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, 56 insertions, 0 deletions

diff --git a/arch/alpha/lib/udelay.c b/arch/alpha/lib/udelay.c
new file mode 100644
index 000000000..873648263
--- /dev/null
+++ b/arch/alpha/lib/udelay.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 1993, 2000 Linus Torvalds
+ *
+ * Delay routines, using a pre-computed "loops_per_jiffy" value.
+ */
+
+#include <linux/module.h>
+#include <linux/sched.h> /* for udelay's use of smp_processor_id */
+#include <asm/param.h>
+#include <asm/smp.h>
+#include <linux/delay.h>
+
+/*
+ * Use only for very small delays (< 1 msec). 
+ *
+ * The active part of our cycle counter is only 32-bits wide, and
+ * we're treating the difference between two marks as signed.  On
+ * a 1GHz box, that's about 2 seconds.
+ */
+
+void
+__delay(int loops)
+{
+	int tmp;
+	__asm__ __volatile__(
+		"	rpcc %0\n"
+		"	addl %1,%0,%1\n"
+		"1:	rpcc %0\n"
+		"	subl %1,%0,%0\n"
+		"	bgt %0,1b"
+		: "=&r" (tmp), "=r" (loops) : "1"(loops));
+}
+EXPORT_SYMBOL(__delay);
+
+#ifdef CONFIG_SMP
+#define LPJ	 cpu_data[smp_processor_id()].loops_per_jiffy
+#else
+#define LPJ	 loops_per_jiffy
+#endif
+
+void
+udelay(unsigned long usecs)
+{
+	usecs *= (((unsigned long)HZ << 32) / 1000000) * LPJ;
+	__delay((long)usecs >> 32);
+}
+EXPORT_SYMBOL(udelay);
+
+void
+ndelay(unsigned long nsecs)
+{
+	nsecs *= (((unsigned long)HZ << 32) / 1000000000) * LPJ;
+	__delay((long)nsecs >> 32);
+}
+EXPORT_SYMBOL(ndelay);