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
  ...

7 files changed, 115 insertions, 89 deletions

diff --git a/arch/arm64/include/asm/arm_pmuv3.h b/arch/arm64/include/asm/arm_pmuv3.h
index a4697a0b6835..468a049bc63b 100644
--- a/arch/arm64/include/asm/arm_pmuv3.h
+++ b/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);
 }
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index a33f5996ca9f..c0fc753aac87 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/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;
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 4a9ea103817e..00af1c331c1e 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/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)
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 82a2a003259c..ac36c438b8c1 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/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)
diff --git a/arch/arm64/kvm/pmu.c b/arch/arm64/kvm/pmu.c
index 329819806096..0b3adf3e17b4 100644
--- a/arch/arm64/kvm/pmu.c
+++ b/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;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index c90324060436..7db24de37ed6 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/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);
diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg
index 7ceaa1e0b4bc..8d637ac4b7c6 100644
--- a/arch/arm64/tools/sysreg
+++ b/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