Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas:
 "The main theme of this pull request is security covering variants 2
  and 3 for arm64. I expect to send additional patches next week
  covering an improved firmware interface (requires firmware changes)
  for variant 2 and way for KPTI to be disabled on unaffected CPUs
  (Cavium's ThunderX doesn't work properly with KPTI enabled because of
  a hardware erratum).

  Summary:

   - Security mitigations:
      - variant 2: invalidate the branch predictor with a call to
        secure firmware
      - variant 3: implement KPTI for arm64

   - 52-bit physical address support for arm64 (ARMv8.2)

   - arm64 support for RAS (firmware first only) and SDEI (software
     delegated exception interface; allows firmware to inject a RAS
     error into the OS)

   - perf support for the ARM DynamIQ Shared Unit PMU

   - CPUID and HWCAP bits updated for new floating point multiplication
     instructions in ARMv8.4

   - remove some virtual memory layout printks during boot

   - fix initial page table creation to cope with larger than 32M kernel
     images when 16K pages are enabled"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (104 commits)
  arm64: Fix TTBR + PAN + 52-bit PA logic in cpu_do_switch_mm
  arm64: Turn on KPTI only on CPUs that need it
  arm64: Branch predictor hardening for Cavium ThunderX2
  arm64: Run enable method for errata work arounds on late CPUs
  arm64: Move BP hardening to check_and_switch_context
  arm64: mm: ignore memory above supported physical address size
  arm64: kpti: Fix the interaction between ASID switching and software PAN
  KVM: arm64: Emulate RAS error registers and set HCR_EL2's TERR & TEA
  KVM: arm64: Handle RAS SErrors from EL2 on guest exit
  KVM: arm64: Handle RAS SErrors from EL1 on guest exit
  KVM: arm64: Save ESR_EL2 on guest SError
  KVM: arm64: Save/Restore guest DISR_EL1
  KVM: arm64: Set an impdef ESR for Virtual-SError using VSESR_EL2.
  KVM: arm/arm64: mask/unmask daif around VHE guests
  arm64: kernel: Prepare for a DISR user
  arm64: Unconditionally enable IESB on exception entry/return for firmware-first
  arm64: kernel: Survive corrected RAS errors notified by SError
  arm64: cpufeature: Detect CPU RAS Extentions
  arm64: sysreg: Move to use definitions for all the SCTLR bits
  arm64: cpufeature: __this_cpu_has_cap() shouldn't stop early
  ...

12 files changed, 1999 insertions, 51 deletions

diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index fa87a055..e77f77c 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -48,6 +48,14 @@ config ARM_SCPI_POWER_DOMAIN
 	  This enables support for the SCPI power domains which can be
 	  enabled or disabled via the SCP firmware
 
+config ARM_SDE_INTERFACE
+	bool "ARM Software Delegated Exception Interface (SDEI)"
+	depends on ARM64
+	help
+	  The Software Delegated Exception Interface (SDEI) is an ARM
+	  standard for registering callbacks from the platform firmware
+	  into the OS. This is typically used to implement RAS notifications.
+
 config EDD
 	tristate "BIOS Enhanced Disk Drive calls determine boot disk"
 	depends on X86
diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile
index feaa890..b248238 100644
--- a/drivers/firmware/Makefile
+++ b/drivers/firmware/Makefile
@@ -6,6 +6,7 @@ obj-$(CONFIG_ARM_PSCI_FW)	+= psci.o
 obj-$(CONFIG_ARM_PSCI_CHECKER)	+= psci_checker.o
 obj-$(CONFIG_ARM_SCPI_PROTOCOL)	+= arm_scpi.o
 obj-$(CONFIG_ARM_SCPI_POWER_DOMAIN) += scpi_pm_domain.o
+obj-$(CONFIG_ARM_SDE_INTERFACE)	+= arm_sdei.o
 obj-$(CONFIG_DMI)		+= dmi_scan.o
 obj-$(CONFIG_DMI_SYSFS)		+= dmi-sysfs.o
 obj-$(CONFIG_EDD)		+= edd.o
diff --git a/drivers/firmware/arm_sdei.c b/drivers/firmware/arm_sdei.c
new file mode 100644
index 0000000..1ea7164
--- /dev/null
+++ b/drivers/firmware/arm_sdei.c
@@ -0,0 +1,1092 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2017 Arm Ltd.
+#define pr_fmt(fmt) "sdei: " fmt
+
+#include <linux/acpi.h>
+#include <linux/arm_sdei.h>
+#include <linux/arm-smccc.h>
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/compiler.h>
+#include <linux/cpuhotplug.h>
+#include <linux/cpu.h>
+#include <linux/cpu_pm.h>
+#include <linux/errno.h>
+#include <linux/hardirq.h>
+#include <linux/kernel.h>
+#include <linux/kprobes.h>
+#include <linux/kvm_host.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/notifier.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/percpu.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/ptrace.h>
+#include <linux/preempt.h>
+#include <linux/reboot.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <linux/spinlock.h>
+#include <linux/uaccess.h>
+
+/*
+ * The call to use to reach the firmware.
+ */
+static asmlinkage void (*sdei_firmware_call)(unsigned long function_id,
+		      unsigned long arg0, unsigned long arg1,
+		      unsigned long arg2, unsigned long arg3,
+		      unsigned long arg4, struct arm_smccc_res *res);
+
+/* entry point from firmware to arch asm code */
+static unsigned long sdei_entry_point;
+
+struct sdei_event {
+	/* These three are protected by the sdei_list_lock */
+	struct list_head	list;
+	bool			reregister;
+	bool			reenable;
+
+	u32			event_num;
+	u8			type;
+	u8			priority;
+
+	/* This pointer is handed to firmware as the event argument. */
+	union {
+		/* Shared events */
+		struct sdei_registered_event *registered;
+
+		/* CPU private events */
+		struct sdei_registered_event __percpu *private_registered;
+	};
+};
+
+/* Take the mutex for any API call or modification. Take the mutex first. */
+static DEFINE_MUTEX(sdei_events_lock);
+
+/* and then hold this when modifying the list */
+static DEFINE_SPINLOCK(sdei_list_lock);
+static LIST_HEAD(sdei_list);
+
+/* Private events are registered/enabled via IPI passing one of these */
+struct sdei_crosscall_args {
+	struct sdei_event *event;
+	atomic_t errors;
+	int first_error;
+};
+
+#define CROSSCALL_INIT(arg, event)	(arg.event = event, \
+					 arg.first_error = 0, \
+					 atomic_set(&arg.errors, 0))
+
+static inline int sdei_do_cross_call(void *fn, struct sdei_event * event)
+{
+	struct sdei_crosscall_args arg;
+
+	CROSSCALL_INIT(arg, event);
+	on_each_cpu(fn, &arg, true);
+
+	return arg.first_error;
+}
+
+static inline void
+sdei_cross_call_return(struct sdei_crosscall_args *arg, int err)
+{
+	if (err && (atomic_inc_return(&arg->errors) == 1))
+		arg->first_error = err;
+}
+
+static int sdei_to_linux_errno(unsigned long sdei_err)
+{
+	switch (sdei_err) {
+	case SDEI_NOT_SUPPORTED:
+		return -EOPNOTSUPP;
+	case SDEI_INVALID_PARAMETERS:
+		return -EINVAL;
+	case SDEI_DENIED:
+		return -EPERM;
+	case SDEI_PENDING:
+		return -EINPROGRESS;
+	case SDEI_OUT_OF_RESOURCE:
+		return -ENOMEM;
+	}
+
+	/* Not an error value ... */
+	return sdei_err;
+}
+
+/*
+ * If x0 is any of these values, then the call failed, use sdei_to_linux_errno()
+ * to translate.
+ */
+static int sdei_is_err(struct arm_smccc_res *res)
+{
+	switch (res->a0) {
+	case SDEI_NOT_SUPPORTED:
+	case SDEI_INVALID_PARAMETERS:
+	case SDEI_DENIED:
+	case SDEI_PENDING:
+	case SDEI_OUT_OF_RESOURCE:
+		return true;
+	}
+
+	return false;
+}
+
+static int invoke_sdei_fn(unsigned long function_id, unsigned long arg0,
+			  unsigned long arg1, unsigned long arg2,
+			  unsigned long arg3, unsigned long arg4,
+			  u64 *result)
+{
+	int err = 0;
+	struct arm_smccc_res res;
+
+	if (sdei_firmware_call) {
+		sdei_firmware_call(function_id, arg0, arg1, arg2, arg3, arg4,
+				   &res);
+		if (sdei_is_err(&res))
+			err = sdei_to_linux_errno(res.a0);
+	} else {
+		/*
+		 * !sdei_firmware_call means we failed to probe or called
+		 * sdei_mark_interface_broken(). -EIO is not an error returned
+		 * by sdei_to_linux_errno() and is used to suppress messages
+		 * from this driver.
+		 */
+		err = -EIO;
+		res.a0 = SDEI_NOT_SUPPORTED;
+	}
+
+	if (result)
+		*result = res.a0;
+
+	return err;
+}
+
+static struct sdei_event *sdei_event_find(u32 event_num)
+{
+	struct sdei_event *e, *found = NULL;
+
+	lockdep_assert_held(&sdei_events_lock);
+
+	spin_lock(&sdei_list_lock);
+	list_for_each_entry(e, &sdei_list, list) {
+		if (e->event_num == event_num) {
+			found = e;
+			break;
+		}
+	}
+	spin_unlock(&sdei_list_lock);
+
+	return found;
+}
+
+int sdei_api_event_context(u32 query, u64 *result)
+{
+	return invoke_sdei_fn(SDEI_1_0_FN_SDEI_EVENT_CONTEXT, query, 0, 0, 0, 0,
+			      result);
+}
+NOKPROBE_SYMBOL(sdei_api_event_context);
+
+static int sdei_api_event_get_info(u32 event, u32 info, u64 *result)
+{
+	return invoke_sdei_fn(SDEI_1_0_FN_SDEI_EVENT_GET_INFO, event, info, 0,
+			      0, 0, result);
+}
+
+static struct sdei_event *sdei_event_create(u32 event_num,
+					    sdei_event_callback *cb,
+					    void *cb_arg)
+{
+	int err;
+	u64 result;
+	struct sdei_event *event;
+	struct sdei_registered_event *reg;
+
+	lockdep_assert_held(&sdei_events_lock);
+
+	event = kzalloc(sizeof(*event), GFP_KERNEL);
+	if (!event)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_LIST_HEAD(&event->list);
+	event->event_num = event_num;
+
+	err = sdei_api_event_get_info(event_num, SDEI_EVENT_INFO_EV_PRIORITY,
+				      &result);
+	if (err) {
+		kfree(event);
+		return ERR_PTR(err);
+	}
+	event->priority = result;
+
+	err = sdei_api_event_get_info(event_num, SDEI_EVENT_INFO_EV_TYPE,
+				      &result);
+	if (err) {
+		kfree(event);
+		return ERR_PTR(err);
+	}
+	event->type = result;
+
+	if (event->type == SDEI_EVENT_TYPE_SHARED) {
+		reg = kzalloc(sizeof(*reg), GFP_KERNEL);
+		if (!reg) {
+			kfree(event);
+			return ERR_PTR(-ENOMEM);
+		}
+
+		reg->event_num = event_num;
+		reg->priority = event->priority;
+
+		reg->callback = cb;
+		reg->callback_arg = cb_arg;
+		event->registered = reg;
+	} else {
+		int cpu;
+		struct sdei_registered_event __percpu *regs;
+
+		regs = alloc_percpu(struct sdei_registered_event);
+		if (!regs) {
+			kfree(event);
+			return ERR_PTR(-ENOMEM);
+		}
+
+		for_each_possible_cpu(cpu) {
+			reg = per_cpu_ptr(regs, cpu);
+
+			reg->event_num = event->event_num;
+			reg->priority = event->priority;
+			reg->callback = cb;
+			reg->callback_arg = cb_arg;
+		}
+
+		event->private_registered = regs;
+	}
+
+	if (sdei_event_find(event_num)) {
+		kfree(event->registered);
+		kfree(event);
+		event = ERR_PTR(-EBUSY);
+	} else {
+		spin_lock(&sdei_list_lock);
+		list_add(&event->list, &sdei_list);
+		spin_unlock(&sdei_list_lock);
+	}
+
+	return event;
+}
+
+static void sdei_event_destroy(struct sdei_event *event)
+{
+	lockdep_assert_held(&sdei_events_lock);
+
+	spin_lock(&sdei_list_lock);
+	list_del(&event->list);
+	spin_unlock(&sdei_list_lock);
+
+	if (event->type == SDEI_EVENT_TYPE_SHARED)
+		kfree(event->registered);
+	else
+		free_percpu(event->private_registered);
+
+	kfree(event);
+}
+
+static int sdei_api_get_version(u64 *version)
+{
+	return invoke_sdei_fn(SDEI_1_0_FN_SDEI_VERSION, 0, 0, 0, 0, 0, version);
+}
+
+int sdei_mask_local_cpu(void)
+{
+	int err;
+
+	WARN_ON_ONCE(preemptible());
+
+	err = invoke_sdei_fn(SDEI_1_0_FN_SDEI_PE_MASK, 0, 0, 0, 0, 0, NULL);
+	if (err && err != -EIO) {
+		pr_warn_once("failed to mask CPU[%u]: %d\n",
+			      smp_processor_id(), err);
+		return err;
+	}
+
+	return 0;
+}
+
+static void _ipi_mask_cpu(void *ignored)
+{
+	sdei_mask_local_cpu();
+}
+
+int sdei_unmask_local_cpu(void)
+{
+	int err;
+
+	WARN_ON_ONCE(preemptible());
+
+	err = invoke_sdei_fn(SDEI_1_0_FN_SDEI_PE_UNMASK, 0, 0, 0, 0, 0, NULL);
+	if (err && err != -EIO) {
+		pr_warn_once("failed to unmask CPU[%u]: %d\n",
+			     smp_processor_id(), err);
+		return err;
+	}
+
+	return 0;
+}
+
+static void _ipi_unmask_cpu(void *ignored)
+{
+	sdei_unmask_local_cpu();
+}
+
+static void _ipi_private_reset(void *ignored)
+{
+	int err;
+
+	err = invoke_sdei_fn(SDEI_1_0_FN_SDEI_PRIVATE_RESET, 0, 0, 0, 0, 0,
+			     NULL);
+	if (err && err != -EIO)
+		pr_warn_once("failed to reset CPU[%u]: %d\n",
+			     smp_processor_id(), err);
+}
+
+static int sdei_api_shared_reset(void)
+{
+	return invoke_sdei_fn(SDEI_1_0_FN_SDEI_SHARED_RESET, 0, 0, 0, 0, 0,
+			      NULL);
+}
+
+static void sdei_mark_interface_broken(void)
+{
+	pr_err("disabling SDEI firmware interface\n");
+	on_each_cpu(&_ipi_mask_cpu, NULL, true);
+	sdei_firmware_call = NULL;
+}
+
+static int sdei_platform_reset(void)
+{
+	int err;
+
+	on_each_cpu(&_ipi_private_reset, NULL, true);
+	err = sdei_api_shared_reset();
+	if (err) {
+		pr_err("Failed to reset platform: %d\n", err);
+		sdei_mark_interface_broken();
+	}
+
+	return err;
+}
+
+static int sdei_api_event_enable(u32 event_num)
+{
+	return invoke_sdei_fn(SDEI_1_0_FN_SDEI_EVENT_ENABLE, event_num, 0, 0, 0,
+			      0, NULL);
+}
+
+/* Called directly by the hotplug callbacks */
+static void _local_event_enable(void *data)
+{
+	int err;
+	struct sdei_crosscall_args *arg = data;
+
+	WARN_ON_ONCE(preemptible());
+
+	err = sdei_api_event_enable(arg->event->event_num);
+
+	sdei_cross_call_return(arg, err);
+}
+
+int sdei_event_enable(u32 event_num)
+{
+	int err = -EINVAL;
+	struct sdei_event *event;
+
+	mutex_lock(&sdei_events_lock);
+	event = sdei_event_find(event_num);
+	if (!event) {
+		mutex_unlock(&sdei_events_lock);
+		return -ENOENT;
+	}
+
+	spin_lock(&sdei_list_lock);
+	event->reenable = true;
+	spin_unlock(&sdei_list_lock);
+
+	if (event->type == SDEI_EVENT_TYPE_SHARED)
+		err = sdei_api_event_enable(event->event_num);
+	else
+		err = sdei_do_cross_call(_local_event_enable, event);
+	mutex_unlock(&sdei_events_lock);
+
+	return err;
+}
+EXPORT_SYMBOL(sdei_event_enable);
+
+static int sdei_api_event_disable(u32 event_num)
+{
+	return invoke_sdei_fn(SDEI_1_0_FN_SDEI_EVENT_DISABLE, event_num, 0, 0,
+			      0, 0, NULL);
+}
+
+static void _ipi_event_disable(void *data)
+{
+	int err;
+	struct sdei_crosscall_args *arg = data;
+
+	err = sdei_api_event_disable(arg->event->event_num);
+
+	sdei_cross_call_return(arg, err);
+}
+
+int sdei_event_disable(u32 event_num)
+{
+	int err = -EINVAL;
+	struct sdei_event *event;
+
+	mutex_lock(&sdei_events_lock);
+	event = sdei_event_find(event_num);
+	if (!event) {
+		mutex_unlock(&sdei_events_lock);
+		return -ENOENT;
+	}
+
+	spin_lock(&sdei_list_lock);
+	event->reenable = false;
+	spin_unlock(&sdei_list_lock);
+
+	if (event->type == SDEI_EVENT_TYPE_SHARED)
+		err = sdei_api_event_disable(event->event_num);
+	else
+		err = sdei_do_cross_call(_ipi_event_disable, event);
+	mutex_unlock(&sdei_events_lock);
+
+	return err;
+}
+EXPORT_SYMBOL(sdei_event_disable);
+
+static int sdei_api_event_unregister(u32 event_num)
+{
+	return invoke_sdei_fn(SDEI_1_0_FN_SDEI_EVENT_UNREGISTER, event_num, 0,
+			      0, 0, 0, NULL);
+}
+
+/* Called directly by the hotplug callbacks */
+static void _local_event_unregister(void *data)
+{
+	int err;
+	struct sdei_crosscall_args *arg = data;
+
+	WARN_ON_ONCE(preemptible());
+
+	err = sdei_api_event_unregister(arg->event->event_num);
+
+	sdei_cross_call_return(arg, err);
+}
+
+static int _sdei_event_unregister(struct sdei_event *event)
+{
+	lockdep_assert_held(&sdei_events_lock);
+
+	spin_lock(&sdei_list_lock);
+	event->reregister = false;
+	event->reenable = false;
+	spin_unlock(&sdei_list_lock);
+
+	if (event->type == SDEI_EVENT_TYPE_SHARED)
+		return sdei_api_event_unregister(event->event_num);
+
+	return sdei_do_cross_call(_local_event_unregister, event);
+}
+
+int sdei_event_unregister(u32 event_num)
+{
+	int err;
+	struct sdei_event *event;
+
+	WARN_ON(in_nmi());
+
+	mutex_lock(&sdei_events_lock);
+	event = sdei_event_find(event_num);
+	do {
+		if (!event) {
+			pr_warn("Event %u not registered\n", event_num);
+			err = -ENOENT;
+			break;
+		}
+
+		err = _sdei_event_unregister(event);
+		if (err)
+			break;
+
+		sdei_event_destroy(event);
+	} while (0);
+	mutex_unlock(&sdei_events_lock);
+
+	return err;
+}
+EXPORT_SYMBOL(sdei_event_unregister);
+
+/*
+ * unregister events, but don't destroy them as they are re-registered by
+ * sdei_reregister_shared().
+ */
+static int sdei_unregister_shared(void)
+{
+	int err = 0;
+	struct sdei_event *event;
+
+	mutex_lock(&sdei_events_lock);
+	spin_lock(&sdei_list_lock);
+	list_for_each_entry(event, &sdei_list, list) {
+		if (event->type != SDEI_EVENT_TYPE_SHARED)
+			continue;
+
+		err = _sdei_event_unregister(event);
+		if (err)
+			break;
+	}
+	spin_unlock(&sdei_list_lock);
+	mutex_unlock(&sdei_events_lock);
+
+	return err;
+}
+
+static int sdei_api_event_register(u32 event_num, unsigned long entry_point,
+				   void *arg, u64 flags, u64 affinity)
+{
+	return invoke_sdei_fn(SDEI_1_0_FN_SDEI_EVENT_REGISTER, event_num,
+			      (unsigned long)entry_point, (unsigned long)arg,
+			      flags, affinity, NULL);
+}
+
+/* Called directly by the hotplug callbacks */
+static void _local_event_register(void *data)
+{
+	int err;
+	struct sdei_registered_event *reg;
+	struct sdei_crosscall_args *arg = data;
+
+	WARN_ON(preemptible());
+
+	reg = per_cpu_ptr(arg->event->private_registered, smp_processor_id());
+	err = sdei_api_event_register(arg->event->event_num, sdei_entry_point,
+				      reg, 0, 0);
+
+	sdei_cross_call_return(arg, err);
+}
+
+static int _sdei_event_register(struct sdei_event *event)
+{
+	int err;
+
+	lockdep_assert_held(&sdei_events_lock);
+
+	spin_lock(&sdei_list_lock);
+	event->reregister = true;
+	spin_unlock(&sdei_list_lock);
+
+	if (event->type == SDEI_EVENT_TYPE_SHARED)
+		return sdei_api_event_register(event->event_num,
+					       sdei_entry_point,
+					       event->registered,
+					       SDEI_EVENT_REGISTER_RM_ANY, 0);
+
+
+	err = sdei_do_cross_call(_local_event_register, event);
+	if (err) {
+		spin_lock(&sdei_list_lock);
+		event->reregister = false;
+		event->reenable = false;
+		spin_unlock(&sdei_list_lock);
+
+		sdei_do_cross_call(_local_event_unregister, event);
+	}
+
+	return err;
+}
+
+int sdei_event_register(u32 event_num, sdei_event_callback *cb, void *arg)
+{
+	int err;
+	struct sdei_event *event;
+
+	WARN_ON(in_nmi());
+
+	mutex_lock(&sdei_events_lock);
+	do {
+		if (sdei_event_find(event_num)) {
+			pr_warn("Event %u already registered\n", event_num);
+			err = -EBUSY;
+			break;
+		}
+
+		event = sdei_event_create(event_num, cb, arg);
+		if (IS_ERR(event)) {
+			err = PTR_ERR(event);
+			pr_warn("Failed to create event %u: %d\n", event_num,
+				err);
+			break;
+		}
+
+		err = _sdei_event_register(event);
+		if (err) {
+			sdei_event_destroy(event);
+			pr_warn("Failed to register event %u: %d\n", event_num,
+				err);
+		}
+	} while (0);
+	mutex_unlock(&sdei_events_lock);
+
+	return err;
+}
+EXPORT_SYMBOL(sdei_event_register);
+
+static int sdei_reregister_event(struct sdei_event *event)
+{
+	int err;
+
+	lockdep_assert_held(&sdei_events_lock);
+
+	err = _sdei_event_register(event);
+	if (err) {
+		pr_err("Failed to re-register event %u\n", event->event_num);
+		sdei_event_destroy(event);
+		return err;
+	}
+
+	if (event->reenable) {
+		if (event->type == SDEI_EVENT_TYPE_SHARED)
+			err = sdei_api_event_enable(event->event_num);
+		else
+			err = sdei_do_cross_call(_local_event_enable, event);
+	}
+
+	if (err)
+		pr_err("Failed to re-enable event %u\n", event->event_num);
+
+	return err;
+}
+
+static int sdei_reregister_shared(void)
+{
+	int err = 0;
+	struct sdei_event *event;
+
+	mutex_lock(&sdei_events_lock);
+	spin_lock(&sdei_list_lock);
+	list_for_each_entry(event, &sdei_list, list) {
+		if (event->type != SDEI_EVENT_TYPE_SHARED)
+			continue;
+
+		if (event->reregister) {
+			err = sdei_reregister_event(event);
+			if (err)
+				break;
+		}
+	}
+	spin_unlock(&sdei_list_lock);
+	mutex_unlock(&sdei_events_lock);
+
+	return err;
+}
+
+static int sdei_cpuhp_down(unsigned int cpu)
+{
+	struct sdei_event *event;
+	struct sdei_crosscall_args arg;
+
+	/* un-register private events */
+	spin_lock(&sdei_list_lock);
+	list_for_each_entry(event, &sdei_list, list) {
+		if (event->type == SDEI_EVENT_TYPE_SHARED)
+			continue;
+
+		CROSSCALL_INIT(arg, event);
+		/* call the cross-call function locally... */
+		_local_event_unregister(&arg);
+		if (arg.first_error)
+			pr_err("Failed to unregister event %u: %d\n",
+			       event->event_num, arg.first_error);
+	}
+	spin_unlock(&sdei_list_lock);
+
+	return sdei_mask_local_cpu();
+}
+
+static int sdei_cpuhp_up(unsigned int cpu)
+{
+	struct sdei_event *event;
+	struct sdei_crosscall_args arg;
+
+	/* re-register/enable private events */
+	spin_lock(&sdei_list_lock);
+	list_for_each_entry(event, &sdei_list, list) {
+		if (event->type == SDEI_EVENT_TYPE_SHARED)
+			continue;
+
+		if (event->reregister) {
+			CROSSCALL_INIT(arg, event);
+			/* call the cross-call function locally... */
+			_local_event_register(&arg);
+			if (arg.first_error)
+				pr_err("Failed to re-register event %u: %d\n",
+				       event->event_num, arg.first_error);
+		}
+
+		if (event->reenable) {
+			CROSSCALL_INIT(arg, event);
+			_local_event_enable(&arg);
+			if (arg.first_error)
+				pr_err("Failed to re-enable event %u: %d\n",
+				       event->event_num, arg.first_error);
+		}
+	}
+	spin_unlock(&sdei_list_lock);
+
+	return sdei_unmask_local_cpu();
+}
+
+/* When entering idle, mask/unmask events for this cpu */
+static int sdei_pm_notifier(struct notifier_block *nb, unsigned long action,
+			    void *data)
+{
+	int rv;
+
+	switch (action) {
+	case CPU_PM_ENTER:
+		rv = sdei_mask_local_cpu();
+		break;
+	case CPU_PM_EXIT:
+	case CPU_PM_ENTER_FAILED:
+		rv = sdei_unmask_local_cpu();
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	if (rv)
+		return notifier_from_errno(rv);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block sdei_pm_nb = {
+	.notifier_call = sdei_pm_notifier,
+};
+
+static int sdei_device_suspend(struct device *dev)
+{
+	on_each_cpu(_ipi_mask_cpu, NULL, true);
+
+	return 0;
+}
+
+static int sdei_device_resume(struct device *dev)
+{
+	on_each_cpu(_ipi_unmask_cpu, NULL, true);
+
+	return 0;
+}
+
+/*
+ * We need all events to be reregistered when we resume from hibernate.
+ *
+ * The sequence is freeze->thaw. Reboot. freeze->restore. We unregister
+ * events during freeze, then re-register and re-enable them during thaw
+ * and restore.
+ */
+static int sdei_device_freeze(struct device *dev)
+{
+	int err;
+
+	/* unregister private events */
+	cpuhp_remove_state(CPUHP_AP_ARM_SDEI_STARTING);
+
+	err = sdei_unregister_shared();
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int sdei_device_thaw(struct device *dev)
+{
+	int err;
+
+	/* re-register shared events */
+	err = sdei_reregister_shared();
+	if (err) {
+		pr_warn("Failed to re-register shared events...\n");
+		sdei_mark_interface_broken();
+		return err;
+	}
+
+	err = cpuhp_setup_state(CPUHP_AP_ARM_SDEI_STARTING, "SDEI",
+				&sdei_cpuhp_up, &sdei_cpuhp_down);
+	if (err)
+		pr_warn("Failed to re-register CPU hotplug notifier...\n");
+
+	return err;
+}
+
+static int sdei_device_restore(struct device *dev)
+{
+	int err;
+
+	err = sdei_platform_reset();
+	if (err)
+		return err;
+
+	return sdei_device_thaw(dev);
+}
+
+static const struct dev_pm_ops sdei_pm_ops = {
+	.suspend = sdei_device_suspend,
+	.resume = sdei_device_resume,
+	.freeze = sdei_device_freeze,
+	.thaw = sdei_device_thaw,
+	.restore = sdei_device_restore,
+};
+
+/*
+ * Mask all CPUs and unregister all events on panic, reboot or kexec.
+ */
+static int sdei_reboot_notifier(struct notifier_block *nb, unsigned long action,
+				void *data)
+{
+	/*
+	 * We are going to reset the interface, after this there is no point
+	 * doing work when we take CPUs offline.
+	 */
+	cpuhp_remove_state(CPUHP_AP_ARM_SDEI_STARTING);
+
+	sdei_platform_reset();
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block sdei_reboot_nb = {
+	.notifier_call = sdei_reboot_notifier,
+};
+
+static void sdei_smccc_smc(unsigned long function_id,
+			   unsigned long arg0, unsigned long arg1,
+			   unsigned long arg2, unsigned long arg3,
+			   unsigned long arg4, struct arm_smccc_res *res)
+{
+	arm_smccc_smc(function_id, arg0, arg1, arg2, arg3, arg4, 0, 0, res);
+}
+
+static void sdei_smccc_hvc(unsigned long function_id,
+			   unsigned long arg0, unsigned long arg1,
+			   unsigned long arg2, unsigned long arg3,
+			   unsigned long arg4, struct arm_smccc_res *res)
+{
+	arm_smccc_hvc(function_id, arg0, arg1, arg2, arg3, arg4, 0, 0, res);
+}
+
+static int sdei_get_conduit(struct platform_device *pdev)
+{
+	const char *method;
+	struct device_node *np = pdev->dev.of_node;
+
+	sdei_firmware_call = NULL;
+	if (np) {
+		if (of_property_read_string(np, "method", &method)) {
+			pr_warn("missing \"method\" property\n");
+			return CONDUIT_INVALID;
+		}
+
+		if (!strcmp("hvc", method)) {
+			sdei_firmware_call = &sdei_smccc_hvc;
+			return CONDUIT_HVC;
+		} else if (!strcmp("smc", method)) {
+			sdei_firmware_call = &sdei_smccc_smc;
+			return CONDUIT_SMC;
+		}
+
+		pr_warn("invalid \"method\" property: %s\n", method);
+	} else if (IS_ENABLED(CONFIG_ACPI) && !acpi_disabled) {
+		if (acpi_psci_use_hvc()) {
+			sdei_firmware_call = &sdei_smccc_hvc;
+			return CONDUIT_HVC;
+		} else {
+			sdei_firmware_call = &sdei_smccc_smc;
+			return CONDUIT_SMC;
+		}
+	}
+
+	return CONDUIT_INVALID;
+}
+
+static int sdei_probe(struct platform_device *pdev)
+{
+	int err;
+	u64 ver = 0;
+	int conduit;
+
+	conduit = sdei_get_conduit(pdev);
+	if (!sdei_firmware_call)
+		return 0;
+
+	err = sdei_api_get_version(&ver);
+	if (err == -EOPNOTSUPP)
+		pr_err("advertised but not implemented in platform firmware\n");
+	if (err) {
+		pr_err("Failed to get SDEI version: %d\n", err);
+		sdei_mark_interface_broken();
+		return err;
+	}
+
+	pr_info("SDEIv%d.%d (0x%x) detected in firmware.\n",
+		(int)SDEI_VERSION_MAJOR(ver), (int)SDEI_VERSION_MINOR(ver),
+		(int)SDEI_VERSION_VENDOR(ver));
+
+	if (SDEI_VERSION_MAJOR(ver) != 1) {
+		pr_warn("Conflicting SDEI version detected.\n");
+		sdei_mark_interface_broken();
+		return -EINVAL;
+	}
+
+	err = sdei_platform_reset();
+	if (err)
+		return err;
+
+	sdei_entry_point = sdei_arch_get_entry_point(conduit);
+	if (!sdei_entry_point) {
+		/* Not supported due to hardware or boot configuration */
+		sdei_mark_interface_broken();
+		return 0;
+	}
+
+	err = cpu_pm_register_notifier(&sdei_pm_nb);
+	if (err) {
+		pr_warn("Failed to register CPU PM notifier...\n");
+		goto error;
+	}
+
+	err = register_reboot_notifier(&sdei_reboot_nb);
+	if (err) {
+		pr_warn("Failed to register reboot notifier...\n");
+		goto remove_cpupm;
+	}
+
+	err = cpuhp_setup_state(CPUHP_AP_ARM_SDEI_STARTING, "SDEI",
+				&sdei_cpuhp_up, &sdei_cpuhp_down);
+	if (err) {
+		pr_warn("Failed to register CPU hotplug notifier...\n");
+		goto remove_reboot;
+	}
+
+	return 0;
+
+remove_reboot:
+	unregister_reboot_notifier(&sdei_reboot_nb);
+
+remove_cpupm:
+	cpu_pm_unregister_notifier(&sdei_pm_nb);
+
+error:
+	sdei_mark_interface_broken();
+	return err;
+}
+
+static const struct of_device_id sdei_of_match[] = {
+	{ .compatible = "arm,sdei-1.0" },
+	{}
+};
+
+static struct platform_driver sdei_driver = {
+	.driver		= {
+		.name			= "sdei",
+		.pm			= &sdei_pm_ops,
+		.of_match_table		= sdei_of_match,
+	},
+	.probe		= sdei_probe,
+};
+
+static bool __init sdei_present_dt(void)
+{
+	struct platform_device *pdev;
+	struct device_node *np, *fw_np;
+
+	fw_np = of_find_node_by_name(NULL, "firmware");
+	if (!fw_np)
+		return false;
+
+	np = of_find_matching_node(fw_np, sdei_of_match);
+	of_node_put(fw_np);
+	if (!np)
+		return false;
+
+	pdev = of_platform_device_create(np, sdei_driver.driver.name, NULL);
+	of_node_put(np);
+	if (!pdev)
+		return false;
+
+	return true;
+}
+
+static bool __init sdei_present_acpi(void)
+{
+	acpi_status status;
+	struct platform_device *pdev;
+	struct acpi_table_header *sdei_table_header;
+
+	if (acpi_disabled)
+		return false;
+
+	status = acpi_get_table(ACPI_SIG_SDEI, 0, &sdei_table_header);
+	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
+		const char *msg = acpi_format_exception(status);
+
+		pr_info("Failed to get ACPI:SDEI table, %s\n", msg);
+	}
+	if (ACPI_FAILURE(status))
+		return false;
+
+	pdev = platform_device_register_simple(sdei_driver.driver.name, 0, NULL,
+					       0);
+	if (IS_ERR(pdev))
+		return false;
+
+	return true;
+}
+
+static int __init sdei_init(void)
+{
+	if (sdei_present_dt() || sdei_present_acpi())
+		platform_driver_register(&sdei_driver);
+
+	return 0;
+}
+
+/*
+ * On an ACPI system SDEI needs to be ready before HEST:GHES tries to register
+ * its events. ACPI is initialised from a subsys_initcall(), GHES is initialised
+ * by device_initcall(). We want to be called in the middle.
+ */
+subsys_initcall_sync(sdei_init);
+
+int sdei_event_handler(struct pt_regs *regs,
+		       struct sdei_registered_event *arg)
+{
+	int err;
+	mm_segment_t orig_addr_limit;
+	u32 event_num = arg->event_num;
+
+	orig_addr_limit = get_fs();
+	set_fs(USER_DS);
+
+	err = arg->callback(event_num, regs, arg->callback_arg);
+	if (err)
+		pr_err_ratelimited("event %u on CPU %u failed with error: %d\n",
+				   event_num, smp_processor_id(), err);
+
+	set_fs(orig_addr_limit);
+
+	return err;
+}
+NOKPROBE_SYMBOL(sdei_event_handler);
diff --git a/drivers/firmware/psci.c b/drivers/firmware/psci.c
index d687ca3d..8b25d31 100644
--- a/drivers/firmware/psci.c
+++ b/drivers/firmware/psci.c
@@ -496,6 +496,8 @@ static void __init psci_init_migrate(void)
 static void __init psci_0_2_set_functions(void)
 {
 	pr_info("Using standard PSCI v0.2 function IDs\n");
+	psci_ops.get_version = psci_get_version;
+
 	psci_function_id[PSCI_FN_CPU_SUSPEND] =
 					PSCI_FN_NATIVE(0_2, CPU_SUSPEND);
 	psci_ops.cpu_suspend = psci_cpu_suspend;
diff --git a/drivers/hwtracing/coresight/of_coresight.c b/drivers/hwtracing/coresight/of_coresight.c
index a187941..7c37544 100644
--- a/drivers/hwtracing/coresight/of_coresight.c
+++ b/drivers/hwtracing/coresight/of_coresight.c
@@ -104,26 +104,17 @@ static int of_coresight_alloc_memory(struct device *dev,
 int of_coresight_get_cpu(const struct device_node *node)
 {
 	int cpu;
-	bool found;
-	struct device_node *dn, *np;
+	struct device_node *dn;
 
 	dn = of_parse_phandle(node, "cpu", 0);
-
 	/* Affinity defaults to CPU0 */
 	if (!dn)
 		return 0;
-
-	for_each_possible_cpu(cpu) {
-		np = of_cpu_device_node_get(cpu);
-		found = (dn == np);
-		of_node_put(np);
-		if (found)
-			break;
-	}
+	cpu = of_cpu_node_to_id(dn);
 	of_node_put(dn);
 
 	/* Affinity to CPU0 if no cpu nodes are found */
-	return found ? cpu : 0;
+	return (cpu < 0) ? 0 : cpu;
 }
 EXPORT_SYMBOL_GPL(of_coresight_get_cpu);
 
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index a874777..a57c0fb 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -1070,31 +1070,6 @@ static int __init gic_validate_dist_version(void __iomem *dist_base)
 	return 0;
 }
 
-static int get_cpu_number(struct device_node *dn)
-{
-	const __be32 *cell;
-	u64 hwid;
-	int cpu;
-
-	cell = of_get_property(dn, "reg", NULL);
-	if (!cell)
-		return -1;
-
-	hwid = of_read_number(cell, of_n_addr_cells(dn));
-
-	/*
-	 * Non affinity bits must be set to 0 in the DT
-	 */
-	if (hwid & ~MPIDR_HWID_BITMASK)
-		return -1;
-
-	for_each_possible_cpu(cpu)
-		if (cpu_logical_map(cpu) == hwid)
-			return cpu;
-
-	return -1;
-}
-
 /* Create all possible partitions at boot time */
 static void __init gic_populate_ppi_partitions(struct device_node *gic_node)
 {
@@ -1145,8 +1120,8 @@ static void __init gic_populate_ppi_partitions(struct device_node *gic_node)
 			if (WARN_ON(!cpu_node))
 				continue;
 
-			cpu = get_cpu_number(cpu_node);
-			if (WARN_ON(cpu == -1))
+			cpu = of_cpu_node_to_id(cpu_node);
+			if (WARN_ON(cpu < 0))
 				continue;
 
 			pr_cont("%pOF[%d] ", cpu_node, cpu);
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 26618ba..a9d6fe8 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -316,6 +316,32 @@ struct device_node *of_get_cpu_node(int cpu, unsigned int *thread)
 EXPORT_SYMBOL(of_get_cpu_node);
 
 /**
+ * of_cpu_node_to_id: Get the logical CPU number for a given device_node
+ *
+ * @cpu_node: Pointer to the device_node for CPU.
+ *
+ * Returns the logical CPU number of the given CPU device_node.
+ * Returns -ENODEV if the CPU is not found.
+ */
+int of_cpu_node_to_id(struct device_node *cpu_node)
+{
+	int cpu;
+	bool found = false;
+	struct device_node *np;
+
+	for_each_possible_cpu(cpu) {
+		np = of_cpu_device_node_get(cpu);
+		found = (cpu_node == np);
+		of_node_put(np);
+		if (found)
+			return cpu;
+	}
+
+	return -ENODEV;
+}
+EXPORT_SYMBOL(of_cpu_node_to_id);
+
+/**
  * __of_device_is_compatible() - Check if the node matches given constraints
  * @device: pointer to node
  * @compat: required compatible string, NULL or "" for any match
diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig
index b8f44b0..da5724c 100644
--- a/drivers/perf/Kconfig
+++ b/drivers/perf/Kconfig
@@ -17,6 +17,15 @@ config ARM_PMU_ACPI
 	depends on ARM_PMU && ACPI
 	def_bool y
 
+config ARM_DSU_PMU
+	tristate "ARM DynamIQ Shared Unit (DSU) PMU"
+	depends on ARM64
+	  help
+	  Provides support for performance monitor unit in ARM DynamIQ Shared
+	  Unit (DSU). The DSU integrates one or more cores with an L3 memory
+	  system, control logic. The PMU allows counting various events related
+	  to DSU.
+
 config HISI_PMU
        bool "HiSilicon SoC PMU"
        depends on ARM64 && ACPI
diff --git a/drivers/perf/Makefile b/drivers/perf/Makefile
index 710a013..c2f2741 100644
--- a/drivers/perf/Makefile
+++ b/drivers/perf/Makefile
@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_ARM_DSU_PMU) += arm_dsu_pmu.o
 obj-$(CONFIG_ARM_PMU) += arm_pmu.o arm_pmu_platform.o
 obj-$(CONFIG_ARM_PMU_ACPI) += arm_pmu_acpi.o
 obj-$(CONFIG_HISI_PMU) += hisilicon/
diff --git a/drivers/perf/arm_dsu_pmu.c b/drivers/perf/arm_dsu_pmu.c
new file mode 100644
index 0000000..93c50e3
--- /dev/null
+++ b/drivers/perf/arm_dsu_pmu.c
@@ -0,0 +1,843 @@
+/*
+ * ARM DynamIQ Shared Unit (DSU) PMU driver
+ *
+ * Copyright (C) ARM Limited, 2017.
+ *
+ * Based on ARM CCI-PMU, ARMv8 PMU-v3 drivers.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ */
+
+#define PMUNAME		"arm_dsu"
+#define DRVNAME		PMUNAME "_pmu"
+#define pr_fmt(fmt)	DRVNAME ": " fmt
+
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+#include <linux/bug.h>
+#include <linux/cpumask.h>
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/perf_event.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock.h>
+#include <linux/smp.h>
+#include <linux/sysfs.h>
+#include <linux/types.h>
+
+#include <asm/arm_dsu_pmu.h>
+#include <asm/local64.h>
+
+/* PMU event codes */
+#define DSU_PMU_EVT_CYCLES		0x11
+#define DSU_PMU_EVT_CHAIN		0x1e
+
+#define DSU_PMU_MAX_COMMON_EVENTS	0x40
+
+#define DSU_PMU_MAX_HW_CNTRS		32
+#define DSU_PMU_HW_COUNTER_MASK		(DSU_PMU_MAX_HW_CNTRS - 1)
+
+#define CLUSTERPMCR_E			BIT(0)
+#define CLUSTERPMCR_P			BIT(1)
+#define CLUSTERPMCR_C			BIT(2)
+#define CLUSTERPMCR_N_SHIFT		11
+#define CLUSTERPMCR_N_MASK		0x1f
+#define CLUSTERPMCR_IDCODE_SHIFT	16
+#define CLUSTERPMCR_IDCODE_MASK		0xff
+#define CLUSTERPMCR_IMP_SHIFT		24
+#define CLUSTERPMCR_IMP_MASK		0xff
+#define CLUSTERPMCR_RES_MASK		0x7e8
+#define CLUSTERPMCR_RES_VAL		0x40
+
+#define DSU_ACTIVE_CPU_MASK		0x0
+#define DSU_ASSOCIATED_CPU_MASK		0x1
+
+/*
+ * We use the index of the counters as they appear in the counter
+ * bit maps in the PMU registers (e.g CLUSTERPMSELR).
+ * i.e,
+ *	counter 0	- Bit 0
+ *	counter 1	- Bit 1
+ *	...
+ *	Cycle counter	- Bit 31
+ */
+#define DSU_PMU_IDX_CYCLE_COUNTER	31
+
+/* All event counters are 32bit, with a 64bit Cycle counter */
+#define DSU_PMU_COUNTER_WIDTH(idx)	\
+	(((idx) == DSU_PMU_IDX_CYCLE_COUNTER) ? 64 : 32)
+
+#define DSU_PMU_COUNTER_MASK(idx)	\
+	GENMASK_ULL((DSU_PMU_COUNTER_WIDTH((idx)) - 1), 0)
+
+#define DSU_EXT_ATTR(_name, _func, _config)		\
+	(&((struct dev_ext_attribute[]) {				\
+		{							\
+			.attr = __ATTR(_name, 0444, _func, NULL),	\
+			.var = (void *)_config				\
+		}							\
+	})[0].attr.attr)
+
+#define DSU_EVENT_ATTR(_name, _config)		\
+	DSU_EXT_ATTR(_name, dsu_pmu_sysfs_event_show, (unsigned long)_config)
+
+#define DSU_FORMAT_ATTR(_name, _config)		\
+	DSU_EXT_ATTR(_name, dsu_pmu_sysfs_format_show, (char *)_config)
+
+#define DSU_CPUMASK_ATTR(_name, _config)	\
+	DSU_EXT_ATTR(_name, dsu_pmu_cpumask_show, (unsigned long)_config)
+
+struct dsu_hw_events {
+	DECLARE_BITMAP(used_mask, DSU_PMU_MAX_HW_CNTRS);
+	struct perf_event	*events[DSU_PMU_MAX_HW_CNTRS];
+};
+
+/*
+ * struct dsu_pmu	- DSU PMU descriptor
+ *
+ * @pmu_lock		: Protects accesses to DSU PMU register from normal vs
+ *			  interrupt handler contexts.
+ * @hw_events		: Holds the event counter state.
+ * @associated_cpus	: CPUs attached to the DSU.
+ * @active_cpu		: CPU to which the PMU is bound for accesses.
+ * @cpuhp_node		: Node for CPU hotplug notifier link.
+ * @num_counters	: Number of event counters implemented by the PMU,
+ *			  excluding the cycle counter.
+ * @irq			: Interrupt line for counter overflow.
+ * @cpmceid_bitmap	: Bitmap for the availability of architected common
+ *			  events (event_code < 0x40).
+ */
+struct dsu_pmu {
+	struct pmu			pmu;
+	struct device			*dev;
+	raw_spinlock_t			pmu_lock;
+	struct dsu_hw_events		hw_events;
+	cpumask_t			associated_cpus;
+	cpumask_t			active_cpu;
+	struct hlist_node		cpuhp_node;
+	s8				num_counters;
+	int				irq;
+	DECLARE_BITMAP(cpmceid_bitmap, DSU_PMU_MAX_COMMON_EVENTS);
+};
+
+static unsigned long dsu_pmu_cpuhp_state;
+
+static inline struct dsu_pmu *to_dsu_pmu(struct pmu *pmu)
+{
+	return container_of(pmu, struct dsu_pmu, pmu);
+}
+
+static ssize_t dsu_pmu_sysfs_event_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	struct dev_ext_attribute *eattr = container_of(attr,
+					struct dev_ext_attribute, attr);
+	return snprintf(buf, PAGE_SIZE, "event=0x%lx\n",
+					 (unsigned long)eattr->var);
+}
+
+static ssize_t dsu_pmu_sysfs_format_show(struct device *dev,
+					 struct device_attribute *attr,
+					 char *buf)
+{
+	struct dev_ext_attribute *eattr = container_of(attr,
+					struct dev_ext_attribute, attr);
+	return snprintf(buf, PAGE_SIZE, "%s\n", (char *)eattr->var);
+}
+
+static ssize_t dsu_pmu_cpumask_show(struct device *dev,
+				    struct device_attribute *attr,
+				    char *buf)
+{
+	struct pmu *pmu = dev_get_drvdata(dev);
+	struct dsu_pmu *dsu_pmu = to_dsu_pmu(pmu);
+	struct dev_ext_attribute *eattr = container_of(attr,
+					struct dev_ext_attribute, attr);
+	unsigned long mask_id = (unsigned long)eattr->var;
+	const cpumask_t *cpumask;
+
+	switch (mask_id) {
+	case DSU_ACTIVE_CPU_MASK:
+		cpumask = &dsu_pmu->active_cpu;
+		break;
+	case DSU_ASSOCIATED_CPU_MASK:
+		cpumask = &dsu_pmu->associated_cpus;
+		break;
+	default:
+		return 0;
+	}
+	return cpumap_print_to_pagebuf(true, buf, cpumask);
+}
+
+static struct attribute *dsu_pmu_format_attrs[] = {
+	DSU_FORMAT_ATTR(event, "config:0-31"),
+	NULL,
+};
+
+static const struct attribute_group dsu_pmu_format_attr_group = {
+	.name = "format",
+	.attrs = dsu_pmu_format_attrs,
+};
+
+static struct attribute *dsu_pmu_event_attrs[] = {
+	DSU_EVENT_ATTR(cycles, 0x11),
+	DSU_EVENT_ATTR(bus_access, 0x19),
+	DSU_EVENT_ATTR(memory_error, 0x1a),
+	DSU_EVENT_ATTR(bus_cycles, 0x1d),
+	DSU_EVENT_ATTR(l3d_cache_allocate, 0x29),
+	DSU_EVENT_ATTR(l3d_cache_refill, 0x2a),
+	DSU_EVENT_ATTR(l3d_cache, 0x2b),
+	DSU_EVENT_ATTR(l3d_cache_wb, 0x2c),
+	NULL,
+};
+
+static umode_t
+dsu_pmu_event_attr_is_visible(struct kobject *kobj, struct attribute *attr,
+				int unused)
+{
+	struct pmu *pmu = dev_get_drvdata(kobj_to_dev(kobj));
+	struct dsu_pmu *dsu_pmu = to_dsu_pmu(pmu);
+	struct dev_ext_attribute *eattr = container_of(attr,
+					struct dev_ext_attribute, attr.attr);
+	unsigned long evt = (unsigned long)eattr->var;
+
+	return test_bit(evt, dsu_pmu->cpmceid_bitmap) ? attr->mode : 0;
+}
+
+static const struct attribute_group dsu_pmu_events_attr_group = {
+	.name = "events",
+	.attrs = dsu_pmu_event_attrs,
+	.is_visible = dsu_pmu_event_attr_is_visible,
+};
+
+static struct attribute *dsu_pmu_cpumask_attrs[] = {
+	DSU_CPUMASK_ATTR(cpumask, DSU_ACTIVE_CPU_MASK),
+	DSU_CPUMASK_ATTR(associated_cpus, DSU_ASSOCIATED_CPU_MASK),
+	NULL,
+};
+
+static const struct attribute_group dsu_pmu_cpumask_attr_group = {
+	.attrs = dsu_pmu_cpumask_attrs,
+};
+
+static const struct attribute_group *dsu_pmu_attr_groups[] = {
+	&dsu_pmu_cpumask_attr_group,
+	&dsu_pmu_events_attr_group,
+	&dsu_pmu_format_attr_group,
+	NULL,
+};
+
+static int dsu_pmu_get_online_cpu_any_but(struct dsu_pmu *dsu_pmu, int cpu)
+{
+	struct cpumask online_supported;
+
+	cpumask_and(&online_supported,
+			 &dsu_pmu->associated_cpus, cpu_online_mask);
+	return cpumask_any_but(&online_supported, cpu);
+}
+
+static inline bool dsu_pmu_counter_valid(struct dsu_pmu *dsu_pmu, u32 idx)
+{
+	return (idx < dsu_pmu->num_counters) ||
+	       (idx == DSU_PMU_IDX_CYCLE_COUNTER);
+}
+
+static inline u64 dsu_pmu_read_counter(struct perf_event *event)
+{
+	u64 val;
+	unsigned long flags;
+	struct dsu_pmu *dsu_pmu = to_dsu_pmu(event->pmu);
+	int idx = event->hw.idx;
+
+	if (WARN_ON(!cpumask_test_cpu(smp_processor_id(),
+				 &dsu_pmu->associated_cpus)))
+		return 0;
+
+	if (!dsu_pmu_counter_valid(dsu_pmu, idx)) {
+		dev_err(event->pmu->dev,
+			"Trying reading invalid counter %d\n", idx);
+		return 0;
+	}
+
+	raw_spin_lock_irqsave(&dsu_pmu->pmu_lock, flags);
+	if (idx == DSU_PMU_IDX_CYCLE_COUNTER)
+		val = __dsu_pmu_read_pmccntr();
+	else
+		val = __dsu_pmu_read_counter(idx);
+	raw_spin_unlock_irqrestore(&dsu_pmu->pmu_lock, flags);
+
+	return val;
+}
+
+static void dsu_pmu_write_counter(struct perf_event *event, u64 val)
+{
+	unsigned long flags;
+	struct dsu_pmu *dsu_pmu = to_dsu_pmu(event->pmu);
+	int idx = event->hw.idx;
+
+	if (WARN_ON(!cpumask_test_cpu(smp_processor_id(),
+			 &dsu_pmu->associated_cpus)))
+		return;
+
+	if (!dsu_pmu_counter_valid(dsu_pmu, idx)) {
+		dev_err(event->pmu->dev,
+			"writing to invalid counter %d\n", idx);
+		return;
+	}
+
+	raw_spin_lock_irqsave(&dsu_pmu->pmu_lock, flags);
+	if (idx == DSU_PMU_IDX_CYCLE_COUNTER)
+		__dsu_pmu_write_pmccntr(val);
+	else
+		__dsu_pmu_write_counter(idx, val);
+	raw_spin_unlock_irqrestore(&dsu_pmu->pmu_lock, flags);
+}
+
+static int dsu_pmu_get_event_idx(struct dsu_hw_events *hw_events,
+				 struct perf_event *event)
+{
+	int idx;
+	unsigned long evtype = event->attr.config;
+	struct dsu_pmu *dsu_pmu = to_dsu_pmu(event->pmu);
+	unsigned long *used_mask = hw_events->used_mask;
+
+	if (evtype == DSU_PMU_EVT_CYCLES) {
+		if (test_and_set_bit(DSU_PMU_IDX_CYCLE_COUNTER, used_mask))
+			return -EAGAIN;
+		return DSU_PMU_IDX_CYCLE_COUNTER;
+	}
+
+	idx = find_first_zero_bit(used_mask, dsu_pmu->num_counters);
+	if (idx >= dsu_pmu->num_counters)
+		return -EAGAIN;
+	set_bit(idx, hw_events->used_mask);
+	return idx;
+}
+
+static void dsu_pmu_enable_counter(struct dsu_pmu *dsu_pmu, int idx)
+{
+	__dsu_pmu_counter_interrupt_enable(idx);
+	__dsu_pmu_enable_counter(idx);
+}
+
+static void dsu_pmu_disable_counter(struct dsu_pmu *dsu_pmu, int idx)
+{
+	__dsu_pmu_disable_counter(idx);
+	__dsu_pmu_counter_interrupt_disable(idx);
+}
+
+static inline void dsu_pmu_set_event(struct dsu_pmu *dsu_pmu,
+					struct perf_event *event)
+{
+	int idx = event->hw.idx;
+	unsigned long flags;
+
+	if (!dsu_pmu_counter_valid(dsu_pmu, idx)) {
+		dev_err(event->pmu->dev,
+			"Trying to set invalid counter %d\n", idx);
+		return;
+	}
+
+	raw_spin_lock_irqsave(&dsu_pmu->pmu_lock, flags);
+	__dsu_pmu_set_event(idx, event->hw.config_base);
+	raw_spin_unlock_irqrestore(&dsu_pmu->pmu_lock, flags);
+}
+
+static void dsu_pmu_event_update(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	u64 delta, prev_count, new_count;
+
+	do {
+		/* We may also be called from the irq handler */
+		prev_count = local64_read(&hwc->prev_count);
+		new_count = dsu_pmu_read_counter(event);
+	} while (local64_cmpxchg(&hwc->prev_count, prev_count, new_count) !=
+			prev_count);
+	delta = (new_count - prev_count) & DSU_PMU_COUNTER_MASK(hwc->idx);
+	local64_add(delta, &event->count);
+}
+
+static void dsu_pmu_read(struct perf_event *event)
+{
+	dsu_pmu_event_update(event);
+}
+
+static inline u32 dsu_pmu_get_reset_overflow(void)
+{
+	return __dsu_pmu_get_reset_overflow();
+}
+
+/**
+ * dsu_pmu_set_event_period: Set the period for the counter.
+ *
+ * All DSU PMU event counters, except the cycle counter are 32bit
+ * counters. To handle cases of extreme interrupt latency, we program
+ * the counter with half of the max count for the counters.
+ */
+static void dsu_pmu_set_event_period(struct perf_event *event)
+{
+	int idx = event->hw.idx;
+	u64 val = DSU_PMU_COUNTER_MASK(idx) >> 1;
+
+	local64_set(&event->hw.prev_count, val);
+	dsu_pmu_write_counter(event, val);
+}
+
+static irqreturn_t dsu_pmu_handle_irq(int irq_num, void *dev)
+{
+	int i;
+	bool handled = false;
+	struct dsu_pmu *dsu_pmu = dev;
+	struct dsu_hw_events *hw_events = &dsu_pmu->hw_events;
+	unsigned long overflow;
+
+	overflow = dsu_pmu_get_reset_overflow();
+	if (!overflow)
+		return IRQ_NONE;
+
+	for_each_set_bit(i, &overflow, DSU_PMU_MAX_HW_CNTRS) {
+		struct perf_event *event = hw_events->events[i];
+
+		if (!event)
+			continue;
+		dsu_pmu_event_update(event);
+		dsu_pmu_set_event_period(event);
+		handled = true;
+	}
+
+	return IRQ_RETVAL(handled);
+}
+
+static void dsu_pmu_start(struct perf_event *event, int pmu_flags)
+{
+	struct dsu_pmu *dsu_pmu = to_dsu_pmu(event->pmu);
+
+	/* We always reprogram the counter */
+	if (pmu_flags & PERF_EF_RELOAD)
+		WARN_ON(!(event->hw.state & PERF_HES_UPTODATE));
+	dsu_pmu_set_event_period(event);
+	if (event->hw.idx != DSU_PMU_IDX_CYCLE_COUNTER)
+		dsu_pmu_set_event(dsu_pmu, event);
+	event->hw.state = 0;
+	dsu_pmu_enable_counter(dsu_pmu, event->hw.idx);
+}
+
+static void dsu_pmu_stop(struct perf_event *event, int pmu_flags)
+{
+	struct dsu_pmu *dsu_pmu = to_dsu_pmu(event->pmu);
+
+	if (event->hw.state & PERF_HES_STOPPED)
+		return;
+	dsu_pmu_disable_counter(dsu_pmu, event->hw.idx);
+	dsu_pmu_event_update(event);
+	event->hw.state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
+}
+
+static int dsu_pmu_add(struct perf_event *event, int flags)
+{
+	struct dsu_pmu *dsu_pmu = to_dsu_pmu(event->pmu);
+	struct dsu_hw_events *hw_events = &dsu_pmu->hw_events;
+	struct hw_perf_event *hwc = &event->hw;
+	int idx;
+
+	if (WARN_ON_ONCE(!cpumask_test_cpu(smp_processor_id(),
+					   &dsu_pmu->associated_cpus)))
+		return -ENOENT;
+
+	idx = dsu_pmu_get_event_idx(hw_events, event);
+	if (idx < 0)
+		return idx;
+
+	hwc->idx = idx;
+	hw_events->events[idx] = event;
+	hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
+
+	if (flags & PERF_EF_START)
+		dsu_pmu_start(event, PERF_EF_RELOAD);
+
+	perf_event_update_userpage(event);
+	return 0;
+}
+
+static void dsu_pmu_del(struct perf_event *event, int flags)
+{
+	struct dsu_pmu *dsu_pmu = to_dsu_pmu(event->pmu);
+	struct dsu_hw_events *hw_events = &dsu_pmu->hw_events;
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	dsu_pmu_stop(event, PERF_EF_UPDATE);
+	hw_events->events[idx] = NULL;
+	clear_bit(idx, hw_events->used_mask);
+	perf_event_update_userpage(event);
+}
+
+static void dsu_pmu_enable(struct pmu *pmu)
+{
+	u32 pmcr;
+	unsigned long flags;
+	struct dsu_pmu *dsu_pmu = to_dsu_pmu(pmu);
+
+	/* If no counters are added, skip enabling the PMU */
+	if (bitmap_empty(dsu_pmu->hw_events.used_mask, DSU_PMU_MAX_HW_CNTRS))
+		return;
+
+	raw_spin_lock_irqsave(&dsu_pmu->pmu_lock, flags);
+	pmcr = __dsu_pmu_read_pmcr();
+	pmcr |= CLUSTERPMCR_E;
+	__dsu_pmu_write_pmcr(pmcr);
+	raw_spin_unlock_irqrestore(&dsu_pmu->pmu_lock, flags);
+}
+
+static void dsu_pmu_disable(struct pmu *pmu)
+{
+	u32 pmcr;
+	unsigned long flags;
+	struct dsu_pmu *dsu_pmu = to_dsu_pmu(pmu);
+
+	raw_spin_lock_irqsave(&dsu_pmu->pmu_lock, flags);
+	pmcr = __dsu_pmu_read_pmcr();
+	pmcr &= ~CLUSTERPMCR_E;
+	__dsu_pmu_write_pmcr(pmcr);
+	raw_spin_unlock_irqrestore(&dsu_pmu->pmu_lock, flags);
+}
+
+static bool dsu_pmu_validate_event(struct pmu *pmu,
+				  struct dsu_hw_events *hw_events,
+				  struct perf_event *event)
+{
+	if (is_software_event(event))
+		return true;
+	/* Reject groups spanning multiple HW PMUs. */
+	if (event->pmu != pmu)
+		return false;
+	return dsu_pmu_get_event_idx(hw_events, event) >= 0;
+}
+
+/*
+ * Make sure the group of events can be scheduled at once
+ * on the PMU.
+ */
+static bool dsu_pmu_validate_group(struct perf_event *event)
+{
+	struct perf_event *sibling, *leader = event->group_leader;
+	struct dsu_hw_events fake_hw;
+
+	if (event->group_leader == event)
+		return true;
+
+	memset(fake_hw.used_mask, 0, sizeof(fake_hw.used_mask));
+	if (!dsu_pmu_validate_event(event->pmu, &fake_hw, leader))
+		return false;
+	list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
+		if (!dsu_pmu_validate_event(event->pmu, &fake_hw, sibling))
+			return false;
+	}
+	return dsu_pmu_validate_event(event->pmu, &fake_hw, event);
+}
+
+static int dsu_pmu_event_init(struct perf_event *event)
+{
+	struct dsu_pmu *dsu_pmu = to_dsu_pmu(event->pmu);
+
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
+	/* We don't support sampling */
+	if (is_sampling_event(event)) {
+		dev_dbg(dsu_pmu->pmu.dev, "Can't support sampling events\n");
+		return -EOPNOTSUPP;
+	}
+
+	/* We cannot support task bound events */
+	if (event->cpu < 0 || event->attach_state & PERF_ATTACH_TASK) {
+		dev_dbg(dsu_pmu->pmu.dev, "Can't support per-task counters\n");
+		return -EINVAL;
+	}
+
+	if (has_branch_stack(event) ||
+	    event->attr.exclude_user ||
+	    event->attr.exclude_kernel ||
+	    event->attr.exclude_hv ||
+	    event->attr.exclude_idle ||
+	    event->attr.exclude_host ||
+	    event->attr.exclude_guest) {
+		dev_dbg(dsu_pmu->pmu.dev, "Can't support filtering\n");
+		return -EINVAL;
+	}
+
+	if (!cpumask_test_cpu(event->cpu, &dsu_pmu->associated_cpus)) {
+		dev_dbg(dsu_pmu->pmu.dev,
+			 "Requested cpu is not associated with the DSU\n");
+		return -EINVAL;
+	}
+	/*
+	 * Choose the current active CPU to read the events. We don't want
+	 * to migrate the event contexts, irq handling etc to the requested
+	 * CPU. As long as the requested CPU is within the same DSU, we
+	 * are fine.
+	 */
+	event->cpu = cpumask_first(&dsu_pmu->active_cpu);
+	if (event->cpu >= nr_cpu_ids)
+		return -EINVAL;
+	if (!dsu_pmu_validate_group(event))
+		return -EINVAL;
+
+	event->hw.config_base = event->attr.config;
+	return 0;
+}
+
+static struct dsu_pmu *dsu_pmu_alloc(struct platform_device *pdev)
+{
+	struct dsu_pmu *dsu_pmu;
+
+	dsu_pmu = devm_kzalloc(&pdev->dev, sizeof(*dsu_pmu), GFP_KERNEL);
+	if (!dsu_pmu)
+		return ERR_PTR(-ENOMEM);
+
+	raw_spin_lock_init(&dsu_pmu->pmu_lock);
+	/*
+	 * Initialise the number of counters to -1, until we probe
+	 * the real number on a connected CPU.
+	 */
+	dsu_pmu->num_counters = -1;
+	return dsu_pmu;
+}
+
+/**
+ * dsu_pmu_dt_get_cpus: Get the list of CPUs in the cluster.
+ */
+static int dsu_pmu_dt_get_cpus(struct device_node *dev, cpumask_t *mask)
+{
+	int i = 0, n, cpu;
+	struct device_node *cpu_node;
+
+	n = of_count_phandle_with_args(dev, "cpus", NULL);
+	if (n <= 0)
+		return -ENODEV;
+	for (; i < n; i++) {
+		cpu_node = of_parse_phandle(dev, "cpus", i);
+		if (!cpu_node)
+			break;
+		cpu = of_cpu_node_to_id(cpu_node);
+		of_node_put(cpu_node);
+		/*
+		 * We have to ignore the failures here and continue scanning
+		 * the list to handle cases where the nr_cpus could be capped
+		 * in the running kernel.
+		 */
+		if (cpu < 0)
+			continue;
+		cpumask_set_cpu(cpu, mask);
+	}
+	return 0;
+}
+
+/*
+ * dsu_pmu_probe_pmu: Probe the PMU details on a CPU in the cluster.
+ */
+static void dsu_pmu_probe_pmu(struct dsu_pmu *dsu_pmu)
+{
+	u64 num_counters;
+	u32 cpmceid[2];
+
+	num_counters = (__dsu_pmu_read_pmcr() >> CLUSTERPMCR_N_SHIFT) &
+						CLUSTERPMCR_N_MASK;
+	/* We can only support up to 31 independent counters */
+	if (WARN_ON(num_counters > 31))
+		num_counters = 31;
+	dsu_pmu->num_counters = num_counters;
+	if (!dsu_pmu->num_counters)
+		return;
+	cpmceid[0] = __dsu_pmu_read_pmceid(0);
+	cpmceid[1] = __dsu_pmu_read_pmceid(1);
+	bitmap_from_u32array(dsu_pmu->cpmceid_bitmap,
+				DSU_PMU_MAX_COMMON_EVENTS,
+				cpmceid,
+				ARRAY_SIZE(cpmceid));
+}
+
+static void dsu_pmu_set_active_cpu(int cpu, struct dsu_pmu *dsu_pmu)
+{
+	cpumask_set_cpu(cpu, &dsu_pmu->active_cpu);
+	if (irq_set_affinity_hint(dsu_pmu->irq, &dsu_pmu->active_cpu))
+		pr_warn("Failed to set irq affinity to %d\n", cpu);
+}
+
+/*
+ * dsu_pmu_init_pmu: Initialise the DSU PMU configurations if
+ * we haven't done it already.
+ */
+static void dsu_pmu_init_pmu(struct dsu_pmu *dsu_pmu)
+{
+	if (dsu_pmu->num_counters == -1)
+		dsu_pmu_probe_pmu(dsu_pmu);
+	/* Reset the interrupt overflow mask */
+	dsu_pmu_get_reset_overflow();
+}
+
+static int dsu_pmu_device_probe(struct platform_device *pdev)
+{
+	int irq, rc;
+	struct dsu_pmu *dsu_pmu;
+	char *name;
+	static atomic_t pmu_idx = ATOMIC_INIT(-1);
+
+	dsu_pmu = dsu_pmu_alloc(pdev);
+	if (IS_ERR(dsu_pmu))
+		return PTR_ERR(dsu_pmu);
+
+	rc = dsu_pmu_dt_get_cpus(pdev->dev.of_node, &dsu_pmu->associated_cpus);
+	if (rc) {
+		dev_warn(&pdev->dev, "Failed to parse the CPUs\n");
+		return rc;
+	}
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_warn(&pdev->dev, "Failed to find IRQ\n");
+		return -EINVAL;
+	}
+
+	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%s_%d",
+				PMUNAME, atomic_inc_return(&pmu_idx));
+	if (!name)
+		return -ENOMEM;
+	rc = devm_request_irq(&pdev->dev, irq, dsu_pmu_handle_irq,
+			      IRQF_NOBALANCING, name, dsu_pmu);
+	if (rc) {
+		dev_warn(&pdev->dev, "Failed to request IRQ %d\n", irq);
+		return rc;
+	}
+
+	dsu_pmu->irq = irq;
+	platform_set_drvdata(pdev, dsu_pmu);
+	rc = cpuhp_state_add_instance(dsu_pmu_cpuhp_state,
+						&dsu_pmu->cpuhp_node);
+	if (rc)
+		return rc;
+
+	dsu_pmu->pmu = (struct pmu) {
+		.task_ctx_nr	= perf_invalid_context,
+		.module		= THIS_MODULE,
+		.pmu_enable	= dsu_pmu_enable,
+		.pmu_disable	= dsu_pmu_disable,
+		.event_init	= dsu_pmu_event_init,
+		.add		= dsu_pmu_add,
+		.del		= dsu_pmu_del,
+		.start		= dsu_pmu_start,
+		.stop		= dsu_pmu_stop,
+		.read		= dsu_pmu_read,
+
+		.attr_groups	= dsu_pmu_attr_groups,
+	};
+
+	rc = perf_pmu_register(&dsu_pmu->pmu, name, -1);
+	if (rc) {
+		cpuhp_state_remove_instance(dsu_pmu_cpuhp_state,
+						 &dsu_pmu->cpuhp_node);
+		irq_set_affinity_hint(dsu_pmu->irq, NULL);
+	}
+
+	return rc;
+}
+
+static int dsu_pmu_device_remove(struct platform_device *pdev)
+{
+	struct dsu_pmu *dsu_pmu = platform_get_drvdata(pdev);
+
+	perf_pmu_unregister(&dsu_pmu->pmu);
+	cpuhp_state_remove_instance(dsu_pmu_cpuhp_state, &dsu_pmu->cpuhp_node);
+	irq_set_affinity_hint(dsu_pmu->irq, NULL);
+
+	return 0;
+}
+
+static const struct of_device_id dsu_pmu_of_match[] = {
+	{ .compatible = "arm,dsu-pmu", },
+	{},
+};
+
+static struct platform_driver dsu_pmu_driver = {
+	.driver = {
+		.name	= DRVNAME,
+		.of_match_table = of_match_ptr(dsu_pmu_of_match),
+	},
+	.probe = dsu_pmu_device_probe,
+	.remove = dsu_pmu_device_remove,
+};
+
+static int dsu_pmu_cpu_online(unsigned int cpu, struct hlist_node *node)
+{
+	struct dsu_pmu *dsu_pmu = hlist_entry_safe(node, struct dsu_pmu,
+						   cpuhp_node);
+
+	if (!cpumask_test_cpu(cpu, &dsu_pmu->associated_cpus))
+		return 0;
+
+	/* If the PMU is already managed, there is nothing to do */
+	if (!cpumask_empty(&dsu_pmu->active_cpu))
+		return 0;
+
+	dsu_pmu_init_pmu(dsu_pmu);
+	dsu_pmu_set_active_cpu(cpu, dsu_pmu);
+
+	return 0;
+}
+
+static int dsu_pmu_cpu_teardown(unsigned int cpu, struct hlist_node *node)
+{
+	int dst;
+	struct dsu_pmu *dsu_pmu = hlist_entry_safe(node, struct dsu_pmu,
+						   cpuhp_node);
+
+	if (!cpumask_test_and_clear_cpu(cpu, &dsu_pmu->active_cpu))
+		return 0;
+
+	dst = dsu_pmu_get_online_cpu_any_but(dsu_pmu, cpu);
+	/* If there are no active CPUs in the DSU, leave IRQ disabled */
+	if (dst >= nr_cpu_ids) {
+		irq_set_affinity_hint(dsu_pmu->irq, NULL);
+		return 0;
+	}
+
+	perf_pmu_migrate_context(&dsu_pmu->pmu, cpu, dst);
+	dsu_pmu_set_active_cpu(dst, dsu_pmu);
+
+	return 0;
+}
+
+static int __init dsu_pmu_init(void)
+{
+	int ret;
+
+	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
+					DRVNAME,
+					dsu_pmu_cpu_online,
+					dsu_pmu_cpu_teardown);
+	if (ret < 0)
+		return ret;
+	dsu_pmu_cpuhp_state = ret;
+	return platform_driver_register(&dsu_pmu_driver);
+}
+
+static void __exit dsu_pmu_exit(void)
+{
+	platform_driver_unregister(&dsu_pmu_driver);
+	cpuhp_remove_multi_state(dsu_pmu_cpuhp_state);
+}
+
+module_init(dsu_pmu_init);
+module_exit(dsu_pmu_exit);
+
+MODULE_DEVICE_TABLE(of, dsu_pmu_of_match);
+MODULE_DESCRIPTION("Perf driver for ARM DynamIQ Shared Unit");
+MODULE_AUTHOR("Suzuki K Poulose <suzuki.poulose@arm.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/perf/arm_pmu_platform.c b/drivers/perf/arm_pmu_platform.c
index 91b224ec..46501cc 100644
--- a/drivers/perf/arm_pmu_platform.c
+++ b/drivers/perf/arm_pmu_platform.c
@@ -82,19 +82,10 @@ static int pmu_parse_irq_affinity(struct device_node *node, int i)
 		return -EINVAL;
 	}
 
-	/* Now look up the logical CPU number */
-	for_each_possible_cpu(cpu) {
-		struct device_node *cpu_dn;
-
-		cpu_dn = of_cpu_device_node_get(cpu);
-		of_node_put(cpu_dn);
-
-		if (dn == cpu_dn)
-			break;
-	}
-
-	if (cpu >= nr_cpu_ids) {
+	cpu = of_cpu_node_to_id(dn);
+	if (cpu < 0) {
 		pr_warn("failed to find logical CPU for %s\n", dn->name);
+		cpu = nr_cpu_ids;
 	}
 
 	of_node_put(dn);
diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c
index 8ce262f..51b40ae 100644
--- a/drivers/perf/arm_spe_pmu.c
+++ b/drivers/perf/arm_spe_pmu.c
@@ -1164,6 +1164,15 @@ static int arm_spe_pmu_device_dt_probe(struct platform_device *pdev)
 	struct arm_spe_pmu *spe_pmu;
 	struct device *dev = &pdev->dev;
 
+	/*
+	 * If kernelspace is unmapped when running at EL0, then the SPE
+	 * buffer will fault and prematurely terminate the AUX session.
+	 */
+	if (arm64_kernel_unmapped_at_el0()) {
+		dev_warn_once(dev, "profiling buffer inaccessible. Try passing \"kpti=off\" on the kernel command line\n");
+		return -EPERM;
+	}
+
 	spe_pmu = devm_kzalloc(dev, sizeof(*spe_pmu), GFP_KERNEL);
 	if (!spe_pmu) {
 		dev_err(dev, "failed to allocate spe_pmu\n");