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, 560 insertions, 0 deletions

diff --git a/drivers/soc/tegra/regulators-tegra20.c b/drivers/soc/tegra/regulators-tegra20.c
new file mode 100644
index 000000000..6a2f90ab9
--- /dev/null
+++ b/drivers/soc/tegra/regulators-tegra20.c
@@ -0,0 +1,560 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Voltage regulators coupler for NVIDIA Tegra20
+ * Copyright (C) 2019 GRATE-DRIVER project
+ *
+ * Voltage constraints borrowed from downstream kernel sources
+ * Copyright (C) 2010-2011 NVIDIA Corporation
+ */
+
+#define pr_fmt(fmt)	"tegra voltage-coupler: " fmt
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/reboot.h>
+#include <linux/regulator/coupler.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/machine.h>
+#include <linux/suspend.h>
+
+#include <soc/tegra/fuse.h>
+#include <soc/tegra/pmc.h>
+
+struct tegra_regulator_coupler {
+	struct regulator_coupler coupler;
+	struct regulator_dev *core_rdev;
+	struct regulator_dev *cpu_rdev;
+	struct regulator_dev *rtc_rdev;
+	struct notifier_block reboot_notifier;
+	struct notifier_block suspend_notifier;
+	int core_min_uV, cpu_min_uV;
+	bool sys_reboot_mode_req;
+	bool sys_reboot_mode;
+	bool sys_suspend_mode_req;
+	bool sys_suspend_mode;
+};
+
+static inline struct tegra_regulator_coupler *
+to_tegra_coupler(struct regulator_coupler *coupler)
+{
+	return container_of(coupler, struct tegra_regulator_coupler, coupler);
+}
+
+static int tegra20_core_limit(struct tegra_regulator_coupler *tegra,
+			      struct regulator_dev *core_rdev)
+{
+	int core_min_uV = 0;
+	int core_max_uV;
+	int core_cur_uV;
+	int err;
+
+	/*
+	 * Tegra20 SoC has critical DVFS-capable devices that are
+	 * permanently-active or active at a boot time, like EMC
+	 * (DRAM controller) or Display controller for example.
+	 *
+	 * The voltage of a CORE SoC power domain shall not be dropped below
+	 * a minimum level, which is determined by device's clock rate.
+	 * This means that we can't fully allow CORE voltage scaling until
+	 * the state of all DVFS-critical CORE devices is synced.
+	 */
+	if (tegra_pmc_core_domain_state_synced() && !tegra->sys_reboot_mode) {
+		pr_info_once("voltage state synced\n");
+		return 0;
+	}
+
+	if (tegra->core_min_uV > 0)
+		return tegra->core_min_uV;
+
+	core_cur_uV = regulator_get_voltage_rdev(core_rdev);
+	if (core_cur_uV < 0)
+		return core_cur_uV;
+
+	core_max_uV = max(core_cur_uV, 1200000);
+
+	err = regulator_check_voltage(core_rdev, &core_min_uV, &core_max_uV);
+	if (err)
+		return err;
+
+	/*
+	 * Limit minimum CORE voltage to a value left from bootloader or,
+	 * if it's unreasonably low value, to the most common 1.2v or to
+	 * whatever maximum value defined via board's device-tree.
+	 */
+	tegra->core_min_uV = core_max_uV;
+
+	pr_info("core voltage initialized to %duV\n", tegra->core_min_uV);
+
+	return tegra->core_min_uV;
+}
+
+static int tegra20_core_rtc_max_spread(struct regulator_dev *core_rdev,
+				       struct regulator_dev *rtc_rdev)
+{
+	struct coupling_desc *c_desc = &core_rdev->coupling_desc;
+	struct regulator_dev *rdev;
+	int max_spread;
+	unsigned int i;
+
+	for (i = 1; i < c_desc->n_coupled; i++) {
+		max_spread = core_rdev->constraints->max_spread[i - 1];
+		rdev = c_desc->coupled_rdevs[i];
+
+		if (rdev == rtc_rdev && max_spread)
+			return max_spread;
+	}
+
+	pr_err_once("rtc-core max-spread is undefined in device-tree\n");
+
+	return 150000;
+}
+
+static int tegra20_cpu_nominal_uV(void)
+{
+	switch (tegra_sku_info.soc_speedo_id) {
+	case 0:
+		return 1100000;
+	case 1:
+		return 1025000;
+	default:
+		return 1125000;
+	}
+}
+
+static int tegra20_core_nominal_uV(void)
+{
+	switch (tegra_sku_info.soc_speedo_id) {
+	default:
+		return 1225000;
+	case 2:
+		return 1300000;
+	}
+}
+
+static int tegra20_core_rtc_update(struct tegra_regulator_coupler *tegra,
+				   struct regulator_dev *core_rdev,
+				   struct regulator_dev *rtc_rdev,
+				   int cpu_uV, int cpu_min_uV)
+{
+	int core_min_uV, core_max_uV = INT_MAX;
+	int rtc_min_uV, rtc_max_uV = INT_MAX;
+	int core_target_uV;
+	int rtc_target_uV;
+	int max_spread;
+	int core_uV;
+	int rtc_uV;
+	int err;
+
+	/*
+	 * RTC and CORE voltages should be no more than 170mV from each other,
+	 * CPU should be below RTC and CORE by at least 120mV. This applies
+	 * to all Tegra20 SoC's.
+	 */
+	max_spread = tegra20_core_rtc_max_spread(core_rdev, rtc_rdev);
+
+	/*
+	 * The core voltage scaling is currently not hooked up in drivers,
+	 * hence we will limit the minimum core voltage to a reasonable value.
+	 * This should be good enough for the time being.
+	 */
+	core_min_uV = tegra20_core_limit(tegra, core_rdev);
+	if (core_min_uV < 0)
+		return core_min_uV;
+
+	err = regulator_check_voltage(core_rdev, &core_min_uV, &core_max_uV);
+	if (err)
+		return err;
+
+	err = regulator_check_consumers(core_rdev, &core_min_uV, &core_max_uV,
+					PM_SUSPEND_ON);
+	if (err)
+		return err;
+
+	/* prepare voltage level for suspend */
+	if (tegra->sys_suspend_mode)
+		core_min_uV = clamp(tegra20_core_nominal_uV(),
+				    core_min_uV, core_max_uV);
+
+	core_uV = regulator_get_voltage_rdev(core_rdev);
+	if (core_uV < 0)
+		return core_uV;
+
+	core_min_uV = max(cpu_min_uV + 125000, core_min_uV);
+	if (core_min_uV > core_max_uV)
+		return -EINVAL;
+
+	if (cpu_uV + 120000 > core_uV)
+		pr_err("core-cpu voltage constraint violated: %d %d\n",
+		       core_uV, cpu_uV + 120000);
+
+	rtc_uV = regulator_get_voltage_rdev(rtc_rdev);
+	if (rtc_uV < 0)
+		return rtc_uV;
+
+	if (cpu_uV + 120000 > rtc_uV)
+		pr_err("rtc-cpu voltage constraint violated: %d %d\n",
+		       rtc_uV, cpu_uV + 120000);
+
+	if (abs(core_uV - rtc_uV) > 170000)
+		pr_err("core-rtc voltage constraint violated: %d %d\n",
+		       core_uV, rtc_uV);
+
+	rtc_min_uV = max(cpu_min_uV + 125000, core_min_uV - max_spread);
+
+	err = regulator_check_voltage(rtc_rdev, &rtc_min_uV, &rtc_max_uV);
+	if (err)
+		return err;
+
+	while (core_uV != core_min_uV || rtc_uV != rtc_min_uV) {
+		if (core_uV < core_min_uV) {
+			core_target_uV = min(core_uV + max_spread, core_min_uV);
+			core_target_uV = min(rtc_uV + max_spread, core_target_uV);
+		} else {
+			core_target_uV = max(core_uV - max_spread, core_min_uV);
+			core_target_uV = max(rtc_uV - max_spread, core_target_uV);
+		}
+
+		if (core_uV == core_target_uV)
+			goto update_rtc;
+
+		err = regulator_set_voltage_rdev(core_rdev,
+						 core_target_uV,
+						 core_max_uV,
+						 PM_SUSPEND_ON);
+		if (err)
+			return err;
+
+		core_uV = core_target_uV;
+update_rtc:
+		if (rtc_uV < rtc_min_uV) {
+			rtc_target_uV = min(rtc_uV + max_spread, rtc_min_uV);
+			rtc_target_uV = min(core_uV + max_spread, rtc_target_uV);
+		} else {
+			rtc_target_uV = max(rtc_uV - max_spread, rtc_min_uV);
+			rtc_target_uV = max(core_uV - max_spread, rtc_target_uV);
+		}
+
+		if (rtc_uV == rtc_target_uV)
+			continue;
+
+		err = regulator_set_voltage_rdev(rtc_rdev,
+						 rtc_target_uV,
+						 rtc_max_uV,
+						 PM_SUSPEND_ON);
+		if (err)
+			return err;
+
+		rtc_uV = rtc_target_uV;
+	}
+
+	return 0;
+}
+
+static int tegra20_core_voltage_update(struct tegra_regulator_coupler *tegra,
+				       struct regulator_dev *cpu_rdev,
+				       struct regulator_dev *core_rdev,
+				       struct regulator_dev *rtc_rdev)
+{
+	int cpu_uV;
+
+	cpu_uV = regulator_get_voltage_rdev(cpu_rdev);
+	if (cpu_uV < 0)
+		return cpu_uV;
+
+	return tegra20_core_rtc_update(tegra, core_rdev, rtc_rdev,
+				       cpu_uV, cpu_uV);
+}
+
+static int tegra20_cpu_voltage_update(struct tegra_regulator_coupler *tegra,
+				      struct regulator_dev *cpu_rdev,
+				      struct regulator_dev *core_rdev,
+				      struct regulator_dev *rtc_rdev)
+{
+	int cpu_min_uV_consumers = 0;
+	int cpu_max_uV = INT_MAX;
+	int cpu_min_uV = 0;
+	int cpu_uV;
+	int err;
+
+	err = regulator_check_voltage(cpu_rdev, &cpu_min_uV, &cpu_max_uV);
+	if (err)
+		return err;
+
+	err = regulator_check_consumers(cpu_rdev, &cpu_min_uV, &cpu_max_uV,
+					PM_SUSPEND_ON);
+	if (err)
+		return err;
+
+	err = regulator_check_consumers(cpu_rdev, &cpu_min_uV_consumers,
+					&cpu_max_uV, PM_SUSPEND_ON);
+	if (err)
+		return err;
+
+	cpu_uV = regulator_get_voltage_rdev(cpu_rdev);
+	if (cpu_uV < 0)
+		return cpu_uV;
+
+	/* store boot voltage level */
+	if (!tegra->cpu_min_uV)
+		tegra->cpu_min_uV = cpu_uV;
+
+	/*
+	 * CPU's regulator may not have any consumers, hence the voltage
+	 * must not be changed in that case because CPU simply won't
+	 * survive the voltage drop if it's running on a higher frequency.
+	 */
+	if (!cpu_min_uV_consumers)
+		cpu_min_uV = cpu_uV;
+
+	/* restore boot voltage level */
+	if (tegra->sys_reboot_mode)
+		cpu_min_uV = max(cpu_min_uV, tegra->cpu_min_uV);
+
+	/* prepare voltage level for suspend */
+	if (tegra->sys_suspend_mode)
+		cpu_min_uV = clamp(tegra20_cpu_nominal_uV(),
+				   cpu_min_uV, cpu_max_uV);
+
+	if (cpu_min_uV > cpu_uV) {
+		err = tegra20_core_rtc_update(tegra, core_rdev, rtc_rdev,
+					      cpu_uV, cpu_min_uV);
+		if (err)
+			return err;
+
+		err = regulator_set_voltage_rdev(cpu_rdev, cpu_min_uV,
+						 cpu_max_uV, PM_SUSPEND_ON);
+		if (err)
+			return err;
+	} else if (cpu_min_uV < cpu_uV)  {
+		err = regulator_set_voltage_rdev(cpu_rdev, cpu_min_uV,
+						 cpu_max_uV, PM_SUSPEND_ON);
+		if (err)
+			return err;
+
+		err = tegra20_core_rtc_update(tegra, core_rdev, rtc_rdev,
+					      cpu_uV, cpu_min_uV);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int tegra20_regulator_balance_voltage(struct regulator_coupler *coupler,
+					     struct regulator_dev *rdev,
+					     suspend_state_t state)
+{
+	struct tegra_regulator_coupler *tegra = to_tegra_coupler(coupler);
+	struct regulator_dev *core_rdev = tegra->core_rdev;
+	struct regulator_dev *cpu_rdev = tegra->cpu_rdev;
+	struct regulator_dev *rtc_rdev = tegra->rtc_rdev;
+
+	if ((core_rdev != rdev && cpu_rdev != rdev && rtc_rdev != rdev) ||
+	    state != PM_SUSPEND_ON) {
+		pr_err("regulators are not coupled properly\n");
+		return -EINVAL;
+	}
+
+	tegra->sys_reboot_mode = READ_ONCE(tegra->sys_reboot_mode_req);
+	tegra->sys_suspend_mode = READ_ONCE(tegra->sys_suspend_mode_req);
+
+	if (rdev == cpu_rdev)
+		return tegra20_cpu_voltage_update(tegra, cpu_rdev,
+						  core_rdev, rtc_rdev);
+
+	if (rdev == core_rdev)
+		return tegra20_core_voltage_update(tegra, cpu_rdev,
+						   core_rdev, rtc_rdev);
+
+	pr_err("changing %s voltage not permitted\n", rdev_get_name(rtc_rdev));
+
+	return -EPERM;
+}
+
+static int tegra20_regulator_prepare_suspend(struct tegra_regulator_coupler *tegra,
+					     bool sys_suspend_mode)
+{
+	int err;
+
+	if (!tegra->core_rdev || !tegra->rtc_rdev || !tegra->cpu_rdev)
+		return 0;
+
+	/*
+	 * All power domains are enabled early during resume from suspend
+	 * by GENPD core.  Domains like VENC may require a higher voltage
+	 * when enabled during resume from suspend.  This also prepares
+	 * hardware for resuming from LP0.
+	 */
+
+	WRITE_ONCE(tegra->sys_suspend_mode_req, sys_suspend_mode);
+
+	err = regulator_sync_voltage_rdev(tegra->cpu_rdev);
+	if (err)
+		return err;
+
+	err = regulator_sync_voltage_rdev(tegra->core_rdev);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int tegra20_regulator_suspend(struct notifier_block *notifier,
+				     unsigned long mode, void *arg)
+{
+	struct tegra_regulator_coupler *tegra;
+	int ret = 0;
+
+	tegra = container_of(notifier, struct tegra_regulator_coupler,
+			     suspend_notifier);
+
+	switch (mode) {
+	case PM_HIBERNATION_PREPARE:
+	case PM_RESTORE_PREPARE:
+	case PM_SUSPEND_PREPARE:
+		ret = tegra20_regulator_prepare_suspend(tegra, true);
+		break;
+
+	case PM_POST_HIBERNATION:
+	case PM_POST_RESTORE:
+	case PM_POST_SUSPEND:
+		ret = tegra20_regulator_prepare_suspend(tegra, false);
+		break;
+	}
+
+	if (ret)
+		pr_err("failed to prepare regulators: %d\n", ret);
+
+	return notifier_from_errno(ret);
+}
+
+static int tegra20_regulator_prepare_reboot(struct tegra_regulator_coupler *tegra,
+					    bool sys_reboot_mode)
+{
+	int err;
+
+	if (!tegra->core_rdev || !tegra->rtc_rdev || !tegra->cpu_rdev)
+		return 0;
+
+	WRITE_ONCE(tegra->sys_reboot_mode_req, true);
+
+	/*
+	 * Some devices use CPU soft-reboot method and in this case we
+	 * should ensure that voltages are sane for the reboot by restoring
+	 * the minimum boot levels.
+	 */
+	err = regulator_sync_voltage_rdev(tegra->cpu_rdev);
+	if (err)
+		return err;
+
+	err = regulator_sync_voltage_rdev(tegra->core_rdev);
+	if (err)
+		return err;
+
+	WRITE_ONCE(tegra->sys_reboot_mode_req, sys_reboot_mode);
+
+	return 0;
+}
+
+static int tegra20_regulator_reboot(struct notifier_block *notifier,
+				    unsigned long event, void *cmd)
+{
+	struct tegra_regulator_coupler *tegra;
+	int ret;
+
+	if (event != SYS_RESTART)
+		return NOTIFY_DONE;
+
+	tegra = container_of(notifier, struct tegra_regulator_coupler,
+			     reboot_notifier);
+
+	ret = tegra20_regulator_prepare_reboot(tegra, true);
+
+	return notifier_from_errno(ret);
+}
+
+static int tegra20_regulator_attach(struct regulator_coupler *coupler,
+				    struct regulator_dev *rdev)
+{
+	struct tegra_regulator_coupler *tegra = to_tegra_coupler(coupler);
+	struct device_node *np = rdev->dev.of_node;
+
+	if (of_property_read_bool(np, "nvidia,tegra-core-regulator") &&
+	    !tegra->core_rdev) {
+		tegra->core_rdev = rdev;
+		return 0;
+	}
+
+	if (of_property_read_bool(np, "nvidia,tegra-rtc-regulator") &&
+	    !tegra->rtc_rdev) {
+		tegra->rtc_rdev = rdev;
+		return 0;
+	}
+
+	if (of_property_read_bool(np, "nvidia,tegra-cpu-regulator") &&
+	    !tegra->cpu_rdev) {
+		tegra->cpu_rdev = rdev;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static int tegra20_regulator_detach(struct regulator_coupler *coupler,
+				    struct regulator_dev *rdev)
+{
+	struct tegra_regulator_coupler *tegra = to_tegra_coupler(coupler);
+
+	/*
+	 * We don't expect regulators to be decoupled during reboot,
+	 * this may race with the reboot handler and shouldn't ever
+	 * happen in practice.
+	 */
+	if (WARN_ON_ONCE(system_state > SYSTEM_RUNNING))
+		return -EPERM;
+
+	if (tegra->core_rdev == rdev) {
+		tegra->core_rdev = NULL;
+		return 0;
+	}
+
+	if (tegra->rtc_rdev == rdev) {
+		tegra->rtc_rdev = NULL;
+		return 0;
+	}
+
+	if (tegra->cpu_rdev == rdev) {
+		tegra->cpu_rdev = NULL;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static struct tegra_regulator_coupler tegra20_coupler = {
+	.coupler = {
+		.attach_regulator = tegra20_regulator_attach,
+		.detach_regulator = tegra20_regulator_detach,
+		.balance_voltage = tegra20_regulator_balance_voltage,
+	},
+	.reboot_notifier.notifier_call = tegra20_regulator_reboot,
+	.suspend_notifier.notifier_call = tegra20_regulator_suspend,
+};
+
+static int __init tegra_regulator_coupler_init(void)
+{
+	int err;
+
+	if (!of_machine_is_compatible("nvidia,tegra20"))
+		return 0;
+
+	err = register_reboot_notifier(&tegra20_coupler.reboot_notifier);
+	WARN_ON(err);
+
+	err = register_pm_notifier(&tegra20_coupler.suspend_notifier);
+	WARN_ON(err);
+
+	return regulator_coupler_register(&tegra20_coupler.coupler);
+}
+arch_initcall(tegra_regulator_coupler_init);