Merge tag 'irqchip-6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/maz/arm-platforms into irq/core

Pull irqchip updates from Marc Zyngier:

  - A number of Loogson/Loogarch fixes

  - Allow the core code to retrigger an interrupt that has
    fired while the same interrupt is being handled on another
    CPU, papering over a GICv3 architecture issue

  - Work around an integration problem on ASR8601, where the CPU
    numbering isn't representable in the GIC implementation...

  - Add some missing interrupt to the STM32 irqchip

  - A bunch of warning squashing triggered by W=1 builds

Link: https://lore.kernel.org/r/20230623224345.3577134-1-maz@kernel.org

54 files changed, 660 insertions, 244 deletions

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;