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

Pull networking fixes from David Miller:

 1) Must teardown SR-IOV before unregistering netdev in igb driver, from
    Alex Williamson.

 2) Fix ipv6 route unreachable crash in IPVS, from Alex Gartrell.

 3) Default route selection in ipv4 should take the prefix length, table
    ID, and TOS into account, from Julian Anastasov.

 4) sch_plug must have a reset method in order to purge all buffered
    packets when the qdisc is reset, likewise for sch_choke, from WANG
    Cong.

 5) Fix deadlock and races in slave_changelink/br_setport in bridging.
    From Nikolay Aleksandrov.

 6) mlx4 bug fixes (wrong index in port even propagation to VFs,
    overzealous BUG_ON assertion, etc.) from Ido Shamay, Jack
    Morgenstein, and Or Gerlitz.

 7) Turn off klog message about SCTP userspace interface compat that
    makes no sense at all, from Daniel Borkmann.

 8) Fix unbounded restarts of inet frag eviction process, causing NMI
    watchdog soft lockup messages, from Florian Westphal.

 9) Suspend/resume fixes for r8152 from Hayes Wang.

10) Fix busy loop when MSG_WAITALL|MSG_PEEK is used in TCP recv, from
    Sabrina Dubroca.

11) Fix performance regression when removing a lot of routes from the
    ipv4 routing tables, from Alexander Duyck.

12) Fix device leak in AF_PACKET, from Lars Westerhoff.

13) AF_PACKET also has a header length comparison bug due to signedness,
    from Alexander Drozdov.

14) Fix bug in EBPF tail call generation on x86, from Daniel Borkmann.

15) Memory leaks, TSO stats, watchdog timeout and other fixes to
    thunderx driver from Sunil Goutham and Thanneeru Srinivasulu.

16) act_bpf can leak memory when replacing programs, from Daniel
    Borkmann.

17) WOL packet fixes in gianfar driver, from Claudiu Manoil.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (79 commits)
  stmmac: fix missing MODULE_LICENSE in stmmac_platform
  gianfar: Enable device wakeup when appropriate
  gianfar: Fix suspend/resume for wol magic packet
  gianfar: Fix warning when CONFIG_PM off
  act_pedit: check binding before calling tcf_hash_release()
  net: sk_clone_lock() should only do get_net() if the parent is not a kernel socket
  net: sched: fix refcount imbalance in actions
  r8152: reset device when tx timeout
  r8152: add pre_reset and post_reset
  qlcnic: Fix corruption while copying
  act_bpf: fix memory leaks when replacing bpf programs
  net: thunderx: Fix for crash while BGX teardown
  net: thunderx: Add PCI driver shutdown routine
  net: thunderx: Fix crash when changing rss with mutliple traffic flows
  net: thunderx: Set watchdog timeout value
  net: thunderx: Wakeup TXQ only if CQE_TX are processed
  net: thunderx: Suppress alloc_pages() failure warnings
  net: thunderx: Fix TSO packet statistic
  net: thunderx: Fix memory leak when changing queue count
  net: thunderx: Fix RQ_DROP miscalculation
  ...

27 files changed, 562 insertions, 292 deletions

diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index caeb39561567..bf9eb2ecf960 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -104,6 +104,57 @@ static void *macb_rx_buffer(struct macb *bp, unsigned int index)
 	return bp->rx_buffers + bp->rx_buffer_size * macb_rx_ring_wrap(index);
 }
 
+/* I/O accessors */
+static u32 hw_readl_native(struct macb *bp, int offset)
+{
+	return __raw_readl(bp->regs + offset);
+}
+
+static void hw_writel_native(struct macb *bp, int offset, u32 value)
+{
+	__raw_writel(value, bp->regs + offset);
+}
+
+static u32 hw_readl(struct macb *bp, int offset)
+{
+	return readl_relaxed(bp->regs + offset);
+}
+
+static void hw_writel(struct macb *bp, int offset, u32 value)
+{
+	writel_relaxed(value, bp->regs + offset);
+}
+
+/*
+ * Find the CPU endianness by using the loopback bit of NCR register. When the
+ * CPU is in big endian we need to program swaped mode for management
+ * descriptor access.
+ */
+static bool hw_is_native_io(void __iomem *addr)
+{
+	u32 value = MACB_BIT(LLB);
+
+	__raw_writel(value, addr + MACB_NCR);
+	value = __raw_readl(addr + MACB_NCR);
+
+	/* Write 0 back to disable everything */
+	__raw_writel(0, addr + MACB_NCR);
+
+	return value == MACB_BIT(LLB);
+}
+
+static bool hw_is_gem(void __iomem *addr, bool native_io)
+{
+	u32 id;
+
+	if (native_io)
+		id = __raw_readl(addr + MACB_MID);
+	else
+		id = readl_relaxed(addr + MACB_MID);
+
+	return MACB_BFEXT(IDNUM, id) >= 0x2;
+}
+
 static void macb_set_hwaddr(struct macb *bp)
 {
 	u32 bottom;
@@ -160,7 +211,7 @@ static void macb_get_hwaddr(struct macb *bp)
 		}
 	}
 
-	netdev_info(bp->dev, "invalid hw address, using random\n");
+	dev_info(&bp->pdev->dev, "invalid hw address, using random\n");
 	eth_hw_addr_random(bp->dev);
 }
 
@@ -252,7 +303,6 @@ static void macb_handle_link_change(struct net_device *dev)
 	struct macb *bp = netdev_priv(dev);
 	struct phy_device *phydev = bp->phy_dev;
 	unsigned long flags;
-
 	int status_change = 0;
 
 	spin_lock_irqsave(&bp->lock, flags);
@@ -449,14 +499,14 @@ err_out:
 
 static void macb_update_stats(struct macb *bp)
 {
-	u32 __iomem *reg = bp->regs + MACB_PFR;
 	u32 *p = &bp->hw_stats.macb.rx_pause_frames;
 	u32 *end = &bp->hw_stats.macb.tx_pause_frames + 1;
+	int offset = MACB_PFR;
 
 	WARN_ON((unsigned long)(end - p - 1) != (MACB_TPF - MACB_PFR) / 4);
 
-	for(; p < end; p++, reg++)
-		*p += readl_relaxed(reg);
+	for(; p < end; p++, offset += 4)
+		*p += bp->macb_reg_readl(bp, offset);
 }
 
 static int macb_halt_tx(struct macb *bp)
@@ -1107,12 +1157,6 @@ static void macb_poll_controller(struct net_device *dev)
 }
 #endif
 
-static inline unsigned int macb_count_tx_descriptors(struct macb *bp,
-						     unsigned int len)
-{
-	return (len + bp->max_tx_length - 1) / bp->max_tx_length;
-}
-
 static unsigned int macb_tx_map(struct macb *bp,
 				struct macb_queue *queue,
 				struct sk_buff *skb)
@@ -1263,11 +1307,11 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	 * socket buffer: skb fragments of jumbo frames may need to be
 	 * splitted into many buffer descriptors.
 	 */
-	count = macb_count_tx_descriptors(bp, skb_headlen(skb));
+	count = DIV_ROUND_UP(skb_headlen(skb), bp->max_tx_length);
 	nr_frags = skb_shinfo(skb)->nr_frags;
 	for (f = 0; f < nr_frags; f++) {
 		frag_size = skb_frag_size(&skb_shinfo(skb)->frags[f]);
-		count += macb_count_tx_descriptors(bp, frag_size);
+		count += DIV_ROUND_UP(frag_size, bp->max_tx_length);
 	}
 
 	spin_lock_irqsave(&bp->lock, flags);
@@ -1603,7 +1647,6 @@ static u32 macb_dbw(struct macb *bp)
 static void macb_configure_dma(struct macb *bp)
 {
 	u32 dmacfg;
-	u32 tmp, ncr;
 
 	if (macb_is_gem(bp)) {
 		dmacfg = gem_readl(bp, DMACFG) & ~GEM_BF(RXBS, -1L);
@@ -1613,22 +1656,11 @@ static void macb_configure_dma(struct macb *bp)
 		dmacfg |= GEM_BIT(TXPBMS) | GEM_BF(RXBMS, -1L);
 		dmacfg &= ~GEM_BIT(ENDIA_PKT);
 
-		/* Find the CPU endianness by using the loopback bit of net_ctrl
-		 * register. save it first. When the CPU is in big endian we
-		 * need to program swaped mode for management descriptor access.
-		 */
-		ncr = macb_readl(bp, NCR);
-		__raw_writel(MACB_BIT(LLB), bp->regs + MACB_NCR);
-		tmp =  __raw_readl(bp->regs + MACB_NCR);
-
-		if (tmp == MACB_BIT(LLB))
+		if (bp->native_io)
 			dmacfg &= ~GEM_BIT(ENDIA_DESC);
 		else
 			dmacfg |= GEM_BIT(ENDIA_DESC); /* CPU in big endian */
 
-		/* Restore net_ctrl */
-		macb_writel(bp, NCR, ncr);
-
 		if (bp->dev->features & NETIF_F_HW_CSUM)
 			dmacfg |= GEM_BIT(TXCOEN);
 		else
@@ -1897,19 +1929,19 @@ static int macb_change_mtu(struct net_device *dev, int new_mtu)
 
 static void gem_update_stats(struct macb *bp)
 {
-	int i;
+	unsigned int i;
 	u32 *p = &bp->hw_stats.gem.tx_octets_31_0;
 
 	for (i = 0; i < GEM_STATS_LEN; ++i, ++p) {
 		u32 offset = gem_statistics[i].offset;
-		u64 val = readl_relaxed(bp->regs + offset);
+		u64 val = bp->macb_reg_readl(bp, offset);
 
 		bp->ethtool_stats[i] += val;
 		*p += val;
 
 		if (offset == GEM_OCTTXL || offset == GEM_OCTRXL) {
 			/* Add GEM_OCTTXH, GEM_OCTRXH */
-			val = readl_relaxed(bp->regs + offset + 4);
+			val = bp->macb_reg_readl(bp, offset + 4);
 			bp->ethtool_stats[i] += ((u64)val) << 32;
 			*(++p) += val;
 		}
@@ -1976,7 +2008,7 @@ static int gem_get_sset_count(struct net_device *dev, int sset)
 
 static void gem_get_ethtool_strings(struct net_device *dev, u32 sset, u8 *p)
 {
-	int i;
+	unsigned int i;
 
 	switch (sset) {
 	case ETH_SS_STATS:
@@ -2190,7 +2222,7 @@ static void macb_configure_caps(struct macb *bp, const struct macb_config *dt_co
 	if (dt_conf)
 		bp->caps = dt_conf->caps;
 
-	if (macb_is_gem_hw(bp->regs)) {
+	if (hw_is_gem(bp->regs, bp->native_io)) {
 		bp->caps |= MACB_CAPS_MACB_IS_GEM;
 
 		dcfg = gem_readl(bp, DCFG1);
@@ -2201,10 +2233,11 @@ static void macb_configure_caps(struct macb *bp, const struct macb_config *dt_co
 			bp->caps |= MACB_CAPS_FIFO_MODE;
 	}
 
-	netdev_dbg(bp->dev, "Cadence caps 0x%08x\n", bp->caps);
+	dev_dbg(&bp->pdev->dev, "Cadence caps 0x%08x\n", bp->caps);
 }
 
 static void macb_probe_queues(void __iomem *mem,
+			      bool native_io,
 			      unsigned int *queue_mask,
 			      unsigned int *num_queues)
 {
@@ -2219,7 +2252,7 @@ static void macb_probe_queues(void __iomem *mem,
 	 * we are early in the probe process and don't have the
 	 * MACB_CAPS_MACB_IS_GEM flag positioned
 	 */
-	if (!macb_is_gem_hw(mem))
+	if (!hw_is_gem(mem, native_io))
 		return;
 
 	/* bit 0 is never set but queue 0 always exists */
@@ -2786,6 +2819,7 @@ static int macb_probe(struct platform_device *pdev)
 	struct clk *pclk, *hclk, *tx_clk;
 	unsigned int queue_mask, num_queues;
 	struct macb_platform_data *pdata;
+	bool native_io;
 	struct phy_device *phydev;
 	struct net_device *dev;
 	struct resource *regs;
@@ -2794,6 +2828,11 @@ static int macb_probe(struct platform_device *pdev)
 	struct macb *bp;
 	int err;
 
+	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	mem = devm_ioremap_resource(&pdev->dev, regs);
+	if (IS_ERR(mem))
+		return PTR_ERR(mem);
+
 	if (np) {
 		const struct of_device_id *match;
 
@@ -2809,14 +2848,9 @@ static int macb_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	mem = devm_ioremap_resource(&pdev->dev, regs);
-	if (IS_ERR(mem)) {
-		err = PTR_ERR(mem);
-		goto err_disable_clocks;
-	}
+	native_io = hw_is_native_io(mem);
 
-	macb_probe_queues(mem, &queue_mask, &num_queues);
+	macb_probe_queues(mem, native_io, &queue_mask, &num_queues);
 	dev = alloc_etherdev_mq(sizeof(*bp), num_queues);
 	if (!dev) {
 		err = -ENOMEM;
@@ -2831,6 +2865,14 @@ static int macb_probe(struct platform_device *pdev)
 	bp->pdev = pdev;
 	bp->dev = dev;
 	bp->regs = mem;
+	bp->native_io = native_io;
+	if (native_io) {
+		bp->macb_reg_readl = hw_readl_native;
+		bp->macb_reg_writel = hw_writel_native;
+	} else {
+		bp->macb_reg_readl = hw_readl;
+		bp->macb_reg_writel = hw_writel;
+	}
 	bp->num_queues = num_queues;
 	bp->queue_mask = queue_mask;
 	if (macb_config)
@@ -2838,9 +2880,8 @@ static int macb_probe(struct platform_device *pdev)
 	bp->pclk = pclk;
 	bp->hclk = hclk;
 	bp->tx_clk = tx_clk;
-	if (macb_config->jumbo_max_len) {
+	if (macb_config)
 		bp->jumbo_max_len = macb_config->jumbo_max_len;
-	}
 
 	spin_lock_init(&bp->lock);
 
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index d74655993d4b..1895b6b2addd 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -429,18 +429,12 @@
 	 | GEM_BF(name, value))
 
 /* Register access macros */
-#define macb_readl(port,reg)				\
-	readl_relaxed((port)->regs + MACB_##reg)
-#define macb_writel(port,reg,value)			\
-	writel_relaxed((value), (port)->regs + MACB_##reg)
-#define gem_readl(port, reg)				\
-	readl_relaxed((port)->regs + GEM_##reg)
-#define gem_writel(port, reg, value)			\
-	writel_relaxed((value), (port)->regs + GEM_##reg)
-#define queue_readl(queue, reg)				\
-	readl_relaxed((queue)->bp->regs + (queue)->reg)
-#define queue_writel(queue, reg, value)			\
-	writel_relaxed((value), (queue)->bp->regs + (queue)->reg)
+#define macb_readl(port, reg)		(port)->macb_reg_readl((port), MACB_##reg)
+#define macb_writel(port, reg, value)	(port)->macb_reg_writel((port), MACB_##reg, (value))
+#define gem_readl(port, reg)		(port)->macb_reg_readl((port), GEM_##reg)
+#define gem_writel(port, reg, value)	(port)->macb_reg_writel((port), GEM_##reg, (value))
+#define queue_readl(queue, reg)		(queue)->bp->macb_reg_readl((queue)->bp, (queue)->reg)
+#define queue_writel(queue, reg, value)	(queue)->bp->macb_reg_writel((queue)->bp, (queue)->reg, (value))
 
 /* Conditional GEM/MACB macros.  These perform the operation to the correct
  * register dependent on whether the device is a GEM or a MACB.  For registers
@@ -785,6 +779,11 @@ struct macb_queue {
 
 struct macb {
 	void __iomem		*regs;
+	bool			native_io;
+
+	/* hardware IO accessors */
+	u32	(*macb_reg_readl)(struct macb *bp, int offset);
+	void	(*macb_reg_writel)(struct macb *bp, int offset, u32 value);
 
 	unsigned int		rx_tail;
 	unsigned int		rx_prepared_head;
@@ -817,9 +816,9 @@ struct macb {
 
 	struct mii_bus		*mii_bus;
 	struct phy_device	*phy_dev;
-	unsigned int 		link;
-	unsigned int 		speed;
-	unsigned int 		duplex;
+	int 			link;
+	int 			speed;
+	int 			duplex;
 
 	u32			caps;
 	unsigned int		dma_burst_length;
@@ -843,9 +842,4 @@ static inline bool macb_is_gem(struct macb *bp)
 	return !!(bp->caps & MACB_CAPS_MACB_IS_GEM);
 }
 
-static inline bool macb_is_gem_hw(void __iomem *addr)
-{
-	return !!(MACB_BFEXT(IDNUM, readl_relaxed(addr + MACB_MID)) >= 0x2);
-}
-
 #endif /* _MACB_H */
diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h
index dda8a02b7322..8aee250904ec 100644
--- a/drivers/net/ethernet/cavium/thunder/nic.h
+++ b/drivers/net/ethernet/cavium/thunder/nic.h
@@ -125,6 +125,15 @@
  */
 #define NICPF_CLK_PER_INT_TICK		2
 
+/* Time to wait before we decide that a SQ is stuck.
+ *
+ * Since both pkt rx and tx notifications are done with same CQ,
+ * when packets are being received at very high rate (eg: L2 forwarding)
+ * then freeing transmitted skbs will be delayed and watchdog
+ * will kick in, resetting interface. Hence keeping this value high.
+ */
+#define	NICVF_TX_TIMEOUT		(50 * HZ)
+
 struct nicvf_cq_poll {
 	u8	cq_idx;		/* Completion queue index */
 	struct	napi_struct napi;
@@ -216,8 +225,9 @@ struct nicvf_drv_stats {
 	/* Tx */
 	u64 tx_frames_ok;
 	u64 tx_drops;
-	u64 tx_busy;
 	u64 tx_tso;
+	u64 txq_stop;
+	u64 txq_wake;
 };
 
 struct nicvf {
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
index 16bd2d772db9..a4228e664567 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
@@ -66,9 +66,10 @@ static const struct nicvf_stat nicvf_drv_stats[] = {
 	NICVF_DRV_STAT(rx_frames_jumbo),
 	NICVF_DRV_STAT(rx_drops),
 	NICVF_DRV_STAT(tx_frames_ok),
-	NICVF_DRV_STAT(tx_busy),
 	NICVF_DRV_STAT(tx_tso),
 	NICVF_DRV_STAT(tx_drops),
+	NICVF_DRV_STAT(txq_stop),
+	NICVF_DRV_STAT(txq_wake),
 };
 
 static const struct nicvf_stat nicvf_queue_stats[] = {
@@ -126,6 +127,7 @@ static void nicvf_set_msglevel(struct net_device *netdev, u32 lvl)
 
 static void nicvf_get_strings(struct net_device *netdev, u32 sset, u8 *data)
 {
+	struct nicvf *nic = netdev_priv(netdev);
 	int stats, qidx;
 
 	if (sset != ETH_SS_STATS)
@@ -141,7 +143,7 @@ static void nicvf_get_strings(struct net_device *netdev, u32 sset, u8 *data)
 		data += ETH_GSTRING_LEN;
 	}
 
-	for (qidx = 0; qidx < MAX_RCV_QUEUES_PER_QS; qidx++) {
+	for (qidx = 0; qidx < nic->qs->rq_cnt; qidx++) {
 		for (stats = 0; stats < nicvf_n_queue_stats; stats++) {
 			sprintf(data, "rxq%d: %s", qidx,
 				nicvf_queue_stats[stats].name);
@@ -149,7 +151,7 @@ static void nicvf_get_strings(struct net_device *netdev, u32 sset, u8 *data)
 		}
 	}
 
-	for (qidx = 0; qidx < MAX_SND_QUEUES_PER_QS; qidx++) {
+	for (qidx = 0; qidx < nic->qs->sq_cnt; qidx++) {
 		for (stats = 0; stats < nicvf_n_queue_stats; stats++) {
 			sprintf(data, "txq%d: %s", qidx,
 				nicvf_queue_stats[stats].name);
@@ -170,12 +172,14 @@ static void nicvf_get_strings(struct net_device *netdev, u32 sset, u8 *data)
 
 static int nicvf_get_sset_count(struct net_device *netdev, int sset)
 {
+	struct nicvf *nic = netdev_priv(netdev);
+
 	if (sset != ETH_SS_STATS)
 		return -EINVAL;
 
 	return nicvf_n_hw_stats + nicvf_n_drv_stats +
 		(nicvf_n_queue_stats *
-		 (MAX_RCV_QUEUES_PER_QS + MAX_SND_QUEUES_PER_QS)) +
+		 (nic->qs->rq_cnt + nic->qs->sq_cnt)) +
 		BGX_RX_STATS_COUNT + BGX_TX_STATS_COUNT;
 }
 
@@ -197,13 +201,13 @@ static void nicvf_get_ethtool_stats(struct net_device *netdev,
 		*(data++) = ((u64 *)&nic->drv_stats)
 				[nicvf_drv_stats[stat].index];
 
-	for (qidx = 0; qidx < MAX_RCV_QUEUES_PER_QS; qidx++) {
+	for (qidx = 0; qidx < nic->qs->rq_cnt; qidx++) {
 		for (stat = 0; stat < nicvf_n_queue_stats; stat++)
 			*(data++) = ((u64 *)&nic->qs->rq[qidx].stats)
 					[nicvf_queue_stats[stat].index];
 	}
 
-	for (qidx = 0; qidx < MAX_SND_QUEUES_PER_QS; qidx++) {
+	for (qidx = 0; qidx < nic->qs->sq_cnt; qidx++) {
 		for (stat = 0; stat < nicvf_n_queue_stats; stat++)
 			*(data++) = ((u64 *)&nic->qs->sq[qidx].stats)
 					[nicvf_queue_stats[stat].index];
@@ -543,6 +547,7 @@ static int nicvf_set_channels(struct net_device *dev,
 {
 	struct nicvf *nic = netdev_priv(dev);
 	int err = 0;
+	bool if_up = netif_running(dev);
 
 	if (!channel->rx_count || !channel->tx_count)
 		return -EINVAL;
@@ -551,6 +556,9 @@ static int nicvf_set_channels(struct net_device *dev,
 	if (channel->tx_count > MAX_SND_QUEUES_PER_QS)
 		return -EINVAL;
 
+	if (if_up)
+		nicvf_stop(dev);
+
 	nic->qs->rq_cnt = channel->rx_count;
 	nic->qs->sq_cnt = channel->tx_count;
 	nic->qs->cq_cnt = max(nic->qs->rq_cnt, nic->qs->sq_cnt);
@@ -559,11 +567,9 @@ static int nicvf_set_channels(struct net_device *dev,
 	if (err)
 		return err;
 
-	if (!netif_running(dev))
-		return err;
+	if (if_up)
+		nicvf_open(dev);
 
-	nicvf_stop(dev);
-	nicvf_open(dev);
 	netdev_info(dev, "Setting num Tx rings to %d, Rx rings to %d success\n",
 		    nic->qs->sq_cnt, nic->qs->rq_cnt);
 
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 8b119a035b7e..3b90afb8c293 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -234,7 +234,7 @@ static void  nicvf_handle_mbx_intr(struct nicvf *nic)
 				    nic->duplex == DUPLEX_FULL ?
 				"Full duplex" : "Half duplex");
 			netif_carrier_on(nic->netdev);
-			netif_tx_wake_all_queues(nic->netdev);
+			netif_tx_start_all_queues(nic->netdev);
 		} else {
 			netdev_info(nic->netdev, "%s: Link is Down\n",
 				    nic->netdev->name);
@@ -425,6 +425,7 @@ static void nicvf_snd_pkt_handler(struct net_device *netdev,
 	if (skb) {
 		prefetch(skb);
 		dev_consume_skb_any(skb);
+		sq->skbuff[cqe_tx->sqe_ptr] = (u64)NULL;
 	}
 }
 
@@ -476,12 +477,13 @@ static void nicvf_rcv_pkt_handler(struct net_device *netdev,
 static int nicvf_cq_intr_handler(struct net_device *netdev, u8 cq_idx,
 				 struct napi_struct *napi, int budget)
 {
-	int processed_cqe, work_done = 0;
+	int processed_cqe, work_done = 0, tx_done = 0;
 	int cqe_count, cqe_head;
 	struct nicvf *nic = netdev_priv(netdev);
 	struct queue_set *qs = nic->qs;
 	struct cmp_queue *cq = &qs->cq[cq_idx];
 	struct cqe_rx_t *cq_desc;
+	struct netdev_queue *txq;
 
 	spin_lock_bh(&cq->lock);
 loop:
@@ -496,8 +498,8 @@ loop:
 	cqe_head = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_HEAD, cq_idx) >> 9;
 	cqe_head &= 0xFFFF;
 
-	netdev_dbg(nic->netdev, "%s cqe_count %d cqe_head %d\n",
-		   __func__, cqe_count, cqe_head);
+	netdev_dbg(nic->netdev, "%s CQ%d cqe_count %d cqe_head %d\n",
+		   __func__, cq_idx, cqe_count, cqe_head);
 	while (processed_cqe < cqe_count) {
 		/* Get the CQ descriptor */
 		cq_desc = (struct cqe_rx_t *)GET_CQ_DESC(cq, cqe_head);
@@ -511,8 +513,8 @@ loop:
 			break;
 		}
 
-		netdev_dbg(nic->netdev, "cq_desc->cqe_type %d\n",
-			   cq_desc->cqe_type);
+		netdev_dbg(nic->netdev, "CQ%d cq_desc->cqe_type %d\n",
+			   cq_idx, cq_desc->cqe_type);
 		switch (cq_desc->cqe_type) {
 		case CQE_TYPE_RX:
 			nicvf_rcv_pkt_handler(netdev, napi, cq,
@@ -522,6 +524,7 @@ loop:
 		case CQE_TYPE_SEND:
 			nicvf_snd_pkt_handler(netdev, cq,
 					      (void *)cq_desc, CQE_TYPE_SEND);
+			tx_done++;
 		break;
 		case CQE_TYPE_INVALID:
 		case CQE_TYPE_RX_SPLIT:
@@ -532,8 +535,9 @@ loop:
 		}
 		processed_cqe++;
 	}
-	netdev_dbg(nic->netdev, "%s processed_cqe %d work_done %d budget %d\n",
-		   __func__, processed_cqe, work_done, budget);
+	netdev_dbg(nic->netdev,
+		   "%s CQ%d processed_cqe %d work_done %d budget %d\n",
+		   __func__, cq_idx, processed_cqe, work_done, budget);
 
 	/* Ring doorbell to inform H/W to reuse processed CQEs */
 	nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_DOOR,
@@ -543,6 +547,19 @@ loop:
 		goto loop;
 
 done:
+	/* Wakeup TXQ if its stopped earlier due to SQ full */
+	if (tx_done) {
+		txq = netdev_get_tx_queue(netdev, cq_idx);
+		if (netif_tx_queue_stopped(txq)) {
+			netif_tx_start_queue(txq);
+			nic->drv_stats.txq_wake++;
+			if (netif_msg_tx_err(nic))
+				netdev_warn(netdev,
+					    "%s: Transmit queue wakeup SQ%d\n",
+					    netdev->name, cq_idx);
+		}
+	}
+
 	spin_unlock_bh(&cq->lock);
 	return work_done;
 }
@@ -554,15 +571,10 @@ static int nicvf_poll(struct napi_struct *napi, int budget)
 	struct net_device *netdev = napi->dev;
 	struct nicvf *nic = netdev_priv(netdev);
 	struct nicvf_cq_poll *cq;
-	struct netdev_queue *txq;
 
 	cq = container_of(napi, struct nicvf_cq_poll, napi);
 	work_done = nicvf_cq_intr_handler(netdev, cq->cq_idx, napi, budget);
 
-	txq = netdev_get_tx_queue(netdev, cq->cq_idx);
-	if (netif_tx_queue_stopped(txq))
-		netif_tx_wake_queue(txq);
-
 	if (work_done < budget) {
 		/* Slow packet rate, exit polling */
 		napi_complete(napi);
@@ -833,9 +845,9 @@ static netdev_tx_t nicvf_xmit(struct sk_buff *skb, struct net_device *netdev)
 		return NETDEV_TX_OK;
 	}
 
-	if (!nicvf_sq_append_skb(nic, skb) && !netif_tx_queue_stopped(txq)) {
+	if (!netif_tx_queue_stopped(txq) && !nicvf_sq_append_skb(nic, skb)) {
 		netif_tx_stop_queue(txq);
-		nic->drv_stats.tx_busy++;
+		nic->drv_stats.txq_stop++;
 		if (netif_msg_tx_err(nic))
 			netdev_warn(netdev,
 				    "%s: Transmit ring full, stopping SQ%d\n",
@@ -859,7 +871,6 @@ int nicvf_stop(struct net_device *netdev)
 	nicvf_send_msg_to_pf(nic, &mbx);
 
 	netif_carrier_off(netdev);
-	netif_tx_disable(netdev);
 
 	/* Disable RBDR & QS error interrupts */
 	for (qidx = 0; qidx < qs->rbdr_cnt; qidx++) {
@@ -894,6 +905,8 @@ int nicvf_stop(struct net_device *netdev)
 		kfree(cq_poll);
 	}
 
+	netif_tx_disable(netdev);
+
 	/* Free resources */
 	nicvf_config_data_transfer(nic, false);
 
@@ -988,6 +1001,9 @@ int nicvf_open(struct net_device *netdev)
 	for (qidx = 0; qidx < qs->rbdr_cnt; qidx++)
 		nicvf_enable_intr(nic, NICVF_INTR_RBDR, qidx);
 
+	nic->drv_stats.txq_stop = 0;
+	nic->drv_stats.txq_wake = 0;
+
 	netif_carrier_on(netdev);
 	netif_tx_start_all_queues(netdev);
 
@@ -1278,6 +1294,7 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	netdev->hw_features = netdev->features;
 
 	netdev->netdev_ops = &nicvf_netdev_ops;
+	netdev->watchdog_timeo = NICVF_TX_TIMEOUT;
 
 	INIT_WORK(&nic->reset_task, nicvf_reset_task);
 
@@ -1318,11 +1335,17 @@ static void nicvf_remove(struct pci_dev *pdev)
 	pci_disable_device(pdev);
 }
 
+static void nicvf_shutdown(struct pci_dev *pdev)
+{
+	nicvf_remove(pdev);
+}
+
 static struct pci_driver nicvf_driver = {
 	.name = DRV_NAME,
 	.id_table = nicvf_id_table,
 	.probe = nicvf_probe,
 	.remove = nicvf_remove,
+	.shutdown = nicvf_shutdown,
 };
 
 static int __init nicvf_init_module(void)
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index d69d228d11a0..ca4240aa6d15 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -103,9 +103,11 @@ static inline int nicvf_alloc_rcv_buffer(struct nicvf *nic, gfp_t gfp,
 
 	/* Allocate a new page */
 	if (!nic->rb_page) {
-		nic->rb_page = alloc_pages(gfp | __GFP_COMP, order);
+		nic->rb_page = alloc_pages(gfp | __GFP_COMP | __GFP_NOWARN,
+					   order);
 		if (!nic->rb_page) {
-			netdev_err(nic->netdev, "Failed to allocate new rcv buffer\n");
+			netdev_err(nic->netdev,
+				   "Failed to allocate new rcv buffer\n");
 			return -ENOMEM;
 		}
 		nic->rb_page_offset = 0;
@@ -382,7 +384,8 @@ static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq)
 		return;
 
 	if (sq->tso_hdrs)
-		dma_free_coherent(&nic->pdev->dev, sq->dmem.q_len,
+		dma_free_coherent(&nic->pdev->dev,
+				  sq->dmem.q_len * TSO_HEADER_SIZE,
 				  sq->tso_hdrs, sq->tso_hdrs_phys);
 
 	kfree(sq->skbuff);
@@ -863,10 +866,11 @@ void nicvf_sq_free_used_descs(struct net_device *netdev, struct snd_queue *sq,
 			continue;
 		}
 		skb = (struct sk_buff *)sq->skbuff[sq->head];
+		if (skb)
+			dev_kfree_skb_any(skb);
 		atomic64_add(1, (atomic64_t *)&netdev->stats.tx_packets);
 		atomic64_add(hdr->tot_len,
 			     (atomic64_t *)&netdev->stats.tx_bytes);
-		dev_kfree_skb_any(skb);
 		nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1);
 	}
 }
@@ -992,7 +996,7 @@ static inline void nicvf_sq_add_gather_subdesc(struct snd_queue *sq, int qentry,
 
 	memset(gather, 0, SND_QUEUE_DESC_SIZE);
 	gather->subdesc_type = SQ_DESC_TYPE_GATHER;
-	gather->ld_type = NIC_SEND_LD_TYPE_E_LDWB;
+	gather->ld_type = NIC_SEND_LD_TYPE_E_LDD;
 	gather->size = size;
 	gather->addr = data;
 }
@@ -1048,7 +1052,7 @@ static int nicvf_sq_append_tso(struct nicvf *nic, struct snd_queue *sq,
 		}
 		nicvf_sq_add_hdr_subdesc(sq, hdr_qentry,
 					 seg_subdescs - 1, skb, seg_len);
-		sq->skbuff[hdr_qentry] = 0;
+		sq->skbuff[hdr_qentry] = (u64)NULL;
 		qentry = nicvf_get_nxt_sqentry(sq, qentry);
 
 		desc_cnt += seg_subdescs;
@@ -1062,6 +1066,7 @@ static int nicvf_sq_append_tso(struct nicvf *nic, struct snd_queue *sq,
 	/* Inform HW to xmit all TSO segments */
 	nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_DOOR,
 			      skb_get_queue_mapping(skb), desc_cnt);
+	nic->drv_stats.tx_tso++;
 	return 1;
 }
 
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
index 8341bdf755d1..f0937b7bfe9f 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
@@ -62,7 +62,7 @@
 #define SND_QUEUE_CNT		8
 #define CMP_QUEUE_CNT		8 /* Max of RCV and SND qcount */
 
-#define SND_QSIZE		SND_QUEUE_SIZE4
+#define SND_QSIZE		SND_QUEUE_SIZE2
 #define SND_QUEUE_LEN		(1ULL << (SND_QSIZE + 10))
 #define MAX_SND_QUEUE_LEN	(1ULL << (SND_QUEUE_SIZE6 + 10))
 #define SND_QUEUE_THRESH	2ULL
@@ -70,7 +70,10 @@
 /* Since timestamp not enabled, otherwise 2 */
 #define MAX_CQE_PER_PKT_XMIT		1
 
-#define CMP_QSIZE		CMP_QUEUE_SIZE4
+/* Keep CQ and SQ sizes same, if timestamping
+ * is enabled this equation will change.
+ */
+#define CMP_QSIZE		CMP_QUEUE_SIZE2
 #define CMP_QUEUE_LEN		(1ULL << (CMP_QSIZE + 10))
 #define CMP_QUEUE_CQE_THRESH	0
 #define CMP_QUEUE_TIMER_THRESH	220 /* 10usec */
@@ -87,7 +90,12 @@
 
 #define MAX_CQES_FOR_TX		((SND_QUEUE_LEN / MIN_SQ_DESC_PER_PKT_XMIT) * \
 				 MAX_CQE_PER_PKT_XMIT)
-#define RQ_CQ_DROP		((CMP_QUEUE_LEN - MAX_CQES_FOR_TX) / 256)
+/* Calculate number of CQEs to reserve for all SQEs.
+ * Its 1/256th level of CQ size.
+ * '+ 1' to account for pipelining
+ */
+#define RQ_CQ_DROP		((256 / (CMP_QUEUE_LEN / \
+				 (CMP_QUEUE_LEN - MAX_CQES_FOR_TX))) + 1)
 
 /* Descriptor size in bytes */
 #define SND_QUEUE_DESC_SIZE	16
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 633ec05dfe05..b961a89dc626 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -673,7 +673,10 @@ static void bgx_lmac_disable(struct bgx *bgx, u8 lmacid)
 	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cmrx_cfg);</