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, 799 insertions, 0 deletions

diff --git a/drivers/net/ethernet/broadcom/bcm4908_enet.c b/drivers/net/ethernet/broadcom/bcm4908_enet.c
new file mode 100644
index 000000000..33d86683a
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bcm4908_enet.c
@@ -0,0 +1,799 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2021 Rafał Miłecki <rafal@milecki.pl>
+ */
+
+#include <linux/delay.h>
+#include <linux/etherdevice.h>
+#include <linux/if_vlan.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_net.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+
+#include "bcm4908_enet.h"
+#include "unimac.h"
+
+#define ENET_DMA_CH_RX_CFG			ENET_DMA_CH0_CFG
+#define ENET_DMA_CH_TX_CFG			ENET_DMA_CH1_CFG
+#define ENET_DMA_CH_RX_STATE_RAM		ENET_DMA_CH0_STATE_RAM
+#define ENET_DMA_CH_TX_STATE_RAM		ENET_DMA_CH1_STATE_RAM
+
+#define ENET_TX_BDS_NUM				200
+#define ENET_RX_BDS_NUM				200
+#define ENET_RX_BDS_NUM_MAX			8192
+
+#define ENET_DMA_INT_DEFAULTS			(ENET_DMA_CH_CFG_INT_DONE | \
+						 ENET_DMA_CH_CFG_INT_NO_DESC | \
+						 ENET_DMA_CH_CFG_INT_BUFF_DONE)
+#define ENET_DMA_MAX_BURST_LEN			8 /* in 64 bit words */
+
+#define ENET_MTU_MAX				ETH_DATA_LEN /* Is it possible to support 2044? */
+#define BRCM_MAX_TAG_LEN			6
+#define ENET_MAX_ETH_OVERHEAD			(ETH_HLEN + BRCM_MAX_TAG_LEN + VLAN_HLEN + \
+						 ETH_FCS_LEN + 4) /* 32 */
+
+#define ENET_RX_SKB_BUF_SIZE			(NET_SKB_PAD + NET_IP_ALIGN + \
+						 ETH_HLEN + BRCM_MAX_TAG_LEN + VLAN_HLEN + \
+						 ENET_MTU_MAX + ETH_FCS_LEN + 4)
+#define ENET_RX_SKB_BUF_ALLOC_SIZE		(SKB_DATA_ALIGN(ENET_RX_SKB_BUF_SIZE) + \
+						 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+#define ENET_RX_BUF_DMA_OFFSET			(NET_SKB_PAD + NET_IP_ALIGN)
+#define ENET_RX_BUF_DMA_SIZE			(ENET_RX_SKB_BUF_SIZE - ENET_RX_BUF_DMA_OFFSET)
+
+struct bcm4908_enet_dma_ring_bd {
+	__le32 ctl;
+	__le32 addr;
+} __packed;
+
+struct bcm4908_enet_dma_ring_slot {
+	union {
+		void *buf;			/* RX */
+		struct sk_buff *skb;		/* TX */
+	};
+	unsigned int len;
+	dma_addr_t dma_addr;
+};
+
+struct bcm4908_enet_dma_ring {
+	int is_tx;
+	int read_idx;
+	int write_idx;
+	int length;
+	u16 cfg_block;
+	u16 st_ram_block;
+	struct napi_struct napi;
+
+	union {
+		void *cpu_addr;
+		struct bcm4908_enet_dma_ring_bd *buf_desc;
+	};
+	dma_addr_t dma_addr;
+
+	struct bcm4908_enet_dma_ring_slot *slots;
+};
+
+struct bcm4908_enet {
+	struct device *dev;
+	struct net_device *netdev;
+	void __iomem *base;
+	int irq_tx;
+
+	struct bcm4908_enet_dma_ring tx_ring;
+	struct bcm4908_enet_dma_ring rx_ring;
+};
+
+/***
+ * R/W ops
+ */
+
+static u32 enet_read(struct bcm4908_enet *enet, u16 offset)
+{
+	return readl(enet->base + offset);
+}
+
+static void enet_write(struct bcm4908_enet *enet, u16 offset, u32 value)
+{
+	writel(value, enet->base + offset);
+}
+
+static void enet_maskset(struct bcm4908_enet *enet, u16 offset, u32 mask, u32 set)
+{
+	u32 val;
+
+	WARN_ON(set & ~mask);
+
+	val = enet_read(enet, offset);
+	val = (val & ~mask) | (set & mask);
+	enet_write(enet, offset, val);
+}
+
+static void enet_set(struct bcm4908_enet *enet, u16 offset, u32 set)
+{
+	enet_maskset(enet, offset, set, set);
+}
+
+static u32 enet_umac_read(struct bcm4908_enet *enet, u16 offset)
+{
+	return enet_read(enet, ENET_UNIMAC + offset);
+}
+
+static void enet_umac_write(struct bcm4908_enet *enet, u16 offset, u32 value)
+{
+	enet_write(enet, ENET_UNIMAC + offset, value);
+}
+
+static void enet_umac_set(struct bcm4908_enet *enet, u16 offset, u32 set)
+{
+	enet_set(enet, ENET_UNIMAC + offset, set);
+}
+
+/***
+ * Helpers
+ */
+
+static void bcm4908_enet_set_mtu(struct bcm4908_enet *enet, int mtu)
+{
+	enet_umac_write(enet, UMAC_MAX_FRAME_LEN, mtu + ENET_MAX_ETH_OVERHEAD);
+}
+
+/***
+ * DMA ring ops
+ */
+
+static void bcm4908_enet_dma_ring_intrs_on(struct bcm4908_enet *enet,
+					   struct bcm4908_enet_dma_ring *ring)
+{
+	enet_write(enet, ring->cfg_block + ENET_DMA_CH_CFG_INT_MASK, ENET_DMA_INT_DEFAULTS);
+}
+
+static void bcm4908_enet_dma_ring_intrs_off(struct bcm4908_enet *enet,
+					    struct bcm4908_enet_dma_ring *ring)
+{
+	enet_write(enet, ring->cfg_block + ENET_DMA_CH_CFG_INT_MASK, 0);
+}
+
+static void bcm4908_enet_dma_ring_intrs_ack(struct bcm4908_enet *enet,
+					    struct bcm4908_enet_dma_ring *ring)
+{
+	enet_write(enet, ring->cfg_block + ENET_DMA_CH_CFG_INT_STAT, ENET_DMA_INT_DEFAULTS);
+}
+
+/***
+ * DMA
+ */
+
+static int bcm4908_dma_alloc_buf_descs(struct bcm4908_enet *enet,
+				       struct bcm4908_enet_dma_ring *ring)
+{
+	int size = ring->length * sizeof(struct bcm4908_enet_dma_ring_bd);
+	struct device *dev = enet->dev;
+
+	ring->cpu_addr = dma_alloc_coherent(dev, size, &ring->dma_addr, GFP_KERNEL);
+	if (!ring->cpu_addr)
+		return -ENOMEM;
+
+	if (((uintptr_t)ring->cpu_addr) & (0x40 - 1)) {
+		dev_err(dev, "Invalid DMA ring alignment\n");
+		goto err_free_buf_descs;
+	}
+
+	ring->slots = kcalloc(ring->length, sizeof(*ring->slots), GFP_KERNEL);
+	if (!ring->slots)
+		goto err_free_buf_descs;
+
+	return 0;
+
+err_free_buf_descs:
+	dma_free_coherent(dev, size, ring->cpu_addr, ring->dma_addr);
+	ring->cpu_addr = NULL;
+	return -ENOMEM;
+}
+
+static void bcm4908_enet_dma_free(struct bcm4908_enet *enet)
+{
+	struct bcm4908_enet_dma_ring *tx_ring = &enet->tx_ring;
+	struct bcm4908_enet_dma_ring *rx_ring = &enet->rx_ring;
+	struct device *dev = enet->dev;
+	int size;
+
+	size = rx_ring->length * sizeof(struct bcm4908_enet_dma_ring_bd);
+	if (rx_ring->cpu_addr)
+		dma_free_coherent(dev, size, rx_ring->cpu_addr, rx_ring->dma_addr);
+	kfree(rx_ring->slots);
+
+	size = tx_ring->length * sizeof(struct bcm4908_enet_dma_ring_bd);
+	if (tx_ring->cpu_addr)
+		dma_free_coherent(dev, size, tx_ring->cpu_addr, tx_ring->dma_addr);
+	kfree(tx_ring->slots);
+}
+
+static int bcm4908_enet_dma_alloc(struct bcm4908_enet *enet)
+{
+	struct bcm4908_enet_dma_ring *tx_ring = &enet->tx_ring;
+	struct bcm4908_enet_dma_ring *rx_ring = &enet->rx_ring;
+	struct device *dev = enet->dev;
+	int err;
+
+	tx_ring->length = ENET_TX_BDS_NUM;
+	tx_ring->is_tx = 1;
+	tx_ring->cfg_block = ENET_DMA_CH_TX_CFG;
+	tx_ring->st_ram_block = ENET_DMA_CH_TX_STATE_RAM;
+	err = bcm4908_dma_alloc_buf_descs(enet, tx_ring);
+	if (err) {
+		dev_err(dev, "Failed to alloc TX buf descriptors: %d\n", err);
+		return err;
+	}
+
+	rx_ring->length = ENET_RX_BDS_NUM;
+	rx_ring->is_tx = 0;
+	rx_ring->cfg_block = ENET_DMA_CH_RX_CFG;
+	rx_ring->st_ram_block = ENET_DMA_CH_RX_STATE_RAM;
+	err = bcm4908_dma_alloc_buf_descs(enet, rx_ring);
+	if (err) {
+		dev_err(dev, "Failed to alloc RX buf descriptors: %d\n", err);
+		bcm4908_enet_dma_free(enet);
+		return err;
+	}
+
+	return 0;
+}
+
+static void bcm4908_enet_dma_reset(struct bcm4908_enet *enet)
+{
+	struct bcm4908_enet_dma_ring *rings[] = { &enet->rx_ring, &enet->tx_ring };
+	int i;
+
+	/* Disable the DMA controller and channel */
+	for (i = 0; i < ARRAY_SIZE(rings); i++)
+		enet_write(enet, rings[i]->cfg_block + ENET_DMA_CH_CFG, 0);
+	enet_maskset(enet, ENET_DMA_CONTROLLER_CFG, ENET_DMA_CTRL_CFG_MASTER_EN, 0);
+
+	/* Reset channels state */
+	for (i = 0; i < ARRAY_SIZE(rings); i++) {
+		struct bcm4908_enet_dma_ring *ring = rings[i];
+
+		enet_write(enet, ring->st_ram_block + ENET_DMA_CH_STATE_RAM_BASE_DESC_PTR, 0);
+		enet_write(enet, ring->st_ram_block + ENET_DMA_CH_STATE_RAM_STATE_DATA, 0);
+		enet_write(enet, ring->st_ram_block + ENET_DMA_CH_STATE_RAM_DESC_LEN_STATUS, 0);
+		enet_write(enet, ring->st_ram_block + ENET_DMA_CH_STATE_RAM_DESC_BASE_BUFPTR, 0);
+	}
+}
+
+static int bcm4908_enet_dma_alloc_rx_buf(struct bcm4908_enet *enet, unsigned int idx)
+{
+	struct bcm4908_enet_dma_ring_bd *buf_desc = &enet->rx_ring.buf_desc[idx];
+	struct bcm4908_enet_dma_ring_slot *slot = &enet->rx_ring.slots[idx];
+	struct device *dev = enet->dev;
+	u32 tmp;
+	int err;
+
+	slot->buf = napi_alloc_frag(ENET_RX_SKB_BUF_ALLOC_SIZE);
+	if (!slot->buf)
+		return -ENOMEM;
+
+	slot->dma_addr = dma_map_single(dev, slot->buf + ENET_RX_BUF_DMA_OFFSET,
+					ENET_RX_BUF_DMA_SIZE, DMA_FROM_DEVICE);
+	err = dma_mapping_error(dev, slot->dma_addr);
+	if (err) {
+		dev_err(dev, "Failed to map DMA buffer: %d\n", err);
+		skb_free_frag(slot->buf);
+		slot->buf = NULL;
+		return err;
+	}
+
+	tmp = ENET_RX_BUF_DMA_SIZE << DMA_CTL_LEN_DESC_BUFLENGTH_SHIFT;
+	tmp |= DMA_CTL_STATUS_OWN;
+	if (idx == enet->rx_ring.length - 1)
+		tmp |= DMA_CTL_STATUS_WRAP;
+	buf_desc->ctl = cpu_to_le32(tmp);
+	buf_desc->addr = cpu_to_le32(slot->dma_addr);
+
+	return 0;
+}
+
+static void bcm4908_enet_dma_ring_init(struct bcm4908_enet *enet,
+				       struct bcm4908_enet_dma_ring *ring)
+{
+	int reset_channel = 0; /* We support only 1 main channel (with TX and RX) */
+	int reset_subch = ring->is_tx ? 1 : 0;
+
+	/* Reset the DMA channel */
+	enet_write(enet, ENET_DMA_CTRL_CHANNEL_RESET, BIT(reset_channel * 2 + reset_subch));
+	enet_write(enet, ENET_DMA_CTRL_CHANNEL_RESET, 0);
+
+	enet_write(enet, ring->cfg_block + ENET_DMA_CH_CFG, 0);
+	enet_write(enet, ring->cfg_block + ENET_DMA_CH_CFG_MAX_BURST, ENET_DMA_MAX_BURST_LEN);
+	enet_write(enet, ring->cfg_block + ENET_DMA_CH_CFG_INT_MASK, 0);
+
+	enet_write(enet, ring->st_ram_block + ENET_DMA_CH_STATE_RAM_BASE_DESC_PTR,
+		   (uint32_t)ring->dma_addr);
+
+	ring->read_idx = 0;
+	ring->write_idx = 0;
+}
+
+static void bcm4908_enet_dma_uninit(struct bcm4908_enet *enet)
+{
+	struct bcm4908_enet_dma_ring *rx_ring = &enet->rx_ring;
+	struct bcm4908_enet_dma_ring_slot *slot;
+	struct device *dev = enet->dev;
+	int i;
+
+	for (i = rx_ring->length - 1; i >= 0; i--) {
+		slot = &rx_ring->slots[i];
+		if (!slot->buf)
+			continue;
+		dma_unmap_single(dev, slot->dma_addr, slot->len, DMA_FROM_DEVICE);
+		skb_free_frag(slot->buf);
+		slot->buf = NULL;
+	}
+}
+
+static int bcm4908_enet_dma_init(struct bcm4908_enet *enet)
+{
+	struct bcm4908_enet_dma_ring *rx_ring = &enet->rx_ring;
+	struct device *dev = enet->dev;
+	int err;
+	int i;
+
+	for (i = 0; i < rx_ring->length; i++) {
+		err = bcm4908_enet_dma_alloc_rx_buf(enet, i);
+		if (err) {
+			dev_err(dev, "Failed to alloc RX buffer: %d\n", err);
+			bcm4908_enet_dma_uninit(enet);
+			return err;
+		}
+	}
+
+	bcm4908_enet_dma_ring_init(enet, &enet->tx_ring);
+	bcm4908_enet_dma_ring_init(enet, &enet->rx_ring);
+
+	return 0;
+}
+
+static void bcm4908_enet_dma_tx_ring_enable(struct bcm4908_enet *enet,
+					    struct bcm4908_enet_dma_ring *ring)
+{
+	enet_write(enet, ring->cfg_block + ENET_DMA_CH_CFG, ENET_DMA_CH_CFG_ENABLE);
+}
+
+static void bcm4908_enet_dma_tx_ring_disable(struct bcm4908_enet *enet,
+					     struct bcm4908_enet_dma_ring *ring)
+{
+	enet_write(enet, ring->cfg_block + ENET_DMA_CH_CFG, 0);
+}
+
+static void bcm4908_enet_dma_rx_ring_enable(struct bcm4908_enet *enet,
+					    struct bcm4908_enet_dma_ring *ring)
+{
+	enet_set(enet, ring->cfg_block + ENET_DMA_CH_CFG, ENET_DMA_CH_CFG_ENABLE);
+}
+
+static void bcm4908_enet_dma_rx_ring_disable(struct bcm4908_enet *enet,
+					     struct bcm4908_enet_dma_ring *ring)
+{
+	unsigned long deadline;
+	u32 tmp;
+
+	enet_maskset(enet, ring->cfg_block + ENET_DMA_CH_CFG, ENET_DMA_CH_CFG_ENABLE, 0);
+
+	deadline = jiffies + usecs_to_jiffies(2000);
+	do {
+		tmp = enet_read(enet, ring->cfg_block + ENET_DMA_CH_CFG);
+		if (!(tmp & ENET_DMA_CH_CFG_ENABLE))
+			return;
+		enet_maskset(enet, ring->cfg_block + ENET_DMA_CH_CFG, ENET_DMA_CH_CFG_ENABLE, 0);
+		usleep_range(10, 30);
+	} while (!time_after_eq(jiffies, deadline));
+
+	dev_warn(enet->dev, "Timeout waiting for DMA TX stop\n");
+}
+
+/***
+ * Ethernet driver
+ */
+
+static void bcm4908_enet_gmac_init(struct bcm4908_enet *enet)
+{
+	u32 cmd;
+
+	bcm4908_enet_set_mtu(enet, enet->netdev->mtu);
+
+	cmd = enet_umac_read(enet, UMAC_CMD);
+	enet_umac_write(enet, UMAC_CMD, cmd | CMD_SW_RESET);
+	enet_umac_write(enet, UMAC_CMD, cmd & ~CMD_SW_RESET);
+
+	enet_set(enet, ENET_FLUSH, ENET_FLUSH_RXFIFO_FLUSH | ENET_FLUSH_TXFIFO_FLUSH);
+	enet_maskset(enet, ENET_FLUSH, ENET_FLUSH_RXFIFO_FLUSH | ENET_FLUSH_TXFIFO_FLUSH, 0);
+
+	enet_set(enet, ENET_MIB_CTRL, ENET_MIB_CTRL_CLR_MIB);
+	enet_maskset(enet, ENET_MIB_CTRL, ENET_MIB_CTRL_CLR_MIB, 0);
+
+	cmd = enet_umac_read(enet, UMAC_CMD);
+	cmd &= ~(CMD_SPEED_MASK << CMD_SPEED_SHIFT);
+	cmd &= ~CMD_TX_EN;
+	cmd &= ~CMD_RX_EN;
+	cmd |= CMD_SPEED_1000 << CMD_SPEED_SHIFT;
+	enet_umac_write(enet, UMAC_CMD, cmd);
+
+	enet_maskset(enet, ENET_GMAC_STATUS,
+		     ENET_GMAC_STATUS_ETH_SPEED_MASK |
+		     ENET_GMAC_STATUS_HD |
+		     ENET_GMAC_STATUS_AUTO_CFG_EN |
+		     ENET_GMAC_STATUS_LINK_UP,
+		     ENET_GMAC_STATUS_ETH_SPEED_1000 |
+		     ENET_GMAC_STATUS_AUTO_CFG_EN |
+		     ENET_GMAC_STATUS_LINK_UP);
+}
+
+static irqreturn_t bcm4908_enet_irq_handler(int irq, void *dev_id)
+{
+	struct bcm4908_enet *enet = dev_id;
+	struct bcm4908_enet_dma_ring *ring;
+
+	ring = (irq == enet->irq_tx) ? &enet->tx_ring : &enet->rx_ring;
+
+	bcm4908_enet_dma_ring_intrs_off(enet, ring);
+	bcm4908_enet_dma_ring_intrs_ack(enet, ring);
+
+	napi_schedule(&ring->napi);
+
+	return IRQ_HANDLED;
+}
+
+static int bcm4908_enet_open(struct net_device *netdev)
+{
+	struct bcm4908_enet *enet = netdev_priv(netdev);
+	struct bcm4908_enet_dma_ring *tx_ring = &enet->tx_ring;
+	struct bcm4908_enet_dma_ring *rx_ring = &enet->rx_ring;
+	struct device *dev = enet->dev;
+	int err;
+
+	err = request_irq(netdev->irq, bcm4908_enet_irq_handler, 0, "enet", enet);
+	if (err) {
+		dev_err(dev, "Failed to request IRQ %d: %d\n", netdev->irq, err);
+		return err;
+	}
+
+	if (enet->irq_tx > 0) {
+		err = request_irq(enet->irq_tx, bcm4908_enet_irq_handler, 0,
+				  "tx", enet);
+		if (err) {
+			dev_err(dev, "Failed to request IRQ %d: %d\n",
+				enet->irq_tx, err);
+			free_irq(netdev->irq, enet);
+			return err;
+		}
+	}
+
+	bcm4908_enet_gmac_init(enet);
+	bcm4908_enet_dma_reset(enet);
+	bcm4908_enet_dma_init(enet);
+
+	enet_umac_set(enet, UMAC_CMD, CMD_TX_EN | CMD_RX_EN);
+
+	enet_set(enet, ENET_DMA_CONTROLLER_CFG, ENET_DMA_CTRL_CFG_MASTER_EN);
+	enet_maskset(enet, ENET_DMA_CONTROLLER_CFG, ENET_DMA_CTRL_CFG_FLOWC_CH1_EN, 0);
+
+	if (enet->irq_tx > 0) {
+		napi_enable(&tx_ring->napi);
+		bcm4908_enet_dma_ring_intrs_ack(enet, tx_ring);
+		bcm4908_enet_dma_ring_intrs_on(enet, tx_ring);
+	}
+
+	bcm4908_enet_dma_rx_ring_enable(enet, rx_ring);
+	napi_enable(&rx_ring->napi);
+	netif_carrier_on(netdev);
+	netif_start_queue(netdev);
+	bcm4908_enet_dma_ring_intrs_ack(enet, rx_ring);
+	bcm4908_enet_dma_ring_intrs_on(enet, rx_ring);
+
+	return 0;
+}
+
+static int bcm4908_enet_stop(struct net_device *netdev)
+{
+	struct bcm4908_enet *enet = netdev_priv(netdev);
+	struct bcm4908_enet_dma_ring *tx_ring = &enet->tx_ring;
+	struct bcm4908_enet_dma_ring *rx_ring = &enet->rx_ring;
+
+	netif_stop_queue(netdev);
+	netif_carrier_off(netdev);
+	napi_disable(&rx_ring->napi);
+	napi_disable(&tx_ring->napi);
+	netdev_reset_queue(netdev);
+
+	bcm4908_enet_dma_rx_ring_disable(enet, &enet->rx_ring);
+	bcm4908_enet_dma_tx_ring_disable(enet, &enet->tx_ring);
+
+	bcm4908_enet_dma_uninit(enet);
+
+	free_irq(enet->irq_tx, enet);
+	free_irq(enet->netdev->irq, enet);
+
+	return 0;
+}
+
+static netdev_tx_t bcm4908_enet_start_xmit(struct sk_buff *skb, struct net_device *netdev)
+{
+	struct bcm4908_enet *enet = netdev_priv(netdev);
+	struct bcm4908_enet_dma_ring *ring = &enet->tx_ring;
+	struct bcm4908_enet_dma_ring_slot *slot;
+	struct device *dev = enet->dev;
+	struct bcm4908_enet_dma_ring_bd *buf_desc;
+	int free_buf_descs;
+	u32 tmp;
+
+	/* Free transmitted skbs */
+	if (enet->irq_tx < 0 &&
+	    !(le32_to_cpu(ring->buf_desc[ring->read_idx].ctl) & DMA_CTL_STATUS_OWN))
+		napi_schedule(&enet->tx_ring.napi);
+
+	/* Don't use the last empty buf descriptor */
+	if (ring->read_idx <= ring->write_idx)
+		free_buf_descs = ring->read_idx - ring->write_idx + ring->length;
+	else
+		free_buf_descs = ring->read_idx - ring->write_idx;
+	if (free_buf_descs < 2) {
+		netif_stop_queue(netdev);
+		return NETDEV_TX_BUSY;
+	}
+
+	/* Hardware removes OWN bit after sending data */
+	buf_desc = &ring->buf_desc[ring->write_idx];
+	if (unlikely(le32_to_cpu(buf_desc->ctl) & DMA_CTL_STATUS_OWN)) {
+		netif_stop_queue(netdev);
+		return NETDEV_TX_BUSY;
+	}
+
+	slot = &ring->slots[ring->write_idx];
+	slot->skb = skb;
+	slot->len = skb->len;
+	slot->dma_addr = dma_map_single(dev, skb->data, skb->len, DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(dev, slot->dma_addr)))
+		return NETDEV_TX_BUSY;
+
+	tmp = skb->len << DMA_CTL_LEN_DESC_BUFLENGTH_SHIFT;
+	tmp |= DMA_CTL_STATUS_OWN;
+	tmp |= DMA_CTL_STATUS_SOP;
+	tmp |= DMA_CTL_STATUS_EOP;
+	tmp |= DMA_CTL_STATUS_APPEND_CRC;
+	if (ring->write_idx + 1 == ring->length - 1)
+		tmp |= DMA_CTL_STATUS_WRAP;
+
+	netdev_sent_queue(enet->netdev, skb->len);
+
+	buf_desc->addr = cpu_to_le32((uint32_t)slot->dma_addr);
+	buf_desc->ctl = cpu_to_le32(tmp);
+
+	bcm4908_enet_dma_tx_ring_enable(enet, &enet->tx_ring);
+
+	if (++ring->write_idx == ring->length - 1)
+		ring->write_idx = 0;
+
+	return NETDEV_TX_OK;
+}
+
+static int bcm4908_enet_poll_rx(struct napi_struct *napi, int weight)
+{
+	struct bcm4908_enet_dma_ring *rx_ring = container_of(napi, struct bcm4908_enet_dma_ring, napi);
+	struct bcm4908_enet *enet = container_of(rx_ring, struct bcm4908_enet, rx_ring);
+	struct device *dev = enet->dev;
+	int handled = 0;
+
+	while (handled < weight) {
+		struct bcm4908_enet_dma_ring_bd *buf_desc;
+		struct bcm4908_enet_dma_ring_slot slot;
+		struct sk_buff *skb;
+		u32 ctl;
+		int len;
+		int err;
+
+		buf_desc = &enet->rx_ring.buf_desc[enet->rx_ring.read_idx];
+		ctl = le32_to_cpu(buf_desc->ctl);
+		if (ctl & DMA_CTL_STATUS_OWN)
+			break;
+
+		slot = enet->rx_ring.slots[enet->rx_ring.read_idx];
+
+		/* Provide new buffer before unpinning the old one */
+		err = bcm4908_enet_dma_alloc_rx_buf(enet, enet->rx_ring.read_idx);
+		if (err)
+			break;
+
+		if (++enet->rx_ring.read_idx == enet->rx_ring.length)
+			enet->rx_ring.read_idx = 0;
+
+		len = (ctl & DMA_CTL_LEN_DESC_BUFLENGTH) >> DMA_CTL_LEN_DESC_BUFLENGTH_SHIFT;
+
+		if (len < ETH_ZLEN ||
+		    (ctl & (DMA_CTL_STATUS_SOP | DMA_CTL_STATUS_EOP)) != (DMA_CTL_STATUS_SOP | DMA_CTL_STATUS_EOP)) {
+			skb_free_frag(slot.buf);
+			enet->netdev->stats.rx_dropped++;
+			break;
+		}
+
+		dma_unmap_single(dev, slot.dma_addr, ENET_RX_BUF_DMA_SIZE, DMA_FROM_DEVICE);
+
+		skb = build_skb(slot.buf, ENET_RX_SKB_BUF_ALLOC_SIZE);
+		if (unlikely(!skb)) {
+			skb_free_frag(slot.buf);
+			enet->netdev->stats.rx_dropped++;
+			break;
+		}
+		skb_reserve(skb, ENET_RX_BUF_DMA_OFFSET);
+		skb_put(skb, len - ETH_FCS_LEN);
+		skb->protocol = eth_type_trans(skb, enet->netdev);
+
+		netif_receive_skb(skb);
+
+		enet->netdev->stats.rx_packets++;
+		enet->netdev->stats.rx_bytes += len;
+
+		handled++;
+	}
+
+	if (handled < weight) {
+		napi_complete_done(napi, handled);
+		bcm4908_enet_dma_ring_intrs_on(enet, rx_ring);
+	}
+
+	/* Hardware could disable ring if it run out of descriptors */
+	bcm4908_enet_dma_rx_ring_enable(enet, &enet->rx_ring);
+
+	return handled;
+}
+
+static int bcm4908_enet_poll_tx(struct napi_struct *napi, int weight)
+{
+	struct bcm4908_enet_dma_ring *tx_ring = container_of(napi, struct bcm4908_enet_dma_ring, napi);
+	struct bcm4908_enet *enet = container_of(tx_ring, struct bcm4908_enet, tx_ring);
+	struct bcm4908_enet_dma_ring_bd *buf_desc;
+	struct bcm4908_enet_dma_ring_slot *slot;
+	struct device *dev = enet->dev;
+	unsigned int bytes = 0;
+	int handled = 0;
+
+	while (handled < weight && tx_ring->read_idx != tx_ring->write_idx) {
+		buf_desc = &tx_ring->buf_desc[tx_ring->read_idx];
+		if (le32_to_cpu(buf_desc->ctl) & DMA_CTL_STATUS_OWN)
+			break;
+		slot = &tx_ring->slots[tx_ring->read_idx];
+
+		dma_unmap_single(dev, slot->dma_addr, slot->len, DMA_TO_DEVICE);
+		dev_kfree_skb(slot->skb);
+
+		handled++;
+		bytes += slot->len;
+
+		if (++tx_ring->read_idx == tx_ring->length)
+			tx_ring->read_idx = 0;
+	}
+
+	netdev_completed_queue(enet->netdev, handled, bytes);
+	enet->netdev->stats.tx_packets += handled;
+	enet->netdev->stats.tx_bytes += bytes;
+
+	if (handled < weight) {
+		napi_complete_done(napi, handled);
+		bcm4908_enet_dma_ring_intrs_on(enet, tx_ring);
+	}
+
+	if (netif_queue_stopped(enet->netdev))
+		netif_wake_queue(enet->netdev);
+
+	return handled;
+}
+
+static int bcm4908_enet_change_mtu(struct net_device *netdev, int new_mtu)
+{
+	struct bcm4908_enet *enet = netdev_priv(netdev);
+
+	bcm4908_enet_set_mtu(enet, new_mtu);
+
+	return 0;
+}
+
+static const struct net_device_ops bcm4908_enet_netdev_ops = {
+	.ndo_open = bcm4908_enet_open,
+	.ndo_stop = bcm4908_enet_stop,
+	.ndo_start_xmit = bcm4908_enet_start_xmit,
+	.ndo_set_mac_address = eth_mac_addr,
+	.ndo_change_mtu = bcm4908_enet_change_mtu,
+};
+
+static int bcm4908_enet_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct net_device *netdev;
+	struct bcm4908_enet *enet;
+	int err;
+
+	netdev = devm_alloc_etherdev(dev, sizeof(*enet));
+	if (!netdev)
+		return -ENOMEM;
+
+	enet = netdev_priv(netdev);
+	enet->dev = dev;
+	enet->netdev = netdev;
+
+	enet->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(enet->base)) {
+		dev_err(dev, "Failed to map registers: %ld\n", PTR_ERR(enet->base));
+		return PTR_ERR(enet->base);
+	}
+
+	netdev->irq = platform_get_irq_byname(pdev, "rx");
+	if (netdev->irq < 0)
+		return netdev->irq;
+
+	enet->irq_tx = platform_get_irq_byname(pdev, "tx");
+
+	err = dma_set_coherent_mask(dev, DMA_BIT_MASK(32));
+	if (err)
+		return err;
+
+	err = bcm4908_enet_dma_alloc(enet);
+	if (err)
+		return err;
+
+	SET_NETDEV_DEV(netdev, &pdev->dev);
+	err = of_get_ethdev_address(dev->of_node, netdev);
+	if (err == -EPROBE_DEFER)
+		goto err_dma_free;
+	if (err)
+		eth_hw_addr_random(netdev);
+	netdev->netdev_ops = &bcm4908_enet_netdev_ops;
+	netdev->min_mtu = ETH_ZLEN;
+	netdev->mtu = ETH_DATA_LEN;
+	netdev->max_mtu = ENET_MTU_MAX;
+	netif_napi_add_tx(netdev, &enet->tx_ring.napi, bcm4908_enet_poll_tx);
+	netif_napi_add(netdev, &enet->rx_ring.napi, bcm4908_enet_poll_rx);
+
+	err = register_netdev(netdev);
+	if (err)
+		goto err_dma_free;
+
+	platform_set_drvdata(pdev, enet);
+
+	return 0;
+
+err_dma_free:
+	bcm4908_enet_dma_free(enet);
+
+	return err;
+}
+
+static int bcm4908_enet_remove(struct platform_device *pdev)
+{
+	struct bcm4908_enet *enet = platform_get_drvdata(pdev);
+
+	unregister_netdev(enet->netdev);
+	netif_napi_del(&enet->rx_ring.napi);
+	netif_napi_del(&enet->tx_ring.napi);
+	bcm4908_enet_dma_free(enet);
+
+	return 0;
+}
+
+static const struct of_device_id bcm4908_enet_of_match[] = {
+	{ .compatible = "brcm,bcm4908-enet"},
+	{},
+};
+
+static struct platform_driver bcm4908_enet_driver = {
+	.driver = {
+		.name = "bcm4908_enet",
+		.of_match_table = bcm4908_enet_of_match,
+	},
+	.probe	= bcm4908_enet_probe,
+	.remove = bcm4908_enet_remove,
+};
+module_platform_driver(bcm4908_enet_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DEVICE_TABLE(of, bcm4908_enet_of_match);