diff options
Diffstat (limited to 'drivers/net/ethernet/intel/ixgbe/ixgbe_main.c')
| -rw-r--r-- | drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2460 |
1 files changed, 1674 insertions, 786 deletions
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index b53087a980ef..034618e79169 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2018 Intel Corporation. */ +/* Copyright(c) 1999 - 2024 Intel Corporation. */ #include <linux/types.h> #include <linux/module.h> @@ -9,6 +9,7 @@ #include <linux/string.h> #include <linux/in.h> #include <linux/interrupt.h> +#include <linux/iopoll.h> #include <linux/ip.h> #include <linux/tcp.h> #include <linux/sctp.h> @@ -27,6 +28,8 @@ #include <linux/bpf.h> #include <linux/bpf_trace.h> #include <linux/atomic.h> +#include <linux/numa.h> +#include <generated/utsrelease.h> #include <scsi/fc/fc_fcoe.h> #include <net/udp_tunnel.h> #include <net/pkt_cls.h> @@ -34,15 +37,20 @@ #include <net/tc_act/tc_mirred.h> #include <net/vxlan.h> #include <net/mpls.h> -#include <net/xdp_sock.h> +#include <net/netdev_queues.h> +#include <net/xdp_sock_drv.h> +#include <net/xfrm.h> #include "ixgbe.h" #include "ixgbe_common.h" +#include "ixgbe_e610.h" #include "ixgbe_dcb_82599.h" +#include "ixgbe_mbx.h" #include "ixgbe_phy.h" #include "ixgbe_sriov.h" #include "ixgbe_model.h" #include "ixgbe_txrx_common.h" +#include "devlink/devlink.h" char ixgbe_driver_name[] = "ixgbe"; static const char ixgbe_driver_string[] = @@ -54,8 +62,6 @@ char ixgbe_default_device_descr[] = static char ixgbe_default_device_descr[] = "Intel(R) 10 Gigabit Network Connection"; #endif -#define DRV_VERSION "5.1.0-k" -const char ixgbe_driver_version[] = DRV_VERSION; static const char ixgbe_copyright[] = "Copyright (c) 1999-2016 Intel Corporation."; @@ -70,6 +76,7 @@ static const struct ixgbe_info *ixgbe_info_tbl[] = { [board_x550em_x_fw] = &ixgbe_x550em_x_fw_info, [board_x550em_a] = &ixgbe_x550em_a_info, [board_x550em_a_fw] = &ixgbe_x550em_a_fw_info, + [board_e610] = &ixgbe_e610_info, }; /* ixgbe_pci_tbl - PCI Device ID Table @@ -128,6 +135,11 @@ static const struct pci_device_id ixgbe_pci_tbl[] = { {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_SFP), board_x550em_a }, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_1G_T), board_x550em_a_fw }, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_1G_T_L), board_x550em_a_fw }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_BACKPLANE), board_e610}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_SFP), board_e610}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_10G_T), board_e610}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_2_5G_T), board_e610}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_E610_SGMII), board_e610}, /* required last entry */ {0, } }; @@ -150,8 +162,8 @@ MODULE_PARM_DESC(max_vfs, "Maximum number of virtual functions to allocate per physical function - default is zero and maximum value is 63. (Deprecated)"); #endif /* CONFIG_PCI_IOV */ -static unsigned int allow_unsupported_sfp; -module_param(allow_unsupported_sfp, uint, 0); +static bool allow_unsupported_sfp; +module_param(allow_unsupported_sfp, bool, 0444); MODULE_PARM_DESC(allow_unsupported_sfp, "Allow unsupported and untested SFP+ modules on 82599-based adapters"); @@ -160,15 +172,19 @@ static int debug = -1; module_param(debug, int, 0); MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); -MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); +MODULE_IMPORT_NS("LIBIE_FWLOG"); MODULE_DESCRIPTION("Intel(R) 10 Gigabit PCI Express Network Driver"); MODULE_LICENSE("GPL v2"); -MODULE_VERSION(DRV_VERSION); + +DEFINE_STATIC_KEY_FALSE(ixgbe_xdp_locking_key); +EXPORT_SYMBOL(ixgbe_xdp_locking_key); static struct workqueue_struct *ixgbe_wq; static bool ixgbe_check_cfg_remove(struct ixgbe_hw *hw, struct pci_dev *pdev); static void ixgbe_watchdog_link_is_down(struct ixgbe_adapter *); +static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *); +static void ixgbe_watchdog_update_link(struct ixgbe_adapter *); static const struct net_device_ops ixgbe_netdev_ops; @@ -201,7 +217,7 @@ static int ixgbe_read_pci_cfg_word_parent(struct ixgbe_adapter *adapter, return 0; } -static s32 ixgbe_get_parent_bus_info(struct ixgbe_adapter *adapter) +static int ixgbe_get_parent_bus_info(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; u16 link_status = 0; @@ -225,15 +241,18 @@ static s32 ixgbe_get_parent_bus_info(struct ixgbe_adapter *adapter) } /** - * ixgbe_check_from_parent - Determine whether PCIe info should come from parent + * ixgbe_pcie_from_parent - Determine whether PCIe info should come from parent * @hw: hw specific details * * This function is used by probe to determine whether a device's PCI-Express * bandwidth details should be gathered from the parent bus instead of from the * device. Used to ensure that various locations all have the correct device ID * checks. + * + * Return: true if information should be collected from the parent bus, false + * otherwise */ -static inline bool ixgbe_pcie_from_parent(struct ixgbe_hw *hw) +static bool ixgbe_pcie_from_parent(struct ixgbe_hw *hw) { switch (hw->device_id) { case IXGBE_DEV_ID_82599_SFP_SF_QP: @@ -872,6 +891,7 @@ static void ixgbe_set_ivar(struct ixgbe_adapter *adapter, s8 direction, case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: if (direction == -1) { /* other causes */ msix_vector |= IXGBE_IVAR_ALLOC_VAL; @@ -911,6 +931,7 @@ void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter, case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: mask = (qmask & 0xFFFFFFFF); IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS_EX(0), mask); mask = (qmask >> 32); @@ -948,10 +969,6 @@ static void ixgbe_update_xoff_rx_lfc(struct ixgbe_adapter *adapter) for (i = 0; i < adapter->num_tx_queues; i++) clear_bit(__IXGBE_HANG_CHECK_ARMED, &adapter->tx_ring[i]->state); - - for (i = 0; i < adapter->num_xdp_queues; i++) - clear_bit(__IXGBE_HANG_CHECK_ARMED, - &adapter->xdp_ring[i]->state); } static void ixgbe_update_xoff_received(struct ixgbe_adapter *adapter) @@ -1021,7 +1038,49 @@ static u64 ixgbe_get_tx_pending(struct ixgbe_ring *ring) return ((head <= tail) ? tail : tail + ring->count) - head; } -static inline bool ixgbe_check_tx_hang(struct ixgbe_ring *tx_ring) +/** + * ixgbe_get_vf_idx - provide VF index number based on queue index + * @adapter: pointer to the adapter struct + * @queue: Tx queue identifier + * @vf: output VF index + * + * Provide VF index number associated to the input queue. + * + * Returns: 0 if VF provided or error number. + */ +static int ixgbe_get_vf_idx(struct ixgbe_adapter *adapter, u16 queue, u16 *vf) +{ + struct ixgbe_hw *hw = &adapter->hw; + u8 queue_count; + u32 reg; + + if (queue >= adapter->num_tx_queues) + return -EINVAL; + + /* Determine number of queues by checking + * number of virtual functions + */ + reg = IXGBE_READ_REG(hw, IXGBE_GCR_EXT); + switch (reg & IXGBE_GCR_EXT_VT_MODE_MASK) { + case IXGBE_GCR_EXT_VT_MODE_64: + queue_count = IXGBE_64VFS_QUEUES; + break; + case IXGBE_GCR_EXT_VT_MODE_32: + queue_count = IXGBE_32VFS_QUEUES; + break; + case IXGBE_GCR_EXT_VT_MODE_16: + queue_count = IXGBE_16VFS_QUEUES; + break; + default: + return -EINVAL; + } + + *vf = queue / queue_count; + + return 0; +} + +static bool ixgbe_check_tx_hang(struct ixgbe_ring *tx_ring) { u32 tx_done = ixgbe_get_tx_completed(tx_ring); u32 tx_done_old = tx_ring->tx_stats.tx_done_old; @@ -1077,7 +1136,7 @@ static void ixgbe_tx_timeout_reset(struct ixgbe_adapter *adapter) static int ixgbe_tx_maxrate(struct net_device *netdev, int queue_index, u32 maxrate) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; u32 bcnrc_val = ixgbe_link_mbps(adapter); @@ -1102,6 +1161,186 @@ static int ixgbe_tx_maxrate(struct net_device *netdev, } /** + * ixgbe_update_tx_ring_stats - Update Tx ring specific counters + * @tx_ring: ring to update + * @q_vector: queue vector ring belongs to + * @pkts: number of processed packets + * @bytes: number of processed bytes + */ +void ixgbe_update_tx_ring_stats(struct ixgbe_ring *tx_ring, + struct ixgbe_q_vector *q_vector, u64 pkts, + u64 bytes) +{ + u64_stats_update_begin(&tx_ring->syncp); + tx_ring->stats.bytes += bytes; + tx_ring->stats.packets += pkts; + u64_stats_update_end(&tx_ring->syncp); + q_vector->tx.total_bytes += bytes; + q_vector->tx.total_packets += pkts; +} + +/** + * ixgbe_update_rx_ring_stats - Update Rx ring specific counters + * @rx_ring: ring to update + * @q_vector: queue vector ring belongs to + * @pkts: number of processed packets + * @bytes: number of processed bytes + */ +void ixgbe_update_rx_ring_stats(struct ixgbe_ring *rx_ring, + struct ixgbe_q_vector *q_vector, u64 pkts, + u64 bytes) +{ + u64_stats_update_begin(&rx_ring->syncp); + rx_ring->stats.bytes += bytes; + rx_ring->stats.packets += pkts; + u64_stats_update_end(&rx_ring->syncp); + q_vector->rx.total_bytes += bytes; + q_vector->rx.total_packets += pkts; +} + +/** + * ixgbe_pf_handle_tx_hang - handle Tx hang on PF + * @tx_ring: tx ring number + * @next: next ring + * + * Prints a message containing details about the tx hang. + */ +static void ixgbe_pf_handle_tx_hang(struct ixgbe_ring *tx_ring, + unsigned int next) +{ + struct ixgbe_adapter *adapter = netdev_priv(tx_ring->netdev); + struct ixgbe_hw *hw = &adapter->hw; + + e_err(drv, "Detected Tx Unit Hang\n" + " Tx Queue <%d>\n" + " TDH, TDT <%x>, <%x>\n" + " next_to_use <%x>\n" + " next_to_clean <%x>\n" + "tx_buffer_info[next_to_clean]\n" + " time_stamp <%lx>\n" + " jiffies <%lx>\n", + tx_ring->queue_index, + IXGBE_READ_REG(hw, IXGBE_TDH(tx_ring->reg_idx)), + IXGBE_READ_REG(hw, IXGBE_TDT(tx_ring->reg_idx)), + tx_ring->next_to_use, next, + tx_ring->tx_buffer_info[next].time_stamp, jiffies); + + netif_stop_subqueue(tx_ring->netdev, + tx_ring->queue_index); +} + +/** + * ixgbe_vf_handle_tx_hang - handle Tx hang on VF + * @adapter: structure containing ring specific data + * @vf: VF index + * + * Print a message containing details about malicious driver detection. + * Set malicious VF link down if the detection happened several times. + */ +static void ixgbe_vf_handle_tx_hang(struct ixgbe_adapter *adapter, u16 vf) +{ + struct ixgbe_hw *hw = &adapter->hw; + + if (adapter->hw.mac.type != ixgbe_mac_e610) + return; + + e_warn(drv, + "Malicious Driver Detection tx hang detected on PF %d VF %d MAC: %pM", + hw->bus.func, vf, adapter->vfinfo[vf].vf_mac_addresses); + + adapter->tx_hang_count[vf]++; + if (adapter->tx_hang_count[vf] == IXGBE_MAX_TX_VF_HANGS) { + ixgbe_set_vf_link_state(adapter, vf, + IFLA_VF_LINK_STATE_DISABLE); + adapter->tx_hang_count[vf] = 0; + } +} + +static u32 ixgbe_poll_tx_icache(struct ixgbe_hw *hw, u16 queue, u16 idx) +{ + IXGBE_WRITE_REG(hw, IXGBE_TXDESCIC, queue * idx); + return IXGBE_READ_REG(hw, IXGBE_TXDESCIC); +} + +/** + * ixgbe_check_illegal_queue - search for queue with illegal packet + * @adapter: structure containing ring specific data + * @queue: queue index + * + * Check if tx descriptor connected with input queue + * contains illegal packet. + * + * Returns: true if queue contain illegal packet. + */ +static bool ixgbe_check_illegal_queue(struct ixgbe_adapter *adapter, + u16 queue) +{ + u32 hdr_len_reg, mss_len_reg, type_reg; + struct ixgbe_hw *hw = &adapter->hw; + u32 mss_len, header_len, reg; + + for (u16 i = 0; i < IXGBE_MAX_TX_DESCRIPTORS; i++) { + /* HW will clear bit IXGBE_TXDESCIC_READY when address + * is written to address field. HW will set this bit + * when iCache read is done, and data is ready at TIC_DWx. + * Set descriptor address. + */ + read_poll_timeout(ixgbe_poll_tx_icache, reg, + !(reg & IXGBE_TXDESCIC_READY), 0, 0, false, + hw, queue, i); + + /* read tx descriptor access registers */ + hdr_len_reg = IXGBE_READ_REG(hw, IXGBE_TIC_DW2(IXGBE_VLAN_MACIP_LENS_REG)); + type_reg = IXGBE_READ_REG(hw, IXGBE_TIC_DW2(IXGBE_TYPE_TUCMD_MLHL)); + mss_len_reg = IXGBE_READ_REG(hw, IXGBE_TIC_DW2(IXGBE_MSS_L4LEN_IDX)); + + /* check if Advanced Context Descriptor */ + if (FIELD_GET(IXGBE_ADVTXD_DTYP_MASK, type_reg) != + IXGBE_ADVTXD_DTYP_CTXT) + continue; + + /* check for illegal MSS and Header length */ + mss_len = FIELD_GET(IXGBE_ADVTXD_MSS_MASK, mss_len_reg); + header_len = FIELD_GET(IXGBE_ADVTXD_HEADER_LEN_MASK, + hdr_len_reg); + if ((mss_len + header_len) > SZ_16K) { + e_warn(probe, "mss len + header len too long\n"); + return true; + } + } + + return false; +} + +/** + * ixgbe_handle_mdd_event - handle mdd event + * @adapter: structure containing ring specific data + * @tx_ring: tx descriptor ring to handle + * + * Reset VF driver if malicious vf detected or + * illegal packet in an any queue detected. + */ +static void ixgbe_handle_mdd_event(struct ixgbe_adapter *adapter, + struct ixgbe_ring *tx_ring) +{ + u16 vf, q; + + if (adapter->vfinfo && ixgbe_check_mdd_event(adapter)) { + /* vf mdd info and malicious vf detected */ + if (!ixgbe_get_vf_idx(adapter, tx_ring->queue_index, &vf)) + ixgbe_vf_handle_tx_hang(adapter, vf); + } else { + /* malicious vf not detected */ + for (q = 0; q < IXGBE_MAX_TX_QUEUES; q++) { + if (ixgbe_check_illegal_queue(adapter, q) && + !ixgbe_get_vf_idx(adapter, q, &vf)) + /* illegal queue detected */ + ixgbe_vf_handle_tx_hang(adapter, vf); + } + } +} + +/** * ixgbe_clean_tx_irq - Reclaim resources after transmit completes * @q_vector: structure containing interrupt and ring information * @tx_ring: tx ring to clean @@ -1116,6 +1355,7 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, unsigned int total_bytes = 0, total_packets = 0, total_ipsec = 0; unsigned int budget = q_vector->tx.work_limit; unsigned int i = tx_ring->next_to_clean; + struct netdev_queue *txq; if (test_bit(__IXGBE_DOWN, &adapter->state)) return true; @@ -1202,35 +1442,18 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, i += tx_ring->count; tx_ring->next_to_clean = i; - u64_stats_update_begin(&tx_ring->syncp); - tx_ring->stats.bytes += total_bytes; - tx_ring->stats.packets += total_packets; - u64_stats_update_end(&tx_ring->syncp); - q_vector->tx.total_bytes += total_bytes; - q_vector->tx.total_packets += total_packets; + ixgbe_update_tx_ring_stats(tx_ring, q_vector, total_packets, + total_bytes); adapter->tx_ipsec += total_ipsec; + if (ring_is_xdp(tx_ring)) + return !!budget; + if (check_for_tx_hang(tx_ring) && ixgbe_check_tx_hang(tx_ring)) { - /* schedule immediate reset if we believe we hung */ - struct ixgbe_hw *hw = &adapter->hw; - e_err(drv, "Detected Tx Unit Hang %s\n" - " Tx Queue <%d>\n" - " TDH, TDT <%x>, <%x>\n" - " next_to_use <%x>\n" - " next_to_clean <%x>\n" - "tx_buffer_info[next_to_clean]\n" - " time_stamp <%lx>\n" - " jiffies <%lx>\n", - ring_is_xdp(tx_ring) ? "(XDP)" : "", - tx_ring->queue_index, - IXGBE_READ_REG(hw, IXGBE_TDH(tx_ring->reg_idx)), - IXGBE_READ_REG(hw, IXGBE_TDT(tx_ring->reg_idx)), - tx_ring->next_to_use, i, - tx_ring->tx_buffer_info[i].time_stamp, jiffies); - - if (!ring_is_xdp(tx_ring)) - netif_stop_subqueue(tx_ring->netdev, - tx_ring->queue_index); + if (adapter->hw.mac.type == ixgbe_mac_e610) + ixgbe_handle_mdd_event(adapter, tx_ring); + + ixgbe_pf_handle_tx_hang(tx_ring, i); e_info(probe, "tx hang %d detected on queue %d, resetting adapter\n", @@ -1243,27 +1466,14 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, return true; } - if (ring_is_xdp(tx_ring)) - return !!budget; - - netdev_tx_completed_queue(txring_txq(tx_ring), - total_packets, total_bytes); - #define TX_WAKE_THRESHOLD (DESC_NEEDED * 2) - if (unlikely(total_packets && 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(); - if (__netif_subqueue_stopped(tx_ring->netdev, - tx_ring->queue_index) - && !test_bit(__IXGBE_DOWN, &adapter->state)) { - netif_wake_subqueue(tx_ring->netdev, - tx_ring->queue_index); - ++tx_ring->tx_stats.restart_queue; - } - } + txq = netdev_get_tx_queue(tx_ring->netdev, tx_ring->queue_index); + if (!__netif_txq_completed_wake(txq, total_packets, total_bytes, + ixgbe_desc_unused(tx_ring), + TX_WAKE_THRESHOLD, + !netif_carrier_ok(tx_ring->netdev) || + test_bit(__IXGBE_DOWN, &adapter->state))) + ++tx_ring->tx_stats.restart_queue; return !!budget; } @@ -1395,7 +1605,7 @@ static int __ixgbe_notify_dca(struct device *dev, void *data) IXGBE_DCA_CTRL_DCA_MODE_CB2); break; } - /* fall through - DCA is disabled. */ + fallthrough; /* DCA is disabled. */ case DCA_PROVIDER_REMOVE: if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) { dca_remove_requester(dev); @@ -1520,7 +1730,7 @@ static inline void ixgbe_rx_checksum(struct ixgbe_ring *ring, } } -static inline unsigned int ixgbe_rx_offset(struct ixgbe_ring *rx_ring) +static unsigned int ixgbe_rx_offset(struct ixgbe_ring *rx_ring) { return ring_uses_build_skb(rx_ring) ? IXGBE_SKB_PAD : 0; } @@ -1561,7 +1771,7 @@ static bool ixgbe_alloc_mapped_page(struct ixgbe_ring *rx_ring, bi->dma = dma; bi->page = page; - bi->page_offset = ixgbe_rx_offset(rx_ring); + bi->page_offset = rx_ring->rx_offset; page_ref_add(page, USHRT_MAX - 1); bi->pagecnt_bias = USHRT_MAX; rx_ring->rx_stats.alloc_rx_page++; @@ -1784,7 +1994,7 @@ static bool ixgbe_is_non_eop(struct ixgbe_ring *rx_ring, static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring, struct sk_buff *skb) { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[0]; unsigned char *va; unsigned int pull_len; @@ -1799,14 +2009,14 @@ static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring, * we need the header to contain the greater of either ETH_HLEN or * 60 bytes if the skb->len is less than 60 for skb_pad. */ - pull_len = eth_get_headlen(va, IXGBE_RX_HDR_SIZE); + pull_len = eth_get_headlen(skb->dev, 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))); /* update all of the pointers */ skb_frag_size_sub(frag, pull_len); - frag->page_offset += pull_len; + skb_frag_off_add(frag, pull_len); skb->data_len -= pull_len; skb->tail += pull_len; } @@ -1824,14 +2034,9 @@ static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring, static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring, struct sk_buff *skb) { - /* if the page was released unmap it, else just sync our portion */ - if (unlikely(IXGBE_CB(skb)->page_released)) { - dma_unmap_page_attrs(rx_ring->dev, IXGBE_CB(skb)->dma, - ixgbe_rx_pg_size(rx_ring), - DMA_FROM_DEVICE, - IXGBE_RX_DMA_ATTR); - } else if (ring_uses_build_skb(rx_ring)) { - unsigned long offset = (unsigned long)(skb->data) & ~PAGE_MASK; + if (ring_uses_build_skb(rx_ring)) { + unsigned long mask = (unsigned long)ixgbe_rx_pg_size(rx_ring) - 1; + unsigned long offset = (unsigned long)(skb->data) & mask; dma_sync_single_range_for_cpu(rx_ring->dev, IXGBE_CB(skb)->dma, @@ -1839,14 +2044,22 @@ static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring, skb_headlen(skb), DMA_FROM_DEVICE); } else { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[0]; dma_sync_single_range_for_cpu(rx_ring->dev, IXGBE_CB(skb)->dma, - frag->page_offset, + skb_frag_off(frag), skb_frag_size(frag), DMA_FROM_DEVICE); } + + /* If the page was released, just unmap it. */ + if (unlikely(IXGBE_CB(skb)->page_released)) { + dma_unmap_page_attrs(rx_ring->dev, IXGBE_CB(skb)->dma, + ixgbe_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + IXGBE_RX_DMA_ATTR); + } } /** @@ -1877,10 +2090,6 @@ bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring, { struct net_device *netdev = rx_ring->netdev; - /* XDP packets use error pointer so abort at this point */ - if (IS_ERR(skb)) - return true; - /* Verify netdev is present, and that packet does not have any * errors that would be unacceptable to the netdev. */ @@ -1938,23 +2147,19 @@ static void ixgbe_reuse_rx_page(struct ixgbe_ring *rx_ring, new_buff->pagecnt_bias = old_buff->pagecnt_bias; } -static inline bool ixgbe_page_is_reserved(struct page *page) -{ - return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page); -} - -static bool ixgbe_can_reuse_rx_page(struct ixgbe_rx_buffer *rx_buffer) +static bool ixgbe_can_reuse_rx_page(struct ixgbe_rx_buffer *rx_buffer, + int rx_buffer_pgcnt) { unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; struct page *page = rx_buffer->page; - /* avoid re-using remote pages */ - if (unlikely(ixgbe_page_is_reserved(page))) + /* 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_buffer_pgcnt - pagecnt_bias) > 1)) return false; #else /* The last offset is a bit aggressive in that we assume the @@ -2003,8 +2208,8 @@ static void ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring, #if (PAGE_SIZE < 8192) unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2; #else - unsigned int truesize = ring_uses_build_skb(rx_ring) ? - SKB_DATA_ALIGN(IXGBE_SKB_PAD + size) : + unsigned int truesize = rx_ring->rx_offset ? + SKB_DATA_ALIGN(rx_ring->rx_offset + size) : SKB_DATA_ALIGN(size); #endif skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page, @@ -2019,11 +2224,18 @@ static void ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring, static struct ixgbe_rx_buffer *ixgbe_get_rx_buffer(struct ixgbe_ring *rx_ring, union ixgbe_adv_rx_desc *rx_desc, struct sk_buff **skb, - const unsigned int size) + const unsigned int size, + int *rx_buffer_pgcnt) { struct ixgbe_rx_buffer *rx_buffer; rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + *rx_buffer_pgcnt = +#if (PAGE_SIZE < 8192) + page_count(rx_buffer->page); +#else + 0; +#endif prefetchw(rx_buffer->page); *skb = rx_buffer->skb; @@ -2053,13 +2265,14 @@ skip_sync: static void ixgbe_put_rx_buffer(struct ixgbe_ring *rx_ring, struct ixgbe_rx_buffer *rx_buffer, - struct sk_buff *skb) + struct sk_buff *skb, + int rx_buffer_pgcnt) { - if (ixgbe_can_reuse_rx_page(rx_buffer)) { + if (ixgbe_can_reuse_rx_page(rx_buffer, rx_buffer_pgcnt)) { /* hand second half of page back to the ring */ ixgbe_reuse_rx_page(rx_ring, rx_buffer); } else { - if (!IS_ERR(skb) && IXGBE_CB(skb)->dma == rx_buffer->dma) { + if (skb && IXGBE_CB(skb)->dma == rx_buffer->dma) { /* the page has been released from the ring */ IXGBE_CB(skb)->page_released = true; } else { @@ -2093,10 +2306,8 @@ static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring, struct sk_buff *skb; /* prefetch first cache line of first page */ - prefetch(xdp->data); -#if L1_CACHE_BYTES < 128 - prefetch(xdp->data + L1_CACHE_BYTES); -#endif + net_prefetch(xdp->data); + /* Note, we get here by enabling legacy-rx via: * * ethtool --set-priv-flags <dev> legacy-rx on @@ -2155,17 +2366,14 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, struct sk_buff *skb; /* Prefetch first cache line of first page. If xdp->data_meta - * is unused, this points extactly as xdp->data, otherwise we + * is unused, this points exactly as xdp->data, otherwise we * likely have a consumer accessing first few bytes of meta * data, and then actual data. */ - prefetch(xdp->data_meta); -#if L1_CACHE_BYTES < 128 - prefetch(xdp->data_meta + L1_CACHE_BYTES); -#endif + net_prefetch(xdp->data_meta); /* build an skb to around the page buffer */ - skb = build_skb(xdp->data_hard_start, truesize); + skb = napi_build_skb(xdp->data_hard_start, truesize); if (unlikely(!skb)) return NULL; @@ -2189,16 +2397,16 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, return skb; } -static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter, - struct ixgbe_ring *rx_ring, - struct xdp_buff *xdp) +static int ixgbe_run_xdp(struct ixgbe_adapter *adapter, + struct ixgbe_ring *rx_ring, + struct xdp_buff *xdp) { int err, result = IXGBE_XDP_PASS; struct bpf_prog *xdp_prog; + struct ixgbe_ring *ring; struct xdp_frame *xdpf; u32 act; - rcu_read_lock(); xdp_prog = READ_ONCE(rx_ring->xdp_prog); if (!xdp_prog) @@ -2211,48 +2419,63 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter, case XDP_PASS: break; case XDP_TX: - xdpf = convert_to_xdp_frame(xdp); - if (unlikely(!xdpf)) { - result = IXGBE_XDP_CONSUMED; - break; - } - result = ixgbe_xmit_xdp_ring(adapter, xdpf); + xdpf = xdp_convert_buff_to_frame(xdp); + if (unlikely(!xdpf)) + goto out_failure; + ring = ixgbe_determine_xdp_ring(adapter); + if (static_branch_unlikely(&ixgbe_xdp_locking_key)) + spin_lock(&ring->tx_lock); + result = ixgbe_xmit_xdp_ring(ring, xdpf); + if (static_branch_unlikely(&ixgbe_xdp_locking_key)) + spin_unlock(&ring->tx_lock); + if (result == IXGBE_XDP_CONSUMED) + goto out_failure; break; case XDP_REDIRECT: err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog); - if (!err) - result = IXGBE_XDP_REDIR; - else - result = IXGBE_XDP_CONSUMED; + if (err) + goto out_failure; + result = IXGBE_XDP_REDIR; break; default: - bpf_warn_invalid_xdp_action(act); - /* fallthrough */ + bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, act); + fallthrough; case XDP_ABORTED: +out_failure: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); - /* fallthrough -- handle aborts by dropping packet */ + fallthrough; /* handle aborts by dropping packet */ case XDP_DROP: result = IXGBE_XDP_CONSUMED; break; } xdp_out: - rcu_read_unlock(); - return ERR_PTR(-result); + return result; +} + +static unsigned int ixgbe_rx_frame_truesize(struct ixgbe_ring *rx_ring, + unsigned int size) +{ + unsigned int truesize; + +#if (PAGE_SIZE < 8192) + truesize = ixgbe_rx_pg_size(rx_ring) / 2; /* Must be power-of-2 */ +#else + truesize = rx_ring->rx_offset ? + SKB_DATA_ALIGN(rx_ring->rx_offset + size) + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) : + SKB_DATA_ALIGN(size); +#endif + return truesize; } static void ixgbe_rx_buffer_flip(struct ixgbe_ring *rx_ring, struct ixgbe_rx_buffer *rx_buffer, unsigned int size) { + unsigned int truesize = ixgbe_rx_frame_truesize(rx_ring, size); #if (PAGE_SIZE < 8192) - unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2; - rx_buffer->page_offset ^= truesize; #else - unsigned int truesize = ring_uses_build_skb(rx_ring) ? - SKB_DATA_ALIGN(IXGBE_SKB_PAD + size) : - SKB_DATA_ALIGN(size); - rx_buffer->page_offset += truesize; #endif } @@ -2266,7 +2489,7 @@ static void ixgbe_rx_buffer_flip(struct ixgbe_ring *rx_ring, * This function provides a "bounce buffer" approach to Rx interrupt * processing. The advantage to this is that on systems that have * expensive overhead for IOMMU access this provides a means of avoiding - * it by maintaining the mapping of the page to the syste. + * it by maintaining the mapping of the page to the system. * * Returns amount of work completed **/ @@ -2274,22 +2497,29 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, struct ixgbe_ring *rx_ring, const int budget) { - unsigned int total_rx_bytes = 0, total_rx_packets = 0; + unsigned int total_rx_bytes = 0, total_rx_packets = 0, frame_sz = 0; struct ixgbe_adapter *adapter = q_vector->adapter; #ifdef IXGBE_FCOE int ddp_bytes; unsigned int mss = 0; #endif /* IXGBE_FCOE */ u16 cleaned_count = ixgbe_desc_unused(rx_ring); + unsigned int offset = rx_ring->rx_offset; unsigned int xdp_xmit = 0; struct xdp_buff xdp; + int xdp_res = 0; - xdp.rxq = &rx_ring->xdp_rxq; + /* Frame size depend on rx_ring setup when PAGE_SIZE=4K */ +#if (PAGE_SIZE < 8192) + frame_sz = ixgbe_rx_frame_truesize(rx_ring, 0); +#endif + xdp_init_buff(&xdp, frame_sz, &rx_ring->xdp_rxq); while (likely(total_rx_packets < budget)) { union ixgbe_adv_rx_desc *rx_desc; struct ixgbe_rx_buffer *rx_buffer; struct sk_buff *skb; + int rx_buffer_pgcnt; unsigned int size; /* return some buffers to hardware, one at a time is too slow */ @@ -2309,23 +2539,24 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, */ dma_rmb(); - rx_buffer = ixgbe_get_rx_buffer(rx_ring, rx_desc, &skb, size); + rx_buffer = ixgbe_get_rx_buffer(rx_ring, rx_desc, &skb, size, &rx_buffer_pgcnt); /* retrieve a buffer from the ring */ if (!skb) { - xdp.data = page_address(rx_buffer->page) + - rx_buffer->page_offset; - xdp.data_meta = xdp.data; - xdp.data_hard_start = xdp.data - - ixgbe_rx_offset(rx_ring); - xdp.data_end = xdp.data + size; - - skb = ixgbe_run_xdp(adapter, rx_ring, &xdp); + unsigned char *hard_start; + + hard_start = page_address(rx_buffer->page) + + rx_buffer->page_offset - offset; + 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 = ixgbe_rx_frame_truesize(rx_ring, size); +#endif + xdp_res = ixgbe_run_xdp(adapter, rx_ring, &xdp); } - if (IS_ERR(skb)) { - unsigned int xdp_res = -PTR_ERR(skb); - + if (xdp_res) { if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) { xdp_xmit |= xdp_res; ixgbe_rx_buffer_flip(rx_ring, rx_buffer, size); @@ -2345,13 +2576,13 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, } /* exit if we failed to retrieve a buffer */ - if (!skb) { + if (!xdp_res && !skb) { rx_ring->rx_stats.alloc_rx_buff_failed++; rx_buffer->pagecnt_bias++; break; } - ixgbe_put_rx_buffer(rx_ring, rx_buffer, skb); + ixgbe_put_rx_buffer(rx_ring, rx_buffer, skb, rx_buffer_pgcnt); cleaned_count++; /* place incomplete frames back on ring for completion */ @@ -2359,7 +2590,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, continue; /* verify the packet layout is correct */ - if (ixgbe_cleanup_headers(rx_ring, rx_desc, skb)) + if (xdp_res || ixgbe_cleanup_headers(rx_ring, rx_desc, skb)) continue; /* probably a little skewed due to removing CRC */ @@ -2400,24 +2631,16 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, } if (xdp_xmit & IXGBE_XDP_REDIR) - xdp_do_flush_map(); + xdp_do_flush(); if (xdp_xmit & IXGBE_XDP_TX) { - struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()]; + struct ixgbe_ring *ring = ixgbe_determine_xdp_ring(adapter); - /* Force memory writes to complete before letting h/w - * know there are new descriptors to fetch. - */ - wmb(); - writel(ring->next_to_use, ring->tail); + ixgbe_xdp_ring_update_tail_locked(ring); } - u64_stats_update_begin(&rx_ring->syncp); - rx_ring->stats.packets += total_rx_packets; - rx_ring->stats.bytes += total_rx_bytes; - u64_stats_update_end(&rx_ring->syncp); - q_vector->rx.total_packets += total_rx_packets; - q_vector->rx.total_bytes += total_rx_bytes; + ixgbe_update_rx_ring_stats(rx_ring, q_vector, total_rx_packets, + total_rx_bytes); return total_rx_packets; } @@ -2468,6 +2691,7 @@ static void ixgbe_configure_msix(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: ixgbe_set_ivar(adapter, -1, 1, v_idx); break; default: @@ -2481,6 +2705,9 @@ static void ixgbe_configure_msix(struct ixgbe_adapter *adapter) IXGBE_EIMS_MAILBOX | IXGBE_EIMS_LSC); + if (adapter->hw.mac.type == ixgbe_mac_e610) + mask &= ~IXGBE_EIMS_FW_EVENT; + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIAC, mask); } @@ -2620,7 +2847,7 @@ adjust_by_size: /* 16K ints/sec to 9.2K ints/sec */ avg_wire_size *= 15; avg_wire_size += 11452; - } else if (avg_wire_size <= 1980) { + } else if (avg_wire_size < 1968) { /* 9.2K ints/sec to 8K ints/sec */ avg_wire_size *= 5; avg_wire_size += 22420; @@ -2653,6 +2880,8 @@ adjust_by_size: case IXGBE_LINK_SPEED_2_5GB_FULL: case IXGBE_LINK_SPEED_1GB_FULL: case IXGBE_LINK_SPEED_10_FULL: + if (avg_wire_size > 8064) + avg_wire_size = 8064; itr += DIV_ROUND_UP(avg_wire_size, IXGBE_ITR_ADAPTIVE_MIN_INC * 64) * IXGBE_ITR_ADAPTIVE_MIN_INC; @@ -2695,6 +2924,7 @@ void ixgbe_write_eitr(struct ixgbe_q_vector *q_vector) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: /* * set the WDIS bit to not clear the timer bits and cause an * immediate assertion of the interrupt @@ -2737,7 +2967,6 @@ static void ixgbe_check_overtemp_subtask(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; u32 eicr = adapter->interrupt_event; - s32 rc; if (test_bit(__IXGBE_DOWN, &adapter->state)) return; @@ -2771,14 +3000,13 @@ static void ixgbe_check_overtemp_subtask(struct ixgbe_adapter *adapter) } /* Check if this is not due to overtemp */ - if (hw->phy.ops.check_overtemp(hw) != IXGBE_ERR_OVERTEMP) + if (!hw->phy.ops.check_overtemp(hw)) return; break; case IXGBE_DEV_ID_X550EM_A_1G_T: case IXGBE_DEV_ID_X550EM_A_1G_T_L: - rc = hw->phy.ops.check_overtemp(hw); - if (rc != IXGBE_ERR_OVERTEMP) + if (!hw->phy.ops.check_overtemp(hw)) return; break; default: @@ -2919,57 +3147,249 @@ static void ixgbe_check_lsc(struct ixgbe_adapter *adapter) } } -static inline void ixgbe_irq_enable_queues(struct ixgbe_adapter *adapter, - u64 qmask) +/** + * ixgbe_check_phy_fw_load - check if PHY FW load failed + * @adapter: pointer to adapter structure + * @link_cfg_err: bitmap from the link info structure + * + * Check if external PHY FW load failed and print an error message if it did. + */ +static void ixgbe_check_phy_fw_load(struct ixgbe_adapter *adapter, + u8 link_cfg_err) +{ + if (!(link_cfg_err & IXGBE_ACI_LINK_EXTERNAL_PHY_LOAD_FAILURE)) { + adapter->flags2 &= ~IXGBE_FLAG2_PHY_FW_LOAD_FAILED; + return; + } + + if (adapter->flags2 & IXGBE_FLAG2_PHY_FW_LOAD_FAILED) + return; + + if (link_cfg_err & IXGBE_ACI_LINK_EXTERNAL_PHY_LOAD_FAILURE) { + netdev_err(adapter->netdev, "Device failed to load the FW for the external PHY. Please download and install the latest NVM for your device and try again\n"); + adapter->flags2 |= IXGBE_FLAG2_PHY_FW_LOAD_FAILED; + } +} + +/** + * ixgbe_check_module_power - check module power level + * @adapter: pointer to adapter structure + * @link_cfg_err: bitmap from the link info structure + * + * Check module power level returned by a previous call to aci_get_link_info + * and print error messages if module power level is not supported. + */ +static void ixgbe_check_module_power(struct ixgbe_adapter *adapter, + u8 link_cfg_err) +{ + /* If module power level is supported, clear the flag. */ + if (!(link_cfg_err & (IXGBE_ACI_LINK_INVAL_MAX_POWER_LIMIT | + IXGBE_ACI_LINK_MODULE_POWER_UNSUPPORTED))) { + adapter->flags2 &= ~IXGBE_FLAG2_MOD_POWER_UNSUPPORTED; + return; + } + + /* If IXGBE_FLAG2_MOD_POWER_UNSUPPORTED was previously set and the + * above block didn't clear this bit, there's nothing to do. + */ + if (adapter->flags2 & IXGBE_FLAG2_MOD_POWER_UNSUPPORTED) + return; + + if (link_cfg_err & IXGBE_ACI_LINK_INVAL_MAX_POWER_LIMIT) { + netdev_err(adapter->netdev, "The installed module is incompatible with the device's NVM image. Cannot start link.\n"); + adapter->flags2 |= IXGBE_FLAG2_MOD_POWER_UNSUPPORTED; + } else if (link_cfg_err & IXGBE_ACI_LINK_MODULE_POWER_UNSUPPORTED) { + netdev_err(adapter->netdev, "The module's power requirements exceed the device's power supply. Cannot start link.\n"); + adapter->flags2 |= IXGBE_FLAG2_MOD_POWER_UNSUPPORTED; + } +} + +/** + * ixgbe_check_link_cfg_err - check if link configuration failed + * @adapter: pointer to adapter structure + * @link_cfg_err: bitmap from the link info structure + * + * Print if any link configuration failure happens due to the value in the + * link_cfg_err parameter in the link info structure. + */ +static void ixgbe_check_link_cfg_err(struct ixgbe_adapter *adapter, + u8 link_cfg_err) +{ + ixgbe_check_module_power(adapter, link_cfg_err); + ixgbe_check_phy_fw_load(adapter, link_cfg_err); +} + +/** + * ixgbe_process_link_status_event - process the link event + * @adapter: pointer to adapter structure + * @link_up: true if the physical link is up and false if it is down + * @link_speed: current link speed received from the link event + * + * Return: 0 on success or negative value on failure. + */ +static int +ixgbe_process_link_status_event(struct ixgbe_adapter *adapter, bool link_up, + u16 link_speed) { - u32 mask; struct ixgbe_hw *hw = &adapter->hw; + int status; - switch (hw->mac.type) { - case ixgbe_mac_82598EB: - mask = (IXGBE_EIMS_RTX_QUEUE & qmask); - IXGBE_WRITE_REG(hw, IXGBE_EIMS, mask); - break; - case ixgbe_mac_82599EB: - case ixgbe_mac_X540: - case ixgbe_mac_X550: - case ixgbe_mac_X550EM_x: - case ixgbe_mac_x550em_a: - mask = (qmask & 0xFFFFFFFF); - if (mask) - IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(0), mask); - mask = (qmask >> 32); - if (mask) - IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(1), mask); - break; - default: - break; + /* Update the link info structures and re-enable link events, + * don't bail on failure due to other book keeping needed. + */ + status = ixgbe_update_link_info(hw); + if (status) + e_dev_err("Failed to update link status, err %d aq_err %d\n", + status, hw->aci.last_status); + + ixgbe_check_link_cfg_err(adapter, hw->link.link_info.link_cfg_err); + + /* Check if the link state is up after updating link info, and treat + * this event as an UP event since the link is actually UP now. + */ + if (hw->link.link_info.link_info & IXGBE_ACI_LINK_UP) + link_up = true; + + /* Turn off PHY if media was removed. */ + if (!(adapter->flags2 & IXGBE_FLAG2_NO_MEDIA) && + !(hw->link.link_info.link_info & IXGBE_ACI_MEDIA_AVAILABLE)) + adapter->flags2 |= IXGBE_FLAG2_NO_MEDIA; + + if (link_up == adapter->link_up && + link_up == netif_carrier_ok(adapter->netdev) && + link_speed == adapter->link_speed) + return 0; + + adapter->flags |= IXGBE_FLAG_NEED_LINK_UPDATE; + adapter->link_check_timeout = jiffies; + ixgbe_watchdog_update_link(adapter); + + if (link_up) + ixgbe_watchdog_link_is_up(adapter); + else + ixgbe_watchdog_link_is_down(adapter); + + return 0; +} + +/** + * ixgbe_handle_link_status_event - handle link status event via ACI + * @adapter: pointer to adapter structure + * @e: event structure containing link status info + */ +static void +ixgbe_handle_link_status_event(struct ixgbe_adapter *adapter, + struct ixgbe_aci_event *e) +{ + struct ixgbe_aci_cmd_get_link_status_data *link_data; + u16 link_speed; + bool link_up; + + link_data = (struct ixgbe_aci_cmd_get_link_status_data *)e->msg_buf; + + link_up = !!(link_data->link_info & IXGBE_ACI_LINK_UP); + link_speed = le16_to_cpu(link_data->link_speed); + + if (ixgbe_process_link_status_event(adapter, link_up, link_speed)) + e_dev_warn("Could not process link status event"); +} + +/** + * ixgbe_schedule_fw_event - schedule Firmware event + * @adapter: pointer to the adapter structure + * + * If the adapter is not in down, removing or resetting state, + * an event is scheduled. + */ +static void ixgbe_schedule_fw_event(struct ixgbe_adapter *adapter) +{ + if (!test_bit(__IXGBE_DOWN, &adapter->state) && + !test_bit(__IXGBE_REMOVING, &adapter->state) && + !test_bit(__IXGBE_RESETTING, &adapter->state)) { + adapter->flags2 |= IXGBE_FLAG2_FW_ASYNC_EVENT; + ixgbe_service_event_schedule(adapter); } - /* skip the flush */ } -static inline void ixgbe_irq_disable_queues(struct ixgbe_adapter *adapter, - u64 qmask) +/** + * ixgbe_aci_event_cleanup - release msg_buf memory + * @event: pointer to the event holding msg_buf to be released + * + * Clean memory allocated for event's msg_buf. Implements auto memory cleanup. + */ +static void ixgbe_aci_event_cleanup(struct ixgbe_aci_event *event) { - u32 mask; + kfree(event->msg_buf); +} + +/** + * ixgbe_handle_fw_event - handle Firmware event + * @adapter: pointer to the adapter structure + * + * Obtain an event from the ACI and then and then process it according to the + * type of the event and the opcode. + */ +static void ixgbe_handle_fw_event(struct ixgbe_adapter *adapter) +{ + struct ixgbe_aci_event event __cleanup(ixgbe_aci_event_cleanup); struct ixgbe_hw *hw = &adapter->hw; + bool pending = false; + int err; + + if (adapter->flags2 & IXGBE_FLAG2_FW_ASYNC_EVENT) + adapter->flags2 &= ~IXGBE_FLAG2_FW_ASYNC_EVENT; + event.buf_len = IXGBE_ACI_MAX_BUFFER_SIZE; + event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL); + if (!event.msg_buf) + return; + + do { + err = ixgbe_aci_get_event(hw, &event, &pending); + if (err) + break; + + switch (le16_to_cpu(event.desc.opcode)) { + case ixgbe_aci_opc_get_link_status: + ixgbe_handle_link_status_event(adapter, &event); + break; + case ixgbe_aci_opc_temp_tca_event: + e_crit(drv, "%s\n", ixgbe_overheat_msg); + ixgbe_down(adapter); + break; + case libie_aqc_opc_fw_logs_event: + libie_get_fwlog_data(&hw->fwlog, event.msg_buf, + le16_to_cpu(event.desc.datalen)); + break; + default: + e_warn(hw, "unknown FW async event captured\n"); + break; + } + } while (pending); +} + +static inline void ixgbe_irq_enable_queues(struct ixgbe_adapter *adapter, + u64 qmask) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 mask; switch (hw->mac.type) { case ixgbe_mac_82598EB: mask = (IXGBE_EIMS_RTX_QUEUE & qmask); - IXGBE_WRITE_REG(hw, IXGBE_EIMC, mask); + IXGBE_WRITE_REG(hw, IXGBE_EIMS, mask); break; case ixgbe_mac_82599EB: case ixgbe_mac_X540: case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: mask = (qmask & 0xFFFFFFFF); if (mask) - IXGBE_WRITE_REG(hw, IXGBE_EIMC_EX(0), mask); + IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(0), mask); mask = (qmask >> 32); if (mask) - IXGBE_WRITE_REG(hw, IXGBE_EIMC_EX(1), mask); + IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(1), mask); break; default: break; @@ -3013,10 +3433,13 @@ static inline void ixgbe_irq_enable(struct ixgbe_adapter *adapter, bool queues, case ixgbe_mac_82599EB: mask |= IXGBE_EIMS_GPI_SDP1(hw); mask |= IXGBE_EIMS_GPI_SDP2(hw); - /* fall through */ + fallthrough; case ixgbe_mac_X540: case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: + case ixgbe_mac_e610: + mask |= IXGBE_EIMS_FW_EVENT; + fallthrough; case ixgbe_mac_x550em_a: if (adapter->hw.device_id == IXGBE_DEV_ID_X550EM_X_SFP || adapter->hw.device_id == IXGBE_DEV_ID_X550EM_A_SFP || @@ -3073,12 +3496,16 @@ static irqreturn_t ixgbe_msix_other(int irq, void *data) if (eicr & IXGBE_EICR_MAILBOX) ixgbe_msg_task(adapter); + if (eicr & IXGBE_EICR_FW_EVENT) + ixgbe_schedule_fw_event(adapter); + switch (hw->mac.type) { case ixgbe_mac_82599EB: case ixgbe_mac_X540: case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: if (hw->phy.type == ixgbe_phy_x550em_ext_t && (eicr & IXGBE_EICR_GPI_SDP0_X540)) { adapter->flags2 |= IXGBE_FLAG2_PHY_INTERRUPT; @@ -3162,7 +3589,7 @@ int ixgbe_poll(struct napi_struct *napi, int budget) #endif ixgbe_for_each_ring(ring, q_vector->tx) { - bool wd = ring->xsk_umem ? + bool wd = ring->xsk_pool ? ixgbe_clean_xdp_tx_irq(q_vector, ring, budget) : ixgbe_clean_tx_irq(q_vector, ring, budget); @@ -3182,7 +3609,7 @@ int ixgbe_poll(struct napi_struct *napi, int budget) per_ring_budget = budget; ixgbe_for_each_ring(ring, q_vector->rx) { - int cleaned = ring->xsk_umem ? + int cleaned = ring->xsk_pool ? ixgbe_clean_rx_irq_zc(q_vector, ring, per_ring_budget) : ixgbe_clean_rx_irq(q_vector, ring, @@ -3250,8 +3677,8 @@ static int ixgbe_request_msix_irqs(struct ixgbe_adapter *adapter) /* If Flow Director is enabled, set interrupt affinity */ if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) { /* assign the mask for this irq */ - irq_set_affinity_hint(entry->vector, - &q_vector->affinity_mask); + irq_update_affinity_hint(entry->vector, + &q_vector->affinity_mask); } } @@ -3267,8 +3694,8 @@ static int ixgbe_request_msix_irqs(struct ixgbe_adapter *adapter) free_queue_irqs: while (vector) { vector--; - irq_set_affinity_hint(adapter->msix_entries[vector].vector, - NULL); + irq_update_affinity_hint(adapter->msix_entries[vector].vector, + NULL); free_irq(adapter->msix_entries[vector].vector, adapter->q_vector[vector]); } @@ -3316,14 +3743,18 @@ static irqreturn_t ixgbe_intr(int irq, void *data) if (eicr & IXGBE_EICR_LSC) ixgbe_check_lsc(adapter); + if (eicr & IXGBE_EICR_FW_EVENT) + ixgbe_schedule_fw_event(adapter); + switch (hw->mac.type) { case ixgbe_mac_82599EB: ixgbe_check_sfp_event(adapter, eicr); - /* Fall through */ + fallthrough; case ixgbe_mac_X540: case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: if (eicr & IXGBE_EICR_ECC) { e_info(link, "Received ECC Err, initiating reset\n"); set_bit(__IXGBE_RESET_REQUESTED, &adapter->state); @@ -3401,7 +3832,7 @@ static void ixgbe_free_irq(struct ixgbe_adapter *adapter) continue; /* clear the affinity_mask in the IRQ descriptor */ - irq_set_affinity_hint(entry->vector, NULL); + irq_update_affinity_hint(entry->vector, NULL); free_irq(entry->vector, q_vector); } @@ -3424,6 +3855,7 @@ static inline void ixgbe_irq_disable(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, 0xFFFF0000); IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC_EX(0), ~0); IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC_EX(1), ~0); @@ -3477,9 +3909,9 @@ void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter, u32 txdctl = IXGBE_TXDCTL_ENABLE; u8 reg_idx = ring->reg_idx; - ring->xsk_umem = NULL; + ring->xsk_pool = NULL; if (ring_is_xdp(ring)) - ring->xsk_umem = ixgbe_xsk_umem(adapter, ring); + ring->xsk_pool = ixgbe_xsk_pool(adapter, ring); /* disable queue to avoid issues while updating state */ IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), 0); @@ -3671,8 +4103,12 @@ void ixgbe_set_rx_drop_en(struct ixgbe_adapter *adapter) static void ixgbe_set_rx_drop_en(struct ixgbe_adapter *adapter) #endif { - int i; bool pfc_en = adapter->dcb_cfg.pfc_mode_enable; + struct ixgbe_hw *hw = &adapter->hw; + int i; + + if (hw->mac.ops.disable_mdd) + hw->mac.ops.disable_mdd(hw); if (adapter->ixgbe_ieee_pfc) pfc_en |= !!(adapter->ixgbe_ieee_pfc->pfc_en); @@ -3694,6 +4130,9 @@ static void ixgbe_set_rx_drop_en(struct ixgbe_adapter *adapter) for (i = 0; i < adapter->num_rx_queues; i++) ixgbe_disable_rx_drop(adapter, adapter->rx_ring[i]); } + + if (hw->mac.ops.enable_mdd) + hw->mac.ops.enable_mdd(hw); } #define IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT 2 @@ -3719,9 +4158,8 @@ static void ixgbe_configure_srrctl(struct ixgbe_adapter *adapter, srrctl = IXGBE_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT; /* configure the packet buffer length */ - if (rx_ring->xsk_umem) { - u32 xsk_buf_len = rx_ring->xsk_umem->chunk_size_nohr - - XDP_PACKET_HEADROOM; + if (rx_ring->xsk_pool) { + u32 xsk_buf_len = xsk_pool_get_rx_frame_size(rx_ring->xsk_pool); /* If the MAC support setting RXDCTL.RLPML, the * SRRCTL[n].BSIZEPKT is set to PAGE_SIZE and @@ -3953,8 +4391,11 @@ static void ixgbe_setup_mrqc(struct ixgbe_adapter *adapter) else mrqc = IXGBE_MRQC_VMDQRSS64EN; - /* Enable L3/L4 for Tx Switched packets */ - mrqc |= IXGBE_MRQC_L3L4TXSWEN; + /* Enable L3/L4 for Tx Switched packets only for X550, + * older devices do not support this feature + */ + if (hw->mac.type >= ixgbe_mac_X550) + mrqc |= IXGBE_MRQC_L3L4TXSWEN; } else { if (tcs > 4) mrqc = IXGBE_MRQC_RTRSS8TCEN; @@ -4063,13 +4504,12 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, u8 reg_idx = ring->reg_idx; xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); - ring->xsk_umem = ixgbe_xsk_umem(adapter, ring); - if (ring->xsk_umem) { - ring->zca.free = ixgbe_zca_free; + ring->xsk_pool = ixgbe_xsk_pool(adapter, ring); + if (ring->xsk_pool) { WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, - MEM_TYPE_ZERO_COPY, - &ring->zca)); - + MEM_TYPE_XSK_BUFF_POOL, + NULL)); + xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq); } else { WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_PAGE_SHARED, NULL)); @@ -4124,9 +4564,10 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, #endif } - if (ring->xsk_umem && hw->mac.type != ixgbe_mac_82599EB) { - u32 xsk_buf_len = ring->xsk_umem->chunk_size_nohr - - XDP_PACKET_HEADROOM; + ring->rx_offset = ixgbe_rx_offset(ring); + + if (ring->xsk_pool && hw->mac.type != ixgbe_mac_82599EB) { + u32 xsk_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool); rxdctl &= ~(IXGBE_RXDCTL_RLPMLMASK | IXGBE_RXDCTL_RLPML_EN); @@ -4148,7 +4589,7 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl); ixgbe_rx_desc_queue_enable(adapter, ring); - if (ring->xsk_umem) + if (ring->xsk_pool) ixgbe_alloc_rx_buffers_zc(ring, ixgbe_desc_unused(ring)); else ixgbe_alloc_rx_buffers(ring, ixgbe_desc_unused(ring)); @@ -4301,7 +4742,6 @@ static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter) if (test_bit(__IXGBE_RX_FCOE, &rx_ring->state)) set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state); - clear_bit(__IXGBE_RX_BUILD_SKB_ENABLED, &rx_ring->state); if (adapter->flags2 & IXGBE_FLAG2_RX_LEGACY) continue; @@ -4340,9 +4780,10 @@ static void ixgbe_setup_rdrxctl(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: if (adapter->num_vfs) rdrxctl |= IXGBE_RDRXCTL_PSP; - /* fall through */ + fallthrough; case ixgbe_mac_82599EB: case ixgbe_mac_X540: /* Disable RSC for ACK packets */ @@ -4415,7 +4856,7 @@ static void ixgbe_configure_rx(struct ixgbe_adapter *adapter) static int ixgbe_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; /* add VID to filter table */ @@ -4474,7 +4915,7 @@ void ixgbe_update_pf_promisc_vlvf(struct ixgbe_adapter *adapter, u32 vid) static int ixgbe_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; /* remove VID from filter table */ @@ -4507,6 +4948,7 @@ static void ixgbe_vlan_strip_disable(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: for (i = 0; i < adapter->num_rx_queues; i++) { struct ixgbe_ring *ring = adapter->rx_ring[i]; @@ -4545,6 +4987,7 @@ static void ixgbe_vlan_strip_enable(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: for (i = 0; i < adapter->num_rx_queues; i++) { struct ixgbe_ring *ring = adapter->rx_ring[i]; @@ -4619,7 +5062,7 @@ static void ixgbe_scrub_vfta(struct ixgbe_adapter *adapter, u32 vfta_offset) /* pull VLAN ID from VLVF */ vid = vlvf & VLAN_VID_MASK; - /* only concern outselves with a certain range */ + /* only concern ourselves with a certain range */ if (vid < vid_start || vid >= vid_end) continue; @@ -4697,7 +5140,7 @@ static void ixgbe_restore_vlan(struct ixgbe_adapter *adapter) **/ static int ixgbe_write_mc_addr_list(struct net_device *netdev) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; if (!netif_running(netdev)) @@ -4873,7 +5316,7 @@ int ixgbe_del_mac_filter(struct ixgbe_adapter *adapter, static int ixgbe_uc_sync(struct net_device *netdev, const unsigned char *addr) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); int ret; ret = ixgbe_add_mac_filter(adapter, addr, VMDQ_P(0)); @@ -4883,7 +5326,7 @@ static int ixgbe_uc_sync(struct net_device *netdev, const unsigned char *addr) static int ixgbe_uc_unsync(struct net_device *netdev, const unsigned char *addr) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); ixgbe_del_mac_filter(adapter, addr, VMDQ_P(0)); @@ -4901,7 +5344,7 @@ static int ixgbe_uc_unsync(struct net_device *netdev, const unsigned char *addr) **/ void ixgbe_set_rx_mode(struct net_device *netdev) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; u32 fctrl, vmolr = IXGBE_VMOLR_BAM | IXGBE_VMOLR_AUPE; netdev_features_t features = netdev->features; @@ -5001,24 +5444,41 @@ static void ixgbe_napi_disable_all(struct ixgbe_adapter *adapter) napi_disable(&adapter->q_vector[q_idx]->napi); } -static void ixgbe_clear_udp_tunnel_port(struct ixgbe_adapter *adapter, u32 mask) +static int ixgbe_udp_tunnel_sync(struct net_device *dev, unsigned int table) { + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); struct ixgbe_hw *hw = &adapter->hw; - u32 vxlanctrl; + struct udp_tunnel_info ti; - if (!(adapter->flags & (IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE | - IXGBE_FLAG_GENEVE_OFFLOAD_CAPABLE))) - return; + udp_tunnel_nic_get_port(dev, table, 0, &ti); + if (ti.type == UDP_TUNNEL_TYPE_VXLAN) + adapter->vxlan_port = ti.port; + else + adapter->geneve_port = ti.port; - vxlanctrl = IXGBE_READ_REG(hw, IXGBE_VXLANCTRL) & ~mask; - IXGBE_WRITE_REG(hw, IXGBE_VXLANCTRL, vxlanctrl); + IXGBE_WRITE_REG(hw, IXGBE_VXLANCTRL, + ntohs(adapter->vxlan_port) | + ntohs(adapter->geneve_port) << + IXGBE_VXLANCTRL_GENEVE_UDPPORT_SHIFT); + return 0; +} - if (mask & IXGBE_VXLANCTRL_VXLAN_UDPPORT_MASK) - adapter->vxlan_port = 0; +static const struct udp_tunnel_nic_info ixgbe_udp_tunnels_x550 = { + .sync_table = ixgbe_udp_tunnel_sync, + .flags = UDP_TUNNEL_NIC_INFO_IPV4_ONLY, + .tables = { + { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, }, + }, +}; - if (mask & IXGBE_VXLANCTRL_GENEVE_UDPPORT_MASK) - adapter->geneve_port = 0; -} +static const struct udp_tunnel_nic_info ixgbe_udp_tunnels_x550em_a = { + .sync_table = ixgbe_udp_tunnel_sync, + .flags = UDP_TUNNEL_NIC_INFO_IPV4_ONLY, + .tables = { + { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, }, + { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, }, + }, +}; #ifdef CONFIG_IXGBE_DCB /** @@ -5036,15 +5496,15 @@ static void ixgbe_configure_dcb(struct ixgbe_adapter *adapter) if (!(adapter->flags & IXGBE_FLAG_DCB_ENABLED)) { if (hw->mac.type == ixgbe_mac_82598EB) - netif_set_gso_max_size(adapter->netdev, 65536); + netif_set_tso_max_size(adapter->netdev, 65536); return; } if (hw->mac.type == ixgbe_mac_82598EB) - netif_set_gso_max_size(adapter->netdev, 32768); + netif_set_tso_max_size(adapter->netdev, 32768); #ifdef IXGBE_FCOE - if (adapter->netdev->features & NETIF_F_FCOE_MTU) + if (adapter->netdev->fcoe_mtu) max_frame = max(max_frame, IXGBE_FCOE_JUMBO_FRAME_SIZE); #endif @@ -5101,8 +5561,7 @@ 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) && - (tc < IXGBE_FCOE_JUMBO_FRAME_SIZE) && + if (dev->fcoe_mtu && tc < IXGBE_FCOE_JUMBO_FRAME_SIZE && (pb == ixgbe_fcoe_get_tc(adapter))) tc = IXGBE_FCOE_JUMBO_FRAME_SIZE; #endif @@ -5113,6 +5572,7 @@ static int ixgbe_hpbthresh(struct ixgbe_adapter *adapter, int pb) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: dv_id = IXGBE_DV_X540(link, tc); break; default: @@ -5145,7 +5605,7 @@ static int ixgbe_hpbthresh(struct ixgbe_adapter *adapter, int pb) } /** - * ixgbe_lpbthresh - calculate low water mark for for flow control + * ixgbe_lpbthresh - calculate low water mark for flow control * * @adapter: board private structure to calculate for * @pb: packet buffer to calculate @@ -5162,8 +5622,7 @@ static int ixgbe_lpbthresh(struct ixgbe_adapter *adapter, int pb) #ifdef IXGBE_FCOE /* FCoE traffic class uses FCOE jumbo frames */ - if ((dev->features & NETIF_F_FCOE_MTU) && - (tc < IXGBE_FCOE_JUMBO_FRAME_SIZE) && + if (dev->fcoe_mtu && tc < IXGBE_FCOE_JUMBO_FRAME_SIZE && (pb == netdev_get_prio_tc_map(dev, adapter->fcoe.up))) tc = IXGBE_FCOE_JUMBO_FRAME_SIZE; #endif @@ -5174,6 +5633,7 @@ static int ixgbe_lpbthresh(struct ixgbe_adapter *adapter, int pb) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: dv_id = IXGBE_LOW_DV_X540(tc); break; default: @@ -5231,7 +5691,7 @@ static void ixgbe_fdir_filter_restore(struct ixgbe_adapter *adapter) struct ixgbe_hw *hw = &adapter->hw; struct hlist_node *node2; struct ixgbe_fdir_filter *filter; - u64 action; + u8 queue; spin_lock(&adapter->fdir_perfect_lock); @@ -5240,17 +5700,34 @@ static void ixgbe_fdir_filter_restore(struct ixgbe_adapter *adapter) hlist_for_each_entry_safe(filter, node2, &adapter->fdir_filter_list, fdir_node) { - action = filter->action; - if (action != IXGBE_FDIR_DROP_QUEUE && action != 0) - action = - (action >> ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF) - 1; + if (filter->action == IXGBE_FDIR_DROP_QUEUE) { + queue = IXGBE_FDIR_DROP_QUEUE; + } else { + u32 ring = ethtool_get_flow_spec_ring(filter->action); + u8 vf = ethtool_get_flow_spec_ring_vf(filter->action); + + if (!vf && (ring >= adapter->num_rx_queues)) { + e_err(drv, "FDIR restore failed without VF, ring: %u\n", + ring); + continue; + } else if (vf && + ((vf > adapter->num_vfs) || + ring >= adapter->num_rx_queues_per_pool)) { + e_err(drv, "FDIR restore failed with VF, vf: %hhu, ring: %u\n", + vf, ring); + continue; + } + + /* Map the ring onto the absolute queue index */ + if (!vf) + queue = adapter->rx_ring[ring]->reg_idx; + else + queue = ((vf - 1) * + adapter->num_rx_queues_per_pool) + ring; + } ixgbe_fdir_write_perfect_filter_82599(hw, - &filter->filter, - filter->sw_idx, - (action == IXGBE_FDIR_DROP_QUEUE) ? - IXGBE_FDIR_DROP_QUEUE : - adapter->rx_ring[action]->reg_idx); + &filter->filter, filter->sw_idx, queue); } spin_unlock(&adapter->fdir_perfect_lock); @@ -5265,7 +5742,7 @@ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring) u16 i = rx_ring->next_to_clean; struct ixgbe_rx_buffer *rx_buffer = &rx_ring->rx_buffer_info[i]; - if (rx_ring->xsk_umem) { + if (rx_ring->xsk_pool) { ixgbe_xsk_clean_rx_ring(rx_ring); goto skip_free; } @@ -5369,9 +5846,10 @@ static int ixgbe_fwd_ring_up(struct ixgbe_adapter *adapter, return err; } -static int ixgbe_macvlan_up(struct net_device *vdev, void *data) +static int ixgbe_macvlan_up(struct net_device *vdev, + struct netdev_nested_priv *priv) { - struct ixgbe_adapter *adapter = data; + struct ixgbe_adapter *adapter = (struct ixgbe_adapter *)priv->data; struct ixgbe_fwd_adapter *accel; if (!netif_is_macvlan(vdev)) @@ -5388,8 +5866,12 @@ static int ixgbe_macvlan_up(struct net_device *vdev, void *data) static void ixgbe_configure_dfwd(struct ixgbe_adapter *adapter) { + struct netdev_nested_priv priv = { + .data = (void *)adapter, + }; + netdev_walk_all_upper_dev_rcu(adapter->netdev, - ixgbe_macvlan_up, adapter); + ixgbe_macvlan_up, &priv); } static void ixgbe_configure(struct ixgbe_adapter *adapter) @@ -5454,6 +5936,48 @@ static void ixgbe_configure(struct ixgbe_adapter *adapter) } /** + * ixgbe_enable_link_status_events - enable link status events + * @adapter: pointer to the adapter structure + * @mask: event mask to be set + * + * Enables link status events by invoking ixgbe_configure_lse() + * + * Return: the exit code of the operation. + */ +static int ixgbe_enable_link_status_events(struct ixgbe_adapter *adapter, + u16 mask) +{ + int err; + + err = ixgbe_configure_lse(&adapter->hw, true, mask); + if (err) + return err; + + adapter->lse_mask = mask; + return 0; +} + +/** + * ixgbe_disable_link_status_events - disable link status events + * @adapter: pointer to the adapter structure + * + * Disables link status events by invoking ixgbe_configure_lse() + * + * Return: the exit code of the operation. + */ +static int ixgbe_disable_link_status_events(struct ixgbe_adapter *adapter) +{ + int err; + + err = ixgbe_configure_lse(&adapter->hw, false, adapter->lse_mask); + if (err) + return err; + + adapter->lse_mask = 0; + return 0; +} + +/** * ixgbe_sfp_link_config - set up SFP+ link * @adapter: pointer to private adapter struct **/ @@ -5476,13 +6000,21 @@ static void ixgbe_sfp_link_config(struct ixgbe_adapter *adapter) * ixgbe_non_sfp_link_config - set up non-SFP+ link * @hw: pointer to private hardware struct * - * Returns 0 on success, negative on failure + * Configure non-SFP link. + * + * Return: 0 on success, negative on failure **/ static int ixgbe_non_sfp_link_config(struct ixgbe_hw *hw) { - u32 speed; + struct ixgbe_adapter *adapter = container_of(hw, struct ixgbe_adapter, + hw); + u16 mask = ~((u16)(IXGBE_ACI_LINK_EVENT_UPDOWN | + IXGBE_ACI_LINK_EVENT_MEDIA_NA | + IXGBE_ACI_LINK_EVENT_MODULE_QUAL_FAIL | + IXGBE_ACI_LINK_EVENT_PHY_FW_LOAD_FAIL)); bool autoneg, link_up = false; - int ret = IXGBE_ERR_LINK_SETUP; + int ret = -EIO; + u32 speed; if (hw->mac.ops.check_link) ret = hw->mac.ops.check_link(hw, &speed, &link_up, false); @@ -5491,18 +6023,107 @@ static int ixgbe_non_sfp_link_config(struct ixgbe_hw *hw) return ret; speed = hw->phy.autoneg_advertised; - if ((!speed) && (hw->mac.ops.get_link_capabilities)) + if (!speed && hw->mac.ops.get_link_capabilities) { ret = hw->mac.ops.get_link_capabilities(hw, &speed, &autoneg); + /* remove NBASE-T speeds from default autonegotiation + * to accommodate broken network switches in the field + * which cannot cope with advertised NBASE-T speeds + */ + speed &= ~(IXGBE_LINK_SPEED_5GB_FULL | + IXGBE_LINK_SPEED_2_5GB_FULL); + } + if (ret) return ret; - if (hw->mac.ops.setup_link) + if (hw->mac.ops.setup_link) { + if (adapter->hw.mac.type == ixgbe_mac_e610) { + ret = ixgbe_enable_link_status_events(adapter, mask); + if (ret) + return ret; + } ret = hw->mac.ops.setup_link(hw, speed, link_up); + } return ret; } +/** + * ixgbe_check_media_subtask - check for media + * @adapter: pointer to adapter structure + * + * If media is available then initialize PHY user configuration. Configure the + * PHY if the interface is up. + */ +static void ixgbe_check_media_subtask(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + + /* No need to check for media if it's already present */ + if (!(adapter->flags2 & IXGBE_FLAG2_NO_MEDIA)) + return; + + /* Refresh link info and check if media is present */ + if (ixgbe_update_link_info(hw)) + return; + + ixgbe_check_link_cfg_err(adapter, hw->link.link_info.link_cfg_err); + + if (hw->link.link_info.link_info & IXGBE_ACI_MEDIA_AVAILABLE) { + /* PHY settings are reset on media insertion, reconfigure + * PHY to preserve settings. + */ + if (!(ixgbe_non_sfp_link_config(&adapter->hw))) + adapter->flags2 &= ~IXGBE_FLAG2_NO_MEDIA; + + /* A Link Status Event will be generated; the event handler + * will complete bringing the interface up + */ + } +} + +/** + * ixgbe_clear_vf_stats_counters - Clear out VF stats after reset + * @adapter: board private structure + * + * On a reset we need to clear out the VF stats or accounting gets + * messed up because they're not clear on read. + **/ +static void ixgbe_clear_vf_stats_counters(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + int i; + + for (i = 0; i < adapter->num_vfs; i++) { + adapter->vfinfo[i].last_vfstats.gprc = + IXGBE_READ_REG(hw, IXGBE_PVFGPRC(i)); + adapter->vfinfo[i].saved_rst_vfstats.gprc += + adapter->vfinfo[i].vfstats.gprc; + adapter->vfinfo[i].vfstats.gprc = 0; + adapter->vfinfo[i].last_vfstats.gptc = + IXGBE_READ_REG(hw, IXGBE_PVFGPTC(i)); + adapter->vfinfo[i].saved_rst_vfstats.gptc += + adapter->vfinfo[i].vfstats.gptc; + adapter->vfinfo[i].vfstats.gptc = 0; + adapter->vfinfo[i].last_vfstats.gorc = + IXGBE_READ_REG(hw, IXGBE_PVFGORC_LSB(i)); + adapter->vfinfo[i].saved_rst_vfstats.gorc += + adapter->vfinfo[i].vfstats.gorc; + adapter->vfinfo[i].vfstats.gorc = 0; + adapter->vfinfo[i].last_vfstats.gotc = + IXGBE_READ_REG(hw, IXGBE_PVFGOTC_LSB(i)); + adapter->vfinfo[i].saved_rst_vfstats.gotc += + adapter->vfinfo[i].vfstats.gotc; + adapter->vfinfo[i].vfstats.gotc = 0; + adapter->vfinfo[i].last_vfstats.mprc = + IXGBE_READ_REG(hw, IXGBE_PVFMPRC(i)); + adapter->vfinfo[i].saved_rst_vfstats.mprc += + adapter->vfinfo[i].vfstats.mprc; + adapter->vfinfo[i].vfstats.mprc = 0; + } +} + static void ixgbe_setup_gpie(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; @@ -5525,6 +6146,7 @@ static void ixgbe_setup_gpie(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: default: IXGBE_WRITE_REG(hw, IXGBE_EIAM_EX(0), 0xFFFFFFFF); IXGBE_WRITE_REG(hw, IXGBE_EIAM_EX(1), 0xFFFFFFFF); @@ -5638,15 +6260,18 @@ static void ixgbe_up_complete(struct ixgbe_adapter *adapter) adapter->link_check_timeout = jiffies; mod_timer(&adapter->service_timer, jiffies); + ixgbe_clear_vf_stats_counters(adapter); /* Set PF Reset Done bit so PF/VF Mail Ops can work */ ctrl_ext = IXGBE_READ_REG(hw, IXGBE_CTRL_EXT); ctrl_ext |= IXGBE_CTRL_EXT_PFRSTD; IXGBE_WRITE_REG(hw, IXGBE_CTRL_EXT, ctrl_ext); + + /* update setting rx tx for all active vfs */ + ixgbe_set_all_vfs(adapter); } void ixgbe_reinit_locked(struct ixgbe_adapter *adapter) { - WARN_ON(in_interrupt()); /* put off any impending NetWatchDogTimeout */ netif_trans_update(adapter->netdev); @@ -5872,10 +6497,11 @@ dma_engine_disable: case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: IXGBE_WRITE_REG(hw, IXGBE_DMATXCTL, (IXGBE_READ_REG(hw, IXGBE_DMATXCTL) & ~IXGBE_DMATXCTL_TE)); - /* fall through */ + fallthrough; default: break; } @@ -5901,13 +6527,13 @@ void ixgbe_reset(struct ixgbe_adapter *adapter) err = hw->mac.ops.init_hw(hw); switch (err) { case 0: - case IXGBE_ERR_SFP_NOT_PRESENT: - case IXGBE_ERR_SFP_NOT_SUPPORTED: + case -ENOENT: + case -EOPNOTSUPP: break; - case IXGBE_ERR_MASTER_REQUESTS_PENDING: - e_dev_err("master disable timed out\n"); + case -EALREADY: + e_dev_err("primary disable timed out\n"); break; - case IXGBE_ERR_EEPROM_VERSION: + case -EACCES: /* We are running on a pre-production device, log a warning */ e_dev_warn("This device is a pre-production adapter/LOM. " "Please be aware there may be issues associated with " @@ -5953,7 +6579,7 @@ static void ixgbe_clean_tx_ring(struct ixgbe_ring *tx_ring) u16 i = tx_ring->next_to_clean; struct ixgbe_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i]; - if (tx_ring->xsk_umem) { + if (tx_ring->xsk_pool) { ixgbe_xsk_clean_tx_ring(tx_ring); goto out; } @@ -6090,7 +6716,7 @@ void ixgbe_down(struct ixgbe_adapter *adapter) adapter->flags2 &= ~IXGBE_FLAG2_FDIR_REQUIRES_REINIT; adapter->flags &= ~IXGBE_FLAG_NEED_LINK_UPDATE; - del_timer_sync(&adapter->service_timer); + timer_delete_sync(&adapter->service_timer); if (adapter->num_vfs) { /* Clear EITR Select mapping */ @@ -6100,11 +6726,8 @@ void ixgbe_down(struct ixgbe_adapter *adapter) for (i = 0 ; i < adapter->num_vfs; i++) adapter->vfinfo[i].clear_to_send = false; - /* ping all the active vfs to let them know we are going down */ - ixgbe_ping_all_vfs(adapter); - - /* Disable all VFTE/VFRE TX/RX */ - ixgbe_disable_tx_rx(adapter); + /* update setting rx tx for all active vfs */ + ixgbe_set_all_vfs(adapter); } /* disable transmits in the hardware now that interrupts are off */ @@ -6119,10 +6742,12 @@ void ixgbe_down(struct ixgbe_adapter *adapter) ixgbe_clean_all_tx_rings(adapter); ixgbe_clean_all_rx_rings(adapter); + if (adapter->hw.mac.type == ixgbe_mac_e610) + ixgbe_disable_link_status_events(adapter); } /** - * ixgbe_eee_capable - helper function to determine EEE support on X550 + * ixgbe_set_eee_capable - helper function to determine EEE support on X550 * @adapter: board private structure */ static void ixgbe_set_eee_capable(struct ixgbe_adapter *adapter) @@ -6149,10 +6774,11 @@ static void ixgbe_set_eee_capable(struct ixgbe_adapter *adapter) /** * ixgbe_tx_timeout - Respond to a Tx Hang * @netdev: network interface device structure + * @txqueue: queue number that timed out **/ -static void ixgbe_tx_timeout(struct net_device *netdev) +static void ixgbe_tx_timeout(struct net_device *netdev, unsigned int __always_unused txqueue) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); /* Do the reset outside of interrupt context */ ixgbe_tx_timeout_reset(adapter); @@ -6173,6 +6799,7 @@ static void ixgbe_init_dcb(struct ixgbe_adapter *adapter) break; case ixgbe_mac_X540: case ixgbe_mac_X550: + case ixgbe_mac_e610: adapter->dcb_cfg.num_tcs.pg_tcs = X540_TRAFFIC_CLASS; adapter->dcb_cfg.num_tcs.pfc_tcs = X540_TRAFFIC_CLASS; break; @@ -6236,6 +6863,8 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter, hw->subsystem_vendor_id = pdev->subsystem_vendor; hw->subsystem_device_id = pdev->subsystem_device; + hw->mac.max_link_up_time = IXGBE_LINK_UP_TIME; + /* get_invariants needs the device IDs */ ii->get_invariants(hw); @@ -6284,6 +6913,10 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter, if (ixgbe_init_rss_key(adapter)) return -ENOMEM; + adapter->af_xdp_zc_qps = bitmap_zalloc(IXGBE_MAX_XDP_QS, GFP_KERNEL); + if (!adapter->af_xdp_zc_qps) + return -ENOMEM; + /* Set MAC specific capability flags and exceptions */ switch (hw->mac.type) { case ixgbe_mac_82598EB: @@ -6314,7 +6947,6 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter, adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE; break; case ixgbe_mac_x550em_a: - adapter->flags |= IXGBE_FLAG_GENEVE_OFFLOAD_CAPABLE; switch (hw->device_id) { case IXGBE_DEV_ID_X550EM_A_1G_T: case IXGBE_DEV_ID_X550EM_A_1G_T_L: @@ -6323,7 +6955,7 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter, default: break; } - /* fall through */ + fallthrough; case ixgbe_mac_X550EM_x: #ifdef CONFIG_IXGBE_DCB adapter->flags &= ~IXGBE_FLAG_DCB_CAPABLE; @@ -6334,19 +6966,25 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter, adapter->fcoe.up = 0; #endif /* IXGBE_DCB */ #endif /* IXGBE_FCOE */ - /* Fall Through */ + fallthrough; case ixgbe_mac_X550: if (hw->mac.type == ixgbe_mac_X550) adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE; #ifdef CONFIG_IXGBE_DCA adapter->flags &= ~IXGBE_FLAG_DCA_CAPABLE; #endif - adapter->flags |= IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE; break; default: break; } + /* Make sure the SWFW semaphore is in a valid state */ + if (hw->mac.ops.init_swfw_sync) + hw->mac.ops.init_swfw_sync(hw); + + if (hw->mac.type == ixgbe_mac_e610) + mutex_init(&hw->aci.lock); + #ifdef IXGBE_FCOE /* FCoE support exists, always init the FCoE lock */ spin_lock_init(&adapter->fcoe.lock); @@ -6355,6 +6993,9 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter, /* n-tuple support exists, always init our spinlock */ spin_lock_init(&adapter->fdir_perfect_lock); + /* init spinlock to avoid concurrency of VF resources */ + spin_lock_init(&adapter->vfs_lock); + #ifdef CONFIG_IXGBE_DCB ixgbe_init_dcb(adapter); #endif @@ -6393,7 +7034,7 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter, adapter->tx_work_limit = IXGBE_DEFAULT_TX_WORK; /* initialize eeprom parameters */ - if (ixgbe_init_eeprom_params_generic(hw)) { + if (hw->eeprom.ops.init_params(hw)) { e_dev_err("EEPROM initialization failed\n"); return -EIO; } @@ -6402,6 +7043,10 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter, set_bit(0, adapter->fwd_bitmask); set_bit(__IXGBE_DOWN, &adapter->state); + /* enable locking for XDP_TX if we have more CPUs than queues */ + if (nr_cpu_ids > IXGBE_MAX_XDP_QS) + static_branch_enable(&ixgbe_xdp_locking_key); + return 0; } @@ -6415,7 +7060,7 @@ int ixgbe_setup_tx_resources(struct ixgbe_ring *tx_ring) { struct device *dev = tx_ring->dev; int orig_node = dev_to_node(dev); - int ring_node = -1; + int ring_node = NUMA_NO_NODE; int size; size = sizeof(struct ixgbe_tx_buffer) * tx_ring->count; @@ -6497,6 +7142,13 @@ err_setup_tx: return err; } +static int ixgbe_rx_napi_id(struct ixgbe_ring *rx_ring) +{ + struct ixgbe_q_vector *q_vector = rx_ring->q_vector; + + return q_vector ? q_vector->napi.napi_id : 0; +} + /** * ixgbe_setup_rx_resources - allocate Rx resources (Descriptors) * @adapter: pointer to ixgbe_adapter @@ -6509,7 +7161,7 @@ int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter, { struct device *dev = rx_ring->dev; int orig_node = dev_to_node(dev); - int ring_node = -1; + int ring_node = NUMA_NO_NODE; int size; size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count; @@ -6544,10 +7196,10 @@ int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter, /* XDP RX-queue info */ if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, adapter->netdev, - rx_ring->queue_index) < 0) + rx_ring->queue_index, ixgbe_rx_napi_id(rx_ring)) < 0) goto err; - rx_ring->xdp_prog = adapter->xdp_prog; + WRITE_ONCE(rx_ring->xdp_prog, adapter->xdp_prog); return 0; err: @@ -6678,6 +7330,18 @@ static void ixgbe_free_all_rx_resources(struct ixgbe_adapter *adapter) } /** + * ixgbe_max_xdp_frame_size - returns the maximum allowed frame size for XDP + * @adapter: device handle, pointer to adapter + */ +static int ixgbe_max_xdp_frame_size(struct ixgbe_adapter *adapter) +{ + if (PAGE_SIZE >= 8192 || adapter->flags2 & IXGBE_FLAG2_RX_LEGACY) + return IXGBE_RXBUFFER_2K; + else + return IXGBE_RXBUFFER_3K; +} + +/** * ixgbe_change_mtu - Change the Maximum Transfer Unit * @netdev: network interface device structure * @new_mtu: new value for maximum frame size @@ -6686,20 +7350,14 @@ static void ixgbe_free_all_rx_resources(struct ixgbe_adapter *adapter) **/ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); - if (adapter->xdp_prog) { - int new_frame_size = new_mtu + ETH_HLEN + ETH_FCS_LEN + - VLAN_HLEN; - int i; - - for (i = 0; i < adapter->num_rx_queues; i++) { - struct ixgbe_ring *ring = adapter->rx_ring[i]; + if (ixgbe_enabled_xdp_adapter(adapter)) { + int new_frame_size = new_mtu + IXGBE_PKT_HDR_PAD; - if (new_frame_size > ixgbe_rx_bufsz(ring)) { - e_warn(probe, "Requested MTU size is not supported with XDP\n"); - return -EINVAL; - } + if (new_frame_size > ixgbe_max_xdp_frame_size(adapter)) { + e_warn(probe, "Requested MTU size is not supported with XDP\n"); + return -EINVAL; } } @@ -6713,10 +7371,11 @@ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu) (new_mtu > ETH_DATA_LEN)) e_warn(probe, "Setting MTU > 1500 will disable legacy VFs\n"); - e_info(probe, "changing MTU from %d to %d\n", netdev->mtu, new_mtu); + netdev_dbg(netdev, "changing MTU from %d to %d\n", + netdev->mtu, new_mtu); /* must set new MTU before calling down or up */ - netdev->mtu = new_mtu; + WRITE_ONCE(netdev->mtu, new_mtu); if (netif_running(netdev)) ixgbe_reinit_locked(adapter); @@ -6738,7 +7397,7 @@ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu) **/ int ixgbe_open(struct net_device *netdev) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; int err, queues; @@ -6779,8 +7438,20 @@ int ixgbe_open(struct net_device *netdev) ixgbe_up_complete(adapter); - ixgbe_clear_udp_tunnel_port(adapter, IXGBE_VXLANCTRL_ALL_UDPPORT_MASK); - udp_tunnel_get_rx_info(netdev); + udp_tunnel_nic_reset_ntf(netdev); + if (adapter->hw.mac.type == ixgbe_mac_e610) { + int err = ixgbe_update_link_info(&adapter->hw); + + if (err) + e_dev_err("Failed to update link info, err %d.\n", err); + + ixgbe_check_link_cfg_err(adapter, + adapter->hw.link.link_info.link_cfg_err); + + err = ixgbe_non_sfp_link_config(&adapter->hw); + if (err) + e_dev_err("Link setup failed, err %d.\n", err); + } return 0; @@ -6830,7 +7501,7 @@ static void ixgbe_close_suspend(struct ixgbe_adapter *adapter) **/ int ixgbe_close(struct net_device *netdev) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); ixgbe_ptp_stop(adapter); @@ -6844,21 +7515,14 @@ int ixgbe_close(struct net_device *netdev) return 0; } -#ifdef CONFIG_PM -static int ixgbe_resume(struct pci_dev *pdev) +static int ixgbe_resume(struct device *dev_d) { + struct pci_dev *pdev = to_pci_dev(dev_d); struct ixgbe_adapter *adapter = pci_get_drvdata(pdev); struct net_device *netdev = adapter->netdev; u32 err; adapter->hw.hw_addr = adapter->io_addr; - pci_set_power_state(pdev, PCI_D0); - pci_restore_state(pdev); - /* - * pci_restore_state clears dev->state_saved so call - * pci_save_state to restore it. - */ - pci_save_state(pdev); err = pci_enable_device_mem(pdev); if (err) { @@ -6869,7 +7533,7 @@ static int ixgbe_resume(struct pci_dev *pdev) clear_bit(__IXGBE_DISABLED, &adapter->state); pci_set_master(pdev); - pci_wake_from_d3(pdev, false); + device_wakeup_disable(dev_d); ixgbe_reset(adapter); @@ -6887,7 +7551,6 @@ static int ixgbe_resume(struct pci_dev *pdev) return err; } -#endif /* CONFIG_PM */ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake) { @@ -6896,9 +7559,6 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake) struct ixgbe_hw *hw = &adapter->hw; u32 ctrl; u32 wufc = adapter->wol; -#ifdef CONFIG_PM - int retval = 0; -#endif rtnl_lock(); netif_device_detach(netdev); @@ -6909,12 +7569,6 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake) ixgbe_clear_interrupt_scheme(adapter); rtnl_unlock(); -#ifdef CONFIG_PM - retval = pci_save_state(pdev); - if (retval) - return retval; - -#endif if (hw->mac.ops.stop_link_on_d3) hw->mac.ops.stop_link_on_d3(hw); @@ -6951,6 +7605,7 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: pci_wake_from_d3(pdev, !!wufc); break; default: @@ -6969,26 +7624,18 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake) return 0; } -#ifdef CONFIG_PM -static int ixgbe_suspend(struct pci_dev *pdev, pm_message_t state) +static int ixgbe_suspend(struct device *dev_d) { + struct pci_dev *pdev = to_pci_dev(dev_d); int retval; bool wake; retval = __ixgbe_shutdown(pdev, &wake); - if (retval) - return retval; - if (wake) { - pci_prepare_to_sleep(pdev); - } else { - pci_wake_from_d3(pdev, false); - pci_set_power_state(pdev, PCI_D3hot); - } + device_set_wakeup_enable(dev_d, wake); - return 0; + return retval; } -#endif /* CONFIG_PM */ static void ixgbe_shutdown(struct pci_dev *pdev) { @@ -7034,7 +7681,10 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) } for (i = 0; i < adapter->num_rx_queues; i++) { - struct ixgbe_ring *rx_ring = adapter->rx_ring[i]; + struct ixgbe_ring *rx_ring = READ_ONCE(adapter->rx_ring[i]); + + if (!rx_ring) + continue; non_eop_descs += rx_ring->rx_stats.non_eop_descs; alloc_rx_page += rx_ring->rx_stats.alloc_rx_page; alloc_rx_page_failed += rx_ring->rx_stats.alloc_rx_page_failed; @@ -7055,15 +7705,20 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) packets = 0; /* gather some stats to the adapter struct that are per queue */ for (i = 0; i < adapter->num_tx_queues; i++) { - struct ixgbe_ring *tx_ring = adapter->tx_ring[i]; + struct ixgbe_ring *tx_ring = READ_ONCE(adapter->tx_ring[i]); + + if (!tx_ring) + continue; restart_queue += tx_ring->tx_stats.restart_queue; tx_busy += tx_ring->tx_stats.tx_busy; bytes += tx_ring->stats.bytes; packets += tx_ring->stats.packets; } for (i = 0; i < adapter->num_xdp_queues; i++) { - struct ixgbe_ring *xdp_ring = adapter->xdp_ring[i]; + struct ixgbe_ring *xdp_ring = READ_ONCE(adapter->xdp_ring[i]); + if (!xdp_ring) + continue; restart_queue += xdp_ring->tx_stats.restart_queue; tx_busy += xdp_ring->tx_stats.tx_busy; bytes += xdp_ring->stats.bytes; @@ -7098,6 +7753,7 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: hwstats->pxonrxc[i] += IXGBE_READ_REG(hw, IXGBE_PXONRXCNT(i)); break; @@ -7110,11 +7766,12 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) for (i = 0; i < 16; i++) { hwstats->qptc[i] += IXGBE_READ_REG(hw, IXGBE_QPTC(i)); hwstats->qprc[i] += IXGBE_READ_REG(hw, IXGBE_QPRC(i)); - if ((hw->mac.type == ixgbe_mac_82599EB) || - (hw->mac.type == ixgbe_mac_X540) || - (hw->mac.type == ixgbe_mac_X550) || - (hw->mac.type == ixgbe_mac_X550EM_x) || - (hw->mac.type == ixgbe_mac_x550em_a)) { + if (hw->mac.type == ixgbe_mac_82599EB || + hw->mac.type == ixgbe_mac_X540 || + hw->mac.type == ixgbe_mac_X550 || + hw->mac.type == ixgbe_mac_X550EM_x || + hw->mac.type == ixgbe_mac_x550em_a || + hw->mac.type == ixgbe_mac_e610) { hwstats->qbtc[i] += IXGBE_READ_REG(hw, IXGBE_QBTC_L(i)); IXGBE_READ_REG(hw, IXGBE_QBTC_H(i)); /* to clear */ hwstats->qbrc[i] += IXGBE_READ_REG(hw, IXGBE_QBRC_L(i)); @@ -7140,12 +7797,13 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: /* OS2BMC stats are X540 and later */ hwstats->o2bgptc += IXGBE_READ_REG(hw, IXGBE_O2BGPTC); hwstats->o2bspc += IXGBE_READ_REG(hw, IXGBE_O2BSPC); hwstats->b2ospc += IXGBE_READ_REG(hw, IXGBE_B2OSPC); hwstats->b2ogprc += IXGBE_READ_REG(hw, IXGBE_B2OGPRC); - /* fall through */ + fallthrough; case ixgbe_mac_82599EB: for (i = 0; i < 16; i++) adapter->hw_rx_no_dma_resources += @@ -7233,6 +7891,32 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) netdev->stats.rx_length_errors = hwstats->rlec; netdev->stats.rx_crc_errors = hwstats->crcerrs; netdev->stats.rx_missed_errors = total_mpc; + + /* VF Stats Collection - skip while resetting because these + * are not clear on read and otherwise you'll sometimes get + * crazy values. + */ + if (!test_bit(__IXGBE_RESETTING, &adapter->state)) { + for (i = 0; i < adapter->num_vfs; i++) { + UPDATE_VF_COUNTER_32bit(IXGBE_PVFGPRC(i), + adapter->vfinfo[i].last_vfstats.gprc, + adapter->vfinfo[i].vfstats.gprc); + UPDATE_VF_COUNTER_32bit(IXGBE_PVFGPTC(i), + adapter->vfinfo[i].last_vfstats.gptc, + adapter->vfinfo[i].vfstats.gptc); + UPDATE_VF_COUNTER_36bit(IXGBE_PVFGORC_LSB(i), + IXGBE_PVFGORC_MSB(i), + adapter->vfinfo[i].last_vfstats.gorc, + adapter->vfinfo[i].vfstats.gorc); + UPDATE_VF_COUNTER_36bit(IXGBE_PVFGOTC_LSB(i), + IXGBE_PVFGOTC_MSB(i), + adapter->vfinfo[i].last_vfstats.gotc, + adapter->vfinfo[i].vfstats.gotc); + UPDATE_VF_COUNTER_32bit(IXGBE_PVFMPRC(i), + adapter->vfinfo[i].last_vfstats.mprc, + adapter->vfinfo[i].vfstats.mprc); + } + } } /** @@ -7296,12 +7980,9 @@ static void ixgbe_check_hang_subtask(struct ixgbe_adapter *adapter) return; /* Force detection of hung controller */ - if (netif_carrier_ok(adapter->netdev)) { + if (netif_carrier_ok(adapter->netdev)) for (i = 0; i < adapter->num_tx_queues; i++) set_check_for_tx_hang(adapter->tx_ring[i]); - for (i = 0; i < adapter->num_xdp_queues; i++) - set_check_for_tx_hang(adapter->xdp_ring[i]); - } if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) { /* @@ -7414,6 +8095,7 @@ static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: case ixgbe_mac_82599EB: { u32 mflcn = IXGBE_READ_REG(hw, IXGBE_MFLCN); u32 fccfg = IXGBE_READ_REG(hw, IXGBE_FCCFG); @@ -7463,6 +8145,9 @@ static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *adapter) netif_carrier_on(netdev); ixgbe_check_vf_rate_limit(adapter); + if (adapter->num_vfs && hw->mac.ops.enable_mdd) + hw->mac.ops.enable_mdd(hw); + /* enable transmits */ netif_tx_wake_all_queues(adapter->netdev); @@ -7490,6 +8175,8 @@ static void ixgbe_watchdog_link_is_down(struct ixgbe_adapter *adapter) if (!netif_carrier_ok(netdev)) return; + adapter->link_down_events++; + /* poll for SFP+ cable when link is down */ if (ixgbe_is_sfp(hw) && hw->mac.type == ixgbe_mac_82598EB) adapter->flags2 |= IXGBE_FLAG2_SEARCH_FOR_SFP; @@ -7515,13 +8202,6 @@ static bool ixgbe_ring_tx_pending(struct ixgbe_adapter *adapter) return true; } - for (i = 0; i < adapter->num_xdp_queues; i++) { - struct ixgbe_ring *ring = adapter->xdp_ring[i]; - - if (ring->next_to_use != ring->next_to_clean) - return true; - } - return false; } @@ -7576,6 +8256,27 @@ static void ixgbe_watchdog_flush_tx(struct ixgbe_adapter *adapter) } #ifdef CONFIG_PCI_IOV +static void ixgbe_bad_vf_abort(struct ixgbe_adapter *adapter, u32 vf) +{ + struct ixgbe_hw *hw = &adapter->hw; + + if (adapter->hw.mac.type == ixgbe_mac_82599EB && + adapter->flags2 & IXGBE_FLAG2_AUTO_DISABLE_VF) { + adapter->vfinfo[vf].primary_abort_count++; + if (adapter->vfinfo[vf].primary_abort_count == + IXGBE_PRIMARY_ABORT_LIMIT) { + ixgbe_set_vf_link_state(adapter, vf, + IFLA_VF_LINK_STATE_DISABLE); + adapter->vfinfo[vf].primary_abort_count = 0; + + e_info(drv, + "Malicious Driver Detection event detected on PF %d VF %d MAC: %pM mdd-disable-vf=on", + hw->bus.func, vf, + adapter->vfinfo[vf].vf_mac_addresses); + } + } +} + static void ixgbe_check_for_bad_vf(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; @@ -7607,8 +8308,10 @@ static void ixgbe_check_for_bad_vf(struct ixgbe_adapter *adapter) continue; pci_read_config_word(vfdev, PCI_STATUS, &status_reg); if (status_reg != IXGBE_FAILED_READ_CFG_WORD && - status_reg & PCI_STATUS_REC_MASTER_ABORT) + status_reg & PCI_STATUS_REC_MASTER_ABORT) { + ixgbe_bad_vf_abort(adapter, vf); pcie_flr(vfdev); + } } } @@ -7677,7 +8380,7 @@ static void ixgbe_watchdog_subtask(struct ixgbe_adapter *adapter) static void ixgbe_sfp_detection_subtask(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; - s32 err; + int err; /* not searching for SFP so there is nothing to do here */ if (!(adapter->flags2 & IXGBE_FLAG2_SEARCH_FOR_SFP) && @@ -7695,10 +8398,10 @@ static void ixgbe_sfp_detection_subtask(struct ixgbe_adapter *adapter) adapter->sfp_poll_time = jiffies + IXGBE_SFP_POLL_JIFFIES - 1; err = hw->phy.ops.identify_sfp(hw); - if (err == IXGBE_ERR_SFP_NOT_SUPPORTED) + if (err == -EOPNOTSUPP) goto sfp_out; - if (err == IXGBE_ERR_SFP_NOT_PRESENT) { + if (err == -ENOENT) { /* If no cable is present, then we need to reset * the next time we find a good cable. */ adapter->flags2 |= IXGBE_FLAG2_SFP_NEEDS_RESET; @@ -7724,7 +8427,7 @@ static void ixgbe_sfp_detection_subtask(struct ixgbe_adapter *adapter) else err = hw->mac.ops.setup_sfp(hw); - if (err == IXGBE_ERR_SFP_NOT_SUPPORTED) + if (err == -EOPNOTSUPP) goto sfp_out; adapter->flags |= IXGBE_FLAG_NEED_LINK_CONFIG; @@ -7733,8 +8436,8 @@ static void ixgbe_sfp_detection_subtask(struct ixgbe_adapter *adapter) sfp_out: clear_bit(__IXGBE_IN_SFP_INIT, &adapter->state); - if ((err == IXGBE_ERR_SFP_NOT_SUPPORTED) && - (adapter->netdev->reg_state == NETREG_REGISTERED)) { + if (err == -EOPNOTSUPP && + adapter->netdev->reg_state == NETREG_REGISTERED) { e_dev_err("failed to initialize because an unsupported " "SFP+ module type was detected.\n"); e_dev_err("Reload the driver after installing a " @@ -7786,7 +8489,8 @@ static void ixgbe_sfp_link_config_subtask(struct ixgbe_adapter *adapter) **/ static void ixgbe_service_timer(struct timer_list *t) { - struct ixgbe_adapter *adapter = from_timer(adapter, t, service_timer); + struct ixgbe_adapter *adapter = timer_container_of(adapter, t, + service_timer); unsigned long next_event_offset; /* poll faster when waiting for link */ @@ -7804,7 +8508,7 @@ static void ixgbe_service_timer(struct timer_list *t) static void ixgbe_phy_interrupt_subtask(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; - u32 status; + bool overtemp; if (!(adapter->flags2 & IXGBE_FLAG2_PHY_INTERRUPT)) return; @@ -7814,11 +8518,9 @@ static void ixgbe_phy_interrupt_subtask(struct ixgbe_adapter *adapter) if (!hw->phy.ops.handle_lasi) return; - status = hw->phy.ops.handle_lasi(&adapter->hw); - if (status != IXGBE_ERR_OVERTEMP) - return; - - e_crit(drv, "%s\n", ixgbe_overheat_msg); + hw->phy.ops.handle_lasi(&adapter->hw, &overtemp); + if (overtemp) + e_crit(drv, "%s\n", ixgbe_overheat_msg); } static void ixgbe_reset_subtask(struct ixgbe_adapter *adapter) @@ -7843,6 +8545,34 @@ static void ixgbe_reset_subtask(struct ixgbe_adapter *adapter) rtnl_unlock(); } +static int ixgbe_check_fw_api_mismatch(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + + if (hw->mac.type != ixgbe_mac_e610) + return 0; + + if (hw->mac.ops.get_fw_ver && hw->mac.ops.get_fw_ver(hw)) + return 0; + + if (hw->api_maj_ver > IXGBE_FW_API_VER_MAJOR) { + e_dev_err("The driver for the device stopped because the NVM image is newer than expected. You must install the most recent version of the network driver.\n"); + + adapter->flags2 |= IXGBE_FLAG2_API_MISMATCH; + return -EOPNOTSUPP; + } else if (hw->api_maj_ver == IXGBE_FW_API_VER_MAJOR && + hw->api_min_ver > IXGBE_FW_API_VER_MINOR + IXGBE_FW_API_VER_DIFF_ALLOWED) { + e_dev_info("The driver for the device detected a newer version of the NVM image than expected. Please install the most recent version of the network driver.\n"); + adapter->flags2 |= IXGBE_FLAG2_API_MISMATCH; + } else if (hw->api_maj_ver < IXGBE_FW_API_VER_MAJOR || + hw->api_min_ver < IXGBE_FW_API_VER_MINOR - IXGBE_FW_API_VER_DIFF_ALLOWED) { + e_dev_info("The driver for the device detected an older version of the NVM image than expected. Please update the NVM image.\n"); + adapter->flags2 |= IXGBE_FLAG2_API_MISMATCH; + } + + return 0; +} + /** * ixgbe_check_fw_error - Check firmware for errors * @adapter: the adapter private structure @@ -7853,12 +8583,14 @@ static bool ixgbe_check_fw_error(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; u32 fwsm; + int err; /* read fwsm.ext_err_ind register and log errors */ fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw)); + /* skip if E610's FW is reloading, warning in that case may be misleading */ if (fwsm & IXGBE_FWSM_EXT_ERR_IND_MASK || - !(fwsm & IXGBE_FWSM_FW_VAL_BIT)) + (!(fwsm & IXGBE_FWSM_FW_VAL_BIT) && !(hw->mac.type == ixgbe_mac_e610))) e_dev_warn("Warning firmware error detected FWSM: 0x%08X\n", fwsm); @@ -7866,10 +8598,53 @@ static bool ixgbe_check_fw_error(struct ixgbe_adapter *adapter) e_dev_err("Firmware recovery mode detected. Limiting functionality. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode.\n"); return true; } + if (!(adapter->flags2 & IXGBE_FLAG2_API_MISMATCH)) { + err = ixgbe_check_fw_api_mismatch(adapter); + if (err) + return true; + } + + /* return here if FW rollback mode has been already detected */ + if (adapter->flags2 & IXGBE_FLAG2_FW_ROLLBACK) + return false; + + if (hw->mac.ops.fw_rollback_mode && hw->mac.ops.fw_rollback_mode(hw)) { + struct ixgbe_nvm_info *nvm_info = &adapter->hw.flash.nvm; + char ver_buff[64] = ""; + + if (hw->mac.ops.get_fw_ver && hw->mac.ops.get_fw_ver(hw)) + goto no_version; + + if (hw->mac.ops.get_nvm_ver && + hw->mac.ops.get_nvm_ver(hw, nvm_info)) + goto no_version; + + snprintf(ver_buff, sizeof(ver_buff), + "Current version is NVM:%x.%x.%x, FW:%d.%d. ", + nvm_info->major, nvm_info->minor, nvm_info->eetrack, + hw->fw_maj_ver, hw->fw_maj_ver); +no_version: + e_dev_warn("Firmware rollback mode detected. %sDevice may exhibit limited functionality. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware rollback mode.", + ver_buff); + + adapter->flags2 |= IXGBE_FLAG2_FW_ROLLBACK; + } return false; } +static void ixgbe_recovery_service_task(struct work_struct *work) +{ + struct ixgbe_adapter *adapter = container_of(work, + struct ixgbe_adapter, + service_task); + + ixgbe_handle_fw_event(adapter); + ixgbe_service_event_complete(adapter); + + mod_timer(&adapter->service_timer, jiffies + msecs_to_jiffies(100)); +} + /** * ixgbe_service_task - manages and runs subtasks * @work: pointer to work_struct containing our data @@ -7890,18 +8665,19 @@ static void ixgbe_service_task(struct work_struct *work) } if (ixgbe_check_fw_error(adapter)) { if (!test_bit(__IXGBE_DOWN, &adapter->state)) { - rtnl_lock(); + if (adapter->mii_bus) { + mdiobus_unregister(adapter->mii_bus); + adapter->mii_bus = NULL; + } unregister_netdev(adapter->netdev); - rtnl_unlock(); } ixgbe_service_event_complete(adapter); return; } - if (adapter->flags2 & IXGBE_FLAG2_UDP_TUN_REREG_NEEDED) { - rtnl_lock(); - adapter->flags2 &= ~IXGBE_FLAG2_UDP_TUN_REREG_NEEDED; - udp_tunnel_get_rx_info(adapter->netdev); - rtnl_unlock(); + if (adapter->hw.mac.type == ixgbe_mac_e610) { + if (adapter->flags2 & IXGBE_FLAG2_FW_ASYNC_EVENT) + ixgbe_handle_fw_event(adapter); + ixgbe_check_media_subtask(adapter); } ixgbe_reset_subtask(adapter); ixgbe_phy_interrupt_subtask(adapter); @@ -7936,6 +8712,7 @@ static int ixgbe_tso(struct ixgbe_ring *tx_ring, } ip; union { struct tcphdr *tcp; + struct udphdr *udp; unsigned char *hdr; } l4; u32 paylen, l4_offset; @@ -7959,7 +8736,8 @@ static int ixgbe_tso(struct ixgbe_ring *tx_ring, l4.hdr = skb_checksum_start(skb); /* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */ - type_tucmd = IXGBE_ADVTXD_TUCMD_L4T_TCP; + type_tucmd = (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) ? + IXGBE_ADVTXD_TUCMD_L4T_UDP : IXGBE_ADVTXD_TUCMD_L4T_TCP; /* initialize outer IP header fields */ if (ip.v4->version == 4) { @@ -7989,12 +8767,20 @@ static int ixgbe_tso(struct ixgbe_ring *tx_ring, /* determine offset of inner transport header */ l4_offset = l4.hdr - skb->data; - /* compute length of segmentation header */ - *hdr_len = (l4.tcp->doff * 4) + l4_offset; - /* remove payload length from inner checksum */ paylen = skb->len - l4_offset; - csum_replace_by_diff(&l4.tcp->check, (__force __wsum)htonl(paylen)); + + if (type_tucmd & IXGBE_ADVTXD_TUCMD_L4T_TCP) { + /* compute length of segmentation header */ + *hdr_len = (l4.tcp->doff * 4) + l4_offset; + csum_replace_by_diff(&l4.tcp->check, + (__force __wsum)htonl(paylen)); + } else { + /* compute length of segmentation header */ + *hdr_len = sizeof(*l4.udp) + l4_offset; + csum_replace_by_diff(&l4.udp->check, + (__force __wsum)htonl(paylen)); + } /* update gso size and bytecount with header size */ first->gso_segs = skb_shinfo(skb)->gso_segs; @@ -8018,15 +8804,6 @@ static int ixgbe_tso(struct ixgbe_ring *tx_ring, return 1; } -static inline bool ixgbe_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 ixgbe_tx_csum(struct ixgbe_ring *tx_ring, struct ixgbe_tx_buffer *first, struct ixgbe_ipsec_tx_data *itd) @@ -8047,19 +8824,16 @@ csum_failed: switch (skb->csum_offset) { case offsetof(struct tcphdr, check): type_tucmd = IXGBE_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)) && - ixgbe_ipv6_csum_is_sctp(skb))) { + if (skb_csum_is_sctp(skb)) { type_tucmd = IXGBE_ADVTXD_TUCMD_L4T_SCTP; break; } - /* fall through */ + fallthrough; default: skb_checksum_help(skb); goto csum_failed; @@ -8143,22 +8917,10 @@ static void ixgbe_tx_olinfo_status(union ixgbe_adv_tx_desc *tx_desc, static int __ixgbe_maybe_stop_tx(struct ixgbe_ring *tx_ring, u16 size) { - 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. - */ - smp_mb(); - - /* We need to check again in a case another CPU has just - * made room available. - */ - if (likely(ixgbe_desc_unused(tx_ring) < size)) + if (!netif_subqueue_try_stop(tx_ring->netdev, tx_ring->queue_index, + ixgbe_desc_unused(tx_ring), size)) return -EBUSY; - /* A reprieve! - use start_queue because it doesn't call schedule */ - netif_start_subqueue(tx_ring->netdev, tx_ring->queue_index); ++tx_ring->tx_stats.restart_queue; return 0; } @@ -8178,7 +8940,7 @@ static int ixgbe_tx_map(struct ixgbe_ring *tx_ring, struct sk_buff *skb = first->skb; struct ixgbe_tx_buffer *tx_buffer; union ixgbe_adv_tx_desc *tx_desc; - struct skb_frag_struct *frag; + skb_frag_t *frag; dma_addr_t dma; unsigned int data_len, size; u32 tx_flags = first->tx_flags; @@ -8293,13 +9055,8 @@ static int ixgbe_tx_map(struct ixgbe_ring *tx_ring, ixgbe_maybe_stop_tx(tx_ring, DESC_NEEDED); - if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { + if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) { writel(i, tx_ring->tail); - - /* we need this if more than one processor can write to our tail - * at a time, it synchronizes IO on IA64/Altix systems - */ - mmiowb(); } return 0; @@ -8373,7 +9130,7 @@ static void ixgbe_atr(struct ixgbe_ring *ring, struct ixgbe_adapter *adapter = q_vector->adapter; if (unlikely(skb_tail_pointer(skb) < hdr.network + - VXLAN_HEADROOM)) + vxlan_headroom(0))) return; /* verify the port is recognized as VXLAN */ @@ -8479,8 +9236,7 @@ static void ixgbe_atr(struct ixgbe_ring *ring, #ifdef IXGBE_FCOE static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { struct ixgbe_adapter *adapter; struct ixgbe_ring_feature *f; @@ -8504,13 +9260,13 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, switch (vlan_get_protocol(skb)) { case htons(ETH_P_FCOE): case htons(ETH_P_FIP): - adapter = netdev_priv(dev); + adapter = ixgbe_from_netdev(dev); if (!sb_dev && (adapter->flags & IXGBE_FLAG_FCOE_ENABLED)) break; - /* fall through */ + fallthrough; default: - return fallback(dev, skb, sb_dev); + return netdev_pick_tx(dev, skb, sb_dev); } f = &adapter->ring_feature[RING_F_FCOE]; @@ -8525,61 +9281,86 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, } #endif -int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter, +int ixgbe_xmit_xdp_ring(struct ixgbe_ring *ring, struct xdp_frame *xdpf) { - struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()]; - struct ixgbe_tx_buffer *tx_buffer; - union ixgbe_adv_tx_desc *tx_desc; - u32 len, cmd_type; - dma_addr_t dma; - u16 i; + 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 i = 0, index = ring->next_to_use; + struct ixgbe_tx_buffer *tx_head = &ring->tx_buffer_info[index]; + struct ixgbe_tx_buffer *tx_buff = tx_head; + union ixgbe_adv_tx_desc *tx_desc = IXGBE_TX_DESC(ring, index); + u32 cmd_type, len = xdpf->len; + void *data = xdpf->data; - len = xdpf->len; - - if (unlikely(!ixgbe_desc_unused(ring))) + if (unlikely(ixgbe_desc_unused(ring) < 1 + nr_frags)) return IXGBE_XDP_CONSUMED; - dma = dma_map_single(ring->dev, xdpf->data, len, DMA_TO_DEVICE); - if (dma_mapping_error(ring->dev, dma)) - return IXGBE_XDP_CONSUMED; + tx_head->bytecount = xdp_get_frame_len(xdpf); + tx_head->gso_segs = 1; + tx_head->xdpf = xdpf; - /* record the location of the first descriptor for this packet */ - tx_buffer = &ring->tx_buffer_info[ring->next_to_use]; - tx_buffer->bytecount = len; - tx_buffer->gso_segs = 1; - tx_buffer->protocol = 0; + tx_desc->read.olinfo_status = + cpu_to_le32(tx_head->bytecount << IXGBE_ADVTXD_PAYLEN_SHIFT); - i = ring->next_to_use; - tx_desc = IXGBE_TX_DESC(ring, i); + for (;;) { + dma_addr_t dma; + + dma = dma_map_single(ring->dev, data, len, DMA_TO_DEVICE); + if (dma_mapping_error(ring->dev, dma)) + goto unmap; - dma_unmap_len_set(tx_buffer, len, len); - dma_unmap_addr_set(tx_buffer, dma, dma); - tx_buffer->xdpf = xdpf; + dma_unmap_len_set(tx_buff, len, len); + dma_unmap_addr_set(tx_buff, dma, dma); - tx_desc->read.buffer_addr = cpu_to_le64(dma); + cmd_type = IXGBE_ADVTXD_DTYP_DATA | IXGBE_ADVTXD_DCMD_DEXT | + IXGBE_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_buff->protocol = 0; + if (++index == ring->count) + index = 0; + + if (i == nr_frags) + break; + + tx_buff = &ring->tx_buffer_info[index]; + tx_desc = IXGBE_TX_DESC(ring, index); + tx_desc->read.olinfo_status = 0; + + data = skb_frag_address(&sinfo->frags[i]); + len = skb_frag_size(&sinfo->frags[i]); + i++; + } /* put descriptor type bits */ - cmd_type = IXGBE_ADVTXD_DTYP_DATA | - IXGBE_ADVTXD_DCMD_DEXT | - IXGBE_ADVTXD_DCMD_IFCS; - cmd_type |= len | IXGBE_TXD_CMD; - tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type); - tx_desc->read.olinfo_status = - cpu_to_le32(len << IXGBE_ADVTXD_PAYLEN_SHIFT); + tx_desc->read.cmd_type_len |= cpu_to_le32(IXGBE_TXD_CMD); /* Avoid any potential race with xdp_xmit and cleanup */ smp_wmb(); - /* set next_to_watch value indicating a packet is present */ - i++; - if (i == ring->count) - i = 0; - - tx_buffer->next_to_watch = tx_desc; - ring->next_to_use = i; + tx_head->next_to_watch = tx_desc; + ring->next_to_use = index; return IXGBE_XDP_TX; + +unmap: + for (;;) { + tx_buff = &ring->tx_buffer_info[index]; + if (dma_unmap_len(tx_buff, len)) + dma_unmap_page(ring->dev, dma_unmap_addr(tx_buff, dma), + dma_unmap_len(tx_buff, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buff, len, 0); + if (tx_buff == tx_head) + break; + + if (!index) + index += ring->count; + index--; + } + + return IXGBE_XDP_CONSUMED; } netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, @@ -8603,7 +9384,8 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, * otherwise try next time */ for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) - count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size); + count += TXD_USE_COUNT(skb_frag_size( + &skb_shinfo(skb)->frags[f])); if (ixgbe_maybe_stop_tx(tx_ring, count + 3)) { tx_ring->tx_stats.tx_busy++; @@ -8635,7 +9417,8 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && adapter->ptp_clock) { - if (!test_and_set_bit_lock(__IXGBE_PTP_TX_IN_PROGRESS, + if (adapter->tstamp_config.tx_type == HWTSTAMP_TX_ON && + !test_and_set_bit_lock(__IXGBE_PTP_TX_IN_PROGRESS, &adapter->state)) { skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; tx_flags |= IXGBE_TX_FLAGS_TSTAMP; @@ -8670,7 +9453,7 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, if (skb_cow_head(skb, 0)) goto out_drop; - vhdr = (struct vlan_ethhdr *)skb->data; + vhdr = skb_vlan_eth_hdr(skb); vhdr->h_vlan_TCI = htons(tx_flags >> IXGBE_TX_FLAGS_VLAN_SHIFT); } else { @@ -8696,7 +9479,7 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, #endif /* IXGBE_FCOE */ #ifdef CONFIG_IXGBE_IPSEC - if (secpath_exists(skb) && + if (xfrm_offload(skb) && !ixgbe_ipsec_tx(tx_ring, first, &ipsec_tx)) goto out_drop; #endif @@ -8736,7 +9519,7 @@ static netdev_tx_t __ixgbe_xmit_frame(struct sk_buff *skb, struct net_device *netdev, struct ixgbe_ring *ring) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_ring *tx_ring; /* @@ -8746,7 +9529,7 @@ static netdev_tx_t __ixgbe_xmit_frame(struct sk_buff *skb, if (skb_put_padto(skb, 17)) return NETDEV_TX_OK; - tx_ring = ring ? ring : adapter->tx_ring[skb->queue_mapping]; + tx_ring = ring ? ring : adapter->tx_ring[skb_get_queue_mapping(skb)]; if (unlikely(test_bit(__IXGBE_TX_DISABLED, &tx_ring->state))) return NETDEV_TX_BUSY; @@ -8768,14 +9551,14 @@ static netdev_tx_t ixgbe_xmit_frame(struct sk_buff *skb, **/ static int ixgbe_set_mac(struct net_device *netdev, void *p) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; struct sockaddr *addr = 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); ixgbe_mac_set_default_filter(adapter); @@ -8786,7 +9569,7 @@ static int ixgbe_set_mac(struct net_device *netdev, void *p) static int ixgbe_mdio_read(struct net_device *netdev, int prtad, int devad, u16 addr) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; u16 value; int rc; @@ -8795,7 +9578,8 @@ ixgbe_mdio_read(struct net_device *netdev, int prtad, int devad, u16 addr) int regnum = addr; if (devad != MDIO_DEVAD_NONE) - regnum |= (devad << 16) | MII_ADDR_C45; + return mdiobus_c45_read(adapter->mii_bus, prtad, + devad, regnum); return mdiobus_read(adapter->mii_bus, prtad, regnum); } @@ -8811,14 +9595,15 @@ ixgbe_mdio_read(struct net_device *netdev, int prtad, int devad, u16 addr) static int ixgbe_mdio_write(struct net_device *netdev, int prtad, int devad, u16 addr, u16 value) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); struct ixgbe_hw *hw = &adapter->hw; if (adapter->mii_bus) { int regnum = addr; if (devad != MDIO_DEVAD_NONE) - regnum |= (devad << 16) | MII_ADDR_C45; + return mdiobus_c45_write(adapter->mii_bus, prtad, devad, + regnum, value); return mdiobus_write(adapter->mii_bus, prtad, regnum, value); } @@ -8830,17 +9615,13 @@ static int ixgbe_mdio_write(struct net_device *netdev, int prtad, int devad, static int ixgbe_ioctl(struct net_device *netdev, struct ifreq *req, int cmd) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); switch (cmd) { - case SIOCSHWTSTAMP: - return ixgbe_ptp_set_ts_config(adapter, req); - case SIOCGHWTSTAMP: - return ixgbe_ptp_get_ts_config(adapter, req); case SIOCGMIIPHY: if (!adapter->hw.phy.ops.read_reg) return -EOPNOTSUPP; - /* fall through */ + fallthrough; default: return mdio_mii_ioctl(&adapter->hw.phy.mdio, if_mii(req), cmd); } @@ -8856,7 +9637,7 @@ static int ixgbe_ioctl(struct net_device *netdev, struct ifreq *req, int cmd) static int ixgbe_add_sanmac_netdev(struct net_device *dev) { int err = 0; - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); struct ixgbe_hw *hw = &adapter->hw; if (is_valid_ether_addr(hw->mac.san_addr)) { @@ -8880,7 +9661,7 @@ static int ixgbe_add_sanmac_netdev(struct net_device *dev) static int ixgbe_del_sanmac_netdev(struct net_device *dev) { int err = 0; - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); struct ixgbe_mac_info *mac = &adapter->hw.mac; if (is_valid_ether_addr(mac->san_addr)) { @@ -8899,10 +9680,10 @@ static void ixgbe_get_ring_stats64(struct rtnl_link_stats64 *stats, if (ring) { do { - start = u64_stats_fetch_begin_irq(&ring->syncp); + start = u64_stats_fetch_begin(&ring->syncp); packets = ring->stats.packets; bytes = ring->stats.bytes; - } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + } while (u64_stats_fetch_retry(&ring->syncp, start)); stats->tx_packets += packets; stats->tx_bytes += bytes; } @@ -8911,7 +9692,7 @@ static void ixgbe_get_ring_stats64(struct rtnl_link_stats64 *stats, static void ixgbe_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); int i; rcu_read_lock(); @@ -8922,10 +9703,10 @@ static void ixgbe_get_stats64(struct net_device *netdev, if (ring) { do { - start = u64_stats_fetch_begin_irq(&ring->syncp); + start = u64_stats_fetch_begin(&ring->syncp); packets = ring->stats.packets; bytes = ring->stats.bytes; - } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + } while (u64_stats_fetch_retry(&ring->syncp, start)); stats->rx_packets += packets; stats->rx_bytes += bytes; } @@ -8951,6 +9732,23 @@ static void ixgbe_get_stats64(struct net_device *netdev, stats->rx_missed_errors = netdev->stats.rx_missed_errors; } +static int ixgbe_ndo_get_vf_stats(struct net_device *netdev, int vf, + struct ifla_vf_stats *vf_stats) +{ + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); + + if (vf < 0 || vf >= adapter->num_vfs) + return -EINVAL; + + vf_stats->rx_packets = adapter->vfinfo[vf].vfstats.gprc; + vf_stats->rx_bytes = adapter->vfinfo[vf].vfstats.gorc; + vf_stats->tx_packets = adapter->vfinfo[vf].vfstats.gptc; + vf_stats->tx_bytes = adapter->vfinfo[vf].vfstats.gotc; + vf_stats->multicast = adapter->vfinfo[vf].vfstats.mprc; + + return 0; +} + #ifdef CONFIG_IXGBE_DCB /** * ixgbe_validate_rtr - verify 802.1Qp to Rx packet buffer mapping is valid. @@ -9015,9 +9813,10 @@ static void ixgbe_set_prio_tc_map(struct ixgbe_adapter *adapter) } #endif /* CONFIG_IXGBE_DCB */ -static int ixgbe_reassign_macvlan_pool(struct net_device *vdev, void *data) +static int ixgbe_reassign_macvlan_pool(struct net_device *vdev, + struct netdev_nested_priv *priv) { - struct ixgbe_adapter *adapter = data; + struct ixgbe_adapter *adapter = (struct ixgbe_adapter *)priv->data; struct ixgbe_fwd_adapter *accel; int pool; @@ -9053,14 +9852,17 @@ static int ixgbe_reassign_macvlan_pool(struct net_device *vdev, void *data) static void ixgbe_defrag_macvlan_pools(struct net_device *dev) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); + struct netdev_nested_priv priv = { + .data = (void *)adapter, + }; /* flush any stale bits out of the fwd bitmask */ bitmap_clear(adapter->fwd_bitmask, 1, 63); /* walk through upper devices reassigning pools */ netdev_walk_all_upper_dev_rcu(dev, ixgbe_reassign_macvlan_pool, - adapter); + &priv); } /** @@ -9071,7 +9873,7 @@ static void ixgbe_defrag_macvlan_pools(struct net_device *dev) */ int ixgbe_setup_tc(struct net_device *dev, u8 tc) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); struct ixgbe_hw *hw = &adapter->hw; /* Hardware supports up to 8 traffic classes */ @@ -9234,14 +10036,18 @@ struct upper_walk_data { u8 queue; }; -static int get_macvlan_queue(struct net_device *upper, void *_data) +static int get_macvlan_queue(struct net_device *upper, + struct netdev_nested_priv *priv) { if (netif_is_macvlan(upper)) { struct ixgbe_fwd_adapter *vadapter = macvlan_accel_priv(upper); - struct upper_walk_data *data = _data; - struct ixgbe_adapter *adapter = data->adapter; - int ifindex = data->ifindex; + struct ixgbe_adapter *adapter; + struct upper_walk_data *data; + int ifindex; + data = (struct upper_walk_data *)priv->data; + ifindex = data->ifindex; + adapter = data->adapter; if (vadapter && upper->ifindex == ifindex) { data->queue = adapter->rx_ring[vadapter->rx_base_queue]->reg_idx; data->action = data->queue; @@ -9257,6 +10063,7 @@ static int handle_redirect_action(struct ixgbe_adapter *adapter, int ifindex, { struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ]; unsigned int num_vfs = adapter->num_vfs, vf; + struct netdev_nested_priv priv; struct upper_walk_data data; struct net_device *upper; @@ -9276,8 +10083,9 @@ static int handle_redirect_action(struct ixgbe_adapter *adapter, int ifindex, data.ifindex = ifindex; data.action = 0; data.queue = 0; + priv.data = (void *)&data; if (netdev_walk_all_upper_dev_rcu(adapter->netdev, - get_macvlan_queue, &data)) { + get_macvlan_queue, &priv)) { *action = data.action; *queue = data.queue; @@ -9488,6 +10296,10 @@ static int ixgbe_configure_clsu32(struct ixgbe_adapter *adapter, jump->mat = nexthdr[i].jump; adapter->jump_tables[link_uhtid] = jump; break; + } else { + kfree(mask); + kfree(input); + kfree(jump); } } return 0; @@ -9550,8 +10362,10 @@ static int ixgbe_configure_clsu32(struct ixgbe_adapter *adapter, ixgbe_atr_compute_perfect_hash_82599(&input->filter, mask); err = ixgbe_fdir_write_perfect_filter_82599(hw, &input->filter, input->sw_idx, queue); - if (!err) - ixgbe_update_ethtool_fdir_entry(adapter, input, input->sw_idx); + if (err) + goto err_out_w_lock; + + ixgbe_update_ethtool_fdir_entry(adapter, input, input->sw_idx); spin_unlock(&adapter->fdir_perfect_lock); if ((uhtid != 0x800) && (adapter->jump_tables[uhtid])) @@ -9605,27 +10419,6 @@ static int ixgbe_setup_tc_block_cb(enum tc_setup_type type, void *type_data, } } -static int ixgbe_setup_tc_block(struct net_device *dev, - struct tc_block_offload *f) -{ - struct ixgbe_adapter *adapter = netdev_priv(dev); - - if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS) - return -EOPNOTSUPP; - - switch (f->command) { - case TC_BLOCK_BIND: - return tcf_block_cb_register(f->block, ixgbe_setup_tc_block_cb, - adapter, adapter, f->extack); - case TC_BLOCK_UNBIND: - tcf_block_cb_unregister(f->block, ixgbe_setup_tc_block_cb, - adapter); - return 0; - default: - return -EOPNOTSUPP; - } -} - static int ixgbe_setup_tc_mqprio(struct net_device *dev, struct tc_mqprio_qopt *mqprio) { @@ -9633,12 +10426,19 @@ static int ixgbe_setup_tc_mqprio(struct net_device *dev, return ixgbe_setup_tc(dev, mqprio->num_tc); } +static LIST_HEAD(ixgbe_block_cb_list); + static int __ixgbe_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data) { + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); + switch (type) { case TC_SETUP_BLOCK: - return ixgbe_setup_tc_block(dev, type_data); + return flow_block_cb_setup_simple(type_data, + &ixgbe_block_cb_list, + ixgbe_setup_tc_block_cb, + adapter, adapter, true); case TC_SETUP_QDISC_MQPRIO: return ixgbe_setup_tc_mqprio(dev, type_data); default: @@ -9659,7 +10459,7 @@ void ixgbe_sriov_reinit(struct ixgbe_adapter *adapter) #endif void ixgbe_do_reset(struct net_device *netdev) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); if (netif_running(netdev)) ixgbe_reinit_locked(adapter); @@ -9670,7 +10470,7 @@ void ixgbe_do_reset(struct net_device *netdev) static netdev_features_t ixgbe_fix_features(struct net_device *netdev, netdev_features_t features) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); /* If Rx checksum is disabled, then RSC/LRO should also be disabled */ if (!(features & NETIF_F_RXCSUM)) @@ -9707,7 +10507,7 @@ static void ixgbe_reset_l2fw_offload(struct ixgbe_adapter *adapter) static int ixgbe_set_features(struct net_device *netdev, netdev_features_t features) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev); netdev_features_t changed = netdev->features ^ features; bool need_reset = false; @@ -9764,26 +10564,6 @@ static int ixgbe_set_features(struct net_device *netdev, netdev->features = features; - if ((adapter->flags & IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE)) { - if (features & NETIF_F_RXCSUM) { - adapter->flags2 |= IXGBE_FLAG2_UDP_TUN_REREG_NEEDED; - } else { - u32 port_mask = IXGBE_VXLANCTRL_VXLAN_UDPPORT_MASK; - - ixgbe_clear_udp_tunnel_port(adapter, port_mask); - } - } - - if ((adapter->flags & IXGBE_FLAG_GENEVE_OFFLOAD_CAPABLE)) { - if (features & NETIF_F_RXCSUM) { - adapter->flags2 |= IXGBE_FLAG2_UDP_TUN_REREG_NEEDED; - } else { - u32 port_mask = IXGBE_VXLANCTRL_GENEVE_UDPPORT_MASK; - - ixgbe_clear_udp_tunnel_port(adapter, port_mask); - } - } - if ((changed & NETIF_F_HW_L2FW_DOFFLOAD) && adapter->num_rx_pools > 1) ixgbe_reset_l2fw_offload(adapter); else if (need_reset) @@ -9792,130 +10572,18 @@ static int ixgbe_set_features(struct net_device *netdev, NETIF_F_HW_VLAN_CTAG_FILTER)) ixgbe_set_rx_mode(netdev); - return 0; -} - -/** - * ixgbe_add_udp_tunnel_port - Get notifications about adding UDP tunnel ports - * @dev: The port's netdev - * @ti: Tunnel endpoint information - **/ -static void ixgbe_add_udp_tunnel_port(struct net_device *dev, - struct udp_tunnel_info *ti) -{ - struct ixgbe_adapter *adapter = netdev_priv(dev); - struct ixgbe_hw *hw = &adapter->hw; - __be16 port = ti->port; - u32 port_shift = 0; - u32 reg; - - if (ti->sa_family != AF_INET) - return; - - switch (ti->type) { - case UDP_TUNNEL_TYPE_VXLAN: - if (!(adapter->flags & IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE)) - return; - - if (adapter->vxlan_port == port) - return; - - if (adapter->vxlan_port) { - netdev_info(dev, - "VXLAN port %d set, not adding port %d\n", - ntohs(adapter->vxlan_port), - ntohs(port)); - return; - } - - adapter->vxlan_port = port; - break; - case UDP_TUNNEL_TYPE_GENEVE: - if (!(adapter->flags & IXGBE_FLAG_GENEVE_OFFLOAD_CAPABLE)) - return; - - if (adapter->geneve_port == port) - return; - - if (adapter->geneve_port) { - netdev_info(dev, - "GENEVE port %d set, not adding port %d\n", - ntohs(adapter->geneve_port), - ntohs(port)); - return; - } - - port_shift = IXGBE_VXLANCTRL_GENEVE_UDPPORT_SHIFT; - adapter->geneve_port = port; - break; - default: - return; - } - - reg = IXGBE_READ_REG(hw, IXGBE_VXLANCTRL) | ntohs(port) << port_shift; - IXGBE_WRITE_REG(hw, IXGBE_VXLANCTRL, reg); -} - -/** - * ixgbe_del_udp_tunnel_port - Get notifications about removing UDP tunnel ports - * @dev: The port's netdev - * @ti: Tunnel endpoint information - **/ -static void ixgbe_del_udp_tunnel_port(struct net_device *dev, - struct udp_tunnel_info *ti) -{ - struct ixgbe_adapter *adapter = netdev_priv(dev); - u32 port_mask; - - if (ti->type != UDP_TUNNEL_TYPE_VXLAN && - ti->type != UDP_TUNNEL_TYPE_GENEVE) - return; - - if (ti->sa_family != AF_INET) - return; - - switch (ti->type) { - case UDP_TUNNEL_TYPE_VXLAN: - if (!(adapter->flags & IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE)) - return; - - if (adapter->vxlan_port != ti->port) { - netdev_info(dev, "VXLAN port %d not found\n", - ntohs(ti->port)); - return; - } - - port_mask = IXGBE_VXLANCTRL_VXLAN_UDPPORT_MASK; - break; - case UDP_TUNNEL_TYPE_GENEVE: - if (!(adapter->flags & IXGBE_FLAG_GENEVE_OFFLOAD_CAPABLE)) - return; - - if (adapter->geneve_port != ti->port) { - netdev_info(dev, "GENEVE port %d not found\n", - ntohs(ti->port)); - return; - } - - port_mask = IXGBE_VXLANCTRL_GENEVE_UDPPORT_MASK; - break; - default: - return; - } - - ixgbe_clear_udp_tunnel_port(adapter, port_mask); - adapter->flags2 |= IXGBE_FLAG2_UDP_TUN_REREG_NEEDED; + return 1; } static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, - u16 flags, + u16 flags, bool *notified, struct netlink_ext_ack *extack) { /* guarantee we can provide a unique filter for the unicast address */ if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); u16 pool = VMDQ_P(0); if (netdev_uc_count(dev) >= ixgbe_available_rars(adapter, pool)) @@ -10003,7 +10671,7 @@ static int ixgbe_ndo_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags, struct netlink_ext_ack *extack) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); struct nlattr *attr, *br_spec; int rem; @@ -10014,18 +10682,10 @@ static int ixgbe_ndo_bridge_setlink(struct net_device *dev, if (!br_spec) return -EINVAL; - nla_for_each_nested(attr, br_spec, rem) { - int status; - __u16 mode; + nla_for_each_nested_type(attr, IFLA_BRIDGE_MODE, br_spec, rem) { + __u16 mode = nla_get_u16(attr); + int status = ixgbe_configure_bridge_mode(adapter, mode); - if (nla_type(attr) != IFLA_BRIDGE_MODE) - continue; - - if (nla_len(attr) < sizeof(mode)) - return -EINVAL; - - mode = nla_get_u16(attr); - status = ixgbe_configure_bridge_mode(adapter, mode); if (status) return status; @@ -10039,7 +10699,7 @@ static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u32 filter_mask, int nlflags) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) return 0; @@ -10051,7 +10711,7 @@ static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev) { - struct ixgbe_adapter *adapter = netdev_priv(pdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(pdev); struct ixgbe_fwd_adapter *accel; int tcs = adapter->hw_tcs ? : 1; int pool, err; @@ -10148,7 +10808,7 @@ static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev) static void ixgbe_fwd_del(struct net_device *pdev, void *priv) { struct ixgbe_fwd_adapter *accel = priv; - struct ixgbe_adapter *adapter = netdev_priv(pdev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(pdev); unsigned int rxbase = accel->rx_base_queue; unsigned int i; @@ -10191,10 +10851,11 @@ ixgbe_features_check(struct sk_buff *skb, struct net_device *dev, unsigned int network_hdr_len, mac_hdr_len; /* Make certain the headers can be described by a context descriptor */ - mac_hdr_len = skb_network_header(skb) - skb->data; + mac_hdr_len = skb_network_offset(skb); if (unlikely(mac_hdr_len > IXGBE_MAX_MAC_HDR_LEN)) return features & ~(NETIF_F_HW_CSUM | NETIF_F_SCTP_CRC | + NETIF_F_GSO_UDP_L4 | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_TSO | NETIF_F_TSO6); @@ -10203,6 +10864,7 @@ ixgbe_features_check(struct sk_buff *skb, struct net_device *dev, if (unlikely(network_hdr_len > IXGBE_MAX_NETWORK_HDR_LEN)) return features & ~(NETIF_F_HW_CSUM | NETIF_F_SCTP_CRC | + NETIF_F_GSO_UDP_L4 | NETIF_F_TSO | NETIF_F_TSO6); @@ -10224,8 +10886,10 @@ ixgbe_features_check(struct sk_buff *skb, struct net_device *dev, static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) { int i, frame_size = dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); struct bpf_prog *old_prog; + bool need_reset; + int num_queues; if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) return -EINVAL; @@ -10244,47 +10908,63 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) return -EINVAL; } - if (nr_cpu_ids > MAX_XDP_QUEUES) + /* if the number of cpus is much larger than the maximum of queues, + * we should stop it and then return with ENOMEM like before. + */ + if (nr_cpu_ids > IXGBE_MAX_XDP_QS * 2) return -ENOMEM; old_prog = xchg(&adapter->xdp_prog, prog); + need_reset = (!!prog != !!old_prog); /* If transitioning XDP modes reconfigure rings */ - if (!!prog != !!old_prog) { - int err = ixgbe_setup_tc(dev, adapter->hw_tcs); + if (need_reset) { + int err; - if (err) { - rcu_assign_pointer(adapter->xdp_prog, old_prog); + if (!prog) + /* Wait until ndo_xsk_wakeup completes. */ + synchronize_rcu(); + err = ixgbe_setup_tc(dev, adapter->hw_tcs); + + if (err) return -EINVAL; - } + if (!prog) + xdp_features_clear_redirect_target(dev); } else { - for (i = 0; i < adapter->num_rx_queues; i++) - (void)xchg(&adapter->rx_ring[i]->xdp_prog, - adapter->xdp_prog); + for (i = 0; i < adapter->num_rx_queues; i++) { + WRITE_ONCE(adapter->rx_ring[i]->xdp_prog, + adapter->xdp_prog); + } } if (old_prog) bpf_prog_put(old_prog); + /* Kick start the NAPI context if there is an AF_XDP socket open + * on that queue id. This so that receiving will start. + */ + if (need_reset && prog) { + num_queues = min_t(int, adapter->num_rx_queues, + adapter->num_xdp_queues); + for (i = 0; i < num_queues; i++) + if (adapter->xdp_ring[i]->xsk_pool) + (void)ixgbe_xsk_wakeup(adapter->netdev, i, + XDP_WAKEUP_RX); + xdp_features_set_redirect_target(dev, true); + } + return 0; } static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); switch (xdp->command) { case XDP_SETUP_PROG: return ixgbe_xdp_setup(dev, xdp->prog); - case XDP_QUERY_PROG: - xdp->prog_id = adapter->xdp_prog ? - adapter->xdp_prog->aux->id : 0; - return 0; - case XDP_QUERY_XSK_UMEM: - return ixgbe_xsk_umem_query(adapter, &xdp->xsk.umem, - xdp->xsk.queue_id); - case XDP_SETUP_XSK_UMEM: - return ixgbe_xsk_umem_setup(adapter, xdp->xsk.umem, + case XDP_SETUP_XSK_POOL: + return ixgbe_xsk_pool_setup(adapter, xdp->xsk.pool, xdp->xsk.queue_id); default: @@ -10301,45 +10981,63 @@ void ixgbe_xdp_ring_update_tail(struct ixgbe_ring *ring) writel(ring->next_to_use, ring->tail); } +void ixgbe_xdp_ring_update_tail_locked(struct ixgbe_ring *ring) +{ + if (static_branch_unlikely(&ixgbe_xdp_locking_key)) + spin_lock(&ring->tx_lock); + ixgbe_xdp_ring_update_tail(ring); + if (static_branch_unlikely(&ixgbe_xdp_locking_key)) + spin_unlock(&ring->tx_lock); +} + static int ixgbe_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags) { - struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); struct ixgbe_ring *ring; - int drops = 0; + int nxmit = 0; int i; if (unlikely(test_bit(__IXGBE_DOWN, &adapter->state))) return -ENETDOWN; + if (!netif_carrier_ok(adapter->netdev) || + !netif_running(adapter->netdev)) + 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. */ - ring = adapter->xdp_prog ? adapter->xdp_ring[smp_processor_id()] : NULL; + ring = adapter->xdp_prog ? ixgbe_determine_xdp_ring(adapter) : NULL; if (unlikely(!ring)) return -ENXIO; if (unlikely(test_bit(__IXGBE_TX_DISABLED, &ring->state))) return -ENXIO; + if (static_branch_unlikely(&ixgbe_xdp_locking_key)) + spin_lock(&ring->tx_lock); + for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; int err; - err = ixgbe_xmit_xdp_ring(adapter, xdpf); - if (err != IXGBE_XDP_TX) { - xdp_return_frame_rx_napi(xdpf); - drops++; - } + err = ixgbe_xmit_xdp_ring(ring, xdpf); + if (err != IXGBE_XDP_TX) + break; + nxmit++; } if (unlikely(flags & XDP_XMIT_FLUSH)) ixgbe_xdp_ring_update_tail(ring); - return n - drops; + if (static_branch_unlikely(&ixgbe_xdp_locking_key)) + spin_unlock(&ring->tx_lock); + + return nxmit; } static const struct net_device_ops ixgbe_netdev_ops = { @@ -10354,14 +11052,16 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_set_tx_maxrate = ixgbe_tx_maxrate, .ndo_vlan_rx_add_vid = ixgbe_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = ixgbe_vlan_rx_kill_vid, - .ndo_do_ioctl = ixgbe_ioctl, + .ndo_eth_ioctl = ixgbe_ioctl, .ndo_set_vf_mac = ixgbe_ndo_set_vf_mac, .ndo_set_vf_vlan = ixgbe_ndo_set_vf_vlan, .ndo_set_vf_rate = ixgbe_ndo_set_vf_bw, .ndo_set_vf_spoofchk = ixgbe_ndo_set_vf_spoofchk, + .ndo_set_vf_link_state = ixgbe_ndo_set_vf_link_state, .ndo_set_vf_rss_query_en = ixgbe_ndo_set_vf_rss_query_en, .ndo_set_vf_trust = ixgbe_ndo_set_vf_trust, .ndo_get_vf_config = ixgbe_ndo_get_vf_config, + .ndo_get_vf_stats = ixgbe_ndo_get_vf_stats, .ndo_get_stats64 = ixgbe_get_stats64, .ndo_setup_tc = __ixgbe_setup_tc, #ifdef IXGBE_FCOE @@ -10381,12 +11081,12 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_bridge_getlink = ixgbe_ndo_bridge_getlink, .ndo_dfwd_add_station = ixgbe_fwd_add, .ndo_dfwd_del_station = ixgbe_fwd_del, - .ndo_udp_tunnel_add = ixgbe_add_udp_tunnel_port, - .ndo_udp_tunnel_del = ixgbe_del_udp_tunnel_port, .ndo_features_check = ixgbe_features_check, .ndo_bpf = ixgbe_xdp, .ndo_xdp_xmit = ixgbe_xdp_xmit, - .ndo_xsk_async_xmit = ixgbe_xsk_async_xmit, + .ndo_xsk_wakeup = ixgbe_xsk_wakeup, + .ndo_hwtstamp_get = ixgbe_ptp_hwtstamp_get, + .ndo_hwtstamp_set = ixgbe_ptp_hwtstamp_set, }; static void ixgbe_disable_txr_hw(struct ixgbe_adapter *adapter, @@ -10477,6 +11177,44 @@ static void ixgbe_reset_rxr_stats(struct ixgbe_ring *rx_ring) } /** + * ixgbe_irq_disable_single - Disable single IRQ vector + * @adapter: adapter structure + * @ring: ring index + **/ +static void ixgbe_irq_disable_single(struct ixgbe_adapter *adapter, u32 ring) +{ + struct ixgbe_hw *hw = &adapter->hw; + u64 qmask = BIT_ULL(ring); + u32 mask; + + switch (adapter->hw.mac.type) { + case ixgbe_mac_82598EB: + mask = qmask & IXGBE_EIMC_RTX_QUEUE; + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, mask); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + mask = (qmask & 0xFFFFFFFF); + if (mask) + IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(0), mask); + mask = (qmask >> 32); + if (mask) + IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(1), mask); + break; + default: + break; + } + IXGBE_WRITE_FLUSH(&adapter->hw); + if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) + synchronize_irq(adapter->msix_entries[ring].vector); + else + synchronize_irq(adapter->pdev->irq); +} + +/** * ixgbe_txrx_ring_disable - Disable Rx/Tx/XDP Tx rings * @adapter: adapter structure * @ring: ring index @@ -10492,6 +11230,11 @@ void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring) tx_ring = adapter->tx_ring[ring]; xdp_ring = adapter->xdp_ring[ring]; + ixgbe_irq_disable_single(adapter, ring); + + /* Rx/Tx/XDP Tx share the same napi context. */ + napi_disable(&rx_ring->q_vector->napi); + ixgbe_disable_txr(adapter, tx_ring); if (xdp_ring) ixgbe_disable_txr(adapter, xdp_ring); @@ -10500,9 +11243,6 @@ void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring) if (xdp_ring) synchronize_rcu(); - /* Rx/Tx/XDP Tx share the same napi context. */ - napi_disable(&rx_ring->q_vector->napi); - ixgbe_clean_tx_ring(tx_ring); if (xdp_ring) ixgbe_clean_tx_ring(xdp_ring); @@ -10530,9 +11270,6 @@ void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring) tx_ring = adapter->tx_ring[ring]; xdp_ring = adapter->xdp_ring[ring]; - /* Rx/Tx/XDP Tx share the same napi context. */ - napi_enable(&rx_ring->q_vector->napi); - ixgbe_configure_tx_ring(adapter, tx_ring); if (xdp_ring) ixgbe_configure_tx_ring(adapter, xdp_ring); @@ -10541,13 +11278,18 @@ void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring) clear_bit(__IXGBE_TX_DISABLED, &tx_ring->state); if (xdp_ring) clear_bit(__IXGBE_TX_DISABLED, &xdp_ring->state); + + /* Rx/Tx/XDP Tx share the same napi context. */ + napi_enable(&rx_ring->q_vector->napi); + ixgbe_irq_enable_queues(adapter, BIT_ULL(ring)); + IXGBE_WRITE_FLUSH(&adapter->hw); } /** * ixgbe_enumerate_functions - Get the number of ports this device has * @adapter: adapter structure * - * This function enumerates the phsyical functions co-located on a single slot, + * This function enumerates the physical functions co-located on a single slot, * in order to determine how many ports a device has. This is most useful in * determining the required GT/s of PCIe bandwidth necessary for optimal * performance. @@ -10625,7 +11367,7 @@ bool ixgbe_wol_supported(struct ixgbe_adapter *adapter, u16 device_id, /* only support first port */ if (hw->bus.func != 0) break; - /* fall through */ + fallthrough; case IXGBE_SUBDEV_ID_82599_SP_560FLR: case IXGBE_SUBDEV_ID_82599_SFP: case IXGBE_SUBDEV_ID_82599_RNDC: @@ -10658,6 +11400,24 @@ bool ixgbe_wol_supported(struct ixgbe_adapter *adapter, u16 device_id, } /** + * ixgbe_set_fw_version_e610 - Set FW version specifically on E610 adapters + * @adapter: the adapter private structure + * + * This function is used by probe and ethtool to determine the FW version to + * format to display. The FW version is taken from the EEPROM/NVM. + * + */ +void ixgbe_set_fw_version_e610(struct ixgbe_adapter *adapter) +{ + struct ixgbe_orom_info *orom = &adapter->hw.flash.orom; + struct ixgbe_nvm_info *nvm = &adapter->hw.flash.nvm; + + snprintf(adapter->eeprom_id, sizeof(adapter->eeprom_id), + "%x.%02x 0x%x %d.%d.%d", nvm->major, nvm->minor, + nvm->eetrack, orom->major, orom->build, orom->patch); +} + +/** * ixgbe_set_fw_version - Set FW version * @adapter: the adapter private structure * @@ -10669,6 +11429,11 @@ static void ixgbe_set_fw_version(struct ixgbe_adapter *adapter) struct ixgbe_hw *hw = &adapter->hw; struct ixgbe_nvm_version nvm_ver; + if (adapter->hw.mac.type == ixgbe_mac_e610) { + ixgbe_set_fw_version_e610(adapter); + return; + } + ixgbe_get_oem_prod_version(hw, &nvm_ver); if (nvm_ver.oem_valid) { snprintf(adapter->eeprom_id, sizeof(adapter->eeprom_id), @@ -10693,6 +11458,66 @@ static void ixgbe_set_fw_version(struct ixgbe_adapter *adapter) } /** + * ixgbe_recovery_probe - Handle FW recovery mode during probe + * @adapter: the adapter private structure + * + * Perform limited driver initialization when FW error is detected. + * + * Return: 0 on successful probe for E610, -EIO if recovery mode is detected + * for non-E610 adapter, error status code on any other case. + */ +static int ixgbe_recovery_probe(struct ixgbe_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct pci_dev *pdev = adapter->pdev; + struct ixgbe_hw *hw = &adapter->hw; + bool disable_dev; + int err = -EIO; + + if (hw->mac.type != ixgbe_mac_e610) + goto clean_up_probe; + + ixgbe_get_hw_control(adapter); + mutex_init(&hw->aci.lock); + err = ixgbe_get_flash_data(&adapter->hw); + if (err) + goto shutdown_aci; + + timer_setup(&adapter->service_timer, ixgbe_service_timer, 0); + INIT_WORK(&adapter->service_task, ixgbe_recovery_service_task); + set_bit(__IXGBE_SERVICE_INITED, &adapter->state); + clear_bit(__IXGBE_SERVICE_SCHED, &adapter->state); + + if (hw->mac.ops.get_bus_info) + hw->mac.ops.get_bus_info(hw); + + pci_set_drvdata(pdev, adapter); + /* We are creating devlink interface so NIC can be managed, + * e.g. new NVM image loaded + */ + devl_lock(adapter->devlink); + ixgbe_devlink_register_port(adapter); + SET_NETDEV_DEVLINK_PORT(adapter->netdev, + &adapter->devlink_port); + ixgbe_devlink_init_regions(adapter); + devl_register(adapter->devlink); + devl_unlock(adapter->devlink); + + return 0; +shutdown_aci: + mutex_destroy(&adapter->hw.aci.lock); + ixgbe_release_hw_control(adapter); +clean_up_probe: + disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state); + free_netdev(netdev); + devlink_free(adapter->devlink); + pci_release_mem_regions(pdev); + if (disable_dev) + pci_disable_device(pdev); + return err; +} + +/** * ixgbe_probe - Device Initialization Routine * @pdev: PCI device information struct * @ent: entry in ixgbe_pci_tbl @@ -10706,12 +11531,13 @@ static void ixgbe_set_fw_version(struct ixgbe_adapter *adapter) static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { struct net_device *netdev; + struct ixgbe_netdevice_priv *netdev_priv_wrapper; struct ixgbe_adapter *adapter = NULL; struct ixgbe_hw *hw; const struct ixgbe_info *ii = ixgbe_info_tbl[ent->driver_data]; - int i, err, pci_using_dac, expected_gts; unsigned int indices = MAX_TX_QUEUES; u8 part_str[IXGBE_PBANUM_LENGTH]; + int i, err, expected_gts; bool disable_dev = false; #ifdef IXGBE_FCOE u16 device_caps; @@ -10731,16 +11557,11 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) return err; - if (!dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) { - 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; - } - pci_using_dac = 0; + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (err) { + dev_err(&pdev->dev, + "No usable DMA configuration, aborting\n"); + goto err_dma; } err = pci_request_mem_regions(pdev, ixgbe_driver_name); @@ -10750,8 +11571,6 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_pci_reg; } - pci_enable_pcie_error_reporting(pdev); - pci_set_master(pdev); pci_save_state(pdev); @@ -10762,9 +11581,17 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) #else indices = IXGBE_MAX_RSS_INDICES; #endif + } else if (ii->mac == ixgbe_mac_e610) { + indices = IXGBE_MAX_RSS_INDICES_X550; + } + + adapter = ixgbe_allocate_devlink(&pdev->dev); + if (IS_ERR(adapter)) { + err = PTR_ERR(adapter); + goto err_devlink; } - netdev = alloc_etherdev_mq(sizeof(struct ixgbe_adapter), indices); + netdev = alloc_etherdev_mq(sizeof(*netdev_priv_wrapper), indices); if (!netdev) { err = -ENOMEM; goto err_alloc_etherdev; @@ -10772,7 +11599,8 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) SET_NETDEV_DEV(netdev, &pdev->dev); - adapter = netdev_priv(netdev); + netdev_priv_wrapper = netdev_priv(netdev); + netdev_priv_wrapper->adapter = adapter; adapter->netdev = netdev; adapter->pdev = pdev; @@ -10788,11 +11616,6 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_ioremap; } - netdev->netdev_ops = &ixgbe_netdev_ops; - ixgbe_set_ethtool_ops(netdev); - netdev->watchdog_timeo = 5 * HZ; - strlcpy(netdev->name, pci_name(pdev), sizeof(netdev->name)); - /* Setup hw api */ hw->mac.ops = *ii->mac_ops; hw->mac.type = ii->mac; @@ -10822,14 +11645,44 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw->phy.mdio.mdio_read = ixgbe_mdio_read; hw->phy.mdio.mdio_write = ixgbe_mdio_write; + netdev->netdev_ops = &ixgbe_netdev_ops; + ixgbe_set_ethtool_ops(netdev); + netdev->watchdog_timeo = 5 * HZ; + strscpy(netdev->name, pci_name(pdev), sizeof(netdev->name)); + /* setup the private structure */ err = ixgbe_sw_init(adapter, ii); if (err) goto err_sw_init; - /* Make sure the SWFW semaphore is in a valid state */ - if (hw->mac.ops.init_swfw_sync) - hw->mac.ops.init_swfw_sync(hw); + if (ixgbe_check_fw_error(adapter)) + return ixgbe_recovery_probe(adapter); + + if (adapter->hw.mac.type == ixgbe_mac_e610) { + err = ixgbe_get_caps(&adapter->hw); + if (err) + dev_err(&pdev->dev, "ixgbe_get_caps failed %d\n", err); + + err = ixgbe_get_flash_data(&adapter->hw); + if (err) + goto err_sw_init; + } + + if (adapter->hw.mac.type == ixgbe_mac_82599EB) + adapter->flags2 |= IXGBE_FLAG2_AUTO_DISABLE_VF; + + switch (adapter->hw.mac.type) { + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_e610: + netdev->udp_tunnel_nic_info = &ixgbe_udp_tunnels_x550; + break; + case ixgbe_mac_x550em_a: + netdev->udp_tunnel_nic_info = &ixgbe_udp_tunnels_x550em_a; + break; + default: + break; + } /* Make it possible the adapter to be woken up via WOL */ switch (adapter->hw.mac.type) { @@ -10838,6 +11691,7 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: IXGBE_WRITE_REG(&adapter->hw, IXGBE_WUS, ~0); break; default: @@ -10862,9 +11716,9 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = hw->mac.ops.reset_hw(hw); hw->phy.reset_if_overtemp = false; ixgbe_set_eee_capable(adapter); - if (err == IXGBE_ERR_SFP_NOT_PRESENT) { + if (err == -ENOENT) { err = 0; - } else if (err == IXGBE_ERR_SFP_NOT_SUPPORTED) { + } else if (err == -EOPNOTSUPP) { e_dev_err("failed to load because an unsupported SFP+ or QSFP module type was detected.\n"); e_dev_err("Reload the driver after installing a supported module.\n"); goto err_sw_init; @@ -10904,7 +11758,7 @@ skip_sriov: IXGBE_GSO_PARTIAL_FEATURES; if (hw->mac.type >= ixgbe_mac_82599EB) - netdev->features |= NETIF_F_SCTP_CRC; + netdev->features |= NETIF_F_SCTP_CRC | NETIF_F_GSO_UDP_L4; #ifdef CONFIG_IXGBE_IPSEC #define IXGBE_ESP_FEATURES (NETIF_F_HW_ESP | \ @@ -10926,8 +11780,7 @@ skip_sriov: netdev->hw_features |= NETIF_F_NTUPLE | NETIF_F_HW_TC; - if (pci_using_dac) - netdev->features |= NETIF_F_HIGHDMA; + netdev->features |= NETIF_F_HIGHDMA; netdev->vlan_features |= netdev->features | NETIF_F_TSO_MANGLEID; netdev->hw_enc_features |= netdev->vlan_features; @@ -10945,6 +11798,9 @@ skip_sriov: netdev->priv_flags |= IFF_UNICAST_FLT; netdev->priv_flags |= IFF_SUPP_NOFCS; + netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_XSK_ZEROCOPY; + /* MTU range: 68 - 9710 */ netdev->min_mtu = ETH_MIN_MTU; netdev->max_mtu = IXGBE_MAX_JUMBO_FRAME_SIZE - (ETH_HLEN + ETH_FCS_LEN); @@ -10972,8 +11828,7 @@ skip_sriov: NETIF_F_FCOE_CRC; netdev->vlan_features |= NETIF_F_FSO | - NETIF_F_FCOE_CRC | - NETIF_F_FCOE_MTU; + NETIF_F_FCOE_CRC; } #endif /* IXGBE_FCOE */ if (adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE) @@ -10981,11 +11836,6 @@ skip_sriov: if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) netdev->features |= NETIF_F_LRO; - if (ixgbe_check_fw_error(adapter)) { - err = -EIO; - goto err_sw_init; - } - /* make sure the EEPROM is good */ if (hw->eeprom.ops.validate_checksum(hw, NULL) < 0) { e_dev_err("The EEPROM Checksum Is Not Valid\n"); @@ -10996,7 +11846,7 @@ skip_sriov: eth_platform_get_mac_address(&adapter->pdev->dev, adapter->hw.mac.perm_addr); - memcpy(netdev->dev_addr, hw->mac.perm_addr, netdev->addr_len); + eth_hw_addr_set(netdev, hw->mac.perm_addr); if (!is_valid_ether_addr(netdev->dev_addr)) { e_dev_err("invalid MAC address\n"); @@ -11066,9 +11916,9 @@ skip_sriov: if (expected_gts > 0) ixgbe_check_minimum_link(adapter, expected_gts); - err = ixgbe_read_pba_string_generic(hw, part_str, sizeof(part_str)); + err = hw->eeprom.ops.read_pba_string(hw, part_str, sizeof(part_str)); if (err) - strlcpy(part_str, "Unknown", sizeof(part_str)); + strscpy(part_str, "Unknown", sizeof(part_str)); if (ixgbe_is_sfp(hw) && hw->phy.sfp_type != ixgbe_sfp_type_not_present) e_dev_info("MAC: %d, PHY: %d, SFP+: %d, PBA No: %s\n", hw->mac.type, hw->phy.type, hw->phy.sfp_type, @@ -11081,7 +11931,7 @@ skip_sriov: /* reset the hardware with the new settings */ err = hw->mac.ops.start_hw(hw); - if (err == IXGBE_ERR_EEPROM_VERSION) { + if (err == -EACCES) { /* We are running on a pre-production device, log a warning */ e_dev_warn("This device is a pre-production adapter/LOM. " "Please be aware there may be issues associated " @@ -11092,6 +11942,11 @@ skip_sriov: } strcpy(netdev->name, "eth%d"); pci_set_drvdata(pdev, adapter); + + devl_lock(adapter->devlink); + ixgbe_devlink_register_port(adapter); + SET_NETDEV_DEVLINK_PORT(adapter->netdev, &adapter->devlink_port); + err = register_netdev(netdev); if (err) goto err_register; @@ -11121,8 +11976,8 @@ skip_sriov: */ if (hw->mac.ops.set_fw_drv_ver) hw->mac.ops.set_fw_drv_ver(hw, 0xFF, 0xFF, 0xFF, 0xFF, - sizeof(ixgbe_driver_version) - 1, - ixgbe_driver_version); + sizeof(UTS_RELEASE) - 1, + UTS_RELEASE); /* add san mac addr to netdev */ ixgbe_add_sanmac_netdev(netdev); @@ -11142,25 +11997,43 @@ skip_sriov: IXGBE_LINK_SPEED_10GB_FULL | IXGBE_LINK_SPEED_1GB_FULL, true); - ixgbe_mii_bus_init(hw); + err = ixgbe_mii_bus_init(hw); + if (err) + goto err_netdev; + + ixgbe_devlink_init_regions(adapter); + devl_register(adapter->devlink); + devl_unlock(adapter->devlink); + + if (ixgbe_fwlog_init(hw)) + e_dev_info("Firmware logging not supported\n"); return 0; +err_netdev: + unregister_netdev(netdev); err_register: + devl_port_unregister(&adapter->devlink_port); + devl_unlock(adapter->devlink); ixgbe_release_hw_control(adapter); ixgbe_clear_interrupt_scheme(adapter); err_sw_init: + if (hw->mac.type == ixgbe_mac_e610) + mutex_destroy(&adapter->hw.aci.lock); ixgbe_disable_sriov(adapter); adapter->flags2 &= ~IXGBE_FLAG2_SEARCH_FOR_SFP; iounmap(adapter->io_addr); kfree(adapter->jump_tables[0]); kfree(adapter->mac_table); kfree(adapter->rss_key); + bitmap_free(adapter->af_xdp_zc_qps); err_ioremap: disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state); free_netdev(netdev); err_alloc_etherdev: + devlink_free(adapter->devlink); pci_release_mem_regions(pdev); +err_devlink: err_pci_reg: err_dma: if (!adapter || disable_dev) @@ -11173,7 +12046,7 @@ err_dma: * @pdev: PCI device information struct * * ixgbe_remove is called by the PCI subsystem to alert the driver - * that it should release a PCI device. The could be caused by a + * that it should release a PCI device. This could be caused by a * Hot-Plug event, or because the driver is going to be removed from * memory. **/ @@ -11189,11 +12062,18 @@ static void ixgbe_remove(struct pci_dev *pdev) return; netdev = adapter->netdev; + devl_lock(adapter->devlink); + devl_unregister(adapter->devlink); + ixgbe_devlink_destroy_regions(adapter); + ixgbe_fwlog_deinit(&adapter->hw); ixgbe_dbg_adapter_exit(adapter); set_bit(__IXGBE_REMOVING, &adapter->state); cancel_work_sync(&adapter->service_task); + if (adapter->hw.mac.type == ixgbe_mac_e610) + ixgbe_disable_link_status_events(adapter); + if (adapter->mii_bus) mdiobus_unregister(adapter->mii_bus); @@ -11219,6 +12099,9 @@ static void ixgbe_remove(struct pci_dev *pdev) if (netdev->reg_state == NETREG_REGISTERED) unregister_netdev(netdev); + devl_port_unregister(&adapter->devlink_port); + devl_unlock(adapter->devlink); + ixgbe_stop_ipsec_offload(adapter); ixgbe_clear_interrupt_scheme(adapter); @@ -11244,13 +12127,17 @@ static void ixgbe_remove(struct pci_dev *pdev) kfree(adapter->mac_table); kfree(adapter->rss_key); + bitmap_free(adapter->af_xdp_zc_qps); disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state); free_netdev(netdev); - pci_disable_pcie_error_reporting(pdev); + if (adapter->hw.mac.type == ixgbe_mac_e610) + mutex_destroy(&adapter->hw.aci.lock); if (disable_dev) pci_disable_device(pdev); + + devlink_free(adapter->devlink); } /** @@ -11305,7 +12192,7 @@ static pci_ers_result_t ixgbe_io_error_detected(struct pci_dev *pdev, if ((pf_func & 1) == (pdev->devfn & 1)) { unsigned int device_id; - vf = (req_id & 0x7F) >> 1; + vf = FIELD_GET(0x7F, req_id); e_dev_err("VF %d has caused a PCIe error\n", vf); e_dev_err("TLP: dw0: %8.8x\tdw1: %8.8x\tdw2: " "%8.8x\tdw3: %8.8x\n", @@ -11326,6 +12213,9 @@ static pci_ers_result_t ixgbe_io_error_detected(struct pci_dev *pdev, case ixgbe_mac_x550em_a: device_id = IXGBE_DEV_ID_X550EM_A_VF; break; + case ixgbe_mac_e610: + device_id = IXGBE_DEV_ID_E610_VF; + break; default: device_id = 0; break; @@ -11408,7 +12298,6 @@ static pci_ers_result_t ixgbe_io_slot_reset(struct pci_dev *pdev) adapter->hw.hw_addr = adapter->io_addr; pci_set_master(pdev); pci_restore_state(pdev); - pci_save_state(pdev); pci_wake_from_d3(pdev, false); @@ -11454,16 +12343,15 @@ static const struct pci_error_handlers ixgbe_err_handler = { .resume = ixgbe_io_resume, }; +static DEFINE_SIMPLE_DEV_PM_OPS(ixgbe_pm_ops, ixgbe_suspend, ixgbe_resume); + static struct pci_driver ixgbe_driver = { - .name = ixgbe_driver_name, - .id_table = ixgbe_pci_tbl, - .probe = ixgbe_probe, - .remove = ixgbe_remove, -#ifdef CONFIG_PM - .suspend = ixgbe_suspend, - .resume = ixgbe_resume, -#endif - .shutdown = ixgbe_shutdown, + .name = ixgbe_driver_name, + .id_table = ixgbe_pci_tbl, + .probe = ixgbe_probe, + .remove = ixgbe_remove, + .driver.pm = pm_sleep_ptr(&ixgbe_pm_ops), + .shutdown = ixgbe_shutdown, .sriov_configure = ixgbe_pci_sriov_configure, .err_handler = &ixgbe_err_handler }; @@ -11477,7 +12365,7 @@ static struct pci_driver ixgbe_driver = { static int __init ixgbe_init_module(void) { int ret; - pr_info("%s - version %s\n", ixgbe_driver_string, ixgbe_driver_version); + pr_info("%s\n", ixgbe_driver_string); pr_info("%s\n", ixgbe_copyright); ixgbe_wq = create_singlethread_workqueue(ixgbe_driver_name); |