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, 772 insertions, 0 deletions

diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c
new file mode 100644
index 000000000..3115b2c12
--- /dev/null
+++ b/drivers/net/ethernet/qualcomm/emac/emac.c
@@ -0,0 +1,772 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2013-2016, The Linux Foundation. All rights reserved.
+ */
+
+/* Qualcomm Technologies, Inc. EMAC Gigabit Ethernet Driver */
+
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_net.h>
+#include <linux/of_device.h>
+#include <linux/phy.h>
+#include <linux/platform_device.h>
+#include <linux/acpi.h>
+#include "emac.h"
+#include "emac-mac.h"
+#include "emac-phy.h"
+#include "emac-sgmii.h"
+
+#define EMAC_MSG_DEFAULT (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK |  \
+		NETIF_MSG_TIMER | NETIF_MSG_IFDOWN | NETIF_MSG_IFUP)
+
+#define EMAC_RRD_SIZE					     4
+/* The RRD size if timestamping is enabled: */
+#define EMAC_TS_RRD_SIZE				     6
+#define EMAC_TPD_SIZE					     4
+#define EMAC_RFD_SIZE					     2
+
+#define REG_MAC_RX_STATUS_BIN		 EMAC_RXMAC_STATC_REG0
+#define REG_MAC_RX_STATUS_END		EMAC_RXMAC_STATC_REG22
+#define REG_MAC_TX_STATUS_BIN		 EMAC_TXMAC_STATC_REG0
+#define REG_MAC_TX_STATUS_END		EMAC_TXMAC_STATC_REG24
+
+#define RXQ0_NUM_RFD_PREF_DEF				     8
+#define TXQ0_NUM_TPD_PREF_DEF				     5
+
+#define EMAC_PREAMBLE_DEF				     7
+
+#define DMAR_DLY_CNT_DEF				    15
+#define DMAW_DLY_CNT_DEF				     4
+
+#define IMR_NORMAL_MASK		(ISR_ERROR | ISR_OVER | ISR_TX_PKT)
+
+#define ISR_TX_PKT      (\
+	TX_PKT_INT      |\
+	TX_PKT_INT1     |\
+	TX_PKT_INT2     |\
+	TX_PKT_INT3)
+
+#define ISR_OVER        (\
+	RFD0_UR_INT     |\
+	RFD1_UR_INT     |\
+	RFD2_UR_INT     |\
+	RFD3_UR_INT     |\
+	RFD4_UR_INT     |\
+	RXF_OF_INT      |\
+	TXF_UR_INT)
+
+#define ISR_ERROR       (\
+	DMAR_TO_INT     |\
+	DMAW_TO_INT     |\
+	TXQ_TO_INT)
+
+/* in sync with enum emac_clk_id */
+static const char * const emac_clk_name[] = {
+	"axi_clk", "cfg_ahb_clk", "high_speed_clk", "mdio_clk", "tx_clk",
+	"rx_clk", "sys_clk"
+};
+
+void emac_reg_update32(void __iomem *addr, u32 mask, u32 val)
+{
+	u32 data = readl(addr);
+
+	writel(((data & ~mask) | val), addr);
+}
+
+/* reinitialize */
+int emac_reinit_locked(struct emac_adapter *adpt)
+{
+	int ret;
+
+	mutex_lock(&adpt->reset_lock);
+
+	emac_mac_down(adpt);
+	emac_sgmii_reset(adpt);
+	ret = emac_mac_up(adpt);
+
+	mutex_unlock(&adpt->reset_lock);
+
+	return ret;
+}
+
+/* NAPI */
+static int emac_napi_rtx(struct napi_struct *napi, int budget)
+{
+	struct emac_rx_queue *rx_q =
+		container_of(napi, struct emac_rx_queue, napi);
+	struct emac_adapter *adpt = netdev_priv(rx_q->netdev);
+	struct emac_irq *irq = rx_q->irq;
+	int work_done = 0;
+
+	emac_mac_rx_process(adpt, rx_q, &work_done, budget);
+
+	if (work_done < budget) {
+		napi_complete_done(napi, work_done);
+
+		irq->mask |= rx_q->intr;
+		writel(irq->mask, adpt->base + EMAC_INT_MASK);
+	}
+
+	return work_done;
+}
+
+/* Transmit the packet */
+static netdev_tx_t emac_start_xmit(struct sk_buff *skb,
+				   struct net_device *netdev)
+{
+	struct emac_adapter *adpt = netdev_priv(netdev);
+
+	return emac_mac_tx_buf_send(adpt, &adpt->tx_q, skb);
+}
+
+static irqreturn_t emac_isr(int _irq, void *data)
+{
+	struct emac_irq *irq = data;
+	struct emac_adapter *adpt =
+		container_of(irq, struct emac_adapter, irq);
+	struct emac_rx_queue *rx_q = &adpt->rx_q;
+	u32 isr, status;
+
+	/* disable the interrupt */
+	writel(0, adpt->base + EMAC_INT_MASK);
+
+	isr = readl_relaxed(adpt->base + EMAC_INT_STATUS);
+
+	status = isr & irq->mask;
+	if (status == 0)
+		goto exit;
+
+	if (status & ISR_ERROR) {
+		net_err_ratelimited("%s: error interrupt 0x%lx\n",
+				    adpt->netdev->name, status & ISR_ERROR);
+		/* reset MAC */
+		schedule_work(&adpt->work_thread);
+	}
+
+	/* Schedule the napi for receive queue with interrupt
+	 * status bit set
+	 */
+	if (status & rx_q->intr) {
+		if (napi_schedule_prep(&rx_q->napi)) {
+			irq->mask &= ~rx_q->intr;
+			__napi_schedule(&rx_q->napi);
+		}
+	}
+
+	if (status & TX_PKT_INT)
+		emac_mac_tx_process(adpt, &adpt->tx_q);
+
+	if (status & ISR_OVER)
+		net_warn_ratelimited("%s: TX/RX overflow interrupt\n",
+				     adpt->netdev->name);
+
+exit:
+	/* enable the interrupt */
+	writel(irq->mask, adpt->base + EMAC_INT_MASK);
+
+	return IRQ_HANDLED;
+}
+
+/* Configure VLAN tag strip/insert feature */
+static int emac_set_features(struct net_device *netdev,
+			     netdev_features_t features)
+{
+	netdev_features_t changed = features ^ netdev->features;
+	struct emac_adapter *adpt = netdev_priv(netdev);
+
+	/* We only need to reprogram the hardware if the VLAN tag features
+	 * have changed, and if it's already running.
+	 */
+	if (!(changed & (NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX)))
+		return 0;
+
+	if (!netif_running(netdev))
+		return 0;
+
+	/* emac_mac_mode_config() uses netdev->features to configure the EMAC,
+	 * so make sure it's set first.
+	 */
+	netdev->features = features;
+
+	return emac_reinit_locked(adpt);
+}
+
+/* Configure Multicast and Promiscuous modes */
+static void emac_rx_mode_set(struct net_device *netdev)
+{
+	struct emac_adapter *adpt = netdev_priv(netdev);
+	struct netdev_hw_addr *ha;
+
+	emac_mac_mode_config(adpt);
+
+	/* update multicast address filtering */
+	emac_mac_multicast_addr_clear(adpt);
+	netdev_for_each_mc_addr(ha, netdev)
+		emac_mac_multicast_addr_set(adpt, ha->addr);
+}
+
+/* Change the Maximum Transfer Unit (MTU) */
+static int emac_change_mtu(struct net_device *netdev, int new_mtu)
+{
+	struct emac_adapter *adpt = netdev_priv(netdev);
+
+	netif_dbg(adpt, hw, adpt->netdev,
+		  "changing MTU from %d to %d\n", netdev->mtu,
+		  new_mtu);
+	netdev->mtu = new_mtu;
+
+	if (netif_running(netdev))
+		return emac_reinit_locked(adpt);
+
+	return 0;
+}
+
+/* Called when the network interface is made active */
+static int emac_open(struct net_device *netdev)
+{
+	struct emac_adapter *adpt = netdev_priv(netdev);
+	struct emac_irq	*irq = &adpt->irq;
+	int ret;
+
+	ret = request_irq(irq->irq, emac_isr, 0, "emac-core0", irq);
+	if (ret) {
+		netdev_err(adpt->netdev, "could not request emac-core0 irq\n");
+		return ret;
+	}
+
+	/* allocate rx/tx dma buffer & descriptors */
+	ret = emac_mac_rx_tx_rings_alloc_all(adpt);
+	if (ret) {
+		netdev_err(adpt->netdev, "error allocating rx/tx rings\n");
+		free_irq(irq->irq, irq);
+		return ret;
+	}
+
+	ret = emac_sgmii_open(adpt);
+	if (ret) {
+		emac_mac_rx_tx_rings_free_all(adpt);
+		free_irq(irq->irq, irq);
+		return ret;
+	}
+
+	ret = emac_mac_up(adpt);
+	if (ret) {
+		emac_mac_rx_tx_rings_free_all(adpt);
+		free_irq(irq->irq, irq);
+		emac_sgmii_close(adpt);
+		return ret;
+	}
+
+	return 0;
+}
+
+/* Called when the network interface is disabled */
+static int emac_close(struct net_device *netdev)
+{
+	struct emac_adapter *adpt = netdev_priv(netdev);
+
+	mutex_lock(&adpt->reset_lock);
+
+	emac_sgmii_close(adpt);
+	emac_mac_down(adpt);
+	emac_mac_rx_tx_rings_free_all(adpt);
+
+	free_irq(adpt->irq.irq, &adpt->irq);
+
+	mutex_unlock(&adpt->reset_lock);
+
+	return 0;
+}
+
+/* Respond to a TX hang */
+static void emac_tx_timeout(struct net_device *netdev, unsigned int txqueue)
+{
+	struct emac_adapter *adpt = netdev_priv(netdev);
+
+	schedule_work(&adpt->work_thread);
+}
+
+/**
+ * emac_update_hw_stats - read the EMAC stat registers
+ * @adpt: pointer to adapter struct
+ *
+ * Reads the stats registers and write the values to adpt->stats.
+ *
+ * adpt->stats.lock must be held while calling this function,
+ * and while reading from adpt->stats.
+ */
+void emac_update_hw_stats(struct emac_adapter *adpt)
+{
+	struct emac_stats *stats = &adpt->stats;
+	u64 *stats_itr = &adpt->stats.rx_ok;
+	void __iomem *base = adpt->base;
+	unsigned int addr;
+
+	addr = REG_MAC_RX_STATUS_BIN;
+	while (addr <= REG_MAC_RX_STATUS_END) {
+		*stats_itr += readl_relaxed(base + addr);
+		stats_itr++;
+		addr += sizeof(u32);
+	}
+
+	/* additional rx status */
+	stats->rx_crc_align += readl_relaxed(base + EMAC_RXMAC_STATC_REG23);
+	stats->rx_jabbers += readl_relaxed(base + EMAC_RXMAC_STATC_REG24);
+
+	/* update tx status */
+	addr = REG_MAC_TX_STATUS_BIN;
+	stats_itr = &stats->tx_ok;
+
+	while (addr <= REG_MAC_TX_STATUS_END) {
+		*stats_itr += readl_relaxed(base + addr);
+		stats_itr++;
+		addr += sizeof(u32);
+	}
+
+	/* additional tx status */
+	stats->tx_col += readl_relaxed(base + EMAC_TXMAC_STATC_REG25);
+}
+
+/* Provide network statistics info for the interface */
+static void emac_get_stats64(struct net_device *netdev,
+			     struct rtnl_link_stats64 *net_stats)
+{
+	struct emac_adapter *adpt = netdev_priv(netdev);
+	struct emac_stats *stats = &adpt->stats;
+
+	spin_lock(&stats->lock);
+
+	emac_update_hw_stats(adpt);
+
+	/* return parsed statistics */
+	net_stats->rx_packets = stats->rx_ok;
+	net_stats->tx_packets = stats->tx_ok;
+	net_stats->rx_bytes = stats->rx_byte_cnt;
+	net_stats->tx_bytes = stats->tx_byte_cnt;
+	net_stats->multicast = stats->rx_mcast;
+	net_stats->collisions = stats->tx_1_col + stats->tx_2_col * 2 +
+				stats->tx_late_col + stats->tx_abort_col;
+
+	net_stats->rx_errors = stats->rx_frag + stats->rx_fcs_err +
+			       stats->rx_len_err + stats->rx_sz_ov +
+			       stats->rx_align_err;
+	net_stats->rx_fifo_errors = stats->rx_rxf_ov;
+	net_stats->rx_length_errors = stats->rx_len_err;
+	net_stats->rx_crc_errors = stats->rx_fcs_err;
+	net_stats->rx_frame_errors = stats->rx_align_err;
+	net_stats->rx_over_errors = stats->rx_rxf_ov;
+	net_stats->rx_missed_errors = stats->rx_rxf_ov;
+
+	net_stats->tx_errors = stats->tx_late_col + stats->tx_abort_col +
+			       stats->tx_underrun + stats->tx_trunc;
+	net_stats->tx_fifo_errors = stats->tx_underrun;
+	net_stats->tx_aborted_errors = stats->tx_abort_col;
+	net_stats->tx_window_errors = stats->tx_late_col;
+
+	spin_unlock(&stats->lock);
+}
+
+static const struct net_device_ops emac_netdev_ops = {
+	.ndo_open		= emac_open,
+	.ndo_stop		= emac_close,
+	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_start_xmit		= emac_start_xmit,
+	.ndo_set_mac_address	= eth_mac_addr,
+	.ndo_change_mtu		= emac_change_mtu,
+	.ndo_eth_ioctl		= phy_do_ioctl_running,
+	.ndo_tx_timeout		= emac_tx_timeout,
+	.ndo_get_stats64	= emac_get_stats64,
+	.ndo_set_features       = emac_set_features,
+	.ndo_set_rx_mode        = emac_rx_mode_set,
+};
+
+/* Watchdog task routine, called to reinitialize the EMAC */
+static void emac_work_thread(struct work_struct *work)
+{
+	struct emac_adapter *adpt =
+		container_of(work, struct emac_adapter, work_thread);
+
+	emac_reinit_locked(adpt);
+}
+
+/* Initialize various data structures  */
+static void emac_init_adapter(struct emac_adapter *adpt)
+{
+	u32 reg;
+
+	adpt->rrd_size = EMAC_RRD_SIZE;
+	adpt->tpd_size = EMAC_TPD_SIZE;
+	adpt->rfd_size = EMAC_RFD_SIZE;
+
+	/* descriptors */
+	adpt->tx_desc_cnt = EMAC_DEF_TX_DESCS;
+	adpt->rx_desc_cnt = EMAC_DEF_RX_DESCS;
+
+	/* dma */
+	adpt->dma_order = emac_dma_ord_out;
+	adpt->dmar_block = emac_dma_req_4096;
+	adpt->dmaw_block = emac_dma_req_128;
+	adpt->dmar_dly_cnt = DMAR_DLY_CNT_DEF;
+	adpt->dmaw_dly_cnt = DMAW_DLY_CNT_DEF;
+	adpt->tpd_burst = TXQ0_NUM_TPD_PREF_DEF;
+	adpt->rfd_burst = RXQ0_NUM_RFD_PREF_DEF;
+
+	/* irq moderator */
+	reg = ((EMAC_DEF_RX_IRQ_MOD >> 1) << IRQ_MODERATOR2_INIT_SHFT) |
+	      ((EMAC_DEF_TX_IRQ_MOD >> 1) << IRQ_MODERATOR_INIT_SHFT);
+	adpt->irq_mod = reg;
+
+	/* others */
+	adpt->preamble = EMAC_PREAMBLE_DEF;
+
+	/* default to automatic flow control */
+	adpt->automatic = true;
+
+	/* Disable single-pause-frame mode by default */
+	adpt->single_pause_mode = false;
+}
+
+/* Get the clock */
+static int emac_clks_get(struct platform_device *pdev,
+			 struct emac_adapter *adpt)
+{
+	unsigned int i;
+
+	for (i = 0; i < EMAC_CLK_CNT; i++) {
+		struct clk *clk = devm_clk_get(&pdev->dev, emac_clk_name[i]);
+
+		if (IS_ERR(clk)) {
+			dev_err(&pdev->dev,
+				"could not claim clock %s (error=%li)\n",
+				emac_clk_name[i], PTR_ERR(clk));
+
+			return PTR_ERR(clk);
+		}
+
+		adpt->clk[i] = clk;
+	}
+
+	return 0;
+}
+
+/* Initialize clocks */
+static int emac_clks_phase1_init(struct platform_device *pdev,
+				 struct emac_adapter *adpt)
+{
+	int ret;
+
+	/* On ACPI platforms, clocks are controlled by firmware and/or
+	 * ACPI, not by drivers.
+	 */
+	if (has_acpi_companion(&pdev->dev))
+		return 0;
+
+	ret = emac_clks_get(pdev, adpt);
+	if (ret)
+		return ret;
+
+	ret = clk_prepare_enable(adpt->clk[EMAC_CLK_AXI]);
+	if (ret)
+		return ret;
+
+	ret = clk_prepare_enable(adpt->clk[EMAC_CLK_CFG_AHB]);
+	if (ret)
+		goto disable_clk_axi;
+
+	ret = clk_set_rate(adpt->clk[EMAC_CLK_HIGH_SPEED], 19200000);
+	if (ret)
+		goto disable_clk_cfg_ahb;
+
+	ret = clk_prepare_enable(adpt->clk[EMAC_CLK_HIGH_SPEED]);
+	if (ret)
+		goto disable_clk_cfg_ahb;
+
+	return 0;
+
+disable_clk_cfg_ahb:
+	clk_disable_unprepare(adpt->clk[EMAC_CLK_CFG_AHB]);
+disable_clk_axi:
+	clk_disable_unprepare(adpt->clk[EMAC_CLK_AXI]);
+
+	return ret;
+}
+
+/* Enable clocks; needs emac_clks_phase1_init to be called before */
+static int emac_clks_phase2_init(struct platform_device *pdev,
+				 struct emac_adapter *adpt)
+{
+	int ret;
+
+	if (has_acpi_companion(&pdev->dev))
+		return 0;
+
+	ret = clk_set_rate(adpt->clk[EMAC_CLK_TX], 125000000);
+	if (ret)
+		return ret;
+
+	ret = clk_prepare_enable(adpt->clk[EMAC_CLK_TX]);
+	if (ret)
+		return ret;
+
+	ret = clk_set_rate(adpt->clk[EMAC_CLK_HIGH_SPEED], 125000000);
+	if (ret)
+		return ret;
+
+	ret = clk_set_rate(adpt->clk[EMAC_CLK_MDIO], 25000000);
+	if (ret)
+		return ret;
+
+	ret = clk_prepare_enable(adpt->clk[EMAC_CLK_MDIO]);
+	if (ret)
+		return ret;
+
+	ret = clk_prepare_enable(adpt->clk[EMAC_CLK_RX]);
+	if (ret)
+		return ret;
+
+	return clk_prepare_enable(adpt->clk[EMAC_CLK_SYS]);
+}
+
+static void emac_clks_teardown(struct emac_adapter *adpt)
+{
+
+	unsigned int i;
+
+	for (i = 0; i < EMAC_CLK_CNT; i++)
+		clk_disable_unprepare(adpt->clk[i]);
+}
+
+/* Get the resources */
+static int emac_probe_resources(struct platform_device *pdev,
+				struct emac_adapter *adpt)
+{
+	struct net_device *netdev = adpt->netdev;
+	int ret = 0;
+
+	/* get mac address */
+	if (device_get_ethdev_address(&pdev->dev, netdev))
+		eth_hw_addr_random(netdev);
+
+	/* Core 0 interrupt */
+	ret = platform_get_irq(pdev, 0);
+	if (ret < 0)
+		return ret;
+	adpt->irq.irq = ret;
+
+	/* base register address */
+	adpt->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(adpt->base))
+		return PTR_ERR(adpt->base);
+
+	/* CSR register address */
+	adpt->csr = devm_platform_ioremap_resource(pdev, 1);
+	if (IS_ERR(adpt->csr))
+		return PTR_ERR(adpt->csr);
+
+	netdev->base_addr = (unsigned long)adpt->base;
+
+	return 0;
+}
+
+static const struct of_device_id emac_dt_match[] = {
+	{
+		.compatible = "qcom,fsm9900-emac",
+	},
+	{}
+};
+MODULE_DEVICE_TABLE(of, emac_dt_match);
+
+#if IS_ENABLED(CONFIG_ACPI)
+static const struct acpi_device_id emac_acpi_match[] = {
+	{
+		.id = "QCOM8070",
+	},
+	{}
+};
+MODULE_DEVICE_TABLE(acpi, emac_acpi_match);
+#endif
+
+static int emac_probe(struct platform_device *pdev)
+{
+	struct net_device *netdev;
+	struct emac_adapter *adpt;
+	struct emac_sgmii *phy;
+	u16 devid, revid;
+	u32 reg;
+	int ret;
+
+	/* The TPD buffer address is limited to:
+	 * 1. PTP:	45bits. (Driver doesn't support yet.)
+	 * 2. NON-PTP:	46bits.
+	 */
+	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(46));
+	if (ret) {
+		dev_err(&pdev->dev, "could not set DMA mask\n");
+		return ret;
+	}
+
+	netdev = alloc_etherdev(sizeof(struct emac_adapter));
+	if (!netdev)
+		return -ENOMEM;
+
+	dev_set_drvdata(&pdev->dev, netdev);
+	SET_NETDEV_DEV(netdev, &pdev->dev);
+	emac_set_ethtool_ops(netdev);
+
+	adpt = netdev_priv(netdev);
+	adpt->netdev = netdev;
+	adpt->msg_enable = EMAC_MSG_DEFAULT;
+
+	phy = &adpt->phy;
+	atomic_set(&phy->decode_error_count, 0);
+
+	mutex_init(&adpt->reset_lock);
+	spin_lock_init(&adpt->stats.lock);
+
+	adpt->irq.mask = RX_PKT_INT0 | IMR_NORMAL_MASK;
+
+	ret = emac_probe_resources(pdev, adpt);
+	if (ret)
+		goto err_undo_netdev;
+
+	/* initialize clocks */
+	ret = emac_clks_phase1_init(pdev, adpt);
+	if (ret) {
+		dev_err(&pdev->dev, "could not initialize clocks\n");
+		goto err_undo_netdev;
+	}
+
+	netdev->watchdog_timeo = EMAC_WATCHDOG_TIME;
+	netdev->irq = adpt->irq.irq;
+
+	netdev->netdev_ops = &emac_netdev_ops;
+
+	emac_init_adapter(adpt);
+
+	/* init external phy */
+	ret = emac_phy_config(pdev, adpt);
+	if (ret)
+		goto err_undo_clocks;
+
+	/* init internal sgmii phy */
+	ret = emac_sgmii_config(pdev, adpt);
+	if (ret)
+		goto err_undo_mdiobus;
+
+	/* enable clocks */
+	ret = emac_clks_phase2_init(pdev, adpt);
+	if (ret) {
+		dev_err(&pdev->dev, "could not initialize clocks\n");
+		goto err_undo_mdiobus;
+	}
+
+	/* set hw features */
+	netdev->features = NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM |
+			NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_HW_VLAN_CTAG_RX |
+			NETIF_F_HW_VLAN_CTAG_TX;
+	netdev->hw_features = netdev->features;
+
+	netdev->vlan_features |= NETIF_F_SG | NETIF_F_HW_CSUM |
+				 NETIF_F_TSO | NETIF_F_TSO6;
+
+	/* MTU range: 46 - 9194 */
+	netdev->min_mtu = EMAC_MIN_ETH_FRAME_SIZE -
+			  (ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN);
+	netdev->max_mtu = EMAC_MAX_ETH_FRAME_SIZE -
+			  (ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN);
+
+	INIT_WORK(&adpt->work_thread, emac_work_thread);
+
+	/* Initialize queues */
+	emac_mac_rx_tx_ring_init_all(pdev, adpt);
+
+	netif_napi_add(netdev, &adpt->rx_q.napi, emac_napi_rtx);
+
+	ret = register_netdev(netdev);
+	if (ret) {
+		dev_err(&pdev->dev, "could not register net device\n");
+		goto err_undo_napi;
+	}
+
+	reg =  readl_relaxed(adpt->base + EMAC_DMA_MAS_CTRL);
+	devid = (reg & DEV_ID_NUM_BMSK)  >> DEV_ID_NUM_SHFT;
+	revid = (reg & DEV_REV_NUM_BMSK) >> DEV_REV_NUM_SHFT;
+	reg = readl_relaxed(adpt->base + EMAC_CORE_HW_VERSION);
+
+	netif_info(adpt, probe, netdev,
+		   "hardware id %d.%d, hardware version %d.%d.%d\n",
+		   devid, revid,
+		   (reg & MAJOR_BMSK) >> MAJOR_SHFT,
+		   (reg & MINOR_BMSK) >> MINOR_SHFT,
+		   (reg & STEP_BMSK)  >> STEP_SHFT);
+
+	return 0;
+
+err_undo_napi:
+	netif_napi_del(&adpt->rx_q.napi);
+err_undo_mdiobus:
+	put_device(&adpt->phydev->mdio.dev);
+	mdiobus_unregister(adpt->mii_bus);
+err_undo_clocks:
+	emac_clks_teardown(adpt);
+err_undo_netdev:
+	free_netdev(netdev);
+
+	return ret;
+}
+
+static int emac_remove(struct platform_device *pdev)
+{
+	struct net_device *netdev = dev_get_drvdata(&pdev->dev);
+	struct emac_adapter *adpt = netdev_priv(netdev);
+
+	unregister_netdev(netdev);
+	netif_napi_del(&adpt->rx_q.napi);
+
+	emac_clks_teardown(adpt);
+
+	put_device(&adpt->phydev->mdio.dev);
+	mdiobus_unregister(adpt->mii_bus);
+
+	if (adpt->phy.digital)
+		iounmap(adpt->phy.digital);
+	iounmap(adpt->phy.base);
+
+	free_netdev(netdev);
+
+	return 0;
+}
+
+static void emac_shutdown(struct platform_device *pdev)
+{
+	struct net_device *netdev = dev_get_drvdata(&pdev->dev);
+	struct emac_adapter *adpt = netdev_priv(netdev);
+
+	if (netdev->flags & IFF_UP) {
+		/* Closing the SGMII turns off its interrupts */
+		emac_sgmii_close(adpt);
+
+		/* Resetting the MAC turns off all DMA and its interrupts */
+		emac_mac_reset(adpt);
+	}
+}
+
+static struct platform_driver emac_platform_driver = {
+	.probe	= emac_probe,
+	.remove	= emac_remove,
+	.driver = {
+		.name		= "qcom-emac",
+		.of_match_table = emac_dt_match,
+		.acpi_match_table = ACPI_PTR(emac_acpi_match),
+	},
+	.shutdown = emac_shutdown,
+};
+
+module_platform_driver(emac_platform_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:qcom-emac");