Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 746 insertions, 0 deletions

diff --git a/drivers/net/ethernet/apm/xgene-v2/main.c b/drivers/net/ethernet/apm/xgene-v2/main.c
new file mode 100644
index 000000000..379d19d18
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/main.c
@@ -0,0 +1,746 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ *	      Keyur Chudgar <kchudgar@apm.com>
+ */
+
+#include "main.h"
+
+static const struct acpi_device_id xge_acpi_match[];
+
+static int xge_get_resources(struct xge_pdata *pdata)
+{
+	struct platform_device *pdev;
+	struct net_device *ndev;
+	int phy_mode, ret = 0;
+	struct resource *res;
+	struct device *dev;
+
+	pdev = pdata->pdev;
+	dev = &pdev->dev;
+	ndev = pdata->ndev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(dev, "Resource enet_csr not defined\n");
+		return -ENODEV;
+	}
+
+	pdata->resources.base_addr = devm_ioremap(dev, res->start,
+						  resource_size(res));
+	if (!pdata->resources.base_addr) {
+		dev_err(dev, "Unable to retrieve ENET Port CSR region\n");
+		return -ENOMEM;
+	}
+
+	if (device_get_ethdev_address(dev, ndev))
+		eth_hw_addr_random(ndev);
+
+	memcpy(ndev->perm_addr, ndev->dev_addr, ndev->addr_len);
+
+	phy_mode = device_get_phy_mode(dev);
+	if (phy_mode < 0) {
+		dev_err(dev, "Unable to get phy-connection-type\n");
+		return phy_mode;
+	}
+	pdata->resources.phy_mode = phy_mode;
+
+	if (pdata->resources.phy_mode != PHY_INTERFACE_MODE_RGMII) {
+		dev_err(dev, "Incorrect phy-connection-type specified\n");
+		return -ENODEV;
+	}
+
+	ret = platform_get_irq(pdev, 0);
+	if (ret < 0)
+		return ret;
+	pdata->resources.irq = ret;
+
+	return 0;
+}
+
+static int xge_refill_buffers(struct net_device *ndev, u32 nbuf)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct xge_desc_ring *ring = pdata->rx_ring;
+	const u8 slots = XGENE_ENET_NUM_DESC - 1;
+	struct device *dev = &pdata->pdev->dev;
+	struct xge_raw_desc *raw_desc;
+	u64 addr_lo, addr_hi;
+	u8 tail = ring->tail;
+	struct sk_buff *skb;
+	dma_addr_t dma_addr;
+	u16 len;
+	int i;
+
+	for (i = 0; i < nbuf; i++) {
+		raw_desc = &ring->raw_desc[tail];
+
+		len = XGENE_ENET_STD_MTU;
+		skb = netdev_alloc_skb(ndev, len);
+		if (unlikely(!skb))
+			return -ENOMEM;
+
+		dma_addr = dma_map_single(dev, skb->data, len, DMA_FROM_DEVICE);
+		if (dma_mapping_error(dev, dma_addr)) {
+			netdev_err(ndev, "DMA mapping error\n");
+			dev_kfree_skb_any(skb);
+			return -EINVAL;
+		}
+
+		ring->pkt_info[tail].skb = skb;
+		ring->pkt_info[tail].dma_addr = dma_addr;
+
+		addr_hi = GET_BITS(NEXT_DESC_ADDRH, le64_to_cpu(raw_desc->m1));
+		addr_lo = GET_BITS(NEXT_DESC_ADDRL, le64_to_cpu(raw_desc->m1));
+		raw_desc->m1 = cpu_to_le64(SET_BITS(NEXT_DESC_ADDRL, addr_lo) |
+					   SET_BITS(NEXT_DESC_ADDRH, addr_hi) |
+					   SET_BITS(PKT_ADDRH,
+						    upper_32_bits(dma_addr)));
+
+		dma_wmb();
+		raw_desc->m0 = cpu_to_le64(SET_BITS(PKT_ADDRL, dma_addr) |
+					   SET_BITS(E, 1));
+		tail = (tail + 1) & slots;
+	}
+
+	ring->tail = tail;
+
+	return 0;
+}
+
+static int xge_init_hw(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	int ret;
+
+	ret = xge_port_reset(ndev);
+	if (ret)
+		return ret;
+
+	xge_port_init(ndev);
+	pdata->nbufs = NUM_BUFS;
+
+	return 0;
+}
+
+static irqreturn_t xge_irq(const int irq, void *data)
+{
+	struct xge_pdata *pdata = data;
+
+	if (napi_schedule_prep(&pdata->napi)) {
+		xge_intr_disable(pdata);
+		__napi_schedule(&pdata->napi);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int xge_request_irq(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	int ret;
+
+	snprintf(pdata->irq_name, IRQ_ID_SIZE, "%s", ndev->name);
+
+	ret = request_irq(pdata->resources.irq, xge_irq, 0, pdata->irq_name,
+			  pdata);
+	if (ret)
+		netdev_err(ndev, "Failed to request irq %s\n", pdata->irq_name);
+
+	return ret;
+}
+
+static void xge_free_irq(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+
+	free_irq(pdata->resources.irq, pdata);
+}
+
+static bool is_tx_slot_available(struct xge_raw_desc *raw_desc)
+{
+	if (GET_BITS(E, le64_to_cpu(raw_desc->m0)) &&
+	    (GET_BITS(PKT_SIZE, le64_to_cpu(raw_desc->m0)) == SLOT_EMPTY))
+		return true;
+
+	return false;
+}
+
+static netdev_tx_t xge_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct device *dev = &pdata->pdev->dev;
+	struct xge_desc_ring *tx_ring;
+	struct xge_raw_desc *raw_desc;
+	static dma_addr_t dma_addr;
+	u64 addr_lo, addr_hi;
+	void *pkt_buf;
+	u8 tail;
+	u16 len;
+
+	tx_ring = pdata->tx_ring;
+	tail = tx_ring->tail;
+	len = skb_headlen(skb);
+	raw_desc = &tx_ring->raw_desc[tail];
+
+	if (!is_tx_slot_available(raw_desc)) {
+		netif_stop_queue(ndev);
+		return NETDEV_TX_BUSY;
+	}
+
+	/* Packet buffers should be 64B aligned */
+	pkt_buf = dma_alloc_coherent(dev, XGENE_ENET_STD_MTU, &dma_addr,
+				     GFP_ATOMIC);
+	if (unlikely(!pkt_buf)) {
+		dev_kfree_skb_any(skb);
+		return NETDEV_TX_OK;
+	}
+	memcpy(pkt_buf, skb->data, len);
+
+	addr_hi = GET_BITS(NEXT_DESC_ADDRH, le64_to_cpu(raw_desc->m1));
+	addr_lo = GET_BITS(NEXT_DESC_ADDRL, le64_to_cpu(raw_desc->m1));
+	raw_desc->m1 = cpu_to_le64(SET_BITS(NEXT_DESC_ADDRL, addr_lo) |
+				   SET_BITS(NEXT_DESC_ADDRH, addr_hi) |
+				   SET_BITS(PKT_ADDRH,
+					    upper_32_bits(dma_addr)));
+
+	tx_ring->pkt_info[tail].skb = skb;
+	tx_ring->pkt_info[tail].dma_addr = dma_addr;
+	tx_ring->pkt_info[tail].pkt_buf = pkt_buf;
+
+	dma_wmb();
+
+	raw_desc->m0 = cpu_to_le64(SET_BITS(PKT_ADDRL, dma_addr) |
+				   SET_BITS(PKT_SIZE, len) |
+				   SET_BITS(E, 0));
+	skb_tx_timestamp(skb);
+	xge_wr_csr(pdata, DMATXCTRL, 1);
+
+	tx_ring->tail = (tail + 1) & (XGENE_ENET_NUM_DESC - 1);
+
+	return NETDEV_TX_OK;
+}
+
+static bool is_tx_hw_done(struct xge_raw_desc *raw_desc)
+{
+	if (GET_BITS(E, le64_to_cpu(raw_desc->m0)) &&
+	    !GET_BITS(PKT_SIZE, le64_to_cpu(raw_desc->m0)))
+		return true;
+
+	return false;
+}
+
+static void xge_txc_poll(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct device *dev = &pdata->pdev->dev;
+	struct xge_desc_ring *tx_ring;
+	struct xge_raw_desc *raw_desc;
+	dma_addr_t dma_addr;
+	struct sk_buff *skb;
+	void *pkt_buf;
+	u32 data;
+	u8 head;
+
+	tx_ring = pdata->tx_ring;
+	head = tx_ring->head;
+
+	data = xge_rd_csr(pdata, DMATXSTATUS);
+	if (!GET_BITS(TXPKTCOUNT, data))
+		return;
+
+	while (1) {
+		raw_desc = &tx_ring->raw_desc[head];
+
+		if (!is_tx_hw_done(raw_desc))
+			break;
+
+		dma_rmb();
+
+		skb = tx_ring->pkt_info[head].skb;
+		dma_addr = tx_ring->pkt_info[head].dma_addr;
+		pkt_buf = tx_ring->pkt_info[head].pkt_buf;
+		pdata->stats.tx_packets++;
+		pdata->stats.tx_bytes += skb->len;
+		dma_free_coherent(dev, XGENE_ENET_STD_MTU, pkt_buf, dma_addr);
+		dev_kfree_skb_any(skb);
+
+		/* clear pktstart address and pktsize */
+		raw_desc->m0 = cpu_to_le64(SET_BITS(E, 1) |
+					   SET_BITS(PKT_SIZE, SLOT_EMPTY));
+		xge_wr_csr(pdata, DMATXSTATUS, 1);
+
+		head = (head + 1) & (XGENE_ENET_NUM_DESC - 1);
+	}
+
+	if (netif_queue_stopped(ndev))
+		netif_wake_queue(ndev);
+
+	tx_ring->head = head;
+}
+
+static int xge_rx_poll(struct net_device *ndev, unsigned int budget)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct device *dev = &pdata->pdev->dev;
+	struct xge_desc_ring *rx_ring;
+	struct xge_raw_desc *raw_desc;
+	struct sk_buff *skb;
+	dma_addr_t dma_addr;
+	int processed = 0;
+	u8 head, rx_error;
+	int i, ret;
+	u32 data;
+	u16 len;
+
+	rx_ring = pdata->rx_ring;
+	head = rx_ring->head;
+
+	data = xge_rd_csr(pdata, DMARXSTATUS);
+	if (!GET_BITS(RXPKTCOUNT, data))
+		return 0;
+
+	for (i = 0; i < budget; i++) {
+		raw_desc = &rx_ring->raw_desc[head];
+
+		if (GET_BITS(E, le64_to_cpu(raw_desc->m0)))
+			break;
+
+		dma_rmb();
+
+		skb = rx_ring->pkt_info[head].skb;
+		rx_ring->pkt_info[head].skb = NULL;
+		dma_addr = rx_ring->pkt_info[head].dma_addr;
+		len = GET_BITS(PKT_SIZE, le64_to_cpu(raw_desc->m0));
+		dma_unmap_single(dev, dma_addr, XGENE_ENET_STD_MTU,
+				 DMA_FROM_DEVICE);
+
+		rx_error = GET_BITS(D, le64_to_cpu(raw_desc->m2));
+		if (unlikely(rx_error)) {
+			pdata->stats.rx_errors++;
+			dev_kfree_skb_any(skb);
+			goto out;
+		}
+
+		skb_put(skb, len);
+		skb->protocol = eth_type_trans(skb, ndev);
+
+		pdata->stats.rx_packets++;
+		pdata->stats.rx_bytes += len;
+		napi_gro_receive(&pdata->napi, skb);
+out:
+		ret = xge_refill_buffers(ndev, 1);
+		xge_wr_csr(pdata, DMARXSTATUS, 1);
+		xge_wr_csr(pdata, DMARXCTRL, 1);
+
+		if (ret)
+			break;
+
+		head = (head + 1) & (XGENE_ENET_NUM_DESC - 1);
+		processed++;
+	}
+
+	rx_ring->head = head;
+
+	return processed;
+}
+
+static void xge_delete_desc_ring(struct net_device *ndev,
+				 struct xge_desc_ring *ring)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct device *dev = &pdata->pdev->dev;
+	u16 size;
+
+	if (!ring)
+		return;
+
+	size = XGENE_ENET_DESC_SIZE * XGENE_ENET_NUM_DESC;
+	if (ring->desc_addr)
+		dma_free_coherent(dev, size, ring->desc_addr, ring->dma_addr);
+
+	kfree(ring->pkt_info);
+	kfree(ring);
+}
+
+static void xge_free_buffers(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct xge_desc_ring *ring = pdata->rx_ring;
+	struct device *dev = &pdata->pdev->dev;
+	struct sk_buff *skb;
+	dma_addr_t dma_addr;
+	int i;
+
+	for (i = 0; i < XGENE_ENET_NUM_DESC; i++) {
+		skb = ring->pkt_info[i].skb;
+		dma_addr = ring->pkt_info[i].dma_addr;
+
+		if (!skb)
+			continue;
+
+		dma_unmap_single(dev, dma_addr, XGENE_ENET_STD_MTU,
+				 DMA_FROM_DEVICE);
+		dev_kfree_skb_any(skb);
+	}
+}
+
+static void xge_delete_desc_rings(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+
+	xge_txc_poll(ndev);
+	xge_delete_desc_ring(ndev, pdata->tx_ring);
+
+	xge_rx_poll(ndev, 64);
+	xge_free_buffers(ndev);
+	xge_delete_desc_ring(ndev, pdata->rx_ring);
+}
+
+static struct xge_desc_ring *xge_create_desc_ring(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct device *dev = &pdata->pdev->dev;
+	struct xge_desc_ring *ring;
+	u16 size;
+
+	ring = kzalloc(sizeof(*ring), GFP_KERNEL);
+	if (!ring)
+		return NULL;
+
+	ring->ndev = ndev;
+
+	size = XGENE_ENET_DESC_SIZE * XGENE_ENET_NUM_DESC;
+	ring->desc_addr = dma_alloc_coherent(dev, size, &ring->dma_addr,
+					     GFP_KERNEL);
+	if (!ring->desc_addr)
+		goto err;
+
+	ring->pkt_info = kcalloc(XGENE_ENET_NUM_DESC, sizeof(*ring->pkt_info),
+				 GFP_KERNEL);
+	if (!ring->pkt_info)
+		goto err;
+
+	xge_setup_desc(ring);
+
+	return ring;
+
+err:
+	xge_delete_desc_ring(ndev, ring);
+
+	return NULL;
+}
+
+static int xge_create_desc_rings(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct xge_desc_ring *ring;
+	int ret;
+
+	/* create tx ring */
+	ring = xge_create_desc_ring(ndev);
+	if (!ring)
+		goto err;
+
+	pdata->tx_ring = ring;
+	xge_update_tx_desc_addr(pdata);
+
+	/* create rx ring */
+	ring = xge_create_desc_ring(ndev);
+	if (!ring)
+		goto err;
+
+	pdata->rx_ring = ring;
+	xge_update_rx_desc_addr(pdata);
+
+	ret = xge_refill_buffers(ndev, XGENE_ENET_NUM_DESC);
+	if (ret)
+		goto err;
+
+	return 0;
+err:
+	xge_delete_desc_rings(ndev);
+
+	return -ENOMEM;
+}
+
+static int xge_open(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	int ret;
+
+	ret = xge_create_desc_rings(ndev);
+	if (ret)
+		return ret;
+
+	napi_enable(&pdata->napi);
+	ret = xge_request_irq(ndev);
+	if (ret)
+		return ret;
+
+	xge_intr_enable(pdata);
+	xge_wr_csr(pdata, DMARXCTRL, 1);
+
+	phy_start(ndev->phydev);
+	xge_mac_enable(pdata);
+	netif_start_queue(ndev);
+
+	return 0;
+}
+
+static int xge_close(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+
+	netif_stop_queue(ndev);
+	xge_mac_disable(pdata);
+	phy_stop(ndev->phydev);
+
+	xge_intr_disable(pdata);
+	xge_free_irq(ndev);
+	napi_disable(&pdata->napi);
+	xge_delete_desc_rings(ndev);
+
+	return 0;
+}
+
+static int xge_napi(struct napi_struct *napi, const int budget)
+{
+	struct net_device *ndev = napi->dev;
+	struct xge_pdata *pdata;
+	int processed;
+
+	pdata = netdev_priv(ndev);
+
+	xge_txc_poll(ndev);
+	processed = xge_rx_poll(ndev, budget);
+
+	if (processed < budget) {
+		napi_complete_done(napi, processed);
+		xge_intr_enable(pdata);
+	}
+
+	return processed;
+}
+
+static int xge_set_mac_addr(struct net_device *ndev, void *addr)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	int ret;
+
+	ret = eth_mac_addr(ndev, addr);
+	if (ret)
+		return ret;
+
+	xge_mac_set_station_addr(pdata);
+
+	return 0;
+}
+
+static bool is_tx_pending(struct xge_raw_desc *raw_desc)
+{
+	if (!GET_BITS(E, le64_to_cpu(raw_desc->m0)))
+		return true;
+
+	return false;
+}
+
+static void xge_free_pending_skb(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct device *dev = &pdata->pdev->dev;
+	struct xge_desc_ring *tx_ring;
+	struct xge_raw_desc *raw_desc;
+	dma_addr_t dma_addr;
+	struct sk_buff *skb;
+	void *pkt_buf;
+	int i;
+
+	tx_ring = pdata->tx_ring;
+
+	for (i = 0; i < XGENE_ENET_NUM_DESC; i++) {
+		raw_desc = &tx_ring->raw_desc[i];
+
+		if (!is_tx_pending(raw_desc))
+			continue;
+
+		skb = tx_ring->pkt_info[i].skb;
+		dma_addr = tx_ring->pkt_info[i].dma_addr;
+		pkt_buf = tx_ring->pkt_info[i].pkt_buf;
+		dma_free_coherent(dev, XGENE_ENET_STD_MTU, pkt_buf, dma_addr);
+		dev_kfree_skb_any(skb);
+	}
+}
+
+static void xge_timeout(struct net_device *ndev, unsigned int txqueue)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+
+	rtnl_lock();
+
+	if (!netif_running(ndev))
+		goto out;
+
+	netif_stop_queue(ndev);
+	xge_intr_disable(pdata);
+	napi_disable(&pdata->napi);
+
+	xge_wr_csr(pdata, DMATXCTRL, 0);
+	xge_txc_poll(ndev);
+	xge_free_pending_skb(ndev);
+	xge_wr_csr(pdata, DMATXSTATUS, ~0U);
+
+	xge_setup_desc(pdata->tx_ring);
+	xge_update_tx_desc_addr(pdata);
+	xge_mac_init(pdata);
+
+	napi_enable(&pdata->napi);
+	xge_intr_enable(pdata);
+	xge_mac_enable(pdata);
+	netif_start_queue(ndev);
+
+out:
+	rtnl_unlock();
+}
+
+static void xge_get_stats64(struct net_device *ndev,
+			    struct rtnl_link_stats64 *storage)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct xge_stats *stats = &pdata->stats;
+
+	storage->tx_packets += stats->tx_packets;
+	storage->tx_bytes += stats->tx_bytes;
+
+	storage->rx_packets += stats->rx_packets;
+	storage->rx_bytes += stats->rx_bytes;
+	storage->rx_errors += stats->rx_errors;
+}
+
+static const struct net_device_ops xgene_ndev_ops = {
+	.ndo_open = xge_open,
+	.ndo_stop = xge_close,
+	.ndo_start_xmit = xge_start_xmit,
+	.ndo_set_mac_address = xge_set_mac_addr,
+	.ndo_tx_timeout = xge_timeout,
+	.ndo_get_stats64 = xge_get_stats64,
+};
+
+static int xge_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct net_device *ndev;
+	struct xge_pdata *pdata;
+	int ret;
+
+	ndev = alloc_etherdev(sizeof(*pdata));
+	if (!ndev)
+		return -ENOMEM;
+
+	pdata = netdev_priv(ndev);
+
+	pdata->pdev = pdev;
+	pdata->ndev = ndev;
+	SET_NETDEV_DEV(ndev, dev);
+	platform_set_drvdata(pdev, pdata);
+	ndev->netdev_ops = &xgene_ndev_ops;
+
+	ndev->features |= NETIF_F_GSO |
+			  NETIF_F_GRO;
+
+	ret = xge_get_resources(pdata);
+	if (ret)
+		goto err;
+
+	ndev->hw_features = ndev->features;
+	xge_set_ethtool_ops(ndev);
+
+	ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(64));
+	if (ret) {
+		netdev_err(ndev, "No usable DMA configuration\n");
+		goto err;
+	}
+
+	ret = xge_init_hw(ndev);
+	if (ret)
+		goto err;
+
+	ret = xge_mdio_config(ndev);
+	if (ret)
+		goto err;
+
+	netif_napi_add(ndev, &pdata->napi, xge_napi);
+
+	ret = register_netdev(ndev);
+	if (ret) {
+		netdev_err(ndev, "Failed to register netdev\n");
+		goto err_mdio_remove;
+	}
+
+	return 0;
+
+err_mdio_remove:
+	xge_mdio_remove(ndev);
+err:
+	free_netdev(ndev);
+
+	return ret;
+}
+
+static int xge_remove(struct platform_device *pdev)
+{
+	struct xge_pdata *pdata;
+	struct net_device *ndev;
+
+	pdata = platform_get_drvdata(pdev);
+	ndev = pdata->ndev;
+
+	rtnl_lock();
+	if (netif_running(ndev))
+		dev_close(ndev);
+	rtnl_unlock();
+
+	xge_mdio_remove(ndev);
+	unregister_netdev(ndev);
+	free_netdev(ndev);
+
+	return 0;
+}
+
+static void xge_shutdown(struct platform_device *pdev)
+{
+	struct xge_pdata *pdata;
+
+	pdata = platform_get_drvdata(pdev);
+	if (!pdata)
+		return;
+
+	if (!pdata->ndev)
+		return;
+
+	xge_remove(pdev);
+}
+
+static const struct acpi_device_id xge_acpi_match[] = {
+	{ "APMC0D80" },
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, xge_acpi_match);
+
+static struct platform_driver xge_driver = {
+	.driver = {
+		   .name = "xgene-enet-v2",
+		   .acpi_match_table = ACPI_PTR(xge_acpi_match),
+	},
+	.probe = xge_probe,
+	.remove = xge_remove,
+	.shutdown = xge_shutdown,
+};
+module_platform_driver(xge_driver);
+
+MODULE_DESCRIPTION("APM X-Gene SoC Ethernet v2 driver");
+MODULE_AUTHOR("Iyappan Subramanian <isubramanian@apm.com>");
+MODULE_LICENSE("GPL");