--- zzzz-none-000/linux-3.10.107/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c 2021-02-04 17:41:59.000000000 +0000 @@ -1,7 +1,7 @@ /******************************************************************************* Intel 82599 Virtual Function driver - Copyright(c) 1999 - 2012 Intel Corporation. + Copyright(c) 1999 - 2015 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -13,8 +13,7 @@ more details. You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + this program; if not, see . The full GNU General Public License is included in this distribution in the file called "COPYING". @@ -25,7 +24,6 @@ *******************************************************************************/ - /****************************************************************************** Copyright (c)2006 - 2007 Myricom, Inc. for some LRO specific code ******************************************************************************/ @@ -58,7 +56,7 @@ static const char ixgbevf_driver_string[] = "Intel(R) 10 Gigabit PCI Express Virtual Function Network Driver"; -#define DRV_VERSION "2.7.12-k" +#define DRV_VERSION "2.12.1-k" const char ixgbevf_driver_version[] = DRV_VERSION; static char ixgbevf_copyright[] = "Copyright (c) 2009 - 2012 Intel Corporation."; @@ -66,6 +64,8 @@ static const struct ixgbevf_info *ixgbevf_info_tbl[] = { [board_82599_vf] = &ixgbevf_82599_vf_info, [board_X540_vf] = &ixgbevf_X540_vf_info, + [board_X550_vf] = &ixgbevf_X550_vf_info, + [board_X550EM_x_vf] = &ixgbevf_X550EM_x_vf_info, }; /* ixgbevf_pci_tbl - PCI Device ID Table @@ -76,16 +76,18 @@ * { Vendor ID, Device ID, SubVendor ID, SubDevice ID, * Class, Class Mask, private data (not used) } */ -static DEFINE_PCI_DEVICE_TABLE(ixgbevf_pci_tbl) = { +static const struct pci_device_id ixgbevf_pci_tbl[] = { {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_VF), board_82599_vf }, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X540_VF), board_X540_vf }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550_VF), board_X550_vf }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_VF), board_X550EM_x_vf }, /* required last entry */ {0, } }; MODULE_DEVICE_TABLE(pci, ixgbevf_pci_tbl); MODULE_AUTHOR("Intel Corporation, "); -MODULE_DESCRIPTION("Intel(R) 82599 Virtual Function Driver"); +MODULE_DESCRIPTION("Intel(R) 10 Gigabit Virtual Function Network Driver"); MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_VERSION); @@ -94,22 +96,70 @@ module_param(debug, int, 0); MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); +static void ixgbevf_service_event_schedule(struct ixgbevf_adapter *adapter) +{ + if (!test_bit(__IXGBEVF_DOWN, &adapter->state) && + !test_bit(__IXGBEVF_REMOVING, &adapter->state) && + !test_and_set_bit(__IXGBEVF_SERVICE_SCHED, &adapter->state)) + schedule_work(&adapter->service_task); +} + +static void ixgbevf_service_event_complete(struct ixgbevf_adapter *adapter) +{ + BUG_ON(!test_bit(__IXGBEVF_SERVICE_SCHED, &adapter->state)); + + /* flush memory to make sure state is correct before next watchdog */ + smp_mb__before_atomic(); + clear_bit(__IXGBEVF_SERVICE_SCHED, &adapter->state); +} + /* forward decls */ +static void ixgbevf_queue_reset_subtask(struct ixgbevf_adapter *adapter); static void ixgbevf_set_itr(struct ixgbevf_q_vector *q_vector); static void ixgbevf_free_all_rx_resources(struct ixgbevf_adapter *adapter); -static inline void ixgbevf_release_rx_desc(struct ixgbe_hw *hw, - struct ixgbevf_ring *rx_ring, - u32 val) -{ - /* - * Force memory writes to complete before letting h/w - * know there are new descriptors to fetch. (Only - * applicable for weak-ordered memory model archs, - * such as IA-64). +static void ixgbevf_remove_adapter(struct ixgbe_hw *hw) +{ + struct ixgbevf_adapter *adapter = hw->back; + + if (!hw->hw_addr) + return; + hw->hw_addr = NULL; + dev_err(&adapter->pdev->dev, "Adapter removed\n"); + if (test_bit(__IXGBEVF_SERVICE_INITED, &adapter->state)) + ixgbevf_service_event_schedule(adapter); +} + +static void ixgbevf_check_remove(struct ixgbe_hw *hw, u32 reg) +{ + u32 value; + + /* The following check not only optimizes a bit by not + * performing a read on the status register when the + * register just read was a status register read that + * returned IXGBE_FAILED_READ_REG. It also blocks any + * potential recursion. */ - wmb(); - IXGBE_WRITE_REG(hw, IXGBE_VFRDT(rx_ring->reg_idx), val); + if (reg == IXGBE_VFSTATUS) { + ixgbevf_remove_adapter(hw); + return; + } + value = ixgbevf_read_reg(hw, IXGBE_VFSTATUS); + if (value == IXGBE_FAILED_READ_REG) + ixgbevf_remove_adapter(hw); +} + +u32 ixgbevf_read_reg(struct ixgbe_hw *hw, u32 reg) +{ + u8 __iomem *reg_addr = ACCESS_ONCE(hw->hw_addr); + u32 value; + + if (IXGBE_REMOVED(reg_addr)) + return IXGBE_FAILED_READ_REG; + value = readl(reg_addr + reg); + if (unlikely(value == IXGBE_FAILED_READ_REG)) + ixgbevf_check_remove(hw, reg); + return value; } /** @@ -118,12 +168,13 @@ * @direction: 0 for Rx, 1 for Tx, -1 for other causes * @queue: queue to map the corresponding interrupt to * @msix_vector: the vector to map to the corresponding queue - */ + **/ static void ixgbevf_set_ivar(struct ixgbevf_adapter *adapter, s8 direction, u8 queue, u8 msix_vector) { u32 ivar, index; struct ixgbe_hw *hw = &adapter->hw; + if (direction == -1) { /* other causes */ msix_vector |= IXGBE_IVAR_ALLOC_VAL; @@ -132,7 +183,7 @@ ivar |= msix_vector; IXGBE_WRITE_REG(hw, IXGBE_VTIVAR_MISC, ivar); } else { - /* tx or rx causes */ + /* Tx or Rx causes */ msix_vector |= IXGBE_IVAR_ALLOC_VAL; index = ((16 * (queue & 1)) + (8 * direction)); ivar = IXGBE_READ_REG(hw, IXGBE_VTIVAR(queue >> 1)); @@ -143,38 +194,93 @@ } static void ixgbevf_unmap_and_free_tx_resource(struct ixgbevf_ring *tx_ring, - struct ixgbevf_tx_buffer - *tx_buffer_info) + struct ixgbevf_tx_buffer *tx_buffer) { - if (tx_buffer_info->dma) { - if (tx_buffer_info->mapped_as_page) - dma_unmap_page(tx_ring->dev, - tx_buffer_info->dma, - tx_buffer_info->length, - DMA_TO_DEVICE); - else + if (tx_buffer->skb) { + dev_kfree_skb_any(tx_buffer->skb); + if (dma_unmap_len(tx_buffer, len)) dma_unmap_single(tx_ring->dev, - tx_buffer_info->dma, - tx_buffer_info->length, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), DMA_TO_DEVICE); - tx_buffer_info->dma = 0; + } else if (dma_unmap_len(tx_buffer, len)) { + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); } - if (tx_buffer_info->skb) { - dev_kfree_skb_any(tx_buffer_info->skb); - tx_buffer_info->skb = NULL; + tx_buffer->next_to_watch = NULL; + tx_buffer->skb = NULL; + dma_unmap_len_set(tx_buffer, len, 0); + /* tx_buffer must be completely set up in the transmit path */ +} + +static u64 ixgbevf_get_tx_completed(struct ixgbevf_ring *ring) +{ + return ring->stats.packets; +} + +static u32 ixgbevf_get_tx_pending(struct ixgbevf_ring *ring) +{ + struct ixgbevf_adapter *adapter = netdev_priv(ring->netdev); + struct ixgbe_hw *hw = &adapter->hw; + + u32 head = IXGBE_READ_REG(hw, IXGBE_VFTDH(ring->reg_idx)); + u32 tail = IXGBE_READ_REG(hw, IXGBE_VFTDT(ring->reg_idx)); + + if (head != tail) + return (head < tail) ? + tail - head : (tail + ring->count - head); + + return 0; +} + +static inline bool ixgbevf_check_tx_hang(struct ixgbevf_ring *tx_ring) +{ + u32 tx_done = ixgbevf_get_tx_completed(tx_ring); + u32 tx_done_old = tx_ring->tx_stats.tx_done_old; + u32 tx_pending = ixgbevf_get_tx_pending(tx_ring); + + clear_check_for_tx_hang(tx_ring); + + /* Check for a hung queue, but be thorough. This verifies + * that a transmit has been completed since the previous + * check AND there is at least one packet pending. The + * ARMED bit is set to indicate a potential hang. + */ + if ((tx_done_old == tx_done) && tx_pending) { + /* make sure it is true for two checks in a row */ + return test_and_set_bit(__IXGBEVF_HANG_CHECK_ARMED, + &tx_ring->state); } - tx_buffer_info->time_stamp = 0; - /* tx_buffer_info must be completely set up in the transmit path */ + /* reset the countdown */ + clear_bit(__IXGBEVF_HANG_CHECK_ARMED, &tx_ring->state); + + /* update completed stats and continue */ + tx_ring->tx_stats.tx_done_old = tx_done; + + return false; } -#define IXGBE_MAX_TXD_PWR 14 -#define IXGBE_MAX_DATA_PER_TXD (1 << IXGBE_MAX_TXD_PWR) +static void ixgbevf_tx_timeout_reset(struct ixgbevf_adapter *adapter) +{ + /* Do the reset outside of interrupt context */ + if (!test_bit(__IXGBEVF_DOWN, &adapter->state)) { + adapter->flags |= IXGBEVF_FLAG_RESET_REQUESTED; + ixgbevf_service_event_schedule(adapter); + } +} -/* Tx Descriptors needed, worst case */ -#define TXD_USE_COUNT(S) DIV_ROUND_UP((S), IXGBE_MAX_DATA_PER_TXD) -#define DESC_NEEDED (MAX_SKB_FRAGS + 4) +/** + * ixgbevf_tx_timeout - Respond to a Tx Hang + * @netdev: network interface device structure + **/ +static void ixgbevf_tx_timeout(struct net_device *netdev) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); -static void ixgbevf_tx_timeout(struct net_device *netdev); + ixgbevf_tx_timeout_reset(adapter); +} /** * ixgbevf_clean_tx_irq - Reclaim resources after transmit completes @@ -185,20 +291,21 @@ struct ixgbevf_ring *tx_ring) { struct ixgbevf_adapter *adapter = q_vector->adapter; - union ixgbe_adv_tx_desc *tx_desc, *eop_desc; - struct ixgbevf_tx_buffer *tx_buffer_info; - unsigned int i, count = 0; + struct ixgbevf_tx_buffer *tx_buffer; + union ixgbe_adv_tx_desc *tx_desc; unsigned int total_bytes = 0, total_packets = 0; + unsigned int budget = tx_ring->count / 2; + unsigned int i = tx_ring->next_to_clean; if (test_bit(__IXGBEVF_DOWN, &adapter->state)) return true; - i = tx_ring->next_to_clean; - tx_buffer_info = &tx_ring->tx_buffer_info[i]; - eop_desc = tx_buffer_info->next_to_watch; + tx_buffer = &tx_ring->tx_buffer_info[i]; + tx_desc = IXGBEVF_TX_DESC(tx_ring, i); + i -= tx_ring->count; do { - bool cleaned = false; + union ixgbe_adv_tx_desc *eop_desc = tx_buffer->next_to_watch; /* if next_to_watch is not set then there is no work pending */ if (!eop_desc) @@ -212,101 +319,179 @@ break; /* clear next_to_watch to prevent false hangs */ - tx_buffer_info->next_to_watch = NULL; + tx_buffer->next_to_watch = NULL; - for ( ; !cleaned; count++) { - struct sk_buff *skb; - tx_desc = IXGBEVF_TX_DESC(tx_ring, i); - cleaned = (tx_desc == eop_desc); - skb = tx_buffer_info->skb; - - if (cleaned && skb) { - unsigned int segs, bytecount; - - /* gso_segs is currently only valid for tcp */ - segs = skb_shinfo(skb)->gso_segs ?: 1; - /* multiply data chunks by size of headers */ - bytecount = ((segs - 1) * skb_headlen(skb)) + - skb->len; - total_packets += segs; - total_bytes += bytecount; + /* update the statistics for this packet */ + total_bytes += tx_buffer->bytecount; + total_packets += tx_buffer->gso_segs; + + /* free the skb */ + dev_kfree_skb_any(tx_buffer->skb); + + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + + /* clear tx_buffer data */ + tx_buffer->skb = NULL; + dma_unmap_len_set(tx_buffer, len, 0); + + /* unmap remaining buffers */ + while (tx_desc != eop_desc) { + tx_buffer++; + tx_desc++; + i++; + if (unlikely(!i)) { + i -= tx_ring->count; + tx_buffer = tx_ring->tx_buffer_info; + tx_desc = IXGBEVF_TX_DESC(tx_ring, 0); } - ixgbevf_unmap_and_free_tx_resource(tx_ring, - tx_buffer_info); - - tx_desc->wb.status = 0; - - i++; - if (i == tx_ring->count) - i = 0; + /* unmap any remaining paged data */ + if (dma_unmap_len(tx_buffer, len)) { + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + } + } - tx_buffer_info = &tx_ring->tx_buffer_info[i]; + /* move us one more past the eop_desc for start of next pkt */ + tx_buffer++; + tx_desc++; + i++; + if (unlikely(!i)) { + i -= tx_ring->count; + tx_buffer = tx_ring->tx_buffer_info; + tx_desc = IXGBEVF_TX_DESC(tx_ring, 0); } - eop_desc = tx_buffer_info->next_to_watch; - } while (count < tx_ring->count); + /* issue prefetch for next Tx descriptor */ + prefetch(tx_desc); + + /* update budget accounting */ + budget--; + } while (likely(budget)); + 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; + + if (check_for_tx_hang(tx_ring) && ixgbevf_check_tx_hang(tx_ring)) { + struct ixgbe_hw *hw = &adapter->hw; + union ixgbe_adv_tx_desc *eop_desc; + + eop_desc = tx_ring->tx_buffer_info[i].next_to_watch; + + pr_err("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" + " next_to_watch <%p>\n" + " eop_desc->wb.status <%x>\n" + " time_stamp <%lx>\n" + " jiffies <%lx>\n", + tx_ring->queue_index, + IXGBE_READ_REG(hw, IXGBE_VFTDH(tx_ring->reg_idx)), + IXGBE_READ_REG(hw, IXGBE_VFTDT(tx_ring->reg_idx)), + tx_ring->next_to_use, i, + eop_desc, (eop_desc ? eop_desc->wb.status : 0), + tx_ring->tx_buffer_info[i].time_stamp, jiffies); + + netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index); + + /* schedule immediate reset if we believe we hung */ + ixgbevf_tx_timeout_reset(adapter); + + return true; + } #define TX_WAKE_THRESHOLD (DESC_NEEDED * 2) - if (unlikely(count && netif_carrier_ok(tx_ring->netdev) && - (IXGBE_DESC_UNUSED(tx_ring) >= TX_WAKE_THRESHOLD))) { + if (unlikely(total_packets && netif_carrier_ok(tx_ring->netdev) && + (ixgbevf_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(__IXGBEVF_DOWN, &adapter->state)) { netif_wake_subqueue(tx_ring->netdev, tx_ring->queue_index); - ++adapter->restart_queue; + ++tx_ring->tx_stats.restart_queue; } } - u64_stats_update_begin(&tx_ring->syncp); - tx_ring->total_bytes += total_bytes; - tx_ring->total_packets += total_packets; - u64_stats_update_end(&tx_ring->syncp); - q_vector->tx.total_bytes += total_bytes; - q_vector->tx.total_packets += total_packets; - - return count < tx_ring->count; + return !!budget; } /** - * ixgbevf_receive_skb - Send a completed packet up the stack + * ixgbevf_rx_skb - Helper function to determine proper Rx method * @q_vector: structure containing interrupt and ring information * @skb: packet to send up - * @status: hardware indication of status of receive - * @rx_desc: rx descriptor **/ -static void ixgbevf_receive_skb(struct ixgbevf_q_vector *q_vector, - struct sk_buff *skb, u8 status, - union ixgbe_adv_rx_desc *rx_desc) +static void ixgbevf_rx_skb(struct ixgbevf_q_vector *q_vector, + struct sk_buff *skb) { - struct ixgbevf_adapter *adapter = q_vector->adapter; - bool is_vlan = (status & IXGBE_RXD_STAT_VP); - u16 tag = le16_to_cpu(rx_desc->wb.upper.vlan); +#ifdef CONFIG_NET_RX_BUSY_POLL + skb_mark_napi_id(skb, &q_vector->napi); - if (is_vlan && test_bit(tag & VLAN_VID_MASK, adapter->active_vlans)) - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), tag); + if (ixgbevf_qv_busy_polling(q_vector)) { + netif_receive_skb(skb); + /* exit early if we busy polled */ + return; + } +#endif /* CONFIG_NET_RX_BUSY_POLL */ - if (!(adapter->flags & IXGBE_FLAG_IN_NETPOLL)) - napi_gro_receive(&q_vector->napi, skb); - else - netif_rx(skb); + napi_gro_receive(&q_vector->napi, skb); +} + +#define IXGBE_RSS_L4_TYPES_MASK \ + ((1ul << IXGBE_RXDADV_RSSTYPE_IPV4_TCP) | \ + (1ul << IXGBE_RXDADV_RSSTYPE_IPV4_UDP) | \ + (1ul << IXGBE_RXDADV_RSSTYPE_IPV6_TCP) | \ + (1ul << IXGBE_RXDADV_RSSTYPE_IPV6_UDP)) + +static inline void ixgbevf_rx_hash(struct ixgbevf_ring *ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + u16 rss_type; + + if (!(ring->netdev->features & NETIF_F_RXHASH)) + return; + + rss_type = le16_to_cpu(rx_desc->wb.lower.lo_dword.hs_rss.pkt_info) & + IXGBE_RXDADV_RSSTYPE_MASK; + + if (!rss_type) + return; + + skb_set_hash(skb, le32_to_cpu(rx_desc->wb.lower.hi_dword.rss), + (IXGBE_RSS_L4_TYPES_MASK & (1ul << rss_type)) ? + PKT_HASH_TYPE_L4 : PKT_HASH_TYPE_L3); } /** * ixgbevf_rx_checksum - indicate in skb if hw indicated a good cksum - * @ring: pointer to Rx descriptor ring structure - * @status_err: hardware indication of status of receive + * @ring: structure containig ring specific data + * @rx_desc: current Rx descriptor being processed * @skb: skb currently being received and modified **/ static inline void ixgbevf_rx_checksum(struct ixgbevf_ring *ring, - u32 status_err, struct sk_buff *skb) + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) { skb_checksum_none_assert(skb); @@ -315,77 +500,404 @@ return; /* if IP and error */ - if ((status_err & IXGBE_RXD_STAT_IPCS) && - (status_err & IXGBE_RXDADV_ERR_IPE)) { - ring->hw_csum_rx_error++; + if (ixgbevf_test_staterr(rx_desc, IXGBE_RXD_STAT_IPCS) && + ixgbevf_test_staterr(rx_desc, IXGBE_RXDADV_ERR_IPE)) { + ring->rx_stats.csum_err++; return; } - if (!(status_err & IXGBE_RXD_STAT_L4CS)) + if (!ixgbevf_test_staterr(rx_desc, IXGBE_RXD_STAT_L4CS)) return; - if (status_err & IXGBE_RXDADV_ERR_TCPE) { - ring->hw_csum_rx_error++; + if (ixgbevf_test_staterr(rx_desc, IXGBE_RXDADV_ERR_TCPE)) { + ring->rx_stats.csum_err++; return; } /* It must be a TCP or UDP packet with a valid checksum */ skb->ip_summed = CHECKSUM_UNNECESSARY; - ring->hw_csum_rx_good++; +} + +/** + * ixgbevf_process_skb_fields - Populate skb header fields from Rx descriptor + * @rx_ring: rx descriptor ring packet is being transacted on + * @rx_desc: pointer to the EOP Rx descriptor + * @skb: pointer to current skb being populated + * + * This function checks the ring, descriptor, and packet information in + * order to populate the checksum, VLAN, protocol, and other fields within + * the skb. + **/ +static void ixgbevf_process_skb_fields(struct ixgbevf_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + ixgbevf_rx_hash(rx_ring, rx_desc, skb); + ixgbevf_rx_checksum(rx_ring, rx_desc, skb); + + if (ixgbevf_test_staterr(rx_desc, IXGBE_RXD_STAT_VP)) { + u16 vid = le16_to_cpu(rx_desc->wb.upper.vlan); + unsigned long *active_vlans = netdev_priv(rx_ring->netdev); + + if (test_bit(vid & VLAN_VID_MASK, active_vlans)) + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid); + } + + skb->protocol = eth_type_trans(skb, rx_ring->netdev); +} + +/** + * ixgbevf_is_non_eop - process handling of non-EOP buffers + * @rx_ring: Rx ring being processed + * @rx_desc: Rx descriptor for current buffer + * @skb: current socket buffer containing buffer in progress + * + * This function updates next to clean. If the buffer is an EOP buffer + * this function exits returning false, otherwise it will place the + * sk_buff in the next buffer to be chained and return true indicating + * that this is in fact a non-EOP buffer. + **/ +static bool ixgbevf_is_non_eop(struct ixgbevf_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc) +{ + u32 ntc = rx_ring->next_to_clean + 1; + + /* fetch, update, and store next to clean */ + ntc = (ntc < rx_ring->count) ? ntc : 0; + rx_ring->next_to_clean = ntc; + + prefetch(IXGBEVF_RX_DESC(rx_ring, ntc)); + + if (likely(ixgbevf_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP))) + return false; + + return true; +} + +static bool ixgbevf_alloc_mapped_page(struct ixgbevf_ring *rx_ring, + struct ixgbevf_rx_buffer *bi) +{ + struct page *page = bi->page; + dma_addr_t dma = bi->dma; + + /* since we are recycling buffers we should seldom need to alloc */ + if (likely(page)) + return true; + + /* alloc new page for storage */ + page = dev_alloc_page(); + if (unlikely(!page)) { + rx_ring->rx_stats.alloc_rx_page_failed++; + return false; + } + + /* map page for use */ + dma = dma_map_page(rx_ring->dev, page, 0, + PAGE_SIZE, DMA_FROM_DEVICE); + + /* if mapping failed free memory back to system since + * there isn't much point in holding memory we can't use + */ + if (dma_mapping_error(rx_ring->dev, dma)) { + __free_page(page); + + rx_ring->rx_stats.alloc_rx_buff_failed++; + return false; + } + + bi->dma = dma; + bi->page = page; + bi->page_offset = 0; + + return true; } /** * ixgbevf_alloc_rx_buffers - Replace used receive buffers; packet split - * @adapter: address of board private structure + * @rx_ring: rx descriptor ring (for a specific queue) to setup buffers on + * @cleaned_count: number of buffers to replace **/ -static void ixgbevf_alloc_rx_buffers(struct ixgbevf_adapter *adapter, - struct ixgbevf_ring *rx_ring, - int cleaned_count) +static void ixgbevf_alloc_rx_buffers(struct ixgbevf_ring *rx_ring, + u16 cleaned_count) { - struct pci_dev *pdev = adapter->pdev; union ixgbe_adv_rx_desc *rx_desc; struct ixgbevf_rx_buffer *bi; unsigned int i = rx_ring->next_to_use; - bi = &rx_ring->rx_buffer_info[i]; + /* nothing to do or no valid netdev defined */ + if (!cleaned_count || !rx_ring->netdev) + return; - while (cleaned_count--) { - rx_desc = IXGBEVF_RX_DESC(rx_ring, i); + rx_desc = IXGBEVF_RX_DESC(rx_ring, i); + bi = &rx_ring->rx_buffer_info[i]; + i -= rx_ring->count; - if (!bi->skb) { - struct sk_buff *skb; + do { + if (!ixgbevf_alloc_mapped_page(rx_ring, bi)) + break; - skb = netdev_alloc_skb_ip_align(rx_ring->netdev, - rx_ring->rx_buf_len); - if (!skb) { - adapter->alloc_rx_buff_failed++; - goto no_buffers; - } - bi->skb = skb; + /* Refresh the desc even if pkt_addr didn't change + * because each write-back erases this info. + */ + rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset); - bi->dma = dma_map_single(&pdev->dev, skb->data, - rx_ring->rx_buf_len, - DMA_FROM_DEVICE); - if (dma_mapping_error(&pdev->dev, bi->dma)) { - dev_kfree_skb(skb); - bi->skb = NULL; - dev_err(&pdev->dev, "RX DMA map failed\n"); - break; - } + rx_desc++; + bi++; + i++; + if (unlikely(!i)) { + rx_desc = IXGBEVF_RX_DESC(rx_ring, 0); + bi = rx_ring->rx_buffer_info; + i -= rx_ring->count; } - rx_desc->read.pkt_addr = cpu_to_le64(bi->dma); - i++; - if (i == rx_ring->count) - i = 0; - bi = &rx_ring->rx_buffer_info[i]; - } + /* clear the hdr_addr for the next_to_use descriptor */ + rx_desc->read.hdr_addr = 0; + + cleaned_count--; + } while (cleaned_count); + + i += rx_ring->count; -no_buffers: if (rx_ring->next_to_use != i) { + /* record the next descriptor to use */ rx_ring->next_to_use = i; - ixgbevf_release_rx_desc(&adapter->hw, rx_ring, i); + + /* update next to alloc since we have filled the ring */ + rx_ring->next_to_alloc = i; + + /* Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. (Only + * applicable for weak-ordered memory model archs, + * such as IA-64). + */ + wmb(); + ixgbevf_write_tail(rx_ring, i); + } +} + +/** + * ixgbevf_cleanup_headers - Correct corrupted or empty headers + * @rx_ring: rx descriptor ring packet is being transacted on + * @rx_desc: pointer to the EOP Rx descriptor + * @skb: pointer to current skb being fixed + * + * Check for corrupted packet headers caused by senders on the local L2 + * embedded NIC switch not setting up their Tx Descriptors right. These + * should be very rare. + * + * Also address the case where we are pulling data in on pages only + * and as such no data is present in the skb header. + * + * In addition if skb is not at least 60 bytes we need to pad it so that + * it is large enough to qualify as a valid Ethernet frame. + * + * Returns true if an error was encountered and skb was freed. + **/ +static bool ixgbevf_cleanup_headers(struct ixgbevf_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + /* verify that the packet does not have any known errors */ + if (unlikely(ixgbevf_test_staterr(rx_desc, + IXGBE_RXDADV_ERR_FRAME_ERR_MASK))) { + struct net_device *netdev = rx_ring->netdev; + + if (!(netdev->features & NETIF_F_RXALL)) { + dev_kfree_skb_any(skb); + return true; + } } + + /* if eth_skb_pad returns an error the skb was freed */ + if (eth_skb_pad(skb)) + return true; + + return false; +} + +/** + * ixgbevf_reuse_rx_page - page flip buffer and store it back on the ring + * @rx_ring: rx descriptor ring to store buffers on + * @old_buff: donor buffer to have page reused + * + * Synchronizes page for reuse by the adapter + **/ +static void ixgbevf_reuse_rx_page(struct ixgbevf_ring *rx_ring, + struct ixgbevf_rx_buffer *old_buff) +{ + struct ixgbevf_rx_buffer *new_buff; + u16 nta = rx_ring->next_to_alloc; + + new_buff = &rx_ring->rx_buffer_info[nta]; + + /* update, and store next to alloc */ + nta++; + rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; + + /* transfer page from old buffer to new buffer */ + new_buff->page = old_buff->page; + new_buff->dma = old_buff->dma; + new_buff->page_offset = old_buff->page_offset; + + /* sync the buffer for use by the device */ + dma_sync_single_range_for_device(rx_ring->dev, new_buff->dma, + new_buff->page_offset, + IXGBEVF_RX_BUFSZ, + DMA_FROM_DEVICE); +} + +static inline bool ixgbevf_page_is_reserved(struct page *page) +{ + return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page); +} + +/** + * ixgbevf_add_rx_frag - Add contents of Rx buffer to sk_buff + * @rx_ring: rx descriptor ring to transact packets on + * @rx_buffer: buffer containing page to add + * @rx_desc: descriptor containing length of buffer written by hardware + * @skb: sk_buff to place the data into + * + * This function will add the data contained in rx_buffer->page to the skb. + * This is done either through a direct copy if the data in the buffer is + * less than the skb header size, otherwise it will just attach the page as + * a frag to the skb. + * + * The function will then update the page offset if necessary and return + * true if the buffer can be reused by the adapter. + **/ +static bool ixgbevf_add_rx_frag(struct ixgbevf_ring *rx_ring, + struct ixgbevf_rx_buffer *rx_buffer, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + struct page *page = rx_buffer->page; + unsigned char *va = page_address(page) + rx_buffer->page_offset; + unsigned int size = le16_to_cpu(rx_desc->wb.upper.length); +#if (PAGE_SIZE < 8192) + unsigned int truesize = IXGBEVF_RX_BUFSZ; +#else + unsigned int truesize = ALIGN(size, L1_CACHE_BYTES); +#endif + unsigned int pull_len; + + if (unlikely(skb_is_nonlinear(skb))) + goto add_tail_frag; + + if (likely(size <= IXGBEVF_RX_HDR_SIZE)) { + memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long))); + + /* page is not reserved, we can reuse buffer as is */ + if (likely(!ixgbevf_page_is_reserved(page))) + return true; + + /* this page cannot be reused so discard it */ + put_page(page); + return false; + } + + /* we need the header to contain the greater of either ETH_HLEN or + * 60 bytes if the skb->len is less than 60 for skb_pad. + */ + pull_len = eth_get_headlen(va, IXGBEVF_RX_HDR_SIZE); + + /* align pull length to size of long to optimize memcpy performance */ + memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long))); + + /* update all of the pointers */ + va += pull_len; + size -= pull_len; + +add_tail_frag: + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, + (unsigned long)va & ~PAGE_MASK, size, truesize); + + /* avoid re-using remote pages */ + if (unlikely(ixgbevf_page_is_reserved(page))) + return false; + +#if (PAGE_SIZE < 8192) + /* if we are only owner of page we can reuse it */ + if (unlikely(page_count(page) != 1)) + return false; + + /* flip page offset to other buffer */ + rx_buffer->page_offset ^= IXGBEVF_RX_BUFSZ; + +#else + /* move offset up to the next cache line */ + rx_buffer->page_offset += truesize; + + if (rx_buffer->page_offset > (PAGE_SIZE - IXGBEVF_RX_BUFSZ)) + return false; + +#endif + /* Even if we own the page, we are not allowed to use atomic_set() + * This would break get_page_unless_zero() users. + */ + atomic_inc(&page->_count); + + return true; +} + +static struct sk_buff *ixgbevf_fetch_rx_buffer(struct ixgbevf_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + struct ixgbevf_rx_buffer *rx_buffer; + struct page *page; + + rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + page = rx_buffer->page; + prefetchw(page); + + if (likely(!skb)) { + void *page_addr = page_address(page) + + rx_buffer->page_offset; + + /* prefetch first cache line of first page */ + prefetch(page_addr); +#if L1_CACHE_BYTES < 128 + prefetch(page_addr + L1_CACHE_BYTES); +#endif + + /* allocate a skb to store the frags */ + skb = netdev_alloc_skb_ip_align(rx_ring->netdev, + IXGBEVF_RX_HDR_SIZE); + if (unlikely(!skb)) { + rx_ring->rx_stats.alloc_rx_buff_failed++; + return NULL; + } + + /* we will be copying header into skb->data in + * pskb_may_pull so it is in our interest to prefetch + * it now to avoid a possible cache miss + */ + prefetchw(skb->data); + } + + /* we are reusing so sync this buffer for CPU use */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + IXGBEVF_RX_BUFSZ, + DMA_FROM_DEVICE); + + /* pull page into skb */ + if (ixgbevf_add_rx_frag(rx_ring, rx_buffer, rx_desc, skb)) { + /* hand second half of page back to the ring */ + ixgbevf_reuse_rx_page(rx_ring, rx_buffer); + } else { + /* we are not reusing the buffer so unmap it */ + dma_unmap_page(rx_ring->dev, rx_buffer->dma, + PAGE_SIZE, DMA_FROM_DEVICE); + } + + /* clear contents of buffer_info */ + rx_buffer->dma = 0; + rx_buffer->page = NULL; + + return skb; } static inline void ixgbevf_irq_enable_queues(struct ixgbevf_adapter *adapter, @@ -396,137 +908,90 @@ IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, qmask); } -static bool ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, - struct ixgbevf_ring *rx_ring, - int budget) +static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, + struct ixgbevf_ring *rx_ring, + int budget) { - struct ixgbevf_adapter *adapter = q_vector->adapter; - struct pci_dev *pdev = adapter->pdev; - union ixgbe_adv_rx_desc *rx_desc, *next_rxd; - struct ixgbevf_rx_buffer *rx_buffer_info, *next_buffer; - struct sk_buff *skb; - unsigned int i; - u32 len, staterr; - int cleaned_count = 0; unsigned int total_rx_bytes = 0, total_rx_packets = 0; + u16 cleaned_count = ixgbevf_desc_unused(rx_ring); + struct sk_buff *skb = rx_ring->skb; - i = rx_ring->next_to_clean; - rx_desc = IXGBEVF_RX_DESC(rx_ring, i); - staterr = le32_to_cpu(rx_desc->wb.upper.status_error); - rx_buffer_info = &rx_ring->rx_buffer_info[i]; + while (likely(total_rx_packets < budget)) { + union ixgbe_adv_rx_desc *rx_desc; - while (staterr & IXGBE_RXD_STAT_DD) { - if (!budget) + /* return some buffers to hardware, one at a time is too slow */ + if (cleaned_count >= IXGBEVF_RX_BUFFER_WRITE) { + ixgbevf_alloc_rx_buffers(rx_ring, cleaned_count); + cleaned_count = 0; + } + + rx_desc = IXGBEVF_RX_DESC(rx_ring, rx_ring->next_to_clean); + + if (!ixgbevf_test_staterr(rx_desc, IXGBE_RXD_STAT_DD)) break; - budget--; - rmb(); /* read descriptor and rx_buffer_info after status DD */ - len = le16_to_cpu(rx_desc->wb.upper.length); - skb = rx_buffer_info->skb; - prefetch(skb->data - NET_IP_ALIGN); - rx_buffer_info->skb = NULL; - - if (rx_buffer_info->dma) { - dma_unmap_single(&pdev->dev, rx_buffer_info->dma, - rx_ring->rx_buf_len, - DMA_FROM_DEVICE); - rx_buffer_info->dma = 0; - skb_put(skb, len); - } + /* This memory barrier is needed to keep us from reading + * any other fields out of the rx_desc until we know the + * RXD_STAT_DD bit is set + */ + rmb(); - i++; - if (i == rx_ring->count) - i = 0; + /* retrieve a buffer from the ring */ + skb = ixgbevf_fetch_rx_buffer(rx_ring, rx_desc, skb); - next_rxd = IXGBEVF_RX_DESC(rx_ring, i); - prefetch(next_rxd); - cleaned_count++; + /* exit if we failed to retrieve a buffer */ + if (!skb) + break; - next_buffer = &rx_ring->rx_buffer_info[i]; + cleaned_count++; - if (!(staterr & IXGBE_RXD_STAT_EOP)) { - skb->next = next_buffer->skb; - IXGBE_CB(skb->next)->prev = skb; - adapter->non_eop_descs++; - goto next_desc; - } - - /* we should not be chaining buffers, if we did drop the skb */ - if (IXGBE_CB(skb)->prev) { - do { - struct sk_buff *this = skb; - skb = IXGBE_CB(skb)->prev; - dev_kfree_skb(this); - } while (skb); - goto next_desc; - } + /* fetch next buffer in frame if non-eop */ + if (ixgbevf_is_non_eop(rx_ring, rx_desc)) + continue; - /* ERR_MASK will only have valid bits if EOP set */ - if (unlikely(staterr & IXGBE_RXDADV_ERR_FRAME_ERR_MASK)) { - dev_kfree_skb_irq(skb); - goto next_desc; + /* verify the packet layout is correct */ + if (ixgbevf_cleanup_headers(rx_ring, rx_desc, skb)) { + skb = NULL; + continue; } - ixgbevf_rx_checksum(rx_ring, staterr, skb); - /* probably a little skewed due to removing CRC */ total_rx_bytes += skb->len; - total_rx_packets++; - - /* - * Work around issue of some types of VM to VM loop back - * packets not getting split correctly - */ - if (staterr & IXGBE_RXD_STAT_LB) { - u32 header_fixup_len = skb_headlen(skb); - if (header_fixup_len < 14) - skb_push(skb, header_fixup_len); - } - skb->protocol = eth_type_trans(skb, rx_ring->netdev); /* Workaround hardware that can't do proper VEPA multicast * source pruning. */ - if ((skb->pkt_type & (PACKET_BROADCAST | PACKET_MULTICAST)) && - !(compare_ether_addr(adapter->netdev->dev_addr, - eth_hdr(skb)->h_source))) { + if ((skb->pkt_type == PACKET_BROADCAST || + skb->pkt_type == PACKET_MULTICAST) && + ether_addr_equal(rx_ring->netdev->dev_addr, + eth_hdr(skb)->h_source)) { dev_kfree_skb_irq(skb); - goto next_desc; + continue; } - ixgbevf_receive_skb(q_vector, skb, staterr, rx_desc); + /* populate checksum, VLAN, and protocol */ + ixgbevf_process_skb_fields(rx_ring, rx_desc, skb); -next_desc: - rx_desc->wb.upper.status_error = 0; + ixgbevf_rx_skb(q_vector, skb); - /* return some buffers to hardware, one at a time is too slow */ - if (cleaned_count >= IXGBEVF_RX_BUFFER_WRITE) { - ixgbevf_alloc_rx_buffers(adapter, rx_ring, - cleaned_count); - cleaned_count = 0; - } + /* reset skb pointer */ + skb = NULL; - /* use prefetched values */ - rx_desc = next_rxd; - rx_buffer_info = &rx_ring->rx_buffer_info[i]; - - staterr = le32_to_cpu(rx_desc->wb.upper.status_error); + /* update budget accounting */ + total_rx_packets++; } - rx_ring->next_to_clean = i; - cleaned_count = IXGBE_DESC_UNUSED(rx_ring); - - if (cleaned_count) - ixgbevf_alloc_rx_buffers(adapter, rx_ring, cleaned_count); + /* place incomplete frames back on ring for completion */ + rx_ring->skb = skb; u64_stats_update_begin(&rx_ring->syncp); - rx_ring->total_packets += total_rx_packets; - rx_ring->total_bytes += total_rx_bytes; + 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; - return !!budget; + return total_rx_packets; } /** @@ -543,33 +1008,45 @@ container_of(napi, struct ixgbevf_q_vector, napi); struct ixgbevf_adapter *adapter = q_vector->adapter; struct ixgbevf_ring *ring; - int per_ring_budget; + int per_ring_budget, work_done = 0; bool clean_complete = true; ixgbevf_for_each_ring(ring, q_vector->tx) clean_complete &= ixgbevf_clean_tx_irq(q_vector, ring); +#ifdef CONFIG_NET_RX_BUSY_POLL + if (!ixgbevf_qv_lock_napi(q_vector)) + return budget; +#endif + /* attempt to distribute budget to each queue fairly, but don't allow - * the budget to go below 1 because we'll exit polling */ + * the budget to go below 1 because we'll exit polling + */ if (q_vector->rx.count > 1) per_ring_budget = max(budget/q_vector->rx.count, 1); else per_ring_budget = budget; - adapter->flags |= IXGBE_FLAG_IN_NETPOLL; - ixgbevf_for_each_ring(ring, q_vector->rx) - clean_complete &= ixgbevf_clean_rx_irq(q_vector, ring, - per_ring_budget); - adapter->flags &= ~IXGBE_FLAG_IN_NETPOLL; + ixgbevf_for_each_ring(ring, q_vector->rx) { + int cleaned = ixgbevf_clean_rx_irq(q_vector, ring, + per_ring_budget); + work_done += cleaned; + clean_complete &= (cleaned < per_ring_budget); + } + +#ifdef CONFIG_NET_RX_BUSY_POLL + ixgbevf_qv_unlock_napi(q_vector); +#endif /* If all work not completed, return budget and keep polling */ if (!clean_complete) return budget; /* all work done, exit the polling mode */ - napi_complete(napi); + napi_complete_done(napi, work_done); if (adapter->rx_itr_setting & 1) ixgbevf_set_itr(q_vector); - if (!test_bit(__IXGBEVF_DOWN, &adapter->state)) + if (!test_bit(__IXGBEVF_DOWN, &adapter->state) && + !test_bit(__IXGBEVF_REMOVING, &adapter->state)) ixgbevf_irq_enable_queues(adapter, 1 << q_vector->v_idx); @@ -579,16 +1056,15 @@ /** * ixgbevf_write_eitr - write VTEITR register in hardware specific way * @q_vector: structure containing interrupt and ring information - */ -static void ixgbevf_write_eitr(struct ixgbevf_q_vector *q_vector) + **/ +void ixgbevf_write_eitr(struct ixgbevf_q_vector *q_vector) { struct ixgbevf_adapter *adapter = q_vector->adapter; struct ixgbe_hw *hw = &adapter->hw; int v_idx = q_vector->v_idx; u32 itr_reg = q_vector->itr & IXGBE_MAX_EITR; - /* - * set the WDIS bit to not clear the timer bits and cause an + /* set the WDIS bit to not clear the timer bits and cause an * immediate assertion of the interrupt */ itr_reg |= IXGBE_EITR_CNT_WDIS; @@ -596,6 +1072,40 @@ IXGBE_WRITE_REG(hw, IXGBE_VTEITR(v_idx), itr_reg); } +#ifdef CONFIG_NET_RX_BUSY_POLL +/* must be called with local_bh_disable()d */ +static int ixgbevf_busy_poll_recv(struct napi_struct *napi) +{ + struct ixgbevf_q_vector *q_vector = + container_of(napi, struct ixgbevf_q_vector, napi); + struct ixgbevf_adapter *adapter = q_vector->adapter; + struct ixgbevf_ring *ring; + int found = 0; + + if (test_bit(__IXGBEVF_DOWN, &adapter->state)) + return LL_FLUSH_FAILED; + + if (!ixgbevf_qv_lock_poll(q_vector)) + return LL_FLUSH_BUSY; + + ixgbevf_for_each_ring(ring, q_vector->rx) { + found = ixgbevf_clean_rx_irq(q_vector, ring, 4); +#ifdef BP_EXTENDED_STATS + if (found) + ring->stats.cleaned += found; + else + ring->stats.misses++; +#endif + if (found) + break; + } + + ixgbevf_qv_unlock_poll(q_vector); + + return found; +} +#endif /* CONFIG_NET_RX_BUSY_POLL */ + /** * ixgbevf_configure_msix - Configure MSI-X hardware * @adapter: board private structure @@ -611,12 +1121,12 @@ q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; adapter->eims_enable_mask = 0; - /* - * Populate the IVAR table and set the ITR values to the + /* Populate the IVAR table and set the ITR values to the * corresponding register. */ for (v_idx = 0; v_idx < q_vectors; v_idx++) { struct ixgbevf_ring *ring; + q_vector = adapter->q_vector[v_idx]; ixgbevf_for_each_ring(ring, q_vector->rx) @@ -626,13 +1136,13 @@ ixgbevf_set_ivar(adapter, 1, ring->reg_idx, v_idx); if (q_vector->tx.ring && !q_vector->rx.ring) { - /* tx only vector */ + /* Tx only vector */ if (adapter->tx_itr_setting == 1) q_vector->itr = IXGBE_10K_ITR; else q_vector->itr = adapter->tx_itr_setting; } else { - /* rx or rx/tx vector */ + /* Rx or Rx/Tx vector */ if (adapter->rx_itr_setting == 1) q_vector->itr = IXGBE_20K_ITR; else @@ -663,13 +1173,13 @@ * @q_vector: structure containing interrupt and ring information * @ring_container: structure containing ring performance data * - * Stores a new ITR value based on packets and byte - * counts during the last interrupt. The advantage of per interrupt - * computation is faster updates and more accurate ITR for the current - * traffic pattern. Constants in this function were computed - * based on theoretical maximum wire speed and thresholds were set based - * on testing data as well as attempting to minimize response time - * while increasing bulk throughput. + * Stores a new ITR value based on packets and byte + * counts during the last interrupt. The advantage of per interrupt + * computation is faster updates and more accurate ITR for the current + * traffic pattern. Constants in this function were computed + * based on theoretical maximum wire speed and thresholds were set based + * on testing data as well as attempting to minimize response time + * while increasing bulk throughput. **/ static void ixgbevf_update_itr(struct ixgbevf_q_vector *q_vector, struct ixgbevf_ring_container *ring_container) @@ -683,7 +1193,7 @@ if (packets == 0) return; - /* simple throttlerate management + /* simple throttle rate management * 0-20MB/s lowest (100000 ints/s) * 20-100MB/s low (20000 ints/s) * 100-1249MB/s bulk (8000 ints/s) @@ -756,37 +1266,11 @@ static irqreturn_t ixgbevf_msix_other(int irq, void *data) { struct ixgbevf_adapter *adapter = data; - struct pci_dev *pdev = adapter->pdev; struct ixgbe_hw *hw = &adapter->hw; - u32 msg; - bool got_ack = false; hw->mac.get_link_status = 1; - if (!hw->mbx.ops.check_for_ack(hw)) - got_ack = true; - if (!hw->mbx.ops.check_for_msg(hw)) { - hw->mbx.ops.read(hw, &msg, 1); - - if ((msg & IXGBE_MBVFICR_VFREQ_MASK) == IXGBE_PF_CONTROL_MSG) { - mod_timer(&adapter->watchdog_timer, - round_jiffies(jiffies + 1)); - adapter->link_up = false; - } - - if (msg & IXGBE_VT_MSGTYPE_NACK) - dev_info(&pdev->dev, - "Last Request of type %2.2x to PF Nacked\n", - msg & 0xFF); - hw->mbx.v2p_mailbox |= IXGBE_VFMAILBOX_PFSTS; - } - - /* checking for the ack clears the PFACK bit. Place - * it back in the v2p_mailbox cache so that anyone - * polling for an ack will not miss it - */ - if (got_ack) - hw->mbx.v2p_mailbox |= IXGBE_VFMAILBOX_PFACK; + ixgbevf_service_event_schedule(adapter); IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, adapter->eims_other); @@ -814,8 +1298,8 @@ { struct ixgbevf_q_vector *q_vector = a->q_vector[v_idx]; - a->rx_ring[r_idx].next = q_vector->rx.ring; - q_vector->rx.ring = &a->rx_ring[r_idx]; + a->rx_ring[r_idx]->next = q_vector->rx.ring; + q_vector->rx.ring = a->rx_ring[r_idx]; q_vector->rx.count++; } @@ -824,8 +1308,8 @@ { struct ixgbevf_q_vector *q_vector = a->q_vector[v_idx]; - a->tx_ring[t_idx].next = q_vector->tx.ring; - q_vector->tx.ring = &a->tx_ring[t_idx]; + a->tx_ring[t_idx]->next = q_vector->tx.ring; + q_vector->tx.ring = a->tx_ring[t_idx]; q_vector->tx.count++; } @@ -852,8 +1336,7 @@ q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - /* - * The ideal configuration... + /* The ideal configuration... * We have enough vectors to map one per queue. */ if (q_vectors == adapter->num_rx_queues + adapter->num_tx_queues) { @@ -865,8 +1348,7 @@ goto out; } - /* - * If we don't have enough vectors for a 1-to-1 + /* If we don't have enough vectors for a 1-to-1 * mapping, we'll have to group them so there are * multiple queues per vector. */ @@ -928,8 +1410,8 @@ q_vector->name, q_vector); if (err) { hw_dbg(&adapter->hw, - "request_irq failed for MSIX interrupt " - "Error: %d\n", err); + "request_irq failed for MSIX interrupt Error: %d\n", + err); goto free_queue_irqs; } } @@ -937,8 +1419,8 @@ err = request_irq(adapter->msix_entries[vector].vector, &ixgbevf_msix_other, 0, netdev->name, adapter); if (err) { - hw_dbg(&adapter->hw, - "request_irq for msix_other failed: %d\n", err); + hw_dbg(&adapter->hw, "request_irq for msix_other failed: %d\n", + err); goto free_queue_irqs; } @@ -970,6 +1452,7 @@ for (i = 0; i < q_vectors; i++) { struct ixgbevf_q_vector *q_vector = adapter->q_vector[i]; + q_vector->rx.ring = NULL; q_vector->tx.ring = NULL; q_vector->rx.count = 0; @@ -991,8 +1474,7 @@ err = ixgbevf_request_msix_irqs(adapter); if (err) - hw_dbg(&adapter->hw, - "request_irq failed, Error %d\n", err); + hw_dbg(&adapter->hw, "request_irq failed, Error %d\n", err); return err; } @@ -1053,6 +1535,72 @@ } /** + * ixgbevf_configure_tx_ring - Configure 82599 VF Tx ring after Reset + * @adapter: board private structure + * @ring: structure containing ring specific data + * + * Configure the Tx descriptor ring after a reset. + **/ +static void ixgbevf_configure_tx_ring(struct ixgbevf_adapter *adapter, + struct ixgbevf_ring *ring) +{ + struct ixgbe_hw *hw = &adapter->hw; + u64 tdba = ring->dma; + int wait_loop = 10; + u32 txdctl = IXGBE_TXDCTL_ENABLE; + u8 reg_idx = ring->reg_idx; + + /* disable queue to avoid issues while updating state */ + IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH); + IXGBE_WRITE_FLUSH(hw); + + IXGBE_WRITE_REG(hw, IXGBE_VFTDBAL(reg_idx), tdba & DMA_BIT_MASK(32)); + IXGBE_WRITE_REG(hw, IXGBE_VFTDBAH(reg_idx), tdba >> 32); + IXGBE_WRITE_REG(hw, IXGBE_VFTDLEN(reg_idx), + ring->count * sizeof(union ixgbe_adv_tx_desc)); + + /* disable head writeback */ + IXGBE_WRITE_REG(hw, IXGBE_VFTDWBAH(reg_idx), 0); + IXGBE_WRITE_REG(hw, IXGBE_VFTDWBAL(reg_idx), 0); + + /* enable relaxed ordering */ + IXGBE_WRITE_REG(hw, IXGBE_VFDCA_TXCTRL(reg_idx), + (IXGBE_DCA_TXCTRL_DESC_RRO_EN | + IXGBE_DCA_TXCTRL_DATA_RRO_EN)); + + /* reset head and tail pointers */ + IXGBE_WRITE_REG(hw, IXGBE_VFTDH(reg_idx), 0); + IXGBE_WRITE_REG(hw, IXGBE_VFTDT(reg_idx), 0); + ring->tail = adapter->io_addr + IXGBE_VFTDT(reg_idx); + + /* reset ntu and ntc to place SW in sync with hardwdare */ + ring->next_to_clean = 0; + ring->next_to_use = 0; + + /* In order to avoid issues WTHRESH + PTHRESH should always be equal + * to or less than the number of on chip descriptors, which is + * currently 40. + */ + txdctl |= (8 << 16); /* WTHRESH = 8 */ + + /* Setting PTHRESH to 32 both improves performance */ + txdctl |= (1 << 8) | /* HTHRESH = 1 */ + 32; /* PTHRESH = 32 */ + + clear_bit(__IXGBEVF_HANG_CHECK_ARMED, &ring->state); + + IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(reg_idx), txdctl); + + /* poll to verify queue is enabled */ + do { + usleep_range(1000, 2000); + txdctl = IXGBE_READ_REG(hw, IXGBE_VFTXDCTL(reg_idx)); + } while (--wait_loop && !(txdctl & IXGBE_TXDCTL_ENABLE)); + if (!wait_loop) + pr_err("Could not enable Tx Queue %d\n", reg_idx); +} + +/** * ixgbevf_configure_tx - Configure 82599 VF Transmit Unit after Reset * @adapter: board private structure * @@ -1060,85 +1608,169 @@ **/ static void ixgbevf_configure_tx(struct ixgbevf_adapter *adapter) { - u64 tdba; - struct ixgbe_hw *hw = &adapter->hw; - u32 i, j, tdlen, txctrl; + u32 i; /* Setup the HW Tx Head and Tail descriptor pointers */ - for (i = 0; i < adapter->num_tx_queues; i++) { - struct ixgbevf_ring *ring = &adapter->tx_ring[i]; - j = ring->reg_idx; - tdba = ring->dma; - tdlen = ring->count * sizeof(union ixgbe_adv_tx_desc); - IXGBE_WRITE_REG(hw, IXGBE_VFTDBAL(j), - (tdba & DMA_BIT_MASK(32))); - IXGBE_WRITE_REG(hw, IXGBE_VFTDBAH(j), (tdba >> 32)); - IXGBE_WRITE_REG(hw, IXGBE_VFTDLEN(j), tdlen); - IXGBE_WRITE_REG(hw, IXGBE_VFTDH(j), 0); - IXGBE_WRITE_REG(hw, IXGBE_VFTDT(j), 0); - adapter->tx_ring[i].head = IXGBE_VFTDH(j); - adapter->tx_ring[i].tail = IXGBE_VFTDT(j); - /* Disable Tx Head Writeback RO bit, since this hoses - * bookkeeping if things aren't delivered in order. - */ - txctrl = IXGBE_READ_REG(hw, IXGBE_VFDCA_TXCTRL(j)); - txctrl &= ~IXGBE_DCA_TXCTRL_TX_WB_RO_EN; - IXGBE_WRITE_REG(hw, IXGBE_VFDCA_TXCTRL(j), txctrl); - } + for (i = 0; i < adapter->num_tx_queues; i++) + ixgbevf_configure_tx_ring(adapter, adapter->tx_ring[i]); } #define IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT 2 static void ixgbevf_configure_srrctl(struct ixgbevf_adapter *adapter, int index) { - struct ixgbevf_ring *rx_ring; struct ixgbe_hw *hw = &adapter->hw; u32 srrctl; - rx_ring = &adapter->rx_ring[index]; - srrctl = IXGBE_SRRCTL_DROP_EN; + srrctl |= IXGBEVF_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT; + srrctl |= IXGBEVF_RX_BUFSZ >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF; - srrctl |= ALIGN(rx_ring->rx_buf_len, 1024) >> - IXGBE_SRRCTL_BSIZEPKT_SHIFT; - IXGBE_WRITE_REG(hw, IXGBE_VFSRRCTL(index), srrctl); } -static void ixgbevf_set_rx_buffer_len(struct ixgbevf_adapter *adapter) +static void ixgbevf_setup_psrtype(struct ixgbevf_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; - struct net_device *netdev = adapter->netdev; - int max_frame = netdev->mtu + ETH_HLEN + ETH_FCS_LEN; - int i; - u16 rx_buf_len; - /* notify the PF of our intent to use this size of frame */ - ixgbevf_rlpml_set_vf(hw, max_frame); + /* PSRTYPE must be initialized in 82599 */ + u32 psrtype = IXGBE_PSRTYPE_TCPHDR | IXGBE_PSRTYPE_UDPHDR | + IXGBE_PSRTYPE_IPV4HDR | IXGBE_PSRTYPE_IPV6HDR | + IXGBE_PSRTYPE_L2HDR; - /* PF will allow an extra 4 bytes past for vlan tagged frames */ - max_frame += VLAN_HLEN; + if (adapter->num_rx_queues > 1) + psrtype |= 1 << 29; - /* - * Allocate buffer sizes that fit well into 32K and - * take into account max frame size of 9.5K - */ - if ((hw->mac.type == ixgbe_mac_X540_vf) && - (max_frame <= MAXIMUM_ETHERNET_VLAN_SIZE)) - rx_buf_len = MAXIMUM_ETHERNET_VLAN_SIZE; - else if (max_frame <= IXGBEVF_RXBUFFER_2K) - rx_buf_len = IXGBEVF_RXBUFFER_2K; - else if (max_frame <= IXGBEVF_RXBUFFER_4K) - rx_buf_len = IXGBEVF_RXBUFFER_4K; - else if (max_frame <= IXGBEVF_RXBUFFER_8K) - rx_buf_len = IXGBEVF_RXBUFFER_8K; - else - rx_buf_len = IXGBEVF_RXBUFFER_10K; + IXGBE_WRITE_REG(hw, IXGBE_VFPSRTYPE, psrtype); +} - for (i = 0; i < adapter->num_rx_queues; i++) - adapter->rx_ring[i].rx_buf_len = rx_buf_len; +#define IXGBEVF_MAX_RX_DESC_POLL 10 +static void ixgbevf_disable_rx_queue(struct ixgbevf_adapter *adapter, + struct ixgbevf_ring *ring) +{ + struct ixgbe_hw *hw = &adapter->hw; + int wait_loop = IXGBEVF_MAX_RX_DESC_POLL; + u32 rxdctl; + u8 reg_idx = ring->reg_idx; + + if (IXGBE_REMOVED(hw->hw_addr)) + return; + rxdctl = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(reg_idx)); + rxdctl &= ~IXGBE_RXDCTL_ENABLE; + + /* write value back with RXDCTL.ENABLE bit cleared */ + IXGBE_WRITE_REG(hw, IXGBE_VFRXDCTL(reg_idx), rxdctl); + + /* the hardware may take up to 100us to really disable the Rx queue */ + do { + udelay(10); + rxdctl = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(reg_idx)); + } while (--wait_loop && (rxdctl & IXGBE_RXDCTL_ENABLE)); + + if (!wait_loop) + pr_err("RXDCTL.ENABLE queue %d not cleared while polling\n", + reg_idx); +} + +static void ixgbevf_rx_desc_queue_enable(struct ixgbevf_adapter *adapter, + struct ixgbevf_ring *ring) +{ + struct ixgbe_hw *hw = &adapter->hw; + int wait_loop = IXGBEVF_MAX_RX_DESC_POLL; + u32 rxdctl; + u8 reg_idx = ring->reg_idx; + + if (IXGBE_REMOVED(hw->hw_addr)) + return; + do { + usleep_range(1000, 2000); + rxdctl = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(reg_idx)); + } while (--wait_loop && !(rxdctl & IXGBE_RXDCTL_ENABLE)); + + if (!wait_loop) + pr_err("RXDCTL.ENABLE queue %d not set while polling\n", + reg_idx); +} + +static void ixgbevf_setup_vfmrqc(struct ixgbevf_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 vfmrqc = 0, vfreta = 0; + u16 rss_i = adapter->num_rx_queues; + u8 i, j; + + /* Fill out hash function seeds */ + netdev_rss_key_fill(adapter->rss_key, sizeof(adapter->rss_key)); + for (i = 0; i < IXGBEVF_VFRSSRK_REGS; i++) + IXGBE_WRITE_REG(hw, IXGBE_VFRSSRK(i), adapter->rss_key[i]); + + for (i = 0, j = 0; i < IXGBEVF_X550_VFRETA_SIZE; i++, j++) { + if (j == rss_i) + j = 0; + + adapter->rss_indir_tbl[i] = j; + + vfreta |= j << (i & 0x3) * 8; + if ((i & 3) == 3) { + IXGBE_WRITE_REG(hw, IXGBE_VFRETA(i >> 2), vfreta); + vfreta = 0; + } + } + + /* Perform hash on these packet types */ + vfmrqc |= IXGBE_VFMRQC_RSS_FIELD_IPV4 | + IXGBE_VFMRQC_RSS_FIELD_IPV4_TCP | + IXGBE_VFMRQC_RSS_FIELD_IPV6 | + IXGBE_VFMRQC_RSS_FIELD_IPV6_TCP; + + vfmrqc |= IXGBE_VFMRQC_RSSEN; + + IXGBE_WRITE_REG(hw, IXGBE_VFMRQC, vfmrqc); +} + +static void ixgbevf_configure_rx_ring(struct ixgbevf_adapter *adapter, + struct ixgbevf_ring *ring) +{ + struct ixgbe_hw *hw = &adapter->hw; + u64 rdba = ring->dma; + u32 rxdctl; + u8 reg_idx = ring->reg_idx; + + /* disable queue to avoid issues while updating state */ + rxdctl = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(reg_idx)); + ixgbevf_disable_rx_queue(adapter, ring); + + IXGBE_WRITE_REG(hw, IXGBE_VFRDBAL(reg_idx), rdba & DMA_BIT_MASK(32)); + IXGBE_WRITE_REG(hw, IXGBE_VFRDBAH(reg_idx), rdba >> 32); + IXGBE_WRITE_REG(hw, IXGBE_VFRDLEN(reg_idx), + ring->count * sizeof(union ixgbe_adv_rx_desc)); + + /* enable relaxed ordering */ + IXGBE_WRITE_REG(hw, IXGBE_VFDCA_RXCTRL(reg_idx), + IXGBE_DCA_RXCTRL_DESC_RRO_EN); + + /* reset head and tail pointers */ + IXGBE_WRITE_REG(hw, IXGBE_VFRDH(reg_idx), 0); + IXGBE_WRITE_REG(hw, IXGBE_VFRDT(reg_idx), 0); + ring->tail = adapter->io_addr + IXGBE_VFRDT(reg_idx); + + /* reset ntu and ntc to place SW in sync with hardwdare */ + ring->next_to_clean = 0; + ring->next_to_use = 0; + ring->next_to_alloc = 0; + + ixgbevf_configure_srrctl(adapter, reg_idx); + + /* allow any size packet since we can handle overflow */ + rxdctl &= ~IXGBE_RXDCTL_RLPML_EN; + + rxdctl |= IXGBE_RXDCTL_ENABLE | IXGBE_RXDCTL_VME; + IXGBE_WRITE_REG(hw, IXGBE_VFRXDCTL(reg_idx), rxdctl); + + ixgbevf_rx_desc_queue_enable(adapter, ring); + ixgbevf_alloc_rx_buffers(ring, ixgbevf_desc_unused(ring)); } /** @@ -1149,34 +1781,22 @@ **/ static void ixgbevf_configure_rx(struct ixgbevf_adapter *adapter) { - u64 rdba; + int i; struct ixgbe_hw *hw = &adapter->hw; - int i, j; - u32 rdlen; + struct net_device *netdev = adapter->netdev; - /* PSRTYPE must be initialized in 82599 */ - IXGBE_WRITE_REG(hw, IXGBE_VFPSRTYPE, 0); + ixgbevf_setup_psrtype(adapter); + if (hw->mac.type >= ixgbe_mac_X550_vf) + ixgbevf_setup_vfmrqc(adapter); - /* set_rx_buffer_len must be called before ring initialization */ - ixgbevf_set_rx_buffer_len(adapter); + /* notify the PF of our intent to use this size of frame */ + ixgbevf_rlpml_set_vf(hw, netdev->mtu + ETH_HLEN + ETH_FCS_LEN); - rdlen = adapter->rx_ring[0].count * sizeof(union ixgbe_adv_rx_desc); /* Setup the HW Rx Head and Tail Descriptor Pointers and - * the Base and Length of the Rx Descriptor Ring */ - for (i = 0; i < adapter->num_rx_queues; i++) { - rdba = adapter->rx_ring[i].dma; - j = adapter->rx_ring[i].reg_idx; - IXGBE_WRITE_REG(hw, IXGBE_VFRDBAL(j), - (rdba & DMA_BIT_MASK(32))); - IXGBE_WRITE_REG(hw, IXGBE_VFRDBAH(j), (rdba >> 32)); - IXGBE_WRITE_REG(hw, IXGBE_VFRDLEN(j), rdlen); - IXGBE_WRITE_REG(hw, IXGBE_VFRDH(j), 0); - IXGBE_WRITE_REG(hw, IXGBE_VFRDT(j), 0); - adapter->rx_ring[i].head = IXGBE_VFRDH(j); - adapter->rx_ring[i].tail = IXGBE_VFRDT(j); - - ixgbevf_configure_srrctl(adapter, j); - } + * the Base and Length of the Rx Descriptor Ring + */ + for (i = 0; i < adapter->num_rx_queues; i++) + ixgbevf_configure_rx_ring(adapter, adapter->rx_ring[i]); } static int ixgbevf_vlan_rx_add_vid(struct net_device *netdev, @@ -1246,14 +1866,14 @@ if (!netdev_uc_empty(netdev)) { struct netdev_hw_addr *ha; + netdev_for_each_uc_addr(ha, netdev) { hw->mac.ops.set_uc_addr(hw, ++count, ha->addr); udelay(200); } } else { - /* - * If the list is empty then send message to PF driver to - * clear all macvlans on this VF. + /* If the list is empty then send message to PF driver to + * clear all MAC VLANs on this VF. */ hw->mac.ops.set_uc_addr(hw, 0, NULL); } @@ -1274,9 +1894,17 @@ { struct ixgbevf_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; + unsigned int flags = netdev->flags; + int xcast_mode; + + xcast_mode = (flags & IFF_ALLMULTI) ? IXGBEVF_XCAST_MODE_ALLMULTI : + (flags & (IFF_BROADCAST | IFF_MULTICAST)) ? + IXGBEVF_XCAST_MODE_MULTI : IXGBEVF_XCAST_MODE_NONE; spin_lock_bh(&adapter->mbx_lock); + hw->mac.ops.update_xcast_mode(hw, netdev, xcast_mode); + /* reprogram multicast list */ hw->mac.ops.update_mc_addr_list(hw, netdev); @@ -1293,6 +1921,9 @@ for (q_idx = 0; q_idx < q_vectors; q_idx++) { q_vector = adapter->q_vector[q_idx]; +#ifdef CONFIG_NET_RX_BUSY_POLL + ixgbevf_qv_init_lock(adapter->q_vector[q_idx]); +#endif napi_enable(&q_vector->napi); } } @@ -1306,48 +1937,68 @@ for (q_idx = 0; q_idx < q_vectors; q_idx++) { q_vector = adapter->q_vector[q_idx]; napi_disable(&q_vector->napi); +#ifdef CONFIG_NET_RX_BUSY_POLL + while (!ixgbevf_qv_disable(adapter->q_vector[q_idx])) { + pr_info("QV %d locked\n", q_idx); + usleep_range(1000, 20000); + } +#endif /* CONFIG_NET_RX_BUSY_POLL */ } } -static void ixgbevf_configure(struct ixgbevf_adapter *adapter) +static int ixgbevf_configure_dcb(struct ixgbevf_adapter *adapter) { - struct net_device *netdev = adapter->netdev; - int i; + struct ixgbe_hw *hw = &adapter->hw; + unsigned int def_q = 0; + unsigned int num_tcs = 0; + unsigned int num_rx_queues = adapter->num_rx_queues; + unsigned int num_tx_queues = adapter->num_tx_queues; + int err; - ixgbevf_set_rx_mode(netdev); + spin_lock_bh(&adapter->mbx_lock); - ixgbevf_restore_vlan(adapter); + /* fetch queue configuration from the PF */ + err = ixgbevf_get_queues(hw, &num_tcs, &def_q); - ixgbevf_configure_tx(adapter); - ixgbevf_configure_rx(adapter); - for (i = 0; i < adapter->num_rx_queues; i++) { - struct ixgbevf_ring *ring = &adapter->rx_ring[i]; - ixgbevf_alloc_rx_buffers(adapter, ring, - IXGBE_DESC_UNUSED(ring)); + spin_unlock_bh(&adapter->mbx_lock); + + if (err) + return err; + + if (num_tcs > 1) { + /* we need only one Tx queue */ + num_tx_queues = 1; + + /* update default Tx ring register index */ + adapter->tx_ring[0]->reg_idx = def_q; + + /* we need as many queues as traffic classes */ + num_rx_queues = num_tcs; } + + /* if we have a bad config abort request queue reset */ + if ((adapter->num_rx_queues != num_rx_queues) || + (adapter->num_tx_queues != num_tx_queues)) { + /* force mailbox timeout to prevent further messages */ + hw->mbx.timeout = 0; + + /* wait for watchdog to come around and bail us out */ + adapter->flags |= IXGBEVF_FLAG_QUEUE_RESET_REQUESTED; + } + + return 0; } -#define IXGBE_MAX_RX_DESC_POLL 10 -static inline void ixgbevf_rx_desc_queue_enable(struct ixgbevf_adapter *adapter, - int rxr) +static void ixgbevf_configure(struct ixgbevf_adapter *adapter) { - struct ixgbe_hw *hw = &adapter->hw; - int j = adapter->rx_ring[rxr].reg_idx; - int k; + ixgbevf_configure_dcb(adapter); - for (k = 0; k < IXGBE_MAX_RX_DESC_POLL; k++) { - if (IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(j)) & IXGBE_RXDCTL_ENABLE) - break; - else - msleep(1); - } - if (k >= IXGBE_MAX_RX_DESC_POLL) { - hw_dbg(hw, "RXDCTL.ENABLE on Rx queue %d " - "not set within the polling period\n", rxr); - } + ixgbevf_set_rx_mode(adapter->netdev); - ixgbevf_release_rx_desc(hw, &adapter->rx_ring[rxr], - adapter->rx_ring[rxr].count - 1); + ixgbevf_restore_vlan(adapter); + + ixgbevf_configure_tx(adapter); + ixgbevf_configure_rx(adapter); } static void ixgbevf_save_reset_stats(struct ixgbevf_adapter *adapter) @@ -1391,7 +2042,8 @@ static void ixgbevf_negotiate_api(struct ixgbevf_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; - int api[] = { ixgbe_mbox_api_11, + int api[] = { ixgbe_mbox_api_12, + ixgbe_mbox_api_11, ixgbe_mbox_api_10, ixgbe_mbox_api_unknown }; int err = 0, idx = 0; @@ -1412,37 +2064,6 @@ { struct net_device *netdev = adapter->netdev; struct ixgbe_hw *hw = &adapter->hw; - int i, j = 0; - int num_rx_rings = adapter->num_rx_queues; - u32 txdctl, rxdctl; - - for (i = 0; i < adapter->num_tx_queues; i++) { - j = adapter->tx_ring[i].reg_idx; - txdctl = IXGBE_READ_REG(hw, IXGBE_VFTXDCTL(j)); - /* enable WTHRESH=8 descriptors, to encourage burst writeback */ - txdctl |= (8 << 16); - IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(j), txdctl); - } - - for (i = 0; i < adapter->num_tx_queues; i++) { - j = adapter->tx_ring[i].reg_idx; - txdctl = IXGBE_READ_REG(hw, IXGBE_VFTXDCTL(j)); - txdctl |= IXGBE_TXDCTL_ENABLE; - IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(j), txdctl); - } - - for (i = 0; i < num_rx_rings; i++) { - j = adapter->rx_ring[i].reg_idx; - rxdctl = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(j)); - rxdctl |= IXGBE_RXDCTL_ENABLE | IXGBE_RXDCTL_VME; - if (hw->mac.type == ixgbe_mac_X540_vf) { - rxdctl &= ~IXGBE_RXDCTL_RLPMLMASK; - rxdctl |= ((netdev->mtu + ETH_HLEN + ETH_FCS_LEN) | - IXGBE_RXDCTL_RLPML_EN); - } - IXGBE_WRITE_REG(hw, IXGBE_VFRXDCTL(j), rxdctl); - ixgbevf_rx_desc_queue_enable(adapter, i); - } ixgbevf_configure_msix(adapter); @@ -1455,9 +2076,14 @@ spin_unlock_bh(&adapter->mbx_lock); + smp_mb__before_atomic(); clear_bit(__IXGBEVF_DOWN, &adapter->state); ixgbevf_napi_enable_all(adapter); + /* clear any pending interrupts, may auto mask */ + IXGBE_READ_REG(hw, IXGBE_VTEICR); + ixgbevf_irq_enable(adapter); + /* enable transmits */ netif_tx_start_all_queues(netdev); @@ -1465,135 +2091,48 @@ ixgbevf_init_last_counter_stats(adapter); hw->mac.get_link_status = 1; - mod_timer(&adapter->watchdog_timer, jiffies); -} - -static int ixgbevf_reset_queues(struct ixgbevf_adapter *adapter) -{ - struct ixgbe_hw *hw = &adapter->hw; - struct ixgbevf_ring *rx_ring; - unsigned int def_q = 0; - unsigned int num_tcs = 0; - unsigned int num_rx_queues = 1; - int err, i; - - spin_lock_bh(&adapter->mbx_lock); - - /* fetch queue configuration from the PF */ - err = ixgbevf_get_queues(hw, &num_tcs, &def_q); - - spin_unlock_bh(&adapter->mbx_lock); - - if (err) - return err; - - if (num_tcs > 1) { - /* update default Tx ring register index */ - adapter->tx_ring[0].reg_idx = def_q; - - /* we need as many queues as traffic classes */ - num_rx_queues = num_tcs; - } - - /* nothing to do if we have the correct number of queues */ - if (adapter->num_rx_queues == num_rx_queues) - return 0; - - /* allocate new rings */ - rx_ring = kcalloc(num_rx_queues, - sizeof(struct ixgbevf_ring), GFP_KERNEL); - if (!rx_ring) - return -ENOMEM; - - /* setup ring fields */ - for (i = 0; i < num_rx_queues; i++) { - rx_ring[i].count = adapter->rx_ring_count; - rx_ring[i].queue_index = i; - rx_ring[i].reg_idx = i; - rx_ring[i].dev = &adapter->pdev->dev; - rx_ring[i].netdev = adapter->netdev; - - /* allocate resources on the ring */ - err = ixgbevf_setup_rx_resources(adapter, &rx_ring[i]); - if (err) { - while (i) { - i--; - ixgbevf_free_rx_resources(adapter, &rx_ring[i]); - } - kfree(rx_ring); - return err; - } - } - - /* free the existing rings and queues */ - ixgbevf_free_all_rx_resources(adapter); - adapter->num_rx_queues = 0; - kfree(adapter->rx_ring); - - /* move new rings into position on the adapter struct */ - adapter->rx_ring = rx_ring; - adapter->num_rx_queues = num_rx_queues; - - /* reset ring to vector mapping */ - ixgbevf_reset_q_vectors(adapter); - ixgbevf_map_rings_to_vectors(adapter); - - return 0; + mod_timer(&adapter->service_timer, jiffies); } void ixgbevf_up(struct ixgbevf_adapter *adapter) { - struct ixgbe_hw *hw = &adapter->hw; - - ixgbevf_negotiate_api(adapter); - - ixgbevf_reset_queues(adapter); - ixgbevf_configure(adapter); ixgbevf_up_complete(adapter); - - /* clear any pending interrupts, may auto mask */ - IXGBE_READ_REG(hw, IXGBE_VTEICR); - - ixgbevf_irq_enable(adapter); } /** * ixgbevf_clean_rx_ring - Free Rx Buffers per Queue - * @adapter: board private structure * @rx_ring: ring to free buffers from **/ -static void ixgbevf_clean_rx_ring(struct ixgbevf_adapter *adapter, - struct ixgbevf_ring *rx_ring) +static void ixgbevf_clean_rx_ring(struct ixgbevf_ring *rx_ring) { - struct pci_dev *pdev = adapter->pdev; + struct device *dev = rx_ring->dev; unsigned long size; unsigned int i; + /* Free Rx ring sk_buff */ + if (rx_ring->skb) { + dev_kfree_skb(rx_ring->skb); + rx_ring->skb = NULL; + } + + /* ring already cleared, nothing to do */ if (!rx_ring->rx_buffer_info) return; - /* Free all the Rx ring sk_buffs */ + /* Free all the Rx ring pages */ for (i = 0; i < rx_ring->count; i++) { - struct ixgbevf_rx_buffer *rx_buffer_info; + struct ixgbevf_rx_buffer *rx_buffer; - rx_buffer_info = &rx_ring->rx_buffer_info[i]; - if (rx_buffer_info->dma) { - dma_unmap_single(&pdev->dev, rx_buffer_info->dma, - rx_ring->rx_buf_len, - DMA_FROM_DEVICE); - rx_buffer_info->dma = 0; - } - if (rx_buffer_info->skb) { - struct sk_buff *skb = rx_buffer_info->skb; - rx_buffer_info->skb = NULL; - do { - struct sk_buff *this = skb; - skb = IXGBE_CB(skb)->prev; - dev_kfree_skb(this); - } while (skb); - } + rx_buffer = &rx_ring->rx_buffer_info[i]; + if (rx_buffer->dma) + dma_unmap_page(dev, rx_buffer->dma, + PAGE_SIZE, DMA_FROM_DEVICE); + rx_buffer->dma = 0; + if (rx_buffer->page) + __free_page(rx_buffer->page); + rx_buffer->page = NULL; } size = sizeof(struct ixgbevf_rx_buffer) * rx_ring->count; @@ -1601,23 +2140,13 @@ /* Zero out the descriptor ring */ memset(rx_ring->desc, 0, rx_ring->size); - - rx_ring->next_to_clean = 0; - rx_ring->next_to_use = 0; - - if (rx_ring->head) - writel(0, adapter->hw.hw_addr + rx_ring->head); - if (rx_ring->tail) - writel(0, adapter->hw.hw_addr + rx_ring->tail); } /** * ixgbevf_clean_tx_ring - Free Tx Buffers - * @adapter: board private structure * @tx_ring: ring to be cleaned **/ -static void ixgbevf_clean_tx_ring(struct ixgbevf_adapter *adapter, - struct ixgbevf_ring *tx_ring) +static void ixgbevf_clean_tx_ring(struct ixgbevf_ring *tx_ring) { struct ixgbevf_tx_buffer *tx_buffer_info; unsigned long size; @@ -1636,14 +2165,6 @@ memset(tx_ring->tx_buffer_info, 0, size); memset(tx_ring->desc, 0, tx_ring->size); - - tx_ring->next_to_use = 0; - tx_ring->next_to_clean = 0; - - if (tx_ring->head) - writel(0, adapter->hw.hw_addr + tx_ring->head); - if (tx_ring->tail) - writel(0, adapter->hw.hw_addr + tx_ring->tail); } /** @@ -1655,7 +2176,7 @@ int i; for (i = 0; i < adapter->num_rx_queues; i++) - ixgbevf_clean_rx_ring(adapter, &adapter->rx_ring[i]); + ixgbevf_clean_rx_ring(adapter->rx_ring[i]); } /** @@ -1667,46 +2188,44 @@ int i; for (i = 0; i < adapter->num_tx_queues; i++) - ixgbevf_clean_tx_ring(adapter, &adapter->tx_ring[i]); + ixgbevf_clean_tx_ring(adapter->tx_ring[i]); } void ixgbevf_down(struct ixgbevf_adapter *adapter) { struct net_device *netdev = adapter->netdev; struct ixgbe_hw *hw = &adapter->hw; - u32 txdctl; - int i, j; + int i; /* signal that we are down to the interrupt handler */ - set_bit(__IXGBEVF_DOWN, &adapter->state); - /* disable receives */ + if (test_and_set_bit(__IXGBEVF_DOWN, &adapter->state)) + return; /* do nothing if already down */ - netif_tx_disable(netdev); + /* disable all enabled Rx queues */ + for (i = 0; i < adapter->num_rx_queues; i++) + ixgbevf_disable_rx_queue(adapter, adapter->rx_ring[i]); - msleep(10); + usleep_range(10000, 20000); netif_tx_stop_all_queues(netdev); + /* call carrier off first to avoid false dev_watchdog timeouts */ + netif_carrier_off(netdev); + netif_tx_disable(netdev); + ixgbevf_irq_disable(adapter); ixgbevf_napi_disable_all(adapter); - del_timer_sync(&adapter->watchdog_timer); - /* can't call flush scheduled work here because it can deadlock - * if linkwatch_event tries to acquire the rtnl_lock which we are - * holding */ - while (adapter->flags & IXGBE_FLAG_IN_WATCHDOG_TASK) - msleep(1); + del_timer_sync(&adapter->service_timer); /* disable transmits in the hardware now that interrupts are off */ for (i = 0; i < adapter->num_tx_queues; i++) { - j = adapter->tx_ring[i].reg_idx; - txdctl = IXGBE_READ_REG(hw, IXGBE_VFTXDCTL(j)); - IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(j), - (txdctl & ~IXGBE_TXDCTL_ENABLE)); - } + u8 reg_idx = adapter->tx_ring[i]->reg_idx; - netif_carrier_off(netdev); + IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(reg_idx), + IXGBE_TXDCTL_SWFLSH); + } if (!pci_channel_offline(adapter->pdev)) ixgbevf_reset(adapter); @@ -1733,10 +2252,12 @@ struct ixgbe_hw *hw = &adapter->hw; struct net_device *netdev = adapter->netdev; - if (hw->mac.ops.reset_hw(hw)) + if (hw->mac.ops.reset_hw(hw)) { hw_dbg(hw, "PF still resetting\n"); - else + } else { hw->mac.ops.init_hw(hw); + ixgbevf_negotiate_api(adapter); + } if (is_valid_ether_addr(adapter->hw.mac.addr)) { memcpy(netdev->dev_addr, adapter->hw.mac.addr, @@ -1744,12 +2265,13 @@ memcpy(netdev->perm_addr, adapter->hw.mac.addr, netdev->addr_len); } + + adapter->last_reset = jiffies; } static int ixgbevf_acquire_msix_vectors(struct ixgbevf_adapter *adapter, int vectors) { - int err = 0; int vector_threshold; /* We'll want at least 2 (vector_threshold): @@ -1763,33 +2285,24 @@ * Right now, we simply care about how many we'll get; we'll * set them up later while requesting irq's. */ - while (vectors >= vector_threshold) { - err = pci_enable_msix(adapter->pdev, adapter->msix_entries, - vectors); - if (!err || err < 0) /* Success or a nasty failure. */ - break; - else /* err == number of vectors we should try again with */ - vectors = err; - } + vectors = pci_enable_msix_range(adapter->pdev, adapter->msix_entries, + vector_threshold, vectors); - if (vectors < vector_threshold) - err = -ENOMEM; - - if (err) { + if (vectors < 0) { dev_err(&adapter->pdev->dev, "Unable to allocate MSI-X interrupts\n"); kfree(adapter->msix_entries); adapter->msix_entries = NULL; - } else { - /* - * Adjust for only the vectors we'll use, which is minimum - * of max_msix_q_vectors + NON_Q_VECTORS, or the number of - * vectors we were allocated. - */ - adapter->num_msix_vectors = vectors; + return vectors; } - return err; + /* Adjust for only the vectors we'll use, which is minimum + * of max_msix_q_vectors + NON_Q_VECTORS, or the number of + * vectors we were allocated. + */ + adapter->num_msix_vectors = vectors; + + return 0; } /** @@ -1805,9 +2318,40 @@ **/ static void ixgbevf_set_num_queues(struct ixgbevf_adapter *adapter) { + struct ixgbe_hw *hw = &adapter->hw; + unsigned int def_q = 0; + unsigned int num_tcs = 0; + int err; + /* Start with base case */ adapter->num_rx_queues = 1; adapter->num_tx_queues = 1; + + spin_lock_bh(&adapter->mbx_lock); + + /* fetch queue configuration from the PF */ + err = ixgbevf_get_queues(hw, &num_tcs, &def_q); + + spin_unlock_bh(&adapter->mbx_lock); + + if (err) + return; + + /* we need as many queues as traffic classes */ + if (num_tcs > 1) { + adapter->num_rx_queues = num_tcs; + } else { + u16 rss = min_t(u16, num_online_cpus(), IXGBEVF_MAX_RSS_QUEUES); + + switch (hw->api_version) { + case ixgbe_mbox_api_11: + case ixgbe_mbox_api_12: + adapter->num_rx_queues = rss; + adapter->num_tx_queues = rss; + default: + break; + } + } } /** @@ -1820,40 +2364,50 @@ **/ static int ixgbevf_alloc_queues(struct ixgbevf_adapter *adapter) { - int i; + struct ixgbevf_ring *ring; + int rx = 0, tx = 0; - adapter->tx_ring = kcalloc(adapter->num_tx_queues, - sizeof(struct ixgbevf_ring), GFP_KERNEL); - if (!adapter->tx_ring) - goto err_tx_ring_allocation; - - adapter->rx_ring = kcalloc(adapter->num_rx_queues, - sizeof(struct ixgbevf_ring), GFP_KERNEL); - if (!adapter->rx_ring) - goto err_rx_ring_allocation; + for (; tx < adapter->num_tx_queues; tx++) { + ring = kzalloc(sizeof(*ring), GFP_KERNEL); + if (!ring) + goto err_allocation; - for (i = 0; i < adapter->num_tx_queues; i++) { - adapter->tx_ring[i].count = adapter->tx_ring_count; - adapter->tx_ring[i].queue_index = i; - /* reg_idx may be remapped later by DCB config */ - adapter->tx_ring[i].reg_idx = i; - adapter->tx_ring[i].dev = &adapter->pdev->dev; - adapter->tx_ring[i].netdev = adapter->netdev; + ring->dev = &adapter->pdev->dev; + ring->netdev = adapter->netdev; + ring->count = adapter->tx_ring_count; + ring->queue_index = tx; + ring->reg_idx = tx; + + adapter->tx_ring[tx] = ring; } - for (i = 0; i < adapter->num_rx_queues; i++) { - adapter->rx_ring[i].count = adapter->rx_ring_count; - adapter->rx_ring[i].queue_index = i; - adapter->rx_ring[i].reg_idx = i; - adapter->rx_ring[i].dev = &adapter->pdev->dev; - adapter->rx_ring[i].netdev = adapter->netdev; + for (; rx < adapter->num_rx_queues; rx++) { + ring = kzalloc(sizeof(*ring), GFP_KERNEL); + if (!ring) + goto err_allocation; + + ring->dev = &adapter->pdev->dev; + ring->netdev = adapter->netdev; + + ring->count = adapter->rx_ring_count; + ring->queue_index = rx; + ring->reg_idx = rx; + + adapter->rx_ring[rx] = ring; } return 0; -err_rx_ring_allocation: - kfree(adapter->tx_ring); -err_tx_ring_allocation: +err_allocation: + while (tx) { + kfree(adapter->tx_ring[--tx]); + adapter->tx_ring[tx] = NULL; + } + + while (rx) { + kfree(adapter->rx_ring[--rx]); + adapter->rx_ring[rx] = NULL; + } return -ENOMEM; } @@ -1870,8 +2424,7 @@ int err = 0; int vector, v_budget; - /* - * It's easy to be greedy for MSI-X vectors, but it really + /* It's easy to be greedy for MSI-X vectors, but it really * doesn't do us much good if we have a lot more vectors * than CPU's. So let's be conservative and only ask for * (roughly) the same number of vectors as there are CPU's. @@ -1882,7 +2435,8 @@ v_budget += NON_Q_VECTORS; /* A failure in MSI-X entry allocation isn't fatal, but it does - * mean we disable MSI-X capabilities of the adapter. */ + * mean we disable MSI-X capabilities of the adapter. + */ adapter->msix_entries = kcalloc(v_budget, sizeof(struct msix_entry), GFP_KERNEL); if (!adapter->msix_entries) { @@ -1929,6 +2483,9 @@ q_vector->v_idx = q_idx; netif_napi_add(adapter->netdev, &q_vector->napi, ixgbevf_poll, 64); +#ifdef CONFIG_NET_RX_BUSY_POLL + napi_hash_add(&q_vector->napi); +#endif adapter->q_vector[q_idx] = q_vector; } @@ -1938,6 +2495,9 @@ while (q_idx) { q_idx--; q_vector = adapter->q_vector[q_idx]; +#ifdef CONFIG_NET_RX_BUSY_POLL + napi_hash_del(&q_vector->napi); +#endif netif_napi_del(&q_vector->napi); kfree(q_vector); adapter->q_vector[q_idx] = NULL; @@ -1961,6 +2521,9 @@ struct ixgbevf_q_vector *q_vector = adapter->q_vector[q_idx]; adapter->q_vector[q_idx] = NULL; +#ifdef CONFIG_NET_RX_BUSY_POLL + napi_hash_del(&q_vector->napi); +#endif netif_napi_del(&q_vector->napi); kfree(q_vector); } @@ -1999,8 +2562,7 @@ err = ixgbevf_alloc_q_vectors(adapter); if (err) { - hw_dbg(&adapter->hw, "Unable to allocate memory for queue " - "vectors\n"); + hw_dbg(&adapter->hw, "Unable to allocate memory for queue vectors\n"); goto err_alloc_q_vectors; } @@ -2010,8 +2572,7 @@ goto err_alloc_queues; } - hw_dbg(&adapter->hw, "Multiqueue %s: Rx Queue count = %u, " - "Tx Queue count = %u\n", + hw_dbg(&adapter->hw, "Multiqueue %s: Rx Queue count = %u, Tx Queue count = %u\n", (adapter->num_rx_queues > 1) ? "Enabled" : "Disabled", adapter->num_rx_queues, adapter->num_tx_queues); @@ -2035,6 +2596,17 @@ **/ static void ixgbevf_clear_interrupt_scheme(struct ixgbevf_adapter *adapter) { + int i; + + for (i = 0; i < adapter->num_tx_queues; i++) { + kfree(adapter->tx_ring[i]); + adapter->tx_ring[i] = NULL; + } + for (i = 0; i < adapter->num_rx_queues; i++) { + kfree(adapter->rx_ring[i]); + adapter->rx_ring[i] = NULL; + } + adapter->num_tx_queues = 0; adapter->num_rx_queues = 0; @@ -2044,7 +2616,6 @@ /** * ixgbevf_sw_init - Initialize general software structures - * (struct ixgbevf_adapter) * @adapter: board private structure to initialize * * ixgbevf_sw_init initializes the Adapter private data structure. @@ -2059,7 +2630,6 @@ int err; /* PCI config space info */ - hw->vendor_id = pdev->vendor; hw->device_id = pdev->device; hw->revision_id = pdev->revision; @@ -2072,6 +2642,9 @@ hw->mac.max_tx_queues = 2; hw->mac.max_rx_queues = 2; + /* lock to protect mailbox accesses */ + spin_lock_init(&adapter->mbx_lock); + err = hw->mac.ops.reset_hw(hw); if (err) { dev_info(&pdev->dev, @@ -2082,6 +2655,7 @@ pr_err("init_shared_code failed: %d\n", err); goto out; } + ixgbevf_negotiate_api(adapter); err = hw->mac.ops.get_mac_addr(hw, hw->mac.addr); if (err) dev_info(&pdev->dev, "Error reading MAC address\n"); @@ -2097,9 +2671,6 @@ memcpy(hw->mac.addr, netdev->dev_addr, netdev->addr_len); } - /* lock to protect mailbox accesses */ - spin_lock_init(&adapter->mbx_lock); - /* Enable dynamic interrupt throttling rates */ adapter->rx_itr_setting = 1; adapter->tx_itr_setting = 1; @@ -2129,8 +2700,8 @@ { \ u64 current_counter_lsb = IXGBE_READ_REG(hw, reg_lsb); \ u64 current_counter_msb = IXGBE_READ_REG(hw, reg_msb); \ - u64 current_counter = (current_counter_msb << 32) | \ - current_counter_lsb; \ + u64 current_counter = (current_counter_msb << 32) | \ + current_counter_lsb; \ if (current_counter < last_counter) \ counter += 0x1000000000LL; \ last_counter = current_counter; \ @@ -2146,7 +2717,8 @@ struct ixgbe_hw *hw = &adapter->hw; int i; - if (!adapter->link_up) + if (test_bit(__IXGBEVF_DOWN, &adapter->state) || + test_bit(__IXGBEVF_RESETTING, &adapter->state)) return; UPDATE_VF_COUNTER_32bit(IXGBE_VFGPRC, adapter->stats.last_vfgprc, @@ -2164,172 +2736,219 @@ for (i = 0; i < adapter->num_rx_queues; i++) { adapter->hw_csum_rx_error += - adapter->rx_ring[i].hw_csum_rx_error; - adapter->hw_csum_rx_good += - adapter->rx_ring[i].hw_csum_rx_good; - adapter->rx_ring[i].hw_csum_rx_error = 0; - adapter->rx_ring[i].hw_csum_rx_good = 0; + adapter->rx_ring[i]->hw_csum_rx_error; + adapter->rx_ring[i]->hw_csum_rx_error = 0; } } /** - * ixgbevf_watchdog - Timer Call-back + * ixgbevf_service_timer - Timer Call-back * @data: pointer to adapter cast into an unsigned long **/ -static void ixgbevf_watchdog(unsigned long data) +static void ixgbevf_service_timer(unsigned long data) { struct ixgbevf_adapter *adapter = (struct ixgbevf_adapter *)data; + + /* Reset the timer */ + mod_timer(&adapter->service_timer, (HZ * 2) + jiffies); + + ixgbevf_service_event_schedule(adapter); +} + +static void ixgbevf_reset_subtask(struct ixgbevf_adapter *adapter) +{ + if (!(adapter->flags & IXGBEVF_FLAG_RESET_REQUESTED)) + return; + + adapter->flags &= ~IXGBEVF_FLAG_RESET_REQUESTED; + + /* If we're already down or resetting, just bail */ + if (test_bit(__IXGBEVF_DOWN, &adapter->state) || + test_bit(__IXGBEVF_RESETTING, &adapter->state)) + return; + + adapter->tx_timeout_count++; + + ixgbevf_reinit_locked(adapter); +} + +/** + * ixgbevf_check_hang_subtask - check for hung queues and dropped interrupts + * @adapter: pointer to the device adapter structure + * + * This function serves two purposes. First it strobes the interrupt lines + * in order to make certain interrupts are occurring. Secondly it sets the + * bits needed to check for TX hangs. As a result we should immediately + * determine if a hang has occurred. + **/ +static void ixgbevf_check_hang_subtask(struct ixgbevf_adapter *adapter) +{ struct ixgbe_hw *hw = &adapter->hw; u32 eics = 0; int i; - /* - * Do the watchdog outside of interrupt context due to the lovely - * delays that some of the newer hardware requires - */ + /* If we're down or resetting, just bail */ + if (test_bit(__IXGBEVF_DOWN, &adapter->state) || + test_bit(__IXGBEVF_RESETTING, &adapter->state)) + return; - if (test_bit(__IXGBEVF_DOWN, &adapter->state)) - goto watchdog_short_circuit; + /* Force detection of hung controller */ + if (netif_carrier_ok(adapter->netdev)) { + for (i = 0; i < adapter->num_tx_queues; i++) + set_check_for_tx_hang(adapter->tx_ring[i]); + } - /* get one bit for every active tx/rx interrupt vector */ + /* get one bit for every active Tx/Rx interrupt vector */ for (i = 0; i < adapter->num_msix_vectors - NON_Q_VECTORS; i++) { struct ixgbevf_q_vector *qv = adapter->q_vector[i]; + if (qv->rx.ring || qv->tx.ring) eics |= 1 << i; } + /* Cause software interrupt to ensure rings are cleaned */ IXGBE_WRITE_REG(hw, IXGBE_VTEICS, eics); +} + +/** + * ixgbevf_watchdog_update_link - update the link status + * @adapter: pointer to the device adapter structure + **/ +static void ixgbevf_watchdog_update_link(struct ixgbevf_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 link_speed = adapter->link_speed; + bool link_up = adapter->link_up; + s32 err; + + spin_lock_bh(&adapter->mbx_lock); -watchdog_short_circuit: - schedule_work(&adapter->watchdog_task); + err = hw->mac.ops.check_link(hw, &link_speed, &link_up, false); + + spin_unlock_bh(&adapter->mbx_lock); + + /* if check for link returns error we will need to reset */ + if (err && time_after(jiffies, adapter->last_reset + (10 * HZ))) { + adapter->flags |= IXGBEVF_FLAG_RESET_REQUESTED; + link_up = false; + } + + adapter->link_up = link_up; + adapter->link_speed = link_speed; } /** - * ixgbevf_tx_timeout - Respond to a Tx Hang - * @netdev: network interface device structure + * ixgbevf_watchdog_link_is_up - update netif_carrier status and + * print link up message + * @adapter: pointer to the device adapter structure **/ -static void ixgbevf_tx_timeout(struct net_device *netdev) +static void ixgbevf_watchdog_link_is_up(struct ixgbevf_adapter *adapter) { - struct ixgbevf_adapter *adapter = netdev_priv(netdev); + struct net_device *netdev = adapter->netdev; - /* Do the reset outside of interrupt context */ - schedule_work(&adapter->reset_task); + /* only continue if link was previously down */ + if (netif_carrier_ok(netdev)) + return; + + dev_info(&adapter->pdev->dev, "NIC Link is Up %s\n", + (adapter->link_speed == IXGBE_LINK_SPEED_10GB_FULL) ? + "10 Gbps" : + (adapter->link_speed == IXGBE_LINK_SPEED_1GB_FULL) ? + "1 Gbps" : + (adapter->link_speed == IXGBE_LINK_SPEED_100_FULL) ? + "100 Mbps" : + "unknown speed"); + + netif_carrier_on(netdev); } -static void ixgbevf_reset_task(struct work_struct *work) +/** + * ixgbevf_watchdog_link_is_down - update netif_carrier status and + * print link down message + * @adapter: pointer to the adapter structure + **/ +static void ixgbevf_watchdog_link_is_down(struct ixgbevf_adapter *adapter) { - struct ixgbevf_adapter *adapter; - adapter = container_of(work, struct ixgbevf_adapter, reset_task); + struct net_device *netdev = adapter->netdev; - /* If we're already down or resetting, just bail */ + adapter->link_speed = 0; + + /* only continue if link was up previously */ + if (!netif_carrier_ok(netdev)) + return; + + dev_info(&adapter->pdev->dev, "NIC Link is Down\n"); + + netif_carrier_off(netdev); +} + +/** + * ixgbevf_watchdog_subtask - worker thread to bring link up + * @work: pointer to work_struct containing our data + **/ +static void ixgbevf_watchdog_subtask(struct ixgbevf_adapter *adapter) +{ + /* if interface is down do nothing */ if (test_bit(__IXGBEVF_DOWN, &adapter->state) || test_bit(__IXGBEVF_RESETTING, &adapter->state)) return; - adapter->tx_timeout_count++; + ixgbevf_watchdog_update_link(adapter); - ixgbevf_reinit_locked(adapter); + if (adapter->link_up) + ixgbevf_watchdog_link_is_up(adapter); + else + ixgbevf_watchdog_link_is_down(adapter); + + ixgbevf_update_stats(adapter); } /** - * ixgbevf_watchdog_task - worker thread to bring link up + * ixgbevf_service_task - manages and runs subtasks * @work: pointer to work_struct containing our data **/ -static void ixgbevf_watchdog_task(struct work_struct *work) +static void ixgbevf_service_task(struct work_struct *work) { struct ixgbevf_adapter *adapter = container_of(work, struct ixgbevf_adapter, - watchdog_task); - struct net_device *netdev = adapter->netdev; + service_task); struct ixgbe_hw *hw = &adapter->hw; - u32 link_speed = adapter->link_speed; - bool link_up = adapter->link_up; - s32 need_reset; - - adapter->flags |= IXGBE_FLAG_IN_WATCHDOG_TASK; - - /* - * Always check the link on the watchdog because we have - * no LSC interrupt - */ - spin_lock_bh(&adapter->mbx_lock); - - need_reset = hw->mac.ops.check_link(hw, &link_speed, &link_up, false); - - spin_unlock_bh(&adapter->mbx_lock); - - if (need_reset) { - adapter->link_up = link_up; - adapter->link_speed = link_speed; - netif_carrier_off(netdev); - netif_tx_stop_all_queues(netdev); - schedule_work(&adapter->reset_task); - goto pf_has_reset; - } - adapter->link_up = link_up; - adapter->link_speed = link_speed; - if (link_up) { - if (!netif_carrier_ok(netdev)) { - char *link_speed_string; - switch (link_speed) { - case IXGBE_LINK_SPEED_10GB_FULL: - link_speed_string = "10 Gbps"; - break; - case IXGBE_LINK_SPEED_1GB_FULL: - link_speed_string = "1 Gbps"; - break; - case IXGBE_LINK_SPEED_100_FULL: - link_speed_string = "100 Mbps"; - break; - default: - link_speed_string = "unknown speed"; - break; - } - dev_info(&adapter->pdev->dev, - "NIC Link is Up, %s\n", link_speed_string); - netif_carrier_on(netdev); - netif_tx_wake_all_queues(netdev); - } - } else { - adapter->link_up = false; - adapter->link_speed = 0; - if (netif_carrier_ok(netdev)) { - dev_info(&adapter->pdev->dev, "NIC Link is Down\n"); - netif_carrier_off(netdev); - netif_tx_stop_all_queues(netdev); + if (IXGBE_REMOVED(hw->hw_addr)) { + if (!test_bit(__IXGBEVF_DOWN, &adapter->state)) { + rtnl_lock(); + ixgbevf_down(adapter); + rtnl_unlock(); } + return; } - ixgbevf_update_stats(adapter); - -pf_has_reset: - /* Reset the timer */ - if (!test_bit(__IXGBEVF_DOWN, &adapter->state)) - mod_timer(&adapter->watchdog_timer, - round_jiffies(jiffies + (2 * HZ))); + ixgbevf_queue_reset_subtask(adapter); + ixgbevf_reset_subtask(adapter); + ixgbevf_watchdog_subtask(adapter); + ixgbevf_check_hang_subtask(adapter); - adapter->flags &= ~IXGBE_FLAG_IN_WATCHDOG_TASK; + ixgbevf_service_event_complete(adapter); } /** * ixgbevf_free_tx_resources - Free Tx Resources per Queue - * @adapter: board private structure * @tx_ring: Tx descriptor ring for a specific queue * * Free all transmit software resources **/ -void ixgbevf_free_tx_resources(struct ixgbevf_adapter *adapter, - struct ixgbevf_ring *tx_ring) +void ixgbevf_free_tx_resources(struct ixgbevf_ring *tx_ring) { - struct pci_dev *pdev = adapter->pdev; - - ixgbevf_clean_tx_ring(adapter, tx_ring); + ixgbevf_clean_tx_ring(tx_ring); vfree(tx_ring->tx_buffer_info); tx_ring->tx_buffer_info = NULL; - dma_free_coherent(&pdev->dev, tx_ring->size, tx_ring->desc, + /* if not set, then don't free */ + if (!tx_ring->desc) + return; + + dma_free_coherent(tx_ring->dev, tx_ring->size, tx_ring->desc, tx_ring->dma); tx_ring->desc = NULL; @@ -2346,23 +2965,18 @@ int i; for (i = 0; i < adapter->num_tx_queues; i++) - if (adapter->tx_ring[i].desc) - ixgbevf_free_tx_resources(adapter, - &adapter->tx_ring[i]); - + if (adapter->tx_ring[i]->desc) + ixgbevf_free_tx_resources(adapter->tx_ring[i]); } /** * ixgbevf_setup_tx_resources - allocate Tx resources (Descriptors) - * @adapter: board private structure - * @tx_ring: tx descriptor ring (for a specific queue) to setup + * @tx_ring: Tx descriptor ring (for a specific queue) to setup * * Return 0 on success, negative on failure **/ -int ixgbevf_setup_tx_resources(struct ixgbevf_adapter *adapter, - struct ixgbevf_ring *tx_ring) +int ixgbevf_setup_tx_resources(struct ixgbevf_ring *tx_ring) { - struct pci_dev *pdev = adapter->pdev; int size; size = sizeof(struct ixgbevf_tx_buffer) * tx_ring->count; @@ -2374,20 +2988,17 @@ tx_ring->size = tx_ring->count * sizeof(union ixgbe_adv_tx_desc); tx_ring->size = ALIGN(tx_ring->size, 4096); - tx_ring->desc = dma_alloc_coherent(&pdev->dev, tx_ring->size, + tx_ring->desc = dma_alloc_coherent(tx_ring->dev, tx_ring->size, &tx_ring->dma, GFP_KERNEL); if (!tx_ring->desc) goto err; - tx_ring->next_to_use = 0; - tx_ring->next_to_clean = 0; return 0; err: vfree(tx_ring->tx_buffer_info); tx_ring->tx_buffer_info = NULL; - hw_dbg(&adapter->hw, "Unable to allocate memory for the transmit " - "descriptor ring\n"); + hw_dbg(&adapter->hw, "Unable to allocate memory for the transmit descriptor ring\n"); return -ENOMEM; } @@ -2406,11 +3017,10 @@ int i, err = 0; for (i = 0; i < adapter->num_tx_queues; i++) { - err = ixgbevf_setup_tx_resources(adapter, &adapter->tx_ring[i]); + err = ixgbevf_setup_tx_resources(adapter->tx_ring[i]); if (!err) continue; - hw_dbg(&adapter->hw, - "Allocation for Tx Queue %u failed\n", i); + hw_dbg(&adapter->hw, "Allocation for Tx Queue %u failed\n", i); break; } @@ -2419,40 +3029,34 @@ /** * ixgbevf_setup_rx_resources - allocate Rx resources (Descriptors) - * @adapter: board private structure - * @rx_ring: rx descriptor ring (for a specific queue) to setup + * @rx_ring: Rx descriptor ring (for a specific queue) to setup * * Returns 0 on success, negative on failure **/ -int ixgbevf_setup_rx_resources(struct ixgbevf_adapter *adapter, - struct ixgbevf_ring *rx_ring) +int ixgbevf_setup_rx_resources(struct ixgbevf_ring *rx_ring) { - struct pci_dev *pdev = adapter->pdev; int size; size = sizeof(struct ixgbevf_rx_buffer) * rx_ring->count; rx_ring->rx_buffer_info = vzalloc(size); if (!rx_ring->rx_buffer_info) - goto alloc_failed; + goto err; /* Round up to nearest 4K */ rx_ring->size = rx_ring->count * sizeof(union ixgbe_adv_rx_desc); rx_ring->size = ALIGN(rx_ring->size, 4096); - rx_ring->desc = dma_alloc_coherent(&pdev->dev, rx_ring->size, + rx_ring->desc = dma_alloc_coherent(rx_ring->dev, rx_ring->size, &rx_ring->dma, GFP_KERNEL); - if (!rx_ring->desc) { - vfree(rx_ring->rx_buffer_info); - rx_ring->rx_buffer_info = NULL; - goto alloc_failed; - } - - rx_ring->next_to_clean = 0; - rx_ring->next_to_use = 0; + if (!rx_ring->desc) + goto err; return 0; -alloc_failed: +err: + vfree(rx_ring->rx_buffer_info); + rx_ring->rx_buffer_info = NULL; + dev_err(rx_ring->dev, "Unable to allocate memory for the Rx descriptor ring\n"); return -ENOMEM; } @@ -2471,11 +3075,10 @@ int i, err = 0; for (i = 0; i < adapter->num_rx_queues; i++) { - err = ixgbevf_setup_rx_resources(adapter, &adapter->rx_ring[i]); + err = ixgbevf_setup_rx_resources(adapter->rx_ring[i]); if (!err) continue; - hw_dbg(&adapter->hw, - "Allocation for Rx Queue %u failed\n", i); + hw_dbg(&adapter->hw, "Allocation for Rx Queue %u failed\n", i); break; } return err; @@ -2483,22 +3086,18 @@ /** * ixgbevf_free_rx_resources - Free Rx Resources - * @adapter: board private structure * @rx_ring: ring to clean the resources from * * Free all receive software resources **/ -void ixgbevf_free_rx_resources(struct ixgbevf_adapter *adapter, - struct ixgbevf_ring *rx_ring) +void ixgbevf_free_rx_resources(struct ixgbevf_ring *rx_ring) { - struct pci_dev *pdev = adapter->pdev; - - ixgbevf_clean_rx_ring(adapter, rx_ring); + ixgbevf_clean_rx_ring(rx_ring); vfree(rx_ring->rx_buffer_info); rx_ring->rx_buffer_info = NULL; - dma_free_coherent(&pdev->dev, rx_ring->size, rx_ring->desc, + dma_free_coherent(rx_ring->dev, rx_ring->size, rx_ring->desc, rx_ring->dma); rx_ring->desc = NULL; @@ -2515,66 +3114,8 @@ int i; for (i = 0; i < adapter->num_rx_queues; i++) - if (adapter->rx_ring[i].desc) - ixgbevf_free_rx_resources(adapter, - &adapter->rx_ring[i]); -} - -static int ixgbevf_setup_queues(struct ixgbevf_adapter *adapter) -{ - struct ixgbe_hw *hw = &adapter->hw; - struct ixgbevf_ring *rx_ring; - unsigned int def_q = 0; - unsigned int num_tcs = 0; - unsigned int num_rx_queues = 1; - int err, i; - - spin_lock_bh(&adapter->mbx_lock); - - /* fetch queue configuration from the PF */ - err = ixgbevf_get_queues(hw, &num_tcs, &def_q); - - spin_unlock_bh(&adapter->mbx_lock); - - if (err) - return err; - - if (num_tcs > 1) { - /* update default Tx ring register index */ - adapter->tx_ring[0].reg_idx = def_q; - - /* we need as many queues as traffic classes */ - num_rx_queues = num_tcs; - } - - /* nothing to do if we have the correct number of queues */ - if (adapter->num_rx_queues == num_rx_queues) - return 0; - - /* allocate new rings */ - rx_ring = kcalloc(num_rx_queues, - sizeof(struct ixgbevf_ring), GFP_KERNEL); - if (!rx_ring) - return -ENOMEM; - - /* setup ring fields */ - for (i = 0; i < num_rx_queues; i++) { - rx_ring[i].count = adapter->rx_ring_count; - rx_ring[i].queue_index = i; - rx_ring[i].reg_idx = i; - rx_ring[i].dev = &adapter->pdev->dev; - rx_ring[i].netdev = adapter->netdev; - } - - /* free the existing ring and queues */ - adapter->num_rx_queues = 0; - kfree(adapter->rx_ring); - - /* move new rings into position on the adapter struct */ - adapter->rx_ring = rx_ring; - adapter->num_rx_queues = num_rx_queues; - - return 0; + if (adapter->rx_ring[i]->desc) + ixgbevf_free_rx_resources(adapter->rx_ring[i]); } /** @@ -2604,28 +3145,23 @@ if (!adapter->num_msix_vectors) return -ENOMEM; - /* disallow open during test */ - if (test_bit(__IXGBEVF_TESTING, &adapter->state)) - return -EBUSY; - if (hw->adapter_stopped) { ixgbevf_reset(adapter); /* if adapter is still stopped then PF isn't up and - * the vf can't start. */ + * the VF can't start. + */ if (hw->adapter_stopped) { err = IXGBE_ERR_MBX; - pr_err("Unable to start - perhaps the PF Driver isn't " - "up yet\n"); + pr_err("Unable to start - perhaps the PF Driver isn't up yet\n"); goto err_setup_reset; } } - ixgbevf_negotiate_api(adapter); + /* disallow open during test */ + if (test_bit(__IXGBEVF_TESTING, &adapter->state)) + return -EBUSY; - /* setup queue reg_idx and Rx queue count */ - err = ixgbevf_setup_queues(adapter); - if (err) - goto err_setup_queues; + netif_carrier_off(netdev); /* allocate transmit descriptors */ err = ixgbevf_setup_all_tx_resources(adapter); @@ -2639,22 +3175,17 @@ ixgbevf_configure(adapter); - /* - * Map the Tx/Rx rings to the vectors we were allotted. + /* Map the Tx/Rx rings to the vectors we were allotted. * if request_irq will be called in this function map_rings * must be called *before* up_complete */ ixgbevf_map_rings_to_vectors(adapter); - ixgbevf_up_complete(adapter); - - /* clear any pending interrupts, may auto mask */ - IXGBE_READ_REG(hw, IXGBE_VTEICR); err = ixgbevf_request_irq(adapter); if (err) goto err_req_irq; - ixgbevf_irq_enable(adapter); + ixgbevf_up_complete(adapter); return 0; @@ -2664,7 +3195,6 @@ ixgbevf_free_all_rx_resources(adapter); err_setup_tx: ixgbevf_free_all_tx_resources(adapter); -err_setup_queues: ixgbevf_reset(adapter); err_setup_reset: @@ -2696,6 +3226,34 @@ return 0; } +static void ixgbevf_queue_reset_subtask(struct ixgbevf_adapter *adapter) +{ + struct net_device *dev = adapter->netdev; + + if (!(adapter->flags & IXGBEVF_FLAG_QUEUE_RESET_REQUESTED)) + return; + + adapter->flags &= ~IXGBEVF_FLAG_QUEUE_RESET_REQUESTED; + + /* if interface is down do nothing */ + if (test_bit(__IXGBEVF_DOWN, &adapter->state) || + test_bit(__IXGBEVF_RESETTING, &adapter->state)) + return; + + /* Hardware has to reinitialize queues and interrupts to + * match packet buffer alignment. Unfortunately, the + * hardware is not flexible enough to do this dynamically. + */ + if (netif_running(dev)) + ixgbevf_close(dev); + + ixgbevf_clear_interrupt_scheme(adapter); + ixgbevf_init_interrupt_scheme(adapter); + + if (netif_running(dev)) + ixgbevf_open(dev); +} + static void ixgbevf_tx_ctxtdesc(struct ixgbevf_ring *tx_ring, u32 vlan_macip_lens, u32 type_tucmd, u32 mss_l4len_idx) @@ -2718,25 +3276,30 @@ } static int ixgbevf_tso(struct ixgbevf_ring *tx_ring, - struct sk_buff *skb, u32 tx_flags, u8 *hdr_len) + struct ixgbevf_tx_buffer *first, + u8 *hdr_len) { + struct sk_buff *skb = first->skb; u32 vlan_macip_lens, type_tucmd; u32 mss_l4len_idx, l4len; + int err; + + if (skb->ip_summed != CHECKSUM_PARTIAL) + return 0; if (!skb_is_gso(skb)) return 0; - if (skb_header_cloned(skb)) { - int err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); - if (err) - return err; - } + err = skb_cow_head(skb, 0); + if (err < 0) + return err; /* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */ type_tucmd = IXGBE_ADVTXD_TUCMD_L4T_TCP; - if (skb->protocol == htons(ETH_P_IP)) { + if (first->protocol == htons(ETH_P_IP)) { struct iphdr *iph = ip_hdr(skb); + iph->tot_len = 0; iph->check = 0; tcp_hdr(skb)->check = ~csum_tcpudp_magic(iph->saddr, @@ -2744,12 +3307,17 @@ IPPROTO_TCP, 0); type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4; + first->tx_flags |= IXGBE_TX_FLAGS_TSO | + IXGBE_TX_FLAGS_CSUM | + IXGBE_TX_FLAGS_IPV4; } else if (skb_is_gso_v6(skb)) { ipv6_hdr(skb)->payload_len = 0; tcp_hdr(skb)->check = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, 0, IPPROTO_TCP, 0); + first->tx_flags |= IXGBE_TX_FLAGS_TSO | + IXGBE_TX_FLAGS_CSUM; } /* compute header lengths */ @@ -2757,6 +3325,10 @@ *hdr_len += l4len; *hdr_len = skb_transport_offset(skb) + l4len; + /* update GSO size and bytecount with header size */ + first->gso_segs = skb_shinfo(skb)->gso_segs; + first->bytecount += (first->gso_segs - 1) * *hdr_len; + /* mss_l4len_id: use 1 as index for TSO */ mss_l4len_idx = l4len << IXGBE_ADVTXD_L4LEN_SHIFT; mss_l4len_idx |= skb_shinfo(skb)->gso_size << IXGBE_ADVTXD_MSS_SHIFT; @@ -2765,7 +3337,7 @@ /* vlan_macip_lens: HEADLEN, MACLEN, VLAN tag */ vlan_macip_lens = skb_network_header_len(skb); vlan_macip_lens |= skb_network_offset(skb) << IXGBE_ADVTXD_MACLEN_SHIFT; - vlan_macip_lens |= tx_flags & IXGBE_TX_FLAGS_VLAN_MASK; + vlan_macip_lens |= first->tx_flags & IXGBE_TX_FLAGS_VLAN_MASK; ixgbevf_tx_ctxtdesc(tx_ring, vlan_macip_lens, type_tucmd, mss_l4len_idx); @@ -2773,30 +3345,32 @@ return 1; } -static bool ixgbevf_tx_csum(struct ixgbevf_ring *tx_ring, - struct sk_buff *skb, u32 tx_flags) +static void ixgbevf_tx_csum(struct ixgbevf_ring *tx_ring, + struct ixgbevf_tx_buffer *first) { + struct sk_buff *skb = first->skb; u32 vlan_macip_lens = 0; u32 mss_l4len_idx = 0; u32 type_tucmd = 0; if (skb->ip_summed == CHECKSUM_PARTIAL) { u8 l4_hdr = 0; - switch (skb->protocol) { - case __constant_htons(ETH_P_IP): + + switch (first->protocol) { + case htons(ETH_P_IP): vlan_macip_lens |= skb_network_header_len(skb); type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4; l4_hdr = ip_hdr(skb)->protocol; break; - case __constant_htons(ETH_P_IPV6): + case htons(ETH_P_IPV6): vlan_macip_lens |= skb_network_header_len(skb); l4_hdr = ipv6_hdr(skb)->nexthdr; break; default: if (unlikely(net_ratelimit())) { dev_warn(tx_ring->dev, - "partial checksum but proto=%x!\n", - skb->protocol); + "partial checksum but proto=%x!\n", + first->protocol); } break; } @@ -2819,209 +3393,218 @@ default: if (unlikely(net_ratelimit())) { dev_warn(tx_ring->dev, - "partial checksum but l4 proto=%x!\n", - l4_hdr); + "partial checksum but l4 proto=%x!\n", + l4_hdr); } break; } + + /* update TX checksum flag */ + first->tx_flags |= IXGBE_TX_FLAGS_CSUM; } /* vlan_macip_lens: MACLEN, VLAN tag */ vlan_macip_lens |= skb_network_offset(skb) << IXGBE_ADVTXD_MACLEN_SHIFT; - vlan_macip_lens |= tx_flags & IXGBE_TX_FLAGS_VLAN_MASK; + vlan_macip_lens |= first->tx_flags & IXGBE_TX_FLAGS_VLAN_MASK; ixgbevf_tx_ctxtdesc(tx_ring, vlan_macip_lens, type_tucmd, mss_l4len_idx); - - return (skb->ip_summed == CHECKSUM_PARTIAL); } -static int ixgbevf_tx_map(struct ixgbevf_ring *tx_ring, - struct sk_buff *skb, u32 tx_flags) +static __le32 ixgbevf_tx_cmd_type(u32 tx_flags) { - struct ixgbevf_tx_buffer *tx_buffer_info; - unsigned int len; - unsigned int total = skb->len; - unsigned int offset = 0, size; - int count = 0; - unsigned int nr_frags = skb_shinfo(skb)->nr_frags; - unsigned int f; - int i; + /* set type for advanced descriptor with frame checksum insertion */ + __le32 cmd_type = cpu_to_le32(IXGBE_ADVTXD_DTYP_DATA | + IXGBE_ADVTXD_DCMD_IFCS | + IXGBE_ADVTXD_DCMD_DEXT); - i = tx_ring->next_to_use; + /* set HW VLAN bit if VLAN is present */ + if (tx_flags & IXGBE_TX_FLAGS_VLAN) + cmd_type |= cpu_to_le32(IXGBE_ADVTXD_DCMD_VLE); - len = min(skb_headlen(skb), total); - while (len) { - tx_buffer_info = &tx_ring->tx_buffer_info[i]; - size = min(len, (unsigned int)IXGBE_MAX_DATA_PER_TXD); + /* set segmentation enable bits for TSO/FSO */ + if (tx_flags & IXGBE_TX_FLAGS_TSO) + cmd_type |= cpu_to_le32(IXGBE_ADVTXD_DCMD_TSE); - tx_buffer_info->length = size; - tx_buffer_info->mapped_as_page = false; - tx_buffer_info->dma = dma_map_single(tx_ring->dev, - skb->data + offset, - size, DMA_TO_DEVICE); - if (dma_mapping_error(tx_ring->dev, tx_buffer_info->dma)) - goto dma_error; + return cmd_type; +} - len -= size; - total -= size; - offset += size; - count++; - i++; - if (i == tx_ring->count) - i = 0; - } +static void ixgbevf_tx_olinfo_status(union ixgbe_adv_tx_desc *tx_desc, + u32 tx_flags, unsigned int paylen) +{ + __le32 olinfo_status = cpu_to_le32(paylen << IXGBE_ADVTXD_PAYLEN_SHIFT); - for (f = 0; f < nr_frags; f++) { - const struct skb_frag_struct *frag; + /* enable L4 checksum for TSO and TX checksum offload */ + if (tx_flags & IXGBE_TX_FLAGS_CSUM) + olinfo_status |= cpu_to_le32(IXGBE_ADVTXD_POPTS_TXSM); - frag = &skb_shinfo(skb)->frags[f]; - len = min((unsigned int)skb_frag_size(frag), total); - offset = 0; - - while (len) { - tx_buffer_info = &tx_ring->tx_buffer_info[i]; - size = min(len, (unsigned int)IXGBE_MAX_DATA_PER_TXD); - - tx_buffer_info->length = size; - tx_buffer_info->dma = - skb_frag_dma_map(tx_ring->dev, frag, - offset, size, DMA_TO_DEVICE); - if (dma_mapping_error(tx_ring->dev, - tx_buffer_info->dma)) - goto dma_error; - tx_buffer_info->mapped_as_page = true; - - len -= size; - total -= size; - offset += size; - count++; - i++; - if (i == tx_ring->count) - i = 0; - } - if (total == 0) - break; - } + /* enble IPv4 checksum for TSO */ + if (tx_flags & IXGBE_TX_FLAGS_IPV4) + olinfo_status |= cpu_to_le32(IXGBE_ADVTXD_POPTS_IXSM); - if (i == 0) - i = tx_ring->count - 1; - else - i = i - 1; - tx_ring->tx_buffer_info[i].skb = skb; + /* use index 1 context for TSO/FSO/FCOE */ + if (tx_flags & IXGBE_TX_FLAGS_TSO) + olinfo_status |= cpu_to_le32(1 << IXGBE_ADVTXD_IDX_SHIFT); - return count; + /* Check Context must be set if Tx switch is enabled, which it + * always is for case where virtual functions are running + */ + olinfo_status |= cpu_to_le32(IXGBE_ADVTXD_CC); -dma_error: - dev_err(tx_ring->dev, "TX DMA map failed\n"); + tx_desc->read.olinfo_status = olinfo_status; +} - /* clear timestamp and dma mappings for failed tx_buffer_info map */ - tx_buffer_info->dma = 0; - count--; - - /* clear timestamp and dma mappings for remaining portion of packet */ - while (count >= 0) { - count--; - i--; - if (i < 0) - i += tx_ring->count; - tx_buffer_info = &tx_ring->tx_buffer_info[i]; - ixgbevf_unmap_and_free_tx_resource(tx_ring, tx_buffer_info); - } +static void ixgbevf_tx_map(struct ixgbevf_ring *tx_ring, + struct ixgbevf_tx_buffer *first, + const u8 hdr_len) +{ + dma_addr_t dma; + struct sk_buff *skb = first->skb; + struct ixgbevf_tx_buffer *tx_buffer; + union ixgbe_adv_tx_desc *tx_desc; + struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; + unsigned int data_len = skb->data_len; + unsigned int size = skb_headlen(skb); + unsigned int paylen = skb->len - hdr_len; + u32 tx_flags = first->tx_flags; + __le32 cmd_type; + u16 i = tx_ring->next_to_use; - return count; -} + tx_desc = IXGBEVF_TX_DESC(tx_ring, i); -static void ixgbevf_tx_queue(struct ixgbevf_ring *tx_ring, int tx_flags, - int count, unsigned int first, u32 paylen, - u8 hdr_len) -{ - union ixgbe_adv_tx_desc *tx_desc = NULL; - struct ixgbevf_tx_buffer *tx_buffer_info; - u32 olinfo_status = 0, cmd_type_len = 0; - unsigned int i; + ixgbevf_tx_olinfo_status(tx_desc, tx_flags, paylen); + cmd_type = ixgbevf_tx_cmd_type(tx_flags); - u32 txd_cmd = IXGBE_TXD_CMD_EOP | IXGBE_TXD_CMD_RS | IXGBE_TXD_CMD_IFCS; + dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE); + if (dma_mapping_error(tx_ring->dev, dma)) + goto dma_error; - cmd_type_len |= IXGBE_ADVTXD_DTYP_DATA; + /* record length, and DMA address */ + dma_unmap_len_set(first, len, size); + dma_unmap_addr_set(first, dma, dma); - cmd_type_len |= IXGBE_ADVTXD_DCMD_IFCS | IXGBE_ADVTXD_DCMD_DEXT; + tx_desc->read.buffer_addr = cpu_to_le64(dma); - if (tx_flags & IXGBE_TX_FLAGS_VLAN) - cmd_type_len |= IXGBE_ADVTXD_DCMD_VLE; + for (;;) { + while (unlikely(size > IXGBE_MAX_DATA_PER_TXD)) { + tx_desc->read.cmd_type_len = + cmd_type | cpu_to_le32(IXGBE_MAX_DATA_PER_TXD); - if (tx_flags & IXGBE_TX_FLAGS_CSUM) - olinfo_status |= IXGBE_ADVTXD_POPTS_TXSM; + i++; + tx_desc++; + if (i == tx_ring->count) { + tx_desc = IXGBEVF_TX_DESC(tx_ring, 0); + i = 0; + } - if (tx_flags & IXGBE_TX_FLAGS_TSO) { - cmd_type_len |= IXGBE_ADVTXD_DCMD_TSE; + dma += IXGBE_MAX_DATA_PER_TXD; + size -= IXGBE_MAX_DATA_PER_TXD; - /* use index 1 context for tso */ - olinfo_status |= (1 << IXGBE_ADVTXD_IDX_SHIFT); - if (tx_flags & IXGBE_TX_FLAGS_IPV4) - olinfo_status |= IXGBE_ADVTXD_POPTS_IXSM; - } + tx_desc->read.buffer_addr = cpu_to_le64(dma); + tx_desc->read.olinfo_status = 0; + } - /* - * Check Context must be set if Tx switch is enabled, which it - * always is for case where virtual functions are running - */ - olinfo_status |= IXGBE_ADVTXD_CC; + if (likely(!data_len)) + break; - olinfo_status |= ((paylen - hdr_len) << IXGBE_ADVTXD_PAYLEN_SHIFT); + tx_desc->read.cmd_type_len = cmd_type | cpu_to_le32(size); - i = tx_ring->next_to_use; - while (count--) { - tx_buffer_info = &tx_ring->tx_buffer_info[i]; - tx_desc = IXGBEVF_TX_DESC(tx_ring, i); - tx_desc->read.buffer_addr = cpu_to_le64(tx_buffer_info->dma); - tx_desc->read.cmd_type_len = - cpu_to_le32(cmd_type_len | tx_buffer_info->length); - tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status); i++; - if (i == tx_ring->count) + tx_desc++; + if (i == tx_ring->count) { + tx_desc = IXGBEVF_TX_DESC(tx_ring, 0); i = 0; + } + + size = skb_frag_size(frag); + data_len -= size; + + dma = skb_frag_dma_map(tx_ring->dev, frag, 0, size, + DMA_TO_DEVICE); + if (dma_mapping_error(tx_ring->dev, dma)) + goto dma_error; + + tx_buffer = &tx_ring->tx_buffer_info[i]; + dma_unmap_len_set(tx_buffer, len, size); + dma_unmap_addr_set(tx_buffer, dma, dma); + + tx_desc->read.buffer_addr = cpu_to_le64(dma); + tx_desc->read.olinfo_status = 0; + + frag++; } - tx_desc->read.cmd_type_len |= cpu_to_le32(txd_cmd); + /* write last descriptor with RS and EOP bits */ + cmd_type |= cpu_to_le32(size) | cpu_to_le32(IXGBE_TXD_CMD); + tx_desc->read.cmd_type_len = cmd_type; - tx_ring->tx_buffer_info[first].time_stamp = jiffies; + /* set the timestamp */ + first->time_stamp = jiffies; - /* Force memory writes to complete before letting h/w - * know there are new descriptors to fetch. (Only - * applicable for weak-ordered memory model archs, - * such as IA-64). + /* Force memory writes to complete before letting h/w know there + * are new descriptors to fetch. (Only applicable for weak-ordered + * memory model archs, such as IA-64). + * + * We also need this memory barrier (wmb) to make certain all of the + * status bits have been updated before next_to_watch is written. */ wmb(); - tx_ring->tx_buffer_info[first].next_to_watch = tx_desc; + /* set next_to_watch value indicating a packet is present */ + first->next_to_watch = tx_desc; + + i++; + if (i == tx_ring->count) + i = 0; + + tx_ring->next_to_use = i; + + /* notify HW of packet */ + ixgbevf_write_tail(tx_ring, i); + + return; +dma_error: + dev_err(tx_ring->dev, "TX DMA map failed\n"); + + /* clear dma mappings for failed tx_buffer_info map */ + for (;;) { + tx_buffer = &tx_ring->tx_buffer_info[i]; + ixgbevf_unmap_and_free_tx_resource(tx_ring, tx_buffer); + if (tx_buffer == first) + break; + if (i == 0) + i = tx_ring->count; + i--; + } + tx_ring->next_to_use = i; } static int __ixgbevf_maybe_stop_tx(struct ixgbevf_ring *tx_ring, int size) { - struct ixgbevf_adapter *adapter = netdev_priv(tx_ring->netdev); - 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. */ + * 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)) + * made room available. + */ + if (likely(ixgbevf_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); - ++adapter->restart_queue; + ++tx_ring->tx_stats.restart_queue; + return 0; } static int ixgbevf_maybe_stop_tx(struct ixgbevf_ring *tx_ring, int size) { - if (likely(IXGBE_DESC_UNUSED(tx_ring) >= size)) + if (likely(ixgbevf_desc_unused(tx_ring) >= size)) return 0; return __ixgbevf_maybe_stop_tx(tx_ring, size); } @@ -3029,25 +3612,25 @@ static int ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev) { struct ixgbevf_adapter *adapter = netdev_priv(netdev); + struct ixgbevf_tx_buffer *first; struct ixgbevf_ring *tx_ring; - unsigned int first; - unsigned int tx_flags = 0; - u8 hdr_len = 0; - int r_idx = 0, tso; + int tso; + u32 tx_flags = 0; u16 count = TXD_USE_COUNT(skb_headlen(skb)); #if PAGE_SIZE > IXGBE_MAX_DATA_PER_TXD unsigned short f; #endif + u8 hdr_len = 0; u8 *dst_mac = skb_header_pointer(skb, 0, 0, NULL); + if (!dst_mac || is_link_local_ether_addr(dst_mac)) { - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } - tx_ring = &adapter->tx_ring[r_idx]; + tx_ring = adapter->tx_ring[skb->queue_mapping]; - /* - * need: 1 descriptor per page * PAGE_SIZE/IXGBE_MAX_DATA_PER_TXD, + /* need: 1 descriptor per page * PAGE_SIZE/IXGBE_MAX_DATA_PER_TXD, * + 1 desc for skb_headlen/IXGBE_MAX_DATA_PER_TXD, * + 2 desc gap to keep tail from touching head, * + 1 desc for context descriptor, @@ -3060,38 +3643,41 @@ count += skb_shinfo(skb)->nr_frags; #endif if (ixgbevf_maybe_stop_tx(tx_ring, count + 3)) { - adapter->tx_busy++; + tx_ring->tx_stats.tx_busy++; return NETDEV_TX_BUSY; } - if (vlan_tx_tag_present(skb)) { - tx_flags |= vlan_tx_tag_get(skb); + /* record the location of the first descriptor for this packet */ + first = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + first->skb = skb; + first->bytecount = skb->len; + first->gso_segs = 1; + + if (skb_vlan_tag_present(skb)) { + tx_flags |= skb_vlan_tag_get(skb); tx_flags <<= IXGBE_TX_FLAGS_VLAN_SHIFT; tx_flags |= IXGBE_TX_FLAGS_VLAN; } - first = tx_ring->next_to_use; + /* record initial flags and protocol */ + first->tx_flags = tx_flags; + first->protocol = vlan_get_protocol(skb); + + tso = ixgbevf_tso(tx_ring, first, &hdr_len); + if (tso < 0) + goto out_drop; + else if (!tso) + ixgbevf_tx_csum(tx_ring, first); - if (skb->protocol == htons(ETH_P_IP)) - tx_flags |= IXGBE_TX_FLAGS_IPV4; - tso = ixgbevf_tso(tx_ring, skb, tx_flags, &hdr_len); - if (tso < 0) { - dev_kfree_skb_any(skb); - return NETDEV_TX_OK; - } + ixgbevf_tx_map(tx_ring, first, hdr_len); - if (tso) - tx_flags |= IXGBE_TX_FLAGS_TSO | IXGBE_TX_FLAGS_CSUM; - else if (ixgbevf_tx_csum(tx_ring, skb, tx_flags)) - tx_flags |= IXGBE_TX_FLAGS_CSUM; - - ixgbevf_tx_queue(tx_ring, tx_flags, - ixgbevf_tx_map(tx_ring, skb, tx_flags), - first, skb->len, hdr_len); + ixgbevf_maybe_stop_tx(tx_ring, DESC_NEEDED); - writel(tx_ring->next_to_use, adapter->hw.hw_addr + tx_ring->tail); + return NETDEV_TX_OK; - ixgbevf_maybe_stop_tx(tx_ring, DESC_NEEDED); +out_drop: + dev_kfree_skb_any(first->skb); + first->skb = NULL; return NETDEV_TX_OK; } @@ -3134,15 +3720,17 @@ static int ixgbevf_change_mtu(struct net_device *netdev, int new_mtu) { struct ixgbevf_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN; int max_possible_frame = MAXIMUM_ETHERNET_VLAN_SIZE; switch (adapter->hw.api_version) { case ixgbe_mbox_api_11: + case ixgbe_mbox_api_12: max_possible_frame = IXGBE_MAX_JUMBO_FRAME_SIZE; break; default: - if (adapter->hw.mac.type == ixgbe_mac_X540_vf) + if (adapter->hw.mac.type != ixgbe_mac_82599_vf) max_possible_frame = IXGBE_MAX_JUMBO_FRAME_SIZE; break; } @@ -3151,17 +3739,35 @@ if ((new_mtu < 68) || (max_frame > max_possible_frame)) return -EINVAL; - hw_dbg(&adapter->hw, "changing MTU from %d to %d\n", + hw_dbg(hw, "changing MTU from %d to %d\n", netdev->mtu, new_mtu); /* must set new MTU before calling down or up */ netdev->mtu = new_mtu; - if (netif_running(netdev)) - ixgbevf_reinit_locked(adapter); + /* notify the PF of our intent to use this size of frame */ + ixgbevf_rlpml_set_vf(hw, max_frame); return 0; } +#ifdef CONFIG_NET_POLL_CONTROLLER +/* Polling 'interrupt' - used by things like netconsole to send skbs + * without having to re-enable interrupts. It's not called while + * the interrupt routine is executing. + */ +static void ixgbevf_netpoll(struct net_device *netdev) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + int i; + + /* if interface is down do nothing */ + if (test_bit(__IXGBEVF_DOWN, &adapter->state)) + return; + for (i = 0; i < adapter->num_rx_queues; i++) + ixgbevf_msix_clean_rings(0, adapter->q_vector[i]); +} +#endif /* CONFIG_NET_POLL_CONTROLLER */ + static int ixgbevf_suspend(struct pci_dev *pdev, pm_message_t state) { struct net_device *netdev = pci_get_drvdata(pdev); @@ -3189,7 +3795,8 @@ return retval; #endif - pci_disable_device(pdev); + if (!test_and_set_bit(__IXGBEVF_DISABLED, &adapter->state)) + pci_disable_device(pdev); return 0; } @@ -3197,14 +3804,12 @@ #ifdef CONFIG_PM static int ixgbevf_resume(struct pci_dev *pdev) { - struct ixgbevf_adapter *adapter = pci_get_drvdata(pdev); - struct net_device *netdev = adapter->netdev; + struct net_device *netdev = pci_get_drvdata(pdev); + struct ixgbevf_adapter *adapter = netdev_priv(netdev); u32 err; - pci_set_power_state(pdev, PCI_D0); pci_restore_state(pdev); - /* - * pci_restore_state clears dev->state_saved so call + /* pci_restore_state clears dev->state_saved so call * pci_save_state to restore it. */ pci_save_state(pdev); @@ -3214,8 +3819,12 @@ dev_err(&pdev->dev, "Cannot enable PCI device from suspend\n"); return err; } + smp_mb__before_atomic(); + clear_bit(__IXGBEVF_DISABLED, &adapter->state); pci_set_master(pdev); + ixgbevf_reset(adapter); + rtnl_lock(); err = ixgbevf_init_interrupt_scheme(adapter); rtnl_unlock(); @@ -3224,8 +3833,6 @@ return err; } - ixgbevf_reset(adapter); - if (netif_running(netdev)) { err = ixgbevf_open(netdev); if (err) @@ -3257,23 +3864,23 @@ stats->multicast = adapter->stats.vfmprc - adapter->stats.base_vfmprc; for (i = 0; i < adapter->num_rx_queues; i++) { - ring = &adapter->rx_ring[i]; + ring = adapter->rx_ring[i]; do { - start = u64_stats_fetch_begin_bh(&ring->syncp); - bytes = ring->total_bytes; - packets = ring->total_packets; - } while (u64_stats_fetch_retry_bh(&ring->syncp, start)); + start = u64_stats_fetch_begin_irq(&ring->syncp); + bytes = ring->stats.bytes; + packets = ring->stats.packets; + } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); stats->rx_bytes += bytes; stats->rx_packets += packets; } for (i = 0; i < adapter->num_tx_queues; i++) { - ring = &adapter->tx_ring[i]; + ring = adapter->tx_ring[i]; do { - start = u64_stats_fetch_begin_bh(&ring->syncp); - bytes = ring->total_bytes; - packets = ring->total_packets; - } while (u64_stats_fetch_retry_bh(&ring->syncp, start)); + start = u64_stats_fetch_begin_irq(&ring->syncp); + bytes = ring->stats.bytes; + packets = ring->stats.packets; + } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); stats->tx_bytes += bytes; stats->tx_packets += packets; } @@ -3293,6 +3900,13 @@ .ndo_tx_timeout = ixgbevf_tx_timeout, .ndo_vlan_rx_add_vid = ixgbevf_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = ixgbevf_vlan_rx_kill_vid, +#ifdef CONFIG_NET_RX_BUSY_POLL + .ndo_busy_poll = ixgbevf_busy_poll_recv, +#endif +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = ixgbevf_netpoll, +#endif + .ndo_features_check = passthru_features_check, }; static void ixgbevf_assign_netdev_ops(struct net_device *dev) @@ -3319,26 +3933,20 @@ struct ixgbevf_adapter *adapter = NULL; struct ixgbe_hw *hw = NULL; const struct ixgbevf_info *ii = ixgbevf_info_tbl[ent->driver_data]; - static int cards_found; int err, pci_using_dac; + bool disable_dev = false; err = pci_enable_device(pdev); if (err) return err; - if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)) && - !dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64))) { + if (!dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) { pci_using_dac = 1; } else { - err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (err) { - err = dma_set_coherent_mask(&pdev->dev, - DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, "No usable DMA " - "configuration, aborting\n"); - goto err_dma; - } + dev_err(&pdev->dev, "No usable DMA configuration, aborting\n"); + goto err_dma; } pci_using_dac = 0; } @@ -3360,7 +3968,6 @@ SET_NETDEV_DEV(netdev, &pdev->dev); - pci_set_drvdata(pdev, netdev); adapter = netdev_priv(netdev); adapter->netdev = netdev; @@ -3369,14 +3976,14 @@ hw->back = adapter; adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE); - /* - * call save state here in standalone driver because it relies on + /* call save state here in standalone driver because it relies on * adapter struct to exist, and needs to call netdev_priv */ pci_save_state(pdev); hw->hw_addr = ioremap(pci_resource_start(pdev, 0), pci_resource_len(pdev, 0)); + adapter->io_addr = hw->hw_addr; if (!hw->hw_addr) { err = -EIO; goto err_ioremap; @@ -3384,9 +3991,7 @@ ixgbevf_assign_netdev_ops(netdev); - adapter->bd_number = cards_found; - - /* Setup hw api */ + /* Setup HW API */ memcpy(&hw->mac.ops, ii->mac_ops, sizeof(hw->mac.ops)); hw->mac.type = ii->mac; @@ -3406,34 +4011,39 @@ } netdev->hw_features = NETIF_F_SG | - NETIF_F_IP_CSUM | - NETIF_F_IPV6_CSUM | - NETIF_F_TSO | - NETIF_F_TSO6 | - NETIF_F_RXCSUM; + NETIF_F_IP_CSUM | + NETIF_F_IPV6_CSUM | + NETIF_F_TSO | + NETIF_F_TSO6 | + NETIF_F_RXCSUM; netdev->features = netdev->hw_features | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER; - netdev->vlan_features |= NETIF_F_TSO; - netdev->vlan_features |= NETIF_F_TSO6; - netdev->vlan_features |= NETIF_F_IP_CSUM; - netdev->vlan_features |= NETIF_F_IPV6_CSUM; - netdev->vlan_features |= NETIF_F_SG; + netdev->vlan_features |= NETIF_F_TSO | + NETIF_F_TSO6 | + NETIF_F_IP_CSUM | + NETIF_F_IPV6_CSUM | + NETIF_F_SG; if (pci_using_dac) netdev->features |= NETIF_F_HIGHDMA; netdev->priv_flags |= IFF_UNICAST_FLT; - init_timer(&adapter->watchdog_timer); - adapter->watchdog_timer.function = ixgbevf_watchdog; - adapter->watchdog_timer.data = (unsigned long)adapter; + if (IXGBE_REMOVED(hw->hw_addr)) { + err = -EIO; + goto err_sw_init; + } + + setup_timer(&adapter->service_timer, &ixgbevf_service_timer, + (unsigned long)adapter); - INIT_WORK(&adapter->reset_task, ixgbevf_reset_task); - INIT_WORK(&adapter->watchdog_task, ixgbevf_watchdog_task); + INIT_WORK(&adapter->service_task, ixgbevf_service_task); + set_bit(__IXGBEVF_SERVICE_INITED, &adapter->state); + clear_bit(__IXGBEVF_SERVICE_SCHED, &adapter->state); err = ixgbevf_init_interrupt_scheme(adapter); if (err) @@ -3445,31 +4055,44 @@ if (err) goto err_register; + pci_set_drvdata(pdev, netdev); netif_carrier_off(netdev); ixgbevf_init_last_counter_stats(adapter); - /* print the MAC address */ - hw_dbg(hw, "%pM\n", netdev->dev_addr); - - hw_dbg(hw, "MAC: %d\n", hw->mac.type); + /* print the VF info */ + dev_info(&pdev->dev, "%pM\n", netdev->dev_addr); + dev_info(&pdev->dev, "MAC: %d\n", hw->mac.type); + + switch (hw->mac.type) { + case ixgbe_mac_X550_vf: + dev_info(&pdev->dev, "Intel(R) X550 Virtual Function\n"); + break; + case ixgbe_mac_X540_vf: + dev_info(&pdev->dev, "Intel(R) X540 Virtual Function\n"); + break; + case ixgbe_mac_82599_vf: + default: + dev_info(&pdev->dev, "Intel(R) 82599 Virtual Function\n"); + break; + } - hw_dbg(hw, "Intel(R) 82599 Virtual Function\n"); - cards_found++; return 0; err_register: ixgbevf_clear_interrupt_scheme(adapter); err_sw_init: ixgbevf_reset_interrupt_capability(adapter); - iounmap(hw->hw_addr); + iounmap(adapter->io_addr); err_ioremap: + disable_dev = !test_and_set_bit(__IXGBEVF_DISABLED, &adapter->state); free_netdev(netdev); err_alloc_etherdev: pci_release_regions(pdev); err_pci_reg: err_dma: - pci_disable_device(pdev); + if (!adapter || disable_dev) + pci_disable_device(pdev); return err; } @@ -3485,14 +4108,16 @@ static void ixgbevf_remove(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); - struct ixgbevf_adapter *adapter = netdev_priv(netdev); + struct ixgbevf_adapter *adapter; + bool disable_dev; - set_bit(__IXGBEVF_DOWN, &adapter->state); + if (!netdev) + return; - del_timer_sync(&adapter->watchdog_timer); + adapter = netdev_priv(netdev); - cancel_work_sync(&adapter->reset_task); - cancel_work_sync(&adapter->watchdog_task); + set_bit(__IXGBEVF_REMOVING, &adapter->state); + cancel_work_sync(&adapter->service_task); if (netdev->reg_state == NETREG_REGISTERED) unregister_netdev(netdev); @@ -3500,17 +4125,16 @@ ixgbevf_clear_interrupt_scheme(adapter); ixgbevf_reset_interrupt_capability(adapter); - iounmap(adapter->hw.hw_addr); + iounmap(adapter->io_addr); pci_release_regions(pdev); hw_dbg(&adapter->hw, "Remove complete\n"); - kfree(adapter->tx_ring); - kfree(adapter->rx_ring); - + disable_dev = !test_and_set_bit(__IXGBEVF_DISABLED, &adapter->state); free_netdev(netdev); - pci_disable_device(pdev); + if (disable_dev) + pci_disable_device(pdev); } /** @@ -3520,22 +4144,30 @@ * * This function is called after a PCI bus error affecting * this device has been detected. - */ + **/ static pci_ers_result_t ixgbevf_io_error_detected(struct pci_dev *pdev, pci_channel_state_t state) { struct net_device *netdev = pci_get_drvdata(pdev); struct ixgbevf_adapter *adapter = netdev_priv(netdev); + if (!test_bit(__IXGBEVF_SERVICE_INITED, &adapter->state)) + return PCI_ERS_RESULT_DISCONNECT; + + rtnl_lock(); netif_device_detach(netdev); - if (state == pci_channel_io_perm_failure) + if (state == pci_channel_io_perm_failure) { + rtnl_unlock(); return PCI_ERS_RESULT_DISCONNECT; + } if (netif_running(netdev)) ixgbevf_down(adapter); - pci_disable_device(pdev); + if (!test_and_set_bit(__IXGBEVF_DISABLED, &adapter->state)) + pci_disable_device(pdev); + rtnl_unlock(); /* Request a slot slot reset. */ return PCI_ERS_RESULT_NEED_RESET; @@ -3547,7 +4179,7 @@ * * Restart the card from scratch, as if from a cold-boot. Implementation * resembles the first-half of the ixgbevf_resume routine. - */ + **/ static pci_ers_result_t ixgbevf_io_slot_reset(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); @@ -3559,6 +4191,8 @@ return PCI_ERS_RESULT_DISCONNECT; } + smp_mb__before_atomic(); + clear_bit(__IXGBEVF_DISABLED, &adapter->state); pci_set_master(pdev); ixgbevf_reset(adapter); @@ -3573,7 +4207,7 @@ * This callback is called when the error recovery driver tells us that * its OK to resume normal operation. Implementation resembles the * second-half of the ixgbevf_resume routine. - */ + **/ static void ixgbevf_io_resume(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); @@ -3593,17 +4227,17 @@ }; static struct pci_driver ixgbevf_driver = { - .name = ixgbevf_driver_name, - .id_table = ixgbevf_pci_tbl, - .probe = ixgbevf_probe, - .remove = ixgbevf_remove, + .name = ixgbevf_driver_name, + .id_table = ixgbevf_pci_tbl, + .probe = ixgbevf_probe, + .remove = ixgbevf_remove, #ifdef CONFIG_PM /* Power Management Hooks */ - .suspend = ixgbevf_suspend, - .resume = ixgbevf_resume, + .suspend = ixgbevf_suspend, + .resume = ixgbevf_resume, #endif - .shutdown = ixgbevf_shutdown, - .err_handler = &ixgbevf_err_handler + .shutdown = ixgbevf_shutdown, + .err_handler = &ixgbevf_err_handler }; /** @@ -3615,6 +4249,7 @@ static int __init ixgbevf_init_module(void) { int ret; + pr_info("%s - version %s\n", ixgbevf_driver_string, ixgbevf_driver_version); @@ -3645,6 +4280,7 @@ char *ixgbevf_get_hw_dev_name(struct ixgbe_hw *hw) { struct ixgbevf_adapter *adapter = hw->back; + return adapter->netdev->name; }