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, 45 insertions, 0 deletions

diff --git a/include/uapi/asm-generic/sembuf.h b/include/uapi/asm-generic/sembuf.h
new file mode 100644
index 000000000..f54e48fc9
--- /dev/null
+++ b/include/uapi/asm-generic/sembuf.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_GENERIC_SEMBUF_H
+#define __ASM_GENERIC_SEMBUF_H
+
+#include <asm/bitsperlong.h>
+#include <asm/ipcbuf.h>
+
+/*
+ * The semid64_ds structure for most architectures (though it came from x86_32
+ * originally). Note extra padding because this structure is passed back and
+ * forth between kernel and user space.
+ *
+ * semid64_ds was originally meant to be architecture specific, but
+ * everyone just ended up making identical copies without specific
+ * optimizations, so we may just as well all use the same one.
+ *
+ * 64 bit architectures use a 64-bit long time field here, while
+ * 32 bit architectures have a pair of unsigned long values.
+ *
+ * On big-endian systems, the padding is in the wrong place for
+ * historic reasons, so user space has to reconstruct a time_t
+ * value using
+ *
+ * user_semid_ds.sem_otime = kernel_semid64_ds.sem_otime +
+ *		((long long)kernel_semid64_ds.sem_otime_high << 32)
+ *
+ * Pad space is left for 2 miscellaneous 32-bit values
+ */
+struct semid64_ds {
+	struct ipc64_perm sem_perm;	/* permissions .. see ipc.h */
+#if __BITS_PER_LONG == 64
+	long		sem_otime;	/* last semop time */
+	long		sem_ctime;	/* last change time */
+#else
+	unsigned long	sem_otime;	/* last semop time */
+	unsigned long	sem_otime_high;
+	unsigned long	sem_ctime;	/* last change time */
+	unsigned long	sem_ctime_high;
+#endif
+	unsigned long	sem_nsems;	/* no. of semaphores in array */
+	unsigned long	__unused3;
+	unsigned long	__unused4;
+};
+
+#endif /* __ASM_GENERIC_SEMBUF_H */