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

Pull networking fixes from David Miller:
 "A little more than usual this time around. Been travelling, so that is
  part of it.

  Anyways, here are the highlights:

   1) Deal with memcontrol races wrt. listener dismantle, from Eric
      Dumazet.

   2) Handle page allocation failures properly in nfp driver, from Jaku
      Kicinski.

   3) Fix memory leaks in macsec, from Sabrina Dubroca.

   4) Fix crashes in pppol2tp_session_ioctl(), from Guillaume Nault.

   5) Several fixes in bnxt_en driver, including preventing potential
      NVRAM parameter corruption from Michael Chan.

   6) Fix for KRACK attacks in wireless, from Johannes Berg.

   7) rtnetlink event generation fixes from Xin Long.

   8) Deadlock in mlxsw driver, from Ido Schimmel.

   9) Disallow arithmetic operations on context pointers in bpf, from
      Jakub Kicinski.

  10) Missing sock_owned_by_user() check in sctp_icmp_redirect(), from
      Xin Long.

  11) Only TCP is supported for sockmap, make that explicit with a
      check, from John Fastabend.

  12) Fix IP options state races in DCCP and TCP, from Eric Dumazet.

  13) Fix panic in packet_getsockopt(), also from Eric Dumazet.

  14) Add missing locked in hv_sock layer, from Dexuan Cui.

  15) Various aquantia bug fixes, including several statistics handling
      cures. From Igor Russkikh et al.

  16) Fix arithmetic overflow in devmap code, from John Fastabend.

  17) Fix busted socket memory accounting when we get a fault in the tcp
      zero copy paths. From Willem de Bruijn.

  18) Don't leave opt->tot_len uninitialized in ipv6, from Eric Dumazet"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (106 commits)
  stmmac: Don't access tx_q->dirty_tx before netif_tx_lock
  ipv6: flowlabel: do not leave opt->tot_len with garbage
  of_mdio: Fix broken PHY IRQ in case of probe deferral
  textsearch: fix typos in library helpers
  rxrpc: Don't release call mutex on error pointer
  net: stmmac: Prevent infinite loop in get_rx_timestamp_status()
  net: stmmac: Fix stmmac_get_rx_hwtstamp()
  net: stmmac: Add missing call to dev_kfree_skb()
  mlxsw: spectrum_router: Configure TIGCR on init
  mlxsw: reg: Add Tunneling IPinIP General Configuration Register
  net: ethtool: remove error check for legacy setting transceiver type
  soreuseport: fix initialization race
  net: bridge: fix returning of vlan range op errors
  sock: correct sk_wmem_queued accounting on efault in tcp zerocopy
  bpf: add test cases to bpf selftests to cover all access tests
  bpf: fix pattern matches for direct packet access
  bpf: fix off by one for range markings with L{T, E} patterns
  bpf: devmap fix arithmetic overflow in bitmap_size calculation
  net: aquantia: Bad udp rate on default interrupt coalescing
  net: aquantia: Enable coalescing management via ethtool interface
  ...

drivers/net/can/flexcan.c

@@ -182,22 +182,23 @@
 /* FLEXCAN hardware feature flags
  *
  * Below is some version info we got:
- *    SOC   Version   IP-Version  Glitch- [TR]WRN_INT Memory err RTR re-
- *                                Filter? connected?  detection  ception in MB
- *   MX25  FlexCAN2  03.00.00.00     no        no         no        no
- *   MX28  FlexCAN2  03.00.04.00    yes       yes         no        no
- *   MX35  FlexCAN2  03.00.00.00     no        no         no        no
- *   MX53  FlexCAN2  03.00.00.00    yes        no         no        no
- *   MX6s  FlexCAN3  10.00.12.00    yes       yes         no       yes
- *   VF610 FlexCAN3  ?               no       yes        yes       yes?
+ *    SOC   Version   IP-Version  Glitch- [TR]WRN_INT IRQ Err Memory err RTR re-
+ *                                Filter? connected?  Passive detection  ception in MB
+ *   MX25  FlexCAN2  03.00.00.00     no        no         ?       no        no
+ *   MX28  FlexCAN2  03.00.04.00    yes       yes        no       no        no
+ *   MX35  FlexCAN2  03.00.00.00     no        no         ?       no        no
+ *   MX53  FlexCAN2  03.00.00.00    yes        no        no       no        no
+ *   MX6s  FlexCAN3  10.00.12.00    yes       yes        no       no       yes
+ *   VF610 FlexCAN3  ?               no       yes         ?      yes       yes?
  *
  * Some SOCs do not have the RX_WARN & TX_WARN interrupt line connected.
  */
-#define FLEXCAN_QUIRK_BROKEN_ERR_STATE	BIT(1) /* [TR]WRN_INT not connected */
+#define FLEXCAN_QUIRK_BROKEN_WERR_STATE	BIT(1) /* [TR]WRN_INT not connected */
 #define FLEXCAN_QUIRK_DISABLE_RXFG	BIT(2) /* Disable RX FIFO Global mask */
 #define FLEXCAN_QUIRK_ENABLE_EACEN_RRS	BIT(3) /* Enable EACEN and RRS bit in ctrl2 */
 #define FLEXCAN_QUIRK_DISABLE_MECR	BIT(4) /* Disable Memory error detection */
 #define FLEXCAN_QUIRK_USE_OFF_TIMESTAMP	BIT(5) /* Use timestamp based offloading */
+#define FLEXCAN_QUIRK_BROKEN_PERR_STATE	BIT(6) /* No interrupt for error passive */
 
 /* Structure of the message buffer */
 struct flexcan_mb {
@@ -281,14 +282,17 @@ struct flexcan_priv {
 };
 
 static const struct flexcan_devtype_data fsl_p1010_devtype_data = {
-	.quirks = FLEXCAN_QUIRK_BROKEN_ERR_STATE,
+	.quirks = FLEXCAN_QUIRK_BROKEN_WERR_STATE |
+		FLEXCAN_QUIRK_BROKEN_PERR_STATE,
 };
 
-static const struct flexcan_devtype_data fsl_imx28_devtype_data;
+static const struct flexcan_devtype_data fsl_imx28_devtype_data = {
+	.quirks = FLEXCAN_QUIRK_BROKEN_PERR_STATE,
+};
 
 static const struct flexcan_devtype_data fsl_imx6q_devtype_data = {
 	.quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS |
-		FLEXCAN_QUIRK_USE_OFF_TIMESTAMP,
+		FLEXCAN_QUIRK_USE_OFF_TIMESTAMP | FLEXCAN_QUIRK_BROKEN_PERR_STATE,
 };
 
 static const struct flexcan_devtype_data fsl_vf610_devtype_data = {
@@ -335,6 +339,22 @@ static inline void flexcan_write(u32 val, void __iomem *addr)
 }
 #endif
 
+static inline void flexcan_error_irq_enable(const struct flexcan_priv *priv)
+{
+	struct flexcan_regs __iomem *regs = priv->regs;
+	u32 reg_ctrl = (priv->reg_ctrl_default | FLEXCAN_CTRL_ERR_MSK);
+
+	flexcan_write(reg_ctrl, &regs->ctrl);
+}
+
+static inline void flexcan_error_irq_disable(const struct flexcan_priv *priv)
+{
+	struct flexcan_regs __iomem *regs = priv->regs;
+	u32 reg_ctrl = (priv->reg_ctrl_default & ~FLEXCAN_CTRL_ERR_MSK);
+
+	flexcan_write(reg_ctrl, &regs->ctrl);
+}
+
 static inline int flexcan_transceiver_enable(const struct flexcan_priv *priv)
 {
 	if (!priv->reg_xceiver)
@@ -713,6 +733,7 @@ static irqreturn_t flexcan_irq(int irq, void *dev_id)
 	struct flexcan_regs __iomem *regs = priv->regs;
 	irqreturn_t handled = IRQ_NONE;
 	u32 reg_iflag1, reg_esr;
+	enum can_state last_state = priv->can.state;
 
 	reg_iflag1 = flexcan_read(&regs->iflag1);
 
@@ -765,8 +786,10 @@ static irqreturn_t flexcan_irq(int irq, void *dev_id)
 		flexcan_write(reg_esr & FLEXCAN_ESR_ALL_INT, &regs->esr);
 	}
 
-	/* state change interrupt */
-	if (reg_esr & FLEXCAN_ESR_ERR_STATE)
+	/* state change interrupt or broken error state quirk fix is enabled */
+	if ((reg_esr & FLEXCAN_ESR_ERR_STATE) ||
+	    (priv->devtype_data->quirks & (FLEXCAN_QUIRK_BROKEN_WERR_STATE |
+	                                   FLEXCAN_QUIRK_BROKEN_PERR_STATE)))
 		flexcan_irq_state(dev, reg_esr);
 
 	/* bus error IRQ - handle if bus error reporting is activated */
@@ -774,6 +797,44 @@ static irqreturn_t flexcan_irq(int irq, void *dev_id)
 	    (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING))
 		flexcan_irq_bus_err(dev, reg_esr);
 
+	/* availability of error interrupt among state transitions in case
+	 * bus error reporting is de-activated and
+	 * FLEXCAN_QUIRK_BROKEN_PERR_STATE is enabled:
+	 *  +--------------------------------------------------------------+
+	 *  | +----------------------------------------------+ [stopped /  |
+	 *  | |                                              |  sleeping] -+
+	 *  +-+-> active <-> warning <-> passive -> bus off -+
+	 *        ___________^^^^^^^^^^^^_______________________________
+	 *        disabled(1)  enabled             disabled
+	 *
+	 * (1): enabled if FLEXCAN_QUIRK_BROKEN_WERR_STATE is enabled
+	 */
+	if ((last_state != priv->can.state) &&
+	    (priv->devtype_data->quirks & FLEXCAN_QUIRK_BROKEN_PERR_STATE) &&
+	    !(priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING)) {
+		switch (priv->can.state) {
+		case CAN_STATE_ERROR_ACTIVE:
+			if (priv->devtype_data->quirks &
+			    FLEXCAN_QUIRK_BROKEN_WERR_STATE)
+				flexcan_error_irq_enable(priv);
+			else
+				flexcan_error_irq_disable(priv);
+			break;
+
+		case CAN_STATE_ERROR_WARNING:
+			flexcan_error_irq_enable(priv);
+			break;
+
+		case CAN_STATE_ERROR_PASSIVE:
+		case CAN_STATE_BUS_OFF:
+			flexcan_error_irq_disable(priv);
+			break;
+
+		default:
+			break;
+		}
+	}
+
 	return handled;
 }
 
@@ -887,7 +948,7 @@ static int flexcan_chip_start(struct net_device *dev)
 	 * on most Flexcan cores, too. Otherwise we don't get
 	 * any error warning or passive interrupts.
 	 */
-	if (priv->devtype_data->quirks & FLEXCAN_QUIRK_BROKEN_ERR_STATE ||
+	if (priv->devtype_data->quirks & FLEXCAN_QUIRK_BROKEN_WERR_STATE ||
 	    priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING)
 		reg_ctrl |= FLEXCAN_CTRL_ERR_MSK;
 	else

drivers/net/can/usb/esd_usb2.c

@@ -333,7 +333,7 @@ static void esd_usb2_rx_can_msg(struct esd_usb2_net_priv *priv,
 		}
 
 		cf->can_id = id & ESD_IDMASK;
-		cf->can_dlc = get_can_dlc(msg->msg.rx.dlc);
+		cf->can_dlc = get_can_dlc(msg->msg.rx.dlc & ~ESD_RTR);
 
 		if (id & ESD_EXTID)
 			cf->can_id |= CAN_EFF_FLAG;

drivers/net/can/usb/gs_usb.c

@@ -375,6 +375,8 @@ static void gs_usb_receive_bulk_callback(struct urb *urb)
 
 		gs_free_tx_context(txc);
 
+		atomic_dec(&dev->active_tx_urbs);
+
 		netif_wake_queue(netdev);
 	}
 
@@ -463,14 +465,6 @@ static void gs_usb_xmit_callback(struct urb *urb)
 			  urb->transfer_buffer_length,
 			  urb->transfer_buffer,
 			  urb->transfer_dma);
-
-	atomic_dec(&dev->active_tx_urbs);
-
-	if (!netif_device_present(netdev))
-		return;
-
-	if (netif_queue_stopped(netdev))
-		netif_wake_queue(netdev);
 }
 
 static netdev_tx_t gs_can_start_xmit(struct sk_buff *skb,

drivers/net/dsa/mv88e6060.c

@@ -214,8 +214,14 @@ static int mv88e6060_setup(struct dsa_switch *ds)
 
 static int mv88e6060_set_addr(struct dsa_switch *ds, u8 *addr)
 {
-	/* Use the same MAC Address as FD Pause frames for all ports */
-	REG_WRITE(REG_GLOBAL, GLOBAL_MAC_01, (addr[0] << 9) | addr[1]);
+	u16 val = addr[0] << 8 | addr[1];
+
+	/* The multicast bit is always transmitted as a zero, so the switch uses
+	 * bit 8 for "DiffAddr", where 0 means all ports transmit the same SA.
+	 */
+	val &= 0xfeff;
+
+	REG_WRITE(REG_GLOBAL, GLOBAL_MAC_01, val);
 	REG_WRITE(REG_GLOBAL, GLOBAL_MAC_23, (addr[2] << 8) | addr[3]);
 	REG_WRITE(REG_GLOBAL, GLOBAL_MAC_45, (addr[4] << 8) | addr[5]);
 

drivers/net/ethernet/amazon/ena/ena_ethtool.c

@@ -742,8 +742,8 @@ static void ena_get_channels(struct net_device *netdev,
 {
 	struct ena_adapter *adapter = netdev_priv(netdev);
 
-	channels->max_rx = ENA_MAX_NUM_IO_QUEUES;
-	channels->max_tx = ENA_MAX_NUM_IO_QUEUES;
+	channels->max_rx = adapter->num_queues;
+	channels->max_tx = adapter->num_queues;
 	channels->max_other = 0;
 	channels->max_combined = 0;
 	channels->rx_count = adapter->num_queues;

drivers/net/ethernet/amazon/ena/ena_netdev.c

@@ -966,7 +966,7 @@ static inline void ena_rx_checksum(struct ena_ring *rx_ring,
 		u64_stats_update_begin(&rx_ring->syncp);
 		rx_ring->rx_stats.bad_csum++;
 		u64_stats_update_end(&rx_ring->syncp);
-		netif_err(rx_ring->adapter, rx_err, rx_ring->netdev,
+		netif_dbg(rx_ring->adapter, rx_err, rx_ring->netdev,
 			  "RX IPv4 header checksum error\n");
 		return;
 	}
@@ -979,7 +979,7 @@ static inline void ena_rx_checksum(struct ena_ring *rx_ring,
 			u64_stats_update_begin(&rx_ring->syncp);
 			rx_ring->rx_stats.bad_csum++;
 			u64_stats_update_end(&rx_ring->syncp);
-			netif_err(rx_ring->adapter, rx_err, rx_ring->netdev,
+			netif_dbg(rx_ring->adapter, rx_err, rx_ring->netdev,
 				  "RX L4 checksum error\n");
 			skb->ip_summed = CHECKSUM_NONE;
 			return;
@@ -3064,7 +3064,8 @@ static void ena_release_bars(struct ena_com_dev *ena_dev, struct pci_dev *pdev)
 	if (ena_dev->mem_bar)
 		devm_iounmap(&pdev->dev, ena_dev->mem_bar);
 
-	devm_iounmap(&pdev->dev, ena_dev->reg_bar);
+	if (ena_dev->reg_bar)
+		devm_iounmap(&pdev->dev, ena_dev->reg_bar);
 
 	release_bars = pci_select_bars(pdev, IORESOURCE_MEM) & ENA_BAR_MASK;
 	pci_release_selected_regions(pdev, release_bars);

drivers/net/ethernet/aquantia/atlantic/aq_cfg.h

@@ -22,8 +22,12 @@
 
 #define AQ_CFG_FORCE_LEGACY_INT 0U
 
-#define AQ_CFG_IS_INTERRUPT_MODERATION_DEF   1U
-#define AQ_CFG_INTERRUPT_MODERATION_RATE_DEF 0xFFFFU
+#define AQ_CFG_INTERRUPT_MODERATION_OFF		0
+#define AQ_CFG_INTERRUPT_MODERATION_ON		1
+#define AQ_CFG_INTERRUPT_MODERATION_AUTO	0xFFFFU
+
+#define AQ_CFG_INTERRUPT_MODERATION_USEC_MAX (0x1FF * 2)
+
 #define AQ_CFG_IRQ_MASK                      0x1FFU
 
 #define AQ_CFG_VECS_MAX   8U

drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c

@@ -56,10 +56,6 @@ aq_ethtool_set_link_ksettings(struct net_device *ndev,
 	return aq_nic_set_link_ksettings(aq_nic, cmd);
 }
 
-/* there "5U" is number of queue[#] stats lines (InPackets+...+InErrors) */
-static const unsigned int aq_ethtool_stat_queue_lines = 5U;
-static const unsigned int aq_ethtool_stat_queue_chars =
-	5U * ETH_GSTRING_LEN;
 static const char aq_ethtool_stat_names[][ETH_GSTRING_LEN] = {
 	"InPackets",
 	"InUCast",
@@ -83,56 +79,26 @@ static const char aq_ethtool_stat_names[][ETH_GSTRING_LEN] = {
 	"InOctetsDma",
 	"OutOctetsDma",
 	"InDroppedDma",
-	"Queue[0] InPackets",
-	"Queue[0] OutPackets",
-	"Queue[0] InJumboPackets",
-	"Queue[0] InLroPackets",
-	"Queue[0] InErrors",
-	"Queue[1] InPackets",
-	"Queue[1] OutPackets",
-	"Queue[1] InJumboPackets",
-	"Queue[1] InLroPackets",
-	"Queue[1] InErrors",
-	"Queue[2] InPackets",
-	"Queue[2] OutPackets",
-	"Queue[2] InJumboPackets",
-	"Queue[2] InLroPackets",
-	"Queue[2] InErrors",
-	"Queue[3] InPackets",
-	"Queue[3] OutPackets",
-	"Queue[3] InJumboPackets",
-	"Queue[3] InLroPackets",
-	"Queue[3] InErrors",
-	"Queue[4] InPackets",
-	"Queue[4] OutPackets",
-	"Queue[4] InJumboPackets",
-	"Queue[4] InLroPackets",
-	"Queue[4] InErrors",
-	"Queue[5] InPackets",
-	"Queue[5] OutPackets",
-	"Queue[5] InJumboPackets",
-	"Queue[5] InLroPackets",
-	"Queue[5] InErrors",
-	"Queue[6] InPackets",
-	"Queue[6] OutPackets",
-	"Queue[6] InJumboPackets",
-	"Queue[6] InLroPackets",
-	"Queue[6] InErrors",
-	"Queue[7] InPackets",
-	"Queue[7] OutPackets",
-	"Queue[7] InJumboPackets",
-	"Queue[7] InLroPackets",
-	"Queue[7] InErrors",
+};
+
+static const char aq_ethtool_queue_stat_names[][ETH_GSTRING_LEN] = {
+	"Queue[%d] InPackets",
+	"Queue[%d] OutPackets",
+	"Queue[%d] Restarts",
+	"Queue[%d] InJumboPackets",
+	"Queue[%d] InLroPackets",
+	"Queue[%d] InErrors",
 };
 
 static void aq_ethtool_stats(struct net_device *ndev,
 			     struct ethtool_stats *stats, u64 *data)
 {
 	struct aq_nic_s *aq_nic = netdev_priv(ndev);
+	struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(aq_nic);
 
-/* ASSERT: Need add lines to aq_ethtool_stat_names if AQ_CFG_VECS_MAX > 8 */
-	BUILD_BUG_ON(AQ_CFG_VECS_MAX > 8);
-	memset(data, 0, ARRAY_SIZE(aq_ethtool_stat_names) * sizeof(u64));
+	memset(data, 0, (ARRAY_SIZE(aq_ethtool_stat_names) +
+				ARRAY_SIZE(aq_ethtool_queue_stat_names) *
+				cfg->vecs) * sizeof(u64));
 	aq_nic_get_stats(aq_nic, data);
 }
 
@@ -154,8 +120,8 @@ static void aq_ethtool_get_drvinfo(struct net_device *ndev,
 
 	strlcpy(drvinfo->bus_info, pdev ? pci_name(pdev) : "",
 		sizeof(drvinfo->bus_info));
-	drvinfo->n_stats = ARRAY_SIZE(aq_ethtool_stat_names) -
-		(AQ_CFG_VECS_MAX - cfg->vecs) * aq_ethtool_stat_queue_lines;
+	drvinfo->n_stats = ARRAY_SIZE(aq_ethtool_stat_names) +
+		cfg->vecs * ARRAY_SIZE(aq_ethtool_queue_stat_names);
 	drvinfo->testinfo_len = 0;
 	drvinfo->regdump_len = regs_count;
 	drvinfo->eedump_len = 0;
@@ -164,14 +130,25 @@ static void aq_ethtool_get_drvinfo(struct net_device *ndev,
 static void aq_ethtool_get_strings(struct net_device *ndev,
 				   u32 stringset, u8 *data)
 {
+	int i, si;
 	struct aq_nic_s *aq_nic = netdev_priv(ndev);
 	struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(aq_nic);
+	u8 *p = data;
 
-	if (stringset == ETH_SS_STATS)
-		memcpy(data, *aq_ethtool_stat_names,
-		       sizeof(aq_ethtool_stat_names) -
-		       (AQ_CFG_VECS_MAX - cfg->vecs) *
-		       aq_ethtool_stat_queue_chars);
+	if (stringset == ETH_SS_STATS) {
+		memcpy(p, *aq_ethtool_stat_names,
+		       sizeof(aq_ethtool_stat_names));
+		p = p + sizeof(aq_ethtool_stat_names);
+		for (i = 0; i < cfg->vecs; i++) {
+			for (si = 0;
+				si < ARRAY_SIZE(aq_ethtool_queue_stat_names);
+				si++) {
+				snprintf(p, ETH_GSTRING_LEN,
+					 aq_ethtool_queue_stat_names[si], i);
+				p += ETH_GSTRING_LEN;
+			}
+		}
+	}
 }
 
 static int aq_ethtool_get_sset_count(struct net_device *ndev, int stringset)
@@ -182,9 +159,8 @@ static int aq_ethtool_get_sset_count(struct net_device *ndev, int stringset)
 
 	switch (stringset) {
 	case ETH_SS_STATS:
-		ret = ARRAY_SIZE(aq_ethtool_stat_names) -
-			(AQ_CFG_VECS_MAX - cfg->vecs) *
-			aq_ethtool_stat_queue_lines;
+		ret = ARRAY_SIZE(aq_ethtool_stat_names) +
+			cfg->vecs * ARRAY_SIZE(aq_ethtool_queue_stat_names);
 		break;
 	default:
 		ret = -EOPNOTSUPP;
@@ -245,6 +221,69 @@ static int aq_ethtool_get_rxnfc(struct net_device *ndev,
 	return err;
 }
 
+int aq_ethtool_get_coalesce(struct net_device *ndev,
+			    struct ethtool_coalesce *coal)
+{
+	struct aq_nic_s *aq_nic = netdev_priv(ndev);
+	struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(aq_nic);
+
+	if (cfg->itr == AQ_CFG_INTERRUPT_MODERATION_ON ||
+	    cfg->itr == AQ_CFG_INTERRUPT_MODERATION_AUTO) {
+		coal->rx_coalesce_usecs = cfg->rx_itr;
+		coal->tx_coalesce_usecs = cfg->tx_itr;
+		coal->rx_max_coalesced_frames = 0;
+		coal->tx_max_coalesced_frames = 0;
+	} else {
+		coal->rx_coalesce_usecs = 0;
+		coal->tx_coalesce_usecs = 0;
+		coal->rx_max_coalesced_frames = 1;
+		coal->tx_max_coalesced_frames = 1;
+	}
+	return 0;
+}
+
+int aq_ethtool_set_coalesce(struct net_device *ndev,
+			    struct ethtool_coalesce *coal)
+{
+	struct aq_nic_s *aq_nic = netdev_priv(ndev);
+	struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(aq_nic);
+
+	/* This is not yet supported
+	 */
+	if (coal->use_adaptive_rx_coalesce || coal->use_adaptive_tx_coalesce)
+		return -EOPNOTSUPP;
+
+	/* Atlantic only supports timing based coalescing
+	 */
+	if (coal->rx_max_coalesced_frames > 1 ||
+	    coal->rx_coalesce_usecs_irq ||
+	    coal->rx_max_coalesced_frames_irq)
+		return -EOPNOTSUPP;
+
+	if (coal->tx_max_coalesced_frames > 1 ||
+	    coal->tx_coalesce_usecs_irq ||
+	    coal->tx_max_coalesced_frames_irq)
+		return -EOPNOTSUPP;
+
+	/* We do not support frame counting. Check this
+	 */
+	if (!(coal->rx_max_coalesced_frames == !coal->rx_coalesce_usecs))
+		return -EOPNOTSUPP;
+	if (!(coal->tx_max_coalesced_frames == !coal->tx_coalesce_usecs))
+		return -EOPNOTSUPP;
+
+	if (coal->rx_coalesce_usecs > AQ_CFG_INTERRUPT_MODERATION_USEC_MAX ||
+	    coal->tx_coalesce_usecs > AQ_CFG_INTERRUPT_MODERATION_USEC_MAX)
+		return -EINVAL;
+
+	cfg->itr = AQ_CFG_INTERRUPT_MODERATION_ON;
+
+	cfg->rx_itr = coal->rx_coalesce_usecs;
+	cfg->tx_itr = coal->tx_coalesce_usecs;
+
+	return aq_nic_update_interrupt_moderation_settings(aq_nic);
+}
+
 const struct ethtool_ops aq_ethtool_ops = {
 	.get_link            = aq_ethtool_get_link,
 	.get_regs_len        = aq_ethtool_get_regs_len,
@@ -259,4 +298,6 @@ const struct ethtool_ops aq_ethtool_ops = {
 	.get_ethtool_stats   = aq_ethtool_stats,
 	.get_link_ksettings  = aq_ethtool_get_link_ksettings,
 	.set_link_ksettings  = aq_ethtool_set_link_ksettings,
+	.get_coalesce	     = aq_ethtool_get_coalesce,
+	.set_coalesce	     = aq_ethtool_set_coalesce,
 };

drivers/net/ethernet/aquantia/atlantic/aq_hw.h

@@ -151,8 +151,7 @@ struct aq_hw_ops {
 				     [ETH_ALEN],
 				     u32 count);
 
-	int (*hw_interrupt_moderation_set)(struct aq_hw_s *self,
-					   bool itr_enabled);
+	int (*hw_interrupt_moderation_set)(struct aq_hw_s *self);
 
 	int (*hw_rss_set)(struct aq_hw_s *self,
 			  struct aq_rss_parameters *rss_params);
@@ -163,6 +162,8 @@ struct aq_hw_ops {
 	int (*hw_get_regs)(struct aq_hw_s *self,
 			   struct aq_hw_caps_s *aq_hw_caps, u32 *regs_buff);
 
+	int (*hw_update_stats)(struct aq_hw_s *self);
+
 	int (*hw_get_hw_stats)(struct aq_hw_s *self, u64 *data,
 			       unsigned int *p_count);
 

drivers/net/ethernet/aquantia/atlantic/aq_nic.c

@@ -16,6 +16,7 @@
 #include "aq_pci_func.h"
 #include "aq_nic_internal.h"
 
+#include <linux/moduleparam.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/timer.h>
@@ -24,6 +25,18 @@
 #include <linux/tcp.h>
 #include <net/ip.h>
 
+static unsigned int aq_itr = AQ_CFG_INTERRUPT_MODERATION_AUTO;
+module_param_named(aq_itr, aq_itr, uint, 0644);
+MODULE_PARM_DESC(aq_itr, "Interrupt throttling mode");
+
+static unsigned int aq_itr_tx;
+module_param_named(aq_itr_tx, aq_itr_tx, uint, 0644);
+MODULE_PARM_DESC(aq_itr_tx, "TX interrupt throttle rate");
+
+static unsigned int aq_itr_rx;
+module_param_named(aq_itr_rx, aq_itr_rx, uint, 0644);
+MODULE_PARM_DESC(aq_itr_rx, "RX interrupt throttle rate");
+
 static void aq_nic_rss_init(struct aq_nic_s *self, unsigned int num_rss_queues)
 {
 	struct aq_nic_cfg_s *cfg = &self->aq_nic_cfg;
@@ -61,9 +74,9 @@ static void aq_nic_cfg_init_defaults(struct aq_nic_s *self)
 
 	cfg->is_polling = AQ_CFG_IS_POLLING_DEF;
 
-	cfg->is_interrupt_moderation = AQ_CFG_IS_INTERRUPT_MODERATION_DEF;
-	cfg->itr = cfg->is_interrupt_moderation ?
-		AQ_CFG_INTERRUPT_MODERATION_RATE_DEF : 0U;
+	cfg->itr = aq_itr;
+	cfg->tx_itr = aq_itr_tx;
+	cfg->rx_itr = aq_itr_rx;
 
 	cfg->is_rss = AQ_CFG_IS_RSS_DEF;
 	cfg->num_rss_queues = AQ_CFG_NUM_RSS_QUEUES_DEF;
@@ -126,10 +139,12 @@ static int aq_nic_update_link_status(struct aq_nic_s *self)
 	if (err)
 		return err;
 
-	if (self->link_status.mbps != self->aq_hw->aq_link_status.mbps)
+	if (self->link_status.mbps != self->aq_hw->aq_link_status.mbps) {
 		pr_info("%s: link change old %d new %d\n",
 			AQ_CFG_DRV_NAME, self->link_status.mbps,
 			self->aq_hw->aq_link_status.mbps);
+		aq_nic_update_interrupt_moderation_settings(self);
+	}
 
 	self->link_status = self->aq_hw->aq_link_status;
 	if (!netif_carrier_ok(self->ndev) && self->link_status.mbps) {
@@ -164,8 +179,8 @@ static void aq_nic_service_timer_cb(unsigned long param)
 	if (err)
 		goto err_exit;
 
-	self->aq_hw_ops.hw_interrupt_moderation_set(self->aq_hw,
-		    self->aq_nic_cfg.is_interrupt_moderation);
+	if (self->aq_hw_ops.hw_update_stats)
+		self->aq_hw_ops.hw_update_stats(self->aq_hw);
 
 	memset(&stats_rx, 0U, sizeof(struct aq_ring_stats_rx_s));
 	memset(&stats_tx, 0U, sizeof(struct aq_ring_stats_tx_s));
@@ -334,6 +349,7 @@ struct aq_nic_s *aq_nic_alloc_hot(struct net_device *ndev)
 	}
 	if (netif_running(ndev))
 		netif_tx_disable(ndev);
+	netif_carrier_off(self->ndev);
 
 	for (self->aq_vecs = 0; self->aq_vecs < self->aq_nic_cfg.vecs;
 		self->aq_vecs++) {
@@ -421,9 +437,8 @@ int aq_nic_start(struct aq_nic_s *self)
 	if (err < 0)
 		goto err_exit;
 
-	err = self->aq_hw_ops.hw_interrupt_moderation_set(self->aq_hw,
-			    self->aq_nic_cfg.is_interrupt_moderation);
-	if (err < 0)
+	err = aq_nic_update_interrupt_moderation_settings(self);
+	if (err)
 		goto err_exit;
 	setup_timer(&self->service_timer, &aq_nic_service_timer_cb,
 		    (unsigned long)self);
@@ -645,6 +660,11 @@ err_exit:
 	return err;
 }
 
+int aq_nic_update_interrupt_moderation_settings(struct aq_nic_s *self)
+{
+	return self->aq_hw_ops.hw_interrupt_moderation_set(self->aq_hw);
+}
+
 int aq_nic_set_packet_filter(struct aq_nic_s *self, unsigned int flags)
 {
 	int err = 0;
@@ -899,6 +919,7 @@ int aq_nic_stop(struct aq_nic_s *self)
 	unsigned int i = 0U;
 
 	netif_tx_disable(self->ndev);
+	netif_carrier_off(self->ndev);
 
 	del_timer_sync(&self->service_timer);
 

drivers/net/ethernet/aquantia/atlantic/aq_nic.h

@@ -40,6 +40,8 @@ struct aq_nic_cfg_s {
 	u32 vecs;		/* vecs==allocated irqs */
 	u32 irq_type;
 	u32 itr;
+	u16 rx_itr;
+	u16 tx_itr;
 	u32 num_rss_queues;
 	u32 mtu;
 	u32 ucp_0x364;
@@ -49,7 +51,6 @@ struct aq_nic_cfg_s {
 	u16 is_mc_list_enabled;
 	u16 mc_list_count;
 	bool is_autoneg;
-	bool is_interrupt_moderation;
 	bool is_polling;
 	bool is_rss;
 	bool is_lro;
@@ -104,5 +105,6 @@ int aq_nic_set_link_ksettings(struct aq_nic_s *self,
 struct aq_nic_cfg_s *aq_nic_get_cfg(struct aq_nic_s *self);
 u32 aq_nic_get_fw_version(struct aq_nic_s *self);
 int aq_nic_change_pm_state(struct aq_nic_s *self, pm_message_t *pm_msg);
+int aq_nic_update_interrupt_moderation_settings(struct aq_nic_s *self);
 
 #endif /* AQ_NIC_H */

drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c

@@ -85,6 +85,7 @@ int aq_pci_func_init(struct aq_pci_func_s *self)
 	int err = 0;
 	unsigned int bar = 0U;
 	unsigned int port = 0U;
+	unsigned int numvecs = 0U;
 
 	err = pci_enable_device(self->pdev);
 	if (err < 0)
@@ -142,10 +143,12 @@ int aq_pci_func_init(struct aq_pci_func_s *self)
 		}
 	}
 
-	/*enable interrupts */
+	numvecs = min((u8)AQ_CFG_VECS_DEF, self->aq_hw_caps.msix_irqs);
+	numvecs = min(numvecs, num_online_cpus());
+
+	/* enable interrupts */
 #if !AQ_CFG_FORCE_LEGACY_INT
-	err = pci_alloc_irq_vectors(self->pdev, self->aq_hw_caps.msix_irqs,
-			      self->aq_hw_caps.msix_irqs, PCI_IRQ_MSIX);
+	err = pci_alloc_irq_vectors(self->pdev, numvecs, numvecs, PCI_IRQ_MSIX);
 
 	if (err < 0) {
 		err = pci_alloc_irq_vectors(self->pdev, 1, 1,
@@ -153,7 +156,7 @@ int aq_pci_func_init(struct aq_pci_func_s *self)
 		if (err < 0)
 			goto err_exit;
 	}
-#endif
+#endif /* AQ_CFG_FORCE_LEGACY_INT */
 
 	/* net device init */
 	for (port = 0; port < self->ports; ++port) {
@@ -265,6 +268,9 @@ void aq_pci_func_free(struct aq_pci_func_s *self)
 		aq_nic_ndev_free(self->port[port]);
 	}
 
+	if (self->mmio)
+		iounmap(self->mmio);
+
 	kfree(self);
 
 err_exit:;

drivers/net/ethernet/aquantia/atlantic/aq_vec.c

@@ -373,8 +373,11 @@ int aq_vec_get_sw_stats(struct aq_vec_s *self, u64 *data, unsigned int *p_count)
 	memset(&stats_tx, 0U, sizeof(struct aq_ring_stats_tx_s));
 	aq_vec_add_stats(self, &stats_rx, &stats_tx);
 
+	/* This data should mimic aq_ethtool_queue_stat_names structure
+	 */
 	data[count] += stats_rx.packets;
 	data[++count] += stats_tx.packets;
+	data[++count] += stats_tx.queue_restarts;
 	data[++count] += stats_rx.jumbo_packets;
 	data[++count] += stats_rx.lro_packets;
 	data[++count] += stats_rx.errors;

drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c

@@ -765,24 +765,23 @@ err_exit:
 	return err;
 }
 
-static int hw_atl_a0_hw_interrupt_moderation_set(struct aq_hw_s *self,
-						 bool itr_enabled)
+static int hw_atl_a0_hw_interrupt_moderation_set(struct aq_hw_s *self)
 {
 	unsigned int i = 0U;
+	u32 itr_rx;
 
-	if (itr_enabled && self->aq_nic_cfg->itr) {
-		if (self->aq_nic_cfg->itr != 0xFFFFU) {
+	if (self->aq_nic_cfg->itr) {
+		if (self->aq_nic_cfg->itr != AQ_CFG_INTERRUPT_MODERATION_AUTO) {
 			u32 itr_ = (self->aq_nic_cfg->itr >> 1);
 
 			itr_ = min(AQ_CFG_IRQ_MASK, itr_);
 
-			PHAL_ATLANTIC_A0->itr_rx = 0x80000000U |
-					(itr_ << 0x10);
+			itr_rx = 0x80000000U | (itr_ << 0x10);
 		} else  {
 			u32 n = 0xFFFFU & aq_hw_read_reg(self, 0x00002A00U);
 
 			if (n < self->aq_link_status.mbps) {
-				PHAL_ATLANTIC_A0->itr_rx = 0U;
+				itr_rx = 0U;
 			} else {
 				static unsigned int hw_timers_tbl_[] = {
 					0x01CU, /* 10Gbit */
@@ -797,8 +796,7 @@ static int hw_atl_a0_hw_interrupt_moderation_set(struct aq_hw_s *self,
 					hw_atl_utils_mbps_2_speed_index(
 						self->aq_link_status.mbps);
 
-				PHAL_ATLANTIC_A0->itr_rx =
-					0x80000000U |
+				itr_rx = 0x80000000U |
 					(hw_timers_tbl_[speed_index] << 0x10U);
 			}
 
@@ -806,11 +804,11 @@ static int hw_atl_a0_hw_interrupt_moderation_set(struct aq_hw_s *self,
 			aq_hw_write_reg(self, 0x00002A00U, 0x8D000000U);
 		}
 	} else {
-		PHAL_ATLANTIC_A0->itr_rx = 0U;
+		itr_rx = 0U;
 	}
 
 	for (i = HW_ATL_A0_RINGS_MAX; i--;)
-		reg_irq_thr_set(self, PHAL_ATLANTIC_A0->itr_rx, i);
+		reg_irq_thr_set(self, itr_rx, i);
 
 	return aq_hw_err_from_flags(self);
 }
@@ -885,6 +883,7 @@ static struct aq_hw_ops hw_atl_ops_ = {
 	.hw_rss_set                  = hw_atl_a0_hw_rss_set,
 	.hw_rss_hash_set             = hw_atl_a0_hw_rss_hash_set,
 	.hw_get_regs                 = hw_atl_utils_hw_get_regs,
+	.hw_update_stats             = hw_atl_utils_update_stats,
 	.hw_get_hw_stats             = hw_atl_utils_get_hw_stats,
 	.hw_get_fw_version           = hw_atl_utils_get_fw_version,
 };

drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c

@@ -788,39 +788,45 @@ err_exit:
 	return err;
 }
 
-static int hw_atl_b0_hw_interrupt_moderation_set(struct aq_hw_s *self,
-						 bool itr_enabled)
+static int hw_atl_b0_hw_interrupt_moderation_set(struct aq_hw_s *self)
 {
 	unsigned int i = 0U;
+	u32 itr_tx = 2U;
+	u32 itr_rx = 2U;
 
-	if (itr_enabled && self->aq_nic_cfg->itr) {
+	switch (self->aq_nic_cfg->itr) {
+	case  AQ_CFG_INTERRUPT_MODERATION_ON:
+	case  AQ_CFG_INTERRUPT_MODERATION_AUTO:
 		tdm_tx_desc_wr_wb_irq_en_set(self, 0U);
 		tdm_tdm_intr_moder_en_set(self, 1U);
 		rdm_rx_desc_wr_wb_irq_en_set(self, 0U);
 		rdm_rdm_intr_moder_en_set(self, 1U);
 
-		PHAL_ATLANTIC_B0->itr_tx = 2U;
-		PHAL_ATLANTIC_B0->itr_rx = 2U;
+		if (self->aq_nic_cfg->itr == AQ_CFG_INTERRUPT_MODERATION_ON) {
+			/* HW timers are in 2us units */
+			int tx_max_timer = self->aq_nic_cfg->tx_itr / 2;
+			int tx_min_timer = tx_max_timer / 2;
 
-		if (self->aq_nic_cfg->itr != 0xFFFFU) {
-			unsigned int max_timer = self->aq_nic_cfg->itr / 2U;
-			unsigned int min_timer = self->aq_nic_cfg->itr / 32U;
+			int rx_max_timer = self->aq_nic_cfg->rx_itr / 2;
+			int rx_min_timer = rx_max_timer / 2;
 
-			max_timer = min(0x1FFU, max_timer);
-			min_timer = min(0xFFU, min_timer);
+			tx_max_timer = min(HW_ATL_INTR_MODER_MAX, tx_max_timer);
+			tx_min_timer = min(HW_ATL_INTR_MODER_MIN, tx_min_timer);
+			rx_max_timer = min(HW_ATL_INTR_MODER_MAX, rx_max_timer);
+			rx_min_timer = min(HW_ATL_INTR_MODER_MIN, rx_min_timer);
 
-			PHAL_ATLANTIC_B0->itr_tx |= min_timer << 0x8U;
-			PHAL_ATLANTIC_B0->itr_tx |= max_timer << 0x10U;
-			PHAL_ATLANTIC_B0->itr_rx |= min_timer << 0x8U;
-			PHAL_ATLANTIC_B0->itr_rx |= max_timer << 0x10U;
+			itr_tx |= tx_min_timer << 0x8U;
+			itr_tx |= tx_max_timer << 0x10U;
+			itr_rx |= rx_min_timer << 0x8U;
+			itr_rx |= rx_max_timer << 0x10U;
 		} else {
 			static unsigned int hw_atl_b0_timers_table_tx_[][2] = {
-				{0xffU, 0xffU}, /* 10Gbit */
-				{0xffU, 0x1ffU}, /* 5Gbit */
-				{0xffU, 0x1ffU}, /* 5Gbit 5GS */
-				{0xffU, 0x1ffU}, /* 2.5Gbit */
-				{0xffU, 0x1ffU}, /* 1Gbit */
-				{0xffU, 0x1ffU}, /* 100Mbit */
+				{0xfU, 0xffU}, /* 10Gbit */
+				{0xfU, 0x1ffU}, /* 5Gbit */
+				{0xfU, 0x1ffU}, /* 5Gbit 5GS */
+				{0xfU, 0x1ffU}, /* 2.5Gbit */
+				{0xfU, 0x1ffU}, /* 1Gbit */
+				{0xfU, 0x1ffU}, /* 100Mbit */
 			};
 
 			static unsigned int hw_atl_b0_timers_table_rx_[][2] = {
@@ -836,34 +842,36 @@ static int hw_atl_b0_hw_interrupt_moderation_set(struct aq_hw_s *self,
 					hw_atl_utils_mbps_2_speed_index(
 						self->aq_link_status.mbps);
 
-			PHAL_ATLANTIC_B0->itr_tx |=
-				hw_atl_b0_timers_table_tx_[speed_index]
-				[0] << 0x8U; /* set min timer value */
-			PHAL_ATLANTIC_B0->itr_tx |=
-				hw_atl_b0_timers_table_tx_[speed_index]
-				[1] << 0x10U; /* set max timer value */
+			/* Update user visible ITR settings */
+			self->aq_nic_cfg->tx_itr = hw_atl_b0_timers_table_tx_
+							[speed_index][1] * 2;
+			self->aq_nic_cfg->rx_itr = hw_atl_b0_timers_table_rx_
+							[speed_index][1] * 2;
 
-			PHAL_ATLANTIC_B0->itr_rx |=
-				hw_atl_b0_timers_table_rx_[speed_index]
-				[0] << 0x8U; /* set min timer value */
-			PHAL_ATLANTIC_B0->itr_rx |=
-				hw_atl_b0_timers_table_rx_[speed_index]
-				[1] << 0x10U; /* set max timer value */
+			itr_tx |= hw_atl_b0_timers_table_tx_
+						[speed_index][0] << 0x8U;
+			itr_tx |= hw_atl_b0_timers_table_tx_
+						[speed_index][1] << 0x10U;
+
+			itr_rx |= hw_atl_b0_timers_table_rx_
+						[speed_index][0] << 0x8U;
+			itr_rx |= hw_atl_b0_timers_table_rx_
+						[speed_index][1] << 0x10U;
 		}
-	} else {
+		break;
+	case AQ_CFG_INTERRUPT_MODERATION_OFF:
 		tdm_tx_desc_wr_wb_irq_en_set(self, 1U);
 		tdm_tdm_intr_moder_en_set(self, 0U);
 		rdm_rx_desc_wr_wb_irq_en_set(self, 1U);
 		rdm_rdm_intr_moder_en_set(self, 0U);
-		PHAL_ATLANTIC_B0->itr_tx = 0U;
-		PHAL_ATLANTIC_B0->itr_rx = 0U;
+		itr_tx = 0U;
+		itr_rx = 0U;
+		break;
 	}
 
 	for (i = HW_ATL_B0_RINGS_MAX; i--;) {
-		reg_tx_intr_moder_ctrl_set(self,
-					   PHAL_ATLANTIC_B0->itr_tx, i);
-		reg_rx_intr_moder_ctrl_set(self,
-					   PHAL_ATLANTIC_B0->itr_rx, i);
+		reg_tx_intr_moder_ctrl_set(self, itr_tx, i);
+		reg_rx_intr_moder_ctrl_set(self, itr_rx, i);
 	}
 
 	return aq_hw_err_from_flags(self);
@@ -939,6 +947,7 @@ static struct aq_hw_ops hw_atl_ops_ = {
 	.hw_rss_set                  = hw_atl_b0_hw_rss_set,
 	.hw_rss_hash_set             = hw_atl_b0_hw_rss_hash_set,
 	.hw_get_regs                 = hw_atl_utils_hw_get_regs,
+	.hw_update_stats             = hw_atl_utils_update_stats,
 	.hw_get_hw_stats             = hw_atl_utils_get_hw_stats,
 	.hw_get_fw_version           = hw_atl_utils_get_fw_version,
 };

drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h

@@ -139,6 +139,9 @@
 
 #define HW_ATL_B0_FW_VER_EXPECTED 0x01050006U
 
+#define HW_ATL_INTR_MODER_MAX  0x1FF
+#define HW_ATL_INTR_MODER_MIN  0xFF
+
 /* Hardware tx descriptor */
 struct __packed hw_atl_txd_s {
 	u64 buf_addr;

drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c

@@ -255,6 +255,15 @@ err_exit:
 	return err;
 }
 
+int hw_atl_utils_mpi_read_mbox(struct aq_hw_s *self,
+			       struct hw_aq_atl_utils_mbox_header *pmbox)
+{
+	return hw_atl_utils_fw_downld_dwords(self,
+				      PHAL_ATLANTIC->mbox_addr,
+				      (u32 *)(void *)pmbox,
+				      sizeof(*pmbox) / sizeof(u32));
+}
+
 void hw_atl_utils_mpi_read_stats(struct aq_hw_s *self,
 				 struct hw_aq_atl_utils_mbox *pmbox)
 {
@@ -267,9 +276,6 @@ void hw_atl_utils_mpi_read_stats(struct aq_hw_s *self,
 	if (err < 0)
 		goto err_exit;
 
-	if (pmbox != &PHAL_ATLANTIC->mbox)
-		memcpy(pmbox, &PHAL_ATLANTIC->mbox, sizeof(*pmbox));
-
 	if (IS_CHIP_FEATURE(REVISION_A0)) {
 		unsigned int mtu = self->aq_nic_cfg ?
 					self->aq_nic_cfg->mtu : 1514U;
@@ -299,17 +305,17 @@ void hw_atl_utils_mpi_set(struct aq_hw_s *self,
 {
 	int err = 0;
 	u32 transaction_id = 0;
+	struct hw_aq_atl_utils_mbox_header mbox;
 
 	if (state == MPI_RESET) {
-		hw_atl_utils_mpi_read_stats(self, &PHAL_ATLANTIC->mbox);
+		hw_atl_utils_mpi_read_mbox(self, &mbox);
 
-		transaction_id = PHAL_ATLANTIC->mbox.transaction_id;
+		transaction_id = mbox.transaction_id;
 
 		AQ_HW_WAIT_FOR(transaction_id !=
-				(hw_atl_utils_mpi_read_stats
-					(self, &PHAL_ATLANTIC->mbox),
-					PHAL_ATLANTIC->mbox.transaction_id),
-					1000U, 100U);
+				(hw_atl_utils_mpi_read_mbox(self, &mbox),
+				 mbox.transaction_id),
+			       1000U, 100U);
 		if (err < 0)
 			goto err_exit;
 	}
@@ -492,16 +498,51 @@ int hw_atl_utils_hw_set_power(struct aq_hw_s *self,
 	return 0;
 }
 
+int hw_atl_utils_update_stats(struct aq_hw_s *self)
+{
+	struct hw_atl_s *hw_self = PHAL_ATLANTIC;
+	struct hw_aq_atl_utils_mbox mbox;
+
+	if (!self->aq_link_status.mbps)
+		return 0;
+
+	hw_atl_utils_mpi_read_stats(self, &mbox);
+
+#define AQ_SDELTA(_N_) (hw_self->curr_stats._N_ += \
+			mbox.stats._N_ - hw_self->last_stats._N_)
+
+	AQ_SDELTA(uprc);
+	AQ_SDELTA(mprc);
+	AQ_SDELTA(bprc);
+	AQ_SDELTA(erpt);
+
+	AQ_SDELTA(uptc);
+	AQ_SDELTA(mptc);
+	AQ_SDELTA(bptc);
+	AQ_SDELTA(erpr);
+
+	AQ_SDELTA(ubrc);
+	AQ_SDELTA(ubtc);
+	AQ_SDELTA(mbrc);
+	AQ_SDELTA(mbtc);
+	AQ_SDELTA(bbrc);
+	AQ_SDELTA(bbtc);
+	AQ_SDELTA(dpc);
+
+#undef AQ_SDELTA
+
+	memcpy(&hw_self->last_stats, &mbox.stats, sizeof(mbox.stats));
+
+	return 0;
+}
+
 int hw_atl_utils_get_hw_stats(struct aq_hw_s *self,
 			      u64 *data, unsigned int *p_count)
 {
-	struct hw_atl_stats_s *stats = NULL;
+	struct hw_atl_s *hw_self = PHAL_ATLANTIC;
+	struct hw_atl_stats_s *stats = &hw_self->curr_stats;
 	int i = 0;
 
-	hw_atl_utils_mpi_read_stats(self, &PHAL_ATLANTIC->mbox);
-
-	stats = &PHAL_ATLANTIC->mbox.stats;
-
 	data[i] = stats->uprc + stats->mprc + stats->bprc;
 	data[++i] = stats->uprc;
 	data[++i] = stats->mprc;

drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h

@@ -115,19 +115,22 @@ struct __packed hw_aq_atl_utils_fw_rpc {
 	};
 };
 
-struct __packed hw_aq_atl_utils_mbox {
+struct __packed hw_aq_atl_utils_mbox_header {
 	u32 version;
 	u32 transaction_id;
-	int error;
+	u32 error;
+};
+
+struct __packed hw_aq_atl_utils_mbox {
+	struct hw_aq_atl_utils_mbox_header header;
 	struct hw_atl_stats_s stats;
 };
 
 struct __packed hw_atl_s {
 	struct aq_hw_s base;
-	struct hw_aq_atl_utils_mbox mbox;
+	struct hw_atl_stats_s last_stats;
+	struct hw_atl_stats_s curr_stats;
 	u64 speed;
-	u32 itr_tx;
-	u32 itr_rx;
 	unsigned int chip_features;
 	u32 fw_ver_actual;
 	atomic_t dpc;
@@ -170,6 +173,9 @@ enum hal_atl_utils_fw_state_e {
 
 void hw_atl_utils_hw_chip_features_init(struct aq_hw_s *self, u32 *p);
 
+int hw_atl_utils_mpi_read_mbox(struct aq_hw_s *self,
+			       struct hw_aq_atl_utils_mbox_header *pmbox);
+
 void hw_atl_utils_mpi_read_stats(struct aq_hw_s *self,
 				 struct hw_aq_atl_utils_mbox *pmbox);
 
@@ -199,6 +205,8 @@ int hw_atl_utils_hw_deinit(struct aq_hw_s *self);
 
 int hw_atl_utils_get_fw_version(struct aq_hw_s *self, u32 *fw_version);
 
+int hw_atl_utils_update_stats(struct aq_hw_s *self);
+
 int hw_atl_utils_get_hw_stats(struct aq_hw_s *self,
 			      u64 *data,
 			      unsigned int *p_count);

drivers/net/ethernet/broadcom/bnxt/bnxt.c

@@ -214,6 +214,8 @@ static const u16 bnxt_async_events_arr[] = {
 	ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CFG_CHANGE,
 };
 
+static struct workqueue_struct *bnxt_pf_wq;
+
 static bool bnxt_vf_pciid(enum board_idx idx)
 {
 	return (idx == NETXTREME_C_VF || idx == NETXTREME_E_VF);
@@ -1024,12 +1026,28 @@ static int bnxt_discard_rx(struct bnxt *bp, struct bnxt_napi *bnapi,
 	return 0;
 }
 
+static void bnxt_queue_sp_work(struct bnxt *bp)
+{
+	if (BNXT_PF(bp))
+		queue_work(bnxt_pf_wq, &bp->sp_task);
+	else
+		schedule_work(&bp->sp_task);
+}
+
+static void bnxt_cancel_sp_work(struct bnxt *bp)
+{
+	if (BNXT_PF(bp))
+		flush_workqueue(bnxt_pf_wq);
+	else
+		cancel_work_sync(&bp->sp_task);
+}
+
 static void bnxt_sched_reset(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
 {
 	if (!rxr->bnapi->in_reset) {
 		rxr->bnapi->in_reset = true;
 		set_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event);
-		schedule_work(&bp->sp_task);
+		bnxt_queue_sp_work(bp);
 	}
 	rxr->rx_next_cons = 0xffff;
 }
@@ -1717,7 +1735,7 @@ static int bnxt_async_event_process(struct bnxt *bp,
 	default:
 		goto async_event_process_exit;
 	}
-	schedule_work(&bp->sp_task);
+	bnxt_queue_sp_work(bp);
 async_event_process_exit:
 	bnxt_ulp_async_events(bp, cmpl);
 	return 0;
@@ -1751,7 +1769,7 @@ static int bnxt_hwrm_handler(struct bnxt *bp, struct tx_cmp *txcmp)
 
 		set_bit(vf_id - bp->pf.first_vf_id, bp->pf.vf_event_bmap);
 		set_bit(BNXT_HWRM_EXEC_FWD_REQ_SP_EVENT, &bp->sp_event);
-		schedule_work(&bp->sp_task);
+		bnxt_queue_sp_work(bp);
 		break;
 
 	case CMPL_BASE_TYPE_HWRM_ASYNC_EVENT:
@@ -3448,6 +3466,12 @@ int _hwrm_send_message(struct bnxt *bp, void *msg, u32 msg_len, int timeout)
 	return bnxt_hwrm_do_send_msg(bp, msg, msg_len, timeout, false);
 }
 
+int _hwrm_send_message_silent(struct bnxt *bp, void *msg, u32 msg_len,
+			      int timeout)
+{
+	return bnxt_hwrm_do_send_msg(bp, msg, msg_len, timeout, true);
+}
+
 int hwrm_send_message(struct bnxt *bp, void *msg, u32 msg_len, int timeout)
 {
 	int rc;
@@ -6327,7 +6351,9 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 	}
 
 	if (link_re_init) {
+		mutex_lock(&bp->link_lock);
 		rc = bnxt_update_phy_setting(bp);
+		mutex_unlock(&bp->link_lock);
 		if (rc)
 			netdev_warn(bp->dev, "failed to update phy settings\n");
 	}
@@ -6647,7 +6673,7 @@ static void bnxt_set_rx_mode(struct net_device *dev)
 		vnic->rx_mask = mask;
 
 		set_bit(BNXT_RX_MASK_SP_EVENT, &bp->sp_event);
-		schedule_work(&bp->sp_task);
+		bnxt_queue_sp_work(bp);
 	}
 }
 
@@ -6920,7 +6946,7 @@ static void bnxt_tx_timeout(struct net_device *dev)
 
 	netdev_err(bp->dev,  "TX timeout detected, starting reset task!\n");
 	set_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event);
-	schedule_work(&bp->sp_task);
+	bnxt_queue_sp_work(bp);
 }
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
@@ -6952,7 +6978,7 @@ static void bnxt_timer(unsigned long data)
 	if (bp->link_info.link_up && (bp->flags & BNXT_FLAG_PORT_STATS) &&
 	    bp->stats_coal_ticks) {
 		set_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event);
-		schedule_work(&bp->sp_task);
+		bnxt_queue_sp_work(bp);
 	}
 bnxt_restart_timer:
 	mod_timer(&bp->timer, jiffies + bp->current_interval);
@@ -7025,30 +7051,28 @@ static void bnxt_sp_task(struct work_struct *work)
 	if (test_and_clear_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event))
 		bnxt_hwrm_port_qstats(bp);
 
-	/* These functions below will clear BNXT_STATE_IN_SP_TASK.  They
-	 * must be the last functions to be called before exiting.
-	 */
 	if (test_and_clear_bit(BNXT_LINK_CHNG_SP_EVENT, &bp->sp_event)) {
-		int rc = 0;
+		int rc;
 
+		mutex_lock(&bp->link_lock);
 		if (test_and_clear_bit(BNXT_LINK_SPEED_CHNG_SP_EVENT,
 				       &bp->sp_event))
 			bnxt_hwrm_phy_qcaps(bp);
 
-		bnxt_rtnl_lock_sp(bp);
-		if (test_bit(BNXT_STATE_OPEN, &bp->state))
-			rc = bnxt_update_link(bp, true);
-		bnxt_rtnl_unlock_sp(bp);
+		rc = bnxt_update_link(bp, true);
+		mutex_unlock(&bp->link_lock);
 		if (rc)
 			netdev_err(bp->dev, "SP task can't update link (rc: %x)\n",
 				   rc);
 	}
 	if (test_and_clear_bit(BNXT_HWRM_PORT_MODULE_SP_EVENT, &bp->sp_event)) {
-		bnxt_rtnl_lock_sp(bp);
-		if (test_bit(BNXT_STATE_OPEN, &bp->state))
-			bnxt_get_port_module_status(bp);
-		bnxt_rtnl_unlock_sp(bp);
+		mutex_lock(&bp->link_lock);
+		bnxt_get_port_module_status(bp);
+		mutex_unlock(&bp->link_lock);
 	}
+	/* These functions below will clear BNXT_STATE_IN_SP_TASK.  They
+	 * must be the last functions to be called before exiting.
+	 */
 	if (test_and_clear_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event))
 		bnxt_reset(bp, false);
 
@@ -7433,7 +7457,7 @@ static int bnxt_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 	spin_unlock_bh(&bp->ntp_fltr_lock);
 
 	set_bit(BNXT_RX_NTP_FLTR_SP_EVENT, &bp->sp_event);
-	schedule_work(&bp->sp_task);
+	bnxt_queue_sp_work(bp);
 
 	return new_fltr->sw_id;
 
@@ -7516,7 +7540,7 @@ static void bnxt_udp_tunnel_add(struct net_device *dev,
 		if (bp->vxlan_port_cnt == 1) {
 			bp->vxlan_port = ti->port;
 			set_bit(BNXT_VXLAN_ADD_PORT_SP_EVENT, &bp->sp_event);
-			schedule_work(&bp->sp_task);
+			bnxt_queue_sp_work(bp);
 		}
 		break;
 	case UDP_TUNNEL_TYPE_GENEVE:
@@ -7533,7 +7557,7 @@ static void bnxt_udp_tunnel_add(struct net_device *dev,
 		return;
 	}
 
-	schedule_work(&bp->sp_task);
+	bnxt_queue_sp_work(bp);
 }
 
 static void bnxt_udp_tunnel_del(struct net_device *dev,
@@ -7572,7 +7596,7 @@ static void bnxt_udp_tunnel_del(struct net_device *dev,
 		return;
 	}
 
-	schedule_work(&bp->sp_task);
+	bnxt_queue_sp_work(bp);
 }
 
 static int bnxt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
@@ -7720,7 +7744,7 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	pci_disable_pcie_error_reporting(pdev);
 	unregister_netdev(dev);
 	bnxt_shutdown_tc(bp);
-	cancel_work_sync(&bp->sp_task);
+	bnxt_cancel_sp_work(bp);
 	bp->sp_event = 0;
 
 	bnxt_clear_int_mode(bp);
@@ -7748,6 +7772,7 @@ static int bnxt_probe_phy(struct bnxt *bp)
 			   rc);
 		return rc;
 	}
+	mutex_init(&bp->link_lock);
 
 	rc = bnxt_update_link(bp, false);
 	if (rc) {
@@ -7946,7 +7971,7 @@ static void bnxt_parse_log_pcie_link(struct bnxt *bp)
 	enum pcie_link_width width = PCIE_LNK_WIDTH_UNKNOWN;
 	enum pci_bus_speed speed = PCI_SPEED_UNKNOWN;
 
-	if (pcie_get_minimum_link(bp->pdev, &speed, &width) ||
+	if (pcie_get_minimum_link(pci_physfn(bp->pdev), &speed, &width) ||
 	    speed == PCI_SPEED_UNKNOWN || width == PCIE_LNK_WIDTH_UNKNOWN)
 		netdev_info(bp->dev, "Failed to determine PCIe Link Info\n");
 	else
@@ -8138,8 +8163,17 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	else
 		device_set_wakeup_capable(&pdev->dev, false);
 
-	if (BNXT_PF(bp))
+	if (BNXT_PF(bp)) {
+		if (!bnxt_pf_wq) {
+			bnxt_pf_wq =
+				create_singlethread_workqueue("bnxt_pf_wq");
+			if (!bnxt_pf_wq) {
+				dev_err(&pdev->dev, "Unable to create workqueue.\n");
+				goto init_err_pci_clean;
+			}
+		}
 		bnxt_init_tc(bp);
+	}
 
 	rc = register_netdev(dev);
 	if (rc)
@@ -8375,4 +8409,17 @@ static struct pci_driver bnxt_pci_driver = {
 #endif
 };
 
-module_pci_driver(bnxt_pci_driver);
+static int __init bnxt_init(void)
+{
+	return pci_register_driver(&bnxt_pci_driver);
+}
+
+static void __exit bnxt_exit(void)
+{
+	pci_unregister_driver(&bnxt_pci_driver);
+	if (bnxt_pf_wq)
+		destroy_workqueue(bnxt_pf_wq);
+}
+
+module_init(bnxt_init);
+module_exit(bnxt_exit);

drivers/net/ethernet/broadcom/bnxt/bnxt.h

@@ -1290,6 +1290,10 @@ struct bnxt {
 	unsigned long		*ntp_fltr_bmap;
 	int			ntp_fltr_count;
 
+	/* To protect link related settings during link changes and
+	 * ethtool settings changes.
+	 */
+	struct mutex		link_lock;
 	struct bnxt_link_info	link_info;
 	struct ethtool_eee	eee;
 	u32			lpi_tmr_lo;
@@ -1358,6 +1362,7 @@ void bnxt_set_ring_params(struct bnxt *);
 int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode);
 void bnxt_hwrm_cmd_hdr_init(struct bnxt *, void *, u16, u16, u16);
 int _hwrm_send_message(struct bnxt *, void *, u32, int);
+int _hwrm_send_message_silent(struct bnxt *bp, void *msg, u32 len, int timeout);
 int hwrm_send_message(struct bnxt *, void *, u32, int);
 int hwrm_send_message_silent(struct bnxt *, void *, u32, int);
 int bnxt_hwrm_func_rgtr_async_events(struct bnxt *bp, unsigned long *bmap,