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/arch/arm/lib/delay.c b/arch/arm/lib/delay.c
new file mode 100644
index 000000000..7e9304012
--- /dev/null
+++ b/arch/arm/lib/delay.c
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Delay loops based on the OpenRISC implementation.
+ *
+ * Copyright (C) 2012 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#include <linux/clocksource.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+/*
+ * Default to the loop-based delay implementation.
+ */
+struct arm_delay_ops arm_delay_ops __ro_after_init = {
+	.delay		= __loop_delay,
+	.const_udelay	= __loop_const_udelay,
+	.udelay		= __loop_udelay,
+};
+
+static const struct delay_timer *delay_timer;
+static bool delay_calibrated;
+static u64 delay_res;
+
+bool delay_read_timer(unsigned long *timer_val)
+{
+	if (!delay_timer)
+		return false;
+	*timer_val = delay_timer->read_current_timer();
+	return true;
+}
+EXPORT_SYMBOL_GPL(delay_read_timer);
+
+static inline u64 cyc_to_ns(u64 cyc, u32 mult, u32 shift)
+{
+	return (cyc * mult) >> shift;
+}
+
+static void __timer_delay(unsigned long cycles)
+{
+	cycles_t start = get_cycles();
+
+	while ((get_cycles() - start) < cycles)
+		cpu_relax();
+}
+
+static void __timer_const_udelay(unsigned long xloops)
+{
+	unsigned long long loops = xloops;
+	loops *= arm_delay_ops.ticks_per_jiffy;
+	__timer_delay(loops >> UDELAY_SHIFT);
+}
+
+static void __timer_udelay(unsigned long usecs)
+{
+	__timer_const_udelay(usecs * UDELAY_MULT);
+}
+
+void __init register_current_timer_delay(const struct delay_timer *timer)
+{
+	u32 new_mult, new_shift;
+	u64 res;
+
+	clocks_calc_mult_shift(&new_mult, &new_shift, timer->freq,
+			       NSEC_PER_SEC, 3600);
+	res = cyc_to_ns(1ULL, new_mult, new_shift);
+
+	if (res > 1000) {
+		pr_err("Ignoring delay timer %ps, which has insufficient resolution of %lluns\n",
+			timer, res);
+		return;
+	}
+
+	if (!delay_calibrated && (!delay_res || (res < delay_res))) {
+		pr_info("Switching to timer-based delay loop, resolution %lluns\n", res);
+		delay_timer			= timer;
+		lpj_fine			= timer->freq / HZ;
+		delay_res			= res;
+
+		/* cpufreq may scale loops_per_jiffy, so keep a private copy */
+		arm_delay_ops.ticks_per_jiffy	= lpj_fine;
+		arm_delay_ops.delay		= __timer_delay;
+		arm_delay_ops.const_udelay	= __timer_const_udelay;
+		arm_delay_ops.udelay		= __timer_udelay;
+	} else {
+		pr_info("Ignoring duplicate/late registration of read_current_timer delay\n");
+	}
+}
+
+unsigned long calibrate_delay_is_known(void)
+{
+	delay_calibrated = true;
+	return lpj_fine;
+}
+
+void calibration_delay_done(void)
+{
+	delay_calibrated = true;
+}