netdev.c

Intel 82546系列lan driver源码

			 * 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);
	}
}

#ifdef CONFIG_E1000E_NAPI
/**
 * e1000_alloc_jumbo_rx_buffers - Replace used jumbo receive buffers
 * @adapter: address of board private structure
 * @rx_ring: pointer to receive ring 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);
	}
}
#endif /* CONFIG_E1000E_NAPI */

/**
 * 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
 **/
#ifdef CONFIG_E1000E_NAPI
static bool e1000_clean_rx_irq(struct e1000_adapter *adapter,
			       int *work_done, int work_to_do)
#else
static bool e1000_clean_rx_irq(struct e1000_adapter *adapter)
#endif
{
	struct net_device *netdev = adapter->netdev;
	struct pci_dev *pdev = adapter->pdev;
	struct e1000_hw *hw = &adapter->hw;
	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;

#ifdef CONFIG_E1000E_NAPI
		if (*work_done >= work_to_do)
			break;
		(*work_done)++;
#endif

		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("Receive packet consumed multiple buffers\n");
			/* 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)
{
	if (buffer_info->dma) {
		pci_unmap_page(adapter->pdev, buffer_info->dma,
			       buffer_info->length, PCI_DMA_TODEVICE);
		buffer_info->dma = 0;
	}
	if (buffer_info->skb) {
		dev_kfree_skb_any(buffer_info->skb);
		buffer_info->skb = NULL;
	}
}

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 if there is more work to do (later)
 **/
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;
	bool cleaned = 0, retval = 1;
	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)) {
		for (cleaned = 0; !cleaned; ) {
			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;
#ifdef NETIF_F_TSO
				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;
#else
				total_tx_packets++;
				total_tx_bytes += skb->len;
#endif
			}

			e1000_put_txbuf(adapter, buffer_info);
			tx_desc->upper.data = 0;

			i++;
			if (i == tx_ring->count)
				i = 0;
#ifdef CONFIG_E1000E_NAPI
			if (total_tx_packets >= tx_ring->count) {
				retval = 0;
				goto done_cleaning;
			}
#endif
		}

		eop = tx_ring->buffer_info[i].next_to_watch;
		eop_desc = E1000_TX_DESC(*tx_ring, eop);
	}

#ifdef CONFIG_E1000E_NAPI
done_cleaning:
#endif
	tx_ring->next_to_clean = i;

#define TX_WAKE_THRESHOLD 32
	if (cleaned && 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[eop].dma &&
		    time_after(jiffies, tx_ring->buffer_info[eop].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 retval;
}

/**
 * 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
 **/
#ifdef CONFIG_E1000E_NAPI
static bool e1000_clean_rx_irq_ps(struct e1000_adapter *adapter,
				  int *work_done, int work_to_do)
#else
static bool e1000_clean_rx_irq_ps(struct e1000_adapter *adapter)
#endif
{
	struct e1000_hw *hw = &adapter->hw;
	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) {
#ifdef CONFIG_E1000E_NAPI
		if (*work_done >= work_to_do)
			break;
		(*work_done)++;
#endif
		skb = buffer_info->skb;