Merge tag 'perf-tools-for-v7.0-1-2026-02-21' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

Pull perf tools updates from Arnaldo Carvalho de Melo:

 - Introduce 'perf sched stats' tool with record/report/diff workflows
   using schedstat counters

 - Add a faster libdw based addr2line implementation and allow selecting
   it or its alternatives via 'perf config addr2line.style='

 - Data-type profiling fixes and improvements including the ability to
   select fields using 'perf report''s -F/-fields, e.g.:

     'perf report --fields overhead,type'

 - Add 'perf test' regression tests for Data-type profiling with C and
   Rust workloads

 - Fix srcline printing with inlines in callchains, make sure this has
   coverage in 'perf test'

 - Fix printing of leaf IP in LBR callchains

 - Fix display of metrics without sufficient permission in 'perf stat'

 - Print all machines in 'perf kvm report -vvv', not just the host

 - Switch from SHA-1 to BLAKE2s for build ID generation, remove SHA-1
   code

 - Fix 'perf report's histogram entry collapsing with '-F' option

 - Use system's cacheline size instead of a hardcoded value in 'perf
   report'

 - Allow filtering conversion by time range in 'perf data'

 - Cover conversion to CTF using 'perf data' in 'perf test'

 - Address newer glibc const-correctness (-Werror=discarded-qualifiers)
   issues

 - Fixes and improvements for ARM's CoreSight support, simplify ARM SPE
   event config in 'perf mem', update docs for 'perf c2c' including the
   ARM events it can be used with

 - Build support for generating metrics from arch specific python
   script, add extra AMD, Intel, ARM64 metrics using it

 - Add AMD Zen 6 events and metrics

 - Add JSON file with OpenHW Risc-V CVA6 hardware counters

 - Add 'perf kvm' stats live testing

 - Add more 'perf stat' tests to 'perf test'

 - Fix segfault in `perf lock contention -b/--use-bpf`

 - Fix various 'perf test' cases for s390

 - Build system cleanups, bump minimum shellcheck version to 0.7.2

 - Support building the capstone based annotation routines as a plugin

 - Allow passing extra Clang flags via EXTRA_BPF_FLAGS

* tag 'perf-tools-for-v7.0-1-2026-02-21' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (255 commits)
  perf test script: Add python script testing support
  perf test script: Add perl script testing support
  perf script: Allow the generated script to be a path
  perf test: perf data --to-ctf testing
  perf test: Test pipe mode with data conversion --to-json
  perf json: Pipe mode --to-ctf support
  perf json: Pipe mode --to-json support
  perf check: Add libbabeltrace to the listed features
  perf build: Allow passing extra Clang flags via EXTRA_BPF_FLAGS
  perf test data_type_profiling.sh: Skip just the Rust tests if code_with_type workload is missing
  tools build: Fix feature test for rust compiler
  perf libunwind: Fix calls to thread__e_machine()
  perf stat: Add no-affinity flag
  perf evlist: Reduce affinity use and move into iterator, fix no affinity
  perf evlist: Missing TPEBS close in evlist__close()
  perf evlist: Special map propagation for tool events that read on 1 CPU
  perf stat-shadow: In prepare_metric fix guard on reading NULL perf_stat_evsel
  Revert "perf tool_pmu: More accurately set the cpus for tool events"
  tools build: Emit dependencies file for test-rust.bin
  tools build: Make test-rust.bin be removed by the 'clean' target
  ...

9 files changed, 571 insertions, 21 deletions

diff --git a/tools/lib/perf/Documentation/libperf.txt b/tools/lib/perf/Documentation/libperf.txt
index 4072bc9b7670..576ecc5fc312 100644
--- a/tools/lib/perf/Documentation/libperf.txt
+++ b/tools/lib/perf/Documentation/libperf.txt
@@ -211,6 +211,8 @@ SYNOPSIS
   struct perf_record_header_feature;
   struct perf_record_compressed;
   struct perf_record_compressed2;
+  struct perf_record_schedstat_cpu;
+  struct perf_record_schedstat_domain;
 --
 
 DESCRIPTION
diff --git a/tools/lib/perf/Makefile b/tools/lib/perf/Makefile
index 7fbb50b74c00..32301a1d8f0c 100644
--- a/tools/lib/perf/Makefile
+++ b/tools/lib/perf/Makefile
@@ -42,7 +42,6 @@ libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
 TEST_ARGS := $(if $(V),-v)
 
 INCLUDES = \
--I$(OUTPUT)arch/$(SRCARCH)/include/generated/uapi \
 -I$(srctree)/tools/lib/perf/include \
 -I$(srctree)/tools/lib/ \
 -I$(srctree)/tools/include \
@@ -51,9 +50,9 @@ INCLUDES = \
 -I$(srctree)/tools/include/uapi
 
 # Append required CFLAGS
+override CFLAGS := $(INCLUDES) $(CFLAGS)
 override CFLAGS += -g -Werror -Wall
 override CFLAGS += -fPIC
-override CFLAGS += $(INCLUDES)
 override CFLAGS += -fvisibility=hidden
 override CFLAGS += $(EXTRA_WARNINGS)
 override CFLAGS += $(EXTRA_CFLAGS)
@@ -100,16 +99,7 @@ $(LIBAPI)-clean:
 	$(call QUIET_CLEAN, libapi)
 	$(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null
 
-uapi-asm := $(OUTPUT)arch/$(SRCARCH)/include/generated/uapi/asm
-ifeq ($(SRCARCH),arm64)
-	syscall-y := $(uapi-asm)/unistd_64.h
-endif
-uapi-asm-generic:
-	$(if $(syscall-y),\
-		$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.asm-headers obj=$(uapi-asm) \
-		generic=include/uapi/asm-generic $(syscall-y),)
-
-$(LIBPERF_IN): uapi-asm-generic FORCE
+$(LIBPERF_IN): FORCE
 	$(Q)$(MAKE) $(build)=libperf
 
 $(LIBPERF_A): $(LIBPERF_IN)
@@ -130,7 +120,7 @@ all: fixdep
 clean: $(LIBAPI)-clean
 	$(call QUIET_CLEAN, libperf) $(RM) $(LIBPERF_A) \
                 *.o *~ *.a *.so *.so.$(VERSION) *.so.$(LIBPERF_VERSION) .*.d .*.cmd tests/*.o LIBPERF-CFLAGS $(LIBPERF_PC) \
-                $(TESTS_STATIC) $(TESTS_SHARED) $(syscall-y)
+                $(TESTS_STATIC) $(TESTS_SHARED)
 
 TESTS_IN = tests-in.o
 
@@ -179,6 +169,7 @@ install_lib: libs
 		cp -fpR $(LIBPERF_ALL) $(DESTDIR)$(libdir_SQ)
 
 HDRS := bpf_perf.h core.h cpumap.h threadmap.h evlist.h evsel.h event.h mmap.h
+HDRS += schedstat-v15.h schedstat-v16.h schedstat-v17.h
 INTERNAL_HDRS := cpumap.h evlist.h evsel.h lib.h mmap.h rc_check.h threadmap.h xyarray.h
 
 INSTALL_HDRS_PFX := $(DESTDIR)$(prefix)/include/perf
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index 3ed023f4b190..1f210dadd666 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -101,6 +101,28 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
 		evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus);
 	}
 
+	/*
+	 * Tool events may only read on the first CPU index to avoid double
+	 * counting things like duration_time. Make the evsel->cpus contain just
+	 * that single entry otherwise we may spend time changing affinity to
+	 * CPUs that just have tool events, etc.
+	 */
+	if (evsel->reads_only_on_cpu_idx0 && perf_cpu_map__nr(evsel->cpus) > 0) {
+		struct perf_cpu_map *srcs[3] = {
+			evlist->all_cpus,
+			evlist->user_requested_cpus,
+			evsel->pmu_cpus,
+		};
+		for (size_t i = 0; i < ARRAY_SIZE(srcs); i++) {
+			if (!srcs[i])
+				continue;
+
+			perf_cpu_map__put(evsel->cpus);
+			evsel->cpus = perf_cpu_map__new_int(perf_cpu_map__cpu(srcs[i], 0).cpu);
+			break;
+		}
+	}
+
 	/* Sanity check assert before the evsel is potentially removed. */
 	assert(!evsel->requires_cpu || !perf_cpu_map__has_any_cpu(evsel->cpus));
 
@@ -133,16 +155,22 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
 
 static void perf_evlist__propagate_maps(struct perf_evlist *evlist)
 {
-	struct perf_evsel *evsel, *n;
-
 	evlist->needs_map_propagation = true;
 
 	/* Clear the all_cpus set which will be merged into during propagation. */
 	perf_cpu_map__put(evlist->all_cpus);
 	evlist->all_cpus = NULL;
 
-	list_for_each_entry_safe(evsel, n, &evlist->entries, node)
-		__perf_evlist__propagate_maps(evlist, evsel);
+	/* 2 rounds so that reads_only_on_cpu_idx0 benefit from knowing the other CPU maps. */
+	for (int round = 0; round < 2; round++) {
+		struct perf_evsel *evsel, *n;
+
+		list_for_each_entry_safe(evsel, n, &evlist->entries, node) {
+			if ((!evsel->reads_only_on_cpu_idx0 && round == 0) ||
+			    (evsel->reads_only_on_cpu_idx0 && round == 1))
+				__perf_evlist__propagate_maps(evlist, evsel);
+		}
+	}
 }
 
 void perf_evlist__add(struct perf_evlist *evlist,
diff --git a/tools/lib/perf/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h
index fefe64ba5e26..b988034f1371 100644
--- a/tools/lib/perf/include/internal/evsel.h
+++ b/tools/lib/perf/include/internal/evsel.h
@@ -128,6 +128,8 @@ struct perf_evsel {
 	bool			 requires_cpu;
 	/** Is the PMU for the event a core one? Effects the handling of own_cpus. */
 	bool			 is_pmu_core;
+	/** Does the evsel on read on the first CPU index such as tool time events? */
+	bool			 reads_only_on_cpu_idx0;
 	int			 idx;
 };
 
diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h
index 43a8cb04994f..9043dc72b5d6 100644
--- a/tools/lib/perf/include/perf/event.h
+++ b/tools/lib/perf/include/perf/event.h
@@ -496,6 +496,71 @@ struct perf_record_bpf_metadata {
 	struct perf_record_bpf_metadata_entry entries[];
 };
 
+struct perf_record_schedstat_cpu_v15 {
+#define CPU_FIELD(_type, _name, _desc, _format, _is_pct, _pct_of, _ver)		_type _name
+#include "schedstat-v15.h"
+#undef CPU_FIELD
+};
+
+struct perf_record_schedstat_cpu_v16 {
+#define CPU_FIELD(_type, _name, _desc, _format, _is_pct, _pct_of, _ver)		_type _name
+#include "schedstat-v16.h"
+#undef CPU_FIELD
+};
+
+struct perf_record_schedstat_cpu_v17 {
+#define CPU_FIELD(_type, _name, _desc, _format, _is_pct, _pct_of, _ver)		_type _name
+#include "schedstat-v17.h"
+#undef CPU_FIELD
+};
+
+struct perf_record_schedstat_cpu {
+	struct perf_event_header header;
+	__u64			 timestamp;
+	__u32			 cpu;
+	__u16			 version;
+	/* Padding */
+	char			 __pad[2];
+	union {
+		struct perf_record_schedstat_cpu_v15 v15;
+		struct perf_record_schedstat_cpu_v16 v16;
+		struct perf_record_schedstat_cpu_v17 v17;
+	};
+};
+
+struct perf_record_schedstat_domain_v15 {
+#define DOMAIN_FIELD(_type, _name, _desc, _format, _is_jiffies, _ver)		_type _name
+#include "schedstat-v15.h"
+#undef DOMAIN_FIELD
+};
+
+struct perf_record_schedstat_domain_v16 {
+#define DOMAIN_FIELD(_type, _name, _desc, _format, _is_jiffies, _ver)		_type _name
+#include "schedstat-v16.h"
+#undef DOMAIN_FIELD
+};
+
+struct perf_record_schedstat_domain_v17 {
+#define DOMAIN_FIELD(_type, _name, _desc, _format, _is_jiffies, _ver)		_type _name
+#include "schedstat-v17.h"
+#undef DOMAIN_FIELD
+};
+
+#define DOMAIN_NAME_LEN		16
+
+struct perf_record_schedstat_domain {
+	struct perf_event_header header;
+	__u64			 timestamp;
+	__u32			 cpu;
+	__u16			 version;
+	__u16			 domain;
+	union {
+		struct perf_record_schedstat_domain_v15 v15;
+		struct perf_record_schedstat_domain_v16 v16;
+		struct perf_record_schedstat_domain_v17 v17;
+	};
+};
+
 enum perf_user_event_type { /* above any possible kernel type */
 	PERF_RECORD_USER_TYPE_START		= 64,
 	PERF_RECORD_HEADER_ATTR			= 64,
@@ -519,6 +584,8 @@ enum perf_user_event_type { /* above any possible kernel type */
 	PERF_RECORD_FINISHED_INIT		= 82,
 	PERF_RECORD_COMPRESSED2			= 83,
 	PERF_RECORD_BPF_METADATA		= 84,
+	PERF_RECORD_SCHEDSTAT_CPU		= 85,
+	PERF_RECORD_SCHEDSTAT_DOMAIN		= 86,
 	PERF_RECORD_HEADER_MAX
 };
 
@@ -562,6 +629,8 @@ union perf_event {
 	struct perf_record_compressed		pack;
 	struct perf_record_compressed2		pack2;
 	struct perf_record_bpf_metadata		bpf_metadata;
+	struct perf_record_schedstat_cpu	schedstat_cpu;
+	struct perf_record_schedstat_domain	schedstat_domain;
 };
 
 #endif /* __LIBPERF_EVENT_H */
diff --git a/tools/lib/perf/include/perf/schedstat-v15.h b/tools/lib/perf/include/perf/schedstat-v15.h
new file mode 100644
index 000000000000..639458df05f8
--- /dev/null
+++ b/tools/lib/perf/include/perf/schedstat-v15.h
@@ -0,0 +1,146 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifdef CPU_FIELD
+CPU_FIELD(__u32, yld_count, "sched_yield() count",
+	  "%11u", false, yld_count, v15);
+CPU_FIELD(__u32, array_exp, "Legacy counter can be ignored",
+	  "%11u", false, array_exp, v15);
+CPU_FIELD(__u32, sched_count, "schedule() called",
+	  "%11u", false, sched_count, v15);
+CPU_FIELD(__u32, sched_goidle, "schedule() left the processor idle",
+	  "%11u", true, sched_count, v15);
+CPU_FIELD(__u32, ttwu_count, "try_to_wake_up() was called",
+	  "%11u", false, ttwu_count, v15);
+CPU_FIELD(__u32, ttwu_local, "try_to_wake_up() was called to wake up the local cpu",
+	  "%11u", true, ttwu_count, v15);
+CPU_FIELD(__u64, rq_cpu_time, "total runtime by tasks on this processor (in jiffies)",
+	  "%11llu", false, rq_cpu_time, v15);
+CPU_FIELD(__u64, run_delay, "total waittime by tasks on this processor (in jiffies)",
+	  "%11llu", true, rq_cpu_time, v15);
+CPU_FIELD(__u64, pcount, "total timeslices run on this cpu",
+	  "%11llu", false, pcount, v15);
+#endif
+
+#ifdef DOMAIN_FIELD
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category idle> ");
+#endif
+DOMAIN_FIELD(__u32, idle_lb_count,
+	     "load_balance() count on cpu idle", "%11u", true, v15);
+DOMAIN_FIELD(__u32, idle_lb_balanced,
+	     "load_balance() found balanced on cpu idle", "%11u", true, v15);
+DOMAIN_FIELD(__u32, idle_lb_failed,
+	     "load_balance() move task failed on cpu idle", "%11u", true, v15);
+DOMAIN_FIELD(__u32, idle_lb_imbalance,
+	     "imbalance sum on cpu idle", "%11u", false, v15);
+DOMAIN_FIELD(__u32, idle_lb_gained,
+	     "pull_task() count on cpu idle", "%11u", false, v15);
+DOMAIN_FIELD(__u32, idle_lb_hot_gained,
+	     "pull_task() when target task was cache-hot on cpu idle", "%11u", false, v15);
+DOMAIN_FIELD(__u32, idle_lb_nobusyq,
+	     "load_balance() failed to find busier queue on cpu idle", "%11u", true, v15);
+DOMAIN_FIELD(__u32, idle_lb_nobusyg,
+	     "load_balance() failed to find busier group on cpu idle", "%11u", true, v15);
+#ifdef DERIVED_CNT_FIELD
+DERIVED_CNT_FIELD(idle_lb_success_count, "load_balance() success count on cpu idle", "%11u",
+		  idle_lb_count, idle_lb_balanced, idle_lb_failed, v15);
+#endif
+#ifdef DERIVED_AVG_FIELD
+DERIVED_AVG_FIELD(idle_lb_avg_pulled,
+		  "avg task pulled per successful lb attempt (cpu idle)", "%11.2Lf",
+		  idle_lb_count, idle_lb_balanced, idle_lb_failed, idle_lb_gained, v15);
+#endif
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category busy> ");
+#endif
+DOMAIN_FIELD(__u32, busy_lb_count,
+	     "load_balance() count on cpu busy", "%11u", true, v15);
+DOMAIN_FIELD(__u32, busy_lb_balanced,
+	     "load_balance() found balanced on cpu busy", "%11u", true, v15);
+DOMAIN_FIELD(__u32, busy_lb_failed,
+	     "load_balance() move task failed on cpu busy", "%11u", true, v15);
+DOMAIN_FIELD(__u32, busy_lb_imbalance,
+	     "imbalance sum on cpu busy", "%11u", false, v15);
+DOMAIN_FIELD(__u32, busy_lb_gained,
+	     "pull_task() count on cpu busy", "%11u", false, v15);
+DOMAIN_FIELD(__u32, busy_lb_hot_gained,
+	     "pull_task() when target task was cache-hot on cpu busy", "%11u", false, v15);
+DOMAIN_FIELD(__u32, busy_lb_nobusyq,
+	     "load_balance() failed to find busier queue on cpu busy", "%11u", true, v15);
+DOMAIN_FIELD(__u32, busy_lb_nobusyg,
+	     "load_balance() failed to find busier group on cpu busy", "%11u", true, v15);
+#ifdef DERIVED_CNT_FIELD
+DERIVED_CNT_FIELD(busy_lb_success_count, "load_balance() success count on cpu busy", "%11u",
+		  busy_lb_count, busy_lb_balanced, busy_lb_failed, v15);
+#endif
+#ifdef DERIVED_AVG_FIELD
+DERIVED_AVG_FIELD(busy_lb_avg_pulled,
+		  "avg task pulled per successful lb attempt (cpu busy)", "%11.2Lf",
+		  busy_lb_count, busy_lb_balanced, busy_lb_failed, busy_lb_gained, v15);
+#endif
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category newidle> ");
+#endif
+DOMAIN_FIELD(__u32, newidle_lb_count,
+	     "load_balance() count on cpu newly idle", "%11u", true, v15);
+DOMAIN_FIELD(__u32, newidle_lb_balanced,
+	     "load_balance() found balanced on cpu newly idle", "%11u", true, v15);
+DOMAIN_FIELD(__u32, newidle_lb_failed,
+	     "load_balance() move task failed on cpu newly idle", "%11u", true, v15);
+DOMAIN_FIELD(__u32, newidle_lb_imbalance,
+	     "imbalance sum on cpu newly idle", "%11u", false, v15);
+DOMAIN_FIELD(__u32, newidle_lb_gained,
+	     "pull_task() count on cpu newly idle", "%11u", false, v15);
+DOMAIN_FIELD(__u32, newidle_lb_hot_gained,
+	     "pull_task() when target task was cache-hot on cpu newly idle", "%11u", false, v15);
+DOMAIN_FIELD(__u32, newidle_lb_nobusyq,
+	     "load_balance() failed to find busier queue on cpu newly idle", "%11u", true, v15);
+DOMAIN_FIELD(__u32, newidle_lb_nobusyg,
+	     "load_balance() failed to find busier group on cpu newly idle", "%11u", true, v15);
+#ifdef DERIVED_CNT_FIELD
+DERIVED_CNT_FIELD(newidle_lb_success_count,
+		  "load_balance() success count on cpu newly idle", "%11u",
+		  newidle_lb_count, newidle_lb_balanced, newidle_lb_failed, v15);
+#endif
+#ifdef DERIVED_AVG_FIELD
+DERIVED_AVG_FIELD(newidle_lb_avg_pulled,
+		  "avg task pulled per successful lb attempt (cpu newly idle)", "%11.2Lf",
+		  newidle_lb_count, newidle_lb_balanced, newidle_lb_failed, newidle_lb_gained, v15);
+#endif
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category active_load_balance()> ");
+#endif
+DOMAIN_FIELD(__u32, alb_count,
+	     "active_load_balance() count", "%11u", false, v15);
+DOMAIN_FIELD(__u32, alb_failed,
+	     "active_load_balance() move task failed", "%11u", false, v15);
+DOMAIN_FIELD(__u32, alb_pushed,
+	     "active_load_balance() successfully moved a task", "%11u", false, v15);
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category sched_balance_exec()> ");
+#endif
+DOMAIN_FIELD(__u32, sbe_count,
+	     "sbe_count is not used", "%11u", false, v15);
+DOMAIN_FIELD(__u32, sbe_balanced,
+	     "sbe_balanced is not used", "%11u", false, v15);
+DOMAIN_FIELD(__u32, sbe_pushed,
+	     "sbe_pushed is not used", "%11u", false, v15);
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category sched_balance_fork()> ");
+#endif
+DOMAIN_FIELD(__u32, sbf_count,
+	     "sbf_count is not used", "%11u", false, v15);
+DOMAIN_FIELD(__u32, sbf_balanced,
+	     "sbf_balanced is not used", "%11u", false, v15);
+DOMAIN_FIELD(__u32, sbf_pushed,
+	     "sbf_pushed is not used", "%11u", false, v15);
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Wakeup Info> ");
+#endif
+DOMAIN_FIELD(__u32, ttwu_wake_remote,
+	     "try_to_wake_up() awoke a task that last ran on a diff cpu", "%11u", false, v15);
+DOMAIN_FIELD(__u32, ttwu_move_affine,
+	     "try_to_wake_up() moved task because cache-cold on own cpu", "%11u", false, v15);
+DOMAIN_FIELD(__u32, ttwu_move_balance,
+	     "try_to_wake_up() started passive balancing", "%11u", false, v15);
+#endif /* DOMAIN_FIELD */
diff --git a/tools/lib/perf/include/perf/schedstat-v16.h b/tools/lib/perf/include/perf/schedstat-v16.h
new file mode 100644
index 000000000000..3462b79c29af
--- /dev/null
+++ b/tools/lib/perf/include/perf/schedstat-v16.h
@@ -0,0 +1,146 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifdef CPU_FIELD
+CPU_FIELD(__u32, yld_count, "sched_yield() count",
+	  "%11u", false, yld_count, v16);
+CPU_FIELD(__u32, array_exp, "Legacy counter can be ignored",
+	  "%11u", false, array_exp, v16);
+CPU_FIELD(__u32, sched_count, "schedule() called",
+	  "%11u", false, sched_count, v16);
+CPU_FIELD(__u32, sched_goidle, "schedule() left the processor idle",
+	  "%11u", true, sched_count, v16);
+CPU_FIELD(__u32, ttwu_count, "try_to_wake_up() was called",
+	  "%11u", false, ttwu_count, v16);
+CPU_FIELD(__u32, ttwu_local, "try_to_wake_up() was called to wake up the local cpu",
+	  "%11u", true, ttwu_count, v16);
+CPU_FIELD(__u64, rq_cpu_time, "total runtime by tasks on this processor (in jiffies)",
+	  "%11llu", false, rq_cpu_time, v16);
+CPU_FIELD(__u64, run_delay, "total waittime by tasks on this processor (in jiffies)",
+	  "%11llu", true, rq_cpu_time, v16);
+CPU_FIELD(__u64, pcount, "total timeslices run on this cpu",
+	  "%11llu", false, pcount, v16);
+#endif /* CPU_FIELD */
+
+#ifdef DOMAIN_FIELD
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category busy> ");
+#endif
+DOMAIN_FIELD(__u32, busy_lb_count,
+	     "load_balance() count on cpu busy", "%11u", true, v16);
+DOMAIN_FIELD(__u32, busy_lb_balanced,
+	     "load_balance() found balanced on cpu busy", "%11u", true, v16);
+DOMAIN_FIELD(__u32, busy_lb_failed,
+	     "load_balance() move task failed on cpu busy", "%11u", true, v16);
+DOMAIN_FIELD(__u32, busy_lb_imbalance,
+	     "imbalance sum on cpu busy", "%11u", false, v16);
+DOMAIN_FIELD(__u32, busy_lb_gained,
+	     "pull_task() count on cpu busy", "%11u", false, v16);
+DOMAIN_FIELD(__u32, busy_lb_hot_gained,
+	     "pull_task() when target task was cache-hot on cpu busy", "%11u", false, v16);
+DOMAIN_FIELD(__u32, busy_lb_nobusyq,
+	     "load_balance() failed to find busier queue on cpu busy", "%11u", true, v16);
+DOMAIN_FIELD(__u32, busy_lb_nobusyg,
+	     "load_balance() failed to find busier group on cpu busy", "%11u", true, v16);
+#ifdef DERIVED_CNT_FIELD
+DERIVED_CNT_FIELD(busy_lb_success_count, "load_balance() success count on cpu busy", "%11u",
+		  busy_lb_count, busy_lb_balanced, busy_lb_failed, v16);
+#endif
+#ifdef DERIVED_AVG_FIELD
+DERIVED_AVG_FIELD(busy_lb_avg_pulled,
+		  "avg task pulled per successful lb attempt (cpu busy)", "%11.2Lf",
+		  busy_lb_count, busy_lb_balanced, busy_lb_failed, busy_lb_gained, v16);
+#endif
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category idle> ");
+#endif
+DOMAIN_FIELD(__u32, idle_lb_count,
+	     "load_balance() count on cpu idle", "%11u", true, v16);
+DOMAIN_FIELD(__u32, idle_lb_balanced,
+	     "load_balance() found balanced on cpu idle", "%11u", true, v16);
+DOMAIN_FIELD(__u32, idle_lb_failed,
+	     "load_balance() move task failed on cpu idle", "%11u", true, v16);
+DOMAIN_FIELD(__u32, idle_lb_imbalance,
+	     "imbalance sum on cpu idle", "%11u", false, v16);
+DOMAIN_FIELD(__u32, idle_lb_gained,
+	     "pull_task() count on cpu idle", "%11u", false, v16);
+DOMAIN_FIELD(__u32, idle_lb_hot_gained,
+	     "pull_task() when target task was cache-hot on cpu idle", "%11u", false, v16);
+DOMAIN_FIELD(__u32, idle_lb_nobusyq,
+	     "load_balance() failed to find busier queue on cpu idle", "%11u", true, v16);
+DOMAIN_FIELD(__u32, idle_lb_nobusyg,
+	     "load_balance() failed to find busier group on cpu idle", "%11u", true, v16);
+#ifdef DERIVED_CNT_FIELD
+DERIVED_CNT_FIELD(idle_lb_success_count, "load_balance() success count on cpu idle", "%11u",
+		  idle_lb_count, idle_lb_balanced, idle_lb_failed, v16);
+#endif
+#ifdef DERIVED_AVG_FIELD
+DERIVED_AVG_FIELD(idle_lb_avg_pulled,
+		  "avg task pulled per successful lb attempt (cpu idle)", "%11.2Lf",
+		  idle_lb_count, idle_lb_balanced, idle_lb_failed, idle_lb_gained, v16);
+#endif
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category newidle> ");
+#endif
+DOMAIN_FIELD(__u32, newidle_lb_count,
+	     "load_balance() count on cpu newly idle", "%11u", true, v16);
+DOMAIN_FIELD(__u32, newidle_lb_balanced,
+	     "load_balance() found balanced on cpu newly idle", "%11u", true, v16);
+DOMAIN_FIELD(__u32, newidle_lb_failed,
+	     "load_balance() move task failed on cpu newly idle", "%11u", true, v16);
+DOMAIN_FIELD(__u32, newidle_lb_imbalance,
+	     "imbalance sum on cpu newly idle", "%11u", false, v16);
+DOMAIN_FIELD(__u32, newidle_lb_gained,
+	     "pull_task() count on cpu newly idle", "%11u", false, v16);
+DOMAIN_FIELD(__u32, newidle_lb_hot_gained,
+	     "pull_task() when target task was cache-hot on cpu newly idle", "%11u", false, v16);
+DOMAIN_FIELD(__u32, newidle_lb_nobusyq,
+	     "load_balance() failed to find busier queue on cpu newly idle", "%11u", true, v16);
+DOMAIN_FIELD(__u32, newidle_lb_nobusyg,
+	     "load_balance() failed to find busier group on cpu newly idle", "%11u", true, v16);
+#ifdef DERIVED_CNT_FIELD
+DERIVED_CNT_FIELD(newidle_lb_success_count,
+		  "load_balance() success count on cpu newly idle", "%11u",
+		  newidle_lb_count, newidle_lb_balanced, newidle_lb_failed, v16);
+#endif
+#ifdef DERIVED_AVG_FIELD
+DERIVED_AVG_FIELD(newidle_lb_avg_count,
+		  "avg task pulled per successful lb attempt (cpu newly idle)", "%11.2Lf",
+		  newidle_lb_count, newidle_lb_balanced, newidle_lb_failed, newidle_lb_gained, v16);
+#endif
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category active_load_balance()> ");
+#endif
+DOMAIN_FIELD(__u32, alb_count,
+	     "active_load_balance() count", "%11u", false, v16);
+DOMAIN_FIELD(__u32, alb_failed,
+	     "active_load_balance() move task failed", "%11u", false, v16);
+DOMAIN_FIELD(__u32, alb_pushed,
+	     "active_load_balance() successfully moved a task", "%11u", false, v16);
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category sched_balance_exec()> ");
+#endif
+DOMAIN_FIELD(__u32, sbe_count,
+	     "sbe_count is not used", "%11u", false, v16);
+DOMAIN_FIELD(__u32, sbe_balanced,
+	     "sbe_balanced is not used", "%11u", false, v16);
+DOMAIN_FIELD(__u32, sbe_pushed,
+	     "sbe_pushed is not used", "%11u", false, v16);
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category sched_balance_fork()> ");
+#endif
+DOMAIN_FIELD(__u32, sbf_count,
+	     "sbf_count is not used", "%11u", false, v16);
+DOMAIN_FIELD(__u32, sbf_balanced,
+	     "sbf_balanced is not used", "%11u", false, v16);
+DOMAIN_FIELD(__u32, sbf_pushed,
+	     "sbf_pushed is not used", "%11u", false, v16);
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Wakeup Info> ");
+#endif
+DOMAIN_FIELD(__u32, ttwu_wake_remote,
+	     "try_to_wake_up() awoke a task that last ran on a diff cpu", "%11u", false, v16);
+DOMAIN_FIELD(__u32, ttwu_move_affine,
+	     "try_to_wake_up() moved task because cache-cold on own cpu", "%11u", false, v16);
+DOMAIN_FIELD(__u32, ttwu_move_balance,
+	     "try_to_wake_up() started passive balancing", "%11u", false, v16);
+#endif /* DOMAIN_FIELD */
diff --git a/tools/lib/perf/include/perf/schedstat-v17.h b/tools/lib/perf/include/perf/schedstat-v17.h
new file mode 100644
index 000000000000..865dc7c1039c
--- /dev/null
+++ b/tools/lib/perf/include/perf/schedstat-v17.h
@@ -0,0 +1,164 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifdef CPU_FIELD
+CPU_FIELD(__u32, yld_count, "sched_yield() count",
+	  "%11u", false, yld_count, v17);
+CPU_FIELD(__u32, array_exp, "Legacy counter can be ignored",
+	  "%11u", false, array_exp, v17);
+CPU_FIELD(__u32, sched_count, "schedule() called",
+	  "%11u", false, sched_count, v17);
+CPU_FIELD(__u32, sched_goidle, "schedule() left the processor idle",
+	  "%11u", true, sched_count, v17);
+CPU_FIELD(__u32, ttwu_count, "try_to_wake_up() was called",
+	  "%11u", false, ttwu_count, v17);
+CPU_FIELD(__u32, ttwu_local, "try_to_wake_up() was called to wake up the local cpu",
+	  "%11u", true, ttwu_count, v17);
+CPU_FIELD(__u64, rq_cpu_time, "total runtime by tasks on this processor (in jiffies)",
+	  "%11llu", false, rq_cpu_time, v17);
+CPU_FIELD(__u64, run_delay, "total waittime by tasks on this processor (in jiffies)",
+	  "%11llu", true, rq_cpu_time, v17);
+CPU_FIELD(__u64, pcount, "total timeslices run on this cpu",
+	  "%11llu", false, pcount, v17);
+#endif /* CPU_FIELD */
+
+#ifdef DOMAIN_FIELD
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category busy> ");
+#endif
+DOMAIN_FIELD(__u32, busy_lb_count,
+	     "load_balance() count on cpu busy", "%11u", true, v17);
+DOMAIN_FIELD(__u32, busy_lb_balanced,
+	     "load_balance() found balanced on cpu busy", "%11u", true, v17);
+DOMAIN_FIELD(__u32, busy_lb_failed,
+	     "load_balance() move task failed on cpu busy", "%11u", true, v17);
+DOMAIN_FIELD(__u32, busy_lb_imbalance_load,
+	     "imbalance in load on cpu busy", "%11u", false, v17);
+DOMAIN_FIELD(__u32, busy_lb_imbalance_util,
+	     "imbalance in utilization on cpu busy", "%11u", false, v17);
+DOMAIN_FIELD(__u32, busy_lb_imbalance_task,
+	     "imbalance in number of tasks on cpu busy", "%11u", false, v17);
+DOMAIN_FIELD(__u32, busy_lb_imbalance_misfit,
+	     "imbalance in misfit tasks on cpu busy", "%11u", false, v17);
+DOMAIN_FIELD(__u32, busy_lb_gained,
+	     "pull_task() count on cpu busy", "%11u", false, v17);
+DOMAIN_FIELD(__u32, busy_lb_hot_gained,
+	     "pull_task() when target task was cache-hot on cpu busy", "%11u", false, v17);
+DOMAIN_FIELD(__u32, busy_lb_nobusyq,
+	     "load_balance() failed to find busier queue on cpu busy", "%11u", true, v17);
+DOMAIN_FIELD(__u32, busy_lb_nobusyg,
+	     "load_balance() failed to find busier group on cpu busy", "%11u", true, v17);
+#ifdef DERIVED_CNT_FIELD
+DERIVED_CNT_FIELD(busy_lb_success_count, "load_balance() success count on cpu busy", "%11u",
+		  busy_lb_count, busy_lb_balanced, busy_lb_failed, v17);
+#endif
+#ifdef DERIVED_AVG_FIELD
+DERIVED_AVG_FIELD(busy_lb_avg_pulled,
+		  "avg task pulled per successful lb attempt (cpu busy)", "%11.2Lf",
+		  busy_lb_count, busy_lb_balanced, busy_lb_failed, busy_lb_gained, v17);
+#endif
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category idle> ");
+#endif
+DOMAIN_FIELD(__u32, idle_lb_count,
+	     "load_balance() count on cpu idle", "%11u", true, v17);
+DOMAIN_FIELD(__u32, idle_lb_balanced,
+	     "load_balance() found balanced on cpu idle", "%11u", true, v17);
+DOMAIN_FIELD(__u32, idle_lb_failed,
+	     "load_balance() move task failed on cpu idle", "%11u", true, v17);
+DOMAIN_FIELD(__u32, idle_lb_imbalance_load,
+	     "imbalance in load on cpu idle", "%11u", false, v17);
+DOMAIN_FIELD(__u32, idle_lb_imbalance_util,
+	     "imbalance in utilization on cpu idle", "%11u", false, v17);
+DOMAIN_FIELD(__u32, idle_lb_imbalance_task,
+	     "imbalance in number of tasks on cpu idle", "%11u", false, v17);
+DOMAIN_FIELD(__u32, idle_lb_imbalance_misfit,
+	     "imbalance in misfit tasks on cpu idle", "%11u", false, v17);
+DOMAIN_FIELD(__u32, idle_lb_gained,
+	     "pull_task() count on cpu idle", "%11u", false, v17);
+DOMAIN_FIELD(__u32, idle_lb_hot_gained,
+	     "pull_task() when target task was cache-hot on cpu idle", "%11u", false, v17);
+DOMAIN_FIELD(__u32, idle_lb_nobusyq,
+	     "load_balance() failed to find busier queue on cpu idle", "%11u", true, v17);
+DOMAIN_FIELD(__u32, idle_lb_nobusyg,
+	     "load_balance() failed to find busier group on cpu idle", "%11u", true, v17);
+#ifdef DERIVED_CNT_FIELD
+DERIVED_CNT_FIELD(idle_lb_success_count, "load_balance() success count on cpu idle", "%11u",
+		  idle_lb_count, idle_lb_balanced, idle_lb_failed, v17);
+#endif
+#ifdef DERIVED_AVG_FIELD
+DERIVED_AVG_FIELD(idle_lb_avg_pulled,
+		  "avg task pulled per successful lb attempt (cpu idle)", "%11.2Lf",
+		  idle_lb_count, idle_lb_balanced, idle_lb_failed, idle_lb_gained, v17);
+#endif
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category newidle> ");
+#endif
+DOMAIN_FIELD(__u32, newidle_lb_count,
+	     "load_balance() count on cpu newly idle", "%11u", true, v17);
+DOMAIN_FIELD(__u32, newidle_lb_balanced,
+	     "load_balance() found balanced on cpu newly idle", "%11u", true, v17);
+DOMAIN_FIELD(__u32, newidle_lb_failed,
+	     "load_balance() move task failed on cpu newly idle", "%11u", true, v17);
+DOMAIN_FIELD(__u32, newidle_lb_imbalance_load,
+	     "imbalance in load on cpu newly idle", "%11u", false, v17);
+DOMAIN_FIELD(__u32, newidle_lb_imbalance_util,
+	     "imbalance in utilization on cpu newly idle", "%11u", false, v17);
+DOMAIN_FIELD(__u32, newidle_lb_imbalance_task,
+	     "imbalance in number of tasks on cpu newly idle", "%11u", false, v17);
+DOMAIN_FIELD(__u32, newidle_lb_imbalance_misfit,
+	     "imbalance in misfit tasks on cpu newly idle", "%11u", false, v17);
+DOMAIN_FIELD(__u32, newidle_lb_gained,
+	     "pull_task() count on cpu newly idle", "%11u", false, v17);
+DOMAIN_FIELD(__u32, newidle_lb_hot_gained,
+	     "pull_task() when target task was cache-hot on cpu newly idle", "%11u", false, v17);
+DOMAIN_FIELD(__u32, newidle_lb_nobusyq,
+	     "load_balance() failed to find busier queue on cpu newly idle", "%11u", true, v17);
+DOMAIN_FIELD(__u32, newidle_lb_nobusyg,
+	     "load_balance() failed to find busier group on cpu newly idle", "%11u", true, v17);
+#ifdef DERIVED_CNT_FIELD
+DERIVED_CNT_FIELD(newidle_lb_success_count,
+		  "load_balance() success count on cpu newly idle", "%11u",
+		  newidle_lb_count, newidle_lb_balanced, newidle_lb_failed, v17);
+#endif
+#ifdef DERIVED_AVG_FIELD
+DERIVED_AVG_FIELD(newidle_lb_avg_pulled,
+		  "avg task pulled per successful lb attempt (cpu newly idle)", "%11.2Lf",
+		  newidle_lb_count, newidle_lb_balanced, newidle_lb_failed, newidle_lb_gained, v17);
+#endif
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category active_load_balance()> ");
+#endif
+DOMAIN_FIELD(__u32, alb_count,
+	     "active_load_balance() count", "%11u", false, v17);
+DOMAIN_FIELD(__u32, alb_failed,
+	     "active_load_balance() move task failed", "%11u", false, v17);
+DOMAIN_FIELD(__u32, alb_pushed,
+	     "active_load_balance() successfully moved a task", "%11u", false, v17);
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category sched_balance_exec()> ");
+#endif
+DOMAIN_FIELD(__u32, sbe_count,
+	     "sbe_count is not used", "%11u", false, v17);
+DOMAIN_FIELD(__u32, sbe_balanced,
+	     "sbe_balanced is not used", "%11u", false, v17);
+DOMAIN_FIELD(__u32, sbe_pushed,
+	     "sbe_pushed is not used", "%11u", false, v17);
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category sched_balance_fork()> ");
+#endif
+DOMAIN_FIELD(__u32, sbf_count,
+	     "sbf_count is not used", "%11u", false, v17);
+DOMAIN_FIELD(__u32, sbf_balanced,
+	     "sbf_balanced is not used", "%11u", false, v17);
+DOMAIN_FIELD(__u32, sbf_pushed,
+	     "sbf_pushed is not used", "%11u", false, v17);
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Wakeup Info> ");
+#endif
+DOMAIN_FIELD(__u32, ttwu_wake_remote,
+	     "try_to_wake_up() awoke a task that last ran on a diff cpu", "%11u", false, v17);
+DOMAIN_FIELD(__u32, ttwu_move_affine,
+	     "try_to_wake_up() moved task because cache-cold on own cpu", "%11u", false, v17);
+DOMAIN_FIELD(__u32, ttwu_move_balance,
+	     "try_to_wake_up() started passive balancing", "%11u", false, v17);
+#endif /* DOMAIN_FIELD */
diff --git a/tools/lib/subcmd/help.c b/tools/lib/subcmd/help.c
index ddaeb4eb3e24..db94aa685b73 100644
--- a/tools/lib/subcmd/help.c
+++ b/tools/lib/subcmd/help.c
@@ -97,11 +97,13 @@ void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes)
 			ei++;
 		}
 	}
-	if (ci != cj) {
-		while (ci < cmds->cnt) {
-			cmds->names[cj++] = cmds->names[ci];
-			cmds->names[ci++] = NULL;
+	while (ci < cmds->cnt) {
+		if (ci != cj) {
+			cmds->names[cj] = cmds->names[ci];
+			cmds->names[ci] = NULL;
 		}
+		ci++;
+		cj++;
 	}
 	for (ci = cj; ci < cmds->cnt; ci++)
 		assert(cmds->names[ci] == NULL);