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

Pull arm64 updates from Catalin Marinas:
 "The major features are support for LPA2 (52-bit VA/PA with 4K and 16K
  pages), the dpISA extension and Rust enabled on arm64. The changes are
  mostly contained within the usual arch/arm64/, drivers/perf, the arm64
  Documentation and kselftests. The exception is the Rust support which
  touches some generic build files.

  Summary:

   - Reorganise the arm64 kernel VA space and add support for LPA2 (at
     stage 1, KVM stage 2 was merged earlier) - 52-bit VA/PA address
     range with 4KB and 16KB pages

   - Enable Rust on arm64

   - Support for the 2023 dpISA extensions (data processing ISA), host
     only

   - arm64 perf updates:

      - StarFive's StarLink (integrates one or more CPU cores with a
        shared L3 memory system) PMU support

      - Enable HiSilicon Erratum 162700402 quirk for HIP09

      - Several updates for the HiSilicon PCIe PMU driver

      - Arm CoreSight PMU support

      - Convert all drivers under drivers/perf/ to use .remove_new()

   - Miscellaneous:

      - Don't enable workarounds for "rare" errata by default

      - Clean up the DAIF flags handling for EL0 returns (in preparation
        for NMI support)

      - Kselftest update for ptrace()

      - Update some of the sysreg field definitions

      - Slight improvement in the code generation for inline asm I/O
        accessors to permit offset addressing

      - kretprobes: acquire regs via a BRK exception (previously done
        via a trampoline handler)

      - SVE/SME cleanups, comment updates

      - Allow CALL_OPS+CC_OPTIMIZE_FOR_SIZE with clang (previously
        disabled due to gcc silently ignoring -falign-functions=N)"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (134 commits)
  Revert "mm: add arch hook to validate mmap() prot flags"
  Revert "arm64: mm: add support for WXN memory translation attribute"
  Revert "ARM64: Dynamically allocate cpumasks and increase supported CPUs to 512"
  ARM64: Dynamically allocate cpumasks and increase supported CPUs to 512
  kselftest/arm64: Add 2023 DPISA hwcap test coverage
  kselftest/arm64: Add basic FPMR test
  kselftest/arm64: Handle FPMR context in generic signal frame parser
  arm64/hwcap: Define hwcaps for 2023 DPISA features
  arm64/ptrace: Expose FPMR via ptrace
  arm64/signal: Add FPMR signal handling
  arm64/fpsimd: Support FEAT_FPMR
  arm64/fpsimd: Enable host kernel access to FPMR
  arm64/cpufeature: Hook new identification registers up to cpufeature
  docs: perf: Fix build warning of hisi-pcie-pmu.rst
  perf: starfive: Only allow COMPILE_TEST for 64-bit architectures
  MAINTAINERS: Add entry for StarFive StarLink PMU
  docs: perf: Add description for StarFive's StarLink PMU
  dt-bindings: perf: starfive: Add JH8100 StarLink PMU
  perf: starfive: Add StarLink PMU support
  docs: perf: Update usage for target filter of hisi-pcie-pmu
  ...

30 files changed, 885 insertions, 208 deletions

diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig
index ec6e0d9194a1..004d86230aa6 100644
--- a/drivers/perf/Kconfig
+++ b/drivers/perf/Kconfig
@@ -86,6 +86,15 @@ config RISCV_PMU_SBI
 	  full perf feature support i.e. counter overflow, privilege mode
 	  filtering, counter configuration.
 
+config STARFIVE_STARLINK_PMU
+	depends on ARCH_STARFIVE || (COMPILE_TEST && 64BIT)
+	bool "StarFive StarLink PMU"
+	help
+	   Provide support for StarLink Performance Monitor Unit.
+	   StarLink Performance Monitor Unit integrates one or more cores with
+	   an L3 memory system. The L3 cache events are added into perf event
+	   subsystem, allowing monitoring of various L3 cache perf events.
+
 config ARM_PMU_ACPI
 	depends on ARM_PMU && ACPI
 	def_bool y
diff --git a/drivers/perf/Makefile b/drivers/perf/Makefile
index a06338e3401c..29b1c28203ef 100644
--- a/drivers/perf/Makefile
+++ b/drivers/perf/Makefile
@@ -15,6 +15,7 @@ obj-$(CONFIG_QCOM_L3_PMU) += qcom_l3_pmu.o
 obj-$(CONFIG_RISCV_PMU) += riscv_pmu.o
 obj-$(CONFIG_RISCV_PMU_LEGACY) += riscv_pmu_legacy.o
 obj-$(CONFIG_RISCV_PMU_SBI) += riscv_pmu_sbi.o
+obj-$(CONFIG_STARFIVE_STARLINK_PMU) += starfive_starlink_pmu.o
 obj-$(CONFIG_THUNDERX2_PMU) += thunderx2_pmu.o
 obj-$(CONFIG_XGENE_PMU) += xgene_pmu.o
 obj-$(CONFIG_ARM_SPE_PMU) += arm_spe_pmu.o
diff --git a/drivers/perf/alibaba_uncore_drw_pmu.c b/drivers/perf/alibaba_uncore_drw_pmu.c
index 19d459a36be5..a9277dcf90ce 100644
--- a/drivers/perf/alibaba_uncore_drw_pmu.c
+++ b/drivers/perf/alibaba_uncore_drw_pmu.c
@@ -729,7 +729,7 @@ static int ali_drw_pmu_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int ali_drw_pmu_remove(struct platform_device *pdev)
+static void ali_drw_pmu_remove(struct platform_device *pdev)
 {
 	struct ali_drw_pmu *drw_pmu = platform_get_drvdata(pdev);
 
@@ -739,8 +739,6 @@ static int ali_drw_pmu_remove(struct platform_device *pdev)
 
 	ali_drw_pmu_uninit_irq(drw_pmu);
 	perf_pmu_unregister(&drw_pmu->pmu);
-
-	return 0;
 }
 
 static int ali_drw_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
@@ -795,7 +793,7 @@ static struct platform_driver ali_drw_pmu_driver = {
 		   .acpi_match_table = ali_drw_acpi_match,
 		   },
 	.probe = ali_drw_pmu_probe,
-	.remove = ali_drw_pmu_remove,
+	.remove_new = ali_drw_pmu_remove,
 };
 
 static int __init ali_drw_pmu_init(void)
diff --git a/drivers/perf/amlogic/meson_g12_ddr_pmu.c b/drivers/perf/amlogic/meson_g12_ddr_pmu.c
index 15d52ab3276a..99cc791892bc 100644
--- a/drivers/perf/amlogic/meson_g12_ddr_pmu.c
+++ b/drivers/perf/amlogic/meson_g12_ddr_pmu.c
@@ -355,11 +355,9 @@ static int g12_ddr_pmu_probe(struct platform_device *pdev)
 	return meson_ddr_pmu_create(pdev);
 }
 
-static int g12_ddr_pmu_remove(struct platform_device *pdev)
+static void g12_ddr_pmu_remove(struct platform_device *pdev)
 {
 	meson_ddr_pmu_remove(pdev);
-
-	return 0;
 }
 
 static const struct of_device_id meson_ddr_pmu_dt_match[] = {
@@ -381,7 +379,7 @@ MODULE_DEVICE_TABLE(of, meson_ddr_pmu_dt_match);
 
 static struct platform_driver g12_ddr_pmu_driver = {
 	.probe = g12_ddr_pmu_probe,
-	.remove = g12_ddr_pmu_remove,
+	.remove_new = g12_ddr_pmu_remove,
 
 	.driver = {
 		.name = "meson-g12-ddr-pmu",
diff --git a/drivers/perf/arm-cci.c b/drivers/perf/arm-cci.c
index 61de861eaf91..6be03f81ae5d 100644
--- a/drivers/perf/arm-cci.c
+++ b/drivers/perf/arm-cci.c
@@ -1697,16 +1697,14 @@ error_pmu_init:
 	return ret;
 }
 
-static int cci_pmu_remove(struct platform_device *pdev)
+static void cci_pmu_remove(struct platform_device *pdev)
 {
 	if (!g_cci_pmu)
-		return 0;
+		return;
 
 	cpuhp_remove_state(CPUHP_AP_PERF_ARM_CCI_ONLINE);
 	perf_pmu_unregister(&g_cci_pmu->pmu);
 	g_cci_pmu = NULL;
-
-	return 0;
 }
 
 static struct platform_driver cci_pmu_driver = {
@@ -1716,7 +1714,7 @@ static struct platform_driver cci_pmu_driver = {
 		   .suppress_bind_attrs = true,
 		  },
 	.probe = cci_pmu_probe,
-	.remove = cci_pmu_remove,
+	.remove_new = cci_pmu_remove,
 };
 
 module_platform_driver(cci_pmu_driver);
diff --git a/drivers/perf/arm-ccn.c b/drivers/perf/arm-ccn.c
index 728d13d8e98a..641471bd5eff 100644
--- a/drivers/perf/arm-ccn.c
+++ b/drivers/perf/arm-ccn.c
@@ -1515,13 +1515,11 @@ static int arm_ccn_probe(struct platform_device *pdev)
 	return arm_ccn_pmu_init(ccn);
 }
 
-static int arm_ccn_remove(struct platform_device *pdev)
+static void arm_ccn_remove(struct platform_device *pdev)
 {
 	struct arm_ccn *ccn = platform_get_drvdata(pdev);
 
 	arm_ccn_pmu_cleanup(ccn);
-
-	return 0;
 }
 
 static const struct of_device_id arm_ccn_match[] = {
@@ -1539,7 +1537,7 @@ static struct platform_driver arm_ccn_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe = arm_ccn_probe,
-	.remove = arm_ccn_remove,
+	.remove_new = arm_ccn_remove,
 };
 
 static int __init arm_ccn_init(void)
diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c
index 7e3aa7e2345f..7ef9c7e4836b 100644
--- a/drivers/perf/arm-cmn.c
+++ b/drivers/perf/arm-cmn.c
@@ -493,6 +493,7 @@ static void arm_cmn_show_logid(struct seq_file *s, int x, int y, int p, int d)
 
 	for (dn = cmn->dns; dn->type; dn++) {
 		struct arm_cmn_nodeid nid = arm_cmn_nid(cmn, dn->id);
+		int pad = dn->logid < 10;
 
 		if (dn->type == CMN_TYPE_XP)
 			continue;
@@ -503,7 +504,7 @@ static void arm_cmn_show_logid(struct seq_file *s, int x, int y, int p, int d)
 		if (nid.x != x || nid.y != y || nid.port != p || nid.dev != d)
 			continue;
 
-		seq_printf(s, "   #%-2d  |", dn->logid);
+		seq_printf(s, " %*c#%-*d  |", pad + 1, ' ', 3 - pad, dn->logid);
 		return;
 	}
 	seq_puts(s, "        |");
@@ -516,7 +517,7 @@ static int arm_cmn_map_show(struct seq_file *s, void *data)
 
 	seq_puts(s, "     X");
 	for (x = 0; x < cmn->mesh_x; x++)
-		seq_printf(s, "    %d    ", x);
+		seq_printf(s, "    %-2d   ", x);
 	seq_puts(s, "\nY P D+");
 	y = cmn->mesh_y;
 	while (y--) {
@@ -526,13 +527,13 @@ static int arm_cmn_map_show(struct seq_file *s, void *data)
 		for (x = 0; x < cmn->mesh_x; x++)
 			seq_puts(s, "--------+");
 
-		seq_printf(s, "\n%d    |", y);
+		seq_printf(s, "\n%-2d   |", y);
 		for (x = 0; x < cmn->mesh_x; x++) {
 			struct arm_cmn_node *xp = cmn->xps + xp_base + x;
 
 			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);
+			seq_printf(s, " XP #%-3d|", xp_base + x);
 		}
 
 		seq_puts(s, "\n     |");
@@ -2515,7 +2516,7 @@ static int arm_cmn_probe(struct platform_device *pdev)
 	return err;
 }
 
-static int arm_cmn_remove(struct platform_device *pdev)
+static void arm_cmn_remove(struct platform_device *pdev)
 {
 	struct arm_cmn *cmn = platform_get_drvdata(pdev);
 
@@ -2524,7 +2525,6 @@ static int arm_cmn_remove(struct platform_device *pdev)
 	perf_pmu_unregister(&cmn->pmu);
 	cpuhp_state_remove_instance_nocalls(arm_cmn_hp_state, &cmn->cpuhp_node);
 	debugfs_remove(cmn->debug);
-	return 0;
 }
 
 #ifdef CONFIG_OF
@@ -2555,7 +2555,7 @@ static struct platform_driver arm_cmn_driver = {
 		.acpi_match_table = ACPI_PTR(arm_cmn_acpi_match),
 	},
 	.probe = arm_cmn_probe,
-	.remove = arm_cmn_remove,
+	.remove_new = arm_cmn_remove,
 };
 
 static int __init arm_cmn_init(void)
diff --git a/drivers/perf/arm_cspmu/arm_cspmu.c b/drivers/perf/arm_cspmu/arm_cspmu.c
index 50b89b989ce7..b9a252272f1e 100644
--- a/drivers/perf/arm_cspmu/arm_cspmu.c
+++ b/drivers/perf/arm_cspmu/arm_cspmu.c
@@ -27,6 +27,7 @@
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/of.h>
 #include <linux/perf_event.h>
 #include <linux/platform_device.h>
 
@@ -100,13 +101,6 @@
 #define ARM_CSPMU_ACTIVE_CPU_MASK		0x0
 #define ARM_CSPMU_ASSOCIATED_CPU_MASK		0x1
 
-/* Check and use default if implementer doesn't provide attribute callback */
-#define CHECK_DEFAULT_IMPL_OPS(ops, callback)			\
-	do {							\
-		if (!ops->callback)				\
-			ops->callback = arm_cspmu_ ## callback;	\
-	} while (0)
-
 /*
  * Maximum poll count for reading counter value using high-low-high sequence.
  */
@@ -121,7 +115,9 @@ static void arm_cspmu_set_ev_filter(struct arm_cspmu *cspmu,
 
 static struct acpi_apmt_node *arm_cspmu_apmt_node(struct device *dev)
 {
-	return *(struct acpi_apmt_node **)dev_get_platdata(dev);
+	struct acpi_apmt_node **ptr = dev_get_platdata(dev);
+
+	return ptr ? *ptr : NULL;
 }
 
 /*
@@ -317,6 +313,10 @@ static const char *arm_cspmu_get_name(const struct arm_cspmu *cspmu)
 
 	dev = cspmu->dev;
 	apmt_node = arm_cspmu_apmt_node(dev);
+	if (!apmt_node)
+		return devm_kasprintf(dev, GFP_KERNEL, PMUNAME "_%u",
+				      atomic_fetch_inc(&pmu_idx[0]));
+
 	pmu_type = apmt_node->type;
 
 	if (pmu_type >= ACPI_APMT_NODE_TYPE_COUNT) {
@@ -408,21 +408,32 @@ static struct arm_cspmu_impl_match *arm_cspmu_impl_match_get(u32 pmiidr)
 	return NULL;
 }
 
+#define DEFAULT_IMPL_OP(name)	.name = arm_cspmu_##name
+
 static int arm_cspmu_init_impl_ops(struct arm_cspmu *cspmu)
 {
 	int ret = 0;
-	struct arm_cspmu_impl_ops *impl_ops = &cspmu->impl.ops;
 	struct acpi_apmt_node *apmt_node = arm_cspmu_apmt_node(cspmu->dev);
 	struct arm_cspmu_impl_match *match;
 
-	/*
-	 * Get PMU implementer and product id from APMT node.
-	 * If APMT node doesn't have implementer/product id, try get it
-	 * from PMIIDR.
-	 */
-	cspmu->impl.pmiidr =
-		(apmt_node->impl_id) ? apmt_node->impl_id :
-				       readl(cspmu->base0 + PMIIDR);
+	/* Start with a default PMU implementation */
+	cspmu->impl.module = THIS_MODULE;
+	cspmu->impl.pmiidr = readl(cspmu->base0 + PMIIDR);
+	cspmu->impl.ops = (struct arm_cspmu_impl_ops) {
+		DEFAULT_IMPL_OP(get_event_attrs),
+		DEFAULT_IMPL_OP(get_format_attrs),
+		DEFAULT_IMPL_OP(get_identifier),
+		DEFAULT_IMPL_OP(get_name),
+		DEFAULT_IMPL_OP(is_cycle_counter_event),
+		DEFAULT_IMPL_OP(event_type),
+		DEFAULT_IMPL_OP(event_filter),
+		DEFAULT_IMPL_OP(set_ev_filter),
+		DEFAULT_IMPL_OP(event_attr_is_visible),
+	};
+
+	/* Firmware may override implementer/product ID from PMIIDR */
+	if (apmt_node && apmt_node->impl_id)
+		cspmu->impl.pmiidr = apmt_node->impl_id;
 
 	/* Find implementer specific attribute ops. */
 	match = arm_cspmu_impl_match_get(cspmu->impl.pmiidr);
@@ -450,24 +461,9 @@ static int arm_cspmu_init_impl_ops(struct arm_cspmu *cspmu)
 		}
 
 		mutex_unlock(&arm_cspmu_lock);
+	}
 
-		if (ret)
-			return ret;
-	} else
-		cspmu->impl.module = THIS_MODULE;
-
-	/* Use default callbacks if implementer doesn't provide one. */
-	CHECK_DEFAULT_IMPL_OPS(impl_ops, get_event_attrs);
-	CHECK_DEFAULT_IMPL_OPS(impl_ops, get_format_attrs);
-	CHECK_DEFAULT_IMPL_OPS(impl_ops, get_identifier);
-	CHECK_DEFAULT_IMPL_OPS(impl_ops, get_name);
-	CHECK_DEFAULT_IMPL_OPS(impl_ops, is_cycle_counter_event);
-	CHECK_DEFAULT_IMPL_OPS(impl_ops, event_type);
-	CHECK_DEFAULT_IMPL_OPS(impl_ops, event_filter);
-	CHECK_DEFAULT_IMPL_OPS(impl_ops, event_attr_is_visible);
-	CHECK_DEFAULT_IMPL_OPS(impl_ops, set_ev_filter);
-
-	return 0;
+	return ret;
 }
 
 static struct attribute_group *
@@ -512,23 +508,16 @@ arm_cspmu_alloc_format_attr_group(struct arm_cspmu *cspmu)
 	return format_group;
 }
 
-static struct attribute_group **
-arm_cspmu_alloc_attr_group(struct arm_cspmu *cspmu)
+static int arm_cspmu_alloc_attr_groups(struct arm_cspmu *cspmu)
 {
-	struct attribute_group **attr_groups = NULL;
-	struct device *dev = cspmu->dev;
+	const struct attribute_group **attr_groups = cspmu->attr_groups;
 	const struct arm_cspmu_impl_ops *impl_ops = &cspmu->impl.ops;
 
 	cspmu->identifier = impl_ops->get_identifier(cspmu);
 	cspmu->name = impl_ops->get_name(cspmu);
 
 	if (!cspmu->identifier || !cspmu->name)
-		return NULL;
-
-	attr_groups = devm_kcalloc(dev, 5, sizeof(struct attribute_group *),
-				   GFP_KERNEL);
-	if (!attr_groups)
-		return NULL;
+		return -ENOMEM;
 
 	attr_groups[0] = arm_cspmu_alloc_event_attr_group(cspmu);
 	attr_groups[1] = arm_cspmu_alloc_format_attr_group(cspmu);
@@ -536,18 +525,14 @@ arm_cspmu_alloc_attr_group(struct arm_cspmu *cspmu)
 	attr_groups[3] = &arm_cspmu_cpumask_attr_group;
 
 	if (!attr_groups[0] || !attr_groups[1])
-		return NULL;
+		return -ENOMEM;
 
-	return attr_groups;
+	return 0;
 }
 
 static inline void arm_cspmu_reset_counters(struct arm_cspmu *cspmu)
 {
-	u32 pmcr = 0;
-
-	pmcr |= PMCR_P;
-	pmcr |= PMCR_C;
-	writel(pmcr, cspmu->base0 + PMCR);
+	writel(PMCR_C | PMCR_P, cspmu->base0 + PMCR);
 }
 
 static inline void arm_cspmu_start_counters(struct arm_cspmu *cspmu)
@@ -962,7 +947,14 @@ static struct arm_cspmu *arm_cspmu_alloc(struct platform_device *pdev)
 	platform_set_drvdata(pdev, cspmu);
 
 	apmt_node = arm_cspmu_apmt_node(dev);
-	cspmu->has_atomic_dword = apmt_node->flags & ACPI_APMT_FLAGS_ATOMIC;
+	if (apmt_node) {
+		cspmu->has_atomic_dword = apmt_node->flags & ACPI_APMT_FLAGS_ATOMIC;
+	} else {
+		u32 width = 0;
+
+		device_property_read_u32(dev, "reg-io-width", &width);
+		cspmu->has_atomic_dword = (width == 8);
+	}
 
 	return cspmu;
 }
@@ -1153,11 +1145,6 @@ static int arm_cspmu_acpi_get_cpus(struct arm_cspmu *cspmu)
 		}
 	}
 
-	if (cpumask_empty(&cspmu->associated_cpus)) {
-		dev_dbg(cspmu->dev, "No cpu associated with the PMU\n");
-		return -ENODEV;
-	}
-
 	return 0;
 }
 #else
@@ -1167,19 +1154,45 @@ static int arm_cspmu_acpi_get_cpus(struct arm_cspmu *cspmu)
 }
 #endif
 
+static int arm_cspmu_of_get_cpus(struct arm_cspmu *cspmu)
+{
+	struct of_phandle_iterator it;
+	int ret, cpu;
+
+	of_for_each_phandle(&it, ret, dev_of_node(cspmu->dev), "cpus", NULL, 0) {
+		cpu = of_cpu_node_to_id(it.node);
+		if (cpu < 0)
+			continue;
+		cpumask_set_cpu(cpu, &cspmu->associated_cpus);
+	}
+	return ret == -ENOENT ? 0 : ret;
+}
+
 static int arm_cspmu_get_cpus(struct arm_cspmu *cspmu)
 {
-	return arm_cspmu_acpi_get_cpus(cspmu);
+	int ret = 0;
+
+	if (arm_cspmu_apmt_node(cspmu->dev))
+		ret = arm_cspmu_acpi_get_cpus(cspmu);
+	else if (device_property_present(cspmu->dev, "cpus"))
+		ret = arm_cspmu_of_get_cpus(cspmu);
+	else
+		cpumask_copy(&cspmu->associated_cpus, cpu_possible_mask);
+
+	if (!ret && cpumask_empty(&cspmu->associated_cpus)) {
+		dev_dbg(cspmu->dev, "No cpu associated with the PMU\n");
+		ret = -ENODEV;
+	}
+	return ret;
 }
 
 static int arm_cspmu_register_pmu(struct arm_cspmu *cspmu)
 {
 	int ret, capabilities;
-	struct attribute_group **attr_groups;
 
-	attr_groups = arm_cspmu_alloc_attr_group(cspmu);
-	if (!attr_groups)
-		return -ENOMEM;
+	ret = arm_cspmu_alloc_attr_groups(cspmu);
+	if (ret)
+		return ret;
 
 	ret = cpuhp_state_add_instance(arm_cspmu_cpuhp_state,
 				       &cspmu->cpuhp_node);
@@ -1201,12 +1214,11 @@ static int arm_cspmu_register_pmu(struct arm_cspmu *cspmu)
 		.start		= arm_cspmu_start,
 		.stop		= arm_cspmu_stop,
 		.read		= arm_cspmu_read,
-		.attr_groups	= (const struct attribute_group **)attr_groups,
+		.attr_groups	= cspmu->attr_groups,
 		.capabilities	= capabilities,
 	};
 
 	/* Hardware counter init */
-	arm_cspmu_stop_counters(cspmu);
 	arm_cspmu_reset_counters(cspmu);
 
 	ret = perf_pmu_register(&cspmu->pmu, cspmu->name, -1);
@@ -1252,14 +1264,12 @@ static int arm_cspmu_device_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int arm_cspmu_device_remove(struct platform_device *pdev)
+static void arm_cspmu_device_remove(struct platform_device *pdev)
 {
 	struct arm_cspmu *cspmu = platform_get_drvdata(pdev);
 
 	perf_pmu_unregister(&cspmu->pmu);
 	cpuhp_state_remove_instance(arm_cspmu_cpuhp_state, &cspmu->cpuhp_node);
-
-	return 0;
 }
 
 static const struct platform_device_id arm_cspmu_id[] = {
@@ -1268,13 +1278,20 @@ static const struct platform_device_id arm_cspmu_id[] = {
 };
 MODULE_DEVICE_TABLE(platform, arm_cspmu_id);
 
+static const struct of_device_id arm_cspmu_of_match[] = {
+	{ .compatible = "arm,coresight-pmu" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, arm_cspmu_of_match);
+
 static struct platform_driver arm_cspmu_driver = {
 	.driver = {
-			.name = DRVNAME,
-			.suppress_bind_attrs = true,
-		},
+		.name = DRVNAME,
+		.of_match_table = arm_cspmu_of_match,
+		.suppress_bind_attrs = true,
+	},
 	.probe = arm_cspmu_device_probe,
-	.remove = arm_cspmu_device_remove,
+	.remove_new = arm_cspmu_device_remove,
 	.id_table = arm_cspmu_id,
 };
 
diff --git a/drivers/perf/arm_cspmu/arm_cspmu.h b/drivers/perf/arm_cspmu/arm_cspmu.h
index 2fe723555a6b..c9163acfe810 100644
--- a/drivers/perf/arm_cspmu/arm_cspmu.h
+++ b/drivers/perf/arm_cspmu/arm_cspmu.h
@@ -157,6 +157,7 @@ struct arm_cspmu {
 	int cycle_counter_logical_idx;
 
 	struct arm_cspmu_hw_events hw_events;
+	const struct attribute_group *attr_groups[5];
 
 	struct arm_cspmu_impl impl;
 };
diff --git a/drivers/perf/arm_cspmu/nvidia_cspmu.c b/drivers/perf/arm_cspmu/nvidia_cspmu.c
index 0382b702f092..5b84b701ad62 100644
--- a/drivers/perf/arm_cspmu/nvidia_cspmu.c
+++ b/drivers/perf/arm_cspmu/nvidia_cspmu.c
@@ -388,12 +388,6 @@ static int nv_cspmu_init_ops(struct arm_cspmu *cspmu)
 	impl_ops->get_format_attrs		= nv_cspmu_get_format_attrs;
 	impl_ops->get_name			= nv_cspmu_get_name;
 
-	/* Set others to NULL to use default callback. */
-	impl_ops->event_type			= NULL;
-	impl_ops->event_attr_is_visible		= NULL;
-	impl_ops->get_identifier		= NULL;
-	impl_ops->is_cycle_counter_event	= NULL;
-
 	return 0;
 }
 
diff --git a/drivers/perf/arm_dmc620_pmu.c b/drivers/perf/arm_dmc620_pmu.c
index 30cea6859574..8a81be2dd5ec 100644
--- a/drivers/perf/arm_dmc620_pmu.c
+++ b/drivers/perf/arm_dmc620_pmu.c
@@ -724,7 +724,7 @@ out_teardown_dev:
 	return ret;
 }
 
-static int dmc620_pmu_device_remove(struct platform_device *pdev)
+static void dmc620_pmu_device_remove(struct platform_device *pdev)
 {
 	struct dmc620_pmu *dmc620_pmu = platform_get_drvdata(pdev);
 
@@ -732,8 +732,6 @@ static int dmc620_pmu_device_remove(struct platform_device *pdev)
 
 	/* perf will synchronise RCU before devres can free dmc620_pmu */
 	perf_pmu_unregister(&dmc620_pmu->pmu);
-
-	return 0;
 }
 
 static const struct acpi_device_id dmc620_acpi_match[] = {
@@ -748,7 +746,7 @@ static struct platform_driver dmc620_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe	= dmc620_pmu_device_probe,
-	.remove	= dmc620_pmu_device_remove,
+	.remove_new = dmc620_pmu_device_remove,
 };
 
 static int __init dmc620_pmu_init(void)
diff --git a/drivers/perf/arm_dsu_pmu.c b/drivers/perf/arm_dsu_pmu.c
index 7ec4498e312f..bae3ca37f846 100644
--- a/drivers/perf/arm_dsu_pmu.c
+++ b/drivers/perf/arm_dsu_pmu.c
@@ -774,14 +774,12 @@ static int dsu_pmu_device_probe(struct platform_device *pdev)
 	return rc;
 }
 
-static int dsu_pmu_device_remove(struct platform_device *pdev)
+static void 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);
-
-	return 0;
 }
 
 static const struct of_device_id dsu_pmu_of_match[] = {
@@ -806,7 +804,7 @@ static struct platform_driver dsu_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe = dsu_pmu_device_probe,
-	.remove = dsu_pmu_device_remove,
+	.remove_new = dsu_pmu_device_remove,
 };
 
 static int dsu_pmu_cpu_online(unsigned int cpu, struct hlist_node *node)
diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c
index 9e5d7fa647b6..719aa953a1c4 100644
--- a/drivers/perf/arm_smmuv3_pmu.c
+++ b/drivers/perf/arm_smmuv3_pmu.c
@@ -965,14 +965,12 @@ out_unregister:
 	return err;
 }
 
-static int smmu_pmu_remove(struct platform_device *pdev)
+static void smmu_pmu_remove(struct platform_device *pdev)
 {
 	struct smmu_pmu *smmu_pmu = platform_get_drvdata(pdev);
 
 	perf_pmu_unregister(&smmu_pmu->pmu);
 	cpuhp_state_remove_instance_nocalls(cpuhp_state_num, &smmu_pmu->node);
-
-	return 0;
 }
 
 static void smmu_pmu_shutdown(struct platform_device *pdev)
@@ -997,7 +995,7 @@ static struct platform_driver smmu_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe = smmu_pmu_probe,
-	.remove = smmu_pmu_remove,
+	.remove_new = smmu_pmu_remove,
 	.shutdown = smmu_pmu_shutdown,
 };
 
diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c
index b622d75d8c9e..35f0de03416f 100644
--- a/drivers/perf/arm_spe_pmu.c
+++ b/drivers/perf/arm_spe_pmu.c
@@ -1263,14 +1263,13 @@ out_free_handle:
 	return ret;
 }
 
-static int arm_spe_pmu_device_remove(struct platform_device *pdev)
+static void arm_spe_pmu_device_remove(struct platform_device *pdev)
 {
 	struct arm_spe_pmu *spe_pmu = platform_get_drvdata(pdev);
 
 	arm_spe_pmu_perf_destroy(spe_pmu);
 	arm_spe_pmu_dev_teardown(spe_pmu);
 	free_percpu(spe_pmu->handle);
-	return 0;
 }
 
 static struct platform_driver arm_spe_pmu_driver = {
@@ -1281,7 +1280,7 @@ static struct platform_driver arm_spe_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe	= arm_spe_pmu_device_probe,
-	.remove	= arm_spe_pmu_device_remove,
+	.remove_new = arm_spe_pmu_device_remove,
 };
 
 static int __init arm_spe_pmu_init(void)
diff --git a/drivers/perf/fsl_imx8_ddr_perf.c b/drivers/perf/fsl_imx8_ddr_perf.c
index 7dbfaee372c7..4e8fa5a48fcf 100644
--- a/drivers/perf/fsl_imx8_ddr_perf.c
+++ b/drivers/perf/fsl_imx8_ddr_perf.c
@@ -826,7 +826,7 @@ cpuhp_state_err:
 	return ret;
 }
 
-static int ddr_perf_remove(struct platform_device *pdev)
+static void ddr_perf_remove(struct platform_device *pdev)
 {
 	struct ddr_pmu *pmu = platform_get_drvdata(pdev);
 
@@ -836,7 +836,6 @@ static int ddr_perf_remove(struct platform_device *pdev)
 	perf_pmu_unregister(&pmu->pmu);
 
 	ida_free(&ddr_ida, pmu->id);
-	return 0;
 }
 
 static struct platform_driver imx_ddr_pmu_driver = {
@@ -846,7 +845,7 @@ static struct platform_driver imx_ddr_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe          = ddr_perf_probe,
-	.remove         = ddr_perf_remove,
+	.remove_new     = ddr_perf_remove,
 };
 
 module_platform_driver(imx_ddr_pmu_driver);
diff --git a/drivers/perf/fsl_imx9_ddr_perf.c b/drivers/perf/fsl_imx9_ddr_perf.c
index 9685645bfe04..72c2d3074cde 100644
--- a/drivers/perf/fsl_imx9_ddr_perf.c
+++ b/drivers/perf/fsl_imx9_ddr_perf.c
@@ -679,7 +679,7 @@ format_string_err:
 	return ret;
 }
 
-static int ddr_perf_remove(struct platform_device *pdev)
+static void ddr_perf_remove(struct platform_device *pdev)
 {
 	struct ddr_pmu *pmu = platform_get_drvdata(pdev);
 
@@ -689,8 +689,6 @@ static int ddr_perf_remove(struct platform_device *pdev)
 	perf_pmu_unregister(&pmu->pmu);
 
 	ida_free(&ddr_ida, pmu->id);
-
-	return 0;
 }
 
 static struct platform_driver imx_ddr_pmu_driver = {
@@ -700,7 +698,7 @@ static struct platform_driver imx_ddr_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe          = ddr_perf_probe,
-	.remove         = ddr_perf_remove,
+	.remove_new     = ddr_perf_remove,
 };
 module_platform_driver(imx_ddr_pmu_driver);
 
diff --git a/drivers/perf/hisilicon/hisi_pcie_pmu.c b/drivers/perf/hisilicon/hisi_pcie_pmu.c
index b90ba8aca3fa..5d1f0e9fdb08 100644
--- a/drivers/perf/hisilicon/hisi_pcie_pmu.c
+++ b/drivers/perf/hisilicon/hisi_pcie_pmu.c
@@ -216,10 +216,8 @@ static void hisi_pcie_pmu_writeq(struct hisi_pcie_pmu *pcie_pmu, u32 reg_offset,
 	writeq_relaxed(val, pcie_pmu->base + offset);
 }
 
-static void hisi_pcie_pmu_config_filter(struct perf_event *event)
+static u64 hisi_pcie_pmu_get_event_ctrl_val(struct perf_event *event)
 {
-	struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu);
-	struct hw_perf_event *hwc = &event->hw;
 	u64 port, trig_len, thr_len, len_mode;
 	u64 reg = HISI_PCIE_INIT_SET;
 
@@ -256,10 +254,19 @@ static void hisi_pcie_pmu_config_filter(struct perf_event *event)
 	else
 		reg |= FIELD_PREP(HISI_PCIE_LEN_M, HISI_PCIE_LEN_M_DEFAULT);
 
+	return reg;
+}
+
+static void hisi_pcie_pmu_config_event_ctrl(struct perf_event *event)
+{
+	struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	u64 reg = hisi_pcie_pmu_get_event_ctrl_val(event);
+
 	hisi_pcie_pmu_writeq(pcie_pmu, HISI_PCIE_EVENT_CTRL, hwc->idx, reg);
 }
 
-static void hisi_pcie_pmu_clear_filter(struct perf_event *event)
+static void hisi_pcie_pmu_clear_event_ctrl(struct perf_event *event)
 {
 	struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
@@ -299,18 +306,24 @@ static bool hisi_pcie_pmu_valid_filter(struct perf_event *event,
 	if (hisi_pcie_get_trig_len(event) > HISI_PCIE_TRIG_MAX_VAL)
 		return false;
 
-	if (requester_id) {
-		if (!hisi_pcie_pmu_valid_requester_id(pcie_pmu, requester_id))
-			return false;
-	}
+	/* Need to explicitly set filter of "port" or "bdf" */
+	if (!hisi_pcie_get_port(event) &&
+	    !hisi_pcie_pmu_valid_requester_id(pcie_pmu, requester_id))
+		return false;
 
 	return true;
 }
 
+/*
+ * Check Whether two events share the same config. The same config means not
+ * only the event code, but also the filter settings of the two events are
+ * the same.
+ */
 static bool hisi_pcie_pmu_cmp_event(struct perf_event *target,
 					struct perf_event *event)
 {
-	return hisi_pcie_get_real_event(target) == hisi_pcie_get_real_event(event);
+	return hisi_pcie_pmu_get_event_ctrl_val(target) ==
+	       hisi_pcie_pmu_get_event_ctrl_val(event);
 }
 
 static bool hisi_pcie_pmu_validate_event_group(struct perf_event *event)
@@ -385,40 +398,32 @@ static u64 hisi_pcie_pmu_read_counter(struct perf_event *event)
 	return hisi_pcie_pmu_readq(pcie_pmu, event->hw.event_base, idx);
 }
 
-static int hisi_pcie_pmu_find_related_event(struct hisi_pcie_pmu *pcie_pmu,
-					    struct perf_event *event)
+/*
+ * Check all work events, if a relevant event is found then we return it
+ * first, otherwise return the first idle counter (need to reset).
+ */
+static int hisi_pcie_pmu_get_event_idx(struct hisi_pcie_pmu *pcie_pmu,
+					struct perf_event *event)
 {
+	int first_idle = -EAGAIN;
 	struct perf_event *sibling;
 	int idx;
 
 	for (idx = 0; idx < HISI_PCIE_MAX_COUNTERS; idx++) {
 		sibling = pcie_pmu->hw_events[idx];
-		if (!sibling)
-			continue;
-
-		if (!hisi_pcie_pmu_cmp_event(sibling, event))
+		if (!sibling) {
+			if (first_idle == -EAGAIN)
+				first_idle = idx;
 			continue;
+		}
 
 		/* Related events must be used in group */
-		if (sibling->group_leader == event->group_leader)
+		if (hisi_pcie_pmu_cmp_event(sibling, event) &&
+		    sibling->group_leader == event->group_leader)
 			return idx;
-		else
-			return -EINVAL;
 	}
 
-	return idx;
-}
-
-static int hisi_pcie_pmu_get_event_idx(struct hisi_pcie_pmu *pcie_pmu)
-{
-	int idx;
-
-	for (idx = 0; idx < HISI_PCIE_MAX_COUNTERS; idx++) {
-		if (!pcie_pmu->hw_events[idx])
-			return idx;
-	}
-
-	return -EINVAL;
+	return first_idle;
 }
 
 static void hisi_pcie_pmu_event_update(struct perf_event *event)
@@ -505,7 +510,7 @@ static void hisi_pcie_pmu_start(struct perf_event *event, int flags)
 	WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
 	hwc->state = 0;
 
-	hisi_pcie_pmu_config_filter(event);
+	hisi_pcie_pmu_config_event_ctrl(event);
 	hisi_pcie_pmu_enable_counter(pcie_pmu, hwc);
 	hisi_pcie_pmu_enable_int(pcie_pmu, hwc);
 	hisi_pcie_pmu_set_period(event);
@@ -526,7 +531,7 @@ static void hisi_pcie_pmu_stop(struct perf_event *event, int flags)
 	hisi_pcie_pmu_event_update(event);
 	hisi_pcie_pmu_disable_int(pcie_pmu, hwc);
 	hisi_pcie_pmu_disable_counter(pcie_pmu, hwc);
-	hisi_pcie_pmu_clear_filter(event);
+	hisi_pcie_pmu_clear_event_ctrl(event);
 	WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
 	hwc->state |= PERF_HES_STOPPED;
 
@@ -544,27 +549,18 @@ static int hisi_pcie_pmu_add(struct perf_event *event, int flags)
 
 	hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
 
-	/* Check all working events to find a related event. */
-	idx = hisi_pcie_pmu_find_related_event(pcie_pmu, event);
-	if (idx < 0)
-		return idx;
-
-	/* Current event shares an enabled counter with the related event */
-	if (idx < HISI_PCIE_MAX_COUNTERS) {
-		hwc->idx = idx;
-		goto start_count;
-	}
-
-	idx = hisi_pcie_pmu_get_event_idx(pcie_pmu);
+	idx = hisi_pcie_pmu_get_event_idx(pcie_pmu, event);
 	if (idx < 0)
 		return idx;
 
 	hwc->idx = idx;
-	pcie_pmu->hw_events[idx] = event;
-	/* Reset Counter to avoid previous statistic interference. */
-	hisi_pcie_pmu_reset_counter(pcie_pmu, idx);
 
-start_count:
+	/* No enabled counter found with related event, reset it */
+	if (!pcie_pmu->hw_events[idx]) {
+		hisi_pcie_pmu_reset_counter(pcie_pmu, idx);
+		pcie_pmu->hw_events[idx] = event;
+	}
+
 	if (flags & PERF_EF_START)
 		hisi_pcie_pmu_start(event, PERF_EF_RELOAD);
 
@@ -714,10 +710,18 @@ static struct attribute *hisi_pcie_pmu_events_attr[] = {
 	HISI_PCIE_PMU_EVENT_ATTR(rx_mrd_cnt, 0x10210),
 	HISI_PCIE_PMU_EVENT_ATTR(tx_mrd_latency, 0x0011),
 	HISI_PCIE_PMU_EVENT_ATTR(tx_mrd_cnt, 0x10011),
+	HISI_PCIE_PMU_EVENT_ATTR(rx_mwr_flux, 0x0104),
+	HISI_PCIE_PMU_EVENT_ATTR(rx_mwr_time, 0x10104),
 	HISI_PCIE_PMU_EVENT_ATTR(rx_mrd_flux, 0x0804),
 	HISI_PCIE_PMU_EVENT_ATTR(rx_mrd_time, 0x10804),
+	HISI_PCIE_PMU_EVENT_ATTR(rx_cpl_flux, 0x2004),
+	HISI_PCIE_PMU_EVENT_ATTR(rx_cpl_time, 0x12004),
+	HISI_PCIE_PMU_EVENT_ATTR(tx_mwr_flux, 0x0105),
+	HISI_PCIE_PMU_EVENT_ATTR(tx_mwr_time, 0x10105),
 	HISI_PCIE_PMU_EVENT_ATTR(tx_mrd_flux, 0x0405),
 	HISI_PCIE_PMU_EVENT_ATTR(tx_mrd_time, 0x10405),
+	HISI_PCIE_PMU_EVENT_ATTR(tx_cpl_flux, 0x1005),
+	HISI_PCIE_PMU_EVENT_ATTR(tx_cpl_time, 0x11005),
 	NULL
 };
 
diff --git a/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c b/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c
index 40f1bc9f9b91..0e923f94fa5b 100644
--- a/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c
@@ -341,7 +341,7 @@ static int hisi_cpa_pmu_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int hisi_cpa_pmu_remove(struct platform_device *pdev)
+static void hisi_cpa_pmu_remove(struct platform_device *pdev)
 {
 	struct hisi_pmu *cpa_pmu = platform_get_drvdata(pdev);
 
@@ -349,7 +349,6 @@ static int hisi_cpa_pmu_remove(struct platform_device *pdev)
 	cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_CPA_ONLINE,
 					    &cpa_pmu->node);
 	hisi_cpa_pmu_enable_pm(cpa_pmu);
-	return 0;
 }
 
 static struct platform_driver hisi_cpa_pmu_driver = {
@@ -359,7 +358,7 @@ static struct platform_driver hisi_cpa_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe = hisi_cpa_pmu_probe,
-	.remove = hisi_cpa_pmu_remove,
+	.remove_new = hisi_cpa_pmu_remove,
 };
 
 static int __init hisi_cpa_pmu_module_init(void)
diff --git a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
index ffb039d05d07..b804e3738113 100644
--- a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
@@ -531,14 +531,13 @@ static int hisi_ddrc_pmu_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int hisi_ddrc_pmu_remove(struct platform_device *pdev)
+static void hisi_ddrc_pmu_remove(struct platform_device *pdev)
 {
 	struct hisi_pmu *ddrc_pmu = platform_get_drvdata(pdev);
 
 	perf_pmu_unregister(&ddrc_pmu->pmu);
 	cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE,
 					    &ddrc_pmu->node);
-	return 0;
 }
 
 static struct platform_driver hisi_ddrc_pmu_driver = {
@@ -548,7 +547,7 @@ static struct platform_driver hisi_ddrc_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe = hisi_ddrc_pmu_probe,
-	.remove = hisi_ddrc_pmu_remove,
+	.remove_new = hisi_ddrc_pmu_remove,
 };
 
 static int __init hisi_ddrc_pmu_module_init(void)
diff --git a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
index 15caf99e1eef..21e69b1cdd4d 100644
--- a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
@@ -534,14 +534,13 @@ static int hisi_hha_pmu_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int hisi_hha_pmu_remove(struct platform_device *pdev)
+static void hisi_hha_pmu_remove(struct platform_device *pdev)
 {
 	struct hisi_pmu *hha_pmu = platform_get_drvdata(pdev);
 
 	perf_pmu_unregister(&hha_pmu->pmu);
 	cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE,
 					    &hha_pmu->node);
-	return 0;
 }
 
 static struct platform_driver hisi_hha_pmu_driver = {
@@ -551,7 +550,7 @@ static struct platform_driver hisi_hha_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe = hisi_hha_pmu_probe,
-	.remove = hisi_hha_pmu_remove,
+	.remove_new = hisi_hha_pmu_remove,
 };
 
 static int __init hisi_hha_pmu_module_init(void)
diff --git a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
index 794dbcd19b7a..51ba76871097 100644
--- a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
@@ -568,14 +568,13 @@ static int hisi_l3c_pmu_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int hisi_l3c_pmu_remove(struct platform_device *pdev)
+static void hisi_l3c_pmu_remove(struct platform_device *pdev)
 {
 	struct hisi_pmu *l3c_pmu = platform_get_drvdata(pdev);
 
 	perf_pmu_unregister(&l3c_pmu->pmu);
 	cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_L3_ONLINE,
 					    &l3c_pmu->node);
-	return 0;
 }
 
 static struct platform_driver hisi_l3c_pmu_driver = {
@@ -585,7 +584,7 @@ static struct platform_driver hisi_l3c_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe = hisi_l3c_pmu_probe,
-	.remove = hisi_l3c_pmu_remove,
+	.remove_new = hisi_l3c_pmu_remove,
 };
 
 static int __init hisi_l3c_pmu_module_init(void)
diff --git a/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c
index 797cf201996a..3cdb35c741f9 100644
--- a/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c
@@ -514,14 +514,13 @@ static int hisi_pa_pmu_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int hisi_pa_pmu_remove(struct platform_device *pdev)
+static void hisi_pa_pmu_remove(struct platform_device *pdev)
 {
 	struct hisi_pmu *pa_pmu = platform_get_drvdata(pdev);
 
 	perf_pmu_unregister(&pa_pmu->pmu);
 	cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_PA_ONLINE,
 					    &pa_pmu->node);
-	return 0;
 }
 
 static const struct acpi_device_id hisi_pa_pmu_acpi_match[] = {
@@ -539,7 +538,7 @@ static struct platform_driver hisi_pa_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe = hisi_pa_pmu_probe,
-	.remove = hisi_pa_pmu_remove,
+	.remove_new = hisi_pa_pmu_remove,
 };
 
 static int __init hisi_pa_pmu_module_init(void)
diff --git a/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c
index e706ca567676..765bbd61db26 100644
--- a/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c
@@ -460,14 +460,13 @@ static int hisi_sllc_pmu_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int hisi_sllc_pmu_remove(struct platform_device *pdev)
+static void hisi_sllc_pmu_remove(struct platform_device *pdev)
 {
 	struct hisi_pmu *sllc_pmu = platform_get_drvdata(pdev);
 
 	perf_pmu_unregister(&sllc_pmu->pmu);
 	cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_SLLC_ONLINE,
 					    &sllc_pmu->node);
-	return 0;
 }
 
 static struct platform_driver hisi_sllc_pmu_driver = {
@@ -477,7 +476,7 @@ static struct platform_driver hisi_sllc_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe = hisi_sllc_pmu_probe,
-	.remove = hisi_sllc_pmu_remove,
+	.remove_new = hisi_sllc_pmu_remove,
 };
 
 static int __init hisi_sllc_pmu_module_init(void)
diff --git a/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c
index 636fb79647c8..481dcc9e8fbf 100644
--- a/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c
@@ -287,12 +287,52 @@ static u64 hisi_uc_pmu_read_counter(struct hisi_pmu *uc_pmu,
 	return readq(uc_pmu->base + HISI_UC_CNTR_REGn(hwc->idx));
 }
 
-static void hisi_uc_pmu_write_counter(struct hisi_pmu *uc_pmu,
+static bool hisi_uc_pmu_get_glb_en_state(struct hisi_pmu *uc_pmu)
+{
+	u32 val;
+
+	val = readl(uc_pmu->base + HISI_UC_EVENT_CTRL_REG);
+	return !!FIELD_GET(HISI_UC_EVENT_GLB_EN, val);
+}
+
+static void hisi_uc_pmu_write_counter_normal(struct hisi_pmu *uc_pmu,
 				      struct hw_perf_event *hwc, u64 val)
 {
 	writeq(val, uc_pmu->base + HISI_UC_CNTR_REGn(hwc->idx));
 }
 
+static void hisi_uc_pmu_write_counter_quirk_v2(struct hisi_pmu *uc_pmu,
+				      struct hw_perf_event *hwc, u64 val)
+{
+	hisi_uc_pmu_start_counters(uc_pmu);
+	hisi_uc_pmu_write_counter_normal(uc_pmu, hwc, val);
+	hisi_uc_pmu_stop_counters(uc_pmu);
+}
+
+static void hisi_uc_pmu_write_counter(struct hisi_pmu *uc_pmu,
+				      struct hw_perf_event *hwc, u64 val)
+{
+	bool enable = hisi_uc_pmu_get_glb_en_state(uc_pmu);
+	bool erratum = uc_pmu->identifier == HISI_PMU_V2;
+
+	/*
+	 * HiSilicon UC PMU v2 suffers the erratum 162700402 that the
+	 * PMU counter cannot be set due to the lack of clock under power
+	 * saving mode. This will lead to error or inaccurate counts.
+	 * The clock can be enabled by the PMU global enabling control.
+	 * The irq handler and pmu_start() will call the function to set
+	 * period. If the function under irq context, the PMU has been
+	 * enabled therefore we set counter directly. Other situations
+	 * the PMU is disabled, we need to enable it to turn on the
+	 * counter clock to set period, and then restore PMU enable
+	 * status, the counter can hold its value without a clock.
+	 */
+	if (enable || !erratum)
+		hisi_uc_pmu_write_counter_normal(uc_pmu, hwc, val);
+	else
+		hisi_uc_pmu_write_counter_quirk_v2(uc_pmu, hwc, val);
+}
+
 static void hisi_uc_pmu_enable_counter_int(struct hisi_pmu *uc_pmu,
 					   struct hw_perf_event *hwc)
 {
diff --git a/drivers/perf/marvell_cn10k_ddr_pmu.c b/drivers/perf/marvell_cn10k_ddr_pmu.c
index 524ba82bfce2..e2abca188dbe 100644
--- a/drivers/perf/marvell_cn10k_ddr_pmu.c
+++ b/drivers/perf/marvell_cn10k_ddr_pmu.c
@@ -697,7 +697,7 @@ error:
 	return ret;
 }
 
-static int cn10k_ddr_perf_remove(struct platform_device *pdev)
+static void cn10k_ddr_perf_remove(struct platform_device *pdev)
 {
 	struct cn10k_ddr_pmu *ddr_pmu = platform_get_drvdata(pdev);
 
@@ -706,7 +706,6 @@ static int cn10k_ddr_perf_remove(struct platform_device *pdev)
 				&ddr_pmu->node);
 
 	perf_pmu_unregister(&ddr_pmu->pmu);
-	return 0;
 }
 
 #ifdef CONFIG_OF
@@ -733,7 +732,7 @@ static struct platform_driver cn10k_ddr_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe		= cn10k_ddr_perf_probe,
-	.remove		= cn10k_ddr_perf_remove,
+	.remove_new	= cn10k_ddr_perf_remove,
 };
 
 static int __init cn10k_ddr_pmu_init(void)
diff --git a/drivers/perf/marvell_cn10k_tad_pmu.c b/drivers/perf/marvell_cn10k_tad_pmu.c
index fec8e82edb95..9e635f355470 100644
--- a/drivers/perf/marvell_cn10k_tad_pmu.c
+++ b/drivers/perf/marvell_cn10k_tad_pmu.c
@@ -351,15 +351,13 @@ static int tad_pmu_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int tad_pmu_remove(struct platform_device *pdev)
+static void tad_pmu_remove(struct platform_device *pdev)
 {
 	struct tad_pmu *pmu = platform_get_drvdata(pdev);
 
 	cpuhp_state_remove_instance_nocalls(tad_pmu_cpuhp_state,
 						&pmu->node);
 	perf_pmu_unregister(&pmu->pmu);
-
-	return 0;
 }
 
 #ifdef CONFIG_OF
@@ -385,7 +383,7 @@ static struct platform_driver tad_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe          = tad_pmu_probe,
-	.remove         = tad_pmu_remove,
+	.remove_new     = tad_pmu_remove,
 };
 
 static int tad_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
diff --git a/drivers/perf/qcom_l2_pmu.c b/drivers/perf/qcom_l2_pmu.c
index 3f9a98c17a89..148df5ae8ef8 100644
--- a/drivers/perf/qcom_l2_pmu.c
+++ b/drivers/perf/qcom_l2_pmu.c
@@ -965,7 +965,7 @@ out_unregister:
 	return err;
 }
 
-static int l2_cache_pmu_remove(struct platform_device *pdev)
+static void l2_cache_pmu_remove(struct platform_device *pdev)
 {
 	struct l2cache_pmu *l2cache_pmu =
 		to_l2cache_pmu(platform_get_drvdata(pdev));
@@ -973,7 +973,6 @@ static int l2_cache_pmu_remove(struct platform_device *pdev)
 	perf_pmu_unregister(&l2cache_pmu->pmu);
 	cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_QCOM_L2_ONLINE,
 				    &l2cache_pmu->node);
-	return 0;
 }
 
 static struct platform_driver l2_cache_pmu_driver = {
@@ -983,7 +982,7 @@ static struct platform_driver l2_cache_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe = l2_cache_pmu_probe,
-	.remove = l2_cache_pmu_remove,
+	.remove_new = l2_cache_pmu_remove,
 };
 
 static int __init register_l2_cache_pmu_driver(void)
diff --git a/drivers/perf/starfive_starlink_pmu.c b/drivers/perf/starfive_starlink_pmu.c
new file mode 100644
index 000000000000..5e5a672b4229
--- /dev/null
+++ b/drivers/perf/starfive_starlink_pmu.c
@@ -0,0 +1,642 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * StarFive's StarLink PMU driver
+ *
+ * Copyright (C) 2023 StarFive Technology Co., Ltd.
+ *
+ * Author: Ji Sheng Teoh <jisheng.teoh@starfivetech.com>
+ *
+ */
+
+#define STARLINK_PMU_PDEV_NAME	"starfive_starlink_pmu"
+#define pr_fmt(fmt)	STARLINK_PMU_PDEV_NAME ": " fmt
+
+#include <linux/bitmap.h>
+#include <linux/cpu_pm.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mod_devicetable.h>
+#include <linux/perf_event.h>
+#include <linux/platform_device.h>
+#include <linux/sysfs.h>
+
+#define STARLINK_PMU_MAX_COUNTERS			64
+#define STARLINK_PMU_NUM_COUNTERS			16
+#define STARLINK_PMU_IDX_CYCLE_COUNTER			63
+
+#define STARLINK_PMU_EVENT_SELECT			0x060
+#define STARLINK_PMU_EVENT_COUNTER			0x160
+#define STARLINK_PMU_COUNTER_MASK			GENMASK_ULL(63, 0)
+#define STARLINK_PMU_CYCLE_COUNTER			0x058
+
+#define STARLINK_PMU_CONTROL				0x040
+#define STARLINK_PMU_GLOBAL_ENABLE			BIT_ULL(0)
+
+#define STARLINK_PMU_INTERRUPT_ENABLE			0x050
+#define STARLINK_PMU_COUNTER_OVERFLOW_STATUS		0x048
+#define STARLINK_PMU_CYCLE_OVERFLOW_MASK		BIT_ULL(63)
+
+#define STARLINK_CYCLES				0x058
+#define CACHE_READ_REQUEST			0x04000701
+#define CACHE_WRITE_REQUEST			0x03000001
+#define CACHE_RELEASE_REQUEST			0x0003e001
+#define CACHE_READ_HIT				0x00901202
+#define CACHE_READ_MISS				0x04008002
+#define CACHE_WRITE_HIT				0x006c0002
+#define CACHE_WRITE_MISS			0x03000002
+#define CACHE_WRITEBACK				0x00000403
+
+#define to_starlink_pmu(p) (container_of(p, struct starlink_pmu, pmu))
+
+#define STARLINK_FORMAT_ATTR(_name, _config)				      \
+	(&((struct dev_ext_attribute[]) {				      \
+		{ .attr = __ATTR(_name, 0444, starlink_pmu_sysfs_format_show, NULL), \
+		  .var = (void *)_config, }				      \
+	})[0].attr.attr)
+
+#define STARLINK_EVENT_ATTR(_name, _id)					     \
+	PMU_EVENT_ATTR_ID(_name, starlink_pmu_sysfs_event_show, _id)
+
+static int starlink_pmu_cpuhp_state;
+
+struct starlink_hw_events {
+	struct perf_event	*events[STARLINK_PMU_MAX_COUNTERS];
+	DECLARE_BITMAP(used_mask, STARLINK_PMU_MAX_COUNTERS);
+};
+
+struct starlink_pmu {
+	struct pmu					pmu;
+	struct starlink_hw_events			__percpu *hw_events;
+	struct hlist_node				node;
+	struct notifier_block				starlink_pmu_pm_nb;
+	void __iomem					*pmu_base;
+	cpumask_t					cpumask;
+	int						irq;
+};
+
+static ssize_t
+starlink_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 sysfs_emit(buf, "%s\n", (char *)eattr->var);
+}
+
+static struct attribute *starlink_pmu_format_attrs[] = {
+	STARLINK_FORMAT_ATTR(event, "config:0-31"),
+	NULL
+};
+
+static const struct attribute_group starlink_pmu_format_attr_group = {
+	.name = "format",
+	.attrs = starlink_pmu_format_attrs,
+};
+
+static ssize_t
+starlink_pmu_sysfs_event_show(struct device *dev,
+			      struct device_attribute *attr,
+			      char *buf)
+{
+	struct perf_pmu_events_attr *eattr = container_of(attr,
+							  struct perf_pmu_events_attr, attr);
+
+	return sysfs_emit(buf, "event=0x%02llx\n", eattr->id);
+}
+
+static struct attribute *starlink_pmu_event_attrs[] = {
+	STARLINK_EVENT_ATTR(cycles, STARLINK_CYCLES),
+	STARLINK_EVENT_ATTR(read_request, CACHE_READ_REQUEST),
+	STARLINK_EVENT_ATTR(write_request, CACHE_WRITE_REQUEST),
+	STARLINK_EVENT_ATTR(release_request, CACHE_RELEASE_REQUEST),
+	STARLINK_EVENT_ATTR(read_hit, CACHE_READ_HIT),
+	STARLINK_EVENT_ATTR(read_miss, CACHE_READ_MISS),
+	STARLINK_EVENT_ATTR(write_hit, CACHE_WRITE_HIT),
+	STARLINK_EVENT_ATTR(write_miss, CACHE_WRITE_MISS),
+	STARLINK_EVENT_ATTR(writeback, CACHE_WRITEBACK),
+	NULL
+};
+
+static const struct attribute_group starlink_pmu_events_attr_group = {
+	.name = "events",
+	.attrs = starlink_pmu_event_attrs,
+};
+
+static ssize_t
+cpumask_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct starlink_pmu *starlink_pmu = to_starlink_pmu(dev_get_drvdata(dev));
+
+	return cpumap_print_to_pagebuf(true, buf, &starlink_pmu->cpumask);
+}
+
+static DEVICE_ATTR_RO(cpumask);
+
+static struct attribute *starlink_pmu_cpumask_attrs[] = {
+	&dev_attr_cpumask.attr,
+	NULL
+};
+
+static const struct attribute_group starlink_pmu_cpumask_attr_group = {
+	.attrs = starlink_pmu_cpumask_attrs,
+};
+
+static const struct attribute_group *starlink_pmu_attr_groups[] = {
+	&starlink_pmu_format_attr_group,
+	&starlink_pmu_events_attr_group,
+	&starlink_pmu_cpumask_attr_group,
+	NULL
+};
+
+static void starlink_pmu_set_event_period(struct perf_event *event)
+{
+	struct starlink_pmu *starlink_pmu = to_starlink_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = event->hw.idx;
+
+	/*
+	 * Program counter to half of it's max count to handle
+	 * cases of extreme interrupt latency.
+	 */
+	u64 val = STARLINK_PMU_COUNTER_MASK >> 1;
+
+	local64_set(&hwc->prev_count, val);
+	if (hwc->config == STARLINK_CYCLES)
+		writeq(val, starlink_pmu->pmu_base + STARLINK_PMU_CYCLE_COUNTER);
+	else
+		writeq(val, starlink_pmu->pmu_base + STARLINK_PMU_EVENT_COUNTER +
+		       idx * sizeof(u64));
+}
+
+static void starlink_pmu_counter_start(struct perf_event *event,
+				       struct starlink_pmu *starlink_pmu)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = event->hw.idx;
+	u64 val;
+
+	/*
+	 * Enable counter overflow interrupt[63:0],
+	 * which is mapped as follow:
+	 *
+	 * event counter 0	- Bit [0]
+	 * event counter 1	- Bit [1]
+	 * ...
+	 * cycle counter	- Bit [63]
+	 */
+	val = readq(starlink_pmu->pmu_base + STARLINK_PMU_INTERRUPT_ENABLE);
+
+	if (hwc->config == STARLINK_CYCLES) {
+		/*
+		 * Cycle count has its dedicated register, and it starts
+		 * counting as soon as STARLINK_PMU_GLOBAL_ENABLE is set.
+		 */
+		val |= STARLINK_PMU_CYCLE_OVERFLOW_MASK;
+	} else {
+		writeq(event->hw.config, starlink_pmu->pmu_base +
+		       STARLINK_PMU_EVENT_SELECT + idx * sizeof(u64));
+
+		val |= BIT_ULL(idx);
+	}
+
+	writeq(val, starlink_pmu->pmu_base + STARLINK_PMU_INTERRUPT_ENABLE);
+
+	writeq(STARLINK_PMU_GLOBAL_ENABLE, starlink_pmu->pmu_base +
+	       STARLINK_PMU_CONTROL);
+}
+
+static void starlink_pmu_counter_stop(struct perf_event *event,
+				      struct starlink_pmu *starlink_pmu)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = event->hw.idx;
+	u64 val;
+
+	val = readq(starlink_pmu->pmu_base + STARLINK_PMU_CONTROL);
+	val &= ~STARLINK_PMU_GLOBAL_ENABLE;
+	writeq(val, starlink_pmu->pmu_base + STARLINK_PMU_CONTROL);
+
+	val = readq(starlink_pmu->pmu_base + STARLINK_PMU_INTERRUPT_ENABLE);
+	if (hwc->config == STARLINK_CYCLES)
+		val &= ~STARLINK_PMU_CYCLE_OVERFLOW_MASK;
+	else
+		val &= ~BIT_ULL(idx);
+
+	writeq(val, starlink_pmu->pmu_base + STARLINK_PMU_INTERRUPT_ENABLE);
+}
+
+static void starlink_pmu_update(struct perf_event *event)
+{
+	struct starlink_pmu *starlink_pmu = to_starlink_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+	u64 prev_raw_count, new_raw_count;
+	u64 oldval;
+	u64 delta;
+
+	do {
+		prev_raw_count = local64_read(&hwc->prev_count);
+		if (hwc->config == STARLINK_CYCLES)
+			new_raw_count = readq(starlink_pmu->pmu_base +
+					      STARLINK_PMU_CYCLE_COUNTER);
+		else
+			new_raw_count = readq(starlink_pmu->pmu_base +
+					      STARLINK_PMU_EVENT_COUNTER +
+					      idx * sizeof(u64));
+		oldval = local64_cmpxchg(&hwc->prev_count, prev_raw_count,
+					 new_raw_count);
+	} while (oldval != prev_raw_count);
+
+	delta = (new_raw_count - prev_raw_count) & STARLINK_PMU_COUNTER_MASK;
+	local64_add(delta, &event->count);
+}
+
+static void starlink_pmu_start(struct perf_event *event, int flags)
+{
+	struct starlink_pmu *starlink_pmu = to_starlink_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED)))
+		return;
+
+	if (flags & PERF_EF_RELOAD)
+		WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+
+	hwc->state = 0;
+
+	starlink_pmu_set_event_period(event);
+	starlink_pmu_counter_start(event, starlink_pmu);
+
+	perf_event_update_userpage(event);
+}
+
+static void starlink_pmu_stop(struct perf_event *event, int flags)
+{
+	struct starlink_pmu *starlink_pmu = to_starlink_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (hwc->state & PERF_HES_STOPPED)
+		return;
+
+	starlink_pmu_counter_stop(event, starlink_pmu);
+	starlink_pmu_update(event);
+	hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
+}
+
+static int starlink_pmu_add(struct perf_event *event, int flags)
+{
+	struct starlink_pmu *starlink_pmu = to_starlink_pmu(event->pmu);
+	struct starlink_hw_events *hw_events =
+					this_cpu_ptr(starlink_pmu->hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+	unsigned long *used_mask = hw_events->used_mask;
+	u32 n_events = STARLINK_PMU_NUM_COUNTERS;
+	int idx;
+
+	/*
+	 * Cycle counter has dedicated register to hold counter value.
+	 * Event other than cycle count has to be enabled through
+	 * event select register, and assigned with independent counter
+	 * as they appear.
+	 */
+
+	if (hwc->config == STARLINK_CYCLES) {
+		idx = STARLINK_PMU_IDX_CYCLE_COUNTER;
+	} else {
+		idx = find_first_zero_bit(used_mask, n_events);
+		/* All counter are in use */
+		if (idx < 0)
+			return idx;
+
+		set_bit(idx, used_mask);
+	}
+
+	hwc->idx = idx;
+	hw_events->events[idx] = event;
+	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+
+	if (flags & PERF_EF_START)
+		starlink_pmu_start(event, PERF_EF_RELOAD);
+
+	perf_event_update_userpage(event);
+
+	return 0;
+}
+
+static void starlink_pmu_del(struct perf_event *event, int flags)
+{
+	struct starlink_pmu *starlink_pmu = to_starlink_pmu(event->pmu);
+	struct starlink_hw_events *hw_events =
+					this_cpu_ptr(starlink_pmu->hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+
+	starlink_pmu_stop(event, PERF_EF_UPDATE);
+	hw_events->events[hwc->idx] = NULL;
+	clear_bit(hwc->idx, hw_events->used_mask);
+
+	perf_event_update_userpage(event);
+}
+
+static bool starlink_pmu_validate_event_group(struct perf_event *event)
+{
+	struct perf_event *leader = event->group_leader;
+	struct perf_event *sibling;
+	int counter = 1;
+
+	/*
+	 * Ensure hardware events in the group are on the same PMU,
+	 * software events are acceptable.
+	 */
+	if (event->group_leader->pmu != event->pmu &&
+	    !is_software_event(event->group_leader))
+		return false;
+
+	for_each_sibling_event(sibling, leader) {
+		if (sibling->pmu != event->pmu && !is_software_event(sibling))
+			return false;
+
+		counter++;
+	}
+
+	return counter <= STARLINK_PMU_NUM_COUNTERS;
+}
+
+static int starlink_pmu_event_init(struct perf_event *event)
+{
+	struct starlink_pmu *starlink_pmu = to_starlink_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+
+	/*
+	 * Sampling is not supported, as counters are shared
+	 * by all CPU.
+	 */
+	if (hwc->sample_period)
+		return -EOPNOTSUPP;
+
+	/*
+	 * Per-task and attach to a task are not supported,
+	 * as uncore events are not specific to any CPU.
+	 */
+	if (event->cpu < 0 || event->attach_state & PERF_ATTACH_TASK)
+		return -EOPNOTSUPP;
+
+	if (!starlink_pmu_validate_event_group(event))
+		return -EINVAL;
+
+	hwc->idx = -1;
+	hwc->config = event->attr.config;
+	event->cpu = cpumask_first(&starlink_pmu->cpumask);
+
+	return 0;
+}
+
+static irqreturn_t starlink_pmu_handle_irq(int irq_num, void *data)
+{
+	struct starlink_pmu *starlink_pmu = data;
+	struct starlink_hw_events *hw_events =
+			this_cpu_ptr(starlink_pmu->hw_events);
+	bool handled = false;
+	int idx;
+	u64 overflow_status;
+
+	for (idx = 0; idx < STARLINK_PMU_MAX_COUNTERS; idx++) {
+		struct perf_event *event = hw_events->events[idx];
+
+		if (!event)
+			continue;
+
+		overflow_status = readq(starlink_pmu->pmu_base +
+					STARLINK_PMU_COUNTER_OVERFLOW_STATUS);
+		if (!(overflow_status & BIT_ULL(idx)))
+			continue;
+
+		writeq(BIT_ULL(idx), starlink_pmu->pmu_base +
+		       STARLINK_PMU_COUNTER_OVERFLOW_STATUS);
+
+		starlink_pmu_update(event);
+		starlink_pmu_set_event_period(event);
+		handled = true;
+	}
+	return IRQ_RETVAL(handled);
+}
+
+static int starlink_setup_irqs(struct starlink_pmu *starlink_pmu,
+			       struct platform_device *pdev)
+{
+	int ret, irq;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return -EINVAL;
+
+	ret = devm_request_irq(&pdev->dev, irq, starlink_pmu_handle_irq,
+			       0, STARLINK_PMU_PDEV_NAME, starlink_pmu);
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret, "Failed to request IRQ\n");
+
+	starlink_pmu->irq = irq;
+
+	return 0;
+}
+
+static int starlink_pmu_pm_notify(struct notifier_block *b,
+				  unsigned long cmd, void *v)
+{
+	struct starlink_pmu *starlink_pmu = container_of(b, struct starlink_pmu,
+							 starlink_pmu_pm_nb);
+	struct starlink_hw_events *hw_events =
+					this_cpu_ptr(starlink_pmu->hw_events);
+	int enabled = bitmap_weight(hw_events->used_mask,
+				    STARLINK_PMU_MAX_COUNTERS);
+	struct perf_event *event;
+	int idx;
+
+	if (!enabled)
+		return NOTIFY_OK;
+
+	for (idx = 0; idx < STARLINK_PMU_MAX_COUNTERS; idx++) {
+		event = hw_events->events[idx];
+		if (!event)
+			continue;
+
+		switch (cmd) {
+		case CPU_PM_ENTER:
+			/* Stop and update the counter */
+			starlink_pmu_stop(event, PERF_EF_UPDATE);
+			break;
+		case CPU_PM_EXIT:
+		case CPU_PM_ENTER_FAILED:
+			/* Restore and enable the counter */
+			starlink_pmu_start(event, PERF_EF_RELOAD);
+			break;
+		default:
+			break;
+		}
+	}
+
+	return NOTIFY_OK;
+}
+
+static int starlink_pmu_pm_register(struct starlink_pmu *starlink_pmu)
+{
+	if (!IS_ENABLED(CONFIG_CPU_PM))
+		return 0;
+
+	starlink_pmu->starlink_pmu_pm_nb.notifier_call = starlink_pmu_pm_notify;
+	return cpu_pm_register_notifier(&starlink_pmu->starlink_pmu_pm_nb);
+}
+
+static void starlink_pmu_pm_unregister(struct starlink_pmu *starlink_pmu)
+{
+	if (!IS_ENABLED(CONFIG_CPU_PM))
+		return;
+
+	cpu_pm_unregister_notifier(&starlink_pmu->starlink_pmu_pm_nb);
+}
+
+static void starlink_pmu_destroy(struct starlink_pmu *starlink_pmu)
+{
+	starlink_pmu_pm_unregister(starlink_pmu);
+	cpuhp_state_remove_instance(starlink_pmu_cpuhp_state,
+				    &starlink_pmu->node);
+}
+
+static int starlink_pmu_probe(struct platform_device *pdev)
+{
+	struct starlink_pmu *starlink_pmu;
+	struct starlink_hw_events *hw_events;
+	struct resource *res;
+	int cpuid, i, ret;
+
+	starlink_pmu = devm_kzalloc(&pdev->dev, sizeof(*starlink_pmu), GFP_KERNEL);
+	if (!starlink_pmu)
+		return -ENOMEM;
+
+	starlink_pmu->pmu_base =
+			devm_platform_get_and_ioremap_resource(pdev, 0, &res);
+	if (IS_ERR(starlink_pmu->pmu_base))
+		return PTR_ERR(starlink_pmu->pmu_base);
+
+	starlink_pmu->hw_events = alloc_percpu_gfp(struct starlink_hw_events,
+						   GFP_KERNEL);
+	if (!starlink_pmu->hw_events) {
+		dev_err(&pdev->dev, "Failed to allocate per-cpu PMU data\n");
+		return -ENOMEM;
+	}
+
+	for_each_possible_cpu(cpuid) {
+		hw_events = per_cpu_ptr(starlink_pmu->hw_events, cpuid);
+		for (i = 0; i < STARLINK_PMU_MAX_COUNTERS; i++)
+			hw_events->events[i] = NULL;
+	}
+
+	ret = starlink_setup_irqs(starlink_pmu, pdev);
+	if (ret)
+		return ret;
+
+	ret = cpuhp_state_add_instance(starlink_pmu_cpuhp_state,
+				       &starlink_pmu->node);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to register hotplug\n");
+		return ret;
+	}
+
+	ret = starlink_pmu_pm_register(starlink_pmu);
+	if (ret) {
+		cpuhp_state_remove_instance(starlink_pmu_cpuhp_state,
+					    &starlink_pmu->node);
+		return ret;
+	}
+
+	starlink_pmu->pmu = (struct pmu) {
+		.task_ctx_nr	= perf_invalid_context,
+		.event_init	= starlink_pmu_event_init,
+		.add		= starlink_pmu_add,
+		.del		= starlink_pmu_del,
+		.start		= starlink_pmu_start,
+		.stop		= starlink_pmu_stop,
+		.read		= starlink_pmu_update,
+		.attr_groups	= starlink_pmu_attr_groups,
+	};
+
+	ret = perf_pmu_register(&starlink_pmu->pmu, STARLINK_PMU_PDEV_NAME, -1);
+	if (ret)
+		starlink_pmu_destroy(starlink_pmu);
+
+	return ret;
+}
+
+static const struct of_device_id starlink_pmu_of_match[] = {
+	{ .compatible = "starfive,jh8100-starlink-pmu" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, starlink_pmu_of_match);
+
+static struct platform_driver starlink_pmu_driver = {
+	.driver = {
+		.name	= STARLINK_PMU_PDEV_NAME,
+		.of_match_table = starlink_pmu_of_match,
+		.suppress_bind_attrs = true,
+	},
+	.probe = starlink_pmu_probe,
+};
+
+static int
+starlink_pmu_online_cpu(unsigned int cpu, struct hlist_node *node)
+{
+	struct starlink_pmu *starlink_pmu = hlist_entry_safe(node,
+							     struct starlink_pmu,
+							     node);
+
+	if (cpumask_empty(&starlink_pmu->cpumask))
+		cpumask_set_cpu(cpu, &starlink_pmu->cpumask);
+
+	WARN_ON(irq_set_affinity(starlink_pmu->irq, cpumask_of(cpu)));
+
+	return 0;
+}
+
+static int
+starlink_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
+{
+	struct starlink_pmu *starlink_pmu = hlist_entry_safe(node,
+							     struct starlink_pmu,
+							     node);
+	unsigned int target;
+
+	if (!cpumask_test_and_clear_cpu(cpu, &starlink_pmu->cpumask))
+		return 0;
+
+	target = cpumask_any_but(cpu_online_mask, cpu);
+	if (target >= nr_cpu_ids)
+		return 0;
+
+	perf_pmu_migrate_context(&starlink_pmu->pmu, cpu, target);
+
+	cpumask_set_cpu(target, &starlink_pmu->cpumask);
+	WARN_ON(irq_set_affinity(starlink_pmu->irq, cpumask_of(target)));
+
+	return 0;
+}
+
+static int __init starlink_pmu_init(void)
+{
+	int ret;
+
+	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
+				      "soc/starfive/starlink_pmu:online",
+				      starlink_pmu_online_cpu,
+				      starlink_pmu_offline_cpu);
+	if (ret < 0)
+		return ret;
+
+	starlink_pmu_cpuhp_state = ret;
+
+	return platform_driver_register(&starlink_pmu_driver);
+}
+
+device_initcall(starlink_pmu_init);
diff --git a/drivers/perf/thunderx2_pmu.c b/drivers/perf/thunderx2_pmu.c
index 1edb9c03704f..e16d10c763de 100644
--- a/drivers/perf/thunderx2_pmu.c
+++ b/drivers/perf/thunderx2_pmu.c
@@ -993,7 +993,7 @@ static int tx2_uncore_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int tx2_uncore_remove(struct platform_device *pdev)
+static void tx2_uncore_remove(struct platform_device *pdev)
 {
 	struct tx2_uncore_pmu *tx2_pmu, *temp;
 	struct device *dev = &pdev->dev;
@@ -1009,7 +1009,6 @@ static int tx2_uncore_remove(struct platform_device *pdev)
 			}
 		}
 	}
-	return 0;
 }
 
 static struct platform_driver tx2_uncore_driver = {
@@ -1019,7 +1018,7 @@ static struct platform_driver tx2_uncore_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe = tx2_uncore_probe,
-	.remove = tx2_uncore_remove,
+	.remove_new = tx2_uncore_remove,
 };
 
 static int __init tx2_uncore_driver_init(void)
diff --git a/drivers/perf/xgene_pmu.c b/drivers/perf/xgene_pmu.c
index 7ce344248dda..0d49343d704b 100644
--- a/drivers/perf/xgene_pmu.c
+++ b/drivers/perf/xgene_pmu.c
@@ -1937,7 +1937,7 @@ xgene_pmu_dev_cleanup(struct xgene_pmu *xgene_pmu, struct list_head *pmus)
 	}
 }
 
-static int xgene_pmu_remove(struct platform_device *pdev)
+static void xgene_pmu_remove(struct platform_device *pdev)
 {
 	struct xgene_pmu *xgene_pmu = dev_get_drvdata(&pdev->dev);
 
@@ -1947,13 +1947,11 @@ static int xgene_pmu_remove(struct platform_device *pdev)
 	xgene_pmu_dev_cleanup(xgene_pmu, &xgene_pmu->mcpmus);
 	cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_APM_XGENE_ONLINE,
 				    &xgene_pmu->node);
-
-	return 0;
 }
 
 static struct platform_driver xgene_pmu_driver = {
 	.probe = xgene_pmu_probe,
-	.remove = xgene_pmu_remove,
+	.remove_new = xgene_pmu_remove,
 	.driver = {
 		.name		= "xgene-pmu",
 		.of_match_table = xgene_pmu_of_match,