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, 148 insertions, 0 deletions

diff --git a/lib/percpu_test.c b/lib/percpu_test.c
new file mode 100644
index 000000000..ce7124b16
--- /dev/null
+++ b/lib/percpu_test.c
@@ -0,0 +1,148 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/limits.h>
+#include <linux/module.h>
+
+/* validate @native and @pcp counter values match @expected */
+#define CHECK(native, pcp, expected)                                    \
+	do {                                                            \
+		WARN((native) != (expected),                            \
+		     "raw %ld (0x%lx) != expected %lld (0x%llx)",	\
+		     (native), (native),				\
+		     (long long)(expected), (long long)(expected));	\
+		WARN(__this_cpu_read(pcp) != (expected),                \
+		     "pcp %ld (0x%lx) != expected %lld (0x%llx)",	\
+		     __this_cpu_read(pcp), __this_cpu_read(pcp),	\
+		     (long long)(expected), (long long)(expected));	\
+	} while (0)
+
+static DEFINE_PER_CPU(long, long_counter);
+static DEFINE_PER_CPU(unsigned long, ulong_counter);
+
+static int __init percpu_test_init(void)
+{
+	/*
+	 * volatile prevents compiler from optimizing it uses, otherwise the
+	 * +ul_one/-ul_one below would replace with inc/dec instructions.
+	 */
+	volatile unsigned int ui_one = 1;
+	unsigned long long ull = 0;
+	unsigned long ul = 0;
+	long l = 0;
+
+	pr_info("percpu test start\n");
+
+	preempt_disable();
+
+	l += -1;
+	__this_cpu_add(long_counter, -1);
+	CHECK(l, long_counter, -1);
+
+	l += 1;
+	__this_cpu_add(long_counter, 1);
+	CHECK(l, long_counter, 0);
+
+	ul = 0;
+	__this_cpu_write(ulong_counter, 0);
+
+	ul += 1UL;
+	__this_cpu_add(ulong_counter, 1UL);
+	CHECK(ul, ulong_counter, 1);
+
+	ul += -1UL;
+	__this_cpu_add(ulong_counter, -1UL);
+	CHECK(ul, ulong_counter, 0);
+
+	ul += -(unsigned long)1;
+	__this_cpu_add(ulong_counter, -(unsigned long)1);
+	CHECK(ul, ulong_counter, -1);
+
+	ul = 0;
+	__this_cpu_write(ulong_counter, 0);
+
+	ul -= 1;
+	__this_cpu_dec(ulong_counter);
+	CHECK(ul, ulong_counter, -1);
+	CHECK(ul, ulong_counter, ULONG_MAX);
+
+	l += -ui_one;
+	__this_cpu_add(long_counter, -ui_one);
+	CHECK(l, long_counter, 0xffffffff);
+
+	l += ui_one;
+	__this_cpu_add(long_counter, ui_one);
+	CHECK(l, long_counter, (long)0x100000000LL);
+
+
+	l = 0;
+	__this_cpu_write(long_counter, 0);
+
+	l -= ui_one;
+	__this_cpu_sub(long_counter, ui_one);
+	CHECK(l, long_counter, -1);
+
+	l = 0;
+	__this_cpu_write(long_counter, 0);
+
+	l += ui_one;
+	__this_cpu_add(long_counter, ui_one);
+	CHECK(l, long_counter, 1);
+
+	l += -ui_one;
+	__this_cpu_add(long_counter, -ui_one);
+	CHECK(l, long_counter, (long)0x100000000LL);
+
+	l = 0;
+	__this_cpu_write(long_counter, 0);
+
+	l -= ui_one;
+	this_cpu_sub(long_counter, ui_one);
+	CHECK(l, long_counter, -1);
+	CHECK(l, long_counter, ULONG_MAX);
+
+	ul = 0;
+	__this_cpu_write(ulong_counter, 0);
+
+	ul += ui_one;
+	__this_cpu_add(ulong_counter, ui_one);
+	CHECK(ul, ulong_counter, 1);
+
+	ul = 0;
+	__this_cpu_write(ulong_counter, 0);
+
+	ul -= ui_one;
+	__this_cpu_sub(ulong_counter, ui_one);
+	CHECK(ul, ulong_counter, -1);
+	CHECK(ul, ulong_counter, ULONG_MAX);
+
+	ul = ull = 0;
+	__this_cpu_write(ulong_counter, 0);
+
+	ul = ull += UINT_MAX;
+	__this_cpu_add(ulong_counter, ull);
+	CHECK(ul, ulong_counter, UINT_MAX);
+
+	ul = 3;
+	__this_cpu_write(ulong_counter, 3);
+
+	ul = this_cpu_sub_return(ulong_counter, ui_one);
+	CHECK(ul, ulong_counter, 2);
+
+	ul = __this_cpu_sub_return(ulong_counter, ui_one);
+	CHECK(ul, ulong_counter, 1);
+
+	preempt_enable();
+
+	pr_info("percpu test done\n");
+	return -EAGAIN;  /* Fail will directly unload the module */
+}
+
+static void __exit percpu_test_exit(void)
+{
+}
+
+module_init(percpu_test_init)
+module_exit(percpu_test_exit)
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Greg Thelen");
+MODULE_DESCRIPTION("percpu operations test");