diff options
Diffstat (limited to 'drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c')
| -rw-r--r-- | drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 3164 |
1 files changed, 1693 insertions, 1471 deletions
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index e51d552410a..75467f83772 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel 82599 Virtual Function driver - Copyright(c) 1999 - 2012 Intel Corporation. + Copyright(c) 1999 - 2014 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, @@ -42,6 +42,7 @@ #include <linux/in.h> #include <linux/ip.h> #include <linux/tcp.h> +#include <linux/sctp.h> #include <linux/ipv6.h> #include <linux/slab.h> #include <net/checksum.h> @@ -57,7 +58,7 @@ const char ixgbevf_driver_name[] = "ixgbevf"; static const char ixgbevf_driver_string[] = "Intel(R) 10 Gigabit PCI Express Virtual Function Network Driver"; -#define DRV_VERSION "2.2.0-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."; @@ -75,33 +76,78 @@ static const struct ixgbevf_info *ixgbevf_info_tbl[] = { * { Vendor ID, Device ID, SubVendor ID, SubDevice ID, * Class, Class Mask, private data (not used) } */ -static 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}, - +static DEFINE_PCI_DEVICE_TABLE(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 }, /* required last entry */ {0, } }; MODULE_DEVICE_TABLE(pci, ixgbevf_pci_tbl); MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); -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); -#define DEFAULT_DEBUG_LEVEL_SHIFT 3 +#define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV|NETIF_MSG_PROBE|NETIF_MSG_LINK) +static int debug = -1; +module_param(debug, int, 0); +MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); /* forward decls */ -static void ixgbevf_set_itr_msix(struct ixgbevf_q_vector *q_vector); -static void ixgbevf_write_eitr(struct ixgbevf_adapter *adapter, int v_idx, - u32 itr_reg); +static void ixgbevf_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 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_WORK_INIT, &adapter->state)) + schedule_work(&adapter->watchdog_task); +} + +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. + */ + 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; -static inline void ixgbevf_release_rx_desc(struct ixgbe_hw *hw, - struct ixgbevf_ring *rx_ring, + 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; +} + +static inline void ixgbevf_release_rx_desc(struct ixgbevf_ring *rx_ring, u32 val) { + rx_ring->next_to_use = val; + /* * Force memory writes to complete before letting h/w * know there are new descriptors to fetch. (Only @@ -109,16 +155,15 @@ static inline void ixgbevf_release_rx_desc(struct ixgbe_hw *hw, * such as IA-64). */ wmb(); - IXGBE_WRITE_REG(hw, IXGBE_VFRDT(rx_ring->reg_idx), val); + ixgbevf_write_tail(rx_ring, val); } -/* +/** * ixgbevf_set_ivar - set IVAR registers - maps interrupt causes to vectors * @adapter: pointer to adapter struct * @direction: 0 for Rx, 1 for Tx, -1 for other causes * @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) @@ -143,142 +188,158 @@ static void ixgbevf_set_ivar(struct ixgbevf_adapter *adapter, s8 direction, } } -static void ixgbevf_unmap_and_free_tx_resource(struct ixgbevf_adapter *adapter, - struct ixgbevf_tx_buffer - *tx_buffer_info) +static void ixgbevf_unmap_and_free_tx_resource(struct ixgbevf_ring *tx_ring, + struct ixgbevf_tx_buffer *tx_buffer) { - if (tx_buffer_info->dma) { - if (tx_buffer_info->mapped_as_page) - dma_unmap_page(&adapter->pdev->dev, - tx_buffer_info->dma, - tx_buffer_info->length, - DMA_TO_DEVICE); - else - dma_unmap_single(&adapter->pdev->dev, - tx_buffer_info->dma, - tx_buffer_info->length, + if (tx_buffer->skb) { + dev_kfree_skb_any(tx_buffer->skb); + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), DMA_TO_DEVICE); - 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_info->time_stamp = 0; - /* tx_buffer_info must be completely set up in the transmit path */ + 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 */ } #define IXGBE_MAX_TXD_PWR 14 #define IXGBE_MAX_DATA_PER_TXD (1 << IXGBE_MAX_TXD_PWR) /* Tx Descriptors needed, worst case */ -#define TXD_USE_COUNT(S) (((S) >> IXGBE_MAX_TXD_PWR) + \ - (((S) & (IXGBE_MAX_DATA_PER_TXD - 1)) ? 1 : 0)) -#ifdef MAX_SKB_FRAGS -#define DESC_NEEDED (TXD_USE_COUNT(IXGBE_MAX_DATA_PER_TXD) /* skb->data */ + \ - MAX_SKB_FRAGS * TXD_USE_COUNT(PAGE_SIZE) + 1) /* for context */ -#else -#define DESC_NEEDED TXD_USE_COUNT(IXGBE_MAX_DATA_PER_TXD) -#endif +#define TXD_USE_COUNT(S) DIV_ROUND_UP((S), IXGBE_MAX_DATA_PER_TXD) +#define DESC_NEEDED (MAX_SKB_FRAGS + 4) static void ixgbevf_tx_timeout(struct net_device *netdev); /** * ixgbevf_clean_tx_irq - Reclaim resources after transmit completes - * @adapter: board private structure + * @q_vector: board private structure * @tx_ring: tx ring to clean **/ -static bool ixgbevf_clean_tx_irq(struct ixgbevf_adapter *adapter, +static bool ixgbevf_clean_tx_irq(struct ixgbevf_q_vector *q_vector, struct ixgbevf_ring *tx_ring) { - struct net_device *netdev = adapter->netdev; - struct ixgbe_hw *hw = &adapter->hw; - union ixgbe_adv_tx_desc *tx_desc, *eop_desc; - struct ixgbevf_tx_buffer *tx_buffer_info; - unsigned int i, eop, count = 0; + struct ixgbevf_adapter *adapter = q_vector->adapter; + 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; - i = tx_ring->next_to_clean; - eop = tx_ring->tx_buffer_info[i].next_to_watch; - eop_desc = IXGBE_TX_DESC_ADV(*tx_ring, eop); - - while ((eop_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD)) && - (count < tx_ring->work_limit)) { - bool cleaned = false; - rmb(); /* read buffer_info after eop_desc */ - /* eop could change between read and DD-check */ - if (unlikely(eop != tx_ring->tx_buffer_info[i].next_to_watch)) - goto cont_loop; - for ( ; !cleaned; count++) { - struct sk_buff *skb; - tx_desc = IXGBE_TX_DESC_ADV(*tx_ring, i); - tx_buffer_info = &tx_ring->tx_buffer_info[i]; - cleaned = (i == eop); - 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; - } + if (test_bit(__IXGBEVF_DOWN, &adapter->state)) + return true; + + tx_buffer = &tx_ring->tx_buffer_info[i]; + tx_desc = IXGBEVF_TX_DESC(tx_ring, i); + i -= tx_ring->count; + + do { + 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) + break; - ixgbevf_unmap_and_free_tx_resource(adapter, - tx_buffer_info); + /* prevent any other reads prior to eop_desc */ + read_barrier_depends(); - tx_desc->wb.status = 0; + /* if DD is not set pending work has not been completed */ + if (!(eop_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD))) + break; + + /* clear next_to_watch to prevent false hangs */ + tx_buffer->next_to_watch = NULL; + + /* 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 (i == tx_ring->count) - i = 0; + if (unlikely(!i)) { + i -= tx_ring->count; + tx_buffer = tx_ring->tx_buffer_info; + tx_desc = IXGBEVF_TX_DESC(tx_ring, 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); + } } -cont_loop: - eop = tx_ring->tx_buffer_info[i].next_to_watch; - eop_desc = IXGBE_TX_DESC_ADV(*tx_ring, eop); - } + /* 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); + } + /* 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; #define TX_WAKE_THRESHOLD (DESC_NEEDED * 2) - if (unlikely(count && netif_carrier_ok(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(); -#ifdef HAVE_TX_MQ - if (__netif_subqueue_stopped(netdev, tx_ring->queue_index) && - !test_bit(__IXGBEVF_DOWN, &adapter->state)) { - netif_wake_subqueue(netdev, tx_ring->queue_index); - ++adapter->restart_queue; - } -#else - if (netif_queue_stopped(netdev) && + + if (__netif_subqueue_stopped(tx_ring->netdev, + tx_ring->queue_index) && !test_bit(__IXGBEVF_DOWN, &adapter->state)) { - netif_wake_queue(netdev); - ++adapter->restart_queue; + netif_wake_subqueue(tx_ring->netdev, + tx_ring->queue_index); + ++tx_ring->tx_stats.restart_queue; } -#endif - } - - /* re-arm the interrupt */ - if ((count >= tx_ring->work_limit) && - (!test_bit(__IXGBEVF_DOWN, &adapter->state))) { - IXGBE_WRITE_REG(hw, IXGBE_VTEICS, tx_ring->v_idx); } - u64_stats_update_begin(&tx_ring->syncp); - tx_ring->total_bytes += total_bytes; - tx_ring->total_packets += total_packets; - u64_stats_update_end(&tx_ring->syncp); - - return count < tx_ring->work_limit; + return !!budget; } /** @@ -286,46 +347,68 @@ cont_loop: * @q_vector: structure containing interrupt and ring information * @skb: packet to send up * @status: hardware indication of status of receive - * @rx_ring: rx descriptor ring (for a specific queue) to setup * @rx_desc: rx descriptor **/ static void ixgbevf_receive_skb(struct ixgbevf_q_vector *q_vector, struct sk_buff *skb, u8 status, - struct ixgbevf_ring *ring, union ixgbe_adv_rx_desc *rx_desc) { 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); - if (is_vlan && test_bit(tag, adapter->active_vlans)) - __vlan_hwaccel_put_tag(skb, tag); + if (is_vlan && test_bit(tag & VLAN_VID_MASK, adapter->active_vlans)) + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), tag); if (!(adapter->flags & IXGBE_FLAG_IN_NETPOLL)) - napi_gro_receive(&q_vector->napi, skb); + napi_gro_receive(&q_vector->napi, skb); else - netif_rx(skb); + netif_rx(skb); +} + +/** + * 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_rx_skb(struct ixgbevf_q_vector *q_vector, + struct sk_buff *skb, u8 status, + union ixgbe_adv_rx_desc *rx_desc) +{ +#ifdef CONFIG_NET_RX_BUSY_POLL + skb_mark_napi_id(skb, &q_vector->napi); + + if (ixgbevf_qv_busy_polling(q_vector)) { + netif_receive_skb(skb); + /* exit early if we busy polled */ + return; + } +#endif /* CONFIG_NET_RX_BUSY_POLL */ + + ixgbevf_receive_skb(q_vector, skb, status, rx_desc); } /** * ixgbevf_rx_checksum - indicate in skb if hw indicated a good cksum - * @adapter: address of board private structure + * @ring: pointer to Rx descriptor ring structure * @status_err: hardware indication of status of receive * @skb: skb currently being received and modified **/ -static inline void ixgbevf_rx_checksum(struct ixgbevf_adapter *adapter, +static inline void ixgbevf_rx_checksum(struct ixgbevf_ring *ring, u32 status_err, struct sk_buff *skb) { skb_checksum_none_assert(skb); /* Rx csum disabled */ - if (!(adapter->flags & IXGBE_FLAG_RX_CSUM_ENABLED)) + if (!(ring->netdev->features & NETIF_F_RXCSUM)) return; /* if IP and error */ if ((status_err & IXGBE_RXD_STAT_IPCS) && (status_err & IXGBE_RXDADV_ERR_IPE)) { - adapter->hw_csum_rx_error++; + ring->rx_stats.csum_err++; return; } @@ -333,219 +416,130 @@ static inline void ixgbevf_rx_checksum(struct ixgbevf_adapter *adapter, return; if (status_err & IXGBE_RXDADV_ERR_TCPE) { - adapter->hw_csum_rx_error++; + ring->rx_stats.csum_err++; return; } /* It must be a TCP or UDP packet with a valid checksum */ skb->ip_summed = CHECKSUM_UNNECESSARY; - adapter->hw_csum_rx_good++; } /** * 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 **/ -static void ixgbevf_alloc_rx_buffers(struct ixgbevf_adapter *adapter, - struct ixgbevf_ring *rx_ring, +static void ixgbevf_alloc_rx_buffers(struct ixgbevf_ring *rx_ring, int cleaned_count) { - struct pci_dev *pdev = adapter->pdev; union ixgbe_adv_rx_desc *rx_desc; struct ixgbevf_rx_buffer *bi; - struct sk_buff *skb; - unsigned int i; - unsigned int bufsz = rx_ring->rx_buf_len + NET_IP_ALIGN; - - i = rx_ring->next_to_use; - bi = &rx_ring->rx_buffer_info[i]; + unsigned int i = rx_ring->next_to_use; while (cleaned_count--) { - rx_desc = IXGBE_RX_DESC_ADV(*rx_ring, i); - - if (!bi->page_dma && - (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED)) { - if (!bi->page) { - bi->page = alloc_page(GFP_ATOMIC | __GFP_COLD); - if (!bi->page) { - adapter->alloc_rx_page_failed++; - goto no_buffers; - } - bi->page_offset = 0; - } else { - /* use a half page if we're re-using */ - bi->page_offset ^= (PAGE_SIZE / 2); - } - - bi->page_dma = dma_map_page(&pdev->dev, bi->page, - bi->page_offset, - (PAGE_SIZE / 2), - DMA_FROM_DEVICE); - } + rx_desc = IXGBEVF_RX_DESC(rx_ring, i); + bi = &rx_ring->rx_buffer_info[i]; - skb = bi->skb; - if (!skb) { - skb = netdev_alloc_skb(adapter->netdev, - bufsz); + if (!bi->skb) { + struct sk_buff *skb; - if (!skb) { - adapter->alloc_rx_buff_failed++; + skb = netdev_alloc_skb_ip_align(rx_ring->netdev, + rx_ring->rx_buf_len); + if (!skb) goto no_buffers; - } - - /* - * Make buffer alignment 2 beyond a 16 byte boundary - * this will result in a 16 byte aligned IP header after - * the 14 byte MAC header is removed - */ - skb_reserve(skb, NET_IP_ALIGN); bi->skb = skb; - } - if (!bi->dma) { - bi->dma = dma_map_single(&pdev->dev, skb->data, + + bi->dma = dma_map_single(rx_ring->dev, skb->data, rx_ring->rx_buf_len, DMA_FROM_DEVICE); + if (dma_mapping_error(rx_ring->dev, bi->dma)) { + dev_kfree_skb(skb); + bi->skb = NULL; + dev_err(rx_ring->dev, "Rx DMA map failed\n"); + break; + } } - /* Refresh the desc even if buffer_addrs didn't change because - * each write-back erases this info. */ - if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) { - rx_desc->read.pkt_addr = cpu_to_le64(bi->page_dma); - rx_desc->read.hdr_addr = cpu_to_le64(bi->dma); - } else { - rx_desc->read.pkt_addr = cpu_to_le64(bi->dma); - } + rx_desc->read.pkt_addr = cpu_to_le64(bi->dma); i++; if (i == rx_ring->count) i = 0; - bi = &rx_ring->rx_buffer_info[i]; } no_buffers: - if (rx_ring->next_to_use != i) { - rx_ring->next_to_use = i; - if (i-- == 0) - i = (rx_ring->count - 1); - - ixgbevf_release_rx_desc(&adapter->hw, rx_ring, i); - } + rx_ring->rx_stats.alloc_rx_buff_failed++; + if (rx_ring->next_to_use != i) + ixgbevf_release_rx_desc(rx_ring, i); } static inline void ixgbevf_irq_enable_queues(struct ixgbevf_adapter *adapter, - u64 qmask) + u32 qmask) { - u32 mask; struct ixgbe_hw *hw = &adapter->hw; - mask = (qmask & 0xFFFFFFFF); - IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, mask); -} - -static inline u16 ixgbevf_get_hdr_info(union ixgbe_adv_rx_desc *rx_desc) -{ - return rx_desc->wb.lower.lo_dword.hs_rss.hdr_info; + IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, qmask); } -static inline u16 ixgbevf_get_pkt_info(union ixgbe_adv_rx_desc *rx_desc) +static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, + struct ixgbevf_ring *rx_ring, + int budget) { - return rx_desc->wb.lower.lo_dword.hs_rss.pkt_info; -} - -static bool ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, - struct ixgbevf_ring *rx_ring, - int *work_done, int work_to_do) -{ - 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; - u16 hdr_info; - bool cleaned = false; int cleaned_count = 0; unsigned int total_rx_bytes = 0, total_rx_packets = 0; i = rx_ring->next_to_clean; - rx_desc = IXGBE_RX_DESC_ADV(*rx_ring, i); + rx_desc = IXGBEVF_RX_DESC(rx_ring, i); staterr = le32_to_cpu(rx_desc->wb.upper.status_error); rx_buffer_info = &rx_ring->rx_buffer_info[i]; while (staterr & IXGBE_RXD_STAT_DD) { - u32 upper_len = 0; - if (*work_done >= work_to_do) + if (!budget) break; - (*work_done)++; + budget--; rmb(); /* read descriptor and rx_buffer_info after status DD */ - if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) { - hdr_info = le16_to_cpu(ixgbevf_get_hdr_info(rx_desc)); - len = (hdr_info & IXGBE_RXDADV_HDRBUFLEN_MASK) >> - IXGBE_RXDADV_HDRBUFLEN_SHIFT; - if (hdr_info & IXGBE_RXDADV_SPH) - adapter->rx_hdr_split++; - if (len > IXGBEVF_RX_HDR_SIZE) - len = IXGBEVF_RX_HDR_SIZE; - upper_len = le16_to_cpu(rx_desc->wb.upper.length); - } else { - len = le16_to_cpu(rx_desc->wb.upper.length); - } - cleaned = true; + len = le16_to_cpu(rx_desc->wb.upper.length); skb = rx_buffer_info->skb; prefetch(skb->data - NET_IP_ALIGN); rx_buffer_info->skb = NULL; if (rx_buffer_info->dma) { - dma_unmap_single(&pdev->dev, rx_buffer_info->dma, + dma_unmap_single(rx_ring->dev, rx_buffer_info->dma, rx_ring->rx_buf_len, DMA_FROM_DEVICE); rx_buffer_info->dma = 0; skb_put(skb, len); } - if (upper_len) { - dma_unmap_page(&pdev->dev, rx_buffer_info->page_dma, - PAGE_SIZE / 2, DMA_FROM_DEVICE); - rx_buffer_info->page_dma = 0; - skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags, - rx_buffer_info->page, - rx_buffer_info->page_offset, - upper_len); - - if ((rx_ring->rx_buf_len > (PAGE_SIZE / 2)) || - (page_count(rx_buffer_info->page) != 1)) - rx_buffer_info->page = NULL; - else - get_page(rx_buffer_info->page); - - skb->len += upper_len; - skb->data_len += upper_len; - skb->truesize += upper_len; - } - i++; if (i == rx_ring->count) i = 0; - next_rxd = IXGBE_RX_DESC_ADV(*rx_ring, i); + next_rxd = IXGBEVF_RX_DESC(rx_ring, i); prefetch(next_rxd); cleaned_count++; next_buffer = &rx_ring->rx_buffer_info[i]; if (!(staterr & IXGBE_RXD_STAT_EOP)) { - if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) { - rx_buffer_info->skb = next_buffer->skb; - rx_buffer_info->dma = next_buffer->dma; - next_buffer->skb = skb; - next_buffer->dma = 0; - } else { - skb->next = next_buffer->skb; - skb->next->prev = skb; - } - adapter->non_eop_descs++; + skb->next = next_buffer->skb; + IXGBE_CB(skb->next)->prev = skb; + rx_ring->rx_stats.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; } @@ -555,32 +549,33 @@ static bool ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, goto next_desc; } - ixgbevf_rx_checksum(adapter, staterr, skb); + 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 + skb->protocol = eth_type_trans(skb, rx_ring->netdev); + + /* Workaround hardware that can't do proper VEPA multicast + * source pruning. */ - if (staterr & IXGBE_RXD_STAT_LB) { - u32 header_fixup_len = skb_headlen(skb); - if (header_fixup_len < 14) - skb_push(skb, header_fixup_len); + 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; } - skb->protocol = eth_type_trans(skb, adapter->netdev); - ixgbevf_receive_skb(q_vector, skb, staterr, rx_ring, rx_desc); + ixgbevf_rx_skb(q_vector, skb, staterr, rx_desc); next_desc: rx_desc->wb.upper.status_error = 0; /* 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); + ixgbevf_alloc_rx_buffers(rx_ring, cleaned_count); cleaned_count = 0; } @@ -592,104 +587,132 @@ next_desc: } rx_ring->next_to_clean = i; - cleaned_count = IXGBE_DESC_UNUSED(rx_ring); + cleaned_count = ixgbevf_desc_unused(rx_ring); if (cleaned_count) - ixgbevf_alloc_rx_buffers(adapter, rx_ring, cleaned_count); + ixgbevf_alloc_rx_buffers(rx_ring, cleaned_count); 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 cleaned; + return total_rx_packets; } /** - * ixgbevf_clean_rxonly - msix (aka one shot) rx clean routine + * ixgbevf_poll - NAPI polling calback * @napi: napi struct with our devices info in it * @budget: amount of work driver is allowed to do this pass, in packets * - * This function is optimized for cleaning one queue only on a single - * q_vector!!! + * This function will clean more than one or more rings associated with a + * q_vector. **/ -static int ixgbevf_clean_rxonly(struct napi_struct *napi, int budget) +static int ixgbevf_poll(struct napi_struct *napi, int budget) { struct ixgbevf_q_vector *q_vector = container_of(napi, struct ixgbevf_q_vector, napi); struct ixgbevf_adapter *adapter = q_vector->adapter; - struct ixgbevf_ring *rx_ring = NULL; - int work_done = 0; - long r_idx; + struct ixgbevf_ring *ring; + int per_ring_budget; + bool clean_complete = true; - r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues); - rx_ring = &(adapter->rx_ring[r_idx]); + ixgbevf_for_each_ring(ring, q_vector->tx) + clean_complete &= ixgbevf_clean_tx_irq(q_vector, ring); - ixgbevf_clean_rx_irq(q_vector, rx_ring, &work_done, budget); +#ifdef CONFIG_NET_RX_BUSY_POLL + if (!ixgbevf_qv_lock_napi(q_vector)) + return budget; +#endif - /* If all Rx work done, exit the polling mode */ - if (work_done < budget) { - napi_complete(napi); - if (adapter->itr_setting & 1) - ixgbevf_set_itr_msix(q_vector); - if (!test_bit(__IXGBEVF_DOWN, &adapter->state)) - ixgbevf_irq_enable_queues(adapter, rx_ring->v_idx); - } + /* attempt to distribute budget to each queue fairly, but don't allow + * the budget to go below 1 because we'll exit polling */ + if (q_vector->rx.count > 1) + per_ring_budget = max(budget/q_vector->rx.count, 1); + else + per_ring_budget = budget; + + 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) + < per_ring_budget); + adapter->flags &= ~IXGBE_FLAG_IN_NETPOLL; + +#ifdef CONFIG_NET_RX_BUSY_POLL + ixgbevf_qv_unlock_napi(q_vector); +#endif - return work_done; + /* If all work not completed, return budget and keep polling */ + if (!clean_complete) + return budget; + /* all work done, exit the polling mode */ + napi_complete(napi); + if (adapter->rx_itr_setting & 1) + ixgbevf_set_itr(q_vector); + if (!test_bit(__IXGBEVF_DOWN, &adapter->state) && + !test_bit(__IXGBEVF_REMOVING, &adapter->state)) + ixgbevf_irq_enable_queues(adapter, + 1 << q_vector->v_idx); + + return 0; } /** - * ixgbevf_clean_rxonly_many - msix (aka one shot) rx clean routine - * @napi: napi struct with our devices info in it - * @budget: amount of work driver is allowed to do this pass, in packets - * - * This function will clean more than one rx queue associated with a - * q_vector. - **/ -static int ixgbevf_clean_rxonly_many(struct napi_struct *napi, int budget) + * ixgbevf_write_eitr - write VTEITR register in hardware specific way + * @q_vector: structure containing interrupt and ring information + */ +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 + * immediate assertion of the interrupt + */ + itr_reg |= IXGBE_EITR_CNT_WDIS; + + 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); + container_of(napi, struct ixgbevf_q_vector, napi); struct ixgbevf_adapter *adapter = q_vector->adapter; - struct ixgbevf_ring *rx_ring = NULL; - int work_done = 0, i; - long r_idx; - u64 enable_mask = 0; + struct ixgbevf_ring *ring; + int found = 0; - /* attempt to distribute budget to each queue fairly, but don't allow - * the budget to go below 1 because we'll exit polling */ - budget /= (q_vector->rxr_count ?: 1); - budget = max(budget, 1); - r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues); - for (i = 0; i < q_vector->rxr_count; i++) { - rx_ring = &(adapter->rx_ring[r_idx]); - ixgbevf_clean_rx_irq(q_vector, rx_ring, &work_done, budget); - enable_mask |= rx_ring->v_idx; - r_idx = find_next_bit(q_vector->rxr_idx, adapter->num_rx_queues, - r_idx + 1); - } + if (test_bit(__IXGBEVF_DOWN, &adapter->state)) + return LL_FLUSH_FAILED; -#ifndef HAVE_NETDEV_NAPI_LIST - if (!netif_running(adapter->netdev)) - work_done = 0; + 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 - r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues); - rx_ring = &(adapter->rx_ring[r_idx]); - - /* If all Rx work done, exit the polling mode */ - if (work_done < budget) { - napi_complete(napi); - if (adapter->itr_setting & 1) - ixgbevf_set_itr_msix(q_vector); - if (!test_bit(__IXGBEVF_DOWN, &adapter->state)) - ixgbevf_irq_enable_queues(adapter, enable_mask); + if (found) + break; } - return work_done; -} + ixgbevf_qv_unlock_poll(q_vector); + return found; +} +#endif /* CONFIG_NET_RX_BUSY_POLL */ /** * ixgbevf_configure_msix - Configure MSI-X hardware @@ -701,56 +724,49 @@ static int ixgbevf_clean_rxonly_many(struct napi_struct *napi, int budget) static void ixgbevf_configure_msix(struct ixgbevf_adapter *adapter) { struct ixgbevf_q_vector *q_vector; - struct ixgbe_hw *hw = &adapter->hw; - int i, j, q_vectors, v_idx, r_idx; - u32 mask; + int q_vectors, v_idx; q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; + adapter->eims_enable_mask = 0; /* * Populate the IVAR table and set the ITR values to the * corresponding register. */ for (v_idx = 0; v_idx < q_vectors; v_idx++) { + struct ixgbevf_ring *ring; q_vector = adapter->q_vector[v_idx]; - /* XXX for_each_set_bit(...) */ - r_idx = find_first_bit(q_vector->rxr_idx, - adapter->num_rx_queues); - - for (i = 0; i < q_vector->rxr_count; i++) { - j = adapter->rx_ring[r_idx].reg_idx; - ixgbevf_set_ivar(adapter, 0, j, v_idx); - r_idx = find_next_bit(q_vector->rxr_idx, - adapter->num_rx_queues, - r_idx + 1); - } - r_idx = find_first_bit(q_vector->txr_idx, - adapter->num_tx_queues); - - for (i = 0; i < q_vector->txr_count; i++) { - j = adapter->tx_ring[r_idx].reg_idx; - ixgbevf_set_ivar(adapter, 1, j, v_idx); - r_idx = find_next_bit(q_vector->txr_idx, - adapter->num_tx_queues, - r_idx + 1); + + ixgbevf_for_each_ring(ring, q_vector->rx) + ixgbevf_set_ivar(adapter, 0, ring->reg_idx, v_idx); + + ixgbevf_for_each_ring(ring, q_vector->tx) + ixgbevf_set_ivar(adapter, 1, ring->reg_idx, v_idx); + + if (q_vector->tx.ring && !q_vector->rx.ring) { + /* tx only vector */ + if (adapter->tx_itr_setting == 1) + q_vector->itr = IXGBE_10K_ITR; + else + q_vector->itr = adapter->tx_itr_setting; + } else { + /* rx or rx/tx vector */ + if (adapter->rx_itr_setting == 1) + q_vector->itr = IXGBE_20K_ITR; + else + q_vector->itr = adapter->rx_itr_setting; } - /* if this is a tx only vector halve the interrupt rate */ - if (q_vector->txr_count && !q_vector->rxr_count) - q_vector->eitr = (adapter->eitr_param >> 1); - else if (q_vector->rxr_count) - /* rx only */ - q_vector->eitr = adapter->eitr_param; + /* add q_vector eims value to global eims_enable_mask */ + adapter->eims_enable_mask |= 1 << v_idx; - ixgbevf_write_eitr(adapter, v_idx, q_vector->eitr); + ixgbevf_write_eitr(q_vector); } ixgbevf_set_ivar(adapter, -1, 1, v_idx); - - /* set up to autoclear timer, and the vectors */ - mask = IXGBE_EIMS_ENABLE_MASK; - mask &= ~IXGBE_EIMS_OTHER; - IXGBE_WRITE_REG(hw, IXGBE_VTEIAC, mask); + /* setup eims_other and add value to global eims_enable_mask */ + adapter->eims_other = 1 << v_idx; + adapter->eims_enable_mask |= adapter->eims_other; } enum latency_range { @@ -762,11 +778,8 @@ enum latency_range { /** * ixgbevf_update_itr - update the dynamic ITR value based on statistics - * @adapter: pointer to adapter - * @eitr: eitr setting (ints per sec) to give last timeslice - * @itr_setting: current throttle rate in ints/second - * @packets: the number of packets during this measurement interval - * @bytes: the number of bytes during this measurement interval + * @q_vector: structure containing interrupt and ring information + * @ring_container: structure containing ring performance data * * Stores a new ITR value based on packets and byte * counts during the last interrupt. The advantage of per interrupt @@ -776,17 +789,17 @@ enum latency_range { * on testing data as well as attempting to minimize response time * while increasing bulk throughput. **/ -static u8 ixgbevf_update_itr(struct ixgbevf_adapter *adapter, - u32 eitr, u8 itr_setting, - int packets, int bytes) +static void ixgbevf_update_itr(struct ixgbevf_q_vector *q_vector, + struct ixgbevf_ring_container *ring_container) { - unsigned int retval = itr_setting; + int bytes = ring_container->total_bytes; + int packets = ring_container->total_packets; u32 timepassed_us; u64 bytes_perint; + u8 itr_setting = ring_container->itr; if (packets == 0) - goto update_itr_done; - + return; /* simple throttlerate management * 0-20MB/s lowest (100000 ints/s) @@ -794,231 +807,98 @@ static u8 ixgbevf_update_itr(struct ixgbevf_adapter *adapter, * 100-1249MB/s bulk (8000 ints/s) */ /* what was last interrupt timeslice? */ - timepassed_us = 1000000/eitr; + timepassed_us = q_vector->itr >> 2; bytes_perint = bytes / timepassed_us; /* bytes/usec */ switch (itr_setting) { case lowest_latency: - if (bytes_perint > adapter->eitr_low) - retval = low_latency; + if (bytes_perint > 10) + itr_setting = low_latency; break; case low_latency: - if (bytes_perint > adapter->eitr_high) - retval = bulk_latency; - else if (bytes_perint <= adapter->eitr_low) - retval = lowest_latency; + if (bytes_perint > 20) + itr_setting = bulk_latency; + else if (bytes_perint <= 10) + itr_setting = lowest_latency; break; case bulk_latency: - if (bytes_perint <= adapter->eitr_high) - retval = low_latency; + if (bytes_perint <= 20) + itr_setting = low_latency; break; } -update_itr_done: - return retval; + /* clear work counters since we have the values we need */ + ring_container->total_bytes = 0; + ring_container->total_packets = 0; + + /* write updated itr to ring container */ + ring_container->itr = itr_setting; } -/** - * ixgbevf_write_eitr - write VTEITR register in hardware specific way - * @adapter: pointer to adapter struct - * @v_idx: vector index into q_vector array - * @itr_reg: new value to be written in *register* format, not ints/s - * - * This function is made to be called by ethtool and by the driver - * when it needs to update VTEITR registers at runtime. Hardware - * specific quirks/differences are taken care of here. - */ -static void ixgbevf_write_eitr(struct ixgbevf_adapter *adapter, int v_idx, - u32 itr_reg) +static void ixgbevf_set_itr(struct ixgbevf_q_vector *q_vector) { - struct ixgbe_hw *hw = &adapter->hw; + u32 new_itr = q_vector->itr; + u8 current_itr; - itr_reg = EITR_INTS_PER_SEC_TO_REG(itr_reg); + ixgbevf_update_itr(q_vector, &q_vector->tx); + ixgbevf_update_itr(q_vector, &q_vector->rx); - /* - * set the WDIS bit to not clear the timer bits and cause an - * immediate assertion of the interrupt - */ - itr_reg |= IXGBE_EITR_CNT_WDIS; - - IXGBE_WRITE_REG(hw, IXGBE_VTEITR(v_idx), itr_reg); -} - -static void ixgbevf_set_itr_msix(struct ixgbevf_q_vector *q_vector) -{ - struct ixgbevf_adapter *adapter = q_vector->adapter; - u32 new_itr; - u8 current_itr, ret_itr; - int i, r_idx, v_idx = q_vector->v_idx; - struct ixgbevf_ring *rx_ring, *tx_ring; - - r_idx = find_first_bit(q_vector->txr_idx, adapter->num_tx_queues); - for (i = 0; i < q_vector->txr_count; i++) { - tx_ring = &(adapter->tx_ring[r_idx]); - ret_itr = ixgbevf_update_itr(adapter, q_vector->eitr, - q_vector->tx_itr, - tx_ring->total_packets, - tx_ring->total_bytes); - /* if the result for this queue would decrease interrupt - * rate for this vector then use that result */ - q_vector->tx_itr = ((q_vector->tx_itr > ret_itr) ? - q_vector->tx_itr - 1 : ret_itr); - r_idx = find_next_bit(q_vector->txr_idx, adapter->num_tx_queues, - r_idx + 1); - } - - r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues); - for (i = 0; i < q_vector->rxr_count; i++) { - rx_ring = &(adapter->rx_ring[r_idx]); - ret_itr = ixgbevf_update_itr(adapter, q_vector->eitr, - q_vector->rx_itr, - rx_ring->total_packets, - rx_ring->total_bytes); - /* if the result for this queue would decrease interrupt - * rate for this vector then use that result */ - q_vector->rx_itr = ((q_vector->rx_itr > ret_itr) ? - q_vector->rx_itr - 1 : ret_itr); - r_idx = find_next_bit(q_vector->rxr_idx, adapter->num_rx_queues, - r_idx + 1); - } - - current_itr = max(q_vector->rx_itr, q_vector->tx_itr); + current_itr = max(q_vector->rx.itr, q_vector->tx.itr); switch (current_itr) { /* counts and packets in update_itr are dependent on these numbers */ case lowest_latency: - new_itr = 100000; + new_itr = IXGBE_100K_ITR; break; case low_latency: - new_itr = 20000; /* aka hwitr = ~200 */ + new_itr = IXGBE_20K_ITR; break; case bulk_latency: default: - new_itr = 8000; + new_itr = IXGBE_8K_ITR; break; } - if (new_itr != q_vector->eitr) { - u32 itr_reg; - - /* save the algorithm value here, not the smoothed one */ - q_vector->eitr = new_itr; + if (new_itr != q_vector->itr) { /* do an exponential smoothing */ - new_itr = ((q_vector->eitr * 90)/100) + ((new_itr * 10)/100); - itr_reg = EITR_INTS_PER_SEC_TO_REG(new_itr); - ixgbevf_write_eitr(adapter, v_idx, itr_reg); - } -} - -static irqreturn_t ixgbevf_msix_mbx(int irq, void *data) -{ - struct net_device *netdev = data; - struct ixgbevf_adapter *adapter = netdev_priv(netdev); - struct ixgbe_hw *hw = &adapter->hw; - u32 eicr; - u32 msg; - bool got_ack = false; - - eicr = IXGBE_READ_REG(hw, IXGBE_VTEICS); - IXGBE_WRITE_REG(hw, IXGBE_VTEICR, eicr); - - if (!hw->mbx.ops.check_for_ack(hw)) - got_ack = true; - - if (!hw->mbx.ops.check_for_msg(hw)) { - hw->mbx.ops.read(hw, &msg, 1); + new_itr = (10 * new_itr * q_vector->itr) / + ((9 * new_itr) + q_vector->itr); - if ((msg & IXGBE_MBVFICR_VFREQ_MASK) == IXGBE_PF_CONTROL_MSG) - mod_timer(&adapter->watchdog_timer, - round_jiffies(jiffies + 1)); + /* save the algorithm value here */ + q_vector->itr = new_itr; - if (msg & IXGBE_VT_MSGTYPE_NACK) - pr_warn("Last Request of type %2.2x to PF Nacked\n", - msg & 0xFF); - /* - * Restore the PFSTS bit in case someone is polling for a - * return message from the PF - */ - hw->mbx.v2p_mailbox |= IXGBE_VFMAILBOX_PFSTS; + ixgbevf_write_eitr(q_vector); } - - /* - * 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; - - return IRQ_HANDLED; } -static irqreturn_t ixgbevf_msix_clean_tx(int irq, void *data) +static irqreturn_t ixgbevf_msix_other(int irq, void *data) { - struct ixgbevf_q_vector *q_vector = data; - struct ixgbevf_adapter *adapter = q_vector->adapter; - struct ixgbevf_ring *tx_ring; - int i, r_idx; + struct ixgbevf_adapter *adapter = data; + struct ixgbe_hw *hw = &adapter->hw; - if (!q_vector->txr_count) - return IRQ_HANDLED; + hw->mac.get_link_status = 1; - r_idx = find_first_bit(q_vector->txr_idx, adapter->num_tx_queues); - for (i = 0; i < q_vector->txr_count; i++) { - tx_ring = &(adapter->tx_ring[r_idx]); - tx_ring->total_bytes = 0; - tx_ring->total_packets = 0; - ixgbevf_clean_tx_irq(adapter, tx_ring); - r_idx = find_next_bit(q_vector->txr_idx, adapter->num_tx_queues, - r_idx + 1); - } + if (!test_bit(__IXGBEVF_DOWN, &adapter->state) && + !test_bit(__IXGBEVF_REMOVING, &adapter->state)) + mod_timer(&adapter->watchdog_timer, jiffies); - if (adapter->itr_setting & 1) - ixgbevf_set_itr_msix(q_vector); + IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, adapter->eims_other); return IRQ_HANDLED; } /** - * ixgbevf_msix_clean_rx - single unshared vector rx clean (all queues) + * ixgbevf_msix_clean_rings - single unshared vector rx clean (all queues) * @irq: unused * @data: pointer to our q_vector struct for this interrupt vector **/ -static irqreturn_t ixgbevf_msix_clean_rx(int irq, void *data) +static irqreturn_t ixgbevf_msix_clean_rings(int irq, void *data) { struct ixgbevf_q_vector *q_vector = data; - struct ixgbevf_adapter *adapter = q_vector->adapter; - struct ixgbe_hw *hw = &adapter->hw; - struct ixgbevf_ring *rx_ring; - int r_idx; - int i; - - r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues); - for (i = 0; i < q_vector->rxr_count; i++) { - rx_ring = &(adapter->rx_ring[r_idx]); - rx_ring->total_bytes = 0; - rx_ring->total_packets = 0; - r_idx = find_next_bit(q_vector->rxr_idx, adapter->num_rx_queues, - r_idx + 1); - } - - if (!q_vector->rxr_count) - return IRQ_HANDLED; - - r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues); - rx_ring = &(adapter->rx_ring[r_idx]); - /* disable interrupts on this vector only */ - IXGBE_WRITE_REG(hw, IXGBE_VTEIMC, rx_ring->v_idx); - napi_schedule(&q_vector->napi); - - return IRQ_HANDLED; -} - -static irqreturn_t ixgbevf_msix_clean_many(int irq, void *data) -{ - ixgbevf_msix_clean_rx(irq, data); - ixgbevf_msix_clean_tx(irq, data); + /* EIAM disabled interrupts (on this vector) for us */ + if (q_vector->rx.ring || q_vector->tx.ring) + napi_schedule(&q_vector->napi); return IRQ_HANDLED; } @@ -1028,9 +908,9 @@ static inline void map_vector_to_rxq(struct ixgbevf_adapter *a, int v_idx, { struct ixgbevf_q_vector *q_vector = a->q_vector[v_idx]; - set_bit(r_idx, q_vector->rxr_idx); - q_vector->rxr_count++; - a->rx_ring[r_idx].v_idx = 1 << v_idx; + a->rx_ring[r_idx]->next = q_vector->rx.ring; + q_vector->rx.ring = a->rx_ring[r_idx]; + q_vector->rx.count++; } static inline void map_vector_to_txq(struct ixgbevf_adapter *a, int v_idx, @@ -1038,9 +918,9 @@ static inline void map_vector_to_txq(struct ixgbevf_adapter *a, int v_idx, { struct ixgbevf_q_vector *q_vector = a->q_vector[v_idx]; - set_bit(t_idx, q_vector->txr_idx); - q_vector->txr_count++; - a->tx_ring[t_idx].v_idx = 1 << v_idx; + a->tx_ring[t_idx]->next = q_vector->tx.ring; + q_vector->tx.ring = a->tx_ring[t_idx]; + q_vector->tx.count++; } /** @@ -1116,37 +996,30 @@ out: static int ixgbevf_request_msix_irqs(struct ixgbevf_adapter *adapter) { struct net_device *netdev = adapter->netdev; - irqreturn_t (*handler)(int, void *); - int i, vector, q_vectors, err; + int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; + int vector, err; int ri = 0, ti = 0; - /* Decrement for Other and TCP Timer vectors */ - q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - -#define SET_HANDLER(_v) (((_v)->rxr_count && (_v)->txr_count) \ - ? &ixgbevf_msix_clean_many : \ - (_v)->rxr_count ? &ixgbevf_msix_clean_rx : \ - (_v)->txr_count ? &ixgbevf_msix_clean_tx : \ - NULL) for (vector = 0; vector < q_vectors; vector++) { - handler = SET_HANDLER(adapter->q_vector[vector]); - - if (handler == &ixgbevf_msix_clean_rx) { - sprintf(adapter->name[vector], "%s-%s-%d", - netdev->name, "rx", ri++); - } else if (handler == &ixgbevf_msix_clean_tx) { - sprintf(adapter->name[vector], "%s-%s-%d", - netdev->name, "tx", ti++); - } else if (handler == &ixgbevf_msix_clean_many) { - sprintf(adapter->name[vector], "%s-%s-%d", - netdev->name, "TxRx", vector); + struct ixgbevf_q_vector *q_vector = adapter->q_vector[vector]; + struct msix_entry *entry = &adapter->msix_entries[vector]; + + if (q_vector->tx.ring && q_vector->rx.ring) { + snprintf(q_vector->name, sizeof(q_vector->name) - 1, + "%s-%s-%d", netdev->name, "TxRx", ri++); + ti++; + } else if (q_vector->rx.ring) { + snprintf(q_vector->name, sizeof(q_vector->name) - 1, + "%s-%s-%d", netdev->name, "rx", ri++); + } else if (q_vector->tx.ring) { + snprintf(q_vector->name, sizeof(q_vector->name) - 1, + "%s-%s-%d", netdev->name, "tx", ti++); } else { /* skip this unused q_vector */ continue; } - err = request_irq(adapter->msix_entries[vector].vector, - handler, 0, adapter->name[vector], - adapter->q_vector[vector]); + err = request_irq(entry->vector, &ixgbevf_msix_clean_rings, 0, + q_vector->name, q_vector); if (err) { hw_dbg(&adapter->hw, "request_irq failed for MSIX interrupt " @@ -1155,24 +1028,33 @@ static int ixgbevf_request_msix_irqs(struct ixgbevf_adapter *adapter) } } - sprintf(adapter->name[vector], "%s:mbx", netdev->name); err = request_irq(adapter->msix_entries[vector].vector, - &ixgbevf_msix_mbx, 0, adapter->name[vector], netdev); + &ixgbevf_msix_other, 0, netdev->name, adapter); if (err) { hw_dbg(&adapter->hw, - "request_irq for msix_mbx failed: %d\n", err); + "request_irq for msix_other failed: %d\n", err); goto free_queue_irqs; } return 0; free_queue_irqs: - for (i = vector - 1; i >= 0; i--) - free_irq(adapter->msix_entries[--vector].vector, - &(adapter->q_vector[i])); - pci_disable_msix(adapter->pdev); - kfree(adapter->msix_entries); - adapter->msix_entries = NULL; + while (vector) { + vector--; + free_irq(adapter->msix_entries[vector].vector, + adapter->q_vector[vector]); + } + /* This failure is non-recoverable - it indicates the system is + * out of MSIX vector resources and the VF driver cannot run + * without them. Set the number of msix vectors to zero + * indicating that not enough can be allocated. The error + * will be returned to the user indicating device open failed. + * Any further attempts to force the driver to open will also + * fail. The only way to recover is to unload the driver and + * reload it again. If the system has recovered some MSIX + * vectors then it may succeed. + */ + adapter->num_msix_vectors = 0; return err; } @@ -1182,11 +1064,10 @@ static inline void ixgbevf_reset_q_vectors(struct ixgbevf_adapter *adapter) for (i = 0; i < q_vectors; i++) { struct ixgbevf_q_vector *q_vector = adapter->q_vector[i]; - bitmap_zero(q_vector->rxr_idx, MAX_RX_QUEUES); - bitmap_zero(q_vector->txr_idx, MAX_TX_QUEUES); - q_vector->rxr_count = 0; - q_vector->txr_count = 0; - q_vector->eitr = adapter->eitr_param; + q_vector->rx.ring = NULL; + q_vector->tx.ring = NULL; + q_vector->rx.count = 0; + q_vector->tx.count = 0; } } @@ -1212,17 +1093,20 @@ static int ixgbevf_request_irq(struct ixgbevf_adapter *adapter) static void ixgbevf_free_irq(struct ixgbevf_adapter *adapter) { - struct net_device *netdev = adapter->netdev; int i, q_vectors; q_vectors = adapter->num_msix_vectors; - i = q_vectors - 1; - free_irq(adapter->msix_entries[i].vector, netdev); + free_irq(adapter->msix_entries[i].vector, adapter); i--; for (; i >= 0; i--) { + /* free only the irqs that were actually requested */ + if (!adapter->q_vector[i]->rx.ring && + !adapter->q_vector[i]->tx.ring) + continue; + free_irq(adapter->msix_entries[i].vector, adapter->q_vector[i]); } @@ -1236,10 +1120,12 @@ static void ixgbevf_free_irq(struct ixgbevf_adapter *adapter) **/ static inline void ixgbevf_irq_disable(struct ixgbevf_adapter *adapter) { - int i; struct ixgbe_hw *hw = &adapter->hw; + int i; + IXGBE_WRITE_REG(hw, IXGBE_VTEIAM, 0); IXGBE_WRITE_REG(hw, IXGBE_VTEIMC, ~0); + IXGBE_WRITE_REG(hw, IXGBE_VTEIAC, 0); IXGBE_WRITE_FLUSH(hw); @@ -1251,23 +1137,77 @@ static inline void ixgbevf_irq_disable(struct ixgbevf_adapter *adapter) * ixgbevf_irq_enable - Enable default interrupt generation settings * @adapter: board private structure **/ -static inline void ixgbevf_irq_enable(struct ixgbevf_adapter *adapter, - bool queues, bool flush) +static inline void ixgbevf_irq_enable(struct ixgbevf_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + + IXGBE_WRITE_REG(hw, IXGBE_VTEIAM, adapter->eims_enable_mask); + IXGBE_WRITE_REG(hw, IXGBE_VTEIAC, adapter->eims_enable_mask); + IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, adapter->eims_enable_mask); +} + +/** + * 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; - u32 mask; - u64 qmask; + 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)); - mask = (IXGBE_EIMS_ENABLE_MASK & ~IXGBE_EIMS_RTX_QUEUE); - qmask = ~0; + /* disable head writeback */ + IXGBE_WRITE_REG(hw, IXGBE_VFTDWBAH(reg_idx), 0); + IXGBE_WRITE_REG(hw, IXGBE_VFTDWBAL(reg_idx), 0); - IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, mask); + /* enable relaxed ordering */ + IXGBE_WRITE_REG(hw, IXGBE_VFDCA_TXCTRL(reg_idx), + (IXGBE_DCA_TXCTRL_DESC_RRO_EN | + IXGBE_DCA_TXCTRL_DATA_RRO_EN)); - if (queues) - ixgbevf_irq_enable_queues(adapter, qmask); + /* 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); - if (flush) - IXGBE_WRITE_FLUSH(hw); + /* 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 */ + + 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); } /** @@ -1278,31 +1218,11 @@ static inline void ixgbevf_irq_enable(struct ixgbevf_adapter *adapter, **/ 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 @@ -1313,36 +1233,157 @@ static void ixgbevf_configure_srrctl(struct ixgbevf_adapter *adapter, int index) struct ixgbe_hw *hw = &adapter->hw; u32 srrctl; - rx_ring = &adapter->rx_ring[index]; + rx_ring = adapter->rx_ring[index]; srrctl = IXGBE_SRRCTL_DROP_EN; - if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) { - u16 bufsz = IXGBEVF_RXBUFFER_2048; - /* grow the amount we can receive on large page machines */ - if (bufsz < (PAGE_SIZE / 2)) - bufsz = (PAGE_SIZE / 2); - /* cap the bufsz at our largest descriptor size */ - bufsz = min((u16)IXGBEVF_MAX_RXBUFFER, bufsz); - - srrctl |= bufsz >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; - srrctl |= IXGBE_SRRCTL_DESCTYPE_HDR_SPLIT_ALWAYS; - srrctl |= ((IXGBEVF_RX_HDR_SIZE << - IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT) & - IXGBE_SRRCTL_BSIZEHDR_MASK); - } else { - srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF; + srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF; + + srrctl |= ALIGN(rx_ring->rx_buf_len, 1024) >> + IXGBE_SRRCTL_BSIZEPKT_SHIFT; - if (rx_ring->rx_buf_len == MAXIMUM_ETHERNET_VLAN_SIZE) - srrctl |= IXGBEVF_RXBUFFER_2048 >> - IXGBE_SRRCTL_BSIZEPKT_SHIFT; - else - srrctl |= rx_ring->rx_buf_len >> - IXGBE_SRRCTL_BSIZEPKT_SHIFT; - } IXGBE_WRITE_REG(hw, IXGBE_VFSRRCTL(index), srrctl); } +static void ixgbevf_setup_psrtype(struct ixgbevf_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + + /* PSRTYPE must be initialized in 82599 */ + u32 psrtype = IXGBE_PSRTYPE_TCPHDR | IXGBE_PSRTYPE_UDPHDR | + IXGBE_PSRTYPE_IPV4HDR | IXGBE_PSRTYPE_IPV6HDR | + IXGBE_PSRTYPE_L2HDR; + + if (adapter->num_rx_queues > 1) + psrtype |= 1 << 29; + + IXGBE_WRITE_REG(hw, IXGBE_VFPSRTYPE, psrtype); +} + +static void ixgbevf_set_rx_buffer_len(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); + + /* PF will allow an extra 4 bytes past for vlan tagged frames */ + max_frame += VLAN_HLEN; + + /* + * 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; + + 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_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; + + ixgbevf_configure_srrctl(adapter, reg_idx); + + /* prevent DMA from exceeding buffer space available */ + rxdctl &= ~IXGBE_RXDCTL_RLPMLMASK; + rxdctl |= ring->rx_buf_len | 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)); +} + /** * ixgbevf_configure_rx - Configure 82599 VF Receive Unit after Reset * @adapter: board private structure @@ -1351,89 +1392,62 @@ static void ixgbevf_configure_srrctl(struct ixgbevf_adapter *adapter, int index) **/ static void ixgbevf_configure_rx(struct ixgbevf_adapter *adapter) { - u64 rdba; - struct ixgbe_hw *hw = &adapter->hw; - struct net_device *netdev = adapter->netdev; - int max_frame = netdev->mtu + ETH_HLEN + ETH_FCS_LEN; - int i, j; - u32 rdlen; - int rx_buf_len; + int i; - /* Decide whether to use packet split mode or not */ - if (netdev->mtu > ETH_DATA_LEN) { - if (adapter->flags & IXGBE_FLAG_RX_PS_CAPABLE) - adapter->flags |= IXGBE_FLAG_RX_PS_ENABLED; - else - adapter->flags &= ~IXGBE_FLAG_RX_PS_ENABLED; - } else { - if (adapter->flags & IXGBE_FLAG_RX_1BUF_CAPABLE) - adapter->flags &= ~IXGBE_FLAG_RX_PS_ENABLED; - else - adapter->flags |= IXGBE_FLAG_RX_PS_ENABLED; - } - - /* Set the RX buffer length according to the mode */ - if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) { - /* PSRTYPE must be initialized in 82599 */ - u32 psrtype = IXGBE_PSRTYPE_TCPHDR | - IXGBE_PSRTYPE_UDPHDR | - IXGBE_PSRTYPE_IPV4HDR | - IXGBE_PSRTYPE_IPV6HDR | - IXGBE_PSRTYPE_L2HDR; - IXGBE_WRITE_REG(hw, IXGBE_VFPSRTYPE, psrtype); - rx_buf_len = IXGBEVF_RX_HDR_SIZE; - } else { - IXGBE_WRITE_REG(hw, IXGBE_VFPSRTYPE, 0); - if (netdev->mtu <= ETH_DATA_LEN) - rx_buf_len = MAXIMUM_ETHERNET_VLAN_SIZE; - else - rx_buf_len = ALIGN(max_frame, 1024); - } + ixgbevf_setup_psrtype(adapter); + + /* set_rx_buffer_len must be called before ring initialization */ + ixgbevf_set_rx_buffer_len(adapter); - 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); - adapter->rx_ring[i].rx_buf_len = rx_buf_len; - - ixgbevf_configure_srrctl(adapter, j); - } + 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, u16 vid) +static int ixgbevf_vlan_rx_add_vid(struct net_device *netdev, + __be16 proto, u16 vid) { struct ixgbevf_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; + int err; + + spin_lock_bh(&adapter->mbx_lock); /* add VID to filter table */ - if (hw->mac.ops.set_vfta) - hw->mac.ops.set_vfta(hw, vid, 0, true); + err = hw->mac.ops.set_vfta(hw, vid, 0, true); + + spin_unlock_bh(&adapter->mbx_lock); + + /* translate error return types so error makes sense */ + if (err == IXGBE_ERR_MBX) + return -EIO; + + if (err == IXGBE_ERR_INVALID_ARGUMENT) + return -EACCES; + set_bit(vid, adapter->active_vlans); - return 0; + return err; } -static int ixgbevf_vlan_rx_kill_vid(struct net_device *netdev, u16 vid) +static int ixgbevf_vlan_rx_kill_vid(struct net_device *netdev, + __be16 proto, u16 vid) { struct ixgbevf_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; + int err = -EOPNOTSUPP; + + spin_lock_bh(&adapter->mbx_lock); /* remove VID from filter table */ - if (hw->mac.ops.set_vfta) - hw->mac.ops.set_vfta(hw, vid, 0, false); + err = hw->mac.ops.set_vfta(hw, vid, 0, false); + + spin_unlock_bh(&adapter->mbx_lock); + clear_bit(vid, adapter->active_vlans); - return 0; + return err; } static void ixgbevf_restore_vlan(struct ixgbevf_adapter *adapter) @@ -1441,7 +1455,8 @@ static void ixgbevf_restore_vlan(struct ixgbevf_adapter *adapter) u16 vid; for_each_set_bit(vid, adapter->active_vlans, VLAN_N_VID) - ixgbevf_vlan_rx_add_vid(adapter->netdev, vid); + ixgbevf_vlan_rx_add_vid(adapter->netdev, + htons(ETH_P_8021Q), vid); } static int ixgbevf_write_uc_addr_list(struct net_device *netdev) @@ -1473,23 +1488,27 @@ static int ixgbevf_write_uc_addr_list(struct net_device *netdev) } /** - * ixgbevf_set_rx_mode - Multicast set + * ixgbevf_set_rx_mode - Multicast and unicast set * @netdev: network interface device structure * * The set_rx_method entry point is called whenever the multicast address - * list or the network interface flags are updated. This routine is - * responsible for configuring the hardware for proper multicast mode. + * list, unicast address list or the network interface flags are updated. + * This routine is responsible for configuring the hardware for proper + * multicast mode and configuring requested unicast filters. **/ static void ixgbevf_set_rx_mode(struct net_device *netdev) { struct ixgbevf_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; + spin_lock_bh(&adapter->mbx_lock); + /* reprogram multicast list */ - if (hw->mac.ops.update_mc_addr_list) - hw->mac.ops.update_mc_addr_list(hw, netdev); + hw->mac.ops.update_mc_addr_list(hw, netdev); ixgbevf_write_uc_addr_list(netdev); + + spin_unlock_bh(&adapter->mbx_lock); } static void ixgbevf_napi_enable_all(struct ixgbevf_adapter *adapter) @@ -1499,15 +1518,11 @@ static void ixgbevf_napi_enable_all(struct ixgbevf_adapter *adapter) int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; for (q_idx = 0; q_idx < q_vectors; q_idx++) { - struct napi_struct *napi; q_vector = adapter->q_vector[q_idx]; - if (!q_vector->rxr_count) - continue; - napi = &q_vector->napi; - if (q_vector->rxr_count > 1) - napi->poll = &ixgbevf_clean_rxonly_many; - - napi_enable(napi); +#ifdef CONFIG_NET_RX_BUSY_POLL + ixgbevf_qv_init_lock(adapter->q_vector[q_idx]); +#endif + napi_enable(&q_vector->napi); } } @@ -1519,52 +1534,64 @@ static void ixgbevf_napi_disable_all(struct ixgbevf_adapter *adapter) for (q_idx = 0; q_idx < q_vectors; q_idx++) { q_vector = adapter->q_vector[q_idx]; - if (!q_vector->rxr_count) - continue; napi_disable(&q_vector->napi); +#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 = 1; + 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, ring->count); - ring->next_to_use = ring->count - 1; - writel(ring->next_to_use, adapter->hw.hw_addr + ring->tail); + 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; + } + + /* if we have a bad config abort request queue reset */ + if (adapter->num_rx_queues != num_rx_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_restore_vlan(adapter); - ixgbevf_release_rx_desc(&adapter->hw, &adapter->rx_ring[rxr], - (adapter->rx_ring[rxr].count - 1)); + ixgbevf_configure_tx(adapter); + ixgbevf_configure_rx(adapter); } static void ixgbevf_save_reset_stats(struct ixgbevf_adapter *adapter) @@ -1605,51 +1632,43 @@ static void ixgbevf_init_last_counter_stats(struct ixgbevf_adapter *adapter) adapter->stats.base_vfmprc = adapter->stats.last_vfmprc; } -static int ixgbevf_up_complete(struct ixgbevf_adapter *adapter) +static void ixgbevf_negotiate_api(struct ixgbevf_adapter *adapter) { - 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; + int api[] = { ixgbe_mbox_api_11, + ixgbe_mbox_api_10, + ixgbe_mbox_api_unknown }; + int err = 0, idx = 0; - 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); - } + spin_lock_bh(&adapter->mbx_lock); - 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); + while (api[idx] != ixgbe_mbox_api_unknown) { + err = ixgbevf_negotiate_api_version(hw, api[idx]); + if (!err) + break; + idx++; } + spin_unlock_bh(&adapter->mbx_lock); +} + +static void ixgbevf_up_complete(struct ixgbevf_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct ixgbe_hw *hw = &adapter->hw; + ixgbevf_configure_msix(adapter); - if (hw->mac.ops.set_rar) { - if (is_valid_ether_addr(hw->mac.addr)) - hw->mac.ops.set_rar(hw, 0, hw->mac.addr, 0); - else - hw->mac.ops.set_rar(hw, 0, hw->mac.perm_addr, 0); - } + spin_lock_bh(&adapter->mbx_lock); + + if (is_valid_ether_addr(hw->mac.addr)) + hw->mac.ops.set_rar(hw, 0, hw->mac.addr, 0); + else + hw->mac.ops.set_rar(hw, 0, hw->mac.perm_addr, 0); + + spin_unlock_bh(&adapter->mbx_lock); + smp_mb__before_atomic(); clear_bit(__IXGBEVF_DOWN, &adapter->state); ixgbevf_napi_enable_all(adapter); @@ -1659,40 +1678,30 @@ static int ixgbevf_up_complete(struct ixgbevf_adapter *adapter) ixgbevf_save_reset_stats(adapter); ixgbevf_init_last_counter_stats(adapter); - /* bring the link up in the watchdog, this could race with our first - * link up interrupt but shouldn't be a problem */ - adapter->flags |= IXGBE_FLAG_NEED_LINK_UPDATE; - adapter->link_check_timeout = jiffies; + hw->mac.get_link_status = 1; mod_timer(&adapter->watchdog_timer, jiffies); - return 0; } -int ixgbevf_up(struct ixgbevf_adapter *adapter) +void ixgbevf_up(struct ixgbevf_adapter *adapter) { - int err; struct ixgbe_hw *hw = &adapter->hw; ixgbevf_configure(adapter); - err = ixgbevf_up_complete(adapter); + ixgbevf_up_complete(adapter); /* clear any pending interrupts, may auto mask */ IXGBE_READ_REG(hw, IXGBE_VTEICR); - ixgbevf_irq_enable(adapter, true, true); - - return err; + 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; unsigned long size; unsigned int i; @@ -1705,7 +1714,7 @@ static void ixgbevf_clean_rx_ring(struct ixgbevf_adapter *adapter, rx_buffer_info = &rx_ring->rx_buffer_info[i]; if (rx_buffer_info->dma) { - dma_unmap_single(&pdev->dev, rx_buffer_info->dma, + dma_unmap_single(rx_ring->dev, rx_buffer_info->dma, rx_ring->rx_buf_len, DMA_FROM_DEVICE); rx_buffer_info->dma = 0; @@ -1715,18 +1724,10 @@ static void ixgbevf_clean_rx_ring(struct ixgbevf_adapter *adapter, rx_buffer_info->skb = NULL; do { struct sk_buff *this = skb; - skb = skb->prev; + skb = IXGBE_CB(skb)->prev; dev_kfree_skb(this); } while (skb); } - if (!rx_buffer_info->page) - continue; - dma_unmap_page(&pdev->dev, rx_buffer_info->page_dma, - PAGE_SIZE / 2, DMA_FROM_DEVICE); - rx_buffer_info->page_dma = 0; - put_page(rx_buffer_info->page); - rx_buffer_info->page = NULL; - rx_buffer_info->page_offset = 0; } size = sizeof(struct ixgbevf_rx_buffer) * rx_ring->count; @@ -1734,23 +1735,13 @@ static void ixgbevf_clean_rx_ring(struct ixgbevf_adapter *adapter, /* 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; @@ -1760,24 +1751,15 @@ static void ixgbevf_clean_tx_ring(struct ixgbevf_adapter *adapter, return; /* Free all the Tx ring sk_buffs */ - for (i = 0; i < tx_ring->count; i++) { tx_buffer_info = &tx_ring->tx_buffer_info[i]; - ixgbevf_unmap_and_free_tx_resource(adapter, tx_buffer_info); + ixgbevf_unmap_and_free_tx_resource(tx_ring, tx_buffer_info); } size = sizeof(struct ixgbevf_tx_buffer) * tx_ring->count; 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); } /** @@ -1789,7 +1771,7 @@ static void ixgbevf_clean_all_rx_rings(struct ixgbevf_adapter *adapter) 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]); } /** @@ -1801,19 +1783,22 @@ static void ixgbevf_clean_all_tx_rings(struct ixgbevf_adapter *adapter) 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 */ + + /* disable all enabled rx queues */ + for (i = 0; i < adapter->num_rx_queues; i++) + ixgbevf_disable_rx_queue(adapter, adapter->rx_ring[i]); netif_tx_disable(netdev); @@ -1834,10 +1819,10 @@ void ixgbevf_down(struct ixgbevf_adapter *adapter) /* 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; + + IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(reg_idx), + IXGBE_TXDCTL_SWFLSH); } netif_carrier_off(netdev); @@ -1851,24 +1836,13 @@ void ixgbevf_down(struct ixgbevf_adapter *adapter) void ixgbevf_reinit_locked(struct ixgbevf_adapter *adapter) { - struct ixgbe_hw *hw = &adapter->hw; - WARN_ON(in_interrupt()); while (test_and_set_bit(__IXGBEVF_RESETTING, &adapter->state)) msleep(1); - /* - * Check if PF is up before re-init. If not then skip until - * later when the PF is up and ready to service requests from - * the VF via mailbox. If the VF is up and running then the - * watchdog task will continue to schedule reset tasks until - * the PF is up and running. - */ - if (!hw->mac.ops.reset_hw(hw)) { - ixgbevf_down(adapter); - ixgbevf_up(adapter); - } + ixgbevf_down(adapter); + ixgbevf_up(adapter); clear_bit(__IXGBEVF_RESETTING, &adapter->state); } @@ -1878,10 +1852,12 @@ void ixgbevf_reset(struct ixgbevf_adapter *adapter) 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, @@ -1891,15 +1867,14 @@ void ixgbevf_reset(struct ixgbevf_adapter *adapter) } } -static void ixgbevf_acquire_msix_vectors(struct ixgbevf_adapter *adapter, - int vectors) +static int ixgbevf_acquire_msix_vectors(struct ixgbevf_adapter *adapter, + int vectors) { - int err, vector_threshold; + int vector_threshold; - /* We'll want at least 3 (vector_threshold): - * 1) TxQ[0] Cleanup - * 2) RxQ[0] Cleanup - * 3) Other (Link Status Change, etc.) + /* We'll want at least 2 (vector_threshold): + * 1) TxQ[0] + RxQ[0] handler + * 2) Other (Link Status Change, etc.) */ vector_threshold = MIN_MSIX_COUNT; @@ -1908,38 +1883,28 @@ static void ixgbevf_acquire_msix_vectors(struct ixgbevf_adapter *adapter, * 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) /* Success in acquiring all requested vectors. */ - break; - else if (err < 0) - vectors = 0; /* Nasty failure, quit now */ - 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) { - /* Can't allocate enough MSI-X interrupts? Oh well. - * This just means we'll go with either a single MSI - * vector or fall back to legacy interrupts. - */ - hw_dbg(&adapter->hw, - "Unable to allocate MSI-X interrupts\n"); + 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; } + + /* 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; } -/* - * ixgbevf_set_num_queues: Allocate queues for device, feature dependent +/** + * ixgbevf_set_num_queues - Allocate queues for device, feature dependent * @adapter: board private structure to initialize * * This is the top level queue allocation routine. The order here is very @@ -1951,11 +1916,28 @@ static void ixgbevf_acquire_msix_vectors(struct ixgbevf_adapter *adapter, **/ 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; - adapter->num_rx_pools = adapter->num_rx_queues; - adapter->num_rx_queues_per_pool = 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; } /** @@ -1968,35 +1950,50 @@ static void ixgbevf_set_num_queues(struct ixgbevf_adapter *adapter) **/ 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; + for (; tx < adapter->num_tx_queues; tx++) { + ring = kzalloc(sizeof(*ring), GFP_KERNEL); + if (!ring) + goto err_allocation; - adapter->rx_ring = kcalloc(adapter->num_rx_queues, - sizeof(struct ixgbevf_ring), GFP_KERNEL); - if (!adapter->rx_ring) - goto err_rx_ring_allocation; + ring->dev = &adapter->pdev->dev; + ring->netdev = adapter->netdev; + ring->count = adapter->tx_ring_count; + ring->queue_index = tx; + ring->reg_idx = tx; - 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; - adapter->tx_ring[i].reg_idx = i; + 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; + 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; } @@ -2009,6 +2006,7 @@ err_tx_ring_allocation: **/ static int ixgbevf_set_interrupt_capability(struct ixgbevf_adapter *adapter) { + struct net_device *netdev = adapter->netdev; int err = 0; int vector, v_budget; @@ -2016,10 +2014,12 @@ static int ixgbevf_set_interrupt_capability(struct ixgbevf_adapter *adapter) * It's easy to be greedy for MSI-X vectors, but it really * doesn't do us much good if we have a lot more vectors * than CPU's. So let's be conservative and only ask for - * (roughly) twice the number of vectors as there are CPU's. + * (roughly) the same number of vectors as there are CPU's. + * The default is to use pairs of vectors. */ - v_budget = min(adapter->num_rx_queues + adapter->num_tx_queues, - (int)(num_online_cpus() * 2)) + NON_Q_VECTORS; + v_budget = max(adapter->num_rx_queues, adapter->num_tx_queues); + v_budget = min_t(int, v_budget, num_online_cpus()); + v_budget += NON_Q_VECTORS; /* A failure in MSI-X entry allocation isn't fatal, but it does * mean we disable MSI-X capabilities of the adapter. */ @@ -2033,7 +2033,15 @@ static int ixgbevf_set_interrupt_capability(struct ixgbevf_adapter *adapter) for (vector = 0; vector < v_budget; vector++) adapter->msix_entries[vector].entry = vector; - ixgbevf_acquire_msix_vectors(adapter, v_budget); + err = ixgbevf_acquire_msix_vectors(adapter, v_budget); + if (err) + goto out; + + err = netif_set_real_num_tx_queues(netdev, adapter->num_tx_queues); + if (err) + goto out; + + err = netif_set_real_num_rx_queues(netdev, adapter->num_rx_queues); out: return err; @@ -2050,12 +2058,8 @@ static int ixgbevf_alloc_q_vectors(struct ixgbevf_adapter *adapter) { int q_idx, num_q_vectors; struct ixgbevf_q_vector *q_vector; - int napi_vectors; - int (*poll)(struct napi_struct *, int); num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - napi_vectors = adapter->num_rx_queues; - poll = &ixgbevf_clean_rxonly; for (q_idx = 0; q_idx < num_q_vectors; q_idx++) { q_vector = kzalloc(sizeof(struct ixgbevf_q_vector), GFP_KERNEL); @@ -2063,10 +2067,11 @@ static int ixgbevf_alloc_q_vectors(struct ixgbevf_adapter *adapter) goto err_out; q_vector->adapter = adapter; q_vector->v_idx = q_idx; - q_vector->eitr = adapter->eitr_param; - if (q_idx < napi_vectors) - netif_napi_add(adapter->netdev, &q_vector->napi, - (*poll), 64); + netif_napi_add(adapter->netdev, &q_vector->napi, + ixgbevf_poll, 64); +#ifdef CONFIG_NET_RX_BUSY_POLL + napi_hash_add(&q_vector->napi); +#endif adapter->q_vector[q_idx] = q_vector; } @@ -2076,6 +2081,9 @@ err_out: 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; @@ -2093,18 +2101,16 @@ err_out: **/ static void ixgbevf_free_q_vectors(struct ixgbevf_adapter *adapter) { - int q_idx, num_q_vectors; - int napi_vectors; - - num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - napi_vectors = adapter->num_rx_queues; + int q_idx, num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; for (q_idx = 0; q_idx < num_q_vectors; q_idx++) { struct ixgbevf_q_vector *q_vector = adapter->q_vector[q_idx]; adapter->q_vector[q_idx] = NULL; - if (q_idx < napi_vectors) - netif_napi_del(&q_vector->napi); +#ifdef CONFIG_NET_RX_BUSY_POLL + napi_hash_del(&q_vector->napi); +#endif + netif_napi_del(&q_vector->napi); kfree(q_vector); } } @@ -2170,6 +2176,33 @@ err_set_interrupt: } /** + * ixgbevf_clear_interrupt_scheme - Clear the current interrupt scheme settings + * @adapter: board private structure to clear interrupt scheme on + * + * We go through and clear interrupt specific resources and reset the structure + * to pre-load conditions + **/ +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; + + ixgbevf_free_q_vectors(adapter); + ixgbevf_reset_interrupt_capability(adapter); +} + +/** * ixgbevf_sw_init - Initialize general software structures * (struct ixgbevf_adapter) * @adapter: board private structure to initialize @@ -2178,10 +2211,11 @@ err_set_interrupt: * Fields are initialized based on PCI device information and * OS network device settings (MTU size). **/ -static int __devinit ixgbevf_sw_init(struct ixgbevf_adapter *adapter) +static int ixgbevf_sw_init(struct ixgbevf_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; struct pci_dev *pdev = adapter->pdev; + struct net_device *netdev = adapter->netdev; int err; /* PCI config space info */ @@ -2193,37 +2227,50 @@ static int __devinit ixgbevf_sw_init(struct ixgbevf_adapter *adapter) hw->subsystem_device_id = pdev->subsystem_device; hw->mbx.ops.init_params(hw); - hw->mac.max_tx_queues = MAX_TX_QUEUES; - hw->mac.max_rx_queues = MAX_RX_QUEUES; + + /* assume legacy case in which PF would only give VF 2 queues */ + 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, - "PF still in reset state, assigning new address\n"); - dev_hw_addr_random(adapter->netdev, hw->mac.addr); + "PF still in reset state. Is the PF interface up?\n"); } else { err = hw->mac.ops.init_hw(hw); if (err) { 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"); + else if (is_zero_ether_addr(adapter->hw.mac.addr)) + dev_info(&pdev->dev, + "MAC address not assigned by administrator.\n"); + memcpy(netdev->dev_addr, hw->mac.addr, netdev->addr_len); } - /* Enable dynamic interrupt throttling rates */ - adapter->eitr_param = 20000; - adapter->itr_setting = 1; + if (!is_valid_ether_addr(netdev->dev_addr)) { + dev_info(&pdev->dev, "Assigning random MAC address\n"); + eth_hw_addr_random(netdev); + memcpy(hw->mac.addr, netdev->dev_addr, netdev->addr_len); + } - /* set defaults for eitr in MegaBytes */ - adapter->eitr_low = 10; - adapter->eitr_high = 20; + /* Enable dynamic interrupt throttling rates */ + adapter->rx_itr_setting = 1; + adapter->tx_itr_setting = 1; /* set default ring sizes */ adapter->tx_ring_count = IXGBEVF_DEFAULT_TXD; adapter->rx_ring_count = IXGBEVF_DEFAULT_RXD; - /* enable rx csum by default */ - adapter->flags |= IXGBE_FLAG_RX_CSUM_ENABLED; - set_bit(__IXGBEVF_DOWN, &adapter->state); + return 0; out: return err; @@ -2258,6 +2305,10 @@ out: void ixgbevf_update_stats(struct ixgbevf_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; + int i; + + if (!adapter->link_up) + return; UPDATE_VF_COUNTER_32bit(IXGBE_VFGPRC, adapter->stats.last_vfgprc, adapter->stats.vfgprc); @@ -2271,6 +2322,12 @@ void ixgbevf_update_stats(struct ixgbevf_adapter *adapter) adapter->stats.vfgotc); UPDATE_VF_COUNTER_32bit(IXGBE_VFMPRC, adapter->stats.last_vfmprc, adapter->stats.vfmprc); + + for (i = 0; i < adapter->num_rx_queues; i++) { + adapter->hw_csum_rx_error += + adapter->rx_ring[i]->hw_csum_rx_error; + adapter->rx_ring[i]->hw_csum_rx_error = 0; + } } /** @@ -2281,7 +2338,7 @@ static void ixgbevf_watchdog(unsigned long data) { struct ixgbevf_adapter *adapter = (struct ixgbevf_adapter *)data; struct ixgbe_hw *hw = &adapter->hw; - u64 eics = 0; + u32 eics = 0; int i; /* @@ -2295,11 +2352,11 @@ static void ixgbevf_watchdog(unsigned long data) /* get one bit for every active tx/rx interrupt vector */ for (i = 0; i < adapter->num_msix_vectors - NON_Q_VECTORS; i++) { struct ixgbevf_q_vector *qv = adapter->q_vector[i]; - if (qv->rxr_count || qv->txr_count) - eics |= (1 << i); + if (qv->rx.ring || qv->tx.ring) + eics |= 1 << i; } - IXGBE_WRITE_REG(hw, IXGBE_VTEICS, (u32)eics); + IXGBE_WRITE_REG(hw, IXGBE_VTEICS, eics); watchdog_short_circuit: schedule_work(&adapter->watchdog_task); @@ -2324,6 +2381,7 @@ static void ixgbevf_reset_task(struct work_struct *work) /* If we're already down or resetting, just bail */ if (test_bit(__IXGBEVF_DOWN, &adapter->state) || + test_bit(__IXGBEVF_REMOVING, &adapter->state) || test_bit(__IXGBEVF_RESETTING, &adapter->state)) return; @@ -2345,6 +2403,17 @@ static void ixgbevf_watchdog_task(struct work_struct *work) struct ixgbe_hw *hw = &adapter->hw; u32 link_speed = adapter->link_speed; bool link_up = adapter->link_up; + s32 need_reset; + + if (IXGBE_REMOVED(hw->hw_addr)) { + if (!test_bit(__IXGBEVF_DOWN, &adapter->state)) { + rtnl_lock(); + ixgbevf_down(adapter); + rtnl_unlock(); + } + return; + } + ixgbevf_queue_reset_subtask(adapter); adapter->flags |= IXGBE_FLAG_IN_WATCHDOG_TASK; @@ -2352,30 +2421,42 @@ static void ixgbevf_watchdog_task(struct work_struct *work) * Always check the link on the watchdog because we have * no LSC interrupt */ - if (hw->mac.ops.check_link) { - if ((hw->mac.ops.check_link(hw, &link_speed, - &link_up, false)) != 0) { - 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; - } - } else { - /* always assume link is up, if no check link - * function */ - link_speed = IXGBE_LINK_SPEED_10GB_FULL; - link_up = true; + 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)) { - hw_dbg(&adapter->hw, "NIC Link is Up, %u Gbps\n", - (link_speed == IXGBE_LINK_SPEED_10GB_FULL) ? - 10 : 1); + 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); } @@ -2383,7 +2464,7 @@ static void ixgbevf_watchdog_task(struct work_struct *work) adapter->link_up = false; adapter->link_speed = 0; if (netif_carrier_ok(netdev)) { - hw_dbg(&adapter->hw, "NIC Link is Down\n"); + dev_info(&adapter->pdev->dev, "NIC Link is Down\n"); netif_carrier_off(netdev); netif_tx_stop_all_queues(netdev); } @@ -2393,7 +2474,8 @@ static void ixgbevf_watchdog_task(struct work_struct *work) pf_has_reset: /* Reset the timer */ - if (!test_bit(__IXGBEVF_DOWN, &adapter->state)) + if (!test_bit(__IXGBEVF_DOWN, &adapter->state) && + !test_bit(__IXGBEVF_REMOVING, &adapter->state)) mod_timer(&adapter->watchdog_timer, round_jiffies(jiffies + (2 * HZ))); @@ -2402,22 +2484,22 @@ pf_has_reset: /** * 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; @@ -2434,23 +2516,18 @@ static void ixgbevf_free_all_tx_resources(struct ixgbevf_adapter *adapter) 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 * * 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; @@ -2462,14 +2539,11 @@ int ixgbevf_setup_tx_resources(struct ixgbevf_adapter *adapter, 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; - tx_ring->work_limit = tx_ring->count; return 0; err: @@ -2495,7 +2569,7 @@ static int ixgbevf_setup_all_tx_resources(struct ixgbevf_adapter *adapter) 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, @@ -2508,47 +2582,34 @@ static int ixgbevf_setup_all_tx_resources(struct ixgbevf_adapter *adapter) /** * ixgbevf_setup_rx_resources - allocate Rx resources (Descriptors) - * @adapter: board private structure * @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) { - hw_dbg(&adapter->hw, - "Unable to vmalloc buffer memory for " - "the receive descriptor ring\n"); - goto alloc_failed; - } + if (!rx_ring->rx_buffer_info) + 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) { - hw_dbg(&adapter->hw, - "Unable to allocate memory for " - "the receive descriptor ring\n"); - 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; } @@ -2567,7 +2628,7 @@ static int ixgbevf_setup_all_rx_resources(struct ixgbevf_adapter *adapter) 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, @@ -2579,22 +2640,18 @@ static int ixgbevf_setup_all_rx_resources(struct ixgbevf_adapter *adapter) /** * 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; @@ -2611,9 +2668,8 @@ static void ixgbevf_free_all_rx_resources(struct ixgbevf_adapter *adapter) 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]); + if (adapter->rx_ring[i]->desc) + ixgbevf_free_rx_resources(adapter->rx_ring[i]); } /** @@ -2634,6 +2690,15 @@ static int ixgbevf_open(struct net_device *netdev) struct ixgbe_hw *hw = &adapter->hw; int err; + /* A previous failure to open the device because of a lack of + * available MSIX vector resources may have reset the number + * of msix vectors variable to zero. The only way to recover + * is to unload/reload the driver and hope that the system has + * been able to recover some MSIX vector resources. + */ + if (!adapter->num_msix_vectors) + return -ENOMEM; + /* disallow open during test */ if (test_bit(__IXGBEVF_TESTING, &adapter->state)) return -EBUSY; @@ -2669,9 +2734,7 @@ static int ixgbevf_open(struct net_device *netdev) */ ixgbevf_map_rings_to_vectors(adapter); - err = ixgbevf_up_complete(adapter); - if (err) - goto err_up; + ixgbevf_up_complete(adapter); /* clear any pending interrupts, may auto mask */ IXGBE_READ_REG(hw, IXGBE_VTEICR); @@ -2679,14 +2742,12 @@ static int ixgbevf_open(struct net_device *netdev) if (err) goto err_req_irq; - ixgbevf_irq_enable(adapter, true, true); + ixgbevf_irq_enable(adapter); return 0; err_req_irq: ixgbevf_down(adapter); -err_up: - ixgbevf_free_irq(adapter); err_setup_rx: ixgbevf_free_all_rx_resources(adapter); err_setup_tx: @@ -2722,340 +2783,361 @@ static int ixgbevf_close(struct net_device *netdev) return 0; } -static int ixgbevf_tso(struct ixgbevf_adapter *adapter, - struct ixgbevf_ring *tx_ring, - struct sk_buff *skb, u32 tx_flags, u8 *hdr_len) +static void ixgbevf_queue_reset_subtask(struct ixgbevf_adapter *adapter) { - struct ixgbe_adv_tx_context_desc *context_desc; - unsigned int i; - int err; - struct ixgbevf_tx_buffer *tx_buffer_info; - u32 vlan_macip_lens = 0, type_tucmd_mlhl; - u32 mss_l4len_idx, l4len; + struct net_device *dev = adapter->netdev; - if (skb_is_gso(skb)) { - if (skb_header_cloned(skb)) { - err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); - if (err) - return err; - } - l4len = tcp_hdrlen(skb); - *hdr_len += l4len; - - if (skb->protocol == htons(ETH_P_IP)) { - struct iphdr *iph = ip_hdr(skb); - iph->tot_len = 0; - iph->check = 0; - tcp_hdr(skb)->check = ~csum_tcpudp_magic(iph->saddr, - iph->daddr, 0, - IPPROTO_TCP, - 0); - adapter->hw_tso_ctxt++; - } else if (skb_is_gso_v6(skb)) { - ipv6_hdr(skb)->payload_len = 0; - tcp_hdr(skb)->check = - ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - 0, IPPROTO_TCP, 0); - adapter->hw_tso6_ctxt++; - } + if (!(adapter->flags & IXGBEVF_FLAG_QUEUE_RESET_REQUESTED)) + return; - i = tx_ring->next_to_use; + adapter->flags &= ~IXGBEVF_FLAG_QUEUE_RESET_REQUESTED; - tx_buffer_info = &tx_ring->tx_buffer_info[i]; - context_desc = IXGBE_TX_CTXTDESC_ADV(*tx_ring, i); - - /* VLAN MACLEN IPLEN */ - if (tx_flags & IXGBE_TX_FLAGS_VLAN) - vlan_macip_lens |= - (tx_flags & IXGBE_TX_FLAGS_VLAN_MASK); - vlan_macip_lens |= ((skb_network_offset(skb)) << - IXGBE_ADVTXD_MACLEN_SHIFT); - *hdr_len += skb_network_offset(skb); - vlan_macip_lens |= - (skb_transport_header(skb) - skb_network_header(skb)); - *hdr_len += - (skb_transport_header(skb) - skb_network_header(skb)); - context_desc->vlan_macip_lens = cpu_to_le32(vlan_macip_lens); - context_desc->seqnum_seed = 0; - - /* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */ - type_tucmd_mlhl = (IXGBE_TXD_CMD_DEXT | - IXGBE_ADVTXD_DTYP_CTXT); - - if (skb->protocol == htons(ETH_P_IP)) - type_tucmd_mlhl |= IXGBE_ADVTXD_TUCMD_IPV4; - type_tucmd_mlhl |= IXGBE_ADVTXD_TUCMD_L4T_TCP; - context_desc->type_tucmd_mlhl = cpu_to_le32(type_tucmd_mlhl); - - /* MSS L4LEN IDX */ - mss_l4len_idx = - (skb_shinfo(skb)->gso_size << IXGBE_ADVTXD_MSS_SHIFT); - mss_l4len_idx |= (l4len << IXGBE_ADVTXD_L4LEN_SHIFT); - /* use index 1 for TSO */ - mss_l4len_idx |= (1 << IXGBE_ADVTXD_IDX_SHIFT); - context_desc->mss_l4len_idx = cpu_to_le32(mss_l4len_idx); - - tx_buffer_info->time_stamp = jiffies; - tx_buffer_info->next_to_watch = i; + /* if interface is down do nothing */ + if (test_bit(__IXGBEVF_DOWN, &adapter->state) || + test_bit(__IXGBEVF_RESETTING, &adapter->state)) + return; - i++; - if (i == tx_ring->count) - i = 0; - tx_ring->next_to_use = i; + /* 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); - return true; - } + ixgbevf_clear_interrupt_scheme(adapter); + ixgbevf_init_interrupt_scheme(adapter); - return false; + if (netif_running(dev)) + ixgbevf_open(dev); } -static bool ixgbevf_tx_csum(struct ixgbevf_adapter *adapter, - struct ixgbevf_ring *tx_ring, - struct sk_buff *skb, u32 tx_flags) +static void ixgbevf_tx_ctxtdesc(struct ixgbevf_ring *tx_ring, + u32 vlan_macip_lens, u32 type_tucmd, + u32 mss_l4len_idx) { struct ixgbe_adv_tx_context_desc *context_desc; - unsigned int i; - struct ixgbevf_tx_buffer *tx_buffer_info; - u32 vlan_macip_lens = 0, type_tucmd_mlhl = 0; + u16 i = tx_ring->next_to_use; - if (skb->ip_summed == CHECKSUM_PARTIAL || - (tx_flags & IXGBE_TX_FLAGS_VLAN)) { - i = tx_ring->next_to_use; - tx_buffer_info = &tx_ring->tx_buffer_info[i]; - context_desc = IXGBE_TX_CTXTDESC_ADV(*tx_ring, i); - - if (tx_flags & IXGBE_TX_FLAGS_VLAN) - vlan_macip_lens |= (tx_flags & - IXGBE_TX_FLAGS_VLAN_MASK); - vlan_macip_lens |= (skb_network_offset(skb) << - IXGBE_ADVTXD_MACLEN_SHIFT); - if (skb->ip_summed == CHECKSUM_PARTIAL) - vlan_macip_lens |= (skb_transport_header(skb) - - skb_network_header(skb)); - - context_desc->vlan_macip_lens = cpu_to_le32(vlan_macip_lens); - context_desc->seqnum_seed = 0; - - type_tucmd_mlhl |= (IXGBE_TXD_CMD_DEXT | - IXGBE_ADVTXD_DTYP_CTXT); - - if (skb->ip_summed == CHECKSUM_PARTIAL) { - switch (skb->protocol) { - case __constant_htons(ETH_P_IP): - type_tucmd_mlhl |= IXGBE_ADVTXD_TUCMD_IPV4; - if (ip_hdr(skb)->protocol == IPPROTO_TCP) - type_tucmd_mlhl |= - IXGBE_ADVTXD_TUCMD_L4T_TCP; - break; - case __constant_htons(ETH_P_IPV6): - /* XXX what about other V6 headers?? */ - if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP) - type_tucmd_mlhl |= - IXGBE_ADVTXD_TUCMD_L4T_TCP; - break; - default: - if (unlikely(net_ratelimit())) { - pr_warn("partial checksum but " - "proto=%x!\n", skb->protocol); - } - break; - } - } - - context_desc->type_tucmd_mlhl = cpu_to_le32(type_tucmd_mlhl); - /* use index zero for tx checksum offload */ - context_desc->mss_l4len_idx = 0; + context_desc = IXGBEVF_TX_CTXTDESC(tx_ring, i); - tx_buffer_info->time_stamp = jiffies; - tx_buffer_info->next_to_watch = i; - - adapter->hw_csum_tx_good++; - i++; - if (i == tx_ring->count) - i = 0; - tx_ring->next_to_use = i; + i++; + tx_ring->next_to_use = (i < tx_ring->count) ? i : 0; - return true; - } + /* set bits to identify this as an advanced context descriptor */ + type_tucmd |= IXGBE_TXD_CMD_DEXT | IXGBE_ADVTXD_DTYP_CTXT; - return false; + context_desc->vlan_macip_lens = cpu_to_le32(vlan_macip_lens); + context_desc->seqnum_seed = 0; + context_desc->type_tucmd_mlhl = cpu_to_le32(type_tucmd); + context_desc->mss_l4len_idx = cpu_to_le32(mss_l4len_idx); } -static int ixgbevf_tx_map(struct ixgbevf_adapter *adapter, - struct ixgbevf_ring *tx_ring, - struct sk_buff *skb, u32 tx_flags, - unsigned int first) +static int ixgbevf_tso(struct ixgbevf_ring *tx_ring, + struct ixgbevf_tx_buffer *first, + u8 *hdr_len) { - struct pci_dev *pdev = adapter->pdev; - 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; + struct sk_buff *skb = first->skb; + u32 vlan_macip_lens, type_tucmd; + u32 mss_l4len_idx, l4len; + int err; - i = tx_ring->next_to_use; + if (skb->ip_summed != CHECKSUM_PARTIAL) + return 0; - 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); - - tx_buffer_info->length = size; - tx_buffer_info->mapped_as_page = false; - tx_buffer_info->dma = dma_map_single(&adapter->pdev->dev, - skb->data + offset, - size, DMA_TO_DEVICE); - if (dma_mapping_error(&pdev->dev, tx_buffer_info->dma)) - goto dma_error; - tx_buffer_info->time_stamp = jiffies; - tx_buffer_info->next_to_watch = i; + if (!skb_is_gso(skb)) + return 0; - len -= size; - total -= size; - offset += size; - count++; - i++; - if (i == tx_ring->count) - i = 0; + 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)) { + struct iphdr *iph = ip_hdr(skb); + iph->tot_len = 0; + iph->check = 0; + tcp_hdr(skb)->check = ~csum_tcpudp_magic(iph->saddr, + iph->daddr, 0, + IPPROTO_TCP, + 0); + type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4; + 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 */ + l4len = tcp_hdrlen(skb); + *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; + mss_l4len_idx |= 1 << IXGBE_ADVTXD_IDX_SHIFT; + + /* vlan_macip_lens: HEADLEN, MACLEN, VLAN tag */ + vlan_macip_lens = skb_network_header_len(skb); + vlan_macip_lens |= skb_network_offset(skb) << IXGBE_ADVTXD_MACLEN_SHIFT; + vlan_macip_lens |= first->tx_flags & IXGBE_TX_FLAGS_VLAN_MASK; + + ixgbevf_tx_ctxtdesc(tx_ring, vlan_macip_lens, + type_tucmd, mss_l4len_idx); + + return 1; +} + +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 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 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", + first->protocol); + } + break; + } + + switch (l4_hdr) { + case IPPROTO_TCP: + type_tucmd |= IXGBE_ADVTXD_TUCMD_L4T_TCP; + mss_l4len_idx = tcp_hdrlen(skb) << + IXGBE_ADVTXD_L4LEN_SHIFT; + break; + case IPPROTO_SCTP: + type_tucmd |= IXGBE_ADVTXD_TUCMD_L4T_SCTP; + mss_l4len_idx = sizeof(struct sctphdr) << + IXGBE_ADVTXD_L4LEN_SHIFT; + break; + case IPPROTO_UDP: + mss_l4len_idx = sizeof(struct udphdr) << + IXGBE_ADVTXD_L4LEN_SHIFT; + break; + default: + if (unlikely(net_ratelimit())) { + dev_warn(tx_ring->dev, + "partial checksum but l4 proto=%x!\n", + l4_hdr); + } + break; + } + + /* update TX checksum flag */ + first->tx_flags |= IXGBE_TX_FLAGS_CSUM; } - for (f = 0; f < nr_frags; f++) { - const struct skb_frag_struct *frag; + /* vlan_macip_lens: MACLEN, VLAN tag */ + vlan_macip_lens |= skb_network_offset(skb) << IXGBE_ADVTXD_MACLEN_SHIFT; + vlan_macip_lens |= first->tx_flags & IXGBE_TX_FLAGS_VLAN_MASK; - frag = &skb_shinfo(skb)->frags[f]; - len = min((unsigned int)skb_frag_size(frag), total); - offset = 0; + ixgbevf_tx_ctxtdesc(tx_ring, vlan_macip_lens, + type_tucmd, mss_l4len_idx); +} - while (len) { - tx_buffer_info = &tx_ring->tx_buffer_info[i]; - size = min(len, (unsigned int)IXGBE_MAX_DATA_PER_TXD); +static __le32 ixgbevf_tx_cmd_type(u32 tx_flags) +{ + /* 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); - tx_buffer_info->length = size; - tx_buffer_info->dma = - skb_frag_dma_map(&adapter->pdev->dev, frag, - offset, size, DMA_TO_DEVICE); - tx_buffer_info->mapped_as_page = true; - if (dma_mapping_error(&pdev->dev, tx_buffer_info->dma)) - goto dma_error; - tx_buffer_info->time_stamp = jiffies; - tx_buffer_info->next_to_watch = i; + /* 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 -= size; - total -= size; - offset += size; - count++; - i++; - if (i == tx_ring->count) - i = 0; - } - if (total == 0) - break; - } + /* set segmentation enable bits for TSO/FSO */ + if (tx_flags & IXGBE_TX_FLAGS_TSO) + cmd_type |= cpu_to_le32(IXGBE_ADVTXD_DCMD_TSE); - if (i == 0) - i = tx_ring->count - 1; - else - i = i - 1; - tx_ring->tx_buffer_info[i].skb = skb; - tx_ring->tx_buffer_info[first].next_to_watch = i; + return cmd_type; +} - return count; +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); -dma_error: - dev_err(&pdev->dev, "TX DMA map failed\n"); + /* 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); - /* clear timestamp and dma mappings for failed tx_buffer_info map */ - tx_buffer_info->dma = 0; - tx_buffer_info->time_stamp = 0; - tx_buffer_info->next_to_watch = 0; - count--; + /* enble IPv4 checksum for TSO */ + if (tx_flags & IXGBE_TX_FLAGS_IPV4) + olinfo_status |= cpu_to_le32(IXGBE_ADVTXD_POPTS_IXSM); - /* 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(adapter, tx_buffer_info); - } + /* 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); + + tx_desc->read.olinfo_status = olinfo_status; } -static void ixgbevf_tx_queue(struct ixgbevf_adapter *adapter, - struct ixgbevf_ring *tx_ring, int tx_flags, - int count, u32 paylen, u8 hdr_len) +static void ixgbevf_tx_map(struct ixgbevf_ring *tx_ring, + struct ixgbevf_tx_buffer *first, + const 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; + 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; - u32 txd_cmd = IXGBE_TXD_CMD_EOP | IXGBE_TXD_CMD_RS | IXGBE_TXD_CMD_IFCS; + tx_desc = IXGBEVF_TX_DESC(tx_ring, i); - cmd_type_len |= IXGBE_ADVTXD_DTYP_DATA; + ixgbevf_tx_olinfo_status(tx_desc, tx_flags, paylen); + cmd_type = ixgbevf_tx_cmd_type(tx_flags); - cmd_type_len |= IXGBE_ADVTXD_DCMD_IFCS | IXGBE_ADVTXD_DCMD_DEXT; + dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE); + if (dma_mapping_error(tx_ring->dev, dma)) + goto dma_error; - if (tx_flags & IXGBE_TX_FLAGS_VLAN) - cmd_type_len |= IXGBE_ADVTXD_DCMD_VLE; + /* record length, and DMA address */ + dma_unmap_len_set(first, len, size); + dma_unmap_addr_set(first, dma, dma); - if (tx_flags & IXGBE_TX_FLAGS_TSO) { - cmd_type_len |= IXGBE_ADVTXD_DCMD_TSE; + tx_desc->read.buffer_addr = cpu_to_le64(dma); - olinfo_status |= IXGBE_TXD_POPTS_TXSM << - IXGBE_ADVTXD_POPTS_SHIFT; + 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); - /* use index 1 context for tso */ - olinfo_status |= (1 << IXGBE_ADVTXD_IDX_SHIFT); - if (tx_flags & IXGBE_TX_FLAGS_IPV4) - olinfo_status |= IXGBE_TXD_POPTS_IXSM << - IXGBE_ADVTXD_POPTS_SHIFT; + i++; + tx_desc++; + if (i == tx_ring->count) { + tx_desc = IXGBEVF_TX_DESC(tx_ring, 0); + i = 0; + } - } else if (tx_flags & IXGBE_TX_FLAGS_CSUM) - olinfo_status |= IXGBE_TXD_POPTS_TXSM << - IXGBE_ADVTXD_POPTS_SHIFT; + dma += IXGBE_MAX_DATA_PER_TXD; + size -= IXGBE_MAX_DATA_PER_TXD; - olinfo_status |= ((paylen - hdr_len) << IXGBE_ADVTXD_PAYLEN_SHIFT); + tx_desc->read.buffer_addr = cpu_to_le64(dma); + tx_desc->read.olinfo_status = 0; + } + + if (likely(!data_len)) + break; + + 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 = IXGBE_TX_DESC_ADV(*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; - /* - * 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). + /* 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). + * + * 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(); + /* 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; - writel(i, adapter->hw.hw_addr + tx_ring->tail); } -static int __ixgbevf_maybe_stop_tx(struct net_device *netdev, - struct ixgbevf_ring *tx_ring, int size) +static int __ixgbevf_maybe_stop_tx(struct ixgbevf_ring *tx_ring, int size) { - struct ixgbevf_adapter *adapter = netdev_priv(netdev); - - netif_stop_subqueue(netdev, tx_ring->queue_index); + netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index); /* Herbert's original patch had: * smp_mb__after_netif_stop_queue(); * but since that doesn't exist yet, just open code it. */ @@ -3063,36 +3145,67 @@ static int __ixgbevf_maybe_stop_tx(struct net_device *netdev, /* We need to check again in a case another CPU has just * made room available. */ - if (likely(IXGBE_DESC_UNUSED(tx_ring) < size)) + if (likely(ixgbevf_desc_unused(tx_ring) < size)) return -EBUSY; /* A reprieve! - use start_queue because it doesn't call schedule */ - netif_start_subqueue(netdev, tx_ring->queue_index); - ++adapter->restart_queue; + netif_start_subqueue(tx_ring->netdev, tx_ring->queue_index); + ++tx_ring->tx_stats.restart_queue; + return 0; } -static int ixgbevf_maybe_stop_tx(struct net_device *netdev, - struct ixgbevf_ring *tx_ring, int size) +static int ixgbevf_maybe_stop_tx(struct ixgbevf_ring *tx_ring, int size) { - if (likely(IXGBE_DESC_UNUSED(tx_ring) >= size)) + if (likely(ixgbevf_desc_unused(tx_ring) >= size)) return 0; - return __ixgbevf_maybe_stop_tx(netdev, tx_ring, size); + return __ixgbevf_maybe_stop_tx(tx_ring, size); } static int ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev) { 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; + 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; - int r_idx = 0, tso; - int count = 0; + u8 *dst_mac = skb_header_pointer(skb, 0, 0, NULL); - unsigned int f; + if (!dst_mac || is_link_local_ether_addr(dst_mac)) { + dev_kfree_skb(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, + * + 1 desc for skb_headlen/IXGBE_MAX_DATA_PER_TXD, + * + 2 desc gap to keep tail from touching head, + * + 1 desc for context descriptor, + * otherwise try next time + */ +#if PAGE_SIZE > IXGBE_MAX_DATA_PER_TXD + for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) + count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size); +#else + count += skb_shinfo(skb)->nr_frags; +#endif + if (ixgbevf_maybe_stop_tx(tx_ring, count + 3)) { + tx_ring->tx_stats.tx_busy++; + return NETDEV_TX_BUSY; + } + + /* 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 (vlan_tx_tag_present(skb)) { tx_flags |= vlan_tx_tag_get(skb); @@ -3100,42 +3213,25 @@ static int ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev) tx_flags |= IXGBE_TX_FLAGS_VLAN; } - /* four things can cause us to need a context descriptor */ - if (skb_is_gso(skb) || - (skb->ip_summed == CHECKSUM_PARTIAL) || - (tx_flags & IXGBE_TX_FLAGS_VLAN)) - count++; - - count += TXD_USE_COUNT(skb_headlen(skb)); - for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) - count += TXD_USE_COUNT(skb_frag_size(&skb_shinfo(skb)->frags[f])); - - if (ixgbevf_maybe_stop_tx(netdev, tx_ring, count)) { - adapter->tx_busy++; - return NETDEV_TX_BUSY; - } + /* record initial flags and protocol */ + first->tx_flags = tx_flags; + first->protocol = vlan_get_protocol(skb); - first = tx_ring->next_to_use; + 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(adapter, 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; - else if (ixgbevf_tx_csum(adapter, tx_ring, skb, tx_flags) && - (skb->ip_summed == CHECKSUM_PARTIAL)) - tx_flags |= IXGBE_TX_FLAGS_CSUM; + ixgbevf_maybe_stop_tx(tx_ring, DESC_NEEDED); - ixgbevf_tx_queue(adapter, tx_ring, tx_flags, - ixgbevf_tx_map(adapter, tx_ring, skb, tx_flags, first), - skb->len, hdr_len); + return NETDEV_TX_OK; - ixgbevf_maybe_stop_tx(netdev, tx_ring, DESC_NEEDED); +out_drop: + dev_kfree_skb_any(first->skb); + first->skb = NULL; return NETDEV_TX_OK; } @@ -3159,8 +3255,11 @@ static int ixgbevf_set_mac(struct net_device *netdev, void *p) memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len); memcpy(hw->mac.addr, addr->sa_data, netdev->addr_len); - if (hw->mac.ops.set_rar) - hw->mac.ops.set_rar(hw, 0, hw->mac.addr, 0); + spin_lock_bh(&adapter->mbx_lock); + + hw->mac.ops.set_rar(hw, 0, hw->mac.addr, 0); + + spin_unlock_bh(&adapter->mbx_lock); return 0; } @@ -3175,13 +3274,18 @@ static int ixgbevf_set_mac(struct net_device *netdev, void *p) 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; - u32 msg[2]; - if (adapter->hw.mac.type == ixgbe_mac_X540_vf) + switch (adapter->hw.api_version) { + case ixgbe_mbox_api_11: max_possible_frame = IXGBE_MAX_JUMBO_FRAME_SIZE; + break; + default: + if (adapter->hw.mac.type == ixgbe_mac_X540_vf) + max_possible_frame = IXGBE_MAX_JUMBO_FRAME_SIZE; + break; + } /* MTU < 68 is an error and causes problems on some kernels */ if ((new_mtu < 68) || (max_frame > max_possible_frame)) @@ -3192,35 +3296,93 @@ static int ixgbevf_change_mtu(struct net_device *netdev, int new_mtu) /* must set new MTU before calling down or up */ netdev->mtu = new_mtu; - msg[0] = IXGBE_VF_SET_LPE; - msg[1] = max_frame; - hw->mbx.ops.write_posted(hw, msg, 2); - if (netif_running(netdev)) ixgbevf_reinit_locked(adapter); return 0; } -static void ixgbevf_shutdown(struct pci_dev *pdev) +static int ixgbevf_suspend(struct pci_dev *pdev, pm_message_t state) { struct net_device *netdev = pci_get_drvdata(pdev); struct ixgbevf_adapter *adapter = netdev_priv(netdev); +#ifdef CONFIG_PM + int retval = 0; +#endif netif_device_detach(netdev); if (netif_running(netdev)) { + rtnl_lock(); ixgbevf_down(adapter); ixgbevf_free_irq(adapter); ixgbevf_free_all_tx_resources(adapter); ixgbevf_free_all_rx_resources(adapter); + rtnl_unlock(); } + ixgbevf_clear_interrupt_scheme(adapter); + #ifdef CONFIG_PM - pci_save_state(pdev); + retval = pci_save_state(pdev); + if (retval) + return retval; + #endif + if (!test_and_set_bit(__IXGBEVF_DISABLED, &adapter->state)) + pci_disable_device(pdev); + + return 0; +} + +#ifdef CONFIG_PM +static int ixgbevf_resume(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + u32 err; + + pci_restore_state(pdev); + /* + * pci_restore_state clears dev->state_saved so call + * pci_save_state to restore it. + */ + pci_save_state(pdev); + + err = pci_enable_device_mem(pdev); + if (err) { + 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(); + if (err) { + dev_err(&pdev->dev, "Cannot initialize interrupts\n"); + return err; + } + + if (netif_running(netdev)) { + err = ixgbevf_open(netdev); + if (err) + return err; + } + + netif_device_attach(netdev); + + return err; +} - pci_disable_device(pdev); +#endif /* CONFIG_PM */ +static void ixgbevf_shutdown(struct pci_dev *pdev) +{ + ixgbevf_suspend(pdev, PMSG_SUSPEND); } static struct rtnl_link_stats64 *ixgbevf_get_stats(struct net_device *netdev, @@ -3237,23 +3399,23 @@ static struct rtnl_link_stats64 *ixgbevf_get_stats(struct net_device *netdev, 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; } @@ -3261,20 +3423,7 @@ static struct rtnl_link_stats64 *ixgbevf_get_stats(struct net_device *netdev, return stats; } -static int ixgbevf_set_features(struct net_device *netdev, - netdev_features_t features) -{ - struct ixgbevf_adapter *adapter = netdev_priv(netdev); - - if (features & NETIF_F_RXCSUM) - adapter->flags |= IXGBE_FLAG_RX_CSUM_ENABLED; - else - adapter->flags &= ~IXGBE_FLAG_RX_CSUM_ENABLED; - - return 0; -} - -static const struct net_device_ops ixgbe_netdev_ops = { +static const struct net_device_ops ixgbevf_netdev_ops = { .ndo_open = ixgbevf_open, .ndo_stop = ixgbevf_close, .ndo_start_xmit = ixgbevf_xmit_frame, @@ -3286,12 +3435,14 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_tx_timeout = ixgbevf_tx_timeout, .ndo_vlan_rx_add_vid = ixgbevf_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = ixgbevf_vlan_rx_kill_vid, - .ndo_set_features = ixgbevf_set_features, +#ifdef CONFIG_NET_RX_BUSY_POLL + .ndo_busy_poll = ixgbevf_busy_poll_recv, +#endif }; static void ixgbevf_assign_netdev_ops(struct net_device *dev) { - dev->netdev_ops = &ixgbe_netdev_ops; + dev->netdev_ops = &ixgbevf_netdev_ops; ixgbevf_set_ethtool_ops(dev); dev->watchdog_timeo = 5 * HZ; } @@ -3307,8 +3458,7 @@ static void ixgbevf_assign_netdev_ops(struct net_device *dev) * The OS initialization, configuring of the adapter private structure, * and a hardware reset occur. **/ -static int __devinit ixgbevf_probe(struct pci_dev *pdev, - const struct pci_device_id *ent) +static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { struct net_device *netdev; struct ixgbevf_adapter *adapter = NULL; @@ -3321,19 +3471,14 @@ static int __devinit ixgbevf_probe(struct pci_dev *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; } @@ -3346,12 +3491,8 @@ static int __devinit ixgbevf_probe(struct pci_dev *pdev, pci_set_master(pdev); -#ifdef HAVE_TX_MQ netdev = alloc_etherdev_mq(sizeof(struct ixgbevf_adapter), MAX_TX_QUEUES); -#else - netdev = alloc_etherdev(sizeof(struct ixgbevf_adapter)); -#endif if (!netdev) { err = -ENOMEM; goto err_alloc_etherdev; @@ -3366,7 +3507,7 @@ static int __devinit ixgbevf_probe(struct pci_dev *pdev, adapter->pdev = pdev; hw = &adapter->hw; hw->back = adapter; - adapter->msg_enable = (1 << DEFAULT_DEBUG_LEVEL_SHIFT) - 1; + adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE); /* * call save state here in standalone driver because it relies on @@ -3376,6 +3517,7 @@ static int __devinit ixgbevf_probe(struct pci_dev *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; @@ -3392,12 +3534,17 @@ static int __devinit ixgbevf_probe(struct pci_dev *pdev, memcpy(&hw->mbx.ops, &ixgbevf_mbx_ops, sizeof(struct ixgbe_mbx_operations)); - adapter->flags &= ~IXGBE_FLAG_RX_PS_CAPABLE; - adapter->flags &= ~IXGBE_FLAG_RX_PS_ENABLED; - adapter->flags |= IXGBE_FLAG_RX_1BUF_CAPABLE; - /* setup the private structure */ err = ixgbevf_sw_init(adapter); + if (err) + goto err_sw_init; + + /* The HW MAC address was set and/or determined in sw_init */ + if (!is_valid_ether_addr(netdev->dev_addr)) { + pr_err("invalid MAC address\n"); + err = -EIO; + goto err_sw_init; + } netdev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | @@ -3407,9 +3554,9 @@ static int __devinit ixgbevf_probe(struct pci_dev *pdev, NETIF_F_RXCSUM; netdev->features = netdev->hw_features | - NETIF_F_HW_VLAN_TX | - NETIF_F_HW_VLAN_RX | - NETIF_F_HW_VLAN_FILTER; + 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; @@ -3422,71 +3569,54 @@ static int __devinit ixgbevf_probe(struct pci_dev *pdev, netdev->priv_flags |= IFF_UNICAST_FLT; - /* The HW MAC address was set and/or determined in sw_init */ - memcpy(netdev->dev_addr, adapter->hw.mac.addr, netdev->addr_len); - memcpy(netdev->perm_addr, adapter->hw.mac.addr, netdev->addr_len); - - if (!is_valid_ether_addr(netdev->dev_addr)) { - pr_err("invalid MAC address\n"); - err = -EIO; - goto err_sw_init; - } - 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; + } INIT_WORK(&adapter->reset_task, ixgbevf_reset_task); INIT_WORK(&adapter->watchdog_task, ixgbevf_watchdog_task); + set_bit(__IXGBEVF_WORK_INIT, &adapter->state); err = ixgbevf_init_interrupt_scheme(adapter); if (err) goto err_sw_init; - /* pick up the PCI bus settings for reporting later */ - if (hw->mac.ops.get_bus_info) - hw->mac.ops.get_bus_info(hw); - strcpy(netdev->name, "eth%d"); err = register_netdev(netdev); if (err) goto err_register; - adapter->netdev_registered = true; - netif_carrier_off(netdev); ixgbevf_init_last_counter_stats(adapter); /* print the MAC address */ - hw_dbg(hw, "%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x\n", - netdev->dev_addr[0], - netdev->dev_addr[1], - netdev->dev_addr[2], - netdev->dev_addr[3], - netdev->dev_addr[4], - netdev->dev_addr[5]); + hw_dbg(hw, "%pM\n", netdev->dev_addr); hw_dbg(hw, "MAC: %d\n", hw->mac.type); - hw_dbg(hw, "LRO is disabled\n"); - hw_dbg(hw, "Intel(R) 82599 Virtual Function\n"); cards_found++; return 0; 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: free_netdev(netdev); err_alloc_etherdev: pci_release_regions(pdev); err_pci_reg: err_dma: - pci_disable_device(pdev); + if (!test_and_set_bit(__IXGBEVF_DISABLED, &adapter->state)) + pci_disable_device(pdev); return err; } @@ -3499,44 +3629,136 @@ err_dma: * Hot-Plug event, or because the driver is going to be removed from * memory. **/ -static void __devexit ixgbevf_remove(struct pci_dev *pdev) +static void ixgbevf_remove(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); struct ixgbevf_adapter *adapter = netdev_priv(netdev); - set_bit(__IXGBEVF_DOWN, &adapter->state); + set_bit(__IXGBEVF_REMOVING, &adapter->state); del_timer_sync(&adapter->watchdog_timer); cancel_work_sync(&adapter->reset_task); cancel_work_sync(&adapter->watchdog_task); - if (adapter->netdev_registered) { + if (netdev->reg_state == NETREG_REGISTERED) unregister_netdev(netdev); - adapter->netdev_registered = false; - } + ixgbevf_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); - free_netdev(netdev); - pci_disable_device(pdev); + if (!test_and_set_bit(__IXGBEVF_DISABLED, &adapter->state)) + pci_disable_device(pdev); +} + +/** + * ixgbevf_io_error_detected - called when PCI error is detected + * @pdev: Pointer to PCI device + * @state: The current pci connection state + * + * This function is called after a PCI bus error affecting + * this device has been detected. + */ +static pci_ers_result_t ixgbevf_io_error_detected(struct pci_dev *pdev, + pci_channel_state_t state) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + + if (!test_bit(__IXGBEVF_WORK_INIT, &adapter->state)) + return PCI_ERS_RESULT_DISCONNECT; + + rtnl_lock(); + netif_device_detach(netdev); + + if (state == pci_channel_io_perm_failure) { + rtnl_unlock(); + return PCI_ERS_RESULT_DISCONNECT; + } + + if (netif_running(netdev)) + ixgbevf_down(adapter); + + 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; } +/** + * ixgbevf_io_slot_reset - called after the pci bus has been reset. + * @pdev: Pointer to PCI device + * + * Restart the card from scratch, as if from a cold-boot. Implementation + * resembles the first-half of the ixgbevf_resume routine. + */ +static pci_ers_result_t ixgbevf_io_slot_reset(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + + if (pci_enable_device_mem(pdev)) { + dev_err(&pdev->dev, + "Cannot re-enable PCI device after reset.\n"); + return PCI_ERS_RESULT_DISCONNECT; + } + + smp_mb__before_atomic(); + clear_bit(__IXGBEVF_DISABLED, &adapter->state); + pci_set_master(pdev); + + ixgbevf_reset(adapter); + + return PCI_ERS_RESULT_RECOVERED; +} + +/** + * ixgbevf_io_resume - called when traffic can start flowing again. + * @pdev: Pointer to PCI device + * + * This callback is called when the error recovery driver tells us that + * its OK to resume normal operation. Implementation resembles the + * second-half of the ixgbevf_resume routine. + */ +static void ixgbevf_io_resume(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + + if (netif_running(netdev)) + ixgbevf_up(adapter); + + netif_device_attach(netdev); +} + +/* PCI Error Recovery (ERS) */ +static const struct pci_error_handlers ixgbevf_err_handler = { + .error_detected = ixgbevf_io_error_detected, + .slot_reset = ixgbevf_io_slot_reset, + .resume = ixgbevf_io_resume, +}; + static struct pci_driver ixgbevf_driver = { .name = ixgbevf_driver_name, .id_table = ixgbevf_pci_tbl, .probe = ixgbevf_probe, - .remove = __devexit_p(ixgbevf_remove), + .remove = ixgbevf_remove, +#ifdef CONFIG_PM + /* Power Management Hooks */ + .suspend = ixgbevf_suspend, + .resume = ixgbevf_resume, +#endif .shutdown = ixgbevf_shutdown, + .err_handler = &ixgbevf_err_handler }; /** |