Merge tag 'perf-tools-for-v6.9-2024-03-13' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

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

   - Support new 'cluster' aggregation mode for shared resources
     depending on the hardware configuration:

        $ sudo perf stat -a --per-cluster -e cycles,instructions sleep 1

         Performance counter stats for 'system wide':

        S0-D0-CLS0    2         85,051,822      cycles
        S0-D0-CLS0    2         73,909,908      instructions      #    0.87  insn per cycle
        S0-D0-CLS2    2         93,365,918      cycles
        S0-D0-CLS2    2         83,006,158      instructions      #    0.89  insn per cycle
        S0-D0-CLS4    2        104,157,523      cycles
        S0-D0-CLS4    2         53,234,396      instructions      #    0.51  insn per cycle
        S0-D0-CLS6    2         65,891,079      cycles
        S0-D0-CLS6    2         41,478,273      instructions      #    0.63  insn per cycle

               1.002407989 seconds time elapsed

   - Various fixes and cleanups for event metrics including NaN handling

  perf script:

   - Use libcapstone if available to disassemble the instructions. This
     enables 'perf script -F disasm' and 'perf script --insn-trace=disasm'
     (for Intel-PT):

        $ perf script -F event,ip,disasm
        cycles:P:  ffffffffa988d428             wrmsr
        cycles:P:  ffffffffa9839d25             movq %rax, %r14
        cycles:P:  ffffffffa9cdcaf0             endbr64
        cycles:P:  ffffffffa988d428             wrmsr
        cycles:P:  ffffffffa988d428             wrmsr
        cycles:P:  ffffffffaa401f86             iretq
        cycles:P:  ffffffffa99c4de5             movq 0x30(%rcx), %r8
        cycles:P:  ffffffffa988d428             wrmsr
        cycles:P:  ffffffffaa401f86             iretq
        cycles:P:  ffffffffa9907983             movl 0x68(%rbx), %eax
        cycles:P:  ffffffffa988d428             wrmsr

   - Expose sample ID / stream ID to python scripts

  perf test:

   - Add more perf test cases from Redhat internal test suites. This
     time it adds the base infra and a few perf probe tests. More to
     come. :)

   - Add 'perf test -p' for parallel execution and fix some issues found
     by the parallel test

   - Support symbol test to print symbols in given (active) module:

        $ perf test -F -v Symbols --dso /lib/modules/$(uname -r)/kernel/fs/ext4/ext4.ko
        --- start ---
        Testing /lib/modules/6.5.13-1rodete2-amd64/kernel/fs/ext4/ext4.ko
        Overlapping symbols:
         7a990-7a9a0 l __pfx_ext4_exit_fs
         7a990-7a9a0 g __pfx_cleanup_module
        Overlapping symbols:
         7a9a0-7aa1c l ext4_exit_fs
         7a9a0-7aa1c g cleanup_module
        ...

  JSON metric updates:

   - A new round of Intel metric updates

   - Support Power11 PVR (compatible to Power10)

   - Fix cache latency events on Zen 4 to set SliceId properly

  Internal:

   - Fix reference counting for 'map' data structure, tireless work from
     Ian!

   - More memory optimization for struct thread and annotate histogram.
     Now, 'perf report' (TUI) and 'perf annotate' should be much
     lighter-weight in terms of memory footprint

   - Support cross-arch perf register access. Clean up the build
     configuration so that it can detect arch-register support at
     runtime. This can allow to parse register data in sample which was
     recorded in a different arch

  Others:

   - Sync task state in 'perf sched' to kernel using trace event fields.
     The task states have been changed so tools cannot assume a fixed
     encoding

   - Clean up 'perf mem' to generalize the arch-specific events

   - Add support for local and global variables to data type profiling.
     This would increase the success rate of type resolution with DWARF

   - Add short option -H for --hierarchy in 'perf report' and 'perf top'"

* tag 'perf-tools-for-v6.9-2024-03-13' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (154 commits)
  perf annotate: Add comments in the data structures
  perf annotate: Remove sym_hist.addr[] array
  perf annotate: Calculate instruction overhead using hashmap
  perf annotate: Add a hashmap for symbol histogram
  perf threads: Reduce table size from 256 to 8
  perf threads: Switch from rbtree to hashmap
  perf threads: Move threads to its own files
  perf machine: Move machine's threads into its own abstraction
  perf machine: Move fprintf to for_each loop and a callback
  perf trace: Ignore thread hashing in summary
  perf report: Sort child tasks by tid
  perf vendor events amd: Fix Zen 4 cache latency events
  perf version: Display availability of OpenCSD support
  perf vendor events intel: Add umasks/occ_sel to PCU events.
  perf map: Fix map reference count issues
  libperf evlist: Avoid out-of-bounds access
  perf lock contention: Account contending locks too
  perf metrics: Fix segv for metrics with no events
  perf metrics: Fix metric matching
  perf pmu: Fix a potential memory leak in perf_pmu__lookup()
  ...

1 files changed, 257 insertions, 0 deletions

diff --git a/tools/perf/tests/tests-scripts.c b/tools/perf/tests/tests-scripts.c
new file mode 100644
index 000000000000..e2042b368269
--- /dev/null
+++ b/tools/perf/tests/tests-scripts.c
@@ -0,0 +1,257 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <dirent.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <linux/ctype.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/zalloc.h>
+#include <string.h>
+#include <stdlib.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include <subcmd/exec-cmd.h>
+#include <subcmd/parse-options.h>
+#include <sys/wait.h>
+#include <sys/stat.h>
+#include <api/io.h>
+#include "builtin.h"
+#include "tests-scripts.h"
+#include "color.h"
+#include "debug.h"
+#include "hist.h"
+#include "intlist.h"
+#include "string2.h"
+#include "symbol.h"
+#include "tests.h"
+#include "util/rlimit.h"
+#include "util/util.h"
+
+static int shell_tests__dir_fd(void)
+{
+	char path[PATH_MAX], *exec_path;
+	static const char * const devel_dirs[] = { "./tools/perf/tests/shell", "./tests/shell", };
+
+	for (size_t i = 0; i < ARRAY_SIZE(devel_dirs); ++i) {
+		int fd = open(devel_dirs[i], O_PATH);
+
+		if (fd >= 0)
+			return fd;
+	}
+
+	/* Then installed path. */
+	exec_path = get_argv_exec_path();
+	scnprintf(path, sizeof(path), "%s/tests/shell", exec_path);
+	free(exec_path);
+	return open(path, O_PATH);
+}
+
+static char *shell_test__description(int dir_fd, const char *name)
+{
+	struct io io;
+	char buf[128], desc[256];
+	int ch, pos = 0;
+
+	io__init(&io, openat(dir_fd, name, O_RDONLY), buf, sizeof(buf));
+	if (io.fd < 0)
+		return NULL;
+
+	/* Skip first line - should be #!/bin/sh Shebang */
+	if (io__get_char(&io) != '#')
+		goto err_out;
+	if (io__get_char(&io) != '!')
+		goto err_out;
+	do {
+		ch = io__get_char(&io);
+		if (ch < 0)
+			goto err_out;
+	} while (ch != '\n');
+
+	do {
+		ch = io__get_char(&io);
+		if (ch < 0)
+			goto err_out;
+	} while (ch == '#' || isspace(ch));
+	while (ch > 0 && ch != '\n') {
+		desc[pos++] = ch;
+		if (pos >= (int)sizeof(desc) - 1)
+			break;
+		ch = io__get_char(&io);
+	}
+	while (pos > 0 && isspace(desc[--pos]))
+		;
+	desc[++pos] = '\0';
+	close(io.fd);
+	return strdup(desc);
+err_out:
+	close(io.fd);
+	return NULL;
+}
+
+/* Is this full file path a shell script */
+static bool is_shell_script(int dir_fd, const char *path)
+{
+	const char *ext;
+
+	ext = strrchr(path, '.');
+	if (!ext)
+		return false;
+	if (!strcmp(ext, ".sh")) { /* Has .sh extension */
+		if (faccessat(dir_fd, path, R_OK | X_OK, 0) == 0) /* Is executable */
+			return true;
+	}
+	return false;
+}
+
+/* Is this file in this dir a shell script (for test purposes) */
+static bool is_test_script(int dir_fd, const char *name)
+{
+	return is_shell_script(dir_fd, name);
+}
+
+/* Duplicate a string and fall over and die if we run out of memory */
+static char *strdup_check(const char *str)
+{
+	char *newstr;
+
+	newstr = strdup(str);
+	if (!newstr) {
+		pr_err("Out of memory while duplicating test script string\n");
+		abort();
+	}
+	return newstr;
+}
+
+static int shell_test__run(struct test_suite *test, int subtest __maybe_unused)
+{
+	const char *file = test->priv;
+	int err;
+	char *cmd = NULL;
+
+	if (asprintf(&cmd, "%s%s", file, verbose ? " -v" : "") < 0)
+		return TEST_FAIL;
+	err = system(cmd);
+	free(cmd);
+	if (!err)
+		return TEST_OK;
+
+	return WEXITSTATUS(err) == 2 ? TEST_SKIP : TEST_FAIL;
+}
+
+static void append_script(int dir_fd, const char *name, char *desc,
+			  struct test_suite ***result,
+			  size_t *result_sz)
+{
+	char filename[PATH_MAX], link[128];
+	struct test_suite *test_suite, **result_tmp;
+	struct test_case *tests;
+	size_t len;
+
+	snprintf(link, sizeof(link), "/proc/%d/fd/%d", getpid(), dir_fd);
+	len = readlink(link, filename, sizeof(filename));
+	if (len < 0) {
+		pr_err("Failed to readlink %s", link);
+		return;
+	}
+	filename[len++] = '/';
+	strcpy(&filename[len], name);
+
+	tests = calloc(2, sizeof(*tests));
+	if (!tests) {
+		pr_err("Out of memory while building script test suite list\n");
+		return;
+	}
+	tests[0].name = strdup_check(name);
+	tests[0].desc = strdup_check(desc);
+	tests[0].run_case = shell_test__run;
+
+	test_suite = zalloc(sizeof(*test_suite));
+	if (!test_suite) {
+		pr_err("Out of memory while building script test suite list\n");
+		free(tests);
+		return;
+	}
+	test_suite->desc = desc;
+	test_suite->test_cases = tests;
+	test_suite->priv = strdup_check(filename);
+	/* Realloc is good enough, though we could realloc by chunks, not that
+	 * anyone will ever measure performance here */
+	result_tmp = realloc(*result, (*result_sz + 1) * sizeof(*result_tmp));
+	if (result_tmp == NULL) {
+		pr_err("Out of memory while building script test suite list\n");
+		free(tests);
+		free(test_suite);
+		return;
+	}
+	/* Add file to end and NULL terminate the struct array */
+	*result = result_tmp;
+	(*result)[*result_sz] = test_suite;
+	(*result_sz)++;
+}
+
+static void append_scripts_in_dir(int dir_fd,
+				  struct test_suite ***result,
+				  size_t *result_sz)
+{
+	struct dirent **entlist;
+	struct dirent *ent;
+	int n_dirs, i;
+
+	/* List files, sorted by alpha */
+	n_dirs = scandirat(dir_fd, ".", &entlist, NULL, alphasort);
+	if (n_dirs == -1)
+		return;
+	for (i = 0; i < n_dirs && (ent = entlist[i]); i++) {
+		int fd;
+
+		if (ent->d_name[0] == '.')
+			continue; /* Skip hidden files */
+		if (is_test_script(dir_fd, ent->d_name)) { /* It's a test */
+			char *desc = shell_test__description(dir_fd, ent->d_name);
+
+			if (desc) /* It has a desc line - valid script */
+				append_script(dir_fd, ent->d_name, desc, result, result_sz);
+			continue;
+		}
+		if (ent->d_type != DT_DIR) {
+			struct stat st;
+
+			if (ent->d_type != DT_UNKNOWN)
+				continue;
+			fstatat(dir_fd, ent->d_name, &st, 0);
+			if (!S_ISDIR(st.st_mode))
+				continue;
+		}
+		fd = openat(dir_fd, ent->d_name, O_PATH);
+		append_scripts_in_dir(fd, result, result_sz);
+	}
+	for (i = 0; i < n_dirs; i++) /* Clean up */
+		zfree(&entlist[i]);
+	free(entlist);
+}
+
+struct test_suite **create_script_test_suites(void)
+{
+	struct test_suite **result = NULL, **result_tmp;
+	size_t result_sz = 0;
+	int dir_fd = shell_tests__dir_fd(); /* Walk  dir */
+
+	/*
+	 * Append scripts if fd is good, otherwise return a NULL terminated zero
+	 * length array.
+	 */
+	if (dir_fd >= 0)
+		append_scripts_in_dir(dir_fd, &result, &result_sz);
+
+	result_tmp = realloc(result, (result_sz + 1) * sizeof(*result_tmp));
+	if (result_tmp == NULL) {
+		pr_err("Out of memory while building script test suite list\n");
+		abort();
+	}
+	/* NULL terminate the test suite array. */
+	result = result_tmp;
+	result[result_sz] = NULL;
+	if (dir_fd >= 0)
+		close(dir_fd);
+	return result;
+}