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, 716 insertions, 0 deletions

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c
new file mode 100644
index 000000000..da07a2fbe
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c
@@ -0,0 +1,716 @@
+/*
+ * Copyright 2013 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs
+ */
+#include "priv.h"
+
+#include <subdev/bios.h>
+#include <subdev/bios/boost.h>
+#include <subdev/bios/cstep.h>
+#include <subdev/bios/perf.h>
+#include <subdev/bios/vpstate.h>
+#include <subdev/fb.h>
+#include <subdev/therm.h>
+#include <subdev/volt.h>
+
+#include <core/option.h>
+
+/******************************************************************************
+ * misc
+ *****************************************************************************/
+static u32
+nvkm_clk_adjust(struct nvkm_clk *clk, bool adjust,
+		u8 pstate, u8 domain, u32 input)
+{
+	struct nvkm_bios *bios = clk->subdev.device->bios;
+	struct nvbios_boostE boostE;
+	u8  ver, hdr, cnt, len;
+	u32 data;
+
+	data = nvbios_boostEm(bios, pstate, &ver, &hdr, &cnt, &len, &boostE);
+	if (data) {
+		struct nvbios_boostS boostS;
+		u8  idx = 0, sver, shdr;
+		u32 subd;
+
+		input = max(boostE.min, input);
+		input = min(boostE.max, input);
+		do {
+			sver = ver;
+			shdr = hdr;
+			subd = nvbios_boostSp(bios, idx++, data, &sver, &shdr,
+					      cnt, len, &boostS);
+			if (subd && boostS.domain == domain) {
+				if (adjust)
+					input = input * boostS.percent / 100;
+				input = max(boostS.min, input);
+				input = min(boostS.max, input);
+				break;
+			}
+		} while (subd);
+	}
+
+	return input;
+}
+
+/******************************************************************************
+ * C-States
+ *****************************************************************************/
+static bool
+nvkm_cstate_valid(struct nvkm_clk *clk, struct nvkm_cstate *cstate,
+		  u32 max_volt, int temp)
+{
+	const struct nvkm_domain *domain = clk->domains;
+	struct nvkm_volt *volt = clk->subdev.device->volt;
+	int voltage;
+
+	while (domain && domain->name != nv_clk_src_max) {
+		if (domain->flags & NVKM_CLK_DOM_FLAG_VPSTATE) {
+			u32 freq = cstate->domain[domain->name];
+			switch (clk->boost_mode) {
+			case NVKM_CLK_BOOST_NONE:
+				if (clk->base_khz && freq > clk->base_khz)
+					return false;
+				fallthrough;
+			case NVKM_CLK_BOOST_BIOS:
+				if (clk->boost_khz && freq > clk->boost_khz)
+					return false;
+			}
+		}
+		domain++;
+	}
+
+	if (!volt)
+		return true;
+
+	voltage = nvkm_volt_map(volt, cstate->voltage, temp);
+	if (voltage < 0)
+		return false;
+	return voltage <= min(max_volt, volt->max_uv);
+}
+
+static struct nvkm_cstate *
+nvkm_cstate_find_best(struct nvkm_clk *clk, struct nvkm_pstate *pstate,
+		      struct nvkm_cstate *cstate)
+{
+	struct nvkm_device *device = clk->subdev.device;
+	struct nvkm_volt *volt = device->volt;
+	int max_volt;
+
+	if (!pstate || !cstate)
+		return NULL;
+
+	if (!volt)
+		return cstate;
+
+	max_volt = volt->max_uv;
+	if (volt->max0_id != 0xff)
+		max_volt = min(max_volt,
+			       nvkm_volt_map(volt, volt->max0_id, clk->temp));
+	if (volt->max1_id != 0xff)
+		max_volt = min(max_volt,
+			       nvkm_volt_map(volt, volt->max1_id, clk->temp));
+	if (volt->max2_id != 0xff)
+		max_volt = min(max_volt,
+			       nvkm_volt_map(volt, volt->max2_id, clk->temp));
+
+	list_for_each_entry_from_reverse(cstate, &pstate->list, head) {
+		if (nvkm_cstate_valid(clk, cstate, max_volt, clk->temp))
+			return cstate;
+	}
+
+	return NULL;
+}
+
+static struct nvkm_cstate *
+nvkm_cstate_get(struct nvkm_clk *clk, struct nvkm_pstate *pstate, int cstatei)
+{
+	struct nvkm_cstate *cstate;
+	if (cstatei == NVKM_CLK_CSTATE_HIGHEST)
+		return list_last_entry(&pstate->list, typeof(*cstate), head);
+	else {
+		list_for_each_entry(cstate, &pstate->list, head) {
+			if (cstate->id == cstatei)
+				return cstate;
+		}
+	}
+	return NULL;
+}
+
+static int
+nvkm_cstate_prog(struct nvkm_clk *clk, struct nvkm_pstate *pstate, int cstatei)
+{
+	struct nvkm_subdev *subdev = &clk->subdev;
+	struct nvkm_device *device = subdev->device;
+	struct nvkm_therm *therm = device->therm;
+	struct nvkm_volt *volt = device->volt;
+	struct nvkm_cstate *cstate;
+	int ret;
+
+	if (!list_empty(&pstate->list)) {
+		cstate = nvkm_cstate_get(clk, pstate, cstatei);
+		cstate = nvkm_cstate_find_best(clk, pstate, cstate);
+		if (!cstate)
+			return -EINVAL;
+	} else {
+		cstate = &pstate->base;
+	}
+
+	if (therm) {
+		ret = nvkm_therm_cstate(therm, pstate->fanspeed, +1);
+		if (ret && ret != -ENODEV) {
+			nvkm_error(subdev, "failed to raise fan speed: %d\n", ret);
+			return ret;
+		}
+	}
+
+	if (volt) {
+		ret = nvkm_volt_set_id(volt, cstate->voltage,
+				       pstate->base.voltage, clk->temp, +1);
+		if (ret && ret != -ENODEV) {
+			nvkm_error(subdev, "failed to raise voltage: %d\n", ret);
+			return ret;
+		}
+	}
+
+	ret = clk->func->calc(clk, cstate);
+	if (ret == 0) {
+		ret = clk->func->prog(clk);
+		clk->func->tidy(clk);
+	}
+
+	if (volt) {
+		ret = nvkm_volt_set_id(volt, cstate->voltage,
+				       pstate->base.voltage, clk->temp, -1);
+		if (ret && ret != -ENODEV)
+			nvkm_error(subdev, "failed to lower voltage: %d\n", ret);
+	}
+
+	if (therm) {
+		ret = nvkm_therm_cstate(therm, pstate->fanspeed, -1);
+		if (ret && ret != -ENODEV)
+			nvkm_error(subdev, "failed to lower fan speed: %d\n", ret);
+	}
+
+	return ret;
+}
+
+static void
+nvkm_cstate_del(struct nvkm_cstate *cstate)
+{
+	list_del(&cstate->head);
+	kfree(cstate);
+}
+
+static int
+nvkm_cstate_new(struct nvkm_clk *clk, int idx, struct nvkm_pstate *pstate)
+{
+	struct nvkm_bios *bios = clk->subdev.device->bios;
+	struct nvkm_volt *volt = clk->subdev.device->volt;
+	const struct nvkm_domain *domain = clk->domains;
+	struct nvkm_cstate *cstate = NULL;
+	struct nvbios_cstepX cstepX;
+	u8  ver, hdr;
+	u32 data;
+
+	data = nvbios_cstepXp(bios, idx, &ver, &hdr, &cstepX);
+	if (!data)
+		return -ENOENT;
+
+	if (volt && nvkm_volt_map_min(volt, cstepX.voltage) > volt->max_uv)
+		return -EINVAL;
+
+	cstate = kzalloc(sizeof(*cstate), GFP_KERNEL);
+	if (!cstate)
+		return -ENOMEM;
+
+	*cstate = pstate->base;
+	cstate->voltage = cstepX.voltage;
+	cstate->id = idx;
+
+	while (domain && domain->name != nv_clk_src_max) {
+		if (domain->flags & NVKM_CLK_DOM_FLAG_CORE) {
+			u32 freq = nvkm_clk_adjust(clk, true, pstate->pstate,
+						   domain->bios, cstepX.freq);
+			cstate->domain[domain->name] = freq;
+		}
+		domain++;
+	}
+
+	list_add(&cstate->head, &pstate->list);
+	return 0;
+}
+
+/******************************************************************************
+ * P-States
+ *****************************************************************************/
+static int
+nvkm_pstate_prog(struct nvkm_clk *clk, int pstatei)
+{
+	struct nvkm_subdev *subdev = &clk->subdev;
+	struct nvkm_fb *fb = subdev->device->fb;
+	struct nvkm_pci *pci = subdev->device->pci;
+	struct nvkm_pstate *pstate;
+	int ret, idx = 0;
+
+	list_for_each_entry(pstate, &clk->states, head) {
+		if (idx++ == pstatei)
+			break;
+	}
+
+	nvkm_debug(subdev, "setting performance state %d\n", pstatei);
+	clk->pstate = pstatei;
+
+	nvkm_pcie_set_link(pci, pstate->pcie_speed, pstate->pcie_width);
+
+	if (fb && fb->ram && fb->ram->func->calc) {
+		struct nvkm_ram *ram = fb->ram;
+		int khz = pstate->base.domain[nv_clk_src_mem];
+		do {
+			ret = ram->func->calc(ram, khz);
+			if (ret == 0)
+				ret = ram->func->prog(ram);
+		} while (ret > 0);
+		ram->func->tidy(ram);
+	}
+
+	return nvkm_cstate_prog(clk, pstate, NVKM_CLK_CSTATE_HIGHEST);
+}
+
+static void
+nvkm_pstate_work(struct work_struct *work)
+{
+	struct nvkm_clk *clk = container_of(work, typeof(*clk), work);
+	struct nvkm_subdev *subdev = &clk->subdev;
+	int pstate;
+
+	if (!atomic_xchg(&clk->waiting, 0))
+		return;
+	clk->pwrsrc = power_supply_is_system_supplied();
+
+	nvkm_trace(subdev, "P %d PWR %d U(AC) %d U(DC) %d A %d T %d°C D %d\n",
+		   clk->pstate, clk->pwrsrc, clk->ustate_ac, clk->ustate_dc,
+		   clk->astate, clk->temp, clk->dstate);
+
+	pstate = clk->pwrsrc ? clk->ustate_ac : clk->ustate_dc;
+	if (clk->state_nr && pstate != -1) {
+		pstate = (pstate < 0) ? clk->astate : pstate;
+		pstate = min(pstate, clk->state_nr - 1);
+		pstate = max(pstate, clk->dstate);
+	} else {
+		pstate = clk->pstate = -1;
+	}
+
+	nvkm_trace(subdev, "-> %d\n", pstate);
+	if (pstate != clk->pstate) {
+		int ret = nvkm_pstate_prog(clk, pstate);
+		if (ret) {
+			nvkm_error(subdev, "error setting pstate %d: %d\n",
+				   pstate, ret);
+		}
+	}
+
+	wake_up_all(&clk->wait);
+}
+
+static int
+nvkm_pstate_calc(struct nvkm_clk *clk, bool wait)
+{
+	atomic_set(&clk->waiting, 1);
+	schedule_work(&clk->work);
+	if (wait)
+		wait_event(clk->wait, !atomic_read(&clk->waiting));
+	return 0;
+}
+
+static void
+nvkm_pstate_info(struct nvkm_clk *clk, struct nvkm_pstate *pstate)
+{
+	const struct nvkm_domain *clock = clk->domains - 1;
+	struct nvkm_cstate *cstate;
+	struct nvkm_subdev *subdev = &clk->subdev;
+	char info[3][32] = { "", "", "" };
+	char name[4] = "--";
+	int i = -1;
+
+	if (pstate->pstate != 0xff)
+		snprintf(name, sizeof(name), "%02x", pstate->pstate);
+
+	while ((++clock)->name != nv_clk_src_max) {
+		u32 lo = pstate->base.domain[clock->name];
+		u32 hi = lo;
+		if (hi == 0)
+			continue;
+
+		nvkm_debug(subdev, "%02x: %10d KHz\n", clock->name, lo);
+		list_for_each_entry(cstate, &pstate->list, head) {
+			u32 freq = cstate->domain[clock->name];
+			lo = min(lo, freq);
+			hi = max(hi, freq);
+			nvkm_debug(subdev, "%10d KHz\n", freq);
+		}
+
+		if (clock->mname && ++i < ARRAY_SIZE(info)) {
+			lo /= clock->mdiv;
+			hi /= clock->mdiv;
+			if (lo == hi) {
+				snprintf(info[i], sizeof(info[i]), "%s %d MHz",
+					 clock->mname, lo);
+			} else {
+				snprintf(info[i], sizeof(info[i]),
+					 "%s %d-%d MHz", clock->mname, lo, hi);
+			}
+		}
+	}
+
+	nvkm_debug(subdev, "%s: %s %s %s\n", name, info[0], info[1], info[2]);
+}
+
+static void
+nvkm_pstate_del(struct nvkm_pstate *pstate)
+{
+	struct nvkm_cstate *cstate, *temp;
+
+	list_for_each_entry_safe(cstate, temp, &pstate->list, head) {
+		nvkm_cstate_del(cstate);
+	}
+
+	list_del(&pstate->head);
+	kfree(pstate);
+}
+
+static int
+nvkm_pstate_new(struct nvkm_clk *clk, int idx)
+{
+	struct nvkm_bios *bios = clk->subdev.device->bios;
+	const struct nvkm_domain *domain = clk->domains - 1;
+	struct nvkm_pstate *pstate;
+	struct nvkm_cstate *cstate;
+	struct nvbios_cstepE cstepE;
+	struct nvbios_perfE perfE;
+	u8  ver, hdr, cnt, len;
+	u32 data;
+
+	data = nvbios_perfEp(bios, idx, &ver, &hdr, &cnt, &len, &perfE);
+	if (!data)
+		return -EINVAL;
+	if (perfE.pstate == 0xff)
+		return 0;
+
+	pstate = kzalloc(sizeof(*pstate), GFP_KERNEL);
+	cstate = &pstate->base;
+	if (!pstate)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&pstate->list);
+
+	pstate->pstate = perfE.pstate;
+	pstate->fanspeed = perfE.fanspeed;
+	pstate->pcie_speed = perfE.pcie_speed;
+	pstate->pcie_width = perfE.pcie_width;
+	cstate->voltage = perfE.voltage;
+	cstate->domain[nv_clk_src_core] = perfE.core;
+	cstate->domain[nv_clk_src_shader] = perfE.shader;
+	cstate->domain[nv_clk_src_mem] = perfE.memory;
+	cstate->domain[nv_clk_src_vdec] = perfE.vdec;
+	cstate->domain[nv_clk_src_dom6] = perfE.disp;
+
+	while (ver >= 0x40 && (++domain)->name != nv_clk_src_max) {
+		struct nvbios_perfS perfS;
+		u8  sver = ver, shdr = hdr;
+		u32 perfSe = nvbios_perfSp(bios, data, domain->bios,
+					  &sver, &shdr, cnt, len, &perfS);
+		if (perfSe == 0 || sver != 0x40)
+			continue;
+
+		if (domain->flags & NVKM_CLK_DOM_FLAG_CORE) {
+			perfS.v40.freq = nvkm_clk_adjust(clk, false,
+							 pstate->pstate,
+							 domain->bios,
+							 perfS.v40.freq);
+		}
+
+		cstate->domain[domain->name] = perfS.v40.freq;
+	}
+
+	data = nvbios_cstepEm(bios, pstate->pstate, &ver, &hdr, &cstepE);
+	if (data) {
+		int idx = cstepE.index;
+		do {
+			nvkm_cstate_new(clk, idx, pstate);
+		} while(idx--);
+	}
+
+	nvkm_pstate_info(clk, pstate);
+	list_add_tail(&pstate->head, &clk->states);
+	clk->state_nr++;
+	return 0;
+}
+
+/******************************************************************************
+ * Adjustment triggers
+ *****************************************************************************/
+static int
+nvkm_clk_ustate_update(struct nvkm_clk *clk, int req)
+{
+	struct nvkm_pstate *pstate;
+	int i = 0;
+
+	if (!clk->allow_reclock)
+		return -ENOSYS;
+
+	if (req != -1 && req != -2) {
+		list_for_each_entry(pstate, &clk->states, head) {
+			if (pstate->pstate == req)
+				break;
+			i++;
+		}
+
+		if (pstate->pstate != req)
+			return -EINVAL;
+		req = i;
+	}
+
+	return req + 2;
+}
+
+static int
+nvkm_clk_nstate(struct nvkm_clk *clk, const char *mode, int arglen)
+{
+	int ret = 1;
+
+	if (clk->allow_reclock && !strncasecmpz(mode, "auto", arglen))
+		return -2;
+
+	if (strncasecmpz(mode, "disabled", arglen)) {
+		char save = mode[arglen];
+		long v;
+
+		((char *)mode)[arglen] = '\0';
+		if (!kstrtol(mode, 0, &v)) {
+			ret = nvkm_clk_ustate_update(clk, v);
+			if (ret < 0)
+				ret = 1;
+		}
+		((char *)mode)[arglen] = save;
+	}
+
+	return ret - 2;
+}
+
+int
+nvkm_clk_ustate(struct nvkm_clk *clk, int req, int pwr)
+{
+	int ret = nvkm_clk_ustate_update(clk, req);
+	if (ret >= 0) {
+		if (ret -= 2, pwr) clk->ustate_ac = ret;
+		else		   clk->ustate_dc = ret;
+		return nvkm_pstate_calc(clk, true);
+	}
+	return ret;
+}
+
+int
+nvkm_clk_astate(struct nvkm_clk *clk, int req, int rel, bool wait)
+{
+	if (!rel) clk->astate  = req;
+	if ( rel) clk->astate += rel;
+	clk->astate = min(clk->astate, clk->state_nr - 1);
+	clk->astate = max(clk->astate, 0);
+	return nvkm_pstate_calc(clk, wait);
+}
+
+int
+nvkm_clk_tstate(struct nvkm_clk *clk, u8 temp)
+{
+	if (clk->temp == temp)
+		return 0;
+	clk->temp = temp;
+	return nvkm_pstate_calc(clk, false);
+}
+
+int
+nvkm_clk_dstate(struct nvkm_clk *clk, int req, int rel)
+{
+	if (!rel) clk->dstate  = req;
+	if ( rel) clk->dstate += rel;
+	clk->dstate = min(clk->dstate, clk->state_nr - 1);
+	clk->dstate = max(clk->dstate, 0);
+	return nvkm_pstate_calc(clk, true);
+}
+
+int
+nvkm_clk_pwrsrc(struct nvkm_device *device)
+{
+	if (device->clk)
+		return nvkm_pstate_calc(device->clk, false);
+	return 0;
+}
+
+/******************************************************************************
+ * subdev base class implementation
+ *****************************************************************************/
+
+int
+nvkm_clk_read(struct nvkm_clk *clk, enum nv_clk_src src)
+{
+	return clk->func->read(clk, src);
+}
+
+static int
+nvkm_clk_fini(struct nvkm_subdev *subdev, bool suspend)
+{
+	struct nvkm_clk *clk = nvkm_clk(subdev);
+	flush_work(&clk->work);
+	if (clk->func->fini)
+		clk->func->fini(clk);
+	return 0;
+}
+
+static int
+nvkm_clk_init(struct nvkm_subdev *subdev)
+{
+	struct nvkm_clk *clk = nvkm_clk(subdev);
+	const struct nvkm_domain *clock = clk->domains;
+	int ret;
+
+	memset(&clk->bstate, 0x00, sizeof(clk->bstate));
+	INIT_LIST_HEAD(&clk->bstate.list);
+	clk->bstate.pstate = 0xff;
+
+	while (clock->name != nv_clk_src_max) {
+		ret = nvkm_clk_read(clk, clock->name);
+		if (ret < 0) {
+			nvkm_error(subdev, "%02x freq unknown\n", clock->name);
+			return ret;
+		}
+		clk->bstate.base.domain[clock->name] = ret;
+		clock++;
+	}
+
+	nvkm_pstate_info(clk, &clk->bstate);
+
+	if (clk->func->init)
+		return clk->func->init(clk);
+
+	clk->astate = clk->state_nr - 1;
+	clk->dstate = 0;
+	clk->pstate = -1;
+	clk->temp = 90; /* reasonable default value */
+	nvkm_pstate_calc(clk, true);
+	return 0;
+}
+
+static void *
+nvkm_clk_dtor(struct nvkm_subdev *subdev)
+{
+	struct nvkm_clk *clk = nvkm_clk(subdev);
+	struct nvkm_pstate *pstate, *temp;
+
+	/* Early return if the pstates have been provided statically */
+	if (clk->func->pstates)
+		return clk;
+
+	list_for_each_entry_safe(pstate, temp, &clk->states, head) {
+		nvkm_pstate_del(pstate);
+	}
+
+	return clk;
+}
+
+static const struct nvkm_subdev_func
+nvkm_clk = {
+	.dtor = nvkm_clk_dtor,
+	.init = nvkm_clk_init,
+	.fini = nvkm_clk_fini,
+};
+
+int
+nvkm_clk_ctor(const struct nvkm_clk_func *func, struct nvkm_device *device,
+	      enum nvkm_subdev_type type, int inst, bool allow_reclock, struct nvkm_clk *clk)
+{
+	struct nvkm_subdev *subdev = &clk->subdev;
+	struct nvkm_bios *bios = device->bios;
+	int ret, idx, arglen;
+	const char *mode;
+	struct nvbios_vpstate_header h;
+
+	nvkm_subdev_ctor(&nvkm_clk, device, type, inst, subdev);
+
+	if (bios && !nvbios_vpstate_parse(bios, &h)) {
+		struct nvbios_vpstate_entry base, boost;
+		if (!nvbios_vpstate_entry(bios, &h, h.boost_id, &boost))
+			clk->boost_khz = boost.clock_mhz * 1000;
+		if (!nvbios_vpstate_entry(bios, &h, h.base_id, &base))
+			clk->base_khz = base.clock_mhz * 1000;
+	}
+
+	clk->func = func;
+	INIT_LIST_HEAD(&clk->states);
+	clk->domains = func->domains;
+	clk->ustate_ac = -1;
+	clk->ustate_dc = -1;
+	clk->allow_reclock = allow_reclock;
+
+	INIT_WORK(&clk->work, nvkm_pstate_work);
+	init_waitqueue_head(&clk->wait);
+	atomic_set(&clk->waiting, 0);
+
+	/* If no pstates are provided, try and fetch them from the BIOS */
+	if (!func->pstates) {
+		idx = 0;
+		do {
+			ret = nvkm_pstate_new(clk, idx++);
+		} while (ret == 0);
+	} else {
+		for (idx = 0; idx < func->nr_pstates; idx++)
+			list_add_tail(&func->pstates[idx].head, &clk->states);
+		clk->state_nr = func->nr_pstates;
+	}
+
+	mode = nvkm_stropt(device->cfgopt, "NvClkMode", &arglen);
+	if (mode) {
+		clk->ustate_ac = nvkm_clk_nstate(clk, mode, arglen);
+		clk->ustate_dc = nvkm_clk_nstate(clk, mode, arglen);
+	}
+
+	mode = nvkm_stropt(device->cfgopt, "NvClkModeAC", &arglen);
+	if (mode)
+		clk->ustate_ac = nvkm_clk_nstate(clk, mode, arglen);
+
+	mode = nvkm_stropt(device->cfgopt, "NvClkModeDC", &arglen);
+	if (mode)
+		clk->ustate_dc = nvkm_clk_nstate(clk, mode, arglen);
+
+	clk->boost_mode = nvkm_longopt(device->cfgopt, "NvBoost",
+				       NVKM_CLK_BOOST_NONE);
+	return 0;
+}
+
+int
+nvkm_clk_new_(const struct nvkm_clk_func *func, struct nvkm_device *device,
+	      enum nvkm_subdev_type type, int inst, bool allow_reclock, struct nvkm_clk **pclk)
+{
+	if (!(*pclk = kzalloc(sizeof(**pclk), GFP_KERNEL)))
+		return -ENOMEM;
+	return nvkm_clk_ctor(func, device, type, inst, allow_reclock, *pclk);
+}