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, 579 insertions, 0 deletions

diff --git a/drivers/cpufreq/vexpress-spc-cpufreq.c b/drivers/cpufreq/vexpress-spc-cpufreq.c
new file mode 100644
index 000000000..d295f405c
--- /dev/null
+++ b/drivers/cpufreq/vexpress-spc-cpufreq.c
@@ -0,0 +1,579 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Versatile Express SPC CPUFreq Interface driver
+ *
+ * Copyright (C) 2013 - 2019 ARM Ltd.
+ * Sudeep Holla <sudeep.holla@arm.com>
+ *
+ * Copyright (C) 2013 Linaro.
+ * Viresh Kumar <viresh.kumar@linaro.org>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/clk.h>
+#include <linux/cpu.h>
+#include <linux/cpufreq.h>
+#include <linux/cpumask.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/pm_opp.h>
+#include <linux/slab.h>
+#include <linux/topology.h>
+#include <linux/types.h>
+
+/* Currently we support only two clusters */
+#define A15_CLUSTER	0
+#define A7_CLUSTER	1
+#define MAX_CLUSTERS	2
+
+#ifdef CONFIG_BL_SWITCHER
+#include <asm/bL_switcher.h>
+static bool bL_switching_enabled;
+#define is_bL_switching_enabled()	bL_switching_enabled
+#define set_switching_enabled(x)	(bL_switching_enabled = (x))
+#else
+#define is_bL_switching_enabled()	false
+#define set_switching_enabled(x)	do { } while (0)
+#define bL_switch_request(...)		do { } while (0)
+#define bL_switcher_put_enabled()	do { } while (0)
+#define bL_switcher_get_enabled()	do { } while (0)
+#endif
+
+#define ACTUAL_FREQ(cluster, freq)  ((cluster == A7_CLUSTER) ? freq << 1 : freq)
+#define VIRT_FREQ(cluster, freq)    ((cluster == A7_CLUSTER) ? freq >> 1 : freq)
+
+static struct clk *clk[MAX_CLUSTERS];
+static struct cpufreq_frequency_table *freq_table[MAX_CLUSTERS + 1];
+static atomic_t cluster_usage[MAX_CLUSTERS + 1];
+
+static unsigned int clk_big_min;	/* (Big) clock frequencies */
+static unsigned int clk_little_max;	/* Maximum clock frequency (Little) */
+
+static DEFINE_PER_CPU(unsigned int, physical_cluster);
+static DEFINE_PER_CPU(unsigned int, cpu_last_req_freq);
+
+static struct mutex cluster_lock[MAX_CLUSTERS];
+
+static inline int raw_cpu_to_cluster(int cpu)
+{
+	return topology_physical_package_id(cpu);
+}
+
+static inline int cpu_to_cluster(int cpu)
+{
+	return is_bL_switching_enabled() ?
+		MAX_CLUSTERS : raw_cpu_to_cluster(cpu);
+}
+
+static unsigned int find_cluster_maxfreq(int cluster)
+{
+	int j;
+	u32 max_freq = 0, cpu_freq;
+
+	for_each_online_cpu(j) {
+		cpu_freq = per_cpu(cpu_last_req_freq, j);
+
+		if (cluster == per_cpu(physical_cluster, j) &&
+		    max_freq < cpu_freq)
+			max_freq = cpu_freq;
+	}
+
+	return max_freq;
+}
+
+static unsigned int clk_get_cpu_rate(unsigned int cpu)
+{
+	u32 cur_cluster = per_cpu(physical_cluster, cpu);
+	u32 rate = clk_get_rate(clk[cur_cluster]) / 1000;
+
+	/* For switcher we use virtual A7 clock rates */
+	if (is_bL_switching_enabled())
+		rate = VIRT_FREQ(cur_cluster, rate);
+
+	return rate;
+}
+
+static unsigned int ve_spc_cpufreq_get_rate(unsigned int cpu)
+{
+	if (is_bL_switching_enabled())
+		return per_cpu(cpu_last_req_freq, cpu);
+	else
+		return clk_get_cpu_rate(cpu);
+}
+
+static unsigned int
+ve_spc_cpufreq_set_rate(u32 cpu, u32 old_cluster, u32 new_cluster, u32 rate)
+{
+	u32 new_rate, prev_rate;
+	int ret;
+	bool bLs = is_bL_switching_enabled();
+
+	mutex_lock(&cluster_lock[new_cluster]);
+
+	if (bLs) {
+		prev_rate = per_cpu(cpu_last_req_freq, cpu);
+		per_cpu(cpu_last_req_freq, cpu) = rate;
+		per_cpu(physical_cluster, cpu) = new_cluster;
+
+		new_rate = find_cluster_maxfreq(new_cluster);
+		new_rate = ACTUAL_FREQ(new_cluster, new_rate);
+	} else {
+		new_rate = rate;
+	}
+
+	ret = clk_set_rate(clk[new_cluster], new_rate * 1000);
+	if (!ret) {
+		/*
+		 * FIXME: clk_set_rate hasn't returned an error here however it
+		 * may be that clk_change_rate failed due to hardware or
+		 * firmware issues and wasn't able to report that due to the
+		 * current design of the clk core layer. To work around this
+		 * problem we will read back the clock rate and check it is
+		 * correct. This needs to be removed once clk core is fixed.
+		 */
+		if (clk_get_rate(clk[new_cluster]) != new_rate * 1000)
+			ret = -EIO;
+	}
+
+	if (WARN_ON(ret)) {
+		if (bLs) {
+			per_cpu(cpu_last_req_freq, cpu) = prev_rate;
+			per_cpu(physical_cluster, cpu) = old_cluster;
+		}
+
+		mutex_unlock(&cluster_lock[new_cluster]);
+
+		return ret;
+	}
+
+	mutex_unlock(&cluster_lock[new_cluster]);
+
+	/* Recalc freq for old cluster when switching clusters */
+	if (old_cluster != new_cluster) {
+		/* Switch cluster */
+		bL_switch_request(cpu, new_cluster);
+
+		mutex_lock(&cluster_lock[old_cluster]);
+
+		/* Set freq of old cluster if there are cpus left on it */
+		new_rate = find_cluster_maxfreq(old_cluster);
+		new_rate = ACTUAL_FREQ(old_cluster, new_rate);
+
+		if (new_rate &&
+		    clk_set_rate(clk[old_cluster], new_rate * 1000)) {
+			pr_err("%s: clk_set_rate failed: %d, old cluster: %d\n",
+			       __func__, ret, old_cluster);
+		}
+		mutex_unlock(&cluster_lock[old_cluster]);
+	}
+
+	return 0;
+}
+
+/* Set clock frequency */
+static int ve_spc_cpufreq_set_target(struct cpufreq_policy *policy,
+				     unsigned int index)
+{
+	u32 cpu = policy->cpu, cur_cluster, new_cluster, actual_cluster;
+	unsigned int freqs_new;
+
+	cur_cluster = cpu_to_cluster(cpu);
+	new_cluster = actual_cluster = per_cpu(physical_cluster, cpu);
+
+	freqs_new = freq_table[cur_cluster][index].frequency;
+
+	if (is_bL_switching_enabled()) {
+		if (actual_cluster == A15_CLUSTER && freqs_new < clk_big_min)
+			new_cluster = A7_CLUSTER;
+		else if (actual_cluster == A7_CLUSTER &&
+			 freqs_new > clk_little_max)
+			new_cluster = A15_CLUSTER;
+	}
+
+	return ve_spc_cpufreq_set_rate(cpu, actual_cluster, new_cluster,
+				       freqs_new);
+}
+
+static inline u32 get_table_count(struct cpufreq_frequency_table *table)
+{
+	int count;
+
+	for (count = 0; table[count].frequency != CPUFREQ_TABLE_END; count++)
+		;
+
+	return count;
+}
+
+/* get the minimum frequency in the cpufreq_frequency_table */
+static inline u32 get_table_min(struct cpufreq_frequency_table *table)
+{
+	struct cpufreq_frequency_table *pos;
+	u32 min_freq = ~0;
+
+	cpufreq_for_each_entry(pos, table)
+		if (pos->frequency < min_freq)
+			min_freq = pos->frequency;
+	return min_freq;
+}
+
+/* get the maximum frequency in the cpufreq_frequency_table */
+static inline u32 get_table_max(struct cpufreq_frequency_table *table)
+{
+	struct cpufreq_frequency_table *pos;
+	u32 max_freq = 0;
+
+	cpufreq_for_each_entry(pos, table)
+		if (pos->frequency > max_freq)
+			max_freq = pos->frequency;
+	return max_freq;
+}
+
+static bool search_frequency(struct cpufreq_frequency_table *table, int size,
+			     unsigned int freq)
+{
+	int count;
+
+	for (count = 0; count < size; count++) {
+		if (table[count].frequency == freq)
+			return true;
+	}
+
+	return false;
+}
+
+static int merge_cluster_tables(void)
+{
+	int i, j, k = 0, count = 1;
+	struct cpufreq_frequency_table *table;
+
+	for (i = 0; i < MAX_CLUSTERS; i++)
+		count += get_table_count(freq_table[i]);
+
+	table = kcalloc(count, sizeof(*table), GFP_KERNEL);
+	if (!table)
+		return -ENOMEM;
+
+	freq_table[MAX_CLUSTERS] = table;
+
+	/* Add in reverse order to get freqs in increasing order */
+	for (i = MAX_CLUSTERS - 1; i >= 0; i--, count = k) {
+		for (j = 0; freq_table[i][j].frequency != CPUFREQ_TABLE_END;
+		     j++) {
+			if (i == A15_CLUSTER &&
+			    search_frequency(table, count, freq_table[i][j].frequency))
+				continue; /* skip duplicates */
+			table[k++].frequency =
+				VIRT_FREQ(i, freq_table[i][j].frequency);
+		}
+	}
+
+	table[k].driver_data = k;
+	table[k].frequency = CPUFREQ_TABLE_END;
+
+	return 0;
+}
+
+static void _put_cluster_clk_and_freq_table(struct device *cpu_dev,
+					    const struct cpumask *cpumask)
+{
+	u32 cluster = raw_cpu_to_cluster(cpu_dev->id);
+
+	if (!freq_table[cluster])
+		return;
+
+	clk_put(clk[cluster]);
+	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table[cluster]);
+}
+
+static void put_cluster_clk_and_freq_table(struct device *cpu_dev,
+					   const struct cpumask *cpumask)
+{
+	u32 cluster = cpu_to_cluster(cpu_dev->id);
+	int i;
+
+	if (atomic_dec_return(&cluster_usage[cluster]))
+		return;
+
+	if (cluster < MAX_CLUSTERS)
+		return _put_cluster_clk_and_freq_table(cpu_dev, cpumask);
+
+	for_each_present_cpu(i) {
+		struct device *cdev = get_cpu_device(i);
+
+		if (!cdev)
+			return;
+
+		_put_cluster_clk_and_freq_table(cdev, cpumask);
+	}
+
+	/* free virtual table */
+	kfree(freq_table[cluster]);
+}
+
+static int _get_cluster_clk_and_freq_table(struct device *cpu_dev,
+					   const struct cpumask *cpumask)
+{
+	u32 cluster = raw_cpu_to_cluster(cpu_dev->id);
+	int ret;
+
+	if (freq_table[cluster])
+		return 0;
+
+	/*
+	 * platform specific SPC code must initialise the opp table
+	 * so just check if the OPP count is non-zero
+	 */
+	ret = dev_pm_opp_get_opp_count(cpu_dev) <= 0;
+	if (ret)
+		goto out;
+
+	ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table[cluster]);
+	if (ret)
+		goto out;
+
+	clk[cluster] = clk_get(cpu_dev, NULL);
+	if (!IS_ERR(clk[cluster]))
+		return 0;
+
+	dev_err(cpu_dev, "%s: Failed to get clk for cpu: %d, cluster: %d\n",
+		__func__, cpu_dev->id, cluster);
+	ret = PTR_ERR(clk[cluster]);
+	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table[cluster]);
+
+out:
+	dev_err(cpu_dev, "%s: Failed to get data for cluster: %d\n", __func__,
+		cluster);
+	return ret;
+}
+
+static int get_cluster_clk_and_freq_table(struct device *cpu_dev,
+					  const struct cpumask *cpumask)
+{
+	u32 cluster = cpu_to_cluster(cpu_dev->id);
+	int i, ret;
+
+	if (atomic_inc_return(&cluster_usage[cluster]) != 1)
+		return 0;
+
+	if (cluster < MAX_CLUSTERS) {
+		ret = _get_cluster_clk_and_freq_table(cpu_dev, cpumask);
+		if (ret)
+			atomic_dec(&cluster_usage[cluster]);
+		return ret;
+	}
+
+	/*
+	 * Get data for all clusters and fill virtual cluster with a merge of
+	 * both
+	 */
+	for_each_present_cpu(i) {
+		struct device *cdev = get_cpu_device(i);
+
+		if (!cdev)
+			return -ENODEV;
+
+		ret = _get_cluster_clk_and_freq_table(cdev, cpumask);
+		if (ret)
+			goto put_clusters;
+	}
+
+	ret = merge_cluster_tables();
+	if (ret)
+		goto put_clusters;
+
+	/* Assuming 2 cluster, set clk_big_min and clk_little_max */
+	clk_big_min = get_table_min(freq_table[A15_CLUSTER]);
+	clk_little_max = VIRT_FREQ(A7_CLUSTER,
+				   get_table_max(freq_table[A7_CLUSTER]));
+
+	return 0;
+
+put_clusters:
+	for_each_present_cpu(i) {
+		struct device *cdev = get_cpu_device(i);
+
+		if (!cdev)
+			return -ENODEV;
+
+		_put_cluster_clk_and_freq_table(cdev, cpumask);
+	}
+
+	atomic_dec(&cluster_usage[cluster]);
+
+	return ret;
+}
+
+/* Per-CPU initialization */
+static int ve_spc_cpufreq_init(struct cpufreq_policy *policy)
+{
+	u32 cur_cluster = cpu_to_cluster(policy->cpu);
+	struct device *cpu_dev;
+	int ret;
+
+	cpu_dev = get_cpu_device(policy->cpu);
+	if (!cpu_dev) {
+		pr_err("%s: failed to get cpu%d device\n", __func__,
+		       policy->cpu);
+		return -ENODEV;
+	}
+
+	if (cur_cluster < MAX_CLUSTERS) {
+		int cpu;
+
+		dev_pm_opp_get_sharing_cpus(cpu_dev, policy->cpus);
+
+		for_each_cpu(cpu, policy->cpus)
+			per_cpu(physical_cluster, cpu) = cur_cluster;
+	} else {
+		/* Assumption: during init, we are always running on A15 */
+		per_cpu(physical_cluster, policy->cpu) = A15_CLUSTER;
+	}
+
+	ret = get_cluster_clk_and_freq_table(cpu_dev, policy->cpus);
+	if (ret)
+		return ret;
+
+	policy->freq_table = freq_table[cur_cluster];
+	policy->cpuinfo.transition_latency = 1000000; /* 1 ms */
+
+	if (is_bL_switching_enabled())
+		per_cpu(cpu_last_req_freq, policy->cpu) =
+						clk_get_cpu_rate(policy->cpu);
+
+	dev_info(cpu_dev, "%s: CPU %d initialized\n", __func__, policy->cpu);
+	return 0;
+}
+
+static int ve_spc_cpufreq_exit(struct cpufreq_policy *policy)
+{
+	struct device *cpu_dev;
+
+	cpu_dev = get_cpu_device(policy->cpu);
+	if (!cpu_dev) {
+		pr_err("%s: failed to get cpu%d device\n", __func__,
+		       policy->cpu);
+		return -ENODEV;
+	}
+
+	put_cluster_clk_and_freq_table(cpu_dev, policy->related_cpus);
+	return 0;
+}
+
+static struct cpufreq_driver ve_spc_cpufreq_driver = {
+	.name			= "vexpress-spc",
+	.flags			= CPUFREQ_HAVE_GOVERNOR_PER_POLICY |
+					CPUFREQ_NEED_INITIAL_FREQ_CHECK,
+	.verify			= cpufreq_generic_frequency_table_verify,
+	.target_index		= ve_spc_cpufreq_set_target,
+	.get			= ve_spc_cpufreq_get_rate,
+	.init			= ve_spc_cpufreq_init,
+	.exit			= ve_spc_cpufreq_exit,
+	.register_em		= cpufreq_register_em_with_opp,
+	.attr			= cpufreq_generic_attr,
+};
+
+#ifdef CONFIG_BL_SWITCHER
+static int bL_cpufreq_switcher_notifier(struct notifier_block *nfb,
+					unsigned long action, void *_arg)
+{
+	pr_debug("%s: action: %ld\n", __func__, action);
+
+	switch (action) {
+	case BL_NOTIFY_PRE_ENABLE:
+	case BL_NOTIFY_PRE_DISABLE:
+		cpufreq_unregister_driver(&ve_spc_cpufreq_driver);
+		break;
+
+	case BL_NOTIFY_POST_ENABLE:
+		set_switching_enabled(true);
+		cpufreq_register_driver(&ve_spc_cpufreq_driver);
+		break;
+
+	case BL_NOTIFY_POST_DISABLE:
+		set_switching_enabled(false);
+		cpufreq_register_driver(&ve_spc_cpufreq_driver);
+		break;
+
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block bL_switcher_notifier = {
+	.notifier_call = bL_cpufreq_switcher_notifier,
+};
+
+static int __bLs_register_notifier(void)
+{
+	return bL_switcher_register_notifier(&bL_switcher_notifier);
+}
+
+static int __bLs_unregister_notifier(void)
+{
+	return bL_switcher_unregister_notifier(&bL_switcher_notifier);
+}
+#else
+static int __bLs_register_notifier(void) { return 0; }
+static int __bLs_unregister_notifier(void) { return 0; }
+#endif
+
+static int ve_spc_cpufreq_probe(struct platform_device *pdev)
+{
+	int ret, i;
+
+	set_switching_enabled(bL_switcher_get_enabled());
+
+	for (i = 0; i < MAX_CLUSTERS; i++)
+		mutex_init(&cluster_lock[i]);
+
+	if (!is_bL_switching_enabled())
+		ve_spc_cpufreq_driver.flags |= CPUFREQ_IS_COOLING_DEV;
+
+	ret = cpufreq_register_driver(&ve_spc_cpufreq_driver);
+	if (ret) {
+		pr_info("%s: Failed registering platform driver: %s, err: %d\n",
+			__func__, ve_spc_cpufreq_driver.name, ret);
+	} else {
+		ret = __bLs_register_notifier();
+		if (ret)
+			cpufreq_unregister_driver(&ve_spc_cpufreq_driver);
+		else
+			pr_info("%s: Registered platform driver: %s\n",
+				__func__, ve_spc_cpufreq_driver.name);
+	}
+
+	bL_switcher_put_enabled();
+	return ret;
+}
+
+static int ve_spc_cpufreq_remove(struct platform_device *pdev)
+{
+	bL_switcher_get_enabled();
+	__bLs_unregister_notifier();
+	cpufreq_unregister_driver(&ve_spc_cpufreq_driver);
+	bL_switcher_put_enabled();
+	pr_info("%s: Un-registered platform driver: %s\n", __func__,
+		ve_spc_cpufreq_driver.name);
+	return 0;
+}
+
+static struct platform_driver ve_spc_cpufreq_platdrv = {
+	.driver = {
+		.name	= "vexpress-spc-cpufreq",
+	},
+	.probe		= ve_spc_cpufreq_probe,
+	.remove		= ve_spc_cpufreq_remove,
+};
+module_platform_driver(ve_spc_cpufreq_platdrv);
+
+MODULE_ALIAS("platform:vexpress-spc-cpufreq");
+MODULE_AUTHOR("Viresh Kumar <viresh.kumar@linaro.org>");
+MODULE_AUTHOR("Sudeep Holla <sudeep.holla@arm.com>");
+MODULE_DESCRIPTION("Vexpress SPC ARM big LITTLE cpufreq driver");
+MODULE_LICENSE("GPL v2");