e1000e: Add support for BM PHYs on ICH9

This patch adds support for the BM PHY, a new PHY model being used
on ICH9-based implementations.

This new PHY exposes issues in the ICH9 silicon when receiving
jumbo frames large enough to use more than a certain part of the
Rx FIFO, and this unfortunately breaks packet split jumbo receives.
For this reason we re-introduce (for affected adapters only) the
jumbo single-skb receive routine back so that people who do
wish to use jumbo frames on these ich9 platforms can do so.
Part of this problem has to do with CPU sleep states and to make
sure that all the wake up timings are correctly we force them
with the recently merged pm_qos infrastructure written by Mark
Gross. (See http://lkml.org/lkml/2007/10/4/400).

To make code read a bit easier we introduce a _IS_ICH flag so
that we don't need to do mac type checks over the code.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Signed-off-by: Auke Kok <auke-jan.h.kok@intel.com>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>

1 files changed, 322 insertions, 8 deletions

diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c
index 8991ab8911e..8cbb40f3a50 100644
--- a/drivers/net/e1000e/netdev.c
+++ b/drivers/net/e1000e/netdev.c
@@ -43,10 +43,11 @@
 #include <linux/if_vlan.h>
 #include <linux/cpu.h>
 #include <linux/smp.h>
+#include <linux/pm_qos_params.h>
 
 #include "e1000.h"
 
-#define DRV_VERSION "0.2.1"
+#define DRV_VERSION "0.3.3.3-k2"
 char e1000e_driver_name[] = "e1000e";
 const char e1000e_driver_version[] = DRV_VERSION;
 
@@ -341,6 +342,89 @@ no_buffers:
 }
 
 /**
+ * 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);
+	}
+}
+
+/**
  * e1000_clean_rx_irq - Send received data up the network stack; legacy
  * @adapter: board private structure
  *
@@ -783,6 +867,186 @@ next_desc:
 }
 
 /**
+ * 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)) {
+			ndev_err(netdev, "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
  **/
@@ -802,6 +1066,10 @@ static void e1000_clean_rx_ring(struct e1000_adapter *adapter)
 				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,
@@ -809,6 +1077,11 @@ static void e1000_clean_rx_ring(struct e1000_adapter *adapter)
 			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;
@@ -1755,10 +2028,12 @@ static void e1000_setup_rctl(struct e1000_adapter *adapter)
 	 * a lot of memory, since we allocate 3 pages at all times
 	 * per packet.
 	 */
-	adapter->rx_ps_pages = 0;
 	pages = PAGE_USE_COUNT(adapter->netdev->mtu);
-	if ((pages <= 3) && (PAGE_SIZE <= 16384) && (rctl & E1000_RCTL_LPE))
+	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 */
@@ -1819,9 +2094,12 @@ static void e1000_configure_rx(struct e1000_adapter *adapter)
 			sizeof(union e1000_rx_desc_packet_split);
 		adapter->clean_rx = e1000_clean_rx_irq_ps;
 		adapter->alloc_rx_buf = e1000_alloc_rx_buffers_ps;
+	} else if (adapter->netdev->mtu > ETH_FRAME_LEN + ETH_FCS_LEN) {
+		rdlen = rx_ring->count * sizeof(struct e1000_rx_desc);
+		adapter->clean_rx = e1000_clean_jumbo_rx_irq;
+		adapter->alloc_rx_buf = e1000_alloc_jumbo_rx_buffers;
 	} else {
-		rdlen = rx_ring->count *
-			sizeof(struct e1000_rx_desc);
+		rdlen = rx_ring->count * sizeof(struct e1000_rx_desc);
 		adapter->clean_rx = e1000_clean_rx_irq;
 		adapter->alloc_rx_buf = e1000_alloc_rx_buffers;
 	}
@@ -1885,8 +2163,21 @@ static void e1000_configure_rx(struct e1000_adapter *adapter)
 	 * units), e.g. using jumbo frames when setting to E1000_ERT_2048
 	 */
 	if ((adapter->flags & FLAG_HAS_ERT) &&
-	    (adapter->netdev->mtu > ETH_DATA_LEN))
-		ew32(ERT, E1000_ERT_2048);
+	    (adapter->netdev->mtu > ETH_DATA_LEN)) {
+		u32 rxdctl = er32(RXDCTL(0));
+		ew32(RXDCTL(0), rxdctl | 0x3);
+		ew32(ERT, E1000_ERT_2048 | (1 << 13));
+		/*
+		 * With jumbo frames and early-receive enabled, excessive
+		 * C4->C2 latencies result in dropped transactions.
+		 */
+		pm_qos_update_requirement(PM_QOS_CPU_DMA_LATENCY,
+					  e1000e_driver_name, 55);
+	} else {
+		pm_qos_update_requirement(PM_QOS_CPU_DMA_LATENCY,
+					  e1000e_driver_name,
+					  PM_QOS_DEFAULT_VALUE);
+	}
 
 	/* Enable Receives */
 	ew32(RCTL, rctl);
@@ -2155,6 +2446,14 @@ void e1000e_reset(struct e1000_adapter *adapter)
 
 	/* Allow time for pending master requests to run */
 	mac->ops.reset_hw(hw);
+
+	/*
+	 * For parts with AMT enabled, let the firmware know
+	 * that the network interface is in control
+	 */
+	if ((adapter->flags & FLAG_HAS_AMT) && e1000e_check_mng_mode(hw))
+		e1000_get_hw_control(adapter);
+
 	ew32(WUC, 0);
 
 	if (mac->ops.init_hw(hw))
@@ -3469,6 +3768,8 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu)
 	 * means we reserve 2 more, this pushes us to allocate from the next
 	 * larger slab size.
 	 * i.e. RXBUFFER_2048 --> size-4096 slab
+	 * However with the new *_jumbo_rx* routines, jumbo receives will use
+	 * fragmented skbs
 	 */
 
 	if (max_frame <= 256)
@@ -3626,6 +3927,9 @@ static int e1000_suspend(struct pci_dev *pdev, pm_message_t state)
 			ew32(CTRL_EXT, ctrl_ext);
 		}
 
+		if (adapter->flags & FLAG_IS_ICH)
+			e1000e_disable_gig_wol_ich8lan(&adapter->hw);
+
 		/* Allow time for pending master requests to run */
 		e1000e_disable_pcie_master(&adapter->hw);
 
@@ -4292,6 +4596,13 @@ static struct pci_device_id e1000_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH9_IFE_GT), board_ich9lan },
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH9_IGP_AMT), board_ich9lan },
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH9_IGP_C), board_ich9lan },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH9_IGP_M), board_ich9lan },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH9_IGP_M_AMT), board_ich9lan },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH9_IGP_M_V), board_ich9lan },
+
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH10_R_BM_LM), board_ich9lan },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH10_R_BM_LF), board_ich9lan },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH10_R_BM_V), board_ich9lan },
 
 	{ }	/* terminate list */
 };
@@ -4326,7 +4637,9 @@ static int __init e1000_init_module(void)
 	printk(KERN_INFO "%s: Copyright (c) 1999-2008 Intel Corporation.\n",
 	       e1000e_driver_name);
 	ret = pci_register_driver(&e1000_driver);
-
+	pm_qos_add_requirement(PM_QOS_CPU_DMA_LATENCY, e1000e_driver_name,
+			       PM_QOS_DEFAULT_VALUE);
+				
 	return ret;
 }
 module_init(e1000_init_module);
@@ -4340,6 +4653,7 @@ module_init(e1000_init_module);
 static void __exit e1000_exit_module(void)
 {
 	pci_unregister_driver(&e1000_driver);
+	pm_qos_remove_requirement(PM_QOS_CPU_DMA_LATENCY, e1000e_driver_name);
 }
 module_exit(e1000_exit_module);