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, 486 insertions, 0 deletions

diff --git a/drivers/mmc/host/dw_mmc-k3.c b/drivers/mmc/host/dw_mmc-k3.c
new file mode 100644
index 000000000..0311a37dd
--- /dev/null
+++ b/drivers/mmc/host/dw_mmc-k3.c
@@ -0,0 +1,486 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2013 Linaro Ltd.
+ * Copyright (c) 2013 HiSilicon Limited.
+ */
+
+#include <linux/bitops.h>
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/mfd/syscon.h>
+#include <linux/mmc/host.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
+
+#include "dw_mmc.h"
+#include "dw_mmc-pltfm.h"
+
+/*
+ * hi6220 sd only support io voltage 1.8v and 3v
+ * Also need config AO_SCTRL_SEL18 accordingly
+ */
+#define AO_SCTRL_SEL18		BIT(10)
+#define AO_SCTRL_CTRL3		0x40C
+
+#define DWMMC_SDIO_ID 2
+
+#define SOC_SCTRL_SCPERCTRL5    (0x314)
+#define SDCARD_IO_SEL18         BIT(2)
+
+#define SDCARD_RD_THRESHOLD  (512)
+
+#define GENCLK_DIV (7)
+
+#define GPIO_CLK_ENABLE                   BIT(16)
+#define GPIO_CLK_DIV_MASK                 GENMASK(11, 8)
+#define GPIO_USE_SAMPLE_DLY_MASK          GENMASK(13, 13)
+#define UHS_REG_EXT_SAMPLE_PHASE_MASK     GENMASK(20, 16)
+#define UHS_REG_EXT_SAMPLE_DRVPHASE_MASK  GENMASK(25, 21)
+#define UHS_REG_EXT_SAMPLE_DLY_MASK       GENMASK(30, 26)
+
+#define TIMING_MODE     3
+#define TIMING_CFG_NUM 10
+
+#define NUM_PHASES (40)
+
+#define ENABLE_SHIFT_MIN_SMPL (4)
+#define ENABLE_SHIFT_MAX_SMPL (12)
+#define USE_DLY_MIN_SMPL (11)
+#define USE_DLY_MAX_SMPL (14)
+
+struct k3_priv {
+	int ctrl_id;
+	u32 cur_speed;
+	struct regmap	*reg;
+};
+
+static unsigned long dw_mci_hi6220_caps[] = {
+	MMC_CAP_CMD23,
+	MMC_CAP_CMD23,
+	0
+};
+
+struct hs_timing {
+	u32 drv_phase;
+	u32 smpl_dly;
+	u32 smpl_phase_max;
+	u32 smpl_phase_min;
+};
+
+static struct hs_timing hs_timing_cfg[TIMING_MODE][TIMING_CFG_NUM] = {
+	{ /* reserved */ },
+	{ /* SD */
+		{7, 0, 15, 15,},  /* 0: LEGACY 400k */
+		{6, 0,  4,  4,},  /* 1: MMC_HS */
+		{6, 0,  3,  3,},  /* 2: SD_HS */
+		{6, 0, 15, 15,},  /* 3: SDR12 */
+		{6, 0,  2,  2,},  /* 4: SDR25 */
+		{4, 0, 11,  0,},  /* 5: SDR50 */
+		{6, 4, 15,  0,},  /* 6: SDR104 */
+		{0},              /* 7: DDR50 */
+		{0},              /* 8: DDR52 */
+		{0},              /* 9: HS200 */
+	},
+	{ /* SDIO */
+		{7, 0, 15, 15,},  /* 0: LEGACY 400k */
+		{0},              /* 1: MMC_HS */
+		{6, 0, 15, 15,},  /* 2: SD_HS */
+		{6, 0, 15, 15,},  /* 3: SDR12 */
+		{6, 0,  0,  0,},  /* 4: SDR25 */
+		{4, 0, 12,  0,},  /* 5: SDR50 */
+		{5, 4, 15,  0,},  /* 6: SDR104 */
+		{0},              /* 7: DDR50 */
+		{0},              /* 8: DDR52 */
+		{0},              /* 9: HS200 */
+	}
+};
+
+static void dw_mci_k3_set_ios(struct dw_mci *host, struct mmc_ios *ios)
+{
+	int ret;
+
+	ret = clk_set_rate(host->ciu_clk, ios->clock);
+	if (ret)
+		dev_warn(host->dev, "failed to set rate %uHz\n", ios->clock);
+
+	host->bus_hz = clk_get_rate(host->ciu_clk);
+}
+
+static const struct dw_mci_drv_data k3_drv_data = {
+	.set_ios		= dw_mci_k3_set_ios,
+};
+
+static int dw_mci_hi6220_parse_dt(struct dw_mci *host)
+{
+	struct k3_priv *priv;
+
+	priv = devm_kzalloc(host->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->reg = syscon_regmap_lookup_by_phandle(host->dev->of_node,
+					 "hisilicon,peripheral-syscon");
+	if (IS_ERR(priv->reg))
+		priv->reg = NULL;
+
+	priv->ctrl_id = of_alias_get_id(host->dev->of_node, "mshc");
+	if (priv->ctrl_id < 0)
+		priv->ctrl_id = 0;
+
+	if (priv->ctrl_id >= TIMING_MODE)
+		return -EINVAL;
+
+	host->priv = priv;
+	return 0;
+}
+
+static int dw_mci_hi6220_switch_voltage(struct mmc_host *mmc, struct mmc_ios *ios)
+{
+	struct dw_mci_slot *slot = mmc_priv(mmc);
+	struct k3_priv *priv;
+	struct dw_mci *host;
+	int min_uv, max_uv;
+	int ret;
+
+	host = slot->host;
+	priv = host->priv;
+
+	if (!priv || !priv->reg)
+		return 0;
+
+	if (ios->signal_voltage == MMC_SIGNAL_VOLTAGE_330) {
+		ret = regmap_update_bits(priv->reg, AO_SCTRL_CTRL3,
+					 AO_SCTRL_SEL18, 0);
+		min_uv = 3000000;
+		max_uv = 3000000;
+	} else if (ios->signal_voltage == MMC_SIGNAL_VOLTAGE_180) {
+		ret = regmap_update_bits(priv->reg, AO_SCTRL_CTRL3,
+					 AO_SCTRL_SEL18, AO_SCTRL_SEL18);
+		min_uv = 1800000;
+		max_uv = 1800000;
+	} else {
+		dev_dbg(host->dev, "voltage not supported\n");
+		return -EINVAL;
+	}
+
+	if (ret) {
+		dev_dbg(host->dev, "switch voltage failed\n");
+		return ret;
+	}
+
+	if (IS_ERR_OR_NULL(mmc->supply.vqmmc))
+		return 0;
+
+	ret = regulator_set_voltage(mmc->supply.vqmmc, min_uv, max_uv);
+	if (ret) {
+		dev_dbg(host->dev, "Regulator set error %d: %d - %d\n",
+				 ret, min_uv, max_uv);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void dw_mci_hi6220_set_ios(struct dw_mci *host, struct mmc_ios *ios)
+{
+	int ret;
+	unsigned int clock;
+
+	clock = (ios->clock <= 25000000) ? 25000000 : ios->clock;
+
+	ret = clk_set_rate(host->biu_clk, clock);
+	if (ret)
+		dev_warn(host->dev, "failed to set rate %uHz\n", clock);
+
+	host->bus_hz = clk_get_rate(host->biu_clk);
+}
+
+static int dw_mci_hi6220_execute_tuning(struct dw_mci_slot *slot, u32 opcode)
+{
+	return 0;
+}
+
+static const struct dw_mci_drv_data hi6220_data = {
+	.caps			= dw_mci_hi6220_caps,
+	.num_caps		= ARRAY_SIZE(dw_mci_hi6220_caps),
+	.switch_voltage		= dw_mci_hi6220_switch_voltage,
+	.set_ios		= dw_mci_hi6220_set_ios,
+	.parse_dt		= dw_mci_hi6220_parse_dt,
+	.execute_tuning		= dw_mci_hi6220_execute_tuning,
+};
+
+static void dw_mci_hs_set_timing(struct dw_mci *host, int timing,
+				     int smpl_phase)
+{
+	u32 drv_phase;
+	u32 smpl_dly;
+	u32 use_smpl_dly = 0;
+	u32 enable_shift = 0;
+	u32 reg_value;
+	int ctrl_id;
+	struct k3_priv *priv;
+
+	priv = host->priv;
+	ctrl_id = priv->ctrl_id;
+
+	drv_phase = hs_timing_cfg[ctrl_id][timing].drv_phase;
+	smpl_dly   = hs_timing_cfg[ctrl_id][timing].smpl_dly;
+	if (smpl_phase == -1)
+		smpl_phase = (hs_timing_cfg[ctrl_id][timing].smpl_phase_max +
+			     hs_timing_cfg[ctrl_id][timing].smpl_phase_min) / 2;
+
+	switch (timing) {
+	case MMC_TIMING_UHS_SDR104:
+		if (smpl_phase >= USE_DLY_MIN_SMPL &&
+				smpl_phase <= USE_DLY_MAX_SMPL)
+			use_smpl_dly = 1;
+		fallthrough;
+	case MMC_TIMING_UHS_SDR50:
+		if (smpl_phase >= ENABLE_SHIFT_MIN_SMPL &&
+				smpl_phase <= ENABLE_SHIFT_MAX_SMPL)
+			enable_shift = 1;
+		break;
+	}
+
+	mci_writel(host, GPIO, 0x0);
+	usleep_range(5, 10);
+
+	reg_value = FIELD_PREP(UHS_REG_EXT_SAMPLE_PHASE_MASK, smpl_phase) |
+		    FIELD_PREP(UHS_REG_EXT_SAMPLE_DLY_MASK, smpl_dly) |
+		    FIELD_PREP(UHS_REG_EXT_SAMPLE_DRVPHASE_MASK, drv_phase);
+	mci_writel(host, UHS_REG_EXT, reg_value);
+
+	mci_writel(host, ENABLE_SHIFT, enable_shift);
+
+	reg_value = FIELD_PREP(GPIO_CLK_DIV_MASK, GENCLK_DIV) |
+			     FIELD_PREP(GPIO_USE_SAMPLE_DLY_MASK, use_smpl_dly);
+	mci_writel(host, GPIO, (unsigned int)reg_value | GPIO_CLK_ENABLE);
+
+	/* We should delay 1ms wait for timing setting finished. */
+	usleep_range(1000, 2000);
+}
+
+static int dw_mci_hi3660_init(struct dw_mci *host)
+{
+	mci_writel(host, CDTHRCTL, SDMMC_SET_THLD(SDCARD_RD_THRESHOLD,
+		    SDMMC_CARD_RD_THR_EN));
+
+	dw_mci_hs_set_timing(host, MMC_TIMING_LEGACY, -1);
+	host->bus_hz /= (GENCLK_DIV + 1);
+
+	return 0;
+}
+
+static int dw_mci_set_sel18(struct dw_mci *host, bool set)
+{
+	int ret;
+	unsigned int val;
+	struct k3_priv *priv;
+
+	priv = host->priv;
+
+	val = set ? SDCARD_IO_SEL18 : 0;
+	ret = regmap_update_bits(priv->reg, SOC_SCTRL_SCPERCTRL5,
+				 SDCARD_IO_SEL18, val);
+	if (ret) {
+		dev_err(host->dev, "sel18 %u error\n", val);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void dw_mci_hi3660_set_ios(struct dw_mci *host, struct mmc_ios *ios)
+{
+	int ret;
+	unsigned long wanted;
+	unsigned long actual;
+	struct k3_priv *priv = host->priv;
+
+	if (!ios->clock || ios->clock == priv->cur_speed)
+		return;
+
+	wanted = ios->clock * (GENCLK_DIV + 1);
+	ret = clk_set_rate(host->ciu_clk, wanted);
+	if (ret) {
+		dev_err(host->dev, "failed to set rate %luHz\n", wanted);
+		return;
+	}
+	actual = clk_get_rate(host->ciu_clk);
+
+	dw_mci_hs_set_timing(host, ios->timing, -1);
+	host->bus_hz = actual / (GENCLK_DIV + 1);
+	host->current_speed = 0;
+	priv->cur_speed = host->bus_hz;
+}
+
+static int dw_mci_get_best_clksmpl(unsigned int sample_flag)
+{
+	int i;
+	int interval;
+	unsigned int v;
+	unsigned int len;
+	unsigned int range_start = 0;
+	unsigned int range_length = 0;
+	unsigned int middle_range = 0;
+
+	if (!sample_flag)
+		return -EIO;
+
+	if (~sample_flag == 0)
+		return 0;
+
+	i = ffs(sample_flag) - 1;
+
+	/*
+	* A clock cycle is divided into 32 phases,
+	* each of which is represented by a bit,
+	* finding the optimal phase.
+	*/
+	while (i < 32) {
+		v = ror32(sample_flag, i);
+		len = ffs(~v) - 1;
+
+		if (len > range_length) {
+			range_length = len;
+			range_start = i;
+		}
+
+		interval = ffs(v >> len) - 1;
+		if (interval < 0)
+			break;
+
+		i += len + interval;
+	}
+
+	middle_range = range_start + range_length / 2;
+	if (middle_range >= 32)
+		middle_range %= 32;
+
+	return middle_range;
+}
+
+static int dw_mci_hi3660_execute_tuning(struct dw_mci_slot *slot, u32 opcode)
+{
+	int i = 0;
+	struct dw_mci *host = slot->host;
+	struct mmc_host *mmc = slot->mmc;
+	int smpl_phase = 0;
+	u32 tuning_sample_flag = 0;
+	int best_clksmpl = 0;
+
+	for (i = 0; i < NUM_PHASES; ++i, ++smpl_phase) {
+		smpl_phase %= 32;
+
+		mci_writel(host, TMOUT, ~0);
+		dw_mci_hs_set_timing(host, mmc->ios.timing, smpl_phase);
+
+		if (!mmc_send_tuning(mmc, opcode, NULL))
+			tuning_sample_flag |= (1 << smpl_phase);
+		else
+			tuning_sample_flag &= ~(1 << smpl_phase);
+	}
+
+	best_clksmpl = dw_mci_get_best_clksmpl(tuning_sample_flag);
+	if (best_clksmpl < 0) {
+		dev_err(host->dev, "All phases bad!\n");
+		return -EIO;
+	}
+
+	dw_mci_hs_set_timing(host, mmc->ios.timing, best_clksmpl);
+
+	dev_info(host->dev, "tuning ok best_clksmpl %u tuning_sample_flag %x\n",
+		 best_clksmpl, tuning_sample_flag);
+	return 0;
+}
+
+static int dw_mci_hi3660_switch_voltage(struct mmc_host *mmc,
+					struct mmc_ios *ios)
+{
+	int ret = 0;
+	struct dw_mci_slot *slot = mmc_priv(mmc);
+	struct k3_priv *priv;
+	struct dw_mci *host;
+
+	host = slot->host;
+	priv = host->priv;
+
+	if (!priv || !priv->reg)
+		return 0;
+
+	if (priv->ctrl_id == DWMMC_SDIO_ID)
+		return 0;
+
+	if (ios->signal_voltage == MMC_SIGNAL_VOLTAGE_330)
+		ret = dw_mci_set_sel18(host, 0);
+	else if (ios->signal_voltage == MMC_SIGNAL_VOLTAGE_180)
+		ret = dw_mci_set_sel18(host, 1);
+	if (ret)
+		return ret;
+
+	if (!IS_ERR(mmc->supply.vqmmc)) {
+		ret = mmc_regulator_set_vqmmc(mmc, ios);
+		if (ret < 0) {
+			dev_err(host->dev, "Regulator set error %d\n", ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static const struct dw_mci_drv_data hi3660_data = {
+	.init = dw_mci_hi3660_init,
+	.set_ios = dw_mci_hi3660_set_ios,
+	.parse_dt = dw_mci_hi6220_parse_dt,
+	.execute_tuning = dw_mci_hi3660_execute_tuning,
+	.switch_voltage  = dw_mci_hi3660_switch_voltage,
+};
+
+static const struct of_device_id dw_mci_k3_match[] = {
+	{ .compatible = "hisilicon,hi3660-dw-mshc", .data = &hi3660_data, },
+	{ .compatible = "hisilicon,hi4511-dw-mshc", .data = &k3_drv_data, },
+	{ .compatible = "hisilicon,hi6220-dw-mshc", .data = &hi6220_data, },
+	{},
+};
+MODULE_DEVICE_TABLE(of, dw_mci_k3_match);
+
+static int dw_mci_k3_probe(struct platform_device *pdev)
+{
+	const struct dw_mci_drv_data *drv_data;
+	const struct of_device_id *match;
+
+	match = of_match_node(dw_mci_k3_match, pdev->dev.of_node);
+	drv_data = match->data;
+
+	return dw_mci_pltfm_register(pdev, drv_data);
+}
+
+static const struct dev_pm_ops dw_mci_k3_dev_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
+	SET_RUNTIME_PM_OPS(dw_mci_runtime_suspend,
+			   dw_mci_runtime_resume,
+			   NULL)
+};
+
+static struct platform_driver dw_mci_k3_pltfm_driver = {
+	.probe		= dw_mci_k3_probe,
+	.remove		= dw_mci_pltfm_remove,
+	.driver		= {
+		.name		= "dwmmc_k3",
+		.probe_type	= PROBE_PREFER_ASYNCHRONOUS,
+		.of_match_table	= dw_mci_k3_match,
+		.pm		= &dw_mci_k3_dev_pm_ops,
+	},
+};
+
+module_platform_driver(dw_mci_k3_pltfm_driver);
+
+MODULE_DESCRIPTION("K3 Specific DW-MSHC Driver Extension");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:dwmmc_k3");