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, 773 insertions, 0 deletions

diff --git a/sound/soc/ti/davinci-i2s.c b/sound/soc/ti/davinci-i2s.c
new file mode 100644
index 000000000..e6e77a5f3
--- /dev/null
+++ b/sound/soc/ti/davinci-i2s.c
@@ -0,0 +1,773 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * ALSA SoC I2S (McBSP) Audio Layer for TI DAVINCI processor
+ *
+ * Author:      Vladimir Barinov, <vbarinov@embeddedalley.com>
+ * Copyright:   (C) 2007 MontaVista Software, Inc., <source@mvista.com>
+ *
+ * DT support	(c) 2016 Petr Kulhavy, Barix AG <petr@barix.com>
+ *		based on davinci-mcasp.c DT support
+ *
+ * TODO:
+ * on DA850 implement HW FIFOs instead of DMA into DXR and DRR registers
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/clk.h>
+#include <linux/platform_data/davinci_asp.h>
+
+#include <sound/core.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include <sound/initval.h>
+#include <sound/soc.h>
+#include <sound/dmaengine_pcm.h>
+
+#include "edma-pcm.h"
+#include "davinci-i2s.h"
+
+#define DRV_NAME "davinci-i2s"
+
+/*
+ * NOTE:  terminology here is confusing.
+ *
+ *  - This driver supports the "Audio Serial Port" (ASP),
+ *    found on dm6446, dm355, and other DaVinci chips.
+ *
+ *  - But it labels it a "Multi-channel Buffered Serial Port"
+ *    (McBSP) as on older chips like the dm642 ... which was
+ *    backward-compatible, possibly explaining that confusion.
+ *
+ *  - OMAP chips have a controller called McBSP, which is
+ *    incompatible with the DaVinci flavor of McBSP.
+ *
+ *  - Newer DaVinci chips have a controller called McASP,
+ *    incompatible with ASP and with either McBSP.
+ *
+ * In short:  this uses ASP to implement I2S, not McBSP.
+ * And it won't be the only DaVinci implemention of I2S.
+ */
+#define DAVINCI_MCBSP_DRR_REG	0x00
+#define DAVINCI_MCBSP_DXR_REG	0x04
+#define DAVINCI_MCBSP_SPCR_REG	0x08
+#define DAVINCI_MCBSP_RCR_REG	0x0c
+#define DAVINCI_MCBSP_XCR_REG	0x10
+#define DAVINCI_MCBSP_SRGR_REG	0x14
+#define DAVINCI_MCBSP_PCR_REG	0x24
+
+#define DAVINCI_MCBSP_SPCR_RRST		(1 << 0)
+#define DAVINCI_MCBSP_SPCR_RINTM(v)	((v) << 4)
+#define DAVINCI_MCBSP_SPCR_XRST		(1 << 16)
+#define DAVINCI_MCBSP_SPCR_XINTM(v)	((v) << 20)
+#define DAVINCI_MCBSP_SPCR_GRST		(1 << 22)
+#define DAVINCI_MCBSP_SPCR_FRST		(1 << 23)
+#define DAVINCI_MCBSP_SPCR_FREE		(1 << 25)
+
+#define DAVINCI_MCBSP_RCR_RWDLEN1(v)	((v) << 5)
+#define DAVINCI_MCBSP_RCR_RFRLEN1(v)	((v) << 8)
+#define DAVINCI_MCBSP_RCR_RDATDLY(v)	((v) << 16)
+#define DAVINCI_MCBSP_RCR_RFIG		(1 << 18)
+#define DAVINCI_MCBSP_RCR_RWDLEN2(v)	((v) << 21)
+#define DAVINCI_MCBSP_RCR_RFRLEN2(v)	((v) << 24)
+#define DAVINCI_MCBSP_RCR_RPHASE	BIT(31)
+
+#define DAVINCI_MCBSP_XCR_XWDLEN1(v)	((v) << 5)
+#define DAVINCI_MCBSP_XCR_XFRLEN1(v)	((v) << 8)
+#define DAVINCI_MCBSP_XCR_XDATDLY(v)	((v) << 16)
+#define DAVINCI_MCBSP_XCR_XFIG		(1 << 18)
+#define DAVINCI_MCBSP_XCR_XWDLEN2(v)	((v) << 21)
+#define DAVINCI_MCBSP_XCR_XFRLEN2(v)	((v) << 24)
+#define DAVINCI_MCBSP_XCR_XPHASE	BIT(31)
+
+#define DAVINCI_MCBSP_SRGR_FWID(v)	((v) << 8)
+#define DAVINCI_MCBSP_SRGR_FPER(v)	((v) << 16)
+#define DAVINCI_MCBSP_SRGR_FSGM		(1 << 28)
+#define DAVINCI_MCBSP_SRGR_CLKSM	BIT(29)
+
+#define DAVINCI_MCBSP_PCR_CLKRP		(1 << 0)
+#define DAVINCI_MCBSP_PCR_CLKXP		(1 << 1)
+#define DAVINCI_MCBSP_PCR_FSRP		(1 << 2)
+#define DAVINCI_MCBSP_PCR_FSXP		(1 << 3)
+#define DAVINCI_MCBSP_PCR_SCLKME	(1 << 7)
+#define DAVINCI_MCBSP_PCR_CLKRM		(1 << 8)
+#define DAVINCI_MCBSP_PCR_CLKXM		(1 << 9)
+#define DAVINCI_MCBSP_PCR_FSRM		(1 << 10)
+#define DAVINCI_MCBSP_PCR_FSXM		(1 << 11)
+
+enum {
+	DAVINCI_MCBSP_WORD_8 = 0,
+	DAVINCI_MCBSP_WORD_12,
+	DAVINCI_MCBSP_WORD_16,
+	DAVINCI_MCBSP_WORD_20,
+	DAVINCI_MCBSP_WORD_24,
+	DAVINCI_MCBSP_WORD_32,
+};
+
+static const unsigned char data_type[SNDRV_PCM_FORMAT_S32_LE + 1] = {
+	[SNDRV_PCM_FORMAT_S8]		= 1,
+	[SNDRV_PCM_FORMAT_S16_LE]	= 2,
+	[SNDRV_PCM_FORMAT_S32_LE]	= 4,
+};
+
+static const unsigned char asp_word_length[SNDRV_PCM_FORMAT_S32_LE + 1] = {
+	[SNDRV_PCM_FORMAT_S8]		= DAVINCI_MCBSP_WORD_8,
+	[SNDRV_PCM_FORMAT_S16_LE]	= DAVINCI_MCBSP_WORD_16,
+	[SNDRV_PCM_FORMAT_S32_LE]	= DAVINCI_MCBSP_WORD_32,
+};
+
+static const unsigned char double_fmt[SNDRV_PCM_FORMAT_S32_LE + 1] = {
+	[SNDRV_PCM_FORMAT_S8]		= SNDRV_PCM_FORMAT_S16_LE,
+	[SNDRV_PCM_FORMAT_S16_LE]	= SNDRV_PCM_FORMAT_S32_LE,
+};
+
+struct davinci_mcbsp_dev {
+	struct device *dev;
+	struct snd_dmaengine_dai_dma_data dma_data[2];
+	int dma_request[2];
+	void __iomem			*base;
+#define MOD_DSP_A	0
+#define MOD_DSP_B	1
+	int				mode;
+	u32				pcr;
+	struct clk			*clk;
+	/*
+	 * Combining both channels into 1 element will at least double the
+	 * amount of time between servicing the dma channel, increase
+	 * effiency, and reduce the chance of overrun/underrun. But,
+	 * it will result in the left & right channels being swapped.
+	 *
+	 * If relabeling the left and right channels is not possible,
+	 * you may want to let the codec know to swap them back.
+	 *
+	 * It may allow x10 the amount of time to service dma requests,
+	 * if the codec is master and is using an unnecessarily fast bit clock
+	 * (ie. tlvaic23b), independent of the sample rate. So, having an
+	 * entire frame at once means it can be serviced at the sample rate
+	 * instead of the bit clock rate.
+	 *
+	 * In the now unlikely case that an underrun still
+	 * occurs, both the left and right samples will be repeated
+	 * so that no pops are heard, and the left and right channels
+	 * won't end up being swapped because of the underrun.
+	 */
+	unsigned enable_channel_combine:1;
+
+	unsigned int fmt;
+	int clk_div;
+	int clk_input_pin;
+	bool i2s_accurate_sck;
+};
+
+static inline void davinci_mcbsp_write_reg(struct davinci_mcbsp_dev *dev,
+					   int reg, u32 val)
+{
+	__raw_writel(val, dev->base + reg);
+}
+
+static inline u32 davinci_mcbsp_read_reg(struct davinci_mcbsp_dev *dev, int reg)
+{
+	return __raw_readl(dev->base + reg);
+}
+
+static void toggle_clock(struct davinci_mcbsp_dev *dev, int playback)
+{
+	u32 m = playback ? DAVINCI_MCBSP_PCR_CLKXP : DAVINCI_MCBSP_PCR_CLKRP;
+	/* The clock needs to toggle to complete reset.
+	 * So, fake it by toggling the clk polarity.
+	 */
+	davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_PCR_REG, dev->pcr ^ m);
+	davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_PCR_REG, dev->pcr);
+}
+
+static void davinci_mcbsp_start(struct davinci_mcbsp_dev *dev,
+		struct snd_pcm_substream *substream)
+{
+	int playback = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK);
+	u32 spcr;
+	u32 mask = playback ? DAVINCI_MCBSP_SPCR_XRST : DAVINCI_MCBSP_SPCR_RRST;
+
+	/* Enable transmitter or receiver */
+	spcr = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG);
+	spcr |= mask;
+
+	if (dev->pcr & (DAVINCI_MCBSP_PCR_FSXM | DAVINCI_MCBSP_PCR_FSRM)) {
+		/* Start frame sync */
+		spcr |= DAVINCI_MCBSP_SPCR_FRST;
+	}
+	davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, spcr);
+}
+
+static void davinci_mcbsp_stop(struct davinci_mcbsp_dev *dev, int playback)
+{
+	u32 spcr;
+
+	/* Reset transmitter/receiver and sample rate/frame sync generators */
+	spcr = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG);
+	spcr &= ~(DAVINCI_MCBSP_SPCR_GRST | DAVINCI_MCBSP_SPCR_FRST);
+	spcr &= playback ? ~DAVINCI_MCBSP_SPCR_XRST : ~DAVINCI_MCBSP_SPCR_RRST;
+	davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, spcr);
+	toggle_clock(dev, playback);
+}
+
+#define DEFAULT_BITPERSAMPLE	16
+
+static int davinci_i2s_set_dai_fmt(struct snd_soc_dai *cpu_dai,
+				   unsigned int fmt)
+{
+	struct davinci_mcbsp_dev *dev = snd_soc_dai_get_drvdata(cpu_dai);
+	unsigned int pcr;
+	unsigned int srgr;
+	bool inv_fs = false;
+	/* Attention srgr is updated by hw_params! */
+	srgr = DAVINCI_MCBSP_SRGR_FSGM |
+		DAVINCI_MCBSP_SRGR_FPER(DEFAULT_BITPERSAMPLE * 2 - 1) |
+		DAVINCI_MCBSP_SRGR_FWID(DEFAULT_BITPERSAMPLE - 1);
+
+	dev->fmt = fmt;
+	/* set master/slave audio interface */
+	switch (fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) {
+	case SND_SOC_DAIFMT_BP_FP:
+		/* cpu is master */
+		pcr = DAVINCI_MCBSP_PCR_FSXM |
+			DAVINCI_MCBSP_PCR_FSRM |
+			DAVINCI_MCBSP_PCR_CLKXM |
+			DAVINCI_MCBSP_PCR_CLKRM;
+		break;
+	case SND_SOC_DAIFMT_BC_FP:
+		pcr = DAVINCI_MCBSP_PCR_FSRM | DAVINCI_MCBSP_PCR_FSXM;
+		/*
+		 * Selection of the clock input pin that is the
+		 * input for the Sample Rate Generator.
+		 * McBSP FSR and FSX are driven by the Sample Rate
+		 * Generator.
+		 */
+		switch (dev->clk_input_pin) {
+		case MCBSP_CLKS:
+			pcr |= DAVINCI_MCBSP_PCR_CLKXM |
+				DAVINCI_MCBSP_PCR_CLKRM;
+			break;
+		case MCBSP_CLKR:
+			pcr |= DAVINCI_MCBSP_PCR_SCLKME;
+			break;
+		default:
+			dev_err(dev->dev, "bad clk_input_pin\n");
+			return -EINVAL;
+		}
+
+		break;
+	case SND_SOC_DAIFMT_BC_FC:
+		/* codec is master */
+		pcr = 0;
+		break;
+	default:
+		printk(KERN_ERR "%s:bad master\n", __func__);
+		return -EINVAL;
+	}
+
+	/* interface format */
+	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_I2S:
+		/* Davinci doesn't support TRUE I2S, but some codecs will have
+		 * the left and right channels contiguous. This allows
+		 * dsp_a mode to be used with an inverted normal frame clk.
+		 * If your codec is master and does not have contiguous
+		 * channels, then you will have sound on only one channel.
+		 * Try using a different mode, or codec as slave.
+		 *
+		 * The TLV320AIC33 is an example of a codec where this works.
+		 * It has a variable bit clock frequency allowing it to have
+		 * valid data on every bit clock.
+		 *
+		 * The TLV320AIC23 is an example of a codec where this does not
+		 * work. It has a fixed bit clock frequency with progressively
+		 * more empty bit clock slots between channels as the sample
+		 * rate is lowered.
+		 */
+		inv_fs = true;
+		fallthrough;
+	case SND_SOC_DAIFMT_DSP_A:
+		dev->mode = MOD_DSP_A;
+		break;
+	case SND_SOC_DAIFMT_DSP_B:
+		dev->mode = MOD_DSP_B;
+		break;
+	default:
+		printk(KERN_ERR "%s:bad format\n", __func__);
+		return -EINVAL;
+	}
+
+	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
+	case SND_SOC_DAIFMT_NB_NF:
+		/* CLKRP Receive clock polarity,
+		 *	1 - sampled on rising edge of CLKR
+		 *	valid on rising edge
+		 * CLKXP Transmit clock polarity,
+		 *	1 - clocked on falling edge of CLKX
+		 *	valid on rising edge
+		 * FSRP  Receive frame sync pol, 0 - active high
+		 * FSXP  Transmit frame sync pol, 0 - active high
+		 */
+		pcr |= (DAVINCI_MCBSP_PCR_CLKXP | DAVINCI_MCBSP_PCR_CLKRP);
+		break;
+	case SND_SOC_DAIFMT_IB_IF:
+		/* CLKRP Receive clock polarity,
+		 *	0 - sampled on falling edge of CLKR
+		 *	valid on falling edge
+		 * CLKXP Transmit clock polarity,
+		 *	0 - clocked on rising edge of CLKX
+		 *	valid on falling edge
+		 * FSRP  Receive frame sync pol, 1 - active low
+		 * FSXP  Transmit frame sync pol, 1 - active low
+		 */
+		pcr |= (DAVINCI_MCBSP_PCR_FSXP | DAVINCI_MCBSP_PCR_FSRP);
+		break;
+	case SND_SOC_DAIFMT_NB_IF:
+		/* CLKRP Receive clock polarity,
+		 *	1 - sampled on rising edge of CLKR
+		 *	valid on rising edge
+		 * CLKXP Transmit clock polarity,
+		 *	1 - clocked on falling edge of CLKX
+		 *	valid on rising edge
+		 * FSRP  Receive frame sync pol, 1 - active low
+		 * FSXP  Transmit frame sync pol, 1 - active low
+		 */
+		pcr |= (DAVINCI_MCBSP_PCR_CLKXP | DAVINCI_MCBSP_PCR_CLKRP |
+			DAVINCI_MCBSP_PCR_FSXP | DAVINCI_MCBSP_PCR_FSRP);
+		break;
+	case SND_SOC_DAIFMT_IB_NF:
+		/* CLKRP Receive clock polarity,
+		 *	0 - sampled on falling edge of CLKR
+		 *	valid on falling edge
+		 * CLKXP Transmit clock polarity,
+		 *	0 - clocked on rising edge of CLKX
+		 *	valid on falling edge
+		 * FSRP  Receive frame sync pol, 0 - active high
+		 * FSXP  Transmit frame sync pol, 0 - active high
+		 */
+		break;
+	default:
+		return -EINVAL;
+	}
+	if (inv_fs == true)
+		pcr ^= (DAVINCI_MCBSP_PCR_FSXP | DAVINCI_MCBSP_PCR_FSRP);
+	davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SRGR_REG, srgr);
+	dev->pcr = pcr;
+	davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_PCR_REG, pcr);
+	return 0;
+}
+
+static int davinci_i2s_dai_set_clkdiv(struct snd_soc_dai *cpu_dai,
+				int div_id, int div)
+{
+	struct davinci_mcbsp_dev *dev = snd_soc_dai_get_drvdata(cpu_dai);
+
+	if (div_id != DAVINCI_MCBSP_CLKGDV)
+		return -ENODEV;
+
+	dev->clk_div = div;
+	return 0;
+}
+
+static int davinci_i2s_hw_params(struct snd_pcm_substream *substream,
+				 struct snd_pcm_hw_params *params,
+				 struct snd_soc_dai *dai)
+{
+	struct davinci_mcbsp_dev *dev = snd_soc_dai_get_drvdata(dai);
+	struct snd_interval *i = NULL;
+	int mcbsp_word_length, master;
+	unsigned int rcr, xcr, srgr, clk_div, freq, framesize;
+	u32 spcr;
+	snd_pcm_format_t fmt;
+	unsigned element_cnt = 1;
+
+	/* general line settings */
+	spcr = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG);
+	if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) {
+		spcr |= DAVINCI_MCBSP_SPCR_RINTM(3) | DAVINCI_MCBSP_SPCR_FREE;
+		davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, spcr);
+	} else {
+		spcr |= DAVINCI_MCBSP_SPCR_XINTM(3) | DAVINCI_MCBSP_SPCR_FREE;
+		davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, spcr);
+	}
+
+	master = dev->fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK;
+	fmt = params_format(params);
+	mcbsp_word_length = asp_word_length[fmt];
+
+	switch (master) {
+	case SND_SOC_DAIFMT_BP_FP:
+		freq = clk_get_rate(dev->clk);
+		srgr = DAVINCI_MCBSP_SRGR_FSGM |
+		       DAVINCI_MCBSP_SRGR_CLKSM;
+		srgr |= DAVINCI_MCBSP_SRGR_FWID(mcbsp_word_length *
+						8 - 1);
+		if (dev->i2s_accurate_sck) {
+			clk_div = 256;
+			do {
+				framesize = (freq / (--clk_div)) /
+				params->rate_num *
+					params->rate_den;
+			} while (((framesize < 33) || (framesize > 4095)) &&
+				 (clk_div));
+			clk_div--;
+			srgr |= DAVINCI_MCBSP_SRGR_FPER(framesize - 1);
+		} else {
+			/* symmetric waveforms */
+			clk_div = freq / (mcbsp_word_length * 16) /
+				  params->rate_num * params->rate_den;
+			srgr |= DAVINCI_MCBSP_SRGR_FPER(mcbsp_word_length *
+							16 - 1);
+		}
+		clk_div &= 0xFF;
+		srgr |= clk_div;
+		break;
+	case SND_SOC_DAIFMT_BC_FP:
+		srgr = DAVINCI_MCBSP_SRGR_FSGM;
+		clk_div = dev->clk_div - 1;
+		srgr |= DAVINCI_MCBSP_SRGR_FWID(mcbsp_word_length * 8 - 1);
+		srgr |= DAVINCI_MCBSP_SRGR_FPER(mcbsp_word_length * 16 - 1);
+		clk_div &= 0xFF;
+		srgr |= clk_div;
+		break;
+	case SND_SOC_DAIFMT_BC_FC:
+		/* Clock and frame sync given from external sources */
+		i = hw_param_interval(params, SNDRV_PCM_HW_PARAM_SAMPLE_BITS);
+		srgr = DAVINCI_MCBSP_SRGR_FSGM;
+		srgr |= DAVINCI_MCBSP_SRGR_FWID(snd_interval_value(i) - 1);
+		pr_debug("%s - %d  FWID set: re-read srgr = %X\n",
+			__func__, __LINE__, snd_interval_value(i) - 1);
+
+		i = hw_param_interval(params, SNDRV_PCM_HW_PARAM_FRAME_BITS);
+		srgr |= DAVINCI_MCBSP_SRGR_FPER(snd_interval_value(i) - 1);
+		break;
+	default:
+		return -EINVAL;
+	}
+	davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SRGR_REG, srgr);
+
+	rcr = DAVINCI_MCBSP_RCR_RFIG;
+	xcr = DAVINCI_MCBSP_XCR_XFIG;
+	if (dev->mode == MOD_DSP_B) {
+		rcr |= DAVINCI_MCBSP_RCR_RDATDLY(0);
+		xcr |= DAVINCI_MCBSP_XCR_XDATDLY(0);
+	} else {
+		rcr |= DAVINCI_MCBSP_RCR_RDATDLY(1);
+		xcr |= DAVINCI_MCBSP_XCR_XDATDLY(1);
+	}
+	/* Determine xfer data type */
+	fmt = params_format(params);
+	if ((fmt > SNDRV_PCM_FORMAT_S32_LE) || !data_type[fmt]) {
+		printk(KERN_WARNING "davinci-i2s: unsupported PCM format\n");
+		return -EINVAL;
+	}
+
+	if (params_channels(params) == 2) {
+		element_cnt = 2;
+		if (double_fmt[fmt] && dev->enable_channel_combine) {
+			element_cnt = 1;
+			fmt = double_fmt[fmt];
+		}
+		switch (master) {
+		case SND_SOC_DAIFMT_BP_FP:
+		case SND_SOC_DAIFMT_BP_FC:
+			rcr |= DAVINCI_MCBSP_RCR_RFRLEN2(0);
+			xcr |= DAVINCI_MCBSP_XCR_XFRLEN2(0);
+			rcr |= DAVINCI_MCBSP_RCR_RPHASE;
+			xcr |= DAVINCI_MCBSP_XCR_XPHASE;
+			break;
+		case SND_SOC_DAIFMT_BC_FC:
+		case SND_SOC_DAIFMT_BC_FP:
+			rcr |= DAVINCI_MCBSP_RCR_RFRLEN2(element_cnt - 1);
+			xcr |= DAVINCI_MCBSP_XCR_XFRLEN2(element_cnt - 1);
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+	mcbsp_word_length = asp_word_length[fmt];
+
+	switch (master) {
+	case SND_SOC_DAIFMT_BP_FP:
+	case SND_SOC_DAIFMT_BP_FC:
+		rcr |= DAVINCI_MCBSP_RCR_RFRLEN1(0);
+		xcr |= DAVINCI_MCBSP_XCR_XFRLEN1(0);
+		break;
+	case SND_SOC_DAIFMT_BC_FC:
+	case SND_SOC_DAIFMT_BC_FP:
+		rcr |= DAVINCI_MCBSP_RCR_RFRLEN1(element_cnt - 1);
+		xcr |= DAVINCI_MCBSP_XCR_XFRLEN1(element_cnt - 1);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	rcr |= DAVINCI_MCBSP_RCR_RWDLEN1(mcbsp_word_length) |
+		DAVINCI_MCBSP_RCR_RWDLEN2(mcbsp_word_length);
+	xcr |= DAVINCI_MCBSP_XCR_XWDLEN1(mcbsp_word_length) |
+		DAVINCI_MCBSP_XCR_XWDLEN2(mcbsp_word_length);
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+		davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_XCR_REG, xcr);
+	else
+		davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_RCR_REG, rcr);
+
+	pr_debug("%s - %d  srgr=%X\n", __func__, __LINE__, srgr);
+	pr_debug("%s - %d  xcr=%X\n", __func__, __LINE__, xcr);
+	pr_debug("%s - %d  rcr=%X\n", __func__, __LINE__, rcr);
+	return 0;
+}
+
+static int davinci_i2s_prepare(struct snd_pcm_substream *substream,
+		struct snd_soc_dai *dai)
+{
+	struct davinci_mcbsp_dev *dev = snd_soc_dai_get_drvdata(dai);
+	int playback = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK);
+	u32 spcr;
+	u32 mask = playback ? DAVINCI_MCBSP_SPCR_XRST : DAVINCI_MCBSP_SPCR_RRST;
+
+	davinci_mcbsp_stop(dev, playback);
+
+	spcr = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG);
+	if (spcr & mask) {
+		/* start off disabled */
+		davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG,
+					spcr & ~mask);
+		toggle_clock(dev, playback);
+	}
+	if (dev->pcr & (DAVINCI_MCBSP_PCR_FSXM | DAVINCI_MCBSP_PCR_FSRM |
+			DAVINCI_MCBSP_PCR_CLKXM | DAVINCI_MCBSP_PCR_CLKRM)) {
+		/* Start the sample generator */
+		spcr |= DAVINCI_MCBSP_SPCR_GRST;
+		davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, spcr);
+	}
+
+	if (playback) {
+		/* Enable the transmitter */
+		spcr = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG);
+		spcr |= DAVINCI_MCBSP_SPCR_XRST;
+		davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, spcr);
+
+		/* wait for any unexpected frame sync error to occur */
+		udelay(100);
+
+		/* Disable the transmitter to clear any outstanding XSYNCERR */
+		spcr = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG);
+		spcr &= ~DAVINCI_MCBSP_SPCR_XRST;
+		davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, spcr);
+		toggle_clock(dev, playback);
+	}
+
+	return 0;
+}
+
+static int davinci_i2s_trigger(struct snd_pcm_substream *substream, int cmd,
+			       struct snd_soc_dai *dai)
+{
+	struct davinci_mcbsp_dev *dev = snd_soc_dai_get_drvdata(dai);
+	int ret = 0;
+	int playback = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK);
+
+	switch (cmd) {
+	case SNDRV_PCM_TRIGGER_START:
+	case SNDRV_PCM_TRIGGER_RESUME:
+	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
+		davinci_mcbsp_start(dev, substream);
+		break;
+	case SNDRV_PCM_TRIGGER_STOP:
+	case SNDRV_PCM_TRIGGER_SUSPEND:
+	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
+		davinci_mcbsp_stop(dev, playback);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+	return ret;
+}
+
+static void davinci_i2s_shutdown(struct snd_pcm_substream *substream,
+		struct snd_soc_dai *dai)
+{
+	struct davinci_mcbsp_dev *dev = snd_soc_dai_get_drvdata(dai);
+	int playback = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK);
+	davinci_mcbsp_stop(dev, playback);
+}
+
+#define DAVINCI_I2S_RATES	SNDRV_PCM_RATE_8000_96000
+#define DAVINCI_I2S_FORMATS	(SNDRV_PCM_FMTBIT_S16_LE | \
+				 SNDRV_PCM_FMTBIT_S32_LE)
+
+static const struct snd_soc_dai_ops davinci_i2s_dai_ops = {
+	.shutdown	= davinci_i2s_shutdown,
+	.prepare	= davinci_i2s_prepare,
+	.trigger	= davinci_i2s_trigger,
+	.hw_params	= davinci_i2s_hw_params,
+	.set_fmt	= davinci_i2s_set_dai_fmt,
+	.set_clkdiv	= davinci_i2s_dai_set_clkdiv,
+
+};
+
+static int davinci_i2s_dai_probe(struct snd_soc_dai *dai)
+{
+	struct davinci_mcbsp_dev *dev = snd_soc_dai_get_drvdata(dai);
+
+	dai->playback_dma_data = &dev->dma_data[SNDRV_PCM_STREAM_PLAYBACK];
+	dai->capture_dma_data = &dev->dma_data[SNDRV_PCM_STREAM_CAPTURE];
+
+	return 0;
+}
+
+static struct snd_soc_dai_driver davinci_i2s_dai = {
+	.probe = davinci_i2s_dai_probe,
+	.playback = {
+		.channels_min = 2,
+		.channels_max = 2,
+		.rates = DAVINCI_I2S_RATES,
+		.formats = DAVINCI_I2S_FORMATS,
+	},
+	.capture = {
+		.channels_min = 2,
+		.channels_max = 2,
+		.rates = DAVINCI_I2S_RATES,
+		.formats = DAVINCI_I2S_FORMATS,
+	},
+	.ops = &davinci_i2s_dai_ops,
+
+};
+
+static const struct snd_soc_component_driver davinci_i2s_component = {
+	.name			= DRV_NAME,
+	.legacy_dai_naming	= 1,
+};
+
+static int davinci_i2s_probe(struct platform_device *pdev)
+{
+	struct snd_dmaengine_dai_dma_data *dma_data;
+	struct davinci_mcbsp_dev *dev;
+	struct resource *mem, *res;
+	void __iomem *io_base;
+	int *dma;
+	int ret;
+
+	mem = platform_get_resource_byname(pdev, IORESOURCE_MEM, "mpu");
+	if (!mem) {
+		dev_warn(&pdev->dev,
+			 "\"mpu\" mem resource not found, using index 0\n");
+		mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+		if (!mem) {
+			dev_err(&pdev->dev, "no mem resource?\n");
+			return -ENODEV;
+		}
+	}
+
+	io_base = devm_ioremap_resource(&pdev->dev, mem);
+	if (IS_ERR(io_base))
+		return PTR_ERR(io_base);
+
+	dev = devm_kzalloc(&pdev->dev, sizeof(struct davinci_mcbsp_dev),
+			   GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+
+	dev->base = io_base;
+
+	/* setup DMA, first TX, then RX */
+	dma_data = &dev->dma_data[SNDRV_PCM_STREAM_PLAYBACK];
+	dma_data->addr = (dma_addr_t)(mem->start + DAVINCI_MCBSP_DXR_REG);
+
+	res = platform_get_resource(pdev, IORESOURCE_DMA, 0);
+	if (res) {
+		dma = &dev->dma_request[SNDRV_PCM_STREAM_PLAYBACK];
+		*dma = res->start;
+		dma_data->filter_data = dma;
+	} else if (IS_ENABLED(CONFIG_OF) && pdev->dev.of_node) {
+		dma_data->filter_data = "tx";
+	} else {
+		dev_err(&pdev->dev, "Missing DMA tx resource\n");
+		return -ENODEV;
+	}
+
+	dma_data = &dev->dma_data[SNDRV_PCM_STREAM_CAPTURE];
+	dma_data->addr = (dma_addr_t)(mem->start + DAVINCI_MCBSP_DRR_REG);
+
+	res = platform_get_resource(pdev, IORESOURCE_DMA, 1);
+	if (res) {
+		dma = &dev->dma_request[SNDRV_PCM_STREAM_CAPTURE];
+		*dma = res->start;
+		dma_data->filter_data = dma;
+	} else if (IS_ENABLED(CONFIG_OF) && pdev->dev.of_node) {
+		dma_data->filter_data = "rx";
+	} else {
+		dev_err(&pdev->dev, "Missing DMA rx resource\n");
+		return -ENODEV;
+	}
+
+	dev->clk = clk_get(&pdev->dev, NULL);
+	if (IS_ERR(dev->clk))
+		return -ENODEV;
+	ret = clk_enable(dev->clk);
+	if (ret)
+		goto err_put_clk;
+
+	dev->dev = &pdev->dev;
+	dev_set_drvdata(&pdev->dev, dev);
+
+	ret = snd_soc_register_component(&pdev->dev, &davinci_i2s_component,
+					 &davinci_i2s_dai, 1);
+	if (ret != 0)
+		goto err_release_clk;
+
+	ret = edma_pcm_platform_register(&pdev->dev);
+	if (ret) {
+		dev_err(&pdev->dev, "register PCM failed: %d\n", ret);
+		goto err_unregister_component;
+	}
+
+	return 0;
+
+err_unregister_component:
+	snd_soc_unregister_component(&pdev->dev);
+err_release_clk:
+	clk_disable(dev->clk);
+err_put_clk:
+	clk_put(dev->clk);
+	return ret;
+}
+
+static int davinci_i2s_remove(struct platform_device *pdev)
+{
+	struct davinci_mcbsp_dev *dev = dev_get_drvdata(&pdev->dev);
+
+	snd_soc_unregister_component(&pdev->dev);
+
+	clk_disable(dev->clk);
+	clk_put(dev->clk);
+	dev->clk = NULL;
+
+	return 0;
+}
+
+static const struct of_device_id davinci_i2s_match[] __maybe_unused = {
+	{ .compatible = "ti,da850-mcbsp" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, davinci_i2s_match);
+
+static struct platform_driver davinci_mcbsp_driver = {
+	.probe		= davinci_i2s_probe,
+	.remove		= davinci_i2s_remove,
+	.driver		= {
+		.name	= "davinci-mcbsp",
+		.of_match_table = of_match_ptr(davinci_i2s_match),
+	},
+};
+
+module_platform_driver(davinci_mcbsp_driver);
+
+MODULE_AUTHOR("Vladimir Barinov");
+MODULE_DESCRIPTION("TI DAVINCI I2S (McBSP) SoC Interface");
+MODULE_LICENSE("GPL");