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, 54 insertions, 0 deletions

diff --git a/lib/bucket_locks.c b/lib/bucket_locks.c
new file mode 100644
index 000000000..d29516ca0
--- /dev/null
+++ b/lib/bucket_locks.c
@@ -0,0 +1,54 @@
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+
+/* Allocate an array of spinlocks to be accessed by a hash. Two arguments
+ * indicate the number of elements to allocate in the array. max_size
+ * gives the maximum number of elements to allocate. cpu_mult gives
+ * the number of locks per CPU to allocate. The size is rounded up
+ * to a power of 2 to be suitable as a hash table.
+ */
+
+int __alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *locks_mask,
+			     size_t max_size, unsigned int cpu_mult, gfp_t gfp,
+			     const char *name, struct lock_class_key *key)
+{
+	spinlock_t *tlocks = NULL;
+	unsigned int i, size;
+#if defined(CONFIG_PROVE_LOCKING)
+	unsigned int nr_pcpus = 2;
+#else
+	unsigned int nr_pcpus = num_possible_cpus();
+#endif
+
+	if (cpu_mult) {
+		nr_pcpus = min_t(unsigned int, nr_pcpus, 64UL);
+		size = min_t(unsigned int, nr_pcpus * cpu_mult, max_size);
+	} else {
+		size = max_size;
+	}
+
+	if (sizeof(spinlock_t) != 0) {
+		tlocks = kvmalloc_objs(spinlock_t, size, gfp);
+		if (!tlocks)
+			return -ENOMEM;
+		for (i = 0; i < size; i++) {
+			spin_lock_init(&tlocks[i]);
+			lockdep_init_map(&tlocks[i].dep_map, name, key, 0);
+		}
+	}
+
+	*locks = tlocks;
+	*locks_mask = size - 1;
+
+	return 0;
+}
+EXPORT_SYMBOL(__alloc_bucket_spinlocks);
+
+void free_bucket_spinlocks(spinlock_t *locks)
+{
+	kvfree(locks);
+}
+EXPORT_SYMBOL(free_bucket_spinlocks);