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

Pull arm64 updates from Will Deacon:
 "ACPI:

   - Improve error reporting when failing to manage SDEI on AGDI device
     removal

  Assembly routines:

   - Improve register constraints so that the compiler can make use of
     the zero register instead of moving an immediate #0 into a GPR

   - Allow the compiler to allocate the registers used for CAS
     instructions

  CPU features and system registers:

   - Cleanups to the way in which CPU features are identified from the
     ID register fields

   - Extend system register definition generation to handle Enum types
     when defining shared register fields

   - Generate definitions for new _EL2 registers and add new fields for
     ID_AA64PFR1_EL1

   - Allow SVE to be disabled separately from SME on the kernel
     command-line

  Tracing:

   - Support for "direct calls" in ftrace, which enables BPF tracing for
     arm64

  Kdump:

   - Don't bother unmapping the crashkernel from the linear mapping,
     which then allows us to use huge (block) mappings and reduce TLB
     pressure when a crashkernel is loaded.

  Memory management:

   - Try again to remove data cache invalidation from the coherent DMA
     allocation path

   - Simplify the fixmap code by mapping at page granularity

   - Allow the kfence pool to be allocated early, preventing the rest of
     the linear mapping from being forced to page granularity

  Perf and PMU:

   - Move CPU PMU code out to drivers/perf/ where it can be reused by
     the 32-bit ARM architecture when running on ARMv8 CPUs

   - Fix race between CPU PMU probing and pKVM host de-privilege

   - Add support for Apple M2 CPU PMU

   - Adjust the generic PERF_COUNT_HW_BRANCH_INSTRUCTIONS event
     dynamically, depending on what the CPU actually supports

   - Minor fixes and cleanups to system PMU drivers

  Stack tracing:

   - Use the XPACLRI instruction to strip PAC from pointers, rather than
     rolling our own function in C

   - Remove redundant PAC removal for toolchains that handle this in
     their builtins

   - Make backtracing more resilient in the face of instrumentation

  Miscellaneous:

   - Fix single-step with KGDB

   - Remove harmless warning when 'nokaslr' is passed on the kernel
     command-line

   - Minor fixes and cleanups across the board"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (72 commits)
  KVM: arm64: Ensure CPU PMU probes before pKVM host de-privilege
  arm64: kexec: include reboot.h
  arm64: delete dead code in this_cpu_set_vectors()
  arm64/cpufeature: Use helper macro to specify ID register for capabilites
  drivers/perf: hisi: add NULL check for name
  drivers/perf: hisi: Remove redundant initialized of pmu->name
  arm64/cpufeature: Consistently use symbolic constants for min_field_value
  arm64/cpufeature: Pull out helper for CPUID register definitions
  arm64/sysreg: Convert HFGITR_EL2 to automatic generation
  ACPI: AGDI: Improve error reporting for problems during .remove()
  arm64: kernel: Fix kernel warning when nokaslr is passed to commandline
  perf/arm-cmn: Fix port detection for CMN-700
  arm64: kgdb: Set PSTATE.SS to 1 to re-enable single-step
  arm64: move PAC masks to <asm/pointer_auth.h>
  arm64: use XPACLRI to strip PAC
  arm64: avoid redundant PAC stripping in __builtin_return_address()
  arm64/sme: Fix some comments of ARM SME
  arm64/signal: Alloc tpidr2 sigframe after checking system_supports_tpidr2()
  arm64/signal: Use system_supports_tpidr2() to check TPIDR2
  arm64/idreg: Don't disable SME when disabling SVE
  ...

20 files changed, 1547 insertions, 86 deletions

diff --git a/drivers/acpi/arm64/agdi.c b/drivers/acpi/arm64/agdi.c
index cf31abd0ed1b..f605302395c3 100644
--- a/drivers/acpi/arm64/agdi.c
+++ b/drivers/acpi/arm64/agdi.c
@@ -64,8 +64,11 @@ static int agdi_remove(struct platform_device *pdev)
 	int err, i;
 
 	err = sdei_event_disable(adata->sdei_event);
-	if (err)
-		return err;
+	if (err) {
+		dev_err(&pdev->dev, "Failed to disable sdei-event #%d (%pe)\n",
+			adata->sdei_event, ERR_PTR(err));
+		return 0;
+	}
 
 	for (i = 0; i < 3; i++) {
 		err = sdei_event_unregister(adata->sdei_event);
@@ -75,7 +78,11 @@ static int agdi_remove(struct platform_device *pdev)
 		schedule();
 	}
 
-	return err;
+	if (err)
+		dev_err(&pdev->dev, "Failed to unregister sdei-event #%d (%pe)\n",
+			adata->sdei_event, ERR_PTR(err));
+
+	return 0;
 }
 
 static struct platform_driver agdi_driver = {
diff --git a/drivers/firmware/arm_sdei.c b/drivers/firmware/arm_sdei.c
index 1e1a51510e83..f9040bd61081 100644
--- a/drivers/firmware/arm_sdei.c
+++ b/drivers/firmware/arm_sdei.c
@@ -43,6 +43,8 @@ static asmlinkage void (*sdei_firmware_call)(unsigned long function_id,
 /* entry point from firmware to arch asm code */
 static unsigned long sdei_entry_point;
 
+static int sdei_hp_state;
+
 struct sdei_event {
 	/* These three are protected by the sdei_list_lock */
 	struct list_head	list;
@@ -301,8 +303,6 @@ 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",
@@ -315,6 +315,7 @@ int sdei_mask_local_cpu(void)
 
 static void _ipi_mask_cpu(void *ignored)
 {
+	WARN_ON_ONCE(preemptible());
 	sdei_mask_local_cpu();
 }
 
@@ -322,8 +323,6 @@ 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",
@@ -336,6 +335,7 @@ int sdei_unmask_local_cpu(void)
 
 static void _ipi_unmask_cpu(void *ignored)
 {
+	WARN_ON_ONCE(preemptible());
 	sdei_unmask_local_cpu();
 }
 
@@ -343,6 +343,8 @@ static void _ipi_private_reset(void *ignored)
 {
 	int err;
 
+	WARN_ON_ONCE(preemptible());
+
 	err = invoke_sdei_fn(SDEI_1_0_FN_SDEI_PRIVATE_RESET, 0, 0, 0, 0, 0,
 			     NULL);
 	if (err && err != -EIO)
@@ -389,8 +391,6 @@ 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);
@@ -479,8 +479,6 @@ 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);
@@ -561,8 +559,6 @@ static void _local_event_register(void *data)
 	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);
@@ -717,6 +713,8 @@ static int sdei_pm_notifier(struct notifier_block *nb, unsigned long action,
 {
 	int rv;
 
+	WARN_ON_ONCE(preemptible());
+
 	switch (action) {
 	case CPU_PM_ENTER:
 		rv = sdei_mask_local_cpu();
@@ -765,7 +763,7 @@ static int sdei_device_freeze(struct device *dev)
 	int err;
 
 	/* unregister private events */
-	cpuhp_remove_state(CPUHP_AP_ARM_SDEI_STARTING);
+	cpuhp_remove_state(sdei_entry_point);
 
 	err = sdei_unregister_shared();
 	if (err)
@@ -786,12 +784,15 @@ static int sdei_device_thaw(struct device *dev)
 		return err;
 	}
 
-	err = cpuhp_setup_state(CPUHP_AP_ARM_SDEI_STARTING, "SDEI",
+	err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "SDEI",
 				&sdei_cpuhp_up, &sdei_cpuhp_down);
-	if (err)
+	if (err < 0) {
 		pr_warn("Failed to re-register CPU hotplug notifier...\n");
+		return err;
+	}
 
-	return err;
+	sdei_hp_state = err;
+	return 0;
 }
 
 static int sdei_device_restore(struct device *dev)
@@ -823,7 +824,7 @@ static int sdei_reboot_notifier(struct notifier_block *nb, unsigned long action,
 	 * 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);
+	cpuhp_remove_state(sdei_hp_state);
 
 	sdei_platform_reset();
 
@@ -1003,13 +1004,15 @@ static int sdei_probe(struct platform_device *pdev)
 		goto remove_cpupm;
 	}
 
-	err = cpuhp_setup_state(CPUHP_AP_ARM_SDEI_STARTING, "SDEI",
+	err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "SDEI",
 				&sdei_cpuhp_up, &sdei_cpuhp_down);
-	if (err) {
+	if (err < 0) {
 		pr_warn("Failed to register CPU hotplug notifier...\n");
 		goto remove_reboot;
 	}
 
+	sdei_hp_state = err;
+
 	return 0;
 
 remove_reboot:
diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig
index 66c259000a44..711f82400086 100644
--- a/drivers/perf/Kconfig
+++ b/drivers/perf/Kconfig
@@ -100,6 +100,16 @@ config ARM_SMMU_V3_PMU
 	   through the SMMU and allow the resulting information to be filtered
 	   based on the Stream ID of the corresponding master.
 
+config ARM_PMUV3
+	depends on HW_PERF_EVENTS && ((ARM && CPU_V7) || ARM64)
+	bool "ARM PMUv3 support" if !ARM64
+	default ARM64
+	  help
+	  Say y if you want to use the ARM performance monitor unit (PMU)
+	  version 3. The PMUv3 is the CPU performance monitors on ARMv8
+	  (aarch32 and aarch64) systems that implement the PMUv3
+	  architecture.
+
 config ARM_DSU_PMU
 	tristate "ARM DynamIQ Shared Unit (DSU) PMU"
 	depends on ARM64
diff --git a/drivers/perf/Makefile b/drivers/perf/Makefile
index 13e45da61100..dabc859540ce 100644
--- a/drivers/perf/Makefile
+++ b/drivers/perf/Makefile
@@ -5,6 +5,7 @@ obj-$(CONFIG_ARM_CMN) += arm-cmn.o
 obj-$(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-$(CONFIG_ARM_PMUV3) += arm_pmuv3.o
 obj-$(CONFIG_ARM_SMMU_V3_PMU) += arm_smmuv3_pmu.o
 obj-$(CONFIG_FSL_IMX8_DDR_PMU) += fsl_imx8_ddr_perf.o
 obj-$(CONFIG_HISI_PMU) += hisilicon/
diff --git a/drivers/perf/alibaba_uncore_drw_pmu.c b/drivers/perf/alibaba_uncore_drw_pmu.c
index a7689fecb49d..5c5be9fc1b15 100644
--- a/drivers/perf/alibaba_uncore_drw_pmu.c
+++ b/drivers/perf/alibaba_uncore_drw_pmu.c
@@ -656,8 +656,7 @@ static int ali_drw_pmu_probe(struct platform_device *pdev)
 	drw_pmu->dev = &pdev->dev;
 	platform_set_drvdata(pdev, drw_pmu);
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	drw_pmu->cfg_base = devm_ioremap_resource(&pdev->dev, res);
+	drw_pmu->cfg_base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
 	if (IS_ERR(drw_pmu->cfg_base))
 		return PTR_ERR(drw_pmu->cfg_base);
 
diff --git a/drivers/perf/amlogic/meson_ddr_pmu_core.c b/drivers/perf/amlogic/meson_ddr_pmu_core.c
index b84346dbac2c..0b24dee1ed3c 100644
--- a/drivers/perf/amlogic/meson_ddr_pmu_core.c
+++ b/drivers/perf/amlogic/meson_ddr_pmu_core.c
@@ -156,10 +156,14 @@ static int meson_ddr_perf_event_add(struct perf_event *event, int flags)
 	u64 config2 = event->attr.config2;
 	int i;
 
-	for_each_set_bit(i, (const unsigned long *)&config1, sizeof(config1))
+	for_each_set_bit(i,
+			 (const unsigned long *)&config1,
+			 BITS_PER_TYPE(config1))
 		meson_ddr_set_axi_filter(event, i);
 
-	for_each_set_bit(i, (const unsigned long *)&config2, sizeof(config2))
+	for_each_set_bit(i,
+			 (const unsigned long *)&config2,
+			 BITS_PER_TYPE(config2))
 		meson_ddr_set_axi_filter(event, i + 64);
 
 	if (flags & PERF_EF_START)
diff --git a/drivers/perf/apple_m1_cpu_pmu.c b/drivers/perf/apple_m1_cpu_pmu.c
index 979a7c2b4f56..8574c6e58c83 100644
--- a/drivers/perf/apple_m1_cpu_pmu.c
+++ b/drivers/perf/apple_m1_cpu_pmu.c
@@ -559,7 +559,21 @@ static int m1_pmu_fire_init(struct arm_pmu *cpu_pmu)
 	return m1_pmu_init(cpu_pmu);
 }
 
+static int m2_pmu_avalanche_init(struct arm_pmu *cpu_pmu)
+{
+	cpu_pmu->name = "apple_avalanche_pmu";
+	return m1_pmu_init(cpu_pmu);
+}
+
+static int m2_pmu_blizzard_init(struct arm_pmu *cpu_pmu)
+{
+	cpu_pmu->name = "apple_blizzard_pmu";
+	return m1_pmu_init(cpu_pmu);
+}
+
 static const struct of_device_id m1_pmu_of_device_ids[] = {
+	{ .compatible = "apple,avalanche-pmu",	.data = m2_pmu_avalanche_init, },
+	{ .compatible = "apple,blizzard-pmu",	.data = m2_pmu_blizzard_init, },
 	{ .compatible = "apple,icestorm-pmu",	.data = m1_pmu_ice_init, },
 	{ .compatible = "apple,firestorm-pmu",	.data = m1_pmu_fire_init, },
 	{ },
@@ -581,4 +595,3 @@ static struct platform_driver m1_pmu_driver = {
 };
 
 module_platform_driver(m1_pmu_driver);
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c
index c9689861be3f..47d359f72957 100644
--- a/drivers/perf/arm-cmn.c
+++ b/drivers/perf/arm-cmn.c
@@ -57,14 +57,12 @@
 #define CMN_INFO_REQ_VC_NUM		GENMASK_ULL(1, 0)
 
 /* XPs also have some local topology info which has uses too */
-#define CMN_MXP__CONNECT_INFO_P0	0x0008
-#define CMN_MXP__CONNECT_INFO_P1	0x0010
-#define CMN_MXP__CONNECT_INFO_P2	0x0028
-#define CMN_MXP__CONNECT_INFO_P3	0x0030
-#define CMN_MXP__CONNECT_INFO_P4	0x0038
-#define CMN_MXP__CONNECT_INFO_P5	0x0040
+#define CMN_MXP__CONNECT_INFO(p)	(0x0008 + 8 * (p))
 #define CMN__CONNECT_INFO_DEVICE_TYPE	GENMASK_ULL(4, 0)
 
+#define CMN_MAX_PORTS			6
+#define CI700_CONNECT_INFO_P2_5_OFFSET	0x10
+
 /* PMU registers occupy the 3rd 4KB page of each node's region */
 #define CMN_PMU_OFFSET			0x2000
 
@@ -166,7 +164,7 @@
 #define CMN_EVENT_BYNODEID(event)	FIELD_GET(CMN_CONFIG_BYNODEID, (event)->attr.config)
 #define CMN_EVENT_NODEID(event)		FIELD_GET(CMN_CONFIG_NODEID, (event)->attr.config)
 
-#define CMN_CONFIG_WP_COMBINE		GENMASK_ULL(27, 24)
+#define CMN_CONFIG_WP_COMBINE		GENMASK_ULL(30, 27)
 #define CMN_CONFIG_WP_DEV_SEL		GENMASK_ULL(50, 48)
 #define CMN_CONFIG_WP_CHN_SEL		GENMASK_ULL(55, 51)
 /* Note that we don't yet support the tertiary match group on newer IPs */
@@ -396,6 +394,25 @@ static struct arm_cmn_node *arm_cmn_node(const struct arm_cmn *cmn,
 	return NULL;
 }
 
+static u32 arm_cmn_device_connect_info(const struct arm_cmn *cmn,
+				       const struct arm_cmn_node *xp, int port)
+{
+	int offset = CMN_MXP__CONNECT_INFO(port);
+
+	if (port >= 2) {
+		if (cmn->model & (CMN600 | CMN650))
+			return 0;
+		/*
+		 * CI-700 may have extra ports, but still has the
+		 * mesh_port_connect_info registers in the way.
+		 */
+		if (cmn->model == CI700)
+			offset += CI700_CONNECT_INFO_P2_5_OFFSET;
+	}
+
+	return readl_relaxed(xp->pmu_base - CMN_PMU_OFFSET + offset);
+}
+
 static struct dentry *arm_cmn_debugfs;
 
 #ifdef CONFIG_DEBUG_FS
@@ -469,7 +486,7 @@ static int arm_cmn_map_show(struct seq_file *s, void *data)
 	y = cmn->mesh_y;
 	while (y--) {
 		int xp_base = cmn->mesh_x * y;
-		u8 port[6][CMN_MAX_DIMENSION];
+		u8 port[CMN_MAX_PORTS][CMN_MAX_DIMENSION];
 
 		for (x = 0; x < cmn->mesh_x; x++)
 			seq_puts(s, "--------+");
@@ -477,14 +494,9 @@ static int arm_cmn_map_show(struct seq_file *s, void *data)
 		seq_printf(s, "\n%d    |", y);
 		for (x = 0; x < cmn->mesh_x; x++) {
 			struct arm_cmn_node *xp = cmn->xps + xp_base + x;
-			void __iomem *base = xp->pmu_base - CMN_PMU_OFFSET;
-
-			port[0][x] = readl_relaxed(base + CMN_MXP__CONNECT_INFO_P0);
-			port[1][x] = readl_relaxed(base + CMN_MXP__CONNECT_INFO_P1);
-			port[2][x] = readl_relaxed(base + CMN_MXP__CONNECT_INFO_P2);
-			port[3][x] = readl_relaxed(base + CMN_MXP__CONNECT_INFO_P3);
-			port[4][x] = readl_relaxed(base + CMN_MXP__CONNECT_INFO_P4);
-			port[5][x] = readl_relaxed(base + CMN_MXP__CONNECT_INFO_P5);
+
+			for (p = 0; p < CMN_MAX_PORTS; p++)
+				port[p][x] = arm_cmn_device_connect_info(cmn, xp, p);
 			seq_printf(s, " XP #%-2d |", xp_base + x);
 		}
 
@@ -1546,7 +1558,7 @@ static int arm_cmn_event_init(struct perf_event *event)
 	type = CMN_EVENT_TYPE(event);
 	/* DTC events (i.e. cycles) already have everything they need */
 	if (type == CMN_TYPE_DTC)
-		return 0;
+		return arm_cmn_validate_group(cmn, event);
 
 	eventid = CMN_EVENT_EVENTID(event);
 	/* For watchpoints we need the actual XP node here */
@@ -2083,18 +2095,9 @@ static int arm_cmn_discover(struct arm_cmn *cmn, unsigned int rgn_offset)
 		 * from this, since in that case we will see at least one XP
 		 * with port 2 connected, for the HN-D.
 		 */
-		if (readq_relaxed(xp_region + CMN_MXP__CONNECT_INFO_P0))
-			xp_ports |= BIT(0);
-		if (readq_relaxed(xp_region + CMN_MXP__CONNECT_INFO_P1))
-			xp_ports |= BIT(1);
-		if (readq_relaxed(xp_region + CMN_MXP__CONNECT_INFO_P2))
-			xp_ports |= BIT(2);
-		if (readq_relaxed(xp_region + CMN_MXP__CONNECT_INFO_P3))
-			xp_ports |= BIT(3);
-		if (readq_relaxed(xp_region + CMN_MXP__CONNECT_INFO_P4))
-			xp_ports |= BIT(4);
-		if (readq_relaxed(xp_region + CMN_MXP__CONNECT_INFO_P5))
-			xp_ports |= BIT(5);
+		for (int p = 0; p < CMN_MAX_PORTS; p++)
+			if (arm_cmn_device_connect_info(cmn, xp, p))
+				xp_ports |= BIT(p);
 
 		if (cmn->multi_dtm && (xp_ports & 0xc))
 			arm_cmn_init_dtm(dtm++, xp, 1);
diff --git a/drivers/perf/arm_cspmu/arm_cspmu.c b/drivers/perf/arm_cspmu/arm_cspmu.c
index e31302ab7e37..a3f1c410b417 100644
--- a/drivers/perf/arm_cspmu/arm_cspmu.c
+++ b/drivers/perf/arm_cspmu/arm_cspmu.c
@@ -1078,12 +1078,14 @@ static int arm_cspmu_request_irq(struct arm_cspmu *cspmu)
 static inline int arm_cspmu_find_cpu_container(int cpu, u32 container_uid)
 {
 	u32 acpi_uid;
-	struct device *cpu_dev = get_cpu_device(cpu);
-	struct acpi_device *acpi_dev = ACPI_COMPANION(cpu_dev);
+	struct device *cpu_dev;
+	struct acpi_device *acpi_dev;
 
+	cpu_dev = get_cpu_device(cpu);
 	if (!cpu_dev)
 		return -ENODEV;
 
+	acpi_dev = ACPI_COMPANION(cpu_dev);
 	while (acpi_dev) {
 		if (!strcmp(acpi_device_hid(acpi_dev),
 			    ACPI_PROCESSOR_CONTAINER_HID) &&
diff --git a/drivers/perf/arm_dmc620_pmu.c b/drivers/perf/arm_dmc620_pmu.c
index 54aa4658fb36..5de06f9a4dd3 100644
--- a/drivers/perf/arm_dmc620_pmu.c
+++ b/drivers/perf/arm_dmc620_pmu.c
@@ -655,8 +655,7 @@ static int dmc620_pmu_device_probe(struct platform_device *pdev)
 		.attr_groups	= dmc620_pmu_attr_groups,
 	};
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	dmc620_pmu->base = devm_ioremap_resource(&pdev->dev, res);
+	dmc620_pmu->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
 	if (IS_ERR(dmc620_pmu->base))
 		return PTR_ERR(dmc620_pmu->base);
 
diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
new file mode 100644
index 000000000000..c98e4039386d
--- /dev/null
+++ b/drivers/perf/arm_pmuv3.c
@@ -0,0 +1,1419 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * ARMv8 PMUv3 Performance Events handling code.
+ *
+ * Copyright (C) 2012 ARM Limited
+ * Author: Will Deacon <will.deacon@arm.com>
+ *
+ * This code is based heavily on the ARMv7 perf event code.
+ */
+
+#include <asm/irq_regs.h>
+#include <asm/perf_event.h>
+#include <asm/virt.h>
+
+#include <clocksource/arm_arch_timer.h>
+
+#include <linux/acpi.h>
+#include <linux/clocksource.h>
+#include <linux/of.h>
+#include <linux/perf/arm_pmu.h>
+#include <linux/perf/arm_pmuv3.h>
+#include <linux/platform_device.h>
+#include <linux/sched_clock.h>
+#include <linux/smp.h>
+
+#include <asm/arm_pmuv3.h>
+
+/* ARMv8 Cortex-A53 specific event types. */
+#define ARMV8_A53_PERFCTR_PREF_LINEFILL				0xC2
+
+/* ARMv8 Cavium ThunderX specific event types. */
+#define ARMV8_THUNDER_PERFCTR_L1D_CACHE_MISS_ST			0xE9
+#define ARMV8_THUNDER_PERFCTR_L1D_CACHE_PREF_ACCESS		0xEA
+#define ARMV8_THUNDER_PERFCTR_L1D_CACHE_PREF_MISS		0xEB
+#define ARMV8_THUNDER_PERFCTR_L1I_CACHE_PREF_ACCESS		0xEC
+#define ARMV8_THUNDER_PERFCTR_L1I_CACHE_PREF_MISS		0xED
+
+/*
+ * ARMv8 Architectural defined events, not all of these may
+ * be supported on any given implementation. Unsupported events will
+ * be disabled at run-time based on the PMCEID registers.
+ */
+static const unsigned armv8_pmuv3_perf_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
+	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV8_PMUV3_PERFCTR_CPU_CYCLES,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV8_PMUV3_PERFCTR_INST_RETIRED,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV8_PMUV3_PERFCTR_L1D_CACHE,
+	[PERF_COUNT_HW_CACHE_MISSES]		= ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL,
+	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
+	[PERF_COUNT_HW_BUS_CYCLES]		= ARMV8_PMUV3_PERFCTR_BUS_CYCLES,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= ARMV8_PMUV3_PERFCTR_STALL_FRONTEND,
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= ARMV8_PMUV3_PERFCTR_STALL_BACKEND,
+};
+
+static const unsigned armv8_pmuv3_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+						[PERF_COUNT_HW_CACHE_OP_MAX]
+						[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1D_CACHE,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL,
+
+	[C(L1I)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1I_CACHE,
+	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL,
+
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL,
+	[C(DTLB)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1D_TLB,
+
+	[C(ITLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL,
+	[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1I_TLB,
+
+	[C(LL)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD,
+	[C(LL)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_LL_CACHE_RD,
+
+	[C(BPU)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_BR_PRED,
+	[C(BPU)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
+};
+
+static const unsigned armv8_a53_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+					      [PERF_COUNT_HW_CACHE_OP_MAX]
+					      [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	[C(L1D)][C(OP_PREFETCH)][C(RESULT_MISS)] = ARMV8_A53_PERFCTR_PREF_LINEFILL,
+
+	[C(NODE)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD,
+	[C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR,
+};
+
+static const unsigned armv8_a57_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+					      [PERF_COUNT_HW_CACHE_OP_MAX]
+					      [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_RD,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_WR,
+
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_RD,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_WR,
+
+	[C(NODE)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD,
+	[C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR,
+};
+
+static const unsigned armv8_a73_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+					      [PERF_COUNT_HW_CACHE_OP_MAX]
+					      [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR,
+};
+
+static const unsigned armv8_thunder_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+						   [PERF_COUNT_HW_CACHE_OP_MAX]
+						   [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_RD,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_THUNDER_PERFCTR_L1D_CACHE_MISS_ST,
+	[C(L1D)][C(OP_PREFETCH)][C(RESULT_ACCESS)] = ARMV8_THUNDER_PERFCTR_L1D_CACHE_PREF_ACCESS,
+	[C(L1D)][C(OP_PREFETCH)][C(RESULT_MISS)] = ARMV8_THUNDER_PERFCTR_L1D_CACHE_PREF_MISS,
+
+	[C(L1I)][C(OP_PREFETCH)][C(RESULT_ACCESS)] = ARMV8_THUNDER_PERFCTR_L1I_CACHE_PREF_ACCESS,
+	[C(L1I)][C(OP_PREFETCH)][C(RESULT_MISS)] = ARMV8_THUNDER_PERFCTR_L1I_CACHE_PREF_MISS,
+
+	[C(DTLB)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_L1D_TLB_RD,
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_RD,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_WR,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_WR,
+};
+
+static const unsigned armv8_vulcan_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+					      [PERF_COUNT_HW_CACHE_OP_MAX]
+					      [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_RD,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_WR,
+
+	[C(DTLB)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_L1D_TLB_RD,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_WR,
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_RD,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_WR,
+
+	[C(NODE)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD,
+	[C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR,
+};
+
+static ssize_t
+armv8pmu_events_sysfs_show(struct device *dev,
+			   struct device_attribute *attr, char *page)
+{
+	struct perf_pmu_events_attr *pmu_attr;
+
+	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
+
+	return sprintf(page, "event=0x%04llx\n", pmu_attr->id);
+}
+
+#define ARMV8_EVENT_ATTR(name, config)						\
+	PMU_EVENT_ATTR_ID(name, armv8pmu_events_sysfs_show, config)
+
+static struct attribute *armv8_pmuv3_event_attrs[] = {
+	ARMV8_EVENT_ATTR(sw_incr, ARMV8_PMUV3_PERFCTR_SW_INCR),
+	ARMV8_EVENT_ATTR(l1i_cache_refill, ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL),
+	ARMV8_EVENT_ATTR(l1i_tlb_refill, ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL),
+	ARMV8_EVENT_ATTR(l1d_cache_refill, ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL),
+	ARMV8_EVENT_ATTR(l1d_cache, ARMV8_PMUV3_PERFCTR_L1D_CACHE),
+	ARMV8_EVENT_ATTR(l1d_tlb_refill, ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL),
+	ARMV8_EVENT_ATTR(ld_retired, ARMV8_PMUV3_PERFCTR_LD_RETIRED),
+	ARMV8_EVENT_ATTR(st_retired, ARMV8_PMUV3_PERFCTR_ST_RETIRED),
+	ARMV8_EVENT_ATTR(inst_retired, ARMV8_PMUV3_PERFCTR_INST_RETIRED),
+	ARMV8_EVENT_ATTR(exc_taken, ARMV8_PMUV3_PERFCTR_EXC_TAKEN),
+	ARMV8_EVENT_ATTR(exc_return, ARMV8_PMUV3_PERFCTR_EXC_RETURN),
+	ARMV8_EVENT_ATTR(cid_write_retired, ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED),
+	ARMV8_EVENT_ATTR(pc_write_retired, ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED),
+	ARMV8_EVENT_ATTR(br_immed_retired, ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED),
+	ARMV8_EVENT_ATTR(br_return_retired, ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED),
+	ARMV8_EVENT_ATTR(unaligned_ldst_retired, ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED),
+	ARMV8_EVENT_ATTR(br_mis_pred, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED),
+	ARMV8_EVENT_ATTR(cpu_cycles, ARMV8_PMUV3_PERFCTR_CPU_CYCLES),
+	ARMV8_EVENT_ATTR(br_pred, ARMV8_PMUV3_PERFCTR_BR_PRED),
+	ARMV8_EVENT_ATTR(mem_access, ARMV8_PMUV3_PERFCTR_MEM_ACCESS),
+	ARMV8_EVENT_ATTR(l1i_cache, ARMV8_PMUV3_PERFCTR_L1I_CACHE),
+	ARMV8_EVENT_ATTR(l1d_cache_wb, ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB),
+	ARMV8_EVENT_ATTR(l2d_cache, ARMV8_PMUV3_PERFCTR_L2D_CACHE),
+	ARMV8_EVENT_ATTR(l2d_cache_refill, ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL),
+	ARMV8_EVENT_ATTR(l2d_cache_wb, ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB),
+	ARMV8_EVENT_ATTR(bus_access, ARMV8_PMUV3_PERFCTR_BUS_ACCESS),
+	ARMV8_EVENT_ATTR(memory_error, ARMV8_PMUV3_PERFCTR_MEMORY_ERROR),
+	ARMV8_EVENT_ATTR(inst_spec, ARMV8_PMUV3_PERFCTR_INST_SPEC),
+	ARMV8_EVENT_ATTR(ttbr_write_retired, ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED),
+	ARMV8_EVENT_ATTR(bus_cycles, ARMV8_PMUV3_PERFCTR_BUS_CYCLES),
+	/* Don't expose the chain event in /sys, since it's useless in isolation */
+	ARMV8_EVENT_ATTR(l1d_cache_allocate, ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE),
+	ARMV8_EVENT_ATTR(l2d_cache_allocate, ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE),
+	ARMV8_EVENT_ATTR(br_retired, ARMV8_PMUV3_PERFCTR_BR_RETIRED),
+	ARMV8_EVENT_ATTR(br_mis_pred_retired, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED),
+	ARMV8_EVENT_ATTR(stall_frontend, ARMV8_PMUV3_PERFCTR_STALL_FRONTEND),
+	ARMV8_EVENT_ATTR(stall_backend, ARMV8_PMUV3_PERFCTR_STALL_BACKEND),
+	ARMV8_EVENT_ATTR(l1d_tlb, ARMV8_PMUV3_PERFCTR_L1D_TLB),
+	ARMV8_EVENT_ATTR(l1i_tlb, ARMV8_PMUV3_PERFCTR_L1I_TLB),
+	ARMV8_EVENT_ATTR(l2i_cache, ARMV8_PMUV3_PERFCTR_L2I_CACHE),
+	ARMV8_EVENT_ATTR(l2i_cache_refill, ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL),
+	ARMV8_EVENT_ATTR(l3d_cache_allocate, ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE),
+	ARMV8_EVENT_ATTR(l3d_cache_refill, ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL),
+	ARMV8_EVENT_ATTR(l3d_cache, ARMV8_PMUV3_PERFCTR_L3D_CACHE),
+	ARMV8_EVENT_ATTR(l3d_cache_wb, ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB),
+	ARMV8_EVENT_ATTR(l2d_tlb_refill, ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL),
+	ARMV8_EVENT_ATTR(l2i_tlb_refill, ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL),
+	ARMV8_EVENT_ATTR(l2d_tlb, ARMV8_PMUV3_PERFCTR_L2D_TLB),
+	ARMV8_EVENT_ATTR(l2i_tlb, ARMV8_PMUV3_PERFCTR_L2I_TLB),
+	ARMV8_EVENT_ATTR(remote_access, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS),
+	ARMV8_EVENT_ATTR(ll_cache, ARMV8_PMUV3_PERFCTR_LL_CACHE),
+	ARMV8_EVENT_ATTR(ll_cache_miss, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS),
+	ARMV8_EVENT_ATTR(dtlb_walk, ARMV8_PMUV3_PERFCTR_DTLB_WALK),
+	ARMV8_EVENT_ATTR(itlb_walk, ARMV8_PMUV3_PERFCTR_ITLB_WALK),
+	ARMV8_EVENT_ATTR(ll_cache_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_RD),
+	ARMV8_EVENT_ATTR(ll_cache_miss_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD),
+	ARMV8_EVENT_ATTR(remote_access_rd, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD),
+	ARMV8_EVENT_ATTR(l1d_cache_lmiss_rd, ARMV8_PMUV3_PERFCTR_L1D_CACHE_LMISS_RD),
+	ARMV8_EVENT_ATTR(op_retired, ARMV8_PMUV3_PERFCTR_OP_RETIRED),
+	ARMV8_EVENT_ATTR(op_spec, ARMV8_PMUV3_PERFCTR_OP_SPEC),
+	ARMV8_EVENT_ATTR(stall, ARMV8_PMUV3_PERFCTR_STALL),
+	ARMV8_EVENT_ATTR(stall_slot_backend, ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND),
+	ARMV8_EVENT_ATTR(stall_slot_frontend, ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND),
+	ARMV8_EVENT_ATTR(stall_slot, ARMV8_PMUV3_PERFCTR_STALL_SLOT),
+	ARMV8_EVENT_ATTR(sample_pop, ARMV8_SPE_PERFCTR_SAMPLE_POP),
+	ARMV8_EVENT_ATTR(sample_feed, ARMV8_SPE_PERFCTR_SAMPLE_FEED),
+	ARMV8_EVENT_ATTR(sample_filtrate, ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE),
+	ARMV8_EVENT_ATTR(sample_collision, ARMV8_SPE_PERFCTR_SAMPLE_COLLISION),
+	ARMV8_EVENT_ATTR(cnt_cycles, ARMV8_AMU_PERFCTR_CNT_CYCLES),
+	ARMV8_EVENT_ATTR(stall_backend_mem, ARMV8_AMU_PERFCTR_STALL_BACKEND_MEM),
+	ARMV8_EVENT_ATTR(l1i_cache_lmiss, ARMV8_PMUV3_PERFCTR_L1I_CACHE_LMISS),
+	ARMV8_EVENT_ATTR(l2d_cache_lmiss_rd, ARMV8_PMUV3_PERFCTR_L2D_CACHE_LMISS_RD),
+	ARMV8_EVENT_ATTR(l2i_cache_lmiss, ARMV8_PMUV3_PERFCTR_L2I_CACHE_LMISS),
+	ARMV8_EVENT_ATTR(l3d_cache_lmiss_rd, ARMV8_PMUV3_PERFCTR_L3D_CACHE_LMISS_RD),
+	ARMV8_EVENT_ATTR(trb_wrap, ARMV8_PMUV3_PERFCTR_TRB_WRAP),
+	ARMV8_EVENT_ATTR(trb_trig, ARMV8_PMUV3_PERFCTR_TRB_TRIG),
+	ARMV8_EVENT_ATTR(trcextout0, ARMV8_PMUV3_PERFCTR_TRCEXTOUT0),
+	ARMV8_EVENT_ATTR(trcextout1, ARMV8_PMUV3_PERFCTR_TRCEXTOUT1),
+	ARMV8_EVENT_ATTR(trcextout2, ARMV8_PMUV3_PERFCTR_TRCEXTOUT2),
+	ARMV8_EVENT_ATTR(trcextout3, ARMV8_PMUV3_PERFCTR_TRCEXTOUT3),
+	ARMV8_EVENT_ATTR(cti_trigout4, ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT4),
+	ARMV8_EVENT_ATTR(cti_trigout5, ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT5),
+	ARMV8_EVENT_ATTR(cti_trigout6, ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT6),
+	ARMV8_EVENT_ATTR(cti_trigout7, ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT7),
+	ARMV8_EVENT_ATTR(ldst_align_lat, ARMV8_PMUV3_PERFCTR_LDST_ALIGN_LAT),
+	ARMV8_EVENT_ATTR(ld_align_lat, ARMV8_PMUV3_PERFCTR_LD_ALIGN_LAT),
+	ARMV8_EVENT_ATTR(st_align_lat, ARMV8_PMUV3_PERFCTR_ST_ALIGN_LAT),
+	ARMV8_EVENT_ATTR(mem_access_checked, ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED),
+	ARMV8_EVENT_ATTR(mem_access_checked_rd, ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_RD),
+	ARMV8_EVENT_ATTR(mem_access_checked_wr, ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_WR),
+	NULL,
+};
+
+static umode_t
+armv8pmu_event_attr_is_visible(struct kobject *kobj,
+			       struct attribute *attr, int unused)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct pmu *pmu = dev_get_drvdata(dev);
+	struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu);
+	struct perf_pmu_events_attr *pmu_attr;
+
+	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr.attr);
+
+	if (pmu_attr->id < ARMV8_PMUV3_MAX_COMMON_EVENTS &&
+	    test_bit(pmu_attr->id, cpu_pmu->pmceid_bitmap))
+		return attr->mode;
+
+	if (pmu_attr->id >= ARMV8_PMUV3_EXT_COMMON_EVENT_BASE) {
+		u64 id = pmu_attr->id - ARMV8_PMUV3_EXT_COMMON_EVENT_BASE;
+
+		if (id < ARMV8_PMUV3_MAX_COMMON_EVENTS &&
+		    test_bit(id, cpu_pmu->pmceid_ext_bitmap))
+			return attr->mode;
+	}
+
+	return 0;
+}
+
+static const struct attribute_group armv8_pmuv3_events_attr_group = {
+	.name = "events",
+	.attrs = armv8_pmuv3_event_attrs,
+	.is_visible = armv8pmu_event_attr_is_visible,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-15");
+PMU_FORMAT_ATTR(long, "config1:0");
+PMU_FORMAT_ATTR(rdpmc, "config1:1");
+
+static int sysctl_perf_user_access __read_mostly;
+
+static inline bool armv8pmu_event_is_64bit(struct perf_event *event)
+{
+	return event->attr.config1 & 0x1;
+}
+
+static inline bool armv8pmu_event_want_user_access(struct perf_event *event)
+{
+	return event->attr.config1 & 0x2;
+}
+
+static struct attribute *armv8_pmuv3_format_attrs[] = {
+	&format_attr_event.attr,
+	&format_attr_long.attr,
+	&format_attr_rdpmc.attr,
+	NULL,
+};
+
+static const struct attribute_group armv8_pmuv3_format_attr_group = {
+	.name = "format",
+	.attrs = armv8_pmuv3_format_attrs,
+};
+
+static ssize_t slots_show(struct device *dev, struct device_attribute *attr,
+			  char *page)
+{
+	struct pmu *pmu = dev_get_drvdata(dev);
+	struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu);
+	u32 slots = cpu_pmu->reg_pmmir & ARMV8_PMU_SLOTS_MASK;
+
+	return sysfs_emit(page, "0x%08x\n", slots);
+}
+
+static DEVICE_ATTR_RO(slots);
+
+static ssize_t bus_slots_show(struct device *dev, struct device_attribute *attr,
+			      char *page)
+{
+	struct pmu *pmu = dev_get_drvdata(dev);
+	struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu);
+	u32 bus_slots = (cpu_pmu->reg_pmmir >> ARMV8_PMU_BUS_SLOTS_SHIFT)
+			& ARMV8_PMU_BUS_SLOTS_MASK;
+
+	return sysfs_emit(page, "0x%08x\n", bus_slots);
+}
+
+static DEVICE_ATTR_RO(bus_slots);
+
+static ssize_t bus_width_show(struct device *dev, struct device_attribute *attr,
+			      char *page)
+{
+	struct pmu *pmu = dev_get_drvdata(dev);
+	struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu);
+	u32 bus_width = (cpu_pmu->reg_pmmir >> ARMV8_PMU_BUS_WIDTH_SHIFT)
+			& ARMV8_PMU_BUS_WIDTH_MASK;
+	u32 val = 0;
+
+	/* Encoded as Log2(number of bytes), plus one */
+	if (bus_width > 2 && bus_width < 13)
+		val = 1 << (bus_width - 1);
+
+	return sysfs_emit(page, "0x%08x\n", val);
+}
+
+static DEVICE_ATTR_RO(bus_width);
+
+static struct attribute *armv8_pmuv3_caps_attrs[] = {
+	&dev_attr_slots.attr,
+	&dev_attr_bus_slots.attr,
+	&dev_attr_bus_width.attr,
+	NULL,
+};
+
+static const struct attribute_group armv8_pmuv3_caps_attr_group = {
+	.name = "caps",
+	.attrs = armv8_pmuv3_caps_attrs,
+};
+
+/*
+ * Perf Events' indices
+ */
+#define	ARMV8_IDX_CYCLE_COUNTER	0
+#define	ARMV8_IDX_COUNTER0	1
+#define	ARMV8_IDX_CYCLE_COUNTER_USER	32
+
+/*
+ * We unconditionally enable ARMv8.5-PMU long event counter support
+ * (64-bit events) where supported. Indicate if this arm_pmu has long
+ * event counter support.
+ *
+ * On AArch32, long counters make no sense (you can't access the top
+ * bits), so we only enable this on AArch64.
+ */
+static bool armv8pmu_has_long_event(struct arm_pmu *cpu_pmu)
+{
+	return (IS_ENABLED(CONFIG_ARM64) && is_pmuv3p5(cpu_pmu->pmuver));
+}
+
+static inline bool armv8pmu_event_has_user_read(struct perf_event *event)
+{
+	return event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT;
+}
+
+/*
+ * We must chain two programmable counters for 64 bit events,
+ * except when we have allocated the 64bit cycle counter (for CPU
+ * cycles event) or when user space counter access is enabled.
+ */
+static inline bool armv8pmu_event_is_chained(struct perf_event *event)
+{
+	int idx = event->hw.idx;
+	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+
+	return !armv8pmu_event_has_user_read(event) &&
+	       armv8pmu_event_is_64bit(event) &&
+	       !armv8pmu_has_long_event(cpu_pmu) &&
+	       (idx != ARMV8_IDX_CYCLE_COUNTER);
+}
+
+/*
+ * ARMv8 low level PMU access
+ */
+
+/*
+ * Perf Event to low level counters mapping
+ */
+#define	ARMV8_IDX_TO_COUNTER(x)	\
+	(((x) - ARMV8_IDX_COUNTER0) & ARMV8_PMU_COUNTER_MASK)
+
+static inline u32 armv8pmu_pmcr_read(void)
+{
+	return read_pmcr();
+}
+
+static inline void armv8pmu_pmcr_write(u32 val)
+{
+	val &= ARMV8_PMU_PMCR_MASK;
+	isb();
+	write_pmcr(val);
+}
+
+static inline int armv8pmu_has_overflowed(u32 pmovsr)
+{
+	return pmovsr & ARMV8_PMU_OVERFLOWED_MASK;
+}
+
+static inline int armv8pmu_counter_has_overflowed(u32 pmnc, int idx)
+{
+	return pmnc & BIT(ARMV8_IDX_TO_COUNTER(idx));
+}
+
+static inline u64 armv8pmu_read_evcntr(int idx)
+{
+	u32 counter = ARMV8_IDX_TO_COUNTER(idx);
+
+	return read_pmevcntrn(counter);
+}
+
+static inline u64 armv8pmu_read_hw_counter(struct perf_event *event)
+{
+	int idx = event->hw.idx;
+	u64 val = armv8pmu_read_evcntr(idx);
+
+	if (armv8pmu_event_is_chained(event))
+		val = (val << 32) | armv8pmu_read_evcntr(idx - 1);
+	return val;
+}
+
+/*
+ * The cycle counter is always a 64-bit counter. When ARMV8_PMU_PMCR_LP
+ * is set the event counters also become 64-bit counters. Unless the
+ * user has requested a long counter (attr.config1) then we want to
+ * interrupt upon 32-bit overflow - we achieve this by applying a bias.
+ */
+static bool armv8pmu_event_needs_bias(struct perf_event *event)
+{
+	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	if (armv8pmu_event_is_64bit(event))
+		return false;
+
+	if (armv8pmu_has_long_event(cpu_pmu) ||
+	    idx == ARMV8_IDX_CYCLE_COUNTER)
+		return true;
+
+	return false;
+}
+
+static u64 armv8pmu_bias_long_counter(struct perf_event *event, u64 value)
+{
+	if (armv8pmu_event_needs_bias(event))
+		value |= GENMASK_ULL(63, 32);
+
+	return value;
+}
+
+static u64 armv8pmu_unbias_long_counter(struct perf_event *event, u64 value)
+{
+	if (armv8pmu_event_needs_bias(event))
+		value &= ~GENMASK_ULL(63, 32);
+
+	return value;
+}
+
+static u64 armv8pmu_read_counter(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+	u64 value;
+
+	if (idx == ARMV8_IDX_CYCLE_COUNTER)
+		value = read_pmccntr();
+	else
+		value = armv8pmu_read_hw_counter(event);
+
+	return  armv8pmu_unbias_long_counter(event, value);
+}
+
+static inline void armv8pmu_write_evcntr(int idx, u64 value)
+{
+	u32 counter = ARMV8_IDX_TO_COUNTER(idx);
+
+	write_pmevcntrn(counter, value);
+}
+
+static inline void armv8pmu_write_hw_counter(struct perf_event *event,
+					     u64 value)
+{
+	int idx = event->hw.idx;
+
+	if (armv8pmu_event_is_chained(event)) {
+		armv8pmu_write_evcntr(idx, upper_32_bits(value));
+		armv8pmu_write_evcntr(idx - 1, lower_32_bits(value));
+	} else {
+		armv8pmu_write_evcntr(idx, value);
+	}
+}
+
+static void armv8pmu_write_counter(struct perf_event *event, u64 value)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	value = armv8pmu_bias_long_counter(event, value);
+
+	if (idx == ARMV8_IDX_CYCLE_COUNTER)
+		write_pmccntr(value);
+	else
+		armv8pmu_write_hw_counter(event, value);
+}
+
+static inline void armv8pmu_write_evtype(int idx, u32 val)
+{
+	u32 counter = ARMV8_IDX_TO_COUNTER(idx);
+
+	val &= ARMV8_PMU_EVTYPE_MASK;
+	write_pmevtypern(counter, val);
+}
+
+static inline void armv8pmu_write_event_type(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	/*
+	 * For chained events, the low counter is programmed to count
+	 * the event of interest and the high counter is programmed
+	 * with CHAIN event code with filters set to count at all ELs.
+	 */
+	if (armv8pmu_event_is_chained(event)) {
+		u32 chain_evt = ARMV8_PMUV3_PERFCTR_CHAIN |
+				ARMV8_PMU_INCLUDE_EL2;
+
+		armv8pmu_write_evtype(idx - 1, hwc->config_base);
+		armv8pmu_write_evtype(idx, chain_evt);
+	} else {
+		if (idx == ARMV8_IDX_CYCLE_COUNTER)
+			write_pmccfiltr(hwc->config_base);
+		else
+			armv8pmu_write_evtype(idx, hwc->config_base);
+	}
+}
+
+static u32 armv8pmu_event_cnten_mask(struct perf_event *event)
+{
+	int counter = ARMV8_IDX_TO_COUNTER(event->hw.idx);
+	u32 mask = BIT(counter);
+
+	if (armv8pmu_event_is_chained(event))
+		mask |= BIT(counter - 1);
+	return mask;
+}
+
+static inline void armv8pmu_enable_counter(u32 mask)
+{
+	/*
+	 * Make sure event configuration register writes are visible before we
+	 * enable the counter.
+	 * */
+	isb();
+	write_pmcntenset(mask);
+}
+
+static inline void armv8pmu_enable_event_counter(struct perf_event *event)
+{
+	struct perf_event_attr *attr = &event->attr;
+	u32 mask = armv8pmu_event_cnten_mask(event);
+
+	kvm_set_pmu_events(mask, attr);
+
+	/* We rely on the hypervisor switch code to enable guest counters */
+	if (!kvm_pmu_counter_deferred(attr))
+		armv8pmu_enable_counter(mask);
+}
+
+static inline void armv8pmu_disable_counter(u32 mask)
+{
+	write_pmcntenclr(mask);
+	/*
+	 * Make sure the effects of disabling the counter are visible before we
+	 * start configuring the event.
+	 */
+	isb();
+}
+
+static inline void armv8pmu_disable_event_counter(struct perf_event *event)
+{
+	struct perf_event_attr *attr = &event->attr;
+	u32 mask = armv8pmu_event_cnten_mask(event);
+
+	kvm_clr_pmu_events(mask);
+
+	/* We rely on the hypervisor switch code to disable guest counters */
+	if (!kvm_pmu_counter_deferred(attr))
+		armv8pmu_disable_counter(mask);
+}
+
+static inline void armv8pmu_enable_intens(u32 mask)
+{
+	write_pmintenset(mask);
+}
+
+static inline void armv8pmu_enable_event_irq(struct perf_event *event)
+{
+	u32 counter = ARMV8_IDX_TO_COUNTER(event->hw.idx);
+	armv8pmu_enable_intens(BIT(counter));
+}
+
+static inline void armv8pmu_disable_intens(u32 mask)
+{
+	write_pmintenclr(mask);
+	isb();
+	/* Clear the overflow flag in case an interrupt is pending. */
+	write_pmovsclr(mask);
+	isb();
+}
+
+static inline void armv8pmu_disable_event_irq(struct perf_event *event)
+{
+	u32 counter = ARMV8_IDX_TO_COUNTER(event->hw.idx);
+	armv8pmu_disable_intens(BIT(counter));
+}
+
+static inline u32 armv8pmu_getreset_flags(void)
+{
+	u32 value;
+
+	/* Read */
+	value = read_pmovsclr();
+
+	/* Write to clear flags */
+	value &= ARMV8_PMU_OVSR_MASK;
+	write_pmovsclr(value);
+
+	return value;
+}
+
+static void armv8pmu_disable_user_access(void)
+{
+	write_pmuserenr(0);
+}
+
+static void armv8pmu_enable_user_access(struct arm_pmu *cpu_pmu)
+{
+	int i;
+	struct pmu_hw_events *cpuc = this_cpu_ptr(cpu_pmu->hw_events);
+
+	/* Clear any unused counters to avoid leaking their contents */
+	for_each_clear_bit(i, cpuc->used_mask, cpu_pmu->num_events) {
+		if (i == ARMV8_IDX_CYCLE_COUNTER)
+			write_pmccntr(0);
+		else
+			armv8pmu_write_evcntr(i, 0);
+	}
+
+	write_pmuserenr(0);
+	write_pmuserenr(ARMV8_PMU_USERENR_ER | ARMV8_PMU_USERENR_CR);
+}
+
+static void armv8pmu_enable_event(struct perf_event *event)
+{
+	/*
+	 * Enable counter and interrupt, and set the counter to count
+	 * the event that we're interested in.
+	 */
+
+	/*
+	 * Disable counter
+	 */
+	armv8pmu_disable_event_counter(event);
+
+	/*
+	 * Set event.
+	 */
+	armv8pmu_write_event_type(event);
+
+	/*
+	 * Enable interrupt for this counter
+	 */
+	armv8pmu_enable_event_irq(event);
+
+	/*
+	 * Enable counter
+	 */
+	armv8pmu_enable_event_counter(event);
+}
+
+static void armv8pmu_disable_event(struct perf_event *event)
+{
+	/*
+	 * Disable counter
+	 */
+	armv8pmu_disable_event_counter(event);
+
+	/*
+	 * Disable interrupt for this counter
+	 */
+	armv8pmu_disable_event_irq(event);
+}
+
+static void armv8pmu_start(struct arm_pmu *cpu_pmu)
+{
+	struct perf_event_context *ctx;
+	int nr_user = 0;
+
+	ctx = perf_cpu_task_ctx();
+	if (ctx)
+		nr_user = ctx->nr_user;
+
+	if (sysctl_perf_user_access && nr_user)
+		armv8pmu_enable_user_access(cpu_pmu);
+	else
+		armv8pmu_disable_user_access();
+
+	/* Enable all counters */
+	armv8pmu_pmcr_write(armv8pmu_pmcr_read() | ARMV8_PMU_PMCR_E);
+}
+
+static void armv8pmu_stop(struct arm_pmu *cpu_pmu)
+{
+	/* Disable all counters */
+	armv8pmu_pmcr_write(armv8pmu_pmcr_read() & ~ARMV8_PMU_PMCR_E);
+}
+
+static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu)
+{
+	u32 pmovsr;
+	struct perf_sample_data data;
+	struct pmu_hw_events *cpuc = this_cpu_ptr(cpu_pmu->hw_events);
+	struct pt_regs *regs;
+	int idx;
+
+	/*
+	 * Get and reset the IRQ flags
+	 */
+	pmovsr = armv8pmu_getreset_flags();
+
+	/*
+	 * Did an overflow occur?
+	 */
+	if (!armv8pmu_has_overflowed(pmovsr))
+		return IRQ_NONE;
+
+	/*
+	 * Handle the counter(s) overflow(s)
+	 */
+	regs = get_irq_regs();
+
+	/*
+	 * Stop the PMU while processing the counter overflows
+	 * to prevent skews in group events.
+	 */
+	armv8pmu_stop(cpu_pmu);
+	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
+		struct perf_event *event = cpuc->events[idx];
+		struct hw_perf_event *hwc;
+
+		/* Ignore if we don't have an event. */
+		if (!event)
+			continue;
+
+		/*
+		 * We have a single interrupt for all counters. Check that
+		 * each counter has overflowed before we process it.
+		 */
+		if (!armv8pmu_counter_has_overflowed(pmovsr, idx))
+			continue;
+
+		hwc = &event->hw;
+		armpmu_event_update(event);
+		perf_sample_data_init(&data, 0, hwc->last_period);
+		if (!armpmu_event_set_period(event))
+			continue;
+
+		/*
+		 * Perf event overflow will queue the processing of the event as
+		 * an irq_work which will be taken care of in the handling of
+		 * IPI_IRQ_WORK.
+		 */
+		if (perf_event_overflow(event, &data, regs))
+			cpu_pmu->disable(event);
+	}
+	armv8pmu_start(cpu_pmu);
+
+	return IRQ_HANDLED;
+}
+
+static int armv8pmu_get_single_idx(struct pmu_hw_events *cpuc,
+				    struct arm_pmu *cpu_pmu)
+{
+	int idx;
+
+	for (idx = ARMV8_IDX_COUNTER0; idx < cpu_pmu->num_events; idx++) {
+		if (!test_and_set_bit(idx, cpuc->used_mask))
+			return idx;
+	}
+	return -EAGAIN;
+}
+
+static int armv8pmu_get_chain_idx(struct pmu_hw_events *cpuc,
+				   struct arm_pmu *cpu_pmu)
+{
+	int idx;
+
+	/*
+	 * Chaining requires two consecutive event counters, where
+	 * the lower idx must be even.
+	 */
+	for (idx = ARMV8_IDX_COUNTER0 + 1; idx < cpu_pmu->num_events; idx += 2) {
+		if (!test_and_set_bit(idx, cpuc->used_mask)) {
+			/* Check if the preceding even counter is available */
+			if (!test_and_set_bit(idx - 1, cpuc->used_mask))
+				return idx;
+			/* Release the Odd counter */
+			clear_bit(idx, cpuc->used_mask);
+		}
+	}
+	return -EAGAIN;
+}
+
+static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
+				  struct perf_event *event)
+{
+	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	unsigned long evtype = hwc->config_base & ARMV8_PMU_EVTYPE_EVENT;
+
+	/* Always prefer to place a cycle counter into the cycle counter. */
+	if (evtype == ARMV8_PMUV3_PERFCTR_CPU_CYCLES) {
+		if (!test_and_set_bit(ARMV8_IDX_CYCLE_COUNTER, cpuc->used_mask))
+			return ARMV8_IDX_CYCLE_COUNTER;
+		else if (armv8pmu_event_is_64bit(event) &&
+			   armv8pmu_event_want_user_access(event) &&
+			   !armv8pmu_has_long_event(cpu_pmu))
+				return -EAGAIN;
+	}
+
+	/*
+	 * Otherwise use events counters
+	 */
+	if (armv8pmu_event_is_chained(event))
+		return	armv8pmu_get_chain_idx(cpuc, cpu_pmu);
+	else
+		return armv8pmu_get_single_idx(cpuc, cpu_pmu);
+}
+
+static void armv8pmu_clear_event_idx(struct pmu_hw_events *cpuc,
+				     struct perf_event *event)
+{
+	int idx = event->hw.idx;
+
+	clear_bit(idx, cpuc->used_mask);
+	if (armv8pmu_event_is_chained(event))
+		clear_bit(idx - 1, cpuc->used_mask);
+}
+
+static int armv8pmu_user_event_idx(struct perf_event *event)
+{
+	if (!sysctl_perf_user_access || !armv8pmu_event_has_user_read(event))
+		return 0;
+
+	/*
+	 * We remap the cycle counter index to 32 to
+	 * match the offset applied to the rest of
+	 * the counter indices.
+	 */
+	if (event->hw.idx == ARMV8_IDX_CYCLE_COUNTER)
+		return ARMV8_IDX_CYCLE_COUNTER_USER;
+
+	return event->hw.idx;
+}
+
+/*
+ * Add an event filter to a given event.
+ */
+static int armv8pmu_set_event_filter(struct hw_perf_event *event,
+				     struct perf_event_attr *attr)
+{
+	unsigned long config_base = 0;
+
+	if (attr->exclude_idle)
+		return -EPERM;
+
+	/*
+	 * If we're running in hyp mode, then we *are* the hypervisor.
+	 * Therefore we ignore exclude_hv in this configuration, since
+	 * there's no hypervisor to sample anyway. This is consistent
+	 * with other architectures (x86 and Power).
+	 */
+	if (is_kernel_in_hyp_mode()) {
+		if (!attr->exclude_kernel && !attr->exclude_host)
+			config_base |= ARMV8_PMU_INCLUDE_EL2;
+		if (attr->exclude_guest)
+			config_base |= ARMV8_PMU_EXCLUDE_EL1;
+		if (attr->exclude_host)
+			config_base |= ARMV8_PMU_EXCLUDE_EL0;
+	} else {
+		if (!attr->exclude_hv && !attr->exclude_host)
+			config_base |= ARMV8_PMU_INCLUDE_EL2;
+	}
+
+	/*
+	 * Filter out !VHE kernels and guest kernels
+	 */
+	if (attr->exclude_kernel)
+		config_base |= ARMV8_PMU_EXCLUDE_EL1;
+
+	if (attr->exclude_user)
+		config_base |= ARMV8_PMU_EXCLUDE_EL0;
+
+	/*
+	 * Install the filter into config_base as this is used to
+	 * construct the event type.
+	 */
+	event->config_base = config_base;
+
+	return 0;
+}
+
+static void armv8pmu_reset(void *info)
+{
+	struct arm_pmu *cpu_pmu = (struct arm_pmu *)info;
+	u32 pmcr;
+
+	/* The counter and interrupt enable registers are unknown at reset. */
+	armv8pmu_disable_counter(U32_MAX);
+	armv8pmu_disable_intens(U32_MAX);
+
+	/* Clear the counters we flip at guest entry/exit */
+	kvm_clr_pmu_events(U32_MAX);
+
+	/*
+	 * Initialize & Reset PMNC. Request overflow interrupt for
+	 * 64 bit cycle counter but cheat in armv8pmu_write_counter().
+	 */
+	pmcr = ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_LC;
+
+	/* Enable long event counter support where available */
+	if (armv8pmu_has_long_event(cpu_pmu))
+		pmcr |= ARMV8_PMU_PMCR_LP;
+
+	armv8pmu_pmcr_write(pmcr);
+}
+
+static int __armv8_pmuv3_map_event_id(struct arm_pmu *armpmu,
+				      struct perf_event *event)
+{
+	if (event->attr.type == PERF_TYPE_HARDWARE &&
+	    event->attr.config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS) {
+
+		if (test_bit(ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED,
+			     armpmu->pmceid_bitmap))
+			return ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED;
+
+		if (test_bit(ARMV8_PMUV3_PERFCTR_BR_RETIRED,
+			     armpmu->pmceid_bitmap))
+			return ARMV8_PMUV3_PERFCTR_BR_RETIRED;
+
+		return HW_OP_UNSUPPORTED;
+	}
+
+	return armpmu_map_event(event, &armv8_pmuv3_perf_map,
+				&armv8_pmuv3_perf_cache_map,
+				ARMV8_PMU_EVTYPE_EVENT);
+}
+
+static int __armv8_pmuv3_map_event(struct perf_event *event,
+				   const unsigned (*extra_event_map)
+						  [PERF_COUNT_HW_MAX],
+				   const unsigned (*extra_cache_map)
+						  [PERF_COUNT_HW_CACHE_MAX]
+						  [PERF_COUNT_HW_CACHE_OP_MAX]
+						  [PERF_COUNT_HW_CACHE_RESULT_MAX])
+{
+	int hw_event_id;
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
+
+	hw_event_id = __armv8_pmuv3_map_event_id(armpmu, event);
+
+	/*
+	 * CHAIN events only work when paired with an adjacent counter, and it
+	 * never makes sense for a user to open one in isolation, as they'll be
+	 * rotated arbitrarily.
+	 */
+	if (hw_event_id == ARMV8_PMUV3_PERFCTR_CHAIN)
+		return -EINVAL;
+
+	if (armv8pmu_event_is_64bit(event))
+		event->hw.flags |= ARMPMU_EVT_64BIT;
+
+	/*
+	 * User events must be allocated into a single counter, and so
+	 * must not be chained.
+	 *
+	 * Most 64-bit events require long counter support, but 64-bit
+	 * CPU_CYCLES events can be placed into the dedicated cycle
+	 * counter when this is free.
+	 */
+	if (armv8pmu_event_want_user_access(event)) {
+		if (!(event->attach_state & PERF_ATTACH_TASK))
+			return -EINVAL;
+		if (armv8pmu_event_is_64bit(event) &&
+		    (hw_event_id != ARMV8_PMUV3_PERFCTR_CPU_CYCLES) &&
+		    !armv8pmu_has_long_event(armpmu))
+			return -EOPNOTSUPP;
+
+		event->hw.flags |= PERF_EVENT_FLAG_USER_READ_CNT;
+	}
+
+	/* Only expose micro/arch events supported by this PMU */
+	if ((hw_event_id > 0) && (hw_event_id < ARMV8_PMUV3_MAX_COMMON_EVENTS)
+	    && test_bit(hw_event_id, armpmu->pmceid_bitmap)) {
+		return hw_event_id;
+	}
+
+	return armpmu_map_event(event, extra_event_map, extra_cache_map,
+				ARMV8_PMU_EVTYPE_EVENT);
+}
+
+static int armv8_pmuv3_map_event(struct perf_event *event)
+{
+	return __armv8_pmuv3_map_event(event, NULL, NULL);
+}
+
+static int armv8_a53_map_event(struct perf_event *event)
+{
+	return __armv8_pmuv3_map_event(event, NULL, &armv8_a53_perf_cache_map);
+}
+
+static int armv8_a57_map_event(struct perf_event *event)
+{
+	return __armv8_pmuv3_map_event(event, NULL, &armv8_a57_perf_cache_map);
+}
+
+static int armv8_a73_map_event(struct perf_event *event)
+{
+	return __armv8_pmuv3_map_event(event, NULL, &armv8_a73_perf_cache_map);
+}
+
+static int armv8_thunder_map_event(struct perf_event *event)
+{
+	return __armv8_pmuv3_map_event(event, NULL,
+				       &armv8_thunder_perf_cache_map);
+}
+
+static int armv8_vulcan_map_event(struct perf_event *event)
+{
+	return __armv8_pmuv3_map_event(event, NULL,
+				       &armv8_vulcan_perf_cache_map);
+}
+
+struct armv8pmu_probe_info {
+	struct arm_pmu *pmu;
+	bool present;
+};
+
+static void __armv8pmu_probe_pmu(void *info)
+{
+	struct armv8pmu_probe_info *probe = info;
+	struct arm_pmu *cpu_pmu = probe->pmu;
+	u64 pmceid_raw[2];
+	u32 pmceid[2];
+	int pmuver;
+
+	pmuver = read_pmuver();
+	if (!pmuv3_implemented(pmuver))
+		return;
+
+	cpu_pmu->pmuver = pmuver;
+	probe->present = true;
+
+	/* Read the nb of CNTx counters supported from PMNC */
+	cpu_pmu->num_events = (armv8pmu_pmcr_read() >> ARMV8_PMU_PMCR_N_SHIFT)
+		& ARMV8_PMU_PMCR_N_MASK;
+
+	/* Add the CPU cycles counter */
+	cpu_pmu->num_events += 1;
+
+	pmceid[0] = pmceid_raw[0] = read_pmceid0();
+	pmceid[1] = pmceid_raw[1] = read_pmceid1();
+
+	bitmap_from_arr32(cpu_pmu->pmceid_bitmap,
+			     pmceid, ARMV8_PMUV3_MAX_COMMON_EVENTS);
+
+	pmceid[0] = pmceid_raw[0] >> 32;
+	pmceid[1] = pmceid_raw[1] >> 32;
+
+	bitmap_from_arr32(cpu_pmu->pmceid_ext_bitmap,
+			     pmceid, ARMV8_PMUV3_MAX_COMMON_EVENTS);
+
+	/* store PMMIR register for sysfs */
+	if (is_pmuv3p4(pmuver) && (pmceid_raw[1] & BIT(31)))
+		cpu_pmu->reg_pmmir = read_pmmir();
+	else
+		cpu_pmu->reg_pmmir = 0;
+}
+
+static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu)
+{
+	struct armv8pmu_probe_info probe = {
+		.pmu = cpu_pmu,
+		.present = false,
+	};
+	int ret;
+
+	ret = smp_call_function_any(&cpu_pmu->supported_cpus,
+				    __armv8pmu_probe_pmu,
+				    &probe, 1);
+	if (ret)
+		return ret;
+
+	return probe.present ? 0 : -ENODEV;
+}
+
+static void armv8pmu_disable_user_access_ipi(void *unused)
+{
+	armv8pmu_disable_user_access();
+}
+
+static int armv8pmu_proc_user_access_handler(struct ctl_table *table, int write,
+		void *buffer, size_t *lenp, loff_t *ppos)
+{
+	int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	if (ret || !write || sysctl_perf_user_access)
+		return ret;
+
+	on_each_cpu(armv8pmu_disable_user_access_ipi, NULL, 1);
+	return 0;
+}
+
+static struct ctl_table armv8_pmu_sysctl_table[] = {
+	{
+		.procname       = "perf_user_access",
+		.data		= &sysctl_perf_user_access,
+		.maxlen		= sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler	= armv8pmu_proc_user_access_handler,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+	{ }
+};
+
+static void armv8_pmu_register_sysctl_table(void)
+{
+	static u32 tbl_registered = 0;
+
+	if (!cmpxchg_relaxed(&tbl_registered, 0, 1))
+		register_sysctl("kernel", armv8_pmu_sysctl_table);
+}
+
+static int armv8_pmu_init(struct arm_pmu *cpu_pmu, char *name,
+			  int (*map_event)(struct perf_event *event),
+			  const struct attribute_group *events,
+			  const struct attribute_group *format,
+			  const struct attribute_group *caps)
+{
+	int ret = armv8pmu_probe_pmu(cpu_pmu);
+	if (ret)
+		return ret;
+
+	cpu_pmu->handle_irq		= armv8pmu_handle_irq;
+	cpu_pmu->enable			= armv8pmu_enable_event;
+	cpu_pmu->disable		= armv8pmu_disable_event;
+	cpu_pmu->read_counter		= armv8pmu_read_counter;
+	cpu_pmu->write_counter		= armv8pmu_write_counter;
+	cpu_pmu->get_event_idx		= armv8pmu_get_event_idx;
+	cpu_pmu->clear_event_idx	= armv8pmu_clear_event_idx;
+	cpu_pmu->start			= armv8pmu_start;
+	cpu_pmu->stop			= armv8pmu_stop;
+	cpu_pmu->reset			= armv8pmu_reset;
+	cpu_pmu->set_event_filter	= armv8pmu_set_event_filter;
+
+	cpu_pmu->pmu.event_idx		= armv8pmu_user_event_idx;
+
+	cpu_pmu->name			= name;
+	cpu_pmu->map_event		= map_event;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = events ?
+			events : &armv8_pmuv3_events_attr_group;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = format ?
+			format : &armv8_pmuv3_format_attr_group;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_CAPS] = caps ?
+			caps : &armv8_pmuv3_caps_attr_group;
+
+	armv8_pmu_register_sysctl_table();
+	return 0;
+}
+
+static int armv8_pmu_init_nogroups(struct arm_pmu *cpu_pmu, char *name,
+				   int (*map_event)(struct perf_event *event))
+{
+	return armv8_pmu_init(cpu_pmu, name, map_event, NULL, NULL, NULL);
+}
+
+#define PMUV3_INIT_SIMPLE(name)						\
+static int name##_pmu_init(struct arm_pmu *cpu_pmu)			\
+{									\
+	return armv8_pmu_init_nogroups(cpu_pmu, #name, armv8_pmuv3_map_event);\
+}
+
+PMUV3_INIT_SIMPLE(armv8_pmuv3)
+
+PMUV3_INIT_SIMPLE(armv8_cortex_a34)
+PMUV3_INIT_SIMPLE(armv8_cortex_a55)
+PMUV3_INIT_SIMPLE(armv8_cortex_a65)
+PMUV3_INIT_SIMPLE(armv8_cortex_a75)
+PMUV3_INIT_SIMPLE(armv8_cortex_a76)
+PMUV3_INIT_SIMPLE(armv8_cortex_a77)
+PMUV3_INIT_SIMPLE(armv8_cortex_a78)
+PMUV3_INIT_SIMPLE(armv9_cortex_a510)
+PMUV3_INIT_SIMPLE(armv9_cortex_a710)
+PMUV3_INIT_SIMPLE(armv8_cortex_x1)
+PMUV3_INIT_SIMPLE(armv9_cortex_x2)
+PMUV3_INIT_SIMPLE(armv8_neoverse_e1)
+PMUV3_INIT_SIMPLE(armv8_neoverse_n1)
+PMUV3_INIT_SIMPLE(armv9_neoverse_n2)
+PMUV3_INIT_SIMPLE(armv8_neoverse_v1)
+
+PMUV3_INIT_SIMPLE(armv8_nvidia_carmel)
+PMUV3_INIT_SIMPLE(armv8_nvidia_denver)
+
+static int armv8_a35_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a35",
+				       armv8_a53_map_event);
+}
+
+static int armv8_a53_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a53",
+				       armv8_a53_map_event);
+}
+
+static int armv8_a57_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a57",
+				       armv8_a57_map_event);
+}
+
+static int armv8_a72_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a72",
+				       armv8_a57_map_event);
+}
+
+static int armv8_a73_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a73",
+				       armv8_a73_map_event);
+}
+
+static int armv8_thunder_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cavium_thunder",
+				       armv8_thunder_map_event);
+}
+
+static int armv8_vulcan_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_brcm_vulcan",
+				       armv8_vulcan_map_event);
+}
+
+static const struct of_device_id armv8_pmu_of_device_ids[] = {
+	{.compatible = "arm,armv8-pmuv3",	.data = armv8_pmuv3_pmu_init},
+	{.compatible = "arm,cortex-a34-pmu",	.data = armv8_cortex_a34_pmu_init},
+	{.compatible = "arm,cortex-a35-pmu",	.data = armv8_a35_pmu_init},
+	{.compatible = "arm,cortex-a53-pmu",	.data = armv8_a53_pmu_init},
+	{.compatible = "arm,cortex-a55-pmu",	.data = armv8_cortex_a55_pmu_init},
+	{.compatible = "arm,cortex-a57-pmu",	.data = armv8_a57_pmu_init},
+	{.compatible = "arm,cortex-a65-pmu",	.data = armv8_cortex_a65_pmu_init},
+	{.compatible = "arm,cortex-a72-pmu",	.data = armv8_a72_pmu_init},
+	{.compatible = "arm,cortex-a73-pmu",	.data = armv8_a73_pmu_init},
+	{.compatible = "arm,cortex-a75-pmu",	.data = armv8_cortex_a75_pmu_init},
+	{.compatible = "arm,cortex-a76-pmu",	.data = armv8_cortex_a76_pmu_init},
+	{.compatible = "arm,cortex-a77-pmu",	.data = armv8_cortex_a77_pmu_init},
+	{.compatible = "arm,cortex-a78-pmu",	.data = armv8_cortex_a78_pmu_init},
+	{.compatible = "arm,cortex-a510-pmu",	.data = armv9_cortex_a510_pmu_init},
+	{.compatible = "arm,cortex-a710-pmu",	.data = armv9_cortex_a710_pmu_init},
+	{.compatible = "arm,cortex-x1-pmu",	.data = armv8_cortex_x1_pmu_init},
+	{.compatible = "arm,cortex-x2-pmu",	.data = armv9_cortex_x2_pmu_init},
+	{.compatible = "arm,neoverse-e1-pmu",	.data = armv8_neoverse_e1_pmu_init},
+	{.compatible = "arm,neoverse-n1-pmu",	.data = armv8_neoverse_n1_pmu_init},
+	{.compatible = "arm,neoverse-n2-pmu",	.data = armv9_neoverse_n2_pmu_init},
+	{.compatible = "arm,neoverse-v1-pmu",	.data = armv8_neoverse_v1_pmu_init},
+	{.compatible = "cavium,thunder-pmu",	.data = armv8_thunder_pmu_init},
+	{.compatible = "brcm,vulcan-pmu",	.data = armv8_vulcan_pmu_init},
+	{.compatible = "nvidia,carmel-pmu",	.data = armv8_nvidia_carmel_pmu_init},
+	{.compatible = "nvidia,denver-pmu",	.data = armv8_nvidia_denver_pmu_init},
+	{},
+};
+
+static int armv8_pmu_device_probe(struct platform_device *pdev)
+{
+	return arm_pmu_device_probe(pdev, armv8_pmu_of_device_ids, NULL);
+}
+
+static struct platform_driver armv8_pmu_driver = {
+	.driver		= {
+		.name	= ARMV8_PMU_PDEV_NAME,
+		.of_match_table = armv8_pmu_of_device_ids,
+		.suppress_bind_attrs = true,
+	},
+	.probe		= armv8_pmu_device_probe,
+};
+
+static int __init armv8_pmu_driver_init(void)
+{
+	if (acpi_disabled)
+		return platform_driver_register(&armv8_pmu_driver);
+	else
+		return arm_pmu_acpi_probe(armv8_pmuv3_pmu_init);
+}
+device_initcall(armv8_pmu_driver_init)
+
+void arch_perf_update_userpage(struct perf_event *event,
+			       struct perf_event_mmap_page *userpg, u64 now)
+{
+	struct clock_read_data *rd;
+	unsigned int seq;
+	u64 ns;
+
+	userpg->cap_user_time = 0;
+	userpg->cap_user_time_zero = 0;
+	userpg->cap_user_time_short = 0;
+	userpg->cap_user_rdpmc = armv8pmu_event_has_user_read(event);
+
+	if (userpg->cap_user_rdpmc) {
+		if (event->hw.flags & ARMPMU_EVT_64BIT)
+			userpg->pmc_width = 64;
+		else
+			userpg->pmc_width = 32;
+	}
+
+	do {
+		rd = sched_clock_read_begin(&seq);
+
+		if (rd->read_sched_clock != arch_timer_read_counter)
+			return;
+
+		userpg->time_mult = rd->mult;
+		userpg->time_shift = rd->shift;
+		userpg->time_zero = rd->epoch_ns;
+		userpg->time_cycles = rd->epoch_cyc;
+		userpg->time_mask = rd->sched_clock_mask;
+
+		/*
+		 * Subtract the cycle base, such that software that
+		 * doesn't know about cap_user_time_short still 'works'
+		 * assuming no wraps.
+		 */
+		ns = mul_u64_u32_shr(rd->epoch_cyc, rd->mult, rd->shift);
+		userpg->time_zero -= ns;
+
+	} while (sched_clock_read_retry(seq));
+
+	userpg->time_offset = userpg->time_zero - now;
+
+	/*
+	 * time_shift is not expected to be greater than 31 due to
+	 * the original published conversion algorithm shifting a
+	 * 32-bit value (now specifies a 64-bit value) - refer
+	 * perf_event_mmap_page documentation in perf_event.h.
+	 */
+	if (userpg->time_shift == 32) {
+		userpg->time_shift = 31;
+		userpg->time_mult >>= 1;
+	}
+
+	/*
+	 * Internal timekeeping for enabled/running/stopped times
+	 * is always computed with the sched_clock.
+	 */
+	userpg->cap_user_time = 1;
+	userpg->cap_user_time_zero = 1;
+	userpg->cap_user_time_short = 1;
+}
diff --git a/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c b/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c
index 4c67d57217a7..40f1bc9f9b91 100644
--- a/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c
@@ -316,7 +316,7 @@ static int hisi_cpa_pmu_probe(struct platform_device *pdev)
 	if (!name)
 		return -ENOMEM;
 
-	hisi_pmu_init(cpa_pmu, name, THIS_MODULE);
+	hisi_pmu_init(cpa_pmu, THIS_MODULE);
 
 	/* Power Management should be disabled before using CPA PMU. */
 	hisi_cpa_pmu_disable_pm(cpa_pmu);
diff --git a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
index 8c3ffcbfd4c0..ffb039d05d07 100644
--- a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
@@ -499,13 +499,6 @@ static int hisi_ddrc_pmu_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	ret = cpuhp_state_add_instance(CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE,
-				       &ddrc_pmu->node);
-	if (ret) {
-		dev_err(&pdev->dev, "Error %d registering hotplug;\n", ret);
-		return ret;
-	}
-
 	if (ddrc_pmu->identifier >= HISI_PMU_V2)
 		name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
 				      "hisi_sccl%u_ddrc%u_%u",
@@ -516,7 +509,17 @@ static int hisi_ddrc_pmu_probe(struct platform_device *pdev)
 				      "hisi_sccl%u_ddrc%u", ddrc_pmu->sccl_id,
 				      ddrc_pmu->index_id);
 
-	hisi_pmu_init(ddrc_pmu, name, THIS_MODULE);
+	if (!name)
+		return -ENOMEM;
+
+	ret = cpuhp_state_add_instance(CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE,
+				       &ddrc_pmu->node);
+	if (ret) {
+		dev_err(&pdev->dev, "Error %d registering hotplug;\n", ret);
+		return ret;
+	}
+
+	hisi_pmu_init(ddrc_pmu, THIS_MODULE);
 
 	ret = perf_pmu_register(&ddrc_pmu->pmu, name, -1);
 	if (ret) {
diff --git a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
index 806698b9eabf..15caf99e1eef 100644
--- a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
@@ -510,6 +510,11 @@ static int hisi_hha_pmu_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_hha%u",
+			      hha_pmu->sccl_id, hha_pmu->index_id);
+	if (!name)
+		return -ENOMEM;
+
 	ret = cpuhp_state_add_instance(CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE,
 				       &hha_pmu->node);
 	if (ret) {
@@ -517,9 +522,7 @@ static int hisi_hha_pmu_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_hha%u",
-			      hha_pmu->sccl_id, hha_pmu->index_id);
-	hisi_pmu_init(hha_pmu, name, THIS_MODULE);
+	hisi_pmu_init(hha_pmu, THIS_MODULE);
 
 	ret = perf_pmu_register(&hha_pmu->pmu, name, -1);
 	if (ret) {
diff --git a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
index 5b2c35f1658a..794dbcd19b7a 100644
--- a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
@@ -544,6 +544,11 @@ static int hisi_l3c_pmu_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_l3c%u",
+			      l3c_pmu->sccl_id, l3c_pmu->ccl_id);
+	if (!name)
+		return -ENOMEM;
+
 	ret = cpuhp_state_add_instance(CPUHP_AP_PERF_ARM_HISI_L3_ONLINE,
 				       &l3c_pmu->node);
 	if (ret) {
@@ -551,13 +556,7 @@ static int hisi_l3c_pmu_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	/*
-	 * CCL_ID is used to identify the L3C in the same SCCL which was
-	 * used _UID by mistake.
-	 */
-	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_l3c%u",
-			      l3c_pmu->sccl_id, l3c_pmu->ccl_id);
-	hisi_pmu_init(l3c_pmu, name, THIS_MODULE);
+	hisi_pmu_init(l3c_pmu, THIS_MODULE);
 
 	ret = perf_pmu_register(&l3c_pmu->pmu, name, -1);
 	if (ret) {
diff --git a/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c
index afe3419f3f6d..71b6687d6696 100644
--- a/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c
@@ -412,7 +412,7 @@ static int hisi_pa_pmu_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	hisi_pmu_init(pa_pmu, name, THIS_MODULE);
+	hisi_pmu_init(pa_pmu, THIS_MODULE);
 	ret = perf_pmu_register(&pa_pmu->pmu, name, -1);
 	if (ret) {
 		dev_err(pa_pmu->dev, "PMU register failed, ret = %d\n", ret);
diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pmu.c
index f1b0f5e1a28f..2823f381930d 100644
--- a/drivers/perf/hisilicon/hisi_uncore_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_pmu.c
@@ -531,12 +531,10 @@ int hisi_uncore_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 }
 EXPORT_SYMBOL_GPL(hisi_uncore_pmu_offline_cpu);
 
-void hisi_pmu_init(struct hisi_pmu *hisi_pmu, const char *name,
-		   struct module *module)
+void hisi_pmu_init(struct hisi_pmu *hisi_pmu, struct module *module)
 {
 	struct pmu *pmu = &hisi_pmu->pmu;
 
-	pmu->name               = name;
 	pmu->module             = module;
 	pmu->task_ctx_nr        = perf_invalid_context;
 	pmu->event_init         = hisi_uncore_pmu_event_init;
diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.h b/drivers/perf/hisilicon/hisi_uncore_pmu.h
index f8e3cc6903d7..07890a8e96ca 100644
--- a/drivers/perf/hisilicon/hisi_uncore_pmu.h
+++ b/drivers/perf/hisilicon/hisi_uncore_pmu.h
@@ -121,6 +121,5 @@ ssize_t hisi_uncore_pmu_identifier_attr_show(struct device *dev,
 int hisi_uncore_pmu_init_irq(struct hisi_pmu *hisi_pmu,
 			     struct platform_device *pdev);
 
-void hisi_pmu_init(struct hisi_pmu *hisi_pmu, const char *name,
-		   struct module *module);
+void hisi_pmu_init(struct hisi_pmu *hisi_pmu, struct module *module);
 #endif /* __HISI_UNCORE_PMU_H__ */
diff --git a/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c
index 1e354433776a..6fe534a665ed 100644
--- a/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c
@@ -445,7 +445,7 @@ static int hisi_sllc_pmu_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	hisi_pmu_init(sllc_pmu, name, THIS_MODULE);
+	hisi_pmu_init(sllc_pmu, THIS_MODULE);
 
 	ret = perf_pmu_register(&sllc_pmu->pmu, name, -1);
 	if (ret) {
diff --git a/drivers/perf/qcom_l3_pmu.c b/drivers/perf/qcom_l3_pmu.c
index 346311a05460..2887edb4eb0b 100644
--- a/drivers/perf/qcom_l3_pmu.c
+++ b/drivers/perf/qcom_l3_pmu.c
@@ -763,8 +763,7 @@ static int qcom_l3_cache_pmu_probe(struct platform_device *pdev)
 		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 	};
 
-	memrc = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	l3pmu->regs = devm_ioremap_resource(&pdev->dev, memrc);
+	l3pmu->regs = devm_platform_get_and_ioremap_resource(pdev, 0, &memrc);
 	if (IS_ERR(l3pmu->regs))
 		return PTR_ERR(l3pmu->regs);