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, 90 insertions, 0 deletions

diff --git a/lib/crypto/utils.c b/lib/crypto/utils.c
new file mode 100644
index 000000000..dec381d5e
--- /dev/null
+++ b/lib/crypto/utils.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Crypto library utility functions
+ *
+ * Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au>
+ */
+
+#include <crypto/utils.h>
+#include <linux/export.h>
+#include <linux/module.h>
+#include <linux/unaligned.h>
+
+/*
+ * XOR @len bytes from @src1 and @src2 together, writing the result to @dst
+ * (which may alias one of the sources).  Don't call this directly; call
+ * crypto_xor() or crypto_xor_cpy() instead.
+ */
+void __crypto_xor(u8 *dst, const u8 *src1, const u8 *src2, unsigned int len)
+{
+	int relalign = 0;
+
+	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) {
+		int size = sizeof(unsigned long);
+		int d = (((unsigned long)dst ^ (unsigned long)src1) |
+			 ((unsigned long)dst ^ (unsigned long)src2)) &
+			(size - 1);
+
+		relalign = d ? 1 << __ffs(d) : size;
+
+		/*
+		 * If we care about alignment, process as many bytes as
+		 * needed to advance dst and src to values whose alignments
+		 * equal their relative alignment. This will allow us to
+		 * process the remainder of the input using optimal strides.
+		 */
+		while (((unsigned long)dst & (relalign - 1)) && len > 0) {
+			*dst++ = *src1++ ^ *src2++;
+			len--;
+		}
+	}
+
+	while (IS_ENABLED(CONFIG_64BIT) && len >= 8 && !(relalign & 7)) {
+		if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) {
+			u64 l = get_unaligned((u64 *)src1) ^
+				get_unaligned((u64 *)src2);
+			put_unaligned(l, (u64 *)dst);
+		} else {
+			*(u64 *)dst = *(u64 *)src1 ^ *(u64 *)src2;
+		}
+		dst += 8;
+		src1 += 8;
+		src2 += 8;
+		len -= 8;
+	}
+
+	while (len >= 4 && !(relalign & 3)) {
+		if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) {
+			u32 l = get_unaligned((u32 *)src1) ^
+				get_unaligned((u32 *)src2);
+			put_unaligned(l, (u32 *)dst);
+		} else {
+			*(u32 *)dst = *(u32 *)src1 ^ *(u32 *)src2;
+		}
+		dst += 4;
+		src1 += 4;
+		src2 += 4;
+		len -= 4;
+	}
+
+	while (len >= 2 && !(relalign & 1)) {
+		if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) {
+			u16 l = get_unaligned((u16 *)src1) ^
+				get_unaligned((u16 *)src2);
+			put_unaligned(l, (u16 *)dst);
+		} else {
+			*(u16 *)dst = *(u16 *)src1 ^ *(u16 *)src2;
+		}
+		dst += 2;
+		src1 += 2;
+		src2 += 2;
+		len -= 2;
+	}
+
+	while (len--)
+		*dst++ = *src1++ ^ *src2++;
+}
+EXPORT_SYMBOL_GPL(__crypto_xor);
+
+MODULE_DESCRIPTION("Crypto library utility functions");
+MODULE_LICENSE("GPL");