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, 82 insertions, 0 deletions

diff --git a/include/asm-generic/bitops/lock.h b/include/asm-generic/bitops/lock.h
new file mode 100644
index 000000000..ffb73b612
--- /dev/null
+++ b/include/asm-generic/bitops/lock.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_BITOPS_LOCK_H_
+#define _ASM_GENERIC_BITOPS_LOCK_H_
+
+#include <linux/atomic.h>
+#include <linux/compiler.h>
+#include <asm/barrier.h>
+
+/**
+ * arch_test_and_set_bit_lock - Set a bit and return its old value, for lock
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is atomic and provides acquire barrier semantics if
+ * the returned value is 0.
+ * It can be used to implement bit locks.
+ */
+static __always_inline int
+arch_test_and_set_bit_lock(unsigned int nr, volatile unsigned long *addr)
+{
+	long old;
+	unsigned long mask = BIT_MASK(nr);
+
+	addr += BIT_WORD(nr);
+	if (READ_ONCE(*addr) & mask)
+		return 1;
+
+	old = raw_atomic_long_fetch_or_acquire(mask, (atomic_long_t *)addr);
+	return !!(old & mask);
+}
+
+
+/**
+ * arch_clear_bit_unlock - Clear a bit in memory, for unlock
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This operation is atomic and provides release barrier semantics.
+ */
+static __always_inline void
+arch_clear_bit_unlock(unsigned int nr, volatile unsigned long *addr)
+{
+	addr += BIT_WORD(nr);
+	raw_atomic_long_fetch_andnot_release(BIT_MASK(nr), (atomic_long_t *)addr);
+}
+
+/**
+ * arch___clear_bit_unlock - Clear a bit in memory, for unlock
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * A weaker form of clear_bit_unlock() as used by __bit_lock_unlock(). If all
+ * the bits in the word are protected by this lock some archs can use weaker
+ * ops to safely unlock.
+ *
+ * See for example x86's implementation.
+ */
+static inline void
+arch___clear_bit_unlock(unsigned int nr, volatile unsigned long *addr)
+{
+	unsigned long old;
+
+	addr += BIT_WORD(nr);
+	old = READ_ONCE(*addr);
+	old &= ~BIT_MASK(nr);
+	raw_atomic_long_set_release((atomic_long_t *)addr, old);
+}
+
+#ifndef arch_xor_unlock_is_negative_byte
+static inline bool arch_xor_unlock_is_negative_byte(unsigned long mask,
+		volatile unsigned long *p)
+{
+	long old;
+
+	old = raw_atomic_long_fetch_xor_release(mask, (atomic_long_t *)p);
+	return !!(old & BIT(7));
+}
+#endif
+
+#include <asm-generic/bitops/instrumented-lock.h>
+
+#endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */