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

Pull networking updates from David Miller:
 "Highlights:

   1) Maintain the TCP retransmit queue using an rbtree, with 1GB
      windows at 100Gb this really has become necessary. From Eric
      Dumazet.

   2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.

   3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
      Lunn.

   4) Add meter action support to openvswitch, from Andy Zhou.

   5) Add a data meta pointer for BPF accessible packets, from Daniel
      Borkmann.

   6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.

   7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.

   8) More work to move the RTNL mutex down, from Florian Westphal.

   9) Add 'bpftool' utility, to help with bpf program introspection.
      From Jakub Kicinski.

  10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
      Dangaard Brouer.

  11) Support 'blocks' of transformations in the packet scheduler which
      can span multiple network devices, from Jiri Pirko.

  12) TC flower offload support in cxgb4, from Kumar Sanghvi.

  13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
      Leitner.

  14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.

  15) Add RED qdisc offloadability, and use it in mlxsw driver. From
      Nogah Frankel.

  16) eBPF based device controller for cgroup v2, from Roman Gushchin.

  17) Add some fundamental tracepoints for TCP, from Song Liu.

  18) Remove garbage collection from ipv6 route layer, this is a
      significant accomplishment. From Wei Wang.

  19) Add multicast route offload support to mlxsw, from Yotam Gigi"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
  tcp: highest_sack fix
  geneve: fix fill_info when link down
  bpf: fix lockdep splat
  net: cdc_ncm: GetNtbFormat endian fix
  openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
  netem: remove unnecessary 64 bit modulus
  netem: use 64 bit divide by rate
  tcp: Namespace-ify sysctl_tcp_default_congestion_control
  net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
  ipv6: set all.accept_dad to 0 by default
  uapi: fix linux/tls.h userspace compilation error
  usbnet: ipheth: prevent TX queue timeouts when device not ready
  vhost_net: conditionally enable tx polling
  uapi: fix linux/rxrpc.h userspace compilation errors
  net: stmmac: fix LPI transitioning for dwmac4
  atm: horizon: Fix irq release error
  net-sysfs: trigger netlink notification on ifalias change via sysfs
  openvswitch: Using kfree_rcu() to simplify the code
  openvswitch: Make local function ovs_nsh_key_attr_size() static
  openvswitch: Fix return value check in ovs_meter_cmd_features()
  ...

15 files changed, 85 insertions, 53 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/Kconfig b/drivers/net/ethernet/mellanox/mlx4/Kconfig
index 22b1cc012bc9..36054e6fb9d3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx4/Kconfig
@@ -38,3 +38,11 @@ config MLX4_DEBUG
 	  mlx4_core driver.  The output can be turned on via the
 	  debug_level module parameter (which can also be set after
 	  the driver is loaded through sysfs).
+
+config MLX4_CORE_GEN2
+	bool "Support for old gen2 Mellanox PCI IDs" if (MLX4_CORE)
+	depends on MLX4_CORE
+	default y
+	---help---
+	  Say Y here if you want to use old gen2 Mellanox devices in the
+	  driver.
diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c
index 53daa6ca5d83..de0f9e5e42ec 100644
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -277,7 +277,7 @@ void mlx4_start_catas_poll(struct mlx4_dev *dev)
 	phys_addr_t addr;
 
 	INIT_LIST_HEAD(&priv->catas_err.list);
-	init_timer(&priv->catas_err.timer);
+	setup_timer(&priv->catas_err.timer, poll_catas, (unsigned long)dev);
 	priv->catas_err.map = NULL;
 
 	if (!mlx4_is_slave(dev)) {
@@ -293,8 +293,6 @@ void mlx4_start_catas_poll(struct mlx4_dev *dev)
 		}
 	}
 
-	priv->catas_err.timer.data     = (unsigned long) dev;
-	priv->catas_err.timer.function = poll_catas;
 	priv->catas_err.timer.expires  =
 		round_jiffies(jiffies + MLX4_CATAS_POLL_INTERVAL);
 	add_timer(&priv->catas_err.timer);
diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c
index 72eb50cd5ecd..d8e9a323122e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cq.c
@@ -69,7 +69,7 @@ void mlx4_cq_tasklet_cb(unsigned long data)
 	list_for_each_entry_safe(mcq, temp, &ctx->process_list, tasklet_ctx.list) {
 		list_del_init(&mcq->tasklet_ctx.list);
 		mcq->tasklet_ctx.comp(mcq);
-		if (atomic_dec_and_test(&mcq->refcount))
+		if (refcount_dec_and_test(&mcq->refcount))
 			complete(&mcq->free);
 		if (time_after(jiffies, end))
 			break;
@@ -92,7 +92,7 @@ static void mlx4_add_cq_to_tasklet(struct mlx4_cq *cq)
 	 * still arrive.
 	 */
 	if (list_empty_careful(&cq->tasklet_ctx.list)) {
-		atomic_inc(&cq->refcount);
+		refcount_inc(&cq->refcount);
 		kick = list_empty(&tasklet_ctx->list);
 		list_add_tail(&cq->tasklet_ctx.list, &tasklet_ctx->list);
 		if (kick)
@@ -344,7 +344,7 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent,
 	cq->cons_index = 0;
 	cq->arm_sn     = 1;
 	cq->uar        = uar;
-	atomic_set(&cq->refcount, 1);
+	refcount_set(&cq->refcount, 1);
 	init_completion(&cq->free);
 	cq->comp = mlx4_add_cq_to_tasklet;
 	cq->tasklet_ctx.priv =
@@ -386,7 +386,7 @@ void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq)
 	    priv->eq_table.eq[MLX4_EQ_ASYNC].irq)
 		synchronize_irq(priv->eq_table.eq[MLX4_EQ_ASYNC].irq);
 
-	if (atomic_dec_and_test(&cq->refcount))
+	if (refcount_dec_and_test(&cq->refcount))
 		complete(&cq->free);
 	wait_for_completion(&cq->free);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 3d4e4a5d00d1..bf1f04164885 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1742,13 +1742,18 @@ static int mlx4_en_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 	return err;
 }
 
+static int mlx4_en_get_max_num_rx_rings(struct net_device *dev)
+{
+	return min_t(int, num_online_cpus(), MAX_RX_RINGS);
+}
+
 static void mlx4_en_get_channels(struct net_device *dev,
 				 struct ethtool_channels *channel)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 
-	channel->max_rx = MAX_RX_RINGS;
-	channel->max_tx = MLX4_EN_MAX_TX_RING_P_UP;
+	channel->max_rx = mlx4_en_get_max_num_rx_rings(dev);
+	channel->max_tx = priv->mdev->profile.max_num_tx_rings_p_up;
 
 	channel->rx_count = priv->rx_ring_num;
 	channel->tx_count = priv->tx_ring_num[TX] /
@@ -1777,7 +1782,7 @@ static int mlx4_en_set_channels(struct net_device *dev,
 	mutex_lock(&mdev->state_lock);
 	xdp_count = priv->tx_ring_num[TX_XDP] ? channel->rx_count : 0;
 	if (channel->tx_count * priv->prof->num_up + xdp_count >
-	    MAX_TX_RINGS) {
+	    priv->mdev->profile.max_num_tx_rings_p_up * priv->prof->num_up) {
 		err = -EINVAL;
 		en_err(priv,
 		       "Total number of TX and XDP rings (%d) exceeds the maximum supported (%d)\n",
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c
index 686e18de9a97..2c2965497ed3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c
@@ -153,7 +153,7 @@ static void mlx4_en_get_profile(struct mlx4_en_dev *mdev)
 	int i;
 
 	params->udp_rss = udp_rss;
-	params->num_tx_rings_p_up = mlx4_low_memory_profile() ?
+	params->max_num_tx_rings_p_up = mlx4_low_memory_profile() ?
 		MLX4_EN_MIN_TX_RING_P_UP :
 		min_t(int, num_online_cpus(), MLX4_EN_MAX_TX_RING_P_UP);
 
@@ -170,8 +170,8 @@ static void mlx4_en_get_profile(struct mlx4_en_dev *mdev)
 		params->prof[i].tx_ring_size = MLX4_EN_DEF_TX_RING_SIZE;
 		params->prof[i].rx_ring_size = MLX4_EN_DEF_RX_RING_SIZE;
 		params->prof[i].num_up = MLX4_EN_NUM_UP_LOW;
-		params->prof[i].num_tx_rings_p_up = params->num_tx_rings_p_up;
-		params->prof[i].tx_ring_num[TX] = params->num_tx_rings_p_up *
+		params->prof[i].num_tx_rings_p_up = params->max_num_tx_rings_p_up;
+		params->prof[i].tx_ring_num[TX] = params->max_num_tx_rings_p_up *
 			params->prof[i].num_up;
 		params->prof[i].rss_rings = 0;
 		params->prof[i].inline_thold = inline_thold;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 9c218f1cfc6c..99051a294fa6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -135,7 +135,7 @@ static int __mlx4_en_setup_tc(struct net_device *dev, enum tc_setup_type type,
 {
 	struct tc_mqprio_qopt *mqprio = type_data;
 
-	if (type != TC_SETUP_MQPRIO)
+	if (type != TC_SETUP_QDISC_MQPRIO)
 		return -EOPNOTSUPP;
 
 	if (mqprio->num_tc && mqprio->num_tc != MLX4_EN_NUM_UP_HIGH)
@@ -1752,6 +1752,7 @@ int mlx4_en_start_port(struct net_device *dev)
 				mlx4_en_arm_cq(priv, cq);
 
 			} else {
+				mlx4_en_init_tx_xdp_ring_descs(priv, tx_ring);
 				mlx4_en_init_recycle_ring(priv, i);
 				/* XDP TX CQ should never be armed */
 			}
@@ -2915,7 +2916,7 @@ static u32 mlx4_xdp_query(struct net_device *dev)
 	return prog_id;
 }
 
-static int mlx4_xdp(struct net_device *dev, struct netdev_xdp *xdp)
+static int mlx4_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
@@ -2957,7 +2958,7 @@ static const struct net_device_ops mlx4_netdev_ops = {
 	.ndo_udp_tunnel_del	= mlx4_en_del_vxlan_port,
 	.ndo_features_check	= mlx4_en_features_check,
 	.ndo_set_tx_maxrate	= mlx4_en_set_tx_maxrate,
-	.ndo_xdp		= mlx4_xdp,
+	.ndo_bpf		= mlx4_xdp,
 };
 
 static const struct net_device_ops mlx4_netdev_ops_master = {
@@ -2994,7 +2995,7 @@ static const struct net_device_ops mlx4_netdev_ops_master = {
 	.ndo_udp_tunnel_del	= mlx4_en_del_vxlan_port,
 	.ndo_features_check	= mlx4_en_features_check,
 	.ndo_set_tx_maxrate	= mlx4_en_set_tx_maxrate,
-	.ndo_xdp		= mlx4_xdp,
+	.ndo_bpf		= mlx4_xdp,
 };
 
 struct mlx4_en_bond {
@@ -3305,7 +3306,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	priv->pflags = MLX4_EN_PRIV_FLAGS_BLUEFLAME;
 	priv->ctrl_flags = cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE |
 			MLX4_WQE_CTRL_SOLICITED);
-	priv->num_tx_rings_p_up = mdev->profile.num_tx_rings_p_up;
+	priv->num_tx_rings_p_up = mdev->profile.max_num_tx_rings_p_up;
 	priv->tx_work_limit = MLX4_EN_DEFAULT_TX_WORK;
 	netdev_rss_key_fill(priv->rss_key, sizeof(priv->rss_key));
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_resources.c b/drivers/net/ethernet/mellanox/mlx4/en_resources.c
index 5a47f9669621..6883ac75d37f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_resources.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_resources.c
@@ -53,7 +53,7 @@ void mlx4_en_fill_qp_context(struct mlx4_en_priv *priv, int size, int stride,
 	if (is_tx) {
 		context->sq_size_stride = ilog2(size) << 3 | (ilog2(stride) - 4);
 		if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PORT_REMAP)
-			context->params2 |= MLX4_QP_BIT_FPP;
+			context->params2 |= cpu_to_be32(MLX4_QP_BIT_FPP);
 
 	} else {
 		context->sq_size_stride = ilog2(TXBB_SIZE) - 4;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index b97a55c827eb..92aec17f4b4d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -254,8 +254,7 @@ void mlx4_en_set_num_rx_rings(struct mlx4_en_dev *mdev)
 					 DEF_RX_RINGS));
 
 		num_rx_rings = mlx4_low_memory_profile() ? MIN_RX_RINGS :
-			min_t(int, num_of_eqs,
-			      netif_get_num_default_rss_queues());
+			min_t(int, num_of_eqs, num_online_cpus());
 		mdev->profile.prof[i].rx_ring_num =
 			rounddown_pow_of_two(num_rx_rings);
 	}
@@ -762,6 +761,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 
 			xdp.data_hard_start = va - frags[0].page_offset;
 			xdp.data = va;
+			xdp_set_data_meta_invalid(&xdp);
 			xdp.data_end = xdp.data + length;
 			orig_data = xdp.data;
 
@@ -778,7 +778,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			case XDP_PASS:
 				break;
 			case XDP_TX:
-				if (likely(!mlx4_en_xmit_frame(ring, frags, dev,
+				if (likely(!mlx4_en_xmit_frame(ring, frags, priv,
 							length, cq_ring,
 							&doorbell_pending))) {
 					frags[0].page = NULL;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 3541a7f9d12e..6b6853773848 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -718,7 +718,7 @@ void mlx4_en_xmit_doorbell(struct mlx4_en_tx_ring *ring)
 #else
 	iowrite32be(
 #endif
-		  ring->doorbell_qpn,
+		  (__force u32)ring->doorbell_qpn,
 		  ring->bf.uar->map + MLX4_SEND_DOORBELL);
 }
 
@@ -1085,13 +1085,35 @@ tx_drop:
 #define MLX4_EN_XDP_TX_REAL_SZ (((CTRL_SIZE + MLX4_EN_XDP_TX_NRTXBB * DS_SIZE) \
 				 / 16) & 0x3f)
 
+void mlx4_en_init_tx_xdp_ring_descs(struct mlx4_en_priv *priv,
+				    struct mlx4_en_tx_ring *ring)
+{
+	int i;
+
+	for (i = 0; i < ring->size; i++) {
+		struct mlx4_en_tx_info *tx_info = &ring->tx_info[i];
+		struct mlx4_en_tx_desc *tx_desc = ring->buf +
+			(i << LOG_TXBB_SIZE);
+
+		tx_info->map0_byte_count = PAGE_SIZE;
+		tx_info->nr_txbb = MLX4_EN_XDP_TX_NRTXBB;
+		tx_info->data_offset = offsetof(struct mlx4_en_tx_desc, data);
+		tx_info->ts_requested = 0;
+		tx_info->nr_maps = 1;
+		tx_info->linear = 1;
+		tx_info->inl = 0;
+
+		tx_desc->data.lkey = ring->mr_key;
+		tx_desc->ctrl.qpn_vlan.fence_size = MLX4_EN_XDP_TX_REAL_SZ;
+		tx_desc->ctrl.srcrb_flags = priv->ctrl_flags;
+	}
+}
+
 netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
 			       struct mlx4_en_rx_alloc *frame,
-			       struct net_device *dev, unsigned int length,
+			       struct mlx4_en_priv *priv, unsigned int length,
 			       int tx_ind, bool *doorbell_pending)
 {
-	struct mlx4_en_priv *priv = netdev_priv(dev);
-	union mlx4_wqe_qpn_vlan	qpn_vlan = {};
 	struct mlx4_en_tx_desc *tx_desc;
 	struct mlx4_en_tx_info *tx_info;
 	struct mlx4_wqe_data_seg *data;
@@ -1123,25 +1145,16 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
 	tx_info->page = frame->page;
 	frame->page = NULL;
 	tx_info->map0_dma = dma;
-	tx_info->map0_byte_count = PAGE_SIZE;
-	tx_info->nr_txbb = MLX4_EN_XDP_TX_NRTXBB;
 	tx_info->nr_bytes = max_t(unsigned int, length, ETH_ZLEN);
-	tx_info->data_offset = offsetof(struct mlx4_en_tx_desc, data);
-	tx_info->ts_requested = 0;
-	tx_info->nr_maps = 1;
-	tx_info->linear = 1;
-	tx_info->inl = 0;
 
 	dma_sync_single_range_for_device(priv->ddev, dma, frame->page_offset,
 					 length, PCI_DMA_TODEVICE);
 
 	data->addr = cpu_to_be64(dma + frame->page_offset);
-	data->lkey = ring->mr_key;
 	dma_wmb();
 	data->byte_count = cpu_to_be32(length);
 
 	/* tx completion can avoid cache line miss for common cases */
-	tx_desc->ctrl.srcrb_flags = priv->ctrl_flags;
 
 	op_own = cpu_to_be32(MLX4_OPCODE_SEND) |
 		((ring->prod & ring->size) ?
@@ -1152,10 +1165,13 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
 
 	ring->prod += MLX4_EN_XDP_TX_NRTXBB;
 
-	qpn_vlan.fence_size = MLX4_EN_XDP_TX_REAL_SZ;
+	/* Ensure new descriptor hits memory
+	 * before setting ownership of this descriptor to HW
+	 */
+	dma_wmb();
+	tx_desc->ctrl.owner_opcode = op_own;
+	ring->xmit_more++;
 
-	mlx4_en_tx_write_desc(ring, tx_desc, qpn_vlan, TXBB_SIZE, 0,
-			      op_own, false, false);
 	*doorbell_pending = true;
 
 	return NETDEV_TX_OK;
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 16c09949afd5..634f603f941c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -57,12 +57,12 @@ MODULE_PARM_DESC(enable_qos, "Enable Enhanced QoS support (default: off)");
 #define MLX4_GET(dest, source, offset)				      \
 	do {							      \
 		void *__p = (char *) (source) + (offset);	      \
-		u64 val;                                              \
-		switch (sizeof(dest)) {			      \
+		__be64 val;                                           \
+		switch (sizeof(dest)) {				      \
 		case 1: (dest) = *(u8 *) __p;	    break;	      \
 		case 2: (dest) = be16_to_cpup(__p); break;	      \
 		case 4: (dest) = be32_to_cpup(__p); break;	      \
-		case 8: val = get_unaligned((u64 *)__p);              \
+		case 8: val = get_unaligned((__be64 *)__p);           \
 			(dest) = be64_to_cpu(val);  break;            \
 		default: __buggy_use_of_MLX4_GET();		      \
 		}						      \
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index e61c99ef741d..4d84cab77105 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -4066,6 +4066,7 @@ int mlx4_restart_one(struct pci_dev *pdev)
 #define MLX_GN(id) { PCI_VDEVICE(MELLANOX, id), 0 }
 
 static const struct pci_device_id mlx4_pci_table[] = {
+#ifdef CONFIG_MLX4_CORE_GEN2
 	/* MT25408 "Hermon" */
 	MLX_SP(PCI_DEVICE_ID_MELLANOX_HERMON_SDR),	/* SDR */
 	MLX_SP(PCI_DEVICE_ID_MELLANOX_HERMON_DDR),	/* DDR */
@@ -4085,6 +4086,7 @@ static const struct pci_device_id mlx4_pci_table[] = {
 	MLX_SP(PCI_DEVICE_ID_MELLANOX_CONNECTX2),
 	/* MT25400 Family [ConnectX-2] */
 	MLX_VF(0x1002),					/* Virtual Function */
+#endif /* CONFIG_MLX4_CORE_GEN2 */
 	/* MT27500 Family [ConnectX-3] */
 	MLX_GN(PCI_DEVICE_ID_MELLANOX_CONNECTX3),
 	MLX_VF(0x1004),					/* Virtual Function */
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index fdb3ad0cbe54..1856e279a7e0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -399,7 +399,7 @@ struct mlx4_en_profile {
 	u32 active_ports;
 	u32 small_pkt_int;
 	u8 no_reset;
-	u8 num_tx_rings_p_up;
+	u8 max_num_tx_rings_p_up;
 	struct mlx4_en_port_profile prof[MLX4_MAX_PORTS + 1];
 };
 
@@ -693,7 +693,7 @@ u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
 netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
 netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
 			       struct mlx4_en_rx_alloc *frame,
-			       struct net_device *dev, unsigned int length,
+			       struct mlx4_en_priv *priv, unsigned int length,
 			       int tx_ind, bool *doorbell_pending);
 void mlx4_en_xmit_doorbell(struct mlx4_en_tx_ring *ring);
 bool mlx4_en_rx_recycle(struct mlx4_en_rx_ring *ring,
@@ -705,6 +705,8 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 			   int node, int queue_index);
 void mlx4_en_destroy_tx_ring(struct mlx4_en_priv *priv,
 			     struct mlx4_en_tx_ring **pring);
+void mlx4_en_init_tx_xdp_ring_descs(struct mlx4_en_priv *priv,
+				    struct mlx4_en_tx_ring *ring);
 int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
 			     struct mlx4_en_tx_ring *ring,
 			     int cq, int user_prio);
diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c
index 728a2fb1f5c0..769598f7b6c8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx4/qp.c
@@ -55,7 +55,7 @@ void mlx4_qp_event(struct mlx4_dev *dev, u32 qpn, int event_type)
 
 	qp = __mlx4_qp_lookup(dev, qpn);
 	if (qp)
-		atomic_inc(&qp->refcount);
+		refcount_inc(&qp->refcount);
 
 	spin_unlock(&qp_table->lock);
 
@@ -66,7 +66,7 @@ void mlx4_qp_event(struct mlx4_dev *dev, u32 qpn, int event_type)
 
 	qp->event(qp, event_type);
 
-	if (atomic_dec_and_test(&qp->refcount))
+	if (refcount_dec_and_test(&qp->refcount))
 		complete(&qp->free);
 }
 
@@ -420,7 +420,7 @@ int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp)
 	if (err)
 		goto err_icm;
 
-	atomic_set(&qp->refcount, 1);
+	refcount_set(&qp->refcount, 1);
 	init_completion(&qp->free);
 
 	return 0;
@@ -520,7 +520,7 @@ EXPORT_SYMBOL_GPL(mlx4_qp_remove);
 
 void mlx4_qp_free(struct mlx4_dev *dev, struct mlx4_qp *qp)
 {
-	if (atomic_dec_and_test(&qp->refcount))
+	if (refcount_dec_and_test(&qp->refcount))
 		complete(&qp->free);
 	wait_for_completion(&qp->free);
 
@@ -925,7 +925,7 @@ int mlx4_qp_to_ready(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 		context->flags &= cpu_to_be32(~(0xf << 28));
 		context->flags |= cpu_to_be32(states[i + 1] << 28);
 		if (states[i + 1] != MLX4_QP_STATE_RTR)
-			context->params2 &= ~MLX4_QP_BIT_FPP;
+			context->params2 &= ~cpu_to_be32(MLX4_QP_BIT_FPP);
 		err = mlx4_qp_modify(dev, mtt, states[i], states[i + 1],
 				     context, 0, 0, qp);
 		if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index fabb53379727..04304dd894c6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -3185,7 +3185,7 @@ static int verify_qp_parameters(struct mlx4_dev *dev,
 	optpar	= be32_to_cpu(*(__be32 *) inbox->buf);
 
 	if (slave != mlx4_master_func_num(dev)) {
-		qp_ctx->params2 &= ~MLX4_QP_BIT_FPP;
+		qp_ctx->params2 &= ~cpu_to_be32(MLX4_QP_BIT_FPP);
 		/* setting QP rate-limit is disallowed for VFs */
 		if (qp_ctx->rate_limit_params)
 			return -EPERM;
diff --git a/drivers/net/ethernet/mellanox/mlx4/srq.c b/drivers/net/ethernet/mellanox/mlx4/srq.c
index bedf52126824..cbe4d9746ddf 100644
--- a/drivers/net/ethernet/mellanox/mlx4/srq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/srq.c
@@ -49,7 +49,7 @@ void mlx4_srq_event(struct mlx4_dev *dev, u32 srqn, int event_type)
 	srq = radix_tree_lookup(&srq_table->tree, srqn & (dev->caps.num_srqs - 1));
 	rcu_read_unlock();
 	if (srq)
-		atomic_inc(&srq->refcount);
+		refcount_inc(&srq->refcount);
 	else {
 		mlx4_warn(dev, "Async event for bogus SRQ %08x\n", srqn);
 		return;
@@ -57,7 +57,7 @@ void mlx4_srq_event(struct mlx4_dev *dev, u32 srqn, int event_type)
 
 	srq->event(srq, event_type);
 
-	if (atomic_dec_and_test(&srq->refcount))
+	if (refcount_dec_and_test(&srq->refcount))
 		complete(&srq->free);
 }
 
@@ -203,7 +203,7 @@ int mlx4_srq_alloc(struct mlx4_dev *dev, u32 pdn, u32 cqn, u16 xrcd,
 	if (err)
 		goto err_radix;
 
-	atomic_set(&srq->refcount, 1);
+	refcount_set(&srq->refcount, 1);
 	init_completion(&srq->free);
 
 	return 0;
@@ -232,7 +232,7 @@ void mlx4_srq_free(struct mlx4_dev *dev, struct mlx4_srq *srq)
 	radix_tree_delete(&srq_table->tree, srq->srqn);
 	spin_unlock_irq(&srq_table->lock);
 
-	if (atomic_dec_and_test(&srq->refcount))
+	if (refcount_dec_and_test(&srq->refcount))
 		complete(&srq->free);
 	wait_for_completion(&srq->free);