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, 634 insertions, 0 deletions

diff --git a/drivers/cpuidle/cpuidle-riscv-sbi.c b/drivers/cpuidle/cpuidle-riscv-sbi.c
new file mode 100644
index 000000000..be383f4b6
--- /dev/null
+++ b/drivers/cpuidle/cpuidle-riscv-sbi.c
@@ -0,0 +1,634 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * RISC-V SBI CPU idle driver.
+ *
+ * Copyright (c) 2021 Western Digital Corporation or its affiliates.
+ * Copyright (c) 2022 Ventana Micro Systems Inc.
+ */
+
+#define pr_fmt(fmt) "cpuidle-riscv-sbi: " fmt
+
+#include <linux/cpuidle.h>
+#include <linux/cpumask.h>
+#include <linux/cpu_pm.h>
+#include <linux/cpu_cooling.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/slab.h>
+#include <linux/platform_device.h>
+#include <linux/pm_domain.h>
+#include <linux/pm_runtime.h>
+#include <asm/cpuidle.h>
+#include <asm/sbi.h>
+#include <asm/smp.h>
+#include <asm/suspend.h>
+
+#include "dt_idle_states.h"
+#include "dt_idle_genpd.h"
+
+struct sbi_cpuidle_data {
+	u32 *states;
+	struct device *dev;
+};
+
+struct sbi_domain_state {
+	bool available;
+	u32 state;
+};
+
+static DEFINE_PER_CPU_READ_MOSTLY(struct sbi_cpuidle_data, sbi_cpuidle_data);
+static DEFINE_PER_CPU(struct sbi_domain_state, domain_state);
+static bool sbi_cpuidle_use_osi;
+static bool sbi_cpuidle_use_cpuhp;
+static bool sbi_cpuidle_pd_allow_domain_state;
+
+static inline void sbi_set_domain_state(u32 state)
+{
+	struct sbi_domain_state *data = this_cpu_ptr(&domain_state);
+
+	data->available = true;
+	data->state = state;
+}
+
+static inline u32 sbi_get_domain_state(void)
+{
+	struct sbi_domain_state *data = this_cpu_ptr(&domain_state);
+
+	return data->state;
+}
+
+static inline void sbi_clear_domain_state(void)
+{
+	struct sbi_domain_state *data = this_cpu_ptr(&domain_state);
+
+	data->available = false;
+}
+
+static inline bool sbi_is_domain_state_available(void)
+{
+	struct sbi_domain_state *data = this_cpu_ptr(&domain_state);
+
+	return data->available;
+}
+
+static int sbi_suspend_finisher(unsigned long suspend_type,
+				unsigned long resume_addr,
+				unsigned long opaque)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_HSM, SBI_EXT_HSM_HART_SUSPEND,
+			suspend_type, resume_addr, opaque, 0, 0, 0);
+
+	return (ret.error) ? sbi_err_map_linux_errno(ret.error) : 0;
+}
+
+static int sbi_suspend(u32 state)
+{
+	if (state & SBI_HSM_SUSP_NON_RET_BIT)
+		return cpu_suspend(state, sbi_suspend_finisher);
+	else
+		return sbi_suspend_finisher(state, 0, 0);
+}
+
+static __cpuidle int sbi_cpuidle_enter_state(struct cpuidle_device *dev,
+					     struct cpuidle_driver *drv, int idx)
+{
+	u32 *states = __this_cpu_read(sbi_cpuidle_data.states);
+	u32 state = states[idx];
+
+	if (state & SBI_HSM_SUSP_NON_RET_BIT)
+		return CPU_PM_CPU_IDLE_ENTER_PARAM(sbi_suspend, idx, state);
+	else
+		return CPU_PM_CPU_IDLE_ENTER_RETENTION_PARAM(sbi_suspend,
+							     idx, state);
+}
+
+static __cpuidle int __sbi_enter_domain_idle_state(struct cpuidle_device *dev,
+						   struct cpuidle_driver *drv, int idx,
+						   bool s2idle)
+{
+	struct sbi_cpuidle_data *data = this_cpu_ptr(&sbi_cpuidle_data);
+	u32 *states = data->states;
+	struct device *pd_dev = data->dev;
+	u32 state;
+	int ret;
+
+	ret = cpu_pm_enter();
+	if (ret)
+		return -1;
+
+	/* Do runtime PM to manage a hierarchical CPU toplogy. */
+	if (s2idle)
+		dev_pm_genpd_suspend(pd_dev);
+	else
+		pm_runtime_put_sync_suspend(pd_dev);
+
+	ct_cpuidle_enter();
+
+	if (sbi_is_domain_state_available())
+		state = sbi_get_domain_state();
+	else
+		state = states[idx];
+
+	ret = sbi_suspend(state) ? -1 : idx;
+
+	ct_cpuidle_exit();
+
+	if (s2idle)
+		dev_pm_genpd_resume(pd_dev);
+	else
+		pm_runtime_get_sync(pd_dev);
+
+	cpu_pm_exit();
+
+	/* Clear the domain state to start fresh when back from idle. */
+	sbi_clear_domain_state();
+	return ret;
+}
+
+static int sbi_enter_domain_idle_state(struct cpuidle_device *dev,
+				       struct cpuidle_driver *drv, int idx)
+{
+	return __sbi_enter_domain_idle_state(dev, drv, idx, false);
+}
+
+static int sbi_enter_s2idle_domain_idle_state(struct cpuidle_device *dev,
+					      struct cpuidle_driver *drv,
+					      int idx)
+{
+	return __sbi_enter_domain_idle_state(dev, drv, idx, true);
+}
+
+static int sbi_cpuidle_cpuhp_up(unsigned int cpu)
+{
+	struct device *pd_dev = __this_cpu_read(sbi_cpuidle_data.dev);
+
+	if (pd_dev)
+		pm_runtime_get_sync(pd_dev);
+
+	return 0;
+}
+
+static int sbi_cpuidle_cpuhp_down(unsigned int cpu)
+{
+	struct device *pd_dev = __this_cpu_read(sbi_cpuidle_data.dev);
+
+	if (pd_dev) {
+		pm_runtime_put_sync(pd_dev);
+		/* Clear domain state to start fresh at next online. */
+		sbi_clear_domain_state();
+	}
+
+	return 0;
+}
+
+static void sbi_idle_init_cpuhp(void)
+{
+	int err;
+
+	if (!sbi_cpuidle_use_cpuhp)
+		return;
+
+	err = cpuhp_setup_state_nocalls(CPUHP_AP_CPU_PM_STARTING,
+					"cpuidle/sbi:online",
+					sbi_cpuidle_cpuhp_up,
+					sbi_cpuidle_cpuhp_down);
+	if (err)
+		pr_warn("Failed %d while setup cpuhp state\n", err);
+}
+
+static const struct of_device_id sbi_cpuidle_state_match[] = {
+	{ .compatible = "riscv,idle-state",
+	  .data = sbi_cpuidle_enter_state },
+	{ },
+};
+
+static bool sbi_suspend_state_is_valid(u32 state)
+{
+	if (state > SBI_HSM_SUSPEND_RET_DEFAULT &&
+	    state < SBI_HSM_SUSPEND_RET_PLATFORM)
+		return false;
+	if (state > SBI_HSM_SUSPEND_NON_RET_DEFAULT &&
+	    state < SBI_HSM_SUSPEND_NON_RET_PLATFORM)
+		return false;
+	return true;
+}
+
+static int sbi_dt_parse_state_node(struct device_node *np, u32 *state)
+{
+	int err = of_property_read_u32(np, "riscv,sbi-suspend-param", state);
+
+	if (err) {
+		pr_warn("%pOF missing riscv,sbi-suspend-param property\n", np);
+		return err;
+	}
+
+	if (!sbi_suspend_state_is_valid(*state)) {
+		pr_warn("Invalid SBI suspend state %#x\n", *state);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int sbi_dt_cpu_init_topology(struct cpuidle_driver *drv,
+				     struct sbi_cpuidle_data *data,
+				     unsigned int state_count, int cpu)
+{
+	/* Currently limit the hierarchical topology to be used in OSI mode. */
+	if (!sbi_cpuidle_use_osi)
+		return 0;
+
+	data->dev = dt_idle_attach_cpu(cpu, "sbi");
+	if (IS_ERR_OR_NULL(data->dev))
+		return PTR_ERR_OR_ZERO(data->dev);
+
+	/*
+	 * Using the deepest state for the CPU to trigger a potential selection
+	 * of a shared state for the domain, assumes the domain states are all
+	 * deeper states.
+	 */
+	drv->states[state_count - 1].flags |= CPUIDLE_FLAG_RCU_IDLE;
+	drv->states[state_count - 1].enter = sbi_enter_domain_idle_state;
+	drv->states[state_count - 1].enter_s2idle =
+					sbi_enter_s2idle_domain_idle_state;
+	sbi_cpuidle_use_cpuhp = true;
+
+	return 0;
+}
+
+static int sbi_cpuidle_dt_init_states(struct device *dev,
+					struct cpuidle_driver *drv,
+					unsigned int cpu,
+					unsigned int state_count)
+{
+	struct sbi_cpuidle_data *data = per_cpu_ptr(&sbi_cpuidle_data, cpu);
+	struct device_node *state_node;
+	struct device_node *cpu_node;
+	u32 *states;
+	int i, ret;
+
+	cpu_node = of_cpu_device_node_get(cpu);
+	if (!cpu_node)
+		return -ENODEV;
+
+	states = devm_kcalloc(dev, state_count, sizeof(*states), GFP_KERNEL);
+	if (!states) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	/* Parse SBI specific details from state DT nodes */
+	for (i = 1; i < state_count; i++) {
+		state_node = of_get_cpu_state_node(cpu_node, i - 1);
+		if (!state_node)
+			break;
+
+		ret = sbi_dt_parse_state_node(state_node, &states[i]);
+		of_node_put(state_node);
+
+		if (ret)
+			return ret;
+
+		pr_debug("sbi-state %#x index %d\n", states[i], i);
+	}
+	if (i != state_count) {
+		ret = -ENODEV;
+		goto fail;
+	}
+
+	/* Initialize optional data, used for the hierarchical topology. */
+	ret = sbi_dt_cpu_init_topology(drv, data, state_count, cpu);
+	if (ret < 0)
+		return ret;
+
+	/* Store states in the per-cpu struct. */
+	data->states = states;
+
+fail:
+	of_node_put(cpu_node);
+
+	return ret;
+}
+
+static void sbi_cpuidle_deinit_cpu(int cpu)
+{
+	struct sbi_cpuidle_data *data = per_cpu_ptr(&sbi_cpuidle_data, cpu);
+
+	dt_idle_detach_cpu(data->dev);
+	sbi_cpuidle_use_cpuhp = false;
+}
+
+static int sbi_cpuidle_init_cpu(struct device *dev, int cpu)
+{
+	struct cpuidle_driver *drv;
+	unsigned int state_count = 0;
+	int ret = 0;
+
+	drv = devm_kzalloc(dev, sizeof(*drv), GFP_KERNEL);
+	if (!drv)
+		return -ENOMEM;
+
+	drv->name = "sbi_cpuidle";
+	drv->owner = THIS_MODULE;
+	drv->cpumask = (struct cpumask *)cpumask_of(cpu);
+
+	/* RISC-V architectural WFI to be represented as state index 0. */
+	drv->states[0].enter = sbi_cpuidle_enter_state;
+	drv->states[0].exit_latency = 1;
+	drv->states[0].target_residency = 1;
+	drv->states[0].power_usage = UINT_MAX;
+	strcpy(drv->states[0].name, "WFI");
+	strcpy(drv->states[0].desc, "RISC-V WFI");
+
+	/*
+	 * If no DT idle states are detected (ret == 0) let the driver
+	 * initialization fail accordingly since there is no reason to
+	 * initialize the idle driver if only wfi is supported, the
+	 * default archictectural back-end already executes wfi
+	 * on idle entry.
+	 */
+	ret = dt_init_idle_driver(drv, sbi_cpuidle_state_match, 1);
+	if (ret <= 0) {
+		pr_debug("HART%ld: failed to parse DT idle states\n",
+			 cpuid_to_hartid_map(cpu));
+		return ret ? : -ENODEV;
+	}
+	state_count = ret + 1; /* Include WFI state as well */
+
+	/* Initialize idle states from DT. */
+	ret = sbi_cpuidle_dt_init_states(dev, drv, cpu, state_count);
+	if (ret) {
+		pr_err("HART%ld: failed to init idle states\n",
+		       cpuid_to_hartid_map(cpu));
+		return ret;
+	}
+
+	ret = cpuidle_register(drv, NULL);
+	if (ret)
+		goto deinit;
+
+	cpuidle_cooling_register(drv);
+
+	return 0;
+deinit:
+	sbi_cpuidle_deinit_cpu(cpu);
+	return ret;
+}
+
+static void sbi_cpuidle_domain_sync_state(struct device *dev)
+{
+	/*
+	 * All devices have now been attached/probed to the PM domain
+	 * topology, hence it's fine to allow domain states to be picked.
+	 */
+	sbi_cpuidle_pd_allow_domain_state = true;
+}
+
+#ifdef CONFIG_DT_IDLE_GENPD
+
+static int sbi_cpuidle_pd_power_off(struct generic_pm_domain *pd)
+{
+	struct genpd_power_state *state = &pd->states[pd->state_idx];
+	u32 *pd_state;
+
+	if (!state->data)
+		return 0;
+
+	if (!sbi_cpuidle_pd_allow_domain_state)
+		return -EBUSY;
+
+	/* OSI mode is enabled, set the corresponding domain state. */
+	pd_state = state->data;
+	sbi_set_domain_state(*pd_state);
+
+	return 0;
+}
+
+struct sbi_pd_provider {
+	struct list_head link;
+	struct device_node *node;
+};
+
+static LIST_HEAD(sbi_pd_providers);
+
+static int sbi_pd_init(struct device_node *np)
+{
+	struct generic_pm_domain *pd;
+	struct sbi_pd_provider *pd_provider;
+	struct dev_power_governor *pd_gov;
+	int ret = -ENOMEM;
+
+	pd = dt_idle_pd_alloc(np, sbi_dt_parse_state_node);
+	if (!pd)
+		goto out;
+
+	pd_provider = kzalloc(sizeof(*pd_provider), GFP_KERNEL);
+	if (!pd_provider)
+		goto free_pd;
+
+	pd->flags |= GENPD_FLAG_IRQ_SAFE | GENPD_FLAG_CPU_DOMAIN;
+
+	/* Allow power off when OSI is available. */
+	if (sbi_cpuidle_use_osi)
+		pd->power_off = sbi_cpuidle_pd_power_off;
+	else
+		pd->flags |= GENPD_FLAG_ALWAYS_ON;
+
+	/* Use governor for CPU PM domains if it has some states to manage. */
+	pd_gov = pd->states ? &pm_domain_cpu_gov : NULL;
+
+	ret = pm_genpd_init(pd, pd_gov, false);
+	if (ret)
+		goto free_pd_prov;
+
+	ret = of_genpd_add_provider_simple(np, pd);
+	if (ret)
+		goto remove_pd;
+
+	pd_provider->node = of_node_get(np);
+	list_add(&pd_provider->link, &sbi_pd_providers);
+
+	pr_debug("init PM domain %s\n", pd->name);
+	return 0;
+
+remove_pd:
+	pm_genpd_remove(pd);
+free_pd_prov:
+	kfree(pd_provider);
+free_pd:
+	dt_idle_pd_free(pd);
+out:
+	pr_err("failed to init PM domain ret=%d %pOF\n", ret, np);
+	return ret;
+}
+
+static void sbi_pd_remove(void)
+{
+	struct sbi_pd_provider *pd_provider, *it;
+	struct generic_pm_domain *genpd;
+
+	list_for_each_entry_safe(pd_provider, it, &sbi_pd_providers, link) {
+		of_genpd_del_provider(pd_provider->node);
+
+		genpd = of_genpd_remove_last(pd_provider->node);
+		if (!IS_ERR(genpd))
+			kfree(genpd);
+
+		of_node_put(pd_provider->node);
+		list_del(&pd_provider->link);
+		kfree(pd_provider);
+	}
+}
+
+static int sbi_genpd_probe(struct device_node *np)
+{
+	struct device_node *node;
+	int ret = 0, pd_count = 0;
+
+	if (!np)
+		return -ENODEV;
+
+	/*
+	 * Parse child nodes for the "#power-domain-cells" property and
+	 * initialize a genpd/genpd-of-provider pair when it's found.
+	 */
+	for_each_child_of_node(np, node) {
+		if (!of_find_property(node, "#power-domain-cells", NULL))
+			continue;
+
+		ret = sbi_pd_init(node);
+		if (ret)
+			goto put_node;
+
+		pd_count++;
+	}
+
+	/* Bail out if not using the hierarchical CPU topology. */
+	if (!pd_count)
+		goto no_pd;
+
+	/* Link genpd masters/subdomains to model the CPU topology. */
+	ret = dt_idle_pd_init_topology(np);
+	if (ret)
+		goto remove_pd;
+
+	return 0;
+
+put_node:
+	of_node_put(node);
+remove_pd:
+	sbi_pd_remove();
+	pr_err("failed to create CPU PM domains ret=%d\n", ret);
+no_pd:
+	return ret;
+}
+
+#else
+
+static inline int sbi_genpd_probe(struct device_node *np)
+{
+	return 0;
+}
+
+#endif
+
+static int sbi_cpuidle_probe(struct platform_device *pdev)
+{
+	int cpu, ret;
+	struct cpuidle_driver *drv;
+	struct cpuidle_device *dev;
+	struct device_node *np, *pds_node;
+
+	/* Detect OSI support based on CPU DT nodes */
+	sbi_cpuidle_use_osi = true;
+	for_each_possible_cpu(cpu) {
+		np = of_cpu_device_node_get(cpu);
+		if (np &&
+		    of_find_property(np, "power-domains", NULL) &&
+		    of_find_property(np, "power-domain-names", NULL)) {
+			continue;
+		} else {
+			sbi_cpuidle_use_osi = false;
+			break;
+		}
+	}
+
+	/* Populate generic power domains from DT nodes */
+	pds_node = of_find_node_by_path("/cpus/power-domains");
+	if (pds_node) {
+		ret = sbi_genpd_probe(pds_node);
+		of_node_put(pds_node);
+		if (ret)
+			return ret;
+	}
+
+	/* Initialize CPU idle driver for each CPU */
+	for_each_possible_cpu(cpu) {
+		ret = sbi_cpuidle_init_cpu(&pdev->dev, cpu);
+		if (ret) {
+			pr_debug("HART%ld: idle driver init failed\n",
+				 cpuid_to_hartid_map(cpu));
+			goto out_fail;
+		}
+	}
+
+	/* Setup CPU hotplut notifiers */
+	sbi_idle_init_cpuhp();
+
+	pr_info("idle driver registered for all CPUs\n");
+
+	return 0;
+
+out_fail:
+	while (--cpu >= 0) {
+		dev = per_cpu(cpuidle_devices, cpu);
+		drv = cpuidle_get_cpu_driver(dev);
+		cpuidle_unregister(drv);
+		sbi_cpuidle_deinit_cpu(cpu);
+	}
+
+	return ret;
+}
+
+static struct platform_driver sbi_cpuidle_driver = {
+	.probe = sbi_cpuidle_probe,
+	.driver = {
+		.name = "sbi-cpuidle",
+		.sync_state = sbi_cpuidle_domain_sync_state,
+	},
+};
+
+static int __init sbi_cpuidle_init(void)
+{
+	int ret;
+	struct platform_device *pdev;
+
+	/*
+	 * The SBI HSM suspend function is only available when:
+	 * 1) SBI version is 0.3 or higher
+	 * 2) SBI HSM extension is available
+	 */
+	if ((sbi_spec_version < sbi_mk_version(0, 3)) ||
+	    sbi_probe_extension(SBI_EXT_HSM) <= 0) {
+		pr_info("HSM suspend not available\n");
+		return 0;
+	}
+
+	ret = platform_driver_register(&sbi_cpuidle_driver);
+	if (ret)
+		return ret;
+
+	pdev = platform_device_register_simple("sbi-cpuidle",
+						-1, NULL, 0);
+	if (IS_ERR(pdev)) {
+		platform_driver_unregister(&sbi_cpuidle_driver);
+		return PTR_ERR(pdev);
+	}
+
+	return 0;
+}
+device_initcall(sbi_cpuidle_init);