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, 1617 insertions, 0 deletions

diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
new file mode 100644
index 000000000..6ba9b0d77
--- /dev/null
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -0,0 +1,1617 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * OMAP2 McSPI controller driver
+ *
+ * Copyright (C) 2005, 2006 Nokia Corporation
+ * Author:	Samuel Ortiz <samuel.ortiz@nokia.com> and
+ *		Juha Yrjola <juha.yrjola@nokia.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
+#include <linux/pinctrl/consumer.h>
+#include <linux/platform_device.h>
+#include <linux/err.h>
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/pm_runtime.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/gcd.h>
+
+#include <linux/spi/spi.h>
+
+#include <linux/platform_data/spi-omap2-mcspi.h>
+
+#define OMAP2_MCSPI_MAX_FREQ		48000000
+#define OMAP2_MCSPI_MAX_DIVIDER		4096
+#define OMAP2_MCSPI_MAX_FIFODEPTH	64
+#define OMAP2_MCSPI_MAX_FIFOWCNT	0xFFFF
+#define SPI_AUTOSUSPEND_TIMEOUT		2000
+
+#define OMAP2_MCSPI_REVISION		0x00
+#define OMAP2_MCSPI_SYSSTATUS		0x14
+#define OMAP2_MCSPI_IRQSTATUS		0x18
+#define OMAP2_MCSPI_IRQENABLE		0x1c
+#define OMAP2_MCSPI_WAKEUPENABLE	0x20
+#define OMAP2_MCSPI_SYST		0x24
+#define OMAP2_MCSPI_MODULCTRL		0x28
+#define OMAP2_MCSPI_XFERLEVEL		0x7c
+
+/* per-channel banks, 0x14 bytes each, first is: */
+#define OMAP2_MCSPI_CHCONF0		0x2c
+#define OMAP2_MCSPI_CHSTAT0		0x30
+#define OMAP2_MCSPI_CHCTRL0		0x34
+#define OMAP2_MCSPI_TX0			0x38
+#define OMAP2_MCSPI_RX0			0x3c
+
+/* per-register bitmasks: */
+#define OMAP2_MCSPI_IRQSTATUS_EOW	BIT(17)
+
+#define OMAP2_MCSPI_MODULCTRL_SINGLE	BIT(0)
+#define OMAP2_MCSPI_MODULCTRL_MS	BIT(2)
+#define OMAP2_MCSPI_MODULCTRL_STEST	BIT(3)
+
+#define OMAP2_MCSPI_CHCONF_PHA		BIT(0)
+#define OMAP2_MCSPI_CHCONF_POL		BIT(1)
+#define OMAP2_MCSPI_CHCONF_CLKD_MASK	(0x0f << 2)
+#define OMAP2_MCSPI_CHCONF_EPOL		BIT(6)
+#define OMAP2_MCSPI_CHCONF_WL_MASK	(0x1f << 7)
+#define OMAP2_MCSPI_CHCONF_TRM_RX_ONLY	BIT(12)
+#define OMAP2_MCSPI_CHCONF_TRM_TX_ONLY	BIT(13)
+#define OMAP2_MCSPI_CHCONF_TRM_MASK	(0x03 << 12)
+#define OMAP2_MCSPI_CHCONF_DMAW		BIT(14)
+#define OMAP2_MCSPI_CHCONF_DMAR		BIT(15)
+#define OMAP2_MCSPI_CHCONF_DPE0		BIT(16)
+#define OMAP2_MCSPI_CHCONF_DPE1		BIT(17)
+#define OMAP2_MCSPI_CHCONF_IS		BIT(18)
+#define OMAP2_MCSPI_CHCONF_TURBO	BIT(19)
+#define OMAP2_MCSPI_CHCONF_FORCE	BIT(20)
+#define OMAP2_MCSPI_CHCONF_FFET		BIT(27)
+#define OMAP2_MCSPI_CHCONF_FFER		BIT(28)
+#define OMAP2_MCSPI_CHCONF_CLKG		BIT(29)
+
+#define OMAP2_MCSPI_CHSTAT_RXS		BIT(0)
+#define OMAP2_MCSPI_CHSTAT_TXS		BIT(1)
+#define OMAP2_MCSPI_CHSTAT_EOT		BIT(2)
+#define OMAP2_MCSPI_CHSTAT_TXFFE	BIT(3)
+
+#define OMAP2_MCSPI_CHCTRL_EN		BIT(0)
+#define OMAP2_MCSPI_CHCTRL_EXTCLK_MASK	(0xff << 8)
+
+#define OMAP2_MCSPI_WAKEUPENABLE_WKEN	BIT(0)
+
+/* We have 2 DMA channels per CS, one for RX and one for TX */
+struct omap2_mcspi_dma {
+	struct dma_chan *dma_tx;
+	struct dma_chan *dma_rx;
+
+	struct completion dma_tx_completion;
+	struct completion dma_rx_completion;
+
+	char dma_rx_ch_name[14];
+	char dma_tx_ch_name[14];
+};
+
+/* use PIO for small transfers, avoiding DMA setup/teardown overhead and
+ * cache operations; better heuristics consider wordsize and bitrate.
+ */
+#define DMA_MIN_BYTES			160
+
+
+/*
+ * Used for context save and restore, structure members to be updated whenever
+ * corresponding registers are modified.
+ */
+struct omap2_mcspi_regs {
+	u32 modulctrl;
+	u32 wakeupenable;
+	struct list_head cs;
+};
+
+struct omap2_mcspi {
+	struct completion	txdone;
+	struct spi_master	*master;
+	/* Virtual base address of the controller */
+	void __iomem		*base;
+	unsigned long		phys;
+	/* SPI1 has 4 channels, while SPI2 has 2 */
+	struct omap2_mcspi_dma	*dma_channels;
+	struct device		*dev;
+	struct omap2_mcspi_regs ctx;
+	int			fifo_depth;
+	bool			slave_aborted;
+	unsigned int		pin_dir:1;
+	size_t			max_xfer_len;
+};
+
+struct omap2_mcspi_cs {
+	void __iomem		*base;
+	unsigned long		phys;
+	int			word_len;
+	u16			mode;
+	struct list_head	node;
+	/* Context save and restore shadow register */
+	u32			chconf0, chctrl0;
+};
+
+static inline void mcspi_write_reg(struct spi_master *master,
+		int idx, u32 val)
+{
+	struct omap2_mcspi *mcspi = spi_master_get_devdata(master);
+
+	writel_relaxed(val, mcspi->base + idx);
+}
+
+static inline u32 mcspi_read_reg(struct spi_master *master, int idx)
+{
+	struct omap2_mcspi *mcspi = spi_master_get_devdata(master);
+
+	return readl_relaxed(mcspi->base + idx);
+}
+
+static inline void mcspi_write_cs_reg(const struct spi_device *spi,
+		int idx, u32 val)
+{
+	struct omap2_mcspi_cs	*cs = spi->controller_state;
+
+	writel_relaxed(val, cs->base +  idx);
+}
+
+static inline u32 mcspi_read_cs_reg(const struct spi_device *spi, int idx)
+{
+	struct omap2_mcspi_cs	*cs = spi->controller_state;
+
+	return readl_relaxed(cs->base + idx);
+}
+
+static inline u32 mcspi_cached_chconf0(const struct spi_device *spi)
+{
+	struct omap2_mcspi_cs *cs = spi->controller_state;
+
+	return cs->chconf0;
+}
+
+static inline void mcspi_write_chconf0(const struct spi_device *spi, u32 val)
+{
+	struct omap2_mcspi_cs *cs = spi->controller_state;
+
+	cs->chconf0 = val;
+	mcspi_write_cs_reg(spi, OMAP2_MCSPI_CHCONF0, val);
+	mcspi_read_cs_reg(spi, OMAP2_MCSPI_CHCONF0);
+}
+
+static inline int mcspi_bytes_per_word(int word_len)
+{
+	if (word_len <= 8)
+		return 1;
+	else if (word_len <= 16)
+		return 2;
+	else /* word_len <= 32 */
+		return 4;
+}
+
+static void omap2_mcspi_set_dma_req(const struct spi_device *spi,
+		int is_read, int enable)
+{
+	u32 l, rw;
+
+	l = mcspi_cached_chconf0(spi);
+
+	if (is_read) /* 1 is read, 0 write */
+		rw = OMAP2_MCSPI_CHCONF_DMAR;
+	else
+		rw = OMAP2_MCSPI_CHCONF_DMAW;
+
+	if (enable)
+		l |= rw;
+	else
+		l &= ~rw;
+
+	mcspi_write_chconf0(spi, l);
+}
+
+static void omap2_mcspi_set_enable(const struct spi_device *spi, int enable)
+{
+	struct omap2_mcspi_cs *cs = spi->controller_state;
+	u32 l;
+
+	l = cs->chctrl0;
+	if (enable)
+		l |= OMAP2_MCSPI_CHCTRL_EN;
+	else
+		l &= ~OMAP2_MCSPI_CHCTRL_EN;
+	cs->chctrl0 = l;
+	mcspi_write_cs_reg(spi, OMAP2_MCSPI_CHCTRL0, cs->chctrl0);
+	/* Flash post-writes */
+	mcspi_read_cs_reg(spi, OMAP2_MCSPI_CHCTRL0);
+}
+
+static void omap2_mcspi_set_cs(struct spi_device *spi, bool enable)
+{
+	struct omap2_mcspi *mcspi = spi_master_get_devdata(spi->master);
+	u32 l;
+
+	/* The controller handles the inverted chip selects
+	 * using the OMAP2_MCSPI_CHCONF_EPOL bit so revert
+	 * the inversion from the core spi_set_cs function.
+	 */
+	if (spi->mode & SPI_CS_HIGH)
+		enable = !enable;
+
+	if (spi->controller_state) {
+		int err = pm_runtime_resume_and_get(mcspi->dev);
+		if (err < 0) {
+			dev_err(mcspi->dev, "failed to get sync: %d\n", err);
+			return;
+		}
+
+		l = mcspi_cached_chconf0(spi);
+
+		if (enable)
+			l &= ~OMAP2_MCSPI_CHCONF_FORCE;
+		else
+			l |= OMAP2_MCSPI_CHCONF_FORCE;
+
+		mcspi_write_chconf0(spi, l);
+
+		pm_runtime_mark_last_busy(mcspi->dev);
+		pm_runtime_put_autosuspend(mcspi->dev);
+	}
+}
+
+static void omap2_mcspi_set_mode(struct spi_master *master)
+{
+	struct omap2_mcspi	*mcspi = spi_master_get_devdata(master);
+	struct omap2_mcspi_regs	*ctx = &mcspi->ctx;
+	u32 l;
+
+	/*
+	 * Choose master or slave mode
+	 */
+	l = mcspi_read_reg(master, OMAP2_MCSPI_MODULCTRL);
+	l &= ~(OMAP2_MCSPI_MODULCTRL_STEST);
+	if (spi_controller_is_slave(master)) {
+		l |= (OMAP2_MCSPI_MODULCTRL_MS);
+	} else {
+		l &= ~(OMAP2_MCSPI_MODULCTRL_MS);
+		l |= OMAP2_MCSPI_MODULCTRL_SINGLE;
+	}
+	mcspi_write_reg(master, OMAP2_MCSPI_MODULCTRL, l);
+
+	ctx->modulctrl = l;
+}
+
+static void omap2_mcspi_set_fifo(const struct spi_device *spi,
+				struct spi_transfer *t, int enable)
+{
+	struct spi_master *master = spi->master;
+	struct omap2_mcspi_cs *cs = spi->controller_state;
+	struct omap2_mcspi *mcspi;
+	unsigned int wcnt;
+	int max_fifo_depth, bytes_per_word;
+	u32 chconf, xferlevel;
+
+	mcspi = spi_master_get_devdata(master);
+
+	chconf = mcspi_cached_chconf0(spi);
+	if (enable) {
+		bytes_per_word = mcspi_bytes_per_word(cs->word_len);
+		if (t->len % bytes_per_word != 0)
+			goto disable_fifo;
+
+		if (t->rx_buf != NULL && t->tx_buf != NULL)
+			max_fifo_depth = OMAP2_MCSPI_MAX_FIFODEPTH / 2;
+		else
+			max_fifo_depth = OMAP2_MCSPI_MAX_FIFODEPTH;
+
+		wcnt = t->len / bytes_per_word;
+		if (wcnt > OMAP2_MCSPI_MAX_FIFOWCNT)
+			goto disable_fifo;
+
+		xferlevel = wcnt << 16;
+		if (t->rx_buf != NULL) {
+			chconf |= OMAP2_MCSPI_CHCONF_FFER;
+			xferlevel |= (bytes_per_word - 1) << 8;
+		}
+
+		if (t->tx_buf != NULL) {
+			chconf |= OMAP2_MCSPI_CHCONF_FFET;
+			xferlevel |= bytes_per_word - 1;
+		}
+
+		mcspi_write_reg(master, OMAP2_MCSPI_XFERLEVEL, xferlevel);
+		mcspi_write_chconf0(spi, chconf);
+		mcspi->fifo_depth = max_fifo_depth;
+
+		return;
+	}
+
+disable_fifo:
+	if (t->rx_buf != NULL)
+		chconf &= ~OMAP2_MCSPI_CHCONF_FFER;
+
+	if (t->tx_buf != NULL)
+		chconf &= ~OMAP2_MCSPI_CHCONF_FFET;
+
+	mcspi_write_chconf0(spi, chconf);
+	mcspi->fifo_depth = 0;
+}
+
+static int mcspi_wait_for_reg_bit(void __iomem *reg, unsigned long bit)
+{
+	unsigned long timeout;
+
+	timeout = jiffies + msecs_to_jiffies(1000);
+	while (!(readl_relaxed(reg) & bit)) {
+		if (time_after(jiffies, timeout)) {
+			if (!(readl_relaxed(reg) & bit))
+				return -ETIMEDOUT;
+			else
+				return 0;
+		}
+		cpu_relax();
+	}
+	return 0;
+}
+
+static int mcspi_wait_for_completion(struct  omap2_mcspi *mcspi,
+				     struct completion *x)
+{
+	if (spi_controller_is_slave(mcspi->master)) {
+		if (wait_for_completion_interruptible(x) ||
+		    mcspi->slave_aborted)
+			return -EINTR;
+	} else {
+		wait_for_completion(x);
+	}
+
+	return 0;
+}
+
+static void omap2_mcspi_rx_callback(void *data)
+{
+	struct spi_device *spi = data;
+	struct omap2_mcspi *mcspi = spi_master_get_devdata(spi->master);
+	struct omap2_mcspi_dma *mcspi_dma = &mcspi->dma_channels[spi->chip_select];
+
+	/* We must disable the DMA RX request */
+	omap2_mcspi_set_dma_req(spi, 1, 0);
+
+	complete(&mcspi_dma->dma_rx_completion);
+}
+
+static void omap2_mcspi_tx_callback(void *data)
+{
+	struct spi_device *spi = data;
+	struct omap2_mcspi *mcspi = spi_master_get_devdata(spi->master);
+	struct omap2_mcspi_dma *mcspi_dma = &mcspi->dma_channels[spi->chip_select];
+
+	/* We must disable the DMA TX request */
+	omap2_mcspi_set_dma_req(spi, 0, 0);
+
+	complete(&mcspi_dma->dma_tx_completion);
+}
+
+static void omap2_mcspi_tx_dma(struct spi_device *spi,
+				struct spi_transfer *xfer,
+				struct dma_slave_config cfg)
+{
+	struct omap2_mcspi	*mcspi;
+	struct omap2_mcspi_dma  *mcspi_dma;
+	struct dma_async_tx_descriptor *tx;
+
+	mcspi = spi_master_get_devdata(spi->master);
+	mcspi_dma = &mcspi->dma_channels[spi->chip_select];
+
+	dmaengine_slave_config(mcspi_dma->dma_tx, &cfg);
+
+	tx = dmaengine_prep_slave_sg(mcspi_dma->dma_tx, xfer->tx_sg.sgl,
+				     xfer->tx_sg.nents,
+				     DMA_MEM_TO_DEV,
+				     DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	if (tx) {
+		tx->callback = omap2_mcspi_tx_callback;
+		tx->callback_param = spi;
+		dmaengine_submit(tx);
+	} else {
+		/* FIXME: fall back to PIO? */
+	}
+	dma_async_issue_pending(mcspi_dma->dma_tx);
+	omap2_mcspi_set_dma_req(spi, 0, 1);
+}
+
+static unsigned
+omap2_mcspi_rx_dma(struct spi_device *spi, struct spi_transfer *xfer,
+				struct dma_slave_config cfg,
+				unsigned es)
+{
+	struct omap2_mcspi	*mcspi;
+	struct omap2_mcspi_dma  *mcspi_dma;
+	unsigned int		count, transfer_reduction = 0;
+	struct scatterlist	*sg_out[2];
+	int			nb_sizes = 0, out_mapped_nents[2], ret, x;
+	size_t			sizes[2];
+	u32			l;
+	int			elements = 0;
+	int			word_len, element_count;
+	struct omap2_mcspi_cs	*cs = spi->controller_state;
+	void __iomem		*chstat_reg = cs->base + OMAP2_MCSPI_CHSTAT0;
+	struct dma_async_tx_descriptor *tx;
+
+	mcspi = spi_master_get_devdata(spi->master);
+	mcspi_dma = &mcspi->dma_channels[spi->chip_select];
+	count = xfer->len;
+
+	/*
+	 *  In the "End-of-Transfer Procedure" section for DMA RX in OMAP35x TRM
+	 *  it mentions reducing DMA transfer length by one element in master
+	 *  normal mode.
+	 */
+	if (mcspi->fifo_depth == 0)
+		transfer_reduction = es;
+
+	word_len = cs->word_len;
+	l = mcspi_cached_chconf0(spi);
+
+	if (word_len <= 8)
+		element_count = count;
+	else if (word_len <= 16)
+		element_count = count >> 1;
+	else /* word_len <= 32 */
+		element_count = count >> 2;
+
+
+	dmaengine_slave_config(mcspi_dma->dma_rx, &cfg);
+
+	/*
+	 *  Reduce DMA transfer length by one more if McSPI is
+	 *  configured in turbo mode.
+	 */
+	if ((l & OMAP2_MCSPI_CHCONF_TURBO) && mcspi->fifo_depth == 0)
+		transfer_reduction += es;
+
+	if (transfer_reduction) {
+		/* Split sgl into two. The second sgl won't be used. */
+		sizes[0] = count - transfer_reduction;
+		sizes[1] = transfer_reduction;
+		nb_sizes = 2;
+	} else {
+		/*
+		 * Don't bother splitting the sgl. This essentially
+		 * clones the original sgl.
+		 */
+		sizes[0] = count;
+		nb_sizes = 1;
+	}
+
+	ret = sg_split(xfer->rx_sg.sgl, xfer->rx_sg.nents, 0, nb_sizes,
+		       sizes, sg_out, out_mapped_nents, GFP_KERNEL);
+
+	if (ret < 0) {
+		dev_err(&spi->dev, "sg_split failed\n");
+		return 0;
+	}
+
+	tx = dmaengine_prep_slave_sg(mcspi_dma->dma_rx, sg_out[0],
+				     out_mapped_nents[0], DMA_DEV_TO_MEM,
+				     DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	if (tx) {
+		tx->callback = omap2_mcspi_rx_callback;
+		tx->callback_param = spi;
+		dmaengine_submit(tx);
+	} else {
+		/* FIXME: fall back to PIO? */
+	}
+
+	dma_async_issue_pending(mcspi_dma->dma_rx);
+	omap2_mcspi_set_dma_req(spi, 1, 1);
+
+	ret = mcspi_wait_for_completion(mcspi, &mcspi_dma->dma_rx_completion);
+	if (ret || mcspi->slave_aborted) {
+		dmaengine_terminate_sync(mcspi_dma->dma_rx);
+		omap2_mcspi_set_dma_req(spi, 1, 0);
+		return 0;
+	}
+
+	for (x = 0; x < nb_sizes; x++)
+		kfree(sg_out[x]);
+
+	if (mcspi->fifo_depth > 0)
+		return count;
+
+	/*
+	 *  Due to the DMA transfer length reduction the missing bytes must
+	 *  be read manually to receive all of the expected data.
+	 */
+	omap2_mcspi_set_enable(spi, 0);
+
+	elements = element_count - 1;
+
+	if (l & OMAP2_MCSPI_CHCONF_TURBO) {
+		elements--;
+
+		if (!mcspi_wait_for_reg_bit(chstat_reg,
+					    OMAP2_MCSPI_CHSTAT_RXS)) {
+			u32 w;
+
+			w = mcspi_read_cs_reg(spi, OMAP2_MCSPI_RX0);
+			if (word_len <= 8)
+				((u8 *)xfer->rx_buf)[elements++] = w;
+			else if (word_len <= 16)
+				((u16 *)xfer->rx_buf)[elements++] = w;
+			else /* word_len <= 32 */
+				((u32 *)xfer->rx_buf)[elements++] = w;
+		} else {
+			int bytes_per_word = mcspi_bytes_per_word(word_len);
+			dev_err(&spi->dev, "DMA RX penultimate word empty\n");
+			count -= (bytes_per_word << 1);
+			omap2_mcspi_set_enable(spi, 1);
+			return count;
+		}
+	}
+	if (!mcspi_wait_for_reg_bit(chstat_reg, OMAP2_MCSPI_CHSTAT_RXS)) {
+		u32 w;
+
+		w = mcspi_read_cs_reg(spi, OMAP2_MCSPI_RX0);
+		if (word_len <= 8)
+			((u8 *)xfer->rx_buf)[elements] = w;
+		else if (word_len <= 16)
+			((u16 *)xfer->rx_buf)[elements] = w;
+		else /* word_len <= 32 */
+			((u32 *)xfer->rx_buf)[elements] = w;
+	} else {
+		dev_err(&spi->dev, "DMA RX last word empty\n");
+		count -= mcspi_bytes_per_word(word_len);
+	}
+	omap2_mcspi_set_enable(spi, 1);
+	return count;
+}
+
+static unsigned
+omap2_mcspi_txrx_dma(struct spi_device *spi, struct spi_transfer *xfer)
+{
+	struct omap2_mcspi	*mcspi;
+	struct omap2_mcspi_cs	*cs = spi->controller_state;
+	struct omap2_mcspi_dma  *mcspi_dma;
+	unsigned int		count;
+	u8			*rx;
+	const u8		*tx;
+	struct dma_slave_config	cfg;
+	enum dma_slave_buswidth width;
+	unsigned es;
+	void __iomem		*chstat_reg;
+	void __iomem            *irqstat_reg;
+	int			wait_res;
+
+	mcspi = spi_master_get_devdata(spi->master);
+	mcspi_dma = &mcspi->dma_channels[spi->chip_select];
+
+	if (cs->word_len <= 8) {
+		width = DMA_SLAVE_BUSWIDTH_1_BYTE;
+		es = 1;
+	} else if (cs->word_len <= 16) {
+		width = DMA_SLAVE_BUSWIDTH_2_BYTES;
+		es = 2;
+	} else {
+		width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		es = 4;
+	}
+
+	count = xfer->len;
+
+	memset(&cfg, 0, sizeof(cfg));
+	cfg.src_addr = cs->phys + OMAP2_MCSPI_RX0;
+	cfg.dst_addr = cs->phys + OMAP2_MCSPI_TX0;
+	cfg.src_addr_width = width;
+	cfg.dst_addr_width = width;
+	cfg.src_maxburst = 1;
+	cfg.dst_maxburst = 1;
+
+	rx = xfer->rx_buf;
+	tx = xfer->tx_buf;
+
+	mcspi->slave_aborted = false;
+	reinit_completion(&mcspi_dma->dma_tx_completion);
+	reinit_completion(&mcspi_dma->dma_rx_completion);
+	reinit_completion(&mcspi->txdone);
+	if (tx) {
+		/* Enable EOW IRQ to know end of tx in slave mode */
+		if (spi_controller_is_slave(spi->master))
+			mcspi_write_reg(spi->master,
+					OMAP2_MCSPI_IRQENABLE,
+					OMAP2_MCSPI_IRQSTATUS_EOW);
+		omap2_mcspi_tx_dma(spi, xfer, cfg);
+	}
+
+	if (rx != NULL)
+		count = omap2_mcspi_rx_dma(spi, xfer, cfg, es);
+
+	if (tx != NULL) {
+		int ret;
+
+		ret = mcspi_wait_for_completion(mcspi, &mcspi_dma->dma_tx_completion);
+		if (ret || mcspi->slave_aborted) {
+			dmaengine_terminate_sync(mcspi_dma->dma_tx);
+			omap2_mcspi_set_dma_req(spi, 0, 0);
+			return 0;
+		}
+
+		if (spi_controller_is_slave(mcspi->master)) {
+			ret = mcspi_wait_for_completion(mcspi, &mcspi->txdone);
+			if (ret || mcspi->slave_aborted)
+				return 0;
+		}
+
+		if (mcspi->fifo_depth > 0) {
+			irqstat_reg = mcspi->base + OMAP2_MCSPI_IRQSTATUS;
+
+			if (mcspi_wait_for_reg_bit(irqstat_reg,
+						OMAP2_MCSPI_IRQSTATUS_EOW) < 0)
+				dev_err(&spi->dev, "EOW timed out\n");
+
+			mcspi_write_reg(mcspi->master, OMAP2_MCSPI_IRQSTATUS,
+					OMAP2_MCSPI_IRQSTATUS_EOW);
+		}
+
+		/* for TX_ONLY mode, be sure all words have shifted out */
+		if (rx == NULL) {
+			chstat_reg = cs->base + OMAP2_MCSPI_CHSTAT0;
+			if (mcspi->fifo_depth > 0) {
+				wait_res = mcspi_wait_for_reg_bit(chstat_reg,
+						OMAP2_MCSPI_CHSTAT_TXFFE);
+				if (wait_res < 0)
+					dev_err(&spi->dev, "TXFFE timed out\n");
+			} else {
+				wait_res = mcspi_wait_for_reg_bit(chstat_reg,
+						OMAP2_MCSPI_CHSTAT_TXS);
+				if (wait_res < 0)
+					dev_err(&spi->dev, "TXS timed out\n");
+			}
+			if (wait_res >= 0 &&
+				(mcspi_wait_for_reg_bit(chstat_reg,
+					OMAP2_MCSPI_CHSTAT_EOT) < 0))
+				dev_err(&spi->dev, "EOT timed out\n");
+		}
+	}
+	return count;
+}
+
+static unsigned
+omap2_mcspi_txrx_pio(struct spi_device *spi, struct spi_transfer *xfer)
+{
+	struct omap2_mcspi_cs	*cs = spi->controller_state;
+	unsigned int		count, c;
+	u32			l;
+	void __iomem		*base = cs->base;
+	void __iomem		*tx_reg;
+	void __iomem		*rx_reg;
+	void __iomem		*chstat_reg;
+	int			word_len;
+
+	count = xfer->len;
+	c = count;
+	word_len = cs->word_len;
+
+	l = mcspi_cached_chconf0(spi);
+
+	/* We store the pre-calculated register addresses on stack to speed
+	 * up the transfer loop. */
+	tx_reg		= base + OMAP2_MCSPI_TX0;
+	rx_reg		= base + OMAP2_MCSPI_RX0;
+	chstat_reg	= base + OMAP2_MCSPI_CHSTAT0;
+
+	if (c < (word_len>>3))
+		return 0;
+
+	if (word_len <= 8) {
+		u8		*rx;
+		const u8	*tx;
+
+		rx = xfer->rx_buf;
+		tx = xfer->tx_buf;
+
+		do {
+			c -= 1;
+			if (tx != NULL) {
+				if (mcspi_wait_for_reg_bit(chstat_reg,
+						OMAP2_MCSPI_CHSTAT_TXS) < 0) {
+					dev_err(&spi->dev, "TXS timed out\n");
+					goto out;
+				}
+				dev_vdbg(&spi->dev, "write-%d %02x\n",
+						word_len, *tx);
+				writel_relaxed(*tx++, tx_reg);
+			}
+			if (rx != NULL) {
+				if (mcspi_wait_for_reg_bit(chstat_reg,
+						OMAP2_MCSPI_CHSTAT_RXS) < 0) {
+					dev_err(&spi->dev, "RXS timed out\n");
+					goto out;
+				}
+
+				if (c == 1 && tx == NULL &&
+				    (l & OMAP2_MCSPI_CHCONF_TURBO)) {
+					omap2_mcspi_set_enable(spi, 0);
+					*rx++ = readl_relaxed(rx_reg);
+					dev_vdbg(&spi->dev, "read-%d %02x\n",
+						    word_len, *(rx - 1));
+					if (mcspi_wait_for_reg_bit(chstat_reg,
+						OMAP2_MCSPI_CHSTAT_RXS) < 0) {
+						dev_err(&spi->dev,
+							"RXS timed out\n");
+						goto out;
+					}
+					c = 0;
+				} else if (c == 0 && tx == NULL) {
+					omap2_mcspi_set_enable(spi, 0);
+				}
+
+				*rx++ = readl_relaxed(rx_reg);
+				dev_vdbg(&spi->dev, "read-%d %02x\n",
+						word_len, *(rx - 1));
+			}
+			/* Add word delay between each word */
+			spi_delay_exec(&xfer->word_delay, xfer);
+		} while (c);
+	} else if (word_len <= 16) {
+		u16		*rx;
+		const u16	*tx;
+
+		rx = xfer->rx_buf;
+		tx = xfer->tx_buf;
+		do {
+			c -= 2;
+			if (tx != NULL) {
+				if (mcspi_wait_for_reg_bit(chstat_reg,
+						OMAP2_MCSPI_CHSTAT_TXS) < 0) {
+					dev_err(&spi->dev, "TXS timed out\n");
+					goto out;
+				}
+				dev_vdbg(&spi->dev, "write-%d %04x\n",
+						word_len, *tx);
+				writel_relaxed(*tx++, tx_reg);
+			}
+			if (rx != NULL) {
+				if (mcspi_wait_for_reg_bit(chstat_reg,
+						OMAP2_MCSPI_CHSTAT_RXS) < 0) {
+					dev_err(&spi->dev, "RXS timed out\n");
+					goto out;
+				}
+
+				if (c == 2 && tx == NULL &&
+				    (l & OMAP2_MCSPI_CHCONF_TURBO)) {
+					omap2_mcspi_set_enable(spi, 0);
+					*rx++ = readl_relaxed(rx_reg);
+					dev_vdbg(&spi->dev, "read-%d %04x\n",
+						    word_len, *(rx - 1));
+					if (mcspi_wait_for_reg_bit(chstat_reg,
+						OMAP2_MCSPI_CHSTAT_RXS) < 0) {
+						dev_err(&spi->dev,
+							"RXS timed out\n");
+						goto out;
+					}
+					c = 0;
+				} else if (c == 0 && tx == NULL) {
+					omap2_mcspi_set_enable(spi, 0);
+				}
+
+				*rx++ = readl_relaxed(rx_reg);
+				dev_vdbg(&spi->dev, "read-%d %04x\n",
+						word_len, *(rx - 1));
+			}
+			/* Add word delay between each word */
+			spi_delay_exec(&xfer->word_delay, xfer);
+		} while (c >= 2);
+	} else if (word_len <= 32) {
+		u32		*rx;
+		const u32	*tx;
+
+		rx = xfer->rx_buf;
+		tx = xfer->tx_buf;
+		do {
+			c -= 4;
+			if (tx != NULL) {
+				if (mcspi_wait_for_reg_bit(chstat_reg,
+						OMAP2_MCSPI_CHSTAT_TXS) < 0) {
+					dev_err(&spi->dev, "TXS timed out\n");
+					goto out;
+				}
+				dev_vdbg(&spi->dev, "write-%d %08x\n",
+						word_len, *tx);
+				writel_relaxed(*tx++, tx_reg);
+			}
+			if (rx != NULL) {
+				if (mcspi_wait_for_reg_bit(chstat_reg,
+						OMAP2_MCSPI_CHSTAT_RXS) < 0) {
+					dev_err(&spi->dev, "RXS timed out\n");
+					goto out;
+				}
+
+				if (c == 4 && tx == NULL &&
+				    (l & OMAP2_MCSPI_CHCONF_TURBO)) {
+					omap2_mcspi_set_enable(spi, 0);
+					*rx++ = readl_relaxed(rx_reg);
+					dev_vdbg(&spi->dev, "read-%d %08x\n",
+						    word_len, *(rx - 1));
+					if (mcspi_wait_for_reg_bit(chstat_reg,
+						OMAP2_MCSPI_CHSTAT_RXS) < 0) {
+						dev_err(&spi->dev,
+							"RXS timed out\n");
+						goto out;
+					}
+					c = 0;
+				} else if (c == 0 && tx == NULL) {
+					omap2_mcspi_set_enable(spi, 0);
+				}
+
+				*rx++ = readl_relaxed(rx_reg);
+				dev_vdbg(&spi->dev, "read-%d %08x\n",
+						word_len, *(rx - 1));
+			}
+			/* Add word delay between each word */
+			spi_delay_exec(&xfer->word_delay, xfer);
+		} while (c >= 4);
+	}
+
+	/* for TX_ONLY mode, be sure all words have shifted out */
+	if (xfer->rx_buf == NULL) {
+		if (mcspi_wait_for_reg_bit(chstat_reg,
+				OMAP2_MCSPI_CHSTAT_TXS) < 0) {
+			dev_err(&spi->dev, "TXS timed out\n");
+		} else if (mcspi_wait_for_reg_bit(chstat_reg,
+				OMAP2_MCSPI_CHSTAT_EOT) < 0)
+			dev_err(&spi->dev, "EOT timed out\n");
+
+		/* disable chan to purge rx datas received in TX_ONLY transfer,
+		 * otherwise these rx datas will affect the direct following
+		 * RX_ONLY transfer.
+		 */
+		omap2_mcspi_set_enable(spi, 0);
+	}
+out:
+	omap2_mcspi_set_enable(spi, 1);
+	return count - c;
+}
+
+static u32 omap2_mcspi_calc_divisor(u32 speed_hz)
+{
+	u32 div;
+
+	for (div = 0; div < 15; div++)
+		if (speed_hz >= (OMAP2_MCSPI_MAX_FREQ >> div))
+			return div;
+
+	return 15;
+}
+
+/* called only when no transfer is active to this device */
+static int omap2_mcspi_setup_transfer(struct spi_device *spi,
+		struct spi_transfer *t)
+{
+	struct omap2_mcspi_cs *cs = spi->controller_state;
+	struct omap2_mcspi *mcspi;
+	u32 l = 0, clkd = 0, div, extclk = 0, clkg = 0;
+	u8 word_len = spi->bits_per_word;
+	u32 speed_hz = spi->max_speed_hz;
+
+	mcspi = spi_master_get_devdata(spi->master);
+
+	if (t != NULL && t->bits_per_word)
+		word_len = t->bits_per_word;
+
+	cs->word_len = word_len;
+
+	if (t && t->speed_hz)
+		speed_hz = t->speed_hz;
+
+	speed_hz = min_t(u32, speed_hz, OMAP2_MCSPI_MAX_FREQ);
+	if (speed_hz < (OMAP2_MCSPI_MAX_FREQ / OMAP2_MCSPI_MAX_DIVIDER)) {
+		clkd = omap2_mcspi_calc_divisor(speed_hz);
+		speed_hz = OMAP2_MCSPI_MAX_FREQ >> clkd;
+		clkg = 0;
+	} else {
+		div = (OMAP2_MCSPI_MAX_FREQ + speed_hz - 1) / speed_hz;
+		speed_hz = OMAP2_MCSPI_MAX_FREQ / div;
+		clkd = (div - 1) & 0xf;
+		extclk = (div - 1) >> 4;
+		clkg = OMAP2_MCSPI_CHCONF_CLKG;
+	}
+
+	l = mcspi_cached_chconf0(spi);
+
+	/* standard 4-wire master mode:  SCK, MOSI/out, MISO/in, nCS
+	 * REVISIT: this controller could support SPI_3WIRE mode.
+	 */
+	if (mcspi->pin_dir == MCSPI_PINDIR_D0_IN_D1_OUT) {
+		l &= ~OMAP2_MCSPI_CHCONF_IS;
+		l &= ~OMAP2_MCSPI_CHCONF_DPE1;
+		l |= OMAP2_MCSPI_CHCONF_DPE0;
+	} else {
+		l |= OMAP2_MCSPI_CHCONF_IS;
+		l |= OMAP2_MCSPI_CHCONF_DPE1;
+		l &= ~OMAP2_MCSPI_CHCONF_DPE0;
+	}
+
+	/* wordlength */
+	l &= ~OMAP2_MCSPI_CHCONF_WL_MASK;
+	l |= (word_len - 1) << 7;
+
+	/* set chipselect polarity; manage with FORCE */
+	if (!(spi->mode & SPI_CS_HIGH))
+		l |= OMAP2_MCSPI_CHCONF_EPOL;	/* active-low; normal */
+	else
+		l &= ~OMAP2_MCSPI_CHCONF_EPOL;
+
+	/* set clock divisor */
+	l &= ~OMAP2_MCSPI_CHCONF_CLKD_MASK;
+	l |= clkd << 2;
+
+	/* set clock granularity */
+	l &= ~OMAP2_MCSPI_CHCONF_CLKG;
+	l |= clkg;
+	if (clkg) {
+		cs->chctrl0 &= ~OMAP2_MCSPI_CHCTRL_EXTCLK_MASK;
+		cs->chctrl0 |= extclk << 8;
+		mcspi_write_cs_reg(spi, OMAP2_MCSPI_CHCTRL0, cs->chctrl0);
+	}
+
+	/* set SPI mode 0..3 */
+	if (spi->mode & SPI_CPOL)
+		l |= OMAP2_MCSPI_CHCONF_POL;
+	else
+		l &= ~OMAP2_MCSPI_CHCONF_POL;
+	if (spi->mode & SPI_CPHA)
+		l |= OMAP2_MCSPI_CHCONF_PHA;
+	else
+		l &= ~OMAP2_MCSPI_CHCONF_PHA;
+
+	mcspi_write_chconf0(spi, l);
+
+	cs->mode = spi->mode;
+
+	dev_dbg(&spi->dev, "setup: speed %d, sample %s edge, clk %s\n",
+			speed_hz,
+			(spi->mode & SPI_CPHA) ? "trailing" : "leading",
+			(spi->mode & SPI_CPOL) ? "inverted" : "normal");
+
+	return 0;
+}
+
+/*
+ * Note that we currently allow DMA only if we get a channel
+ * for both rx and tx. Otherwise we'll do PIO for both rx and tx.
+ */
+static int omap2_mcspi_request_dma(struct omap2_mcspi *mcspi,
+				   struct omap2_mcspi_dma *mcspi_dma)
+{
+	int ret = 0;
+
+	mcspi_dma->dma_rx = dma_request_chan(mcspi->dev,
+					     mcspi_dma->dma_rx_ch_name);
+	if (IS_ERR(mcspi_dma->dma_rx)) {
+		ret = PTR_ERR(mcspi_dma->dma_rx);
+		mcspi_dma->dma_rx = NULL;
+		goto no_dma;
+	}
+
+	mcspi_dma->dma_tx = dma_request_chan(mcspi->dev,
+					     mcspi_dma->dma_tx_ch_name);
+	if (IS_ERR(mcspi_dma->dma_tx)) {
+		ret = PTR_ERR(mcspi_dma->dma_tx);
+		mcspi_dma->dma_tx = NULL;
+		dma_release_channel(mcspi_dma->dma_rx);
+		mcspi_dma->dma_rx = NULL;
+	}
+
+	init_completion(&mcspi_dma->dma_rx_completion);
+	init_completion(&mcspi_dma->dma_tx_completion);
+
+no_dma:
+	return ret;
+}
+
+static void omap2_mcspi_release_dma(struct spi_master *master)
+{
+	struct omap2_mcspi *mcspi = spi_master_get_devdata(master);
+	struct omap2_mcspi_dma	*mcspi_dma;
+	int i;
+
+	for (i = 0; i < master->num_chipselect; i++) {
+		mcspi_dma = &mcspi->dma_channels[i];
+
+		if (mcspi_dma->dma_rx) {
+			dma_release_channel(mcspi_dma->dma_rx);
+			mcspi_dma->dma_rx = NULL;
+		}
+		if (mcspi_dma->dma_tx) {
+			dma_release_channel(mcspi_dma->dma_tx);
+			mcspi_dma->dma_tx = NULL;
+		}
+	}
+}
+
+static void omap2_mcspi_cleanup(struct spi_device *spi)
+{
+	struct omap2_mcspi_cs	*cs;
+
+	if (spi->controller_state) {
+		/* Unlink controller state from context save list */
+		cs = spi->controller_state;
+		list_del(&cs->node);
+
+		kfree(cs);
+	}
+}
+
+static int omap2_mcspi_setup(struct spi_device *spi)
+{
+	bool			initial_setup = false;
+	int			ret;
+	struct omap2_mcspi	*mcspi = spi_master_get_devdata(spi->master);
+	struct omap2_mcspi_regs	*ctx = &mcspi->ctx;
+	struct omap2_mcspi_cs	*cs = spi->controller_state;
+
+	if (!cs) {
+		cs = kzalloc(sizeof(*cs), GFP_KERNEL);
+		if (!cs)
+			return -ENOMEM;
+		cs->base = mcspi->base + spi->chip_select * 0x14;
+		cs->phys = mcspi->phys + spi->chip_select * 0x14;
+		cs->mode = 0;
+		cs->chconf0 = 0;
+		cs->chctrl0 = 0;
+		spi->controller_state = cs;
+		/* Link this to context save list */
+		list_add_tail(&cs->node, &ctx->cs);
+		initial_setup = true;
+	}
+
+	ret = pm_runtime_resume_and_get(mcspi->dev);
+	if (ret < 0) {
+		if (initial_setup)
+			omap2_mcspi_cleanup(spi);
+
+		return ret;
+	}
+
+	ret = omap2_mcspi_setup_transfer(spi, NULL);
+	if (ret && initial_setup)
+		omap2_mcspi_cleanup(spi);
+
+	pm_runtime_mark_last_busy(mcspi->dev);
+	pm_runtime_put_autosuspend(mcspi->dev);
+
+	return ret;
+}
+
+static irqreturn_t omap2_mcspi_irq_handler(int irq, void *data)
+{
+	struct omap2_mcspi *mcspi = data;
+	u32 irqstat;
+
+	irqstat	= mcspi_read_reg(mcspi->master, OMAP2_MCSPI_IRQSTATUS);
+	if (!irqstat)
+		return IRQ_NONE;
+
+	/* Disable IRQ and wakeup slave xfer task */
+	mcspi_write_reg(mcspi->master, OMAP2_MCSPI_IRQENABLE, 0);
+	if (irqstat & OMAP2_MCSPI_IRQSTATUS_EOW)
+		complete(&mcspi->txdone);
+
+	return IRQ_HANDLED;
+}
+
+static int omap2_mcspi_slave_abort(struct spi_master *master)
+{
+	struct omap2_mcspi *mcspi = spi_master_get_devdata(master);
+	struct omap2_mcspi_dma *mcspi_dma = mcspi->dma_channels;
+
+	mcspi->slave_aborted = true;
+	complete(&mcspi_dma->dma_rx_completion);
+	complete(&mcspi_dma->dma_tx_completion);
+	complete(&mcspi->txdone);
+
+	return 0;
+}
+
+static int omap2_mcspi_transfer_one(struct spi_master *master,
+				    struct spi_device *spi,
+				    struct spi_transfer *t)
+{
+
+	/* We only enable one channel at a time -- the one whose message is
+	 * -- although this controller would gladly
+	 * arbitrate among multiple channels.  This corresponds to "single
+	 * channel" master mode.  As a side effect, we need to manage the
+	 * chipselect with the FORCE bit ... CS != channel enable.
+	 */
+
+	struct omap2_mcspi		*mcspi;
+	struct omap2_mcspi_dma		*mcspi_dma;
+	struct omap2_mcspi_cs		*cs;
+	struct omap2_mcspi_device_config *cd;
+	int				par_override = 0;
+	int				status = 0;
+	u32				chconf;
+
+	mcspi = spi_master_get_devdata(master);
+	mcspi_dma = mcspi->dma_channels + spi->chip_select;
+	cs = spi->controller_state;
+	cd = spi->controller_data;
+
+	/*
+	 * The slave driver could have changed spi->mode in which case
+	 * it will be different from cs->mode (the current hardware setup).
+	 * If so, set par_override (even though its not a parity issue) so
+	 * omap2_mcspi_setup_transfer will be called to configure the hardware
+	 * with the correct mode on the first iteration of the loop below.
+	 */
+	if (spi->mode != cs->mode)
+		par_override = 1;
+
+	omap2_mcspi_set_enable(spi, 0);
+
+	if (spi->cs_gpiod)
+		omap2_mcspi_set_cs(spi, spi->mode & SPI_CS_HIGH);
+
+	if (par_override ||
+	    (t->speed_hz != spi->max_speed_hz) ||
+	    (t->bits_per_word != spi->bits_per_word)) {
+		par_override = 1;
+		status = omap2_mcspi_setup_transfer(spi, t);
+		if (status < 0)
+			goto out;
+		if (t->speed_hz == spi->max_speed_hz &&
+		    t->bits_per_word == spi->bits_per_word)
+			par_override = 0;
+	}
+	if (cd && cd->cs_per_word) {
+		chconf = mcspi->ctx.modulctrl;
+		chconf &= ~OMAP2_MCSPI_MODULCTRL_SINGLE;
+		mcspi_write_reg(master, OMAP2_MCSPI_MODULCTRL, chconf);
+		mcspi->ctx.modulctrl =
+			mcspi_read_cs_reg(spi, OMAP2_MCSPI_MODULCTRL);
+	}
+
+	chconf = mcspi_cached_chconf0(spi);
+	chconf &= ~OMAP2_MCSPI_CHCONF_TRM_MASK;
+	chconf &= ~OMAP2_MCSPI_CHCONF_TURBO;
+
+	if (t->tx_buf == NULL)
+		chconf |= OMAP2_MCSPI_CHCONF_TRM_RX_ONLY;
+	else if (t->rx_buf == NULL)
+		chconf |= OMAP2_MCSPI_CHCONF_TRM_TX_ONLY;
+
+	if (cd && cd->turbo_mode && t->tx_buf == NULL) {
+		/* Turbo mode is for more than one word */
+		if (t->len > ((cs->word_len + 7) >> 3))
+			chconf |= OMAP2_MCSPI_CHCONF_TURBO;
+	}
+
+	mcspi_write_chconf0(spi, chconf);
+
+	if (t->len) {
+		unsigned	count;
+
+		if ((mcspi_dma->dma_rx && mcspi_dma->dma_tx) &&
+		    master->cur_msg_mapped &&
+		    master->can_dma(master, spi, t))
+			omap2_mcspi_set_fifo(spi, t, 1);
+
+		omap2_mcspi_set_enable(spi, 1);
+
+		/* RX_ONLY mode needs dummy data in TX reg */
+		if (t->tx_buf == NULL)
+			writel_relaxed(0, cs->base
+					+ OMAP2_MCSPI_TX0);
+
+		if ((mcspi_dma->dma_rx && mcspi_dma->dma_tx) &&
+		    master->cur_msg_mapped &&
+		    master->can_dma(master, spi, t))
+			count = omap2_mcspi_txrx_dma(spi, t);
+		else
+			count = omap2_mcspi_txrx_pio(spi, t);
+
+		if (count != t->len) {
+			status = -EIO;
+			goto out;
+		}
+	}
+
+	omap2_mcspi_set_enable(spi, 0);
+
+	if (mcspi->fifo_depth > 0)
+		omap2_mcspi_set_fifo(spi, t, 0);
+
+out:
+	/* Restore defaults if they were overriden */
+	if (par_override) {
+		par_override = 0;
+		status = omap2_mcspi_setup_transfer(spi, NULL);
+	}
+
+	if (cd && cd->cs_per_word) {
+		chconf = mcspi->ctx.modulctrl;
+		chconf |= OMAP2_MCSPI_MODULCTRL_SINGLE;
+		mcspi_write_reg(master, OMAP2_MCSPI_MODULCTRL, chconf);
+		mcspi->ctx.modulctrl =
+			mcspi_read_cs_reg(spi, OMAP2_MCSPI_MODULCTRL);
+	}
+
+	omap2_mcspi_set_enable(spi, 0);
+
+	if (spi->cs_gpiod)
+		omap2_mcspi_set_cs(spi, !(spi->mode & SPI_CS_HIGH));
+
+	if (mcspi->fifo_depth > 0 && t)
+		omap2_mcspi_set_fifo(spi, t, 0);
+
+	return status;
+}
+
+static int omap2_mcspi_prepare_message(struct spi_master *master,
+				       struct spi_message *msg)
+{
+	struct omap2_mcspi	*mcspi = spi_master_get_devdata(master);
+	struct omap2_mcspi_regs	*ctx = &mcspi->ctx;
+	struct omap2_mcspi_cs	*cs;
+
+	/* Only a single channel can have the FORCE bit enabled
+	 * in its chconf0 register.
+	 * Scan all channels and disable them except the current one.
+	 * A FORCE can remain from a last transfer having cs_change enabled
+	 */
+	list_for_each_entry(cs, &ctx->cs, node) {
+		if (msg->spi->controller_state == cs)
+			continue;
+
+		if ((cs->chconf0 & OMAP2_MCSPI_CHCONF_FORCE)) {
+			cs->chconf0 &= ~OMAP2_MCSPI_CHCONF_FORCE;
+			writel_relaxed(cs->chconf0,
+					cs->base + OMAP2_MCSPI_CHCONF0);
+			readl_relaxed(cs->base + OMAP2_MCSPI_CHCONF0);
+		}
+	}
+
+	return 0;
+}
+
+static bool omap2_mcspi_can_dma(struct spi_master *master,
+				struct spi_device *spi,
+				struct spi_transfer *xfer)
+{
+	struct omap2_mcspi *mcspi = spi_master_get_devdata(spi->master);
+	struct omap2_mcspi_dma *mcspi_dma =
+		&mcspi->dma_channels[spi->chip_select];
+
+	if (!mcspi_dma->dma_rx || !mcspi_dma->dma_tx)
+		return false;
+
+	if (spi_controller_is_slave(master))
+		return true;
+
+	master->dma_rx = mcspi_dma->dma_rx;
+	master->dma_tx = mcspi_dma->dma_tx;
+
+	return (xfer->len >= DMA_MIN_BYTES);
+}
+
+static size_t omap2_mcspi_max_xfer_size(struct spi_device *spi)
+{
+	struct omap2_mcspi *mcspi = spi_master_get_devdata(spi->master);
+	struct omap2_mcspi_dma *mcspi_dma =
+		&mcspi->dma_channels[spi->chip_select];
+
+	if (mcspi->max_xfer_len && mcspi_dma->dma_rx)
+		return mcspi->max_xfer_len;
+
+	return SIZE_MAX;
+}
+
+static int omap2_mcspi_controller_setup(struct omap2_mcspi *mcspi)
+{
+	struct spi_master	*master = mcspi->master;
+	struct omap2_mcspi_regs	*ctx = &mcspi->ctx;
+	int			ret = 0;
+
+	ret = pm_runtime_resume_and_get(mcspi->dev);
+	if (ret < 0)
+		return ret;
+
+	mcspi_write_reg(master, OMAP2_MCSPI_WAKEUPENABLE,
+			OMAP2_MCSPI_WAKEUPENABLE_WKEN);
+	ctx->wakeupenable = OMAP2_MCSPI_WAKEUPENABLE_WKEN;
+
+	omap2_mcspi_set_mode(master);
+	pm_runtime_mark_last_busy(mcspi->dev);
+	pm_runtime_put_autosuspend(mcspi->dev);
+	return 0;
+}
+
+static int omap_mcspi_runtime_suspend(struct device *dev)
+{
+	int error;
+
+	error = pinctrl_pm_select_idle_state(dev);
+	if (error)
+		dev_warn(dev, "%s: failed to set pins: %i\n", __func__, error);
+
+	return 0;
+}
+
+/*
+ * When SPI wake up from off-mode, CS is in activate state. If it was in
+ * inactive state when driver was suspend, then force it to inactive state at
+ * wake up.
+ */
+static int omap_mcspi_runtime_resume(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct omap2_mcspi *mcspi = spi_master_get_devdata(master);
+	struct omap2_mcspi_regs *ctx = &mcspi->ctx;
+	struct omap2_mcspi_cs *cs;
+	int error;
+
+	error = pinctrl_pm_select_default_state(dev);
+	if (error)
+		dev_warn(dev, "%s: failed to set pins: %i\n", __func__, error);
+
+	/* McSPI: context restore */
+	mcspi_write_reg(master, OMAP2_MCSPI_MODULCTRL, ctx->modulctrl);
+	mcspi_write_reg(master, OMAP2_MCSPI_WAKEUPENABLE, ctx->wakeupenable);
+
+	list_for_each_entry(cs, &ctx->cs, node) {
+		/*
+		 * We need to toggle CS state for OMAP take this
+		 * change in account.
+		 */
+		if ((cs->chconf0 & OMAP2_MCSPI_CHCONF_FORCE) == 0) {
+			cs->chconf0 |= OMAP2_MCSPI_CHCONF_FORCE;
+			writel_relaxed(cs->chconf0,
+				       cs->base + OMAP2_MCSPI_CHCONF0);
+			cs->chconf0 &= ~OMAP2_MCSPI_CHCONF_FORCE;
+			writel_relaxed(cs->chconf0,
+				       cs->base + OMAP2_MCSPI_CHCONF0);
+		} else {
+			writel_relaxed(cs->chconf0,
+				       cs->base + OMAP2_MCSPI_CHCONF0);
+		}
+	}
+
+	return 0;
+}
+
+static struct omap2_mcspi_platform_config omap2_pdata = {
+	.regs_offset = 0,
+};
+
+static struct omap2_mcspi_platform_config omap4_pdata = {
+	.regs_offset = OMAP4_MCSPI_REG_OFFSET,
+};
+
+static struct omap2_mcspi_platform_config am654_pdata = {
+	.regs_offset = OMAP4_MCSPI_REG_OFFSET,
+	.max_xfer_len = SZ_4K - 1,
+};
+
+static const struct of_device_id omap_mcspi_of_match[] = {
+	{
+		.compatible = "ti,omap2-mcspi",
+		.data = &omap2_pdata,
+	},
+	{
+		.compatible = "ti,omap4-mcspi",
+		.data = &omap4_pdata,
+	},
+	{
+		.compatible = "ti,am654-mcspi",
+		.data = &am654_pdata,
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, omap_mcspi_of_match);
+
+static int omap2_mcspi_probe(struct platform_device *pdev)
+{
+	struct spi_master	*master;
+	const struct omap2_mcspi_platform_config *pdata;
+	struct omap2_mcspi	*mcspi;
+	struct resource		*r;
+	int			status = 0, i;
+	u32			regs_offset = 0;
+	struct device_node	*node = pdev->dev.of_node;
+	const struct of_device_id *match;
+
+	if (of_property_read_bool(node, "spi-slave"))
+		master = spi_alloc_slave(&pdev->dev, sizeof(*mcspi));
+	else
+		master = spi_alloc_master(&pdev->dev, sizeof(*mcspi));
+	if (!master)
+		return -ENOMEM;
+
+	/* the spi->mode bits understood by this driver: */
+	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
+	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 32);
+	master->setup = omap2_mcspi_setup;
+	master->auto_runtime_pm = true;
+	master->prepare_message = omap2_mcspi_prepare_message;
+	master->can_dma = omap2_mcspi_can_dma;
+	master->transfer_one = omap2_mcspi_transfer_one;
+	master->set_cs = omap2_mcspi_set_cs;
+	master->cleanup = omap2_mcspi_cleanup;
+	master->slave_abort = omap2_mcspi_slave_abort;
+	master->dev.of_node = node;
+	master->max_speed_hz = OMAP2_MCSPI_MAX_FREQ;
+	master->min_speed_hz = OMAP2_MCSPI_MAX_FREQ >> 15;
+	master->use_gpio_descriptors = true;
+
+	platform_set_drvdata(pdev, master);
+
+	mcspi = spi_master_get_devdata(master);
+	mcspi->master = master;
+
+	match = of_match_device(omap_mcspi_of_match, &pdev->dev);
+	if (match) {
+		u32 num_cs = 1; /* default number of chipselect */
+		pdata = match->data;
+
+		of_property_read_u32(node, "ti,spi-num-cs", &num_cs);
+		master->num_chipselect = num_cs;
+		if (of_get_property(node, "ti,pindir-d0-out-d1-in", NULL))
+			mcspi->pin_dir = MCSPI_PINDIR_D0_OUT_D1_IN;
+	} else {
+		pdata = dev_get_platdata(&pdev->dev);
+		master->num_chipselect = pdata->num_cs;
+		mcspi->pin_dir = pdata->pin_dir;
+	}
+	regs_offset = pdata->regs_offset;
+	if (pdata->max_xfer_len) {
+		mcspi->max_xfer_len = pdata->max_xfer_len;
+		master->max_transfer_size = omap2_mcspi_max_xfer_size;
+	}
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	mcspi->base = devm_ioremap_resource(&pdev->dev, r);
+	if (IS_ERR(mcspi->base)) {
+		status = PTR_ERR(mcspi->base);
+		goto free_master;
+	}
+	mcspi->phys = r->start + regs_offset;
+	mcspi->base += regs_offset;
+
+	mcspi->dev = &pdev->dev;
+
+	INIT_LIST_HEAD(&mcspi->ctx.cs);
+
+	mcspi->dma_channels = devm_kcalloc(&pdev->dev, master->num_chipselect,
+					   sizeof(struct omap2_mcspi_dma),
+					   GFP_KERNEL);
+	if (mcspi->dma_channels == NULL) {
+		status = -ENOMEM;
+		goto free_master;
+	}
+
+	for (i = 0; i < master->num_chipselect; i++) {
+		sprintf(mcspi->dma_channels[i].dma_rx_ch_name, "rx%d", i);
+		sprintf(mcspi->dma_channels[i].dma_tx_ch_name, "tx%d", i);
+
+		status = omap2_mcspi_request_dma(mcspi,
+						 &mcspi->dma_channels[i]);
+		if (status == -EPROBE_DEFER)
+			goto free_master;
+	}
+
+	status = platform_get_irq(pdev, 0);
+	if (status < 0) {
+		dev_err_probe(&pdev->dev, status, "no irq resource found\n");
+		goto free_master;
+	}
+	init_completion(&mcspi->txdone);
+	status = devm_request_irq(&pdev->dev, status,
+				  omap2_mcspi_irq_handler, 0, pdev->name,
+				  mcspi);
+	if (status) {
+		dev_err(&pdev->dev, "Cannot request IRQ");
+		goto free_master;
+	}
+
+	pm_runtime_use_autosuspend(&pdev->dev);
+	pm_runtime_set_autosuspend_delay(&pdev->dev, SPI_AUTOSUSPEND_TIMEOUT);
+	pm_runtime_enable(&pdev->dev);
+
+	status = omap2_mcspi_controller_setup(mcspi);
+	if (status < 0)
+		goto disable_pm;
+
+	status = devm_spi_register_controller(&pdev->dev, master);
+	if (status < 0)
+		goto disable_pm;
+
+	return status;
+
+disable_pm:
+	pm_runtime_dont_use_autosuspend(&pdev->dev);
+	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+free_master:
+	omap2_mcspi_release_dma(master);
+	spi_master_put(master);
+	return status;
+}
+
+static int omap2_mcspi_remove(struct platform_device *pdev)
+{
+	struct spi_master *master = platform_get_drvdata(pdev);
+	struct omap2_mcspi *mcspi = spi_master_get_devdata(master);
+
+	omap2_mcspi_release_dma(master);
+
+	pm_runtime_dont_use_autosuspend(mcspi->dev);
+	pm_runtime_put_sync(mcspi->dev);
+	pm_runtime_disable(&pdev->dev);
+
+	return 0;
+}
+
+/* work with hotplug and coldplug */
+MODULE_ALIAS("platform:omap2_mcspi");
+
+static int __maybe_unused omap2_mcspi_suspend(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct omap2_mcspi *mcspi = spi_master_get_devdata(master);
+	int error;
+
+	error = pinctrl_pm_select_sleep_state(dev);
+	if (error)
+		dev_warn(mcspi->dev, "%s: failed to set pins: %i\n",
+			 __func__, error);
+
+	error = spi_master_suspend(master);
+	if (error)
+		dev_warn(mcspi->dev, "%s: master suspend failed: %i\n",
+			 __func__, error);
+
+	return pm_runtime_force_suspend(dev);
+}
+
+static int __maybe_unused omap2_mcspi_resume(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct omap2_mcspi *mcspi = spi_master_get_devdata(master);
+	int error;
+
+	error = spi_master_resume(master);
+	if (error)
+		dev_warn(mcspi->dev, "%s: master resume failed: %i\n",
+			 __func__, error);
+
+	return pm_runtime_force_resume(dev);
+}
+
+static const struct dev_pm_ops omap2_mcspi_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(omap2_mcspi_suspend,
+				omap2_mcspi_resume)
+	.runtime_suspend	= omap_mcspi_runtime_suspend,
+	.runtime_resume		= omap_mcspi_runtime_resume,
+};
+
+static struct platform_driver omap2_mcspi_driver = {
+	.driver = {
+		.name =		"omap2_mcspi",
+		.pm =		&omap2_mcspi_pm_ops,
+		.of_match_table = omap_mcspi_of_match,
+	},
+	.probe =	omap2_mcspi_probe,
+	.remove =	omap2_mcspi_remove,
+};
+
+module_platform_driver(omap2_mcspi_driver);
+MODULE_LICENSE("GPL");