/******************************************************************************* Intel PRO/1000 Linux driver Copyright(c) 1999 - 2008 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, version 2, as published by the Free Software Foundation. This program is distributed in the hope it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with this program; if not, write to the Free Software Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. The full GNU General Public License is included in this distribution in the file called "COPYING". Contact Information: Linux NICS e1000-devel Mailing List Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 *******************************************************************************/ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include "e1000.h" #define DRV_VERSION "1.0.2-k2" char e1000e_driver_name[] = "e1000e"; const char e1000e_driver_version[] = DRV_VERSION; static const struct e1000_info *e1000_info_tbl[] = { [board_82571] = &e1000_82571_info, [board_82572] = &e1000_82572_info, [board_82573] = &e1000_82573_info, [board_82574] = &e1000_82574_info, [board_82583] = &e1000_82583_info, [board_80003es2lan] = &e1000_es2_info, [board_ich8lan] = &e1000_ich8_info, [board_ich9lan] = &e1000_ich9_info, [board_ich10lan] = &e1000_ich10_info, [board_pchlan] = &e1000_pch_info, }; #ifdef DEBUG /** * e1000_get_hw_dev_name - return device name string * used by hardware layer to print debugging information **/ char *e1000e_get_hw_dev_name(struct e1000_hw *hw) { return hw->adapter->netdev->name; } #endif /** * e1000_desc_unused - calculate if we have unused descriptors **/ static int e1000_desc_unused(struct e1000_ring *ring) { if (ring->next_to_clean > ring->next_to_use) return ring->next_to_clean - ring->next_to_use - 1; return ring->count + ring->next_to_clean - ring->next_to_use - 1; } /** * e1000_receive_skb - helper function to handle Rx indications * @adapter: board private structure * @status: descriptor status field as written by hardware * @vlan: descriptor vlan field as written by hardware (no le/be conversion) * @skb: pointer to sk_buff to be indicated to stack **/ static void e1000_receive_skb(struct e1000_adapter *adapter, struct net_device *netdev, struct sk_buff *skb, u8 status, __le16 vlan) { skb->protocol = eth_type_trans(skb, netdev); if (adapter->vlgrp && (status & E1000_RXD_STAT_VP)) vlan_gro_receive(&adapter->napi, adapter->vlgrp, le16_to_cpu(vlan), skb); else napi_gro_receive(&adapter->napi, skb); } /** * e1000_rx_checksum - Receive Checksum Offload for 82543 * @adapter: board private structure * @status_err: receive descriptor status and error fields * @csum: receive descriptor csum field * @sk_buff: socket buffer with received data **/ static void e1000_rx_checksum(struct e1000_adapter *adapter, u32 status_err, u32 csum, struct sk_buff *skb) { u16 status = (u16)status_err; u8 errors = (u8)(status_err >> 24); skb->ip_summed = CHECKSUM_NONE; /* Ignore Checksum bit is set */ if (status & E1000_RXD_STAT_IXSM) return; /* TCP/UDP checksum error bit is set */ if (errors & E1000_RXD_ERR_TCPE) { /* let the stack verify checksum errors */ adapter->hw_csum_err++; return; } /* TCP/UDP Checksum has not been calculated */ if (!(status & (E1000_RXD_STAT_TCPCS | E1000_RXD_STAT_UDPCS))) return; /* It must be a TCP or UDP packet with a valid checksum */ if (status & E1000_RXD_STAT_TCPCS) { /* TCP checksum is good */ skb->ip_summed = CHECKSUM_UNNECESSARY; } else { /* * IP fragment with UDP payload * Hardware complements the payload checksum, so we undo it * and then put the value in host order for further stack use. */ __sum16 sum = (__force __sum16)htons(csum); skb->csum = csum_unfold(~sum); skb->ip_summed = CHECKSUM_COMPLETE; } adapter->hw_csum_good++; } /** * e1000_alloc_rx_buffers - Replace used receive buffers; legacy & extended * @adapter: address of board private structure **/ static void e1000_alloc_rx_buffers(struct e1000_adapter *adapter, int cleaned_count) { struct net_device *netdev = adapter->netdev; struct pci_dev *pdev = adapter->pdev; struct e1000_ring *rx_ring = adapter->rx_ring; struct e1000_rx_desc *rx_desc; struct e1000_buffer *buffer_info; struct sk_buff *skb; unsigned int i; unsigned int bufsz = adapter->rx_buffer_len + NET_IP_ALIGN; i = rx_ring->next_to_use; buffer_info = &rx_ring->buffer_info[i]; while (cleaned_count--) { skb = buffer_info->skb; if (skb) { skb_trim(skb, 0); goto map_skb; } skb = netdev_alloc_skb(netdev, bufsz); if (!skb) { /* Better luck next round */ adapter->alloc_rx_buff_failed++; break; } /* * 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); buffer_info->skb = skb; map_skb: buffer_info->dma = pci_map_single(pdev, skb->data, adapter->rx_buffer_len, PCI_DMA_FROMDEVICE); if (pci_dma_mapping_error(pdev, buffer_info->dma)) { dev_err(&pdev->dev, "RX DMA map failed\n"); adapter->rx_dma_failed++; break; } rx_desc = E1000_RX_DESC(*rx_ring, i); rx_desc->buffer_addr = cpu_to_le64(buffer_info->dma); i++; if (i == rx_ring->count) i = 0; buffer_info = &rx_ring->buffer_info[i]; } if (rx_ring->next_to_use != i) { rx_ring->next_to_use = i; if (i-- == 0) i = (rx_ring->count - 1); /* * Force memory writes to complete before letting h/w * know there are new descriptors to fetch. (Only * applicable for weak-ordered memory model archs, * such as IA-64). */ wmb(); writel(i, adapter->hw.hw_addr + rx_ring->tail); } } /** * e1000_alloc_rx_buffers_ps - Replace used receive buffers; packet split * @adapter: address of board private structure **/ static void e1000_alloc_rx_buffers_ps(struct e1000_adapter *adapter, int cleaned_count) { struct net_device *netdev = adapter->netdev; struct pci_dev *pdev = adapter->pdev; union e1000_rx_desc_packet_split *rx_desc; struct e1000_ring *rx_ring = adapter->rx_ring; struct e1000_buffer *buffer_info; struct e1000_ps_page *ps_page; struct sk_buff *skb; unsigned int i, j; i = rx_ring->next_to_use; buffer_info = &rx_ring->buffer_info[i]; while (cleaned_count--) { rx_desc = E1000_RX_DESC_PS(*rx_ring, i); for (j = 0; j < PS_PAGE_BUFFERS; j++) { ps_page = &buffer_info->ps_pages[j]; if (j >= adapter->rx_ps_pages) { /* all unused desc entries get hw null ptr */ rx_desc->read.buffer_addr[j+1] = ~cpu_to_le64(0); continue; } if (!ps_page->page) { ps_page->page = alloc_page(GFP_ATOMIC); if (!ps_page->page) { adapter->alloc_rx_buff_failed++; goto no_buffers; } ps_page->dma = pci_map_page(pdev, ps_page->page, 0, PAGE_SIZE, PCI_DMA_FROMDEVICE); if (pci_dma_mapping_error(pdev, ps_page->dma)) { dev_err(&adapter->pdev->dev, "RX DMA page map failed\n"); adapter->rx_dma_failed++; goto no_buffers; } } /* * Refresh the desc even if buffer_addrs * didn't change because each write-back * erases this info. */ rx_desc->read.buffer_addr[j+1] = cpu_to_le64(ps_page->dma); } skb = netdev_alloc_skb(netdev, adapter->rx_ps_bsize0 + NET_IP_ALIGN); if (!skb) { adapter->alloc_rx_buff_failed++; break; } /* * 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); buffer_info->skb = skb; buffer_info->dma = pci_map_single(pdev, skb->data, adapter->rx_ps_bsize0, PCI_DMA_FROMDEVICE); if (pci_dma_mapping_error(pdev, buffer_info->dma)) { dev_err(&pdev->dev, "RX DMA map failed\n"); adapter->rx_dma_failed++; /* cleanup skb */ dev_kfree_skb_any(skb); buffer_info->skb = NULL; break; } rx_desc->read.buffer_addr[0] = cpu_to_le64(buffer_info->dma); i++; if (i == rx_ring->count) i = 0; buffer_info = &rx_ring->buffer_info[i]; } no_buffers: if (rx_ring->next_to_use != i) { rx_ring->next_to_use = i; if (!(i--)) i = (rx_ring->count - 1); /* * Force memory writes to complete before letting h/w * know there are new descriptors to fetch. (Only * applicable for weak-ordered memory model archs, * such as IA-64). */ wmb(); /* * Hardware increments by 16 bytes, but packet split * descriptors are 32 bytes...so we increment tail * twice as much. */ writel(i<<1, adapter->hw.hw_addr + rx_ring->tail); } } /** * e1000_alloc_jumbo_rx_buffers - Replace used jumbo receive buffers * @adapter: address of board private structure * @cleaned_count: number of buffers to allocate this pass **/ static void e1000_alloc_jumbo_rx_buffers(struct e1000_adapter *adapter, int cleaned_count) { struct net_device *netdev = adapter->netdev; struct pci_dev *pdev = adapter->pdev; struct e1000_rx_desc *rx_desc; struct e1000_ring *rx_ring = adapter->rx_ring; struct e1000_buffer *buffer_info; struct sk_buff *skb; unsigned int i; unsigned int bufsz = 256 - 16 /* for skb_reserve */ - NET_IP_ALIGN; i = rx_ring->next_to_use; buffer_info = &rx_ring->buffer_info[i]; while (cleaned_count--) { skb = buffer_info->skb; if (skb) { skb_trim(skb, 0); goto check_page; } skb = netdev_alloc_skb(netdev, bufsz); if (unlikely(!skb)) { /* Better luck next round */ adapter->alloc_rx_buff_failed++; break; } /* 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); buffer_info->skb = skb; check_page: /* allocate a new page if necessary */ if (!buffer_info->page) { buffer_info->page = alloc_page(GFP_ATOMIC); if (unlikely(!buffer_info->page)) { adapter->alloc_rx_buff_failed++; break; } } if (!buffer_info->dma) buffer_info->dma = pci_map_page(pdev, buffer_info->page, 0, PAGE_SIZE, PCI_DMA_FROMDEVICE); rx_desc = E1000_RX_DESC(*rx_ring, i); rx_desc->buffer_addr = cpu_to_le64(buffer_info->dma); if (unlikely(++i == rx_ring->count)) i = 0; buffer_info = &rx_ring->buffer_info[i]; } if (likely(rx_ring->next_to_use != i)) { rx_ring->next_to_use = i; if (unlikely(i-- == 0)) i = (rx_ring->count - 1); /* Force memory writes to complete before letting h/w * know there are new descriptors to fetch. (Only * applicable for weak-ordered memory model archs, * such as IA-64). */ wmb(); writel(i, adapter->hw.hw_addr + rx_ring->tail); } } /** * e1000_clean_rx_irq - Send received data up the network stack; legacy * @adapter: board private structure * * the return value indicates whether actual cleaning was done, there * is no guarantee that everything was cleaned **/ static bool e1000_clean_rx_irq(struct e1000_adapter *adapter, int *work_done, int work_to_do) { struct net_device *netdev = adapter->netdev; struct pci_dev *pdev = adapter->pdev; struct e1000_ring *rx_ring = adapter->rx_ring; struct e1000_rx_desc *rx_desc, *next_rxd; struct e1000_buffer *buffer_info, *next_buffer; u32 length; unsigned int i; int cleaned_count = 0; bool cleaned = 0; unsigned int total_rx_bytes = 0, total_rx_packets = 0; i = rx_ring->next_to_clean; rx_desc = E1000_RX_DESC(*rx_ring, i); buffer_info = &rx_ring->buffer_info[i]; while (rx_desc->status & E1000_RXD_STAT_DD) { struct sk_buff *skb; u8 status; if (*work_done >= work_to_do) break; (*work_done)++; status = rx_desc->status; skb = buffer_info->skb; buffer_info->skb = NULL; prefetch(skb->data - NET_IP_ALIGN); i++; if (i == rx_ring->count) i = 0; next_rxd = E1000_RX_DESC(*rx_ring, i); prefetch(next_rxd); next_buffer = &rx_ring->buffer_info[i]; cleaned = 1; cleaned_count++; pci_unmap_single(pdev, buffer_info->dma, adapter->rx_buffer_len, PCI_DMA_FROMDEVICE); buffer_info->dma = 0; length = le16_to_cpu(rx_desc->length); /* !EOP means multiple descriptors were used to store a single * packet, also make sure the frame isn't just CRC only */ if (!(status & E1000_RXD_STAT_EOP) || (length <= 4)) { /* All receives must fit into a single buffer */ e_dbg("%s: Receive packet consumed multiple buffers\n", netdev->name); /* recycle */ buffer_info->skb = skb; goto next_desc; } if (rx_desc->errors & E1000_RXD_ERR_FRAME_ERR_MASK) { /* recycle */ buffer_info->skb = skb; goto next_desc; } /* adjust length to remove Ethernet CRC */ if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) length -= 4; total_rx_bytes += length; total_rx_packets++; /* * code added for copybreak, this should improve * performance for small packets with large amounts * of reassembly being done in the stack */ if (length < copybreak) { struct sk_buff *new_skb = netdev_alloc_skb(netdev, length + NET_IP_ALIGN); if (new_skb) { skb_reserve(new_skb, NET_IP_ALIGN); skb_copy_to_linear_data_offset(new_skb, -NET_IP_ALIGN, (skb->data - NET_IP_ALIGN), (length + NET_IP_ALIGN)); /* save the skb in buffer_info as good */ buffer_info->skb = skb; skb = new_skb; } /* else just continue with the old one */ } /* end copybreak code */ skb_put(skb, length); /* Receive Checksum Offload */ e1000_rx_checksum(adapter, (u32)(status) | ((u32)(rx_desc->errors) << 24), le16_to_cpu(rx_desc->csum), skb); e1000_receive_skb(adapter, netdev, skb,status,rx_desc->special); next_desc: rx_desc->status = 0; /* return some buffers to hardware, one at a time is too slow */ if (cleaned_count >= E1000_RX_BUFFER_WRITE) { adapter->alloc_rx_buf(adapter, cleaned_count); cleaned_count = 0; } /* use prefetched values */ rx_desc = next_rxd; buffer_info = next_buffer; } rx_ring->next_to_clean = i; cleaned_count = e1000_desc_unused(rx_ring); if (cleaned_count) adapter->alloc_rx_buf(adapter, cleaned_count); adapter->total_rx_bytes += total_rx_bytes; adapter->total_rx_packets += total_rx_packets; adapter->net_stats.rx_bytes += total_rx_bytes; adapter->net_stats.rx_packets += total_rx_packets; return cleaned; } static void e1000_put_txbuf(struct e1000_adapter *adapter, struct e1000_buffer *buffer_info) { buffer_info->dma = 0; if (buffer_info->skb) { skb_dma_unmap(&adapter->pdev->dev, buffer_info->skb, DMA_TO_DEVICE); dev_kfree_skb_any(buffer_info->skb); buffer_info->skb = NULL; } buffer_info->time_stamp = 0; } static void e1000_print_tx_hang(struct e1000_adapter *adapter) { struct e1000_ring *tx_ring = adapter->tx_ring; unsigned int i = tx_ring->next_to_clean; unsigned int eop = tx_ring->buffer_info[i].next_to_watch; struct e1000_tx_desc *eop_desc = E1000_TX_DESC(*tx_ring, eop); /* detected Tx unit hang */ e_err("Detected Tx Unit Hang:\n" " TDH <%x>\n" " TDT <%x>\n" " next_to_use <%x>\n" " next_to_clean <%x>\n" "buffer_info[next_to_clean]:\n" " time_stamp <%lx>\n" " next_to_watch <%x>\n" " jiffies <%lx>\n" " next_to_watch.status <%x>\n", readl(adapter->hw.hw_addr + tx_ring->head), readl(adapter->hw.hw_addr + tx_ring->tail), tx_ring->next_to_use, tx_ring->next_to_clean, tx_ring->buffer_info[eop].time_stamp, eop, jiffies, eop_desc->upper.fields.status); } /** * e1000_clean_tx_irq - Reclaim resources after transmit completes * @adapter: board private structure * * the return value indicates whether actual cleaning was done, there * is no guarantee that everything was cleaned **/ static bool e1000_clean_tx_irq(struct e1000_adapter *adapter) { struct net_device *netdev = adapter->netdev; struct e1000_hw *hw = &adapter->hw; struct e1000_ring *tx_ring = adapter->tx_ring; struct e1000_tx_desc *tx_desc, *eop_desc; struct e1000_buffer *buffer_info; unsigned int i, eop; unsigned int count = 0; unsigned int total_tx_bytes = 0, total_tx_packets = 0; i = tx_ring->next_to_clean; eop = tx_ring->buffer_info[i].next_to_watch; eop_desc = E1000_TX_DESC(*tx_ring, eop); while ((eop_desc->upper.data & cpu_to_le32(E1000_TXD_STAT_DD)) && (count < tx_ring->count)) { bool cleaned = false; for (; !cleaned; count++) { tx_desc = E1000_TX_DESC(*tx_ring, i); buffer_info = &tx_ring->buffer_info[i]; cleaned = (i == eop); if (cleaned) { struct sk_buff *skb = buffer_info->skb; unsigned int segs, bytecount; segs = skb_shinfo(skb)->gso_segs ?: 1; /* multiply data chunks by size of headers */ bytecount = ((segs - 1) * skb_headlen(skb)) + skb->len; total_tx_packets += segs; total_tx_bytes += bytecount; } e1000_put_txbuf(adapter, buffer_info); tx_desc->upper.data = 0; i++; if (i == tx_ring->count) i = 0; } eop = tx_ring->buffer_info[i].next_to_watch; eop_desc = E1000_TX_DESC(*tx_ring, eop); } tx_ring->next_to_clean = i; #define TX_WAKE_THRESHOLD 32 if (count && netif_carrier_ok(netdev) && e1000_desc_unused(tx_ring) >= TX_WAKE_THRESHOLD) { /* Make sure that anybody stopping the queue after this * sees the new next_to_clean. */ smp_mb(); if (netif_queue_stopped(netdev) && !(test_bit(__E1000_DOWN, &adapter->state))) { netif_wake_queue(netdev); ++adapter->restart_queue; } } if (adapter->detect_tx_hung) { /* Detect a transmit hang in hardware, this serializes the * check with the clearing of time_stamp and movement of i */ adapter->detect_tx_hung = 0; if (tx_ring->buffer_info[i].time_stamp && time_after(jiffies, tx_ring->buffer_info[i].time_stamp + (adapter->tx_timeout_factor * HZ)) && !(er32(STATUS) & E1000_STATUS_TXOFF)) { e1000_print_tx_hang(adapter); netif_stop_queue(netdev); } } adapter->total_tx_bytes += total_tx_bytes; adapter->total_tx_packets += total_tx_packets; adapter->net_stats.tx_bytes += total_tx_bytes; adapter->net_stats.tx_packets += total_tx_packets; return (count < tx_ring->count); } /** * e1000_clean_rx_irq_ps - Send received data up the network stack; packet split * @adapter: board private structure * * the return value indicates whether actual cleaning was done, there * is no guarantee that everything was cleaned **/ static bool e1000_clean_rx_irq_ps(struct e1000_adapter *adapter, int *work_done, int work_to_do) { union e1000_rx_desc_packet_split *rx_desc, *next_rxd; struct net_device *netdev = adapter->netdev; struct pci_dev *pdev = adapter->pdev; struct e1000_ring *rx_ring = adapter->rx_ring; struct e1000_buffer *buffer_info, *next_buffer; struct e1000_ps_page *ps_page; struct sk_buff *skb; unsigned int i, j; u32 length, staterr; int cleaned_count = 0; bool cleaned = 0; unsigned int total_rx_bytes = 0, total_rx_packets = 0; i = rx_ring->next_to_clean; rx_desc = E1000_RX_DESC_PS(*rx_ring, i); staterr = le32_to_cpu(rx_desc->wb.middle.status_error); buffer_info = &rx_ring->buffer_info[i]; while (staterr & E1000_RXD_STAT_DD) { if (*work_done >= work_to_do) break; (*work_done)++; skb = buffer_info->skb; /* in the packet split case this is header only */ prefetch(skb->data - NET_IP_ALIGN); i++; if (i == rx_ring->count) i = 0; next_rxd = E1000_RX_DESC_PS(*rx_ring, i); prefetch(next_rxd); next_buffer = &rx_ring->buffer_info[i]; cleaned = 1; cleaned_count++; pci_unmap_single(pdev, buffer_info->dma, adapter->rx_ps_bsize0, PCI_DMA_FROMDEVICE); buffer_info->dma = 0; if (!(staterr & E1000_RXD_STAT_EOP)) { e_dbg("%s: Packet Split buffers didn't pick up the " "full packet\n", netdev->name); dev_kfree_skb_irq(skb); goto next_desc; } if (staterr & E1000_RXDEXT_ERR_FRAME_ERR_MASK) { dev_kfree_skb_irq(skb); goto next_desc; } length = le16_to_cpu(rx_desc->wb.middle.length0); if (!length) { e_dbg("%s: Last part of the packet spanning multiple " "descriptors\n", netdev->name); dev_kfree_skb_irq(skb); goto next_desc; } /* Good Receive */ skb_put(skb, length); { /* * this looks ugly, but it seems compiler issues make it * more efficient than reusing j */ int l1 = le16_to_cpu(rx_desc->wb.upper.length[0]); /* * page alloc/put takes too long and effects small packet * throughput, so unsplit small packets and save the alloc/put * only valid in softirq (napi) context to call kmap_* */ if (l1 && (l1 <= copybreak) && ((length + l1) <= adapter->rx_ps_bsize0)) { u8 *vaddr; ps_page = &buffer_info->ps_pages[0]; /* * there is no documentation about how to call * kmap_atomic, so we can't hold the mapping * very long */ pci_dma_sync_single_for_cpu(pdev, ps_page->dma, PAGE_SIZE, PCI_DMA_FROMDEVICE); vaddr = kmap_atomic(ps_page->page, KM_SKB_DATA_SOFTIRQ); memcpy(skb_tail_pointer(skb), vaddr, l1); kunmap_atomic(vaddr, KM_SKB_DATA_SOFTIRQ); pci_dma_sync_single_for_device(pdev, ps_page->dma, PAGE_SIZE, PCI_DMA_FROMDEVICE); /* remove the CRC */ if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) l1 -= 4; skb_put(skb, l1); goto copydone; } /* if */ } for (j = 0; j < PS_PAGE_BUFFERS; j++) { length = le16_to_cpu(rx_desc->wb.upper.length[j]); if (!length) break; ps_page = &buffer_info->ps_pages[j]; pci_unmap_page(pdev, ps_page->dma, PAGE_SIZE, PCI_DMA_FROMDEVICE); ps_page->dma = 0; skb_fill_page_desc(skb, j, ps_page->page, 0, length); ps_page->page = NULL; skb->len += length; skb->data_len += length; skb->truesize += length; } /* strip the ethernet crc, problem is we're using pages now so * this whole operation can get a little cpu intensive */ if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) pskb_trim(skb, skb->len - 4); copydone: total_rx_bytes += skb->len; total_rx_packets++; e1000_rx_checksum(adapter, staterr, le16_to_cpu( rx_desc->wb.lower.hi_dword.csum_ip.csum), skb); if (rx_desc->wb.upper.header_status & cpu_to_le16(E1000_RXDPS_HDRSTAT_HDRSP)) adapter->rx_hdr_split++; e1000_receive_skb(adapter, netdev, skb, staterr, rx_desc->wb.middle.vlan); next_desc: rx_desc->wb.middle.status_error &= cpu_to_le32(~0xFF); buffer_info->skb = NULL; /* return some buffers to hardware, one at a time is too slow */ if (cleaned_count >= E1000_RX_BUFFER_WRITE) { adapter->alloc_rx_buf(adapter, cleaned_count); cleaned_count = 0; } /* use prefetched values */ rx_desc = next_rxd; buffer_info = next_buffer; staterr = le32_to_cpu(rx_desc->wb.middle.status_error); } rx_ring->next_to_clean = i; cleaned_count = e1000_desc_unused(rx_ring); if (cleaned_count) adapter->alloc_rx_buf(adapter, cleaned_count); adapter->total_rx_bytes += total_rx_bytes; adapter->total_rx_packets += total_rx_packets; adapter->net_stats.rx_bytes += total_rx_bytes; adapter->net_stats.rx_packets += total_rx_packets; return cleaned; } /** * e1000_consume_page - helper function **/ static void e1000_consume_page(struct e1000_buffer *bi, struct sk_buff *skb, u16 length) { bi->page = NULL; skb->len += length; skb->data_len += length; skb->truesize += length; } /** * e1000_clean_jumbo_rx_irq - Send received data up the network stack; legacy * @adapter: board private structure * * the return value indicates whether actual cleaning was done, there * is no guarantee that everything was cleaned **/ static bool e1000_clean_jumbo_rx_irq(struct e1000_adapter *adapter, int *work_done, int work_to_do) { struct net_device *netdev = adapter->netdev; struct pci_dev *pdev = adapter->pdev; struct e1000_ring *rx_ring = adapter->rx_ring; struct e1000_rx_desc *rx_desc, *next_rxd; struct e1000_buffer *buffer_info, *next_buffer; u32 length; unsigned int i; int cleaned_count = 0; bool cleaned = false; unsigned int total_rx_bytes=0, total_rx_packets=0; i = rx_ring->next_to_clean; rx_desc = E1000_RX_DESC(*rx_ring, i); buffer_info = &rx_ring->buffer_info[i]; while (rx_desc->status & E1000_RXD_STAT_DD) { struct sk_buff *skb; u8 status; if (*work_done >= work_to_do) break; (*work_done)++; status = rx_desc->status; skb = buffer_info->skb; buffer_info->skb = NULL; ++i; if (i == rx_ring->count) i = 0; next_rxd = E1000_RX_DESC(*rx_ring, i); prefetch(next_rxd); next_buffer = &rx_ring->buffer_info[i]; cleaned = true; cleaned_count++; pci_unmap_page(pdev, buffer_info->dma, PAGE_SIZE, PCI_DMA_FROMDEVICE); buffer_info->dma = 0; length = le16_to_cpu(rx_desc->length); /* errors is only valid for DD + EOP descriptors */ if (unlikely((status & E1000_RXD_STAT_EOP) && (rx_desc->errors & E1000_RXD_ERR_FRAME_ERR_MASK))) { /* recycle both page and skb */ buffer_info->skb = skb; /* an error means any chain goes out the window * too */ if (rx_ring->rx_skb_top) dev_kfree_skb(rx_ring->rx_skb_top); rx_ring->rx_skb_top = NULL; goto next_desc; } #define rxtop rx_ring->rx_skb_top if (!(status & E1000_RXD_STAT_EOP)) { /* this descriptor is only the beginning (or middle) */ if (!rxtop) { /* this is the beginning of a chain */ rxtop = skb; skb_fill_page_desc(rxtop, 0, buffer_info->page, 0, length); } else { /* this is the middle of a chain */ skb_fill_page_desc(rxtop, skb_shinfo(rxtop)->nr_frags, buffer_info->page, 0, length); /* re-use the skb, only consumed the page */ buffer_info->skb = skb; } e1000_consume_page(buffer_info, rxtop, length); goto next_desc; } else { if (rxtop) { /* end of the chain */ skb_fill_page_desc(rxtop, skb_shinfo(rxtop)->nr_frags, buffer_info->page, 0, length); /* re-use the current skb, we only consumed the * page */ buffer_info->skb = skb; skb = rxtop; rxtop = NULL; e1000_consume_page(buffer_info, skb, length); } else { /* no chain, got EOP, this buf is the packet * copybreak to save the put_page/alloc_page */ if (length <= copybreak && skb_tailroom(skb) >= length) { u8 *vaddr; vaddr = kmap_atomic(buffer_info->page, KM_SKB_DATA_SOFTIRQ); memcpy(skb_tail_pointer(skb), vaddr, length); kunmap_atomic(vaddr, KM_SKB_DATA_SOFTIRQ); /* re-use the page, so don't erase * buffer_info->page */ skb_put(skb, length); } else { skb_fill_page_desc(skb, 0, buffer_info->page, 0, length); e1000_consume_page(buffer_info, skb, length); } } } /* Receive Checksum Offload XXX recompute due to CRC strip? */ e1000_rx_checksum(adapter, (u32)(status) | ((u32)(rx_desc->errors) << 24), le16_to_cpu(rx_desc->csum), skb); /* probably a little skewed due to removing CRC */ total_rx_bytes += skb->len; total_rx_packets++; /* eth type trans needs skb->data to point to something */ if (!pskb_may_pull(skb, ETH_HLEN)) { e_err("pskb_may_pull failed.\n"); dev_kfree_skb(skb); goto next_desc; } e1000_receive_skb(adapter, netdev, skb, status, rx_desc->special); next_desc: rx_desc->status = 0; /* return some buffers to hardware, one at a time is too slow */ if (unlikely(cleaned_count >= E1000_RX_BUFFER_WRITE)) { adapter->alloc_rx_buf(adapter, cleaned_count); cleaned_count = 0; } /* use prefetched values */ rx_desc = next_rxd; buffer_info = next_buffer; } rx_ring->next_to_clean = i; cleaned_count = e1000_desc_unused(rx_ring); if (cleaned_count) adapter->alloc_rx_buf(adapter, cleaned_count); adapter->total_rx_bytes += total_rx_bytes; adapter->total_rx_packets += total_rx_packets; adapter->net_stats.rx_bytes += total_rx_bytes; adapter->net_stats.rx_packets += total_rx_packets; return cleaned; } /** * e1000_clean_rx_ring - Free Rx Buffers per Queue * @adapter: board private structure **/ static void e1000_clean_rx_ring(struct e1000_adapter *adapter) { struct e1000_ring *rx_ring = adapter->rx_ring; struct e1000_buffer *buffer_info; struct e1000_ps_page *ps_page; struct pci_dev *pdev = adapter->pdev; unsigned int i, j; /* Free all the Rx ring sk_buffs */ for (i = 0; i < rx_ring->count; i++) { buffer_info = &rx_ring->buffer_info[i]; if (buffer_info->dma) { if (adapter->clean_rx == e1000_clean_rx_irq) pci_unmap_single(pdev, buffer_info->dma, adapter->rx_buffer_len, PCI_DMA_FROMDEVICE); else if (adapter->clean_rx == e1000_clean_jumbo_rx_irq) pci_unmap_page(pdev, buffer_info->dma, PAGE_SIZE, PCI_DMA_FROMDEVICE); else if (adapter->clean_rx == e1000_clean_rx_irq_ps) pci_unmap_single(pdev, buffer_info->dma, adapter->rx_ps_bsize0, PCI_DMA_FROMDEVICE); buffer_info->dma = 0; } if (buffer_info->page) { put_page(buffer_info->page); buffer_info->page = NULL; } if (buffer_info->skb) { dev_kfree_skb(buffer_info->skb); buffer_info->skb = NULL; } for (j = 0; j < PS_PAGE_BUFFERS; j++) { ps_page = &buffer_info->ps_pages[j]; if (!ps_page->page) break; pci_unmap_page(pdev, ps_page->dma, PAGE_SIZE, PCI_DMA_FROMDEVICE); ps_page->dma = 0; put_page(ps_page->page); ps_page->page = NULL; } } /* there also may be some cached data from a chained receive */ if (rx_ring->rx_skb_top) { dev_kfree_skb(rx_ring->rx_skb_top); rx_ring->rx_skb_top = NULL; } /* 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; writel(0, adapter->hw.hw_addr + rx_ring->head); writel(0, adapter->hw.hw_addr + rx_ring->tail); } static void e1000e_downshift_workaround(struct work_struct *work) { struct e1000_adapter *adapter = container_of(work, struct e1000_adapter, downshift_task); e1000e_gig_downshift_workaround_ich8lan(&adapter->hw); } /** * e1000_intr_msi - Interrupt Handler * @irq: interrupt number * @data: pointer to a network interface device structure **/ static irqreturn_t e1000_intr_msi(int irq, void *data) { struct net_device *netdev = data; struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; u32 icr = er32(ICR); /* * read ICR disables interrupts using IAM */ if (icr & E1000_ICR_LSC) { hw->mac.get_link_status = 1; /* * ICH8 workaround-- Call gig speed drop workaround on cable * disconnect (LSC) before accessing any PHY registers */ if ((adapter->flags & FLAG_LSC_GIG_SPEED_DROP) && (!(er32(STATUS) & E1000_STATUS_LU))) schedule_work(&adapter->downshift_task); /* * 80003ES2LAN workaround-- For packet buffer work-around on * link down event; disable receives here in the ISR and reset * adapter in watchdog */ if (netif_carrier_ok(netdev) && adapter->flags & FLAG_RX_NEEDS_RESTART) { /* disable receives */ u32 rctl = er32(RCTL); ew32(RCTL, rctl & ~E1000_RCTL_EN); adapter->flags |= FLAG_RX_RESTART_NOW; } /* guard against interrupt when we're going down */ if (!test_bit(__E1000_DOWN, &adapter->state)) mod_timer(&adapter->watchdog_timer, jiffies + 1); } if (napi_schedule_prep(&adapter->napi)) { adapter->total_tx_bytes = 0; adapter->total_tx_packets = 0; adapter->total_rx_bytes = 0; adapter->total_rx_packets = 0; __napi_schedule(&adapter->napi); } return IRQ_HANDLED; } /** * e1000_intr - Interrupt Handler * @irq: interrupt number * @data: pointer to a network interface device structure **/ static irqreturn_t e1000_intr(int irq, void *data) { struct net_device *netdev = data; struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; u32 rctl, icr = er32(ICR); if (!icr) return IRQ_NONE; /* Not our interrupt */ /* * IMS will not auto-mask if INT_ASSERTED is not set, and if it is * not set, then the adapter didn't send an interrupt */ if (!(icr & E1000_ICR_INT_ASSERTED)) return IRQ_NONE; /* * Interrupt Auto-Mask...upon reading ICR, * interrupts are masked. No need for the * IMC write */ if (icr & E1000_ICR_LSC) { hw->mac.get_link_status = 1; /* * ICH8 workaround-- Call gig speed drop workaround on cable * disconnect (LSC) before accessing any PHY registers */ if ((adapter->flags & FLAG_LSC_GIG_SPEED_DROP) && (!(er32(STATUS) & E1000_STATUS_LU))) schedule_work(&adapter->downshift_task); /* * 80003ES2LAN workaround-- * For packet buffer work-around on link down event; * disable receives here in the ISR and * reset adapter in watchdog */ if (netif_carrier_ok(netdev) && (adapter->flags & FLAG_RX_NEEDS_RESTART)) { /* disable receives */ rctl = er32(RCTL); ew32(RCTL, rctl & ~E1000_RCTL_EN); adapter->flags |= FLAG_RX_RESTART_NOW; } /* guard against interrupt when we're going down */ if (!test_bit(__E1000_DOWN, &adapter->state)) mod_timer(&adapter->watchdog_timer, jiffies + 1); } if (napi_schedule_prep(&adapter->napi)) { adapter->total_tx_bytes = 0; adapter->total_tx_packets = 0; adapter->total_rx_bytes = 0; adapter->total_rx_packets = 0; __napi_schedule(&adapter->napi); } return IRQ_HANDLED; } static irqreturn_t e1000_msix_other(int irq, void *data) { struct net_device *netdev = data; struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; u32 icr = er32(ICR); if (!(icr & E1000_ICR_INT_ASSERTED)) { if (!test_bit(__E1000_DOWN, &adapter->state)) ew32(IMS, E1000_IMS_OTHER); return IRQ_NONE; } if (icr & adapter->eiac_mask) ew32(ICS, (icr & adapter->eiac_mask)); if (icr & E1000_ICR_OTHER) { if (!(icr & E1000_ICR_LSC)) goto no_link_interrupt; hw->mac.get_link_status = 1; /* guard against interrupt when we're going down */ if (!test_bit(__E1000_DOWN, &adapter->state)) mod_timer(&adapter->watchdog_timer, jiffies + 1); } no_link_interrupt: if (!test_bit(__E1000_DOWN, &adapter->state)) ew32(IMS, E1000_IMS_LSC | E1000_IMS_OTHER); return IRQ_HANDLED; } static irqreturn_t e1000_intr_msix_tx(int irq, void *data) { struct net_device *netdev = data; struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; struct e1000_ring *tx_ring = adapter->tx_ring; adapter->total_tx_bytes = 0; adapter->total_tx_packets = 0; if (!e1000_clean_tx_irq(adapter)) /* Ring was not completely cleaned, so fire another interrupt */ ew32(ICS, tx_ring->ims_val); return IRQ_HANDLED; } static irqreturn_t e1000_intr_msix_rx(int irq, void *data) { struct net_device *netdev = data; struct e1000_adapter *adapter = netdev_priv(netdev); /* Write the ITR value calculated at the end of the * previous interrupt. */ if (adapter->rx_ring->set_itr) { writel(1000000000 / (adapter->rx_ring->itr_val * 256), adapter->hw.hw_addr + adapter->rx_ring->itr_register); adapter->rx_ring->set_itr = 0; } if (napi_schedule_prep(&adapter->napi)) { adapter->total_rx_bytes = 0; adapter->total_rx_packets = 0; __napi_schedule(&adapter->napi); } return IRQ_HANDLED; } /** * e1000_configure_msix - Configure MSI-X hardware * * e1000_configure_msix sets up the hardware to properly * generate MSI-X interrupts. **/ static void e1000_configure_msix(struct e1000_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; struct e1000_ring *rx_ring = adapter->rx_ring; struct e1000_ring *tx_ring = adapter->tx_ring; int vector = 0; u32 ctrl_ext, ivar = 0; adapter->eiac_mask = 0; /* Workaround issue with spurious interrupts on 82574 in MSI-X mode */ if (hw->mac.type == e1000_82574) { u32 rfctl = er32(RFCTL); rfctl |= E1000_RFCTL_ACK_DIS; ew32(RFCTL, rfctl); } #define E1000_IVAR_INT_ALLOC_VALID 0x8 /* Configure Rx vector */ rx_ring->ims_val = E1000_IMS_RXQ0; adapter->eiac_mask |= rx_ring->ims_val; if (rx_ring->itr_val) writel(1000000000 / (rx_ring->itr_val * 256), hw->hw_addr + rx_ring->itr_register); else writel(1, hw->hw_addr + rx_ring->itr_register); ivar = E1000_IVAR_INT_ALLOC_VALID | vector; /* Configure Tx vector */ tx_ring->ims_val = E1000_IMS_TXQ0; vector++; if (tx_ring->itr_val) writel(1000000000 / (tx_ring->itr_val * 256), hw->hw_addr + tx_ring->itr_register); else writel(1, hw->hw_addr + tx_ring->itr_register); adapter->eiac_mask |= tx_ring->ims_val; ivar |= ((E1000_IVAR_INT_ALLOC_VALID | vector) << 8); /* set vector for Other Causes, e.g. link changes */ vector++; ivar |= ((E1000_IVAR_INT_ALLOC_VALID | vector) << 16); if (rx_ring->itr_val) writel(1000000000 / (rx_ring->itr_val * 256), hw->hw_addr + E1000_EITR_82574(vector)); else writel(1, hw->hw_addr + E1000_EITR_82574(vector)); /* Cause Tx interrupts on every write back */ ivar |= (1 << 31); ew32(IVAR, ivar); /* enable MSI-X PBA support */ ctrl_ext = er32(CTRL_EXT); ctrl_ext |= E1000_CTRL_EXT_PBA_CLR; /* Auto-Mask Other interrupts upon ICR read */ #define E1000_EIAC_MASK_82574 0x01F00000 ew32(IAM, ~E1000_EIAC_MASK_82574 | E1000_IMS_OTHER); ctrl_ext |= E1000_CTRL_EXT_EIAME; ew32(CTRL_EXT, ctrl_ext); e1e_flush(); } void e1000e_reset_interrupt_capability(struct e1000_adapter *adapter) { if (adapter->msix_entries) { pci_disable_msix(adapter->pdev); kfree(adapter->msix_entries); adapter->msix_entries = NULL; } else if (adapter->flags & FLAG_MSI_ENABLED) { pci_disable_msi(adapter->pdev); adapter->flags &= ~FLAG_MSI_ENABLED; } return; } /** * e1000e_set_interrupt_capability - set MSI or MSI-X if supported * * Attempt to configure interrupts using the best available * capabilities of the hardware and kernel. **/ void e1000e_set_interrupt_capability(struct e1000_adapter *adapter) { int err; int numvecs, i; switch (adapter->int_mode) { case E1000E_INT_MODE_MSIX: if (adapter->flags & FLAG_HAS_MSIX) { numvecs = 3; /* RxQ0, TxQ0 and other */ adapter->msix_entries = kcalloc(numvecs, sizeof(struct msix_entry), GFP_KERNEL); if (adapter->msix_entries) { for (i = 0; i < numvecs; i++) adapter->msix_entries[i].entry = i; err = pci_enable_msix(adapter->pdev, adapter->msix_entries, numvecs); if (err == 0) return; } /* MSI-X failed, so fall through and try MSI */ e_err("Failed to initialize MSI-X interrupts. " "Falling back to MSI interrupts.\n"); e1000e_reset_interrupt_capability(adapter); } adapter->int_mode = E1000E_INT_MODE_MSI; /* Fall through */ case E1000E_INT_MODE_MSI: if (!pci_enable_msi(adapter->pdev)) { adapter->flags |= FLAG_MSI_ENABLED; } else { adapter->int_mode = E1000E_INT_MODE_LEGACY; e_err("Failed to initialize MSI interrupts. Falling " "back to legacy interrupts.\n"); } /* Fall through */ case E1000E_INT_MODE_LEGACY: /* Don't do anything; this is the system default */ break; } return; } /** * e1000_request_msix - Initialize MSI-X interrupts * * e1000_request_msix allocates MSI-X vectors and requests interrupts from the * kernel. **/ static int e1000_request_msix(struct e1000_adapter *adapter) { struct net_device *netdev = adapter->netdev; int err = 0, vector = 0; if (strlen(netdev->name) < (IFNAMSIZ - 5)) sprintf(adapter->rx_ring->name, "%s-rx-0", netdev->name); else memcpy(adapter->rx_ring->name, netdev->name, IFNAMSIZ); err = request_irq(adapter->msix_entries[vector].vector, &e1000_intr_msix_rx, 0, adapter->rx_ring->name, netdev); if (err) goto out; adapter->rx_ring->itr_register = E1000_EITR_82574(vector); adapter->rx_ring->itr_val = adapter->itr; vector++; if (strlen(netdev->name) < (IFNAMSIZ - 5)) sprintf(adapter->tx_ring->name, "%s-tx-0", netdev->name); else memcpy(adapter->tx_ring->name, netdev->name, IFNAMSIZ); err = request_irq(adapter->msix_entries[vector].vector, &e1000_intr_msix_tx, 0, adapter->tx_ring->name, netdev); if (err) goto out; adapter->tx_ring->itr_register = E1000_EITR_82574(vector); adapter->tx_ring->itr_val = adapter->itr; vector++; err = request_irq(adapter->msix_entries[vector].vector, &e1000_msix_other, 0, netdev->name, netdev); if (err) goto out; e1000_configure_msix(adapter); return 0; out: return err; } /** * e1000_request_irq - initialize interrupts * * Attempts to configure interrupts using the best available * capabilities of the hardware and kernel. **/ static int e1000_request_irq(struct e1000_adapter *adapter) { struct net_device *netdev = adapter->netdev; int err; if (adapter->msix_entries) { err = e1000_request_msix(adapter); if (!err) return err; /* fall back to MSI */ e1000e_reset_interrupt_capability(adapter); adapter->int_mode = E1000E_INT_MODE_MSI; e1000e_set_interrupt_capability(adapter); } if (adapter->flags & FLAG_MSI_ENABLED) { err = request_irq(adapter->pdev->irq, &e1000_intr_msi, 0, netdev->name, netdev); if (!err) return err; /* fall back to legacy interrupt */ e1000e_reset_interrupt_capability(adapter); adapter->int_mode = E1000E_INT_MODE_LEGACY; } err = request_irq(adapter->pdev->irq, &e1000_intr, IRQF_SHARED, netdev->name, netdev); if (err) e_err("Unable to allocate interrupt, Error: %d\n", err); return err; } static void e1000_free_irq(struct e1000_adapter *adapter) { struct net_device *netdev = adapter->netdev; if (adapter->msix_entries) { int vector = 0; free_irq(adapter->msix_entries[vector].vector, netdev); vector++; free_irq(adapter->msix_entries[vector].vector, netdev); vector++; /* Other Causes interrupt vector */ free_irq(adapter->msix_entries[vector].vector, netdev); return; } free_irq(adapter->pdev->irq, netdev); } /** * e1000_irq_disable - Mask off interrupt generation on the NIC **/ static void e1000_irq_disable(struct e1000_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; ew32(IMC, ~0); if (adapter->msix_entries) ew32(EIAC_82574, 0); e1e_flush(); synchronize_irq(adapter->pdev->irq); } /** * e1000_irq_enable - Enable default interrupt generation settings **/ static void e1000_irq_enable(struct e1000_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; if (adapter->msix_entries) { ew32(EIAC_82574, adapter->eiac_mask & E1000_EIAC_MASK_82574); ew32(IMS, adapter->eiac_mask | E1000_IMS_OTHER | E1000_IMS_LSC); } else { ew32(IMS, IMS_ENABLE_MASK); } e1e_flush(); } /** * e1000_get_hw_control - get control of the h/w from f/w * @adapter: address of board private structure * * e1000_get_hw_control sets {CTRL_EXT|SWSM}:DRV_LOAD bit. * For ASF and Pass Through versions of f/w this means that * the driver is loaded. For AMT version (only with 82573) * of the f/w this means that the network i/f is open. **/ static void e1000_get_hw_control(struct e1000_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; u32 ctrl_ext; u32 swsm; /* Let firmware know the driver has taken over */ if (adapter->flags & FLAG_HAS_SWSM_ON_LOAD) { swsm = er32(SWSM); ew32(SWSM, swsm | E1000_SWSM_DRV_LOAD); } else if (adapter->flags & FLAG_HAS_CTRLEXT_ON_LOAD) { ctrl_ext = er32(CTRL_EXT); ew32(CTRL_EXT, ctrl_ext | E1000_CTRL_EXT_DRV_LOAD); } } /** * e1000_release_hw_control - release control of the h/w to f/w * @adapter: address of board private structure * * e1000_release_hw_control resets {CTRL_EXT|SWSM}:DRV_LOAD bit. * For ASF and Pass Through versions of f/w this means that the * driver is no longer loaded. For AMT version (only with 82573) i * of the f/w this means that the network i/f is closed. * **/ static void e1000_release_hw_control(struct e1000_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; u32 ctrl_ext; u32 swsm; /* Let firmware taken over control of h/w */ if (adapter->flags & FLAG_HAS_SWSM_ON_LOAD) { swsm = er32(SWSM); ew32(SWSM, swsm & ~E1000_SWSM_DRV_LOAD); } else if (adapter->flags & FLAG_HAS_CTRLEXT_ON_LOAD) { ctrl_ext = er32(CTRL_EXT); ew32(CTRL_EXT, ctrl_ext & ~E1000_CTRL_EXT_DRV_LOAD); } } /** * @e1000_alloc_ring - allocate memory for a ring structure **/ static int e1000_alloc_ring_dma(struct e1000_adapter *adapter, struct e1000_ring *ring) { struct pci_dev *pdev = adapter->pdev; ring->desc = dma_alloc_coherent(&pdev->dev, ring->size, &ring->dma, GFP_KERNEL); if (!ring->desc) return -ENOMEM; return 0; } /** * e1000e_setup_tx_resources - allocate Tx resources (Descriptors) * @adapter: board private structure * * Return 0 on success, negative on failure **/ int e1000e_setup_tx_resources(struct e1000_adapter *adapter) { struct e1000_ring *tx_ring = adapter->tx_ring; int err = -ENOMEM, size; size = sizeof(struct e1000_buffer) * tx_ring->count; tx_ring->buffer_info = vmalloc(size); if (!tx_ring->buffer_info) goto err; memset(tx_ring->buffer_info, 0, size); /* round up to nearest 4K */ tx_ring->size = tx_ring->count * sizeof(struct e1000_tx_desc); tx_ring->size = ALIGN(tx_ring->size, 4096); err = e1000_alloc_ring_dma(adapter, tx_ring); if (err) goto err; tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; return 0; err: vfree(tx_ring->buffer_info); e_err("Unable to allocate memory for the transmit descriptor ring\n"); return err; } /** * e1000e_setup_rx_resources - allocate Rx resources (Descriptors) * @adapter: board private structure * * Returns 0 on success, negative on failure **/ int e1000e_setup_rx_resources(struct e1000_adapter *adapter) { struct e1000_ring *rx_ring = adapter->rx_ring; struct e1000_buffer *buffer_info; int i, size, desc_len, err = -ENOMEM; size = sizeof(struct e1000_buffer) * rx_ring->count; rx_ring->buffer_info = vmalloc(size); if (!rx_ring->buffer_info) goto err; memset(rx_ring->buffer_info, 0, size); for (i = 0; i < rx_ring->count; i++) { buffer_info = &rx_ring->buffer_info[i]; buffer_info->ps_pages = kcalloc(PS_PAGE_BUFFERS, sizeof(struct e1000_ps_page), GFP_KERNEL); if (!buffer_info->ps_pages) goto err_pages; } desc_len = sizeof(union e1000_rx_desc_packet_split); /* Round up to nearest 4K */ rx_ring->size = rx_ring->count * desc_len; rx_ring->size = ALIGN(rx_ring->size, 4096); err = e1000_alloc_ring_dma(adapter, rx_ring); if (err) goto err_pages; rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; rx_ring->rx_skb_top = NULL; return 0; err_pages: for (i = 0; i < rx_ring->count; i++) { buffer_info = &rx_ring->buffer_info[i]; kfree(buffer_info->ps_pages); } err: vfree(rx_ring->buffer_info); e_err("Unable to allocate memory for the transmit descriptor ring\n"); return err; } /** * e1000_clean_tx_ring - Free Tx Buffers * @adapter: board private structure **/ static void e1000_clean_tx_ring(struct e1000_adapter *adapter) { struct e1000_ring *tx_ring = adapter->tx_ring; struct e1000_buffer *buffer_info; unsigned long size; unsigned int i; for (i = 0; i < tx_ring->count; i++) { buffer_info = &tx_ring->buffer_info[i]; e1000_put_txbuf(adapter, buffer_info); } size = sizeof(struct e1000_buffer) * tx_ring->count; memset(tx_ring->buffer_info, 0, size); memset(tx_ring->desc, 0, tx_ring->size); tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; writel(0, adapter->hw.hw_addr + tx_ring->head); writel(0, adapter->hw.hw_addr + tx_ring->tail); } /** * e1000e_free_tx_resources - Free Tx Resources per Queue * @adapter: board private structure * * Free all transmit software resources **/ void e1000e_free_tx_resources(struct e1000_adapter *adapter) { struct pci_dev *pdev = adapter->pdev; struct e1000_ring *tx_ring = adapter->tx_ring; e1000_clean_tx_ring(adapter); vfree(tx_ring->buffer_info); tx_ring->buffer_info = NULL; dma_free_coherent(&pdev->dev, tx_ring->size, tx_ring->desc, tx_ring->dma); tx_ring->desc = NULL; } /** * e1000e_free_rx_resources - Free Rx Resources * @adapter: board private structure * * Free all receive software resources **/ void e1000e_free_rx_resources(struct e1000_adapter *adapter) { struct pci_dev *pdev = adapter->pdev; struct e1000_ring *rx_ring = adapter->rx_ring; int i; e1000_clean_rx_ring(adapter); for (i = 0; i < rx_ring->count; i++) { kfree(rx_ring->buffer_info[i].ps_pages); } vfree(rx_ring->buffer_info); rx_ring->buffer_info = NULL; dma_free_coherent(&pdev->dev, rx_ring->size, rx_ring->desc, rx_ring->dma); rx_ring->desc = NULL; } /** * e1000_update_itr - update the dynamic ITR value based on statistics * @adapter: pointer to adapter * @itr_setting: current adapter->itr * @packets: the number of packets during this measurement interval * @bytes: the number of bytes during this measurement interval * * Stores a new ITR value based on packets and byte * counts during the last interrupt. The advantage of per interrupt * computation is faster updates and more accurate ITR for the current * traffic pattern. Constants in this function were computed * based on theoretical maximum wire speed and thresholds were set based * on testing data as well as attempting to minimize response time * while increasing bulk throughput. This functionality is controlled * by the InterruptThrottleRate module parameter. **/ static unsigned int e1000_update_itr(struct e1000_adapter *adapter, u16 itr_setting, int packets, int bytes) { unsigned int retval = itr_setting; if (packets == 0) goto update_itr_done; switch (itr_setting) { case lowest_latency: /* handle TSO and jumbo frames */ if (bytes/packets > 8000) retval = bulk_latency; else if ((packets < 5) && (bytes > 512)) { retval = low_latency; } break; case low_latency: /* 50 usec aka 20000 ints/s */ if (bytes > 10000) { /* this if handles the TSO accounting */ if (bytes/packets > 8000) { retval = bulk_latency; } else if ((packets < 10) || ((bytes/packets) > 1200)) { retval = bulk_latency; } else if ((packets > 35)) { retval = lowest_latency; } } else if (bytes/packets > 2000) { retval = bulk_latency; } else if (packets <= 2 && bytes < 512) { retval = lowest_latency; } break; case bulk_latency: /* 250 usec aka 4000 ints/s */ if (bytes > 25000) { if (packets > 35) { retval = low_latency; } } else if (bytes < 6000) { retval = low_latency; } break; } update_itr_done: return retval; } static void e1000_set_itr(struct e1000_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; u16 current_itr; u32 new_itr = adapter->itr; /* for non-gigabit speeds, just fix the interrupt rate at 4000 */ if (adapter->link_speed != SPEED_1000) { current_itr = 0; new_itr = 4000; goto set_itr_now; } adapter->tx_itr = e1000_update_itr(adapter, adapter->tx_itr, adapter->total_tx_packets, adapter->total_tx_bytes); /* conservative mode (itr 3) eliminates the lowest_latency setting */ if (adapter->itr_setting == 3 && adapter->tx_itr == lowest_latency) adapter->tx_itr = low_latency; adapter->rx_itr = e1000_update_itr(adapter, adapter->rx_itr, adapter->total_rx_packets, adapter->total_rx_bytes); /* conservative mode (itr 3) eliminates the lowest_latency setting */ if (adapter->itr_setting == 3 && adapter->rx_itr == lowest_latency) adapter->rx_itr = low_latency; current_itr = max(adapter->rx_itr, adapter->tx_itr); switch (current_itr) { /* counts and packets in update_itr are dependent on these numbers */ case lowest_latency: new_itr = 70000; break; case low_latency: new_itr = 20000; /* aka hwitr = ~200 */ break; case bulk_latency: new_itr = 4000; break; default: break; } set_itr_now: if (new_itr != adapter->itr) { /* * this attempts to bias the interrupt rate towards Bulk * by adding intermediate steps when interrupt rate is * increasing */ new_itr = new_itr > adapter->itr ? min(adapter->itr + (new_itr >> 2), new_itr) : new_itr; adapter->itr = new_itr; adapter->rx_ring->itr_val = new_itr; if (adapter->msix_entries) adapter->rx_ring->set_itr = 1; else ew32(ITR, 1000000000 / (new_itr * 256)); } } /** * e1000_alloc_queues - Allocate memory for all rings * @adapter: board private structure to initialize **/ static int __devinit e1000_alloc_queues(struct e1000_adapter *adapter) { adapter->tx_ring = kzalloc(sizeof(struct e1000_ring), GFP_KERNEL); if (!adapter->tx_ring) goto err; adapter->rx_ring = kzalloc(sizeof(struct e1000_ring), GFP_KERNEL); if (!adapter->rx_ring) goto err; return 0; err: e_err("Unable to allocate memory for queues\n"); kfree(adapter->rx_ring); kfree(adapter->tx_ring); return -ENOMEM; } /** * e1000_clean - NAPI Rx polling callback * @napi: struct associated with this polling callback * @budget: amount of packets driver is allowed to process this poll **/ static int e1000_clean(struct napi_struct *napi, int budget) { struct e1000_adapter *adapter = container_of(napi, struct e1000_adapter, napi); struct e1000_hw *hw = &adapter->hw; struct net_device *poll_dev = adapter->netdev; int tx_cleaned = 1, work_done = 0; adapter = netdev_priv(poll_dev); if (adapter->msix_entries && !(adapter->rx_ring->ims_val & adapter->tx_ring->ims_val)) goto clean_rx; tx_cleaned = e1000_clean_tx_irq(adapter); clean_rx: adapter->clean_rx(adapter, &work_done, budget); if (!tx_cleaned) work_done = budget; /* If budget not fully consumed, exit the polling mode */ if (work_done < budget) { if (adapter->itr_setting & 3) e1000_set_itr(adapter); napi_complete(napi); if (!test_bit(__E1000_DOWN, &adapter->state)) { if (adapter->msix_entries) ew32(IMS, adapter->rx_ring->ims_val); else e1000_irq_enable(adapter); } } return work_done; } static void e1000_vlan_rx_add_vid(struct net_device *netdev, u16 vid) { struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; u32 vfta, index; /* don't update vlan cookie if already programmed */ if ((adapter->hw.mng_cookie.status & E1000_MNG_DHCP_COOKIE_STATUS_VLAN) && (vid == adapter->mng_vlan_id)) return; /* add VID to filter table */ index = (vid >> 5) & 0x7F; vfta = E1000_READ_REG_ARRAY(hw, E1000_VFTA, index); vfta |= (1 << (vid & 0x1F)); e1000e_write_vfta(hw, index, vfta); } static void e1000_vlan_rx_kill_vid(struct net_device *netdev, u16 vid) { struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; u32 vfta, index; if (!test_bit(__E1000_DOWN, &adapter->state)) e1000_irq_disable(adapter); vlan_group_set_device(adapter->vlgrp, vid, NULL); if (!test_bit(__E1000_DOWN, &adapter->state)) e1000_irq_enable(adapter); if ((adapter->hw.mng_cookie.status & E1000_MNG_DHCP_COOKIE_STATUS_VLAN) && (vid == adapter->mng_vlan_id)) { /* release control to f/w */ e1000_release_hw_control(adapter); return; } /* remove VID from filter table */ index = (vid >> 5) & 0x7F; vfta = E1000_READ_REG_ARRAY(hw, E1000_VFTA, index); vfta &= ~(1 << (vid & 0x1F)); e1000e_write_vfta(hw, index, vfta); } static void e1000_update_mng_vlan(struct e1000_adapter *adapter) { struct net_device *netdev = adapter->netdev; u16 vid = adapter->hw.mng_cookie.vlan_id; u16 old_vid = adapter->mng_vlan_id; if (!adapter->vlgrp) return; if (!vlan_group_get_device(adapter->vlgrp, vid)) { adapter->mng_vlan_id = E1000_MNG_VLAN_NONE; if (adapter->hw.mng_cookie.status & E1000_MNG_DHCP_COOKIE_STATUS_VLAN) { e1000_vlan_rx_add_vid(netdev, vid); adapter->mng_vlan_id = vid; } if ((old_vid != (u16)E1000_MNG_VLAN_NONE) && (vid != old_vid) && !vlan_group_get_device(adapter->vlgrp, old_vid)) e1000_vlan_rx_kill_vid(netdev, old_vid); } else { adapter->mng_vlan_id = vid; } } static void e1000_vlan_rx_register(struct net_device *netdev, struct vlan_group *grp) { struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; u32 ctrl, rctl; if (!test_bit(__E1000_DOWN, &adapter->state)) e1000_irq_disable(adapter); adapter->vlgrp = grp; if (grp) { /* enable VLAN tag insert/strip */ ctrl = er32(CTRL); ctrl |= E1000_CTRL_VME; ew32(CTRL, ctrl); if (adapter->flags & FLAG_HAS_HW_VLAN_FILTER) { /* enable VLAN receive filtering */ rctl = er32(RCTL); rctl &= ~E1000_RCTL_CFIEN; ew32(RCTL, rctl); e1000_update_mng_vlan(adapter); } } else { /* disable VLAN tag insert/strip */ ctrl = er32(CTRL); ctrl &= ~E1000_CTRL_VME; ew32(CTRL, ctrl); if (adapter->flags & FLAG_HAS_HW_VLAN_FILTER) { if (adapter->mng_vlan_id != (u16)E1000_MNG_VLAN_NONE) { e1000_vlan_rx_kill_vid(netdev, adapter->mng_vlan_id); adapter->mng_vlan_id = E1000_MNG_VLAN_NONE; } } } if (!test_bit(__E1000_DOWN, &adapter->state)) e1000_irq_enable(adapter); } static void e1000_restore_vlan(struct e1000_adapter *adapter) { u16 vid; e1000_vlan_rx_register(adapter->netdev, adapter->vlgrp); if (!adapter->vlgrp) return; for (vid = 0; vid < VLAN_GROUP_ARRAY_LEN; vid++) { if (!vlan_group_get_device(adapter->vlgrp, vid)) continue; e1000_vlan_rx_add_vid(adapter->netdev, vid); } } static void e1000_init_manageability(struct e1000_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; u32 manc, manc2h; if (!(adapter->flags & FLAG_MNG_PT_ENABLED)) return; manc = er32(MANC); /* * enable receiving management packets to the host. this will probably * generate destination unreachable messages from the host OS, but * the packets will be handled on SMBUS */ manc |= E1000_MANC_EN_MNG2HOST; manc2h = er32(MANC2H); #define E1000_MNG2HOST_PORT_623 (1 << 5) #define E1000_MNG2HOST_PORT_664 (1 << 6) manc2h |= E1000_MNG2HOST_PORT_623; manc2h |= E1000_MNG2HOST_PORT_664; ew32(MANC2H, manc2h); ew32(MANC, manc); } /** * e1000_configure_tx - Configure 8254x Transmit Unit after Reset * @adapter: board private structure * * Configure the Tx unit of the MAC after a reset. **/ static void e1000_configure_tx(struct e1000_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; struct e1000_ring *tx_ring = adapter->tx_ring; u64 tdba; u32 tdlen, tctl, tipg, tarc; u32 ipgr1, ipgr2; /* Setup the HW Tx Head and Tail descriptor pointers */ tdba = tx_ring->dma; tdlen = tx_ring->count * sizeof(struct e1000_tx_desc); ew32(TDBAL, (tdba & DMA_BIT_MASK(32))); ew32(TDBAH, (tdba >> 32)); ew32(TDLEN, tdlen); ew32(TDH, 0); ew32(TDT, 0); tx_ring->head = E1000_TDH; tx_ring->tail = E1000_TDT; /* Set the default values for the Tx Inter Packet Gap timer */ tipg = DEFAULT_82543_TIPG_IPGT_COPPER; /* 8 */ ipgr1 = DEFAULT_82543_TIPG_IPGR1; /* 8 */ ipgr2 = DEFAULT_82543_TIPG_IPGR2; /* 6 */ if (adapter->flags & FLAG_TIPG_MEDIUM_FOR_80003ESLAN) ipgr2 = DEFAULT_80003ES2LAN_TIPG_IPGR2; /* 7 */ tipg |= ipgr1 << E1000_TIPG_IPGR1_SHIFT; tipg |= ipgr2 << E1000_TIPG_IPGR2_SHIFT; ew32(TIPG, tipg); /* Set the Tx Interrupt Delay register */ ew32(TIDV, adapter->tx_int_delay); /* Tx irq moderation */ ew32(TADV, adapter->tx_abs_int_delay); /* Program the Transmit Control Register */ tctl = er32(TCTL); tctl &= ~E1000_TCTL_CT; tctl |= E1000_TCTL_PSP | E1000_TCTL_RTLC | (E1000_COLLISION_THRESHOLD << E1000_CT_SHIFT); if (adapter->flags & FLAG_TARC_SPEED_MODE_BIT) { tarc = er32(TARC(0)); /* * set the speed mode bit, we'll clear it if we're not at * gigabit link later */ #define SPEED_MODE_BIT (1 << 21) tarc |= SPEED_MODE_BIT; ew32(TARC(0), tarc); } /* errata: program both queues to unweighted RR */ if (adapter->flags & FLAG_TARC_SET_BIT_ZERO) { tarc = er32(TARC(0)); tarc |= 1; ew32(TARC(0), tarc); tarc = er32(TARC(1)); tarc |= 1; ew32(TARC(1), tarc); } /* Setup Transmit Descriptor Settings for eop descriptor */ adapter->txd_cmd = E1000_TXD_CMD_EOP | E1000_TXD_CMD_IFCS; /* only set IDE if we are delaying interrupts using the timers */ if (adapter->tx_int_delay) adapter->txd_cmd |= E1000_TXD_CMD_IDE; /* enable Report Status bit */ adapter->txd_cmd |= E1000_TXD_CMD_RS; ew32(TCTL, tctl); e1000e_config_collision_dist(hw); adapter->tx_queue_len = adapter->netdev->tx_queue_len; } /** * e1000_setup_rctl - configure the receive control registers * @adapter: Board private structure **/ #define PAGE_USE_COUNT(S) (((S) >> PAGE_SHIFT) + \ (((S) & (PAGE_SIZE - 1)) ? 1 : 0)) static void e1000_setup_rctl(struct e1000_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; u32 rctl, rfctl; u32 psrctl = 0; u32 pages = 0; /* Program MC offset vector base */ rctl = er32(RCTL); rctl &= ~(3 << E1000_RCTL_MO_SHIFT); rctl |= E1000_RCTL_EN | E1000_RCTL_BAM | E1000_RCTL_LBM_NO | E1000_RCTL_RDMTS_HALF | (adapter->hw.mac.mc_filter_type << E1000_RCTL_MO_SHIFT); /* Do not Store bad packets */ rctl &= ~E1000_RCTL_SBP; /* Enable Long Packet receive */ if (adapter->netdev->mtu <= ETH_DATA_LEN) rctl &= ~E1000_RCTL_LPE; else rctl |= E1000_RCTL_LPE; /* Some systems expect that the CRC is included in SMBUS traffic. The * hardware strips the CRC before sending to both SMBUS (BMC) and to * host memory when this is enabled */ if (adapter->flags2 & FLAG2_CRC_STRIPPING) rctl |= E1000_RCTL_SECRC; /* Workaround Si errata on 82577 PHY - configure IPG for jumbos */ if ((hw->phy.type == e1000_phy_82577) && (rctl & E1000_RCTL_LPE)) { u16 phy_data; e1e_rphy(hw, PHY_REG(770, 26), &phy_data); phy_data &= 0xfff8; phy_data |= (1 << 2); e1e_wphy(hw, PHY_REG(770, 26), phy_data); e1e_rphy(hw, 22, &phy_data); phy_data &= 0x0fff; phy_data |= (1 << 14); e1e_wphy(hw, 0x10, 0x2823); e1e_wphy(hw, 0x11, 0x0003); e1e_wphy(hw, 22, phy_data); } /* Setup buffer sizes */ rctl &= ~E1000_RCTL_SZ_4096; rctl |= E1000_RCTL_BSEX; switch (adapter->rx_buffer_len) { case 256: rctl |= E1000_RCTL_SZ_256; rctl &= ~E1000_RCTL_BSEX; break; case 512: rctl |= E1000_RCTL_SZ_512; rctl &= ~E1000_RCTL_BSEX; break; case 1024: rctl |= E1000_RCTL_SZ_1024; rctl &= ~E1000_RCTL_BSEX; break; case 2048: default: rctl |= E1000_RCTL_SZ_2048; rctl &= ~E1000_RCTL_BSEX; break; case 4096: rctl |= E1000_RCTL_SZ_4096; break; case 8192: rctl |= E1000_RCTL_SZ_8192; break; case 16384: rctl |= E1000_RCTL_SZ_16384; break; } /* * 82571 and greater support packet-split where the protocol * header is placed in skb->data and the packet data is * placed in pages hanging off of skb_shinfo(skb)->nr_frags. * In the case of a non-split, skb->data is linearly filled, * followed by the page buffers. Therefore, skb->data is * sized to hold the largest protocol header. * * allocations using alloc_page take too long for regular MTU * so only enable packet split for jumbo frames * * Using pages when the page size is greater than 16k wastes * a lot of memory, since we allocate 3 pages at all times * per packet. */ pages = PAGE_USE_COUNT(adapter->netdev->mtu); if (!(adapter->flags & FLAG_IS_ICH) && (pages <= 3) && (PAGE_SIZE <= 16384) && (rctl & E1000_RCTL_LPE)) adapter->rx_ps_pages = pages; else adapter->rx_ps_pages = 0; if (adapter->rx_ps_pages) { /* Configure extra packet-split registers */ rfctl = er32(RFCTL); rfctl |= E1000_RFCTL_EXTEN; /* * disable packet split support for IPv6 extension headers, * because some malformed IP