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
  ...

Author: willdeacon

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

@@ -0,0 +1,17 @@
+====================================
+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

@@ -0,0 +1,30 @@
+# 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 <[email protected]>
+
+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 <[email protected]>
+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 <[email protected]>
 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;