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, 725 insertions, 0 deletions

diff --git a/drivers/spi/spi-sun6i.c b/drivers/spi/spi-sun6i.c
new file mode 100644
index 000000000..23ad05252
--- /dev/null
+++ b/drivers/spi/spi-sun6i.c
@@ -0,0 +1,725 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2012 - 2014 Allwinner Tech
+ * Pan Nan <pannan@allwinnertech.com>
+ *
+ * Copyright (C) 2014 Maxime Ripard
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/reset.h>
+#include <linux/dmaengine.h>
+
+#include <linux/spi/spi.h>
+
+#define SUN6I_AUTOSUSPEND_TIMEOUT	2000
+
+#define SUN6I_FIFO_DEPTH		128
+#define SUN8I_FIFO_DEPTH		64
+
+#define SUN6I_GBL_CTL_REG		0x04
+#define SUN6I_GBL_CTL_BUS_ENABLE		BIT(0)
+#define SUN6I_GBL_CTL_MASTER			BIT(1)
+#define SUN6I_GBL_CTL_TP			BIT(7)
+#define SUN6I_GBL_CTL_RST			BIT(31)
+
+#define SUN6I_TFR_CTL_REG		0x08
+#define SUN6I_TFR_CTL_CPHA			BIT(0)
+#define SUN6I_TFR_CTL_CPOL			BIT(1)
+#define SUN6I_TFR_CTL_SPOL			BIT(2)
+#define SUN6I_TFR_CTL_CS_MASK			0x30
+#define SUN6I_TFR_CTL_CS(cs)			(((cs) << 4) & SUN6I_TFR_CTL_CS_MASK)
+#define SUN6I_TFR_CTL_CS_MANUAL			BIT(6)
+#define SUN6I_TFR_CTL_CS_LEVEL			BIT(7)
+#define SUN6I_TFR_CTL_DHB			BIT(8)
+#define SUN6I_TFR_CTL_FBS			BIT(12)
+#define SUN6I_TFR_CTL_XCH			BIT(31)
+
+#define SUN6I_INT_CTL_REG		0x10
+#define SUN6I_INT_CTL_RF_RDY			BIT(0)
+#define SUN6I_INT_CTL_TF_ERQ			BIT(4)
+#define SUN6I_INT_CTL_RF_OVF			BIT(8)
+#define SUN6I_INT_CTL_TC			BIT(12)
+
+#define SUN6I_INT_STA_REG		0x14
+
+#define SUN6I_FIFO_CTL_REG		0x18
+#define SUN6I_FIFO_CTL_RF_RDY_TRIG_LEVEL_MASK	0xff
+#define SUN6I_FIFO_CTL_RF_DRQ_EN		BIT(8)
+#define SUN6I_FIFO_CTL_RF_RDY_TRIG_LEVEL_BITS	0
+#define SUN6I_FIFO_CTL_RF_RST			BIT(15)
+#define SUN6I_FIFO_CTL_TF_ERQ_TRIG_LEVEL_MASK	0xff
+#define SUN6I_FIFO_CTL_TF_ERQ_TRIG_LEVEL_BITS	16
+#define SUN6I_FIFO_CTL_TF_DRQ_EN		BIT(24)
+#define SUN6I_FIFO_CTL_TF_RST			BIT(31)
+
+#define SUN6I_FIFO_STA_REG		0x1c
+#define SUN6I_FIFO_STA_RF_CNT_MASK		GENMASK(7, 0)
+#define SUN6I_FIFO_STA_TF_CNT_MASK		GENMASK(23, 16)
+
+#define SUN6I_CLK_CTL_REG		0x24
+#define SUN6I_CLK_CTL_CDR2_MASK			0xff
+#define SUN6I_CLK_CTL_CDR2(div)			(((div) & SUN6I_CLK_CTL_CDR2_MASK) << 0)
+#define SUN6I_CLK_CTL_CDR1_MASK			0xf
+#define SUN6I_CLK_CTL_CDR1(div)			(((div) & SUN6I_CLK_CTL_CDR1_MASK) << 8)
+#define SUN6I_CLK_CTL_DRS			BIT(12)
+
+#define SUN6I_MAX_XFER_SIZE		0xffffff
+
+#define SUN6I_BURST_CNT_REG		0x30
+
+#define SUN6I_XMIT_CNT_REG		0x34
+
+#define SUN6I_BURST_CTL_CNT_REG		0x38
+
+#define SUN6I_TXDATA_REG		0x200
+#define SUN6I_RXDATA_REG		0x300
+
+struct sun6i_spi {
+	struct spi_master	*master;
+	void __iomem		*base_addr;
+	dma_addr_t		dma_addr_rx;
+	dma_addr_t		dma_addr_tx;
+	struct clk		*hclk;
+	struct clk		*mclk;
+	struct reset_control	*rstc;
+
+	struct completion	done;
+
+	const u8		*tx_buf;
+	u8			*rx_buf;
+	int			len;
+	unsigned long		fifo_depth;
+};
+
+static inline u32 sun6i_spi_read(struct sun6i_spi *sspi, u32 reg)
+{
+	return readl(sspi->base_addr + reg);
+}
+
+static inline void sun6i_spi_write(struct sun6i_spi *sspi, u32 reg, u32 value)
+{
+	writel(value, sspi->base_addr + reg);
+}
+
+static inline u32 sun6i_spi_get_rx_fifo_count(struct sun6i_spi *sspi)
+{
+	u32 reg = sun6i_spi_read(sspi, SUN6I_FIFO_STA_REG);
+
+	return FIELD_GET(SUN6I_FIFO_STA_RF_CNT_MASK, reg);
+}
+
+static inline u32 sun6i_spi_get_tx_fifo_count(struct sun6i_spi *sspi)
+{
+	u32 reg = sun6i_spi_read(sspi, SUN6I_FIFO_STA_REG);
+
+	return FIELD_GET(SUN6I_FIFO_STA_TF_CNT_MASK, reg);
+}
+
+static inline void sun6i_spi_disable_interrupt(struct sun6i_spi *sspi, u32 mask)
+{
+	u32 reg = sun6i_spi_read(sspi, SUN6I_INT_CTL_REG);
+
+	reg &= ~mask;
+	sun6i_spi_write(sspi, SUN6I_INT_CTL_REG, reg);
+}
+
+static inline void sun6i_spi_drain_fifo(struct sun6i_spi *sspi)
+{
+	u32 len;
+	u8 byte;
+
+	/* See how much data is available */
+	len = sun6i_spi_get_rx_fifo_count(sspi);
+
+	while (len--) {
+		byte = readb(sspi->base_addr + SUN6I_RXDATA_REG);
+		if (sspi->rx_buf)
+			*sspi->rx_buf++ = byte;
+	}
+}
+
+static inline void sun6i_spi_fill_fifo(struct sun6i_spi *sspi)
+{
+	u32 cnt;
+	int len;
+	u8 byte;
+
+	/* See how much data we can fit */
+	cnt = sspi->fifo_depth - sun6i_spi_get_tx_fifo_count(sspi);
+
+	len = min((int)cnt, sspi->len);
+
+	while (len--) {
+		byte = sspi->tx_buf ? *sspi->tx_buf++ : 0;
+		writeb(byte, sspi->base_addr + SUN6I_TXDATA_REG);
+		sspi->len--;
+	}
+}
+
+static void sun6i_spi_set_cs(struct spi_device *spi, bool enable)
+{
+	struct sun6i_spi *sspi = spi_master_get_devdata(spi->master);
+	u32 reg;
+
+	reg = sun6i_spi_read(sspi, SUN6I_TFR_CTL_REG);
+	reg &= ~SUN6I_TFR_CTL_CS_MASK;
+	reg |= SUN6I_TFR_CTL_CS(spi->chip_select);
+
+	if (enable)
+		reg |= SUN6I_TFR_CTL_CS_LEVEL;
+	else
+		reg &= ~SUN6I_TFR_CTL_CS_LEVEL;
+
+	sun6i_spi_write(sspi, SUN6I_TFR_CTL_REG, reg);
+}
+
+static size_t sun6i_spi_max_transfer_size(struct spi_device *spi)
+{
+	return SUN6I_MAX_XFER_SIZE - 1;
+}
+
+static int sun6i_spi_prepare_dma(struct sun6i_spi *sspi,
+				 struct spi_transfer *tfr)
+{
+	struct dma_async_tx_descriptor *rxdesc, *txdesc;
+	struct spi_master *master = sspi->master;
+
+	rxdesc = NULL;
+	if (tfr->rx_buf) {
+		struct dma_slave_config rxconf = {
+			.direction = DMA_DEV_TO_MEM,
+			.src_addr = sspi->dma_addr_rx,
+			.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES,
+			.src_maxburst = 8,
+		};
+
+		dmaengine_slave_config(master->dma_rx, &rxconf);
+
+		rxdesc = dmaengine_prep_slave_sg(master->dma_rx,
+						 tfr->rx_sg.sgl,
+						 tfr->rx_sg.nents,
+						 DMA_DEV_TO_MEM,
+						 DMA_PREP_INTERRUPT);
+		if (!rxdesc)
+			return -EINVAL;
+	}
+
+	txdesc = NULL;
+	if (tfr->tx_buf) {
+		struct dma_slave_config txconf = {
+			.direction = DMA_MEM_TO_DEV,
+			.dst_addr = sspi->dma_addr_tx,
+			.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES,
+			.dst_maxburst = 8,
+		};
+
+		dmaengine_slave_config(master->dma_tx, &txconf);
+
+		txdesc = dmaengine_prep_slave_sg(master->dma_tx,
+						 tfr->tx_sg.sgl,
+						 tfr->tx_sg.nents,
+						 DMA_MEM_TO_DEV,
+						 DMA_PREP_INTERRUPT);
+		if (!txdesc) {
+			if (rxdesc)
+				dmaengine_terminate_sync(master->dma_rx);
+			return -EINVAL;
+		}
+	}
+
+	if (tfr->rx_buf) {
+		dmaengine_submit(rxdesc);
+		dma_async_issue_pending(master->dma_rx);
+	}
+
+	if (tfr->tx_buf) {
+		dmaengine_submit(txdesc);
+		dma_async_issue_pending(master->dma_tx);
+	}
+
+	return 0;
+}
+
+static int sun6i_spi_transfer_one(struct spi_master *master,
+				  struct spi_device *spi,
+				  struct spi_transfer *tfr)
+{
+	struct sun6i_spi *sspi = spi_master_get_devdata(master);
+	unsigned int mclk_rate, div, div_cdr1, div_cdr2, timeout;
+	unsigned int start, end, tx_time;
+	unsigned int trig_level;
+	unsigned int tx_len = 0, rx_len = 0;
+	bool use_dma;
+	int ret = 0;
+	u32 reg;
+
+	if (tfr->len > SUN6I_MAX_XFER_SIZE)
+		return -EINVAL;
+
+	reinit_completion(&sspi->done);
+	sspi->tx_buf = tfr->tx_buf;
+	sspi->rx_buf = tfr->rx_buf;
+	sspi->len = tfr->len;
+	use_dma = master->can_dma ? master->can_dma(master, spi, tfr) : false;
+
+	/* Clear pending interrupts */
+	sun6i_spi_write(sspi, SUN6I_INT_STA_REG, ~0);
+
+	/* Reset FIFO */
+	sun6i_spi_write(sspi, SUN6I_FIFO_CTL_REG,
+			SUN6I_FIFO_CTL_RF_RST | SUN6I_FIFO_CTL_TF_RST);
+
+	reg = 0;
+
+	if (!use_dma) {
+		/*
+		 * Setup FIFO interrupt trigger level
+		 * Here we choose 3/4 of the full fifo depth, as it's
+		 * the hardcoded value used in old generation of Allwinner
+		 * SPI controller. (See spi-sun4i.c)
+		 */
+		trig_level = sspi->fifo_depth / 4 * 3;
+	} else {
+		/*
+		 * Setup FIFO DMA request trigger level
+		 * We choose 1/2 of the full fifo depth, that value will
+		 * be used as DMA burst length.
+		 */
+		trig_level = sspi->fifo_depth / 2;
+
+		if (tfr->tx_buf)
+			reg |= SUN6I_FIFO_CTL_TF_DRQ_EN;
+		if (tfr->rx_buf)
+			reg |= SUN6I_FIFO_CTL_RF_DRQ_EN;
+	}
+
+	reg |= (trig_level << SUN6I_FIFO_CTL_RF_RDY_TRIG_LEVEL_BITS) |
+	       (trig_level << SUN6I_FIFO_CTL_TF_ERQ_TRIG_LEVEL_BITS);
+
+	sun6i_spi_write(sspi, SUN6I_FIFO_CTL_REG, reg);
+
+	/*
+	 * Setup the transfer control register: Chip Select,
+	 * polarities, etc.
+	 */
+	reg = sun6i_spi_read(sspi, SUN6I_TFR_CTL_REG);
+
+	if (spi->mode & SPI_CPOL)
+		reg |= SUN6I_TFR_CTL_CPOL;
+	else
+		reg &= ~SUN6I_TFR_CTL_CPOL;
+
+	if (spi->mode & SPI_CPHA)
+		reg |= SUN6I_TFR_CTL_CPHA;
+	else
+		reg &= ~SUN6I_TFR_CTL_CPHA;
+
+	if (spi->mode & SPI_LSB_FIRST)
+		reg |= SUN6I_TFR_CTL_FBS;
+	else
+		reg &= ~SUN6I_TFR_CTL_FBS;
+
+	/*
+	 * If it's a TX only transfer, we don't want to fill the RX
+	 * FIFO with bogus data
+	 */
+	if (sspi->rx_buf) {
+		reg &= ~SUN6I_TFR_CTL_DHB;
+		rx_len = tfr->len;
+	} else {
+		reg |= SUN6I_TFR_CTL_DHB;
+	}
+
+	/* We want to control the chip select manually */
+	reg |= SUN6I_TFR_CTL_CS_MANUAL;
+
+	sun6i_spi_write(sspi, SUN6I_TFR_CTL_REG, reg);
+
+	/* Ensure that we have a parent clock fast enough */
+	mclk_rate = clk_get_rate(sspi->mclk);
+	if (mclk_rate < (2 * tfr->speed_hz)) {
+		clk_set_rate(sspi->mclk, 2 * tfr->speed_hz);
+		mclk_rate = clk_get_rate(sspi->mclk);
+	}
+
+	/*
+	 * Setup clock divider.
+	 *
+	 * We have two choices there. Either we can use the clock
+	 * divide rate 1, which is calculated thanks to this formula:
+	 * SPI_CLK = MOD_CLK / (2 ^ cdr)
+	 * Or we can use CDR2, which is calculated with the formula:
+	 * SPI_CLK = MOD_CLK / (2 * (cdr + 1))
+	 * Wether we use the former or the latter is set through the
+	 * DRS bit.
+	 *
+	 * First try CDR2, and if we can't reach the expected
+	 * frequency, fall back to CDR1.
+	 */
+	div_cdr1 = DIV_ROUND_UP(mclk_rate, tfr->speed_hz);
+	div_cdr2 = DIV_ROUND_UP(div_cdr1, 2);
+	if (div_cdr2 <= (SUN6I_CLK_CTL_CDR2_MASK + 1)) {
+		reg = SUN6I_CLK_CTL_CDR2(div_cdr2 - 1) | SUN6I_CLK_CTL_DRS;
+		tfr->effective_speed_hz = mclk_rate / (2 * div_cdr2);
+	} else {
+		div = min(SUN6I_CLK_CTL_CDR1_MASK, order_base_2(div_cdr1));
+		reg = SUN6I_CLK_CTL_CDR1(div);
+		tfr->effective_speed_hz = mclk_rate / (1 << div);
+	}
+
+	sun6i_spi_write(sspi, SUN6I_CLK_CTL_REG, reg);
+	/* Finally enable the bus - doing so before might raise SCK to HIGH */
+	reg = sun6i_spi_read(sspi, SUN6I_GBL_CTL_REG);
+	reg |= SUN6I_GBL_CTL_BUS_ENABLE;
+	sun6i_spi_write(sspi, SUN6I_GBL_CTL_REG, reg);
+
+	/* Setup the transfer now... */
+	if (sspi->tx_buf)
+		tx_len = tfr->len;
+
+	/* Setup the counters */
+	sun6i_spi_write(sspi, SUN6I_BURST_CNT_REG, tfr->len);
+	sun6i_spi_write(sspi, SUN6I_XMIT_CNT_REG, tx_len);
+	sun6i_spi_write(sspi, SUN6I_BURST_CTL_CNT_REG, tx_len);
+
+	if (!use_dma) {
+		/* Fill the TX FIFO */
+		sun6i_spi_fill_fifo(sspi);
+	} else {
+		ret = sun6i_spi_prepare_dma(sspi, tfr);
+		if (ret) {
+			dev_warn(&master->dev,
+				 "%s: prepare DMA failed, ret=%d",
+				 dev_name(&spi->dev), ret);
+			return ret;
+		}
+	}
+
+	/* Enable the interrupts */
+	reg = SUN6I_INT_CTL_TC;
+
+	if (!use_dma) {
+		if (rx_len > sspi->fifo_depth)
+			reg |= SUN6I_INT_CTL_RF_RDY;
+		if (tx_len > sspi->fifo_depth)
+			reg |= SUN6I_INT_CTL_TF_ERQ;
+	}
+
+	sun6i_spi_write(sspi, SUN6I_INT_CTL_REG, reg);
+
+	/* Start the transfer */
+	reg = sun6i_spi_read(sspi, SUN6I_TFR_CTL_REG);
+	sun6i_spi_write(sspi, SUN6I_TFR_CTL_REG, reg | SUN6I_TFR_CTL_XCH);
+
+	tx_time = max(tfr->len * 8 * 2 / (tfr->speed_hz / 1000), 100U);
+	start = jiffies;
+	timeout = wait_for_completion_timeout(&sspi->done,
+					      msecs_to_jiffies(tx_time));
+	end = jiffies;
+	if (!timeout) {
+		dev_warn(&master->dev,
+			 "%s: timeout transferring %u bytes@%iHz for %i(%i)ms",
+			 dev_name(&spi->dev), tfr->len, tfr->speed_hz,
+			 jiffies_to_msecs(end - start), tx_time);
+		ret = -ETIMEDOUT;
+	}
+
+	sun6i_spi_write(sspi, SUN6I_INT_CTL_REG, 0);
+
+	if (ret && use_dma) {
+		dmaengine_terminate_sync(master->dma_rx);
+		dmaengine_terminate_sync(master->dma_tx);
+	}
+
+	return ret;
+}
+
+static irqreturn_t sun6i_spi_handler(int irq, void *dev_id)
+{
+	struct sun6i_spi *sspi = dev_id;
+	u32 status = sun6i_spi_read(sspi, SUN6I_INT_STA_REG);
+
+	/* Transfer complete */
+	if (status & SUN6I_INT_CTL_TC) {
+		sun6i_spi_write(sspi, SUN6I_INT_STA_REG, SUN6I_INT_CTL_TC);
+		sun6i_spi_drain_fifo(sspi);
+		complete(&sspi->done);
+		return IRQ_HANDLED;
+	}
+
+	/* Receive FIFO 3/4 full */
+	if (status & SUN6I_INT_CTL_RF_RDY) {
+		sun6i_spi_drain_fifo(sspi);
+		/* Only clear the interrupt _after_ draining the FIFO */
+		sun6i_spi_write(sspi, SUN6I_INT_STA_REG, SUN6I_INT_CTL_RF_RDY);
+		return IRQ_HANDLED;
+	}
+
+	/* Transmit FIFO 3/4 empty */
+	if (status & SUN6I_INT_CTL_TF_ERQ) {
+		sun6i_spi_fill_fifo(sspi);
+
+		if (!sspi->len)
+			/* nothing left to transmit */
+			sun6i_spi_disable_interrupt(sspi, SUN6I_INT_CTL_TF_ERQ);
+
+		/* Only clear the interrupt _after_ re-seeding the FIFO */
+		sun6i_spi_write(sspi, SUN6I_INT_STA_REG, SUN6I_INT_CTL_TF_ERQ);
+
+		return IRQ_HANDLED;
+	}
+
+	return IRQ_NONE;
+}
+
+static int sun6i_spi_runtime_resume(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct sun6i_spi *sspi = spi_master_get_devdata(master);
+	int ret;
+
+	ret = clk_prepare_enable(sspi->hclk);
+	if (ret) {
+		dev_err(dev, "Couldn't enable AHB clock\n");
+		goto out;
+	}
+
+	ret = clk_prepare_enable(sspi->mclk);
+	if (ret) {
+		dev_err(dev, "Couldn't enable module clock\n");
+		goto err;
+	}
+
+	ret = reset_control_deassert(sspi->rstc);
+	if (ret) {
+		dev_err(dev, "Couldn't deassert the device from reset\n");
+		goto err2;
+	}
+
+	sun6i_spi_write(sspi, SUN6I_GBL_CTL_REG,
+			SUN6I_GBL_CTL_MASTER | SUN6I_GBL_CTL_TP);
+
+	return 0;
+
+err2:
+	clk_disable_unprepare(sspi->mclk);
+err:
+	clk_disable_unprepare(sspi->hclk);
+out:
+	return ret;
+}
+
+static int sun6i_spi_runtime_suspend(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct sun6i_spi *sspi = spi_master_get_devdata(master);
+
+	reset_control_assert(sspi->rstc);
+	clk_disable_unprepare(sspi->mclk);
+	clk_disable_unprepare(sspi->hclk);
+
+	return 0;
+}
+
+static bool sun6i_spi_can_dma(struct spi_master *master,
+			      struct spi_device *spi,
+			      struct spi_transfer *xfer)
+{
+	struct sun6i_spi *sspi = spi_master_get_devdata(master);
+
+	/*
+	 * If the number of spi words to transfer is less or equal than
+	 * the fifo length we can just fill the fifo and wait for a single
+	 * irq, so don't bother setting up dma
+	 */
+	return xfer->len > sspi->fifo_depth;
+}
+
+static int sun6i_spi_probe(struct platform_device *pdev)
+{
+	struct spi_master *master;
+	struct sun6i_spi *sspi;
+	struct resource *mem;
+	int ret = 0, irq;
+
+	master = spi_alloc_master(&pdev->dev, sizeof(struct sun6i_spi));
+	if (!master) {
+		dev_err(&pdev->dev, "Unable to allocate SPI Master\n");
+		return -ENOMEM;
+	}
+
+	platform_set_drvdata(pdev, master);
+	sspi = spi_master_get_devdata(master);
+
+	sspi->base_addr = devm_platform_get_and_ioremap_resource(pdev, 0, &mem);
+	if (IS_ERR(sspi->base_addr)) {
+		ret = PTR_ERR(sspi->base_addr);
+		goto err_free_master;
+	}
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		ret = -ENXIO;
+		goto err_free_master;
+	}
+
+	ret = devm_request_irq(&pdev->dev, irq, sun6i_spi_handler,
+			       0, "sun6i-spi", sspi);
+	if (ret) {
+		dev_err(&pdev->dev, "Cannot request IRQ\n");
+		goto err_free_master;
+	}
+
+	sspi->master = master;
+	sspi->fifo_depth = (unsigned long)of_device_get_match_data(&pdev->dev);
+
+	master->max_speed_hz = 100 * 1000 * 1000;
+	master->min_speed_hz = 3 * 1000;
+	master->use_gpio_descriptors = true;
+	master->set_cs = sun6i_spi_set_cs;
+	master->transfer_one = sun6i_spi_transfer_one;
+	master->num_chipselect = 4;
+	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_LSB_FIRST;
+	master->bits_per_word_mask = SPI_BPW_MASK(8);
+	master->dev.of_node = pdev->dev.of_node;
+	master->auto_runtime_pm = true;
+	master->max_transfer_size = sun6i_spi_max_transfer_size;
+
+	sspi->hclk = devm_clk_get(&pdev->dev, "ahb");
+	if (IS_ERR(sspi->hclk)) {
+		dev_err(&pdev->dev, "Unable to acquire AHB clock\n");
+		ret = PTR_ERR(sspi->hclk);
+		goto err_free_master;
+	}
+
+	sspi->mclk = devm_clk_get(&pdev->dev, "mod");
+	if (IS_ERR(sspi->mclk)) {
+		dev_err(&pdev->dev, "Unable to acquire module clock\n");
+		ret = PTR_ERR(sspi->mclk);
+		goto err_free_master;
+	}
+
+	init_completion(&sspi->done);
+
+	sspi->rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL);
+	if (IS_ERR(sspi->rstc)) {
+		dev_err(&pdev->dev, "Couldn't get reset controller\n");
+		ret = PTR_ERR(sspi->rstc);
+		goto err_free_master;
+	}
+
+	master->dma_tx = dma_request_chan(&pdev->dev, "tx");
+	if (IS_ERR(master->dma_tx)) {
+		/* Check tx to see if we need defer probing driver */
+		if (PTR_ERR(master->dma_tx) == -EPROBE_DEFER) {
+			ret = -EPROBE_DEFER;
+			goto err_free_master;
+		}
+		dev_warn(&pdev->dev, "Failed to request TX DMA channel\n");
+		master->dma_tx = NULL;
+	}
+
+	master->dma_rx = dma_request_chan(&pdev->dev, "rx");
+	if (IS_ERR(master->dma_rx)) {
+		if (PTR_ERR(master->dma_rx) == -EPROBE_DEFER) {
+			ret = -EPROBE_DEFER;
+			goto err_free_dma_tx;
+		}
+		dev_warn(&pdev->dev, "Failed to request RX DMA channel\n");
+		master->dma_rx = NULL;
+	}
+
+	if (master->dma_tx && master->dma_rx) {
+		sspi->dma_addr_tx = mem->start + SUN6I_TXDATA_REG;
+		sspi->dma_addr_rx = mem->start + SUN6I_RXDATA_REG;
+		master->can_dma = sun6i_spi_can_dma;
+	}
+
+	/*
+	 * This wake-up/shutdown pattern is to be able to have the
+	 * device woken up, even if runtime_pm is disabled
+	 */
+	ret = sun6i_spi_runtime_resume(&pdev->dev);
+	if (ret) {
+		dev_err(&pdev->dev, "Couldn't resume the device\n");
+		goto err_free_dma_rx;
+	}
+
+	pm_runtime_set_autosuspend_delay(&pdev->dev, SUN6I_AUTOSUSPEND_TIMEOUT);
+	pm_runtime_use_autosuspend(&pdev->dev);
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+
+	ret = devm_spi_register_master(&pdev->dev, master);
+	if (ret) {
+		dev_err(&pdev->dev, "cannot register SPI master\n");
+		goto err_pm_disable;
+	}
+
+	return 0;
+
+err_pm_disable:
+	pm_runtime_disable(&pdev->dev);
+	sun6i_spi_runtime_suspend(&pdev->dev);
+err_free_dma_rx:
+	if (master->dma_rx)
+		dma_release_channel(master->dma_rx);
+err_free_dma_tx:
+	if (master->dma_tx)
+		dma_release_channel(master->dma_tx);
+err_free_master:
+	spi_master_put(master);
+	return ret;
+}
+
+static int sun6i_spi_remove(struct platform_device *pdev)
+{
+	struct spi_master *master = platform_get_drvdata(pdev);
+
+	pm_runtime_force_suspend(&pdev->dev);
+
+	if (master->dma_tx)
+		dma_release_channel(master->dma_tx);
+	if (master->dma_rx)
+		dma_release_channel(master->dma_rx);
+	return 0;
+}
+
+static const struct of_device_id sun6i_spi_match[] = {
+	{ .compatible = "allwinner,sun6i-a31-spi", .data = (void *)SUN6I_FIFO_DEPTH },
+	{ .compatible = "allwinner,sun8i-h3-spi",  .data = (void *)SUN8I_FIFO_DEPTH },
+	{}
+};
+MODULE_DEVICE_TABLE(of, sun6i_spi_match);
+
+static const struct dev_pm_ops sun6i_spi_pm_ops = {
+	.runtime_resume		= sun6i_spi_runtime_resume,
+	.runtime_suspend	= sun6i_spi_runtime_suspend,
+};
+
+static struct platform_driver sun6i_spi_driver = {
+	.probe	= sun6i_spi_probe,
+	.remove	= sun6i_spi_remove,
+	.driver	= {
+		.name		= "sun6i-spi",
+		.of_match_table	= sun6i_spi_match,
+		.pm		= &sun6i_spi_pm_ops,
+	},
+};
+module_platform_driver(sun6i_spi_driver);
+
+MODULE_AUTHOR("Pan Nan <pannan@allwinnertech.com>");
+MODULE_AUTHOR("Maxime Ripard <maxime.ripard@free-electrons.com>");
+MODULE_DESCRIPTION("Allwinner A31 SPI controller driver");
+MODULE_LICENSE("GPL");