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, 103 insertions, 0 deletions

diff --git a/tools/perf/util/affinity.c b/tools/perf/util/affinity.c
new file mode 100644
index 000000000..6c64b5f69
--- /dev/null
+++ b/tools/perf/util/affinity.c
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Manage affinity to optimize IPIs inside the kernel perf API. */
+#define _GNU_SOURCE 1
+#include <sched.h>
+#include <stdlib.h>
+#include <linux/bitmap.h>
+#include <linux/zalloc.h>
+#include <perf/cpumap.h>
+#include "perf.h"
+#include "cpumap.h"
+#include "affinity.h"
+
+static int get_cpu_set_size(void)
+{
+	int sz = cpu__max_cpu().cpu + 8 - 1;
+	/*
+	 * sched_getaffinity doesn't like masks smaller than the kernel.
+	 * Hopefully that's big enough.
+	 */
+	if (sz < 4096)
+		sz = 4096;
+	return sz / 8;
+}
+
+int affinity__setup(struct affinity *a)
+{
+	int cpu_set_size = get_cpu_set_size();
+
+	a->orig_cpus = bitmap_zalloc(cpu_set_size * 8);
+	if (!a->orig_cpus)
+		return -1;
+	sched_getaffinity(0, cpu_set_size, (cpu_set_t *)a->orig_cpus);
+	a->sched_cpus = bitmap_zalloc(cpu_set_size * 8);
+	if (!a->sched_cpus) {
+		zfree(&a->orig_cpus);
+		return -1;
+	}
+	bitmap_zero((unsigned long *)a->sched_cpus, cpu_set_size);
+	a->changed = false;
+	return 0;
+}
+
+/*
+ * perf_event_open does an IPI internally to the target CPU.
+ * It is more efficient to change perf's affinity to the target
+ * CPU and then set up all events on that CPU, so we amortize
+ * CPU communication.
+ */
+void affinity__set(struct affinity *a, int cpu)
+{
+	int cpu_set_size = get_cpu_set_size();
+
+	/*
+	 * Return:
+	 * - if cpu is -1
+	 * - restrict out of bound access to sched_cpus
+	 */
+	if (cpu == -1 || ((cpu >= (cpu_set_size * 8))))
+		return;
+
+	a->changed = true;
+	__set_bit(cpu, a->sched_cpus);
+	/*
+	 * We ignore errors because affinity is just an optimization.
+	 * This could happen for example with isolated CPUs or cpusets.
+	 * In this case the IPIs inside the kernel's perf API still work.
+	 */
+	sched_setaffinity(0, cpu_set_size, (cpu_set_t *)a->sched_cpus);
+	__clear_bit(cpu, a->sched_cpus);
+}
+
+static void __affinity__cleanup(struct affinity *a)
+{
+	int cpu_set_size = get_cpu_set_size();
+
+	if (a->changed)
+		sched_setaffinity(0, cpu_set_size, (cpu_set_t *)a->orig_cpus);
+	zfree(&a->sched_cpus);
+	zfree(&a->orig_cpus);
+}
+
+void affinity__cleanup(struct affinity *a)
+{
+	if (a != NULL)
+		__affinity__cleanup(a);
+}
+
+void cpu_map__set_affinity(const struct perf_cpu_map *cpumap)
+{
+	int cpu_set_size = get_cpu_set_size();
+	unsigned long *cpuset = bitmap_zalloc(cpu_set_size * 8);
+	struct perf_cpu cpu;
+	unsigned int idx;
+
+	if (!cpuset)
+		return;
+
+	perf_cpu_map__for_each_cpu_skip_any(cpu, idx, cpumap)
+		__set_bit(cpu.cpu, cpuset);
+
+	sched_setaffinity(0, cpu_set_size, (cpu_set_t *)cpuset);
+	zfree(&cpuset);
+}