23 files changed, 378 insertions, 106 deletions

diff --git a/drivers/perf/alibaba_uncore_drw_pmu.c b/drivers/perf/alibaba_uncore_drw_pmu.c
index a9277dcf90ce..89dd38343f93 100644
--- a/drivers/perf/alibaba_uncore_drw_pmu.c
+++ b/drivers/perf/alibaba_uncore_drw_pmu.c
@@ -709,6 +709,7 @@ static int ali_drw_pmu_probe(struct platform_device *pdev)
 
 	drw_pmu->pmu = (struct pmu) {
 		.module		= THIS_MODULE,
+		.parent		= &pdev->dev,
 		.task_ctx_nr	= perf_invalid_context,
 		.event_init	= ali_drw_pmu_event_init,
 		.add		= ali_drw_pmu_add,
@@ -746,18 +747,14 @@ static int ali_drw_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 	struct ali_drw_pmu_irq *irq;
 	struct ali_drw_pmu *drw_pmu;
 	unsigned int target;
-	int ret;
-	cpumask_t node_online_cpus;
 
 	irq = hlist_entry_safe(node, struct ali_drw_pmu_irq, node);
 	if (cpu != irq->cpu)
 		return 0;
 
-	ret = cpumask_and(&node_online_cpus,
-			  cpumask_of_node(cpu_to_node(cpu)), cpu_online_mask);
-	if (ret)
-		target = cpumask_any_but(&node_online_cpus, cpu);
-	else
+	target = cpumask_any_and_but(cpumask_of_node(cpu_to_node(cpu)),
+				     cpu_online_mask, cpu);
+	if (target >= nr_cpu_ids)
 		target = cpumask_any_but(cpu_online_mask, cpu);
 
 	if (target >= nr_cpu_ids)
diff --git a/drivers/perf/amlogic/meson_ddr_pmu_core.c b/drivers/perf/amlogic/meson_ddr_pmu_core.c
index bbc7285fd934..07446d784a1a 100644
--- a/drivers/perf/amlogic/meson_ddr_pmu_core.c
+++ b/drivers/perf/amlogic/meson_ddr_pmu_core.c
@@ -492,6 +492,7 @@ int meson_ddr_pmu_create(struct platform_device *pdev)
 	*pmu = (struct ddr_pmu) {
 		.pmu = {
 			.module		= THIS_MODULE,
+			.parent		= &pdev->dev,
 			.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 			.task_ctx_nr	= perf_invalid_context,
 			.attr_groups	= attr_groups,
diff --git a/drivers/perf/arm-cci.c b/drivers/perf/arm-cci.c
index 6be03f81ae5d..a7fd80677919 100644
--- a/drivers/perf/arm-cci.c
+++ b/drivers/perf/arm-cci.c
@@ -1409,6 +1409,7 @@ static int cci_pmu_init(struct cci_pmu *cci_pmu, struct platform_device *pdev)
 
 	cci_pmu->pmu = (struct pmu) {
 		.module		= THIS_MODULE,
+		.parent		= &pdev->dev,
 		.name		= cci_pmu->model->name,
 		.task_ctx_nr	= perf_invalid_context,
 		.pmu_enable	= cci_pmu_enable,
diff --git a/drivers/perf/arm-ccn.c b/drivers/perf/arm-ccn.c
index 641471bd5eff..f4495ff6525f 100644
--- a/drivers/perf/arm-ccn.c
+++ b/drivers/perf/arm-ccn.c
@@ -1265,6 +1265,7 @@ static int arm_ccn_pmu_init(struct arm_ccn *ccn)
 	/* Perf driver registration */
 	ccn->dt.pmu = (struct pmu) {
 		.module = THIS_MODULE,
+		.parent = ccn->dev,
 		.attr_groups = arm_ccn_pmu_attr_groups,
 		.task_ctx_nr = perf_invalid_context,
 		.event_init = arm_ccn_pmu_event_init,
diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c
index 7ef9c7e4836b..e26ad1d3ed0b 100644
--- a/drivers/perf/arm-cmn.c
+++ b/drivers/perf/arm-cmn.c
@@ -1950,20 +1950,20 @@ static int arm_cmn_pmu_offline_cpu(unsigned int cpu, struct hlist_node *cpuhp_no
 	struct arm_cmn *cmn;
 	unsigned int target;
 	int node;
-	cpumask_t mask;
 
 	cmn = hlist_entry_safe(cpuhp_node, struct arm_cmn, cpuhp_node);
 	if (cpu != cmn->cpu)
 		return 0;
 
 	node = dev_to_node(cmn->dev);
-	if (cpumask_and(&mask, cpumask_of_node(node), cpu_online_mask) &&
-	    cpumask_andnot(&mask, &mask, cpumask_of(cpu)))
-		target = cpumask_any(&mask);
-	else
+
+	target = cpumask_any_and_but(cpumask_of_node(node), cpu_online_mask, cpu);
+	if (target >= nr_cpu_ids)
 		target = cpumask_any_but(cpu_online_mask, cpu);
+
 	if (target < nr_cpu_ids)
 		arm_cmn_migrate(cmn, target);
+
 	return 0;
 }
 
@@ -2482,6 +2482,7 @@ static int arm_cmn_probe(struct platform_device *pdev)
 	cmn->cpu = cpumask_local_spread(0, dev_to_node(cmn->dev));
 	cmn->pmu = (struct pmu) {
 		.module = THIS_MODULE,
+		.parent = cmn->dev,
 		.attr_groups = arm_cmn_attr_groups,
 		.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
 		.task_ctx_nr = perf_invalid_context,
diff --git a/drivers/perf/arm_cspmu/arm_cspmu.c b/drivers/perf/arm_cspmu/arm_cspmu.c
index b9a252272f1e..ba0cf2f466ef 100644
--- a/drivers/perf/arm_cspmu/arm_cspmu.c
+++ b/drivers/perf/arm_cspmu/arm_cspmu.c
@@ -1206,6 +1206,7 @@ static int arm_cspmu_register_pmu(struct arm_cspmu *cspmu)
 	cspmu->pmu = (struct pmu){
 		.task_ctx_nr	= perf_invalid_context,
 		.module		= cspmu->impl.module,
+		.parent		= cspmu->dev,
 		.pmu_enable	= arm_cspmu_enable,
 		.pmu_disable	= arm_cspmu_disable,
 		.event_init	= arm_cspmu_event_init,
@@ -1322,8 +1323,7 @@ static int arm_cspmu_cpu_online(unsigned int cpu, struct hlist_node *node)
 
 static int arm_cspmu_cpu_teardown(unsigned int cpu, struct hlist_node *node)
 {
-	int dst;
-	struct cpumask online_supported;
+	unsigned int dst;
 
 	struct arm_cspmu *cspmu =
 		hlist_entry_safe(node, struct arm_cspmu, cpuhp_node);
@@ -1333,9 +1333,8 @@ static int arm_cspmu_cpu_teardown(unsigned int cpu, struct hlist_node *node)
 		return 0;
 
 	/* Choose a new CPU to migrate ownership of the PMU to */
-	cpumask_and(&online_supported, &cspmu->associated_cpus,
-		    cpu_online_mask);
-	dst = cpumask_any_but(&online_supported, cpu);
+	dst = cpumask_any_and_but(&cspmu->associated_cpus,
+				  cpu_online_mask, cpu);
 	if (dst >= nr_cpu_ids)
 		return 0;
 
diff --git a/drivers/perf/arm_dmc620_pmu.c b/drivers/perf/arm_dmc620_pmu.c
index 8a81be2dd5ec..2ec96e204c40 100644
--- a/drivers/perf/arm_dmc620_pmu.c
+++ b/drivers/perf/arm_dmc620_pmu.c
@@ -673,6 +673,7 @@ static int dmc620_pmu_device_probe(struct platform_device *pdev)
 
 	dmc620_pmu->pmu = (struct pmu) {
 		.module = THIS_MODULE,
+		.parent		= &pdev->dev,
 		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 		.task_ctx_nr	= perf_invalid_context,
 		.event_init	= dmc620_pmu_event_init,
diff --git a/drivers/perf/arm_dsu_pmu.c b/drivers/perf/arm_dsu_pmu.c
index bae3ca37f846..92248a24a1aa 100644
--- a/drivers/perf/arm_dsu_pmu.c
+++ b/drivers/perf/arm_dsu_pmu.c
@@ -230,15 +230,6 @@ static const struct attribute_group *dsu_pmu_attr_groups[] = {
 	NULL,
 };
 
-static int dsu_pmu_get_online_cpu_any_but(struct dsu_pmu *dsu_pmu, int cpu)
-{
-	struct cpumask online_supported;
-
-	cpumask_and(&online_supported,
-			 &dsu_pmu->associated_cpus, cpu_online_mask);
-	return cpumask_any_but(&online_supported, cpu);
-}
-
 static inline bool dsu_pmu_counter_valid(struct dsu_pmu *dsu_pmu, u32 idx)
 {
 	return (idx < dsu_pmu->num_counters) ||
@@ -751,6 +742,7 @@ static int dsu_pmu_device_probe(struct platform_device *pdev)
 
 	dsu_pmu->pmu = (struct pmu) {
 		.task_ctx_nr	= perf_invalid_context,
+		.parent		= &pdev->dev,
 		.module		= THIS_MODULE,
 		.pmu_enable	= dsu_pmu_enable,
 		.pmu_disable	= dsu_pmu_disable,
@@ -827,14 +819,16 @@ static int dsu_pmu_cpu_online(unsigned int cpu, struct hlist_node *node)
 
 static int dsu_pmu_cpu_teardown(unsigned int cpu, struct hlist_node *node)
 {
-	int dst;
-	struct dsu_pmu *dsu_pmu = hlist_entry_safe(node, struct dsu_pmu,
-						   cpuhp_node);
+	struct dsu_pmu *dsu_pmu;
+	unsigned int dst;
+
+	dsu_pmu = hlist_entry_safe(node, struct dsu_pmu, cpuhp_node);
 
 	if (!cpumask_test_and_clear_cpu(cpu, &dsu_pmu->active_cpu))
 		return 0;
 
-	dst = dsu_pmu_get_online_cpu_any_but(dsu_pmu, cpu);
+	dst = cpumask_any_and_but(&dsu_pmu->associated_cpus,
+				  cpu_online_mask, cpu);
 	/* If there are no active CPUs in the DSU, leave IRQ disabled */
 	if (dst >= nr_cpu_ids)
 		return 0;
diff --git a/drivers/perf/arm_pmu_platform.c b/drivers/perf/arm_pmu_platform.c
index 3596db36cbff..4b1a9a92ea11 100644
--- a/drivers/perf/arm_pmu_platform.c
+++ b/drivers/perf/arm_pmu_platform.c
@@ -196,6 +196,7 @@ int arm_pmu_device_probe(struct platform_device *pdev,
 	if (!pmu)
 		return -ENOMEM;
 
+	pmu->pmu.parent = &pdev->dev;
 	pmu->plat_device = pdev;
 
 	ret = pmu_parse_irqs(pmu);
diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c
index 719aa953a1c4..d5fa92ba8373 100644
--- a/drivers/perf/arm_smmuv3_pmu.c
+++ b/drivers/perf/arm_smmuv3_pmu.c
@@ -860,6 +860,7 @@ static int smmu_pmu_probe(struct platform_device *pdev)
 
 	smmu_pmu->pmu = (struct pmu) {
 		.module		= THIS_MODULE,
+		.parent		= &pdev->dev,
 		.task_ctx_nr    = perf_invalid_context,
 		.pmu_enable	= smmu_pmu_enable,
 		.pmu_disable	= smmu_pmu_disable,
diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c
index 35f0de03416f..9100d82bfabc 100644
--- a/drivers/perf/arm_spe_pmu.c
+++ b/drivers/perf/arm_spe_pmu.c
@@ -932,6 +932,7 @@ static int arm_spe_pmu_perf_init(struct arm_spe_pmu *spe_pmu)
 
 	spe_pmu->pmu = (struct pmu) {
 		.module = THIS_MODULE,
+		.parent		= &spe_pmu->pdev->dev,
 		.capabilities	= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE,
 		.attr_groups	= arm_spe_pmu_attr_groups,
 		/*
diff --git a/drivers/perf/dwc_pcie_pmu.c b/drivers/perf/dwc_pcie_pmu.c
index 957058ad0099..c5e328f23841 100644
--- a/drivers/perf/dwc_pcie_pmu.c
+++ b/drivers/perf/dwc_pcie_pmu.c
@@ -690,9 +690,8 @@ static int dwc_pcie_pmu_offline_cpu(unsigned int cpu, struct hlist_node *cpuhp_n
 {
 	struct dwc_pcie_pmu *pcie_pmu;
 	struct pci_dev *pdev;
-	int node;
-	cpumask_t mask;
 	unsigned int target;
+	int node;
 
 	pcie_pmu = hlist_entry_safe(cpuhp_node, struct dwc_pcie_pmu, cpuhp_node);
 	/* Nothing to do if this CPU doesn't own the PMU */
@@ -702,10 +701,9 @@ static int dwc_pcie_pmu_offline_cpu(unsigned int cpu, struct hlist_node *cpuhp_n
 	pcie_pmu->on_cpu = -1;
 	pdev = pcie_pmu->pdev;
 	node = dev_to_node(&pdev->dev);
-	if (cpumask_and(&mask, cpumask_of_node(node), cpu_online_mask) &&
-	    cpumask_andnot(&mask, &mask, cpumask_of(cpu)))
-		target = cpumask_any(&mask);
-	else
+
+	target = cpumask_any_and_but(cpumask_of_node(node), cpu_online_mask, cpu);
+	if (target >= nr_cpu_ids)
 		target = cpumask_any_but(cpu_online_mask, cpu);
 
 	if (target >= nr_cpu_ids) {
diff --git a/drivers/perf/fsl_imx8_ddr_perf.c b/drivers/perf/fsl_imx8_ddr_perf.c
index 4e8fa5a48fcf..1bbdb29743c4 100644
--- a/drivers/perf/fsl_imx8_ddr_perf.c
+++ b/drivers/perf/fsl_imx8_ddr_perf.c
@@ -651,6 +651,7 @@ static int ddr_perf_init(struct ddr_pmu *pmu, void __iomem *base,
 	*pmu = (struct ddr_pmu) {
 		.pmu = (struct pmu) {
 			.module	      = THIS_MODULE,
+			.parent      = dev,
 			.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
 			.task_ctx_nr = perf_invalid_context,
 			.attr_groups = attr_groups,
diff --git a/drivers/perf/hisilicon/hisi_pcie_pmu.c b/drivers/perf/hisilicon/hisi_pcie_pmu.c
index 5d1f0e9fdb08..03c506aa3853 100644
--- a/drivers/perf/hisilicon/hisi_pcie_pmu.c
+++ b/drivers/perf/hisilicon/hisi_pcie_pmu.c
@@ -350,15 +350,27 @@ static bool hisi_pcie_pmu_validate_event_group(struct perf_event *event)
 			return false;
 
 		for (num = 0; num < counters; num++) {
+			/*
+			 * If we find a related event, then it's a valid group
+			 * since we don't need to allocate a new counter for it.
+			 */
 			if (hisi_pcie_pmu_cmp_event(event_group[num], sibling))
 				break;
 		}
 
+		/*
+		 * Otherwise it's a new event but if there's no available counter,
+		 * fail the check since we cannot schedule all the events in
+		 * the group simultaneously.
+		 */
+		if (num == HISI_PCIE_MAX_COUNTERS)
+			return false;
+
 		if (num == counters)
 			event_group[counters++] = sibling;
 	}
 
-	return counters <= HISI_PCIE_MAX_COUNTERS;
+	return true;
 }
 
 static int hisi_pcie_pmu_event_init(struct perf_event *event)
@@ -673,7 +685,6 @@ static int hisi_pcie_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 {
 	struct hisi_pcie_pmu *pcie_pmu = hlist_entry_safe(node, struct hisi_pcie_pmu, node);
 	unsigned int target;
-	cpumask_t mask;
 	int numa_node;
 
 	/* Nothing to do if this CPU doesn't own the PMU */
@@ -684,10 +695,10 @@ static int hisi_pcie_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 
 	/* Choose a local CPU from all online cpus. */
 	numa_node = dev_to_node(&pcie_pmu->pdev->dev);
-	if (cpumask_and(&mask, cpumask_of_node(numa_node), cpu_online_mask) &&
-	    cpumask_andnot(&mask, &mask, cpumask_of(cpu)))
-		target = cpumask_any(&mask);
-	else
+
+	target = cpumask_any_and_but(cpumask_of_node(numa_node),
+				     cpu_online_mask, cpu);
+	if (target >= nr_cpu_ids)
 		target = cpumask_any_but(cpu_online_mask, cpu);
 
 	if (target >= nr_cpu_ids) {
@@ -807,6 +818,7 @@ static int hisi_pcie_alloc_pmu(struct pci_dev *pdev, struct hisi_pcie_pmu *pcie_
 	pcie_pmu->pmu = (struct pmu) {
 		.name		= name,
 		.module		= THIS_MODULE,
+		.parent		= &pdev->dev,
 		.event_init	= hisi_pcie_pmu_event_init,
 		.pmu_enable	= hisi_pcie_pmu_enable,
 		.pmu_disable	= hisi_pcie_pmu_disable,
diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pmu.c
index 04031450d5fe..a60e4c966098 100644
--- a/drivers/perf/hisilicon/hisi_uncore_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_pmu.c
@@ -504,7 +504,6 @@ int hisi_uncore_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 {
 	struct hisi_pmu *hisi_pmu = hlist_entry_safe(node, struct hisi_pmu,
 						     node);
-	cpumask_t pmu_online_cpus;
 	unsigned int target;
 
 	if (!cpumask_test_and_clear_cpu(cpu, &hisi_pmu->associated_cpus))
@@ -518,9 +517,8 @@ int hisi_uncore_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 	hisi_pmu->on_cpu = -1;
 
 	/* Choose a new CPU to migrate ownership of the PMU to */
-	cpumask_and(&pmu_online_cpus, &hisi_pmu->associated_cpus,
-		    cpu_online_mask);
-	target = cpumask_any_but(&pmu_online_cpus, cpu);
+	target = cpumask_any_and_but(&hisi_pmu->associated_cpus,
+				     cpu_online_mask, cpu);
 	if (target >= nr_cpu_ids)
 		return 0;
 
@@ -538,6 +536,7 @@ void hisi_pmu_init(struct hisi_pmu *hisi_pmu, struct module *module)
 	struct pmu *pmu = &hisi_pmu->pmu;
 
 	pmu->module             = module;
+	pmu->parent             = hisi_pmu->dev;
 	pmu->task_ctx_nr        = perf_invalid_context;
 	pmu->event_init         = hisi_uncore_pmu_event_init;
 	pmu->pmu_enable         = hisi_uncore_pmu_enable;
diff --git a/drivers/perf/hisilicon/hns3_pmu.c b/drivers/perf/hisilicon/hns3_pmu.c
index 16869bf5bf4c..e900f8e00b18 100644
--- a/drivers/perf/hisilicon/hns3_pmu.c
+++ b/drivers/perf/hisilicon/hns3_pmu.c
@@ -1085,15 +1085,27 @@ static bool hns3_pmu_validate_event_group(struct perf_event *event)
 			return false;
 
 		for (num = 0; num < counters; num++) {
+			/*
+			 * If we find a related event, then it's a valid group
+			 * since we don't need to allocate a new counter for it.
+			 */
 			if (hns3_pmu_cmp_event(event_group[num], sibling))
 				break;
 		}
 
+		/*
+		 * Otherwise it's a new event but if there's no available counter,
+		 * fail the check since we cannot schedule all the events in
+		 * the group simultaneously.
+		 */
+		if (num == HNS3_PMU_MAX_HW_EVENTS)
+			return false;
+
 		if (num == counters)
 			event_group[counters++] = sibling;
 	}
 
-	return counters <= HNS3_PMU_MAX_HW_EVENTS;
+	return true;
 }
 
 static u32 hns3_pmu_get_filter_condition(struct perf_event *event)
@@ -1419,6 +1431,7 @@ static int hns3_pmu_alloc_pmu(struct pci_dev *pdev, struct hns3_pmu *hns3_pmu)
 	hns3_pmu->pmu = (struct pmu) {
 		.name		= name,
 		.module		= THIS_MODULE,
+		.parent		= &pdev->dev,
 		.event_init	= hns3_pmu_event_init,
 		.pmu_enable	= hns3_pmu_enable,
 		.pmu_disable	= hns3_pmu_disable,
@@ -1515,7 +1528,7 @@ static int hns3_pmu_irq_register(struct pci_dev *pdev,
 		return ret;
 	}
 
-	ret = devm_add_action(&pdev->dev, hns3_pmu_free_irq, pdev);
+	ret = devm_add_action_or_reset(&pdev->dev, hns3_pmu_free_irq, pdev);
 	if (ret) {
 		pci_err(pdev, "failed to add free irq action, ret = %d.\n", ret);
 		return ret;
diff --git a/drivers/perf/qcom_l2_pmu.c b/drivers/perf/qcom_l2_pmu.c
index 148df5ae8ef8..980e3051edd7 100644
--- a/drivers/perf/qcom_l2_pmu.c
+++ b/drivers/perf/qcom_l2_pmu.c
@@ -801,9 +801,8 @@ static int l2cache_pmu_online_cpu(unsigned int cpu, struct hlist_node *node)
 
 static int l2cache_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 {
-	struct cluster_pmu *cluster;
 	struct l2cache_pmu *l2cache_pmu;
-	cpumask_t cluster_online_cpus;
+	struct cluster_pmu *cluster;
 	unsigned int target;
 
 	l2cache_pmu = hlist_entry_safe(node, struct l2cache_pmu, node);
@@ -820,9 +819,8 @@ static int l2cache_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 	cluster->on_cpu = -1;
 
 	/* Any other CPU for this cluster which is still online */
-	cpumask_and(&cluster_online_cpus, &cluster->cluster_cpus,
-		    cpu_online_mask);
-	target = cpumask_any_but(&cluster_online_cpus, cpu);
+	target = cpumask_any_and_but(&cluster->cluster_cpus,
+				     cpu_online_mask, cpu);
 	if (target >= nr_cpu_ids) {
 		disable_irq(cluster->irq);
 		return 0;
@@ -904,6 +902,7 @@ static int l2_cache_pmu_probe(struct platform_device *pdev)
 	l2cache_pmu->pmu = (struct pmu) {
 		/* suffix is instance id for future use with multiple sockets */
 		.name		= "l2cache_0",
+		.parent		= &pdev->dev,
 		.task_ctx_nr    = perf_invalid_context,
 		.pmu_enable	= l2_cache_pmu_enable,
 		.pmu_disable	= l2_cache_pmu_disable,
diff --git a/drivers/perf/qcom_l3_pmu.c b/drivers/perf/qcom_l3_pmu.c
index f16783d03db7..37786e88514e 100644
--- a/drivers/perf/qcom_l3_pmu.c
+++ b/drivers/perf/qcom_l3_pmu.c
@@ -748,6 +748,7 @@ static int qcom_l3_cache_pmu_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	l3pmu->pmu = (struct pmu) {
+		.parent		= &pdev->dev,
 		.task_ctx_nr	= perf_invalid_context,
 
 		.pmu_enable	= qcom_l3_cache__pmu_enable,
diff --git a/drivers/perf/riscv_pmu.c b/drivers/perf/riscv_pmu.c
index c78a6fd6c57f..78c490e0505a 100644
--- a/drivers/perf/riscv_pmu.c
+++ b/drivers/perf/riscv_pmu.c
@@ -191,8 +191,6 @@ void riscv_pmu_stop(struct perf_event *event, int flags)
 	struct hw_perf_event *hwc = &event->hw;
 	struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu);
 
-	WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
-
 	if (!(hwc->state & PERF_HES_STOPPED)) {
 		if (rvpmu->ctr_stop) {
 			rvpmu->ctr_stop(event, 0);
@@ -313,6 +311,10 @@ static int riscv_pmu_event_init(struct perf_event *event)
 	u64 event_config = 0;
 	uint64_t cmask;
 
+	/* driver does not support branch stack sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	hwc->flags = 0;
 	mapped_event = rvpmu->event_map(event, &event_config);
 	if (mapped_event < 0) {
@@ -404,6 +406,7 @@ struct riscv_pmu *riscv_pmu_alloc(void)
 		cpuc->n_events = 0;
 		for (i = 0; i < RISCV_MAX_COUNTERS; i++)
 			cpuc->events[i] = NULL;
+		cpuc->snapshot_addr = NULL;
 	}
 	pmu->pmu = (struct pmu) {
 		.event_init	= riscv_pmu_event_init,
diff --git a/drivers/perf/riscv_pmu_legacy.c b/drivers/perf/riscv_pmu_legacy.c
index fa0bccf4edf2..04487ad7fba0 100644
--- a/drivers/perf/riscv_pmu_legacy.c
+++ b/drivers/perf/riscv_pmu_legacy.c
@@ -136,6 +136,7 @@ static int pmu_legacy_device_probe(struct platform_device *pdev)
 	pmu = riscv_pmu_alloc();
 	if (!pmu)
 		return -ENOMEM;
+	pmu->pmu.parent = &pdev->dev;
 	pmu_legacy_init(pmu);
 
 	return 0;
diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c
index 8cbe6e5f9c39..a2e4005e1fd0 100644
--- a/drivers/perf/riscv_pmu_sbi.c
+++ b/drivers/perf/riscv_pmu_sbi.c
@@ -27,7 +27,7 @@
 
 #define ALT_SBI_PMU_OVERFLOW(__ovl)					\
 asm volatile(ALTERNATIVE_2(						\
-	"csrr %0, " __stringify(CSR_SSCOUNTOVF),			\
+	"csrr %0, " __stringify(CSR_SCOUNTOVF),				\
 	"csrr %0, " __stringify(THEAD_C9XX_CSR_SCOUNTEROF),		\
 		THEAD_VENDOR_ID, ERRATA_THEAD_PMU,			\
 		CONFIG_ERRATA_THEAD_PMU,				\
@@ -57,6 +57,11 @@ asm volatile(ALTERNATIVE(						\
 PMU_FORMAT_ATTR(event, "config:0-47");
 PMU_FORMAT_ATTR(firmware, "config:63");
 
+static bool sbi_v2_available;
+static DEFINE_STATIC_KEY_FALSE(sbi_pmu_snapshot_available);
+#define sbi_pmu_snapshot_available() \
+	static_branch_unlikely(&sbi_pmu_snapshot_available)
+
 static struct attribute *riscv_arch_formats_attr[] = {
 	&format_attr_event.attr,
 	&format_attr_firmware.attr,
@@ -384,7 +389,7 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event)
 			cmask = 1;
 		} else if (event->attr.config == PERF_COUNT_HW_INSTRUCTIONS) {
 			cflags |= SBI_PMU_CFG_FLAG_SKIP_MATCH;
-			cmask = 1UL << (CSR_INSTRET - CSR_CYCLE);
+			cmask = BIT(CSR_INSTRET - CSR_CYCLE);
 		}
 	}
 
@@ -506,24 +511,126 @@ static int pmu_sbi_event_map(struct perf_event *event, u64 *econfig)
 	return ret;
 }
 
+static void pmu_sbi_snapshot_free(struct riscv_pmu *pmu)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct cpu_hw_events *cpu_hw_evt = per_cpu_ptr(pmu->hw_events, cpu);
+
+		if (!cpu_hw_evt->snapshot_addr)
+			continue;
+
+		free_page((unsigned long)cpu_hw_evt->snapshot_addr);
+		cpu_hw_evt->snapshot_addr = NULL;
+		cpu_hw_evt->snapshot_addr_phys = 0;
+	}
+}
+
+static int pmu_sbi_snapshot_alloc(struct riscv_pmu *pmu)
+{
+	int cpu;
+	struct page *snapshot_page;
+
+	for_each_possible_cpu(cpu) {
+		struct cpu_hw_events *cpu_hw_evt = per_cpu_ptr(pmu->hw_events, cpu);
+
+		snapshot_page = alloc_page(GFP_ATOMIC | __GFP_ZERO);
+		if (!snapshot_page) {
+			pmu_sbi_snapshot_free(pmu);
+			return -ENOMEM;
+		}
+		cpu_hw_evt->snapshot_addr = page_to_virt(snapshot_page);
+		cpu_hw_evt->snapshot_addr_phys = page_to_phys(snapshot_page);
+	}
+
+	return 0;
+}
+
+static int pmu_sbi_snapshot_disable(void)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_SNAPSHOT_SET_SHMEM, SBI_SHMEM_DISABLE,
+			SBI_SHMEM_DISABLE, 0, 0, 0, 0);
+	if (ret.error) {
+		pr_warn("failed to disable snapshot shared memory\n");
+		return sbi_err_map_linux_errno(ret.error);
+	}
+
+	return 0;
+}
+
+static int pmu_sbi_snapshot_setup(struct riscv_pmu *pmu, int cpu)
+{
+	struct cpu_hw_events *cpu_hw_evt;
+	struct sbiret ret = {0};
+
+	cpu_hw_evt = per_cpu_ptr(pmu->hw_events, cpu);
+	if (!cpu_hw_evt->snapshot_addr_phys)
+		return -EINVAL;
+
+	if (cpu_hw_evt->snapshot_set_done)
+		return 0;
+
+	if (IS_ENABLED(CONFIG_32BIT))
+		ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_SNAPSHOT_SET_SHMEM,
+				cpu_hw_evt->snapshot_addr_phys,
+				(u64)(cpu_hw_evt->snapshot_addr_phys) >> 32, 0, 0, 0, 0);
+	else
+		ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_SNAPSHOT_SET_SHMEM,
+				cpu_hw_evt->snapshot_addr_phys, 0, 0, 0, 0, 0);
+
+	/* Free up the snapshot area memory and fall back to SBI PMU calls without snapshot */
+	if (ret.error) {
+		if (ret.error != SBI_ERR_NOT_SUPPORTED)
+			pr_warn("pmu snapshot setup failed with error %ld\n", ret.error);
+		return sbi_err_map_linux_errno(ret.error);
+	}
+
+	memset(cpu_hw_evt->snapshot_cval_shcopy, 0, sizeof(u64) * RISCV_MAX_COUNTERS);
+	cpu_hw_evt->snapshot_set_done = true;
+
+	return 0;
+}
+
 static u64 pmu_sbi_ctr_read(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 	struct sbiret ret;
-	union sbi_pmu_ctr_info info;
 	u64 val = 0;
+	struct riscv_pmu *pmu = to_riscv_pmu(event->pmu);
+	struct cpu_hw_events *cpu_hw_evt = this_cpu_ptr(pmu->hw_events);
+	struct riscv_pmu_snapshot_data *sdata = cpu_hw_evt->snapshot_addr;
+	union sbi_pmu_ctr_info info = pmu_ctr_list[idx];
+
+	/* Read the value from the shared memory directly only if counter is stopped */
+	if (sbi_pmu_snapshot_available() && (hwc->state & PERF_HES_STOPPED)) {
+		val = sdata->ctr_values[idx];
+		return val;
+	}
 
 	if (pmu_sbi_is_fw_event(event)) {
 		ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_FW_READ,
 				hwc->idx, 0, 0, 0, 0, 0);
-		if (!ret.error)
-			val = ret.value;
+		if (ret.error)
+			return 0;
+
+		val = ret.value;
+		if (IS_ENABLED(CONFIG_32BIT) && sbi_v2_available && info.width >= 32) {
+			ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_FW_READ_HI,
+					hwc->idx, 0, 0, 0, 0, 0);
+			if (!ret.error)
+				val |= ((u64)ret.value << 32);
+			else
+				WARN_ONCE(1, "Unable to read upper 32 bits of firmware counter error: %ld\n",
+					  ret.error);
+		}
 	} else {
-		info = pmu_ctr_list[idx];
 		val = riscv_pmu_ctr_read_csr(info.csr);
 		if (IS_ENABLED(CONFIG_32BIT))
-			val = ((u64)riscv_pmu_ctr_read_csr(info.csr + 0x80)) << 31 | val;
+			val |= ((u64)riscv_pmu_ctr_read_csr(info.csr + 0x80)) << 32;
 	}
 
 	return val;
@@ -553,6 +660,7 @@ static void pmu_sbi_ctr_start(struct perf_event *event, u64 ival)
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned long flag = SBI_PMU_START_FLAG_SET_INIT_VALUE;
 
+	/* There is no benefit setting SNAPSHOT FLAG for a single counter */
 #if defined(CONFIG_32BIT)
 	ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_START, hwc->idx,
 			1, flag, ival, ival >> 32, 0);
@@ -573,16 +681,36 @@ static void pmu_sbi_ctr_stop(struct perf_event *event, unsigned long flag)
 {
 	struct sbiret ret;
 	struct hw_perf_event *hwc = &event->hw;
+	struct riscv_pmu *pmu = to_riscv_pmu(event->pmu);
+	struct cpu_hw_events *cpu_hw_evt = this_cpu_ptr(pmu->hw_events);
+	struct riscv_pmu_snapshot_data *sdata = cpu_hw_evt->snapshot_addr;
 
 	if ((hwc->flags & PERF_EVENT_FLAG_USER_ACCESS) &&
 	    (hwc->flags & PERF_EVENT_FLAG_USER_READ_CNT))
 		pmu_sbi_reset_scounteren((void *)event);
 
+	if (sbi_pmu_snapshot_available())
+		flag |= SBI_PMU_STOP_FLAG_TAKE_SNAPSHOT;
+
 	ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP, hwc->idx, 1, flag, 0, 0, 0);
-	if (ret.error && (ret.error != SBI_ERR_ALREADY_STOPPED) &&
-		flag != SBI_PMU_STOP_FLAG_RESET)
+	if (!ret.error && sbi_pmu_snapshot_available()) {
+		/*
+		 * The counter snapshot is based on the index base specified by hwc->idx.
+		 * The actual counter value is updated in shared memory at index 0 when counter
+		 * mask is 0x01. To ensure accurate counter values, it's necessary to transfer
+		 * the counter value to shared memory. However, if hwc->idx is zero, the counter
+		 * value is already correctly updated in shared memory, requiring no further
+		 * adjustment.
+		 */
+		if (hwc->idx > 0) {
+			sdata->ctr_values[hwc->idx] = sdata->ctr_values[0];
+			sdata->ctr_values[0] = 0;
+		}
+	} else if (ret.error && (ret.error != SBI_ERR_ALREADY_STOPPED) &&
+		flag != SBI_PMU_STOP_FLAG_RESET) {
 		pr_err("Stopping counter idx %d failed with error %d\n",
 			hwc->idx, sbi_err_map_linux_errno(ret.error));
+	}
 }
 
 static int pmu_sbi_find_num_ctrs(void)
@@ -640,10 +768,39 @@ static inline void pmu_sbi_stop_all(struct riscv_pmu *pmu)
 static inline void pmu_sbi_stop_hw_ctrs(struct riscv_pmu *pmu)
 {
 	struct cpu_hw_events *cpu_hw_evt = this_cpu_ptr(pmu->hw_events);
+	struct riscv_pmu_snapshot_data *sdata = cpu_hw_evt->snapshot_addr;
+	unsigned long flag = 0;
+	int i, idx;
+	struct sbiret ret;
+	u64 temp_ctr_overflow_mask = 0;
+
+	if (sbi_pmu_snapshot_available())
+		flag = SBI_PMU_STOP_FLAG_TAKE_SNAPSHOT;
+
+	/* Reset the shadow copy to avoid save/restore any value from previous overflow */
+	memset(cpu_hw_evt->snapshot_cval_shcopy, 0, sizeof(u64) * RISCV_MAX_COUNTERS);
+
+	for (i = 0; i < BITS_TO_LONGS(RISCV_MAX_COUNTERS); i++) {
+		/* No need to check the error here as we can't do anything about the error */
+		ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP, i * BITS_PER_LONG,
+				cpu_hw_evt->used_hw_ctrs[i], flag, 0, 0, 0);
+		if (!ret.error && sbi_pmu_snapshot_available()) {
+			/* Save the counter values to avoid clobbering */
+			for_each_set_bit(idx, &cpu_hw_evt->used_hw_ctrs[i], BITS_PER_LONG)
+				cpu_hw_evt->snapshot_cval_shcopy[i * BITS_PER_LONG + idx] =
+							sdata->ctr_values[idx];
+			/* Save the overflow mask to avoid clobbering */
+			temp_ctr_overflow_mask |= sdata->ctr_overflow_mask << (i * BITS_PER_LONG);
+		}
+	}
 
-	/* No need to check the error here as we can't do anything about the error */
-	sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP, 0,
-		  cpu_hw_evt->used_hw_ctrs[0], 0, 0, 0, 0);
+	/* Restore the counter values to the shared memory for used hw counters */
+	if (sbi_pmu_snapshot_available()) {
+		for_each_set_bit(idx, cpu_hw_evt->used_hw_ctrs, RISCV_MAX_COUNTERS)
+			sdata->ctr_values[idx] = cpu_hw_evt->snapshot_cval_shcopy[idx];
+		if (temp_ctr_overflow_mask)
+			sdata->ctr_overflow_mask = temp_ctr_overflow_mask;
+	}
 }
 
 /*
@@ -652,11 +809,10 @@ static inline void pmu_sbi_stop_hw_ctrs(struct riscv_pmu *pmu)
  * while the overflowed counters need to be started with updated initialization
  * value.
  */
-static inline void pmu_sbi_start_overflow_mask(struct riscv_pmu *pmu,
-					       unsigned long ctr_ovf_mask)
+static inline void pmu_sbi_start_ovf_ctrs_sbi(struct cpu_hw_events *cpu_hw_evt,
+					      u64 ctr_ovf_mask)
 {
-	int idx = 0;
-	struct cpu_hw_events *cpu_hw_evt = this_cpu_ptr(pmu->hw_events);
+	int idx = 0, i;
 	struct perf_event *event;
 	unsigned long flag = SBI_PMU_START_FLAG_SET_INIT_VALUE;
 	unsigned long ctr_start_mask = 0;
@@ -664,11 +820,12 @@ static inline void pmu_sbi_start_overflow_mask(struct riscv_pmu *pmu,
 	struct hw_perf_event *hwc;
 	u64 init_val = 0;
 
-	ctr_start_mask = cpu_hw_evt->used_hw_ctrs[0] & ~ctr_ovf_mask;
-
-	/* Start all the counters that did not overflow in a single shot */
-	sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_START, 0, ctr_start_mask,
-		  0, 0, 0, 0);
+	for (i = 0; i < BITS_TO_LONGS(RISCV_MAX_COUNTERS); i++) {
+		ctr_start_mask = cpu_hw_evt->used_hw_ctrs[i] & ~ctr_ovf_mask;
+		/* Start all the counters that did not overflow in a single shot */
+		sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_START, i * BITS_PER_LONG, ctr_start_mask,
+			0, 0, 0, 0);
+	}
 
 	/* Reinitialize and start all the counter that overflowed */
 	while (ctr_ovf_mask) {
@@ -691,6 +848,52 @@ static inline void pmu_sbi_start_overflow_mask(struct riscv_pmu *pmu,
 	}
 }
 
+static inline void pmu_sbi_start_ovf_ctrs_snapshot(struct cpu_hw_events *cpu_hw_evt,
+						   u64 ctr_ovf_mask)
+{
+	int i, idx = 0;
+	struct perf_event *event;
+	unsigned long flag = SBI_PMU_START_FLAG_INIT_SNAPSHOT;
+	u64 max_period, init_val = 0;
+	struct hw_perf_event *hwc;
+	struct riscv_pmu_snapshot_data *sdata = cpu_hw_evt->snapshot_addr;
+
+	for_each_set_bit(idx, cpu_hw_evt->used_hw_ctrs, RISCV_MAX_COUNTERS) {
+		if (ctr_ovf_mask & BIT(idx)) {
+			event = cpu_hw_evt->events[idx];
+			hwc = &event->hw;
+			max_period = riscv_pmu_ctr_get_width_mask(event);
+			init_val = local64_read(&hwc->prev_count) & max_period;
+			cpu_hw_evt->snapshot_cval_shcopy[idx] = init_val;
+		}
+		/*
+		 * We do not need to update the non-overflow counters the previous
+		 * value should have been there already.
+		 */
+	}
+
+	for (i = 0; i < BITS_TO_LONGS(RISCV_MAX_COUNTERS); i++) {
+		/* Restore the counter values to relative indices for used hw counters */
+		for_each_set_bit(idx, &cpu_hw_evt->used_hw_ctrs[i], BITS_PER_LONG)
+			sdata->ctr_values[idx] =
+					cpu_hw_evt->snapshot_cval_shcopy[idx + i * BITS_PER_LONG];
+		/* Start all the counters in a single shot */
+		sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_START, idx * BITS_PER_LONG,
+			  cpu_hw_evt->used_hw_ctrs[i], flag, 0, 0, 0);
+	}
+}
+
+static void pmu_sbi_start_overflow_mask(struct riscv_pmu *pmu,
+					u64 ctr_ovf_mask)
+{
+	struct cpu_hw_events *cpu_hw_evt = this_cpu_ptr(pmu->hw_events);
+
+	if (sbi_pmu_snapshot_available())
+		pmu_sbi_start_ovf_ctrs_snapshot(cpu_hw_evt, ctr_ovf_mask);
+	else
+		pmu_sbi_start_ovf_ctrs_sbi(cpu_hw_evt, ctr_ovf_mask);
+}
+
 static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev)
 {
 	struct perf_sample_data data;
@@ -700,10 +903,11 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev)
 	int lidx, hidx, fidx;
 	struct riscv_pmu *pmu;
 	struct perf_event *event;
-	unsigned long overflow;
-	unsigned long overflowed_ctrs = 0;
+	u64 overflow;
+	u64 overflowed_ctrs = 0;
 	struct cpu_hw_events *cpu_hw_evt = dev;
 	u64 start_clock = sched_clock();
+	struct riscv_pmu_snapshot_data *sdata = cpu_hw_evt->snapshot_addr;
 
 	if (WARN_ON_ONCE(!cpu_hw_evt))
 		return IRQ_NONE;
@@ -725,7 +929,10 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev)
 	pmu_sbi_stop_hw_ctrs(pmu);
 
 	/* Overflow status register should only be read after counter are stopped */
-	ALT_SBI_PMU_OVERFLOW(overflow);
+	if (sbi_pmu_snapshot_available())
+		overflow = sdata->ctr_overflow_mask;
+	else
+		ALT_SBI_PMU_OVERFLOW(overflow);
 
 	/*
 	 * Overflow interrupt pending bit should only be cleared after stopping
@@ -751,9 +958,14 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev)
 		if (!info || info->type != SBI_PMU_CTR_TYPE_HW)
 			continue;
 
-		/* compute hardware counter index */
-		hidx = info->csr - CSR_CYCLE;
-		/* check if the corresponding bit is set in sscountovf */
+		if (sbi_pmu_snapshot_available())
+			/* SBI implementation already updated the logical indicies */
+			hidx = lidx;
+		else
+			/* compute hardware counter index */
+			hidx = info->csr - CSR_CYCLE;
+
+		/* check if the corresponding bit is set in sscountovf or overflow mask in shmem */
 		if (!(overflow & BIT(hidx)))
 			continue;
 
@@ -763,7 +975,10 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev)
 		 */
 		overflowed_ctrs |= BIT(lidx);
 		hw_evt = &event->hw;
+		/* Update the event states here so that we know the state while reading */
+		hw_evt->state |= PERF_HES_STOPPED;
 		riscv_pmu_event_update(event);
+		hw_evt->state |= PERF_HES_UPTODATE;
 		perf_sample_data_init(&data, 0, hw_evt->last_period);
 		if (riscv_pmu_event_set_period(event)) {
 			/*
@@ -776,6 +991,8 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev)
 			 */
 			perf_event_overflow(event, &data, regs);
 		}
+		/* Reset the state as we are going to start the counter after the loop */
+		hw_evt->state = 0;
 	}
 
 	pmu_sbi_start_overflow_mask(pmu, overflowed_ctrs);
@@ -807,6 +1024,9 @@ static int pmu_sbi_starting_cpu(unsigned int cpu, struct hlist_node *node)
 		enable_percpu_irq(riscv_pmu_irq, IRQ_TYPE_NONE);
 	}
 
+	if (sbi_pmu_snapshot_available())
+		return pmu_sbi_snapshot_setup(pmu, cpu);
+
 	return 0;
 }
 
@@ -819,6 +1039,9 @@ static int pmu_sbi_dying_cpu(unsigned int cpu, struct hlist_node *node)
 	/* Disable all counters access for user mode now */
 	csr_write(CSR_SCOUNTEREN, 0x0);
 
+	if (sbi_pmu_snapshot_available())
+		return pmu_sbi_snapshot_disable();
+
 	return 0;
 }
 
@@ -927,6 +1150,12 @@ static inline void riscv_pm_pmu_unregister(struct riscv_pmu *pmu) { }
 
 static void riscv_pmu_destroy(struct riscv_pmu *pmu)
 {
+	if (sbi_v2_available) {
+		if (sbi_pmu_snapshot_available()) {
+			pmu_sbi_snapshot_disable();
+			pmu_sbi_snapshot_free(pmu);
+		}
+	}
 	riscv_pm_pmu_unregister(pmu);
 	cpuhp_state_remove_instance(CPUHP_AP_PERF_RISCV_STARTING, &pmu->node);
 }
@@ -1043,7 +1272,6 @@ static struct ctl_table sbi_pmu_sysctl_table[] = {
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= SYSCTL_TWO,
 	},
-	{ }
 };
 
 static int pmu_sbi_device_probe(struct platform_device *pdev)
@@ -1081,6 +1309,7 @@ static int pmu_sbi_device_probe(struct platform_device *pdev)
 	}
 
 	pmu->pmu.attr_groups = riscv_pmu_attr_groups;
+	pmu->pmu.parent = &pdev->dev;
 	pmu->cmask = cmask;
 	pmu->ctr_start = pmu_sbi_ctr_start;
 	pmu->ctr_stop = pmu_sbi_ctr_stop;
@@ -1094,10 +1323,6 @@ static int pmu_sbi_device_probe(struct platform_device *pdev)
 	pmu->event_unmapped = pmu_sbi_event_unmapped;
 	pmu->csr_index = pmu_sbi_csr_index;
 
-	ret = cpuhp_state_add_instance(CPUHP_AP_PERF_RISCV_STARTING, &pmu->node);
-	if (ret)
-		return ret;
-
 	ret = riscv_pm_pmu_register(pmu);
 	if (ret)
 		goto out_unregister;
@@ -1106,8 +1331,34 @@ static int pmu_sbi_device_probe(struct platform_device *pdev)
 	if (ret)
 		goto out_unregister;
 
+	/* SBI PMU Snapsphot is only available in SBI v2.0 */
+	if (sbi_v2_available) {
+		ret = pmu_sbi_snapshot_alloc(pmu);
+		if (ret)
+			goto out_unregister;
+
+		ret = pmu_sbi_snapshot_setup(pmu, smp_processor_id());
+		if (ret) {
+			/* Snapshot is an optional feature. Continue if not available */
+			pmu_sbi_snapshot_free(pmu);
+		} else {
+			pr_info("SBI PMU snapshot detected\n");
+			/*
+			 * We enable it once here for the boot cpu. If snapshot shmem setup
+			 * fails during cpu hotplug process, it will fail to start the cpu
+			 * as we can not handle hetergenous PMUs with different snapshot
+			 * capability.
+			 */
+			static_branch_enable(&sbi_pmu_snapshot_available);
+		}
+	}
+
 	register_sysctl("kernel", sbi_pmu_sysctl_table);
 
+	ret = cpuhp_state_add_instance(CPUHP_AP_PERF_RISCV_STARTING, &pmu->node);
+	if (ret)
+		goto out_unregister;
+
 	return 0;
 
 out_unregister:
@@ -1135,6 +1386,9 @@ static int __init pmu_sbi_devinit(void)
 		return 0;
 	}
 
+	if (sbi_spec_version >= sbi_mk_version(2, 0))
+		sbi_v2_available = true;
+
 	ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_RISCV_STARTING,
 				      "perf/riscv/pmu:starting",
 				      pmu_sbi_starting_cpu, pmu_sbi_dying_cpu);
diff --git a/drivers/perf/thunderx2_pmu.c b/drivers/perf/thunderx2_pmu.c
index e16d10c763de..faf763d2c95c 100644
--- a/drivers/perf/thunderx2_pmu.c
+++ b/drivers/perf/thunderx2_pmu.c
@@ -504,24 +504,19 @@ static void tx2_uncore_event_update(struct perf_event *event)
 
 static enum tx2_uncore_type get_tx2_pmu_type(struct acpi_device *adev)
 {
-	int i = 0;
-	struct acpi_tx2_pmu_device {
-		__u8 id[ACPI_ID_LEN];
-		enum tx2_uncore_type type;
-	} devices[] = {
+	struct acpi_device_id devices[] = {
 		{"CAV901D", PMU_TYPE_L3C},
 		{"CAV901F", PMU_TYPE_DMC},
 		{"CAV901E", PMU_TYPE_CCPI2},
-		{"", PMU_TYPE_INVALID}
+		{}
 	};
+	const struct acpi_device_id *id;
 
-	while (devices[i].type != PMU_TYPE_INVALID) {
-		if (!strcmp(acpi_device_hid(adev), devices[i].id))
-			break;
-		i++;
-	}
+	id = acpi_match_acpi_device(devices, adev);
+	if (!id)
+		return PMU_TYPE_INVALID;
 
-	return devices[i].type;
+	return (enum tx2_uncore_type)id->driver_data;
 }
 
 static bool tx2_uncore_validate_event(struct pmu *pmu,
@@ -729,6 +724,7 @@ static int tx2_uncore_pmu_register(
 	/* Perf event registration */
 	tx2_pmu->pmu = (struct pmu) {
 		.module         = THIS_MODULE,
+		.parent		= tx2_pmu->dev,
 		.attr_groups	= tx2_pmu->attr_groups,
 		.task_ctx_nr	= perf_invalid_context,
 		.event_init	= tx2_uncore_event_init,
@@ -932,9 +928,8 @@ static int tx2_uncore_pmu_online_cpu(unsigned int cpu,
 static int tx2_uncore_pmu_offline_cpu(unsigned int cpu,
 		struct hlist_node *hpnode)
 {
-	int new_cpu;
 	struct tx2_uncore_pmu *tx2_pmu;
-	struct cpumask cpu_online_mask_temp;
+	unsigned int new_cpu;
 
 	tx2_pmu = hlist_entry_safe(hpnode,
 			struct tx2_uncore_pmu, hpnode);
@@ -945,11 +940,8 @@ static int tx2_uncore_pmu_offline_cpu(unsigned int cpu,
 	if (tx2_pmu->hrtimer_callback)
 		hrtimer_cancel(&tx2_pmu->hrtimer);
 
-	cpumask_copy(&cpu_online_mask_temp, cpu_online_mask);
-	cpumask_clear_cpu(cpu, &cpu_online_mask_temp);
-	new_cpu = cpumask_any_and(
-			cpumask_of_node(tx2_pmu->node),
-			&cpu_online_mask_temp);
+	new_cpu = cpumask_any_and_but(cpumask_of_node(tx2_pmu->node),
+				      cpu_online_mask, cpu);
 
 	tx2_pmu->cpu = new_cpu;
 	if (new_cpu >= nr_cpu_ids)
diff --git a/drivers/perf/xgene_pmu.c b/drivers/perf/xgene_pmu.c
index 0d49343d704b..8823b4c6b556 100644
--- a/drivers/perf/xgene_pmu.c
+++ b/drivers/perf/xgene_pmu.c
@@ -1102,6 +1102,7 @@ static int xgene_init_perf(struct xgene_pmu_dev *pmu_dev, char *name)
 
 	/* Perf driver registration */
 	pmu_dev->pmu = (struct pmu) {
+		.parent		= pmu_dev->parent->dev,
 		.attr_groups	= pmu_dev->attr_groups,
 		.task_ctx_nr	= perf_invalid_context,
 		.pmu_enable	= xgene_perf_pmu_enable,