Merge tag 'perf-tools-for-v7.3-2026-08-21' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

Pull perf tools updates from Namhyung Kim:
 "perf c2c:

   - Add 'function view' in perf c2c report TUI (switched by pressing
     'TAB' in the cacheline view) to organize samples around functions
     rather than cachelines in 3-level hierarchy:

	Level 1: Read-side function (sorted by estimated Cycles %)
	Level 2:   Contending writer functions (sorted by Store count)
	Level 3:     Shared cacheline addresses

     Users can navigate the entries and fold/unfold using 'e' key. An
     example output would look like below:

	Shared Data Functions Table     (19 entries, sorted on Cycles %)
	   Cycles    Store
	        %    count  Function / Contending function / Cacheline
	----------------------------------------------------------------------
	+  35.67%      876  + [k] cpupri_set
	+  24.31%      424  + [k] pull_rt_task
	-  16.53%      555  - [k] dequeue_pushable_task
	               145    - [k] pull_rt_task
	               145        0xff2d0082809da080
	               139    - [k] enqueue_pushable_task
	                70        0xff2d00a2071f9640
	                69        0xff2d0082809da000

  python module support:

   - Extend "perf" python module so that it can be fully functional. The
     goal is to run scripts directly, not by 'perf script' command. This
     would give better performance as well as more control to build
     standalone programs with UI.

   - Add LiveSession helper (perf_live.py) to enable live event
     collection directly from Python using perf.evlist and
     perf.parse_events.

  perf stat:

   - Add --hide-zero-events option to suppress zero-count events
   - Reject conflicting --field-separator and --json-output options
   - Fix duplicate event output with --for-each-cgroup

  perf sched latency:

   - Add -H/--histogram and --hist-mode (log|linear) options to show
     scheduler wait latency histograms
   - Add --time option to filter analysis by time span in 'perf sched
     latency'

  ARM CoreSight:

   - Synthesize callchains for instruction samples from CoreSight trace
     using thread stack ('--itrace=g...')
   - Support call indentation ('perf script -F +callindent') to display
     call depth hierarchy on branch samples
   - Decode ETE (Embedded Trace Extension) exception packets

  Build system:

   - Add 'make install-build-deps' target to install required packages
   - Parallelize JSON and metric pre-computation in jevents.py for
     faster builds

  Vendor event/metric updates:

   - Add Intel Nova Lake events and update tables for existing models
   - Update AMD Zen 5 and Zen 6 core events
   - Update Arm64 Tegra410 metrics and PowerPC hcalls

  Internal changes and fixes:

   - Harden trace-event and synthetic event parsing against corrupted
     data
   - Fix unwinding of multi-threaded processes in libdw unwinder
   - Fix memory leaks in various commands and python bindings
   - Speed up 'perf test' shell tests"

* tag 'perf-tools-for-v7.3-2026-08-21' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (232 commits)
  perf vendor events arm64: Fix Tegra410 Olympus event 0x0197
  perf vendor events arm64: fix swapped MetricGroup for Tegra410 L1 prefetcher metrics
  perf evlist: Warn when 'sleep' workload is used without system-wide (-a) option
  perf c2c: document function view in perf-c2c man page
  perf c2c: add function view browser UI and cacheline detail
  perf c2c: build and finalize the function view hierarchy
  perf c2c: add function view hierarchy entry creation
  perf c2c: add function view stats merge and memory management
  perf c2c: add HPP list parsing for function view columns
  perf c2c: add column rendering for function view
  perf c2c: add function view model skeleton
  perf c2c: extract shared data structures into util/c2c.h
  perf test sample-parsing: Validate PERF_FORMAT_GROUP values without LOST
  perf dso: Replace assert with runtime check in dso__read_symbol()
  perf dso: Guard against cache underflow on short reads in dso_cache__memcpy()
  perf dso: Use stored fd error instead of stale errno in file_read() and file_size()
  perf dso: Guard close() against invalid fd in dso__decompress_kmodule_path()
  perf dso: Guard against errno==0 when dso__get_filename() returns NULL
  perf build: install-build-deps: add RHEL family devel package mapping
  perf build: Remove leftover feature tests for removed cxx and clang support
  ...

1 files changed, 32 insertions, 27 deletions

diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 163fc2b6a7ea..d9ecc6628217 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -2,28 +2,31 @@
 #ifndef __PERF_EVSEL_H
 #define __PERF_EVSEL_H 1
 
-#include <linux/list.h>
 #include <stdbool.h>
-#include <sys/types.h>
+
+#include <linux/list.h>
 #include <linux/perf_event.h>
+#include <linux/refcount.h>
 #include <linux/types.h>
+#include <sys/types.h>
+
 #include <internal/evsel.h>
 #include <perf/evsel.h>
+
 #include "symbol_conf.h"
-#include "pmus.h"
-#include "pmu.h"
 
+struct bperf_follower_bpf;
+struct bperf_leader_bpf;
+struct bpf_counter_ops;
 struct bpf_object;
 struct cgroup;
+struct hashmap;
 struct perf_counts;
+struct perf_pmu;
 struct perf_stat_config;
 struct perf_stat_evsel;
-union perf_event;
-struct bpf_counter_ops;
 struct target;
-struct hashmap;
-struct bperf_leader_bpf;
-struct bperf_follower_bpf;
+union perf_event;
 
 typedef int (evsel__sb_cb_t)(union perf_event *event, void *data);
 
@@ -45,6 +48,7 @@ typedef int (evsel__sb_cb_t)(union perf_event *event, void *data);
 struct evsel {
 	struct perf_evsel	core;
 	struct evlist		*evlist;
+	refcount_t		refcnt;
 	off_t			id_offset;
 	int			id_pos;
 	int			is_pos;
@@ -70,6 +74,10 @@ struct evsel {
 		const char		*unit;
 		struct cgroup		*cgrp;
 		const char		*metric_id;
+
+		/* The PMU the event is from. Used for missing_features, PMU name, etc. */
+		struct perf_pmu		*pmu;
+
 		/*
 		 * This point to the first evsel with the same name, intended to store the
 		 * aggregated counts in aggregation mode.
@@ -90,8 +98,8 @@ struct evsel {
 		bool			skippable;
 		bool			retire_lat;
 		bool			dont_regroup;
-		int			bpf_fd;
-		struct bpf_object	*bpf_obj;
+		bool			default_metricgroup; /* A member of the Default metricgroup */
+		bool			default_show_events; /* If a default group member, show the event */
 		struct list_head	config_terms;
 		u64			alternate_hw_config;
 	};
@@ -121,8 +129,6 @@ struct evsel {
 	bool			cmdline_group_boundary;
 	bool			reset_group;
 	bool			needs_auxtrace_mmap;
-	bool			default_metricgroup; /* A member of the Default metricgroup */
-	bool			default_show_events; /* If a default group member, show the event */
 	bool			needs_uniquify;
 	bool			fallenback_eacces;
 	bool			fallenback_eopnotsupp;
@@ -178,9 +184,6 @@ struct evsel {
 	unsigned long		open_flags;
 	int			precise_ip_original;
 
-	/* The PMU the event is from. Used for missing_features, PMU name, etc. */
-	struct perf_pmu		*pmu;
-
 	/* For tool events */
 	/* Beginning time subtracted when the counter is read. */
 	union {
@@ -271,7 +274,7 @@ static inline struct evsel *evsel__new(struct perf_event_attr *attr)
 	return evsel__new_idx(attr, 0);
 }
 
-struct evsel *evsel__clone(struct evsel *dest, struct evsel *orig);
+struct evsel *evsel__clone(struct evsel *orig);
 
 int copy_config_terms(struct list_head *dst, struct list_head *src);
 void free_config_terms(struct list_head *config_terms);
@@ -286,14 +289,13 @@ static inline struct evsel *evsel__newtp(const char *sys, const char *name)
 	return evsel__newtp_idx(sys, name, 0, true);
 }
 
+struct evsel *evsel__get(struct evsel *evsel);
+void evsel__put(struct evsel *evsel);
+
 #ifdef HAVE_LIBTRACEEVENT
 struct tep_event *evsel__tp_format(struct evsel *evsel);
 #endif
 
-void evsel__init(struct evsel *evsel, struct perf_event_attr *attr, int idx);
-void evsel__exit(struct evsel *evsel);
-void evsel__delete(struct evsel *evsel);
-
 void evsel__set_priv_destructor(void (*destructor)(void *priv));
 
 struct callchain_param;
@@ -361,10 +363,6 @@ void arch_evsel__apply_ratio_to_prev(struct evsel *evsel, struct perf_event_attr
 int evsel__set_filter(struct evsel *evsel, const char *filter);
 int evsel__append_tp_filter(struct evsel *evsel, const char *filter);
 int evsel__append_addr_filter(struct evsel *evsel, const char *filter);
-static inline bool evsel__is_non_perf_event_open_pmu(const struct evsel *evsel)
-{
-	return evsel->pmu && evsel->pmu->type > PERF_PMU_TYPE_PE_END;
-}
 
 int evsel__enable_cpu(struct evsel *evsel, int cpu_map_idx);
 int evsel__enable(struct evsel *evsel);
@@ -400,6 +398,12 @@ static inline char *perf_sample__strval(struct perf_sample *sample, const char *
 
 struct tep_format_field;
 
+void *format_field__get_raw_data(struct tep_format_field *field,
+				 struct perf_sample *sample,
+				 bool needs_swap, u16 *len_out);
+unsigned long *format_field__get_cpumask(struct tep_format_field *field,
+					 struct perf_sample *sample,
+					 bool needs_swap, u16 *len_out);
 u64 format_field__intval(struct tep_format_field *field, struct perf_sample *sample, bool needs_swap);
 
 #ifdef HAVE_LIBTRACEEVENT
@@ -503,6 +507,7 @@ static inline bool evsel__is_group_event(struct evsel *evsel)
 	return evsel__is_group_leader(evsel) && evsel->core.nr_members > 1;
 }
 
+bool evsel__is_non_perf_event_open_pmu(const struct evsel *evsel);
 bool evsel__is_function_event(struct evsel *evsel);
 
 static inline bool evsel__is_bpf_output(struct evsel *evsel)
@@ -534,7 +539,7 @@ for ((_evsel) = list_entry((_leader)->core.node.next, struct evsel, core.node);
 	(_evsel) = list_entry((_evsel)->core.node.next, struct evsel, core.node))
 
 #define for_each_group_member(_evsel, _leader)				\
-	for_each_group_member_head(_evsel, _leader, &(_leader)->evlist->core.entries)
+	for_each_group_member_head(_evsel, _leader, &evlist__core((_leader)->evlist)->entries)
 
 /* Iterates group WITH the leader. */
 #define for_each_group_evsel_head(_evsel, _leader, _head)				\
@@ -544,7 +549,7 @@ for ((_evsel) = _leader;								\
 	(_evsel) = list_entry((_evsel)->core.node.next, struct evsel, core.node))
 
 #define for_each_group_evsel(_evsel, _leader)				\
-	for_each_group_evsel_head(_evsel, _leader, &(_leader)->evlist->core.entries)
+	for_each_group_evsel_head(_evsel, _leader, &evlist__core((_leader)->evlist)->entries)
 
 static inline bool evsel__has_branch_callstack(const struct evsel *evsel)
 {