Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-next

6 files changed, 772 insertions, 628 deletions

diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h
index aed217449f0..89eb1f85b9f 100644
--- a/drivers/net/ethernet/intel/igb/e1000_defines.h
+++ b/drivers/net/ethernet/intel/igb/e1000_defines.h
@@ -134,6 +134,8 @@
 #define E1000_RCTL_SZ_256         0x00030000    /* rx buffer size 256 */
 #define E1000_RCTL_VFE            0x00040000    /* vlan filter enable */
 #define E1000_RCTL_CFIEN          0x00080000    /* canonical form enable */
+#define E1000_RCTL_DPF            0x00400000    /* Discard Pause Frames */
+#define E1000_RCTL_PMCF           0x00800000    /* pass MAC control frames */
 #define E1000_RCTL_SECRC          0x04000000    /* Strip Ethernet CRC */
 
 /*
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index e96cef89f12..c4902411d74 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -1769,10 +1769,21 @@ static int igb_set_features(struct net_device *netdev,
 	netdev_features_t features)
 {
 	netdev_features_t changed = netdev->features ^ features;
+	struct igb_adapter *adapter = netdev_priv(netdev);
 
 	if (changed & NETIF_F_HW_VLAN_RX)
 		igb_vlan_mode(netdev, features);
 
+	if (!(changed & NETIF_F_RXALL))
+		return 0;
+
+	netdev->features = features;
+
+	if (netif_running(netdev))
+		igb_reinit_locked(adapter);
+	else
+		igb_reset(adapter);
+
 	return 0;
 }
 
@@ -1954,6 +1965,7 @@ static int __devinit igb_probe(struct pci_dev *pdev,
 
 	/* copy netdev features into list of user selectable features */
 	netdev->hw_features |= netdev->features;
+	netdev->hw_features |= NETIF_F_RXALL;
 
 	/* set this bit last since it cannot be part of hw_features */
 	netdev->features |= NETIF_F_HW_VLAN_FILTER;
@@ -1964,6 +1976,8 @@ static int __devinit igb_probe(struct pci_dev *pdev,
 				 NETIF_F_IPV6_CSUM |
 				 NETIF_F_SG;
 
+	netdev->priv_flags |= IFF_SUPP_NOFCS;
+
 	if (pci_using_dac) {
 		netdev->features |= NETIF_F_HIGHDMA;
 		netdev->vlan_features |= NETIF_F_HIGHDMA;
@@ -3003,6 +3017,22 @@ void igb_setup_rctl(struct igb_adapter *adapter)
 		wr32(E1000_QDE, ALL_QUEUES);
 	}
 
+	/* This is useful for sniffing bad packets. */
+	if (adapter->netdev->features & NETIF_F_RXALL) {
+		/* UPE and MPE will be handled by normal PROMISC logic
+		 * in e1000e_set_rx_mode */
+		rctl |= (E1000_RCTL_SBP | /* Receive bad packets */
+			 E1000_RCTL_BAM | /* RX All Bcast Pkts */
+			 E1000_RCTL_PMCF); /* RX All MAC Ctrl Pkts */
+
+		rctl &= ~(E1000_RCTL_VFE | /* Disable VLAN filter */
+			  E1000_RCTL_DPF | /* Allow filtered pause */
+			  E1000_RCTL_CFIEN); /* Dis VLAN CFIEN Filter */
+		/* Do not mess with E1000_CTRL_VME, it affects transmit as well,
+		 * and that breaks VLANs.
+		 */
+	}
+
 	wr32(E1000_RCTL, rctl);
 }
 
@@ -4293,6 +4323,8 @@ static void igb_tx_map(struct igb_ring *tx_ring,
 
 	/* write last descriptor with RS and EOP bits */
 	cmd_type |= cpu_to_le32(size) | cpu_to_le32(IGB_TXD_DCMD);
+	if (unlikely(skb->no_fcs))
+		cmd_type &= ~(cpu_to_le32(E1000_ADVTXD_DCMD_IFCS));
 	tx_desc->read.cmd_type_len = cmd_type;
 
 	/* set the timestamp */
@@ -6098,8 +6130,9 @@ static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, int budget)
 			goto next_desc;
 		}
 
-		if (igb_test_staterr(rx_desc,
-				     E1000_RXDEXT_ERR_FRAME_ERR_MASK)) {
+		if (unlikely((igb_test_staterr(rx_desc,
+					       E1000_RXDEXT_ERR_FRAME_ERR_MASK))
+			     && !(rx_ring->netdev->features & NETIF_F_RXALL))) {
 			dev_kfree_skb_any(skb);
 			goto next_desc;
 		}
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index f069c1b1075..e0d809d0ed7 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -72,12 +72,6 @@
 
 /* Supported Rx Buffer Sizes */
 #define IXGBE_RXBUFFER_512   512    /* Used for packet split */
-#define IXGBE_RXBUFFER_2K   2048
-#define IXGBE_RXBUFFER_3K   3072
-#define IXGBE_RXBUFFER_4K   4096
-#define IXGBE_RXBUFFER_7K   7168
-#define IXGBE_RXBUFFER_8K   8192
-#define IXGBE_RXBUFFER_15K  15360
 #define IXGBE_MAX_RXBUFFER  16384  /* largest size for a single descriptor */
 
 /*
@@ -102,7 +96,6 @@
 #define IXGBE_TX_FLAGS_FCOE		(u32)(1 << 5)
 #define IXGBE_TX_FLAGS_FSO		(u32)(1 << 6)
 #define IXGBE_TX_FLAGS_TXSW		(u32)(1 << 7)
-#define IXGBE_TX_FLAGS_MAPPED_AS_PAGE	(u32)(1 << 8)
 #define IXGBE_TX_FLAGS_VLAN_MASK	0xffff0000
 #define IXGBE_TX_FLAGS_VLAN_PRIO_MASK	0xe0000000
 #define IXGBE_TX_FLAGS_VLAN_PRIO_SHIFT  29
@@ -156,19 +149,18 @@ struct vf_macvlans {
 struct ixgbe_tx_buffer {
 	union ixgbe_adv_tx_desc *next_to_watch;
 	unsigned long time_stamp;
-	dma_addr_t dma;
-	u32 length;
-	u32 tx_flags;
 	struct sk_buff *skb;
-	u32 bytecount;
-	u16 gso_segs;
+	unsigned int bytecount;
+	unsigned short gso_segs;
+	DEFINE_DMA_UNMAP_ADDR(dma);
+	DEFINE_DMA_UNMAP_LEN(len);
+	u32 tx_flags;
 };
 
 struct ixgbe_rx_buffer {
 	struct sk_buff *skb;
 	dma_addr_t dma;
 	struct page *page;
-	dma_addr_t page_dma;
 	unsigned int page_offset;
 };
 
@@ -180,7 +172,6 @@ struct ixgbe_queue_stats {
 struct ixgbe_tx_queue_stats {
 	u64 restart_queue;
 	u64 tx_busy;
-	u64 completed;
 	u64 tx_done_old;
 };
 
@@ -193,21 +184,15 @@ struct ixgbe_rx_queue_stats {
 	u64 csum_err;
 };
 
-enum ixbge_ring_state_t {
+enum ixgbe_ring_state_t {
 	__IXGBE_TX_FDIR_INIT_DONE,
 	__IXGBE_TX_DETECT_HANG,
 	__IXGBE_HANG_CHECK_ARMED,
-	__IXGBE_RX_PS_ENABLED,
 	__IXGBE_RX_RSC_ENABLED,
 	__IXGBE_RX_CSUM_UDP_ZERO_ERR,
+	__IXGBE_RX_FCOE_BUFSZ,
 };
 
-#define ring_is_ps_enabled(ring) \
-	test_bit(__IXGBE_RX_PS_ENABLED, &(ring)->state)
-#define set_ring_ps_enabled(ring) \
-	set_bit(__IXGBE_RX_PS_ENABLED, &(ring)->state)
-#define clear_ring_ps_enabled(ring) \
-	clear_bit(__IXGBE_RX_PS_ENABLED, &(ring)->state)
 #define check_for_tx_hang(ring) \
 	test_bit(__IXGBE_TX_DETECT_HANG, &(ring)->state)
 #define set_check_for_tx_hang(ring) \
@@ -233,7 +218,6 @@ struct ixgbe_ring {
 	u8 __iomem *tail;
 
 	u16 count;			/* amount of descriptors */
-	u16 rx_buf_len;
 
 	u8 queue_index; /* needed for multiqueue queue management */
 	u8 reg_idx;			/* holds the special value that gets
@@ -241,8 +225,13 @@ struct ixgbe_ring {
 					 * associated with this ring, which is
 					 * different for DCB and RSS modes
 					 */
-	u8 atr_sample_rate;
-	u8 atr_count;
+	union {
+		struct {
+			u8 atr_sample_rate;
+			u8 atr_count;
+		};
+		u16 next_to_alloc;
+	};
 
 	u16 next_to_use;
 	u16 next_to_clean;
@@ -287,6 +276,22 @@ struct ixgbe_ring_feature {
 	int mask;
 } ____cacheline_internodealigned_in_smp;
 
+/*
+ * FCoE requires that all Rx buffers be over 2200 bytes in length.  Since
+ * this is twice the size of a half page we need to double the page order
+ * for FCoE enabled Rx queues.
+ */
+#if defined(IXGBE_FCOE) && (PAGE_SIZE < 8192)
+static inline unsigned int ixgbe_rx_pg_order(struct ixgbe_ring *ring)
+{
+	return test_bit(__IXGBE_RX_FCOE_BUFSZ, &ring->state) ? 1 : 0;
+}
+#else
+#define ixgbe_rx_pg_order(_ring) 0
+#endif
+#define ixgbe_rx_pg_size(_ring) (PAGE_SIZE << ixgbe_rx_pg_order(_ring))
+#define ixgbe_rx_bufsz(_ring) ((PAGE_SIZE / 2) << ixgbe_rx_pg_order(_ring))
+
 struct ixgbe_ring_container {
 	struct ixgbe_ring *ring;	/* pointer to linked list of rings */
 	unsigned int total_bytes;	/* total bytes processed this int */
@@ -554,7 +559,7 @@ struct ixgbe_cb {
 	};
 	dma_addr_t dma;
 	u16 append_cnt;
-	bool delay_unmap;
+	bool page_released;
 };
 #define IXGBE_CB(skb) ((struct ixgbe_cb *)(skb)->cb)
 
@@ -625,7 +630,8 @@ extern void ixgbe_tx_ctxtdesc(struct ixgbe_ring *, u32, u32, u32, u32);
 extern void ixgbe_do_reset(struct net_device *netdev);
 #ifdef IXGBE_FCOE
 extern void ixgbe_configure_fcoe(struct ixgbe_adapter *adapter);
-extern int ixgbe_fso(struct ixgbe_ring *tx_ring, struct sk_buff *skb,
+extern int ixgbe_fso(struct ixgbe_ring *tx_ring,
+		     struct ixgbe_tx_buffer *first,
                      u32 tx_flags, u8 *hdr_len);
 extern void ixgbe_cleanup_fcoe(struct ixgbe_adapter *adapter);
 extern int ixgbe_fcoe_ddp(struct ixgbe_adapter *adapter,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 24f7291dbe5..b09e67cc9d6 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -35,6 +35,7 @@
 #include <linux/netdevice.h>
 #include <linux/ethtool.h>
 #include <linux/vmalloc.h>
+#include <linux/highmem.h>
 #include <linux/uaccess.h>
 
 #include "ixgbe.h"
@@ -1615,7 +1616,6 @@ static int ixgbe_setup_desc_rings(struct ixgbe_adapter *adapter)
 	rx_ring->dev = &adapter->pdev->dev;
 	rx_ring->netdev = adapter->netdev;
 	rx_ring->reg_idx = adapter->rx_ring[0]->reg_idx;
-	rx_ring->rx_buf_len = IXGBE_RXBUFFER_2K;
 
 	err = ixgbe_setup_rx_resources(rx_ring);
 	if (err) {
@@ -1718,13 +1718,15 @@ static bool ixgbe_check_lbtest_frame(struct ixgbe_rx_buffer *rx_buffer,
 
 	frame_size >>= 1;
 
-	data = rx_buffer->skb->data;
+	data = kmap(rx_buffer->page) + rx_buffer->page_offset;
 
 	if (data[3] != 0xFF ||
 	    data[frame_size + 10] != 0xBE ||
 	    data[frame_size + 12] != 0xAF)
 		match = false;
 
+	kunmap(rx_buffer->page);
+
 	return match;
 }
 
@@ -1746,17 +1748,22 @@ static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring,
 		/* check Rx buffer */
 		rx_buffer = &rx_ring->rx_buffer_info[rx_ntc];
 
-		/* unmap Rx buffer, will be remapped by alloc_rx_buffers */
-		dma_unmap_single(rx_ring->dev,
-				 rx_buffer->dma,
-				 rx_ring->rx_buf_len,
-				 DMA_FROM_DEVICE);
-		rx_buffer->dma = 0;
+		/* sync Rx buffer for CPU read */
+		dma_sync_single_for_cpu(rx_ring->dev,
+					rx_buffer->dma,
+					ixgbe_rx_bufsz(rx_ring),
+					DMA_FROM_DEVICE);
 
 		/* verify contents of skb */
 		if (ixgbe_check_lbtest_frame(rx_buffer, size))
 			count++;
 
+		/* sync Rx buffer for device write */
+		dma_sync_single_for_device(rx_ring->dev,
+					   rx_buffer->dma,
+					   ixgbe_rx_bufsz(rx_ring),
+					   DMA_FROM_DEVICE);
+
 		/* unmap buffer on Tx side */
 		tx_buffer = &tx_ring->tx_buffer_info[tx_ntc];
 		ixgbe_unmap_and_free_tx_resource(tx_ring, tx_buffer);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
index da7da752b6b..5f943d3f85c 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
@@ -447,7 +447,7 @@ ddp_out:
 /**
  * ixgbe_fso - ixgbe FCoE Sequence Offload (FSO)
  * @tx_ring: tx desc ring
- * @skb: associated skb
+ * @first: first tx_buffer structure containing skb, tx_flags, and protocol
  * @tx_flags: tx flags
  * @hdr_len: hdr_len to be returned
  *
@@ -455,9 +455,11 @@ ddp_out:
  *
  * Returns : 0 indicates no FSO, > 0 for FSO, < 0 for error
  */
-int ixgbe_fso(struct ixgbe_ring *tx_ring, struct sk_buff *skb,
+int ixgbe_fso(struct ixgbe_ring *tx_ring,
+	      struct ixgbe_tx_buffer *first,
               u32 tx_flags, u8 *hdr_len)
 {
+	struct sk_buff *skb = first->skb;
 	struct fc_frame_header *fh;
 	u32 vlan_macip_lens;
 	u32 fcoe_sof_eof = 0;
@@ -530,9 +532,14 @@ int ixgbe_fso(struct ixgbe_ring *tx_ring, struct sk_buff *skb,
 	*hdr_len = sizeof(struct fcoe_crc_eof);
 
 	/* hdr_len includes fc_hdr if FCoE LSO is enabled */
-	if (skb_is_gso(skb))
-		*hdr_len += (skb_transport_offset(skb) +
-			     sizeof(struct fc_frame_header));
+	if (skb_is_gso(skb)) {
+		*hdr_len += skb_transport_offset(skb) +
+			    sizeof(struct fc_frame_header);
+		/* update gso_segs and bytecount */
+		first->gso_segs = DIV_ROUND_UP(skb->len - *hdr_len,
+					       skb_shinfo(skb)->gso_size);
+		first->bytecount += (first->gso_segs - 1) * *hdr_len;
+	}
 
 	/* mss_l4len_id: use 1 for FSO as TSO, no need for L4LEN */
 	mss_l4len_idx = skb_shinfo(skb)->gso_size << IXGBE_ADVTXD_MSS_SHIFT;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 167e898fbba..1d8f9f83f8e 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -289,7 +289,7 @@ static void ixgbe_dump(struct ixgbe_adapter *adapter)
 	struct ixgbe_reg_info *reginfo;
 	int n = 0;
 	struct ixgbe_ring *tx_ring;
-	struct ixgbe_tx_buffer *tx_buffer_info;
+	struct ixgbe_tx_buffer *tx_buffer;
 	union ixgbe_adv_tx_desc *tx_desc;
 	struct my_u0 { u64 a; u64 b; } *u0;
 	struct ixgbe_ring *rx_ring;
@@ -329,14 +329,13 @@ static void ixgbe_dump(struct ixgbe_adapter *adapter)
 	pr_info("Queue [NTU] [NTC] [bi(ntc)->dma  ] leng ntw timestamp\n");
 	for (n = 0; n < adapter->num_tx_queues; n++) {
 		tx_ring = adapter->tx_ring[n];
-		tx_buffer_info =
-			&tx_ring->tx_buffer_info[tx_ring->next_to_clean];
+		tx_buffer = &tx_ring->tx_buffer_info[tx_ring->next_to_clean];
 		pr_info(" %5d %5X %5X %016llX %04X %p %016llX\n",
 			   n, tx_ring->next_to_use, tx_ring->next_to_clean,
-			   (u64)tx_buffer_info->dma,
-			   tx_buffer_info->length,
-			   tx_buffer_info->next_to_watch,
-			   (u64)tx_buffer_info->time_stamp);
+			   (u64)dma_unmap_addr(tx_buffer, dma),
+			   dma_unmap_len(tx_buffer, len),
+			   tx_buffer->next_to_watch,
+			   (u64)tx_buffer->time_stamp);
 	}
 
 	/* Print TX Rings */
@@ -367,17 +366,17 @@ static void ixgbe_dump(struct ixgbe_adapter *adapter)
 
 		for (i = 0; tx_ring->desc && (i < tx_ring->count); i++) {
 			tx_desc = IXGBE_TX_DESC(tx_ring, i);
-			tx_buffer_info = &tx_ring->tx_buffer_info[i];
+			tx_buffer = &tx_ring->tx_buffer_info[i];
 			u0 = (struct my_u0 *)tx_desc;
 			pr_info("T [0x%03X]    %016llX %016llX %016llX"
 				" %04X  %p %016llX %p", i,
 				le64_to_cpu(u0->a),
 				le64_to_cpu(u0->b),
-				(u64)tx_buffer_info->dma,
-				tx_buffer_info->length,
-				tx_buffer_info->next_to_watch,
-				(u64)tx_buffer_info->time_stamp,
-				tx_buffer_info->skb);
+				(u64)dma_unmap_addr(tx_buffer, dma),
+				dma_unmap_len(tx_buffer, len),
+				tx_buffer->next_to_watch,
+				(u64)tx_buffer->time_stamp,
+				tx_buffer->skb);
 			if (i == tx_ring->next_to_use &&
 				i == tx_ring->next_to_clean)
 				pr_cont(" NTC/U\n");
@@ -389,11 +388,13 @@ static void ixgbe_dump(struct ixgbe_adapter *adapter)
 				pr_cont("\n");
 
 			if (netif_msg_pktdata(adapter) &&
-				tx_buffer_info->dma != 0)
+			    dma_unmap_len(tx_buffer, len) != 0)
 				print_hex_dump(KERN_INFO, "",
 					DUMP_PREFIX_ADDRESS, 16, 1,
-					phys_to_virt(tx_buffer_info->dma),
-					tx_buffer_info->length, true);
+					phys_to_virt(dma_unmap_addr(tx_buffer,
+								    dma)),
+					dma_unmap_len(tx_buffer, len),
+					true);
 		}
 	}
 
@@ -469,17 +470,7 @@ rx_ring_summary:
 					print_hex_dump(KERN_INFO, "",
 					   DUMP_PREFIX_ADDRESS, 16, 1,
 					   phys_to_virt(rx_buffer_info->dma),
-					   rx_ring->rx_buf_len, true);
-
-					if (rx_ring->rx_buf_len
-						< IXGBE_RXBUFFER_2K)
-						print_hex_dump(KERN_INFO, "",
-						  DUMP_PREFIX_ADDRESS, 16, 1,
-						  phys_to_virt(
-						    rx_buffer_info->page_dma +
-						    rx_buffer_info->page_offset
-						  ),
-						  PAGE_SIZE/2, true);
+					   ixgbe_rx_bufsz(rx_ring), true);
 				}
 			}
 
@@ -589,32 +580,26 @@ static inline void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter,
 	}
 }
 
-static inline void ixgbe_unmap_tx_resource(struct ixgbe_ring *ring,
-					   struct ixgbe_tx_buffer *tx_buffer)
+void ixgbe_unmap_and_free_tx_resource(struct ixgbe_ring *ring,
+				      struct ixgbe_tx_buffer *tx_buffer)
 {
-	if (tx_buffer->dma) {
-		if (tx_buffer->tx_flags & IXGBE_TX_FLAGS_MAPPED_AS_PAGE)
-			dma_unmap_page(ring->dev,
-			               tx_buffer->dma,
-			               tx_buffer->length,
-			               DMA_TO_DEVICE);
-		else
+	if (tx_buffer->skb) {
+		dev_kfree_skb_any(tx_buffer->skb);
+		if (dma_unmap_len(tx_buffer, len))
 			dma_unmap_single(ring->dev,
-			                 tx_buffer->dma,
-			                 tx_buffer->length,
-			                 DMA_TO_DEVICE);
+					 dma_unmap_addr(tx_buffer, dma),
+					 dma_unmap_len(tx_buffer, len),
+					 DMA_TO_DEVICE);
+	} else if (dma_unmap_len(tx_buffer, len)) {
+		dma_unmap_page(ring->dev,
+			       dma_unmap_addr(tx_buffer, dma),
+			       dma_unmap_len(tx_buffer, len),
+			       DMA_TO_DEVICE);
 	}
-	tx_buffer->dma = 0;
-}
-
-void ixgbe_unmap_and_free_tx_resource(struct ixgbe_ring *tx_ring,
-				      struct ixgbe_tx_buffer *tx_buffer_info)
-{
-	ixgbe_unmap_tx_resource(tx_ring, tx_buffer_info);
-	if (tx_buffer_info->skb)
-		dev_kfree_skb_any(tx_buffer_info->skb);
-	tx_buffer_info->skb = NULL;
-	/* tx_buffer_info must be completely set up in the transmit path */
+	tx_buffer->next_to_watch = NULL;
+	tx_buffer->skb = NULL;
+	dma_unmap_len_set(tx_buffer, len, 0);
+	/* tx_buffer must be completely set up in the transmit path */
 }
 
 static void ixgbe_update_xoff_received(struct ixgbe_adapter *adapter)
@@ -671,7 +656,7 @@ static void ixgbe_update_xoff_received(struct ixgbe_adapter *adapter)
 
 static u64 ixgbe_get_tx_completed(struct ixgbe_ring *ring)
 {
-	return ring->tx_stats.completed;
+	return ring->stats.packets;
 }
 
 static u64 ixgbe_get_tx_pending(struct ixgbe_ring *ring)
@@ -751,12 +736,16 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
 	union ixgbe_adv_tx_desc *tx_desc;
 	unsigned int total_bytes = 0, total_packets = 0;
 	unsigned int budget = q_vector->tx.work_limit;
-	u16 i = tx_ring->next_to_clean;
+	unsigned int i = tx_ring->next_to_clean;
+
+	if (test_bit(__IXGBE_DOWN, &adapter->state))
+		return true;
 
 	tx_buffer = &tx_ring->tx_buffer_info[i];
 	tx_desc = IXGBE_TX_DESC(tx_ring, i);
+	i -= tx_ring->count;
 
-	for (; budget; budget--) {
+	do {
 		union ixgbe_adv_tx_desc *eop_desc = tx_buffer->next_to_watch;
 
 		/* if next_to_watch is not set then there is no work pending */
@@ -770,36 +759,65 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
 		if (!(eop_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD)))
 			break;
 
-		/* count the packet as being completed */
-		tx_ring->tx_stats.completed++;
-
 		/* clear next_to_watch to prevent false hangs */
 		tx_buffer->next_to_watch = NULL;
 
-		do {
-			ixgbe_unmap_tx_resource(tx_ring, tx_buffer);
-			if (likely(tx_desc == eop_desc)) {
-				eop_desc = NULL;
-				dev_kfree_skb_any(tx_buffer->skb);
-				tx_buffer->skb = NULL;
+		/* update the statistics for this packet */
+		total_bytes += tx_buffer->bytecount;
+		total_packets += tx_buffer->gso_segs;
 
-				total_bytes += tx_buffer->bytecount;
-				total_packets += tx_buffer->gso_segs;
-			}
+		/* free the skb */
+		dev_kfree_skb_any(tx_buffer->skb);
+
+		/* unmap skb header data */
+		dma_unmap_single(tx_ring->dev,
+				 dma_unmap_addr(tx_buffer, dma),
+				 dma_unmap_len(tx_buffer, len),
+				 DMA_TO_DEVICE);
 
+		/* clear tx_buffer data */
+		tx_buffer->skb = NULL;
+		dma_unmap_len_set(tx_buffer, len, 0);
+
+		/* unmap remaining buffers */
+		while (tx_desc != eop_desc) {
 			tx_buffer++;
 			tx_desc++;
 			i++;
-			if (unlikely(i == tx_ring->count)) {
-				i = 0;
-
+			if (unlikely(!i)) {
+				i -= tx_ring->count;
 				tx_buffer = tx_ring->tx_buffer_info;
 				tx_desc = IXGBE_TX_DESC(tx_ring, 0);
 			}
 
-		} while (eop_desc);
-	}
+			/* unmap any remaining paged data */
+			if (dma_unmap_len(tx_buffer, len)) {
+				dma_unmap_page(tx_ring->dev,
+					       dma_unmap_addr(tx_buffer, dma),
+					       dma_unmap_len(tx_buffer, len),
+					       DMA_TO_DEVICE);
+				dma_unmap_len_set(tx_buffer, len, 0);
+			}
+		}
+
+		/* move us one more past the eop_desc for start of next pkt */
+		tx_buffer++;
+		tx_desc++;
+		i++;
+		if (unlikely(!i)) {
+			i -= tx_ring->count;
+			tx_buffer = tx_ring->tx_buffer_info;
+			tx_desc = IXGBE_TX_DESC(tx_ring, 0);
+		}
 
+		/* issue prefetch for next Tx descriptor */
+		prefetch(tx_desc);
+
+		/* update budget accounting */
+		budget--;
+	} while (likely(budget));
+
+	i += tx_ring->count;
 	tx_ring->next_to_clean = i;
 	u64_stats_update_begin(&tx_ring->syncp);
 	tx_ring->stats.bytes += total_bytes;
@@ -811,7 +829,6 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
 	if (check_for_tx_hang(tx_ring) && ixgbe_check_tx_hang(tx_ring)) {
 		/* schedule immediate reset if we believe we hung */
 		struct ixgbe_hw *hw = &adapter->hw;
-		tx_desc = IXGBE_TX_DESC(tx_ring, i);
 		e_err(drv, "Detected Tx Unit Hang\n"
 			"  Tx Queue             <%d>\n"
 			"  TDH, TDT             <%x>, <%x>\n"
@@ -849,9 +866,11 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
 		 * sees the new next_to_clean.
 		 */
 		smp_mb();
-		if (__netif_subqueue_stopped(tx_ring->netdev, tx_ring->queue_index) &&
-		    !test_bit(__IXGBE_DOWN, &adapter->state)) {
-			netif_wake_subqueue(tx_ring->netdev, tx_ring->queue_index);
+		if (__netif_subqueue_stopped(tx_ring->netdev,
+					     tx_ring->queue_index)
+		    && !test_bit(__IXGBE_DOWN, &adapter->state)) {
+			netif_wake_subqueue(tx_ring->netdev,
+					    tx_ring->queue_index);
 			++tx_ring->tx_stats.restart_queue;
 		}
 	}
@@ -1006,6 +1025,7 @@ static inline void ixgbe_rx_hash(struct ixgbe_ring *ring,
 		skb->rxhash = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss);
 }
 
+#ifdef IXGBE_FCOE
 /**
  * ixgbe_rx_is_fcoe - check the rx desc for incoming pkt type
  * @adapter: address of board private structure
@@ -1024,6 +1044,7 @@ static inline bool ixgbe_rx_is_fcoe(struct ixgbe_adapter *adapter,
 			     IXGBE_RXDADV_PKTTYPE_ETQF_SHIFT)));
 }
 
+#endif /* IXGBE_FCOE */
 /**
  * ixgbe_rx_checksum - indicate in skb if hw indicated a good cksum
  * @ring: structure containing ring specific data
@@ -1051,7 +1072,7 @@ static inline void ixgbe_rx_checksum(struct ixgbe_ring *ring,
 		return;
 
 	if (ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_ERR_TCPE)) {
-		u16 pkt_info = rx_desc->wb.lower.lo_dword.hs_rss.pkt_info;
+		__le16 pkt_info = rx_desc->wb.lower.lo_dword.hs_rss.pkt_info;
 
 		/*
 		 * 82599 errata, UDP frames with a 0 checksum can be marked as
@@ -1072,6 +1093,9 @@ static inline void ixgbe_rx_checksum(struct ixgbe_ring *ring,
 static inline void ixgbe_release_rx_desc(struct ixgbe_ring *rx_ring, u32 val)
 {
 	rx_ring->next_to_use = val;
+
+	/* update next to alloc since we have filled the ring */
+	rx_ring->next_to_alloc = val;
 	/*
 	 * Force memory writes to complete before letting h/w
 	 * know there are new descriptors to fetch.  (Only
@@ -1082,67 +1106,46 @@ static inline void ixgbe_release_rx_desc(struct ixgbe_ring *rx_ring, u32 val)
 	writel(val, rx_ring->tail);
 }
 
-static bool ixgbe_alloc_mapped_skb(struct ixgbe_ring *rx_ring,
-				   struct ixgbe_rx_buffer *bi)
-{
-	struct sk_buff *skb = bi->skb;
-	dma_addr_t dma = bi->dma;
-
-	if (dma)
-		return true;
-
-	if (likely(!skb)) {
-		skb = netdev_alloc_skb_ip_align(rx_ring->netdev,
-						rx_ring->rx_buf_len);
-		bi->skb = skb;
-		if (!skb) {
-			rx_ring->rx_stats.alloc_rx_buff_failed++;
-			return false;
-		}
-	}
-
-	dma = dma_map_single(rx_ring->dev, skb->data,
-			     rx_ring->rx_buf_len, DMA_FROM_DEVICE);
-
-	if (dma_mapping_error(rx_ring->dev, dma)) {
-		rx_ring->rx_stats.alloc_rx_buff_failed++;
-		return false;
-	}
-
-	bi->dma = dma;
-	return true;
-}
-
 static bool ixgbe_alloc_mapped_page(struct ixgbe_ring *rx_ring,
 				    struct ixgbe_rx_buffer *bi)
 {
 	struct page *page = bi->page;
-	dma_addr_t page_dma = bi->page_dma;
-	unsigned int page_offset = bi->page_offset ^ (PAGE_SIZE / 2);
+	dma_addr_t dma = bi->dma;
 
-	if (page_dma)
+	/* since we are recycling buffers we should seldom need to alloc */
+	if (likely(dma))
 		return true;
 
-	if (!page) {
-		page = alloc_page(GFP_ATOMIC | __GFP_COLD);
-		bi->page = page;
+	/* alloc new page for storage */
+	if (likely(!page)) {
+		page = alloc_pages(GFP_ATOMIC | __GFP_COLD,
+				   ixgbe_rx_pg_order(rx_ring));
 		if (unlikely(!page)) {
 			rx_ring->rx_stats.alloc_rx_page_failed++;
 			return false;
 		}
+		bi->page = page;
 	}
 
-	page_dma = dma_map_page(rx_ring->dev, page,
-				page_offset, PAGE_SIZE / 2,
-				DMA_FROM_DEVICE);
+	/* map page for use */
+	dma = dma_map_page(rx_ring->dev, page, 0,
+			   ixgbe_rx_pg_size(rx_ring), DMA_FROM_DEVICE);
+
+	/*
+	 * if mapping failed free memory back to system since
+	 * there isn't much point in holding memory we can't use
+	 */
+	if (dma_mapping_error(rx_ring->dev, dma)) {
+		put_page(page);
+		bi->page = NULL;
 
-	if (dma_mapping_error(rx_ring->dev, page_dma)) {
 		rx_ring->rx_stats.alloc_rx_page_failed++;
 		return false;
 	}
 
-	bi->page_dma = page_dma;
-	bi->page_offset = page_offset;
+	bi->dma = dma;
+	bi->page_offset ^= ixgbe_rx_bufsz(rx_ring);
+
 	return true;
 }
 
@@ -1157,30 +1160,23 @@ void ixgbe_alloc_rx_buffers(struct ixgbe_ring *rx_ring, u16 cleaned_count)
 	struct ixgbe_rx_buffer *bi;
 	u16 i = rx_ring->next_to_use;
 
-	/* nothing to do or no valid netdev defined */
-	if (!cleaned_count || !rx_ring->netdev)
+	/* nothing to do */
+	if (!cleaned_count)
 		return;
 
 	rx_desc = IXGBE_RX_DESC(rx_ring, i);
 	bi = &rx_ring->rx_buffer_info[i];
 	i -= rx_ring->count;
 
-	while (cleaned_count--) {
-		if (!ixgbe_alloc_mapped_skb(rx_ring, bi))
+	do {
+		if (!ixgbe_alloc_mapped_page(rx_ring, bi))
 			break;
 
-		/* Refresh the desc even if buffer_addrs didn't change
-		 * because each write-back erases this info. */
-		if (ring_is_ps_enabled(rx_ring)) {
-			rx_desc->read.hdr_addr = cpu_to_le64(bi->dma);
-
-			if (!ixgbe_alloc_mapped_page(rx_ring, bi))
-				break;
-
-			rx_desc->read.pkt_addr = cpu_to_le64(bi->page_dma);
-		} else {
-			rx_desc->read.pkt_addr = cpu_to_le64(bi->dma);
-		}
+		/*
+		 * Refresh the desc even if buffer_addrs didn't change
+		 * because each write-back erases this info.
+		 */
+		rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset);
 
 		rx_desc++;
 		bi++;
@@ -1193,7 +1189,9 @@ void ixgbe_alloc_rx_buffers(struct ixgbe_ring *rx_ring, u16 cleaned_count)
 
 		/* clear the hdr_addr for the next_to_use descriptor */
 		rx_desc->read.hdr_addr = 0;
-	}
+
+		cleaned_count--;
+	} while (cleaned_count);
 
 	i += rx_ring->count;
 
@@ -1201,90 +1199,6 @@ void ixgbe_alloc_rx_buffers(struct ixgbe_ring *rx_ring, u16 cleaned_count)
 		ixgbe_release_rx_desc(rx_ring, i);
 }
 
-static inline u16 ixgbe_get_hlen(union ixgbe_adv_rx_desc *rx_desc)
-{
-	/* HW will not DMA in data larger than the given buffer, even if it
-	 * parses the (NFS, of course) header to be larger.  In that case, it
-	 * fills the header buffer and spills the rest into the page.
-	 */
-	u16 hdr_info = le16_to_cpu(rx_desc->wb.lower.lo_dword.hs_rss.hdr_info);
-	u16 hlen = (hdr_info &  IXGBE_RXDADV_HDRBUFLEN_MASK) >>
-		    IXGBE_RXDADV_HDRBUFLEN_SHIFT;
-	if (hlen > IXGBE_RX_HDR_SIZE)
-		hlen = IXGBE_RX_HDR_SIZE;
-	return hlen;
-}
-
-/**
- * ixgbe_merge_active_tail - merge active tail into lro skb
- * @tail: pointer to active tail in frag_list
- *
- * This function merges the length and data of an active tail into the
- * skb containing the frag_list.  It resets the tail's pointer to the head,
- * but it leaves the heads pointer to tail intact.
- **/
-static inline struct sk_buff *ixgbe_merge_active_tail(struct sk_buff *tail)
-{
-	struct sk_buff *head = IXGBE_CB(tail)->head;
-
-	if (!head)
-		return tail;
-
-	head->len += tail->len;
-	head->data_len += tail->len;
-	head->truesize += tail->len;
-
-	IXGBE_CB(tail)->head = NULL;
-
-	return head;
-}
-
-/**
- * ixgbe_add_active_tail - adds an active tail into the skb frag_list
- * @head: pointer to the start of the skb
- * @tail: pointer to active tail to add to frag_list
- *
- * This function adds an active tail to the end of the frag list.  This tail
- * will still be receiving data so we cannot yet ad it's stats to the main
- * skb.  That is done via ixgbe_merge_active_tail.
- **/
-static inline void ixgbe_add_active_tail(struct sk_buff *head,
-					 struct sk_buff *tail)
-{
-	struct sk_buff *old_tail = IXGBE_CB(head)->tail;
-
-	if (old_tail) {
-		ixgbe_merge_active_tail(old_tail);
-		old_tail->next = tail;
-	} else {
-		skb_shinfo(head)->frag_list = tail;
-	}
-
-	IXGBE_CB(tail)->head = head;
-	IXGBE_CB(head)->tail = tail;
-}
-
-/**
- * ixgbe_close_active_frag_list - cleanup pointers on a frag_list skb
- * @head: pointer to head of an active frag list
- *
- * This function will clear the frag_tail_tracker pointer on an active
- * frag_list and returns true if the pointer was actually set
- **/
-static inline bool ixgbe_close_active_frag_list(struct sk_buff *head)
-{
-	struct sk_buff *tail = IXGBE_CB(head)->tail;
-
-	if (!tail)
-		return false;
-
-	ixgbe_merge_active_tail(tail);
-
-	IXGBE_CB(head)->tail = NULL;
-
-	return true;
-}
-
 /**
  * ixgbe_get_headlen - determine size of header for RSC/LRO/GRO/FCOE
  * @data: pointer to the start of the headers
@@ -1346,7 +1260,7 @@ static unsigned int ixgbe_get_headlen(unsigned char *data,
 		/* record next protocol */
 		nexthdr = hdr.ipv4->protocol;
 		hdr.network += hlen;
-#ifdef CONFIG_FCOE
+#ifdef IXGBE_FCOE
 	} else if (protocol == __constant_htons(ETH_P_FCOE)) {
 		if ((hdr.network - data) > (max_len - FCOE_HEADER_LEN))
 			return max_len;
@@ -1409,7 +1323,7 @@ static void ixgbe_get_rsc_cnt(struct ixgbe_ring *rx_ring,
 static void ixgbe_set_rsc_gso_size(struct ixgbe_ring *ring,
 				   struct sk_buff *skb)
 {
-	u16 hdr_len = ixgbe_get_headlen(skb->data, skb_headlen(skb));
+	u16 hdr_len = skb_headlen(skb);
 
 	/* set gso_size to avoid messing up TCP MSS */
 	skb_shinfo(skb)->gso_size = DIV_ROUND_UP((skb->len - hdr_len),
@@ -1473,149 +1387,346 @@ static void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector,
 		netif_rx(skb);
 }
 
+/**
+ * ixgbe_is_non_eop - process handling of non-EOP buffers
+ * @rx_ring: Rx ring being processed
+ * @rx_desc: Rx descriptor for current buffer
+ * @skb: Current socket buffer containing buffer in progress
+ *
+ * This function updates next to clean.  If the buffer is an EOP buffer
+ * this function exits returning false, otherwise it will place the
+ * sk_buff in the next buffer to be chained and return true indicating
+ * that this is in fact a non-EOP buffer.
+ **/
+static bool ixgbe_is_non_eop(struct ixgbe_ring *rx_ring,
+			     union ixgbe_adv_rx_desc *rx_desc,
+			     struct sk_buff *skb)
+{
+	u32 ntc = rx_ring->next_to_clean + 1;
+
+	/* fetch, update, and store next to clean */
+	ntc = (ntc < rx_ring->count) ? ntc : 0;
+	rx_ring->next_to_clean = ntc;
+
+	prefetch(IXGBE_RX_DESC(rx_ring, ntc));
+
+	if (likely(ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)))
+		return false;
+
+	/* append_cnt indicates packet is RSC, if so fetch nextp */
+	if (IXGBE_CB(skb)->append_cnt) {
+		ntc = le32_to_cpu(rx_desc->wb.upper.status_error);
+		ntc &= IXGBE_RXDADV_NEXTP_MASK;
+		ntc >>= IXGBE_RXDADV_NEXTP_SHIFT;
+	}
+
+	/* place skb in next buffer to be received */
+	rx_ring->rx_buffer_info[ntc].skb = skb;
+	rx_ring->rx_stats.non_eop_descs++;
+
+	return true;
+}
+
+/**
+ * ixgbe_cleanup_headers - Correct corrupted or empty headers
+ * @rx_ring: rx descriptor ring packet is being transacted on
+ * @rx_desc: pointer to the EOP Rx descriptor
+ * @skb: pointer to current skb being fixed
+ *
+ * Check for corrupted packet headers caused by senders on the local L2
+ * embedded NIC switch not setting up their Tx Descriptors right.  These
+ * should be very rare.
+ *
+ * Also address the case where we are pulling data in on pages only
+ * and as such no data is present in the skb header.
+ *
+ * In addition if skb is not at least 60 bytes we need to pad it so that
+ * it is large enough to qualify as a valid Ethernet frame.
+ *
+ * Returns true if an error was encountered and skb was freed.
+ **/
+static bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring,
+				  union ixgbe_adv_rx_desc *rx_desc,
+				  struct sk_buff *skb)
+{
+	struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
+	struct net_device *netdev = rx_ring->netdev;
+	unsigned char *va;
+	unsigned int pull_len;
+
+	/* if the page was released unmap it, else just sync our portion */
+	if (unlikely(IXGBE_CB(skb)->page_released)) {
+		dma_unmap_page(rx_ring->dev, IXGBE_CB(skb)->dma,
+			       ixgbe_rx_pg_size(rx_ring), DMA_FROM_DEVICE);
+		IXGBE_CB(skb)->page_released = false;
+	} else {
+		dma_sync_single_range_for_cpu(rx_ring->dev,
+					      IXGBE_CB(skb)->dma,
+					      frag->page_offset,
+					      ixgbe_rx_bufsz(rx_ring),
+					      D