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, 68 insertions, 0 deletions

diff --git a/lib/hweight.c b/lib/hweight.c
new file mode 100644
index 000000000..0dfcafc3f
--- /dev/null
+++ b/lib/hweight.c
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/export.h>
+#include <linux/bitops.h>
+#include <asm/types.h>
+
+/**
+ * DOC: __sw_hweightN - returns the hamming weight of a N-bit word
+ * @w: the word to weigh
+ *
+ * The Hamming Weight of a number is the total number of bits set in it.
+ */
+
+unsigned int __sw_hweight32(unsigned int w)
+{
+#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER
+	w -= (w >> 1) & 0x55555555;
+	w =  (w & 0x33333333) + ((w >> 2) & 0x33333333);
+	w =  (w + (w >> 4)) & 0x0f0f0f0f;
+	return (w * 0x01010101) >> 24;
+#else
+	unsigned int res = w - ((w >> 1) & 0x55555555);
+	res = (res & 0x33333333) + ((res >> 2) & 0x33333333);
+	res = (res + (res >> 4)) & 0x0F0F0F0F;
+	res = res + (res >> 8);
+	return (res + (res >> 16)) & 0x000000FF;
+#endif
+}
+EXPORT_SYMBOL(__sw_hweight32);
+
+unsigned int __sw_hweight16(unsigned int w)
+{
+	unsigned int res = w - ((w >> 1) & 0x5555);
+	res = (res & 0x3333) + ((res >> 2) & 0x3333);
+	res = (res + (res >> 4)) & 0x0F0F;
+	return (res + (res >> 8)) & 0x00FF;
+}
+EXPORT_SYMBOL(__sw_hweight16);
+
+unsigned int __sw_hweight8(unsigned int w)
+{
+	unsigned int res = w - ((w >> 1) & 0x55);
+	res = (res & 0x33) + ((res >> 2) & 0x33);
+	return (res + (res >> 4)) & 0x0F;
+}
+EXPORT_SYMBOL(__sw_hweight8);
+
+unsigned long __sw_hweight64(__u64 w)
+{
+#if BITS_PER_LONG == 32
+	return __sw_hweight32((unsigned int)(w >> 32)) +
+	       __sw_hweight32((unsigned int)w);
+#elif BITS_PER_LONG == 64
+#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER
+	w -= (w >> 1) & 0x5555555555555555ul;
+	w =  (w & 0x3333333333333333ul) + ((w >> 2) & 0x3333333333333333ul);
+	w =  (w + (w >> 4)) & 0x0f0f0f0f0f0f0f0ful;
+	return (w * 0x0101010101010101ul) >> 56;
+#else
+	__u64 res = w - ((w >> 1) & 0x5555555555555555ul);
+	res = (res & 0x3333333333333333ul) + ((res >> 2) & 0x3333333333333333ul);
+	res = (res + (res >> 4)) & 0x0F0F0F0F0F0F0F0Ful;
+	res = res + (res >> 8);
+	res = res + (res >> 16);
+	return (res + (res >> 32)) & 0x00000000000000FFul;
+#endif
+#endif
+}
+EXPORT_SYMBOL(__sw_hweight64);