Merge tag 'perf-tools-for-v6.14-2025-01-21' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

Pull perf-tools updates from Namhyung Kim:
 "There are a lot of changes in the perf tools in this cycle.

  build:

   - Use generic syscall table to generate syscall numbers on supported
     archs

   - This also enables to get rid of libaudit which was used for syscall
     numbers

   - Remove python2 support as it's deprecated for years

   - Fix issues on static build with libzstd

  perf record:

   - Intel-PT supports "aux-action" config term to pause or resume
     tracing in the aux-buffer. Users can start the intel_pt event as
     "started-paused" and configure other events to control the Intel-PT
     tracing:

         # perf record --kcore -e intel_pt/aux-action=start-paused/   \
             -e syscalls:sys_enter_newuname/aux-action=resume/        \
             -e syscalls:sys_exit_newuname/aux-action=pause/ -- uname

     This requires kernel support (which was added in v6.13)

  perf lock:

   - 'perf lock contention' command has an ability to symbolize locks in
     dynamically allocated objects using slab cache name when it runs
     with BPF. Those dynamic locks would have "&" prefix in the name to
     distinguish them from ordinary (static) locks

        # perf lock con -abl -E 5 sleep 1
           contended   total wait     max wait     avg wait            address   symbol

                   2      1.95 us      1.77 us       975 ns   ffff9d5e852d3498   &task_struct (mutex)
                   1      1.18 us      1.18 us      1.18 us   ffff9d5e852d3538   &task_struct (mutex)
                   4      1.12 us       354 ns       279 ns   ffff9d5e841ca800   &kmalloc-cg-512 (mutex)
                   2       859 ns       617 ns       429 ns   ffffffffa41c3620   delayed_uprobe_lock (mutex)
                   3       691 ns       388 ns       230 ns   ffffffffa41c0940   pack_mutex (mutex)

     This also requires kernel/BPF support (which was added in v6.13)

  perf ftrace:

   - 'perf ftrace latency' command gets a couple of options to support
     linear buckets instead of exponential. Also it's possible to
     specify max and min latency for the linear buckets:

        # perf ftrace latency -abn -T switch_mm_irqs_off --bucket-range=100   \
            --min-latency=200 --max-latency=800 -- sleep 1
        #   DURATION     |      COUNT | GRAPH                                  |
             0 -  200 ns |        186 | ###                                    |
           200 -  300 ns |        256 | #####                                  |
           300 -  400 ns |        364 | #######                                |
           400 -  500 ns |        223 | ####                                   |
           500 -  600 ns |        111 | ##                                     |
           600 -  700 ns |         41 |                                        |
           700 -  800 ns |        141 | ##                                     |
           800 -  ... ns |        169 | ###                                    |

        # statistics  (in nsec)
          total time:              2162212
            avg time:                  967
            max time:                16817
            min time:                  132
               count:                 2236

   - As you can see in the above example, it nows shows the statistics
     at the end so that users can see the avg/max/min latencies easily

   - 'perf ftrace profile' command has --graph-opts option like 'perf
     ftrace trace' so that it can control the tracing behaviors in the
     same way. For example, it can limit the function call depth or
     threshold

  perf script:

   - Improve physical memory resolution in 'mem-phys-addr' script by
     parsing /proc/iomem file

        # perf script mem-phys-addr -- find /
        ...
        Event: mem_inst_retired.all_loads:P
        Memory type                                    count  percentage
        ----------------------------------------  ----------  ----------
        100000000-85f7fffff : System RAM                8929        69.7
          547600000-54785d23f : Kernel data             1240         9.7
          546a00000-5474bdfff : Kernel rodata            490         3.8
          5480ce000-5485fffff : Kernel bss               121         0.9
        0-fff : Reserved                                3860        30.1
        100000-89c01fff : System RAM                      18         0.1
        8a22c000-8df6efff : System RAM                     5         0.0

  Others:

   - 'perf test' gets --runs-per-test option to run the test cases
     repeatedly. This would be helpful to see if it's flaky

   - Add 'parse_events' method to Python perf extension module, so that
     users can use the same event parsing logic in the python code. One
     more step towards implementing perf tools in Python. :)

   - Support opening tracepoint events without libtraceevent. This will
     be helpful if it won't use the tracing data like in 'perf stat'

   - Update ARM Neoverse N2/V2 JSON events and metrics"

* tag 'perf-tools-for-v6.14-2025-01-21' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (176 commits)
  perf test: Update event_groups test to use instructions
  perf bench: Fix undefined behavior in cmpworker()
  perf annotate: Prefer passing evsel to evsel->core.idx
  perf lock: Rename fields in lock_type_table
  perf lock: Add percpu-rwsem for type filter
  perf lock: Fix parse_lock_type which only retrieve one lock flag
  perf lock: Fix return code for functions in __cmd_contention
  perf hist: Fix width calculation in hpp__fmt()
  perf hist: Fix bogus profiles when filters are enabled
  perf hist: Deduplicate cmp/sort/collapse code
  perf test: Improve verbose documentation
  perf test: Add a runs-per-test flag
  perf test: Fix parallel/sequential option documentation
  perf test: Send list output to stdout rather than stderr
  perf test: Rename functions and variables for better clarity
  perf tools: Expose quiet/verbose variables in Makefile.perf
  perf config: Add a function to set one variable in .perfconfig
  perf test perftool_testsuite: Return correct value for skipping
  perf test perftool_testsuite: Add missing description
  perf test record+probe_libc_inet_pton: Make test resilient
  ...

7 files changed, 48 insertions, 103 deletions

diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index 337fde770e45..edec23406dbc 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -296,7 +296,7 @@ int filename__read_int(const char *filename, int *value)
 	int fd = open(filename, O_RDONLY), err = -1;
 
 	if (fd < 0)
-		return -1;
+		return -errno;
 
 	if (read(fd, line, sizeof(line)) > 0) {
 		*value = atoi(line);
@@ -314,7 +314,7 @@ static int filename__read_ull_base(const char *filename,
 	int fd = open(filename, O_RDONLY), err = -1;
 
 	if (fd < 0)
-		return -1;
+		return -errno;
 
 	if (read(fd, line, sizeof(line)) > 0) {
 		*value = strtoull(line, NULL, base);
@@ -372,7 +372,7 @@ int filename__write_int(const char *filename, int value)
 	char buf[64];
 
 	if (fd < 0)
-		return err;
+		return -errno;
 
 	sprintf(buf, "%d", value);
 	if (write(fd, buf, sizeof(buf)) == sizeof(buf))
diff --git a/tools/lib/perf/Documentation/libperf.txt b/tools/lib/perf/Documentation/libperf.txt
index fcfb9499ef9c..59aabdd3cabf 100644
--- a/tools/lib/perf/Documentation/libperf.txt
+++ b/tools/lib/perf/Documentation/libperf.txt
@@ -39,7 +39,6 @@ SYNOPSIS
 
   struct perf_cpu_map *perf_cpu_map__new_any_cpu(void);
   struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list);
-  struct perf_cpu_map *perf_cpu_map__read(FILE *file);
   struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map);
   struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
                                            struct perf_cpu_map *other);
diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c
index cae799ad44e1..fcc47214062a 100644
--- a/tools/lib/perf/cpumap.c
+++ b/tools/lib/perf/cpumap.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
+#include <errno.h>
 #include <perf/cpumap.h>
 #include <stdlib.h>
 #include <linux/refcount.h>
@@ -10,6 +11,9 @@
 #include <ctype.h>
 #include <limits.h>
 #include "internal.h"
+#include <api/fs/fs.h>
+
+#define MAX_NR_CPUS 4096
 
 void perf_cpu_map__set_nr(struct perf_cpu_map *map, int nr_cpus)
 {
@@ -100,12 +104,12 @@ static struct perf_cpu_map *cpu_map__new_sysconf(void)
 static struct perf_cpu_map *cpu_map__new_sysfs_online(void)
 {
 	struct perf_cpu_map *cpus = NULL;
-	FILE *onlnf;
+	char *buf = NULL;
+	size_t buf_len;
 
-	onlnf = fopen("/sys/devices/system/cpu/online", "r");
-	if (onlnf) {
-		cpus = perf_cpu_map__read(onlnf);
-		fclose(onlnf);
+	if (sysfs__read_str("devices/system/cpu/online", &buf, &buf_len) >= 0) {
+		cpus = perf_cpu_map__new(buf);
+		free(buf);
 	}
 	return cpus;
 }
@@ -158,62 +162,6 @@ static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, const struct perf_cpu
 	return cpus;
 }
 
-struct perf_cpu_map *perf_cpu_map__read(FILE *file)
-{
-	struct perf_cpu_map *cpus = NULL;
-	int nr_cpus = 0;
-	struct perf_cpu *tmp_cpus = NULL, *tmp;
-	int max_entries = 0;
-	int n, cpu, prev;
-	char sep;
-
-	sep = 0;
-	prev = -1;
-	for (;;) {
-		n = fscanf(file, "%u%c", &cpu, &sep);
-		if (n <= 0)
-			break;
-		if (prev >= 0) {
-			int new_max = nr_cpus + cpu - prev - 1;
-
-			WARN_ONCE(new_max >= MAX_NR_CPUS, "Perf can support %d CPUs. "
-							  "Consider raising MAX_NR_CPUS\n", MAX_NR_CPUS);
-
-			if (new_max >= max_entries) {
-				max_entries = new_max + MAX_NR_CPUS / 2;
-				tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu));
-				if (tmp == NULL)
-					goto out_free_tmp;
-				tmp_cpus = tmp;
-			}
-
-			while (++prev < cpu)
-				tmp_cpus[nr_cpus++].cpu = prev;
-		}
-		if (nr_cpus == max_entries) {
-			max_entries += MAX_NR_CPUS;
-			tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu));
-			if (tmp == NULL)
-				goto out_free_tmp;
-			tmp_cpus = tmp;
-		}
-
-		tmp_cpus[nr_cpus++].cpu = cpu;
-		if (n == 2 && sep == '-')
-			prev = cpu;
-		else
-			prev = -1;
-		if (n == 1 || sep == '\n')
-			break;
-	}
-
-	if (nr_cpus > 0)
-		cpus = cpu_map__trim_new(nr_cpus, tmp_cpus);
-out_free_tmp:
-	free(tmp_cpus);
-	return cpus;
-}
-
 struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 {
 	struct perf_cpu_map *cpus = NULL;
@@ -238,7 +186,7 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 		p = NULL;
 		start_cpu = strtoul(cpu_list, &p, 0);
 		if (start_cpu >= INT_MAX
-		    || (*p != '\0' && *p != ',' && *p != '-'))
+		    || (*p != '\0' && *p != ',' && *p != '-' && *p != '\n'))
 			goto invalid;
 
 		if (*p == '-') {
@@ -246,7 +194,7 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 			p = NULL;
 			end_cpu = strtoul(cpu_list, &p, 0);
 
-			if (end_cpu >= INT_MAX || (*p != '\0' && *p != ','))
+			if (end_cpu >= INT_MAX || (*p != '\0' && *p != ',' && *p != '\n'))
 				goto invalid;
 
 			if (end_cpu < start_cpu)
@@ -265,7 +213,7 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 					goto invalid;
 
 			if (nr_cpus == max_entries) {
-				max_entries += MAX_NR_CPUS;
+				max_entries += max(end_cpu - start_cpu + 1, 16UL);
 				tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu));
 				if (tmp == NULL)
 					goto invalid;
@@ -279,14 +227,15 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 		cpu_list = p;
 	}
 
-	if (nr_cpus > 0)
+	if (nr_cpus > 0) {
 		cpus = cpu_map__trim_new(nr_cpus, tmp_cpus);
-	else if (*cpu_list != '\0') {
+	} else if (*cpu_list != '\0') {
 		pr_warning("Unexpected characters at end of cpu list ('%s'), using online CPUs.",
 			   cpu_list);
 		cpus = perf_cpu_map__new_online_cpus();
-	} else
+	} else {
 		cpus = perf_cpu_map__new_any_cpu();
+	}
 invalid:
 	free(tmp_cpus);
 out:
@@ -436,46 +385,49 @@ bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu
 }
 
 /*
- * Merge two cpumaps
+ * Merge two cpumaps.
+ *
+ * If 'other' is subset of '*orig', '*orig' keeps itself with no reference count
+ * change (similar to "realloc").
+ *
+ * If '*orig' is subset of 'other', '*orig' reuses 'other' with its reference
+ * count increased.
  *
- * orig either gets freed and replaced with a new map, or reused
- * with no reference count change (similar to "realloc")
- * other has its reference count increased.
+ * Otherwise, '*orig' gets freed and replaced with a new map.
  */
-
-struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
-					 struct perf_cpu_map *other)
+int perf_cpu_map__merge(struct perf_cpu_map **orig, struct perf_cpu_map *other)
 {
 	struct perf_cpu *tmp_cpus;
 	int tmp_len;
 	int i, j, k;
 	struct perf_cpu_map *merged;
 
-	if (perf_cpu_map__is_subset(orig, other))
-		return orig;
-	if (perf_cpu_map__is_subset(other, orig)) {
-		perf_cpu_map__put(orig);
-		return perf_cpu_map__get(other);
+	if (perf_cpu_map__is_subset(*orig, other))
+		return 0;
+	if (perf_cpu_map__is_subset(other, *orig)) {
+		perf_cpu_map__put(*orig);
+		*orig = perf_cpu_map__get(other);
+		return 0;
 	}
 
-	tmp_len = __perf_cpu_map__nr(orig) + __perf_cpu_map__nr(other);
+	tmp_len = __perf_cpu_map__nr(*orig) + __perf_cpu_map__nr(other);
 	tmp_cpus = malloc(tmp_len * sizeof(struct perf_cpu));
 	if (!tmp_cpus)
-		return NULL;
+		return -ENOMEM;
 
 	/* Standard merge algorithm from wikipedia */
 	i = j = k = 0;
-	while (i < __perf_cpu_map__nr(orig) && j < __perf_cpu_map__nr(other)) {
-		if (__perf_cpu_map__cpu(orig, i).cpu <= __perf_cpu_map__cpu(other, j).cpu) {
-			if (__perf_cpu_map__cpu(orig, i).cpu == __perf_cpu_map__cpu(other, j).cpu)
+	while (i < __perf_cpu_map__nr(*orig) && j < __perf_cpu_map__nr(other)) {
+		if (__perf_cpu_map__cpu(*orig, i).cpu <= __perf_cpu_map__cpu(other, j).cpu) {
+			if (__perf_cpu_map__cpu(*orig, i).cpu == __perf_cpu_map__cpu(other, j).cpu)
 				j++;
-			tmp_cpus[k++] = __perf_cpu_map__cpu(orig, i++);
+			tmp_cpus[k++] = __perf_cpu_map__cpu(*orig, i++);
 		} else
 			tmp_cpus[k++] = __perf_cpu_map__cpu(other, j++);
 	}
 
-	while (i < __perf_cpu_map__nr(orig))
-		tmp_cpus[k++] = __perf_cpu_map__cpu(orig, i++);
+	while (i < __perf_cpu_map__nr(*orig))
+		tmp_cpus[k++] = __perf_cpu_map__cpu(*orig, i++);
 
 	while (j < __perf_cpu_map__nr(other))
 		tmp_cpus[k++] = __perf_cpu_map__cpu(other, j++);
@@ -483,8 +435,9 @@ struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
 
 	merged = cpu_map__trim_new(k, tmp_cpus);
 	free(tmp_cpus);
-	perf_cpu_map__put(orig);
-	return merged;
+	perf_cpu_map__put(*orig);
+	*orig = merged;
+	return 0;
 }
 
 struct perf_cpu_map *perf_cpu_map__intersect(struct perf_cpu_map *orig,
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index 83c43dc13313..b1f4c8176b32 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -89,7 +89,7 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
 		evsel->threads = perf_thread_map__get(evlist->threads);
 	}
 
-	evlist->all_cpus = perf_cpu_map__merge(evlist->all_cpus, evsel->cpus);
+	perf_cpu_map__merge(&evlist->all_cpus, evsel->cpus);
 }
 
 static void perf_evlist__propagate_maps(struct perf_evlist *evlist)
diff --git a/tools/lib/perf/include/internal/cpumap.h b/tools/lib/perf/include/internal/cpumap.h
index 49649eb51ce4..e2be2d17c32b 100644
--- a/tools/lib/perf/include/internal/cpumap.h
+++ b/tools/lib/perf/include/internal/cpumap.h
@@ -21,10 +21,6 @@ DECLARE_RC_STRUCT(perf_cpu_map) {
 	struct perf_cpu	map[];
 };
 
-#ifndef MAX_NR_CPUS
-#define MAX_NR_CPUS	2048
-#endif
-
 struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus);
 int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu);
 bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu_map *b);
diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h
index 90457d17fb2f..188a667babc6 100644
--- a/tools/lib/perf/include/perf/cpumap.h
+++ b/tools/lib/perf/include/perf/cpumap.h
@@ -3,7 +3,6 @@
 #define __LIBPERF_CPUMAP_H
 
 #include <perf/core.h>
-#include <stdio.h>
 #include <stdbool.h>
 
 /** A wrapper around a CPU to avoid confusion with the perf_cpu_map's map's indices. */
@@ -37,10 +36,9 @@ LIBPERF_API struct perf_cpu_map *perf_cpu_map__new_online_cpus(void);
  *                     perf_cpu_map__new_online_cpus is returned.
  */
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list);
-LIBPERF_API struct perf_cpu_map *perf_cpu_map__read(FILE *file);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map);
-LIBPERF_API struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
-						     struct perf_cpu_map *other);
+LIBPERF_API int perf_cpu_map__merge(struct perf_cpu_map **orig,
+				    struct perf_cpu_map *other);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__intersect(struct perf_cpu_map *orig,
 							 struct perf_cpu_map *other);
 LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map);
diff --git a/tools/lib/perf/libperf.map b/tools/lib/perf/libperf.map
index 2aa79b696032..fdd8304fe9d0 100644
--- a/tools/lib/perf/libperf.map
+++ b/tools/lib/perf/libperf.map
@@ -6,7 +6,6 @@ LIBPERF_0.0.1 {
 		perf_cpu_map__get;
 		perf_cpu_map__put;
 		perf_cpu_map__new;
-		perf_cpu_map__read;
 		perf_cpu_map__nr;
 		perf_cpu_map__cpu;
 		perf_cpu_map__has_any_cpu_or_is_empty;