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, 88 insertions, 0 deletions

diff --git a/drivers/clocksource/numachip.c b/drivers/clocksource/numachip.c
new file mode 100644
index 000000000..fdb5fc21f
--- /dev/null
+++ b/drivers/clocksource/numachip.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *
+ * Copyright (C) 2015 Numascale AS. All rights reserved.
+ */
+
+#include <linux/clockchips.h>
+
+#include <asm/irq.h>
+#include <asm/numachip/numachip.h>
+#include <asm/numachip/numachip_csr.h>
+
+static DEFINE_PER_CPU(struct clock_event_device, numachip2_ced);
+
+static cycles_t numachip2_timer_read(struct clocksource *cs)
+{
+	return numachip2_read64_lcsr(NUMACHIP2_TIMER_NOW);
+}
+
+static struct clocksource numachip2_clocksource = {
+	.name            = "numachip2",
+	.rating          = 295,
+	.read            = numachip2_timer_read,
+	.mask            = CLOCKSOURCE_MASK(64),
+	.flags           = CLOCK_SOURCE_IS_CONTINUOUS,
+	.mult            = 1,
+	.shift           = 0,
+};
+
+static int numachip2_set_next_event(unsigned long delta, struct clock_event_device *ced)
+{
+	numachip2_write64_lcsr(NUMACHIP2_TIMER_DEADLINE + numachip2_timer(),
+		delta);
+	return 0;
+}
+
+static const struct clock_event_device numachip2_clockevent __initconst = {
+	.name            = "numachip2",
+	.rating          = 400,
+	.set_next_event  = numachip2_set_next_event,
+	.features        = CLOCK_EVT_FEAT_ONESHOT,
+	.mult            = 1,
+	.shift           = 0,
+	.min_delta_ns    = 1250,
+	.min_delta_ticks = 1250,
+	.max_delta_ns    = LONG_MAX,
+	.max_delta_ticks = LONG_MAX,
+};
+
+static void numachip_timer_interrupt(void)
+{
+	struct clock_event_device *ced = this_cpu_ptr(&numachip2_ced);
+
+	ced->event_handler(ced);
+}
+
+static __init void numachip_timer_each(struct work_struct *work)
+{
+	unsigned local_apicid = __this_cpu_read(x86_cpu_to_apicid) & 0xff;
+	struct clock_event_device *ced = this_cpu_ptr(&numachip2_ced);
+
+	/* Setup IPI vector to local core and relative timing mode */
+	numachip2_write64_lcsr(NUMACHIP2_TIMER_INT + numachip2_timer(),
+		(3 << 22) | (X86_PLATFORM_IPI_VECTOR << 14) |
+		(local_apicid << 6));
+
+	*ced = numachip2_clockevent;
+	ced->cpumask = cpumask_of(smp_processor_id());
+	clockevents_register_device(ced);
+}
+
+static int __init numachip_timer_init(void)
+{
+	if (numachip_system != 2)
+		return -ENODEV;
+
+	/* Reset timer */
+	numachip2_write64_lcsr(NUMACHIP2_TIMER_RESET, 0);
+	clocksource_register_hz(&numachip2_clocksource, NSEC_PER_SEC);
+
+	/* Setup per-cpu clockevents */
+	x86_platform_ipi_callback = numachip_timer_interrupt;
+	schedule_on_each_cpu(&numachip_timer_each);
+
+	return 0;
+}
+
+arch_initcall(numachip_timer_init);