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, 550 insertions, 0 deletions

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c
new file mode 100644
index 000000000..b5f396972
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c
@@ -0,0 +1,550 @@
+/*
+ * Copyright 2012 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
+ *          Roy Spliet
+ */
+#define gt215_clk(p) container_of((p), struct gt215_clk, base)
+#include "gt215.h"
+#include "pll.h"
+
+#include <engine/fifo.h>
+#include <subdev/bios.h>
+#include <subdev/bios/pll.h>
+#include <subdev/timer.h>
+
+struct gt215_clk {
+	struct nvkm_clk base;
+	struct gt215_clk_info eng[nv_clk_src_max];
+};
+
+static u32 read_clk(struct gt215_clk *, int, bool);
+static u32 read_pll(struct gt215_clk *, int, u32);
+
+static u32
+read_vco(struct gt215_clk *clk, int idx)
+{
+	struct nvkm_device *device = clk->base.subdev.device;
+	u32 sctl = nvkm_rd32(device, 0x4120 + (idx * 4));
+
+	switch (sctl & 0x00000030) {
+	case 0x00000000:
+		return device->crystal;
+	case 0x00000020:
+		return read_pll(clk, 0x41, 0x00e820);
+	case 0x00000030:
+		return read_pll(clk, 0x42, 0x00e8a0);
+	default:
+		return 0;
+	}
+}
+
+static u32
+read_clk(struct gt215_clk *clk, int idx, bool ignore_en)
+{
+	struct nvkm_device *device = clk->base.subdev.device;
+	u32 sctl, sdiv, sclk;
+
+	/* refclk for the 0xe8xx plls is a fixed frequency */
+	if (idx >= 0x40) {
+		if (device->chipset == 0xaf) {
+			/* no joke.. seriously.. sigh.. */
+			return nvkm_rd32(device, 0x00471c) * 1000;
+		}
+
+		return device->crystal;
+	}
+
+	sctl = nvkm_rd32(device, 0x4120 + (idx * 4));
+	if (!ignore_en && !(sctl & 0x00000100))
+		return 0;
+
+	/* out_alt */
+	if (sctl & 0x00000400)
+		return 108000;
+
+	/* vco_out */
+	switch (sctl & 0x00003000) {
+	case 0x00000000:
+		if (!(sctl & 0x00000200))
+			return device->crystal;
+		return 0;
+	case 0x00002000:
+		if (sctl & 0x00000040)
+			return 108000;
+		return 100000;
+	case 0x00003000:
+		/* vco_enable */
+		if (!(sctl & 0x00000001))
+			return 0;
+
+		sclk = read_vco(clk, idx);
+		sdiv = ((sctl & 0x003f0000) >> 16) + 2;
+		return (sclk * 2) / sdiv;
+	default:
+		return 0;
+	}
+}
+
+static u32
+read_pll(struct gt215_clk *clk, int idx, u32 pll)
+{
+	struct nvkm_device *device = clk->base.subdev.device;
+	u32 ctrl = nvkm_rd32(device, pll + 0);
+	u32 sclk = 0, P = 1, N = 1, M = 1;
+	u32 MP;
+
+	if (!(ctrl & 0x00000008)) {
+		if (ctrl & 0x00000001) {
+			u32 coef = nvkm_rd32(device, pll + 4);
+			M = (coef & 0x000000ff) >> 0;
+			N = (coef & 0x0000ff00) >> 8;
+			P = (coef & 0x003f0000) >> 16;
+
+			/* no post-divider on these..
+			 * XXX: it looks more like two post-"dividers" that
+			 * cross each other out in the default RPLL config */
+			if ((pll & 0x00ff00) == 0x00e800)
+				P = 1;
+
+			sclk = read_clk(clk, 0x00 + idx, false);
+		}
+	} else {
+		sclk = read_clk(clk, 0x10 + idx, false);
+	}
+
+	MP = M * P;
+
+	if (!MP)
+		return 0;
+
+	return sclk * N / MP;
+}
+
+static int
+gt215_clk_read(struct nvkm_clk *base, enum nv_clk_src src)
+{
+	struct gt215_clk *clk = gt215_clk(base);
+	struct nvkm_subdev *subdev = &clk->base.subdev;
+	struct nvkm_device *device = subdev->device;
+	u32 hsrc;
+
+	switch (src) {
+	case nv_clk_src_crystal:
+		return device->crystal;
+	case nv_clk_src_core:
+	case nv_clk_src_core_intm:
+		return read_pll(clk, 0x00, 0x4200);
+	case nv_clk_src_shader:
+		return read_pll(clk, 0x01, 0x4220);
+	case nv_clk_src_mem:
+		return read_pll(clk, 0x02, 0x4000);
+	case nv_clk_src_disp:
+		return read_clk(clk, 0x20, false);
+	case nv_clk_src_vdec:
+		return read_clk(clk, 0x21, false);
+	case nv_clk_src_pmu:
+		return read_clk(clk, 0x25, false);
+	case nv_clk_src_host:
+		hsrc = (nvkm_rd32(device, 0xc040) & 0x30000000) >> 28;
+		switch (hsrc) {
+		case 0:
+			return read_clk(clk, 0x1d, false);
+		case 2:
+		case 3:
+			return 277000;
+		default:
+			nvkm_error(subdev, "unknown HOST clock source %d\n", hsrc);
+			return -EINVAL;
+		}
+	default:
+		nvkm_error(subdev, "invalid clock source %d\n", src);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+gt215_clk_info(struct nvkm_clk *base, int idx, u32 khz,
+	       struct gt215_clk_info *info)
+{
+	struct gt215_clk *clk = gt215_clk(base);
+	u32 oclk, sclk, sdiv;
+	s32 diff;
+
+	info->clk = 0;
+
+	switch (khz) {
+	case 27000:
+		info->clk = 0x00000100;
+		return khz;
+	case 100000:
+		info->clk = 0x00002100;
+		return khz;
+	case 108000:
+		info->clk = 0x00002140;
+		return khz;
+	default:
+		sclk = read_vco(clk, idx);
+		sdiv = min((sclk * 2) / khz, (u32)65);
+		oclk = (sclk * 2) / sdiv;
+		diff = ((khz + 3000) - oclk);
+
+		/* When imprecise, play it safe and aim for a clock lower than
+		 * desired rather than higher */
+		if (diff < 0) {
+			sdiv++;
+			oclk = (sclk * 2) / sdiv;
+		}
+
+		/* divider can go as low as 2, limited here because NVIDIA
+		 * and the VBIOS on my NVA8 seem to prefer using the PLL
+		 * for 810MHz - is there a good reason?
+		 * XXX: PLLs with refclk 810MHz?  */
+		if (sdiv > 4) {
+			info->clk = (((sdiv - 2) << 16) | 0x00003100);
+			return oclk;
+		}
+
+		break;
+	}
+
+	return -ERANGE;
+}
+
+int
+gt215_pll_info(struct nvkm_clk *base, int idx, u32 pll, u32 khz,
+	       struct gt215_clk_info *info)
+{
+	struct gt215_clk *clk = gt215_clk(base);
+	struct nvkm_subdev *subdev = &clk->base.subdev;
+	struct nvbios_pll limits;
+	int P, N, M, diff;
+	int ret;
+
+	info->pll = 0;
+
+	/* If we can get a within [-2, 3) MHz of a divider, we'll disable the
+	 * PLL and use the divider instead. */
+	ret = gt215_clk_info(&clk->base, idx, khz, info);
+	diff = khz - ret;
+	if (!pll || (diff >= -2000 && diff < 3000)) {
+		goto out;
+	}
+
+	/* Try with PLL */
+	ret = nvbios_pll_parse(subdev->device->bios, pll, &limits);
+	if (ret)
+		return ret;
+
+	ret = gt215_clk_info(&clk->base, idx - 0x10, limits.refclk, info);
+	if (ret != limits.refclk)
+		return -EINVAL;
+
+	ret = gt215_pll_calc(subdev, &limits, khz, &N, NULL, &M, &P);
+	if (ret >= 0) {
+		info->pll = (P << 16) | (N << 8) | M;
+	}
+
+out:
+	info->fb_delay = max(((khz + 7566) / 15133), (u32) 18);
+	return ret ? ret : -ERANGE;
+}
+
+static int
+calc_clk(struct gt215_clk *clk, struct nvkm_cstate *cstate,
+	 int idx, u32 pll, int dom)
+{
+	int ret = gt215_pll_info(&clk->base, idx, pll, cstate->domain[dom],
+				 &clk->eng[dom]);
+	if (ret >= 0)
+		return 0;
+	return ret;
+}
+
+static int
+calc_host(struct gt215_clk *clk, struct nvkm_cstate *cstate)
+{
+	int ret = 0;
+	u32 kHz = cstate->domain[nv_clk_src_host];
+	struct gt215_clk_info *info = &clk->eng[nv_clk_src_host];
+
+	if (kHz == 277000) {
+		info->clk = 0;
+		info->host_out = NVA3_HOST_277;
+		return 0;
+	}
+
+	info->host_out = NVA3_HOST_CLK;
+
+	ret = gt215_clk_info(&clk->base, 0x1d, kHz, info);
+	if (ret >= 0)
+		return 0;
+
+	return ret;
+}
+
+int
+gt215_clk_pre(struct nvkm_clk *clk, unsigned long *flags)
+{
+	struct nvkm_device *device = clk->subdev.device;
+	struct nvkm_fifo *fifo = device->fifo;
+
+	/* halt and idle execution engines */
+	nvkm_mask(device, 0x020060, 0x00070000, 0x00000000);
+	nvkm_mask(device, 0x002504, 0x00000001, 0x00000001);
+	/* Wait until the interrupt handler is finished */
+	if (nvkm_msec(device, 2000,
+		if (!nvkm_rd32(device, 0x000100))
+			break;
+	) < 0)
+		return -EBUSY;
+
+	if (fifo)
+		nvkm_fifo_pause(fifo, flags);
+
+	if (nvkm_msec(device, 2000,
+		if (nvkm_rd32(device, 0x002504) & 0x00000010)
+			break;
+	) < 0)
+		return -EIO;
+
+	if (nvkm_msec(device, 2000,
+		u32 tmp = nvkm_rd32(device, 0x00251c) & 0x0000003f;
+		if (tmp == 0x0000003f)
+			break;
+	) < 0)
+		return -EIO;
+
+	return 0;
+}
+
+void
+gt215_clk_post(struct nvkm_clk *clk, unsigned long *flags)
+{
+	struct nvkm_device *device = clk->subdev.device;
+	struct nvkm_fifo *fifo = device->fifo;
+
+	if (fifo && flags)
+		nvkm_fifo_start(fifo, flags);
+
+	nvkm_mask(device, 0x002504, 0x00000001, 0x00000000);
+	nvkm_mask(device, 0x020060, 0x00070000, 0x00040000);
+}
+
+static void
+disable_clk_src(struct gt215_clk *clk, u32 src)
+{
+	struct nvkm_device *device = clk->base.subdev.device;
+	nvkm_mask(device, src, 0x00000100, 0x00000000);
+	nvkm_mask(device, src, 0x00000001, 0x00000000);
+}
+
+static void
+prog_pll(struct gt215_clk *clk, int idx, u32 pll, int dom)
+{
+	struct gt215_clk_info *info = &clk->eng[dom];
+	struct nvkm_device *device = clk->base.subdev.device;
+	const u32 src0 = 0x004120 + (idx * 4);
+	const u32 src1 = 0x004160 + (idx * 4);
+	const u32 ctrl = pll + 0;
+	const u32 coef = pll + 4;
+	u32 bypass;
+
+	if (info->pll) {
+		/* Always start from a non-PLL clock */
+		bypass = nvkm_rd32(device, ctrl)  & 0x00000008;
+		if (!bypass) {
+			nvkm_mask(device, src1, 0x00000101, 0x00000101);
+			nvkm_mask(device, ctrl, 0x00000008, 0x00000008);
+			udelay(20);
+		}
+
+		nvkm_mask(device, src0, 0x003f3141, 0x00000101 | info->clk);
+		nvkm_wr32(device, coef, info->pll);
+		nvkm_mask(device, ctrl, 0x00000015, 0x00000015);
+		nvkm_mask(device, ctrl, 0x00000010, 0x00000000);
+		if (nvkm_msec(device, 2000,
+			if (nvkm_rd32(device, ctrl) & 0x00020000)
+				break;
+		) < 0) {
+			nvkm_mask(device, ctrl, 0x00000010, 0x00000010);
+			nvkm_mask(device, src0, 0x00000101, 0x00000000);
+			return;
+		}
+		nvkm_mask(device, ctrl, 0x00000010, 0x00000010);
+		nvkm_mask(device, ctrl, 0x00000008, 0x00000000);
+		disable_clk_src(clk, src1);
+	} else {
+		nvkm_mask(device, src1, 0x003f3141, 0x00000101 | info->clk);
+		nvkm_mask(device, ctrl, 0x00000018, 0x00000018);
+		udelay(20);
+		nvkm_mask(device, ctrl, 0x00000001, 0x00000000);
+		disable_clk_src(clk, src0);
+	}
+}
+
+static void
+prog_clk(struct gt215_clk *clk, int idx, int dom)
+{
+	struct gt215_clk_info *info = &clk->eng[dom];
+	struct nvkm_device *device = clk->base.subdev.device;
+	nvkm_mask(device, 0x004120 + (idx * 4), 0x003f3141, 0x00000101 | info->clk);
+}
+
+static void
+prog_host(struct gt215_clk *clk)
+{
+	struct gt215_clk_info *info = &clk->eng[nv_clk_src_host];
+	struct nvkm_device *device = clk->base.subdev.device;
+	u32 hsrc = (nvkm_rd32(device, 0xc040));
+
+	switch (info->host_out) {
+	case NVA3_HOST_277:
+		if ((hsrc & 0x30000000) == 0) {
+			nvkm_wr32(device, 0xc040, hsrc | 0x20000000);
+			disable_clk_src(clk, 0x4194);
+		}
+		break;
+	case NVA3_HOST_CLK:
+		prog_clk(clk, 0x1d, nv_clk_src_host);
+		if ((hsrc & 0x30000000) >= 0x20000000) {
+			nvkm_wr32(device, 0xc040, hsrc & ~0x30000000);
+		}
+		break;
+	default:
+		break;
+	}
+
+	/* This seems to be a clock gating factor on idle, always set to 64 */
+	nvkm_wr32(device, 0xc044, 0x3e);
+}
+
+static void
+prog_core(struct gt215_clk *clk, int dom)
+{
+	struct gt215_clk_info *info = &clk->eng[dom];
+	struct nvkm_device *device = clk->base.subdev.device;
+	u32 fb_delay = nvkm_rd32(device, 0x10002c);
+
+	if (fb_delay < info->fb_delay)
+		nvkm_wr32(device, 0x10002c, info->fb_delay);
+
+	prog_pll(clk, 0x00, 0x004200, dom);
+
+	if (fb_delay > info->fb_delay)
+		nvkm_wr32(device, 0x10002c, info->fb_delay);
+}
+
+static int
+gt215_clk_calc(struct nvkm_clk *base, struct nvkm_cstate *cstate)
+{
+	struct gt215_clk *clk = gt215_clk(base);
+	struct gt215_clk_info *core = &clk->eng[nv_clk_src_core];
+	int ret;
+
+	if ((ret = calc_clk(clk, cstate, 0x10, 0x4200, nv_clk_src_core)) ||
+	    (ret = calc_clk(clk, cstate, 0x11, 0x4220, nv_clk_src_shader)) ||
+	    (ret = calc_clk(clk, cstate, 0x20, 0x0000, nv_clk_src_disp)) ||
+	    (ret = calc_clk(clk, cstate, 0x21, 0x0000, nv_clk_src_vdec)) ||
+	    (ret = calc_host(clk, cstate)))
+		return ret;
+
+	/* XXX: Should be reading the highest bit in the VBIOS clock to decide
+	 * whether to use a PLL or not... but using a PLL defeats the purpose */
+	if (core->pll) {
+		ret = gt215_clk_info(&clk->base, 0x10,
+				     cstate->domain[nv_clk_src_core_intm],
+				     &clk->eng[nv_clk_src_core_intm]);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int
+gt215_clk_prog(struct nvkm_clk *base)
+{
+	struct gt215_clk *clk = gt215_clk(base);
+	struct gt215_clk_info *core = &clk->eng[nv_clk_src_core];
+	int ret = 0;
+	unsigned long flags;
+	unsigned long *f = &flags;
+
+	ret = gt215_clk_pre(&clk->base, f);
+	if (ret)
+		goto out;
+
+	if (core->pll)
+		prog_core(clk, nv_clk_src_core_intm);
+
+	prog_core(clk,  nv_clk_src_core);
+	prog_pll(clk, 0x01, 0x004220, nv_clk_src_shader);
+	prog_clk(clk, 0x20, nv_clk_src_disp);
+	prog_clk(clk, 0x21, nv_clk_src_vdec);
+	prog_host(clk);
+
+out:
+	if (ret == -EBUSY)
+		f = NULL;
+
+	gt215_clk_post(&clk->base, f);
+	return ret;
+}
+
+static void
+gt215_clk_tidy(struct nvkm_clk *base)
+{
+}
+
+static const struct nvkm_clk_func
+gt215_clk = {
+	.read = gt215_clk_read,
+	.calc = gt215_clk_calc,
+	.prog = gt215_clk_prog,
+	.tidy = gt215_clk_tidy,
+	.domains = {
+		{ nv_clk_src_crystal  , 0xff },
+		{ nv_clk_src_core     , 0x00, 0, "core", 1000 },
+		{ nv_clk_src_shader   , 0x01, 0, "shader", 1000 },
+		{ nv_clk_src_mem      , 0x02, 0, "memory", 1000 },
+		{ nv_clk_src_vdec     , 0x03 },
+		{ nv_clk_src_disp     , 0x04 },
+		{ nv_clk_src_host     , 0x05 },
+		{ nv_clk_src_core_intm, 0x06 },
+		{ nv_clk_src_max }
+	}
+};
+
+int
+gt215_clk_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst,
+	      struct nvkm_clk **pclk)
+{
+	struct gt215_clk *clk;
+
+	if (!(clk = kzalloc(sizeof(*clk), GFP_KERNEL)))
+		return -ENOMEM;
+	*pclk = &clk->base;
+
+	return nvkm_clk_ctor(&gt215_clk, device, type, inst, true, &clk->base);
+}