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, 592 insertions, 0 deletions

diff --git a/drivers/clk/clk-axi-clkgen.c b/drivers/clk/clk-axi-clkgen.c
new file mode 100644
index 000000000..ac6ff736a
--- /dev/null
+++ b/drivers/clk/clk-axi-clkgen.c
@@ -0,0 +1,592 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AXI clkgen driver
+ *
+ * Copyright 2012-2013 Analog Devices Inc.
+ *  Author: Lars-Peter Clausen <lars@metafoo.de>
+ */
+
+#include <linux/platform_device.h>
+#include <linux/clk-provider.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/module.h>
+#include <linux/err.h>
+
+#define AXI_CLKGEN_V2_REG_RESET		0x40
+#define AXI_CLKGEN_V2_REG_CLKSEL	0x44
+#define AXI_CLKGEN_V2_REG_DRP_CNTRL	0x70
+#define AXI_CLKGEN_V2_REG_DRP_STATUS	0x74
+
+#define AXI_CLKGEN_V2_RESET_MMCM_ENABLE	BIT(1)
+#define AXI_CLKGEN_V2_RESET_ENABLE	BIT(0)
+
+#define AXI_CLKGEN_V2_DRP_CNTRL_SEL	BIT(29)
+#define AXI_CLKGEN_V2_DRP_CNTRL_READ	BIT(28)
+
+#define AXI_CLKGEN_V2_DRP_STATUS_BUSY	BIT(16)
+
+#define MMCM_REG_CLKOUT5_2	0x07
+#define MMCM_REG_CLKOUT0_1	0x08
+#define MMCM_REG_CLKOUT0_2	0x09
+#define MMCM_REG_CLKOUT6_2	0x13
+#define MMCM_REG_CLK_FB1	0x14
+#define MMCM_REG_CLK_FB2	0x15
+#define MMCM_REG_CLK_DIV	0x16
+#define MMCM_REG_LOCK1		0x18
+#define MMCM_REG_LOCK2		0x19
+#define MMCM_REG_LOCK3		0x1a
+#define MMCM_REG_POWER		0x28
+#define MMCM_REG_FILTER1	0x4e
+#define MMCM_REG_FILTER2	0x4f
+
+#define MMCM_CLKOUT_NOCOUNT	BIT(6)
+
+#define MMCM_CLK_DIV_DIVIDE	BIT(11)
+#define MMCM_CLK_DIV_NOCOUNT	BIT(12)
+
+struct axi_clkgen_limits {
+	unsigned int fpfd_min;
+	unsigned int fpfd_max;
+	unsigned int fvco_min;
+	unsigned int fvco_max;
+};
+
+struct axi_clkgen {
+	void __iomem *base;
+	struct clk_hw clk_hw;
+	struct axi_clkgen_limits limits;
+};
+
+static uint32_t axi_clkgen_lookup_filter(unsigned int m)
+{
+	switch (m) {
+	case 0:
+		return 0x01001990;
+	case 1:
+		return 0x01001190;
+	case 2:
+		return 0x01009890;
+	case 3:
+		return 0x01001890;
+	case 4:
+		return 0x01008890;
+	case 5 ... 8:
+		return 0x01009090;
+	case 9 ... 11:
+		return 0x01000890;
+	case 12:
+		return 0x08009090;
+	case 13 ... 22:
+		return 0x01001090;
+	case 23 ... 36:
+		return 0x01008090;
+	case 37 ... 46:
+		return 0x08001090;
+	default:
+		return 0x08008090;
+	}
+}
+
+static const uint32_t axi_clkgen_lock_table[] = {
+	0x060603e8, 0x060603e8, 0x080803e8, 0x0b0b03e8,
+	0x0e0e03e8, 0x111103e8, 0x131303e8, 0x161603e8,
+	0x191903e8, 0x1c1c03e8, 0x1f1f0384, 0x1f1f0339,
+	0x1f1f02ee, 0x1f1f02bc, 0x1f1f028a, 0x1f1f0271,
+	0x1f1f023f, 0x1f1f0226, 0x1f1f020d, 0x1f1f01f4,
+	0x1f1f01db, 0x1f1f01c2, 0x1f1f01a9, 0x1f1f0190,
+	0x1f1f0190, 0x1f1f0177, 0x1f1f015e, 0x1f1f015e,
+	0x1f1f0145, 0x1f1f0145, 0x1f1f012c, 0x1f1f012c,
+	0x1f1f012c, 0x1f1f0113, 0x1f1f0113, 0x1f1f0113,
+};
+
+static uint32_t axi_clkgen_lookup_lock(unsigned int m)
+{
+	if (m < ARRAY_SIZE(axi_clkgen_lock_table))
+		return axi_clkgen_lock_table[m];
+	return 0x1f1f00fa;
+}
+
+static const struct axi_clkgen_limits axi_clkgen_zynqmp_default_limits = {
+	.fpfd_min = 10000,
+	.fpfd_max = 450000,
+	.fvco_min = 800000,
+	.fvco_max = 1600000,
+};
+
+static const struct axi_clkgen_limits axi_clkgen_zynq_default_limits = {
+	.fpfd_min = 10000,
+	.fpfd_max = 300000,
+	.fvco_min = 600000,
+	.fvco_max = 1200000,
+};
+
+static void axi_clkgen_calc_params(const struct axi_clkgen_limits *limits,
+	unsigned long fin, unsigned long fout,
+	unsigned int *best_d, unsigned int *best_m, unsigned int *best_dout)
+{
+	unsigned long d, d_min, d_max, _d_min, _d_max;
+	unsigned long m, m_min, m_max;
+	unsigned long f, dout, best_f, fvco;
+	unsigned long fract_shift = 0;
+	unsigned long fvco_min_fract, fvco_max_fract;
+
+	fin /= 1000;
+	fout /= 1000;
+
+	best_f = ULONG_MAX;
+	*best_d = 0;
+	*best_m = 0;
+	*best_dout = 0;
+
+	d_min = max_t(unsigned long, DIV_ROUND_UP(fin, limits->fpfd_max), 1);
+	d_max = min_t(unsigned long, fin / limits->fpfd_min, 80);
+
+again:
+	fvco_min_fract = limits->fvco_min << fract_shift;
+	fvco_max_fract = limits->fvco_max << fract_shift;
+
+	m_min = max_t(unsigned long, DIV_ROUND_UP(fvco_min_fract, fin) * d_min, 1);
+	m_max = min_t(unsigned long, fvco_max_fract * d_max / fin, 64 << fract_shift);
+
+	for (m = m_min; m <= m_max; m++) {
+		_d_min = max(d_min, DIV_ROUND_UP(fin * m, fvco_max_fract));
+		_d_max = min(d_max, fin * m / fvco_min_fract);
+
+		for (d = _d_min; d <= _d_max; d++) {
+			fvco = fin * m / d;
+
+			dout = DIV_ROUND_CLOSEST(fvco, fout);
+			dout = clamp_t(unsigned long, dout, 1, 128 << fract_shift);
+			f = fvco / dout;
+			if (abs(f - fout) < abs(best_f - fout)) {
+				best_f = f;
+				*best_d = d;
+				*best_m = m << (3 - fract_shift);
+				*best_dout = dout << (3 - fract_shift);
+				if (best_f == fout)
+					return;
+			}
+		}
+	}
+
+	/* Lets see if we find a better setting in fractional mode */
+	if (fract_shift == 0) {
+		fract_shift = 3;
+		goto again;
+	}
+}
+
+struct axi_clkgen_div_params {
+	unsigned int low;
+	unsigned int high;
+	unsigned int edge;
+	unsigned int nocount;
+	unsigned int frac_en;
+	unsigned int frac;
+	unsigned int frac_wf_f;
+	unsigned int frac_wf_r;
+	unsigned int frac_phase;
+};
+
+static void axi_clkgen_calc_clk_params(unsigned int divider,
+	unsigned int frac_divider, struct axi_clkgen_div_params *params)
+{
+
+	memset(params, 0x0, sizeof(*params));
+
+	if (divider == 1) {
+		params->nocount = 1;
+		return;
+	}
+
+	if (frac_divider == 0) {
+		params->high = divider / 2;
+		params->edge = divider % 2;
+		params->low = divider - params->high;
+	} else {
+		params->frac_en = 1;
+		params->frac = frac_divider;
+
+		params->high = divider / 2;
+		params->edge = divider % 2;
+		params->low = params->high;
+
+		if (params->edge == 0) {
+			params->high--;
+			params->frac_wf_r = 1;
+		}
+
+		if (params->edge == 0 || frac_divider == 1)
+			params->low--;
+		if (((params->edge == 0) ^ (frac_divider == 1)) ||
+			(divider == 2 && frac_divider == 1))
+			params->frac_wf_f = 1;
+
+		params->frac_phase = params->edge * 4 + frac_divider / 2;
+	}
+}
+
+static void axi_clkgen_write(struct axi_clkgen *axi_clkgen,
+	unsigned int reg, unsigned int val)
+{
+	writel(val, axi_clkgen->base + reg);
+}
+
+static void axi_clkgen_read(struct axi_clkgen *axi_clkgen,
+	unsigned int reg, unsigned int *val)
+{
+	*val = readl(axi_clkgen->base + reg);
+}
+
+static int axi_clkgen_wait_non_busy(struct axi_clkgen *axi_clkgen)
+{
+	unsigned int timeout = 10000;
+	unsigned int val;
+
+	do {
+		axi_clkgen_read(axi_clkgen, AXI_CLKGEN_V2_REG_DRP_STATUS, &val);
+	} while ((val & AXI_CLKGEN_V2_DRP_STATUS_BUSY) && --timeout);
+
+	if (val & AXI_CLKGEN_V2_DRP_STATUS_BUSY)
+		return -EIO;
+
+	return val & 0xffff;
+}
+
+static int axi_clkgen_mmcm_read(struct axi_clkgen *axi_clkgen,
+	unsigned int reg, unsigned int *val)
+{
+	unsigned int reg_val;
+	int ret;
+
+	ret = axi_clkgen_wait_non_busy(axi_clkgen);
+	if (ret < 0)
+		return ret;
+
+	reg_val = AXI_CLKGEN_V2_DRP_CNTRL_SEL | AXI_CLKGEN_V2_DRP_CNTRL_READ;
+	reg_val |= (reg << 16);
+
+	axi_clkgen_write(axi_clkgen, AXI_CLKGEN_V2_REG_DRP_CNTRL, reg_val);
+
+	ret = axi_clkgen_wait_non_busy(axi_clkgen);
+	if (ret < 0)
+		return ret;
+
+	*val = ret;
+
+	return 0;
+}
+
+static int axi_clkgen_mmcm_write(struct axi_clkgen *axi_clkgen,
+	unsigned int reg, unsigned int val, unsigned int mask)
+{
+	unsigned int reg_val = 0;
+	int ret;
+
+	ret = axi_clkgen_wait_non_busy(axi_clkgen);
+	if (ret < 0)
+		return ret;
+
+	if (mask != 0xffff) {
+		axi_clkgen_mmcm_read(axi_clkgen, reg, &reg_val);
+		reg_val &= ~mask;
+	}
+
+	reg_val |= AXI_CLKGEN_V2_DRP_CNTRL_SEL | (reg << 16) | (val & mask);
+
+	axi_clkgen_write(axi_clkgen, AXI_CLKGEN_V2_REG_DRP_CNTRL, reg_val);
+
+	return 0;
+}
+
+static void axi_clkgen_mmcm_enable(struct axi_clkgen *axi_clkgen,
+	bool enable)
+{
+	unsigned int val = AXI_CLKGEN_V2_RESET_ENABLE;
+
+	if (enable)
+		val |= AXI_CLKGEN_V2_RESET_MMCM_ENABLE;
+
+	axi_clkgen_write(axi_clkgen, AXI_CLKGEN_V2_REG_RESET, val);
+}
+
+static struct axi_clkgen *clk_hw_to_axi_clkgen(struct clk_hw *clk_hw)
+{
+	return container_of(clk_hw, struct axi_clkgen, clk_hw);
+}
+
+static void axi_clkgen_set_div(struct axi_clkgen *axi_clkgen,
+	unsigned int reg1, unsigned int reg2, unsigned int reg3,
+	struct axi_clkgen_div_params *params)
+{
+	axi_clkgen_mmcm_write(axi_clkgen, reg1,
+		(params->high << 6) | params->low, 0xefff);
+	axi_clkgen_mmcm_write(axi_clkgen, reg2,
+		(params->frac << 12) | (params->frac_en << 11) |
+		(params->frac_wf_r << 10) | (params->edge << 7) |
+		(params->nocount << 6), 0x7fff);
+	if (reg3 != 0) {
+		axi_clkgen_mmcm_write(axi_clkgen, reg3,
+			(params->frac_phase << 11) | (params->frac_wf_f << 10), 0x3c00);
+	}
+}
+
+static int axi_clkgen_set_rate(struct clk_hw *clk_hw,
+	unsigned long rate, unsigned long parent_rate)
+{
+	struct axi_clkgen *axi_clkgen = clk_hw_to_axi_clkgen(clk_hw);
+	const struct axi_clkgen_limits *limits = &axi_clkgen->limits;
+	unsigned int d, m, dout;
+	struct axi_clkgen_div_params params;
+	uint32_t power = 0;
+	uint32_t filter;
+	uint32_t lock;
+
+	if (parent_rate == 0 || rate == 0)
+		return -EINVAL;
+
+	axi_clkgen_calc_params(limits, parent_rate, rate, &d, &m, &dout);
+
+	if (d == 0 || dout == 0 || m == 0)
+		return -EINVAL;
+
+	if ((dout & 0x7) != 0 || (m & 0x7) != 0)
+		power |= 0x9800;
+
+	axi_clkgen_mmcm_write(axi_clkgen, MMCM_REG_POWER, power, 0x9800);
+
+	filter = axi_clkgen_lookup_filter(m - 1);
+	lock = axi_clkgen_lookup_lock(m - 1);
+
+	axi_clkgen_calc_clk_params(dout >> 3, dout & 0x7, &params);
+	axi_clkgen_set_div(axi_clkgen,  MMCM_REG_CLKOUT0_1, MMCM_REG_CLKOUT0_2,
+		MMCM_REG_CLKOUT5_2, &params);
+
+	axi_clkgen_calc_clk_params(d, 0, &params);
+	axi_clkgen_mmcm_write(axi_clkgen, MMCM_REG_CLK_DIV,
+		(params.edge << 13) | (params.nocount << 12) |
+		(params.high << 6) | params.low, 0x3fff);
+
+	axi_clkgen_calc_clk_params(m >> 3, m & 0x7, &params);
+	axi_clkgen_set_div(axi_clkgen,  MMCM_REG_CLK_FB1, MMCM_REG_CLK_FB2,
+		MMCM_REG_CLKOUT6_2, &params);
+
+	axi_clkgen_mmcm_write(axi_clkgen, MMCM_REG_LOCK1, lock & 0x3ff, 0x3ff);
+	axi_clkgen_mmcm_write(axi_clkgen, MMCM_REG_LOCK2,
+		(((lock >> 16) & 0x1f) << 10) | 0x1, 0x7fff);
+	axi_clkgen_mmcm_write(axi_clkgen, MMCM_REG_LOCK3,
+		(((lock >> 24) & 0x1f) << 10) | 0x3e9, 0x7fff);
+	axi_clkgen_mmcm_write(axi_clkgen, MMCM_REG_FILTER1, filter >> 16, 0x9900);
+	axi_clkgen_mmcm_write(axi_clkgen, MMCM_REG_FILTER2, filter, 0x9900);
+
+	return 0;
+}
+
+static long axi_clkgen_round_rate(struct clk_hw *hw, unsigned long rate,
+	unsigned long *parent_rate)
+{
+	struct axi_clkgen *axi_clkgen = clk_hw_to_axi_clkgen(hw);
+	const struct axi_clkgen_limits *limits = &axi_clkgen->limits;
+	unsigned int d, m, dout;
+	unsigned long long tmp;
+
+	axi_clkgen_calc_params(limits, *parent_rate, rate, &d, &m, &dout);
+
+	if (d == 0 || dout == 0 || m == 0)
+		return -EINVAL;
+
+	tmp = (unsigned long long)*parent_rate * m;
+	tmp = DIV_ROUND_CLOSEST_ULL(tmp, dout * d);
+
+	return min_t(unsigned long long, tmp, LONG_MAX);
+}
+
+static unsigned int axi_clkgen_get_div(struct axi_clkgen *axi_clkgen,
+	unsigned int reg1, unsigned int reg2)
+{
+	unsigned int val1, val2;
+	unsigned int div;
+
+	axi_clkgen_mmcm_read(axi_clkgen, reg2, &val2);
+	if (val2 & MMCM_CLKOUT_NOCOUNT)
+		return 8;
+
+	axi_clkgen_mmcm_read(axi_clkgen, reg1, &val1);
+
+	div = (val1 & 0x3f) + ((val1 >> 6) & 0x3f);
+	div <<= 3;
+
+	if (val2 & MMCM_CLK_DIV_DIVIDE) {
+		if ((val2 & BIT(7)) && (val2 & 0x7000) != 0x1000)
+			div += 8;
+		else
+			div += 16;
+
+		div += (val2 >> 12) & 0x7;
+	}
+
+	return div;
+}
+
+static unsigned long axi_clkgen_recalc_rate(struct clk_hw *clk_hw,
+	unsigned long parent_rate)
+{
+	struct axi_clkgen *axi_clkgen = clk_hw_to_axi_clkgen(clk_hw);
+	unsigned int d, m, dout;
+	unsigned long long tmp;
+	unsigned int val;
+
+	dout = axi_clkgen_get_div(axi_clkgen, MMCM_REG_CLKOUT0_1,
+		MMCM_REG_CLKOUT0_2);
+	m = axi_clkgen_get_div(axi_clkgen, MMCM_REG_CLK_FB1,
+		MMCM_REG_CLK_FB2);
+
+	axi_clkgen_mmcm_read(axi_clkgen, MMCM_REG_CLK_DIV, &val);
+	if (val & MMCM_CLK_DIV_NOCOUNT)
+		d = 1;
+	else
+		d = (val & 0x3f) + ((val >> 6) & 0x3f);
+
+	if (d == 0 || dout == 0)
+		return 0;
+
+	tmp = (unsigned long long)parent_rate * m;
+	tmp = DIV_ROUND_CLOSEST_ULL(tmp, dout * d);
+
+	return min_t(unsigned long long, tmp, ULONG_MAX);
+}
+
+static int axi_clkgen_enable(struct clk_hw *clk_hw)
+{
+	struct axi_clkgen *axi_clkgen = clk_hw_to_axi_clkgen(clk_hw);
+
+	axi_clkgen_mmcm_enable(axi_clkgen, true);
+
+	return 0;
+}
+
+static void axi_clkgen_disable(struct clk_hw *clk_hw)
+{
+	struct axi_clkgen *axi_clkgen = clk_hw_to_axi_clkgen(clk_hw);
+
+	axi_clkgen_mmcm_enable(axi_clkgen, false);
+}
+
+static int axi_clkgen_set_parent(struct clk_hw *clk_hw, u8 index)
+{
+	struct axi_clkgen *axi_clkgen = clk_hw_to_axi_clkgen(clk_hw);
+
+	axi_clkgen_write(axi_clkgen, AXI_CLKGEN_V2_REG_CLKSEL, index);
+
+	return 0;
+}
+
+static u8 axi_clkgen_get_parent(struct clk_hw *clk_hw)
+{
+	struct axi_clkgen *axi_clkgen = clk_hw_to_axi_clkgen(clk_hw);
+	unsigned int parent;
+
+	axi_clkgen_read(axi_clkgen, AXI_CLKGEN_V2_REG_CLKSEL, &parent);
+
+	return parent;
+}
+
+static const struct clk_ops axi_clkgen_ops = {
+	.recalc_rate = axi_clkgen_recalc_rate,
+	.round_rate = axi_clkgen_round_rate,
+	.set_rate = axi_clkgen_set_rate,
+	.enable = axi_clkgen_enable,
+	.disable = axi_clkgen_disable,
+	.set_parent = axi_clkgen_set_parent,
+	.get_parent = axi_clkgen_get_parent,
+};
+
+static int axi_clkgen_probe(struct platform_device *pdev)
+{
+	const struct axi_clkgen_limits *dflt_limits;
+	struct axi_clkgen *axi_clkgen;
+	struct clk_init_data init;
+	const char *parent_names[2];
+	const char *clk_name;
+	unsigned int i;
+	int ret;
+
+	dflt_limits = device_get_match_data(&pdev->dev);
+	if (!dflt_limits)
+		return -ENODEV;
+
+	axi_clkgen = devm_kzalloc(&pdev->dev, sizeof(*axi_clkgen), GFP_KERNEL);
+	if (!axi_clkgen)
+		return -ENOMEM;
+
+	axi_clkgen->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(axi_clkgen->base))
+		return PTR_ERR(axi_clkgen->base);
+
+	init.num_parents = of_clk_get_parent_count(pdev->dev.of_node);
+	if (init.num_parents < 1 || init.num_parents > 2)
+		return -EINVAL;
+
+	for (i = 0; i < init.num_parents; i++) {
+		parent_names[i] = of_clk_get_parent_name(pdev->dev.of_node, i);
+		if (!parent_names[i])
+			return -EINVAL;
+	}
+
+	memcpy(&axi_clkgen->limits, dflt_limits, sizeof(axi_clkgen->limits));
+
+	clk_name = pdev->dev.of_node->name;
+	of_property_read_string(pdev->dev.of_node, "clock-output-names",
+		&clk_name);
+
+	init.name = clk_name;
+	init.ops = &axi_clkgen_ops;
+	init.flags = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE;
+	init.parent_names = parent_names;
+
+	axi_clkgen_mmcm_enable(axi_clkgen, false);
+
+	axi_clkgen->clk_hw.init = &init;
+	ret = devm_clk_hw_register(&pdev->dev, &axi_clkgen->clk_hw);
+	if (ret)
+		return ret;
+
+	return of_clk_add_hw_provider(pdev->dev.of_node, of_clk_hw_simple_get,
+				      &axi_clkgen->clk_hw);
+}
+
+static int axi_clkgen_remove(struct platform_device *pdev)
+{
+	of_clk_del_provider(pdev->dev.of_node);
+
+	return 0;
+}
+
+static const struct of_device_id axi_clkgen_ids[] = {
+	{
+		.compatible = "adi,zynqmp-axi-clkgen-2.00.a",
+		.data = &axi_clkgen_zynqmp_default_limits,
+	},
+	{
+		.compatible = "adi,axi-clkgen-2.00.a",
+		.data = &axi_clkgen_zynq_default_limits,
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, axi_clkgen_ids);
+
+static struct platform_driver axi_clkgen_driver = {
+	.driver = {
+		.name = "adi-axi-clkgen",
+		.of_match_table = axi_clkgen_ids,
+	},
+	.probe = axi_clkgen_probe,
+	.remove = axi_clkgen_remove,
+};
+module_platform_driver(axi_clkgen_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
+MODULE_DESCRIPTION("Driver for the Analog Devices' AXI clkgen pcore clock generator");