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, 441 insertions, 0 deletions

diff --git a/drivers/phy/rockchip/phy-rockchip-pcie.c b/drivers/phy/rockchip/phy-rockchip-pcie.c
new file mode 100644
index 000000000..75216091d
--- /dev/null
+++ b/drivers/phy/rockchip/phy-rockchip-pcie.c
@@ -0,0 +1,441 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Rockchip PCIe PHY driver
+ *
+ * Copyright (C) 2016 Shawn Lin <shawn.lin@rock-chips.com>
+ * Copyright (C) 2016 ROCKCHIP, Inc.
+ */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include <linux/phy/phy.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/reset.h>
+
+/*
+ * The higher 16-bit of this register is used for write protection
+ * only if BIT(x + 16) set to 1 the BIT(x) can be written.
+ */
+#define HIWORD_UPDATE(val, mask, shift) \
+		((val) << (shift) | (mask) << ((shift) + 16))
+
+#define PHY_MAX_LANE_NUM      4
+#define PHY_CFG_DATA_SHIFT    7
+#define PHY_CFG_ADDR_SHIFT    1
+#define PHY_CFG_DATA_MASK     0xf
+#define PHY_CFG_ADDR_MASK     0x3f
+#define PHY_CFG_RD_MASK       0x3ff
+#define PHY_CFG_WR_ENABLE     1
+#define PHY_CFG_WR_DISABLE    1
+#define PHY_CFG_WR_SHIFT      0
+#define PHY_CFG_WR_MASK       1
+#define PHY_CFG_PLL_LOCK      0x10
+#define PHY_CFG_CLK_TEST      0x10
+#define PHY_CFG_CLK_SCC       0x12
+#define PHY_CFG_SEPE_RATE     BIT(3)
+#define PHY_CFG_PLL_100M      BIT(3)
+#define PHY_PLL_LOCKED        BIT(9)
+#define PHY_PLL_OUTPUT        BIT(10)
+#define PHY_LANE_A_STATUS     0x30
+#define PHY_LANE_B_STATUS     0x31
+#define PHY_LANE_C_STATUS     0x32
+#define PHY_LANE_D_STATUS     0x33
+#define PHY_LANE_RX_DET_SHIFT 11
+#define PHY_LANE_RX_DET_TH    0x1
+#define PHY_LANE_IDLE_OFF     0x1
+#define PHY_LANE_IDLE_MASK    0x1
+#define PHY_LANE_IDLE_A_SHIFT 3
+#define PHY_LANE_IDLE_B_SHIFT 4
+#define PHY_LANE_IDLE_C_SHIFT 5
+#define PHY_LANE_IDLE_D_SHIFT 6
+
+struct rockchip_pcie_data {
+	unsigned int pcie_conf;
+	unsigned int pcie_status;
+	unsigned int pcie_laneoff;
+};
+
+struct rockchip_pcie_phy {
+	struct rockchip_pcie_data *phy_data;
+	struct regmap *reg_base;
+	struct phy_pcie_instance {
+		struct phy *phy;
+		u32 index;
+	} phys[PHY_MAX_LANE_NUM];
+	struct mutex pcie_mutex;
+	struct reset_control *phy_rst;
+	struct clk *clk_pciephy_ref;
+	int pwr_cnt;
+	int init_cnt;
+};
+
+static struct rockchip_pcie_phy *to_pcie_phy(struct phy_pcie_instance *inst)
+{
+	return container_of(inst, struct rockchip_pcie_phy,
+					phys[inst->index]);
+}
+
+static struct phy *rockchip_pcie_phy_of_xlate(struct device *dev,
+					      struct of_phandle_args *args)
+{
+	struct rockchip_pcie_phy *rk_phy = dev_get_drvdata(dev);
+
+	if (args->args_count == 0)
+		return rk_phy->phys[0].phy;
+
+	if (WARN_ON(args->args[0] >= PHY_MAX_LANE_NUM))
+		return ERR_PTR(-ENODEV);
+
+	return rk_phy->phys[args->args[0]].phy;
+}
+
+
+static inline void phy_wr_cfg(struct rockchip_pcie_phy *rk_phy,
+			      u32 addr, u32 data)
+{
+	regmap_write(rk_phy->reg_base, rk_phy->phy_data->pcie_conf,
+		     HIWORD_UPDATE(data,
+				   PHY_CFG_DATA_MASK,
+				   PHY_CFG_DATA_SHIFT) |
+		     HIWORD_UPDATE(addr,
+				   PHY_CFG_ADDR_MASK,
+				   PHY_CFG_ADDR_SHIFT));
+	udelay(1);
+	regmap_write(rk_phy->reg_base, rk_phy->phy_data->pcie_conf,
+		     HIWORD_UPDATE(PHY_CFG_WR_ENABLE,
+				   PHY_CFG_WR_MASK,
+				   PHY_CFG_WR_SHIFT));
+	udelay(1);
+	regmap_write(rk_phy->reg_base, rk_phy->phy_data->pcie_conf,
+		     HIWORD_UPDATE(PHY_CFG_WR_DISABLE,
+				   PHY_CFG_WR_MASK,
+				   PHY_CFG_WR_SHIFT));
+}
+
+static inline u32 phy_rd_cfg(struct rockchip_pcie_phy *rk_phy,
+			     u32 addr)
+{
+	u32 val;
+
+	regmap_write(rk_phy->reg_base, rk_phy->phy_data->pcie_conf,
+		     HIWORD_UPDATE(addr,
+				   PHY_CFG_RD_MASK,
+				   PHY_CFG_ADDR_SHIFT));
+	regmap_read(rk_phy->reg_base,
+		    rk_phy->phy_data->pcie_status,
+		    &val);
+	return val;
+}
+
+static int rockchip_pcie_phy_power_off(struct phy *phy)
+{
+	struct phy_pcie_instance *inst = phy_get_drvdata(phy);
+	struct rockchip_pcie_phy *rk_phy = to_pcie_phy(inst);
+	int err = 0;
+
+	mutex_lock(&rk_phy->pcie_mutex);
+
+	regmap_write(rk_phy->reg_base,
+		     rk_phy->phy_data->pcie_laneoff,
+		     HIWORD_UPDATE(PHY_LANE_IDLE_OFF,
+				   PHY_LANE_IDLE_MASK,
+				   PHY_LANE_IDLE_A_SHIFT + inst->index));
+
+	if (--rk_phy->pwr_cnt)
+		goto err_out;
+
+	err = reset_control_assert(rk_phy->phy_rst);
+	if (err) {
+		dev_err(&phy->dev, "assert phy_rst err %d\n", err);
+		goto err_restore;
+	}
+
+err_out:
+	mutex_unlock(&rk_phy->pcie_mutex);
+	return 0;
+
+err_restore:
+	rk_phy->pwr_cnt++;
+	regmap_write(rk_phy->reg_base,
+		     rk_phy->phy_data->pcie_laneoff,
+		     HIWORD_UPDATE(!PHY_LANE_IDLE_OFF,
+				   PHY_LANE_IDLE_MASK,
+				   PHY_LANE_IDLE_A_SHIFT + inst->index));
+	mutex_unlock(&rk_phy->pcie_mutex);
+	return err;
+}
+
+static int rockchip_pcie_phy_power_on(struct phy *phy)
+{
+	struct phy_pcie_instance *inst = phy_get_drvdata(phy);
+	struct rockchip_pcie_phy *rk_phy = to_pcie_phy(inst);
+	int err = 0;
+	u32 status;
+	unsigned long timeout;
+
+	mutex_lock(&rk_phy->pcie_mutex);
+
+	if (rk_phy->pwr_cnt++)
+		goto err_out;
+
+	err = reset_control_deassert(rk_phy->phy_rst);
+	if (err) {
+		dev_err(&phy->dev, "deassert phy_rst err %d\n", err);
+		goto err_pwr_cnt;
+	}
+
+	regmap_write(rk_phy->reg_base, rk_phy->phy_data->pcie_conf,
+		     HIWORD_UPDATE(PHY_CFG_PLL_LOCK,
+				   PHY_CFG_ADDR_MASK,
+				   PHY_CFG_ADDR_SHIFT));
+
+	regmap_write(rk_phy->reg_base,
+		     rk_phy->phy_data->pcie_laneoff,
+		     HIWORD_UPDATE(!PHY_LANE_IDLE_OFF,
+				   PHY_LANE_IDLE_MASK,
+				   PHY_LANE_IDLE_A_SHIFT + inst->index));
+
+	/*
+	 * No documented timeout value for phy operation below,
+	 * so we make it large enough here. And we use loop-break
+	 * method which should not be harmful.
+	 */
+	timeout = jiffies + msecs_to_jiffies(1000);
+
+	err = -EINVAL;
+	while (time_before(jiffies, timeout)) {
+		regmap_read(rk_phy->reg_base,
+			    rk_phy->phy_data->pcie_status,
+			    &status);
+		if (status & PHY_PLL_LOCKED) {
+			dev_dbg(&phy->dev, "pll locked!\n");
+			err = 0;
+			break;
+		}
+		msleep(20);
+	}
+
+	if (err) {
+		dev_err(&phy->dev, "pll lock timeout!\n");
+		goto err_pll_lock;
+	}
+
+	phy_wr_cfg(rk_phy, PHY_CFG_CLK_TEST, PHY_CFG_SEPE_RATE);
+	phy_wr_cfg(rk_phy, PHY_CFG_CLK_SCC, PHY_CFG_PLL_100M);
+
+	err = -ETIMEDOUT;
+	while (time_before(jiffies, timeout)) {
+		regmap_read(rk_phy->reg_base,
+			    rk_phy->phy_data->pcie_status,
+			    &status);
+		if (!(status & PHY_PLL_OUTPUT)) {
+			dev_dbg(&phy->dev, "pll output enable done!\n");
+			err = 0;
+			break;
+		}
+		msleep(20);
+	}
+
+	if (err) {
+		dev_err(&phy->dev, "pll output enable timeout!\n");
+		goto err_pll_lock;
+	}
+
+	regmap_write(rk_phy->reg_base, rk_phy->phy_data->pcie_conf,
+		     HIWORD_UPDATE(PHY_CFG_PLL_LOCK,
+				   PHY_CFG_ADDR_MASK,
+				   PHY_CFG_ADDR_SHIFT));
+	err = -EINVAL;
+	while (time_before(jiffies, timeout)) {
+		regmap_read(rk_phy->reg_base,
+			    rk_phy->phy_data->pcie_status,
+			    &status);
+		if (status & PHY_PLL_LOCKED) {
+			dev_dbg(&phy->dev, "pll relocked!\n");
+			err = 0;
+			break;
+		}
+		msleep(20);
+	}
+
+	if (err) {
+		dev_err(&phy->dev, "pll relock timeout!\n");
+		goto err_pll_lock;
+	}
+
+err_out:
+	mutex_unlock(&rk_phy->pcie_mutex);
+	return 0;
+
+err_pll_lock:
+	reset_control_assert(rk_phy->phy_rst);
+err_pwr_cnt:
+	rk_phy->pwr_cnt--;
+	mutex_unlock(&rk_phy->pcie_mutex);
+	return err;
+}
+
+static int rockchip_pcie_phy_init(struct phy *phy)
+{
+	struct phy_pcie_instance *inst = phy_get_drvdata(phy);
+	struct rockchip_pcie_phy *rk_phy = to_pcie_phy(inst);
+	int err = 0;
+
+	mutex_lock(&rk_phy->pcie_mutex);
+
+	if (rk_phy->init_cnt++)
+		goto err_out;
+
+	err = clk_prepare_enable(rk_phy->clk_pciephy_ref);
+	if (err) {
+		dev_err(&phy->dev, "Fail to enable pcie ref clock.\n");
+		goto err_refclk;
+	}
+
+	err = reset_control_assert(rk_phy->phy_rst);
+	if (err) {
+		dev_err(&phy->dev, "assert phy_rst err %d\n", err);
+		goto err_reset;
+	}
+
+err_out:
+	mutex_unlock(&rk_phy->pcie_mutex);
+	return 0;
+
+err_reset:
+
+	clk_disable_unprepare(rk_phy->clk_pciephy_ref);
+err_refclk:
+	rk_phy->init_cnt--;
+	mutex_unlock(&rk_phy->pcie_mutex);
+	return err;
+}
+
+static int rockchip_pcie_phy_exit(struct phy *phy)
+{
+	struct phy_pcie_instance *inst = phy_get_drvdata(phy);
+	struct rockchip_pcie_phy *rk_phy = to_pcie_phy(inst);
+
+	mutex_lock(&rk_phy->pcie_mutex);
+
+	if (--rk_phy->init_cnt)
+		goto err_init_cnt;
+
+	clk_disable_unprepare(rk_phy->clk_pciephy_ref);
+
+err_init_cnt:
+	mutex_unlock(&rk_phy->pcie_mutex);
+	return 0;
+}
+
+static const struct phy_ops ops = {
+	.init		= rockchip_pcie_phy_init,
+	.exit		= rockchip_pcie_phy_exit,
+	.power_on	= rockchip_pcie_phy_power_on,
+	.power_off	= rockchip_pcie_phy_power_off,
+	.owner		= THIS_MODULE,
+};
+
+static const struct rockchip_pcie_data rk3399_pcie_data = {
+	.pcie_conf = 0xe220,
+	.pcie_status = 0xe2a4,
+	.pcie_laneoff = 0xe214,
+};
+
+static const struct of_device_id rockchip_pcie_phy_dt_ids[] = {
+	{
+		.compatible = "rockchip,rk3399-pcie-phy",
+		.data = &rk3399_pcie_data,
+	},
+	{}
+};
+
+MODULE_DEVICE_TABLE(of, rockchip_pcie_phy_dt_ids);
+
+static int rockchip_pcie_phy_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct rockchip_pcie_phy *rk_phy;
+	struct phy_provider *phy_provider;
+	struct regmap *grf;
+	const struct of_device_id *of_id;
+	int i;
+	u32 phy_num;
+
+	grf = syscon_node_to_regmap(dev->parent->of_node);
+	if (IS_ERR(grf)) {
+		dev_err(dev, "Cannot find GRF syscon\n");
+		return PTR_ERR(grf);
+	}
+
+	rk_phy = devm_kzalloc(dev, sizeof(*rk_phy), GFP_KERNEL);
+	if (!rk_phy)
+		return -ENOMEM;
+
+	of_id = of_match_device(rockchip_pcie_phy_dt_ids, &pdev->dev);
+	if (!of_id)
+		return -EINVAL;
+
+	rk_phy->phy_data = (struct rockchip_pcie_data *)of_id->data;
+	rk_phy->reg_base = grf;
+
+	mutex_init(&rk_phy->pcie_mutex);
+
+	rk_phy->phy_rst = devm_reset_control_get(dev, "phy");
+	if (IS_ERR(rk_phy->phy_rst)) {
+		if (PTR_ERR(rk_phy->phy_rst) != -EPROBE_DEFER)
+			dev_err(dev,
+				"missing phy property for reset controller\n");
+		return PTR_ERR(rk_phy->phy_rst);
+	}
+
+	rk_phy->clk_pciephy_ref = devm_clk_get(dev, "refclk");
+	if (IS_ERR(rk_phy->clk_pciephy_ref)) {
+		dev_err(dev, "refclk not found.\n");
+		return PTR_ERR(rk_phy->clk_pciephy_ref);
+	}
+
+	/* parse #phy-cells to see if it's legacy PHY model */
+	if (of_property_read_u32(dev->of_node, "#phy-cells", &phy_num))
+		return -ENOENT;
+
+	phy_num = (phy_num == 0) ? 1 : PHY_MAX_LANE_NUM;
+	dev_dbg(dev, "phy number is %d\n", phy_num);
+
+	for (i = 0; i < phy_num; i++) {
+		rk_phy->phys[i].phy = devm_phy_create(dev, dev->of_node, &ops);
+		if (IS_ERR(rk_phy->phys[i].phy)) {
+			dev_err(dev, "failed to create PHY%d\n", i);
+			return PTR_ERR(rk_phy->phys[i].phy);
+		}
+		rk_phy->phys[i].index = i;
+		phy_set_drvdata(rk_phy->phys[i].phy, &rk_phy->phys[i]);
+	}
+
+	platform_set_drvdata(pdev, rk_phy);
+	phy_provider = devm_of_phy_provider_register(dev,
+					rockchip_pcie_phy_of_xlate);
+
+	return PTR_ERR_OR_ZERO(phy_provider);
+}
+
+static struct platform_driver rockchip_pcie_driver = {
+	.probe		= rockchip_pcie_phy_probe,
+	.driver		= {
+		.name	= "rockchip-pcie-phy",
+		.of_match_table = rockchip_pcie_phy_dt_ids,
+	},
+};
+
+module_platform_driver(rockchip_pcie_driver);
+
+MODULE_AUTHOR("Shawn Lin <shawn.lin@rock-chips.com>");
+MODULE_DESCRIPTION("Rockchip PCIe PHY driver");
+MODULE_LICENSE("GPL v2");