the i2c bus which is controlled by the registers. - * This bus will use the i2c_algo_bit structue that implements + * This bus will use the i2c_algo_bit structure that implements * the protocol through toggling of the 4 bits in the register. */ adapter->i2c_adap.owner = THIS_MODULE; @@ -2980,7 +3137,7 @@ static s32 igb_init_i2c(struct igb_adapter *adapter) adapter->i2c_algo.data = adapter; adapter->i2c_adap.algo_data = &adapter->i2c_algo; adapter->i2c_adap.dev.parent = &adapter->pdev->dev; - strlcpy(adapter->i2c_adap.name, "igb BB", + strscpy(adapter->i2c_adap.name, "igb BB", sizeof(adapter->i2c_adap.name)); status = i2c_bit_add_bus(&adapter->i2c_adap); return status; @@ -3006,14 +3163,14 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) s32 ret_val; static int global_quad_port_a; /* global quad port a indication */ const struct e1000_info *ei = igb_info_tbl[ent->driver_data]; - int err, pci_using_dac; u8 part_str[E1000_PBANUM_LENGTH]; + int err; /* Catch broken hardware that put the wrong VF device ID in * the PCIe SR-IOV capability. */ if (pdev->is_virtfn) { - WARN(1, KERN_ERR "%s (%hx:%hx) should not be a VF!\n", + WARN(1, KERN_ERR "%s (%x:%x) should not be a VF!\n", pci_name(pdev), pdev->vendor, pdev->device); return -EINVAL; } @@ -3022,17 +3179,11 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) return err; - pci_using_dac = 0; err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); - if (!err) { - pci_using_dac = 1; - } else { - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "No usable DMA configuration, aborting\n"); - goto err_dma; - } + if (err) { + dev_err(&pdev->dev, + "No usable DMA configuration, aborting\n"); + goto err_dma; } err = pci_request_mem_regions(pdev, igb_driver_name); @@ -3148,8 +3299,7 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (hw->mac.type >= e1000_i350) netdev->hw_features |= NETIF_F_NTUPLE; - if (pci_using_dac) - netdev->features |= NETIF_F_HIGHDMA; + netdev->features |= NETIF_F_HIGHDMA; netdev->vlan_features |= netdev->features | NETIF_F_TSO_MANGLEID; netdev->mpls_features |= NETIF_F_HW_CSUM; @@ -3205,7 +3355,7 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) dev_err(&pdev->dev, "NVM Read Error\n"); } - memcpy(netdev->dev_addr, hw->mac.addr, netdev->addr_len); + eth_hw_addr_set(netdev, hw->mac.addr); if (!is_valid_ether_addr(netdev->dev_addr)) { dev_err(&pdev->dev, "Invalid MAC Address\n"); @@ -3398,7 +3548,9 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) "Width x1" : "unknown"), netdev->dev_addr); } - if ((hw->mac.type >= e1000_i210 || + if ((hw->mac.type == e1000_82576 && + rd32(E1000_EECD) & E1000_EECD_PRES) || + (hw->mac.type >= e1000_i210 || igb_get_flash_presence_i210(hw))) { ret_val = igb_read_part_string(hw, part_str, E1000_PBANUM_LENGTH); @@ -3445,7 +3597,7 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) } } - dev_pm_set_driver_flags(&pdev->dev, DPM_FLAG_NEVER_SKIP); + dev_pm_set_driver_flags(&pdev->dev, DPM_FLAG_NO_DIRECT_COMPLETE); pm_runtime_put_noidle(&pdev->dev); return 0; @@ -3470,6 +3622,7 @@ err_sw_init: err_ioremap: free_netdev(netdev); err_alloc_etherdev: + pci_disable_pcie_error_reporting(pdev); pci_release_mem_regions(pdev); err_pci_reg: err_dma: @@ -3483,6 +3636,7 @@ static int igb_disable_sriov(struct pci_dev *pdev) struct net_device *netdev = pci_get_drvdata(pdev); struct igb_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; + unsigned long flags; /* reclaim resources allocated to VFs */ if (adapter->vf_data) { @@ -3495,12 +3649,13 @@ static int igb_disable_sriov(struct pci_dev *pdev) pci_disable_sriov(pdev); msleep(500); } - + spin_lock_irqsave(&adapter->vfs_lock, flags); kfree(adapter->vf_mac_list); adapter->vf_mac_list = NULL; kfree(adapter->vf_data); adapter->vf_data = NULL; adapter->vfs_allocated_count = 0; + spin_unlock_irqrestore(&adapter->vfs_lock, flags); wr32(E1000_IOVCTL, E1000_IOVCTL_REUSE_VFQ); wrfl(); msleep(100); @@ -3660,7 +3815,9 @@ static void igb_remove(struct pci_dev *pdev) igb_release_hw_control(adapter); #ifdef CONFIG_PCI_IOV + rtnl_lock(); igb_disable_sriov(pdev); + rtnl_unlock(); #endif unregister_netdev(netdev); @@ -3733,13 +3890,13 @@ unsigned int igb_get_max_rss_queues(struct igb_adapter *adapter) max_rss_queues = 1; break; } - /* fall through */ + fallthrough; case e1000_82576: if (!!adapter->vfs_allocated_count) { max_rss_queues = 2; break; } - /* fall through */ + fallthrough; case e1000_82580: case e1000_i354: default: @@ -3815,12 +3972,14 @@ static int igb_sw_init(struct igb_adapter *adapter) /* set default work limits */ adapter->tx_work_limit = IGB_DEFAULT_TX_WORK; - adapter->max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN + - VLAN_HLEN; + adapter->max_frame_size = netdev->mtu + IGB_ETH_PKT_HDR_PAD; adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN; spin_lock_init(&adapter->nfc_lock); spin_lock_init(&adapter->stats64_lock); + + /* init spinlock to avoid concurrency of VF resources */ + spin_lock_init(&adapter->vfs_lock); #ifdef CONFIG_PCI_IOV switch (hw->mac.type) { case e1000_82576: @@ -3876,8 +4035,9 @@ static int igb_sw_init(struct igb_adapter *adapter) } /** - * igb_open - Called when a network interface is made active + * __igb_open - Called when a network interface is made active * @netdev: network interface device structure + * @resuming: indicates whether we are in a resume call * * Returns 0 on success, negative value on failure * @@ -3993,8 +4153,9 @@ int igb_open(struct net_device *netdev) } /** - * igb_close - Disables a network interface + * __igb_close - Disables a network interface * @netdev: network interface device structure + * @suspending: indicates we are in a suspend call * * Returns 0, this is not allowed to fail * @@ -4188,8 +4349,20 @@ static void igb_configure_tx(struct igb_adapter *adapter) **/ int igb_setup_rx_resources(struct igb_ring *rx_ring) { + struct igb_adapter *adapter = netdev_priv(rx_ring->netdev); struct device *dev = rx_ring->dev; - int size; + int size, res; + + /* XDP RX-queue info */ + if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); + res = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, + rx_ring->queue_index, 0); + if (res < 0) { + dev_err(dev, "Failed to register xdp_rxq index %u\n", + rx_ring->queue_index); + return res; + } size = sizeof(struct igb_rx_buffer) * rx_ring->count; @@ -4210,9 +4383,12 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring) rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; + rx_ring->xdp_prog = adapter->xdp_prog; + return 0; err: + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); vfree(rx_ring->rx_buffer_info); rx_ring->rx_buffer_info = NULL; dev_err(dev, "Unable to allocate memory for the Rx descriptor ring\n"); @@ -4328,8 +4504,7 @@ static void igb_setup_mrqc(struct igb_adapter *adapter) else mrqc |= E1000_MRQC_ENABLE_VMDQ; } else { - if (hw->mac.type != e1000_i211) - mrqc |= E1000_MRQC_ENABLE_RSS_MQ; + mrqc |= E1000_MRQC_ENABLE_RSS_MQ; } igb_vmm_control(adapter); @@ -4514,6 +4689,10 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, int reg_idx = ring->reg_idx; u32 rxdctl = 0; + xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); + WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + MEM_TYPE_PAGE_SHARED, NULL)); + /* disable the queue */ wr32(E1000_RXDCTL(reg_idx), 0); @@ -4646,8 +4825,11 @@ static void igb_clean_tx_ring(struct igb_ring *tx_ring) while (i != tx_ring->next_to_use) { union e1000_adv_tx_desc *eop_desc, *tx_desc; - /* Free all the Tx ring sk_buffs */ - dev_kfree_skb_any(tx_buffer->skb); + /* Free all the Tx ring sk_buffs or xdp frames */ + if (tx_buffer->type == IGB_TYPE_SKB) + dev_kfree_skb_any(tx_buffer->skb); + else + xdp_return_frame(tx_buffer->xdpf); /* unmap skb header data */ dma_unmap_single(tx_ring->dev, @@ -4678,6 +4860,8 @@ static void igb_clean_tx_ring(struct igb_ring *tx_ring) DMA_TO_DEVICE); } + tx_buffer->next_to_watch = NULL; + /* move us one more past the eop_desc for start of next pkt */ tx_buffer++; i++; @@ -4718,6 +4902,8 @@ void igb_free_rx_resources(struct igb_ring *rx_ring) { igb_clean_rx_ring(rx_ring); + rx_ring->xdp_prog = NULL; + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); vfree(rx_ring->rx_buffer_info); rx_ring->rx_buffer_info = NULL; @@ -4818,7 +5004,7 @@ static int igb_set_mac(struct net_device *netdev, void *p) if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; - memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len); + eth_hw_addr_set(netdev, addr->sa_data); memcpy(hw->mac.addr, addr->sa_data, netdev->addr_len); /* set the correct pool for the new PF MAC address in entry 0 */ @@ -4878,14 +5064,14 @@ static int igb_vlan_promisc_enable(struct igb_adapter *adapter) /* VLAN filtering needed for VLAN prio filter */ if (adapter->netdev->features & NETIF_F_NTUPLE) break; - /* fall through */ + fallthrough; case e1000_82576: case e1000_82580: case e1000_i354: /* VLAN filtering needed for pool filtering */ if (adapter->vfs_allocated_count) break; - /* fall through */ + fallthrough; default: return 1; } @@ -5165,7 +5351,7 @@ bool igb_has_link(struct igb_adapter *adapter) case e1000_media_type_copper: if (!hw->mac.get_link_status) return true; - /* fall through */ + fallthrough; case e1000_media_type_internal_serdes: hw->mac.ops.check_for_link(hw); link_active = !hw->mac.get_link_status; @@ -5229,7 +5415,7 @@ static void igb_check_lvmmc(struct igb_adapter *adapter) /** * igb_watchdog - Timer Call-back - * @data: pointer to adapter cast into an unsigned long + * @t: pointer to timer_list containing our private info pointer **/ static void igb_watchdog(struct timer_list *t) { @@ -5328,7 +5514,8 @@ static void igb_watchdog_task(struct work_struct *work) break; } - if (adapter->link_speed != SPEED_1000) + if (adapter->link_speed != SPEED_1000 || + !hw->phy.ops.read_reg) goto no_wait; /* wait for Remote receiver status OK */ @@ -5697,7 +5884,7 @@ static void igb_tx_ctxtdesc(struct igb_ring *tx_ring, */ if (tx_ring->launchtime_enable) { ts = ktime_to_timespec64(first->skb->tstamp); - first->skb->tstamp = ktime_set(0, 0); + skb_txtime_consumed(first->skb); context_desc->seqnum_seed = cpu_to_le32(ts.tv_nsec / 32); } else { context_desc->seqnum_seed = 0; @@ -5799,15 +5986,6 @@ static int igb_tso(struct igb_ring *tx_ring, return 1; } -static inline bool igb_ipv6_csum_is_sctp(struct sk_buff *skb) -{ - unsigned int offset = 0; - - ipv6_find_hdr(skb, &offset, IPPROTO_SCTP, NULL, NULL); - - return offset == skb_checksum_start_offset(skb); -} - static void igb_tx_csum(struct igb_ring *tx_ring, struct igb_tx_buffer *first) { struct sk_buff *skb = first->skb; @@ -5825,19 +6003,16 @@ csum_failed: switch (skb->csum_offset) { case offsetof(struct tcphdr, check): type_tucmd = E1000_ADVTXD_TUCMD_L4T_TCP; - /* fall through */ + fallthrough; case offsetof(struct udphdr, check): break; case offsetof(struct sctphdr, checksum): /* validate that this is actually an SCTP request */ - if (((first->protocol == htons(ETH_P_IP)) && - (ip_hdr(skb)->protocol == IPPROTO_SCTP)) || - ((first->protocol == htons(ETH_P_IPV6)) && - igb_ipv6_csum_is_sctp(skb))) { + if (skb_csum_is_sctp(skb)) { type_tucmd = E1000_ADVTXD_TUCMD_L4T_SCTP; break; } - /* fall through */ + fallthrough; default: skb_checksum_help(skb); goto csum_failed; @@ -6087,6 +6262,114 @@ dma_error: return -1; } +int igb_xmit_xdp_ring(struct igb_adapter *adapter, + struct igb_ring *tx_ring, + struct xdp_frame *xdpf) +{ + struct skb_shared_info *sinfo = xdp_get_shared_info_from_frame(xdpf); + u8 nr_frags = unlikely(xdp_frame_has_frags(xdpf)) ? sinfo->nr_frags : 0; + u16 count, i, index = tx_ring->next_to_use; + struct igb_tx_buffer *tx_head = &tx_ring->tx_buffer_info[index]; + struct igb_tx_buffer *tx_buffer = tx_head; + union e1000_adv_tx_desc *tx_desc = IGB_TX_DESC(tx_ring, index); + u32 len = xdpf->len, cmd_type, olinfo_status; + void *data = xdpf->data; + + count = TXD_USE_COUNT(len); + for (i = 0; i < nr_frags; i++) + count += TXD_USE_COUNT(skb_frag_size(&sinfo->frags[i])); + + if (igb_maybe_stop_tx(tx_ring, count + 3)) + return IGB_XDP_CONSUMED; + + i = 0; + /* record the location of the first descriptor for this packet */ + tx_head->bytecount = xdp_get_frame_len(xdpf); + tx_head->type = IGB_TYPE_XDP; + tx_head->gso_segs = 1; + tx_head->xdpf = xdpf; + + olinfo_status = tx_head->bytecount << E1000_ADVTXD_PAYLEN_SHIFT; + /* 82575 requires a unique index per ring */ + if (test_bit(IGB_RING_FLAG_TX_CTX_IDX, &tx_ring->flags)) + olinfo_status |= tx_ring->reg_idx << 4; + tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status); + + for (;;) { + dma_addr_t dma; + + dma = dma_map_single(tx_ring->dev, data, len, DMA_TO_DEVICE); + if (dma_mapping_error(tx_ring->dev, dma)) + goto unmap; + + /* record length, and DMA address */ + dma_unmap_len_set(tx_buffer, len, len); + dma_unmap_addr_set(tx_buffer, dma, dma); + + /* put descriptor type bits */ + cmd_type = E1000_ADVTXD_DTYP_DATA | E1000_ADVTXD_DCMD_DEXT | + E1000_ADVTXD_DCMD_IFCS | len; + + tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type); + tx_desc->read.buffer_addr = cpu_to_le64(dma); + + tx_buffer->protocol = 0; + + if (++index == tx_ring->count) + index = 0; + + if (i == nr_frags) + break; + + tx_buffer = &tx_ring->tx_buffer_info[index]; + tx_desc = IGB_TX_DESC(tx_ring, index); + tx_desc->read.olinfo_status = 0; + + data = skb_frag_address(&sinfo->frags[i]); + len = skb_frag_size(&sinfo->frags[i]); + i++; + } + tx_desc->read.cmd_type_len |= cpu_to_le32(IGB_TXD_DCMD); + + netdev_tx_sent_queue(txring_txq(tx_ring), tx_head->bytecount); + /* set the timestamp */ + tx_head->time_stamp = jiffies; + + /* Avoid any potential race with xdp_xmit and cleanup */ + smp_wmb(); + + /* set next_to_watch value indicating a packet is present */ + tx_head->next_to_watch = tx_desc; + tx_ring->next_to_use = index; + + /* Make sure there is space in the ring for the next send. */ + igb_maybe_stop_tx(tx_ring, DESC_NEEDED); + + if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) + writel(index, tx_ring->tail); + + return IGB_XDP_TX; + +unmap: + for (;;) { + tx_buffer = &tx_ring->tx_buffer_info[index]; + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + if (tx_buffer == tx_head) + break; + + if (!index) + index += tx_ring->count; + index--; + } + + return IGB_XDP_CONSUMED; +} + netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, struct igb_ring *tx_ring) { @@ -6115,6 +6398,7 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, /* record the location of the first descriptor for this packet */ first = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + first->type = IGB_TYPE_SKB; first->skb = skb; first->bytecount = skb->len; first->gso_segs = 1; @@ -6202,8 +6486,9 @@ static netdev_tx_t igb_xmit_frame(struct sk_buff *skb, /** * igb_tx_timeout - Respond to a Tx Hang * @netdev: network interface device structure + * @txqueue: number of the Tx queue that hung (unused) **/ -static void igb_tx_timeout(struct net_device *netdev, unsigned int txqueue) +static void igb_tx_timeout(struct net_device *netdev, unsigned int __always_unused txqueue) { struct igb_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; @@ -6224,9 +6509,18 @@ static void igb_reset_task(struct work_struct *work) struct igb_adapter *adapter; adapter = container_of(work, struct igb_adapter, reset_task); + rtnl_lock(); + /* If we're already down or resetting, just bail */ + if (test_bit(__IGB_DOWN, &adapter->state) || + test_bit(__IGB_RESETTING, &adapter->state)) { + rtnl_unlock(); + return; + } + igb_dump(adapter); netdev_err(adapter->netdev, "Reset adapter\n"); igb_reinit_locked(adapter); + rtnl_unlock(); } /** @@ -6255,7 +6549,22 @@ static void igb_get_stats64(struct net_device *netdev, static int igb_change_mtu(struct net_device *netdev, int new_mtu) { struct igb_adapter *adapter = netdev_priv(netdev); - int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; + int max_frame = new_mtu + IGB_ETH_PKT_HDR_PAD; + + if (adapter->xdp_prog) { + int i; + + for (i = 0; i < adapter->num_rx_queues; i++) { + struct igb_ring *ring = adapter->rx_ring[i]; + + if (max_frame > igb_rx_bufsz(ring)) { + netdev_warn(adapter->netdev, + "Requested MTU size is not supported with XDP. Max frame size is %d\n", + max_frame); + return -EINVAL; + } + } + } /* adjust max frame to be at least the size of a standard frame */ if (max_frame < (ETH_FRAME_LEN + ETH_FCS_LEN)) @@ -6474,12 +6783,119 @@ void igb_update_stats(struct igb_adapter *adapter) } } -static void igb_tsync_interrupt(struct igb_adapter *adapter) +static void igb_perout(struct igb_adapter *adapter, int tsintr_tt) { + int pin = ptp_find_pin(adapter->ptp_clock, PTP_PF_PEROUT, tsintr_tt); + struct e1000_hw *hw = &adapter->hw; + struct timespec64 ts; + u32 tsauxc; + + if (pin < 0 || pin >= IGB_N_PEROUT) + return; + + spin_lock(&adapter->tmreg_lock); + + if (hw->mac.type == e1000_82580 || + hw->mac.type == e1000_i354 || + hw->mac.type == e1000_i350) { + s64 ns = timespec64_to_ns(&adapter->perout[pin].period); + u32 systiml, systimh, level_mask, level, rem; + u64 systim, now; + + /* read systim registers in sequence */ + rd32(E1000_SYSTIMR); + systiml = rd32(E1000_SYSTIML); + systimh = rd32(E1000_SYSTIMH); + systim = (((u64)(systimh & 0xFF)) << 32) | ((u64)systiml); + now = timecounter_cyc2time(&adapter->tc, systim); + + if (pin < 2) { + level_mask = (tsintr_tt == 1) ? 0x80000 : 0x40000; + level = (rd32(E1000_CTRL) & level_mask) ? 1 : 0; + } else { + level_mask = (tsintr_tt == 1) ? 0x80 : 0x40; + level = (rd32(E1000_CTRL_EXT) & level_mask) ? 1 : 0; + } + + div_u64_rem(now, ns, &rem); + systim = systim + (ns - rem); + + /* synchronize pin level with rising/falling edges */ + div_u64_rem(now, ns << 1, &rem); + if (rem < ns) { + /* first half of period */ + if (level == 0) { + /* output is already low, skip this period */ + systim += ns; + pr_notice("igb: periodic output on %s missed falling edge\n", + adapter->sdp_config[pin].name); + } + } else { + /* second half of period */ + if (level == 1) { + /* output is already high, skip this period */ + systim += ns; + pr_notice("igb: periodic output on %s missed rising edge\n", + adapter->sdp_config[pin].name); + } + } + + /* for this chip family tv_sec is the upper part of the binary value, + * so not seconds + */ + ts.tv_nsec = (u32)systim; + ts.tv_sec = ((u32)(systim >> 32)) & 0xFF; + } else { + ts = timespec64_add(adapter->perout[pin].start, + adapter->perout[pin].period); + } + + /* u32 conversion of tv_sec is safe until y2106 */ + wr32((tsintr_tt == 1) ? E1000_TRGTTIML1 : E1000_TRGTTIML0, ts.tv_nsec); + wr32((tsintr_tt == 1) ? E1000_TRGTTIMH1 : E1000_TRGTTIMH0, (u32)ts.tv_sec); + tsauxc = rd32(E1000_TSAUXC); + tsauxc |= TSAUXC_EN_TT0; + wr32(E1000_TSAUXC, tsauxc); + adapter->perout[pin].start = ts; + + spin_unlock(&adapter->tmreg_lock); +} + +static void igb_extts(struct igb_adapter *adapter, int tsintr_tt) +{ + int pin = ptp_find_pin(adapter->ptp_clock, PTP_PF_EXTTS, tsintr_tt); + int auxstmpl = (tsintr_tt == 1) ? E1000_AUXSTMPL1 : E1000_AUXSTMPL0; + int auxstmph = (tsintr_tt == 1) ? E1000_AUXSTMPH1 : E1000_AUXSTMPH0; struct e1000_hw *hw = &adapter->hw; struct ptp_clock_event event; struct timespec64 ts; - u32 ack = 0, tsauxc, sec, nsec, tsicr = rd32(E1000_TSICR); + + if (pin < 0 || pin >= IGB_N_EXTTS) + return; + + if (hw->mac.type == e1000_82580 || + hw->mac.type == e1000_i354 || + hw->mac.type == e1000_i350) { + s64 ns = rd32(auxstmpl); + + ns += ((s64)(rd32(auxstmph) & 0xFF)) << 32; + ts = ns_to_timespec64(ns); + } else { + ts.tv_nsec = rd32(auxstmpl); + ts.tv_sec = rd32(auxstmph); + } + + event.type = PTP_CLOCK_EXTTS; + event.index = tsintr_tt; + event.timestamp = ts.tv_sec * 1000000000ULL + ts.tv_nsec; + ptp_clock_event(adapter->ptp_clock, &event); +} + +static void igb_tsync_interrupt(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + u32 ack = 0, tsicr = rd32(E1000_TSICR); + struct ptp_clock_event event; if (tsicr & TSINTR_SYS_WRAP) { event.type = PTP_CLOCK_PPS; @@ -6495,51 +6911,22 @@ static void igb_tsync_interrupt(struct igb_adapter *adapter) } if (tsicr & TSINTR_TT0) { - spin_lock(&adapter->tmreg_lock); - ts = timespec64_add(adapter->perout[0].start, - adapter->perout[0].period); - /* u32 conversion of tv_sec is safe until y2106 */ - wr32(E1000_TRGTTIML0, ts.tv_nsec); - wr32(E1000_TRGTTIMH0, (u32)ts.tv_sec); - tsauxc = rd32(E1000_TSAUXC); - tsauxc |= TSAUXC_EN_TT0; - wr32(E1000_TSAUXC, tsauxc); - adapter->perout[0].start = ts; - spin_unlock(&adapter->tmreg_lock); + igb_perout(adapter, 0); ack |= TSINTR_TT0; } if (tsicr & TSINTR_TT1) { - spin_lock(&adapter->tmreg_lock); - ts = timespec64_add(adapter->perout[1].start, - adapter->perout[1].period); - wr32(E1000_TRGTTIML1, ts.tv_nsec); - wr32(E1000_TRGTTIMH1, (u32)ts.tv_sec); - tsauxc = rd32(E1000_TSAUXC); - tsauxc |= TSAUXC_EN_TT1; - wr32(E1000_TSAUXC, tsauxc); - adapter->perout[1].start = ts; - spin_unlock(&adapter->tmreg_lock); + igb_perout(adapter, 1); ack |= TSINTR_TT1; } if (tsicr & TSINTR_AUTT0) { - nsec = rd32(E1000_AUXSTMPL0); - sec = rd32(E1000_AUXSTMPH0); - event.type = PTP_CLOCK_EXTTS; - event.index = 0; - event.timestamp = sec * 1000000000ULL + nsec; - ptp_clock_event(adapter->ptp_clock, &event); + igb_extts(adapter, 0); ack |= TSINTR_AUTT0; } if (tsicr & TSINTR_AUTT1) { - nsec = rd32(E1000_AUXSTMPL1); - sec = rd32(E1000_AUXSTMPH1); - event.type = PTP_CLOCK_EXTTS; - event.index = 1; - event.timestamp = sec * 1000000000ULL + nsec; - ptp_clock_event(adapter->ptp_clock, &event); + igb_extts(adapter, 1); ack |= TSINTR_AUTT1; } @@ -6715,7 +7102,7 @@ static int __igb_notify_dca(struct device *dev, void *data) igb_setup_dca(adapter); break; } - /* Fall Through - since DCA is disabled. */ + fallthrough; /* since DCA is disabled. */ case DCA_PROVIDER_REMOVE: if (adapter->flags & IGB_FLAG_DCA_ENABLED) { /* without this a class_device is left @@ -7168,7 +7555,7 @@ static void igb_flush_mac_table(struct igb_adapter *adapter) for (i = 0; i < hw->mac.rar_entry_count; i++) { adapter->mac_table[i].state &= ~IGB_MAC_STATE_IN_USE; - memset(adapter->mac_table[i].addr, 0, ETH_ALEN); + eth_zero_addr(adapter->mac_table[i].addr); adapter->mac_table[i].queue = 0; igb_rar_set_index(adapter, i); } @@ -7317,7 +7704,7 @@ static int igb_del_mac_filter_flags(struct igb_adapter *adapter, } else { adapter->mac_table[i].state = 0; adapter->mac_table[i].queue = 0; - memset(adapter->mac_table[i].addr, 0, ETH_ALEN); + eth_zero_addr(adapter->mac_table[i].addr); } igb_rar_set_index(adapter, i); @@ -7383,6 +7770,20 @@ static int igb_set_vf_mac_filter(struct igb_adapter *adapter, const int vf, struct vf_mac_filter *entry = NULL; int ret = 0; + if ((vf_data->flags & IGB_VF_FLAG_PF_SET_MAC) && + !vf_data->trusted) { + dev_warn(&pdev->dev, + "VF %d requested MAC filter but is administratively denied\n", + vf); + return -EINVAL; + } + if (!is_valid_ether_addr(addr)) { + dev_warn(&pdev->dev, + "VF %d attempted to set invalid MAC filter\n", + vf); + return -EINVAL; + } + switch (info) { case E1000_VF_MAC_FILTER_CLR: /* remove all unicast MAC filters related to the current VF */ @@ -7396,20 +7797,6 @@ static int igb_set_vf_mac_filter(struct igb_adapter *adapter, const int vf, } break; case E1000_VF_MAC_FILTER_ADD: - if ((vf_data->flags & IGB_VF_FLAG_PF_SET_MAC) && - !vf_data->trusted) { - dev_warn(&pdev->dev, - "VF %d requested MAC filter but is administratively denied\n", - vf); - return -EINVAL; - } - if (!is_valid_ether_addr(addr)) { - dev_warn(&pdev->dev, - "VF %d attempted to set invalid MAC filter\n", - vf); - return -EINVAL; - } - /* try to find empty slot in the list */ list_for_each(pos, &adapter->vf_macs.l) { entry = list_entry(pos, struct vf_mac_filter, l); @@ -7577,8 +7964,10 @@ unlock: static void igb_msg_task(struct igb_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; + unsigned long flags; u32 vf; + spin_lock_irqsave(&adapter->vfs_lock, flags); for (vf = 0; vf < adapter->vfs_allocated_count; vf++) { /* process any reset requests */ if (!igb_check_for_rst(hw, vf)) @@ -7592,6 +7981,7 @@ static void igb_msg_task(struct igb_adapter *adapter) if (!igb_check_for_ack(hw, vf)) igb_rcv_ack_from_vf(adapter, vf); } + spin_unlock_irqrestore(&adapter->vfs_lock, flags); } /** @@ -7761,7 +8151,7 @@ static int igb_poll(struct napi_struct *napi, int budget) if (likely(napi_complete_done(napi, work_done))) igb_ring_irq_enable(q_vector); - return min(work_done, budget - 1); + return work_done; } /** @@ -7810,7 +8200,10 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget) total_packets += tx_buffer->gso_segs; /* free the skb */ - napi_consume_skb(tx_buffer->skb, napi_budget); + if (tx_buffer->type == IGB_TYPE_SKB) + napi_consume_skb(tx_buffer->skb, napi_budget); + else + xdp_return_frame(tx_buffer->xdpf); /* unmap skb header data */ dma_unmap_single(tx_ring->dev, @@ -7964,23 +8357,19 @@ static void igb_reuse_rx_page(struct igb_ring *rx_ring, new_buff->pagecnt_bias = old_buff->pagecnt_bias; } -static inline bool igb_page_is_reserved(struct page *page) -{ - return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page); -} - -static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer) +static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, + int rx_buf_pgcnt) { unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; struct page *page = rx_buffer->page; - /* avoid re-using remote pages */ - if (unlikely(igb_page_is_reserved(page))) + /* avoid re-using remote and pfmemalloc pages */ + if (!dev_page_is_reusable(page)) return false; #if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ - if (unlikely((page_ref_count(page) - pagecnt_bias) > 1)) + if (unlikely((rx_buf_pgcnt - pagecnt_bias) > 1)) return false; #else #define IGB_LAST_OFFSET \ @@ -7994,8 +8383,8 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer) * the pagecnt_bias and page count so that we fully restock the * number of references the driver holds. */ - if (unlikely(!pagecnt_bias)) { - page_ref_add(page, USHRT_MAX); + if (unlikely(pagecnt_bias == 1)) { + page_ref_add(page, USHRT_MAX - 1); rx_buffer->pagecnt_bias = USHRT_MAX; } @@ -8034,48 +8423,43 @@ static void igb_add_rx_frag(struct igb_ring *rx_ring, static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring, struct igb_rx_buffer *rx_buffer, - union e1000_adv_rx_desc *rx_desc, - unsigned int size) + struct xdp_buff *xdp, + ktime_t timestamp) { - void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; #if (PAGE_SIZE < 8192) unsigned int truesize = igb_rx_pg_size(rx_ring) / 2; #else - unsigned int truesize = SKB_DATA_ALIGN(size); + unsigned int truesize = SKB_DATA_ALIGN(xdp->data_end - + xdp->data_hard_start); #endif + unsigned int size = xdp->data_end - xdp->data; unsigned int headlen; struct sk_buff *skb; /* prefetch first cache line of first page */ - prefetch(va); -#if L1_CACHE_BYTES < 128 - prefetch(va + L1_CACHE_BYTES); -#endif + net_prefetch(xdp->data); /* allocate a skb to store the frags */ skb = napi_alloc_skb(&rx_ring->q_vector->napi, IGB_RX_HDR_LEN); if (unlikely(!skb)) return NULL; - if (unlikely(igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP))) { - igb_ptp_rx_pktstamp(rx_ring->q_vector, va, skb); - va += IGB_TS_HDR_LEN; - size -= IGB_TS_HDR_LEN; - } + if (timestamp) + skb_hwtstamps(skb)->hwtstamp = timestamp; /* Determine available headroom for copy */ headlen = size; if (headlen > IGB_RX_HDR_LEN) - headlen = eth_get_headlen(skb->dev, va, IGB_RX_HDR_LEN); + headlen = eth_get_headlen(skb->dev, xdp->data, IGB_RX_HDR_LEN); /* align pull length to size of long to optimize memcpy performance */ - memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long))); + memcpy(__skb_put(skb, headlen), xdp->data, ALIGN(headlen, sizeof(long))); /* update all of the pointers */ size -= headlen; if (size) { skb_add_rx_frag(skb, 0, rx_buffer->page, - (va + headlen) - page_address(rx_buffer->page), + (xdp->data + headlen) - page_address(rx_buffer->page), size, truesize); #if (PAGE_SIZE < 8192) rx_buffer->page_offset ^= truesize; @@ -8091,38 +8475,36 @@ static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring, static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring, struct igb_rx_buffer *rx_buffer, - union e1000_adv_rx_desc *rx_desc, - unsigned int size) + struct xdp_buff *xdp, + ktime_t timestamp) { - void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; #if (PAGE_SIZE < 8192) unsigned int truesize = igb_rx_pg_size(rx_ring) / 2; #else unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) + - SKB_DATA_ALIGN(IGB_SKB_PAD + size); + SKB_DATA_ALIGN(xdp->data_end - + xdp->data_hard_start); #endif + unsigned int metasize = xdp->data - xdp->data_meta; struct sk_buff *skb; /* prefetch first cache line of first page */ - prefetch(va); -#if L1_CACHE_BYTES < 128 - prefetch(va + L1_CACHE_BYTES); -#endif + net_prefetch(xdp->data_meta); /* build an skb around the page buffer */ - skb = build_skb(va - IGB_SKB_PAD, truesize); + skb = napi_build_skb(xdp->data_hard_start, truesize); if (unlikely(!skb)) return NULL; /* update pointers within the skb to store the data */ - skb_reserve(skb, IGB_SKB_PAD); - __skb_put(skb, size); + skb_reserve(skb, xdp->data - xdp->data_hard_start); + __skb_put(skb, xdp->data_end - xdp->data); - /* pull timestamp out of packet data */ - if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { - igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb); - __skb_pull(skb, IGB_TS_HDR_LEN); - } + if (metasize) + skb_metadata_set(skb, metasize); + + if (timestamp) + skb_hwtstamps(skb)->hwtstamp = timestamp; /* update buffer offset */ #if (PAGE_SIZE < 8192) @@ -8134,6 +8516,79 @@ static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring, return skb; } +static struct sk_buff *igb_run_xdp(struct igb_adapter *adapter, + struct igb_ring *rx_ring, + struct xdp_buff *xdp) +{ + int err, result = IGB_XDP_PASS; + struct bpf_prog *xdp_prog; + u32 act; + + xdp_prog = READ_ONCE(rx_ring->xdp_prog); + + if (!xdp_prog) + goto xdp_out; + + prefetchw(xdp->data_hard_start); /* xdp_frame write */ + + act = bpf_prog_run_xdp(xdp_prog, xdp); + switch (act) { + case XDP_PASS: + break; + case XDP_TX: + result = igb_xdp_xmit_back(adapter, xdp); + if (result == IGB_XDP_CONSUMED) + goto out_failure; + break; + case XDP_REDIRECT: + err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog); + if (err) + goto out_failure; + result = IGB_XDP_REDIR; + break; + default: + bpf_warn_invalid_xdp_action(adapter->netdev, xdp_prog, act); + fallthrough; + case XDP_ABORTED: +out_failure: + trace_xdp_exception(rx_ring->netdev, xdp_prog, act); + fallthrough; + case XDP_DROP: + result = IGB_XDP_CONSUMED; + break; + } +xdp_out: + return ERR_PTR(-result); +} + +static unsigned int igb_rx_frame_truesize(struct igb_ring *rx_ring, + unsigned int size) +{ + unsigned int truesize; + +#if (PAGE_SIZE < 8192) + truesize = igb_rx_pg_size(rx_ring) / 2; /* Must be power-of-2 */ +#else + truesize = ring_uses_build_skb(rx_ring) ? + SKB_DATA_ALIGN(IGB_SKB_PAD + size) + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) : + SKB_DATA_ALIGN(size); +#endif + return truesize; +} + +static void igb_rx_buffer_flip(struct igb_ring *rx_ring, + struct igb_rx_buffer *rx_buffer, + unsigned int size) +{ + unsigned int truesize = igb_rx_frame_truesize(rx_ring, size); +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif +} + static inline void igb_rx_checksum(struct igb_ring *ring, union e1000_adv_rx_desc *rx_desc, struct sk_buff *skb) @@ -8188,7 +8643,6 @@ static inline void igb_rx_hash(struct igb_ring *ring, * igb_is_non_eop - process handling of non-EOP buffers * @rx_ring: Rx ring being processed * @rx_desc: Rx descriptor for current buffer - * @skb: current socket buffer containing buffer in progress * * This function updates next to clean. If the buffer is an EOP buffer * this function exits returning false, otherwise it will place the @@ -8230,6 +8684,10 @@ static bool igb_cleanup_headers(struct igb_ring *rx_ring, union e1000_adv_rx_desc *rx_desc, struct sk_buff *skb) { + /* XDP packets use error pointer so abort at this point */ + if (IS_ERR(skb)) + return true; + if (unlikely((igb_test_staterr(rx_desc, E1000_RXDEXT_ERR_FRAME_ERR_MASK)))) { struct net_device *netdev = rx_ring->netdev; @@ -8276,7 +8734,7 @@ static void igb_process_skb_fields(struct igb_ring *rx_ring, if (igb_test_staterr(rx_desc, E1000_RXDEXT_STATERR_LB) && test_bit(IGB_RING_FLAG_RX_LB_VLAN_BSWAP, &rx_ring->flags)) - vid = be16_to_cpu(rx_desc->wb.upper.vlan); + vid = be16_to_cpu((__force __be16)rx_desc->wb.upper.vlan); else vid = le16_to_cpu(rx_desc->wb.upper.vlan); @@ -8288,12 +8746,23 @@ static void igb_process_skb_fields(struct igb_ring *rx_ring, skb->protocol = eth_type_trans(skb, rx_ring->netdev); } +static unsigned int igb_rx_offset(struct igb_ring *rx_ring) +{ + return ring_uses_build_skb(rx_ring) ? IGB_SKB_PAD : 0; +} + static struct igb_rx_buffer *igb_get_rx_buffer(struct igb_ring *rx_ring, - const unsigned int size) + const unsigned int size, int *rx_buf_pgcnt) { struct igb_rx_buffer *rx_buffer; rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + *rx_buf_pgcnt = +#if (PAGE_SIZE < 8192) + page_count(rx_buffer->page); +#else + 0; +#endif prefetchw(rx_buffer->page); /* we are reusing so sync this buffer for CPU use */ @@ -8309,9 +8778,9 @@ static struct igb_rx_buffer *igb_get_rx_buffer(struct igb_ring *rx_ring, } static void igb_put_rx_buffer(struct igb_ring *rx_ring, - struct igb_rx_buffer *rx_buffer) + struct igb_rx_buffer *rx_buffer, int rx_buf_pgcnt) { - if (igb_can_reuse_rx_page(rx_buffer)) { + if (igb_can_reuse_rx_page(rx_buffer, rx_buf_pgcnt)) { /* hand second half of page back to the ring */ igb_reuse_rx_page(rx_ring, rx_buffer); } else { @@ -8331,15 +8800,29 @@ static void igb_put_rx_buffer(struct igb_ring *rx_ring, static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) { + struct igb_adapter *adapter = q_vector->adapter; struct igb_ring *rx_ring = q_vector->rx.ring; struct sk_buff *skb = rx_ring->skb; unsigned int total_bytes = 0, total_packets = 0; u16 cleaned_count = igb_desc_unused(rx_ring); + unsigned int xdp_xmit = 0; + struct xdp_buff xdp; + u32 frame_sz = 0; + int rx_buf_pgcnt; + + /* Frame size depend on rx_ring setup when PAGE_SIZE=4K */ +#if (PAGE_SIZE < 8192) + frame_sz = igb_rx_frame_truesize(rx_ring, 0); +#endif + xdp_init_buff(&xdp, frame_sz, &rx_ring->xdp_rxq); while (likely(total_packets < budget)) { union e1000_adv_rx_desc *rx_desc; struct igb_rx_buffer *rx_buffer; + ktime_t timestamp = 0; + int pkt_offset = 0; unsigned int size; + void *pktbuf; /* return some buffers to hardware, one at a time is too slow */ if (cleaned_count >= IGB_RX_BUFFER_WRITE) { @@ -8358,16 +8841,53 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) */ dma_rmb(); - rx_buffer = igb_get_rx_buffer(rx_ring, size); + rx_buffer = igb_get_rx_buffer(rx_ring, size, &rx_buf_pgcnt); + pktbuf = page_address(rx_buffer->page) + rx_buffer->page_offset; + + /* pull rx packet timestamp if available and valid */ + if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { + int ts_hdr_len; + + ts_hdr_len = igb_ptp_rx_pktstamp(rx_ring->q_vector, + pktbuf, ×tamp); + + pkt_offset += ts_hdr_len; + size -= ts_hdr_len; + } /* retrieve a buffer from the ring */ - if (skb) + if (!skb) { + unsigned char *hard_start = pktbuf - igb_rx_offset(rx_ring); + unsigned int offset = pkt_offset + igb_rx_offset(rx_ring); + + xdp_prepare_buff(&xdp, hard_start, offset, size, true); + xdp_buff_clear_frags_flag(&xdp); +#if (PAGE_SIZE > 4096) + /* At larger PAGE_SIZE, frame_sz depend on len size */ + xdp.frame_sz = igb_rx_frame_truesize(rx_ring, size); +#endif + skb = igb_run_xdp(adapter, rx_ring, &xdp); + } + + if (IS_ERR(skb)) { + unsigned int xdp_res = -PTR_ERR(skb); + + if (xdp_res & (IGB_XDP_TX | IGB_XDP_REDIR)) { + xdp_xmit |= xdp_res; + igb_rx_buffer_flip(rx_ring, rx_buffer, size); + } else { + rx_buffer->pagecnt_bias++; + } + total_packets++; + total_bytes += size; + } else if (skb) igb_add_rx_frag(rx_ring, rx_buffer, skb, size); else if (ring_uses_build_skb(rx_ring)) - skb = igb_build_skb(rx_ring, rx_buffer, rx_desc, size); + skb = igb_build_skb(rx_ring, rx_buffer, &xdp, + timestamp); else skb = igb_construct_skb(rx_ring, rx_buffer, - rx_desc, size); + &xdp, timestamp); /* exit if we failed to retrieve a buffer */ if (!skb) { @@ -8376,7 +8896,7 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) break; } - igb_put_rx_buffer(rx_ring, rx_buffer); + igb_put_rx_buffer(rx_ring, rx_buffer, rx_buf_pgcnt); cleaned_count++; /* fetch next buffer in frame if non-eop */ @@ -8407,6 +8927,15 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) /* place incomplete frames back on ring for completion */ rx_ring->skb = skb; + if (xdp_xmit & IGB_XDP_REDIR) + xdp_do_flush(); + + if (xdp_xmit & IGB_XDP_TX) { + struct igb_ring *tx_ring = igb_xdp_tx_queue_mapping(adapter); + + igb_xdp_ring_update_tail(tx_ring); + } + u64_stats_update_begin(&rx_ring->rx_syncp); rx_ring->rx_stats.packets += total_packets; rx_ring->rx_stats.bytes += total_bytes; @@ -8420,11 +8949,6 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) return total_packets; } -static inline unsigned int igb_rx_offset(struct igb_ring *rx_ring) -{ - return ring_uses_build_skb(rx_ring) ? IGB_SKB_PAD : 0; -} - static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, struct igb_rx_buffer *bi) { @@ -8461,14 +8985,16 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, bi->dma = dma; bi->page = page; bi->page_offset = igb_rx_offset(rx_ring); - bi->pagecnt_bias = 1; + page_ref_add(page, USHRT_MAX - 1); + bi->pagecnt_bias = USHRT_MAX; return true; } /** - * igb_alloc_rx_buffers - Replace used receive buffers; packet split - * @adapter: address of board private structure + * igb_alloc_rx_buffers - Replace used receive buffers + * @rx_ring: rx descriptor ring to allocate new receive buffers + * @cleaned_count: count of buffers to allocate **/ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count) { @@ -8537,9 +9063,9 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count) /** * igb_mii_ioctl - - * @netdev: - * @ifreq: - * @cmd: + * @netdev: pointer to netdev struct + * @ifr: interface structure + * @cmd: ioctl command to execute **/ static int igb_mii_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) { @@ -8567,9 +9093,9 @@ static int igb_mii_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) /** * igb_ioctl - - * @netdev: - * @ifreq: - * @cmd: + * @netdev: pointer to netdev struct + * @ifr: interface structure + * @cmd: ioctl command to execute **/ static int igb_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) { @@ -8854,7 +9380,7 @@ static int __maybe_unused igb_suspend(struct device *dev) return __igb_shutdown(to_pci_dev(dev), NULL, 0); } -static int __maybe_unused igb_resume(struct device *dev) +static int __maybe_unused __igb_resume(struct device *dev, bool rpm) { struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); @@ -8897,17 +9423,24 @@ static int __maybe_unused igb_resume(struct device *dev) wr32(E1000_WUS, ~0); - rtnl_lock(); + if (!rpm) + rtnl_lock(); if (!err && netif_running(netdev)) err = __igb_open(netdev, true); if (!err) netif_device_attach(netdev); - rtnl_unlock(); + if (!rpm) + rtnl_unlock(); return err; } +static int __maybe_unused igb_resume(struct device *dev) +{ + return __igb_resume(dev, false); +} + static int __maybe_unused igb_runtime_idle(struct device *dev) { struct net_device *netdev = dev_get_drvdata(dev); @@ -8926,7 +9459,7 @@ static int __maybe_unused igb_runtime_suspend(struct device *dev) static int __maybe_unused igb_runtime_resume(struct device *dev) { - return igb_resume(dev); + return __igb_resume(dev, true); } static void igb_shutdown(struct pci_dev *pdev) @@ -9033,7 +9566,7 @@ static pci_ers_result_t igb_io_error_detected(struct pci_dev *pdev, igb_down(adapter); pci_disable_device(pdev); - /* Request a slot slot reset. */ + /* Request a slot reset. */ return PCI_ERS_RESULT_NEED_RESET; } @@ -9042,7 +9575,7 @@ static pci_ers_result_t igb_io_error_detected(struct pci_dev *pdev, * @pdev: Pointer to PCI device * * Restart the card from scratch, as if from a cold-boot. Implementation - * resembles the first-half of the igb_resume routine. + * resembles the first-half of the __igb_resume routine. **/ static pci_ers_result_t igb_io_slot_reset(struct pci_dev *pdev) { @@ -9082,7 +9615,7 @@ static pci_ers_result_t igb_io_slot_reset(struct pci_dev *pdev) * * 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 igb_resume routine. + * second-half of the __igb_resume routine. */ static void igb_io_resume(struct pci_dev *pdev) { @@ -9384,13 +9917,13 @@ static void igb_vmm_control(struct igb_adapter *adapter) reg = rd32(E1000_DTXCTL); reg |= E1000_DTXCTL_VLAN_ADDED; wr32(E1000_DTXCTL, reg); - /* Fall through */ + fallthrough; case e1000_82580: /* enable replication vlan tag stripping */ reg = rd32(E1000_RPLOLR); reg |= E1000_RPLOLR_STRVLAN; wr32(E1000_RPLOLR, reg); - /* Fall through */ + fallthrough; case e1000_i350: /* none of the above registers are supported by i350 */ break; @@ -9412,11 +9945,10 @@ static void igb_init_dmac(struct igb_adapter *adapter, u32 pba) struct e1000_hw *hw = &adapter->hw; u32 dmac_thr; u16 hwm; + u32 reg; if (hw->mac.type > e1000_82580) { if (adapter->flags & IGB_FLAG_DMAC) { - u32 reg; - /* force threshold to 0. */ wr32(E1000_DMCTXTH, 0); @@ -9449,7 +9981,6 @@ static void igb_init_dmac(struct igb_adapter *adapter, u32 pba) /* Disable BMC-to-OS Watchdog Enable */ if (hw->mac.type != e1000_i354) reg &= ~E1000_DMACR_DC_BMC2OSW_EN; - wr32(E1000_DMACR, reg); /* no lower threshold to disable @@ -9466,12 +9997,12 @@ static void igb_init_dmac(struct igb_adapter *adapter, u32 pba) */ wr32(E1000_DMCTXTH, (IGB_MIN_TXPBSIZE - (IGB_TX_BUF_4096 + adapter->max_frame_size)) >> 6); + } - /* make low power state decision controlled - * by DMA coal - */ + if (hw->mac.type >= e1000_i210 || + (adapter->flags & IGB_FLAG_DMAC)) { reg = rd32(E1000_PCIEMISC); - reg &= ~E1000_PCIEMISC_LX_DECISION; + reg |= E1000_PCIEMISC_LX_DECISION; wr32(E1000_PCIEMISC, reg); } /* endif adapter->dmac is not disabled */ } else if (hw->mac.type == e1000_82580) { |