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, 563 insertions, 0 deletions

diff --git a/drivers/clk/qcom/clk-cpu-8996.c b/drivers/clk/qcom/clk-cpu-8996.c
new file mode 100644
index 000000000..ee76ef958
--- /dev/null
+++ b/drivers/clk/qcom/clk-cpu-8996.c
@@ -0,0 +1,563 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2020, The Linux Foundation. All rights reserved.
+ */
+
+/*
+ * Each of the CPU clusters (Power and Perf) on msm8996 are
+ * clocked via 2 PLLs, a primary and alternate. There are also
+ * 2 Mux'es, a primary and secondary all connected together
+ * as shown below
+ *
+ *                              +-------+
+ *               XO             |       |
+ *           +------------------>0      |
+ *                              |       |
+ *                    PLL/2     | SMUX  +----+
+ *                      +------->1      |    |
+ *                      |       |       |    |
+ *                      |       +-------+    |    +-------+
+ *                      |                    +---->0      |
+ *                      |                         |       |
+ * +---------------+    |             +----------->1      | CPU clk
+ * |Primary PLL    +----+ PLL_EARLY   |           |       +------>
+ * |               +------+-----------+    +------>2 PMUX |
+ * +---------------+      |                |      |       |
+ *                        |   +------+     |   +-->3      |
+ *                        +--^+  ACD +-----+   |  +-------+
+ * +---------------+          +------+         |
+ * |Alt PLL        |                           |
+ * |               +---------------------------+
+ * +---------------+         PLL_EARLY
+ *
+ * The primary PLL is what drives the CPU clk, except for times
+ * when we are reprogramming the PLL itself (for rate changes) when
+ * we temporarily switch to an alternate PLL.
+ *
+ * The primary PLL operates on a single VCO range, between 600MHz
+ * and 3GHz. However the CPUs do support OPPs with frequencies
+ * between 300MHz and 600MHz. In order to support running the CPUs
+ * at those frequencies we end up having to lock the PLL at twice
+ * the rate and drive the CPU clk via the PLL/2 output and SMUX.
+ *
+ * So for frequencies above 600MHz we follow the following path
+ *  Primary PLL --> PLL_EARLY --> PMUX(1) --> CPU clk
+ * and for frequencies between 300MHz and 600MHz we follow
+ *  Primary PLL --> PLL/2 --> SMUX(1) --> PMUX(0) --> CPU clk
+ *
+ * ACD stands for Adaptive Clock Distribution and is used to
+ * detect voltage droops.
+ */
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <soc/qcom/kryo-l2-accessors.h>
+
+#include "clk-alpha-pll.h"
+#include "clk-regmap.h"
+#include "clk-regmap-mux.h"
+
+enum _pmux_input {
+	SMUX_INDEX = 0,
+	PLL_INDEX,
+	ACD_INDEX,
+	ALT_INDEX,
+	NUM_OF_PMUX_INPUTS
+};
+
+#define DIV_2_THRESHOLD		600000000
+#define PWRCL_REG_OFFSET 0x0
+#define PERFCL_REG_OFFSET 0x80000
+#define MUX_OFFSET	0x40
+#define ALT_PLL_OFFSET	0x100
+#define SSSCTL_OFFSET 0x160
+
+#define PMUX_MASK	0x3
+
+static const u8 prim_pll_regs[PLL_OFF_MAX_REGS] = {
+	[PLL_OFF_L_VAL] = 0x04,
+	[PLL_OFF_ALPHA_VAL] = 0x08,
+	[PLL_OFF_USER_CTL] = 0x10,
+	[PLL_OFF_CONFIG_CTL] = 0x18,
+	[PLL_OFF_CONFIG_CTL_U] = 0x1c,
+	[PLL_OFF_TEST_CTL] = 0x20,
+	[PLL_OFF_TEST_CTL_U] = 0x24,
+	[PLL_OFF_STATUS] = 0x28,
+};
+
+static const u8 alt_pll_regs[PLL_OFF_MAX_REGS] = {
+	[PLL_OFF_L_VAL] = 0x04,
+	[PLL_OFF_ALPHA_VAL] = 0x08,
+	[PLL_OFF_ALPHA_VAL_U] = 0x0c,
+	[PLL_OFF_USER_CTL] = 0x10,
+	[PLL_OFF_USER_CTL_U] = 0x14,
+	[PLL_OFF_CONFIG_CTL] = 0x18,
+	[PLL_OFF_TEST_CTL] = 0x20,
+	[PLL_OFF_TEST_CTL_U] = 0x24,
+	[PLL_OFF_STATUS] = 0x28,
+};
+
+/* PLLs */
+
+static const struct alpha_pll_config hfpll_config = {
+	.l = 60,
+	.config_ctl_val = 0x200d4aa8,
+	.config_ctl_hi_val = 0x006,
+	.pre_div_mask = BIT(12),
+	.post_div_mask = 0x3 << 8,
+	.post_div_val = 0x1 << 8,
+	.main_output_mask = BIT(0),
+	.early_output_mask = BIT(3),
+};
+
+static const struct clk_parent_data pll_parent[] = {
+	{ .fw_name = "xo" },
+};
+
+static struct clk_alpha_pll pwrcl_pll = {
+	.offset = PWRCL_REG_OFFSET,
+	.regs = prim_pll_regs,
+	.flags = SUPPORTS_DYNAMIC_UPDATE | SUPPORTS_FSM_MODE,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "pwrcl_pll",
+		.parent_data = pll_parent,
+		.num_parents = ARRAY_SIZE(pll_parent),
+		.ops = &clk_alpha_pll_huayra_ops,
+	},
+};
+
+static struct clk_alpha_pll perfcl_pll = {
+	.offset = PERFCL_REG_OFFSET,
+	.regs = prim_pll_regs,
+	.flags = SUPPORTS_DYNAMIC_UPDATE | SUPPORTS_FSM_MODE,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "perfcl_pll",
+		.parent_data = pll_parent,
+		.num_parents = ARRAY_SIZE(pll_parent),
+		.ops = &clk_alpha_pll_huayra_ops,
+	},
+};
+
+static struct clk_fixed_factor pwrcl_pll_postdiv = {
+	.mult = 1,
+	.div = 2,
+	.hw.init = &(struct clk_init_data){
+		.name = "pwrcl_pll_postdiv",
+		.parent_data = &(const struct clk_parent_data){
+			.hw = &pwrcl_pll.clkr.hw
+		},
+		.num_parents = 1,
+		.ops = &clk_fixed_factor_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_fixed_factor perfcl_pll_postdiv = {
+	.mult = 1,
+	.div = 2,
+	.hw.init = &(struct clk_init_data){
+		.name = "perfcl_pll_postdiv",
+		.parent_data = &(const struct clk_parent_data){
+			.hw = &perfcl_pll.clkr.hw
+		},
+		.num_parents = 1,
+		.ops = &clk_fixed_factor_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_fixed_factor perfcl_pll_acd = {
+	.mult = 1,
+	.div = 1,
+	.hw.init = &(struct clk_init_data){
+		.name = "perfcl_pll_acd",
+		.parent_data = &(const struct clk_parent_data){
+			.hw = &perfcl_pll.clkr.hw
+		},
+		.num_parents = 1,
+		.ops = &clk_fixed_factor_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_fixed_factor pwrcl_pll_acd = {
+	.mult = 1,
+	.div = 1,
+	.hw.init = &(struct clk_init_data){
+		.name = "pwrcl_pll_acd",
+		.parent_data = &(const struct clk_parent_data){
+			.hw = &pwrcl_pll.clkr.hw
+		},
+		.num_parents = 1,
+		.ops = &clk_fixed_factor_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static const struct pll_vco alt_pll_vco_modes[] = {
+	VCO(3,  250000000,  500000000),
+	VCO(2,  500000000,  750000000),
+	VCO(1,  750000000, 1000000000),
+	VCO(0, 1000000000, 2150400000),
+};
+
+static const struct alpha_pll_config altpll_config = {
+	.l = 16,
+	.vco_val = 0x3 << 20,
+	.vco_mask = 0x3 << 20,
+	.config_ctl_val = 0x4001051b,
+	.post_div_mask = 0x3 << 8,
+	.post_div_val = 0x1 << 8,
+	.main_output_mask = BIT(0),
+	.early_output_mask = BIT(3),
+};
+
+static struct clk_alpha_pll pwrcl_alt_pll = {
+	.offset = PWRCL_REG_OFFSET + ALT_PLL_OFFSET,
+	.regs = alt_pll_regs,
+	.vco_table = alt_pll_vco_modes,
+	.num_vco = ARRAY_SIZE(alt_pll_vco_modes),
+	.flags = SUPPORTS_OFFLINE_REQ | SUPPORTS_FSM_MODE,
+	.clkr.hw.init = &(struct clk_init_data) {
+		.name = "pwrcl_alt_pll",
+		.parent_data = pll_parent,
+		.num_parents = ARRAY_SIZE(pll_parent),
+		.ops = &clk_alpha_pll_hwfsm_ops,
+	},
+};
+
+static struct clk_alpha_pll perfcl_alt_pll = {
+	.offset = PERFCL_REG_OFFSET + ALT_PLL_OFFSET,
+	.regs = alt_pll_regs,
+	.vco_table = alt_pll_vco_modes,
+	.num_vco = ARRAY_SIZE(alt_pll_vco_modes),
+	.flags = SUPPORTS_OFFLINE_REQ | SUPPORTS_FSM_MODE,
+	.clkr.hw.init = &(struct clk_init_data) {
+		.name = "perfcl_alt_pll",
+		.parent_data = pll_parent,
+		.num_parents = ARRAY_SIZE(pll_parent),
+		.ops = &clk_alpha_pll_hwfsm_ops,
+	},
+};
+
+struct clk_cpu_8996_pmux {
+	u32	reg;
+	struct notifier_block nb;
+	struct clk_regmap clkr;
+};
+
+static int cpu_clk_notifier_cb(struct notifier_block *nb, unsigned long event,
+			       void *data);
+
+#define to_clk_cpu_8996_pmux_nb(_nb) \
+	container_of(_nb, struct clk_cpu_8996_pmux, nb)
+
+static inline struct clk_cpu_8996_pmux *to_clk_cpu_8996_pmux_hw(struct clk_hw *hw)
+{
+	return container_of(to_clk_regmap(hw), struct clk_cpu_8996_pmux, clkr);
+}
+
+static u8 clk_cpu_8996_pmux_get_parent(struct clk_hw *hw)
+{
+	struct clk_regmap *clkr = to_clk_regmap(hw);
+	struct clk_cpu_8996_pmux *cpuclk = to_clk_cpu_8996_pmux_hw(hw);
+	u32 val;
+
+	regmap_read(clkr->regmap, cpuclk->reg, &val);
+
+	return FIELD_GET(PMUX_MASK, val);
+}
+
+static int clk_cpu_8996_pmux_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct clk_regmap *clkr = to_clk_regmap(hw);
+	struct clk_cpu_8996_pmux *cpuclk = to_clk_cpu_8996_pmux_hw(hw);
+	u32 val;
+
+	val = FIELD_PREP(PMUX_MASK, index);
+
+	return regmap_update_bits(clkr->regmap, cpuclk->reg, PMUX_MASK, val);
+}
+
+static int clk_cpu_8996_pmux_determine_rate(struct clk_hw *hw,
+					   struct clk_rate_request *req)
+{
+	struct clk_hw *parent;
+
+	if (req->rate < (DIV_2_THRESHOLD / 2))
+		return -EINVAL;
+
+	if (req->rate < DIV_2_THRESHOLD)
+		parent = clk_hw_get_parent_by_index(hw, SMUX_INDEX);
+	else
+		parent = clk_hw_get_parent_by_index(hw, ACD_INDEX);
+	if (!parent)
+		return -EINVAL;
+
+	req->best_parent_rate = clk_hw_round_rate(parent, req->rate);
+	req->best_parent_hw = parent;
+
+	return 0;
+}
+
+static const struct clk_ops clk_cpu_8996_pmux_ops = {
+	.set_parent = clk_cpu_8996_pmux_set_parent,
+	.get_parent = clk_cpu_8996_pmux_get_parent,
+	.determine_rate = clk_cpu_8996_pmux_determine_rate,
+};
+
+static const struct clk_parent_data pwrcl_smux_parents[] = {
+	{ .fw_name = "xo" },
+	{ .hw = &pwrcl_pll_postdiv.hw },
+};
+
+static const struct clk_parent_data perfcl_smux_parents[] = {
+	{ .fw_name = "xo" },
+	{ .hw = &perfcl_pll_postdiv.hw },
+};
+
+static struct clk_regmap_mux pwrcl_smux = {
+	.reg = PWRCL_REG_OFFSET + MUX_OFFSET,
+	.shift = 2,
+	.width = 2,
+	.clkr.hw.init = &(struct clk_init_data) {
+		.name = "pwrcl_smux",
+		.parent_data = pwrcl_smux_parents,
+		.num_parents = ARRAY_SIZE(pwrcl_smux_parents),
+		.ops = &clk_regmap_mux_closest_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_regmap_mux perfcl_smux = {
+	.reg = PERFCL_REG_OFFSET + MUX_OFFSET,
+	.shift = 2,
+	.width = 2,
+	.clkr.hw.init = &(struct clk_init_data) {
+		.name = "perfcl_smux",
+		.parent_data = perfcl_smux_parents,
+		.num_parents = ARRAY_SIZE(perfcl_smux_parents),
+		.ops = &clk_regmap_mux_closest_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static const struct clk_hw *pwrcl_pmux_parents[] = {
+	[SMUX_INDEX] = &pwrcl_smux.clkr.hw,
+	[PLL_INDEX] = &pwrcl_pll.clkr.hw,
+	[ACD_INDEX] = &pwrcl_pll_acd.hw,
+	[ALT_INDEX] = &pwrcl_alt_pll.clkr.hw,
+};
+
+static const struct clk_hw *perfcl_pmux_parents[] = {
+	[SMUX_INDEX] = &perfcl_smux.clkr.hw,
+	[PLL_INDEX] = &perfcl_pll.clkr.hw,
+	[ACD_INDEX] = &perfcl_pll_acd.hw,
+	[ALT_INDEX] = &perfcl_alt_pll.clkr.hw,
+};
+
+static struct clk_cpu_8996_pmux pwrcl_pmux = {
+	.reg = PWRCL_REG_OFFSET + MUX_OFFSET,
+	.nb.notifier_call = cpu_clk_notifier_cb,
+	.clkr.hw.init = &(struct clk_init_data) {
+		.name = "pwrcl_pmux",
+		.parent_hws = pwrcl_pmux_parents,
+		.num_parents = ARRAY_SIZE(pwrcl_pmux_parents),
+		.ops = &clk_cpu_8996_pmux_ops,
+		/* CPU clock is critical and should never be gated */
+		.flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL,
+	},
+};
+
+static struct clk_cpu_8996_pmux perfcl_pmux = {
+	.reg = PERFCL_REG_OFFSET + MUX_OFFSET,
+	.nb.notifier_call = cpu_clk_notifier_cb,
+	.clkr.hw.init = &(struct clk_init_data) {
+		.name = "perfcl_pmux",
+		.parent_hws = perfcl_pmux_parents,
+		.num_parents = ARRAY_SIZE(perfcl_pmux_parents),
+		.ops = &clk_cpu_8996_pmux_ops,
+		/* CPU clock is critical and should never be gated */
+		.flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL,
+	},
+};
+
+static const struct regmap_config cpu_msm8996_regmap_config = {
+	.reg_bits		= 32,
+	.reg_stride		= 4,
+	.val_bits		= 32,
+	.max_register		= 0x80210,
+	.fast_io		= true,
+	.val_format_endian	= REGMAP_ENDIAN_LITTLE,
+};
+
+static struct clk_hw *cpu_msm8996_hw_clks[] = {
+	&pwrcl_pll_postdiv.hw,
+	&perfcl_pll_postdiv.hw,
+	&pwrcl_pll_acd.hw,
+	&perfcl_pll_acd.hw,
+};
+
+static struct clk_regmap *cpu_msm8996_clks[] = {
+	&pwrcl_pll.clkr,
+	&perfcl_pll.clkr,
+	&pwrcl_alt_pll.clkr,
+	&perfcl_alt_pll.clkr,
+	&pwrcl_smux.clkr,
+	&perfcl_smux.clkr,
+	&pwrcl_pmux.clkr,
+	&perfcl_pmux.clkr,
+};
+
+static int qcom_cpu_clk_msm8996_register_clks(struct device *dev,
+					      struct regmap *regmap)
+{
+	int i, ret;
+
+	for (i = 0; i < ARRAY_SIZE(cpu_msm8996_hw_clks); i++) {
+		ret = devm_clk_hw_register(dev, cpu_msm8996_hw_clks[i]);
+		if (ret)
+			return ret;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(cpu_msm8996_clks); i++) {
+		ret = devm_clk_register_regmap(dev, cpu_msm8996_clks[i]);
+		if (ret)
+			return ret;
+	}
+
+	clk_alpha_pll_configure(&pwrcl_pll, regmap, &hfpll_config);
+	clk_alpha_pll_configure(&perfcl_pll, regmap, &hfpll_config);
+	clk_alpha_pll_configure(&pwrcl_alt_pll, regmap, &altpll_config);
+	clk_alpha_pll_configure(&perfcl_alt_pll, regmap, &altpll_config);
+
+	/* Enable alt PLLs */
+	clk_prepare_enable(pwrcl_alt_pll.clkr.hw.clk);
+	clk_prepare_enable(perfcl_alt_pll.clkr.hw.clk);
+
+	devm_clk_notifier_register(dev, pwrcl_pmux.clkr.hw.clk, &pwrcl_pmux.nb);
+	devm_clk_notifier_register(dev, perfcl_pmux.clkr.hw.clk, &perfcl_pmux.nb);
+
+	return ret;
+}
+
+#define CPU_AFINITY_MASK 0xFFF
+#define PWRCL_CPU_REG_MASK 0x3
+#define PERFCL_CPU_REG_MASK 0x103
+
+#define L2ACDCR_REG 0x580ULL
+#define L2ACDTD_REG 0x581ULL
+#define L2ACDDVMRC_REG 0x584ULL
+#define L2ACDSSCR_REG 0x589ULL
+
+static DEFINE_SPINLOCK(qcom_clk_acd_lock);
+static void __iomem *base;
+
+static void qcom_cpu_clk_msm8996_acd_init(void __iomem *base)
+{
+	u64 hwid;
+	unsigned long flags;
+
+	spin_lock_irqsave(&qcom_clk_acd_lock, flags);
+
+	hwid = read_cpuid_mpidr() & CPU_AFINITY_MASK;
+
+	kryo_l2_set_indirect_reg(L2ACDTD_REG, 0x00006a11);
+	kryo_l2_set_indirect_reg(L2ACDDVMRC_REG, 0x000e0f0f);
+	kryo_l2_set_indirect_reg(L2ACDSSCR_REG, 0x00000601);
+
+	if (PWRCL_CPU_REG_MASK == (hwid | PWRCL_CPU_REG_MASK)) {
+		writel(0xf, base + PWRCL_REG_OFFSET + SSSCTL_OFFSET);
+		kryo_l2_set_indirect_reg(L2ACDCR_REG, 0x002c5ffd);
+	}
+
+	if (PERFCL_CPU_REG_MASK == (hwid | PERFCL_CPU_REG_MASK)) {
+		kryo_l2_set_indirect_reg(L2ACDCR_REG, 0x002c5ffd);
+		writel(0xf, base + PERFCL_REG_OFFSET + SSSCTL_OFFSET);
+	}
+
+	spin_unlock_irqrestore(&qcom_clk_acd_lock, flags);
+}
+
+static int cpu_clk_notifier_cb(struct notifier_block *nb, unsigned long event,
+			       void *data)
+{
+	struct clk_cpu_8996_pmux *cpuclk = to_clk_cpu_8996_pmux_nb(nb);
+	struct clk_notifier_data *cnd = data;
+	int ret;
+
+	switch (event) {
+	case PRE_RATE_CHANGE:
+		ret = clk_cpu_8996_pmux_set_parent(&cpuclk->clkr.hw, ALT_INDEX);
+		qcom_cpu_clk_msm8996_acd_init(base);
+		break;
+	case POST_RATE_CHANGE:
+		if (cnd->new_rate < DIV_2_THRESHOLD)
+			ret = clk_cpu_8996_pmux_set_parent(&cpuclk->clkr.hw,
+							   SMUX_INDEX);
+		else
+			ret = clk_cpu_8996_pmux_set_parent(&cpuclk->clkr.hw,
+							   ACD_INDEX);
+		break;
+	default:
+		ret = 0;
+		break;
+	}
+
+	return notifier_from_errno(ret);
+};
+
+static int qcom_cpu_clk_msm8996_driver_probe(struct platform_device *pdev)
+{
+	struct regmap *regmap;
+	struct clk_hw_onecell_data *data;
+	struct device *dev = &pdev->dev;
+	int ret;
+
+	data = devm_kzalloc(dev, struct_size(data, hws, 2), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	regmap = devm_regmap_init_mmio(dev, base, &cpu_msm8996_regmap_config);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	ret = qcom_cpu_clk_msm8996_register_clks(dev, regmap);
+	if (ret)
+		return ret;
+
+	qcom_cpu_clk_msm8996_acd_init(base);
+
+	data->hws[0] = &pwrcl_pmux.clkr.hw;
+	data->hws[1] = &perfcl_pmux.clkr.hw;
+	data->num = 2;
+
+	return devm_of_clk_add_hw_provider(dev, of_clk_hw_onecell_get, data);
+}
+
+static const struct of_device_id qcom_cpu_clk_msm8996_match_table[] = {
+	{ .compatible = "qcom,msm8996-apcc" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, qcom_cpu_clk_msm8996_match_table);
+
+static struct platform_driver qcom_cpu_clk_msm8996_driver = {
+	.probe = qcom_cpu_clk_msm8996_driver_probe,
+	.driver = {
+		.name = "qcom-msm8996-apcc",
+		.of_match_table = qcom_cpu_clk_msm8996_match_table,
+	},
+};
+module_platform_driver(qcom_cpu_clk_msm8996_driver);
+
+MODULE_DESCRIPTION("QCOM MSM8996 CPU Clock Driver");
+MODULE_LICENSE("GPL v2");