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, 517 insertions, 0 deletions

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gk104.c b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gk104.c
new file mode 100644
index 000000000..0d8e2ddcc
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gk104.c
@@ -0,0 +1,517 @@
+/*
+ * 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
+ */
+#define gk104_clk(p) container_of((p), struct gk104_clk, base)
+#include "priv.h"
+#include "pll.h"
+
+#include <subdev/timer.h>
+#include <subdev/bios.h>
+#include <subdev/bios/pll.h>
+
+struct gk104_clk_info {
+	u32 freq;
+	u32 ssel;
+	u32 mdiv;
+	u32 dsrc;
+	u32 ddiv;
+	u32 coef;
+};
+
+struct gk104_clk {
+	struct nvkm_clk base;
+	struct gk104_clk_info eng[16];
+};
+
+static u32 read_div(struct gk104_clk *, int, u32, u32);
+static u32 read_pll(struct gk104_clk *, u32);
+
+static u32
+read_vco(struct gk104_clk *clk, u32 dsrc)
+{
+	struct nvkm_device *device = clk->base.subdev.device;
+	u32 ssrc = nvkm_rd32(device, dsrc);
+	if (!(ssrc & 0x00000100))
+		return read_pll(clk, 0x00e800);
+	return read_pll(clk, 0x00e820);
+}
+
+static u32
+read_pll(struct gk104_clk *clk, u32 pll)
+{
+	struct nvkm_device *device = clk->base.subdev.device;
+	u32 ctrl = nvkm_rd32(device, pll + 0x00);
+	u32 coef = nvkm_rd32(device, pll + 0x04);
+	u32 P = (coef & 0x003f0000) >> 16;
+	u32 N = (coef & 0x0000ff00) >> 8;
+	u32 M = (coef & 0x000000ff) >> 0;
+	u32 sclk;
+	u16 fN = 0xf000;
+
+	if (!(ctrl & 0x00000001))
+		return 0;
+
+	switch (pll) {
+	case 0x00e800:
+	case 0x00e820:
+		sclk = device->crystal;
+		P = 1;
+		break;
+	case 0x132000:
+		sclk = read_pll(clk, 0x132020);
+		P = (coef & 0x10000000) ? 2 : 1;
+		break;
+	case 0x132020:
+		sclk = read_div(clk, 0, 0x137320, 0x137330);
+		fN   = nvkm_rd32(device, pll + 0x10) >> 16;
+		break;
+	case 0x137000:
+	case 0x137020:
+	case 0x137040:
+	case 0x1370e0:
+		sclk = read_div(clk, (pll & 0xff) / 0x20, 0x137120, 0x137140);
+		break;
+	default:
+		return 0;
+	}
+
+	if (P == 0)
+		P = 1;
+
+	sclk = (sclk * N) + (((u16)(fN + 4096) * sclk) >> 13);
+	return sclk / (M * P);
+}
+
+static u32
+read_div(struct gk104_clk *clk, int doff, u32 dsrc, u32 dctl)
+{
+	struct nvkm_device *device = clk->base.subdev.device;
+	u32 ssrc = nvkm_rd32(device, dsrc + (doff * 4));
+	u32 sctl = nvkm_rd32(device, dctl + (doff * 4));
+
+	switch (ssrc & 0x00000003) {
+	case 0:
+		if ((ssrc & 0x00030000) != 0x00030000)
+			return device->crystal;
+		return 108000;
+	case 2:
+		return 100000;
+	case 3:
+		if (sctl & 0x80000000) {
+			u32 sclk = read_vco(clk, dsrc + (doff * 4));
+			u32 sdiv = (sctl & 0x0000003f) + 2;
+			return (sclk * 2) / sdiv;
+		}
+
+		return read_vco(clk, dsrc + (doff * 4));
+	default:
+		return 0;
+	}
+}
+
+static u32
+read_mem(struct gk104_clk *clk)
+{
+	struct nvkm_device *device = clk->base.subdev.device;
+	switch (nvkm_rd32(device, 0x1373f4) & 0x0000000f) {
+	case 1: return read_pll(clk, 0x132020);
+	case 2: return read_pll(clk, 0x132000);
+	default:
+		return 0;
+	}
+}
+
+static u32
+read_clk(struct gk104_clk *clk, int idx)
+{
+	struct nvkm_device *device = clk->base.subdev.device;
+	u32 sctl = nvkm_rd32(device, 0x137250 + (idx * 4));
+	u32 sclk, sdiv;
+
+	if (idx < 7) {
+		u32 ssel = nvkm_rd32(device, 0x137100);
+		if (ssel & (1 << idx)) {
+			sclk = read_pll(clk, 0x137000 + (idx * 0x20));
+			sdiv = 1;
+		} else {
+			sclk = read_div(clk, idx, 0x137160, 0x1371d0);
+			sdiv = 0;
+		}
+	} else {
+		u32 ssrc = nvkm_rd32(device, 0x137160 + (idx * 0x04));
+		if ((ssrc & 0x00000003) == 0x00000003) {
+			sclk = read_div(clk, idx, 0x137160, 0x1371d0);
+			if (ssrc & 0x00000100) {
+				if (ssrc & 0x40000000)
+					sclk = read_pll(clk, 0x1370e0);
+				sdiv = 1;
+			} else {
+				sdiv = 0;
+			}
+		} else {
+			sclk = read_div(clk, idx, 0x137160, 0x1371d0);
+			sdiv = 0;
+		}
+	}
+
+	if (sctl & 0x80000000) {
+		if (sdiv)
+			sdiv = ((sctl & 0x00003f00) >> 8) + 2;
+		else
+			sdiv = ((sctl & 0x0000003f) >> 0) + 2;
+		return (sclk * 2) / sdiv;
+	}
+
+	return sclk;
+}
+
+static int
+gk104_clk_read(struct nvkm_clk *base, enum nv_clk_src src)
+{
+	struct gk104_clk *clk = gk104_clk(base);
+	struct nvkm_subdev *subdev = &clk->base.subdev;
+	struct nvkm_device *device = subdev->device;
+
+	switch (src) {
+	case nv_clk_src_crystal:
+		return device->crystal;
+	case nv_clk_src_href:
+		return 100000;
+	case nv_clk_src_mem:
+		return read_mem(clk);
+	case nv_clk_src_gpc:
+		return read_clk(clk, 0x00);
+	case nv_clk_src_rop:
+		return read_clk(clk, 0x01);
+	case nv_clk_src_hubk07:
+		return read_clk(clk, 0x02);
+	case nv_clk_src_hubk06:
+		return read_clk(clk, 0x07);
+	case nv_clk_src_hubk01:
+		return read_clk(clk, 0x08);
+	case nv_clk_src_pmu:
+		return read_clk(clk, 0x0c);
+	case nv_clk_src_vdec:
+		return read_clk(clk, 0x0e);
+	default:
+		nvkm_error(subdev, "invalid clock source %d\n", src);
+		return -EINVAL;
+	}
+}
+
+static u32
+calc_div(struct gk104_clk *clk, int idx, u32 ref, u32 freq, u32 *ddiv)
+{
+	u32 div = min((ref * 2) / freq, (u32)65);
+	if (div < 2)
+		div = 2;
+
+	*ddiv = div - 2;
+	return (ref * 2) / div;
+}
+
+static u32
+calc_src(struct gk104_clk *clk, int idx, u32 freq, u32 *dsrc, u32 *ddiv)
+{
+	u32 sclk;
+
+	/* use one of the fixed frequencies if possible */
+	*ddiv = 0x00000000;
+	switch (freq) {
+	case  27000:
+	case 108000:
+		*dsrc = 0x00000000;
+		if (freq == 108000)
+			*dsrc |= 0x00030000;
+		return freq;
+	case 100000:
+		*dsrc = 0x00000002;
+		return freq;
+	default:
+		*dsrc = 0x00000003;
+		break;
+	}
+
+	/* otherwise, calculate the closest divider */
+	sclk = read_vco(clk, 0x137160 + (idx * 4));
+	if (idx < 7)
+		sclk = calc_div(clk, idx, sclk, freq, ddiv);
+	return sclk;
+}
+
+static u32
+calc_pll(struct gk104_clk *clk, int idx, u32 freq, u32 *coef)
+{
+	struct nvkm_subdev *subdev = &clk->base.subdev;
+	struct nvkm_bios *bios = subdev->device->bios;
+	struct nvbios_pll limits;
+	int N, M, P, ret;
+
+	ret = nvbios_pll_parse(bios, 0x137000 + (idx * 0x20), &limits);
+	if (ret)
+		return 0;
+
+	limits.refclk = read_div(clk, idx, 0x137120, 0x137140);
+	if (!limits.refclk)
+		return 0;
+
+	ret = gt215_pll_calc(subdev, &limits, freq, &N, NULL, &M, &P);
+	if (ret <= 0)
+		return 0;
+
+	*coef = (P << 16) | (N << 8) | M;
+	return ret;
+}
+
+static int
+calc_clk(struct gk104_clk *clk,
+	 struct nvkm_cstate *cstate, int idx, int dom)
+{
+	struct gk104_clk_info *info = &clk->eng[idx];
+	u32 freq = cstate->domain[dom];
+	u32 src0, div0, div1D, div1P = 0;
+	u32 clk0, clk1 = 0;
+
+	/* invalid clock domain */
+	if (!freq)
+		return 0;
+
+	/* first possible path, using only dividers */
+	clk0 = calc_src(clk, idx, freq, &src0, &div0);
+	clk0 = calc_div(clk, idx, clk0, freq, &div1D);
+
+	/* see if we can get any closer using PLLs */
+	if (clk0 != freq && (0x0000ff87 & (1 << idx))) {
+		if (idx <= 7)
+			clk1 = calc_pll(clk, idx, freq, &info->coef);
+		else
+			clk1 = cstate->domain[nv_clk_src_hubk06];
+		clk1 = calc_div(clk, idx, clk1, freq, &div1P);
+	}
+
+	/* select the method which gets closest to target freq */
+	if (abs((int)freq - clk0) <= abs((int)freq - clk1)) {
+		info->dsrc = src0;
+		if (div0) {
+			info->ddiv |= 0x80000000;
+			info->ddiv |= div0;
+		}
+		if (div1D) {
+			info->mdiv |= 0x80000000;
+			info->mdiv |= div1D;
+		}
+		info->ssel = 0;
+		info->freq = clk0;
+	} else {
+		if (div1P) {
+			info->mdiv |= 0x80000000;
+			info->mdiv |= div1P << 8;
+		}
+		info->ssel = (1 << idx);
+		info->dsrc = 0x40000100;
+		info->freq = clk1;
+	}
+
+	return 0;
+}
+
+static int
+gk104_clk_calc(struct nvkm_clk *base, struct nvkm_cstate *cstate)
+{
+	struct gk104_clk *clk = gk104_clk(base);
+	int ret;
+
+	if ((ret = calc_clk(clk, cstate, 0x00, nv_clk_src_gpc)) ||
+	    (ret = calc_clk(clk, cstate, 0x01, nv_clk_src_rop)) ||
+	    (ret = calc_clk(clk, cstate, 0x02, nv_clk_src_hubk07)) ||
+	    (ret = calc_clk(clk, cstate, 0x07, nv_clk_src_hubk06)) ||
+	    (ret = calc_clk(clk, cstate, 0x08, nv_clk_src_hubk01)) ||
+	    (ret = calc_clk(clk, cstate, 0x0c, nv_clk_src_pmu)) ||
+	    (ret = calc_clk(clk, cstate, 0x0e, nv_clk_src_vdec)))
+		return ret;
+
+	return 0;
+}
+
+static void
+gk104_clk_prog_0(struct gk104_clk *clk, int idx)
+{
+	struct gk104_clk_info *info = &clk->eng[idx];
+	struct nvkm_device *device = clk->base.subdev.device;
+	if (!info->ssel) {
+		nvkm_mask(device, 0x1371d0 + (idx * 0x04), 0x8000003f, info->ddiv);
+		nvkm_wr32(device, 0x137160 + (idx * 0x04), info->dsrc);
+	}
+}
+
+static void
+gk104_clk_prog_1_0(struct gk104_clk *clk, int idx)
+{
+	struct nvkm_device *device = clk->base.subdev.device;
+	nvkm_mask(device, 0x137100, (1 << idx), 0x00000000);
+	nvkm_msec(device, 2000,
+		if (!(nvkm_rd32(device, 0x137100) & (1 << idx)))
+			break;
+	);
+}
+
+static void
+gk104_clk_prog_1_1(struct gk104_clk *clk, int idx)
+{
+	struct nvkm_device *device = clk->base.subdev.device;
+	nvkm_mask(device, 0x137160 + (idx * 0x04), 0x00000100, 0x00000000);
+}
+
+static void
+gk104_clk_prog_2(struct gk104_clk *clk, int idx)
+{
+	struct gk104_clk_info *info = &clk->eng[idx];
+	struct nvkm_device *device = clk->base.subdev.device;
+	const u32 addr = 0x137000 + (idx * 0x20);
+	nvkm_mask(device, addr + 0x00, 0x00000004, 0x00000000);
+	nvkm_mask(device, addr + 0x00, 0x00000001, 0x00000000);
+	if (info->coef) {
+		nvkm_wr32(device, addr + 0x04, info->coef);
+		nvkm_mask(device, addr + 0x00, 0x00000001, 0x00000001);
+
+		/* Test PLL lock */
+		nvkm_mask(device, addr + 0x00, 0x00000010, 0x00000000);
+		nvkm_msec(device, 2000,
+			if (nvkm_rd32(device, addr + 0x00) & 0x00020000)
+				break;
+		);
+		nvkm_mask(device, addr + 0x00, 0x00000010, 0x00000010);
+
+		/* Enable sync mode */
+		nvkm_mask(device, addr + 0x00, 0x00000004, 0x00000004);
+	}
+}
+
+static void
+gk104_clk_prog_3(struct gk104_clk *clk, int idx)
+{
+	struct gk104_clk_info *info = &clk->eng[idx];
+	struct nvkm_device *device = clk->base.subdev.device;
+	if (info->ssel)
+		nvkm_mask(device, 0x137250 + (idx * 0x04), 0x00003f00, info->mdiv);
+	else
+		nvkm_mask(device, 0x137250 + (idx * 0x04), 0x0000003f, info->mdiv);
+}
+
+static void
+gk104_clk_prog_4_0(struct gk104_clk *clk, int idx)
+{
+	struct gk104_clk_info *info = &clk->eng[idx];
+	struct nvkm_device *device = clk->base.subdev.device;
+	if (info->ssel) {
+		nvkm_mask(device, 0x137100, (1 << idx), info->ssel);
+		nvkm_msec(device, 2000,
+			u32 tmp = nvkm_rd32(device, 0x137100) & (1 << idx);
+			if (tmp == info->ssel)
+				break;
+		);
+	}
+}
+
+static void
+gk104_clk_prog_4_1(struct gk104_clk *clk, int idx)
+{
+	struct gk104_clk_info *info = &clk->eng[idx];
+	struct nvkm_device *device = clk->base.subdev.device;
+	if (info->ssel) {
+		nvkm_mask(device, 0x137160 + (idx * 0x04), 0x40000000, 0x40000000);
+		nvkm_mask(device, 0x137160 + (idx * 0x04), 0x00000100, 0x00000100);
+	}
+}
+
+static int
+gk104_clk_prog(struct nvkm_clk *base)
+{
+	struct gk104_clk *clk = gk104_clk(base);
+	struct {
+		u32 mask;
+		void (*exec)(struct gk104_clk *, int);
+	} stage[] = {
+		{ 0x007f, gk104_clk_prog_0   }, /* div programming */
+		{ 0x007f, gk104_clk_prog_1_0 }, /* select div mode */
+		{ 0xff80, gk104_clk_prog_1_1 },
+		{ 0x00ff, gk104_clk_prog_2   }, /* (maybe) program pll */
+		{ 0xff80, gk104_clk_prog_3   }, /* final divider */
+		{ 0x007f, gk104_clk_prog_4_0 }, /* (maybe) select pll mode */
+		{ 0xff80, gk104_clk_prog_4_1 },
+	};
+	int i, j;
+
+	for (i = 0; i < ARRAY_SIZE(stage); i++) {
+		for (j = 0; j < ARRAY_SIZE(clk->eng); j++) {
+			if (!(stage[i].mask & (1 << j)))
+				continue;
+			if (!clk->eng[j].freq)
+				continue;
+			stage[i].exec(clk, j);
+		}
+	}
+
+	return 0;
+}
+
+static void
+gk104_clk_tidy(struct nvkm_clk *base)
+{
+	struct gk104_clk *clk = gk104_clk(base);
+	memset(clk->eng, 0x00, sizeof(clk->eng));
+}
+
+static const struct nvkm_clk_func
+gk104_clk = {
+	.read = gk104_clk_read,
+	.calc = gk104_clk_calc,
+	.prog = gk104_clk_prog,
+	.tidy = gk104_clk_tidy,
+	.domains = {
+		{ nv_clk_src_crystal, 0xff },
+		{ nv_clk_src_href   , 0xff },
+		{ nv_clk_src_gpc    , 0x00, NVKM_CLK_DOM_FLAG_CORE | NVKM_CLK_DOM_FLAG_VPSTATE, "core", 2000 },
+		{ nv_clk_src_hubk07 , 0x01, NVKM_CLK_DOM_FLAG_CORE },
+		{ nv_clk_src_rop    , 0x02, NVKM_CLK_DOM_FLAG_CORE },
+		{ nv_clk_src_mem    , 0x03, 0, "memory", 500 },
+		{ nv_clk_src_hubk06 , 0x04, NVKM_CLK_DOM_FLAG_CORE },
+		{ nv_clk_src_hubk01 , 0x05 },
+		{ nv_clk_src_vdec   , 0x06 },
+		{ nv_clk_src_pmu    , 0x07 },
+		{ nv_clk_src_max }
+	}
+};
+
+int
+gk104_clk_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst,
+	      struct nvkm_clk **pclk)
+{
+	struct gk104_clk *clk;
+
+	if (!(clk = kzalloc(sizeof(*clk), GFP_KERNEL)))
+		return -ENOMEM;
+	*pclk = &clk->base;
+
+	return nvkm_clk_ctor(&gk104_clk, device, type, inst, true, &clk->base);
+}