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

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

10 files changed, 156 insertions, 74 deletions

diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index ce2ea2d491ac..2ffe76c0ff74 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -474,7 +474,7 @@ struct mac_device_info;
 /* Helpers to program the MAC core */
 struct stmmac_ops {
 	/* MAC core initialization */
-	void (*core_init)(struct mac_device_info *hw, int mtu);
+	void (*core_init)(struct mac_device_info *hw, struct net_device *dev);
 	/* Enable the MAC RX/TX */
 	void (*set_mac)(void __iomem *ioaddr, bool enable);
 	/* Enable and verify that the IPC module is supported */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
index 4404650b32c5..5270d26f0bc6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
@@ -40,9 +40,7 @@
 #define PRG_ETH0_CLK_M250_DIV_SHIFT	7
 #define PRG_ETH0_CLK_M250_DIV_WIDTH	3
 
-/* divides the result of m25_sel by either 5 (bit unset) or 10 (bit set) */
-#define PRG_ETH0_CLK_M25_DIV_SHIFT	10
-#define PRG_ETH0_CLK_M25_DIV_WIDTH	1
+#define PRG_ETH0_RGMII_TX_CLK_EN	10
 
 #define PRG_ETH0_INVERTED_RMII_CLK	BIT(11)
 #define PRG_ETH0_TX_AND_PHY_REF_CLK	BIT(12)
@@ -63,8 +61,11 @@ struct meson8b_dwmac {
 	struct clk_divider	m250_div;
 	struct clk		*m250_div_clk;
 
-	struct clk_divider	m25_div;
-	struct clk		*m25_div_clk;
+	struct clk_fixed_factor	fixed_div2;
+	struct clk		*fixed_div2_clk;
+
+	struct clk_gate		rgmii_tx_en;
+	struct clk		*rgmii_tx_en_clk;
 
 	u32			tx_delay_ns;
 };
@@ -81,7 +82,7 @@ static void meson8b_dwmac_mask_bits(struct meson8b_dwmac *dwmac, u32 reg,
 	writel(data, dwmac->regs + reg);
 }
 
-static int meson8b_init_clk(struct meson8b_dwmac *dwmac)
+static int meson8b_init_rgmii_tx_clk(struct meson8b_dwmac *dwmac)
 {
 	struct clk_init_data init;
 	int i, ret;
@@ -89,11 +90,6 @@ static int meson8b_init_clk(struct meson8b_dwmac *dwmac)
 	char clk_name[32];
 	const char *clk_div_parents[1];
 	const char *mux_parent_names[MUX_CLK_NUM_PARENTS];
-	static const struct clk_div_table clk_25m_div_table[] = {
-		{ .val = 0, .div = 5 },
-		{ .val = 1, .div = 10 },
-		{ /* sentinel */ },
-	};
 
 	/* get the mux parents from DT */
 	for (i = 0; i < MUX_CLK_NUM_PARENTS; i++) {
@@ -116,7 +112,7 @@ static int meson8b_init_clk(struct meson8b_dwmac *dwmac)
 	snprintf(clk_name, sizeof(clk_name), "%s#m250_sel", dev_name(dev));
 	init.name = clk_name;
 	init.ops = &clk_mux_ops;
-	init.flags = 0;
+	init.flags = CLK_SET_RATE_PARENT;
 	init.parent_names = mux_parent_names;
 	init.num_parents = MUX_CLK_NUM_PARENTS;
 
@@ -144,31 +140,48 @@ static int meson8b_init_clk(struct meson8b_dwmac *dwmac)
 	dwmac->m250_div.shift = PRG_ETH0_CLK_M250_DIV_SHIFT;
 	dwmac->m250_div.width = PRG_ETH0_CLK_M250_DIV_WIDTH;
 	dwmac->m250_div.hw.init = &init;
-	dwmac->m250_div.flags = CLK_DIVIDER_ONE_BASED | CLK_DIVIDER_ALLOW_ZERO;
+	dwmac->m250_div.flags = CLK_DIVIDER_ONE_BASED |
+				CLK_DIVIDER_ALLOW_ZERO |
+				CLK_DIVIDER_ROUND_CLOSEST;
 
 	dwmac->m250_div_clk = devm_clk_register(dev, &dwmac->m250_div.hw);
 	if (WARN_ON(IS_ERR(dwmac->m250_div_clk)))
 		return PTR_ERR(dwmac->m250_div_clk);
 
-	/* create the m25_div */
-	snprintf(clk_name, sizeof(clk_name), "%s#m25_div", dev_name(dev));
+	/* create the fixed_div2 */
+	snprintf(clk_name, sizeof(clk_name), "%s#fixed_div2", dev_name(dev));
 	init.name = devm_kstrdup(dev, clk_name, GFP_KERNEL);
-	init.ops = &clk_divider_ops;
-	init.flags = CLK_IS_BASIC | CLK_SET_RATE_PARENT;
+	init.ops = &clk_fixed_factor_ops;
+	init.flags = CLK_SET_RATE_PARENT;
 	clk_div_parents[0] = __clk_get_name(dwmac->m250_div_clk);
 	init.parent_names = clk_div_parents;
 	init.num_parents = ARRAY_SIZE(clk_div_parents);
 
-	dwmac->m25_div.reg = dwmac->regs + PRG_ETH0;
-	dwmac->m25_div.shift = PRG_ETH0_CLK_M25_DIV_SHIFT;
-	dwmac->m25_div.width = PRG_ETH0_CLK_M25_DIV_WIDTH;
-	dwmac->m25_div.table = clk_25m_div_table;
-	dwmac->m25_div.hw.init = &init;
-	dwmac->m25_div.flags = CLK_DIVIDER_ALLOW_ZERO;
+	dwmac->fixed_div2.mult = 1;
+	dwmac->fixed_div2.div = 2;
+	dwmac->fixed_div2.hw.init = &init;
 
-	dwmac->m25_div_clk = devm_clk_register(dev, &dwmac->m25_div.hw);
-	if (WARN_ON(IS_ERR(dwmac->m25_div_clk)))
-		return PTR_ERR(dwmac->m25_div_clk);
+	dwmac->fixed_div2_clk = devm_clk_register(dev, &dwmac->fixed_div2.hw);
+	if (WARN_ON(IS_ERR(dwmac->fixed_div2_clk)))
+		return PTR_ERR(dwmac->fixed_div2_clk);
+
+	/* create the rgmii_tx_en */
+	init.name = devm_kasprintf(dev, GFP_KERNEL, "%s#rgmii_tx_en",
+				   dev_name(dev));
+	init.ops = &clk_gate_ops;
+	init.flags = CLK_SET_RATE_PARENT;
+	clk_div_parents[0] = __clk_get_name(dwmac->fixed_div2_clk);
+	init.parent_names = clk_div_parents;
+	init.num_parents = ARRAY_SIZE(clk_div_parents);
+
+	dwmac->rgmii_tx_en.reg = dwmac->regs + PRG_ETH0;
+	dwmac->rgmii_tx_en.bit_idx = PRG_ETH0_RGMII_TX_CLK_EN;
+	dwmac->rgmii_tx_en.hw.init = &init;
+
+	dwmac->rgmii_tx_en_clk = devm_clk_register(dev,
+						   &dwmac->rgmii_tx_en.hw);
+	if (WARN_ON(IS_ERR(dwmac->rgmii_tx_en_clk)))
+		return PTR_ERR(dwmac->rgmii_tx_en_clk);
 
 	return 0;
 }
@@ -176,7 +189,6 @@ static int meson8b_init_clk(struct meson8b_dwmac *dwmac)
 static int meson8b_init_prg_eth(struct meson8b_dwmac *dwmac)
 {
 	int ret;
-	unsigned long clk_rate;
 	u8 tx_dly_val = 0;
 
 	switch (dwmac->phy_mode) {
@@ -191,9 +203,6 @@ static int meson8b_init_prg_eth(struct meson8b_dwmac *dwmac)
 
 	case PHY_INTERFACE_MODE_RGMII_ID:
 	case PHY_INTERFACE_MODE_RGMII_TXID:
-		/* Generate a 25MHz clock for the PHY */
-		clk_rate = 25 * 1000 * 1000;
-
 		/* enable RGMII mode */
 		meson8b_dwmac_mask_bits(dwmac, PRG_ETH0, PRG_ETH0_RGMII_MODE,
 					PRG_ETH0_RGMII_MODE);
@@ -204,12 +213,28 @@ static int meson8b_init_prg_eth(struct meson8b_dwmac *dwmac)
 
 		meson8b_dwmac_mask_bits(dwmac, PRG_ETH0, PRG_ETH0_TXDLY_MASK,
 					tx_dly_val << PRG_ETH0_TXDLY_SHIFT);
+
+		/* Configure the 125MHz RGMII TX clock, the IP block changes
+		 * the output automatically (= without us having to configure
+		 * a register) based on the line-speed (125MHz for Gbit speeds,
+		 * 25MHz for 100Mbit/s and 2.5MHz for 10Mbit/s).
+		 */
+		ret = clk_set_rate(dwmac->rgmii_tx_en_clk, 125 * 1000 * 1000);
+		if (ret) {
+			dev_err(&dwmac->pdev->dev,
+				"failed to set RGMII TX clock\n");
+			return ret;
+		}
+
+		ret = clk_prepare_enable(dwmac->rgmii_tx_en_clk);
+		if (ret) {
+			dev_err(&dwmac->pdev->dev,
+				"failed to enable the RGMII TX clock\n");
+			return ret;
+		}
 		break;
 
 	case PHY_INTERFACE_MODE_RMII:
-		/* Use the rate of the mux clock for the internal RMII PHY */
-		clk_rate = clk_get_rate(dwmac->m250_mux_clk);
-
 		/* disable RGMII mode -> enables RMII mode */
 		meson8b_dwmac_mask_bits(dwmac, PRG_ETH0, PRG_ETH0_RGMII_MODE,
 					0);
@@ -231,20 +256,6 @@ static int meson8b_init_prg_eth(struct meson8b_dwmac *dwmac)
 		return -EINVAL;
 	}
 
-	ret = clk_prepare_enable(dwmac->m25_div_clk);
-	if (ret) {
-		dev_err(&dwmac->pdev->dev, "failed to enable the PHY clock\n");
-		return ret;
-	}
-
-	ret = clk_set_rate(dwmac->m25_div_clk, clk_rate);
-	if (ret) {
-		clk_disable_unprepare(dwmac->m25_div_clk);
-
-		dev_err(&dwmac->pdev->dev, "failed to set PHY clock\n");
-		return ret;
-	}
-
 	/* enable TX_CLK and PHY_REF_CLK generator */
 	meson8b_dwmac_mask_bits(dwmac, PRG_ETH0, PRG_ETH0_TX_AND_PHY_REF_CLK,
 				PRG_ETH0_TX_AND_PHY_REF_CLK);
@@ -294,7 +305,7 @@ static int meson8b_dwmac_probe(struct platform_device *pdev)
 				 &dwmac->tx_delay_ns))
 		dwmac->tx_delay_ns = 2;
 
-	ret = meson8b_init_clk(dwmac);
+	ret = meson8b_init_rgmii_tx_clk(dwmac);
 	if (ret)
 		goto err_remove_config_dt;
 
@@ -311,7 +322,8 @@ static int meson8b_dwmac_probe(struct platform_device *pdev)
 	return 0;
 
 err_clk_disable:
-	clk_disable_unprepare(dwmac->m25_div_clk);
+	if (phy_interface_mode_is_rgmii(dwmac->phy_mode))
+		clk_disable_unprepare(dwmac->rgmii_tx_en_clk);
 err_remove_config_dt:
 	stmmac_remove_config_dt(pdev, plat_dat);
 
@@ -322,7 +334,8 @@ static int meson8b_dwmac_remove(struct platform_device *pdev)
 {
 	struct meson8b_dwmac *dwmac = get_stmmac_bsp_priv(&pdev->dev);
 
-	clk_disable_unprepare(dwmac->m25_div_clk);
+	if (phy_interface_mode_is_rgmii(dwmac->phy_mode))
+		clk_disable_unprepare(dwmac->rgmii_tx_en_clk);
 
 	return stmmac_pltfr_remove(pdev);
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index 9eb7f65d8000..a3fa65b1ca8e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -483,7 +483,8 @@ static int sun8i_dwmac_init(struct platform_device *pdev, void *priv)
 	return 0;
 }
 
-static void sun8i_dwmac_core_init(struct mac_device_info *hw, int mtu)
+static void sun8i_dwmac_core_init(struct mac_device_info *hw,
+				  struct net_device *dev)
 {
 	void __iomem *ioaddr = hw->pcsr;
 	u32 v;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index 8a86340ff2d3..540d21786a43 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -25,18 +25,28 @@
 #include <linux/crc32.h>
 #include <linux/slab.h>
 #include <linux/ethtool.h>
+#include <net/dsa.h>
 #include <asm/io.h>
 #include "stmmac_pcs.h"
 #include "dwmac1000.h"
 
-static void dwmac1000_core_init(struct mac_device_info *hw, int mtu)
+static void dwmac1000_core_init(struct mac_device_info *hw,
+				struct net_device *dev)
 {
 	void __iomem *ioaddr = hw->pcsr;
 	u32 value = readl(ioaddr + GMAC_CONTROL);
+	int mtu = dev->mtu;
 
 	/* Configure GMAC core */
 	value |= GMAC_CORE_INIT;
 
+	/* Clear ACS bit because Ethernet switch tagging formats such as
+	 * Broadcom tags can look like invalid LLC/SNAP packets and cause the
+	 * hardware to truncate packets on reception.
+	 */
+	if (netdev_uses_dsa(dev))
+		value &= ~GMAC_CONTROL_ACS;
+
 	if (mtu > 1500)
 		value |= GMAC_CONTROL_2K;
 	if (mtu > 2000)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
index 8ef517356313..91b23f9db31a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
@@ -25,15 +25,26 @@
 *******************************************************************************/
 
 #include <linux/crc32.h>
+#include <net/dsa.h>
 #include <asm/io.h>
 #include "dwmac100.h"
 
-static void dwmac100_core_init(struct mac_device_info *hw, int mtu)
+static void dwmac100_core_init(struct mac_device_info *hw,
+			       struct net_device *dev)
 {
 	void __iomem *ioaddr = hw->pcsr;
 	u32 value = readl(ioaddr + MAC_CONTROL);
 
-	writel((value | MAC_CORE_INIT), ioaddr + MAC_CONTROL);
+	value |= MAC_CORE_INIT;
+
+	/* Clear ASTP bit because Ethernet switch tagging formats such as
+	 * Broadcom tags can look like invalid LLC/SNAP packets and cause the
+	 * hardware to truncate packets on reception.
+	 */
+	if (netdev_uses_dsa(dev))
+		value &= ~MAC_CONTROL_ASTP;
+
+	writel(value, ioaddr + MAC_CONTROL);
 
 #ifdef STMMAC_VLAN_TAG_USED
 	writel(ETH_P_8021Q, ioaddr + MAC_VLAN1);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index f3ed8f7853eb..ed222b20fcf1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -17,16 +17,26 @@
 #include <linux/slab.h>
 #include <linux/ethtool.h>
 #include <linux/io.h>
+#include <net/dsa.h>
 #include "stmmac_pcs.h"
 #include "dwmac4.h"
 
-static void dwmac4_core_init(struct mac_device_info *hw, int mtu)
+static void dwmac4_core_init(struct mac_device_info *hw,
+			     struct net_device *dev)
 {
 	void __iomem *ioaddr = hw->pcsr;
 	u32 value = readl(ioaddr + GMAC_CONFIG);
+	int mtu = dev->mtu;
 
 	value |= GMAC_CORE_INIT;
 
+	/* Clear ACS bit because Ethernet switch tagging formats such as
+	 * Broadcom tags can look like invalid LLC/SNAP packets and cause the
+	 * hardware to truncate packets on reception.
+	 */
+	if (netdev_uses_dsa(dev))
+		value &= ~GMAC_CONFIG_ACS;
+
 	if (mtu > 1500)
 		value |= GMAC_CONFIG_2K;
 	if (mtu > 2000)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
index 7e089bf906b4..c728ffa095de 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
@@ -334,7 +334,7 @@ static void dwmac4_rd_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
 	if (tx_own)
 		tdes3 |= TDES3_OWN;
 
-	if (is_fs & tx_own)
+	if (is_fs && tx_own)
 		/* When the own bit, for the first frame, has to be set, all
 		 * descriptors for the same frame has to be set before, to
 		 * avoid race condition.
@@ -377,7 +377,7 @@ static void dwmac4_rd_prepare_tso_tx_desc(struct dma_desc *p, int is_fs,
 	if (tx_own)
 		tdes3 |= TDES3_OWN;
 
-	if (is_fs & tx_own)
+	if (is_fs && tx_own)
 		/* When the own bit, for the first frame, has to be set, all
 		 * descriptors for the same frame has to be set before, to
 		 * avoid race condition.
@@ -406,7 +406,7 @@ static void dwmac4_display_ring(void *head, unsigned int size, bool rx)
 	pr_info("%s descriptor ring:\n", rx ? "RX" : "TX");
 
 	for (i = 0; i < size; i++) {
-		pr_info("%d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
+		pr_info("%03d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
 			i, (unsigned int)virt_to_phys(p),
 			le32_to_cpu(p->des0), le32_to_cpu(p->des1),
 			le32_to_cpu(p->des2), le32_to_cpu(p->des3));
diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
index 2a828a312814..6768a25b6aa0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
@@ -341,7 +341,7 @@ static void enh_desc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
 	if (tx_own)
 		tdes0 |= ETDES0_OWN;
 
-	if (is_fs & tx_own)
+	if (is_fs && tx_own)
 		/* When the own bit, for the first frame, has to be set, all
 		 * descriptors for the same frame has to be set before, to
 		 * avoid race condition.
@@ -428,7 +428,7 @@ static void enh_desc_display_ring(void *head, unsigned int size, bool rx)
 		u64 x;
 
 		x = *(u64 *)ep;
-		pr_info("%d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
+		pr_info("%03d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
 			i, (unsigned int)virt_to_phys(ep),
 			(unsigned int)x, (unsigned int)(x >> 32),
 			ep->basic.des2, ep->basic.des3);
diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
index db4cee57bb24..ebd9e5e00f16 100644
--- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
@@ -288,7 +288,7 @@ static void ndesc_display_ring(void *head, unsigned int size, bool rx)
 		u64 x;
 
 		x = *(u64 *)p;
-		pr_info("%d [0x%x]: 0x%x 0x%x 0x%x 0x%x",
+		pr_info("%03d [0x%x]: 0x%x 0x%x 0x%x 0x%x",
 			i, (unsigned int)virt_to_phys(p),
 			(unsigned int)x, (unsigned int)(x >> 32),
 			p->des2, p->des3);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index c0af0bc4e714..7ad841434ec8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2003,22 +2003,60 @@ static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode,
 static void stmmac_dma_interrupt(struct stmmac_priv *priv)
 {
 	u32 tx_channel_count = priv->plat->tx_queues_to_use;
-	int status;
+	u32 rx_channel_count = priv->plat->rx_queues_to_use;
+	u32 channels_to_check = tx_channel_count > rx_channel_count ?
+				tx_channel_count : rx_channel_count;
 	u32 chan;
+	bool poll_scheduled = false;
+	int status[channels_to_check];
+
+	/* Each DMA channel can be used for rx and tx simultaneously, yet
+	 * napi_struct is embedded in struct stmmac_rx_queue rather than in a
+	 * stmmac_channel struct.
+	 * Because of this, stmmac_poll currently checks (and possibly wakes)
+	 * all tx queues rather than just a single tx queue.
+	 */
+	for (chan = 0; chan < channels_to_check; chan++)
+		status[chan] = priv->hw->dma->dma_interrupt(priv->ioaddr,
+							    &priv->xstats,
+							    chan);
 
-	for (chan = 0; chan < tx_channel_count; chan++) {
-		struct stmmac_rx_queue *rx_q = &priv->rx_queue[chan];
+	for (chan = 0; chan < rx_channel_count; chan++) {
+		if (likely(status[chan] & handle_rx)) {
+			struct stmmac_rx_queue *rx_q = &priv->rx_queue[chan];
 
-		status = priv->hw->dma->dma_interrupt(priv->ioaddr,
-						      &priv->xstats, chan);
-		if (likely((status & handle_rx)) || (status & handle_tx)) {
 			if (likely(napi_schedule_prep(&rx_q->napi))) {
 				stmmac_disable_dma_irq(priv, chan);
 				__napi_schedule(&rx_q->napi);
+				poll_scheduled = true;
+			}
+		}
+	}
+
+	/* If we scheduled poll, we already know that tx queues will be checked.
+	 * If we didn't schedule poll, see if any DMA channel (used by tx) has a
+	 * completed transmission, if so, call stmmac_poll (once).
+	 */
+	if (!poll_scheduled) {
+		for (chan = 0; chan < tx_channel_count; chan++) {
+			if (status[chan] & handle_tx) {
+				/* It doesn't matter what rx queue we choose
+				 * here. We use 0 since it always exists.
+				 */
+				struct stmmac_rx_queue *rx_q =
+					&priv->rx_queue[0];
+
+				if (likely(napi_schedule_prep(&rx_q->napi))) {
+					stmmac_disable_dma_irq(priv, chan);
+					__napi_schedule(&rx_q->napi);
+				}
+				break;
 			}
 		}
+	}
 
-		if (unlikely(status & tx_hard_error_bump_tc)) {
+	for (chan = 0; chan < tx_channel_count; chan++) {
+		if (unlikely(status[chan] & tx_hard_error_bump_tc)) {
 			/* Try to bump up the dma threshold on this failure */
 			if (unlikely(priv->xstats.threshold != SF_DMA_MODE) &&
 			    (tc <= 256)) {
@@ -2035,7 +2073,7 @@ static void stmmac_dma_interrupt(struct stmmac_priv *priv)
 								    chan);
 				priv->xstats.threshold = tc;
 			}
-		} else if (unlikely(status == tx_hard_error)) {
+		} else if (unlikely(status[chan] == tx_hard_error)) {
 			stmmac_tx_err(priv, chan);
 		}
 	}
@@ -2489,7 +2527,7 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
 	}
 
 	/* Initialize the MAC Core */
-	priv->hw->mac->core_init(priv->hw, dev->mtu);
+	priv->hw->mac->core_init(priv->hw, dev);
 
 	/* Initialize MTL*/
 	if (priv->synopsys_id >= DWMAC_CORE_4_00)
@@ -3404,9 +3442,8 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 			if (netif_msg_rx_status(priv)) {
 				netdev_dbg(priv->dev, "\tdesc: %p [entry %d] buff=0x%x\n",
 					   p, entry, des);
-				if (frame_len > ETH_FRAME_LEN)
-					netdev_dbg(priv->dev, "frame size %d, COE: %d\n",
-						   frame_len, status);
+				netdev_dbg(priv->dev, "frame size %d, COE: %d\n",
+					   frame_len, status);
 			}
 
 			/* The zero-copy is always used for all the sizes