Merge tag 'perf-tools-for-v6.18-1-2025-10-08' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

Pull perf tools updates from Arnaldo Carvalho de Melo:

 - Extended 'perf annotate' with DWARF type information
   (--code-with-type) integration in the TUI, including a 'T'
   hotkey to toggle it

 - Enhanced 'perf bench mem' with new mmap() workloads and control
   over page/chunk sizes

 - Fix 'perf stat' error handling to correctly display unsupported
   events

 - Improved support for Clang cross-compilation

 - Refactored LLVM and Capstone disasm for modularity

 - Introduced the :X modifier to exclude an event from automatic
   regrouping

 - Adjusted KVM sampling defaults to use the "cycles" event to prevent
   failures

 - Added comprehensive support for decoding PowerPC Dispatch Trace Log
   (DTL)

 - Updated Arm SPE tracing logic for better analysis of memory and snoop
   details

 - Synchronized Intel PMU events and metrics with TMA 5.1 across
   multiple processor generations

 - Converted dependencies like libperl and libtracefs to be opt-in

 - Handle more Rust symbols in kallsyms ('N', debugging)

 - Improve the python binding to allow for python based tools to use
   more of the libraries, add a 'ilist' utility to test those new
   bindings

 - Various 'perf test' fixes

 - Kan Liang no longer a perf tools reviewer

* tag 'perf-tools-for-v6.18-1-2025-10-08' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (192 commits)
  perf tools: Fix arm64 libjvmti build by generating unistd_64.h
  perf tests: Don't retest sections in "Object code reading"
  perf docs: Document building with Clang
  perf build: Support build with clang
  perf test coresight: Dismiss clang warning for unroll loop thread
  perf test coresight: Dismiss clang warning for thread loop
  perf test coresight: Dismiss clang warning for memcpy thread
  perf build: Disable thread safety analysis for perl header
  perf build: Correct CROSS_ARCH for clang
  perf python: split Clang options when invoking Popen
  tools build: Align warning options with perf
  perf disasm: Remove unused evsel from 'struct annotate_args'
  perf srcline: Fallback between addr2line implementations
  perf disasm: Make ins__scnprintf() and ins__is_nop() static
  perf dso: Clean up read_symbol() error handling
  perf dso: Support BPF programs in dso__read_symbol()
  perf dso: Move read_symbol() from llvm/capstone to dso
  perf llvm: Reduce LLVM initialization
  perf check: Add libLLVM feature
  perf parse-events: Fix parsing of >30kb event strings
  ...

1 files changed, 23 insertions, 17 deletions

diff --git a/tools/perf/util/bpf-trace-summary.c b/tools/perf/util/bpf-trace-summary.c
index 69fb165da206..8dfe7e678941 100644
--- a/tools/perf/util/bpf-trace-summary.c
+++ b/tools/perf/util/bpf-trace-summary.c
@@ -138,11 +138,14 @@ static bool sc_node_equal(long key1, long key2, void *ctx __maybe_unused)
 	return key1 == key2;
 }
 
-static int print_common_stats(struct syscall_data *data, FILE *fp)
+static int print_common_stats(struct syscall_data *data, int max_summary, FILE *fp)
 {
 	int printed = 0;
 
-	for (int i = 0; i < data->nr_nodes; i++) {
+	if (max_summary == 0 || max_summary > data->nr_nodes)
+		max_summary = data->nr_nodes;
+
+	for (int i = 0; i < max_summary; i++) {
 		struct syscall_node *node = &data->nodes[i];
 		struct syscall_stats *stat = &node->stats;
 		double total = (double)(stat->total_time) / NSEC_PER_MSEC;
@@ -200,7 +203,7 @@ static int update_thread_stats(struct hashmap *hash, struct syscall_key *map_key
 	return 0;
 }
 
-static int print_thread_stat(struct syscall_data *data, FILE *fp)
+static int print_thread_stat(struct syscall_data *data, int max_summary, FILE *fp)
 {
 	int printed = 0;
 
@@ -213,18 +216,18 @@ static int print_thread_stat(struct syscall_data *data, FILE *fp)
 	printed += fprintf(fp, "                                     (msec)    (msec)    (msec)    (msec)        (%%)\n");
 	printed += fprintf(fp, "   --------------- --------  ------ -------- --------- --------- ---------     ------\n");
 
-	printed += print_common_stats(data, fp);
+	printed += print_common_stats(data, max_summary, fp);
 	printed += fprintf(fp, "\n\n");
 
 	return printed;
 }
 
-static int print_thread_stats(struct syscall_data **data, int nr_data, FILE *fp)
+static int print_thread_stats(struct syscall_data **data, int nr_data, int max_summary, FILE *fp)
 {
 	int printed = 0;
 
 	for (int i = 0; i < nr_data; i++)
-		printed += print_thread_stat(data[i], fp);
+		printed += print_thread_stat(data[i], max_summary, fp);
 
 	return printed;
 }
@@ -277,7 +280,7 @@ static int update_total_stats(struct hashmap *hash, struct syscall_key *map_key,
 	return 0;
 }
 
-static int print_total_stats(struct syscall_data **data, int nr_data, FILE *fp)
+static int print_total_stats(struct syscall_data **data, int nr_data, int max_summary, FILE *fp)
 {
 	int printed = 0;
 	int nr_events = 0;
@@ -291,8 +294,11 @@ static int print_total_stats(struct syscall_data **data, int nr_data, FILE *fp)
 	printed += fprintf(fp, "                                     (msec)    (msec)    (msec)    (msec)        (%%)\n");
 	printed += fprintf(fp, "   --------------- --------  ------ -------- --------- --------- ---------     ------\n");
 
-	for (int i = 0; i < nr_data; i++)
-		printed += print_common_stats(data[i], fp);
+	if (max_summary == 0 || max_summary > nr_data)
+		max_summary = nr_data;
+
+	for (int i = 0; i < max_summary; i++)
+		printed += print_common_stats(data[i], max_summary, fp);
 
 	printed += fprintf(fp, "\n\n");
 	return printed;
@@ -333,7 +339,7 @@ static int update_cgroup_stats(struct hashmap *hash, struct syscall_key *map_key
 	return 0;
 }
 
-static int print_cgroup_stat(struct syscall_data *data, FILE *fp)
+static int print_cgroup_stat(struct syscall_data *data, int max_summary, FILE *fp)
 {
 	int printed = 0;
 	struct cgroup *cgrp = __cgroup__find(&cgroups, data->key);
@@ -351,23 +357,23 @@ static int print_cgroup_stat(struct syscall_data *data, FILE *fp)
 	printed += fprintf(fp, "                                     (msec)    (msec)    (msec)    (msec)        (%%)\n");
 	printed += fprintf(fp, "   --------------- --------  ------ -------- --------- --------- ---------     ------\n");
 
-	printed += print_common_stats(data, fp);
+	printed += print_common_stats(data, max_summary, fp);
 	printed += fprintf(fp, "\n\n");
 
 	return printed;
 }
 
-static int print_cgroup_stats(struct syscall_data **data, int nr_data, FILE *fp)
+static int print_cgroup_stats(struct syscall_data **data, int nr_data, int max_summary, FILE *fp)
 {
 	int printed = 0;
 
 	for (int i = 0; i < nr_data; i++)
-		printed += print_cgroup_stat(data[i], fp);
+		printed += print_cgroup_stat(data[i], max_summary, fp);
 
 	return printed;
 }
 
-int trace_print_bpf_summary(FILE *fp)
+int trace_print_bpf_summary(FILE *fp, int max_summary)
 {
 	struct bpf_map *map = skel->maps.syscall_stats_map;
 	struct syscall_key *prev_key, key;
@@ -420,13 +426,13 @@ int trace_print_bpf_summary(FILE *fp)
 
 	switch (skel->rodata->aggr_mode) {
 	case SYSCALL_AGGR_THREAD:
-		printed += print_thread_stats(data, nr_data, fp);
+		printed += print_thread_stats(data, nr_data, max_summary, fp);
 		break;
 	case SYSCALL_AGGR_CPU:
-		printed += print_total_stats(data, nr_data, fp);
+		printed += print_total_stats(data, nr_data, max_summary, fp);
 		break;
 	case SYSCALL_AGGR_CGROUP:
-		printed += print_cgroup_stats(data, nr_data, fp);
+		printed += print_cgroup_stats(data, nr_data, max_summary, fp);
 		break;
 	default:
 		break;