Merge branch 'for-next/perf' into for-next/core

* for-next/perf: (33 commits)
  perf: arm-ni: Fix an NULL vs IS_ERR() bug
  perf: arm_pmuv3: Use BR_RETIRED for HW branch event if enabled
  MAINTAINERS: List Arm interconnect PMUs as supported
  perf: Add driver for Arm NI-700 interconnect PMU
  dt-bindings/perf: Add Arm NI-700 PMU
  perf/arm-cmn: Improve format attr printing
  perf/arm-cmn: Clean up unnecessary NUMA_NO_NODE check
  perf/arm-cmn: Support CMN S3
  dt-bindings: perf: arm-cmn: Add CMN S3
  perf/arm-cmn: Refactor DTC PMU register access
  perf/arm-cmn: Make cycle counts less surprising
  perf/arm-cmn: Improve build-time assertion
  perf/arm-cmn: Ensure dtm_idx is big enough
  perf/arm-cmn: Fix CCLA register offset
  perf/arm-cmn: Refactor node ID handling. Again.
  drivers/perf: hisi_pcie: Export supported Root Ports [bdf_min, bdf_max]
  drivers/perf: hisi_pcie: Fix TLP headers bandwidth counting
  drivers/perf: hisi_pcie: Record hardware counts correctly
  drivers/perf: arm_spe: Use perf_allow_kernel() for permissions
  perf/dwc_pcie: Add support for QCOM vendor devices
  ...

Documentation/admin-guide/perf/arm-ni.rst

+====================================
+Arm Network-on Chip Interconnect PMU
+====================================
+
+NI-700 and friends implement a distinct PMU for each clock domain within the
+interconnect. Correspondingly, the driver exposes multiple PMU devices named
+arm_ni_<x>_cd_<y>, where <x> is an (arbitrary) instance identifier and <y> is
+the clock domain ID within that particular instance. If multiple NI instances
+exist within a system, the PMU devices can be correlated with the underlying
+hardware instance via sysfs parentage.
+
+Each PMU exposes base event aliases for the interface types present in its clock
+domain. These require qualifying with the "eventid" and "nodeid" parameters
+to specify the event code to count and the interface at which to count it
+(per the configured hardware ID as reflected in the xxNI_NODE_INFO register).
+The exception is the "cycles" alias for the PMU cycle counter, which is encoded
+with the PMU node type and needs no further qualification.

Documentation/admin-guide/perf/dwc_pcie_pmu.rst

@@ -46,16 +46,16 @@ Some of the events only exist for specific configurations.
 DesignWare Cores (DWC) PCIe PMU Driver
 =======================================
 
-This driver adds PMU devices for each PCIe Root Port named based on the BDF of
+This driver adds PMU devices for each PCIe Root Port named based on the SBDF of
 the Root Port. For example,
 
-    30:03.0 PCI bridge: Device 1ded:8000 (rev 01)
+    0001:30:03.0 PCI bridge: Device 1ded:8000 (rev 01)
 
-the PMU device name for this Root Port is dwc_rootport_3018.
+the PMU device name for this Root Port is dwc_rootport_13018.
 
 The DWC PCIe PMU driver registers a perf PMU driver, which provides
 description of available events and configuration options in sysfs, see
-/sys/bus/event_source/devices/dwc_rootport_{bdf}.
+/sys/bus/event_source/devices/dwc_rootport_{sbdf}.
 
 The "format" directory describes format of the config fields of the
 perf_event_attr structure. The "events" directory provides configuration
@@ -66,16 +66,16 @@ The "perf list" command shall list the available events from sysfs, e.g.::
 
     $# perf list | grep dwc_rootport
     <...>
-    dwc_rootport_3018/Rx_PCIe_TLP_Data_Payload/        [Kernel PMU event]
+    dwc_rootport_13018/Rx_PCIe_TLP_Data_Payload/        [Kernel PMU event]
     <...>
-    dwc_rootport_3018/rx_memory_read,lane=?/               [Kernel PMU event]
+    dwc_rootport_13018/rx_memory_read,lane=?/               [Kernel PMU event]
 
 Time Based Analysis Event Usage
 -------------------------------
 
 Example usage of counting PCIe RX TLP data payload (Units of bytes)::
 
-    $# perf stat -a -e dwc_rootport_3018/Rx_PCIe_TLP_Data_Payload/
+    $# perf stat -a -e dwc_rootport_13018/Rx_PCIe_TLP_Data_Payload/
 
 The average RX/TX bandwidth can be calculated using the following formula:
 
@@ -88,7 +88,7 @@ Lane Event Usage
 Each lane has the same event set and to avoid generating a list of hundreds
 of events, the user need to specify the lane ID explicitly, e.g.::
 
-    $# perf stat -a -e dwc_rootport_3018/rx_memory_read,lane=4/
+    $# perf stat -a -e dwc_rootport_13018/rx_memory_read,lane=4/
 
 The driver does not support sampling, therefore "perf record" will not
 work. Per-task (without "-a") perf sessions are not supported.

Documentation/admin-guide/perf/hisi-pcie-pmu.rst

@@ -28,7 +28,9 @@ The "identifier" sysfs file allows users to identify the version of the
 PMU hardware device.
 
 The "bus" sysfs file allows users to get the bus number of Root Ports
-monitored by PMU.
+monitored by PMU. Furthermore users can get the Root Ports range in
+[bdf_min, bdf_max] from "bdf_min" and "bdf_max" sysfs attributes
+respectively.
 
 Example usage of perf::
 

Documentation/admin-guide/perf/index.rst

@@ -16,6 +16,7 @@ Performance monitor support
    starfive_starlink_pmu
    arm-ccn
    arm-cmn
+   arm-ni
    xgene-pmu
    arm_dsu_pmu
    thunderx2-pmu

Documentation/devicetree/bindings/perf/arm,cmn.yaml

@@ -16,6 +16,7 @@ properties:
       - arm,cmn-600
       - arm,cmn-650
       - arm,cmn-700
+      - arm,cmn-s3
       - arm,ci-700
 
   reg:

Documentation/devicetree/bindings/perf/arm,ni.yaml

+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/perf/arm,ni.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Arm NI (Network-on-Chip Interconnect) Performance Monitors
+
+maintainers:
+  - Robin Murphy <robin.murphy@arm.com>
+
+properties:
+  compatible:
+    const: arm,ni-700
+
+  reg:
+    items:
+      - description: Complete configuration register space
+
+  interrupts:
+    minItems: 1
+    maxItems: 32
+    description: Overflow interrupts, one per clock domain, in order of domain ID
+
+required:
+  - compatible
+  - reg
+  - interrupts
+
+additionalProperties: false

MAINTAINERS

@@ -1738,6 +1738,17 @@ F:	drivers/mtd/maps/physmap-versatile.*
 F:	drivers/power/reset/arm-versatile-reboot.c
 F:	drivers/soc/versatile/
 
+ARM INTERCONNECT PMU DRIVERS
+M:	Robin Murphy <robin.murphy@arm.com>
+S:	Supported
+F:	Documentation/admin-guide/perf/arm-cmn.rst
+F:	Documentation/admin-guide/perf/arm-ni.rst
+F:	Documentation/devicetree/bindings/perf/arm,cmn.yaml
+F:	Documentation/devicetree/bindings/perf/arm,ni.yaml
+F:	drivers/perf/arm-cmn.c
+F:	drivers/perf/arm-ni.c
+F:	tools/perf/pmu-events/arch/arm64/arm/cmn/
+
 ARM KOMEDA DRM-KMS DRIVER
 M:	Liviu Dudau <liviu.dudau@arm.com>
 S:	Supported

arch/arm/include/asm/arm_pmuv3.h

@@ -127,6 +127,12 @@ static inline u32 read_pmuver(void)
 	return (dfr0 >> 24) & 0xf;
 }
 
+static inline bool pmuv3_has_icntr(void)
+{
+	/* FEAT_PMUv3_ICNTR not accessible for 32-bit */
+	return false;
+}
+
 static inline void write_pmcr(u32 val)
 {
 	write_sysreg(val, PMCR);
@@ -152,6 +158,13 @@ static inline u64 read_pmccntr(void)
 	return read_sysreg(PMCCNTR);
 }
 
+static inline void write_pmicntr(u64 val) {}
+
+static inline u64 read_pmicntr(void)
+{
+	return 0;
+}
+
 static inline void write_pmcntenset(u32 val)
 {
 	write_sysreg(val, PMCNTENSET);
@@ -177,6 +190,13 @@ static inline void write_pmccfiltr(u32 val)
 	write_sysreg(val, PMCCFILTR);
 }
 
+static inline void write_pmicfiltr(u64 val) {}
+
+static inline u64 read_pmicfiltr(void)
+{
+	return 0;
+}
+
 static inline void write_pmovsclr(u32 val)
 {
 	write_sysreg(val, PMOVSR);

arch/arm64/include/asm/arm_pmuv3.h

@@ -33,6 +33,14 @@ static inline void write_pmevtypern(int n, unsigned long val)
 	PMEVN_SWITCH(n, WRITE_PMEVTYPERN);
 }
 
+#define RETURN_READ_PMEVTYPERN(n) \
+	return read_sysreg(pmevtyper##n##_el0)
+static inline unsigned long read_pmevtypern(int n)
+{
+	PMEVN_SWITCH(n, RETURN_READ_PMEVTYPERN);
+	return 0;
+}
+
 static inline unsigned long read_pmmir(void)
 {
 	return read_cpuid(PMMIR_EL1);
@@ -46,6 +54,14 @@ static inline u32 read_pmuver(void)
 			ID_AA64DFR0_EL1_PMUVer_SHIFT);
 }
 
+static inline bool pmuv3_has_icntr(void)
+{
+	u64 dfr1 = read_sysreg(id_aa64dfr1_el1);
+
+	return !!cpuid_feature_extract_unsigned_field(dfr1,
+			ID_AA64DFR1_EL1_PMICNTR_SHIFT);
+}
+
 static inline void write_pmcr(u64 val)
 {
 	write_sysreg(val, pmcr_el0);
@@ -71,22 +87,32 @@ static inline u64 read_pmccntr(void)
 	return read_sysreg(pmccntr_el0);
 }
 
-static inline void write_pmcntenset(u32 val)
+static inline void write_pmicntr(u64 val)
+{
+	write_sysreg_s(val, SYS_PMICNTR_EL0);
+}
+
+static inline u64 read_pmicntr(void)
+{
+	return read_sysreg_s(SYS_PMICNTR_EL0);
+}
+
+static inline void write_pmcntenset(u64 val)
 {
 	write_sysreg(val, pmcntenset_el0);
 }
 
-static inline void write_pmcntenclr(u32 val)
+static inline void write_pmcntenclr(u64 val)
 {
 	write_sysreg(val, pmcntenclr_el0);
 }
 
-static inline void write_pmintenset(u32 val)
+static inline void write_pmintenset(u64 val)
 {
 	write_sysreg(val, pmintenset_el1);
 }
 
-static inline void write_pmintenclr(u32 val)
+static inline void write_pmintenclr(u64 val)
 {
 	write_sysreg(val, pmintenclr_el1);
 }
@@ -96,12 +122,27 @@ static inline void write_pmccfiltr(u64 val)
 	write_sysreg(val, pmccfiltr_el0);
 }
 
-static inline void write_pmovsclr(u32 val)
+static inline u64 read_pmccfiltr(void)
+{
+	return read_sysreg(pmccfiltr_el0);
+}
+
+static inline void write_pmicfiltr(u64 val)
+{
+	write_sysreg_s(val, SYS_PMICFILTR_EL0);
+}
+
+static inline u64 read_pmicfiltr(void)
+{
+	return read_sysreg_s(SYS_PMICFILTR_EL0);
+}
+
+static inline void write_pmovsclr(u64 val)
 {
 	write_sysreg(val, pmovsclr_el0);
 }
 
-static inline u32 read_pmovsclr(void)
+static inline u64 read_pmovsclr(void)
 {
 	return read_sysreg(pmovsclr_el0);
 }

arch/arm64/include/asm/kvm_host.h

@@ -1330,12 +1330,12 @@ void kvm_arch_vcpu_load_debug_state_flags(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_put_debug_state_flags(struct kvm_vcpu *vcpu);
 
 #ifdef CONFIG_KVM
-void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr);
-void kvm_clr_pmu_events(u32 clr);
+void kvm_set_pmu_events(u64 set, struct perf_event_attr *attr);
+void kvm_clr_pmu_events(u64 clr);
 bool kvm_set_pmuserenr(u64 val);
 #else
-static inline void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) {}
-static inline void kvm_clr_pmu_events(u32 clr) {}
+static inline void kvm_set_pmu_events(u64 set, struct perf_event_attr *attr) {}
+static inline void kvm_clr_pmu_events(u64 clr) {}
 static inline bool kvm_set_pmuserenr(u64 val)
 {
 	return false;

arch/arm64/include/asm/sysreg.h

@@ -403,7 +403,6 @@
 #define SYS_PMCNTENCLR_EL0		sys_reg(3, 3, 9, 12, 2)
 #define SYS_PMOVSCLR_EL0		sys_reg(3, 3, 9, 12, 3)
 #define SYS_PMSWINC_EL0			sys_reg(3, 3, 9, 12, 4)
-#define SYS_PMSELR_EL0			sys_reg(3, 3, 9, 12, 5)
 #define SYS_PMCEID0_EL0			sys_reg(3, 3, 9, 12, 6)
 #define SYS_PMCEID1_EL0			sys_reg(3, 3, 9, 12, 7)
 #define SYS_PMCCNTR_EL0			sys_reg(3, 3, 9, 13, 0)

arch/arm64/kvm/pmu-emul.c

@@ -233,7 +233,7 @@ void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu)
 	int i;
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
 
-	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++)
+	for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++)
 		pmu->pmc[i].idx = i;
 }
 
@@ -260,7 +260,7 @@ void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
 	int i;
 
-	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++)
+	for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++)
 		kvm_pmu_release_perf_event(kvm_vcpu_idx_to_pmc(vcpu, i));
 	irq_work_sync(&vcpu->arch.pmu.overflow_work);
 }
@@ -291,7 +291,7 @@ void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
 	if (!(kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E) || !val)
 		return;
 
-	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) {
+	for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) {
 		struct kvm_pmc *pmc;
 
 		if (!(val & BIT(i)))
@@ -323,7 +323,7 @@ void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
 	if (!kvm_vcpu_has_pmu(vcpu) || !val)
 		return;
 
-	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) {
+	for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) {
 		struct kvm_pmc *pmc;
 
 		if (!(val & BIT(i)))
@@ -910,10 +910,10 @@ u8 kvm_arm_pmu_get_max_counters(struct kvm *kvm)
 	struct arm_pmu *arm_pmu = kvm->arch.arm_pmu;
 
 	/*
-	 * The arm_pmu->num_events considers the cycle counter as well.
-	 * Ignore that and return only the general-purpose counters.
+	 * The arm_pmu->cntr_mask considers the fixed counter(s) as well.
+	 * Ignore those and return only the general-purpose counters.
 	 */
-	return arm_pmu->num_events - 1;
+	return bitmap_weight(arm_pmu->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS);
 }
 
 static void kvm_arm_set_pmu(struct kvm *kvm, struct arm_pmu *arm_pmu)

arch/arm64/kvm/pmu.c

@@ -5,6 +5,8 @@
  */
 #include <linux/kvm_host.h>
 #include <linux/perf_event.h>
+#include <linux/perf/arm_pmu.h>
+#include <linux/perf/arm_pmuv3.h>
 
 static DEFINE_PER_CPU(struct kvm_pmu_events, kvm_pmu_events);
 
@@ -35,7 +37,7 @@ struct kvm_pmu_events *kvm_get_pmu_events(void)
  * Add events to track that we may want to switch at guest entry/exit
  * time.
  */
-void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr)
+void kvm_set_pmu_events(u64 set, struct perf_event_attr *attr)
 {
 	struct kvm_pmu_events *pmu = kvm_get_pmu_events();
 
@@ -51,7 +53,7 @@ void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr)
 /*
  * Stop tracking events
  */
-void kvm_clr_pmu_events(u32 clr)
+void kvm_clr_pmu_events(u64 clr)
 {
 	struct kvm_pmu_events *pmu = kvm_get_pmu_events();
 
@@ -62,79 +64,32 @@ void kvm_clr_pmu_events(u32 clr)
 	pmu->events_guest &= ~clr;
 }
 
-#define PMEVTYPER_READ_CASE(idx)				\
-	case idx:						\
-		return read_sysreg(pmevtyper##idx##_el0)
-
-#define PMEVTYPER_WRITE_CASE(idx)				\
-	case idx:						\
-		write_sysreg(val, pmevtyper##idx##_el0);	\
-		break
-
-#define PMEVTYPER_CASES(readwrite)				\
-	PMEVTYPER_##readwrite##_CASE(0);			\
-	PMEVTYPER_##readwrite##_CASE(1);			\
-	PMEVTYPER_##readwrite##_CASE(2);			\
-	PMEVTYPER_##readwrite##_CASE(3);			\
-	PMEVTYPER_##readwrite##_CASE(4);			\
-	PMEVTYPER_##readwrite##_CASE(5);			\
-	PMEVTYPER_##readwrite##_CASE(6);			\
-	PMEVTYPER_##readwrite##_CASE(7);			\
-	PMEVTYPER_##readwrite##_CASE(8);			\
-	PMEVTYPER_##readwrite##_CASE(9);			\
-	PMEVTYPER_##readwrite##_CASE(10);			\
-	PMEVTYPER_##readwrite##_CASE(11);			\
-	PMEVTYPER_##readwrite##_CASE(12);			\
-	PMEVTYPER_##readwrite##_CASE(13);			\
-	PMEVTYPER_##readwrite##_CASE(14);			\
-	PMEVTYPER_##readwrite##_CASE(15);			\
-	PMEVTYPER_##readwrite##_CASE(16);			\
-	PMEVTYPER_##readwrite##_CASE(17);			\
-	PMEVTYPER_##readwrite##_CASE(18);			\
-	PMEVTYPER_##readwrite##_CASE(19);			\
-	PMEVTYPER_##readwrite##_CASE(20);			\
-	PMEVTYPER_##readwrite##_CASE(21);			\
-	PMEVTYPER_##readwrite##_CASE(22);			\
-	PMEVTYPER_##readwrite##_CASE(23);			\
-	PMEVTYPER_##readwrite##_CASE(24);			\
-	PMEVTYPER_##readwrite##_CASE(25);			\
-	PMEVTYPER_##readwrite##_CASE(26);			\
-	PMEVTYPER_##readwrite##_CASE(27);			\
-	PMEVTYPER_##readwrite##_CASE(28);			\
-	PMEVTYPER_##readwrite##_CASE(29);			\
-	PMEVTYPER_##readwrite##_CASE(30)
-
 /*
  * Read a value direct from PMEVTYPER<idx> where idx is 0-30
- * or PMCCFILTR_EL0 where idx is ARMV8_PMU_CYCLE_IDX (31).
+ * or PMxCFILTR_EL0 where idx is 31-32.
  */
 static u64 kvm_vcpu_pmu_read_evtype_direct(int idx)
 {
-	switch (idx) {
-	PMEVTYPER_CASES(READ);
-	case ARMV8_PMU_CYCLE_IDX:
-		return read_sysreg(pmccfiltr_el0);
-	default:
-		WARN_ON(1);
-	}
+	if (idx == ARMV8_PMU_CYCLE_IDX)
+		return read_pmccfiltr();
+	else if (idx == ARMV8_PMU_INSTR_IDX)
+		return read_pmicfiltr();
 
-	return 0;
+	return read_pmevtypern(idx);
 }
 
 /*
  * Write a value direct to PMEVTYPER<idx> where idx is 0-30
- * or PMCCFILTR_EL0 where idx is ARMV8_PMU_CYCLE_IDX (31).
+ * or PMxCFILTR_EL0 where idx is 31-32.
  */
 static void kvm_vcpu_pmu_write_evtype_direct(int idx, u32 val)
 {
-	switch (idx) {
-	PMEVTYPER_CASES(WRITE);
-	case ARMV8_PMU_CYCLE_IDX:
-		write_sysreg(val, pmccfiltr_el0);
-		break;
-	default:
-		WARN_ON(1);
-	}
+	if (idx == ARMV8_PMU_CYCLE_IDX)
+		write_pmccfiltr(val);
+	else if (idx == ARMV8_PMU_INSTR_IDX)
+		write_pmicfiltr(val);
+	else
+		write_pmevtypern(idx, val);
 }
 
 /*
@@ -145,7 +100,7 @@ static void kvm_vcpu_pmu_enable_el0(unsigned long events)
 	u64 typer;
 	u32 counter;
 
-	for_each_set_bit(counter, &events, 32) {
+	for_each_set_bit(counter, &events, ARMPMU_MAX_HWEVENTS) {
 		typer = kvm_vcpu_pmu_read_evtype_direct(counter);
 		typer &= ~ARMV8_PMU_EXCLUDE_EL0;
 		kvm_vcpu_pmu_write_evtype_direct(counter, typer);
@@ -160,7 +115,7 @@ static void kvm_vcpu_pmu_disable_el0(unsigned long events)
 	u64 typer;
 	u32 counter;
 
-	for_each_set_bit(counter, &events, 32) {
+	for_each_set_bit(counter, &events, ARMPMU_MAX_HWEVENTS) {
 		typer = kvm_vcpu_pmu_read_evtype_direct(counter);
 		typer |= ARMV8_PMU_EXCLUDE_EL0;
 		kvm_vcpu_pmu_write_evtype_direct(counter, typer);
@@ -176,7 +131,7 @@ static void kvm_vcpu_pmu_disable_el0(unsigned long events)
 void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu)
 {
 	struct kvm_pmu_events *pmu;
-	u32 events_guest, events_host;
+	u64 events_guest, events_host;
 
 	if (!kvm_arm_support_pmu_v3() || !has_vhe())
 		return;
@@ -197,7 +152,7 @@ void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu)
 void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu)
 {
 	struct kvm_pmu_events *pmu;
-	u32 events_guest, events_host;
+	u64 events_guest, events_host;
 
 	if (!kvm_arm_support_pmu_v3() || !has_vhe())
 		return;

arch/arm64/kvm/sys_regs.c

@@ -18,6 +18,7 @@
 #include <linux/printk.h>
 #include <linux/uaccess.h>
 
+#include <asm/arm_pmuv3.h>
 #include <asm/cacheflush.h>
 #include <asm/cputype.h>
 #include <asm/debug-monitors.h>
@@ -887,7 +888,7 @@ static u64 reset_pmevtyper(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 static u64 reset_pmselr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
 	reset_unknown(vcpu, r);
-	__vcpu_sys_reg(vcpu, r->reg) &= ARMV8_PMU_COUNTER_MASK;
+	__vcpu_sys_reg(vcpu, r->reg) &= PMSELR_EL0_SEL_MASK;
 
 	return __vcpu_sys_reg(vcpu, r->reg);
 }
@@ -979,7 +980,7 @@ static bool access_pmselr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	else
 		/* return PMSELR.SEL field */
 		p->regval = __vcpu_sys_reg(vcpu, PMSELR_EL0)
-			    & ARMV8_PMU_COUNTER_MASK;
+			    & PMSELR_EL0_SEL_MASK;
 
 	return true;
 }
@@ -1047,8 +1048,8 @@ static bool access_pmu_evcntr(struct kvm_vcpu *vcpu,
 			if (pmu_access_event_counter_el0_disabled(vcpu))
 				return false;
 
-			idx = __vcpu_sys_reg(vcpu, PMSELR_EL0)
-			      & ARMV8_PMU_COUNTER_MASK;
+			idx = SYS_FIELD_GET(PMSELR_EL0, SEL,
+					    __vcpu_sys_reg(vcpu, PMSELR_EL0));
 		} else if (r->Op2 == 0) {
 			/* PMCCNTR_EL0 */
 			if (pmu_access_cycle_counter_el0_disabled(vcpu))
@@ -1098,7 +1099,7 @@ static bool access_pmu_evtyper(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 
 	if (r->CRn == 9 && r->CRm == 13 && r->Op2 == 1) {
 		/* PMXEVTYPER_EL0 */
-		idx = __vcpu_sys_reg(vcpu, PMSELR_EL0) & ARMV8_PMU_COUNTER_MASK;
+		idx = SYS_FIELD_GET(PMSELR_EL0, SEL, __vcpu_sys_reg(vcpu, PMSELR_EL0));
 		reg = PMEVTYPER0_EL0 + idx;
 	} else if (r->CRn == 14 && (r->CRm & 12) == 12) {
 		idx = ((r->CRm & 3) << 3) | (r->Op2 & 7);

arch/arm64/tools/sysreg

@@ -2029,6 +2029,31 @@ Sysreg	FAR_EL1	3	0	6	0	0
 Field	63:0	ADDR
 EndSysreg
 
+Sysreg	PMICNTR_EL0	3	3	9	4	0
+Field	63:0	ICNT
+EndSysreg
+
+Sysreg	PMICFILTR_EL0	3	3	9	6	0
+Res0	63:59
+Field	58	SYNC
+Field	57:56	VS
+Res0	55:32
+Field	31	P
+Field	30	U
+Field	29	NSK
+Field	28	NSU
+Field	27	NSH
+Field	26	M
+Res0	25
+Field	24	SH
+Field	23	T
+Field	22	RLK
+Field	21	RLU
+Field	20	RLH
+Res0	19:16
+Field	15:0	evtCount
+EndSysreg
+
 Sysreg	PMSCR_EL1	3	0	9	9	0
 Res0	63:8
 Field	7:6	PCT
@@ -2153,6 +2178,11 @@ Field	4	P
 Field	3:0	ALIGN
 EndSysreg
 
+Sysreg	PMSELR_EL0	3	3	9	12	5
+Res0	63:5
+Field	4:0	SEL
+EndSysreg
+
 SysregFields	CONTEXTIDR_ELx
 Res0	63:32
 Field	31:0	PROCID

drivers/perf/Kconfig

@@ -48,6 +48,13 @@ config ARM_CMN
 	  Support for PMU events monitoring on the Arm CMN-600 Coherent Mesh
 	  Network interconnect.
 
+config ARM_NI
+	tristate "Arm NI-700 PMU support"
+	depends on ARM64 || COMPILE_TEST
+	help
+	  Support for PMU events monitoring on the Arm NI-700 Network-on-Chip
+	  interconnect and family.
+
 config ARM_PMU
 	depends on ARM || ARM64
 	bool "ARM PMU framework"

drivers/perf/Makefile

@@ -3,6 +3,7 @@ obj-$(CONFIG_ARM_CCI_PMU) += arm-cci.o
 obj-$(CONFIG_ARM_CCN) += arm-ccn.o
 obj-$(CONFIG_ARM_CMN) += arm-cmn.o
 obj-$(CONFIG_ARM_DSU_PMU) += arm_dsu_pmu.o
+obj-$(CONFIG_ARM_NI) += arm-ni.o
 obj-$(CONFIG_ARM_PMU) += arm_pmu.o arm_pmu_platform.o
 obj-$(CONFIG_ARM_PMU_ACPI) += arm_pmu_acpi.o
 obj-$(CONFIG_ARM_PMUV3) += arm_pmuv3.o

drivers/perf/alibaba_uncore_drw_pmu.c

@@ -400,7 +400,7 @@ static irqreturn_t ali_drw_pmu_isr(int irq_num, void *data)
 			}
 
 			/* clear common counter intr status */
-			clr_status = FIELD_PREP(ALI_DRW_PMCOM_CNT_OV_INTR_MASK, 1);
+			clr_status = FIELD_PREP(ALI_DRW_PMCOM_CNT_OV_INTR_MASK, status);
 			writel(clr_status,
 			       drw_pmu->cfg_base + ALI_DRW_PMU_OV_INTR_CLR);
 		}

drivers/perf/apple_m1_cpu_pmu.c

@@ -47,46 +47,79 @@
  * implementations, we'll have to introduce per cpu-type tables.
  */
 enum m1_pmu_events {
-	M1_PMU_PERFCTR_UNKNOWN_01	= 0x01,
-	M1_PMU_PERFCTR_CPU_CYCLES	= 0x02,
-	M1_PMU_PERFCTR_INSTRUCTIONS	= 0x8c,
-	M1_PMU_PERFCTR_UNKNOWN_8d	= 0x8d,
-	M1_PMU_PERFCTR_UNKNOWN_8e	= 0x8e,
-	M1_PMU_PERFCTR_UNKNOWN_8f	= 0x8f,
-	M1_PMU_PERFCTR_UNKNOWN_90	= 0x90,
-	M1_PMU_PERFCTR_UNKNOWN_93	= 0x93,
-	M1_PMU_PERFCTR_UNKNOWN_94	= 0x94,
-	M1_PMU_PERFCTR_UNKNOWN_95	= 0x95,
-	M1_PMU_PERFCTR_UNKNOWN_96	= 0x96,
-	M1_PMU_PERFCTR_UNKNOWN_97	= 0x97,
-	M1_PMU_PERFCTR_UNKNOWN_98	= 0x98,
-	M1_PMU_PERFCTR_UNKNOWN_99	= 0x99,
-	M1_PMU_PERFCTR_UNKNOWN_9a	= 0x9a,
-	M1_PMU_PERFCTR_UNKNOWN_9b	= 0x9b,
-	M1_PMU_PERFCTR_UNKNOWN_9c	= 0x9c,
-	M1_PMU_PERFCTR_UNKNOWN_9f	= 0x9f,
-	M1_PMU_PERFCTR_UNKNOWN_bf	= 0xbf,
-	M1_PMU_PERFCTR_UNKNOWN_c0	= 0xc0,
-	M1_PMU_PERFCTR_UNKNOWN_c1	= 0xc1,
-	M1_PMU_PERFCTR_UNKNOWN_c4	= 0xc4,
-	M1_PMU_PERFCTR_UNKNOWN_c5	= 0xc5,
-	M1_PMU_PERFCTR_UNKNOWN_c6	= 0xc6,
-	M1_PMU_PERFCTR_UNKNOWN_c8	= 0xc8,
-	M1_PMU_PERFCTR_UNKNOWN_ca	= 0xca,
-	M1_PMU_PERFCTR_UNKNOWN_cb	= 0xcb,
-	M1_PMU_PERFCTR_UNKNOWN_f5	= 0xf5,
-	M1_PMU_PERFCTR_UNKNOWN_f6	= 0xf6,
-	M1_PMU_PERFCTR_UNKNOWN_f7	= 0xf7,
-	M1_PMU_PERFCTR_UNKNOWN_f8	= 0xf8,
-	M1_PMU_PERFCTR_UNKNOWN_fd	= 0xfd,
-	M1_PMU_PERFCTR_LAST		= M1_PMU_CFG_EVENT,
+	M1_PMU_PERFCTR_RETIRE_UOP				= 0x1,
+	M1_PMU_PERFCTR_CORE_ACTIVE_CYCLE			= 0x2,
+	M1_PMU_PERFCTR_L1I_TLB_FILL				= 0x4,
+	M1_PMU_PERFCTR_L1D_TLB_FILL				= 0x5,
+	M1_PMU_PERFCTR_MMU_TABLE_WALK_INSTRUCTION		= 0x7,
+	M1_PMU_PERFCTR_MMU_TABLE_WALK_DATA			= 0x8,
+	M1_PMU_PERFCTR_L2_TLB_MISS_INSTRUCTION			= 0xa,
+	M1_PMU_PERFCTR_L2_TLB_MISS_DATA				= 0xb,
+	M1_PMU_PERFCTR_MMU_VIRTUAL_MEMORY_FAULT_NONSPEC		= 0xd,
+	M1_PMU_PERFCTR_SCHEDULE_UOP				= 0x52,
+	M1_PMU_PERFCTR_INTERRUPT_PENDING			= 0x6c,
+	M1_PMU_PERFCTR_MAP_STALL_DISPATCH			= 0x70,
+	M1_PMU_PERFCTR_MAP_REWIND				= 0x75,
+	M1_PMU_PERFCTR_MAP_STALL				= 0x76,
+	M1_PMU_PERFCTR_MAP_INT_UOP				= 0x7c,
+	M1_PMU_PERFCTR_MAP_LDST_UOP				= 0x7d,
+	M1_PMU_PERFCTR_MAP_SIMD_UOP				= 0x7e,
+	M1_PMU_PERFCTR_FLUSH_RESTART_OTHER_NONSPEC		= 0x84,
+	M1_PMU_PERFCTR_INST_ALL					= 0x8c,
+	M1_PMU_PERFCTR_INST_BRANCH				= 0x8d,
+	M1_PMU_PERFCTR_INST_BRANCH_CALL				= 0x8e,
+	M1_PMU_PERFCTR_INST_BRANCH_RET				= 0x8f,
+	M1_PMU_PERFCTR_INST_BRANCH_TAKEN			= 0x90,
+	M1_PMU_PERFCTR_INST_BRANCH_INDIR			= 0x93,
+	M1_PMU_PERFCTR_INST_BRANCH_COND				= 0x94,
+	M1_PMU_PERFCTR_INST_INT_LD				= 0x95,
+	M1_PMU_PERFCTR_INST_INT_ST				= 0x96,
+	M1_PMU_PERFCTR_INST_INT_ALU				= 0x97,
+	M1_PMU_PERFCTR_INST_SIMD_LD				= 0x98,
+	M1_PMU_PERFCTR_INST_SIMD_ST				= 0x99,
+	M1_PMU_PERFCTR_INST_SIMD_ALU				= 0x9a,
+	M1_PMU_PERFCTR_INST_LDST				= 0x9b,
+	M1_PMU_PERFCTR_INST_BARRIER				= 0x9c,
+	M1_PMU_PERFCTR_UNKNOWN_9f				= 0x9f,
+	M1_PMU_PERFCTR_L1D_TLB_ACCESS				= 0xa0,
+	M1_PMU_PERFCTR_L1D_TLB_MISS				= 0xa1,
+	M1_PMU_PERFCTR_L1D_CACHE_MISS_ST			= 0xa2,
+	M1_PMU_PERFCTR_L1D_CACHE_MISS_LD			= 0xa3,
+	M1_PMU_PERFCTR_LD_UNIT_UOP				= 0xa6,
+	M1_PMU_PERFCTR_ST_UNIT_UOP				= 0xa7,
+	M1_PMU_PERFCTR_L1D_CACHE_WRITEBACK			= 0xa8,
+	M1_PMU_PERFCTR_LDST_X64_UOP				= 0xb1,
+	M1_PMU_PERFCTR_LDST_XPG_UOP				= 0xb2,
+	M1_PMU_PERFCTR_ATOMIC_OR_EXCLUSIVE_SUCC			= 0xb3,
+	M1_PMU_PERFCTR_ATOMIC_OR_EXCLUSIVE_FAIL			= 0xb4,
+	M1_PMU_PERFCTR_L1D_CACHE_MISS_LD_NONSPEC		= 0xbf,
+	M1_PMU_PERFCTR_L1D_CACHE_MISS_ST_NONSPEC		= 0xc0,
+	M1_PMU_PERFCTR_L1D_TLB_MISS_NONSPEC			= 0xc1,
+	M1_PMU_PERFCTR_ST_MEMORY_ORDER_VIOLATION_NONSPEC	= 0xc4,
+	M1_PMU_PERFCTR_BRANCH_COND_MISPRED_NONSPEC		= 0xc5,
+	M1_PMU_PERFCTR_BRANCH_INDIR_MISPRED_NONSPEC		= 0xc6,
+	M1_PMU_PERFCTR_BRANCH_RET_INDIR_MISPRED_NONSPEC		= 0xc8,
+	M1_PMU_PERFCTR_BRANCH_CALL_INDIR_MISPRED_NONSPEC	= 0xca,
+	M1_PMU_PERFCTR_BRANCH_MISPRED_NONSPEC			= 0xcb,
+	M1_PMU_PERFCTR_L1I_TLB_MISS_DEMAND			= 0xd4,
+	M1_PMU_PERFCTR_MAP_DISPATCH_BUBBLE			= 0xd6,
+	M1_PMU_PERFCTR_L1I_CACHE_MISS_DEMAND			= 0xdb,
+	M1_PMU_PERFCTR_FETCH_RESTART				= 0xde,
+	M1_PMU_PERFCTR_ST_NT_UOP				= 0xe5,
+	M1_PMU_PERFCTR_LD_NT_UOP				= 0xe6,
+	M1_PMU_PERFCTR_UNKNOWN_f5				= 0xf5,
+	M1_PMU_PERFCTR_UNKNOWN_f6				= 0xf6,
+	M1_PMU_PERFCTR_UNKNOWN_f7				= 0xf7,
+	M1_PMU_PERFCTR_UNKNOWN_f8				= 0xf8,
+	M1_PMU_PERFCTR_UNKNOWN_fd				= 0xfd,
+	M1_PMU_PERFCTR_LAST					= M1_PMU_CFG_EVENT,
 
 	/*
 	 * From this point onwards, these are not actual HW events,
 	 * but attributes that get stored in hw->config_base.
 	 */
-	M1_PMU_CFG_COUNT_USER		= BIT(8),
-	M1_PMU_CFG_COUNT_KERNEL		= BIT(9),
+	M1_PMU_CFG_COUNT_USER					= BIT(8),
+	M1_PMU_CFG_COUNT_KERNEL					= BIT(9),
 };
 
 /*
@@ -96,46 +129,45 @@ enum m1_pmu_events {
  * counters had strange affinities.
  */
 static const u16 m1_pmu_event_affinity[M1_PMU_PERFCTR_LAST + 1] = {
-	[0 ... M1_PMU_PERFCTR_LAST]	= ANY_BUT_0_1,
-	[M1_PMU_PERFCTR_UNKNOWN_01]	= BIT(7),
-	[M1_PMU_PERFCTR_CPU_CYCLES]	= ANY_BUT_0_1 | BIT(0),
-	[M1_PMU_PERFCTR_INSTRUCTIONS]	= BIT(7) | BIT(1),
-	[M1_PMU_PERFCTR_UNKNOWN_8d]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_8e]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_8f]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_90]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_93]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_94]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_95]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_96]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_97]	= BIT(7),
-	[M1_PMU_PERFCTR_UNKNOWN_98]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_99]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_9a]	= BIT(7),
-	[M1_PMU_PERFCTR_UNKNOWN_9b]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_9c]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_9f]	= BIT(7),
-	[M1_PMU_PERFCTR_UNKNOWN_bf]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_c0]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_c1]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_c4]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_c5]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_c6]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_c8]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_ca]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_cb]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_f5]	= ONLY_2_4_6,
-	[M1_PMU_PERFCTR_UNKNOWN_f6]	= ONLY_2_4_6,
-	[M1_PMU_PERFCTR_UNKNOWN_f7]	= ONLY_2_4_6,
-	[M1_PMU_PERFCTR_UNKNOWN_f8]	= ONLY_2_TO_7,
-	[M1_PMU_PERFCTR_UNKNOWN_fd]	= ONLY_2_4_6,
+	[0 ... M1_PMU_PERFCTR_LAST]				= ANY_BUT_0_1,
+	[M1_PMU_PERFCTR_RETIRE_UOP]				= BIT(7),
+	[M1_PMU_PERFCTR_CORE_ACTIVE_CYCLE]			= ANY_BUT_0_1 | BIT(0),
+	[M1_PMU_PERFCTR_INST_ALL]				= BIT(7) | BIT(1),
+	[M1_PMU_PERFCTR_INST_BRANCH]				= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_INST_BRANCH_CALL]			= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_INST_BRANCH_RET]			= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_INST_BRANCH_TAKEN]			= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_INST_BRANCH_INDIR]			= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_INST_BRANCH_COND]			= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_INST_INT_LD]				= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_INST_INT_ST]				= BIT(7),
+	[M1_PMU_PERFCTR_INST_INT_ALU]				= BIT(7),
+	[M1_PMU_PERFCTR_INST_SIMD_LD]				= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_INST_SIMD_ST]				= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_INST_SIMD_ALU]				= BIT(7),
+	[M1_PMU_PERFCTR_INST_LDST]				= BIT(7),
+	[M1_PMU_PERFCTR_INST_BARRIER]				= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_UNKNOWN_9f]				= BIT(7),
+	[M1_PMU_PERFCTR_L1D_CACHE_MISS_LD_NONSPEC]		= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_L1D_CACHE_MISS_ST_NONSPEC]		= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_L1D_TLB_MISS_NONSPEC]			= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_ST_MEMORY_ORDER_VIOLATION_NONSPEC]	= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_BRANCH_COND_MISPRED_NONSPEC]		= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_BRANCH_INDIR_MISPRED_NONSPEC]		= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_BRANCH_RET_INDIR_MISPRED_NONSPEC]	= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_BRANCH_CALL_INDIR_MISPRED_NONSPEC]	= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_BRANCH_MISPRED_NONSPEC]			= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_UNKNOWN_f5]				= ONLY_2_4_6,
+	[M1_PMU_PERFCTR_UNKNOWN_f6]				= ONLY_2_4_6,
+	[M1_PMU_PERFCTR_UNKNOWN_f7]				= ONLY_2_4_6,
+	[M1_PMU_PERFCTR_UNKNOWN_f8]				= ONLY_2_TO_7,
+	[M1_PMU_PERFCTR_UNKNOWN_fd]				= ONLY_2_4_6,
 };
 
 static const unsigned m1_pmu_perf_map[PERF_COUNT_HW_MAX] = {
 	PERF_MAP_ALL_UNSUPPORTED,
-	[PERF_COUNT_HW_CPU_CYCLES]	= M1_PMU_PERFCTR_CPU_CYCLES,
-	[PERF_COUNT_HW_INSTRUCTIONS]	= M1_PMU_PERFCTR_INSTRUCTIONS,
-	/* No idea about the rest yet */
+	[PERF_COUNT_HW_CPU_CYCLES]		= M1_PMU_PERFCTR_CORE_ACTIVE_CYCLE,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= M1_PMU_PERFCTR_INST_ALL,
 };
 
 /* sysfs definitions */
@@ -154,8 +186,8 @@ static ssize_t m1_pmu_events_sysfs_show(struct device *dev,
 	PMU_EVENT_ATTR_ID(name, m1_pmu_events_sysfs_show, config)
 
 static struct attribute *m1_pmu_event_attrs[] = {
-	M1_PMU_EVENT_ATTR(cycles, M1_PMU_PERFCTR_CPU_CYCLES),
-	M1_PMU_EVENT_ATTR(instructions, M1_PMU_PERFCTR_INSTRUCTIONS),
+	M1_PMU_EVENT_ATTR(cycles, M1_PMU_PERFCTR_CORE_ACTIVE_CYCLE),
+	M1_PMU_EVENT_ATTR(instructions, M1_PMU_PERFCTR_INST_ALL),
 	NULL,
 };
 
@@ -400,7 +432,7 @@ static irqreturn_t m1_pmu_handle_irq(struct arm_pmu *cpu_pmu)
 
 	regs = get_irq_regs();
 
-	for (idx = 0; idx < cpu_pmu->num_events; idx++) {
+	for_each_set_bit(idx, cpu_pmu->cntr_mask, M1_PMU_NR_COUNTERS) {
 		struct perf_event *event = cpuc->events[idx];
 		struct perf_sample_data data;
 
@@ -560,7 +592,7 @@ static int m1_pmu_init(struct arm_pmu *cpu_pmu, u32 flags)
 	cpu_pmu->reset		  = m1_pmu_reset;
 	cpu_pmu->set_event_filter = m1_pmu_set_event_filter;
 
-	cpu_pmu->num_events	  = M1_PMU_NR_COUNTERS;
+	bitmap_set(cpu_pmu->cntr_mask, 0, M1_PMU_NR_COUNTERS);
 	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = &m1_pmu_events_attr_group;
 	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = &m1_pmu_format_attr_group;
 	return 0;

drivers/perf/arm_pmu.c

@@ -522,7 +522,7 @@ static void armpmu_enable(struct pmu *pmu)
 {
 	struct arm_pmu *armpmu = to_arm_pmu(pmu);
 	struct pmu_hw_events *hw_events = this_cpu_ptr(armpmu->hw_events);
-	bool enabled = !bitmap_empty(hw_events->used_mask, armpmu->num_events);
+	bool enabled = !bitmap_empty(hw_events->used_mask, ARMPMU_MAX_HWEVENTS);
 
 	/* For task-bound events we may be called on other CPUs */
 	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->supported_cpus))
@@ -742,7 +742,7 @@ static void cpu_pm_pmu_setup(struct arm_pmu *armpmu, unsigned long cmd)
 	struct perf_event *event;
 	int idx;
 
-	for (idx = 0; idx < armpmu->num_events; idx++) {
+	for_each_set_bit(idx, armpmu->cntr_mask, ARMPMU_MAX_HWEVENTS) {
 		event = hw_events->events[idx];
 		if (!event)
 			continue;
@@ -772,7 +772,7 @@ static int cpu_pm_pmu_notify(struct notifier_block *b, unsigned long cmd,
 {
 	struct arm_pmu *armpmu = container_of(b, struct arm_pmu, cpu_pm_nb);
 	struct pmu_hw_events *hw_events = this_cpu_ptr(armpmu->hw_events);
-	bool enabled = !bitmap_empty(hw_events->used_mask, armpmu->num_events);
+	bool enabled = !bitmap_empty(hw_events->used_mask, ARMPMU_MAX_HWEVENTS);
 
 	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->supported_cpus))
 		return NOTIFY_DONE;
@@ -924,8 +924,9 @@ int armpmu_register(struct arm_pmu *pmu)
 	if (ret)
 		goto out_destroy;
 
-	pr_info("enabled with %s PMU driver, %d counters available%s\n",
-		pmu->name, pmu->num_events,
+	pr_info("enabled with %s PMU driver, %d (%*pb) counters available%s\n",
+		pmu->name, bitmap_weight(pmu->cntr_mask, ARMPMU_MAX_HWEVENTS),
+		ARMPMU_MAX_HWEVENTS, &pmu->cntr_mask,
 		has_nmi ? ", using NMIs" : "");
 
 	kvm_host_pmu_init(pmu);

drivers/perf/arm_pmu_platform.c

@@ -59,7 +59,7 @@ static int pmu_parse_percpu_irq(struct arm_pmu *pmu, int irq)
 
 static bool pmu_has_irq_affinity(struct device_node *node)
 {
-	return !!of_find_property(node, "interrupt-affinity", NULL);
+	return of_property_present(node, "interrupt-affinity");
 }
 
 static int pmu_parse_irq_affinity(struct device *dev, int i)

drivers/perf/arm_spe_pmu.c

@@ -41,7 +41,7 @@
 
 /*
  * Cache if the event is allowed to trace Context information.
- * This allows us to perform the check, i.e, perfmon_capable(),
+ * This allows us to perform the check, i.e, perf_allow_kernel(),
  * in the context of the event owner, once, during the event_init().
  */
 #define SPE_PMU_HW_FLAGS_CX			0x00001
@@ -50,7 +50,7 @@ static_assert((PERF_EVENT_FLAG_ARCH & SPE_PMU_HW_FLAGS_CX) == SPE_PMU_HW_FLAGS_C
 
 static void set_spe_event_has_cx(struct perf_event *event)
 {
-	if (IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR) && perfmon_capable())
+	if (IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR) && !perf_allow_kernel(&event->attr))
 		event->hw.flags |= SPE_PMU_HW_FLAGS_CX;
 }
 
@@ -745,9 +745,8 @@ static int arm_spe_pmu_event_init(struct perf_event *event)
 
 	set_spe_event_has_cx(event);
 	reg = arm_spe_event_to_pmscr(event);
-	if (!perfmon_capable() &&
-	    (reg & (PMSCR_EL1_PA | PMSCR_EL1_PCT)))
-		return -EACCES;
+	if (reg & (PMSCR_EL1_PA | PMSCR_EL1_PCT))
+		return perf_allow_kernel(&event->attr);
 
 	return 0;
 }

drivers/perf/arm_v6_pmu.c

@@ -64,6 +64,7 @@ enum armv6_counters {
 	ARMV6_CYCLE_COUNTER = 0,
 	ARMV6_COUNTER0,
 	ARMV6_COUNTER1,
+	ARMV6_NUM_COUNTERS
 };
 
 /*
@@ -254,7 +255,7 @@ armv6pmu_handle_irq(struct arm_pmu *cpu_pmu)
 	 */
 	armv6_pmcr_write(pmcr);
 
-	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
+	for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMV6_NUM_COUNTERS) {
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
@@ -391,7 +392,8 @@ static void armv6pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->start		= armv6pmu_start;
 	cpu_pmu->stop		= armv6pmu_stop;
 	cpu_pmu->map_event	= armv6_map_event;
-	cpu_pmu->num_events	= 3;
+
+	bitmap_set(cpu_pmu->cntr_mask, 0, ARMV6_NUM_COUNTERS);
 }
 
 static int armv6_1136_pmu_init(struct arm_pmu *cpu_pmu)

drivers/perf/arm_v7_pmu.c

@@ -649,24 +649,12 @@ static struct attribute_group armv7_pmuv2_events_attr_group = {
 /*
  * Perf Events' indices
  */
-#define	ARMV7_IDX_CYCLE_COUNTER	0
-#define	ARMV7_IDX_COUNTER0	1
-#define	ARMV7_IDX_COUNTER_LAST(cpu_pmu) \
-	(ARMV7_IDX_CYCLE_COUNTER + cpu_pmu->num_events - 1)
-
-#define	ARMV7_MAX_COUNTERS	32
-#define	ARMV7_COUNTER_MASK	(ARMV7_MAX_COUNTERS - 1)
-
+#define	ARMV7_IDX_CYCLE_COUNTER	31
+#define	ARMV7_IDX_COUNTER_MAX	31
 /*
  * ARMv7 low level PMNC access
  */
 
-/*
- * Perf Event to low level counters mapping
- */
-#define	ARMV7_IDX_TO_COUNTER(x)	\
-	(((x) - ARMV7_IDX_COUNTER0) & ARMV7_COUNTER_MASK)
-
 /*
  * Per-CPU PMNC: config reg
  */
@@ -725,19 +713,17 @@ static inline int armv7_pmnc_has_overflowed(u32 pmnc)
 
 static inline int armv7_pmnc_counter_valid(struct arm_pmu *cpu_pmu, int idx)
 {
-	return idx >= ARMV7_IDX_CYCLE_COUNTER &&
-		idx <= ARMV7_IDX_COUNTER_LAST(cpu_pmu);
+	return test_bit(idx, cpu_pmu->cntr_mask);
 }
 
 static inline int armv7_pmnc_counter_has_overflowed(u32 pmnc, int idx)
 {
-	return pmnc & BIT(ARMV7_IDX_TO_COUNTER(idx));
+	return pmnc & BIT(idx);
 }
 
 static inline void armv7_pmnc_select_counter(int idx)
 {
-	u32 counter = ARMV7_IDX_TO_COUNTER(idx);
-	asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (counter));
+	asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (idx));
 	isb();
 }
 
@@ -787,29 +773,25 @@ static inline void armv7_pmnc_write_evtsel(int idx, u32 val)
 
 static inline void armv7_pmnc_enable_counter(int idx)
 {
-	u32 counter = ARMV7_IDX_TO_COUNTER(idx);
-	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (BIT(counter)));
+	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (BIT(idx)));
 }
 
 static inline void armv7_pmnc_disable_counter(int idx)
 {
-	u32 counter = ARMV7_IDX_TO_COUNTER(idx);
-	asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (BIT(counter)));
+	asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (BIT(idx)));
 }
 
 static inline void armv7_pmnc_enable_intens(int idx)
 {
-	u32 counter = ARMV7_IDX_TO_COUNTER(idx);
-	asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (BIT(counter)));
+	asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (BIT(idx)));
 }
 
 static inline void armv7_pmnc_disable_intens(int idx)
 {
-	u32 counter = ARMV7_IDX_TO_COUNTER(idx);
-	asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (BIT(counter)));
+	asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (BIT(idx)));
 	isb();
 	/* Clear the overflow flag in case an interrupt is pending. */
-	asm volatile("mcr p15, 0, %0, c9, c12, 3" : : "r" (BIT(counter)));
+	asm volatile("mcr p15, 0, %0, c9, c12, 3" : : "r" (BIT(idx)));
 	isb();
 }
 
@@ -853,15 +835,12 @@ static void armv7_pmnc_dump_regs(struct arm_pmu *cpu_pmu)
 	asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val));
 	pr_info("CCNT  =0x%08x\n", val);
 
-	for (cnt = ARMV7_IDX_COUNTER0;
-			cnt <= ARMV7_IDX_COUNTER_LAST(cpu_pmu); cnt++) {
+	for_each_set_bit(cnt, cpu_pmu->cntr_mask, ARMV7_IDX_COUNTER_MAX) {
 		armv7_pmnc_select_counter(cnt);
 		asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (val));
-		pr_info("CNT[%d] count =0x%08x\n",
-			ARMV7_IDX_TO_COUNTER(cnt), val);
+		pr_info("CNT[%d] count =0x%08x\n", cnt, val);
 		asm volatile("mrc p15, 0, %0, c9, c13, 1" : "=r" (val));
-		pr_info("CNT[%d] evtsel=0x%08x\n",
-			ARMV7_IDX_TO_COUNTER(cnt), val);
+		pr_info("CNT[%d] evtsel=0x%08x\n", cnt, val);
 	}
 }
 #endif
@@ -958,7 +937,7 @@ static irqreturn_t armv7pmu_handle_irq(struct arm_pmu *cpu_pmu)
 	 */
 	regs = get_irq_regs();
 
-	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
+	for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMPMU_MAX_HWEVENTS) {
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
@@ -1027,7 +1006,7 @@ static int armv7pmu_get_event_idx(struct pmu_hw_events *cpuc,
 	 * For anything other than a cycle counter, try and use
 	 * the events counters
 	 */
-	for (idx = ARMV7_IDX_COUNTER0; idx < cpu_pmu->num_events; ++idx) {
+	for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMV7_IDX_COUNTER_MAX) {
 		if (!test_and_set_bit(idx, cpuc->used_mask))
 			return idx;
 	}
@@ -1073,7 +1052,7 @@ static int armv7pmu_set_event_filter(struct hw_perf_event *event,
 static void armv7pmu_reset(void *info)
 {
 	struct arm_pmu *cpu_pmu = (struct arm_pmu *)info;
-	u32 idx, nb_cnt = cpu_pmu->num_events, val;
+	u32 idx, val;
 
 	if (cpu_pmu->secure_access) {
 		asm volatile("mrc p15, 0, %0, c1, c1, 1" : "=r" (val));
@@ -1082,7 +1061,7 @@ static void armv7pmu_reset(void *info)
 	}
 
 	/* The counter and interrupt enable registers are unknown at reset. */
-	for (idx = ARMV7_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx) {
+	for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMPMU_MAX_HWEVENTS) {
 		armv7_pmnc_disable_counter(idx);
 		armv7_pmnc_disable_intens(idx);
 	}
@@ -1161,20 +1140,22 @@ static void armv7pmu_init(struct arm_pmu *cpu_pmu)
 
 static void armv7_read_num_pmnc_events(void *info)
 {
-	int *nb_cnt = info;
+	int nb_cnt;
+	struct arm_pmu *cpu_pmu = info;
 
 	/* Read the nb of CNTx counters supported from PMNC */
-	*nb_cnt = (armv7_pmnc_read() >> ARMV7_PMNC_N_SHIFT) & ARMV7_PMNC_N_MASK;
+	nb_cnt = (armv7_pmnc_read() >> ARMV7_PMNC_N_SHIFT) & ARMV7_PMNC_N_MASK;
+	bitmap_set(cpu_pmu->cntr_mask, 0, nb_cnt);
 
 	/* Add the CPU cycles counter */
-	*nb_cnt += 1;
+	set_bit(ARMV7_IDX_CYCLE_COUNTER, cpu_pmu->cntr_mask);
 }
 
 static int armv7_probe_num_events(struct arm_pmu *arm_pmu)
 {
 	return smp_call_function_any(&arm_pmu->supported_cpus,
 				     armv7_read_num_pmnc_events,
-				     &arm_pmu->num_events, 1);
+				     arm_pmu, 1);
 }
 
 static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu)
@@ -1524,7 +1505,7 @@ static void krait_pmu_reset(void *info)
 {
 	u32 vval, fval;
 	struct arm_pmu *cpu_pmu = info;
-	u32 idx, nb_cnt = cpu_pmu->num_events;
+	u32 idx;
 
 	armv7pmu_reset(info);
 
@@ -1538,7 +1519,7 @@ static void krait_pmu_reset(void *info)
 	venum_post_pmresr(vval, fval);
 
 	/* Reset PMxEVNCTCR to sane default */
-	for (idx = ARMV7_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx) {
+	for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMV7_IDX_COUNTER_MAX) {
 		armv7_pmnc_select_counter(idx);
 		asm volatile("mcr p15, 0, %0, c9, c15, 0" : : "r" (0));
 	}
@@ -1562,7 +1543,7 @@ static int krait_event_to_bit(struct perf_event *event, unsigned int region,
 	 * Lower bits are reserved for use by the counters (see
 	 * armv7pmu_get_event_idx() for more info)
 	 */
-	bit += ARMV7_IDX_COUNTER_LAST(cpu_pmu) + 1;
+	bit += bitmap_weight(cpu_pmu->cntr_mask, ARMV7_IDX_COUNTER_MAX);
 
 	return bit;
 }
@@ -1845,7 +1826,7 @@ static void scorpion_pmu_reset(void *info)
 {
 	u32 vval, fval;
 	struct arm_pmu *cpu_pmu = info;
-	u32 idx, nb_cnt = cpu_pmu->num_events;
+	u32 idx;
 
 	armv7pmu_reset(info);
 
@@ -1860,7 +1841,7 @@ static void scorpion_pmu_reset(void *info)
 	venum_post_pmresr(vval, fval);
 
 	/* Reset PMxEVNCTCR to sane default */
-	for (idx = ARMV7_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx) {
+	for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMV7_IDX_COUNTER_MAX) {
 		armv7_pmnc_select_counter(idx);
 		asm volatile("mcr p15, 0, %0, c9, c15, 0" : : "r" (0));
 	}
@@ -1883,7 +1864,7 @@ static int scorpion_event_to_bit(struct perf_event *event, unsigned int region,
 	 * Lower bits are reserved for use by the counters (see
 	 * armv7pmu_get_event_idx() for more info)
 	 */
-	bit += ARMV7_IDX_COUNTER_LAST(cpu_pmu) + 1;
+	bit += bitmap_weight(cpu_pmu->cntr_mask, ARMV7_IDX_COUNTER_MAX);
 
 	return bit;
 }

drivers/perf/arm_xscale_pmu.c

@@ -53,6 +53,8 @@ enum xscale_counters {
 	XSCALE_COUNTER2,
 	XSCALE_COUNTER3,
 };
+#define XSCALE1_NUM_COUNTERS	3
+#define XSCALE2_NUM_COUNTERS	5
 
 static const unsigned xscale_perf_map[PERF_COUNT_HW_MAX] = {
 	PERF_MAP_ALL_UNSUPPORTED,
@@ -168,7 +170,7 @@ xscale1pmu_handle_irq(struct arm_pmu *cpu_pmu)
 
 	regs = get_irq_regs();
 
-	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
+	for_each_set_bit(idx, cpu_pmu->cntr_mask, XSCALE1_NUM_COUNTERS) {
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
@@ -364,7 +366,8 @@ static int xscale1pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->start		= xscale1pmu_start;
 	cpu_pmu->stop		= xscale1pmu_stop;
 	cpu_pmu->map_event	= xscale_map_event;
-	cpu_pmu->num_events	= 3;
+
+	bitmap_set(cpu_pmu->cntr_mask, 0, XSCALE1_NUM_COUNTERS);
 
 	return 0;
 }
@@ -500,7 +503,7 @@ xscale2pmu_handle_irq(struct arm_pmu *cpu_pmu)
 
 	regs = get_irq_regs();
 
-	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
+	for_each_set_bit(idx, cpu_pmu->cntr_mask, XSCALE2_NUM_COUNTERS) {
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
@@ -719,7 +722,8 @@ static int xscale2pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->start		= xscale2pmu_start;
 	cpu_pmu->stop		= xscale2pmu_stop;
 	cpu_pmu->map_event	= xscale_map_event;
-	cpu_pmu->num_events	= 5;
+
+	bitmap_set(cpu_pmu->cntr_mask, 0, XSCALE2_NUM_COUNTERS);
 
 	return 0;
 }

drivers/perf/dwc_pcie_pmu.c

@@ -107,6 +107,7 @@ struct dwc_pcie_vendor_id {
 
 static const struct dwc_pcie_vendor_id dwc_pcie_vendor_ids[] = {
 	{.vendor_id = PCI_VENDOR_ID_ALIBABA },
+	{.vendor_id = PCI_VENDOR_ID_QCOM },
 	{} /* terminator */
 };
 
@@ -556,10 +557,10 @@ static int dwc_pcie_register_dev(struct pci_dev *pdev)
 {
 	struct platform_device *plat_dev;
 	struct dwc_pcie_dev_info *dev_info;
-	u32 bdf;
+	u32 sbdf;
 
-	bdf = PCI_DEVID(pdev->bus->number, pdev->devfn);
-	plat_dev = platform_device_register_data(NULL, "dwc_pcie_pmu", bdf,
+	sbdf = (pci_domain_nr(pdev->bus) << 16) | PCI_DEVID(pdev->bus->number, pdev->devfn);
+	plat_dev = platform_device_register_data(NULL, "dwc_pcie_pmu", sbdf,
 						 pdev, sizeof(*pdev));
 
 	if (IS_ERR(plat_dev))
@@ -611,15 +612,15 @@ static int dwc_pcie_pmu_probe(struct platform_device *plat_dev)
 	struct pci_dev *pdev = plat_dev->dev.platform_data;
 	struct dwc_pcie_pmu *pcie_pmu;
 	char *name;
-	u32 bdf, val;
+	u32 sbdf, val;
 	u16 vsec;
 	int ret;
 
 	vsec = pci_find_vsec_capability(pdev, pdev->vendor,
 					DWC_PCIE_VSEC_RAS_DES_ID);
 	pci_read_config_dword(pdev, vsec + PCI_VNDR_HEADER, &val);
-	bdf = PCI_DEVID(pdev->bus->number, pdev->devfn);
-	name = devm_kasprintf(&plat_dev->dev, GFP_KERNEL, "dwc_rootport_%x", bdf);
+	sbdf = plat_dev->id;
+	name = devm_kasprintf(&plat_dev->dev, GFP_KERNEL, "dwc_rootport_%x", sbdf);
 	if (!name)
 		return -ENOMEM;
 
@@ -650,7 +651,7 @@ static int dwc_pcie_pmu_probe(struct platform_device *plat_dev)
 	ret = cpuhp_state_add_instance(dwc_pcie_pmu_hp_state,
 				       &pcie_pmu->cpuhp_node);
 	if (ret) {
-		pci_err(pdev, "Error %d registering hotplug @%x\n", ret, bdf);
+		pci_err(pdev, "Error %d registering hotplug @%x\n", ret, sbdf);
 		return ret;
 	}
 
@@ -663,7 +664,7 @@ static int dwc_pcie_pmu_probe(struct platform_device *plat_dev)
 
 	ret = perf_pmu_register(&pcie_pmu->pmu, name, -1);
 	if (ret) {
-		pci_err(pdev, "Error %d registering PMU @%x\n", ret, bdf);
+		pci_err(pdev, "Error %d registering PMU @%x\n", ret, sbdf);
 		return ret;
 	}
 	ret = devm_add_action_or_reset(&plat_dev->dev, dwc_pcie_unregister_pmu,
@@ -726,7 +727,6 @@ static struct platform_driver dwc_pcie_pmu_driver = {
 static int __init dwc_pcie_pmu_init(void)
 {
 	struct pci_dev *pdev = NULL;
-	bool found = false;
 	int ret;
 
 	for_each_pci_dev(pdev) {
@@ -738,11 +738,7 @@ static int __init dwc_pcie_pmu_init(void)
 			pci_dev_put(pdev);
 			return ret;
 		}
-
-		found = true;
 	}
-	if (!found)
-		return -ENODEV;
 
 	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
 				      "perf/dwc_pcie_pmu:online",

drivers/perf/hisilicon/hisi_pcie_pmu.c

@@ -141,6 +141,22 @@ static ssize_t bus_show(struct device *dev, struct device_attribute *attr, char
 }
 static DEVICE_ATTR_RO(bus);
 
+static ssize_t bdf_min_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(dev_get_drvdata(dev));
+
+	return sysfs_emit(buf, "%#04x\n", pcie_pmu->bdf_min);
+}
+static DEVICE_ATTR_RO(bdf_min);
+
+static ssize_t bdf_max_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(dev_get_drvdata(dev));
+
+	return sysfs_emit(buf, "%#04x\n", pcie_pmu->bdf_max);
+}
+static DEVICE_ATTR_RO(bdf_max);
+
 static struct hisi_pcie_reg_pair
 hisi_pcie_parse_reg_value(struct hisi_pcie_pmu *pcie_pmu, u32 reg_off)
 {
@@ -208,7 +224,7 @@ static void hisi_pcie_pmu_writeq(struct hisi_pcie_pmu *pcie_pmu, u32 reg_offset,
 static u64 hisi_pcie_pmu_get_event_ctrl_val(struct perf_event *event)
 {
 	u64 port, trig_len, thr_len, len_mode;
-	u64 reg = HISI_PCIE_INIT_SET;
+	u64 reg = 0;
 
 	/* Config HISI_PCIE_EVENT_CTRL according to event. */
 	reg |= FIELD_PREP(HISI_PCIE_EVENT_M, hisi_pcie_get_real_event(event));
@@ -452,10 +468,24 @@ static void hisi_pcie_pmu_set_period(struct perf_event *event)
 	struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
+	u64 orig_cnt, cnt;
+
+	orig_cnt = hisi_pcie_pmu_read_counter(event);
 
 	local64_set(&hwc->prev_count, HISI_PCIE_INIT_VAL);
 	hisi_pcie_pmu_writeq(pcie_pmu, HISI_PCIE_CNT, idx, HISI_PCIE_INIT_VAL);
 	hisi_pcie_pmu_writeq(pcie_pmu, HISI_PCIE_EXT_CNT, idx, HISI_PCIE_INIT_VAL);
+
+	/*
+	 * The counter maybe unwritable if the target event is unsupported.
+	 * Check this by comparing the counts after setting the period. If
+	 * the counts stay unchanged after setting the period then update
+	 * the hwc->prev_count correctly. Otherwise the final counts user
+	 * get maybe totally wrong.
+	 */
+	cnt = hisi_pcie_pmu_read_counter(event);
+	if (orig_cnt == cnt)
+		local64_set(&hwc->prev_count, cnt);
 }
 
 static void hisi_pcie_pmu_enable_counter(struct hisi_pcie_pmu *pcie_pmu, struct hw_perf_event *hwc)
@@ -749,6 +779,8 @@ static const struct attribute_group hisi_pcie_pmu_format_group = {
 
 static struct attribute *hisi_pcie_pmu_bus_attrs[] = {
 	&dev_attr_bus.attr,
+	&dev_attr_bdf_max.attr,
+	&dev_attr_bdf_min.attr,
 	NULL
 };
 

include/kvm/arm_pmu.h

@@ -10,7 +10,7 @@
 #include <linux/perf_event.h>
 #include <linux/perf/arm_pmuv3.h>
 
-#define ARMV8_PMU_CYCLE_IDX		(ARMV8_PMU_MAX_COUNTERS - 1)
+#define KVM_ARMV8_PMU_MAX_COUNTERS	32
 
 #if IS_ENABLED(CONFIG_HW_PERF_EVENTS) && IS_ENABLED(CONFIG_KVM)
 struct kvm_pmc {
@@ -19,14 +19,14 @@ struct kvm_pmc {
 };
 
 struct kvm_pmu_events {
-	u32 events_host;
-	u32 events_guest;
+	u64 events_host;
+	u64 events_guest;
 };
 
 struct kvm_pmu {
 	struct irq_work overflow_work;
 	struct kvm_pmu_events events;
-	struct kvm_pmc pmc[ARMV8_PMU_MAX_COUNTERS];
+	struct kvm_pmc pmc[KVM_ARMV8_PMU_MAX_COUNTERS];
 	int irq_num;
 	bool created;
 	bool irq_level;

include/linux/perf/arm_pmu.h

@@ -17,10 +17,14 @@
 #ifdef CONFIG_ARM_PMU
 
 /*
- * The ARMv7 CPU PMU supports up to 32 event counters.
+ * The Armv7 and Armv8.8 or less CPU PMU supports up to 32 event counters.
+ * The Armv8.9/9.4 CPU PMU supports up to 33 event counters.
  */
+#ifdef CONFIG_ARM
 #define ARMPMU_MAX_HWEVENTS		32
-
+#else
+#define ARMPMU_MAX_HWEVENTS		33
+#endif
 /*
  * ARM PMU hw_event flags
  */
@@ -96,7 +100,7 @@ struct arm_pmu {
 	void		(*stop)(struct arm_pmu *);
 	void		(*reset)(void *);
 	int		(*map_event)(struct perf_event *event);
-	int		num_events;
+	DECLARE_BITMAP(cntr_mask, ARMPMU_MAX_HWEVENTS);
 	bool		secure_access; /* 32-bit ARM only */
 #define ARMV8_PMUV3_MAX_COMMON_EVENTS		0x40
 	DECLARE_BITMAP(pmceid_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS);

include/linux/perf/arm_pmuv3.h

@@ -6,8 +6,9 @@
 #ifndef __PERF_ARM_PMUV3_H
 #define __PERF_ARM_PMUV3_H
 
-#define ARMV8_PMU_MAX_COUNTERS	32
-#define ARMV8_PMU_COUNTER_MASK	(ARMV8_PMU_MAX_COUNTERS - 1)
+#define ARMV8_PMU_MAX_GENERAL_COUNTERS	31
+#define ARMV8_PMU_CYCLE_IDX		31
+#define ARMV8_PMU_INSTR_IDX		32 /* Not accessible from AArch32 */
 
 /*
  * Common architectural and microarchitectural event numbers.
@@ -227,8 +228,10 @@
  */
 #define ARMV8_PMU_OVSR_P		GENMASK(30, 0)
 #define ARMV8_PMU_OVSR_C		BIT(31)
+#define ARMV8_PMU_OVSR_F		BIT_ULL(32) /* arm64 only */
 /* Mask for writable bits is both P and C fields */
-#define ARMV8_PMU_OVERFLOWED_MASK	(ARMV8_PMU_OVSR_P | ARMV8_PMU_OVSR_C)
+#define ARMV8_PMU_OVERFLOWED_MASK	(ARMV8_PMU_OVSR_P | ARMV8_PMU_OVSR_C | \
+					ARMV8_PMU_OVSR_F)
 
 /*
  * PMXEVTYPER: Event selection reg

include/linux/perf_event.h

@@ -1602,13 +1602,7 @@ static inline int perf_is_paranoid(void)
 	return sysctl_perf_event_paranoid > -1;
 }
 
-static inline int perf_allow_kernel(struct perf_event_attr *attr)
-{
-	if (sysctl_perf_event_paranoid > 1 && !perfmon_capable())
-		return -EACCES;
-
-	return security_perf_event_open(attr, PERF_SECURITY_KERNEL);
-}
+int perf_allow_kernel(struct perf_event_attr *attr);
 
 static inline int perf_allow_cpu(struct perf_event_attr *attr)
 {

kernel/events/core.c

@@ -13351,6 +13351,15 @@ const struct perf_event_attr *perf_event_attrs(struct perf_event *event)
 	return &event->attr;
 }
 
+int perf_allow_kernel(struct perf_event_attr *attr)
+{
+	if (sysctl_perf_event_paranoid > 1 && !perfmon_capable())
+		return -EACCES;
+
+	return security_perf_event_open(attr, PERF_SECURITY_KERNEL);
+}
+EXPORT_SYMBOL_GPL(perf_allow_kernel);
+
 /*
  * Inherit an event from parent task to child task.
  *