Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) BPF debugger and asm tool by Daniel Borkmann.

 2) Speed up create/bind in AF_PACKET, also from Daniel Borkmann.

 3) Correct reciprocal_divide and update users, from Hannes Frederic
    Sowa and Daniel Borkmann.

 4) Currently we only have a "set" operation for the hw timestamp socket
    ioctl, add a "get" operation to match.  From Ben Hutchings.

 5) Add better trace events for debugging driver datapath problems, also
    from Ben Hutchings.

 6) Implement auto corking in TCP, from Eric Dumazet.  Basically, if we
    have a small send and a previous packet is already in the qdisc or
    device queue, defer until TX completion or we get more data.

 7) Allow userspace to manage ipv6 temporary addresses, from Jiri Pirko.

 8) Add a qdisc bypass option for AF_PACKET sockets, from Daniel
    Borkmann.

 9) Share IP header compression code between Bluetooth and IEEE802154
    layers, from Jukka Rissanen.

10) Fix ipv6 router reachability probing, from Jiri Benc.

11) Allow packets to be captured on macvtap devices, from Vlad Yasevich.

12) Support tunneling in GRO layer, from Jerry Chu.

13) Allow bonding to be configured fully using netlink, from Scott
    Feldman.

14) Allow AF_PACKET users to obtain the VLAN TPID, just like they can
    already get the TCI.  From Atzm Watanabe.

15) New "Heavy Hitter" qdisc, from Terry Lam.

16) Significantly improve the IPSEC support in pktgen, from Fan Du.

17) Allow ipv4 tunnels to cache routes, just like sockets.  From Tom
    Herbert.

18) Add Proportional Integral Enhanced packet scheduler, from Vijay
    Subramanian.

19) Allow openvswitch to mmap'd netlink, from Thomas Graf.

20) Key TCP metrics blobs also by source address, not just destination
    address.  From Christoph Paasch.

21) Support 10G in generic phylib.  From Andy Fleming.

22) Try to short-circuit GRO flow compares using device provided RX
    hash, if provided.  From Tom Herbert.

The wireless and netfilter folks have been busy little bees too.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2064 commits)
  net/cxgb4: Fix referencing freed adapter
  ipv6: reallocate addrconf router for ipv6 address when lo device up
  fib_frontend: fix possible NULL pointer dereference
  rtnetlink: remove IFLA_BOND_SLAVE definition
  rtnetlink: remove check for fill_slave_info in rtnl_have_link_slave_info
  qlcnic: update version to 5.3.55
  qlcnic: Enhance logic to calculate msix vectors.
  qlcnic: Refactor interrupt coalescing code for all adapters.
  qlcnic: Update poll controller code path
  qlcnic: Interrupt code cleanup
  qlcnic: Enhance Tx timeout debugging.
  qlcnic: Use bool for rx_mac_learn.
  bonding: fix u64 division
  rtnetlink: add missing IFLA_BOND_AD_INFO_UNSPEC
  sfc: Use the correct maximum TX DMA ring size for SFC9100
  Add Shradha Shah as the sfc driver maintainer.
  net/vxlan: Share RX skb de-marking and checksum checks with ovs
  tulip: cleanup by using ARRAY_SIZE()
  ip_tunnel: clear IPCB in ip_tunnel_xmit() in case dst_link_failure() is called
  net/cxgb4: Don't retrieve stats during recovery
  ...

4 files changed, 745 insertions, 721 deletions

diff --git a/drivers/net/ethernet/intel/ixgbevf/defines.h b/drivers/net/ethernet/intel/ixgbevf/defines.h
index 3147795bd135..05e4f32d84f7 100644
--- a/drivers/net/ethernet/intel/ixgbevf/defines.h
+++ b/drivers/net/ethernet/intel/ixgbevf/defines.h
@@ -183,6 +183,7 @@ typedef u32 ixgbe_link_speed;
 #define IXGBE_TXD_CMD_DEXT   0x20000000 /* Descriptor extension (0 = legacy) */
 #define IXGBE_TXD_CMD_VLE    0x40000000 /* Add VLAN tag */
 #define IXGBE_TXD_STAT_DD    0x00000001 /* Descriptor Done */
+#define IXGBE_TXD_CMD	     (IXGBE_TXD_CMD_EOP | IXGBE_TXD_CMD_RS)
 
 /* Transmit Descriptor - Advanced */
 union ixgbe_adv_tx_desc {
@@ -277,4 +278,21 @@ struct ixgbe_adv_tx_context_desc {
 #define IXGBE_ERR_RESET_FAILED                  -2
 #define IXGBE_ERR_INVALID_ARGUMENT              -3
 
+/* Transmit Config masks */
+#define IXGBE_TXDCTL_ENABLE		0x02000000 /* Ena specific Tx Queue */
+#define IXGBE_TXDCTL_SWFLSH		0x04000000 /* Tx Desc. wr-bk flushing */
+#define IXGBE_TXDCTL_WTHRESH_SHIFT	16	   /* shift to WTHRESH bits */
+
+#define IXGBE_DCA_RXCTRL_DESC_DCA_EN	(1 << 5)  /* Rx Desc enable */
+#define IXGBE_DCA_RXCTRL_HEAD_DCA_EN	(1 << 6)  /* Rx Desc header ena */
+#define IXGBE_DCA_RXCTRL_DATA_DCA_EN	(1 << 7)  /* Rx Desc payload ena */
+#define IXGBE_DCA_RXCTRL_DESC_RRO_EN	(1 << 9)  /* Rx rd Desc Relax Order */
+#define IXGBE_DCA_RXCTRL_DATA_WRO_EN	(1 << 13) /* Rx wr data Relax Order */
+#define IXGBE_DCA_RXCTRL_HEAD_WRO_EN	(1 << 15) /* Rx wr header RO */
+
+#define IXGBE_DCA_TXCTRL_DESC_DCA_EN	(1 << 5)  /* DCA Tx Desc enable */
+#define IXGBE_DCA_TXCTRL_DESC_RRO_EN	(1 << 9)  /* Tx rd Desc Relax Order */
+#define IXGBE_DCA_TXCTRL_DESC_WRO_EN	(1 << 11) /* Tx Desc writeback RO bit */
+#define IXGBE_DCA_TXCTRL_DATA_RRO_EN	(1 << 13) /* Tx rd data Relax Order */
+
 #endif /* _IXGBEVF_DEFINES_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c
index 54d9acef9c4e..f68b78c732a8 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c
@@ -77,11 +77,11 @@ static const struct ixgbe_stats ixgbe_gstrings_stats[] = {
 	{"tx_bytes", IXGBEVF_STAT(stats.vfgotc, stats.base_vfgotc,
 				  stats.saved_reset_vfgotc)},
 	{"tx_busy", IXGBEVF_ZSTAT(tx_busy)},
+	{"tx_restart_queue", IXGBEVF_ZSTAT(restart_queue)},
+	{"tx_timeout_count", IXGBEVF_ZSTAT(tx_timeout_count)},
 	{"multicast", IXGBEVF_STAT(stats.vfmprc, stats.base_vfmprc,
 				   stats.saved_reset_vfmprc)},
-	{"rx_csum_offload_good", IXGBEVF_ZSTAT(hw_csum_rx_good)},
 	{"rx_csum_offload_errors", IXGBEVF_ZSTAT(hw_csum_rx_error)},
-	{"tx_csum_offload_ctxt", IXGBEVF_ZSTAT(hw_csum_tx_good)},
 #ifdef BP_EXTENDED_STATS
 	{"rx_bp_poll_yield", IXGBEVF_ZSTAT(bp_rx_yields)},
 	{"rx_bp_cleaned", IXGBEVF_ZSTAT(bp_rx_cleaned)},
@@ -286,9 +286,9 @@ static int ixgbevf_set_ringparam(struct net_device *netdev,
 
 	if (!netif_running(adapter->netdev)) {
 		for (i = 0; i < adapter->num_tx_queues; i++)
-			adapter->tx_ring[i].count = new_tx_count;
+			adapter->tx_ring[i]->count = new_tx_count;
 		for (i = 0; i < adapter->num_rx_queues; i++)
-			adapter->rx_ring[i].count = new_rx_count;
+			adapter->rx_ring[i]->count = new_rx_count;
 		adapter->tx_ring_count = new_tx_count;
 		adapter->rx_ring_count = new_rx_count;
 		goto clear_reset;
@@ -303,20 +303,20 @@ static int ixgbevf_set_ringparam(struct net_device *netdev,
 
 		for (i = 0; i < adapter->num_tx_queues; i++) {
 			/* clone ring and setup updated count */
-			tx_ring[i] = adapter->tx_ring[i];
+			tx_ring[i] = *adapter->tx_ring[i];
 			tx_ring[i].count = new_tx_count;
-			err = ixgbevf_setup_tx_resources(adapter, &tx_ring[i]);
-			if (!err)
-				continue;
-			while (i) {
-				i--;
-				ixgbevf_free_tx_resources(adapter, &tx_ring[i]);
-			}
+			err = ixgbevf_setup_tx_resources(&tx_ring[i]);
+			if (err) {
+				while (i) {
+					i--;
+					ixgbevf_free_tx_resources(&tx_ring[i]);
+				}
 
-			vfree(tx_ring);
-			tx_ring = NULL;
+				vfree(tx_ring);
+				tx_ring = NULL;
 
-			goto clear_reset;
+				goto clear_reset;
+			}
 		}
 	}
 
@@ -329,20 +329,20 @@ static int ixgbevf_set_ringparam(struct net_device *netdev,
 
 		for (i = 0; i < adapter->num_rx_queues; i++) {
 			/* clone ring and setup updated count */
-			rx_ring[i] = adapter->rx_ring[i];
+			rx_ring[i] = *adapter->rx_ring[i];
 			rx_ring[i].count = new_rx_count;
-			err = ixgbevf_setup_rx_resources(adapter, &rx_ring[i]);
-			if (!err)
-				continue;
-			while (i) {
-				i--;
-				ixgbevf_free_rx_resources(adapter, &rx_ring[i]);
-			}
+			err = ixgbevf_setup_rx_resources(&rx_ring[i]);
+			if (err) {
+				while (i) {
+					i--;
+					ixgbevf_free_rx_resources(&rx_ring[i]);
+				}
 
-			vfree(rx_ring);
-			rx_ring = NULL;
+				vfree(rx_ring);
+				rx_ring = NULL;
 
-			goto clear_reset;
+				goto clear_reset;
+			}
 		}
 	}
 
@@ -352,9 +352,8 @@ static int ixgbevf_set_ringparam(struct net_device *netdev,
 	/* Tx */
 	if (tx_ring) {
 		for (i = 0; i < adapter->num_tx_queues; i++) {
-			ixgbevf_free_tx_resources(adapter,
-						  &adapter->tx_ring[i]);
-			adapter->tx_ring[i] = tx_ring[i];
+			ixgbevf_free_tx_resources(adapter->tx_ring[i]);
+			*adapter->tx_ring[i] = tx_ring[i];
 		}
 		adapter->tx_ring_count = new_tx_count;
 
@@ -365,9 +364,8 @@ static int ixgbevf_set_ringparam(struct net_device *netdev,
 	/* Rx */
 	if (rx_ring) {
 		for (i = 0; i < adapter->num_rx_queues; i++) {
-			ixgbevf_free_rx_resources(adapter,
-						  &adapter->rx_ring[i]);
-			adapter->rx_ring[i] = rx_ring[i];
+			ixgbevf_free_rx_resources(adapter->rx_ring[i]);
+			*adapter->rx_ring[i] = rx_ring[i];
 		}
 		adapter->rx_ring_count = new_rx_count;
 
@@ -382,7 +380,7 @@ clear_reset:
 	/* free Tx resources if Rx error is encountered */
 	if (tx_ring) {
 		for (i = 0; i < adapter->num_tx_queues; i++)
-			ixgbevf_free_tx_resources(adapter, &tx_ring[i]);
+			ixgbevf_free_tx_resources(&tx_ring[i]);
 		vfree(tx_ring);
 	}
 
@@ -413,15 +411,15 @@ static void ixgbevf_get_ethtool_stats(struct net_device *netdev,
 	    tx_yields = 0, tx_cleaned = 0, tx_missed = 0;
 
 	for (i = 0; i < adapter->num_rx_queues; i++) {
-		rx_yields += adapter->rx_ring[i].bp_yields;
-		rx_cleaned += adapter->rx_ring[i].bp_cleaned;
-		rx_yields += adapter->rx_ring[i].bp_yields;
+		rx_yields += adapter->rx_ring[i]->stats.yields;
+		rx_cleaned += adapter->rx_ring[i]->stats.cleaned;
+		rx_yields += adapter->rx_ring[i]->stats.yields;
 	}
 
 	for (i = 0; i < adapter->num_tx_queues; i++) {
-		tx_yields += adapter->tx_ring[i].bp_yields;
-		tx_cleaned += adapter->tx_ring[i].bp_cleaned;
-		tx_yields += adapter->tx_ring[i].bp_yields;
+		tx_yields += adapter->tx_ring[i]->stats.yields;
+		tx_cleaned += adapter->tx_ring[i]->stats.cleaned;
+		tx_yields += adapter->tx_ring[i]->stats.yields;
 	}
 
 	adapter->bp_rx_yields = rx_yields;
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
index 8971e2d0a984..54829326bb09 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
@@ -46,12 +46,15 @@
 /* wrapper around a pointer to a socket buffer,
  * so a DMA handle can be stored along with the buffer */
 struct ixgbevf_tx_buffer {
-	struct sk_buff *skb;
-	dma_addr_t dma;
-	unsigned long time_stamp;
 	union ixgbe_adv_tx_desc *next_to_watch;
-	u16 length;
-	u16 mapped_as_page;
+	unsigned long time_stamp;
+	struct sk_buff *skb;
+	unsigned int bytecount;
+	unsigned short gso_segs;
+	__be16 protocol;
+	DEFINE_DMA_UNMAP_ADDR(dma);
+	DEFINE_DMA_UNMAP_LEN(len);
+	u32 tx_flags;
 };
 
 struct ixgbevf_rx_buffer {
@@ -59,6 +62,29 @@ struct ixgbevf_rx_buffer {
 	dma_addr_t dma;
 };
 
+struct ixgbevf_stats {
+	u64 packets;
+	u64 bytes;
+#ifdef BP_EXTENDED_STATS
+	u64 yields;
+	u64 misses;
+	u64 cleaned;
+#endif
+};
+
+struct ixgbevf_tx_queue_stats {
+	u64 restart_queue;
+	u64 tx_busy;
+	u64 tx_done_old;
+};
+
+struct ixgbevf_rx_queue_stats {
+	u64 non_eop_descs;
+	u64 alloc_rx_page_failed;
+	u64 alloc_rx_buff_failed;
+	u64 csum_err;
+};
+
 struct ixgbevf_ring {
 	struct ixgbevf_ring *next;
 	struct net_device *netdev;
@@ -70,31 +96,27 @@ struct ixgbevf_ring {
 	unsigned int next_to_use;
 	unsigned int next_to_clean;
 
-	int queue_index; /* needed for multiqueue queue management */
 	union {
 		struct ixgbevf_tx_buffer *tx_buffer_info;
 		struct ixgbevf_rx_buffer *rx_buffer_info;
 	};
 
-	u64			total_bytes;
-	u64			total_packets;
-	struct u64_stats_sync	syncp;
-	u64 hw_csum_rx_error;
-	u64 hw_csum_rx_good;
-#ifdef BP_EXTENDED_STATS
-	u64 bp_yields;
-	u64 bp_misses;
-	u64 bp_cleaned;
-#endif
+	struct ixgbevf_stats stats;
+	struct u64_stats_sync syncp;
+	union {
+		struct ixgbevf_tx_queue_stats tx_stats;
+		struct ixgbevf_rx_queue_stats rx_stats;
+	};
 
-	u16 head;
-	u16 tail;
+	u64 hw_csum_rx_error;
+	u8 __iomem *tail;
 
 	u16 reg_idx; /* holds the special value that gets the hardware register
 		      * offset associated with this ring, which is different
 		      * for DCB and RSS modes */
 
 	u16 rx_buf_len;
+	int queue_index; /* needed for multiqueue queue management */
 };
 
 /* How many Rx Buffers do we bundle into one write to the hardware ? */
@@ -125,8 +147,6 @@ struct ixgbevf_ring {
 #define IXGBE_TX_FLAGS_VLAN		(u32)(1 << 1)
 #define IXGBE_TX_FLAGS_TSO		(u32)(1 << 2)
 #define IXGBE_TX_FLAGS_IPV4		(u32)(1 << 3)
-#define IXGBE_TX_FLAGS_FCOE		(u32)(1 << 4)
-#define IXGBE_TX_FLAGS_FSO		(u32)(1 << 5)
 #define IXGBE_TX_FLAGS_VLAN_MASK	0xffff0000
 #define IXGBE_TX_FLAGS_VLAN_PRIO_MASK	0x0000e000
 #define IXGBE_TX_FLAGS_VLAN_SHIFT	16
@@ -188,7 +208,7 @@ static inline bool ixgbevf_qv_lock_napi(struct ixgbevf_q_vector *q_vector)
 		q_vector->state |= IXGBEVF_QV_STATE_NAPI_YIELD;
 		rc = false;
 #ifdef BP_EXTENDED_STATS
-		q_vector->tx.ring->bp_yields++;
+		q_vector->tx.ring->stats.yields++;
 #endif
 	} else {
 		/* we don't care if someone yielded */
@@ -223,7 +243,7 @@ static inline bool ixgbevf_qv_lock_poll(struct ixgbevf_q_vector *q_vector)
 		q_vector->state |= IXGBEVF_QV_STATE_POLL_YIELD;
 		rc = false;
 #ifdef BP_EXTENDED_STATS
-		q_vector->rx.ring->bp_yields++;
+		q_vector->rx.ring->stats.yields++;
 #endif
 	} else {
 		/* preserve yield marks */
@@ -262,6 +282,7 @@ static inline bool ixgbevf_qv_disable(struct ixgbevf_q_vector *q_vector)
 	spin_lock_bh(&q_vector->lock);
 	if (q_vector->state & IXGBEVF_QV_OWNED)
 		rc = false;
+	q_vector->state |= IXGBEVF_QV_STATE_DISABLED;
 	spin_unlock_bh(&q_vector->lock);
 	return rc;
 }
@@ -315,7 +336,6 @@ static inline u16 ixgbevf_desc_unused(struct ixgbevf_ring *ring)
 struct ixgbevf_adapter {
 	struct timer_list watchdog_timer;
 	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
-	u16 bd_number;
 	struct work_struct reset_task;
 	struct ixgbevf_q_vector *q_vector[MAX_MSIX_Q_VECTORS];
 
@@ -328,25 +348,18 @@ struct ixgbevf_adapter {
 	u32 eims_other;
 
 	/* TX */
-	struct ixgbevf_ring *tx_ring;	/* One per active queue */
 	int num_tx_queues;
+	struct ixgbevf_ring *tx_ring[MAX_TX_QUEUES]; /* One per active queue */
 	u64 restart_queue;
-	u64 hw_csum_tx_good;
-	u64 lsc_int;
-	u64 hw_tso_ctxt;
-	u64 hw_tso6_ctxt;
 	u32 tx_timeout_count;
 
 	/* RX */
-	struct ixgbevf_ring *rx_ring;	/* One per active queue */
 	int num_rx_queues;
+	struct ixgbevf_ring *rx_ring[MAX_TX_QUEUES]; /* One per active queue */
 	u64 hw_csum_rx_error;
 	u64 hw_rx_no_dma_resources;
-	u64 hw_csum_rx_good;
 	u64 non_eop_descs;
 	int num_msix_vectors;
-	struct msix_entry *msix_entries;
-
 	u32 alloc_rx_page_failed;
 	u32 alloc_rx_buff_failed;
 
@@ -356,6 +369,9 @@ struct ixgbevf_adapter {
 	u32 flags;
 #define IXGBE_FLAG_IN_WATCHDOG_TASK             (u32)(1)
 #define IXGBE_FLAG_IN_NETPOLL                   (u32)(1 << 1)
+#define IXGBEVF_FLAG_QUEUE_RESET_REQUESTED	(u32)(1 << 2)
+
+	struct msix_entry *msix_entries;
 
 	/* OS defined structs */
 	struct net_device *netdev;
@@ -364,10 +380,12 @@ struct ixgbevf_adapter {
 	/* structs defined in ixgbe_vf.h */
 	struct ixgbe_hw hw;
 	u16 msg_enable;
-	struct ixgbevf_hw_stats stats;
+	u16 bd_number;
 	/* Interrupt Throttle Rate */
 	u32 eitr_param;
 
+	struct ixgbevf_hw_stats stats;
+
 	unsigned long state;
 	u64 tx_busy;
 	unsigned int tx_ring_count;
@@ -386,9 +404,9 @@ struct ixgbevf_adapter {
 	u32 link_speed;
 	bool link_up;
 
-	struct work_struct watchdog_task;
-
 	spinlock_t mbx_lock;
+
+	struct work_struct watchdog_task;
 };
 
 enum ixbgevf_state_t {
@@ -420,10 +438,10 @@ void ixgbevf_down(struct ixgbevf_adapter *adapter);
 void ixgbevf_reinit_locked(struct ixgbevf_adapter *adapter);
 void ixgbevf_reset(struct ixgbevf_adapter *adapter);
 void ixgbevf_set_ethtool_ops(struct net_device *netdev);
-int ixgbevf_setup_rx_resources(struct ixgbevf_adapter *, struct ixgbevf_ring *);
-int ixgbevf_setup_tx_resources(struct ixgbevf_adapter *, struct ixgbevf_ring *);
-void ixgbevf_free_rx_resources(struct ixgbevf_adapter *, struct ixgbevf_ring *);
-void ixgbevf_free_tx_resources(struct ixgbevf_adapter *, struct ixgbevf_ring *);
+int ixgbevf_setup_rx_resources(struct ixgbevf_ring *);
+int ixgbevf_setup_tx_resources(struct ixgbevf_ring *);
+void ixgbevf_free_rx_resources(struct ixgbevf_ring *);
+void ixgbevf_free_tx_resources(struct ixgbevf_ring *);
 void ixgbevf_update_stats(struct ixgbevf_adapter *adapter);
 int ethtool_ioctl(struct ifreq *ifr);
 
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 92ef4cb5a8e8..9df28985eba7 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -58,7 +58,7 @@ const char ixgbevf_driver_name[] = "ixgbevf";
 static const char ixgbevf_driver_string[] =
 	"Intel(R) 10 Gigabit PCI Express Virtual Function Network Driver";
 
-#define DRV_VERSION "2.11.3-k"
+#define DRV_VERSION "2.12.1-k"
 const char ixgbevf_driver_version[] = DRV_VERSION;
 static char ixgbevf_copyright[] =
 	"Copyright (c) 2009 - 2012 Intel Corporation.";
@@ -95,13 +95,15 @@ module_param(debug, int, 0);
 MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");
 
 /* forward decls */
+static void ixgbevf_queue_reset_subtask(struct ixgbevf_adapter *adapter);
 static void ixgbevf_set_itr(struct ixgbevf_q_vector *q_vector);
 static void ixgbevf_free_all_rx_resources(struct ixgbevf_adapter *adapter);
 
-static inline void ixgbevf_release_rx_desc(struct ixgbe_hw *hw,
-					   struct ixgbevf_ring *rx_ring,
+static inline void ixgbevf_release_rx_desc(struct ixgbevf_ring *rx_ring,
 					   u32 val)
 {
+	rx_ring->next_to_use = val;
+
 	/*
 	 * Force memory writes to complete before letting h/w
 	 * know there are new descriptors to fetch.  (Only
@@ -109,7 +111,7 @@ static inline void ixgbevf_release_rx_desc(struct ixgbe_hw *hw,
 	 * such as IA-64).
 	 */
 	wmb();
-	IXGBE_WRITE_REG(hw, IXGBE_VFRDT(rx_ring->reg_idx), val);
+	writel(val, rx_ring->tail);
 }
 
 /**
@@ -143,28 +145,25 @@ static void ixgbevf_set_ivar(struct ixgbevf_adapter *adapter, s8 direction,
 }
 
 static void ixgbevf_unmap_and_free_tx_resource(struct ixgbevf_ring *tx_ring,
-					       struct ixgbevf_tx_buffer
-					       *tx_buffer_info)
-{
-	if (tx_buffer_info->dma) {
-		if (tx_buffer_info->mapped_as_page)
-			dma_unmap_page(tx_ring->dev,
-				       tx_buffer_info->dma,
-				       tx_buffer_info->length,
-				       DMA_TO_DEVICE);
-		else
+					struct ixgbevf_tx_buffer *tx_buffer)
+{
+	if (tx_buffer->skb) {
+		dev_kfree_skb_any(tx_buffer->skb);
+		if (dma_unmap_len(tx_buffer, len))
 			dma_unmap_single(tx_ring->dev,
-					 tx_buffer_info->dma,
-					 tx_buffer_info->length,
+					 dma_unmap_addr(tx_buffer, dma),
+					 dma_unmap_len(tx_buffer, len),
 					 DMA_TO_DEVICE);
-		tx_buffer_info->dma = 0;
+	} else 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);
 	}
-	if (tx_buffer_info->skb) {
-		dev_kfree_skb_any(tx_buffer_info->skb);
-		tx_buffer_info->skb = NULL;
-	}
-	tx_buffer_info->time_stamp = 0;
-	/* 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 */
 }
 
 #define IXGBE_MAX_TXD_PWR	14
@@ -185,20 +184,21 @@ static bool ixgbevf_clean_tx_irq(struct ixgbevf_q_vector *q_vector,
 				 struct ixgbevf_ring *tx_ring)
 {
 	struct ixgbevf_adapter *adapter = q_vector->adapter;
-	union ixgbe_adv_tx_desc *tx_desc, *eop_desc;
-	struct ixgbevf_tx_buffer *tx_buffer_info;
-	unsigned int i, count = 0;
+	struct ixgbevf_tx_buffer *tx_buffer;
+	union ixgbe_adv_tx_desc *tx_desc;
 	unsigned int total_bytes = 0, total_packets = 0;
+	unsigned int budget = tx_ring->count / 2;
+	unsigned int i = tx_ring->next_to_clean;
 
 	if (test_bit(__IXGBEVF_DOWN, &adapter->state))
 		return true;
 
-	i = tx_ring->next_to_clean;
-	tx_buffer_info = &tx_ring->tx_buffer_info[i];
-	eop_desc = tx_buffer_info->next_to_watch;
+	tx_buffer = &tx_ring->tx_buffer_info[i];
+	tx_desc = IXGBEVF_TX_DESC(tx_ring, i);
+	i -= tx_ring->count;
 
 	do {
-		bool cleaned = false;
+		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 */
 		if (!eop_desc)
@@ -212,67 +212,90 @@ static bool ixgbevf_clean_tx_irq(struct ixgbevf_q_vector *q_vector,
 			break;
 
 		/* clear next_to_watch to prevent false hangs */
-		tx_buffer_info->next_to_watch = NULL;
+		tx_buffer->next_to_watch = NULL;
 
-		for ( ; !cleaned; count++) {
-			struct sk_buff *skb;
-			tx_desc = IXGBEVF_TX_DESC(tx_ring, i);
-			cleaned = (tx_desc == eop_desc);
-			skb = tx_buffer_info->skb;
-
-			if (cleaned && skb) {
-				unsigned int segs, bytecount;
-
-				/* gso_segs is currently only valid for tcp */
-				segs = skb_shinfo(skb)->gso_segs ?: 1;
-				/* multiply data chunks by size of headers */
-				bytecount = ((segs - 1) * skb_headlen(skb)) +
-					    skb->len;
-				total_packets += segs;
-				total_bytes += bytecount;
-			}
+		/* update the statistics for this packet */
+		total_bytes += tx_buffer->bytecount;
+		total_packets += tx_buffer->gso_segs;
 
-			ixgbevf_unmap_and_free_tx_resource(tx_ring,
-							   tx_buffer_info);
+		/* free the skb */
+		dev_kfree_skb_any(tx_buffer->skb);
 
-			tx_desc->wb.status = 0;
+		/* 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 (i == tx_ring->count)
-				i = 0;
+			if (unlikely(!i)) {
+				i -= tx_ring->count;
+				tx_buffer = tx_ring->tx_buffer_info;
+				tx_desc = IXGBEVF_TX_DESC(tx_ring, 0);
+			}
 
-			tx_buffer_info = &tx_ring->tx_buffer_info[i];
+			/* 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 = IXGBEVF_TX_DESC(tx_ring, 0);
 		}
 
-		eop_desc = tx_buffer_info->next_to_watch;
-	} while (count < tx_ring->count);
+		/* 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;
+	tx_ring->stats.packets += total_packets;
+	u64_stats_update_end(&tx_ring->syncp);
+	q_vector->tx.total_bytes += total_bytes;
+	q_vector->tx.total_packets += total_packets;
 
 #define TX_WAKE_THRESHOLD (DESC_NEEDED * 2)
-	if (unlikely(count && netif_carrier_ok(tx_ring->netdev) &&
+	if (unlikely(total_packets && netif_carrier_ok(tx_ring->netdev) &&
 		     (ixgbevf_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_subqueue_stopped(tx_ring->netdev,
 					     tx_ring->queue_index) &&
 		    !test_bit(__IXGBEVF_DOWN, &adapter->state)) {
 			netif_wake_subqueue(tx_ring->netdev,
 					    tx_ring->queue_index);
-			++adapter->restart_queue;
+			++tx_ring->tx_stats.restart_queue;
 		}
 	}
 
-	u64_stats_update_begin(&tx_ring->syncp);
-	tx_ring->total_bytes += total_bytes;
-	tx_ring->total_packets += total_packets;
-	u64_stats_update_end(&tx_ring->syncp);
-	q_vector->tx.total_bytes += total_bytes;
-	q_vector->tx.total_packets += total_packets;
-
-	return count < tx_ring->count;
+	return !!budget;
 }
 
 /**
@@ -341,7 +364,7 @@ static inline void ixgbevf_rx_checksum(struct ixgbevf_ring *ring,
 	/* if IP and error */
 	if ((status_err & IXGBE_RXD_STAT_IPCS) &&
 	    (status_err & IXGBE_RXDADV_ERR_IPE)) {
-		ring->hw_csum_rx_error++;
+		ring->rx_stats.csum_err++;
 		return;
 	}
 
@@ -349,51 +372,46 @@ static inline void ixgbevf_rx_checksum(struct ixgbevf_ring *ring,
 		return;
 
 	if (status_err & IXGBE_RXDADV_ERR_TCPE) {
-		ring->hw_csum_rx_error++;
+		ring->rx_stats.csum_err++;
 		return;
 	}
 
 	/* It must be a TCP or UDP packet with a valid checksum */
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
-	ring->hw_csum_rx_good++;
 }
 
 /**
  * ixgbevf_alloc_rx_buffers - Replace used receive buffers; packet split
- * @adapter: address of board private structure
+ * @rx_ring: rx descriptor ring (for a specific queue) to setup buffers on
  **/
-static void ixgbevf_alloc_rx_buffers(struct ixgbevf_adapter *adapter,
-				     struct ixgbevf_ring *rx_ring,
+static void ixgbevf_alloc_rx_buffers(struct ixgbevf_ring *rx_ring,
 				     int cleaned_count)
 {
-	struct pci_dev *pdev = adapter->pdev;
 	union ixgbe_adv_rx_desc *rx_desc;
 	struct ixgbevf_rx_buffer *bi;
 	unsigned int i = rx_ring->next_to_use;
 
-	bi = &rx_ring->rx_buffer_info[i];
-
 	while (cleaned_count--) {
 		rx_desc = IXGBEVF_RX_DESC(rx_ring, i);
+		bi = &rx_ring->rx_buffer_info[i];
 
 		if (!bi->skb) {
 			struct sk_buff *skb;
 
 			skb = netdev_alloc_skb_ip_align(rx_ring->netdev,
 							rx_ring->rx_buf_len);
-			if (!skb) {
-				adapter->alloc_rx_buff_failed++;
+			if (!skb)
 				goto no_buffers;
-			}
+
 			bi->skb = skb;
 
-			bi->dma = dma_map_single(&pdev->dev, skb->data,
+			bi->dma = dma_map_single(rx_ring->dev, skb->data,
 						 rx_ring->rx_buf_len,
 						 DMA_FROM_DEVICE);
-			if (dma_mapping_error(&pdev->dev, bi->dma)) {
+			if (dma_mapping_error(rx_ring->dev, bi->dma)) {
 				dev_kfree_skb(skb);
 				bi->skb = NULL;
-				dev_err(&pdev->dev, "RX DMA map failed\n");
+				dev_err(rx_ring->dev, "Rx DMA map failed\n");
 				break;
 			}
 		}
@@ -402,14 +420,12 @@ static void ixgbevf_alloc_rx_buffers(struct ixgbevf_adapter *adapter,
 		i++;
 		if (i == rx_ring->count)
 			i = 0;
-		bi = &rx_ring->rx_buffer_info[i];
 	}
 
 no_buffers:
-	if (rx_ring->next_to_use != i) {
-		rx_ring->next_to_use = i;
-		ixgbevf_release_rx_desc(&adapter->hw, rx_ring, i);
-	}
+	rx_ring->rx_stats.alloc_rx_buff_failed++;
+	if (rx_ring->next_to_use != i)
+		ixgbevf_release_rx_desc(rx_ring, i);
 }
 
 static inline void ixgbevf_irq_enable_queues(struct ixgbevf_adapter *adapter,
@@ -424,8 +440,6 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
 				struct ixgbevf_ring *rx_ring,
 				int budget)
 {
-	struct ixgbevf_adapter *adapter = q_vector->adapter;
-	struct pci_dev *pdev = adapter->pdev;
 	union ixgbe_adv_rx_desc *rx_desc, *next_rxd;
 	struct ixgbevf_rx_buffer *rx_buffer_info, *next_buffer;
 	struct sk_buff *skb;
@@ -451,7 +465,7 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
 		rx_buffer_info->skb = NULL;
 
 		if (rx_buffer_info->dma) {
-			dma_unmap_single(&pdev->dev, rx_buffer_info->dma,
+			dma_unmap_single(rx_ring->dev, rx_buffer_info->dma,
 					 rx_ring->rx_buf_len,
 					 DMA_FROM_DEVICE);
 			rx_buffer_info->dma = 0;
@@ -471,7 +485,7 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
 		if (!(staterr & IXGBE_RXD_STAT_EOP)) {
 			skb->next = next_buffer->skb;
 			IXGBE_CB(skb->next)->prev = skb;
-			adapter->non_eop_descs++;
+			rx_ring->rx_stats.non_eop_descs++;
 			goto next_desc;
 		}
 
@@ -503,7 +517,7 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
 		 * source pruning.
 		 */
 		if ((skb->pkt_type & (PACKET_BROADCAST | PACKET_MULTICAST)) &&
-		    ether_addr_equal(adapter->netdev->dev_addr,
+		    ether_addr_equal(rx_ring->netdev->dev_addr,
 				     eth_hdr(skb)->h_source)) {
 			dev_kfree_skb_irq(skb);
 			goto next_desc;
@@ -516,8 +530,7 @@ next_desc:
 
 		/* return some buffers to hardware, one at a time is too slow */
 		if (cleaned_count >= IXGBEVF_RX_BUFFER_WRITE) {
-			ixgbevf_alloc_rx_buffers(adapter, rx_ring,
-						 cleaned_count);
+			ixgbevf_alloc_rx_buffers(rx_ring, cleaned_count);
 			cleaned_count = 0;
 		}
 
@@ -532,11 +545,11 @@ next_desc:
 	cleaned_count = ixgbevf_desc_unused(rx_ring);
 
 	if (cleaned_count)
-		ixgbevf_alloc_rx_buffers(adapter, rx_ring, cleaned_count);
+		ixgbevf_alloc_rx_buffers(rx_ring, cleaned_count);
 
 	u64_stats_update_begin(&rx_ring->syncp);
-	rx_ring->total_packets += total_rx_packets;
-	rx_ring->total_bytes += total_rx_bytes;
+	rx_ring->stats.packets += total_rx_packets;
+	rx_ring->stats.bytes += total_rx_bytes;
 	u64_stats_update_end(&rx_ring->syncp);
 	q_vector->rx.total_packets += total_rx_packets;
 	q_vector->rx.total_bytes += total_rx_bytes;
@@ -641,9 +654,9 @@ static int ixgbevf_busy_poll_recv(struct napi_struct *napi)
 		found = ixgbevf_clean_rx_irq(q_vector, ring, 4);
 #ifdef BP_EXTENDED_STATS
 		if (found)
-			ring->bp_cleaned += found;
+			ring->stats.cleaned += found;
 		else
-			ring->bp_misses++;
+			ring->stats.misses++;
 #endif
 		if (found)
 			break;
@@ -848,8 +861,8 @@ static inline void map_vector_to_rxq(struct ixgbevf_adapter *a, int v_idx,
 {
 	struct ixgbevf_q_vector *q_vector = a->q_vector[v_idx];
 
-	a->rx_ring[r_idx].next = q_vector->rx.ring;
-	q_vector->rx.ring = &a->rx_ring[r_idx];
+	a->rx_ring[r_idx]->next = q_vector->rx.ring;
+	q_vector->rx.ring = a->rx_ring[r_idx];
 	q_vector->rx.count++;
 }
 
@@ -858,8 +871,8 @@ static inline void map_vector_to_txq(struct ixgbevf_adapter *a, int v_idx,
 {
 	struct ixgbevf_q_vector *q_vector = a->q_vector[v_idx];
 
-	a->tx_ring[t_idx].next = q_vector->tx.ring;
-	q_vector->tx.ring = &a->tx_ring[t_idx];
+	a->tx_ring[t_idx]->next = q_vector->tx.ring;
+	q_vector->tx.ring = a->tx_ring[t_idx];
 	q_vector->tx.count++;
 }
 
@@ -1087,6 +1100,70 @@ static inline void ixgbevf_irq_enable(struct ixgbevf_adapter *adapter)
 }
 
 /**
+ * ixgbevf_configure_tx_ring - Configure 82599 VF Tx ring after Reset
+ * @adapter: board private structure
+ * @ring: structure containing ring specific data
+ *
+ * Configure the Tx descriptor ring after a reset.
+ **/
+static void ixgbevf_configure_tx_ring(struct ixgbevf_adapter *adapter,
+				      struct ixgbevf_ring *ring)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	u64 tdba = ring->dma;
+	int wait_loop = 10;
+	u32 txdctl = IXGBE_TXDCTL_ENABLE;
+	u8 reg_idx = ring->reg_idx;
+
+	/* disable queue to avoid issues while updating state */
+	IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH);
+	IXGBE_WRITE_FLUSH(hw);
+
+	IXGBE_WRITE_REG(hw, IXGBE_VFTDBAL(reg_idx), tdba & DMA_BIT_MASK(32));
+	IXGBE_WRITE_REG(hw, IXGBE_VFTDBAH(reg_idx), tdba >> 32);
+	IXGBE_WRITE_REG(hw, IXGBE_VFTDLEN(reg_idx),
+			ring->count * sizeof(union ixgbe_adv_tx_desc));
+
+	/* disable head writeback */
+	IXGBE_WRITE_REG(hw, IXGBE_VFTDWBAH(reg_idx), 0);
+	IXGBE_WRITE_REG(hw, IXGBE_VFTDWBAL(reg_idx), 0);
+
+	/* enable relaxed ordering */
+	IXGBE_WRITE_REG(hw, IXGBE_VFDCA_TXCTRL(reg_idx),
+			(IXGBE_DCA_TXCTRL_DESC_RRO_EN |
+			 IXGBE_DCA_TXCTRL_DATA_RRO_EN));
+
+	/* reset head and tail pointers */
+	IXGBE_WRITE_REG(hw, IXGBE_VFTDH(reg_idx), 0);
+	IXGBE_WRITE_REG(hw, IXGBE_VFTDT(reg_idx), 0);
+	ring->tail = hw->hw_addr + IXGBE_VFTDT(reg_idx);
+
+	/* reset ntu and ntc to place SW in sync with hardwdare */
+	ring->next_to_clean = 0;
+	ring->next_to_use = 0;
+
+	/* In order to avoid issues WTHRESH + PTHRESH should always be equal
+	 * to or less than the number of on chip descriptors, which is
+	 * currently 40.
+	 */
+	txdctl |= (8 << 16);    /* WTHRESH = 8 */
+
+	/* Setting PTHRESH to 32 both improves performance */
+	txdctl |= (1 << 8) |    /* HTHRESH = 1 */
+		  32;          /* PTHRESH = 32 */
+
+	IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(reg_idx), txdctl);
+
+	/* poll to verify queue is enabled */
+	do {
+		usleep_range(1000, 2000);
+		txdctl = IXGBE_READ_REG(hw, IXGBE_VFTXDCTL(reg_idx));
+	}  while (--wait_loop && !(txdctl & IXGBE_TXDCTL_ENABLE));
+	if (!wait_loop)
+		pr_err("Could not enable Tx Queue %d\n", reg_idx);
+}
+
+/**
  * ixgbevf_configure_tx - Configure 82599 VF Transmit Unit after Reset
  * @adapter: board private structure
  *
@@ -1094,31 +1171,11 @@ static inline void ixgbevf_irq_enable(struct ixgbevf_adapter *adapter)
  **/
 static void ixgbevf_configure_tx(struct ixgbevf_adapter *adapter)
 {
-	u64 tdba;
-	struct ixgbe_hw *hw = &adapter->hw;
-	u32 i, j, tdlen, txctrl;
+	u32 i;
 
 	/* Setup the HW Tx Head and Tail descriptor pointers */
-	for (i = 0; i < adapter->num_tx_queues; i++) {
-		struct ixgbevf_ring *ring = &adapter->tx_ring[i];
-		j = ring->reg_idx;
-		tdba = ring->dma;
-		tdlen = ring->count * sizeof(union ixgbe_adv_tx_desc);
-		IXGBE_WRITE_REG(hw, IXGBE_VFTDBAL(j),
-				(tdba & DMA_BIT_MASK(32)));
-		IXGBE_WRITE_REG(hw, IXGBE_VFTDBAH(j), (tdba >> 32));
-		IXGBE_WRITE_REG(hw, IXGBE_VFTDLEN(j), tdlen);
-		IXGBE_WRITE_REG(hw, IXGBE_VFTDH(j), 0);
-		IXGBE_WRITE_REG(hw, IXGBE_VFTDT(j), 0);
-		adapter->tx_ring[i].head = IXGBE_VFTDH(j);
-		adapter->tx_ring[i].tail = IXGBE_VFTDT(j);
-		/* Disable Tx Head Writeback RO bit, since this hoses
-		 * bookkeeping if things aren't delivered in order.
-		 */
-		txctrl = IXGBE_READ_REG(hw, IXGBE_VFDCA_TXCTRL(j));
-		txctrl &= ~IXGBE_DCA_TXCTRL_TX_WB_RO_EN;
-		IXGBE_WRITE_REG(hw, IXGBE_VFDCA_TXCTRL(j), txctrl);
-	}
+	for (i = 0; i < adapter->num_tx_queues; i++)
+		ixgbevf_configure_tx_ring(adapter, adapter->tx_ring[i]);
 }
 
 #define IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT	2
@@ -1129,7 +1186,7 @@ static void ixgbevf_configure_srrctl(struct ixgbevf_adapter *adapter, int index)
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 srrctl;
 
-	rx_ring = &adapter->rx_ring[index];
+	rx_ring = adapter->rx_ring[index];
 
 	srrctl = IXGBE_SRRCTL_DROP_EN;
 
@@ -1187,7 +1244,93 @@ static void ixgbevf_set_rx_buffer_len(struct ixgbevf_adapter *adapter)
 		rx_buf_len = IXGBEVF_RXBUFFER_10K;
 
 	for (i = 0; i < adapter->num_rx_queues; i++)
-		adapter->rx_ring[i].rx_buf_len = rx_buf_len;
+		adapter->rx_ring[i]->rx_buf_len = rx_buf_len;
+}
+
+#define IXGBEVF_MAX_RX_DESC_POLL 10
+static void ixgbevf_disable_rx_queue(struct ixgbevf_adapter *adapter,
+				     struct ixgbevf_ring *ring)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	int wait_loop = IXGBEVF_MAX_RX_DESC_POLL;
+	u32 rxdctl;
+	u8 reg_idx = ring->reg_idx;
+
+	rxdctl = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(reg_idx));
+	rxdctl &= ~IXGBE_RXDCTL_ENABLE;
+
+	/* write value back with RXDCTL.ENABLE bit cleared */
+	IXGBE_WRITE_REG(hw, IXGBE_VFRXDCTL(reg_idx), rxdctl);
+
+	/* the hardware may take up to 100us to really disable the rx queue */
+	do {
+		udelay(10);
+		rxdctl = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(reg_idx));
+	} while (--wait_loop && (rxdctl & IXGBE_RXDCTL_ENABLE));
+
+	if (!wait_loop)
+		pr_err("RXDCTL.ENABLE queue %d not cleared while polling\n",
+		       reg_idx);
+}
+
+static void ixgbevf_rx_desc_queue_enable(struct ixgbevf_adapter *adapter,
+					 struct ixgbevf_ring *ring)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	int wait_loop = IXGBEVF_MAX_RX_DESC_POLL;
+	u32 rxdctl;
+	u8 reg_idx = ring->reg_idx;
+
+	do {
+		usleep_range(1000, 2000);
+		rxdctl = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(reg_idx));
+	} while (--wait_loop && !(rxdctl & IXGBE_RXDCTL_ENABLE));
+
+	if (!wait_loop)
+		pr_err("RXDCTL.ENABLE queue %d not set while polling\n",
+		       reg_idx);
+}
+
+static void ixgbevf_configure_rx_ring(struct ixgbevf_adapter *adapter,
+				      struct ixgbevf_ring *ring)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	u64 rdba = ring->dma;
+	u32 rxdctl;
+	u8 reg_idx = ring->reg_idx;
+
+	/* disable queue to avoid issues while updating state */
+	rxdctl = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(reg_idx));
+	ixgbevf_disable_rx_queue(adapter, ring);
+
+	IXGBE_WRITE_REG(hw, IXGBE_VFRDBAL(reg_idx), rdba & DMA_BIT_MASK(32));
+	IXGBE_WRITE_REG(hw, IXGBE_VFRDBAH(reg_idx), rdba >> 32);
+	IXGBE_WRITE_REG(hw, IXGBE_VFRDLEN(reg_idx),
+			ring->count * sizeof(union ixgbe_adv_rx_desc));
+
+	/* enable relaxed ordering */
+	IXGBE_WRITE_REG(hw, IXGBE_VFDCA_RXCTRL(reg_idx),
+			IXGBE_DCA_RXCTRL_DESC_RRO_EN);
+
+	/* reset head and tail pointers */
+	IXGBE_WRITE_REG(hw, IXGBE_VFRDH(reg_idx), 0);
+	IXGBE_WRITE_REG(hw, IXGBE_VFRDT(reg_idx), 0);
+	ring->tail = hw->hw_addr + IXGBE_VFRDT(reg_idx);
+
+	/* reset ntu and ntc to place SW in sync with hardwdare */
+	ring->next_to_clean = 0;
+	ring->next_to_use = 0;
+
+	ixgbevf_configure_srrctl(adapter, reg_idx);
+
+	/* prevent DMA from exceeding buffer space available */
+	rxdctl &= ~IXGBE_RXDCTL_RLPMLMASK;
+	rxdctl |= ring->rx_buf_len | IXGBE_RXDCTL_RLPML_EN;
+	rxdctl |= IXGBE_RXDCTL_ENABLE | IXGBE_RXDCTL_VME;
+	IXGBE_WRITE_REG(hw, IXGBE_VFRXDCTL(reg_idx), rxdctl);
+
+	ixgbevf_rx_desc_queue_enable(adapter, ring);
+	ixgbevf_alloc_rx_buffers(ring, ixgbevf_desc_unused(ring));
 }
 
 /**
@@ -1198,33 +1341,17 @@ static void ixgbevf_set_rx_buffer_len(struct ixgbevf_adapter *adapter)
  **/
 static void ixgbevf_configure_rx(struct ixgbevf_adapter *adapter)
 {
-	u64 rdba;
-	struct ixgbe_hw *hw = &adapter->hw;
-	int i, j;
-	u32 rdlen;
+	int i;
 
 	ixgbevf_setup_psrtype(adapter);
 
 	/* set_rx_buffer_len must be called before ring initialization */
 	ixgbevf_set_rx_buffer_len(adapter);
 
-	rdlen = adapter->rx_ring[0].count * sizeof(union ixgbe_adv_rx_desc);
 	/* Setup the HW Rx Head and Tail Descriptor Pointers and
 	 * the Base and Length of the Rx Descriptor Ring */
-	for (i = 0; i < adapter->num_rx_queues; i++) {
-		rdba = adapter->rx_ring[i].dma;
-		j = adapter->rx_ring[i].reg_idx;
-		IXGBE_WRITE_REG(hw, IXGBE_VFRDBAL(j),
-				(rdba & DMA_BIT_MASK(32)));
-		IXGBE_WRITE_REG(hw, IXGBE_VFRDBAH(j), (rdba >> 32));
-		IXGBE_WRITE_REG(hw, IXGBE_VFRDLEN(j), rdlen);
-		IXGBE_WRITE_REG(hw, IXGBE_VFRDH(j), 0);
-		IXGBE_WRITE_REG(hw, IXGBE_VFRDT(j), 0);
-		adapter->rx_ring[i].head = IXGBE_VFRDH(j);
-		adapter->rx_ring[i].tail = IXGBE_VFRDT(j);
-
-		ixgbevf_configure_srrctl(adapter, j);
-	}
+	for (i = 0; i < adapter->num_rx_queues; i++)
+		ixgbevf_configure_rx_ring(adapter, adapter->rx_ring[i]);
 }
 
 static int ixgbevf_vlan_rx_add_vid(struct net_device *netdev,
@@ -1366,69 +1493,54 @@ static void ixgbevf_napi_disable_all(struct ixgbevf_adapter *adapter)
 	}
 }
 
-static void ixgbevf_configure(struct ixgbevf_adapter *adapter)
+static int ixgbevf_configure_dcb(struct ixgbevf_adapter *adapter)
 {
-	struct net_device *netdev = adapter->netdev;
-	int i;
+	struct ixgbe_hw *hw = &adapter->hw;
+	unsigned int def_q = 0;
+	unsigned int num_tcs = 0;
+	unsigned int num_rx_queues = 1;
+	int err;
 
-	ixgbevf_set_rx_mode(netdev);
+	spin_lock_bh(&adapter->mbx_lock);
 
-	ixgbevf_restore_vlan(adapter);
+	/* fetch queue configuration from the PF */
+	err = ixgbevf_get_queues(hw, &num_tcs, &def_q);
 
-	ixgbevf_configure_tx(adapter);
-	ixgbevf_configure_rx(adapter);
-	for (i = 0; i < adapter->num_rx_queues; i++) {
-		struct ixgbevf_ring *ring = &adapter->rx_ring[i];
-		ixgbevf_alloc_rx_buffers(adapter, ring,
-					 ixgbevf_desc_unused(ring));
-	}
-}
+	spin_unlock_bh(&adapter->mbx_lock);
 
-#define IXGBEVF_MAX_RX_DESC_POLL 10
-static void ixgbevf_rx_desc_queue_enable(struct ixgbevf_adapter *adapter,
-					 int rxr)
-{
-	struct ixgbe_hw *hw = &adapter->hw;
-	int wait_loop = IXGBEVF_MAX_RX_DESC_POLL;
-	u32 rxdctl;
-	int j = adapter->rx_ring[rxr].reg_idx;
+	if (err)
+		return err;
 
-	do {
-		usleep_range(1000, 2000);
-		rxdctl = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(j));
-	} while (--wait_loop && !(rxdctl & IXGBE_RXDCTL_ENABLE));
+	if (num_tcs > 1) {
+		/* update default Tx ring register index */
+		adapter->tx_ring[0]->reg_idx = def_q;
 
-	if (!wait_loop)
-		hw_dbg(hw, "RXDCTL.ENABLE queue %d not set while polling\n",
-		       rxr);
+		/* we need as many queues as traffic classes */
+		num_rx_queues = num_tcs;
+	}
+
+	/* if we have a bad config abort request queue reset */
+	if (adapter->num_rx_queues != num_rx_queues) {
+		/* force mailbox timeout to prevent further messages */
+		hw->mbx.timeout = 0;
+
+		/* wait for watchdog to come around and bail us out */
+		adapter->flags |= IXGBEVF_FLAG_QUEUE_RESET_REQUESTED;
+	}
 
-	ixgbevf_release_rx_desc(&adapter->hw, &adapter->rx_ring[rxr],
-				(adapter->rx_ring[rxr].count - 1));
+	return 0;
 }
 
-static void ixgbevf_disable_rx_queue(struct ixgbevf_adapter *adapter,
-				     struct ixgbevf_ring *ring)
+static void ixgbevf_configure(struct ixgbevf_adapter *adapter)
 {
-	struct ixgbe_hw *hw = &adapter->hw;
-	int wait_loop = IXGBEVF_MAX_RX_DESC_POLL;
-	u32 rxdctl;
-	u8 reg_idx = ring->reg_idx;
-
-	rxdctl = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(reg_idx));
-	rxdctl &= ~IXGBE_RXDCTL_ENABLE;
+	ixgbevf_configure_dcb(adapter);
 
-	/* write value back with RXDCTL.ENABLE bit cleared */
-	IXGBE_WRITE_REG(hw, IXGBE_VFRXDCTL(reg_idx), rxdctl);
+	ixgbevf_set_rx_mode(adapter->netdev);
 
-	/* the hardware may take up to 100us to really disable the rx queue */
-	do {
-		udelay(10);
-		rxdctl = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(reg_idx));
-	} while (--wait_loop && (rxdctl & IXGBE_RXDCTL_ENABLE));
+	ixgbevf_restore_vlan(adapter);
 
-	if (!wait_loop)
-		hw_dbg(hw, "RXDCTL.ENABLE queue %d not cleared while polling\n",
-		       reg_idx);
+	ixgbevf_configure_tx(adapter);
+	ixgbevf_configure_rx(adapter);
 }
 
 static void ixgbevf_save_reset_stats(struct ixgbevf_adapter *adapter)
@@ -1493,37 +1605,6 @@ static void ixgbevf_up_complete(struct ixgbevf_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
 	struct ixgbe_hw *hw = &adapter->hw;
-	int i, j = 0;
-	int num_rx_rings = adapter->num_rx_queues;
-	u32 txdctl, rxdctl;
-
-	for (i = 0; i < adapter->num_tx_queues; i++) {
-		j = adapter->tx_ring[i].reg_idx;
-		txdctl = IXGBE_READ_REG(hw, IXGBE_VFTXDCTL(j));
-		/* enable WTHRESH=8 descriptors, to encourage burst writeback */
-		txdctl |= (8 << 16);
-		IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(j), txdctl);
-	}
-
-	for (i = 0; i < adapter->num_tx_queues; i++) {
-		j = adapter->tx_ring[i].reg_idx;
-		txdctl = IXGBE_READ_REG(hw, IXGBE_VFTXDCTL(j));
-		txdctl |= IXGBE_TXDCTL_ENABLE;
-		IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(j), txdctl);
-	}
-
-	for (i = 0; i < num_rx_rings; i++) {
-		j = adapter->rx_ring[i].reg_idx;
-		rxdctl = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(j));
-		rxdctl |= IXGBE_RXDCTL_ENABLE | IXGBE_RXDCTL_VME;
-		if (hw->mac.type == ixgbe_mac_X540_vf) {
-			rxdctl &= ~IXGBE_RXDCTL_RLPMLMASK;
-			rxdctl |= ((netdev->mtu + ETH_HLEN + ETH_FCS_LEN) |
-				   IXGBE_RXDCTL_RLPML_EN);
-		}
-		IXGBE_WRITE_REG(hw, IXGBE_VFRXDCTL(j), rxdctl);
-		ixgbevf_rx_desc_queue_enable(adapter, i);
-	}
 
 	ixgbevf_configure_msix(adapter);
 
@@ -1549,85 +1630,10 @@ static void ixgbevf_up_complete(struct ixgbevf_adapter *adapter)
 	mod_timer(&adapter->watchdog_timer, jiffies);
 }
 
-static int ixgbevf_reset_queues(struct ixgbevf_adapter *adapter)
-{
-	struct ixgbe_hw *hw = &adapter->hw;
-	struct ixgbevf_ring *rx_ring;
-	unsigned int def_q = 0;
-	unsigned int num_tcs = 0;
-	unsigned int num_rx_queues = 1;
-	int err, i;
-
-	spin_lock_bh(&adapter->mbx_lock);
-
-	/* fetch queue configuration from the PF */
-	err = ixgbevf_get_queues(hw, &num_tcs, &def_q);
-
-	spin_unlock_bh(&adapter->mbx_lock);
-
-	if (err)
-		return err;
-
-	if (num_tcs > 1) {
-		/* update default Tx ring register index */
-		adapter->tx_ring[0].reg_idx = def_q;
-
-		/* we need as many queues as traffic classes */
-		num_rx_queues = num_tcs;
-	}
-
-	/* nothing to do if we have the correct number of queues */
-	if (adapter->num_rx_queues == num_rx_queues)
-		return 0;
-
-	/* allocate new rings */
-	rx_ring = kcalloc(num_rx_queues,
-			  sizeof(struct ixgbevf_ring), GFP_KERNEL);
-	if (!rx_ring)
-		return -ENOMEM;
-
-	/* setup ring fields */
-	for (i = 0; i < num_rx_queues; i++) {
-		rx_ring[i].count = adapter->rx_ring_count;
-		rx_ring[i].queue_index = i;
-		rx_ring[i].reg_idx = i;
-		rx_ring[i].dev = &adapter->pdev->dev;
-		rx_ring[i].netdev = adapter->netdev;
-
-		/* allocate resources on the ring */
-		err = ixgbevf_setup_rx_resources(adapter, &rx_ring[i]);
-		if (err) {
-			while (i) {
-				i--;
-				ixgbevf_free_rx_resources(adapter, &rx_ring[i]);
-			}
-			kfree(rx_ring);
-			return err;
-		}
-	}
-
-	/* free the existing rings and queues */
-	ixgbevf_free_all_rx_resources(adapter);
-	adapter->num_rx_queues = 0;
-	kfree(adapter->rx_ring);
-
-	/* move new rings into position on the adapter struct */
-	adapter->rx_ring = rx_ring;
-	adapter->num_rx_queues = num_rx_queues;
-
-	/* reset ring to vector mapping */
-	ixgbevf_reset_q_vectors(adapter);
-	ixgbevf_map_rings_to_vectors(adapter);
-
-	return 0;
-}
-
 void ixgbevf_up(struct ixgbevf_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
 
-	ixgbevf_reset_queues(adapter);
-
 	ixgbevf_configure(adapter);
 
 	ixgbevf_up_complete(adapter);
@@ -1640,13 +1646,10 @@ void ixgbevf_up(struct ixgbevf_adapter *adapter)
 
 /**
  * ixgbevf_clean_rx_ring - Free Rx Buffers per Queue
- * @adapter: board private structure
  * @rx_ring: ring to free buffers from
  **/
-static void ixgbevf_clean_rx_ring(struct ixgbevf_adapter *adapter,
-				  struct ixgbevf_ring *rx_ring)
+static void ixgbevf_clean_rx_ring(struct ixgbevf_ring *rx_ring)
 {
-	struct pci_dev *pdev = adapter->pdev;
 	unsigned long size;
 	unsigned int i;
 
@@ -1659,7 +1662,7 @@ static void ixgbevf_clean_rx_ring(struct ixgbevf_adapter *adapter,
 
 		rx_buffer_info = &rx_ring->rx_buffer_info[i];
 		if (rx_buffer_info->dma) {
-			dma_unmap_single(&pdev->dev, rx_buffer_info->dma,
+			dma_unmap_single(rx_ring->dev, rx_buffer_info->dma,
 					 rx_ring->rx_buf_len,
 					 DMA_FROM_DEVICE);
 			rx_buffer_info->dma = 0;
@@ -1680,23 +1683,13 @@ static void ixgbevf_clean_rx_ring(struct ixgbevf_adapter *adapter,
 
 	/* 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;
-
-	if (rx_ring->head)
-		writel(0, adapter->hw.hw_addr + rx_ring->head);
-	if (rx_ring->tail)
-		writel(0, adapter->hw.hw_addr + rx_ring->tail);
 }
 
 /**
  * ixgbevf_clean_tx_ring - Free Tx Buffers
- * @adapter: board private structure
  * @tx_ring: ring to be cleaned
  **/
-static void ixgbevf_clean_tx_ring(struct ixgbevf_adapter *adapter,
-				  struct ixgbevf_ring *tx_ring)
+static void ixgbevf_clean_tx_ring(struct ixgbevf_ring *tx_ring)
 {
 	struct ixgbevf_tx_buffer *tx_buffer_info;
 	unsigned long size;
@@ -1715,14 +1708,6 @@ static void ixgbevf_clean_tx_ring(struct ixgbevf_adapter *adapter,
 	memset(tx_ring->tx_buffer_info, 0, size);
 
 	memset(tx_ring->desc, 0, tx_ring->size);
-
-	tx_ring->next_to_use = 0;
-	tx_ring->next_to_clean = 0;
-
-	if (tx_ring->head)
-		writel(0, adapter->hw.hw_addr + tx_ring->head);
-	if (tx_ring->tail)
-		writel(0, adapter->hw.hw_addr + tx_ring->tail);
 }
 
 /**
@@ -1734,7 +1719,7 @@ static void ixgbevf_clean_all_rx_rings(struct ixgbevf_adapter *adapter)
 	int i;
 
 	for (i = 0; i < adapter->num_rx_queues; i++)
-		ixgbevf_clean_rx_ring(adapter, &adapter->rx_ring[i]);
+		ixgbevf_clean_rx_ring(adapter->rx_ring[i]);
 }
 
 /**
@@ -1746,22 +1731,21 @@ static void ixgbevf_clean_all_tx_rings(struct ixgbevf_adapter *adapter)
 	int i;
 
 	for (i = 0; i < adapter->num_tx_queues; i++)
-		ixgbevf_clean_tx_ring(adapter, &adapter->tx_ring[i]);
+		ixgbevf_clean_tx_ring(adapter->tx_ring[i]);
 }
 
 void ixgbevf_down(struct ixgbevf_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
 	struct ixgbe_hw *hw = &adapter->hw;
-	u32 txdctl;
-	int i, j;
+	int i;
 
 	/* signal that we are down to the interrupt handler */
 	set_bit(__IXGBEVF_DOWN, &adapter->state);
 
 	/* disable all enabled rx queues */
 	for (i = 0; i < adapter->num_rx_queues; i++)
-		ixgbevf_disable_rx_queue(adapter, &adapter->rx_ring[i]);
+		ixgbevf_disable_rx_queue(adapter, adapter->rx_ring[i]);
 
 	netif_tx_disable(netdev);
 
@@ -1782,10 +1766,10 @@ void ixgbevf_down(struct ixgbevf_adapter *adapter)
 
 	/* disable transmits in the hardware now that interrupts are off */
 	for (i = 0; i < adapter->num_tx_queues; i++) {
-		j = adapter->tx_ring[i].reg_idx;
-		txdctl = IXGBE_READ_REG(hw, IXGBE_VFTXDCTL(j));
-		IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(j),
-				(txdctl & ~IXGBE_TXDCTL_ENABLE));
+		u8 reg_idx = adapter->tx_ring[i]->reg_idx;
+
+		IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(reg_idx),
+				IXGBE_TXDCTL_SWFLSH);
 	}
 
 	netif_carrier_off(netdev);
@@ -1889,9 +1873,28 @@ static int ixgbevf_acquire_msix_vectors(struct ixgbevf_adapter *adapter,
  **/
 static void ixgbevf_set_num_queues(struct ixgbevf_adapter *adapter)
 {
+	struct ixgbe_hw *hw = &adapter->hw;
+	unsigned int def_q = 0;
+	unsigned int num_tcs = 0;
+	int err;
+
 	/* Start with base case */
 	adapter->num_rx_queues = 1;
 	adapter->num_tx_queues = 1;
+
+	spin_lock_bh(&adapter->mbx_lock);
+
+	/* fetch queue configuration from the PF */
+	err = ixgbevf_get_queues(hw, &num_tcs, &def_q);
+
+	spin_unlock_bh(&adapter->mbx_lock);
+
+	if (err)
+		return;
+
+	/* we need as many queues as traffic classes */
+	if (num_tcs > 1)
+		adapter->num_rx_queues = num_tcs;
 }
 
 /**
@@ -1904,40 +1907,50 @@ static void ixgbevf_set_num_queues(struct ixgbevf_adapter *adapter)
  **/
 static int ixgbevf_alloc_queues(struct ixgbevf_adapter *adapter)
 {
-	int i;
+	struct ixgbevf_ring *ring;
+	int rx = 0, tx = 0;
 
-	adapter->tx_ring = kcalloc(adapter->num_tx_queues,
-				   sizeof(struct ixgbevf_ring), GFP_KERNEL);
-	if (!adapter->tx_ring)
-		goto err_tx_ring_allocation;
+	for (; tx < adapter->num_tx_queues; tx++) {
+		ring = kzalloc(sizeof(*ring), GFP_KERNEL);
+		if (!ring)
+			goto err_allocation;
 
-	adapter->rx_ring = kcalloc(adapter->num_rx_queues,
-				   sizeof(struct ixgbevf_ring), GFP_KERNEL);
-	if (!adapter->rx_ring)
-		goto err_rx_ring_allocation;
+		ring->dev = &adapter->pdev->dev;
+		ring->netdev = adapter->netdev;
+		ring->count = adapter->tx_ring_count;
+		ring->queue_index = tx;
+		ring->reg_idx = tx;
 
-	for (i = 0; i < adapter->num_tx_queues; i++) {
-		adapter->tx_ring[i].count = adapter->tx_ring_count;
-		adapter->tx_ring[i].queue_index = i;
-		/* reg_idx may be remapped later by DCB config */
-		adapter->tx_ring[i].reg_idx = i;
-		adapter->tx_ring[i].dev = &adapter->pdev->dev;
-		adapter->tx_ring[i].netdev = adapter->netdev;
+		adapter->tx_ring[tx] = ring;
 	}
 
-	for (i = 0; i < adapter->num_rx_queues; i++) {
-		adapter->rx_ring[i].count = adapter->rx_ring_count;
-		adapter->rx_ring[i].queue_index = i;
-		adapter->rx_ring[i].reg_idx = i;
-		adapter->rx_ring[i].dev = &adapter->pdev->dev;
-		adapter->rx_ring[i].netdev = adapter->netdev;
+	for (; rx < adapter->num_rx_queues; rx++) {
+		ring = kzalloc(sizeof(*ring), GFP_KERNEL);
+		if (!ring)
+			goto err_allocation;
+
+		ring->dev = &adapter->pdev->dev;
+		ring->netdev = adapter->netdev;
+
+		ring->count = adapter->rx_ring_count;
+		ring->queue_index = rx;
+		ring->reg_idx = rx;
+
+		adapter->rx_ring[rx] = ring;
 	}
 
 	return 0;
 
-err_rx_ring_allocation:
-	kfree(adapter->tx_ring);
-err_tx_ring_allocation:
+err_allocation:
+	while (tx) {
+		kfree(adapter->tx_ring[--tx]);
+		adapter->tx_ring[tx] = NULL;
+	}
+
+	while (rx) {
+		kfree(adapter->rx_ring[--rx]);
+		adapter->rx_ring[rx] = NULL;
+	}
 	return -ENOMEM;
 }
 
@@ -2128,6 +2141,17 @@ err_set_interrupt:
  **/
 static void ixgbevf_clear_interrupt_scheme(struct ixgbevf_adapter *adapter)
 {
+	int i;
+
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		kfree(adapter->tx_ring[i]);
+		adapter->tx_ring[i] = NULL;
+	}
+	for (i = 0; i < adapter->num_rx_queues; i++) {
+		kfree(adapter->rx_ring[i]);
+		adapter->rx_ring[i] = NULL;
+	}
+
 	adapter->num_tx_queues = 0;
 	adapter->num_rx_queues = 0;
 
@@ -2258,11 +2282,8 @@ void ixgbevf_update_stats(struct ixgbevf_adapter *adapter)
 
 	for (i = 0;  i  < adapter->num_rx_queues;  i++) {
 		adapter->hw_csum_rx_error +=
-			adapter->rx_ring[i].hw_csum_rx_error;
-		adapter->hw_csum_rx_good +=
-			adapter->rx_ring[i].hw_csum_rx_good;
-		adapter->rx_ring[i].hw_csum_rx_error = 0;
-		adapter->rx_ring[i].hw_csum_rx_good = 0;
+			adapter->rx_ring[i]->hw_csum_rx_error;
+		adapter->rx_ring[i]->hw_csum_rx_error = 0;
 	}
 }
 
@@ -2340,6 +2361,8 @@ static void ixgbevf_watchdog_task(struct work_struct *work)
 	bool link_up = adapter->link_up;
 	s32 need_reset;
 
+	ixgbevf_queue_reset_subtask(adapter);
+
 	adapter->flags |= IXGBE_FLAG_IN_WATCHDOG_TASK;
 
 	/*
@@ -2408,22 +2431,22 @@ pf_has_reset:
 
 /**
  * ixgbevf_free_tx_resources - Free Tx Resources per Queue
- * @adapter: board private structure
  * @tx_ring: Tx descriptor ring for a specific queue
  *
  * Free all transmit software resources
  **/
-void ixgbevf_free_tx_resources(struct ixgbevf_adapter *adapter,
-			       struct ixgbevf_ring *tx_ring)
+void ixgbevf_free_tx_resources(struct ixgbevf_ring *tx_ring)
 {
-	struct pci_dev *pdev = adapter->pdev;
-
-	ixgbevf_clean_tx_ring(adapter, tx_ring);
+	ixgbevf_clean_tx_ring(tx_ring);
 
 	vfree(tx_ring->tx_buffer_info);
 	tx_ring->tx_buffer_info = NULL;
 
-	dma_free_coherent(&pdev->dev, tx_ring->size, tx_ring->desc,
+	/* if not set, then don't free */
+	if (!tx_ring->desc)
+		return;
+
+	dma_free_coherent(tx_ring->dev, tx_ring->size, tx_ring->desc,
 			  tx_ring->dma);
 
 	tx_ring->desc = NULL;
@@ -2440,23 +2463,18 @@ static void ixgbevf_free_all_tx_resources(struct ixgbevf_adapter *adapter)
 	int i;
 
 	for (i = 0; i < adapter->num_tx_queues; i++)
-		if (adapter->tx_ring[i].desc)
-			ixgbevf_free_tx_resources(adapter,
-						  &adapter->tx_ring[i]);
-
+		if (adapter->tx_ring[i]->desc)
+			ixgbevf_free_tx_resources(adapter->tx_ring[i]);
 }
 
 /**
  * ixgbevf_setup_tx_resources - allocate Tx resources (Descriptors)
- * @adapter: board private structure
  * @tx_ring:    tx descriptor ring (for a specific queue) to setup
  *
  * Return 0 on success, negative on failure
  **/
-int ixgbevf_setup_tx_resources(struct ixgbevf_adapter *adapter,
-			       struct ixgbevf_ring *tx_ring)
+int ixgbevf_setup_tx_resources(struct ixgbevf_ring *tx_ring)
 {
-	struct pci_dev *pdev = adapter->pdev;
 	int size;
 
 	size = sizeof(struct ixgbevf_tx_buffer) * tx_ring->count;
@@ -2468,13 +2486,11 @@ int ixgbevf_setup_tx_resources(struct ixgbevf_adapter *adapter,
 	tx_ring->size = tx_ring->count * sizeof(union ixgbe_adv_tx_desc);
 	tx_ring->size = ALIGN(tx_ring->size, 4096);
 
-	tx_ring->desc = dma_alloc_coherent(&pdev->dev, tx_ring->size,
+	tx_ring->desc = dma_alloc_coherent(tx_ring->dev, tx_ring->size,
 					   &tx_ring->dma, GFP_KERNEL);
 	if (!tx_ring->desc)
 		goto err;
 
-	tx_ring->next_to_use = 0;
-	tx_ring->next_to_clean = 0;
 	return 0;
 
 err:
@@ -2500,7 +2516,7 @@ static int ixgbevf_setup_all_tx_resources(struct ixgbevf_adapter *adapter)
 	int i, err = 0;
 
 	for (i = 0; i < adapter->num_tx_queues; i++) {
-		err = ixgbevf_setup_tx_resources(adapter, &adapter->tx_ring[i]);
+		err = ixgbevf_setup_tx_resources(adapter->tx_ring[i]);
 		if (!err)
 			continue;
 		hw_dbg(&adapter->hw,
@@ -2513,40 +2529,34 @@ static int ixgbevf_setup_all_tx_resources(struct ixgbevf_adapter *adapter)
 
 /**
  * ixgbevf_setup_rx_resources - allocate Rx resources (Descriptors)
- * @adapter: board private structure
  * @rx_ring:    rx descriptor ring (for a specific queue) to setup
  *
  * Returns 0 on success, negative on failure
  **/
-int ixgbevf_setup_rx_resources(struct ixgbevf_adapter *adapter,
-			       struct ixgbevf_ring *rx_ring)
+int ixgbevf_setup_rx_resources(struct ixgbevf_ring *rx_ring)
 {
-	struct pci_dev *pdev = adapter->pdev;
 	int size;
 
 	size = sizeof(struct ixgbevf_rx_buffer) * rx_ring->count;
 	rx_ring->rx_buffer_info = vzalloc(size);
 	if (!rx_ring->rx_buffer_info)
-		goto alloc_failed;
+		goto err;
 
 	/* Round up to nearest 4K */
 	rx_ring->size = rx_ring->count * sizeof(union ixgbe_adv_rx_desc);
 	rx_ring->size = ALIGN(rx_ring->size, 4096);
 
-	rx_ring->desc = dma_alloc_coherent(&pdev->dev, rx_ring->size,
+	rx_ring->desc = dma_alloc_coherent(rx_ring->dev, rx_ring->size,
 					   &rx_ring->dma, GFP_KERNEL);
 
-	if (!rx_ring->desc) {
-		vfree(rx_ring->rx_buffer_info);
-		rx_ring->rx_buffer_info = NULL;
-		goto alloc_failed;
-	}
-
-	rx_ring->next_to_clean = 0;
-	rx_ring->next_to_use = 0;
+	if (!rx_ring->desc)
+		goto err;
 
 	return 0;
-alloc_failed:
+err:
+	vfree(rx_ring->rx_buffer_info);
+	rx_ring->rx_buffer_info = NULL;
+	dev_err(rx_ring->dev, "Unable to allocate memory for the Rx descriptor ring\n");
 	return -ENOMEM;
 }
 
@@ -2565,7 +2575,7 @@ static int ixgbevf_setup_all_rx_resources(struct ixgbevf_adapter *adapter)
 	int i, err = 0;
 
 	for (i = 0; i < adapter->num_rx_queues; i++) {
-		err = ixgbevf_setup_rx_resources(adapter, &adapter->rx_ring[i]);
+		err = ixgbevf_setup_rx_resources(adapter->rx_ring[i]);
 		if (!err)
 			continue;
 		hw_dbg(&adapter->hw,
@@ -2577,22 +2587,18 @@ static int ixgbevf_setup_all_rx_resources(struct ixgbevf_adapter *adapter)
 
 /**
  * ixgbevf_free_rx_resources - Free Rx Resources
- * @adapter: board private structure
  * @rx_ring: ring to clean the resources from
  *
  * Free all receive software resources
  **/
-void ixgbevf_free_rx_resources(struct ixgbevf_adapter *adapter,
-			       struct ixgbevf_ring *rx_ring)
+void ixgbevf_free_rx_resources(struct ixgbevf_ring *rx_ring)
 {
-	struct pci_dev *pdev = adapter->pdev;
-
-	ixgbevf_clean_rx_ring(adapter, rx_ring);
+	ixgbevf_clean_rx_ring(rx_ring);
 
 	vfree(rx_ring->rx_buffer_info);
 	rx_ring->rx_buffer_info = NULL;
 
-	dma_free_coherent(&pdev->dev, rx_ring->size, rx_ring->desc,
+	dma_free_coherent(rx_ring->dev, rx_ring->size, rx_ring->desc,
 			  rx_ring->dma);
 
 	rx_ring->desc = NULL;
@@ -2609,66 +2615,8 @@ static void ixgbevf_free_all_rx_resources(struct ixgbevf_adapter *adapter)
 	int i;
 
 	for (i = 0; i < adapter->num_rx_queues; i++)
-		if (adapter->rx_ring[i].desc)
-			ixgbevf_free_rx_resources(adapter,
-						  &adapter->rx_ring[i]);
-}
-
-static int ixgbevf_setup_queues(struct ixgbevf_adapter *adapter)
-{
-	struct ixgbe_hw *hw = &adapter->hw;
-	struct ixgbevf_ring *rx_ring;
-	unsigned int def_q = 0;
-	unsigned int num_tcs = 0;
-	unsigned int num_rx_queues = 1;
-	int err, i;
-
-	spin_lock_bh(&adapter->mbx_lock);
-
-	/* fetch queue configuration from the PF */
-	err = ixgbevf_get_queues(hw, &num_tcs, &def_q);
-
-	spin_unlock_bh(&adapter->mbx_lock);
-
-	if (err)
-		return err;
-
-	if (num_tcs > 1) {
-		/* update default Tx ring register index */
-		adapter->tx_ring[0].reg_idx = def_q;
-
-		/* we need as many queues as traffic classes */
-		num_rx_queues = num_tcs;
-	}
-
-	/* nothing to do if we have the correct number of queues */
-	if (adapter->num_rx_queues == num_rx_queues)
-		return 0;
-
-	/* allocate new rings */
-	rx_ring = kcalloc(num_rx_queues,
-			  sizeof(struct ixgbevf_ring), GFP_KERNEL);
-	if (!rx_ring)
-		return -ENOMEM;
-
-	/* setup ring fields */
-	for (i = 0; i < num_rx_queues; i++) {
-		rx_ring[i].count = adapter->rx_ring_count;
-		rx_ring[i].queue_index = i;
-		rx_ring[i].reg_idx = i;
-		rx_ring[i].dev = &adapter->pdev->dev;
-		rx_ring[i].netdev = adapter->netdev;
-	}
-
-	/* free the existing ring and queues */
-	adapter->num_rx_queues = 0;
-	kfree(adapter->rx_ring);
-
-	/* move new rings into position on the adapter struct */
-	adapter->rx_ring = rx_ring;
-	adapter->num_rx_queues = num_rx_queues;
-
-	return 0;
+		if (adapter->rx_ring[i]->desc)
+			ixgbevf_free_rx_resources(adapter->rx_ring[i]);
 }
 
 /**
@@ -2714,11 +2662,6 @@ static int ixgbevf_open(struct net_device *netdev)
 		}
 	}
 
-	/* setup queue reg_idx and Rx queue count */
-	err = ixgbevf_setup_queues(adapter);
-	if (err)
-		goto err_setup_queues;
-
 	/* allocate transmit descriptors */
 	err = ixgbevf_setup_all_tx_resources(adapter);
 	if (err)
@@ -2756,7 +2699,6 @@ err_setup_rx:
 	ixgbevf_free_all_rx_resources(adapter);
 err_setup_tx:
 	ixgbevf_free_all_tx_resources(adapter);
-err_setup_queues:
 	ixgbevf_reset(adapter);
 
 err_setup_reset:
@@ -2788,6 +2730,34 @@ static int ixgbevf_close(struct net_device *netdev)
 	return 0;
 }
 
+static void ixgbevf_queue_reset_subtask(struct ixgbevf_adapter *adapter)
+{
+	struct net_device *dev = adapter->netdev;
+
+	if (!(adapter->flags & IXGBEVF_FLAG_QUEUE_RESET_REQUESTED))
+		return;
+
+	adapter->flags &= ~IXGBEVF_FLAG_QUEUE_RESET_REQUESTED;
+
+	/* if interface is down do nothing */
+	if (test_bit(__IXGBEVF_DOWN, &adapter->state) ||
+	    test_bit(__IXGBEVF_RESETTING, &adapter->state))
+		return;
+
+	/* Hardware has to reinitialize queues and interrupts to
+	 * match packet buffer alignment. Unfortunately, the
+	 * hardware is not flexible enough to do this dynamically.
+	 */
+	if (netif_running(dev))
+		ixgbevf_close(dev);
+
+	ixgbevf_clear_interrupt_scheme(adapter);
+	ixgbevf_init_interrupt_scheme(adapter);
+
+	if (netif_running(dev))
+		ixgbevf_open(dev);
+}
+
 static void ixgbevf_tx_ctxtdesc(struct ixgbevf_ring *tx_ring,
 				u32 vlan_macip_lens, u32 type_tucmd,
 				u32 mss_l4len_idx)
@@ -2810,8 +2780,10 @@ static void ixgbevf_tx_ctxtdesc(struct ixgbevf_ring *tx_ring,
 }
 
 static int ixgbevf_tso(struct ixgbevf_ring *tx_ring,
-		       struct sk_buff *skb, u32 tx_flags, u8 *hdr_len)
+		       struct ixgbevf_tx_buffer *first,
+		       u8 *hdr_len)
 {
+	struct sk_buff *skb = first->skb;
 	u32 vlan_macip_lens, type_tucmd;
 	u32 mss_l4len_idx, l4len;
 
@@ -2836,12 +2808,17 @@ static int ixgbevf_tso(struct ixgbevf_ring *tx_ring,
 							 IPPROTO_TCP,
 							 0);
 		type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4;
+		first->tx_flags |= IXGBE_TX_FLAGS_TSO |
+				   IXGBE_TX_FLAGS_CSUM |
+				   IXGBE_TX_FLAGS_IPV4;
 	} else if (skb_is_gso_v6(skb)) {
 		ipv6_hdr(skb)->payload_len = 0;
 		tcp_hdr(skb)->check =
 		    ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
 				     &ipv6_hdr(skb)->daddr,
 				     0, IPPROTO_TCP, 0);
+		first->tx_flags |= IXGBE_TX_FLAGS_TSO |
+				   IXGBE_TX_FLAGS_CSUM;
 	}
 
 	/* compute header lengths */
@@ -2849,6 +2826,10 @@ static int ixgbevf_tso(struct ixgbevf_ring *tx_ring,
 	*hdr_len += l4len;
 	*hdr_len = skb_transport_offset(skb) + l4len;
 
+	/* update gso size and bytecount with header size */
+	first->gso_segs = skb_shinfo(skb)->gso_segs;
+	first->bytecount += (first->gso_segs - 1) * *hdr_len;
+
 	/* mss_l4len_id: use 1 as index for TSO */
 	mss_l4len_idx = l4len << IXGBE_ADVTXD_L4LEN_SHIFT;
 	mss_l4len_idx |= skb_shinfo(skb)->gso_size << IXGBE_ADVTXD_MSS_SHIFT;
@@ -2857,7 +2838,7 @@ static int ixgbevf_tso(struct ixgbevf_ring *tx_ring,
 	/* vlan_macip_lens: HEADLEN, MACLEN, VLAN tag */
 	vlan_macip_lens = skb_network_header_len(skb);
 	vlan_macip_lens |= skb_network_offset(skb) << IXGBE_ADVTXD_MACLEN_SHIFT;
-	vlan_macip_lens |= tx_flags & IXGBE_TX_FLAGS_VLAN_MASK;
+	vlan_macip_lens |= first->tx_flags & IXGBE_TX_FLAGS_VLAN_MASK;
 
 	ixgbevf_tx_ctxtdesc(tx_ring, vlan_macip_lens,
 			    type_tucmd, mss_l4len_idx);
@@ -2865,9 +2846,10 @@ static int ixgbevf_tso(struct ixgbevf_ring *tx_ring,
 	return 1;
 }
 
-static bool ixgbevf_tx_csum(struct ixgbevf_ring *tx_ring,
-			    struct sk_buff *skb, u32 tx_flags)
+static void ixgbevf_tx_csum(struct ixgbevf_ring *tx_ring,
+			    struct ixgbevf_tx_buffer *first)
 {
+	struct sk_buff *skb = first->skb;
 	u32 vlan_macip_lens = 0;
 	u32 mss_l4len_idx = 0;
 	u32 type_tucmd = 0;
@@ -2888,7 +2870,7 @@ static bool ixgbevf_tx_csum(struct ixgbevf_ring *tx_ring,
 			if (unlikely(net_ratelimit())) {
 				dev_warn(tx_ring->dev,
 				 "partial checksum but proto=%x!\n",
-				 skb->protocol);
+				 first->protocol);
 			}
 			break;
 		}
@@ -2916,184 +2898,190 @@ static bool ixgbevf_tx_csum(struct ixgbevf_ring *tx_ring,
 			}
 			break;
 		}
+
+		/* update TX checksum flag */
+		first->tx_flags |= IXGBE_TX_FLAGS_CSUM;
 	}
 
 	/* vlan_macip_lens: MACLEN, VLAN tag */
 	vlan_macip_lens |= skb_network_offset(skb) << IXGBE_ADVTXD_MACLEN_SHIFT;
-	vlan_macip_lens |= tx_flags & IXGBE_TX_FLAGS_VLAN_MASK;
+	vlan_macip_lens |= first->tx_flags & IXGBE_TX_FLAGS_VLAN_MASK;
 
 	ixgbevf_tx_ctxtdesc(tx_ring, vlan_macip_lens,
 			    type_tucmd, mss_l4len_idx);
-
-	return (skb->ip_summed == CHECKSUM_PARTIAL);
 }
 
-static int ixgbevf_tx_map(struct ixgbevf_ring *tx_ring,
-			  struct sk_buff *skb, u32 tx_flags)
+static __le32 ixgbevf_tx_cmd_type(u32 tx_flags)
 {
-	struct ixgbevf_tx_buffer *tx_buffer_info;
-	unsigned int len;
-	unsigned int total = skb->len;
-	unsigned int offset = 0, size;
-	int count = 0;
-	unsigned int nr_frags = skb_shinfo(skb)->nr_frags;
-	unsigned int f;
-	int i;
+	/* set type for advanced descriptor with frame checksum insertion */
+	__le32 cmd_type = cpu_to_le32(IXGBE_ADVTXD_DTYP_DATA |
+				      IXGBE_ADVTXD_DCMD_IFCS |
+				      IXGBE_ADVTXD_DCMD_DEXT);
 
-	i = tx_ring->next_to_use;
+	/* set HW vlan bit if vlan is present */
+	if (tx_flags & IXGBE_TX_FLAGS_VLAN)
+		cmd_type |= cpu_to_le32(IXGBE_ADVTXD_DCMD_VLE);
 
-	len = min(skb_headlen(skb), total);
-	while (len) {
-		tx_buffer_info = &tx_ring->tx_buffer_info[i];
-		size = min(len, (unsigned int)IXGBE_MAX_DATA_PER_TXD);
-
-		tx_buffer_info->length = size;
-		tx_buffer_info->mapped_as_page = false;
-		tx_buffer_info->dma = dma_map_single(tx_ring->dev,
-						     skb->data + offset,
-						     size, DMA_TO_DEVICE);
-		if (dma_mapping_error(tx_ring->dev, tx_buffer_info->dma))
-			goto dma_error;
+	/* set segmentation enable bits for TSO/FSO */
+	if (tx_flags & IXGBE_TX_FLAGS_TSO)
+		cmd_type |= cpu_to_le32(IXGBE_ADVTXD_DCMD_TSE);
 
-		len -= size;
-		total -= size;
-		offset += size;
-		count++;
-		i++;
-		if (i == tx_ring->count)
-			i = 0;
-	}
+	return cmd_type;
+}
 
-	for (f = 0; f < nr_frags; f++) {
-		const struct skb_frag_struct *frag;
+static void ixgbevf_tx_olinfo_status(union ixgbe_adv_tx_desc *tx_desc,
+				     u32 tx_flags, unsigned int paylen)
+{
+	__le32 olinfo_status = cpu_to_le32(paylen << IXGBE_ADVTXD_PAYLEN_SHIFT);
 
-		frag = &skb_shinfo(skb)->frags[f];
-		len = min((unsigned int)skb_frag_size(frag), total);
-		offset = 0;
+	/* enable L4 checksum for TSO and TX checksum offload */
+	if (tx_flags & IXGBE_TX_FLAGS_CSUM)
+		olinfo_status |= cpu_to_le32(IXGBE_ADVTXD_POPTS_TXSM);
 
-		while (len) {
-			tx_buffer_info = &tx_ring->tx_buffer_info[i];
-			size = min(len, (unsigned int)IXGBE_MAX_DATA_PER_TXD);
+	/* enble IPv4 checksum for TSO */
+	if (tx_flags & IXGBE_TX_FLAGS_IPV4)
+		olinfo_status |= cpu_to_le32(IXGBE_ADVTXD_POPTS_IXSM);
 
-			tx_buffer_info->length = size;
-			tx_buffer_info->dma =
-				skb_frag_dma_map(tx_ring->dev, frag,
-						 offset, size, DMA_TO_DEVICE);
-			if (dma_mapping_error(tx_ring->dev,
-					      tx_buffer_info->dma))
-				goto dma_error;
-			tx_buffer_info->mapped_as_page = true;
+	/* use index 1 context for TSO/FSO/FCOE */
+	if (tx_flags & IXGBE_TX_FLAGS_TSO)
+		olinfo_status |= cpu_to_le32(1 << IXGBE_ADVTXD_IDX_SHIFT);
 
-			len -= size;
-			total -= size;
-			offset += size;
-			count++;
-			i++;
-			if (i == tx_ring->count)
-				i = 0;
-		}
-		if (total == 0)
-			break;
-	}
+	/* Check Context must be set if Tx switch is enabled, which it
+	 * always is for case where virtual functions are running
+	 */
+	olinfo_status |= cpu_to_le32(IXGBE_ADVTXD_CC);
 
-	if (i == 0)
-		i = tx_ring->count - 1;
-	else
-		i = i - 1;
-	tx_ring->tx_buffer_info[i].skb = skb;
+	tx_desc->read.olinfo_status = olinfo_status;
+}
 
-	return count;
+static void ixgbevf_tx_map(struct ixgbevf_ring *tx_ring,
+			   struct ixgbevf_tx_buffer *first,
+			   const u8 hdr_len)
+{
+	dma_addr_t dma;
+	struct sk_buff *skb = first->skb;
+	struct ixgbevf_tx_buffer *tx_buffer;
+	union ixgbe_adv_tx_desc *tx_desc;
+	struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
+	unsigned int data_len = skb->data_len;
+	unsigned int size = skb_headlen(skb);
+	unsigned int paylen = skb->len - hdr_len;
+	u32 tx_flags = first->tx_flags;
+	__le32 cmd_type;
+	u16 i = tx_ring->next_to_use;
 
-dma_error:
-	dev_err(tx_ring->dev, "TX DMA map failed\n");
+	tx_desc = IXGBEVF_TX_DESC(tx_ring, i);
 
-	/* clear timestamp and dma mappings for failed tx_buffer_info map */
-	tx_buffer_info->dma = 0;
-	count--;
+	ixgbevf_tx_olinfo_status(tx_desc, tx_flags, paylen);
+	cmd_type = ixgbevf_tx_cmd_type(tx_flags);
 
-	/* clear timestamp and dma mappings for remaining portion of packet */
-	while (count >= 0) {
-		count--;
-		i--;
-		if (i < 0)
-			i += tx_ring->count;
-		tx_buffer_info = &tx_ring->tx_buffer_info[i];
-		ixgbevf_unmap_and_free_tx_resource(tx_ring, tx_buffer_info);
-	}
+	dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE);
+	if (dma_mapping_error(tx_ring->dev, dma))
+		goto dma_error;
 
-	return count;
-}
+	/* record length, and DMA address */
+	dma_unmap_len_set(first, len, size);
+	dma_unmap_addr_set(first, dma, dma);
 
-static void ixgbevf_tx_queue(struct ixgbevf_ring *tx_ring, int tx_flags,
-			     int count, unsigned int first, u32 paylen,
-			     u8 hdr_len)
-{
-	union ixgbe_adv_tx_desc *tx_desc = NULL;
-	struct ixgbevf_tx_buffer *tx_buffer_info;
-	u32 olinfo_status = 0, cmd_type_len = 0;
-	unsigned int i;
+	tx_desc->read.buffer_addr = cpu_to_le64(dma);
 
-	u32 txd_cmd = IXGBE_TXD_CMD_EOP | IXGBE_TXD_CMD_RS | IXGBE_TXD_CMD_IFCS;
+	for (;;) {
+		while (unlikely(size > IXGBE_MAX_DATA_PER_TXD)) {
+			tx_desc->read.cmd_type_len =
+				cmd_type | cpu_to_le32(IXGBE_MAX_DATA_PER_TXD);
 
-	cmd_type_len |= IXGBE_ADVTXD_DTYP_DATA;
+			i++;
+			tx_desc++;
+			if (i == tx_ring->count) {
+				tx_desc = IXGBEVF_TX_DESC(tx_ring, 0);
+				i = 0;
+			}
 
-	cmd_type_len |= IXGBE_ADVTXD_DCMD_IFCS | IXGBE_ADVTXD_DCMD_DEXT;
+			dma += IXGBE_MAX_DATA_PER_TXD;
+			size -= IXGBE_MAX_DATA_PER_TXD;
 
-	if (tx_flags & IXGBE_TX_FLAGS_VLAN)
-		cmd_type_len |= IXGBE_ADVTXD_DCMD_VLE;
+			tx_desc->read.buffer_addr = cpu_to_le64(dma);
+			tx_desc->read.olinfo_status = 0;
+		}
 
-	if (tx_flags & IXGBE_TX_FLAGS_CSUM)
-		olinfo_status |= IXGBE_ADVTXD_POPTS_TXSM;
+		if (likely(!data_len))
+			break;
 
-	if (tx_flags & IXGBE_TX_FLAGS_TSO) {
-		cmd_type_len |= IXGBE_ADVTXD_DCMD_TSE;
+		tx_desc->read.cmd_type_len = cmd_type | cpu_to_le32(size);
 
-		/* use index 1 context for tso */
-		olinfo_status |= (1 << IXGBE_ADVTXD_IDX_SHIFT);
-		if (tx_flags & IXGBE_TX_FLAGS_IPV4)
-			olinfo_status |= IXGBE_ADVTXD_POPTS_IXSM;
-	}
+		i++;
+		tx_desc++;
+		if (i == tx_ring->count) {
+			tx_desc = IXGBEVF_TX_DESC(tx_ring, 0);
+			i = 0;
+		}
 
-	/*
-	 * Check Context must be set if Tx switch is enabled, which it
-	 * always is for case where virtual functions are running
-	 */
-	olinfo_status |= IXGBE_ADVTXD_CC;
+		size = skb_frag_size(frag);
+		data_len -= size;
 
-	olinfo_status |= ((paylen - hdr_len) << IXGBE_ADVTXD_PAYLEN_SHIFT);
+		dma = skb_frag_dma_map(tx_ring->dev, frag, 0, size,
+				       DMA_TO_DEVICE);
+		if (dma_mapping_error(tx_ring->dev, dma))
+			goto dma_error;
 
-	i = tx_ring->next_to_use;
-	while (count--) {
-		tx_buffer_info = &tx_ring->tx_buffer_info[i];
-		tx_desc = IXGBEVF_TX_DESC(tx_ring, i);
-		tx_desc->read.buffer_addr = cpu_to_le64(tx_buffer_info->dma);
-		tx_desc->read.cmd_type_len =
-			cpu_to_le32(cmd_type_len | tx_buffer_info->length);
-		tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status);
-		i++;
-		if (i == tx_ring->count)
-			i = 0;
+		tx_buffer = &tx_ring->tx_buffer_info[i];
+		dma_unmap_len_set(tx_buffer, len, size);
+		dma_unmap_addr_set(tx_buffer, dma, dma);
+
+		tx_desc->read.buffer_addr = cpu_to_le64(dma);
+		tx_desc->read.olinfo_status = 0;
+
+		frag++;
 	}
 
-	tx_desc->read.cmd_type_len |= cpu_to_le32(txd_cmd);
+	/* write last descriptor with RS and EOP bits */
+	cmd_type |= cpu_to_le32(size) | cpu_to_le32(IXGBE_TXD_CMD);
+	tx_desc->read.cmd_type_len = cmd_type;
 
-	tx_ring->tx_buffer_info[first].time_stamp = jiffies;
+	/* set the timestamp */
+	first->time_stamp = jiffies;
 
-	/* 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).
+	/* 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).
+	 *
+	 * We also need this memory barrier (wmb) to make certain all of the
+	 * status bits have been updated before next_to_watch is written.
 	 */
 	wmb();
 
-	tx_ring->tx_buffer_info[first].next_to_watch = tx_desc;
+	/* set next_to_watch value indicating a packet is present */
+	first->next_to_watch = tx_desc;
+
+	i++;
+	if (i == tx_ring->count)
+		i = 0;
+
+	tx_ring->next_to_use = i;
+
+	/* notify HW of packet */
+	writel(i, tx_ring->tail);
+
+	return;
+dma_error:
+	dev_err(tx_ring->dev, "TX DMA map failed\n");
+
+	/* clear dma mappings for failed tx_buffer_info map */
+	for (;;) {
+		tx_buffer = &tx_ring->tx_buffer_info[i];
+		ixgbevf_unmap_and_free_tx_resource(tx_ring, tx_buffer);
+		if (tx_buffer == first)
+			break;
+		if (i == 0)
+			i = tx_ring->count;
+		i--;
+	}
+
 	tx_ring->next_to_use = i;
 }
 
 static int __ixgbevf_maybe_stop_tx(struct ixgbevf_ring *tx_ring, int size)
 {
-	struct ixgbevf_adapter *adapter = netdev_priv(tx_ring->netdev);
-
 	netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
 	/* Herbert's original patch had:
 	 *  smp_mb__after_netif_stop_queue();
@@ -3107,7 +3095,8 @@ static int __ixgbevf_maybe_stop_tx(struct ixgbevf_ring *tx_ring, int size)
 
 	/* A reprieve! - use start_queue because it doesn't call schedule */
 	netif_start_subqueue(tx_ring->netdev, tx_ring->queue_index);
-	++adapter->restart_queue;
+	++tx_ring->tx_stats.restart_queue;
+
 	return 0;
 }
 
@@ -3121,22 +3110,23 @@ static int ixgbevf_maybe_stop_tx(struct ixgbevf_ring *tx_ring, int size)
 static int ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 {
 	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+	struct ixgbevf_tx_buffer *first;
 	struct ixgbevf_ring *tx_ring;
-	unsigned int first;
-	unsigned int tx_flags = 0;
-	u8 hdr_len = 0;
-	int r_idx = 0, tso;
+	int tso;
+	u32 tx_flags = 0;
 	u16 count = TXD_USE_COUNT(skb_headlen(skb));
 #if PAGE_SIZE > IXGBE_MAX_DATA_PER_TXD
 	unsigned short f;
 #endif
+	u8 hdr_len = 0;
 	u8 *dst_mac = skb_header_pointer(skb, 0, 0, NULL);
+
 	if (!dst_mac || is_link_local_ether_addr(dst_mac)) {
 		dev_kfree_skb(skb);
 		return NETDEV_TX_OK;
 	}
 
-	tx_ring = &adapter->tx_ring[r_idx];
+	tx_ring = adapter->tx_ring[skb->queue_mapping];
 
 	/*
 	 * need: 1 descriptor per page * PAGE_SIZE/IXGBE_MAX_DATA_PER_TXD,
@@ -3152,38 +3142,41 @@ static int ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 	count += skb_shinfo(skb)->nr_frags;
 #endif
 	if (ixgbevf_maybe_stop_tx(tx_ring, count + 3)) {
-		adapter->tx_busy++;
+		tx_ring->tx_stats.tx_busy++;
 		return NETDEV_TX_BUSY;
 	}
 
+	/* record the location of the first descriptor for this packet */
+	first = &tx_ring->tx_buffer_info[tx_ring->next_to_use];
+	first->skb = skb;
+	first->bytecount = skb->len;
+	first->gso_segs = 1;
+
 	if (vlan_tx_tag_present(skb)) {
 		tx_flags |= vlan_tx_tag_get(skb);
 		tx_flags <<= IXGBE_TX_FLAGS_VLAN_SHIFT;
 		tx_flags |= IXGBE_TX_FLAGS_VLAN;
 	}
 
-	first = tx_ring->next_to_use;
+	/* record initial flags and protocol */
+	first->tx_flags = tx_flags;
+	first->protocol = vlan_get_protocol(skb);
 
-	if (skb->protocol == htons(ETH_P_IP))
-		tx_flags |= IXGBE_TX_FLAGS_IPV4;
-	tso = ixgbevf_tso(tx_ring, skb, tx_flags, &hdr_len);
-	if (tso < 0) {
-		dev_kfree_skb_any(skb);
-		return NETDEV_TX_OK;
-	}
+	tso = ixgbevf_tso(tx_ring, first, &hdr_len);
+	if (tso < 0)
+		goto out_drop;
+	else
+		ixgbevf_tx_csum(tx_ring, first);
 
-	if (tso)
-		tx_flags |= IXGBE_TX_FLAGS_TSO | IXGBE_TX_FLAGS_CSUM;
-	else if (ixgbevf_tx_csum(tx_ring, skb, tx_flags))
-		tx_flags |= IXGBE_TX_FLAGS_CSUM;
+	ixgbevf_tx_map(tx_ring, first, hdr_len);
 
-	ixgbevf_tx_queue(tx_ring, tx_flags,
-			 ixgbevf_tx_map(tx_ring, skb, tx_flags),
-			 first, skb->len, hdr_len);
+	ixgbevf_maybe_stop_tx(tx_ring, DESC_NEEDED);
 
-	writel(tx_ring->next_to_use, adapter->hw.hw_addr + tx_ring->tail);
+	return NETDEV_TX_OK;
 
-	ixgbevf_maybe_stop_tx(tx_ring, DESC_NEEDED);
+out_drop:
+	dev_kfree_skb_any(first->skb);
+	first->skb = NULL;
 
 	return NETDEV_TX_OK;
 }
@@ -3289,8 +3282,8 @@ static int ixgbevf_suspend(struct pci_dev *pdev, pm_message_t state)
 #ifdef CONFIG_PM
 static int ixgbevf_resume(struct pci_dev *pdev)
 {
-	struct ixgbevf_adapter *adapter = pci_get_drvdata(pdev);
-	struct net_device *netdev = adapter->netdev;
+	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
 	u32 err;
 
 	pci_set_power_state(pdev, PCI_D0);
@@ -3349,22 +3342,22 @@ static struct rtnl_link_stats64 *ixgbevf_get_stats(struct net_device *netdev,
 	stats->multicast = adapter->stats.vfmprc - adapter->stats.base_vfmprc;
 
 	for (i = 0; i < adapter->num_rx_queues; i++) {
-		ring = &adapter->rx_ring[i];
+		ring = adapter->rx_ring[i];
 		do {
 			start = u64_stats_fetch_begin_bh(&ring->syncp);
-			bytes = ring->total_bytes;
-			packets = ring->total_packets;
+			bytes = ring->stats.bytes;
+			packets = ring->stats.packets;
 		} while (u64_stats_fetch_retry_bh(&ring->syncp, start));
 		stats->rx_bytes += bytes;
 		stats->rx_packets += packets;
 	}
 
 	for (i = 0; i < adapter->num_tx_queues; i++) {
-		ring = &adapter->tx_ring[i];
+		ring = adapter->tx_ring[i];
 		do {
 			start = u64_stats_fetch_begin_bh(&ring->syncp);
-			bytes = ring->total_bytes;
-			packets = ring->total_packets;
+			bytes = ring->stats.bytes;
+			packets = ring->stats.packets;
 		} while (u64_stats_fetch_retry_bh(&ring->syncp, start));
 		stats->tx_bytes += bytes;
 		stats->tx_packets += packets;
@@ -3595,9 +3588,6 @@ static void ixgbevf_remove(struct pci_dev *pdev)
 
 	hw_dbg(&adapter->hw, "Remove complete\n");
 
-	kfree(adapter->tx_ring);
-	kfree(adapter->rx_ring);
-
 	free_netdev(netdev);
 
 	pci_disable_device(pdev);