ftrace: Synchronize the initialization of ftrace_opsgrafted

There's some internal state that ftrace_ops needs to have set, but since
it can be declared outside of the ftrace.c code, it calls
ftrace_ops_init() on the ops in every global function. The issue is that
if two tasks call it on the same ops at the same time it is possible to
have the initialization of one corrupt the initialization of the other
call.

Create a ops_mutex to use to synchronize every initialization of the
ftrace_ops. The mutex is taken within checking the ftrace_ops flag that
states it was initializied but the flag is checked again after the mutex
has been taken. Checking first outside the mutex allows it to shortcut
having to take the mutex. But then the check needs to be done again after
the mute is taken in case of races.

Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260902095501.6b59af20@gandalf.local.home
Fixes: f04f24fb7e48d ("ftrace, kprobes: Fix a deadlock on ftrace_regex_lock")
Reported-by: sashiko-bot@kernel.org
Close: https://lore.kernel.org/all/20260829025528.49A831F000E9@smtp.kernel.org/
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

1 files changed, 213 insertions, 0 deletions

diff --git a/tools/perf/bench/uprobe.c b/tools/perf/bench/uprobe.c
new file mode 100644
index 000000000..616873bca
--- /dev/null
+++ b/tools/perf/bench/uprobe.c
@@ -0,0 +1,213 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/*
+ * uprobe.c
+ *
+ * uprobe benchmarks
+ *
+ *  Copyright (C) 2023, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ */
+#include "../perf.h"
+#include "../util/util.h"
+#include <subcmd/parse-options.h>
+#include "../builtin.h"
+#include "bench.h"
+#include <linux/compiler.h>
+#include <linux/time64.h>
+
+#include <inttypes.h>
+#include <stdio.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <time.h>
+#include <unistd.h>
+#include <stdlib.h>
+
+#define LOOPS_DEFAULT 1000
+static int loops = LOOPS_DEFAULT;
+
+enum bench_uprobe {
+	BENCH_UPROBE__BASELINE,
+	BENCH_UPROBE__EMPTY,
+	BENCH_UPROBE__TRACE_PRINTK,
+	BENCH_UPROBE__EMPTY_RET,
+	BENCH_UPROBE__TRACE_PRINTK_RET,
+};
+
+static const struct option options[] = {
+	OPT_INTEGER('l', "loop",	&loops,		"Specify number of loops"),
+	OPT_END()
+};
+
+static const char * const bench_uprobe_usage[] = {
+	"perf bench uprobe <options>",
+	NULL
+};
+
+#ifdef HAVE_BPF_SKEL
+#include "bench/bpf_skel/bench_uprobe.skel.h"
+
+#define bench_uprobe__attach_uprobe(prog) \
+	skel->links.prog = bpf_program__attach_uprobe_opts(/*prog=*/skel->progs.prog, \
+							   /*pid=*/-1, \
+							   /*binary_path=*/"libc.so.6", \
+							   /*func_offset=*/0, \
+							   /*opts=*/&uprobe_opts); \
+	if (!skel->links.prog) { \
+		err = -errno; \
+		fprintf(stderr, "Failed to attach bench uprobe \"%s\": %m\n", #prog); \
+		goto cleanup; \
+	}
+
+static struct bench_uprobe_bpf *skel;
+
+static int bench_uprobe__setup_bpf_skel(enum bench_uprobe bench)
+{
+	DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
+	int err;
+
+	/* Load and verify BPF application */
+	skel = bench_uprobe_bpf__open();
+	if (!skel) {
+		fprintf(stderr, "Failed to open and load uprobes bench BPF skeleton\n");
+		return -1;
+	}
+
+	err = bench_uprobe_bpf__load(skel);
+	if (err) {
+		fprintf(stderr, "Failed to load and verify BPF skeleton\n");
+		goto cleanup;
+	}
+
+	uprobe_opts.func_name = "usleep";
+	switch (bench) {
+	case BENCH_UPROBE__BASELINE:							break;
+	case BENCH_UPROBE__EMPTY:	 bench_uprobe__attach_uprobe(empty);		break;
+	case BENCH_UPROBE__TRACE_PRINTK: bench_uprobe__attach_uprobe(trace_printk);	break;
+	case BENCH_UPROBE__EMPTY_RET:	 bench_uprobe__attach_uprobe(empty_ret);	break;
+	case BENCH_UPROBE__TRACE_PRINTK_RET: bench_uprobe__attach_uprobe(trace_printk_ret); break;
+	default:
+		fprintf(stderr, "Invalid bench: %d\n", bench);
+		goto cleanup;
+	}
+
+	return err;
+cleanup:
+	bench_uprobe_bpf__destroy(skel);
+	skel = NULL;
+	return err;
+}
+
+static void bench_uprobe__teardown_bpf_skel(void)
+{
+	if (skel) {
+		bench_uprobe_bpf__destroy(skel);
+		skel = NULL;
+	}
+}
+#else
+static int bench_uprobe__setup_bpf_skel(enum bench_uprobe bench __maybe_unused) { return 0; }
+static void bench_uprobe__teardown_bpf_skel(void) {};
+#endif
+
+static int bench_uprobe_format__default_fprintf(const char *name, const char *unit, u64 diff, FILE *fp)
+{
+	static u64 baseline, previous;
+	s64 diff_to_baseline = diff - baseline,
+	    diff_to_previous = diff - previous;
+	int printed = fprintf(fp, "# Executed %'d %s calls\n", loops, name);
+
+	printed += fprintf(fp, " %14s: %'" PRIu64 " %ss", "Total time", diff, unit);
+
+	if (baseline) {
+		printed += fprintf(fp, " %s%'" PRId64 " to baseline", diff_to_baseline > 0 ? "+" : "", diff_to_baseline);
+
+		if (previous != baseline)
+			fprintf(stdout, " %s%'" PRId64 " to previous", diff_to_previous > 0 ? "+" : "", diff_to_previous);
+	}
+
+	printed += fprintf(fp, "\n\n %'.3f %ss/op", (double)diff / (double)loops, unit);
+
+	if (baseline) {
+		printed += fprintf(fp, " %'.3f %ss/op to baseline", (double)diff_to_baseline / (double)loops, unit);
+
+		if (previous != baseline)
+			printed += fprintf(fp, " %'.3f %ss/op to previous", (double)diff_to_previous / (double)loops, unit);
+	} else {
+		baseline = diff;
+	}
+
+	fputc('\n', fp);
+
+	previous = diff;
+
+	return printed + 1;
+}
+
+static int bench_uprobe(int argc, const char **argv, enum bench_uprobe bench)
+{
+	const char *name = "usleep(1000)", *unit = "usec";
+	struct timespec start, end;
+	u64 diff;
+	int i;
+
+	argc = parse_options(argc, argv, options, bench_uprobe_usage, 0);
+
+	if (bench != BENCH_UPROBE__BASELINE && bench_uprobe__setup_bpf_skel(bench) < 0)
+		return 0;
+
+        clock_gettime(CLOCK_REALTIME, &start);
+
+	for (i = 0; i < loops; i++) {
+		usleep(USEC_PER_MSEC);
+	}
+
+	clock_gettime(CLOCK_REALTIME, &end);
+
+	diff = end.tv_sec * NSEC_PER_SEC + end.tv_nsec - (start.tv_sec * NSEC_PER_SEC + start.tv_nsec);
+	diff /= NSEC_PER_USEC;
+
+	switch (bench_format) {
+	case BENCH_FORMAT_DEFAULT:
+		bench_uprobe_format__default_fprintf(name, unit, diff, stdout);
+		break;
+
+	case BENCH_FORMAT_SIMPLE:
+		printf("%" PRIu64 "\n", diff);
+		break;
+
+	default:
+		/* reaching here is something of a disaster */
+		fprintf(stderr, "Unknown format:%d\n", bench_format);
+		exit(1);
+	}
+
+	if (bench != BENCH_UPROBE__BASELINE)
+		bench_uprobe__teardown_bpf_skel();
+
+	return 0;
+}
+
+int bench_uprobe_baseline(int argc, const char **argv)
+{
+	return bench_uprobe(argc, argv, BENCH_UPROBE__BASELINE);
+}
+
+int bench_uprobe_empty(int argc, const char **argv)
+{
+	return bench_uprobe(argc, argv, BENCH_UPROBE__EMPTY);
+}
+
+int bench_uprobe_trace_printk(int argc, const char **argv)
+{
+	return bench_uprobe(argc, argv, BENCH_UPROBE__TRACE_PRINTK);
+}
+
+int bench_uprobe_empty_ret(int argc, const char **argv)
+{
+	return bench_uprobe(argc, argv, BENCH_UPROBE__EMPTY_RET);
+}
+
+int bench_uprobe_trace_printk_ret(int argc, const char **argv)
+{
+	return bench_uprobe(argc, argv, BENCH_UPROBE__TRACE_PRINTK_RET);
+}