netdev.c

grub源码分析文档

		 * 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;
		}

		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_packets += total_rx_packets;
	adapter->total_rx_bytes += total_rx_bytes;
	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 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;
	bool cleaned = 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;
			count++;
			if (count == tx_ring->count) {
				cleaned = 0;
				goto done_cleaning;
			}
		}

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

done_cleaning:
	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[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 cleaned;
}

/**
 * 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("Packet Split buffers didn't pick up the full"
			      " packet\n");
			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("Last part of the packet spanning multiple"
			      " descriptors\n");
			dev_kfree_skb_irq(skb);
			goto next_desc;
		}

		/* Good Receive */
		skb_put(skb, length);

#ifdef CONFIG_E1000_NAPI
		{
		/*
		 * 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);

			skb_put(skb, l1);
			goto copydone;
		} /* if */
		}
#endif

		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;
		}

#ifdef CONFIG_E1000_NAPI
copydone:
#endif
		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_packets += total_rx_packets;
	adapter->total_rx_bytes += total_rx_bytes;
	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;

		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) {