diff options
Diffstat (limited to 'drivers/net/ethernet/intel/igb/igb_main.c')
-rw-r--r-- | drivers/net/ethernet/intel/igb/igb_main.c | 1340 |
1 files changed, 830 insertions, 510 deletions
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index e1ceb37..082ce73 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -61,7 +61,7 @@ #define MAJ 4 #define MIN 0 -#define BUILD 1 +#define BUILD 17 #define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) "." \ __stringify(BUILD) "-k" char igb_driver_name[] = "igb"; @@ -534,31 +534,27 @@ rx_ring_summary: if (staterr & E1000_RXD_STAT_DD) { /* Descriptor Done */ - pr_info("%s[0x%03X] %016llX %016llX -------" - "--------- %p%s\n", "RWB", i, + pr_info("%s[0x%03X] %016llX %016llX ---------------- %s\n", + "RWB", i, le64_to_cpu(u0->a), le64_to_cpu(u0->b), - buffer_info->skb, next_desc); + next_desc); } else { - pr_info("%s[0x%03X] %016llX %016llX %016llX" - " %p%s\n", "R ", i, + pr_info("%s[0x%03X] %016llX %016llX %016llX %s\n", + "R ", i, le64_to_cpu(u0->a), le64_to_cpu(u0->b), (u64)buffer_info->dma, - buffer_info->skb, next_desc); + next_desc); if (netif_msg_pktdata(adapter) && - buffer_info->dma && buffer_info->skb) { - print_hex_dump(KERN_INFO, "", - DUMP_PREFIX_ADDRESS, - 16, 1, buffer_info->skb->data, - IGB_RX_HDR_LEN, true); + buffer_info->dma && buffer_info->page) { print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS, 16, 1, page_address(buffer_info->page) + buffer_info->page_offset, - PAGE_SIZE/2, true); + IGB_RX_BUFSZ, true); } } } @@ -656,80 +652,6 @@ static void igb_cache_ring_register(struct igb_adapter *adapter) } } -static void igb_free_queues(struct igb_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_rx_queues = 0; - adapter->num_tx_queues = 0; -} - -/** - * igb_alloc_queues - Allocate memory for all rings - * @adapter: board private structure to initialize - * - * We allocate one ring per queue at run-time since we don't know the - * number of queues at compile-time. - **/ -static int igb_alloc_queues(struct igb_adapter *adapter) -{ - struct igb_ring *ring; - int i; - - for (i = 0; i < adapter->num_tx_queues; i++) { - ring = kzalloc(sizeof(struct igb_ring), GFP_KERNEL); - if (!ring) - goto err; - ring->count = adapter->tx_ring_count; - ring->queue_index = i; - ring->dev = &adapter->pdev->dev; - ring->netdev = adapter->netdev; - /* For 82575, context index must be unique per ring. */ - if (adapter->hw.mac.type == e1000_82575) - set_bit(IGB_RING_FLAG_TX_CTX_IDX, &ring->flags); - adapter->tx_ring[i] = ring; - } - - for (i = 0; i < adapter->num_rx_queues; i++) { - ring = kzalloc(sizeof(struct igb_ring), GFP_KERNEL); - if (!ring) - goto err; - ring->count = adapter->rx_ring_count; - ring->queue_index = i; - ring->dev = &adapter->pdev->dev; - ring->netdev = adapter->netdev; - /* set flag indicating ring supports SCTP checksum offload */ - if (adapter->hw.mac.type >= e1000_82576) - set_bit(IGB_RING_FLAG_RX_SCTP_CSUM, &ring->flags); - - /* - * On i350, i210, and i211, loopback VLAN packets - * have the tag byte-swapped. - * */ - if (adapter->hw.mac.type >= e1000_i350) - set_bit(IGB_RING_FLAG_RX_LB_VLAN_BSWAP, &ring->flags); - - adapter->rx_ring[i] = ring; - } - - igb_cache_ring_register(adapter); - - return 0; - -err: - igb_free_queues(adapter); - - return -ENOMEM; -} - /** * igb_write_ivar - configure ivar for given MSI-X vector * @hw: pointer to the HW structure @@ -960,6 +882,35 @@ static void igb_reset_interrupt_capability(struct igb_adapter *adapter) } /** + * igb_free_q_vector - Free memory allocated for specific interrupt vector + * @adapter: board private structure to initialize + * @v_idx: Index of vector to be freed + * + * This function frees the memory allocated to the q_vector. In addition if + * NAPI is enabled it will delete any references to the NAPI struct prior + * to freeing the q_vector. + **/ +static void igb_free_q_vector(struct igb_adapter *adapter, int v_idx) +{ + struct igb_q_vector *q_vector = adapter->q_vector[v_idx]; + + if (q_vector->tx.ring) + adapter->tx_ring[q_vector->tx.ring->queue_index] = NULL; + + if (q_vector->rx.ring) + adapter->tx_ring[q_vector->rx.ring->queue_index] = NULL; + + adapter->q_vector[v_idx] = NULL; + netif_napi_del(&q_vector->napi); + + /* + * ixgbe_get_stats64() might access the rings on this vector, + * we must wait a grace period before freeing it. + */ + kfree_rcu(q_vector, rcu); +} + +/** * igb_free_q_vectors - Free memory allocated for interrupt vectors * @adapter: board private structure to initialize * @@ -969,17 +920,14 @@ static void igb_reset_interrupt_capability(struct igb_adapter *adapter) **/ static void igb_free_q_vectors(struct igb_adapter *adapter) { - int v_idx; + int v_idx = adapter->num_q_vectors; - for (v_idx = 0; v_idx < adapter->num_q_vectors; v_idx++) { - struct igb_q_vector *q_vector = adapter->q_vector[v_idx]; - adapter->q_vector[v_idx] = NULL; - if (!q_vector) - continue; - netif_napi_del(&q_vector->napi); - kfree(q_vector); - } + adapter->num_tx_queues = 0; + adapter->num_rx_queues = 0; adapter->num_q_vectors = 0; + + while (v_idx--) + igb_free_q_vector(adapter, v_idx); } /** @@ -990,7 +938,6 @@ static void igb_free_q_vectors(struct igb_adapter *adapter) */ static void igb_clear_interrupt_scheme(struct igb_adapter *adapter) { - igb_free_queues(adapter); igb_free_q_vectors(adapter); igb_reset_interrupt_capability(adapter); } @@ -1001,7 +948,7 @@ static void igb_clear_interrupt_scheme(struct igb_adapter *adapter) * Attempt to configure interrupts using the best available * capabilities of the hardware and kernel. **/ -static int igb_set_interrupt_capability(struct igb_adapter *adapter) +static void igb_set_interrupt_capability(struct igb_adapter *adapter) { int err; int numvecs, i; @@ -1038,7 +985,7 @@ static int igb_set_interrupt_capability(struct igb_adapter *adapter) adapter->msix_entries, numvecs); if (err == 0) - goto out; + return; igb_reset_interrupt_capability(adapter); @@ -1068,105 +1015,183 @@ msi_only: adapter->num_q_vectors = 1; if (!pci_enable_msi(adapter->pdev)) adapter->flags |= IGB_FLAG_HAS_MSI; -out: - /* Notify the stack of the (possibly) reduced queue counts. */ - rtnl_lock(); - netif_set_real_num_tx_queues(adapter->netdev, adapter->num_tx_queues); - err = netif_set_real_num_rx_queues(adapter->netdev, - adapter->num_rx_queues); - rtnl_unlock(); - return err; +} + +static void igb_add_ring(struct igb_ring *ring, + struct igb_ring_container *head) +{ + head->ring = ring; + head->count++; } /** - * igb_alloc_q_vectors - Allocate memory for interrupt vectors + * igb_alloc_q_vector - Allocate memory for a single interrupt vector * @adapter: board private structure to initialize + * @v_count: q_vectors allocated on adapter, used for ring interleaving + * @v_idx: index of vector in adapter struct + * @txr_count: total number of Tx rings to allocate + * @txr_idx: index of first Tx ring to allocate + * @rxr_count: total number of Rx rings to allocate + * @rxr_idx: index of first Rx ring to allocate * - * We allocate one q_vector per queue interrupt. If allocation fails we - * return -ENOMEM. + * We allocate one q_vector. If allocation fails we return -ENOMEM. **/ -static int igb_alloc_q_vectors(struct igb_adapter *adapter) +static int igb_alloc_q_vector(struct igb_adapter *adapter, + int v_count, int v_idx, + int txr_count, int txr_idx, + int rxr_count, int rxr_idx) { struct igb_q_vector *q_vector; - struct e1000_hw *hw = &adapter->hw; - int v_idx; + struct igb_ring *ring; + int ring_count, size; - for (v_idx = 0; v_idx < adapter->num_q_vectors; v_idx++) { - q_vector = kzalloc(sizeof(struct igb_q_vector), - GFP_KERNEL); - if (!q_vector) - goto err_out; - q_vector->adapter = adapter; - q_vector->itr_register = hw->hw_addr + E1000_EITR(0); - q_vector->itr_val = IGB_START_ITR; - netif_napi_add(adapter->netdev, &q_vector->napi, igb_poll, 64); - adapter->q_vector[v_idx] = q_vector; + /* igb only supports 1 Tx and/or 1 Rx queue per vector */ + if (txr_count > 1 || rxr_count > 1) + return -ENOMEM; + + ring_count = txr_count + rxr_count; + size = sizeof(struct igb_q_vector) + + (sizeof(struct igb_ring) * ring_count); + + /* allocate q_vector and rings */ + q_vector = kzalloc(size, GFP_KERNEL); + if (!q_vector) + return -ENOMEM; + + /* initialize NAPI */ + netif_napi_add(adapter->netdev, &q_vector->napi, + igb_poll, 64); + + /* tie q_vector and adapter together */ + adapter->q_vector[v_idx] = q_vector; + q_vector->adapter = adapter; + + /* initialize work limits */ + q_vector->tx.work_limit = adapter->tx_work_limit; + + /* initialize ITR configuration */ + q_vector->itr_register = adapter->hw.hw_addr + E1000_EITR(0); + q_vector->itr_val = IGB_START_ITR; + + /* initialize pointer to rings */ + ring = q_vector->ring; + + if (txr_count) { + /* assign generic ring traits */ + ring->dev = &adapter->pdev->dev; + ring->netdev = adapter->netdev; + + /* configure backlink on ring */ + ring->q_vector = q_vector; + + /* update q_vector Tx values */ + igb_add_ring(ring, &q_vector->tx); + + /* For 82575, context index must be unique per ring. */ + if (adapter->hw.mac.type == e1000_82575) + set_bit(IGB_RING_FLAG_TX_CTX_IDX, &ring->flags); + + /* apply Tx specific ring traits */ + ring->count = adapter->tx_ring_count; + ring->queue_index = txr_idx; + + /* assign ring to adapter */ + adapter->tx_ring[txr_idx] = ring; + + /* push pointer to next ring */ + ring++; } - return 0; + if (rxr_count) { + /* assign generic ring traits */ + ring->dev = &adapter->pdev->dev; + ring->netdev = adapter->netdev; -err_out: - igb_free_q_vectors(adapter); - return -ENOMEM; -} + /* configure backlink on ring */ + ring->q_vector = q_vector; -static void igb_map_rx_ring_to_vector(struct igb_adapter *adapter, - int ring_idx, int v_idx) -{ - struct igb_q_vector *q_vector = adapter->q_vector[v_idx]; + /* update q_vector Rx values */ + igb_add_ring(ring, &q_vector->rx); - q_vector->rx.ring = adapter->rx_ring[ring_idx]; - q_vector->rx.ring->q_vector = q_vector; - q_vector->rx.count++; - q_vector->itr_val = adapter->rx_itr_setting; - if (q_vector->itr_val && q_vector->itr_val <= 3) - q_vector->itr_val = IGB_START_ITR; -} + /* set flag indicating ring supports SCTP checksum offload */ + if (adapter->hw.mac.type >= e1000_82576) + set_bit(IGB_RING_FLAG_RX_SCTP_CSUM, &ring->flags); -static void igb_map_tx_ring_to_vector(struct igb_adapter *adapter, - int ring_idx, int v_idx) -{ - struct igb_q_vector *q_vector = adapter->q_vector[v_idx]; + /* + * On i350, i210, and i211, loopback VLAN packets + * have the tag byte-swapped. + * */ + if (adapter->hw.mac.type >= e1000_i350) + set_bit(IGB_RING_FLAG_RX_LB_VLAN_BSWAP, &ring->flags); - q_vector->tx.ring = adapter->tx_ring[ring_idx]; - q_vector->tx.ring->q_vector = q_vector; - q_vector->tx.count++; - q_vector->itr_val = adapter->tx_itr_setting; - q_vector->tx.work_limit = adapter->tx_work_limit; - if (q_vector->itr_val && q_vector->itr_val <= 3) - q_vector->itr_val = IGB_START_ITR; + /* apply Rx specific ring traits */ + ring->count = adapter->rx_ring_count; + ring->queue_index = rxr_idx; + + /* assign ring to adapter */ + adapter->rx_ring[rxr_idx] = ring; + } + + return 0; } + /** - * igb_map_ring_to_vector - maps allocated queues to vectors + * igb_alloc_q_vectors - Allocate memory for interrupt vectors + * @adapter: board private structure to initialize * - * This function maps the recently allocated queues to vectors. + * We allocate one q_vector per queue interrupt. If allocation fails we + * return -ENOMEM. **/ -static int igb_map_ring_to_vector(struct igb_adapter *adapter) +static int igb_alloc_q_vectors(struct igb_adapter *adapter) { - int i; - int v_idx = 0; + int q_vectors = adapter->num_q_vectors; + int rxr_remaining = adapter->num_rx_queues; + int txr_remaining = adapter->num_tx_queues; + int rxr_idx = 0, txr_idx = 0, v_idx = 0; + int err; - if ((adapter->num_q_vectors < adapter->num_rx_queues) || - (adapter->num_q_vectors < adapter->num_tx_queues)) - return -ENOMEM; + if (q_vectors >= (rxr_remaining + txr_remaining)) { + for (; rxr_remaining; v_idx++) { + err = igb_alloc_q_vector(adapter, q_vectors, v_idx, + 0, 0, 1, rxr_idx); - if (adapter->num_q_vectors >= - (adapter->num_rx_queues + adapter->num_tx_queues)) { - for (i = 0; i < adapter->num_rx_queues; i++) - igb_map_rx_ring_to_vector(adapter, i, v_idx++); - for (i = 0; i < adapter->num_tx_queues; i++) - igb_map_tx_ring_to_vector(adapter, i, v_idx++); - } else { - for (i = 0; i < adapter->num_rx_queues; i++) { - if (i < adapter->num_tx_queues) - igb_map_tx_ring_to_vector(adapter, i, v_idx); - igb_map_rx_ring_to_vector(adapter, i, v_idx++); + if (err) + goto err_out; + + /* update counts and index */ + rxr_remaining--; + rxr_idx++; } - for (; i < adapter->num_tx_queues; i++) - igb_map_tx_ring_to_vector(adapter, i, v_idx++); } + + for (; v_idx < q_vectors; v_idx++) { + int rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - v_idx); + int tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - v_idx); + err = igb_alloc_q_vector(adapter, q_vectors, v_idx, + tqpv, txr_idx, rqpv, rxr_idx); + + if (err) + goto err_out; + + /* update counts and index */ + rxr_remaining -= rqpv; + txr_remaining -= tqpv; + rxr_idx++; + txr_idx++; + } + return 0; + +err_out: + adapter->num_tx_queues = 0; + adapter->num_rx_queues = 0; + adapter->num_q_vectors = 0; + + while (v_idx--) + igb_free_q_vector(adapter, v_idx); + + return -ENOMEM; } /** @@ -1179,9 +1204,7 @@ static int igb_init_interrupt_scheme(struct igb_adapter *adapter) struct pci_dev *pdev = adapter->pdev; int err; - err = igb_set_interrupt_capability(adapter); - if (err) - return err; + igb_set_interrupt_capability(adapter); err = igb_alloc_q_vectors(adapter); if (err) { @@ -1189,24 +1212,10 @@ static int igb_init_interrupt_scheme(struct igb_adapter *adapter) goto err_alloc_q_vectors; } - err = igb_alloc_queues(adapter); - if (err) { - dev_err(&pdev->dev, "Unable to allocate memory for queues\n"); - goto err_alloc_queues; - } - - err = igb_map_ring_to_vector(adapter); - if (err) { - dev_err(&pdev->dev, "Invalid q_vector to ring mapping\n"); - goto err_map_queues; - } - + igb_cache_ring_register(adapter); return 0; -err_map_queues: - igb_free_queues(adapter); -err_alloc_queues: - igb_free_q_vectors(adapter); + err_alloc_q_vectors: igb_reset_interrupt_capability(adapter); return err; @@ -1229,11 +1238,11 @@ static int igb_request_irq(struct igb_adapter *adapter) if (!err) goto request_done; /* fall back to MSI */ + igb_free_all_tx_resources(adapter); + igb_free_all_rx_resources(adapter); igb_clear_interrupt_scheme(adapter); if (!pci_enable_msi(pdev)) adapter->flags |= IGB_FLAG_HAS_MSI; - igb_free_all_tx_resources(adapter); - igb_free_all_rx_resources(adapter); adapter->num_tx_queues = 1; adapter->num_rx_queues = 1; adapter->num_q_vectors = 1; @@ -1243,13 +1252,6 @@ static int igb_request_irq(struct igb_adapter *adapter) "Unable to allocate memory for vectors\n"); goto request_done; } - err = igb_alloc_queues(adapter); - if (err) { - dev_err(&pdev->dev, - "Unable to allocate memory for queues\n"); - igb_free_q_vectors(adapter); - goto request_done; - } igb_setup_all_tx_resources(adapter); igb_setup_all_rx_resources(adapter); } @@ -1706,10 +1708,8 @@ void igb_reset(struct igb_adapter *adapter) /* Enable h/w to recognize an 802.1Q VLAN Ethernet packet */ wr32(E1000_VET, ETHERNET_IEEE_VLAN_TYPE); -#ifdef CONFIG_IGB_PTP /* Re-enable PTP, where applicable. */ igb_ptp_reset(adapter); -#endif /* CONFIG_IGB_PTP */ igb_get_phy_info(hw); } @@ -1783,58 +1783,34 @@ static const struct net_device_ops igb_netdev_ops = { void igb_set_fw_version(struct igb_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; - u16 eeprom_verh, eeprom_verl, comb_verh, comb_verl, comb_offset; - u16 major, build, patch, fw_version; - u32 etrack_id; - - hw->nvm.ops.read(hw, 5, 1, &fw_version); - if (adapter->hw.mac.type != e1000_i211) { - hw->nvm.ops.read(hw, NVM_ETRACK_WORD, 1, &eeprom_verh); - hw->nvm.ops.read(hw, (NVM_ETRACK_WORD + 1), 1, &eeprom_verl); - etrack_id = (eeprom_verh << IGB_ETRACK_SHIFT) | eeprom_verl; - - /* combo image version needs to be found */ - hw->nvm.ops.read(hw, NVM_COMB_VER_PTR, 1, &comb_offset); - if ((comb_offset != 0x0) && - (comb_offset != IGB_NVM_VER_INVALID)) { - hw->nvm.ops.read(hw, (NVM_COMB_VER_OFF + comb_offset - + 1), 1, &comb_verh); - hw->nvm.ops.read(hw, (NVM_COMB_VER_OFF + comb_offset), - 1, &comb_verl); - - /* Only display Option Rom if it exists and is valid */ - if ((comb_verh && comb_verl) && - ((comb_verh != IGB_NVM_VER_INVALID) && - (comb_verl != IGB_NVM_VER_INVALID))) { - major = comb_verl >> IGB_COMB_VER_SHFT; - build = (comb_verl << IGB_COMB_VER_SHFT) | - (comb_verh >> IGB_COMB_VER_SHFT); - patch = comb_verh & IGB_COMB_VER_MASK; - snprintf(adapter->fw_version, - sizeof(adapter->fw_version), - "%d.%d%d, 0x%08x, %d.%d.%d", - (fw_version & IGB_MAJOR_MASK) >> - IGB_MAJOR_SHIFT, - (fw_version & IGB_MINOR_MASK) >> - IGB_MINOR_SHIFT, - (fw_version & IGB_BUILD_MASK), - etrack_id, major, build, patch); - goto out; - } - } - snprintf(adapter->fw_version, sizeof(adapter->fw_version), - "%d.%d%d, 0x%08x", - (fw_version & IGB_MAJOR_MASK) >> IGB_MAJOR_SHIFT, - (fw_version & IGB_MINOR_MASK) >> IGB_MINOR_SHIFT, - (fw_version & IGB_BUILD_MASK), etrack_id); - } else { + struct e1000_fw_version fw; + + igb_get_fw_version(hw, &fw); + + switch (hw->mac.type) { + case e1000_i211: snprintf(adapter->fw_version, sizeof(adapter->fw_version), - "%d.%d%d", - (fw_version & IGB_MAJOR_MASK) >> IGB_MAJOR_SHIFT, - (fw_version & IGB_MINOR_MASK) >> IGB_MINOR_SHIFT, - (fw_version & IGB_BUILD_MASK)); + "%2d.%2d-%d", + fw.invm_major, fw.invm_minor, fw.invm_img_type); + break; + + default: + /* if option is rom valid, display its version too */ + if (fw.or_valid) { + snprintf(adapter->fw_version, + sizeof(adapter->fw_version), + "%d.%d, 0x%08x, %d.%d.%d", + fw.eep_major, fw.eep_minor, fw.etrack_id, + fw.or_major, fw.or_build, fw.or_patch); + /* no option rom */ + } else { + snprintf(adapter->fw_version, + sizeof(adapter->fw_version), + "%d.%d, 0x%08x", + fw.eep_major, fw.eep_minor, fw.etrack_id); + } + break; } -out: return; } @@ -2141,10 +2117,8 @@ static int __devinit igb_probe(struct pci_dev *pdev, #endif -#ifdef CONFIG_IGB_PTP /* do hw tstamp init after resetting */ igb_ptp_init(adapter); -#endif /* CONFIG_IGB_PTP */ dev_info(&pdev->dev, "Intel(R) Gigabit Ethernet Network Connection\n"); /* print bus type/speed/width info */ @@ -2219,9 +2193,7 @@ static void __devexit igb_remove(struct pci_dev *pdev) struct e1000_hw *hw = &adapter->hw; pm_runtime_get_noresume(&pdev->dev); -#ifdef CONFIG_IGB_PTP igb_ptp_stop(adapter); -#endif /* CONFIG_IGB_PTP */ /* * The watchdog timer may be rescheduled, so explicitly @@ -2531,6 +2503,17 @@ static int __igb_open(struct net_device *netdev, bool resuming) if (err) goto err_req_irq; + /* Notify the stack of the actual queue counts. */ + err = netif_set_real_num_tx_queues(adapter->netdev, + adapter->num_tx_queues); + if (err) + goto err_set_queues; + + err = netif_set_real_num_rx_queues(adapter->netdev, + adapter->num_rx_queues); + if (err) + goto err_set_queues; + /* From here on the code is the same as igb_up() */ clear_bit(__IGB_DOWN, &adapter->state); @@ -2560,6 +2543,8 @@ static int __igb_open(struct net_device *netdev, bool resuming) return 0; +err_set_queues: + igb_free_irq(adapter); err_req_irq: igb_release_hw_control(adapter); igb_power_down_link(adapter); @@ -2637,10 +2622,8 @@ int igb_setup_tx_resources(struct igb_ring *tx_ring) tx_ring->size = tx_ring->count * sizeof(union e1000_adv_tx_desc); tx_ring->size = ALIGN(tx_ring->size, 4096); - tx_ring->desc = dma_alloc_coherent(dev, - tx_ring->size, - &tx_ring->dma, - GFP_KERNEL); + tx_ring->desc = dma_alloc_coherent(dev, tx_ring->size, + &tx_ring->dma, GFP_KERNEL); if (!tx_ring->desc) goto err; @@ -2777,18 +2760,16 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring) if (!rx_ring->rx_buffer_info) goto err; - /* Round up to nearest 4K */ rx_ring->size = rx_ring->count * sizeof(union e1000_adv_rx_desc); rx_ring->size = ALIGN(rx_ring->size, 4096); - rx_ring->desc = dma_alloc_coherent(dev, - rx_ring->size, - &rx_ring->dma, - GFP_KERNEL); + rx_ring->desc = dma_alloc_coherent(dev, rx_ring->size, + &rx_ring->dma, GFP_KERNEL); if (!rx_ring->desc) goto err; + rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; @@ -3106,16 +3087,10 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, /* set descriptor configuration */ srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT; -#if (PAGE_SIZE / 2) > IGB_RXBUFFER_16384 - srrctl |= IGB_RXBUFFER_16384 >> E1000_SRRCTL_BSIZEPKT_SHIFT; -#else - srrctl |= (PAGE_SIZE / 2) >> E1000_SRRCTL_BSIZEPKT_SHIFT; -#endif - srrctl |= E1000_SRRCTL_DESCTYPE_HDR_SPLIT_ALWAYS; -#ifdef CONFIG_IGB_PTP + srrctl |= IGB_RX_BUFSZ >> E1000_SRRCTL_BSIZEPKT_SHIFT; + srrctl |= E1000_SRRCTL_DESCTYPE_ADV_ONEBUF; if (hw->mac.type >= e1000_82580) srrctl |= E1000_SRRCTL_TIMESTAMP; -#endif /* CONFIG_IGB_PTP */ /* Only set Drop Enable if we are supporting multiple queues */ if (adapter->vfs_allocated_count || adapter->num_rx_queues > 1) srrctl |= E1000_SRRCTL_DROP_EN; @@ -3305,36 +3280,27 @@ static void igb_clean_rx_ring(struct igb_ring *rx_ring) unsigned long size; u16 i; + if (rx_ring->skb) + dev_kfree_skb(rx_ring->skb); + rx_ring->skb = NULL; + if (!rx_ring->rx_buffer_info) return; /* Free all the Rx ring sk_buffs */ for (i = 0; i < rx_ring->count; i++) { struct igb_rx_buffer *buffer_info = &rx_ring->rx_buffer_info[i]; - if (buffer_info->dma) { - dma_unmap_single(rx_ring->dev, - buffer_info->dma, - IGB_RX_HDR_LEN, - DMA_FROM_DEVICE); - buffer_info->dma = 0; - } - if (buffer_info->skb) { - dev_kfree_skb(buffer_info->skb); - buffer_info->skb = NULL; - } - if (buffer_info->page_dma) { - dma_unmap_page(rx_ring->dev, - buffer_info->page_dma, - PAGE_SIZE / 2, - DMA_FROM_DEVICE); - buffer_info->page_dma = 0; - } - if (buffer_info->page) { - put_page(buffer_info->page); - buffer_info->page = NULL; - buffer_info->page_offset = 0; - } + if (!buffer_info->page) + continue; + + dma_unmap_page(rx_ring->dev, + buffer_info->dma, + PAGE_SIZE, + DMA_FROM_DEVICE); + __free_page(buffer_info->page); + + buffer_info->page = NULL; } size = sizeof(struct igb_rx_buffer) * rx_ring->count; @@ -3343,6 +3309,7 @@ static void igb_clean_rx_ring(struct igb_ring *rx_ring) /* Zero out the descriptor ring */ memset(rx_ring->desc, 0, rx_ring->size); + rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; } @@ -4159,11 +4126,9 @@ static __le32 igb_tx_cmd_type(u32 tx_flags) if (tx_flags & IGB_TX_FLAGS_VLAN) cmd_type |= cpu_to_le32(E1000_ADVTXD_DCMD_VLE); -#ifdef CONFIG_IGB_PTP /* set timestamp bit if present */ if (unlikely(tx_flags & IGB_TX_FLAGS_TSTAMP)) cmd_type |= cpu_to_le32(E1000_ADVTXD_MAC_TSTAMP); -#endif /* CONFIG_IGB_PTP */ /* set segmentation bits for TSO */ if (tx_flags & IGB_TX_FLAGS_TSO) @@ -4372,9 +4337,7 @@ static inline int igb_maybe_stop_tx(struct igb_ring *tx_ring, const u16 size) netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, struct igb_ring *tx_ring) { -#ifdef CONFIG_IGB_PTP struct igb_adapter *adapter = netdev_priv(tx_ring->netdev); -#endif /* CONFIG_IGB_PTP */ struct igb_tx_buffer *first; int tso; u32 tx_flags = 0; @@ -4397,7 +4360,6 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, first->bytecount = skb->len; first->gso_segs = 1; -#ifdef CONFIG_IGB_PTP if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && !(adapter->ptp_tx_skb))) { skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; @@ -4407,7 +4369,6 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, if (adapter->hw.mac.type == e1000_82576) schedule_work(&adapter->ptp_tx_work); } -#endif /* CONFIG_IGB_PTP */ if (vlan_tx_tag_present(skb)) { tx_flags |= IGB_TX_FLAGS_VLAN; @@ -4467,10 +4428,11 @@ static netdev_tx_t igb_xmit_frame(struct sk_buff *skb, * The minimum packet size with TCTL.PSP set is 17 so pad the skb * in order to meet this minimum size requirement. */ - if (skb->len < 17) { - if (skb_padto(skb, 17)) + if (unlikely(skb->len < 17)) { + if (skb_pad(skb, 17 - skb->len)) return NETDEV_TX_OK; skb->len = 17; + skb_set_tail_pointer(skb, 17); } return igb_xmit_frame_ring(skb, igb_tx_queue_mapping(adapter, skb)); @@ -4800,7 +4762,6 @@ static irqreturn_t igb_msix_other(int irq, void *data) mod_timer(&adapter->watchdog_timer, jiffies + 1); } -#ifdef CONFIG_IGB_PTP if (icr & E1000_ICR_TS) { u32 tsicr = rd32(E1000_TSICR); @@ -4811,7 +4772,6 @@ static irqreturn_t igb_msix_other(int irq, void *data) schedule_work(&adapter->ptp_tx_work); } } -#endif /* CONFIG_IGB_PTP */ wr32(E1000_EIMS, adapter->eims_other); @@ -4851,45 +4811,63 @@ static irqreturn_t igb_msix_ring(int irq, void *data) } #ifdef CONFIG_IGB_DCA +static void igb_update_tx_dca(struct igb_adapter *adapter, + struct igb_ring *tx_ring, + int cpu) +{ + struct e1000_hw *hw = &adapter->hw; + u32 txctrl = dca3_get_tag(tx_ring->dev, cpu); + + if (hw->mac.type != e1000_82575) + txctrl <<= E1000_DCA_TXCTRL_CPUID_SHIFT; + + /* + * We can enable relaxed ordering for reads, but not writes when + * DCA is enabled. This is due to a known issue in some chipsets + * which will cause the DCA tag to be cleared. + */ + txctrl |= E1000_DCA_TXCTRL_DESC_RRO_EN | + E1000_DCA_TXCTRL_DATA_RRO_EN | + E1000_DCA_TXCTRL_DESC_DCA_EN; + + wr32(E1000_DCA_TXCTRL(tx_ring->reg_idx), txctrl); +} + +static void igb_update_rx_dca(struct igb_adapter *adapter, + struct igb_ring *rx_ring, + int cpu) +{ + struct e1000_hw *hw = &adapter->hw; + u32 rxctrl = dca3_get_tag(&adapter->pdev->dev, cpu); + + if (hw->mac.type != e1000_82575) + rxctrl <<= E1000_DCA_RXCTRL_CPUID_SHIFT; + + /* + * We can enable relaxed ordering for reads, but not writes when + * DCA is enabled. This is due to a known issue in some chipsets + * which will cause the DCA tag to be cleared. + */ + rxctrl |= E1000_DCA_RXCTRL_DESC_RRO_EN | + E1000_DCA_RXCTRL_DESC_DCA_EN; + + wr32(E1000_DCA_RXCTRL(rx_ring->reg_idx), rxctrl); +} + static void igb_update_dca(struct igb_q_vector *q_vector) { struct igb_adapter *adapter = q_vector->adapter; - struct e1000_hw *hw = &adapter->hw; int cpu = get_cpu(); if (q_vector->cpu == cpu) goto out_no_update; - if (q_vector->tx.ring) { - int q = q_vector->tx.ring->reg_idx; - u32 dca_txctrl = rd32(E1000_DCA_TXCTRL(q)); - if (hw->mac.type == e1000_82575) { - dca_txctrl &= ~E1000_DCA_TXCTRL_CPUID_MASK; - dca_txctrl |= dca3_get_tag(&adapter->pdev->dev, cpu); - } else { - dca_txctrl &= ~E1000_DCA_TXCTRL_CPUID_MASK_82576; - dca_txctrl |= dca3_get_tag(&adapter->pdev->dev, cpu) << - E1000_DCA_TXCTRL_CPUID_SHIFT; - } - dca_txctrl |= E1000_DCA_TXCTRL_DESC_DCA_EN; - wr32(E1000_DCA_TXCTRL(q), dca_txctrl); - } - if (q_vector->rx.ring) { - int q = q_vector->rx.ring->reg_idx; - u32 dca_rxctrl = rd32(E1000_DCA_RXCTRL(q)); - if (hw->mac.type == e1000_82575) { - dca_rxctrl &= ~E1000_DCA_RXCTRL_CPUID_MASK; - dca_rxctrl |= dca3_get_tag(&adapter->pdev->dev, cpu); - } else { - dca_rxctrl &= ~E1000_DCA_RXCTRL_CPUID_MASK_82576; - dca_rxctrl |= dca3_get_tag(&adapter->pdev->dev, cpu) << - E1000_DCA_RXCTRL_CPUID_SHIFT; - } - dca_rxctrl |= E1000_DCA_RXCTRL_DESC_DCA_EN; - dca_rxctrl |= E1000_DCA_RXCTRL_HEAD_DCA_EN; - dca_rxctrl |= E1000_DCA_RXCTRL_DATA_DCA_EN; - wr32(E1000_DCA_RXCTRL(q), dca_rxctrl); - } + if (q_vector->tx.ring) + igb_update_tx_dca(adapter, q_vector->tx.ring, cpu); + + if (q_vector->rx.ring) + igb_update_rx_dca(adapter, q_vector->rx.ring, cpu); + q_vector->cpu = cpu; out_no_update: put_cpu(); @@ -5545,7 +5523,6 @@ static irqreturn_t igb_intr_msi(int irq, void *data) mod_timer(&adapter->watchdog_timer, jiffies + 1); } -#ifdef CONFIG_IGB_PTP if (icr & E1000_ICR_TS) { u32 tsicr = rd32(E1000_TSICR); @@ -5556,7 +5533,6 @@ static irqreturn_t igb_intr_msi(int irq, void *data) schedule_work(&adapter->ptp_tx_work); } } -#endif /* CONFIG_IGB_PTP */ napi_schedule(&q_vector->napi); @@ -5599,7 +5575,6 @@ static irqreturn_t igb_intr(int irq, void *data) mod_timer(&adapter->watchdog_timer, jiffies + 1); } -#ifdef CONFIG_IGB_PTP if (icr & E1000_ICR_TS) { u32 tsicr = rd32(E1000_TSICR); @@ -5610,7 +5585,6 @@ static irqreturn_t igb_intr(int irq, void *data) schedule_work(&adapter->ptp_tx_work); } } -#endif /* CONFIG_IGB_PTP */ napi_schedule(&q_vector->napi); @@ -5840,6 +5814,181 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector) return !!budget; } +/** + * igb_reuse_rx_page - page flip buffer and store it back on the ring + * @rx_ring: rx descriptor ring to store buffers on + * @old_buff: donor buffer to have page reused + * + * Synchronizes page for reuse by the adapter + **/ +static void igb_reuse_rx_page(struct igb_ring *rx_ring, + struct igb_rx_buffer *old_buff) +{ + struct igb_rx_buffer *new_buff; + u16 nta = rx_ring->next_to_alloc; + + new_buff = &rx_ring->rx_buffer_info[nta]; + + /* update, and store next to alloc */ + nta++; + rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; + + /* transfer page from old buffer to new buffer */ + memcpy(new_buff, old_buff, sizeof(struct igb_rx_buffer)); + + /* sync the buffer for use by the device */ + dma_sync_single_range_for_device(rx_ring->dev, old_buff->dma, + old_buff->page_offset, + IGB_RX_BUFSZ, + DMA_FROM_DEVICE); +} + +/** + * igb_add_rx_frag - Add contents of Rx buffer to sk_buff + * @rx_ring: rx descriptor ring to transact packets on + * @rx_buffer: buffer containing page to add + * @rx_desc: descriptor containing length of buffer written by hardware + * @skb: sk_buff to place the data into + * + * This function will add the data contained in rx_buffer->page to the skb. + * This is done either through a direct copy if the data in the buffer is + * less than the skb header size, otherwise it will just attach the page as + * a frag to the skb. + * + * The function will then update the page offset if necessary and return + * true if the buffer can be reused by the adapter. + **/ +static bool igb_add_rx_frag(struct igb_ring *rx_ring, + struct igb_rx_buffer *rx_buffer, + union e1000_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + struct page *page = rx_buffer->page; + unsigned int size = le16_to_cpu(rx_desc->wb.upper.length); + + if ((size <= IGB_RX_HDR_LEN) && !skb_is_nonlinear(skb)) { + unsigned char *va = page_address(page) + rx_buffer->page_offset; + + if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { + igb_ptp_rx_pktstamp(rx_ring->q_vector, va, skb); + va += IGB_TS_HDR_LEN; + size -= IGB_TS_HDR_LEN; + } + + memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long))); + + /* we can reuse buffer as-is, just make sure it is local */ + if (likely(page_to_nid(page) == numa_node_id())) + return true; + + /* this page cannot be reused so discard it */ + put_page(page); + return false; + } + + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, + rx_buffer->page_offset, size, IGB_RX_BUFSZ); + + /* avoid re-using remote pages */ + if (unlikely(page_to_nid(page) != numa_node_id())) + return false; + +#if (PAGE_SIZE < 8192) + /* if we are only owner of page we can reuse it */ + if (unlikely(page_count(page) != 1)) + return false; + + /* flip page offset to other buffer */ + rx_buffer->page_offset ^= IGB_RX_BUFSZ; + + /* + * since we are the only owner of the page and we need to + * increment it, just set the value to 2 in order to avoid + * an unnecessary locked operation + */ + atomic_set(&page->_count, 2); +#else + /* move offset up to the next cache line */ + rx_buffer->page_offset += SKB_DATA_ALIGN(size); + + if (rx_buffer->page_offset > (PAGE_SIZE - IGB_RX_BUFSZ)) + return false; + + /* bump ref count on page before it is given to the stack */ + get_page(page); +#endif + + return true; +} + +static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring, + union e1000_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + struct igb_rx_buffer *rx_buffer; + struct page *page; + + rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + + /* + * This memory barrier is needed to keep us from reading + * any other fields out of the rx_desc until we know the + * RXD_STAT_DD bit is set + */ + rmb(); + + page = rx_buffer->page; + prefetchw(page); + + if (likely(!skb)) { + void *page_addr = page_address(page) + + rx_buffer->page_offset; + + /* prefetch first cache line of first page */ + prefetch(page_addr); +#if L1_CACHE_BYTES < 128 + prefetch(page_addr + L1_CACHE_BYTES); +#endif + + /* allocate a skb to store the frags */ + skb = netdev_alloc_skb_ip_align(rx_ring->netdev, + IGB_RX_HDR_LEN); + if (unlikely(!skb)) { + rx_ring->rx_stats.alloc_failed++; + return NULL; + } + + /* + * we will be copying header into skb->data in + * pskb_may_pull so it is in our interest to prefetch + * it now to avoid a possible cache miss + */ + prefetchw(skb->data); + } + + /* we are reusing so sync this buffer for CPU use */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + IGB_RX_BUFSZ, + DMA_FROM_DEVICE); + + /* pull page into skb */ + if (igb_add_rx_frag(rx_ring, rx_buffer, rx_desc, skb)) { + /* hand second half of page back to the ring */ + igb_reuse_rx_page(rx_ring, rx_buffer); + } else { + /* we are not reusing the buffer so unmap it */ + dma_unmap_page(rx_ring->dev, rx_buffer->dma, + PAGE_SIZE, DMA_FROM_DEVICE); + } + + /* clear contents of rx_buffer */ + rx_buffer->page = NULL; + + return skb; +} + static inline void igb_rx_checksum(struct igb_ring *ring, union e1000_adv_rx_desc *rx_desc, struct sk_buff *skb) @@ -5889,224 +6038,386 @@ static inline void igb_rx_hash(struct igb_ring *ring, skb->rxhash = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss); } -static void igb_rx_vlan(struct igb_ring *ring, - union e1000_adv_rx_desc *rx_desc, - struct sk_buff *skb) +/** + * igb_is_non_eop - process handling of non-EOP buffers + * @rx_ring: Rx ring being processed + * @rx_desc: Rx descriptor for current buffer + * @skb: current socket buffer containing buffer in progress + * + * This function updates next to clean. If the buffer is an EOP buffer + * this function exits returning false, otherwise it will place the + * sk_buff in the next buffer to be chained and return true indicating + * that this is in fact a non-EOP buffer. + **/ +static bool igb_is_non_eop(struct igb_ring *rx_ring, + union e1000_adv_rx_desc *rx_desc) { - if (igb_test_staterr(rx_desc, E1000_RXD_STAT_VP)) { - u16 vid; - if (igb_test_staterr(rx_desc, E1000_RXDEXT_STATERR_LB) && - test_bit(IGB_RING_FLAG_RX_LB_VLAN_BSWAP, &ring->flags)) - vid = be16_to_cpu(rx_desc->wb.upper.vlan); - else - vid = le16_to_cpu(rx_desc->wb.upper.vlan); + u32 ntc = rx_ring->next_to_clean + 1; - __vlan_hwaccel_put_tag(skb, vid); - } + /* fetch, update, and store next to clean */ + ntc = (ntc < rx_ring->count) ? ntc : 0; + rx_ring->next_to_clean = ntc; + + prefetch(IGB_RX_DESC(rx_ring, ntc)); + + if (likely(igb_test_staterr(rx_desc, E1000_RXD_STAT_EOP))) + return false; + + return true; } -static inline u16 igb_get_hlen(union e1000_adv_rx_desc *rx_desc) -{ - /* HW will not DMA in data larger than the given buffer, even if it - * parses the (NFS, of course) header to be larger. In that case, it - * fills the header buffer and spills the rest into the page. +/** + * igb_get_headlen - determine size of header for LRO/GRO + * @data: pointer to the start of the headers + * @max_len: total length of section to find headers in + * + * This function is meant to determine the length of headers that will + * be recognized by hardware for LRO, and GRO offloads. The main + * motivation of doing this is to only perform one pull for IPv4 TCP + * packets so that we can do basic things like calculating the gso_size + * based on the average data per packet. + **/ +static unsigned int igb_get_headlen(unsigned char *data, + unsigned int max_len) +{ + union { + unsigned char *network; + /* l2 headers */ + struct ethhdr *eth; + struct vlan_hdr *vlan; + /* l3 headers */ + struct iphdr *ipv4; + struct ipv6hdr *ipv6; + } hdr; + __be16 protocol; + u8 nexthdr = 0; /* default to not TCP */ + u8 hlen; + + /* this should never happen, but better safe than sorry */ + if (max_len < ETH_HLEN) + return max_len; + + /* initialize network frame pointer */ + hdr.network = data; + + /* set first protocol and move network header forward */ + protocol = hdr.eth->h_proto; + hdr.network += ETH_HLEN; + + /* handle any vlan tag if present */ + if (protocol == __constant_htons(ETH_P_8021Q)) { + if ((hdr.network - data) > (max_len - VLAN_HLEN)) + return max_len; + + protocol = hdr.vlan->h_vlan_encapsulated_proto; + hdr.network += VLAN_HLEN; + } + + /* handle L3 protocols */ + if (protocol == __constant_htons(ETH_P_IP)) { + if ((hdr.network - data) > (max_len - sizeof(struct iphdr))) + return max_len; + + /* access ihl as a u8 to avoid unaligned access on ia64 */ + hlen = (hdr.network[0] & 0x0F) << 2; + + /* verify hlen meets minimum size requirements */ + if (hlen < sizeof(struct iphdr)) + return hdr.network - data; + + /* record next protocol */ + nexthdr = hdr.ipv4->protocol; + hdr.network += hlen; + } else if (protocol == __constant_htons(ETH_P_IPV6)) { + if ((hdr.network - data) > (max_len - sizeof(struct ipv6hdr))) + return max_len; + + /* record next protocol */ + nexthdr = hdr.ipv6->nexthdr; + hdr.network += sizeof(struct ipv6hdr); + } else { + return hdr.network - data; + } + + /* finally sort out TCP */ + if (nexthdr == IPPROTO_TCP) { + if ((hdr.network - data) > (max_len - sizeof(struct tcphdr))) + return max_len; + + /* access doff as a u8 to avoid unaligned access on ia64 */ + hlen = (hdr.network[12] & 0xF0) >> 2; + + /* verify hlen meets minimum size requirements */ + if (hlen < sizeof(struct tcphdr)) + return hdr.network - data; + + hdr.network += hlen; + } else if (nexthdr == IPPROTO_UDP) { + if ((hdr.network - data) > (max_len - sizeof(struct udphdr))) + return max_len; + + hdr.network += sizeof(struct udphdr); + } + + /* + * If everything has gone correctly hdr.network should be the + * data section of the packet and will be the end of the header. + * If not then it probably represents the end of the last recognized + * header. */ - u16 hlen = (le16_to_cpu(rx_desc->wb.lower.lo_dword.hdr_info) & - E1000_RXDADV_HDRBUFLEN_MASK) >> E1000_RXDADV_HDRBUFLEN_SHIFT; - if (hlen > IGB_RX_HDR_LEN) - hlen = IGB_RX_HDR_LEN; - return hlen; + if ((hdr.network - data) < max_len) + return hdr.network - data; + else + return max_len; } -static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, int budget) +/** + * igb_pull_tail - igb specific version of skb_pull_tail + * @rx_ring: rx descriptor ring packet is being transacted on + * @rx_desc: pointer to the EOP Rx descriptor + * @skb: pointer to current skb being adjusted + * + * This function is an igb specific version of __pskb_pull_tail. The + * main difference between this version and the original function is that + * this function can make several assumptions about the state of things + * that allow for significant optimizations versus the standard function. + * As a result we can do things like drop a frag and maintain an accurate + * truesize for the skb. + */ +static void igb_pull_tail(struct igb_ring *rx_ring, + union e1000_adv_rx_desc *rx_desc, + struct sk_buff *skb) { - struct igb_ring *rx_ring = q_vector->rx.ring; - union e1000_adv_rx_desc *rx_desc; - const int current_node = numa_node_id(); - unsigned int total_bytes = 0, total_packets = 0; - u16 cleaned_count = igb_desc_unused(rx_ring); - u16 i = rx_ring->next_to_clean; + struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; + unsigned char *va; + unsigned int pull_len; - rx_desc = IGB_RX_DESC(rx_ring, i); + /* + * it is valid to use page_address instead of kmap since we are + * working with pages allocated out of the lomem pool per + * alloc_page(GFP_ATOMIC) + */ + va = skb_frag_address(frag); - while (igb_test_staterr(rx_desc, E1000_RXD_STAT_DD)) { - struct igb_rx_buffer *buffer_info = &rx_ring->rx_buffer_info[i]; - struct sk_buff *skb = buffer_info->skb; - union e1000_adv_rx_desc *next_rxd; + if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { + /* retrieve timestamp from buffer */ + igb_ptp_rx_pktstamp(rx_ring->q_vector, va, skb); - buffer_info->skb = NULL; - prefetch(skb->data); + /* update pointers to remove timestamp header */ + skb_frag_size_sub(frag, IGB_TS_HDR_LEN); + frag->page_offset += IGB_TS_HDR_LEN; + skb->data_len -= IGB_TS_HDR_LEN; + skb->len -= IGB_TS_HDR_LEN; - i++; - if (i == rx_ring->count) - i = 0; + /* move va to start of packet data */ + va += IGB_TS_HDR_LEN; + } + + /* + * we need the header to contain the greater of either ETH_HLEN or + * 60 bytes if the skb->len is less than 60 for skb_pad. + */ + pull_len = igb_get_headlen(va, IGB_RX_HDR_LEN); - next_rxd = IGB_RX_DESC(rx_ring, i); - prefetch(next_rxd); + /* align pull length to size of long to optimize memcpy performance */ + skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long))); - /* - * This memory barrier is needed to keep us from reading - * any other fields out of the rx_desc until we know the - * RXD_STAT_DD bit is set - */ - rmb(); + /* update all of the pointers */ + skb_frag_size_sub(frag, pull_len); + frag->page_offset += pull_len; + skb->data_len -= pull_len; + skb->tail += pull_len; +} - if (!skb_is_nonlinear(skb)) { - __skb_put(skb, igb_get_hlen(rx_desc)); - dma_unmap_single(rx_ring->dev, buffer_info->dma, - IGB_RX_HDR_LEN, - DMA_FROM_DEVICE); - buffer_info->dma = 0; +/** + * igb_cleanup_headers - Correct corrupted or empty headers + * @rx_ring: rx descriptor ring packet is being transacted on + * @rx_desc: pointer to the EOP Rx descriptor + * @skb: pointer to current skb being fixed + * + * Address the case where we are pulling data in on pages only + * and as such no data is present in the skb header. + * + * In addition if skb is not at least 60 bytes we need to pad it so that + * it is large enough to qualify as a valid Ethernet frame. + * + * Returns true if an error was encountered and skb was freed. + **/ +static bool igb_cleanup_headers(struct igb_ring *rx_ring, + union e1000_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + + if (unlikely((igb_test_staterr(rx_desc, + E1000_RXDEXT_ERR_FRAME_ERR_MASK)))) { + struct net_device *netdev = rx_ring->netdev; + if (!(netdev->features & NETIF_F_RXALL)) { + dev_kfree_skb_any(skb); + return true; } + } - if (rx_desc->wb.upper.length) { - u16 length = le16_to_cpu(rx_desc->wb.upper.length); + /* place header in linear portion of buffer */ + if (skb_is_nonlinear(skb)) + igb_pull_tail(rx_ring, rx_desc, skb); - skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags, - buffer_info->page, - buffer_info->page_offset, - length); + /* if skb_pad returns an error the skb was freed */ + if (unlikely(skb->len < 60)) { + int pad_len = 60 - skb->len; - skb->len += length; - skb->data_len += length; - skb->truesize += PAGE_SIZE / 2; + if (skb_pad(skb, pad_len)) + return true; + __skb_put(skb, pad_len); + } - if ((page_count(buffer_info->page) != 1) || - (page_to_nid(buffer_info->page) != current_node)) - buffer_info->page = NULL; - else - get_page(buffer_info->page); + return false; +} - dma_unmap_page(rx_ring->dev, buffer_info->page_dma, - PAGE_SIZE / 2, DMA_FROM_DEVICE); - buffer_info->page_dma = 0; - } +/** + * igb_process_skb_fields - Populate skb header fields from Rx descriptor + * @rx_ring: rx descriptor ring packet is being transacted on + * @rx_desc: pointer to the EOP Rx descriptor + * @skb: pointer to current skb being populated + * + * This function checks the ring, descriptor, and packet information in + * order to populate the hash, checksum, VLAN, timestamp, protocol, and + * other fields within the skb. + **/ +static void igb_process_skb_fields(struct igb_ring *rx_ring, + union e1000_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + struct net_device *dev = rx_ring->netdev; - if (!igb_test_staterr(rx_desc, E1000_RXD_STAT_EOP)) { - struct igb_rx_buffer *next_buffer; - next_buffer = &rx_ring->rx_buffer_info[i]; - buffer_info->skb = next_buffer->skb; - buffer_info->dma = next_buffer->dma; - next_buffer->skb = skb; - next_buffer->dma = 0; - goto next_desc; - } + igb_rx_hash(rx_ring, rx_desc, skb); - if (unlikely((igb_test_staterr(rx_desc, - E1000_RXDEXT_ERR_FRAME_ERR_MASK)) - && !(rx_ring->netdev->features & NETIF_F_RXALL))) { - dev_kfree_skb_any(skb); - goto next_desc; - } + igb_rx_checksum(rx_ring, rx_desc, skb); -#ifdef CONFIG_IGB_PTP - igb_ptp_rx_hwtstamp(q_vector, rx_desc, skb); -#endif /* CONFIG_IGB_PTP */ - igb_rx_hash(rx_ring, rx_desc, skb); - igb_rx_checksum(rx_ring, rx_desc, skb); - igb_rx_vlan(rx_ring, rx_desc, skb); + igb_ptp_rx_hwtstamp(rx_ring->q_vector, rx_desc, skb); - total_bytes += skb->len; - total_packets++; + if ((dev->features & NETIF_F_HW_VLAN_RX) && + igb_test_staterr(rx_desc, E1000_RXD_STAT_VP)) { + u16 vid; + if (igb_test_staterr(rx_desc, E1000_RXDEXT_STATERR_LB) && + test_bit(IGB_RING_FLAG_RX_LB_VLAN_BSWAP, &rx_ring->flags)) + vid = be16_to_cpu(rx_desc->wb.upper.vlan); + else + vid = le16_to_cpu(rx_desc->wb.upper.vlan); - skb->protocol = eth_type_trans(skb, rx_ring->netdev); + __vlan_hwaccel_put_tag(skb, vid); + } - napi_gro_receive(&q_vector->napi, skb); + skb_record_rx_queue(skb, rx_ring->queue_index); - budget--; -next_desc: - if (!budget) - break; + skb->protocol = eth_type_trans(skb, rx_ring->netdev); +} + +static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) +{ + struct igb_ring *rx_ring = q_vector->rx.ring; + struct sk_buff *skb = rx_ring->skb; + unsigned int total_bytes = 0, total_packets = 0; + u16 cleaned_count = igb_desc_unused(rx_ring); + + do { + union e1000_adv_rx_desc *rx_desc; - cleaned_count++; /* return some buffers to hardware, one at a time is too slow */ if (cleaned_count >= IGB_RX_BUFFER_WRITE) { igb_alloc_rx_buffers(rx_ring, cleaned_count); cleaned_count = 0; } - /* use prefetched values */ - rx_desc = next_rxd; - } + rx_desc = IGB_RX_DESC(rx_ring, rx_ring->next_to_clean); - rx_ring->next_to_clean = i; - u64_stats_update_begin(&rx_ring->rx_syncp); - rx_ring->rx_stats.packets += total_packets; - rx_ring->rx_stats.bytes += total_bytes; - u64_stats_update_end(&rx_ring->rx_syncp); - q_vector->rx.total_packets += total_packets; - q_vector->rx.total_bytes += total_bytes; + if (!igb_test_staterr(rx_desc, E1000_RXD_STAT_DD)) + break; - if (cleaned_count) - igb_alloc_rx_buffers(rx_ring, cleaned_count); + /* retrieve a buffer from the ring */ + skb = igb_fetch_rx_buffer(rx_ring, rx_desc, skb); - return !!budget; -} + /* exit if we failed to retrieve a buffer */ + if (!skb) + break; -static bool igb_alloc_mapped_skb(struct igb_ring *rx_ring, - struct igb_rx_buffer *bi) -{ - struct sk_buff *skb = bi->skb; - dma_addr_t dma = bi->dma; + cleaned_count++; - if (dma) - return true; + /* fetch next buffer in frame if non-eop */ + if (igb_is_non_eop(rx_ring, rx_desc)) + continue; - if (likely(!skb)) { - skb = netdev_alloc_skb_ip_align(rx_ring->netdev, - IGB_RX_HDR_LEN); - bi->skb = skb; - if (!skb) { - rx_ring->rx_stats.alloc_failed++; - return false; + /* verify the packet layout is correct */ + if (igb_cleanup_headers(rx_ring, rx_desc, skb)) { + skb = NULL; + continue; } - /* initialize skb for ring */ - skb_record_rx_queue(skb, rx_ring->queue_index); - } + /* probably a little skewed due to removing CRC */ + total_bytes += skb->len; - dma = dma_map_single(rx_ring->dev, skb->data, - IGB_RX_HDR_LEN, DMA_FROM_DEVICE); + /* populate checksum, timestamp, VLAN, and protocol */ + igb_process_skb_fields(rx_ring, rx_desc, skb); - if (dma_mapping_error(rx_ring->dev, dma)) { - rx_ring->rx_stats.alloc_failed++; - return false; - } + napi_gro_receive(&q_vector->napi, skb); - bi->dma = dma; - return true; + /* reset skb pointer */ + skb = NULL; + + /* update budget accounting */ + total_packets++; + } while (likely(total_packets < budget)); + + /* place incomplete frames back on ring for completion */ + rx_ring->skb = skb; + + u64_stats_update_begin(&rx_ring->rx_syncp); + rx_ring->rx_stats.packets += total_packets; + rx_ring->rx_stats.bytes += total_bytes; + u64_stats_update_end(&rx_ring->rx_syncp); + q_vector->rx.total_packets += total_packets; + q_vector->rx.total_bytes += total_bytes; + + if (cleaned_count) + igb_alloc_rx_buffers(rx_ring, cleaned_count); + + return (total_packets < budget); } static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, struct igb_rx_buffer *bi) { struct page *page = bi->page; - dma_addr_t page_dma = bi->page_dma; - unsigned int page_offset = bi->page_offset ^ (PAGE_SIZE / 2); + dma_addr_t dma; - if (page_dma) + /* since we are recycling buffers we should seldom need to alloc */ + if (likely(page)) return true; - if (!page) { - page = __skb_alloc_page(GFP_ATOMIC, bi->skb); - bi->page = page; - if (unlikely(!page)) { - rx_ring->rx_stats.alloc_failed++; - return false; - } + /* alloc new page for storage */ + page = __skb_alloc_page(GFP_ATOMIC | __GFP_COLD, NULL); + if (unlikely(!page)) { + rx_ring->rx_stats.alloc_failed++; + return false; } - page_dma = dma_map_page(rx_ring->dev, page, - page_offset, PAGE_SIZE / 2, - DMA_FROM_DEVICE); + /* map page for use */ + dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE); + + /* + * if mapping failed free memory back to system since + * there isn't much point in holding memory we can't use + */ + if (dma_mapping_error(rx_ring->dev, dma)) { + __free_page(page); - if (dma_mapping_error(rx_ring->dev, page_dma)) { rx_ring->rx_stats.alloc_failed++; return false; } - bi->page_dma = page_dma; - bi->page_offset = page_offset; + bi->dma = dma; + bi->page = page; + bi->page_offset = 0; + return true; } @@ -6120,22 +6431,23 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count) struct igb_rx_buffer *bi; u16 i = rx_ring->next_to_use; + /* nothing to do */ + if (!cleaned_count) + return; + rx_desc = IGB_RX_DESC(rx_ring, i); bi = &rx_ring->rx_buffer_info[i]; i -= rx_ring->count; - while (cleaned_count--) { - if (!igb_alloc_mapped_skb(rx_ring, bi)) - break; - - /* Refresh the desc even if buffer_addrs didn't change - * because each write-back erases this info. */ - rx_desc->read.hdr_addr = cpu_to_le64(bi->dma); - + do { if (!igb_alloc_mapped_page(rx_ring, bi)) break; - rx_desc->read.pkt_addr = cpu_to_le64(bi->page_dma); + /* + * Refresh the desc even if buffer_addrs didn't change + * because each write-back erases this info. + */ + rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset); rx_desc++; bi++; @@ -6148,17 +6460,25 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count) /* clear the hdr_addr for the next_to_use descriptor */ rx_desc->read.hdr_addr = 0; - } + + cleaned_count--; + } while (cleaned_count); i += rx_ring->count; if (rx_ring->next_to_use != i) { + /* record the next descriptor to use */ rx_ring->next_to_use = i; - /* Force memory writes to complete before letting h/w + /* update next to alloc since we have filled the ring */ + rx_ring->next_to_alloc = i; + + /* + * Force memory writes to complete before letting h/w * know there are new descriptors to fetch. (Only * applicable for weak-ordered memory model archs, - * such as IA-64). */ + * such as IA-64). + */ wmb(); writel(i, rx_ring->tail); } @@ -6207,10 +6527,8 @@ static int igb_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) case SIOCGMIIREG: case SIOCSMIIREG: return igb_mii_ioctl(netdev, ifr, cmd); -#ifdef CONFIG_IGB_PTP case SIOCSHWTSTAMP: return igb_ptp_hwtstamp_ioctl(netdev, ifr, cmd); -#endif /* CONFIG_IGB_PTP */ default: return -EOPNOTSUPP; } @@ -6492,7 +6810,9 @@ static int igb_resume(struct device *dev) wr32(E1000_WUS, ~0); if (netdev->flags & IFF_UP) { + rtnl_lock(); err = __igb_open(netdev, true); + rtnl_unlock(); if (err) return err; } |