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, 681 insertions, 0 deletions

diff --git a/drivers/spi/spi-at91-usart.c b/drivers/spi/spi-at91-usart.c
new file mode 100644
index 000000000..9cd738682
--- /dev/null
+++ b/drivers/spi/spi-at91-usart.c
@@ -0,0 +1,681 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Driver for AT91 USART Controllers as SPI
+//
+// Copyright (C) 2018 Microchip Technology Inc.
+//
+// Author: Radu Pirea <radu.pirea@microchip.com>
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-direction.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/gpio/consumer.h>
+#include <linux/pinctrl/consumer.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+
+#include <linux/spi/spi.h>
+
+#define US_CR			0x00
+#define US_MR			0x04
+#define US_IER			0x08
+#define US_IDR			0x0C
+#define US_CSR			0x14
+#define US_RHR			0x18
+#define US_THR			0x1C
+#define US_BRGR			0x20
+#define US_VERSION		0xFC
+
+#define US_CR_RSTRX		BIT(2)
+#define US_CR_RSTTX		BIT(3)
+#define US_CR_RXEN		BIT(4)
+#define US_CR_RXDIS		BIT(5)
+#define US_CR_TXEN		BIT(6)
+#define US_CR_TXDIS		BIT(7)
+
+#define US_MR_SPI_MASTER	0x0E
+#define US_MR_CHRL		GENMASK(7, 6)
+#define US_MR_CPHA		BIT(8)
+#define US_MR_CPOL		BIT(16)
+#define US_MR_CLKO		BIT(18)
+#define US_MR_WRDBT		BIT(20)
+#define US_MR_LOOP		BIT(15)
+
+#define US_IR_RXRDY		BIT(0)
+#define US_IR_TXRDY		BIT(1)
+#define US_IR_OVRE		BIT(5)
+
+#define US_BRGR_SIZE		BIT(16)
+
+#define US_MIN_CLK_DIV		0x06
+#define US_MAX_CLK_DIV		BIT(16)
+
+#define US_RESET		(US_CR_RSTRX | US_CR_RSTTX)
+#define US_DISABLE		(US_CR_RXDIS | US_CR_TXDIS)
+#define US_ENABLE		(US_CR_RXEN | US_CR_TXEN)
+#define US_OVRE_RXRDY_IRQS	(US_IR_OVRE | US_IR_RXRDY)
+
+#define US_INIT \
+	(US_MR_SPI_MASTER | US_MR_CHRL | US_MR_CLKO | US_MR_WRDBT)
+#define US_DMA_MIN_BYTES       16
+#define US_DMA_TIMEOUT         (msecs_to_jiffies(1000))
+
+/* Register access macros */
+#define at91_usart_spi_readl(port, reg) \
+	readl_relaxed((port)->regs + US_##reg)
+#define at91_usart_spi_writel(port, reg, value) \
+	writel_relaxed((value), (port)->regs + US_##reg)
+
+#define at91_usart_spi_readb(port, reg) \
+	readb_relaxed((port)->regs + US_##reg)
+#define at91_usart_spi_writeb(port, reg, value) \
+	writeb_relaxed((value), (port)->regs + US_##reg)
+
+struct at91_usart_spi {
+	struct platform_device  *mpdev;
+	struct spi_transfer	*current_transfer;
+	void __iomem		*regs;
+	struct device		*dev;
+	struct clk		*clk;
+
+	struct completion	xfer_completion;
+
+	/*used in interrupt to protect data reading*/
+	spinlock_t		lock;
+
+	phys_addr_t		phybase;
+
+	int			irq;
+	unsigned int		current_tx_remaining_bytes;
+	unsigned int		current_rx_remaining_bytes;
+
+	u32			spi_clk;
+	u32			status;
+
+	bool			xfer_failed;
+	bool			use_dma;
+};
+
+static void dma_callback(void *data)
+{
+	struct spi_controller   *ctlr = data;
+	struct at91_usart_spi   *aus = spi_master_get_devdata(ctlr);
+
+	at91_usart_spi_writel(aus, IER, US_IR_RXRDY);
+	aus->current_rx_remaining_bytes = 0;
+	complete(&aus->xfer_completion);
+}
+
+static bool at91_usart_spi_can_dma(struct spi_controller *ctrl,
+				   struct spi_device *spi,
+				   struct spi_transfer *xfer)
+{
+	struct at91_usart_spi *aus = spi_master_get_devdata(ctrl);
+
+	return aus->use_dma && xfer->len >= US_DMA_MIN_BYTES;
+}
+
+static int at91_usart_spi_configure_dma(struct spi_controller *ctlr,
+					struct at91_usart_spi *aus)
+{
+	struct dma_slave_config slave_config;
+	struct device *dev = &aus->mpdev->dev;
+	phys_addr_t phybase = aus->phybase;
+	dma_cap_mask_t mask;
+	int err = 0;
+
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_SLAVE, mask);
+
+	ctlr->dma_tx = dma_request_chan(dev, "tx");
+	if (IS_ERR_OR_NULL(ctlr->dma_tx)) {
+		if (IS_ERR(ctlr->dma_tx)) {
+			err = PTR_ERR(ctlr->dma_tx);
+			goto at91_usart_spi_error_clear;
+		}
+
+		dev_dbg(dev,
+			"DMA TX channel not available, SPI unable to use DMA\n");
+		err = -EBUSY;
+		goto at91_usart_spi_error_clear;
+	}
+
+	ctlr->dma_rx = dma_request_chan(dev, "rx");
+	if (IS_ERR_OR_NULL(ctlr->dma_rx)) {
+		if (IS_ERR(ctlr->dma_rx)) {
+			err = PTR_ERR(ctlr->dma_rx);
+			goto at91_usart_spi_error;
+		}
+
+		dev_dbg(dev,
+			"DMA RX channel not available, SPI unable to use DMA\n");
+		err = -EBUSY;
+		goto at91_usart_spi_error;
+	}
+
+	slave_config.dst_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
+	slave_config.src_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
+	slave_config.dst_addr = (dma_addr_t)phybase + US_THR;
+	slave_config.src_addr = (dma_addr_t)phybase + US_RHR;
+	slave_config.src_maxburst = 1;
+	slave_config.dst_maxburst = 1;
+	slave_config.device_fc = false;
+
+	slave_config.direction = DMA_DEV_TO_MEM;
+	if (dmaengine_slave_config(ctlr->dma_rx, &slave_config)) {
+		dev_err(&ctlr->dev,
+			"failed to configure rx dma channel\n");
+		err = -EINVAL;
+		goto at91_usart_spi_error;
+	}
+
+	slave_config.direction = DMA_MEM_TO_DEV;
+	if (dmaengine_slave_config(ctlr->dma_tx, &slave_config)) {
+		dev_err(&ctlr->dev,
+			"failed to configure tx dma channel\n");
+		err = -EINVAL;
+		goto at91_usart_spi_error;
+	}
+
+	aus->use_dma = true;
+	return 0;
+
+at91_usart_spi_error:
+	if (!IS_ERR_OR_NULL(ctlr->dma_tx))
+		dma_release_channel(ctlr->dma_tx);
+	if (!IS_ERR_OR_NULL(ctlr->dma_rx))
+		dma_release_channel(ctlr->dma_rx);
+	ctlr->dma_tx = NULL;
+	ctlr->dma_rx = NULL;
+
+at91_usart_spi_error_clear:
+	return err;
+}
+
+static void at91_usart_spi_release_dma(struct spi_controller *ctlr)
+{
+	if (ctlr->dma_rx)
+		dma_release_channel(ctlr->dma_rx);
+	if (ctlr->dma_tx)
+		dma_release_channel(ctlr->dma_tx);
+}
+
+static void at91_usart_spi_stop_dma(struct spi_controller *ctlr)
+{
+	if (ctlr->dma_rx)
+		dmaengine_terminate_all(ctlr->dma_rx);
+	if (ctlr->dma_tx)
+		dmaengine_terminate_all(ctlr->dma_tx);
+}
+
+static int at91_usart_spi_dma_transfer(struct spi_controller *ctlr,
+				       struct spi_transfer *xfer)
+{
+	struct at91_usart_spi *aus = spi_master_get_devdata(ctlr);
+	struct dma_chan	 *rxchan = ctlr->dma_rx;
+	struct dma_chan *txchan = ctlr->dma_tx;
+	struct dma_async_tx_descriptor *rxdesc;
+	struct dma_async_tx_descriptor *txdesc;
+	dma_cookie_t cookie;
+
+	/* Disable RX interrupt */
+	at91_usart_spi_writel(aus, IDR, US_IR_RXRDY);
+
+	rxdesc = dmaengine_prep_slave_sg(rxchan,
+					 xfer->rx_sg.sgl,
+					 xfer->rx_sg.nents,
+					 DMA_DEV_TO_MEM,
+					 DMA_PREP_INTERRUPT |
+					 DMA_CTRL_ACK);
+	if (!rxdesc)
+		goto at91_usart_spi_err_dma;
+
+	txdesc = dmaengine_prep_slave_sg(txchan,
+					 xfer->tx_sg.sgl,
+					 xfer->tx_sg.nents,
+					 DMA_MEM_TO_DEV,
+					 DMA_PREP_INTERRUPT |
+					 DMA_CTRL_ACK);
+	if (!txdesc)
+		goto at91_usart_spi_err_dma;
+
+	rxdesc->callback = dma_callback;
+	rxdesc->callback_param = ctlr;
+
+	cookie = rxdesc->tx_submit(rxdesc);
+	if (dma_submit_error(cookie))
+		goto at91_usart_spi_err_dma;
+
+	cookie = txdesc->tx_submit(txdesc);
+	if (dma_submit_error(cookie))
+		goto at91_usart_spi_err_dma;
+
+	rxchan->device->device_issue_pending(rxchan);
+	txchan->device->device_issue_pending(txchan);
+
+	return 0;
+
+at91_usart_spi_err_dma:
+	/* Enable RX interrupt if something fails and fallback to PIO */
+	at91_usart_spi_writel(aus, IER, US_IR_RXRDY);
+	at91_usart_spi_stop_dma(ctlr);
+
+	return -ENOMEM;
+}
+
+static unsigned long at91_usart_spi_dma_timeout(struct at91_usart_spi *aus)
+{
+	return wait_for_completion_timeout(&aus->xfer_completion,
+					   US_DMA_TIMEOUT);
+}
+
+static inline u32 at91_usart_spi_tx_ready(struct at91_usart_spi *aus)
+{
+	return aus->status & US_IR_TXRDY;
+}
+
+static inline u32 at91_usart_spi_rx_ready(struct at91_usart_spi *aus)
+{
+	return aus->status & US_IR_RXRDY;
+}
+
+static inline u32 at91_usart_spi_check_overrun(struct at91_usart_spi *aus)
+{
+	return aus->status & US_IR_OVRE;
+}
+
+static inline u32 at91_usart_spi_read_status(struct at91_usart_spi *aus)
+{
+	aus->status = at91_usart_spi_readl(aus, CSR);
+	return aus->status;
+}
+
+static inline void at91_usart_spi_tx(struct at91_usart_spi *aus)
+{
+	unsigned int len = aus->current_transfer->len;
+	unsigned int remaining = aus->current_tx_remaining_bytes;
+	const u8  *tx_buf = aus->current_transfer->tx_buf;
+
+	if (!remaining)
+		return;
+
+	if (at91_usart_spi_tx_ready(aus)) {
+		at91_usart_spi_writeb(aus, THR, tx_buf[len - remaining]);
+		aus->current_tx_remaining_bytes--;
+	}
+}
+
+static inline void at91_usart_spi_rx(struct at91_usart_spi *aus)
+{
+	int len = aus->current_transfer->len;
+	int remaining = aus->current_rx_remaining_bytes;
+	u8  *rx_buf = aus->current_transfer->rx_buf;
+
+	if (!remaining)
+		return;
+
+	rx_buf[len - remaining] = at91_usart_spi_readb(aus, RHR);
+	aus->current_rx_remaining_bytes--;
+}
+
+static inline void
+at91_usart_spi_set_xfer_speed(struct at91_usart_spi *aus,
+			      struct spi_transfer *xfer)
+{
+	at91_usart_spi_writel(aus, BRGR,
+			      DIV_ROUND_UP(aus->spi_clk, xfer->speed_hz));
+}
+
+static irqreturn_t at91_usart_spi_interrupt(int irq, void *dev_id)
+{
+	struct spi_controller *controller = dev_id;
+	struct at91_usart_spi *aus = spi_master_get_devdata(controller);
+
+	spin_lock(&aus->lock);
+	at91_usart_spi_read_status(aus);
+
+	if (at91_usart_spi_check_overrun(aus)) {
+		aus->xfer_failed = true;
+		at91_usart_spi_writel(aus, IDR, US_IR_OVRE | US_IR_RXRDY);
+		spin_unlock(&aus->lock);
+		return IRQ_HANDLED;
+	}
+
+	if (at91_usart_spi_rx_ready(aus)) {
+		at91_usart_spi_rx(aus);
+		spin_unlock(&aus->lock);
+		return IRQ_HANDLED;
+	}
+
+	spin_unlock(&aus->lock);
+
+	return IRQ_NONE;
+}
+
+static int at91_usart_spi_setup(struct spi_device *spi)
+{
+	struct at91_usart_spi *aus = spi_master_get_devdata(spi->controller);
+	u32 *ausd = spi->controller_state;
+	unsigned int mr = at91_usart_spi_readl(aus, MR);
+
+	if (spi->mode & SPI_CPOL)
+		mr |= US_MR_CPOL;
+	else
+		mr &= ~US_MR_CPOL;
+
+	if (spi->mode & SPI_CPHA)
+		mr |= US_MR_CPHA;
+	else
+		mr &= ~US_MR_CPHA;
+
+	if (spi->mode & SPI_LOOP)
+		mr |= US_MR_LOOP;
+	else
+		mr &= ~US_MR_LOOP;
+
+	if (!ausd) {
+		ausd = kzalloc(sizeof(*ausd), GFP_KERNEL);
+		if (!ausd)
+			return -ENOMEM;
+
+		spi->controller_state = ausd;
+	}
+
+	*ausd = mr;
+
+	dev_dbg(&spi->dev,
+		"setup: bpw %u mode 0x%x -> mr %d %08x\n",
+		spi->bits_per_word, spi->mode, spi->chip_select, mr);
+
+	return 0;
+}
+
+static int at91_usart_spi_transfer_one(struct spi_controller *ctlr,
+				       struct spi_device *spi,
+				       struct spi_transfer *xfer)
+{
+	struct at91_usart_spi *aus = spi_master_get_devdata(ctlr);
+	unsigned long dma_timeout = 0;
+	int ret = 0;
+
+	at91_usart_spi_set_xfer_speed(aus, xfer);
+	aus->xfer_failed = false;
+	aus->current_transfer = xfer;
+	aus->current_tx_remaining_bytes = xfer->len;
+	aus->current_rx_remaining_bytes = xfer->len;
+
+	while ((aus->current_tx_remaining_bytes ||
+		aus->current_rx_remaining_bytes) && !aus->xfer_failed) {
+		reinit_completion(&aus->xfer_completion);
+		if (at91_usart_spi_can_dma(ctlr, spi, xfer) &&
+		    !ret) {
+			ret = at91_usart_spi_dma_transfer(ctlr, xfer);
+			if (ret)
+				continue;
+
+			dma_timeout = at91_usart_spi_dma_timeout(aus);
+
+			if (WARN_ON(dma_timeout == 0)) {
+				dev_err(&spi->dev, "DMA transfer timeout\n");
+				return -EIO;
+			}
+			aus->current_tx_remaining_bytes = 0;
+		} else {
+			at91_usart_spi_read_status(aus);
+			at91_usart_spi_tx(aus);
+		}
+
+		cpu_relax();
+	}
+
+	if (aus->xfer_failed) {
+		dev_err(aus->dev, "Overrun!\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int at91_usart_spi_prepare_message(struct spi_controller *ctlr,
+					  struct spi_message *message)
+{
+	struct at91_usart_spi *aus = spi_master_get_devdata(ctlr);
+	struct spi_device *spi = message->spi;
+	u32 *ausd = spi->controller_state;
+
+	at91_usart_spi_writel(aus, CR, US_ENABLE);
+	at91_usart_spi_writel(aus, IER, US_OVRE_RXRDY_IRQS);
+	at91_usart_spi_writel(aus, MR, *ausd);
+
+	return 0;
+}
+
+static int at91_usart_spi_unprepare_message(struct spi_controller *ctlr,
+					    struct spi_message *message)
+{
+	struct at91_usart_spi *aus = spi_master_get_devdata(ctlr);
+
+	at91_usart_spi_writel(aus, CR, US_RESET | US_DISABLE);
+	at91_usart_spi_writel(aus, IDR, US_OVRE_RXRDY_IRQS);
+
+	return 0;
+}
+
+static void at91_usart_spi_cleanup(struct spi_device *spi)
+{
+	struct at91_usart_spi_device *ausd = spi->controller_state;
+
+	spi->controller_state = NULL;
+	kfree(ausd);
+}
+
+static void at91_usart_spi_init(struct at91_usart_spi *aus)
+{
+	at91_usart_spi_writel(aus, MR, US_INIT);
+	at91_usart_spi_writel(aus, CR, US_RESET | US_DISABLE);
+}
+
+static int at91_usart_gpio_setup(struct platform_device *pdev)
+{
+	struct gpio_descs *cs_gpios;
+
+	cs_gpios = devm_gpiod_get_array_optional(&pdev->dev, "cs", GPIOD_OUT_LOW);
+
+	if (IS_ERR(cs_gpios))
+		return PTR_ERR(cs_gpios);
+
+	return 0;
+}
+
+static int at91_usart_spi_probe(struct platform_device *pdev)
+{
+	struct resource *regs;
+	struct spi_controller *controller;
+	struct at91_usart_spi *aus;
+	struct clk *clk;
+	int irq;
+	int ret;
+
+	regs = platform_get_resource(to_platform_device(pdev->dev.parent),
+				     IORESOURCE_MEM, 0);
+	if (!regs)
+		return -EINVAL;
+
+	irq = platform_get_irq(to_platform_device(pdev->dev.parent), 0);
+	if (irq < 0)
+		return irq;
+
+	clk = devm_clk_get(pdev->dev.parent, "usart");
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	ret = -ENOMEM;
+	controller = spi_alloc_master(&pdev->dev, sizeof(*aus));
+	if (!controller)
+		goto at91_usart_spi_probe_fail;
+
+	ret = at91_usart_gpio_setup(pdev);
+	if (ret)
+		goto at91_usart_spi_probe_fail;
+
+	controller->mode_bits = SPI_CPOL | SPI_CPHA | SPI_LOOP | SPI_CS_HIGH;
+	controller->dev.of_node = pdev->dev.parent->of_node;
+	controller->bits_per_word_mask = SPI_BPW_MASK(8);
+	controller->setup = at91_usart_spi_setup;
+	controller->flags = SPI_MASTER_MUST_RX | SPI_MASTER_MUST_TX;
+	controller->transfer_one = at91_usart_spi_transfer_one;
+	controller->prepare_message = at91_usart_spi_prepare_message;
+	controller->unprepare_message = at91_usart_spi_unprepare_message;
+	controller->can_dma = at91_usart_spi_can_dma;
+	controller->cleanup = at91_usart_spi_cleanup;
+	controller->max_speed_hz = DIV_ROUND_UP(clk_get_rate(clk),
+						US_MIN_CLK_DIV);
+	controller->min_speed_hz = DIV_ROUND_UP(clk_get_rate(clk),
+						US_MAX_CLK_DIV);
+	platform_set_drvdata(pdev, controller);
+
+	aus = spi_master_get_devdata(controller);
+
+	aus->dev = &pdev->dev;
+	aus->regs = devm_ioremap_resource(&pdev->dev, regs);
+	if (IS_ERR(aus->regs)) {
+		ret = PTR_ERR(aus->regs);
+		goto at91_usart_spi_probe_fail;
+	}
+
+	aus->irq = irq;
+	aus->clk = clk;
+
+	ret = devm_request_irq(&pdev->dev, irq, at91_usart_spi_interrupt, 0,
+			       dev_name(&pdev->dev), controller);
+	if (ret)
+		goto at91_usart_spi_probe_fail;
+
+	ret = clk_prepare_enable(clk);
+	if (ret)
+		goto at91_usart_spi_probe_fail;
+
+	aus->spi_clk = clk_get_rate(clk);
+	at91_usart_spi_init(aus);
+
+	aus->phybase = regs->start;
+
+	aus->mpdev = to_platform_device(pdev->dev.parent);
+
+	ret = at91_usart_spi_configure_dma(controller, aus);
+	if (ret)
+		goto at91_usart_fail_dma;
+
+	spin_lock_init(&aus->lock);
+	init_completion(&aus->xfer_completion);
+
+	ret = devm_spi_register_master(&pdev->dev, controller);
+	if (ret)
+		goto at91_usart_fail_register_master;
+
+	dev_info(&pdev->dev,
+		 "AT91 USART SPI Controller version 0x%x at %pa (irq %d)\n",
+		 at91_usart_spi_readl(aus, VERSION),
+		 &regs->start, irq);
+
+	return 0;
+
+at91_usart_fail_register_master:
+	at91_usart_spi_release_dma(controller);
+at91_usart_fail_dma:
+	clk_disable_unprepare(clk);
+at91_usart_spi_probe_fail:
+	spi_master_put(controller);
+	return ret;
+}
+
+__maybe_unused static int at91_usart_spi_runtime_suspend(struct device *dev)
+{
+	struct spi_controller *ctlr = dev_get_drvdata(dev);
+	struct at91_usart_spi *aus = spi_master_get_devdata(ctlr);
+
+	clk_disable_unprepare(aus->clk);
+	pinctrl_pm_select_sleep_state(dev);
+
+	return 0;
+}
+
+__maybe_unused static int at91_usart_spi_runtime_resume(struct device *dev)
+{
+	struct spi_controller *ctrl = dev_get_drvdata(dev);
+	struct at91_usart_spi *aus = spi_master_get_devdata(ctrl);
+
+	pinctrl_pm_select_default_state(dev);
+
+	return clk_prepare_enable(aus->clk);
+}
+
+__maybe_unused static int at91_usart_spi_suspend(struct device *dev)
+{
+	struct spi_controller *ctrl = dev_get_drvdata(dev);
+	int ret;
+
+	ret = spi_controller_suspend(ctrl);
+	if (ret)
+		return ret;
+
+	if (!pm_runtime_suspended(dev))
+		at91_usart_spi_runtime_suspend(dev);
+
+	return 0;
+}
+
+__maybe_unused static int at91_usart_spi_resume(struct device *dev)
+{
+	struct spi_controller *ctrl = dev_get_drvdata(dev);
+	struct at91_usart_spi *aus = spi_master_get_devdata(ctrl);
+	int ret;
+
+	if (!pm_runtime_suspended(dev)) {
+		ret = at91_usart_spi_runtime_resume(dev);
+		if (ret)
+			return ret;
+	}
+
+	at91_usart_spi_init(aus);
+
+	return spi_controller_resume(ctrl);
+}
+
+static int at91_usart_spi_remove(struct platform_device *pdev)
+{
+	struct spi_controller *ctlr = platform_get_drvdata(pdev);
+	struct at91_usart_spi *aus = spi_master_get_devdata(ctlr);
+
+	at91_usart_spi_release_dma(ctlr);
+	clk_disable_unprepare(aus->clk);
+
+	return 0;
+}
+
+static const struct dev_pm_ops at91_usart_spi_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(at91_usart_spi_suspend, at91_usart_spi_resume)
+	SET_RUNTIME_PM_OPS(at91_usart_spi_runtime_suspend,
+			   at91_usart_spi_runtime_resume, NULL)
+};
+
+static struct platform_driver at91_usart_spi_driver = {
+	.driver = {
+		.name = "at91_usart_spi",
+		.pm = &at91_usart_spi_pm_ops,
+	},
+	.probe = at91_usart_spi_probe,
+	.remove = at91_usart_spi_remove,
+};
+
+module_platform_driver(at91_usart_spi_driver);
+
+MODULE_DESCRIPTION("Microchip AT91 USART SPI Controller driver");
+MODULE_AUTHOR("Radu Pirea <radu.pirea@microchip.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:at91_usart_spi");