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, 538 insertions, 0 deletions

diff --git a/drivers/spi/spi-bcm63xx-hsspi.c b/drivers/spi/spi-bcm63xx-hsspi.c
new file mode 100644
index 000000000..b871fd810
--- /dev/null
+++ b/drivers/spi/spi-bcm63xx-hsspi.c
@@ -0,0 +1,538 @@
+/*
+ * Broadcom BCM63XX High Speed SPI Controller driver
+ *
+ * Copyright 2000-2010 Broadcom Corporation
+ * Copyright 2012-2013 Jonas Gorski <jogo@openwrt.org>
+ *
+ * Licensed under the GNU/GPL. See COPYING for details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/clk.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/spi/spi.h>
+#include <linux/mutex.h>
+#include <linux/of.h>
+#include <linux/reset.h>
+#include <linux/pm_runtime.h>
+
+#define HSSPI_GLOBAL_CTRL_REG			0x0
+#define GLOBAL_CTRL_CS_POLARITY_SHIFT		0
+#define GLOBAL_CTRL_CS_POLARITY_MASK		0x000000ff
+#define GLOBAL_CTRL_PLL_CLK_CTRL_SHIFT		8
+#define GLOBAL_CTRL_PLL_CLK_CTRL_MASK		0x0000ff00
+#define GLOBAL_CTRL_CLK_GATE_SSOFF		BIT(16)
+#define GLOBAL_CTRL_CLK_POLARITY		BIT(17)
+#define GLOBAL_CTRL_MOSI_IDLE			BIT(18)
+
+#define HSSPI_GLOBAL_EXT_TRIGGER_REG		0x4
+
+#define HSSPI_INT_STATUS_REG			0x8
+#define HSSPI_INT_STATUS_MASKED_REG		0xc
+#define HSSPI_INT_MASK_REG			0x10
+
+#define HSSPI_PINGx_CMD_DONE(i)			BIT((i * 8) + 0)
+#define HSSPI_PINGx_RX_OVER(i)			BIT((i * 8) + 1)
+#define HSSPI_PINGx_TX_UNDER(i)			BIT((i * 8) + 2)
+#define HSSPI_PINGx_POLL_TIMEOUT(i)		BIT((i * 8) + 3)
+#define HSSPI_PINGx_CTRL_INVAL(i)		BIT((i * 8) + 4)
+
+#define HSSPI_INT_CLEAR_ALL			0xff001f1f
+
+#define HSSPI_PINGPONG_COMMAND_REG(x)		(0x80 + (x) * 0x40)
+#define PINGPONG_CMD_COMMAND_MASK		0xf
+#define PINGPONG_COMMAND_NOOP			0
+#define PINGPONG_COMMAND_START_NOW		1
+#define PINGPONG_COMMAND_START_TRIGGER		2
+#define PINGPONG_COMMAND_HALT			3
+#define PINGPONG_COMMAND_FLUSH			4
+#define PINGPONG_CMD_PROFILE_SHIFT		8
+#define PINGPONG_CMD_SS_SHIFT			12
+
+#define HSSPI_PINGPONG_STATUS_REG(x)		(0x84 + (x) * 0x40)
+
+#define HSSPI_PROFILE_CLK_CTRL_REG(x)		(0x100 + (x) * 0x20)
+#define CLK_CTRL_FREQ_CTRL_MASK			0x0000ffff
+#define CLK_CTRL_SPI_CLK_2X_SEL			BIT(14)
+#define CLK_CTRL_ACCUM_RST_ON_LOOP		BIT(15)
+
+#define HSSPI_PROFILE_SIGNAL_CTRL_REG(x)	(0x104 + (x) * 0x20)
+#define SIGNAL_CTRL_LATCH_RISING		BIT(12)
+#define SIGNAL_CTRL_LAUNCH_RISING		BIT(13)
+#define SIGNAL_CTRL_ASYNC_INPUT_PATH		BIT(16)
+
+#define HSSPI_PROFILE_MODE_CTRL_REG(x)		(0x108 + (x) * 0x20)
+#define MODE_CTRL_MULTIDATA_RD_STRT_SHIFT	8
+#define MODE_CTRL_MULTIDATA_WR_STRT_SHIFT	12
+#define MODE_CTRL_MULTIDATA_RD_SIZE_SHIFT	16
+#define MODE_CTRL_MULTIDATA_WR_SIZE_SHIFT	18
+#define MODE_CTRL_MODE_3WIRE			BIT(20)
+#define MODE_CTRL_PREPENDBYTE_CNT_SHIFT		24
+
+#define HSSPI_FIFO_REG(x)			(0x200 + (x) * 0x200)
+
+
+#define HSSPI_OP_MULTIBIT			BIT(11)
+#define HSSPI_OP_CODE_SHIFT			13
+#define HSSPI_OP_SLEEP				(0 << HSSPI_OP_CODE_SHIFT)
+#define HSSPI_OP_READ_WRITE			(1 << HSSPI_OP_CODE_SHIFT)
+#define HSSPI_OP_WRITE				(2 << HSSPI_OP_CODE_SHIFT)
+#define HSSPI_OP_READ				(3 << HSSPI_OP_CODE_SHIFT)
+#define HSSPI_OP_SETIRQ				(4 << HSSPI_OP_CODE_SHIFT)
+
+#define HSSPI_BUFFER_LEN			512
+#define HSSPI_OPCODE_LEN			2
+
+#define HSSPI_MAX_PREPEND_LEN			15
+
+#define HSSPI_MAX_SYNC_CLOCK			30000000
+
+#define HSSPI_SPI_MAX_CS			8
+#define HSSPI_BUS_NUM				1 /* 0 is legacy SPI */
+
+struct bcm63xx_hsspi {
+	struct completion done;
+	struct mutex bus_mutex;
+
+	struct platform_device *pdev;
+	struct clk *clk;
+	struct clk *pll_clk;
+	void __iomem *regs;
+	u8 __iomem *fifo;
+
+	u32 speed_hz;
+	u8 cs_polarity;
+};
+
+static void bcm63xx_hsspi_set_cs(struct bcm63xx_hsspi *bs, unsigned int cs,
+				 bool active)
+{
+	u32 reg;
+
+	mutex_lock(&bs->bus_mutex);
+	reg = __raw_readl(bs->regs + HSSPI_GLOBAL_CTRL_REG);
+
+	reg &= ~BIT(cs);
+	if (active == !(bs->cs_polarity & BIT(cs)))
+		reg |= BIT(cs);
+
+	__raw_writel(reg, bs->regs + HSSPI_GLOBAL_CTRL_REG);
+	mutex_unlock(&bs->bus_mutex);
+}
+
+static void bcm63xx_hsspi_set_clk(struct bcm63xx_hsspi *bs,
+				  struct spi_device *spi, int hz)
+{
+	unsigned int profile = spi->chip_select;
+	u32 reg;
+
+	reg = DIV_ROUND_UP(2048, DIV_ROUND_UP(bs->speed_hz, hz));
+	__raw_writel(CLK_CTRL_ACCUM_RST_ON_LOOP | reg,
+		     bs->regs + HSSPI_PROFILE_CLK_CTRL_REG(profile));
+
+	reg = __raw_readl(bs->regs + HSSPI_PROFILE_SIGNAL_CTRL_REG(profile));
+	if (hz > HSSPI_MAX_SYNC_CLOCK)
+		reg |= SIGNAL_CTRL_ASYNC_INPUT_PATH;
+	else
+		reg &= ~SIGNAL_CTRL_ASYNC_INPUT_PATH;
+	__raw_writel(reg, bs->regs + HSSPI_PROFILE_SIGNAL_CTRL_REG(profile));
+
+	mutex_lock(&bs->bus_mutex);
+	/* setup clock polarity */
+	reg = __raw_readl(bs->regs + HSSPI_GLOBAL_CTRL_REG);
+	reg &= ~GLOBAL_CTRL_CLK_POLARITY;
+	if (spi->mode & SPI_CPOL)
+		reg |= GLOBAL_CTRL_CLK_POLARITY;
+	__raw_writel(reg, bs->regs + HSSPI_GLOBAL_CTRL_REG);
+	mutex_unlock(&bs->bus_mutex);
+}
+
+static int bcm63xx_hsspi_do_txrx(struct spi_device *spi, struct spi_transfer *t)
+{
+	struct bcm63xx_hsspi *bs = spi_master_get_devdata(spi->master);
+	unsigned int chip_select = spi->chip_select;
+	u16 opcode = 0;
+	int pending = t->len;
+	int step_size = HSSPI_BUFFER_LEN;
+	const u8 *tx = t->tx_buf;
+	u8 *rx = t->rx_buf;
+
+	bcm63xx_hsspi_set_clk(bs, spi, t->speed_hz);
+	bcm63xx_hsspi_set_cs(bs, spi->chip_select, true);
+
+	if (tx && rx)
+		opcode = HSSPI_OP_READ_WRITE;
+	else if (tx)
+		opcode = HSSPI_OP_WRITE;
+	else if (rx)
+		opcode = HSSPI_OP_READ;
+
+	if (opcode != HSSPI_OP_READ)
+		step_size -= HSSPI_OPCODE_LEN;
+
+	if ((opcode == HSSPI_OP_READ && t->rx_nbits == SPI_NBITS_DUAL) ||
+	    (opcode == HSSPI_OP_WRITE && t->tx_nbits == SPI_NBITS_DUAL))
+		opcode |= HSSPI_OP_MULTIBIT;
+
+	__raw_writel(1 << MODE_CTRL_MULTIDATA_WR_SIZE_SHIFT |
+		     1 << MODE_CTRL_MULTIDATA_RD_SIZE_SHIFT | 0xff,
+		     bs->regs + HSSPI_PROFILE_MODE_CTRL_REG(chip_select));
+
+	while (pending > 0) {
+		int curr_step = min_t(int, step_size, pending);
+
+		reinit_completion(&bs->done);
+		if (tx) {
+			memcpy_toio(bs->fifo + HSSPI_OPCODE_LEN, tx, curr_step);
+			tx += curr_step;
+		}
+
+		__raw_writew(opcode | curr_step, bs->fifo);
+
+		/* enable interrupt */
+		__raw_writel(HSSPI_PINGx_CMD_DONE(0),
+			     bs->regs + HSSPI_INT_MASK_REG);
+
+		/* start the transfer */
+		__raw_writel(!chip_select << PINGPONG_CMD_SS_SHIFT |
+			     chip_select << PINGPONG_CMD_PROFILE_SHIFT |
+			     PINGPONG_COMMAND_START_NOW,
+			     bs->regs + HSSPI_PINGPONG_COMMAND_REG(0));
+
+		if (wait_for_completion_timeout(&bs->done, HZ) == 0) {
+			dev_err(&bs->pdev->dev, "transfer timed out!\n");
+			return -ETIMEDOUT;
+		}
+
+		if (rx) {
+			memcpy_fromio(rx, bs->fifo, curr_step);
+			rx += curr_step;
+		}
+
+		pending -= curr_step;
+	}
+
+	return 0;
+}
+
+static int bcm63xx_hsspi_setup(struct spi_device *spi)
+{
+	struct bcm63xx_hsspi *bs = spi_master_get_devdata(spi->master);
+	u32 reg;
+
+	reg = __raw_readl(bs->regs +
+			  HSSPI_PROFILE_SIGNAL_CTRL_REG(spi->chip_select));
+	reg &= ~(SIGNAL_CTRL_LAUNCH_RISING | SIGNAL_CTRL_LATCH_RISING);
+	if (spi->mode & SPI_CPHA)
+		reg |= SIGNAL_CTRL_LAUNCH_RISING;
+	else
+		reg |= SIGNAL_CTRL_LATCH_RISING;
+	__raw_writel(reg, bs->regs +
+		     HSSPI_PROFILE_SIGNAL_CTRL_REG(spi->chip_select));
+
+	mutex_lock(&bs->bus_mutex);
+	reg = __raw_readl(bs->regs + HSSPI_GLOBAL_CTRL_REG);
+
+	/* only change actual polarities if there is no transfer */
+	if ((reg & GLOBAL_CTRL_CS_POLARITY_MASK) == bs->cs_polarity) {
+		if (spi->mode & SPI_CS_HIGH)
+			reg |= BIT(spi->chip_select);
+		else
+			reg &= ~BIT(spi->chip_select);
+		__raw_writel(reg, bs->regs + HSSPI_GLOBAL_CTRL_REG);
+	}
+
+	if (spi->mode & SPI_CS_HIGH)
+		bs->cs_polarity |= BIT(spi->chip_select);
+	else
+		bs->cs_polarity &= ~BIT(spi->chip_select);
+
+	mutex_unlock(&bs->bus_mutex);
+
+	return 0;
+}
+
+static int bcm63xx_hsspi_transfer_one(struct spi_master *master,
+				      struct spi_message *msg)
+{
+	struct bcm63xx_hsspi *bs = spi_master_get_devdata(master);
+	struct spi_transfer *t;
+	struct spi_device *spi = msg->spi;
+	int status = -EINVAL;
+	int dummy_cs;
+	u32 reg;
+
+	/* This controller does not support keeping CS active during idle.
+	 * To work around this, we use the following ugly hack:
+	 *
+	 * a. Invert the target chip select's polarity so it will be active.
+	 * b. Select a "dummy" chip select to use as the hardware target.
+	 * c. Invert the dummy chip select's polarity so it will be inactive
+	 *    during the actual transfers.
+	 * d. Tell the hardware to send to the dummy chip select. Thanks to
+	 *    the multiplexed nature of SPI the actual target will receive
+	 *    the transfer and we see its response.
+	 *
+	 * e. At the end restore the polarities again to their default values.
+	 */
+
+	dummy_cs = !spi->chip_select;
+	bcm63xx_hsspi_set_cs(bs, dummy_cs, true);
+
+	list_for_each_entry(t, &msg->transfers, transfer_list) {
+		status = bcm63xx_hsspi_do_txrx(spi, t);
+		if (status)
+			break;
+
+		msg->actual_length += t->len;
+
+		spi_transfer_delay_exec(t);
+
+		if (t->cs_change)
+			bcm63xx_hsspi_set_cs(bs, spi->chip_select, false);
+	}
+
+	mutex_lock(&bs->bus_mutex);
+	reg = __raw_readl(bs->regs + HSSPI_GLOBAL_CTRL_REG);
+	reg &= ~GLOBAL_CTRL_CS_POLARITY_MASK;
+	reg |= bs->cs_polarity;
+	__raw_writel(reg, bs->regs + HSSPI_GLOBAL_CTRL_REG);
+	mutex_unlock(&bs->bus_mutex);
+
+	msg->status = status;
+	spi_finalize_current_message(master);
+
+	return 0;
+}
+
+static irqreturn_t bcm63xx_hsspi_interrupt(int irq, void *dev_id)
+{
+	struct bcm63xx_hsspi *bs = (struct bcm63xx_hsspi *)dev_id;
+
+	if (__raw_readl(bs->regs + HSSPI_INT_STATUS_MASKED_REG) == 0)
+		return IRQ_NONE;
+
+	__raw_writel(HSSPI_INT_CLEAR_ALL, bs->regs + HSSPI_INT_STATUS_REG);
+	__raw_writel(0, bs->regs + HSSPI_INT_MASK_REG);
+
+	complete(&bs->done);
+
+	return IRQ_HANDLED;
+}
+
+static int bcm63xx_hsspi_probe(struct platform_device *pdev)
+{
+	struct spi_master *master;
+	struct bcm63xx_hsspi *bs;
+	void __iomem *regs;
+	struct device *dev = &pdev->dev;
+	struct clk *clk, *pll_clk = NULL;
+	int irq, ret;
+	u32 reg, rate, num_cs = HSSPI_SPI_MAX_CS;
+	struct reset_control *reset;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	regs = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
+
+	clk = devm_clk_get(dev, "hsspi");
+
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	reset = devm_reset_control_get_optional_exclusive(dev, NULL);
+	if (IS_ERR(reset))
+		return PTR_ERR(reset);
+
+	ret = clk_prepare_enable(clk);
+	if (ret)
+		return ret;
+
+	ret = reset_control_reset(reset);
+	if (ret) {
+		dev_err(dev, "unable to reset device: %d\n", ret);
+		goto out_disable_clk;
+	}
+
+	rate = clk_get_rate(clk);
+	if (!rate) {
+		pll_clk = devm_clk_get(dev, "pll");
+
+		if (IS_ERR(pll_clk)) {
+			ret = PTR_ERR(pll_clk);
+			goto out_disable_clk;
+		}
+
+		ret = clk_prepare_enable(pll_clk);
+		if (ret)
+			goto out_disable_clk;
+
+		rate = clk_get_rate(pll_clk);
+		if (!rate) {
+			ret = -EINVAL;
+			goto out_disable_pll_clk;
+		}
+	}
+
+	master = spi_alloc_master(&pdev->dev, sizeof(*bs));
+	if (!master) {
+		ret = -ENOMEM;
+		goto out_disable_pll_clk;
+	}
+
+	bs = spi_master_get_devdata(master);
+	bs->pdev = pdev;
+	bs->clk = clk;
+	bs->pll_clk = pll_clk;
+	bs->regs = regs;
+	bs->speed_hz = rate;
+	bs->fifo = (u8 __iomem *)(bs->regs + HSSPI_FIFO_REG(0));
+
+	mutex_init(&bs->bus_mutex);
+	init_completion(&bs->done);
+
+	master->dev.of_node = dev->of_node;
+	if (!dev->of_node)
+		master->bus_num = HSSPI_BUS_NUM;
+
+	of_property_read_u32(dev->of_node, "num-cs", &num_cs);
+	if (num_cs > 8) {
+		dev_warn(dev, "unsupported number of cs (%i), reducing to 8\n",
+			 num_cs);
+		num_cs = HSSPI_SPI_MAX_CS;
+	}
+	master->num_chipselect = num_cs;
+	master->setup = bcm63xx_hsspi_setup;
+	master->transfer_one_message = bcm63xx_hsspi_transfer_one;
+	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH |
+			    SPI_RX_DUAL | SPI_TX_DUAL;
+	master->bits_per_word_mask = SPI_BPW_MASK(8);
+	master->auto_runtime_pm = true;
+
+	platform_set_drvdata(pdev, master);
+
+	/* Initialize the hardware */
+	__raw_writel(0, bs->regs + HSSPI_INT_MASK_REG);
+
+	/* clean up any pending interrupts */
+	__raw_writel(HSSPI_INT_CLEAR_ALL, bs->regs + HSSPI_INT_STATUS_REG);
+
+	/* read out default CS polarities */
+	reg = __raw_readl(bs->regs + HSSPI_GLOBAL_CTRL_REG);
+	bs->cs_polarity = reg & GLOBAL_CTRL_CS_POLARITY_MASK;
+	__raw_writel(reg | GLOBAL_CTRL_CLK_GATE_SSOFF,
+		     bs->regs + HSSPI_GLOBAL_CTRL_REG);
+
+	ret = devm_request_irq(dev, irq, bcm63xx_hsspi_interrupt, IRQF_SHARED,
+			       pdev->name, bs);
+
+	if (ret)
+		goto out_put_master;
+
+	pm_runtime_enable(&pdev->dev);
+
+	/* register and we are done */
+	ret = devm_spi_register_master(dev, master);
+	if (ret)
+		goto out_pm_disable;
+
+	return 0;
+
+out_pm_disable:
+	pm_runtime_disable(&pdev->dev);
+out_put_master:
+	spi_master_put(master);
+out_disable_pll_clk:
+	clk_disable_unprepare(pll_clk);
+out_disable_clk:
+	clk_disable_unprepare(clk);
+	return ret;
+}
+
+
+static int bcm63xx_hsspi_remove(struct platform_device *pdev)
+{
+	struct spi_master *master = platform_get_drvdata(pdev);
+	struct bcm63xx_hsspi *bs = spi_master_get_devdata(master);
+
+	/* reset the hardware and block queue progress */
+	__raw_writel(0, bs->regs + HSSPI_INT_MASK_REG);
+	clk_disable_unprepare(bs->pll_clk);
+	clk_disable_unprepare(bs->clk);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int bcm63xx_hsspi_suspend(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct bcm63xx_hsspi *bs = spi_master_get_devdata(master);
+
+	spi_master_suspend(master);
+	clk_disable_unprepare(bs->pll_clk);
+	clk_disable_unprepare(bs->clk);
+
+	return 0;
+}
+
+static int bcm63xx_hsspi_resume(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct bcm63xx_hsspi *bs = spi_master_get_devdata(master);
+	int ret;
+
+	ret = clk_prepare_enable(bs->clk);
+	if (ret)
+		return ret;
+
+	if (bs->pll_clk) {
+		ret = clk_prepare_enable(bs->pll_clk);
+		if (ret) {
+			clk_disable_unprepare(bs->clk);
+			return ret;
+		}
+	}
+
+	spi_master_resume(master);
+
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(bcm63xx_hsspi_pm_ops, bcm63xx_hsspi_suspend,
+			 bcm63xx_hsspi_resume);
+
+static const struct of_device_id bcm63xx_hsspi_of_match[] = {
+	{ .compatible = "brcm,bcm6328-hsspi", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, bcm63xx_hsspi_of_match);
+
+static struct platform_driver bcm63xx_hsspi_driver = {
+	.driver = {
+		.name	= "bcm63xx-hsspi",
+		.pm	= &bcm63xx_hsspi_pm_ops,
+		.of_match_table = bcm63xx_hsspi_of_match,
+	},
+	.probe		= bcm63xx_hsspi_probe,
+	.remove		= bcm63xx_hsspi_remove,
+};
+
+module_platform_driver(bcm63xx_hsspi_driver);
+
+MODULE_ALIAS("platform:bcm63xx_hsspi");
+MODULE_DESCRIPTION("Broadcom BCM63xx High Speed SPI Controller driver");
+MODULE_AUTHOR("Jonas Gorski <jogo@openwrt.org>");
+MODULE_LICENSE("GPL");