Merge tag 'perf-tools-fixes-for-v6.4-1-2023-05-20' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Fail graciously if BUILD_BPF_SKEL=1 is specified and clang isn't
   available

 - Add empty 'struct rq' to 'perf lock contention' to satisfy libbpf
   'runqueue' type verification. This feature is built only with
   BUILD_BPF_SKEL=1

 - Make vmlinux.h use bpf.h and perf_event.h in source directory, not
   system ones that may be old and not have things like 'union
   perf_sample_weight'

 - Add system include paths to BPF builds to pick things missing in the
   headers included by clang -target bpf

 - Update various header copies with the kernel sources

 - Change divide by zero and not supported events behavior to show
   'nan'/'not counted' in 'perf stat' output.

   This happens when using things like 'perf stat -M TopdownL2 true',
   involving JSON metrics

 - Update no event/metric expectations affected by using JSON metrics in
   'perf stat -ddd' perf test

 - Avoid segv with 'perf stat --topdown' for metrics without a group

 - Do not assume which events may have a PMU name, allowing the logic to
   keep an AUX event group together. Makes this usecase work again:

     $ perf record --no-bpf-event -c 10 -e '{intel_pt//,tlb_flush.stlb_any/aux-sample-size=8192/pp}:u' -- sleep 0.1
     [ perf record: Woken up 1 times to write data ]
     [ perf record: Captured and wrote 0.078 MB perf.data ]
     $ perf script -F-dso,+addr | grep -C5 tlb_flush.stlb_any | head -11
     sleep 20444 [003]  7939.510243:  1  branches:uH:  7f5350cc82a2 dl_main+0x9a2 => 7f5350cb38f0 _dl_add_to_namespace_list+0x0
     sleep 20444 [003]  7939.510243:  1  branches:uH:  7f5350cb3908 _dl_add_to_namespace_list+0x18 => 7f5350cbb080 rtld_mutex_dummy+0x0
     sleep 20444 [003]  7939.510243:  1  branches:uH:  7f5350cc8350 dl_main+0xa50 => 0 [unknown]
     sleep 20444 [003]  7939.510244:  1  branches:uH:  7f5350cc83ca dl_main+0xaca => 7f5350caeb60 _dl_process_pt_gnu_property+0x0
     sleep 20444 [003]  7939.510245:  1  branches:uH:  7f5350caeb60 _dl_process_pt_gnu_property+0x0 => 0 [unknown]
     sleep 20444  7939.510245:       10 tlb_flush.stlb_any/aux-sample-size=8192/pp: 0 7f5350caeb60 _dl_process_pt_gnu_property+0x0
     sleep 20444 [003]  7939.510254:  1  branches:uH:  7f5350cc87fe dl_main+0xefe => 7f5350ccd240 strcmp+0x0
     sleep 20444 [003]  7939.510254:  1  branches:uH:  7f5350cc8862 dl_main+0xf62 => 0 [unknown]

 - Add a check for the above use case in 'perf test test_intel_pt'

 - Fix build with refcount checking on arm64, it was still accessing
   fields that need to be wrapped so that the refcounted struct gets
   checked

 - Fix contextid validation in ARM's CS-ETM, so that older kernels
   without that field can still be supported

 - Skip unsupported aggregation for stat events found in perf.data files
   in 'perf script'

 - Add stat test for record and script to check the previous problem

 - Remove needless debuginfod queries from 'perf test java symbol', this
   was just making the test take a long time to complete

 - Address python SafeConfigParser() deprecation warning in 'perf test
   attr'

 - Fix __NR_execve undeclared on i386 'perf bench syscall' build error

* tag 'perf-tools-fixes-for-v6.4-1-2023-05-20' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (33 commits)
  perf bench syscall: Fix __NR_execve undeclared build error
  perf test attr: Fix python SafeConfigParser() deprecation warning
  perf test attr: Update no event/metric expectations
  tools headers disabled-features: Sync with the kernel sources
  tools headers UAPI: Sync arch prctl headers with the kernel sources
  tools headers: Update the copy of x86's mem{cpy,set}_64.S used in 'perf bench'
  tools headers x86 cpufeatures: Sync with the kernel sources
  tools headers UAPI: Sync s390 syscall table file that wires up the memfd_secret syscall
  tools headers UAPI: Sync linux/prctl.h with the kernel sources
  perf metrics: Avoid segv with --topdown for metrics without a group
  perf lock contention: Add empty 'struct rq' to satisfy libbpf 'runqueue' type verification
  perf cs-etm: Fix contextid validation
  perf arm64: Fix build with refcount checking
  perf test: Add stat test for record and script
  perf script: Skip aggregation for stat events
  perf build: Add system include paths to BPF builds
  perf bpf skels: Make vmlinux.h use bpf.h and perf_event.h in source directory
  perf parse-events: Do not break up AUX event group
  perf test test_intel_pt.sh: Test sample mode with event with PMU name
  perf evsel: Modify group pmu name for software events
  ...

71 files changed, 865 insertions, 322 deletions

diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index f8129c624b07..f7ddd73a8c0f 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -198,6 +198,15 @@ struct kvm_arm_copy_mte_tags {
 	__u64 reserved[2];
 };
 
+/*
+ * Counter/Timer offset structure. Describe the virtual/physical offset.
+ * To be used with KVM_ARM_SET_COUNTER_OFFSET.
+ */
+struct kvm_arm_counter_offset {
+	__u64 counter_offset;
+	__u64 reserved;
+};
+
 #define KVM_ARM_TAGS_TO_GUEST		0
 #define KVM_ARM_TAGS_FROM_GUEST		1
 
@@ -372,6 +381,10 @@ enum {
 #endif
 };
 
+/* Device Control API on vm fd */
+#define KVM_ARM_VM_SMCCC_CTRL		0
+#define   KVM_ARM_VM_SMCCC_FILTER	0
+
 /* Device Control API: ARM VGIC */
 #define KVM_DEV_ARM_VGIC_GRP_ADDR	0
 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS	1
@@ -411,6 +424,8 @@ enum {
 #define KVM_ARM_VCPU_TIMER_CTRL		1
 #define   KVM_ARM_VCPU_TIMER_IRQ_VTIMER		0
 #define   KVM_ARM_VCPU_TIMER_IRQ_PTIMER		1
+#define   KVM_ARM_VCPU_TIMER_IRQ_HVTIMER	2
+#define   KVM_ARM_VCPU_TIMER_IRQ_HPTIMER	3
 #define KVM_ARM_VCPU_PVTIME_CTRL	2
 #define   KVM_ARM_VCPU_PVTIME_IPA	0
 
@@ -469,6 +484,27 @@ enum {
 /* run->fail_entry.hardware_entry_failure_reason codes. */
 #define KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED	(1ULL << 0)
 
+enum kvm_smccc_filter_action {
+	KVM_SMCCC_FILTER_HANDLE = 0,
+	KVM_SMCCC_FILTER_DENY,
+	KVM_SMCCC_FILTER_FWD_TO_USER,
+
+#ifdef __KERNEL__
+	NR_SMCCC_FILTER_ACTIONS
+#endif
+};
+
+struct kvm_smccc_filter {
+	__u32 base;
+	__u32 nr_functions;
+	__u8 action;
+	__u8 pad[15];
+};
+
+/* arm64-specific KVM_EXIT_HYPERCALL flags */
+#define KVM_HYPERCALL_EXIT_SMC		(1U << 0)
+#define KVM_HYPERCALL_EXIT_16BIT	(1U << 1)
+
 #endif
 
 #endif /* __ARM_KVM_H__ */
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index b89005819cd5..cb8ca46213be 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -97,7 +97,7 @@
 #define X86_FEATURE_SYSENTER32		( 3*32+15) /* "" sysenter in IA32 userspace */
 #define X86_FEATURE_REP_GOOD		( 3*32+16) /* REP microcode works well */
 #define X86_FEATURE_AMD_LBR_V2		( 3*32+17) /* AMD Last Branch Record Extension Version 2 */
-#define X86_FEATURE_LFENCE_RDTSC	( 3*32+18) /* "" LFENCE synchronizes RDTSC */
+/* FREE, was #define X86_FEATURE_LFENCE_RDTSC		( 3*32+18) "" LFENCE synchronizes RDTSC */
 #define X86_FEATURE_ACC_POWER		( 3*32+19) /* AMD Accumulated Power Mechanism */
 #define X86_FEATURE_NOPL		( 3*32+20) /* The NOPL (0F 1F) instructions */
 #define X86_FEATURE_ALWAYS		( 3*32+21) /* "" Always-present feature */
@@ -226,10 +226,9 @@
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
-#define X86_FEATURE_VNMI		( 8*32+ 1) /* Intel Virtual NMI */
-#define X86_FEATURE_FLEXPRIORITY	( 8*32+ 2) /* Intel FlexPriority */
-#define X86_FEATURE_EPT			( 8*32+ 3) /* Intel Extended Page Table */
-#define X86_FEATURE_VPID		( 8*32+ 4) /* Intel Virtual Processor ID */
+#define X86_FEATURE_FLEXPRIORITY	( 8*32+ 1) /* Intel FlexPriority */
+#define X86_FEATURE_EPT			( 8*32+ 2) /* Intel Extended Page Table */
+#define X86_FEATURE_VPID		( 8*32+ 3) /* Intel Virtual Processor ID */
 
 #define X86_FEATURE_VMMCALL		( 8*32+15) /* Prefer VMMCALL to VMCALL */
 #define X86_FEATURE_XENPV		( 8*32+16) /* "" Xen paravirtual guest */
@@ -307,14 +306,21 @@
 #define X86_FEATURE_SGX_EDECCSSA	(11*32+18) /* "" SGX EDECCSSA user leaf function */
 #define X86_FEATURE_CALL_DEPTH		(11*32+19) /* "" Call depth tracking for RSB stuffing */
 #define X86_FEATURE_MSR_TSX_CTRL	(11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */
+#define X86_FEATURE_SMBA		(11*32+21) /* "" Slow Memory Bandwidth Allocation */
+#define X86_FEATURE_BMEC		(11*32+22) /* "" Bandwidth Monitoring Event Configuration */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
 #define X86_FEATURE_AVX512_BF16		(12*32+ 5) /* AVX512 BFLOAT16 instructions */
 #define X86_FEATURE_CMPCCXADD           (12*32+ 7) /* "" CMPccXADD instructions */
+#define X86_FEATURE_ARCH_PERFMON_EXT	(12*32+ 8) /* "" Intel Architectural PerfMon Extension */
+#define X86_FEATURE_FZRM		(12*32+10) /* "" Fast zero-length REP MOVSB */
+#define X86_FEATURE_FSRS		(12*32+11) /* "" Fast short REP STOSB */
+#define X86_FEATURE_FSRC		(12*32+12) /* "" Fast short REP {CMPSB,SCASB} */
 #define X86_FEATURE_LKGS		(12*32+18) /* "" Load "kernel" (userspace) GS */
 #define X86_FEATURE_AMX_FP16		(12*32+21) /* "" AMX fp16 Support */
 #define X86_FEATURE_AVX_IFMA            (12*32+23) /* "" Support for VPMADD52[H,L]UQ */
+#define X86_FEATURE_LAM			(12*32+26) /* Linear Address Masking */
 
 /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* CLZERO instruction */
@@ -331,6 +337,7 @@
 #define X86_FEATURE_VIRT_SSBD		(13*32+25) /* Virtualized Speculative Store Bypass Disable */
 #define X86_FEATURE_AMD_SSB_NO		(13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */
 #define X86_FEATURE_CPPC		(13*32+27) /* Collaborative Processor Performance Control */
+#define X86_FEATURE_AMD_PSFD            (13*32+28) /* "" Predictive Store Forwarding Disable */
 #define X86_FEATURE_BTC_NO		(13*32+29) /* "" Not vulnerable to Branch Type Confusion */
 #define X86_FEATURE_BRS			(13*32+31) /* Branch Sampling available */
 
@@ -363,6 +370,7 @@
 #define X86_FEATURE_VGIF		(15*32+16) /* Virtual GIF */
 #define X86_FEATURE_X2AVIC		(15*32+18) /* Virtual x2apic */
 #define X86_FEATURE_V_SPEC_CTRL		(15*32+20) /* Virtual SPEC_CTRL */
+#define X86_FEATURE_VNMI		(15*32+25) /* Virtual NMI */
 #define X86_FEATURE_SVME_ADDR_CHK	(15*32+28) /* "" SVME addr check */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */
@@ -427,6 +435,13 @@
 #define X86_FEATURE_V_TSC_AUX		(19*32+ 9) /* "" Virtual TSC_AUX */
 #define X86_FEATURE_SME_COHERENT	(19*32+10) /* "" AMD hardware-enforced cache coherency */
 
+/* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */
+#define X86_FEATURE_NO_NESTED_DATA_BP	(20*32+ 0) /* "" No Nested Data Breakpoints */
+#define X86_FEATURE_LFENCE_RDTSC	(20*32+ 2) /* "" LFENCE always serializing / synchronizes RDTSC */
+#define X86_FEATURE_NULL_SEL_CLR_BASE	(20*32+ 6) /* "" Null Selector Clears Base */
+#define X86_FEATURE_AUTOIBRS		(20*32+ 8) /* "" Automatic IBRS */
+#define X86_FEATURE_NO_SMM_CTL_MSR	(20*32+ 9) /* "" SMM_CTL MSR is not present */
+
 /*
  * BUG word(s)
  */
@@ -467,5 +482,6 @@
 #define X86_BUG_MMIO_UNKNOWN		X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */
 #define X86_BUG_RETBLEED		X86_BUG(27) /* CPU is affected by RETBleed */
 #define X86_BUG_EIBRS_PBRSB		X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
+#define X86_BUG_SMT_RSB			X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index 5dfa4fb76f4b..fafe9be7a6f4 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -75,6 +75,12 @@
 # define DISABLE_CALL_DEPTH_TRACKING	(1 << (X86_FEATURE_CALL_DEPTH & 31))
 #endif
 
+#ifdef CONFIG_ADDRESS_MASKING
+# define DISABLE_LAM		0
+#else
+# define DISABLE_LAM		(1 << (X86_FEATURE_LAM & 31))
+#endif
+
 #ifdef CONFIG_INTEL_IOMMU_SVM
 # define DISABLE_ENQCMD		0
 #else
@@ -115,7 +121,7 @@
 #define DISABLED_MASK10	0
 #define DISABLED_MASK11	(DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \
 			 DISABLE_CALL_DEPTH_TRACKING)
-#define DISABLED_MASK12	0
+#define DISABLED_MASK12	(DISABLE_LAM)
 #define DISABLED_MASK13	0
 #define DISABLED_MASK14	0
 #define DISABLED_MASK15	0
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index ad35355ee43e..3aedae61af4f 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -206,6 +206,8 @@
 
 /* Abbreviated from Intel SDM name IA32_INTEGRITY_CAPABILITIES */
 #define MSR_INTEGRITY_CAPS			0x000002d9
+#define MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT      2
+#define MSR_INTEGRITY_CAPS_ARRAY_BIST          BIT(MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT)
 #define MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT	4
 #define MSR_INTEGRITY_CAPS_PERIODIC_BIST	BIT(MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT)
 
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 7f467fe05d42..1a6a1f987949 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -559,4 +559,7 @@ struct kvm_pmu_event_filter {
 #define KVM_VCPU_TSC_CTRL 0 /* control group for the timestamp counter (TSC) */
 #define   KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */
 
+/* x86-specific KVM_EXIT_HYPERCALL flags. */
+#define KVM_EXIT_HYPERCALL_LONG_MODE	BIT(0)
+
 #endif /* _ASM_X86_KVM_H */
diff --git a/tools/arch/x86/include/uapi/asm/prctl.h b/tools/arch/x86/include/uapi/asm/prctl.h
index 500b96e71f18..e8d7ebbca1a4 100644
--- a/tools/arch/x86/include/uapi/asm/prctl.h
+++ b/tools/arch/x86/include/uapi/asm/prctl.h
@@ -16,8 +16,16 @@
 #define ARCH_GET_XCOMP_GUEST_PERM	0x1024
 #define ARCH_REQ_XCOMP_GUEST_PERM	0x1025
 
+#define ARCH_XCOMP_TILECFG		17
+#define ARCH_XCOMP_TILEDATA		18
+
 #define ARCH_MAP_VDSO_X32		0x2001
 #define ARCH_MAP_VDSO_32		0x2002
 #define ARCH_MAP_VDSO_64		0x2003
 
+#define ARCH_GET_UNTAG_MASK		0x4001
+#define ARCH_ENABLE_TAGGED_ADDR		0x4002
+#define ARCH_GET_MAX_TAG_BITS		0x4003
+#define ARCH_FORCE_TAGGED_SVA		0x4004
+
 #endif /* _ASM_X86_PRCTL_H */
diff --git a/tools/arch/x86/include/uapi/asm/unistd_32.h b/tools/arch/x86/include/uapi/asm/unistd_32.h
index b8ddfc4c4ab0..bc48a4dabe5d 100644
--- a/tools/arch/x86/include/uapi/asm/unistd_32.h
+++ b/tools/arch/x86/include/uapi/asm/unistd_32.h
@@ -2,6 +2,9 @@
 #ifndef __NR_fork
 #define __NR_fork 2
 #endif
+#ifndef __NR_execve
+#define __NR_execve 11
+#endif
 #ifndef __NR_getppid
 #define __NR_getppid 64
 #endif
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index a91ac666f758..d055b82d22cc 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -10,13 +10,6 @@
 .section .noinstr.text, "ax"
 
 /*
- * We build a jump to memcpy_orig by default which gets NOPped out on
- * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which
- * have the enhanced REP MOVSB/STOSB feature (ERMS), change those NOPs
- * to a jmp to memcpy_erms which does the REP; MOVSB mem copy.
- */
-
-/*
  * memcpy - Copy a memory block.
  *
  * Input:
@@ -26,17 +19,21 @@
  *
  * Output:
  * rax original destination
+ *
+ * The FSRM alternative should be done inline (avoiding the call and
+ * the disgusting return handling), but that would require some help
+ * from the compiler for better calling conventions.
+ *
+ * The 'rep movsb' itself is small enough to replace the call, but the
+ * two register moves blow up the code. And one of them is "needed"
+ * only for the return value that is the same as the source input,
+ * which the compiler could/should do much better anyway.
  */
 SYM_TYPED_FUNC_START(__memcpy)
-	ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \
-		      "jmp memcpy_erms", X86_FEATURE_ERMS
+	ALTERNATIVE "jmp memcpy_orig", "", X86_FEATURE_FSRM
 
 	movq %rdi, %rax
 	movq %rdx, %rcx
-	shrq $3, %rcx
-	andl $7, %edx
-	rep movsq
-	movl %edx, %ecx
 	rep movsb
 	RET
 SYM_FUNC_END(__memcpy)
@@ -45,17 +42,6 @@ EXPORT_SYMBOL(__memcpy)
 SYM_FUNC_ALIAS(memcpy, __memcpy)
 EXPORT_SYMBOL(memcpy)
 
-/*
- * memcpy_erms() - enhanced fast string memcpy. This is faster and
- * simpler than memcpy. Use memcpy_erms when possible.
- */
-SYM_FUNC_START_LOCAL(memcpy_erms)
-	movq %rdi, %rax
-	movq %rdx, %rcx
-	rep movsb
-	RET
-SYM_FUNC_END(memcpy_erms)
-
 SYM_FUNC_START_LOCAL(memcpy_orig)
 	movq %rdi, %rax
 
diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S
index 6143b1a6fa2c..7c59a704c458 100644
--- a/tools/arch/x86/lib/memset_64.S
+++ b/tools/arch/x86/lib/memset_64.S
@@ -18,27 +18,22 @@
  * rdx   count (bytes)
  *
  * rax   original destination
+ *
+ * The FSRS alternative should be done inline (avoiding the call and
+ * the disgusting return handling), but that would require some help
+ * from the compiler for better calling conventions.
+ *
+ * The 'rep stosb' itself is small enough to replace the call, but all
+ * the register moves blow up the code. And two of them are "needed"
+ * only for the return value that is the same as the source input,
+ * which the compiler could/should do much better anyway.
  */
 SYM_FUNC_START(__memset)
-	/*
-	 * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended
-	 * to use it when possible. If not available, use fast string instructions.
-	 *
-	 * Otherwise, use original memset function.
-	 */
-	ALTERNATIVE_2 "jmp memset_orig", "", X86_FEATURE_REP_GOOD, \
-		      "jmp memset_erms", X86_FEATURE_ERMS
+	ALTERNATIVE "jmp memset_orig", "", X86_FEATURE_FSRS
 
 	movq %rdi,%r9
+	movb %sil,%al
 	movq %rdx,%rcx
-	andl $7,%edx
-	shrq $3,%rcx
-	/* expand byte value  */
-	movzbl %sil,%esi
-	movabs $0x0101010101010101,%rax
-	imulq %rsi,%rax
-	rep stosq
-	movl %edx,%ecx
 	rep stosb
 	movq %r9,%rax
 	RET
@@ -48,26 +43,6 @@ EXPORT_SYMBOL(__memset)
 SYM_FUNC_ALIAS(memset, __memset)
 EXPORT_SYMBOL(memset)
 
-/*
- * ISO C memset - set a memory block to a byte value. This function uses
- * enhanced rep stosb to override the fast string function.
- * The code is simpler and shorter than the fast string function as well.
- *
- * rdi   destination
- * rsi   value (char)
- * rdx   count (bytes)
- *
- * rax   original destination
- */
-SYM_FUNC_START_LOCAL(memset_erms)
-	movq %rdi,%r9
-	movb %sil,%al
-	movq %rdx,%rcx
-	rep stosb
-	movq %r9,%rax
-	RET
-SYM_FUNC_END(memset_erms)
-
 SYM_FUNC_START_LOCAL(memset_orig)
 	movq %rdi,%r10
 
diff --git a/tools/include/asm/alternative.h b/tools/include/asm/alternative.h
index b54bd860dff6..7ce02a223732 100644
--- a/tools/include/asm/alternative.h
+++ b/tools/include/asm/alternative.h
@@ -4,7 +4,6 @@
 
 /* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */
 
-#define altinstruction_entry #
-#define ALTERNATIVE_2 #
+#define ALTERNATIVE #
 
 #endif
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 642808520d92..a87bbbbca2d4 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -972,6 +972,19 @@ extern "C" {
 #define DRM_IOCTL_GET_STATS             DRM_IOR( 0x06, struct drm_stats)
 #define DRM_IOCTL_SET_VERSION		DRM_IOWR(0x07, struct drm_set_version)
 #define DRM_IOCTL_MODESET_CTL           DRM_IOW(0x08, struct drm_modeset_ctl)
+/**
+ * DRM_IOCTL_GEM_CLOSE - Close a GEM handle.
+ *
+ * GEM handles are not reference-counted by the kernel. User-space is
+ * responsible for managing their lifetime. For example, if user-space imports
+ * the same memory object twice on the same DRM file description, the same GEM
+ * handle is returned by both imports, and user-space needs to ensure
+ * &DRM_IOCTL_GEM_CLOSE is performed once only. The same situation can happen
+ * when a memory object is allocated, then exported and imported again on the
+ * same DRM file description. The &DRM_IOCTL_MODE_GETFB2 IOCTL is an exception
+ * and always returns fresh new GEM handles even if an existing GEM handle
+ * already refers to the same memory object before the IOCTL is performed.
+ */
 #define DRM_IOCTL_GEM_CLOSE		DRM_IOW (0x09, struct drm_gem_close)
 #define DRM_IOCTL_GEM_FLINK		DRM_IOWR(0x0a, struct drm_gem_flink)
 #define DRM_IOCTL_GEM_OPEN		DRM_IOWR(0x0b, struct drm_gem_open)
@@ -1012,7 +1025,37 @@ extern "C" {
 #define DRM_IOCTL_UNLOCK		DRM_IOW( 0x2b, struct drm_lock)
 #define DRM_IOCTL_FINISH		DRM_IOW( 0x2c, struct drm_lock)
 
+/**
+ * DRM_IOCTL_PRIME_HANDLE_TO_FD - Convert a GEM handle to a DMA-BUF FD.
+ *
+ * User-space sets &drm_prime_handle.handle with the GEM handle to export and
+ * &drm_prime_handle.flags, and gets back a DMA-BUF file descriptor in
+ * &drm_prime_handle.fd.
+ *
+ * The export can fail for any driver-specific reason, e.g. because export is
+ * not supported for this specific GEM handle (but might be for others).
+ *
+ * Support for exporting DMA-BUFs is advertised via &DRM_PRIME_CAP_EXPORT.
+ */
 #define DRM_IOCTL_PRIME_HANDLE_TO_FD    DRM_IOWR(0x2d, struct drm_prime_handle)
+/**
+ * DRM_IOCTL_PRIME_FD_TO_HANDLE - Convert a DMA-BUF FD to a GEM handle.
+ *
+ * User-space sets &drm_prime_handle.fd with a DMA-BUF file descriptor to
+ * import, and gets back a GEM handle in &drm_prime_handle.handle.
+ * &drm_prime_handle.flags is unused.
+ *
+ * If an existing GEM handle refers to the memory object backing the DMA-BUF,
+ * that GEM handle is returned. Therefore user-space which needs to handle
+ * arbitrary DMA-BUFs must have a user-space lookup data structure to manually
+ * reference-count duplicated GEM handles. For more information see
+ * &DRM_IOCTL_GEM_CLOSE.
+ *
+ * The import can fail for any driver-specific reason, e.g. because import is
+ * only supported for DMA-BUFs allocated on this DRM device.
+ *
+ * Support for importing DMA-BUFs is advertised via &DRM_PRIME_CAP_IMPORT.
+ */
 #define DRM_IOCTL_PRIME_FD_TO_HANDLE    DRM_IOWR(0x2e, struct drm_prime_handle)
 
 #define DRM_IOCTL_AGP_ACQUIRE		DRM_IO(  0x30)
@@ -1104,8 +1147,13 @@ extern "C" {
  * struct as the output.
  *
  * If the client is DRM master or has &CAP_SYS_ADMIN, &drm_mode_fb_cmd2.handles
- * will be filled with GEM buffer handles. Planes are valid until one has a
- * zero handle -- this can be used to compute the number of planes.
+ * will be filled with GEM buffer handles. Fresh new GEM handles are always
+ * returned, even if another GEM handle referring to the same memory object
+ * already exists on the DRM file description. The caller is responsible for
+ * removing the new handles, e.g. via the &DRM_IOCTL_GEM_CLOSE IOCTL. The same
+ * new handle will be returned for multiple planes in case they use the same
+ * memory object. Planes are valid until one has a zero handle -- this can be
+ * used to compute the number of planes.
  *
  * Otherwise, &drm_mode_fb_cmd2.handles will be zeroed and planes are valid
  * until one has a zero &drm_mode_fb_cmd2.pitches.
@@ -1113,6 +1161,11 @@ extern "C" {
  * If the framebuffer has a format modifier, &DRM_MODE_FB_MODIFIERS will be set
  * in &drm_mode_fb_cmd2.flags and &drm_mode_fb_cmd2.modifier will contain the
  * modifier. Otherwise, user-space must ignore &drm_mode_fb_cmd2.modifier.
+ *
+ * To obtain DMA-BUF FDs for each plane without leaking GEM handles, user-space
+ * can export each handle via &DRM_IOCTL_PRIME_HANDLE_TO_FD, then immediately
+ * close each unique handle via &DRM_IOCTL_GEM_CLOSE, making sure to not
+ * double-close handles which are specified multiple times in the array.
  */
 #define DRM_IOCTL_MODE_GETFB2		DRM_IOWR(0xCE, struct drm_mode_fb_cmd2)
 
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 8df261c5ab9b..dba7c5a5b25e 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -2491,7 +2491,7 @@ struct i915_context_param_engines {
 #define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */
 #define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */
 #define I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT 2 /* see i915_context_engines_parallel_submit */
-	struct i915_engine_class_instance engines[0];
+	struct i915_engine_class_instance engines[];
 } __attribute__((packed));
 
 #define I915_DEFINE_CONTEXT_PARAM_ENGINES(name__, N__) struct { \
@@ -2676,6 +2676,10 @@ enum drm_i915_oa_format {
 	I915_OAR_FORMAT_A32u40_A4u32_B8_C8,
 	I915_OA_FORMAT_A24u40_A14u32_B8_C8,
 
+	/* MTL OAM */
+	I915_OAM_FORMAT_MPEC8u64_B8_C8,
+	I915_OAM_FORMAT_MPEC8u32_B8_C8,
+
 	I915_OA_FORMAT_MAX	    /* non-ABI */
 };
 
@@ -2758,6 +2762,25 @@ enum drm_i915_perf_property_id {
 	 */
 	DRM_I915_PERF_PROP_POLL_OA_PERIOD,
 
+	/**
+	 * Multiple engines may be mapped to the same OA unit. The OA unit is
+	 * identified by class:instance of any engine mapped to it.
+	 *
+	 * This parameter specifies the engine class and must be passed along
+	 * with DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE.
+	 *
+	 * This property is available in perf revision 6.
+	 */
+	DRM_I915_PERF_PROP_OA_ENGINE_CLASS,
+
+	/**
+	 * This parameter specifies the engine instance and must be passed along
+	 * with DRM_I915_PERF_PROP_OA_ENGINE_CLASS.
+	 *
+	 * This property is available in perf revision 6.
+	 */
+	DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE,
+
 	DRM_I915_PERF_PROP_MAX /* non-ABI */
 };
 
diff --git a/tools/include/uapi/linux/const.h b/tools/include/uapi/linux/const.h
index af2a44c08683..a429381e7ca5 100644
--- a/tools/include/uapi/linux/const.h
+++ b/tools/include/uapi/linux/const.h
@@ -28,7 +28,7 @@
 #define _BITUL(x)	(_UL(1) << (x))
 #define _BITULL(x)	(_ULL(1) << (x))
 
-#define __ALIGN_KERNEL(x, a)		__ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1)
+#define __ALIGN_KERNEL(x, a)		__ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1)
 #define __ALIGN_KERNEL_MASK(x, mask)	(((x) + (mask)) & ~(mask))
 
 #define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d))
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
index 07a4cb149305..4b7f2df66b99 100644
--- a/tools/include/uapi/linux/in.h
+++ b/tools/include/uapi/linux/in.h
@@ -162,6 +162,7 @@ struct in_addr {
 #define MCAST_MSFILTER			48
 #define IP_MULTICAST_ALL		49
 #define IP_UNICAST_IF			50
+#define IP_LOCAL_PORT_RANGE		51
 
 #define MCAST_EXCLUDE	0
 #define MCAST_INCLUDE	1
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 4003a166328c..737318b1c1d9 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -341,8 +341,13 @@ struct kvm_run {
 			__u64 nr;
 			__u64 args[6];
 			__u64 ret;
-			__u32 longmode;
-			__u32 pad;
+
+			union {
+#ifndef __KERNEL__
+				__u32 longmode;
+#endif
+				__u64 flags;
+			};
 		} hypercall;
 		/* KVM_EXIT_TPR_ACCESS */
 		struct {
@@ -1184,6 +1189,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 224
 #define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225
 #define KVM_CAP_PMU_EVENT_MASKED_EVENTS 226
+#define KVM_CAP_COUNTER_OFFSET 227
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1543,6 +1549,8 @@ struct kvm_s390_ucas_mapping {
 #define KVM_SET_PMU_EVENT_FILTER  _IOW(KVMIO,  0xb2, struct kvm_pmu_event_filter)
 #define KVM_PPC_SVM_OFF		  _IO(KVMIO,  0xb3)
 #define KVM_ARM_MTE_COPY_TAGS	  _IOR(KVMIO,  0xb4, struct kvm_arm_copy_mte_tags)
+/* Available with KVM_CAP_COUNTER_OFFSET */
+#define KVM_ARM_SET_COUNTER_OFFSET _IOW(KVMIO,  0xb5, struct kvm_arm_counter_offset)
 
 /* ioctl for vm fd */
 #define KVM_CREATE_DEVICE	  _IOWR(KVMIO,  0xe0, struct kvm_create_device)
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index 759b3f53e53f..f23d9a16507f 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -290,6 +290,8 @@ struct prctl_mm_map {
 #define PR_SET_VMA		0x53564d41
 # define PR_SET_VMA_ANON_NAME		0
 
+#define PR_GET_AUXV			0x41555856
+
 #define PR_SET_MEMORY_MERGE		67
 #define PR_GET_MEMORY_MERGE		68
 #endif /* _LINUX_PRCTL_H */
diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
index de6810e94abe..0aa955aa8246 100644
--- a/tools/include/uapi/sound/asound.h
+++ b/tools/include/uapi/sound/asound.h
@@ -429,9 +429,14 @@ struct snd_pcm_sw_params {
 	snd_pcm_uframes_t avail_min;		/* min avail frames for wakeup */
 	snd_pcm_uframes_t xfer_align;		/* obsolete: xfer size need to be a multiple */
 	snd_pcm_uframes_t start_threshold;	/* min hw_avail frames for automatic start */
-	snd_pcm_uframes_t stop_threshold;	/* min avail frames for automatic stop */
-	snd_pcm_uframes_t silence_threshold;	/* min distance from noise for silence filling */
-	snd_pcm_uframes_t silence_size;		/* silence block size */
+	/*
+	 * The following two thresholds alleviate playback buffer underruns; when
+	 * hw_avail drops below the threshold, the respective action is triggered:
+	 */
+	snd_pcm_uframes_t stop_threshold;	/* - stop playback */
+	snd_pcm_uframes_t silence_threshold;	/* - pre-fill buffer with silence */
+	snd_pcm_uframes_t silence_size;		/* max size of silence pre-fill; when >= boundary,
+						 * fill played area with silence immediately */
 	snd_pcm_uframes_t boundary;		/* pointers wrap point */
 	unsigned int proto;			/* protocol version */
 	unsigned int tstamp_type;		/* timestamp type (req. proto >= 2.0.12) */
@@ -570,7 +575,8 @@ struct __snd_pcm_mmap_status64 {
 struct __snd_pcm_mmap_control64 {
 	__pad_before_uframe __pad1;
 	snd_pcm_uframes_t appl_ptr;	 /* RW: appl ptr (0...boundary-1) */
-	__pad_before_uframe __pad2;
+	__pad_before_uframe __pad2;	 // This should be __pad_after_uframe, but binary
+					 // backwards compatibility constraints prevent a fix.
 
 	__pad_before_uframe __pad3;
 	snd_pcm_uframes_t  avail_min;	 /* RW: min available frames for wakeup */
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 4884520f954f..70268442f7ee 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -216,6 +216,12 @@ ifeq ($(call get-executable,$(BISON)),)
   dummy := $(error Error: $(BISON) is missing on this system, please install it)
 endif
 
+ifeq ($(BUILD_BPF_SKEL),1)
+  ifeq ($(call get-executable,$(CLANG)),)
+    dummy := $(error $(CLANG) is missing on this system, please install it to be able to build with BUILD_BPF_SKEL=1)
+  endif
+endif
+
 ifneq ($(OUTPUT),)
   ifeq ($(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\).\([0-9]\+\)/\1\2\3/g') \>\= 371), 1)
     BISON_FILE_PREFIX_MAP := --file-prefix-map=$(OUTPUT)=
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index a42a6a99c2bc..1593c5dcaa9e 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -1057,14 +1057,32 @@ $(SKEL_TMP_OUT) $(LIBAPI_OUTPUT) $(LIBBPF_OUTPUT) $(LIBPERF_OUTPUT) $(LIBSUBCMD_
 
 ifdef BUILD_BPF_SKEL
 BPFTOOL := $(SKEL_TMP_OUT)/bootstrap/bpftool
-BPF_INCLUDE := -I$(SKEL_TMP_OUT)/.. -I$(LIBBPF_INCLUDE)
+# Get Clang's default includes on this system, as opposed to those seen by
+# '-target bpf'. This fixes "missing" files on some architectures/distros,
+# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc.
+#
+# Use '-idirafter': Don't interfere with include mechanics except where the
+# build would have failed anyways.
+define get_sys_includes
+$(shell $(1) $(2) -v -E - </dev/null 2>&1 \
+       | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \
+$(shell $(1) $(2) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}')
+endef
+
+ifneq ($(CROSS_COMPILE),)
+CLANG_TARGET_ARCH = --target=$(notdir $(CROSS_COMPILE:%-=%))
+endif
+
+CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH))
+BPF_INCLUDE := -I$(SKEL_TMP_OUT)/.. -I$(LIBBPF_INCLUDE) $(CLANG_SYS_INCLUDES)
+TOOLS_UAPI_INCLUDE := -I$(srctree)/tools/include/uapi
 
 $(BPFTOOL): | $(SKEL_TMP_OUT)
 	$(Q)CFLAGS= $(MAKE) -C ../bpf/bpftool \
 		OUTPUT=$(SKEL_TMP_OUT)/ bootstrap
 
 $(SKEL_TMP_OUT)/%.bpf.o: util/bpf_skel/%.bpf.c $(LIBBPF) | $(SKEL_TMP_OUT)
-	$(QUIET_CLANG)$(CLANG) -g -O2 -target bpf -Wall -Werror $(BPF_INCLUDE) \
+	$(QUIET_CLANG)$(CLANG) -g -O2 -target bpf -Wall -Werror $(BPF_INCLUDE) $(TOOLS_UAPI_INCLUDE) \
 	  -c $(filter util/bpf_skel/%.bpf.c,$^) -o $@ && $(LLVM_STRIP) -g $@
 
 $(SKEL_OUT)/%.skel.h: $(SKEL_TMP_OUT)/%.bpf.o | $(BPFTOOL)
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 77cb03e6ff87..9ca040bfb1aa 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -78,9 +78,9 @@ static int cs_etm_validate_context_id(struct auxtrace_record *itr,
 	char path[PATH_MAX];
 	int err;
 	u32 val;
-	u64 contextid =
-		evsel->core.attr.config &
-		(perf_pmu__format_bits(&cs_etm_pmu->format, "contextid1") |
+	u64 contextid = evsel->core.attr.config &
+		(perf_pmu__format_bits(&cs_etm_pmu->format, "contextid") |
+		 perf_pmu__format_bits(&cs_etm_pmu->format, "contextid1") |
 		 perf_pmu__format_bits(&cs_etm_pmu->format, "contextid2"));
 
 	if (!contextid)
@@ -114,8 +114,7 @@ static int cs_etm_validate_context_id(struct auxtrace_record *itr,
 		 *  0b00100 Maximum of 32-bit Context ID size.
 		 *  All other values are reserved.
 		 */
-		val = BMVAL(val, 5, 9);
-		if (!val || val != 0x4) {
+		if (BMVAL(val, 5, 9) != 0x4) {
 			pr_err("%s: CONTEXTIDR_EL1 isn't supported, disable with %s/contextid1=0/\n",
 			       CORESIGHT_ETM_PMU_NAME, CORESIGHT_ETM_PMU_NAME);
 			return -EINVAL;
diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c
index d730666ab95d..80b9f6287fe2 100644
--- a/tools/perf/arch/arm64/util/header.c
+++ b/tools/perf/arch/arm64/util/header.c
@@ -29,8 +29,8 @@ static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus)
 		char path[PATH_MAX];
 		FILE *file;
 
-		scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d"MIDR,
-				sysfs, cpus->map[cpu]);
+		scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d" MIDR,
+			  sysfs, RC_CHK_ACCESS(cpus)->map[cpu].cpu);
 
 		file = fopen(path, "r");
 		if (!file) {
diff --git a/tools/perf/arch/arm64/util/pmu.c b/tools/perf/arch/arm64/util/pmu.c
index fa143acb4c8d..ef1ed645097c 100644
--- a/tools/perf/arch/arm64/util/pmu.c
+++ b/tools/perf/arch/arm64/util/pmu.c
@@ -18,7 +18,7 @@ static struct perf_pmu *pmu__find_core_pmu(void)
 		 * The cpumap should cover all CPUs. Otherwise, some CPUs may
 		 * not support some events or have different event IDs.
 		 */
-		if (pmu->cpus->nr != cpu__max_cpu().cpu)
+		if (RC_CHK_ACCESS(pmu->cpus)->nr != cpu__max_cpu().cpu)
 			return NULL;
 
 		return pmu;
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index 799147658dee..b68f47541169 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -449,7 +449,7 @@
 444  common	landlock_create_ruleset	sys_landlock_create_ruleset	sys_landlock_create_ruleset
 445  common	landlock_add_rule	sys_landlock_add_rule		sys_landlock_add_rule
 446  common	landlock_restrict_self	sys_landlock_restrict_self	sys_landlock_restrict_self
-# 447 reserved for memfd_secret
+447  common	memfd_secret		sys_memfd_secret		sys_memfd_secret
 448  common	process_mrelease	sys_process_mrelease		sys_process_mrelease
 449  common	futex_waitv		sys_futex_waitv			sys_futex_waitv
 450  common	set_mempolicy_home_node	sys_set_mempolicy_home_node	sys_set_mempolicy_home_node
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
index 50ae8bd58296..6188e19d3129 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
@@ -7,7 +7,3 @@ MEMCPY_FN(memcpy_orig,
 MEMCPY_FN(__memcpy,
 	"x86-64-movsq",
 	"movsq-based memcpy() in arch/x86/lib/memcpy_64.S")
-
-MEMCPY_FN(memcpy_erms,
-	"x86-64-movsb",
-	"movsb-based memcpy() in arch/x86/lib/memcpy_64.S")
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
index 6eb45a2aa8db..1b9fef7efcdc 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm.S
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -2,7 +2,7 @@
 
 /* Various wrappers to make the kernel .S file build in user-space: */
 
-// memcpy_orig and memcpy_erms are being defined as SYM_L_LOCAL but we need it
+// memcpy_orig is being defined as SYM_L_LOCAL but we need it
 #define SYM_FUNC_START_LOCAL(name)                      \
         SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
 #define memcpy MEMCPY /* don't hide glibc's memcpy() */
diff --git a/tools/perf/bench/mem-memset-x86-64-asm-def.h b/tools/perf/bench/mem-memset-x86-64-asm-def.h
index dac6d2b7c39b..247c72fdfb9d 100644
--- a/tools/perf/bench/mem-memset-x86-64-asm-def.h
+++ b/tools/perf/bench/mem-memset-x86-64-asm-def.h
@@ -7,7 +7,3 @@ MEMSET_FN(memset_orig,
 MEMSET_FN(__memset,
 	"x86-64-stosq",
 	"movsq-based memset() in arch/x86/lib/memset_64.S")
-
-MEMSET_FN(memset_erms,
-	"x86-64-stosb",
-	"movsb-based memset() in arch/x86/lib/memset_64.S")
diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S
index 6f093c483842..abd26c95f1aa 100644
--- a/tools/perf/bench/mem-memset-x86-64-asm.S
+++ b/tools/perf/bench/mem-memset-x86-64-asm.S
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-// memset_orig and memset_erms are being defined as SYM_L_LOCAL but we need it
+// memset_orig is being defined as SYM_L_LOCAL but we need it
 #define SYM_FUNC_START_LOCAL(name)                      \
         SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
 #define memset MEMSET /* don't hide glibc's memset() */
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 006f522d0e7f..c57be48d65bb 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -3647,6 +3647,13 @@ static int process_stat_config_event(struct perf_session *session __maybe_unused
 				     union perf_event *event)
 {
 	perf_event__read_stat_config(&stat_config, &event->stat_config);
+
+	/*
+	 * Aggregation modes are not used since post-processing scripts are
+	 * supposed to take care of such requirements
+	 */
+	stat_config.aggr_mode = AGGR_NONE;
+
 	return 0;
 }
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index cc9fa48d636f..b9ad32f21e57 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -667,6 +667,13 @@ static enum counter_recovery stat_handle_error(struct evsel *counter)
 			evsel_list->core.threads->err_thread = -1;
 			return COUNTER_RETRY;
 		}
+	} else if (counter->skippable) {
+		if (verbose > 0)
+			ui__warning("skipping event %s that kernel failed to open .\n",
+				    evsel__name(counter));
+		counter->supported = false;
+		counter->errored = true;
+		return COUNTER_SKIP;
 	}
 
 	evsel__open_strerror(counter, &target, errno, msg, sizeof(msg));
@@ -1890,15 +1897,28 @@ static int add_default_attributes(void)
 		 * caused by exposing latent bugs. This is fixed properly in:
 		 * https://lore.kernel.org/lkml/bff481ba-e60a-763f-0aa0-3ee53302c480@linux.intel.com/
 		 */
-		if (metricgroup__has_metric("TopdownL1") && !perf_pmu__has_hybrid() &&
-		    metricgroup__parse_groups(evsel_list, "TopdownL1",
-					    /*metric_no_group=*/false,
-					    /*metric_no_merge=*/false,
-					    /*metric_no_threshold=*/true,
-					    stat_config.user_requested_cpu_list,
-					    stat_config.system_wide,
-					    &stat_config.metric_events) < 0)
-			return -1;
+		if (metricgroup__has_metric("TopdownL1") && !perf_pmu__has_hybrid()) {
+			struct evlist *metric_evlist = evlist__new();
+			struct evsel *metric_evsel;
+
+			if (!metric_evlist)
+				return -1;
+
+			if (metricgroup__parse_groups(metric_evlist, "TopdownL1",
+							/*metric_no_group=*/false,
+							/*metric_no_merge=*/false,
+							/*metric_no_threshold=*/true,
+							stat_config.user_requested_cpu_list,
+							stat_config.system_wide,
+							&stat_config.metric_events) < 0)
+				return -1;
+
+			evlist__for_each_entry(metric_evlist, metric_evsel) {
+				metric_evsel->skippable = true;
+			}
+			evlist__splice_list_tail(evsel_list, &metric_evlist->core.entries);
+			evlist__delete(metric_evlist);
+		}
 
 		/* Platform specific attrs */
 		if (evlist__add_default_attrs(evsel_list, default_null_attrs) < 0)
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
index 75d80e70e5cd..1f9047553942 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
@@ -133,6 +133,7 @@
         "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.1",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "Counts the total number of issue slots  that were not consumed by the backend due to backend stalls.  Note that uops must be available for consumption in order for this event to count.  If a uop is not available (IQ is empty), this event will not count.   The rest of these subevents count backend stalls, in cycles, due to an outstanding request which is memory bound vs core bound.   The subevents are not slot based events and therefore can not be precisely added or subtracted from the Backend_Bound_Aux subevents which are slot based.",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -143,6 +144,7 @@
         "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound_aux",
         "MetricThreshold": "tma_backend_bound_aux > 0.2",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "Counts the total number of issue slots  that were not consumed by the backend due to backend stalls.  Note that UOPS must be available for consumption in order for this event to count.  If a uop is not available (IQ is empty), this event will not count.  All of these subevents count backend stalls, in slots, due to a resource limitation.   These are not cycle based events and therefore can not be precisely added or subtracted from the Backend_Bound subevents which are cycle based.  These subevents are supplementary to Backend_Bound and can be used to analyze results from a resource perspective at allocation.",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -153,6 +155,7 @@
         "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -163,6 +166,7 @@
         "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_base",
         "MetricThreshold": "tma_base > 0.6",
+        "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -182,6 +186,7 @@
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.05",
+        "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -209,6 +214,7 @@
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1",
+        "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -255,6 +261,7 @@
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.1",
+        "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -264,6 +271,7 @@
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -291,6 +299,7 @@
         "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL1",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -593,6 +602,7 @@
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.05",
+        "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -611,6 +621,7 @@
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -629,6 +640,7 @@
         "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_ms_uops",
         "MetricThreshold": "tma_ms_uops > 0.05",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS).  This includes uops from flows due to complex instructions, faults, assists, and inserted flows.",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -729,6 +741,7 @@
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_aux_group",
         "MetricName": "tma_resource_bound",
         "MetricThreshold": "tma_resource_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "Counts the total number of issue slots  that were not consumed by the backend due to backend stalls.  Note that uops must be available for consumption in order for this event to count.  If a uop is not available (IQ is empty), this event will not count.",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -739,6 +752,7 @@
         "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.75",
+        "MetricgroupNoGroup": "TopdownL1",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -848,6 +862,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -858,6 +873,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -868,6 +884,7 @@
         "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -919,6 +936,7 @@
         "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -1031,6 +1049,7 @@
         "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB",
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -1041,6 +1060,7 @@
         "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -1121,6 +1141,7 @@
         "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -1141,6 +1162,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. Sample with: UOPS_RETIRED.HEAVY",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2023,6 +2045,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2082,6 +2105,7 @@
         "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn",
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2112,6 +2136,7 @@
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2310,6 +2335,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved.  Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
index 1a85d935c733..0402adbf7d92 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
@@ -98,6 +98,7 @@
         "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.1",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "Counts the total number of issue slots  that were not consumed by the backend due to backend stalls.  Note that uops must be available for consumption in order for this event to count.  If a uop is not available (IQ is empty), this event will not count.   The rest of these subevents count backend stalls, in cycles, due to an outstanding request which is memory bound vs core bound.   The subevents are not slot based events and therefore can not be precisely added or subtracted from the Backend_Bound_Aux subevents which are slot based.",
         "ScaleUnit": "100%"
     },
@@ -107,6 +108,7 @@
         "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound_aux",
         "MetricThreshold": "tma_backend_bound_aux > 0.2",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "Counts the total number of issue slots  that were not consumed by the backend due to backend stalls.  Note that UOPS must be available for consumption in order for this event to count.  If a uop is not available (IQ is empty), this event will not count.  All of these subevents count backend stalls, in slots, due to a resource limitation.   These are not cycle based events and therefore can not be precisely added or subtracted from the Backend_Bound subevents which are cycle based.  These subevents are supplementary to Backend_Bound and can be used to analyze results from a resource perspective at allocation.",
         "ScaleUnit": "100%"
     },
@@ -116,6 +118,7 @@
         "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.",
         "ScaleUnit": "100%"
     },
@@ -125,6 +128,7 @@
         "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_base",
         "MetricThreshold": "tma_base > 0.6",
+        "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
     {
@@ -142,6 +146,7 @@
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.05",
+        "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
     {
@@ -166,6 +171,7 @@
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1",
+        "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
     {
@@ -207,6 +213,7 @@
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.1",
+        "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
     {
@@ -215,6 +222,7 @@
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
     {
@@ -239,6 +247,7 @@
         "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL1",
         "ScaleUnit": "100%"
     },
     {
@@ -499,6 +508,7 @@
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.05",
+        "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
     {
@@ -515,6 +525,7 @@
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
     {
@@ -531,6 +542,7 @@
         "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_ms_uops",
         "MetricThreshold": "tma_ms_uops > 0.05",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS).  This includes uops from flows due to complex instructions, faults, assists, and inserted flows.",
         "ScaleUnit": "100%"
     },
@@ -620,6 +632,7 @@
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_aux_group",
         "MetricName": "tma_resource_bound",
         "MetricThreshold": "tma_resource_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "Counts the total number of issue slots  that were not consumed by the backend due to backend stalls.  Note that uops must be available for consumption in order for this event to count.  If a uop is not available (IQ is empty), this event will not count.",
         "ScaleUnit": "100%"
     },
@@ -629,6 +642,7 @@
         "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.75",
+        "MetricgroupNoGroup": "TopdownL1",
         "ScaleUnit": "100%"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
index 51cf8560a8d3..f9e2316601e1 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
@@ -103,6 +103,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
         "ScaleUnit": "100%"
     },
@@ -112,6 +113,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
@@ -122,6 +124,7 @@
         "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers",
         "ScaleUnit": "100%"
     },
@@ -170,6 +173,7 @@
         "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
@@ -263,6 +267,7 @@
         "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB",
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
@@ -272,6 +277,7 @@
         "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END",
         "ScaleUnit": "100%"
     },
@@ -326,6 +332,7 @@
         "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
         "ScaleUnit": "100%"
     },
@@ -335,6 +342,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.",
         "ScaleUnit": "100%"
     },
@@ -828,6 +836,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
@@ -858,6 +867,7 @@
         "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn",
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
     },
@@ -886,6 +896,7 @@
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
@@ -1048,6 +1059,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved.  Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS",
         "ScaleUnit": "100%"
     },
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json
index fb57c7382408..e9c46d336a8e 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json
@@ -97,6 +97,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS",
         "ScaleUnit": "100%"
     },
@@ -106,6 +107,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
@@ -116,6 +118,7 @@
         "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers",
         "ScaleUnit": "100%"
     },
@@ -164,6 +167,7 @@
         "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
@@ -248,6 +252,7 @@
         "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB",
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
@@ -257,6 +262,7 @@
         "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%"
     },
@@ -311,6 +317,7 @@
         "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
         "ScaleUnit": "100%"
     },
@@ -320,6 +327,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.",
         "ScaleUnit": "100%"
     },
@@ -795,6 +803,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
@@ -825,6 +834,7 @@
         "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn",
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
     },
@@ -853,6 +863,7 @@
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
@@ -1013,6 +1024,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved.  Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS",
         "ScaleUnit": "100%"
     },
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json
index 65ec0c9e55d1..437b9867acb9 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json
@@ -103,6 +103,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
         "ScaleUnit": "100%"
     },
@@ -112,6 +113,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
@@ -122,6 +124,7 @@
         "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers",
         "ScaleUnit": "100%"
     },
@@ -170,6 +173,7 @@
         "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
@@ -263,6 +267,7 @@
         "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB",
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
@@ -272,6 +277,7 @@
         "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END",
         "ScaleUnit": "100%"
     },
@@ -326,6 +332,7 @@
         "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
         "ScaleUnit": "100%"
     },
@@ -335,6 +342,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.",
         "ScaleUnit": "100%"
     },
@@ -829,6 +837,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
@@ -869,6 +878,7 @@
         "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn",
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
     },
@@ -897,6 +907,7 @@
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
@@ -1079,6 +1090,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved.  Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS",
         "ScaleUnit": "100%"
     },
diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
index 8f7dc72accd0..875c766222e3 100644
--- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
@@ -101,6 +101,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
         "ScaleUnit": "100%"
     },
@@ -110,6 +111,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
@@ -120,6 +122,7 @@
         "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers",
         "ScaleUnit": "100%"
     },
@@ -167,6 +170,7 @@
         "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
@@ -271,6 +275,7 @@
         "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB",
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
@@ -280,6 +285,7 @@
         "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%"
     },
@@ -354,6 +360,7 @@
         "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
         "ScaleUnit": "100%"
     },
@@ -372,6 +379,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.",
         "ScaleUnit": "100%"
     },
@@ -1142,6 +1150,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
@@ -1196,6 +1205,7 @@
         "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn",
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
     },
@@ -1224,6 +1234,7 @@
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
@@ -1458,6 +1469,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved.  Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS",
         "ScaleUnit": "100%"
     },
diff --git a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json
index 2528418200bb..9570a88d6d1c 100644
--- a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json
@@ -103,6 +103,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
         "ScaleUnit": "100%"
     },
@@ -112,6 +113,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
@@ -122,6 +124,7 @@
         "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers",
         "ScaleUnit": "100%"
     },
@@ -161,6 +164,7 @@
         "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
@@ -254,6 +258,7 @@
         "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB",
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
@@ -263,6 +268,7 @@
         "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END",
         "ScaleUnit": "100%"
     },
@@ -272,6 +278,7 @@
         "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
         "ScaleUnit": "100%"
     },
@@ -281,6 +288,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.",
         "ScaleUnit": "100%"
     },
@@ -663,6 +671,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
@@ -693,6 +702,7 @@
         "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn",
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
     },
@@ -721,6 +731,7 @@
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
@@ -874,6 +885,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved.  Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS",
         "ScaleUnit": "100%"
     },
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json
index 11f152c346eb..a522202cf684 100644
--- a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json
@@ -103,6 +103,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
         "ScaleUnit": "100%"
     },
@@ -112,6 +113,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
@@ -122,6 +124,7 @@
         "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers",
         "ScaleUnit": "100%"
     },
@@ -161,6 +164,7 @@
         "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
@@ -254,6 +258,7 @@
         "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB",
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
@@ -263,6 +268,7 @@
         "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END",
         "ScaleUnit": "100%"
     },
@@ -272,6 +278,7 @@
         "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
         "ScaleUnit": "100%"
     },
@@ -281,6 +288,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.",
         "ScaleUnit": "100%"
     },
@@ -664,6 +672,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
@@ -704,6 +713,7 @@
         "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn",
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
     },
@@ -732,6 +742,7 @@
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
@@ -905,6 +916,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved.  Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS",
         "ScaleUnit": "100%"
     },
diff --git a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json
index f45ae3483df4..1a2154f28b7b 100644
--- a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json
@@ -115,6 +115,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS",
         "ScaleUnit": "100%"
     },
@@ -124,6 +125,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
@@ -141,6 +143,7 @@
         "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers",
         "ScaleUnit": "100%"
     },
@@ -187,6 +190,7 @@
         "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
@@ -288,6 +292,7 @@
         "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB",
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
@@ -297,6 +302,7 @@
         "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%"
     },
@@ -369,6 +375,7 @@
         "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
         "ScaleUnit": "100%"
     },
@@ -378,6 +385,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.",
         "ScaleUnit": "100%"
     },
@@ -1111,6 +1119,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
@@ -1164,6 +1173,7 @@
         "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn",
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
     },
@@ -1191,6 +1201,7 @@
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
@@ -1360,6 +1371,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved.  Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS",
         "ScaleUnit": "100%"
     },
diff --git a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json
index 0f9b174dfc22..1ef772b40e04 100644
--- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json
@@ -80,6 +80,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS",
         "ScaleUnit": "100%"
     },
@@ -89,6 +90,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
@@ -106,6 +108,7 @@
         "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers",
         "ScaleUnit": "100%"
     },
@@ -152,6 +155,7 @@
         "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
@@ -253,6 +257,7 @@
         "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB",
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
@@ -262,6 +267,7 @@
         "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%"
     },
@@ -334,6 +340,7 @@
         "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
         "ScaleUnit": "100%"
     },
@@ -343,6 +350,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.",
         "ScaleUnit": "100%"
     },
@@ -1134,6 +1142,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
@@ -1187,6 +1196,7 @@
         "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn",
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
     },
@@ -1214,6 +1224,7 @@
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
@@ -1410,6 +1421,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved.  Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS",
         "ScaleUnit": "100%"
     },
diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json
index 5247f69c13b6..11080ccffd51 100644
--- a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json
@@ -103,6 +103,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
         "ScaleUnit": "100%"
     },
@@ -112,6 +113,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
@@ -122,6 +124,7 @@
         "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers",
         "ScaleUnit": "100%"
     },
@@ -161,6 +164,7 @@
         "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
@@ -254,6 +258,7 @@
         "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB",
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
@@ -263,6 +268,7 @@
         "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END",
         "ScaleUnit": "100%"
     },
@@ -299,6 +305,7 @@
         "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
         "ScaleUnit": "100%"
     },
@@ -308,6 +315,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.",
         "ScaleUnit": "100%"
     },
@@ -724,6 +732,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
@@ -754,6 +763,7 @@
         "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn",
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
     },
@@ -782,6 +792,7 @@
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
@@ -917,6 +928,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved.  Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS",
         "ScaleUnit": "100%"
     },
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json
index 89469b10fa30..65a46d659c0a 100644
--- a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json
@@ -103,6 +103,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
         "ScaleUnit": "100%"
     },
@@ -112,6 +113,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
@@ -122,6 +124,7 @@
         "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers",
         "ScaleUnit": "100%"
     },
@@ -161,6 +164,7 @@
         "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
@@ -254,6 +258,7 @@
         "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB",
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
@@ -263,6 +268,7 @@
         "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END",
         "ScaleUnit": "100%"
     },
@@ -299,6 +305,7 @@
         "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
         "ScaleUnit": "100%"
     },
@@ -308,6 +315,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.",
         "ScaleUnit": "100%"
     },
@@ -725,6 +733,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
@@ -765,6 +774,7 @@
         "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn",
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
     },
@@ -793,6 +803,7 @@
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
@@ -948,6 +959,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved.  Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS",
         "ScaleUnit": "100%"
     },
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json
index e8f4e5c01c9f..66a6f657bd6f 100644
--- a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json
@@ -76,6 +76,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
         "ScaleUnit": "100%"
     },
@@ -85,6 +86,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
@@ -95,6 +97,7 @@
         "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers",
         "ScaleUnit": "100%"
     },
@@ -114,6 +117,7 @@
         "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
@@ -160,6 +164,7 @@
         "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB",
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_lcp",
         "ScaleUnit": "100%"
     },
@@ -169,6 +174,7 @@
         "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END",
         "ScaleUnit": "100%"
     },
@@ -205,6 +211,7 @@
         "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
         "ScaleUnit": "100%"
     },
@@ -214,6 +221,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.",
         "ScaleUnit": "100%"
     },
@@ -412,6 +420,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
@@ -422,6 +431,7 @@
         "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn",
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
     },
@@ -450,6 +460,7 @@
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
@@ -487,6 +498,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved.  Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS",
         "ScaleUnit": "100%"
     },
diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json
index 4a99fe515f4b..4b8bc19392a4 100644
--- a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json
@@ -76,6 +76,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
         "ScaleUnit": "100%"
     },
@@ -85,6 +86,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
@@ -95,6 +97,7 @@
         "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers",
         "ScaleUnit": "100%"
     },
@@ -114,6 +117,7 @@
         "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
@@ -160,6 +164,7 @@
         "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB",
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_lcp",
         "ScaleUnit": "100%"
     },
@@ -169,6 +174,7 @@
         "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END",
         "ScaleUnit": "100%"
     },
@@ -205,6 +211,7 @@
         "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
         "ScaleUnit": "100%"
     },
@@ -214,6 +221,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.",
         "ScaleUnit": "100%"
     },
@@ -411,6 +419,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
@@ -421,6 +430,7 @@
         "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn",
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
     },
@@ -449,6 +459,7 @@
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
@@ -486,6 +497,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved.  Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS",
         "ScaleUnit": "100%"
     },
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
index 126300b7ae77..620fc5bd2217 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
@@ -87,6 +87,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS",
         "ScaleUnit": "100%"
     },
@@ -96,6 +97,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
@@ -105,6 +107,7 @@
         "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers",
         "ScaleUnit": "100%"
     },
@@ -151,6 +154,7 @@
         "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
@@ -252,6 +256,7 @@
         "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB",
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
@@ -261,6 +266,7 @@
         "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%"
     },
@@ -351,6 +357,7 @@
         "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
         "ScaleUnit": "100%"
     },
@@ -369,6 +376,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. Sample with: UOPS_RETIRED.HEAVY",
         "ScaleUnit": "100%"
     },
@@ -1216,6 +1224,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
@@ -1269,6 +1278,7 @@
         "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn",
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
     },
@@ -1304,6 +1314,7 @@
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
@@ -1509,6 +1520,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved.  Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS",
         "ScaleUnit": "100%"
     },
diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
index a6d212b349f5..21ef6c9be816 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
@@ -101,6 +101,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
         "ScaleUnit": "100%"
     },
@@ -110,6 +111,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
@@ -120,6 +122,7 @@
         "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers",
         "ScaleUnit": "100%"
     },
@@ -167,6 +170,7 @@
         "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
@@ -271,6 +275,7 @@
         "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB",
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
@@ -280,6 +285,7 @@
         "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%"
     },
@@ -345,6 +351,7 @@
         "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
         "ScaleUnit": "100%"
     },
@@ -363,6 +370,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.",
         "ScaleUnit": "100%"
     },
@@ -1065,6 +1073,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
@@ -1110,6 +1119,7 @@
         "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn",
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
     },
@@ -1138,6 +1148,7 @@
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
@@ -1343,6 +1354,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved.  Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS",
         "ScaleUnit": "100%"
     },
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
index fa2f7f126a30..eb6f12c0343d 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
@@ -101,6 +101,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
         "ScaleUnit": "100%"
     },
@@ -110,6 +111,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
@@ -120,6 +122,7 @@
         "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers",
         "ScaleUnit": "100%"
     },
@@ -167,6 +170,7 @@
         "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
@@ -271,6 +275,7 @@
         "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB",
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
@@ -280,6 +285,7 @@
         "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%"
     },
@@ -354,6 +360,7 @@
         "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
         "ScaleUnit": "100%"
     },
@@ -372,6 +379,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.",
         "ScaleUnit": "100%"
     },
@@ -1123,6 +1131,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
@@ -1177,6 +1186,7 @@
         "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn",
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
     },
@@ -1205,6 +1215,7 @@
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
@@ -1429,6 +1440,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved.  Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS",
         "ScaleUnit": "100%"
     },
diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json
index 4c80d6be6cf1..b442ed4acfbb 100644
--- a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json
@@ -109,6 +109,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS",
         "ScaleUnit": "100%"
     },
@@ -118,6 +119,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
@@ -135,6 +137,7 @@
         "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers",
         "ScaleUnit": "100%"
     },
@@ -181,6 +184,7 @@
         "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
@@ -282,6 +286,7 @@
         "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB",
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
@@ -291,6 +296,7 @@
         "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%"
     },
@@ -363,6 +369,7 @@
         "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
         "ScaleUnit": "100%"
     },
@@ -372,6 +379,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.",
         "ScaleUnit": "100%"
     },
@@ -1125,6 +1133,7 @@
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
@@ -1178,6 +1187,7 @@
         "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn",
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
     },
@@ -1205,6 +1215,7 @@
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
@@ -1374,6 +1385,7 @@
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
+        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved.  Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS",
         "ScaleUnit": "100%"
     },
diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index ca99b9cfe4ad..f57a8f274025 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -52,7 +52,8 @@ _json_event_attributes = [
 # Attributes that are in pmu_metric rather than pmu_event.
 _json_metric_attributes = [
     'metric_name', 'metric_group', 'metric_expr', 'metric_threshold', 'desc',
-    'long_desc', 'unit', 'compat', 'aggr_mode', 'event_grouping'
+    'long_desc', 'unit', 'compat', 'metricgroup_no_group', 'aggr_mode',
+    'event_grouping'
 ]
 # Attributes that are bools or enum int values, encoded as '0', '1',...
 _json_enum_attributes = ['aggr_mode', 'deprecated', 'event_grouping', 'perpkg']
@@ -303,6 +304,7 @@ class JsonEvent:
     self.deprecated = jd.get('Deprecated')
     self.metric_name = jd.get('MetricName')
     self.metric_group = jd.get('MetricGroup')
+    self.metricgroup_no_group = jd.get('MetricgroupNoGroup')
     self.event_grouping = convert_metric_constraint(jd.get('MetricConstraint'))
     self.metric_expr = None
     if 'MetricExpr' in jd:
diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h
index b7dff8f1021f..80349685cf4d 100644
--- a/tools/perf/pmu-events/pmu-events.h
+++ b/tools/perf/pmu-events/pmu-events.h
@@ -59,6 +59,7 @@ struct pmu_metric {
 	const char *compat;
 	const char *desc;
 	const char *long_desc;
+	const char *metricgroup_no_group;
 	enum aggr_mode_class aggr_mode;
 	enum metric_event_groups event_grouping;
 };
diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py
index ccfef861e931..e890c261ad26 100644
--- a/tools/perf/tests/attr.py
+++ b/tools/perf/tests/attr.py
@@ -152,7 +152,7 @@ def parse_version(version):
 #   - expected values assignments
 class Test(object):
     def __init__(self, path, options):
-        parser = configparser.SafeConfigParser()
+        parser = configparser.ConfigParser()
         parser.read(path)
 
         log.warning("running '%s'" % path)
@@ -247,7 +247,7 @@ class Test(object):
         return True
 
     def load_events(self, path, events):
-        parser_event = configparser.SafeConfigParser()
+        parser_event = configparser.ConfigParser()
         parser_event.read(path)
 
         # The event record section header contains 'event' word,
@@ -261,7 +261,7 @@ class Test(object):
             # Read parent event if there's any
             if (':' in section):
                 base = section[section.index(':') + 1:]
-                parser_base = configparser.SafeConfigParser()
+                parser_base = configparser.ConfigParser()
                 parser_base.read(self.test_dir + '/' + base)
                 base_items = parser_base.items('event')
 
diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat
index a21fb65bc012..fccd8ec4d1b0 100644
--- a/tools/perf/tests/attr/base-stat
+++ b/tools/perf/tests/attr/base-stat
@@ -16,7 +16,7 @@ pinned=0
 exclusive=0
 exclude_user=0
 exclude_kernel=0|1
-exclude_hv=0
+exclude_hv=0|1
 exclude_idle=0
 mmap=0
 comm=0
diff --git a/tools/perf/tests/attr/test-stat-default b/tools/perf/tests/attr/test-stat-default
index d8ea6a88163f..a1e2da0a9a6d 100644
--- a/tools/perf/tests/attr/test-stat-default
+++ b/tools/perf/tests/attr/test-stat-default
@@ -40,7 +40,6 @@ fd=6
 type=0
 config=7
 optional=1
-
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND
 [event7:base-stat]
 fd=7
@@ -89,79 +88,98 @@ enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-bad-spec (0x8100)
+# PERF_TYPE_RAW / topdown-fe-bound (0x8200)
 [event13:base-stat]
 fd=13
 group_fd=11
 type=4
-config=33024
+config=33280
 disabled=0
 enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-fe-bound (0x8200)
+# PERF_TYPE_RAW / topdown-be-bound (0x8300)
 [event14:base-stat]
 fd=14
 group_fd=11
 type=4
-config=33280
+config=33536
 disabled=0
 enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-be-bound (0x8300)
+# PERF_TYPE_RAW / topdown-bad-spec (0x8100)
 [event15:base-stat]
 fd=15
 group_fd=11
 type=4
-config=33536
+config=33024
 disabled=0
 enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-heavy-ops (0x8400)
+# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING
 [event16:base-stat]
 fd=16
-group_fd=11
 type=4
-config=33792
-disabled=0
-enable_on_exec=0
-read_format=15
+config=4109
 optional=1
 
-# PERF_TYPE_RAW / topdown-br-mispredict (0x8500)
+# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/
 [event17:base-stat]
 fd=17
-group_fd=11
 type=4
-config=34048
-disabled=0
-enable_on_exec=0
-read_format=15
+config=17039629
 optional=1
 
-# PERF_TYPE_RAW / topdown-fetch-lat (0x8600)
+# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD
 [event18:base-stat]
 fd=18
-group_fd=11
 type=4
-config=34304
-disabled=0
-enable_on_exec=0
-read_format=15
+config=60
 optional=1
 
-# PERF_TYPE_RAW / topdown-mem-bound (0x8700)
+# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY
 [event19:base-stat]
 fd=19
-group_fd=11
 type=4
-config=34560
-disabled=0
-enable_on_exec=0
-read_format=15
+config=2097421
+optional=1
+
+# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK
+[event20:base-stat]
+fd=20
+type=4
+config=316
+optional=1
+
+# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE
+[event21:base-stat]
+fd=21
+type=4
+config=412
+optional=1
+
+# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE
+[event22:base-stat]
+fd=22
+type=4
+config=572
+optional=1
+
+# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS
+[event23:base-stat]
+fd=23
+type=4
+config=706
+optional=1
+
+# PERF_TYPE_RAW / UOPS_ISSUED.ANY
+[event24:base-stat]
+fd=24
+type=4
+config=270
 optional=1
diff --git a/tools/perf/tests/attr/test-stat-detailed-1 b/tools/perf/tests/attr/test-stat-detailed-1
index b656ab93c5bf..1c52cb05c900 100644
--- a/tools/perf/tests/attr/test-stat-detailed-1
+++ b/tools/perf/tests/attr/test-stat-detailed-1
@@ -90,89 +90,108 @@ enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-bad-spec (0x8100)
+# PERF_TYPE_RAW / topdown-fe-bound (0x8200)
 [event13:base-stat]
 fd=13
 group_fd=11
 type=4
-config=33024
+config=33280
 disabled=0
 enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-fe-bound (0x8200)
+# PERF_TYPE_RAW / topdown-be-bound (0x8300)
 [event14:base-stat]
 fd=14
 group_fd=11
 type=4
-config=33280
+config=33536
 disabled=0
 enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-be-bound (0x8300)
+# PERF_TYPE_RAW / topdown-bad-spec (0x8100)
 [event15:base-stat]
 fd=15
 group_fd=11
 type=4
-config=33536
+config=33024
 disabled=0
 enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-heavy-ops (0x8400)
+# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING
 [event16:base-stat]
 fd=16
-group_fd=11
 type=4
-config=33792
-disabled=0
-enable_on_exec=0
-read_format=15
+config=4109
 optional=1
 
-# PERF_TYPE_RAW / topdown-br-mispredict (0x8500)
+# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/
 [event17:base-stat]
 fd=17
-group_fd=11
 type=4
-config=34048
-disabled=0
-enable_on_exec=0
-read_format=15
+config=17039629
 optional=1
 
-# PERF_TYPE_RAW / topdown-fetch-lat (0x8600)
+# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD
 [event18:base-stat]
 fd=18
-group_fd=11
 type=4
-config=34304
-disabled=0
-enable_on_exec=0
-read_format=15
+config=60
 optional=1
 
-# PERF_TYPE_RAW / topdown-mem-bound (0x8700)
+# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY
 [event19:base-stat]
 fd=19
-group_fd=11
 type=4
-config=34560
-disabled=0
-enable_on_exec=0
-read_format=15
+config=2097421
+optional=1
+
+# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK
+[event20:base-stat]
+fd=20
+type=4
+config=316
+optional=1
+
+# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE
+[event21:base-stat]
+fd=21
+type=4
+config=412
+optional=1
+
+# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE
+[event22:base-stat]
+fd=22
+type=4
+config=572
+optional=1
+
+# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS
+[event23:base-stat]
+fd=23
+type=4
+config=706
+optional=1
+
+# PERF_TYPE_RAW / UOPS_ISSUED.ANY
+[event24:base-stat]
+fd=24
+type=4
+config=270
 optional=1
 
 # PERF_TYPE_HW_CACHE /
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
-[event20:base-stat]
-fd=20
+[event25:base-stat]
+fd=25
 type=3
 config=0
 optional=1
@@ -181,8 +200,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
-[event21:base-stat]
-fd=21
+[event26:base-stat]
+fd=26
 type=3
 config=65536
 optional=1
@@ -191,8 +210,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
-[event22:base-stat]
-fd=22
+[event27:base-stat]
+fd=27
 type=3
 config=2
 optional=1
@@ -201,8 +220,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
-[event23:base-stat]
-fd=23
+[event28:base-stat]
+fd=28
 type=3
 config=65538
 optional=1
diff --git a/tools/perf/tests/attr/test-stat-detailed-2 b/tools/perf/tests/attr/test-stat-detailed-2
index 97625090a1c4..7e961d24a885 100644
--- a/tools/perf/tests/attr/test-stat-detailed-2
+++ b/tools/perf/tests/attr/test-stat-detailed-2
@@ -90,89 +90,108 @@ enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-bad-spec (0x8100)
+# PERF_TYPE_RAW / topdown-fe-bound (0x8200)
 [event13:base-stat]
 fd=13
 group_fd=11
 type=4
-config=33024
+config=33280
 disabled=0
 enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-fe-bound (0x8200)
+# PERF_TYPE_RAW / topdown-be-bound (0x8300)
 [event14:base-stat]
 fd=14
 group_fd=11
 type=4
-config=33280
+config=33536
 disabled=0
 enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-be-bound (0x8300)
+# PERF_TYPE_RAW / topdown-bad-spec (0x8100)
 [event15:base-stat]
 fd=15
 group_fd=11
 type=4
-config=33536
+config=33024
 disabled=0
 enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-heavy-ops (0x8400)
+# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING
 [event16:base-stat]
 fd=16
-group_fd=11
 type=4
-config=33792
-disabled=0
-enable_on_exec=0
-read_format=15
+config=4109
 optional=1
 
-# PERF_TYPE_RAW / topdown-br-mispredict (0x8500)
+# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/
 [event17:base-stat]
 fd=17
-group_fd=11
 type=4
-config=34048
-disabled=0
-enable_on_exec=0
-read_format=15
+config=17039629
 optional=1
 
-# PERF_TYPE_RAW / topdown-fetch-lat (0x8600)
+# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD
 [event18:base-stat]
 fd=18
-group_fd=11
 type=4
-config=34304
-disabled=0
-enable_on_exec=0
-read_format=15
+config=60
 optional=1
 
-# PERF_TYPE_RAW / topdown-mem-bound (0x8700)
+# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY
 [event19:base-stat]
 fd=19
-group_fd=11
 type=4
-config=34560
-disabled=0
-enable_on_exec=0
-read_format=15
+config=2097421
+optional=1
+
+# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK
+[event20:base-stat]
+fd=20
+type=4
+config=316
+optional=1
+
+# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE
+[event21:base-stat]
+fd=21
+type=4
+config=412
+optional=1
+
+# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE
+[event22:base-stat]
+fd=22
+type=4
+config=572
+optional=1
+
+# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS
+[event23:base-stat]
+fd=23
+type=4
+config=706
+optional=1
+
+# PERF_TYPE_RAW / UOPS_ISSUED.ANY
+[event24:base-stat]
+fd=24
+type=4
+config=270
 optional=1
 
 # PERF_TYPE_HW_CACHE /
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
-[event20:base-stat]
-fd=20
+[event25:base-stat]
+fd=25
 type=3
 config=0
 optional=1
@@ -181,8 +200,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
-[event21:base-stat]
-fd=21
+[event26:base-stat]
+fd=26
 type=3
 config=65536
 optional=1
@@ -191,8 +210,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
-[event22:base-stat]
-fd=22
+[event27:base-stat]
+fd=27
 type=3
 config=2
 optional=1
@@ -201,8 +220,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
-[event23:base-stat]
-fd=23
+[event28:base-stat]
+fd=28
 type=3
 config=65538
 optional=1
@@ -211,8 +230,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_L1I                <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
-[event24:base-stat]
-fd=24
+[event29:base-stat]
+fd=29
 type=3
 config=1
 optional=1
@@ -221,8 +240,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_L1I                <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
-[event25:base-stat]
-fd=25
+[event30:base-stat]
+fd=30
 type=3
 config=65537
 optional=1
@@ -231,8 +250,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
-[event26:base-stat]
-fd=26
+[event31:base-stat]
+fd=31
 type=3
 config=3
 optional=1
@@ -241,8 +260,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
-[event27:base-stat]
-fd=27
+[event32:base-stat]
+fd=32
 type=3
 config=65539
 optional=1
@@ -251,8 +270,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
-[event28:base-stat]
-fd=28
+[event33:base-stat]
+fd=33
 type=3
 config=4
 optional=1
@@ -261,8 +280,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
-[event29:base-stat]
-fd=29
+[event34:base-stat]
+fd=34
 type=3
 config=65540
 optional=1
diff --git a/tools/perf/tests/attr/test-stat-detailed-3 b/tools/perf/tests/attr/test-stat-detailed-3
index d555042e3fbf..e50535f45977 100644
--- a/tools/perf/tests/attr/test-stat-detailed-3
+++ b/tools/perf/tests/attr/test-stat-detailed-3
@@ -90,89 +90,108 @@ enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-bad-spec (0x8100)
+# PERF_TYPE_RAW / topdown-fe-bound (0x8200)
 [event13:base-stat]
 fd=13
 group_fd=11
 type=4
-config=33024
+config=33280
 disabled=0
 enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-fe-bound (0x8200)
+# PERF_TYPE_RAW / topdown-be-bound (0x8300)
 [event14:base-stat]
 fd=14
 group_fd=11
 type=4
-config=33280
+config=33536
 disabled=0
 enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-be-bound (0x8300)
+# PERF_TYPE_RAW / topdown-bad-spec (0x8100)
 [event15:base-stat]
 fd=15
 group_fd=11
 type=4
-config=33536
+config=33024
 disabled=0
 enable_on_exec=0
 read_format=15
 optional=1
 
-# PERF_TYPE_RAW / topdown-heavy-ops (0x8400)
+# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING
 [event16:base-stat]
 fd=16
-group_fd=11
 type=4
-config=33792
-disabled=0
-enable_on_exec=0
-read_format=15
+config=4109
 optional=1
 
-# PERF_TYPE_RAW / topdown-br-mispredict (0x8500)
+# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/
 [event17:base-stat]
 fd=17
-group_fd=11
 type=4
-config=34048
-disabled=0
-enable_on_exec=0
-read_format=15
+config=17039629
 optional=1
 
-# PERF_TYPE_RAW / topdown-fetch-lat (0x8600)
+# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD
 [event18:base-stat]
 fd=18
-group_fd=11
 type=4
-config=34304
-disabled=0
-enable_on_exec=0
-read_format=15
+config=60
 optional=1
 
-# PERF_TYPE_RAW / topdown-mem-bound (0x8700)
+# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY
 [event19:base-stat]
 fd=19
-group_fd=11
 type=4
-config=34560
-disabled=0
-enable_on_exec=0
-read_format=15
+config=2097421
+optional=1
+
+# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK
+[event20:base-stat]
+fd=20
+type=4
+config=316
+optional=1
+
+# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE
+[event21:base-stat]
+fd=21
+type=4
+config=412
+optional=1
+
+# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE
+[event22:base-stat]
+fd=22
+type=4
+config=572
+optional=1
+
+# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS
+[event23:base-stat]
+fd=23
+type=4
+config=706
+optional=1
+
+# PERF_TYPE_RAW / UOPS_ISSUED.ANY
+[event24:base-stat]
+fd=24
+type=4
+config=270
 optional=1
 
 # PERF_TYPE_HW_CACHE /
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
-[event20:base-stat]
-fd=20
+[event25:base-stat]
+fd=25
 type=3
 config=0
 optional=1
@@ -181,8 +200,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
-[event21:base-stat]
-fd=21
+[event26:base-stat]
+fd=26
 type=3
 config=65536
 optional=1
@@ -191,8 +210,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
-[event22:base-stat]
-fd=22
+[event27:base-stat]
+fd=27
 type=3
 config=2
 optional=1
@@ -201,8 +220,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
-[event23:base-stat]
-fd=23
+[event28:base-stat]
+fd=28
 type=3
 config=65538
 optional=1
@@ -211,8 +230,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_L1I                <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
-[event24:base-stat]
-fd=24
+[event29:base-stat]
+fd=29
 type=3
 config=1
 optional=1
@@ -221,8 +240,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_L1I                <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
-[event25:base-stat]
-fd=25
+[event30:base-stat]
+fd=30
 type=3
 config=65537
 optional=1
@@ -231,8 +250,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
-[event26:base-stat]
-fd=26
+[event31:base-stat]
+fd=31
 type=3
 config=3
 optional=1
@@ -241,8 +260,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
-[event27:base-stat]
-fd=27
+[event32:base-stat]
+fd=32
 type=3
 config=65539
 optional=1
@@ -251,8 +270,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
-[event28:base-stat]
-fd=28
+[event33:base-stat]
+fd=33
 type=3
 config=4
 optional=1
@@ -261,8 +280,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
-[event29:base-stat]
-fd=29
+[event34:base-stat]
+fd=34
 type=3
 config=65540
 optional=1
@@ -271,8 +290,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_PREFETCH        <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
-[event30:base-stat]
-fd=30
+[event35:base-stat]
+fd=35
 type=3
 config=512
 optional=1
@@ -281,8 +300,8 @@ optional=1
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
 # (PERF_COUNT_HW_CACHE_OP_PREFETCH        <<  8) |
 # (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
-[event31:base-stat]
-fd=31
+[event36:base-stat]
+fd=36
 type=3
 config=66048
 optional=1
diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
index cbf0e0c74906..733ead151c63 100644
--- a/tools/perf/tests/expr.c
+++ b/tools/perf/tests/expr.c
@@ -120,7 +120,8 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u
 
 	p = "FOO/0";
 	ret = expr__parse(&val, ctx, p);
-	TEST_ASSERT_VAL("division by zero", ret == -1);
+	TEST_ASSERT_VAL("division by zero", ret == 0);
+	TEST_ASSERT_VAL("division by zero", isnan(val));
 
 	p = "BAR/";
 	ret = expr__parse(&val, ctx, p);
diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c
index 1185b79e6274..c05148ea400c 100644
--- a/tools/perf/tests/parse-metric.c
+++ b/tools/perf/tests/parse-metric.c
@@ -38,6 +38,7 @@ static void load_runtime_stat(struct evlist *evlist, struct value *vals)
 	evlist__alloc_aggr_stats(evlist, 1);
 	evlist__for_each_entry(evlist, evsel) {
 		count = find_value(evsel->name, vals);
+		evsel->supported = true;
 		evsel->stats->aggr->counts.val = count;
 		if (evsel__name_is(evsel, "duration_time"))
 			update_stats(&walltime_nsecs_stats, count);
diff --git a/tools/perf/tests/shell/stat.sh b/tools/perf/tests/shell/stat.sh
index 2c1d3f704995..b154fbb15d54 100755
--- a/tools/perf/tests/shell/stat.sh
+++ b/tools/perf/tests/shell/stat.sh
@@ -28,6 +28,18 @@ test_stat_record_report() {
   echo "stat record and report test [Success]"
 }
 
+test_stat_record_script() {
+  echo "stat record and script test"
+  if ! perf stat record -o - true | perf script -i - 2>&1 | \
+    grep -E -q "CPU[[:space:]]+THREAD[[:space:]]+VAL[[:space:]]+ENA[[:space:]]+RUN[[:space:]]+TIME[[:space:]]+EVENT"
+  then
+    echo "stat record and script test [Failed]"
+    err=1
+    return
+  fi
+  echo "stat record and script test [Success]"
+}
+
 test_stat_repeat_weak_groups() {
   echo "stat repeat weak groups test"
   if ! perf stat -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}' \
@@ -93,6 +105,7 @@ test_topdown_weak_groups() {
 
 test_default_stat
 test_stat_record_report
+test_stat_record_script
 test_stat_repeat_weak_groups
 test_topdown_groups
 test_topdown_weak_groups
diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh
index 4ddb17cb83c5..3a8b9bffa022 100755
--- a/tools/perf/tests/shell/test_intel_pt.sh
+++ b/tools/perf/tests/shell/test_intel_pt.sh
@@ -506,6 +506,13 @@ test_sample()
 		echo "perf record failed with --aux-sample"
 		return 1
 	fi
+	# Check with event with PMU name
+	if perf_record_no_decode -o "${perfdatafile}" -e br_misp_retired.all_branches:u uname ; then
+		if ! perf_record_no_decode -o "${perfdatafile}" -e '{intel_pt//,br_misp_retired.all_branches/aux-sample-size=8192/}:u' uname ; then
+			echo "perf record failed with --aux-sample-size"
+			return 1
+		fi
+	fi
 	echo OK
 	return 0
 }
diff --git a/tools/perf/tests/shell/test_java_symbol.sh b/tools/perf/tests/shell/test_java_symbol.sh
index 90cea8811926..499539d1c479 100755
--- a/tools/perf/tests/shell/test_java_symbol.sh
+++ b/tools/perf/tests/shell/test_java_symbol.sh
@@ -56,7 +56,7 @@ if [ $? -ne 0 ]; then
 	exit 1
 fi
 
-if ! perf inject -i $PERF_DATA -o $PERF_INJ_DATA -j; then
+if ! DEBUGINFOD_URLS='' perf inject -i $PERF_DATA -o $PERF_INJ_DATA -j; then
 	echo "Fail to inject samples"
 	exit 1
 fi
diff --git a/tools/perf/trace/beauty/arch_prctl.c b/tools/perf/trace/beauty/arch_prctl.c
index fe022ca67e60..a211348d3204 100644
--- a/tools/perf/trace/beauty/arch_prctl.c
+++ b/tools/perf/trace/beauty/arch_prctl.c
@@ -12,10 +12,12 @@
 
 static DEFINE_STRARRAY_OFFSET(x86_arch_prctl_codes_1, "ARCH_", x86_arch_prctl_codes_1_offset);
 static DEFINE_STRARRAY_OFFSET(x86_arch_prctl_codes_2, "ARCH_", x86_arch_prctl_codes_2_offset);
+static DEFINE_STRARRAY_OFFSET(x86_arch_prctl_codes_3, "ARCH_", x86_arch_prctl_codes_3_offset);
 
 static struct strarray *x86_arch_prctl_codes[] = {
 	&strarray__x86_arch_prctl_codes_1,
 	&strarray__x86_arch_prctl_codes_2,
+	&strarray__x86_arch_prctl_codes_3,
 };
 
 static DEFINE_STRARRAYS(x86_arch_prctl_codes);
diff --git a/tools/perf/trace/beauty/x86_arch_prctl.sh b/tools/perf/trace/beauty/x86_arch_prctl.sh
index 57fa6aaffe70..fd5c740512c5 100755
--- a/tools/perf/trace/beauty/x86_arch_prctl.sh
+++ b/tools/perf/trace/beauty/x86_arch_prctl.sh
@@ -24,3 +24,4 @@ print_range () {
 
 print_range 1 0x1 0x1001
 print_range 2 0x2 0x2001
+print_range 3 0x4 0x4001
diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c
index 8d3cfbb3cc65..1d48226ae75d 100644
--- a/tools/perf/util/bpf_skel/lock_contention.bpf.c
+++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c
@@ -416,6 +416,8 @@ int contention_end(u64 *ctx)
 	return 0;
 }
 
+struct rq {};
+
 extern struct rq runqueues __ksym;
 
 struct rq___old {
diff --git a/tools/perf/util/bpf_skel/vmlinux.h b/tools/perf/util/bpf_skel/vmlinux.h
index 449b1ea91fc4..c7ed51b0c1ef 100644
--- a/tools/perf/util/bpf_skel/vmlinux.h
+++ b/tools/perf/util/bpf_skel/vmlinux.h
@@ -1,6 +1,7 @@
 #ifndef __VMLINUX_H
 #define __VMLINUX_H
 
+#include <linux/stddef.h> // for define __always_inline
 #include <linux/bpf.h>
 #include <linux/types.h>
 #include <linux/perf_event.h>
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 356c07f03be6..2f5910b31fa9 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -290,6 +290,7 @@ void evsel__init(struct evsel *evsel,
 	evsel->per_pkg_mask  = NULL;
 	evsel->collect_stat  = false;
 	evsel->pmu_name      = NULL;
+	evsel->skippable     = false;
 }
 
 struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx)
@@ -828,26 +829,26 @@ bool evsel__name_is(struct evsel *evsel, const char *name)
 
 const char *evsel__group_pmu_name(const struct evsel *evsel)
 {
-	const struct evsel *leader;
+	struct evsel *leader = evsel__leader(evsel);
+	struct evsel *pos;
 
-	/* If the pmu_name is set use it. pmu_name isn't set for CPU and software events. */
-	if (evsel->pmu_name)
-		return evsel->pmu_name;
 	/*
 	 * Software events may be in a group with other uncore PMU events. Use
-	 * the pmu_name of the group leader to avoid breaking the software event
-	 * out of the group.
+	 * the pmu_name of the first non-software event to avoid breaking the
+	 * software event out of the group.
 	 *
 	 * Aux event leaders, like intel_pt, expect a group with events from
 	 * other PMUs, so substitute the AUX event's PMU in this case.
 	 */
-	leader  = evsel__leader(evsel);
-	if ((evsel->core.attr.type == PERF_TYPE_SOFTWARE || evsel__is_aux_event(leader)) &&
-	    leader->pmu_name) {
-		return leader->pmu_name;
+	if (evsel->core.attr.type == PERF_TYPE_SOFTWARE || evsel__is_aux_event(leader)) {
+		/* Starting with the leader, find the first event with a named PMU. */
+		for_each_group_evsel(pos, leader) {
+			if (pos->pmu_name)
+				return pos->pmu_name;
+		}
 	}
 
-	return "cpu";
+	return evsel->pmu_name ?: "cpu";
 }
 
 const char *evsel__metric_id(const struct evsel *evsel)
@@ -1725,9 +1726,13 @@ static int get_group_fd(struct evsel *evsel, int cpu_map_idx, int thread)
 		return -1;
 
 	fd = FD(leader, cpu_map_idx, thread);
-	BUG_ON(fd == -1);
+	BUG_ON(fd == -1 && !leader->skippable);
 
-	return fd;
+	/*
+	 * When the leader has been skipped, return -2 to distinguish from no
+	 * group leader case.
+	 */
+	return fd == -1 ? -2 : fd;
 }
 
 static void evsel__remove_fd(struct evsel *pos, int nr_cpus, int nr_threads, int thread_idx)
@@ -2109,6 +2114,12 @@ retry_open:
 
 			group_fd = get_group_fd(evsel, idx, thread);
 
+			if (group_fd == -2) {
+				pr_debug("broken group leader for %s\n", evsel->name);
+				err = -EINVAL;
+				goto out_close;
+			}
+
 			test_attr__ready();
 
 			/* Debug message used by test scripts */
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index d575390d80bc..df8928745fc6 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -95,6 +95,7 @@ struct evsel {
 		bool			weak_group;
 		bool			bpf_counter;
 		bool			use_config_name;
+		bool			skippable;
 		int			bpf_fd;
 		struct bpf_object	*bpf_obj;
 		struct list_head	config_terms;
diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y
index 250e444bf032..4ce931cccb63 100644
--- a/tools/perf/util/expr.y
+++ b/tools/perf/util/expr.y
@@ -225,7 +225,11 @@ expr: NUMBER
 {
 	if (fpclassify($3.val) == FP_ZERO) {
 		pr_debug("division by zero\n");
-		YYABORT;
+		assert($3.ids == NULL);
+		if (compute_ids)
+			ids__free($1.ids);
+		$$.val = NAN;
+		$$.ids = NULL;
 	} else if (!compute_ids || (is_const($1.val) && is_const($3.val))) {
 		assert($1.ids == NULL);
 		assert($3.ids == NULL);
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index c566c6859302..5e9c657dd3f7 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -1144,12 +1144,12 @@ static int metricgroup__add_metric_callback(const struct pmu_metric *pm,
 	struct metricgroup__add_metric_data *data = vdata;
 	int ret = 0;
 
-	if (pm->metric_expr &&
-		(match_metric(pm->metric_group, data->metric_name) ||
-		 match_metric(pm->metric_name, data->metric_name))) {
+	if (pm->metric_expr && match_pm_metric(pm, data->metric_name)) {
+		bool metric_no_group = data->metric_no_group ||
+			match_metric(data->metric_name, pm->metricgroup_no_group);
 
 		data->has_match = true;
-		ret = add_metric(data->list, pm, data->modifier, data->metric_no_group,
+		ret = add_metric(data->list, pm, data->modifier, metric_no_group,
 				 data->metric_no_threshold, data->user_requested_cpu_list,
 				 data->system_wide, /*root_metric=*/NULL,
 				 /*visited_metrics=*/NULL, table);
@@ -1672,7 +1672,7 @@ static int metricgroup__topdown_max_level_callback(const struct pmu_metric *pm,
 {
 	unsigned int *max_level = data;
 	unsigned int level;
-	const char *p = strstr(pm->metric_group, "TopdownL");
+	const char *p = strstr(pm->metric_group ?: "", "TopdownL");
 
 	if (!p || p[8] == '\0')
 		return 0;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index d71019dcd614..34ba840ae19a 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -2140,25 +2140,32 @@ static int evlist__cmp(void *state, const struct list_head *l, const struct list
 	int *leader_idx = state;
 	int lhs_leader_idx = *leader_idx, rhs_leader_idx = *leader_idx, ret;
 	const char *lhs_pmu_name, *rhs_pmu_name;
+	bool lhs_has_group = false, rhs_has_group = false;
 
 	/*
 	 * First sort by grouping/leader. Read the leader idx only if the evsel
 	 * is part of a group, as -1 indicates no group.
 	 */
-	if (lhs_core->leader != lhs_core || lhs_core->nr_members > 1)
+	if (lhs_core->leader != lhs_core || lhs_core->nr_members > 1) {
+		lhs_has_group = true;
 		lhs_leader_idx = lhs_core->leader->idx;
-	if (rhs_core->leader != rhs_core || rhs_core->nr_members > 1)
+	}
+	if (rhs_core->leader != rhs_core || rhs_core->nr_members > 1) {
+		rhs_has_group = true;
 		rhs_leader_idx = rhs_core->leader->idx;
+	}
 
 	if (lhs_leader_idx != rhs_leader_idx)
 		return lhs_leader_idx - rhs_leader_idx;
 
-	/* Group by PMU. Groups can't span PMUs. */
-	lhs_pmu_name = evsel__group_pmu_name(lhs);
-	rhs_pmu_name = evsel__group_pmu_name(rhs);
-	ret = strcmp(lhs_pmu_name, rhs_pmu_name);
-	if (ret)
-		return ret;
+	/* Group by PMU if there is a group. Groups can't span PMUs. */
+	if (lhs_has_group && rhs_has_group) {
+		lhs_pmu_name = evsel__group_pmu_name(lhs);
+		rhs_pmu_name = evsel__group_pmu_name(rhs);
+		ret = strcmp(lhs_pmu_name, rhs_pmu_name);
+		if (ret)
+			return ret;
+	}
 
 	/* Architecture specific sorting. */
 	return arch_evlist__cmp(lhs, rhs);
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 73b2ff2ddf29..bf5a6c14dfcd 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -431,7 +431,7 @@ static void print_metric_json(struct perf_stat_config *config __maybe_unused,
 	struct outstate *os = ctx;
 	FILE *out = os->fh;
 
-	fprintf(out, "\"metric-value\" : %f, ", val);
+	fprintf(out, "\"metric-value\" : \"%f\", ", val);
 	fprintf(out, "\"metric-unit\" : \"%s\"", unit);
 	if (!config->metric_only)
 		fprintf(out, "}");
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index eeccab6751d7..1566a206ba42 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -403,12 +403,25 @@ static int prepare_metric(struct evsel **metric_events,
 			if (!aggr)
 				break;
 
-			/*
-			 * If an event was scaled during stat gathering, reverse
-			 * the scale before computing the metric.
-			 */
-			val = aggr->counts.val * (1.0 / metric_events[i]->scale);
-			source_count = evsel__source_count(metric_events[i]);
+                        if (!metric_events[i]->supported) {
+				/*
+				 * Not supported events will have a count of 0,
+				 * which can be confusing in a
+				 * metric. Explicitly set the value to NAN. Not
+				 * counted events (enable time of 0) are read as
+				 * 0.
+				 */
+				val = NAN;
+				source_count = 0;
+			} else {
+				/*
+				 * If an event was scaled during stat gathering,
+				 * reverse the scale before computing the
+				 * metric.
+				 */
+				val = aggr->counts.val * (1.0 / metric_events[i]->scale);
+				source_count = evsel__source_count(metric_events[i]);
+			}
 		}
 		n = strdup(evsel__metric_id(metric_events[i]));
 		if (!n)