Merge remote-tracking branch 'origin/master' into perf/core

Further perf/core patches will depend on:

  d3f7b1bb2040 ("mm/gup: fix gup_fast with dynamic page table folding")

which is already in Linus' tree.

16 files changed, 175 insertions, 57 deletions

diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index ce22bd23082d..6586f7e71cfb 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -1557,9 +1557,16 @@ nocheck:
 	ret = 0;
  out:
 	if (has_branch_stack(event)) {
-		power_pmu_bhrb_enable(event);
-		cpuhw->bhrb_filter = ppmu->bhrb_filter_map(
-					event->attr.branch_sample_type);
+		u64 bhrb_filter = -1;
+
+		if (ppmu->bhrb_filter_map)
+			bhrb_filter = ppmu->bhrb_filter_map(
+				event->attr.branch_sample_type);
+
+		if (bhrb_filter != -1) {
+			cpuhw->bhrb_filter = bhrb_filter;
+			power_pmu_bhrb_enable(event);
+		}
 	}
 
 	perf_pmu_enable(event->pmu);
@@ -1881,7 +1888,6 @@ static int power_pmu_event_init(struct perf_event *event)
 	int n;
 	int err;
 	struct cpu_hw_events *cpuhw;
-	u64 bhrb_filter;
 
 	if (!ppmu)
 		return -ENOENT;
@@ -1987,7 +1993,10 @@ static int power_pmu_event_init(struct perf_event *event)
 	err = power_check_constraints(cpuhw, events, cflags, n + 1);
 
 	if (has_branch_stack(event)) {
-		bhrb_filter = ppmu->bhrb_filter_map(
+		u64 bhrb_filter = -1;
+
+		if (ppmu->bhrb_filter_map)
+			bhrb_filter = ppmu->bhrb_filter_map(
 					event->attr.branch_sample_type);
 
 		if (bhrb_filter == -1) {
@@ -2143,6 +2152,10 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 
 		if (perf_event_overflow(event, &data, regs))
 			power_pmu_stop(event, 0);
+	} else if (period) {
+		/* Account for interrupt in case of invalid SIAR */
+		if (perf_event_account_interrupt(event))
+			power_pmu_stop(event, 0);
 	}
 }
 
@@ -2325,6 +2338,7 @@ int register_power_pmu(struct power_pmu *pmu)
 		pmu->name);
 
 	power_pmu.attr_groups = ppmu->attr_groups;
+	power_pmu.capabilities |= (ppmu->capabilities & PERF_PMU_CAP_EXTENDED_REGS);
 
 #ifdef MSR_HV
 	/*
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index cdb7bfbd157e..6e7e820508df 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -1128,6 +1128,15 @@ static struct bin_attribute *if_bin_attrs[] = {
 	NULL,
 };
 
+static struct attribute *cpumask_attrs[] = {
+	&dev_attr_cpumask.attr,
+	NULL,
+};
+
+static struct attribute_group cpumask_attr_group = {
+	.attrs = cpumask_attrs,
+};
+
 static struct attribute *if_attrs[] = {
 	&dev_attr_catalog_len.attr,
 	&dev_attr_catalog_version.attr,
@@ -1135,7 +1144,6 @@ static struct attribute *if_attrs[] = {
 	&dev_attr_sockets.attr,
 	&dev_attr_chipspersocket.attr,
 	&dev_attr_coresperchip.attr,
-	&dev_attr_cpumask.attr,
 	NULL,
 };
 
@@ -1151,6 +1159,7 @@ static const struct attribute_group *attr_groups[] = {
 	&event_desc_group,
 	&event_long_desc_group,
 	&if_group,
+	&cpumask_attr_group,
 	NULL,
 };
 
diff --git a/arch/powerpc/perf/hv-gpci-requests.h b/arch/powerpc/perf/hv-gpci-requests.h
index e608f9db12dd..8965b4463d43 100644
--- a/arch/powerpc/perf/hv-gpci-requests.h
+++ b/arch/powerpc/perf/hv-gpci-requests.h
@@ -95,7 +95,7 @@ REQUEST(__field(0,	8,	partition_id)
 
 #define REQUEST_NAME system_performance_capabilities
 #define REQUEST_NUM 0x40
-#define REQUEST_IDX_KIND "starting_index=0xffffffffffffffff"
+#define REQUEST_IDX_KIND "starting_index=0xffffffff"
 #include I(REQUEST_BEGIN)
 REQUEST(__field(0,	1,	perf_collect_privileged)
 	__field(0x1,	1,	capability_mask)
@@ -223,7 +223,7 @@ REQUEST(__field(0,	2, partition_id)
 
 #define REQUEST_NAME system_hypervisor_times
 #define REQUEST_NUM 0xF0
-#define REQUEST_IDX_KIND "starting_index=0xffffffffffffffff"
+#define REQUEST_IDX_KIND "starting_index=0xffffffff"
 #include I(REQUEST_BEGIN)
 REQUEST(__count(0,	8,	time_spent_to_dispatch_virtual_processors)
 	__count(0x8,	8,	time_spent_processing_virtual_processor_timers)
@@ -234,7 +234,7 @@ REQUEST(__count(0,	8,	time_spent_to_dispatch_virtual_processors)
 
 #define REQUEST_NAME system_tlbie_count_and_time
 #define REQUEST_NUM 0xF4
-#define REQUEST_IDX_KIND "starting_index=0xffffffffffffffff"
+#define REQUEST_IDX_KIND "starting_index=0xffffffff"
 #include I(REQUEST_BEGIN)
 REQUEST(__count(0,	8,	tlbie_instructions_issued)
 	/*
diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c
index 6884d16ec19b..d48413e28c39 100644
--- a/arch/powerpc/perf/hv-gpci.c
+++ b/arch/powerpc/perf/hv-gpci.c
@@ -48,6 +48,8 @@ EVENT_DEFINE_RANGE_FORMAT(length, config1, 24, 31);
 /* u32, byte offset */
 EVENT_DEFINE_RANGE_FORMAT(offset, config1, 32, 63);
 
+static cpumask_t hv_gpci_cpumask;
+
 static struct attribute *format_attrs[] = {
 	&format_attr_request.attr,
 	&format_attr_starting_index.attr,
@@ -94,7 +96,15 @@ static ssize_t kernel_version_show(struct device *dev,
 	return sprintf(page, "0x%x\n", COUNTER_INFO_VERSION_CURRENT);
 }
 
+static ssize_t cpumask_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	return cpumap_print_to_pagebuf(true, buf, &hv_gpci_cpumask);
+}
+
 static DEVICE_ATTR_RO(kernel_version);
+static DEVICE_ATTR_RO(cpumask);
+
 HV_CAPS_ATTR(version, "0x%x\n");
 HV_CAPS_ATTR(ga, "%d\n");
 HV_CAPS_ATTR(expanded, "%d\n");
@@ -111,6 +121,15 @@ static struct attribute *interface_attrs[] = {
 	NULL,
 };
 
+static struct attribute *cpumask_attrs[] = {
+	&dev_attr_cpumask.attr,
+	NULL,
+};
+
+static struct attribute_group cpumask_attr_group = {
+	.attrs = cpumask_attrs,
+};
+
 static struct attribute_group interface_group = {
 	.name = "interface",
 	.attrs = interface_attrs,
@@ -120,20 +139,12 @@ static const struct attribute_group *attr_groups[] = {
 	&format_group,
 	&event_group,
 	&interface_group,
+	&cpumask_attr_group,
 	NULL,
 };
 
-#define HGPCI_REQ_BUFFER_SIZE	4096
-#define HGPCI_MAX_DATA_BYTES \
-	(HGPCI_REQ_BUFFER_SIZE - sizeof(struct hv_get_perf_counter_info_params))
-
 static DEFINE_PER_CPU(char, hv_gpci_reqb[HGPCI_REQ_BUFFER_SIZE]) __aligned(sizeof(uint64_t));
 
-struct hv_gpci_request_buffer {
-	struct hv_get_perf_counter_info_params params;
-	uint8_t bytes[HGPCI_MAX_DATA_BYTES];
-} __packed;
-
 static unsigned long single_gpci_request(u32 req, u32 starting_index,
 		u16 secondary_index, u8 version_in, u32 offset, u8 length,
 		u64 *value)
@@ -275,6 +286,45 @@ static struct pmu h_gpci_pmu = {
 	.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
 };
 
+static int ppc_hv_gpci_cpu_online(unsigned int cpu)
+{
+	if (cpumask_empty(&hv_gpci_cpumask))
+		cpumask_set_cpu(cpu, &hv_gpci_cpumask);
+
+	return 0;
+}
+
+static int ppc_hv_gpci_cpu_offline(unsigned int cpu)
+{
+	int target;
+
+	/* Check if exiting cpu is used for collecting gpci events */
+	if (!cpumask_test_and_clear_cpu(cpu, &hv_gpci_cpumask))
+		return 0;
+
+	/* Find a new cpu to collect gpci events */
+	target = cpumask_last(cpu_active_mask);
+
+	if (target < 0 || target >= nr_cpu_ids) {
+		pr_err("hv_gpci: CPU hotplug init failed\n");
+		return -1;
+	}
+
+	/* Migrate gpci events to the new target */
+	cpumask_set_cpu(target, &hv_gpci_cpumask);
+	perf_pmu_migrate_context(&h_gpci_pmu, cpu, target);
+
+	return 0;
+}
+
+static int hv_gpci_cpu_hotplug_init(void)
+{
+	return cpuhp_setup_state(CPUHP_AP_PERF_POWERPC_HV_GPCI_ONLINE,
+			  "perf/powerpc/hv_gcpi:online",
+			  ppc_hv_gpci_cpu_online,
+			  ppc_hv_gpci_cpu_offline);
+}
+
 static int hv_gpci_init(void)
 {
 	int r;
@@ -295,6 +345,11 @@ static int hv_gpci_init(void)
 		return -ENODEV;
 	}
 
+	/* init cpuhotplug */
+	r = hv_gpci_cpu_hotplug_init();
+	if (r)
+		return r;
+
 	/* sampling not supported */
 	h_gpci_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
 
diff --git a/arch/powerpc/perf/hv-gpci.h b/arch/powerpc/perf/hv-gpci.h
index a3053eda5dcc..4d108262bed7 100644
--- a/arch/powerpc/perf/hv-gpci.h
+++ b/arch/powerpc/perf/hv-gpci.h
@@ -2,33 +2,6 @@
 #ifndef LINUX_POWERPC_PERF_HV_GPCI_H_
 #define LINUX_POWERPC_PERF_HV_GPCI_H_
 
-#include <linux/types.h>
-
-/* From the document "H_GetPerformanceCounterInfo Interface" v1.07 */
-
-/* H_GET_PERF_COUNTER_INFO argument */
-struct hv_get_perf_counter_info_params {
-	__be32 counter_request; /* I */
-	__be32 starting_index;  /* IO */
-	__be16 secondary_index; /* IO */
-	__be16 returned_values; /* O */
-	__be32 detail_rc; /* O, only needed when called via *_norets() */
-
-	/*
-	 * O, size each of counter_value element in bytes, only set for version
-	 * >= 0x3
-	 */
-	__be16 cv_element_size;
-
-	/* I, 0 (zero) for versions < 0x3 */
-	__u8 counter_info_version_in;
-
-	/* O, 0 (zero) if version < 0x3. Must be set to 0 when making hcall */
-	__u8 counter_info_version_out;
-	__u8 reserved[0xC];
-	__u8 counter_value[];
-} __packed;
-
 /*
  * counter info version => fw version/reference (spec version)
  *
diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c
index a45d694a5d5d..7b25548ec42b 100644
--- a/arch/powerpc/perf/imc-pmu.c
+++ b/arch/powerpc/perf/imc-pmu.c
@@ -1289,7 +1289,7 @@ static int trace_imc_prepare_sample(struct trace_imc_data *mem,
 	header->misc = 0;
 
 	if (cpu_has_feature(CPU_FTR_ARCH_31)) {
-		switch (IMC_TRACE_RECORD_VAL_HVPR(mem->val)) {
+		switch (IMC_TRACE_RECORD_VAL_HVPR(be64_to_cpu(READ_ONCE(mem->val)))) {
 		case 0:/* when MSR HV and PR not set in the trace-record */
 			header->misc |= PERF_RECORD_MISC_GUEST_KERNEL;
 			break;
@@ -1297,7 +1297,7 @@ static int trace_imc_prepare_sample(struct trace_imc_data *mem,
 			header->misc |= PERF_RECORD_MISC_GUEST_USER;
 			break;
 		case 2: /* MSR HV is 1 and PR is 0 */
-			header->misc |= PERF_RECORD_MISC_HYPERVISOR;
+			header->misc |= PERF_RECORD_MISC_KERNEL;
 			break;
 		case 3: /* MSR HV is 1 and PR is 1 */
 			header->misc |= PERF_RECORD_MISC_USER;
@@ -1336,7 +1336,7 @@ static void dump_trace_imc_data(struct perf_event *event)
 			/* If this is a valid record, create the sample */
 			struct perf_output_handle handle;
 
-			if (perf_output_begin(&handle, event, header.size))
+			if (perf_output_begin(&handle, &data, event, header.size))
 				return;
 
 			perf_output_sample(&handle, &header, &data, event);
@@ -1426,8 +1426,6 @@ static void trace_imc_event_del(struct perf_event *event, int flags)
 
 static int trace_imc_event_init(struct perf_event *event)
 {
-	struct task_struct *target;
-
 	if (event->attr.type != event->pmu->type)
 		return -ENOENT;
 
@@ -1458,7 +1456,6 @@ static int trace_imc_event_init(struct perf_event *event)
 	mutex_unlock(&imc_global_refc.lock);
 
 	event->hw.idx = -1;
-	target = event->hw.target;
 
 	event->pmu->task_ctx_nr = perf_hw_context;
 	event->destroy = reset_global_refc;
diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c
index 964437adec18..2848904df638 100644
--- a/arch/powerpc/perf/isa207-common.c
+++ b/arch/powerpc/perf/isa207-common.c
@@ -288,6 +288,15 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
 
 		mask  |= CNST_PMC_MASK(pmc);
 		value |= CNST_PMC_VAL(pmc);
+
+		/*
+		 * PMC5 and PMC6 are used to count cycles and instructions and
+		 * they do not support most of the constraint bits. Add a check
+		 * to exclude PMC5/6 from most of the constraints except for
+		 * EBB/BHRB.
+		 */
+		if (pmc >= 5)
+			goto ebb_bhrb;
 	}
 
 	if (pmc <= 4) {
@@ -357,6 +366,7 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
 		}
 	}
 
+ebb_bhrb:
 	if (!pmc && ebb)
 		/* EBB events must specify the PMC */
 		return -1;
diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h
index 044de65e96b9..7025de5e60e7 100644
--- a/arch/powerpc/perf/isa207-common.h
+++ b/arch/powerpc/perf/isa207-common.h
@@ -13,6 +13,8 @@
 #include <asm/firmware.h>
 #include <asm/cputable.h>
 
+#include "internal.h"
+
 #define EVENT_EBB_MASK		1ull
 #define EVENT_EBB_SHIFT		PERF_EVENT_CONFIG_EBB_SHIFT
 #define EVENT_BHRB_MASK		1ull
diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c
index a213a0aa5d25..6f681b105eec 100644
--- a/arch/powerpc/perf/perf_regs.c
+++ b/arch/powerpc/perf/perf_regs.c
@@ -13,9 +13,11 @@
 #include <asm/ptrace.h>
 #include <asm/perf_regs.h>
 
+u64 PERF_REG_EXTENDED_MASK;
+
 #define PT_REGS_OFFSET(id, r) [id] = offsetof(struct pt_regs, r)
 
-#define REG_RESERVED (~((1ULL << PERF_REG_POWERPC_MAX) - 1))
+#define REG_RESERVED (~(PERF_REG_EXTENDED_MASK | PERF_REG_PMU_MASK))
 
 static unsigned int pt_regs_offset[PERF_REG_POWERPC_MAX] = {
 	PT_REGS_OFFSET(PERF_REG_POWERPC_R0,  gpr[0]),
@@ -69,10 +71,36 @@ static unsigned int pt_regs_offset[PERF_REG_POWERPC_MAX] = {
 	PT_REGS_OFFSET(PERF_REG_POWERPC_MMCRA, dsisr),
 };
 
+/* Function to return the extended register values */
+static u64 get_ext_regs_value(int idx)
+{
+	switch (idx) {
+	case PERF_REG_POWERPC_MMCR0:
+		return mfspr(SPRN_MMCR0);
+	case PERF_REG_POWERPC_MMCR1:
+		return mfspr(SPRN_MMCR1);
+	case PERF_REG_POWERPC_MMCR2:
+		return mfspr(SPRN_MMCR2);
+#ifdef CONFIG_PPC64
+	case PERF_REG_POWERPC_MMCR3:
+		return mfspr(SPRN_MMCR3);
+	case PERF_REG_POWERPC_SIER2:
+		return mfspr(SPRN_SIER2);
+	case PERF_REG_POWERPC_SIER3:
+		return mfspr(SPRN_SIER3);
+#endif
+	default: return 0;
+	}
+}
+
 u64 perf_reg_value(struct pt_regs *regs, int idx)
 {
-	if (WARN_ON_ONCE(idx >= PERF_REG_POWERPC_MAX))
-		return 0;
+	u64 perf_reg_extended_max = PERF_REG_POWERPC_MAX;
+
+	if (cpu_has_feature(CPU_FTR_ARCH_31))
+		perf_reg_extended_max = PERF_REG_MAX_ISA_31;
+	else if (cpu_has_feature(CPU_FTR_ARCH_300))
+		perf_reg_extended_max = PERF_REG_MAX_ISA_300;
 
 	if (idx == PERF_REG_POWERPC_SIER &&
 	   (IS_ENABLED(CONFIG_FSL_EMB_PERF_EVENT) ||
@@ -85,6 +113,16 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 	    IS_ENABLED(CONFIG_PPC32)))
 		return 0;
 
+	if (idx >= PERF_REG_POWERPC_MAX && idx < perf_reg_extended_max)
+		return get_ext_regs_value(idx);
+
+	/*
+	 * If the idx is referring to value beyond the
+	 * supported registers, return 0 with a warning
+	 */
+	if (WARN_ON_ONCE(idx >= perf_reg_extended_max))
+		return 0;
+
 	return regs_get_register(regs, pt_regs_offset[idx]);
 }
 
@@ -106,8 +144,7 @@ u64 perf_reg_abi(struct task_struct *task)
 }
 
 void perf_get_regs_user(struct perf_regs *regs_user,
-			struct pt_regs *regs,
-			struct pt_regs *regs_user_copy)
+			struct pt_regs *regs)
 {
 	regs_user->regs = task_pt_regs(current);
 	regs_user->abi = (regs_user->regs) ? perf_reg_abi(current) :
diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c
index f7cff7f36a1c..9dbe8f9b89b4 100644
--- a/arch/powerpc/perf/power10-pmu.c
+++ b/arch/powerpc/perf/power10-pmu.c
@@ -9,7 +9,6 @@
 #define pr_fmt(fmt)	"power10-pmu: " fmt
 
 #include "isa207-common.h"
-#include "internal.h"
 
 /*
  * Raw event encoding for Power10:
@@ -87,6 +86,8 @@
 #define POWER10_MMCRA_IFM3		0x00000000C0000000UL
 #define POWER10_MMCRA_BHRB_MASK		0x00000000C0000000UL
 
+extern u64 PERF_REG_EXTENDED_MASK;
+
 /* Table of alternatives, sorted by column 0 */
 static const unsigned int power10_event_alternatives[][MAX_ALT] = {
 	{ PM_RUN_CYC_ALT,		PM_RUN_CYC },
@@ -397,6 +398,7 @@ static struct power_pmu power10_pmu = {
 	.cache_events		= &power10_cache_events,
 	.attr_groups		= power10_pmu_attr_groups,
 	.bhrb_nr		= 32,
+	.capabilities           = PERF_PMU_CAP_EXTENDED_REGS,
 };
 
 int init_power10_pmu(void)
@@ -408,6 +410,9 @@ int init_power10_pmu(void)
 	    strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power10"))
 		return -ENODEV;
 
+	/* Set the PERF_REG_EXTENDED_MASK here */
+	PERF_REG_EXTENDED_MASK = PERF_REG_PMU_MASK_31;
+
 	rc = register_power_pmu(&power10_pmu);
 	if (rc)
 		return rc;
diff --git a/arch/powerpc/perf/power5+-pmu.c b/arch/powerpc/perf/power5+-pmu.c
index a62b2cd7914f..3e64b4a1511f 100644
--- a/arch/powerpc/perf/power5+-pmu.c
+++ b/arch/powerpc/perf/power5+-pmu.c
@@ -10,6 +10,8 @@
 #include <asm/reg.h>
 #include <asm/cputable.h>
 
+#include "internal.h"
+
 /*
  * Bits in event code for POWER5+ (POWER5 GS) and POWER5++ (POWER5 GS DD3)
  */
diff --git a/arch/powerpc/perf/power5-pmu.c b/arch/powerpc/perf/power5-pmu.c
index 8732b587cf71..017bb19b73fb 100644
--- a/arch/powerpc/perf/power5-pmu.c
+++ b/arch/powerpc/perf/power5-pmu.c
@@ -10,6 +10,8 @@
 #include <asm/reg.h>
 #include <asm/cputable.h>
 
+#include "internal.h"
+
 /*
  * Bits in event code for POWER5 (not POWER5++)
  */
diff --git a/arch/powerpc/perf/power6-pmu.c b/arch/powerpc/perf/power6-pmu.c
index 0e318cf87129..189974478e9f 100644
--- a/arch/powerpc/perf/power6-pmu.c
+++ b/arch/powerpc/perf/power6-pmu.c
@@ -10,6 +10,8 @@
 #include <asm/reg.h>
 #include <asm/cputable.h>
 
+#include "internal.h"
+
 /*
  * Bits in event code for POWER6
  */
diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c
index 5e0bf09cf077..bacfab104a1a 100644
--- a/arch/powerpc/perf/power7-pmu.c
+++ b/arch/powerpc/perf/power7-pmu.c
@@ -10,6 +10,8 @@
 #include <asm/reg.h>
 #include <asm/cputable.h>
 
+#include "internal.h"
+
 /*
  * Bits in event code for POWER7
  */
diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c
index 05dae38b969a..2a57e93a79dc 100644
--- a/arch/powerpc/perf/power9-pmu.c
+++ b/arch/powerpc/perf/power9-pmu.c
@@ -90,6 +90,8 @@ enum {
 #define POWER9_MMCRA_IFM3		0x00000000C0000000UL
 #define POWER9_MMCRA_BHRB_MASK		0x00000000C0000000UL
 
+extern u64 PERF_REG_EXTENDED_MASK;
+
 /* Nasty Power9 specific hack */
 #define PVR_POWER9_CUMULUS		0x00002000
 
@@ -434,6 +436,7 @@ static struct power_pmu power9_pmu = {
 	.cache_events		= &power9_cache_events,
 	.attr_groups		= power9_pmu_attr_groups,
 	.bhrb_nr		= 32,
+	.capabilities           = PERF_PMU_CAP_EXTENDED_REGS,
 };
 
 int init_power9_pmu(void)
@@ -457,6 +460,9 @@ int init_power9_pmu(void)
 		}
 	}
 
+	/* Set the PERF_REG_EXTENDED_MASK here */
+	PERF_REG_EXTENDED_MASK = PERF_REG_PMU_MASK_300;
+
 	rc = register_power_pmu(&power9_pmu);
 	if (rc)
 		return rc;
diff --git a/arch/powerpc/perf/ppc970-pmu.c b/arch/powerpc/perf/ppc970-pmu.c
index d35223fb112c..7d78df97f272 100644
--- a/arch/powerpc/perf/ppc970-pmu.c
+++ b/arch/powerpc/perf/ppc970-pmu.c
@@ -9,6 +9,8 @@
 #include <asm/reg.h>
 #include <asm/cputable.h>
 
+#include "internal.h"
+
 /*
  * Bits in event code for PPC970
  */