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, 675 insertions, 0 deletions

diff --git a/drivers/soc/mediatek/mtk-pm-domains.c b/drivers/soc/mediatek/mtk-pm-domains.c
new file mode 100644
index 000000000..474b272f9
--- /dev/null
+++ b/drivers/soc/mediatek/mtk-pm-domains.c
@@ -0,0 +1,675 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2020 Collabora Ltd.
+ */
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/mfd/syscon.h>
+#include <linux/of_clk.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/pm_domain.h>
+#include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
+#include <linux/soc/mediatek/infracfg.h>
+
+#include "mt6795-pm-domains.h"
+#include "mt8167-pm-domains.h"
+#include "mt8173-pm-domains.h"
+#include "mt8183-pm-domains.h"
+#include "mt8186-pm-domains.h"
+#include "mt8192-pm-domains.h"
+#include "mt8195-pm-domains.h"
+
+#define MTK_POLL_DELAY_US		10
+#define MTK_POLL_TIMEOUT		USEC_PER_SEC
+
+#define PWR_RST_B_BIT			BIT(0)
+#define PWR_ISO_BIT			BIT(1)
+#define PWR_ON_BIT			BIT(2)
+#define PWR_ON_2ND_BIT			BIT(3)
+#define PWR_CLK_DIS_BIT			BIT(4)
+#define PWR_SRAM_CLKISO_BIT		BIT(5)
+#define PWR_SRAM_ISOINT_B_BIT		BIT(6)
+
+struct scpsys_domain {
+	struct generic_pm_domain genpd;
+	const struct scpsys_domain_data *data;
+	struct scpsys *scpsys;
+	int num_clks;
+	struct clk_bulk_data *clks;
+	int num_subsys_clks;
+	struct clk_bulk_data *subsys_clks;
+	struct regmap *infracfg;
+	struct regmap *smi;
+	struct regulator *supply;
+};
+
+struct scpsys {
+	struct device *dev;
+	struct regmap *base;
+	const struct scpsys_soc_data *soc_data;
+	struct genpd_onecell_data pd_data;
+	struct generic_pm_domain *domains[];
+};
+
+#define to_scpsys_domain(gpd) container_of(gpd, struct scpsys_domain, genpd)
+
+static bool scpsys_domain_is_on(struct scpsys_domain *pd)
+{
+	struct scpsys *scpsys = pd->scpsys;
+	u32 status, status2;
+
+	regmap_read(scpsys->base, pd->data->pwr_sta_offs, &status);
+	status &= pd->data->sta_mask;
+
+	regmap_read(scpsys->base, pd->data->pwr_sta2nd_offs, &status2);
+	status2 &= pd->data->sta_mask;
+
+	/* A domain is on when both status bits are set. */
+	return status && status2;
+}
+
+static int scpsys_sram_enable(struct scpsys_domain *pd)
+{
+	u32 pdn_ack = pd->data->sram_pdn_ack_bits;
+	struct scpsys *scpsys = pd->scpsys;
+	unsigned int tmp;
+	int ret;
+
+	regmap_clear_bits(scpsys->base, pd->data->ctl_offs, pd->data->sram_pdn_bits);
+
+	/* Either wait until SRAM_PDN_ACK all 1 or 0 */
+	ret = regmap_read_poll_timeout(scpsys->base, pd->data->ctl_offs, tmp,
+				       (tmp & pdn_ack) == 0, MTK_POLL_DELAY_US, MTK_POLL_TIMEOUT);
+	if (ret < 0)
+		return ret;
+
+	if (MTK_SCPD_CAPS(pd, MTK_SCPD_SRAM_ISO)) {
+		regmap_set_bits(scpsys->base, pd->data->ctl_offs, PWR_SRAM_ISOINT_B_BIT);
+		udelay(1);
+		regmap_clear_bits(scpsys->base, pd->data->ctl_offs, PWR_SRAM_CLKISO_BIT);
+	}
+
+	return 0;
+}
+
+static int scpsys_sram_disable(struct scpsys_domain *pd)
+{
+	u32 pdn_ack = pd->data->sram_pdn_ack_bits;
+	struct scpsys *scpsys = pd->scpsys;
+	unsigned int tmp;
+
+	if (MTK_SCPD_CAPS(pd, MTK_SCPD_SRAM_ISO)) {
+		regmap_set_bits(scpsys->base, pd->data->ctl_offs, PWR_SRAM_CLKISO_BIT);
+		udelay(1);
+		regmap_clear_bits(scpsys->base, pd->data->ctl_offs, PWR_SRAM_ISOINT_B_BIT);
+	}
+
+	regmap_set_bits(scpsys->base, pd->data->ctl_offs, pd->data->sram_pdn_bits);
+
+	/* Either wait until SRAM_PDN_ACK all 1 or 0 */
+	return regmap_read_poll_timeout(scpsys->base, pd->data->ctl_offs, tmp,
+					(tmp & pdn_ack) == pdn_ack, MTK_POLL_DELAY_US,
+					MTK_POLL_TIMEOUT);
+}
+
+static int _scpsys_bus_protect_enable(const struct scpsys_bus_prot_data *bpd, struct regmap *regmap)
+{
+	int i, ret;
+
+	for (i = 0; i < SPM_MAX_BUS_PROT_DATA; i++) {
+		u32 val, mask = bpd[i].bus_prot_mask;
+
+		if (!mask)
+			break;
+
+		if (bpd[i].bus_prot_reg_update)
+			regmap_set_bits(regmap, bpd[i].bus_prot_set, mask);
+		else
+			regmap_write(regmap, bpd[i].bus_prot_set, mask);
+
+		ret = regmap_read_poll_timeout(regmap, bpd[i].bus_prot_sta,
+					       val, (val & mask) == mask,
+					       MTK_POLL_DELAY_US, MTK_POLL_TIMEOUT);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int scpsys_bus_protect_enable(struct scpsys_domain *pd)
+{
+	int ret;
+
+	ret = _scpsys_bus_protect_enable(pd->data->bp_infracfg, pd->infracfg);
+	if (ret)
+		return ret;
+
+	return _scpsys_bus_protect_enable(pd->data->bp_smi, pd->smi);
+}
+
+static int _scpsys_bus_protect_disable(const struct scpsys_bus_prot_data *bpd,
+				       struct regmap *regmap)
+{
+	int i, ret;
+
+	for (i = SPM_MAX_BUS_PROT_DATA - 1; i >= 0; i--) {
+		u32 val, mask = bpd[i].bus_prot_mask;
+
+		if (!mask)
+			continue;
+
+		if (bpd[i].bus_prot_reg_update)
+			regmap_clear_bits(regmap, bpd[i].bus_prot_clr, mask);
+		else
+			regmap_write(regmap, bpd[i].bus_prot_clr, mask);
+
+		if (bpd[i].ignore_clr_ack)
+			continue;
+
+		ret = regmap_read_poll_timeout(regmap, bpd[i].bus_prot_sta,
+					       val, !(val & mask),
+					       MTK_POLL_DELAY_US, MTK_POLL_TIMEOUT);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int scpsys_bus_protect_disable(struct scpsys_domain *pd)
+{
+	int ret;
+
+	ret = _scpsys_bus_protect_disable(pd->data->bp_smi, pd->smi);
+	if (ret)
+		return ret;
+
+	return _scpsys_bus_protect_disable(pd->data->bp_infracfg, pd->infracfg);
+}
+
+static int scpsys_regulator_enable(struct regulator *supply)
+{
+	return supply ? regulator_enable(supply) : 0;
+}
+
+static int scpsys_regulator_disable(struct regulator *supply)
+{
+	return supply ? regulator_disable(supply) : 0;
+}
+
+static int scpsys_power_on(struct generic_pm_domain *genpd)
+{
+	struct scpsys_domain *pd = container_of(genpd, struct scpsys_domain, genpd);
+	struct scpsys *scpsys = pd->scpsys;
+	bool tmp;
+	int ret;
+
+	ret = scpsys_regulator_enable(pd->supply);
+	if (ret)
+		return ret;
+
+	ret = clk_bulk_prepare_enable(pd->num_clks, pd->clks);
+	if (ret)
+		goto err_reg;
+
+	/* subsys power on */
+	regmap_set_bits(scpsys->base, pd->data->ctl_offs, PWR_ON_BIT);
+	regmap_set_bits(scpsys->base, pd->data->ctl_offs, PWR_ON_2ND_BIT);
+
+	/* wait until PWR_ACK = 1 */
+	ret = readx_poll_timeout(scpsys_domain_is_on, pd, tmp, tmp, MTK_POLL_DELAY_US,
+				 MTK_POLL_TIMEOUT);
+	if (ret < 0)
+		goto err_pwr_ack;
+
+	regmap_clear_bits(scpsys->base, pd->data->ctl_offs, PWR_CLK_DIS_BIT);
+	regmap_clear_bits(scpsys->base, pd->data->ctl_offs, PWR_ISO_BIT);
+	regmap_set_bits(scpsys->base, pd->data->ctl_offs, PWR_RST_B_BIT);
+
+	ret = clk_bulk_prepare_enable(pd->num_subsys_clks, pd->subsys_clks);
+	if (ret)
+		goto err_pwr_ack;
+
+	ret = scpsys_sram_enable(pd);
+	if (ret < 0)
+		goto err_disable_subsys_clks;
+
+	ret = scpsys_bus_protect_disable(pd);
+	if (ret < 0)
+		goto err_disable_sram;
+
+	return 0;
+
+err_disable_sram:
+	scpsys_sram_disable(pd);
+err_disable_subsys_clks:
+	clk_bulk_disable_unprepare(pd->num_subsys_clks, pd->subsys_clks);
+err_pwr_ack:
+	clk_bulk_disable_unprepare(pd->num_clks, pd->clks);
+err_reg:
+	scpsys_regulator_disable(pd->supply);
+	return ret;
+}
+
+static int scpsys_power_off(struct generic_pm_domain *genpd)
+{
+	struct scpsys_domain *pd = container_of(genpd, struct scpsys_domain, genpd);
+	struct scpsys *scpsys = pd->scpsys;
+	bool tmp;
+	int ret;
+
+	ret = scpsys_bus_protect_enable(pd);
+	if (ret < 0)
+		return ret;
+
+	ret = scpsys_sram_disable(pd);
+	if (ret < 0)
+		return ret;
+
+	clk_bulk_disable_unprepare(pd->num_subsys_clks, pd->subsys_clks);
+
+	/* subsys power off */
+	regmap_set_bits(scpsys->base, pd->data->ctl_offs, PWR_ISO_BIT);
+	regmap_set_bits(scpsys->base, pd->data->ctl_offs, PWR_CLK_DIS_BIT);
+	regmap_clear_bits(scpsys->base, pd->data->ctl_offs, PWR_RST_B_BIT);
+	regmap_clear_bits(scpsys->base, pd->data->ctl_offs, PWR_ON_2ND_BIT);
+	regmap_clear_bits(scpsys->base, pd->data->ctl_offs, PWR_ON_BIT);
+
+	/* wait until PWR_ACK = 0 */
+	ret = readx_poll_timeout(scpsys_domain_is_on, pd, tmp, !tmp, MTK_POLL_DELAY_US,
+				 MTK_POLL_TIMEOUT);
+	if (ret < 0)
+		return ret;
+
+	clk_bulk_disable_unprepare(pd->num_clks, pd->clks);
+
+	scpsys_regulator_disable(pd->supply);
+
+	return 0;
+}
+
+static struct
+generic_pm_domain *scpsys_add_one_domain(struct scpsys *scpsys, struct device_node *node)
+{
+	const struct scpsys_domain_data *domain_data;
+	struct scpsys_domain *pd;
+	struct device_node *root_node = scpsys->dev->of_node;
+	struct device_node *smi_node;
+	struct property *prop;
+	const char *clk_name;
+	int i, ret, num_clks;
+	struct clk *clk;
+	int clk_ind = 0;
+	u32 id;
+
+	ret = of_property_read_u32(node, "reg", &id);
+	if (ret) {
+		dev_err(scpsys->dev, "%pOF: failed to retrieve domain id from reg: %d\n",
+			node, ret);
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (id >= scpsys->soc_data->num_domains) {
+		dev_err(scpsys->dev, "%pOF: invalid domain id %d\n", node, id);
+		return ERR_PTR(-EINVAL);
+	}
+
+	domain_data = &scpsys->soc_data->domains_data[id];
+	if (domain_data->sta_mask == 0) {
+		dev_err(scpsys->dev, "%pOF: undefined domain id %d\n", node, id);
+		return ERR_PTR(-EINVAL);
+	}
+
+	pd = devm_kzalloc(scpsys->dev, sizeof(*pd), GFP_KERNEL);
+	if (!pd)
+		return ERR_PTR(-ENOMEM);
+
+	pd->data = domain_data;
+	pd->scpsys = scpsys;
+
+	if (MTK_SCPD_CAPS(pd, MTK_SCPD_DOMAIN_SUPPLY)) {
+		/*
+		 * Find regulator in current power domain node.
+		 * devm_regulator_get() finds regulator in a node and its child
+		 * node, so set of_node to current power domain node then change
+		 * back to original node after regulator is found for current
+		 * power domain node.
+		 */
+		scpsys->dev->of_node = node;
+		pd->supply = devm_regulator_get(scpsys->dev, "domain");
+		scpsys->dev->of_node = root_node;
+		if (IS_ERR(pd->supply)) {
+			dev_err_probe(scpsys->dev, PTR_ERR(pd->supply),
+				      "%pOF: failed to get power supply.\n",
+				      node);
+			return ERR_CAST(pd->supply);
+		}
+	}
+
+	pd->infracfg = syscon_regmap_lookup_by_phandle_optional(node, "mediatek,infracfg");
+	if (IS_ERR(pd->infracfg))
+		return ERR_CAST(pd->infracfg);
+
+	smi_node = of_parse_phandle(node, "mediatek,smi", 0);
+	if (smi_node) {
+		pd->smi = device_node_to_regmap(smi_node);
+		of_node_put(smi_node);
+		if (IS_ERR(pd->smi))
+			return ERR_CAST(pd->smi);
+	}
+
+	num_clks = of_clk_get_parent_count(node);
+	if (num_clks > 0) {
+		/* Calculate number of subsys_clks */
+		of_property_for_each_string(node, "clock-names", prop, clk_name) {
+			char *subsys;
+
+			subsys = strchr(clk_name, '-');
+			if (subsys)
+				pd->num_subsys_clks++;
+			else
+				pd->num_clks++;
+		}
+
+		pd->clks = devm_kcalloc(scpsys->dev, pd->num_clks, sizeof(*pd->clks), GFP_KERNEL);
+		if (!pd->clks)
+			return ERR_PTR(-ENOMEM);
+
+		pd->subsys_clks = devm_kcalloc(scpsys->dev, pd->num_subsys_clks,
+					       sizeof(*pd->subsys_clks), GFP_KERNEL);
+		if (!pd->subsys_clks)
+			return ERR_PTR(-ENOMEM);
+
+	}
+
+	for (i = 0; i < pd->num_clks; i++) {
+		clk = of_clk_get(node, i);
+		if (IS_ERR(clk)) {
+			ret = PTR_ERR(clk);
+			dev_err_probe(scpsys->dev, ret,
+				      "%pOF: failed to get clk at index %d\n", node, i);
+			goto err_put_clocks;
+		}
+
+		pd->clks[clk_ind++].clk = clk;
+	}
+
+	for (i = 0; i < pd->num_subsys_clks; i++) {
+		clk = of_clk_get(node, i + clk_ind);
+		if (IS_ERR(clk)) {
+			ret = PTR_ERR(clk);
+			dev_err_probe(scpsys->dev, ret,
+				      "%pOF: failed to get clk at index %d\n", node,
+				      i + clk_ind);
+			goto err_put_subsys_clocks;
+		}
+
+		pd->subsys_clks[i].clk = clk;
+	}
+
+	/*
+	 * Initially turn on all domains to make the domains usable
+	 * with !CONFIG_PM and to get the hardware in sync with the
+	 * software.  The unused domains will be switched off during
+	 * late_init time.
+	 */
+	if (MTK_SCPD_CAPS(pd, MTK_SCPD_KEEP_DEFAULT_OFF)) {
+		if (scpsys_domain_is_on(pd))
+			dev_warn(scpsys->dev,
+				 "%pOF: A default off power domain has been ON\n", node);
+	} else {
+		ret = scpsys_power_on(&pd->genpd);
+		if (ret < 0) {
+			dev_err(scpsys->dev, "%pOF: failed to power on domain: %d\n", node, ret);
+			goto err_put_subsys_clocks;
+		}
+
+		if (MTK_SCPD_CAPS(pd, MTK_SCPD_ALWAYS_ON))
+			pd->genpd.flags |= GENPD_FLAG_ALWAYS_ON;
+	}
+
+	if (scpsys->domains[id]) {
+		ret = -EINVAL;
+		dev_err(scpsys->dev,
+			"power domain with id %d already exists, check your device-tree\n", id);
+		goto err_put_subsys_clocks;
+	}
+
+	if (!pd->data->name)
+		pd->genpd.name = node->name;
+	else
+		pd->genpd.name = pd->data->name;
+
+	pd->genpd.power_off = scpsys_power_off;
+	pd->genpd.power_on = scpsys_power_on;
+
+	if (MTK_SCPD_CAPS(pd, MTK_SCPD_ACTIVE_WAKEUP))
+		pd->genpd.flags |= GENPD_FLAG_ACTIVE_WAKEUP;
+
+	if (MTK_SCPD_CAPS(pd, MTK_SCPD_KEEP_DEFAULT_OFF))
+		pm_genpd_init(&pd->genpd, NULL, true);
+	else
+		pm_genpd_init(&pd->genpd, NULL, false);
+
+	scpsys->domains[id] = &pd->genpd;
+
+	return scpsys->pd_data.domains[id];
+
+err_put_subsys_clocks:
+	clk_bulk_put(pd->num_subsys_clks, pd->subsys_clks);
+err_put_clocks:
+	clk_bulk_put(pd->num_clks, pd->clks);
+	return ERR_PTR(ret);
+}
+
+static int scpsys_add_subdomain(struct scpsys *scpsys, struct device_node *parent)
+{
+	struct generic_pm_domain *child_pd, *parent_pd;
+	struct device_node *child;
+	int ret;
+
+	for_each_child_of_node(parent, child) {
+		u32 id;
+
+		ret = of_property_read_u32(parent, "reg", &id);
+		if (ret) {
+			dev_err(scpsys->dev, "%pOF: failed to get parent domain id\n", child);
+			goto err_put_node;
+		}
+
+		if (!scpsys->pd_data.domains[id]) {
+			ret = -EINVAL;
+			dev_err(scpsys->dev, "power domain with id %d does not exist\n", id);
+			goto err_put_node;
+		}
+
+		parent_pd = scpsys->pd_data.domains[id];
+
+		child_pd = scpsys_add_one_domain(scpsys, child);
+		if (IS_ERR(child_pd)) {
+			ret = PTR_ERR(child_pd);
+			dev_err_probe(scpsys->dev, ret, "%pOF: failed to get child domain id\n",
+				      child);
+			goto err_put_node;
+		}
+
+		ret = pm_genpd_add_subdomain(parent_pd, child_pd);
+		if (ret) {
+			dev_err(scpsys->dev, "failed to add %s subdomain to parent %s\n",
+				child_pd->name, parent_pd->name);
+			goto err_put_node;
+		} else {
+			dev_dbg(scpsys->dev, "%s add subdomain: %s\n", parent_pd->name,
+				child_pd->name);
+		}
+
+		/* recursive call to add all subdomains */
+		ret = scpsys_add_subdomain(scpsys, child);
+		if (ret)
+			goto err_put_node;
+	}
+
+	return 0;
+
+err_put_node:
+	of_node_put(child);
+	return ret;
+}
+
+static void scpsys_remove_one_domain(struct scpsys_domain *pd)
+{
+	int ret;
+
+	if (scpsys_domain_is_on(pd))
+		scpsys_power_off(&pd->genpd);
+
+	/*
+	 * We're in the error cleanup already, so we only complain,
+	 * but won't emit another error on top of the original one.
+	 */
+	ret = pm_genpd_remove(&pd->genpd);
+	if (ret < 0)
+		dev_err(pd->scpsys->dev,
+			"failed to remove domain '%s' : %d - state may be inconsistent\n",
+			pd->genpd.name, ret);
+
+	clk_bulk_put(pd->num_clks, pd->clks);
+	clk_bulk_put(pd->num_subsys_clks, pd->subsys_clks);
+}
+
+static void scpsys_domain_cleanup(struct scpsys *scpsys)
+{
+	struct generic_pm_domain *genpd;
+	struct scpsys_domain *pd;
+	int i;
+
+	for (i = scpsys->pd_data.num_domains - 1; i >= 0; i--) {
+		genpd = scpsys->pd_data.domains[i];
+		if (genpd) {
+			pd = to_scpsys_domain(genpd);
+			scpsys_remove_one_domain(pd);
+		}
+	}
+}
+
+static const struct of_device_id scpsys_of_match[] = {
+	{
+		.compatible = "mediatek,mt6795-power-controller",
+		.data = &mt6795_scpsys_data,
+	},
+	{
+		.compatible = "mediatek,mt8167-power-controller",
+		.data = &mt8167_scpsys_data,
+	},
+	{
+		.compatible = "mediatek,mt8173-power-controller",
+		.data = &mt8173_scpsys_data,
+	},
+	{
+		.compatible = "mediatek,mt8183-power-controller",
+		.data = &mt8183_scpsys_data,
+	},
+	{
+		.compatible = "mediatek,mt8186-power-controller",
+		.data = &mt8186_scpsys_data,
+	},
+	{
+		.compatible = "mediatek,mt8192-power-controller",
+		.data = &mt8192_scpsys_data,
+	},
+	{
+		.compatible = "mediatek,mt8195-power-controller",
+		.data = &mt8195_scpsys_data,
+	},
+	{ }
+};
+
+static int scpsys_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	const struct scpsys_soc_data *soc;
+	struct device_node *node;
+	struct device *parent;
+	struct scpsys *scpsys;
+	int ret;
+
+	soc = of_device_get_match_data(&pdev->dev);
+	if (!soc) {
+		dev_err(&pdev->dev, "no power controller data\n");
+		return -EINVAL;
+	}
+
+	scpsys = devm_kzalloc(dev, struct_size(scpsys, domains, soc->num_domains), GFP_KERNEL);
+	if (!scpsys)
+		return -ENOMEM;
+
+	scpsys->dev = dev;
+	scpsys->soc_data = soc;
+
+	scpsys->pd_data.domains = scpsys->domains;
+	scpsys->pd_data.num_domains = soc->num_domains;
+
+	parent = dev->parent;
+	if (!parent) {
+		dev_err(dev, "no parent for syscon devices\n");
+		return -ENODEV;
+	}
+
+	scpsys->base = syscon_node_to_regmap(parent->of_node);
+	if (IS_ERR(scpsys->base)) {
+		dev_err(dev, "no regmap available\n");
+		return PTR_ERR(scpsys->base);
+	}
+
+	ret = -ENODEV;
+	for_each_available_child_of_node(np, node) {
+		struct generic_pm_domain *domain;
+
+		domain = scpsys_add_one_domain(scpsys, node);
+		if (IS_ERR(domain)) {
+			ret = PTR_ERR(domain);
+			of_node_put(node);
+			goto err_cleanup_domains;
+		}
+
+		ret = scpsys_add_subdomain(scpsys, node);
+		if (ret) {
+			of_node_put(node);
+			goto err_cleanup_domains;
+		}
+	}
+
+	if (ret) {
+		dev_dbg(dev, "no power domains present\n");
+		return ret;
+	}
+
+	ret = of_genpd_add_provider_onecell(np, &scpsys->pd_data);
+	if (ret) {
+		dev_err(dev, "failed to add provider: %d\n", ret);
+		goto err_cleanup_domains;
+	}
+
+	return 0;
+
+err_cleanup_domains:
+	scpsys_domain_cleanup(scpsys);
+	return ret;
+}
+
+static struct platform_driver scpsys_pm_domain_driver = {
+	.probe = scpsys_probe,
+	.driver = {
+		.name = "mtk-power-controller",
+		.suppress_bind_attrs = true,
+		.of_match_table = scpsys_of_match,
+	},
+};
+builtin_platform_driver(scpsys_pm_domain_driver);