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

Pull networking updates from David Miller:
 "Most notable changes in here:

   1) By far the biggest accomplishment, thanks to a large range of
      contributors, is the addition of multi-send for transmit.  This is
      the result of discussions back in Chicago, and the hard work of
      several individuals.

      Now, when the ->ndo_start_xmit() method of a driver sees
      skb->xmit_more as true, it can choose to defer the doorbell
      telling the driver to start processing the new TX queue entires.

      skb->xmit_more means that the generic networking is guaranteed to
      call the driver immediately with another SKB to send.

      There is logic added to the qdisc layer to dequeue multiple
      packets at a time, and the handling mis-predicted offloads in
      software is now done with no locks held.

      Finally, pktgen is extended to have a "burst" parameter that can
      be used to test a multi-send implementation.

      Several drivers have xmit_more support: i40e, igb, ixgbe, mlx4,
      virtio_net

      Adding support is almost trivial, so export more drivers to
      support this optimization soon.

      I want to thank, in no particular or implied order, Jesper
      Dangaard Brouer, Eric Dumazet, Alexander Duyck, Tom Herbert, Jamal
      Hadi Salim, John Fastabend, Florian Westphal, Daniel Borkmann,
      David Tat, Hannes Frederic Sowa, and Rusty Russell.

   2) PTP and timestamping support in bnx2x, from Michal Kalderon.

   3) Allow adjusting the rx_copybreak threshold for a driver via
      ethtool, and add rx_copybreak support to enic driver.  From
      Govindarajulu Varadarajan.

   4) Significant enhancements to the generic PHY layer and the bcm7xxx
      driver in particular (EEE support, auto power down, etc.) from
      Florian Fainelli.

   5) Allow raw buffers to be used for flow dissection, allowing drivers
      to determine the optimal "linear pull" size for devices that DMA
      into pools of pages.  The objective is to get exactly the
      necessary amount of headers into the linear SKB area pre-pulled,
      but no more.  The new interface drivers use is eth_get_headlen().
      From WANG Cong, with driver conversions (several had their own
      by-hand duplicated implementations) by Alexander Duyck and Eric
      Dumazet.

   6) Support checksumming more smoothly and efficiently for
      encapsulations, and add "foo over UDP" facility.  From Tom
      Herbert.

   7) Add Broadcom SF2 switch driver to DSA layer, from Florian
      Fainelli.

   8) eBPF now can load programs via a system call and has an extensive
      testsuite.  Alexei Starovoitov and Daniel Borkmann.

   9) Major overhaul of the packet scheduler to use RCU in several major
      areas such as the classifiers and rate estimators.  From John
      Fastabend.

  10) Add driver for Intel FM10000 Ethernet Switch, from Alexander
      Duyck.

  11) Rearrange TCP_SKB_CB() to reduce cache line misses, from Eric
      Dumazet.

  12) Add Datacenter TCP congestion control algorithm support, From
      Florian Westphal.

  13) Reorganize sk_buff so that __copy_skb_header() is significantly
      faster.  From Eric Dumazet"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1558 commits)
  netlabel: directly return netlbl_unlabel_genl_init()
  net: add netdev_txq_bql_{enqueue, complete}_prefetchw() helpers
  net: description of dma_cookie cause make xmldocs warning
  cxgb4: clean up a type issue
  cxgb4: potential shift wrapping bug
  i40e: skb->xmit_more support
  net: fs_enet: Add NAPI TX
  net: fs_enet: Remove non NAPI RX
  r8169:add support for RTL8168EP
  net_sched: copy exts->type in tcf_exts_change()
  wimax: convert printk to pr_foo()
  af_unix: remove 0 assignment on static
  ipv6: Do not warn for informational ICMP messages, regardless of type.
  Update Intel Ethernet Driver maintainers list
  bridge: Save frag_max_size between PRE_ROUTING and POST_ROUTING
  tipc: fix bug in multicast congestion handling
  net: better IFF_XMIT_DST_RELEASE support
  net/mlx4_en: remove NETDEV_TX_BUSY
  3c59x: fix bad split of cpu_to_le32(pci_map_single())
  net: bcmgenet: fix Tx ring priority programming
  ...

1 files changed, 40 insertions, 77 deletions

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index ac9f2148cdc5..5032a602d5c9 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -307,7 +307,6 @@ enum ixgbe_ring_f_enum {
 #define MAX_RX_QUEUES (IXGBE_MAX_FDIR_INDICES + 1)
 #define MAX_TX_QUEUES (IXGBE_MAX_FDIR_INDICES + 1)
 #define IXGBE_MAX_L2A_QUEUES 4
-#define IXGBE_MAX_L2A_QUEUES 4
 #define IXGBE_BAD_L2A_QUEUE 3
 #define IXGBE_MAX_MACVLANS	31
 #define IXGBE_MAX_DCBMACVLANS	8
@@ -386,119 +385,87 @@ struct ixgbe_q_vector {
 	char name[IFNAMSIZ + 9];
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
-	unsigned int state;
-#define IXGBE_QV_STATE_IDLE        0
-#define IXGBE_QV_STATE_NAPI	   1     /* NAPI owns this QV */
-#define IXGBE_QV_STATE_POLL	   2     /* poll owns this QV */
-#define IXGBE_QV_STATE_DISABLED	   4     /* QV is disabled */
-#define IXGBE_QV_OWNED (IXGBE_QV_STATE_NAPI | IXGBE_QV_STATE_POLL)
-#define IXGBE_QV_LOCKED (IXGBE_QV_OWNED | IXGBE_QV_STATE_DISABLED)
-#define IXGBE_QV_STATE_NAPI_YIELD  8     /* NAPI yielded this QV */
-#define IXGBE_QV_STATE_POLL_YIELD  16    /* poll yielded this QV */
-#define IXGBE_QV_YIELD (IXGBE_QV_STATE_NAPI_YIELD | IXGBE_QV_STATE_POLL_YIELD)
-#define IXGBE_QV_USER_PEND (IXGBE_QV_STATE_POLL | IXGBE_QV_STATE_POLL_YIELD)
-	spinlock_t lock;
+	atomic_t state;
 #endif  /* CONFIG_NET_RX_BUSY_POLL */
 
 	/* for dynamic allocation of rings associated with this q_vector */
 	struct ixgbe_ring ring[0] ____cacheline_internodealigned_in_smp;
 };
+
 #ifdef CONFIG_NET_RX_BUSY_POLL
+enum ixgbe_qv_state_t {
+	IXGBE_QV_STATE_IDLE = 0,
+	IXGBE_QV_STATE_NAPI,
+	IXGBE_QV_STATE_POLL,
+	IXGBE_QV_STATE_DISABLE
+};
+
 static inline void ixgbe_qv_init_lock(struct ixgbe_q_vector *q_vector)
 {
-
-	spin_lock_init(&q_vector->lock);
-	q_vector->state = IXGBE_QV_STATE_IDLE;
+	/* reset state to idle */
+	atomic_set(&q_vector->state, IXGBE_QV_STATE_IDLE);
 }
 
 /* called from the device poll routine to get ownership of a q_vector */
 static inline bool ixgbe_qv_lock_napi(struct ixgbe_q_vector *q_vector)
 {
-	int rc = true;
-	spin_lock_bh(&q_vector->lock);
-	if (q_vector->state & IXGBE_QV_LOCKED) {
-		WARN_ON(q_vector->state & IXGBE_QV_STATE_NAPI);
-		q_vector->state |= IXGBE_QV_STATE_NAPI_YIELD;
-		rc = false;
+	int rc = atomic_cmpxchg(&q_vector->state, IXGBE_QV_STATE_IDLE,
+				IXGBE_QV_STATE_NAPI);
 #ifdef BP_EXTENDED_STATS
+	if (rc != IXGBE_QV_STATE_IDLE)
 		q_vector->tx.ring->stats.yields++;
 #endif
-	} else {
-		/* we don't care if someone yielded */
-		q_vector->state = IXGBE_QV_STATE_NAPI;
-	}
-	spin_unlock_bh(&q_vector->lock);
-	return rc;
+
+	return rc == IXGBE_QV_STATE_IDLE;
 }
 
 /* returns true is someone tried to get the qv while napi had it */
-static inline bool ixgbe_qv_unlock_napi(struct ixgbe_q_vector *q_vector)
+static inline void ixgbe_qv_unlock_napi(struct ixgbe_q_vector *q_vector)
 {
-	int rc = false;
-	spin_lock_bh(&q_vector->lock);
-	WARN_ON(q_vector->state & (IXGBE_QV_STATE_POLL |
-			       IXGBE_QV_STATE_NAPI_YIELD));
-
-	if (q_vector->state & IXGBE_QV_STATE_POLL_YIELD)
-		rc = true;
-	/* will reset state to idle, unless QV is disabled */
-	q_vector->state &= IXGBE_QV_STATE_DISABLED;
-	spin_unlock_bh(&q_vector->lock);
-	return rc;
+	WARN_ON(atomic_read(&q_vector->state) != IXGBE_QV_STATE_NAPI);
+
+	/* flush any outstanding Rx frames */
+	if (q_vector->napi.gro_list)
+		napi_gro_flush(&q_vector->napi, false);
+
+	/* reset state to idle */
+	atomic_set(&q_vector->state, IXGBE_QV_STATE_IDLE);
 }
 
 /* called from ixgbe_low_latency_poll() */
 static inline bool ixgbe_qv_lock_poll(struct ixgbe_q_vector *q_vector)
 {
-	int rc = true;
-	spin_lock_bh(&q_vector->lock);
-	if ((q_vector->state & IXGBE_QV_LOCKED)) {
-		q_vector->state |= IXGBE_QV_STATE_POLL_YIELD;
-		rc = false;
+	int rc = atomic_cmpxchg(&q_vector->state, IXGBE_QV_STATE_IDLE,
+				IXGBE_QV_STATE_POLL);
 #ifdef BP_EXTENDED_STATS
-		q_vector->rx.ring->stats.yields++;
+	if (rc != IXGBE_QV_STATE_IDLE)
+		q_vector->tx.ring->stats.yields++;
 #endif
-	} else {
-		/* preserve yield marks */
-		q_vector->state |= IXGBE_QV_STATE_POLL;
-	}
-	spin_unlock_bh(&q_vector->lock);
-	return rc;
+	return rc == IXGBE_QV_STATE_IDLE;
 }
 
 /* returns true if someone tried to get the qv while it was locked */
-static inline bool ixgbe_qv_unlock_poll(struct ixgbe_q_vector *q_vector)
+static inline void ixgbe_qv_unlock_poll(struct ixgbe_q_vector *q_vector)
 {
-	int rc = false;
-	spin_lock_bh(&q_vector->lock);
-	WARN_ON(q_vector->state & (IXGBE_QV_STATE_NAPI));
-
-	if (q_vector->state & IXGBE_QV_STATE_POLL_YIELD)
-		rc = true;
-	/* will reset state to idle, unless QV is disabled */
-	q_vector->state &= IXGBE_QV_STATE_DISABLED;
-	spin_unlock_bh(&q_vector->lock);
-	return rc;
+	WARN_ON(atomic_read(&q_vector->state) != IXGBE_QV_STATE_POLL);
+
+	/* reset state to idle */
+	atomic_set(&q_vector->state, IXGBE_QV_STATE_IDLE);
 }
 
 /* true if a socket is polling, even if it did not get the lock */
 static inline bool ixgbe_qv_busy_polling(struct ixgbe_q_vector *q_vector)
 {
-	WARN_ON(!(q_vector->state & IXGBE_QV_OWNED));
-	return q_vector->state & IXGBE_QV_USER_PEND;
+	return atomic_read(&q_vector->state) == IXGBE_QV_STATE_POLL;
 }
 
 /* false if QV is currently owned */
 static inline bool ixgbe_qv_disable(struct ixgbe_q_vector *q_vector)
 {
-	int rc = true;
-	spin_lock_bh(&q_vector->lock);
-	if (q_vector->state & IXGBE_QV_OWNED)
-		rc = false;
-	q_vector->state |= IXGBE_QV_STATE_DISABLED;
-	spin_unlock_bh(&q_vector->lock);
-
-	return rc;
+	int rc = atomic_cmpxchg(&q_vector->state, IXGBE_QV_STATE_IDLE,
+				IXGBE_QV_STATE_DISABLE);
+
+	return rc == IXGBE_QV_STATE_IDLE;
 }
 
 #else /* CONFIG_NET_RX_BUSY_POLL */
@@ -643,9 +610,7 @@ struct ixgbe_adapter {
 	 * thus the additional *_CAPABLE flags.
 	 */
 	u32 flags;
-#define IXGBE_FLAG_MSI_CAPABLE                  (u32)(1 << 0)
 #define IXGBE_FLAG_MSI_ENABLED                  (u32)(1 << 1)
-#define IXGBE_FLAG_MSIX_CAPABLE                 (u32)(1 << 2)
 #define IXGBE_FLAG_MSIX_ENABLED                 (u32)(1 << 3)
 #define IXGBE_FLAG_RX_1BUF_CAPABLE              (u32)(1 << 4)
 #define IXGBE_FLAG_RX_PS_CAPABLE                (u32)(1 << 5)
@@ -760,8 +725,6 @@ struct ixgbe_adapter {
 	u8 __iomem *io_addr; /* Mainly for iounmap use */
 	u32 wol;
 
-	u16 bd_number;
-
 	u16 eeprom_verh;
 	u16 eeprom_verl;
 	u16 eeprom_cap;