kbuild: rust: keep Rust objects out of Clang LTO with inline helpersgrafted

Under `CONFIG_LTO_CLANG` + `CONFIG_RUST_INLINE_HELPERS`, one may hit
`objtool` errors such as:

    vmlinux.o: error: objtool: _R..._3Gsp4boot+0xd6a:
    can't find jump dest instruction at .text._R..._3Gsp4boot+0x1dfd

The reason is that in such builds, the Clang invocation that compiles
the combined Rust plus helpers bitcode emits LLVM bitcode (again) --
the final code generation happens in the linker's LTO step, which the
`-mllvm` trap options passed to Clang do not reach.

This, in turn, means that unreachable traps are missing, and the
impossible paths do not merely fallthrough to the next symbol, but past
the end of their own section, since LTO builds place each function in
its own section.

Thus filter `CC_FLAGS_LTO` out of the Clang invocation, so that it always
emits machine code directly, with the traps in place.

Assisted-by: LLM
Cc: Gary Guo <gary@garyguo.net>
Cc: Boqun Feng <boqun@kernel.org>
Cc: Alice Ryhl <aliceryhl@google.com>
Cc: Matthew Maurer <mmaurer@google.com>
Cc: Josh Poimboeuf <jpoimboe@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: stable@vger.kernel.org
Fixes: 3a2486cc1da5 ("kbuild: rust: provide an option to inline C helpers into Rust")
Acked-by: Gary Guo <gary@garyguo.net>
Link: https://patch.msgid.link/20260816133233.197500-2-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>

1 files changed, 83 insertions, 0 deletions

diff --git a/fs/unicode/utf8n.h b/fs/unicode/utf8n.h
new file mode 100644
index 000000000..fc703aa4b
--- /dev/null
+++ b/fs/unicode/utf8n.h
@@ -0,0 +1,83 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2014 SGI.
+ * All rights reserved.
+ */
+
+#ifndef UTF8NORM_H
+#define UTF8NORM_H
+
+#include <linux/types.h>
+#include <linux/export.h>
+#include <linux/string.h>
+#include <linux/module.h>
+#include <linux/unicode.h>
+
+int utf8version_is_supported(const struct unicode_map *um, unsigned int version);
+
+/*
+ * Determine the length of the normalized from of the string,
+ * excluding any terminating NULL byte.
+ * Returns 0 if only ignorable code points are present.
+ * Returns -1 if the input is not valid UTF-8.
+ */
+ssize_t utf8nlen(const struct unicode_map *um, enum utf8_normalization n,
+		const char *s, size_t len);
+
+/* Needed in struct utf8cursor below. */
+#define UTF8HANGULLEAF	(12)
+
+/*
+ * Cursor structure used by the normalizer.
+ */
+struct utf8cursor {
+	const struct unicode_map *um;
+	enum utf8_normalization n;
+	const char	*s;
+	const char	*p;
+	const char	*ss;
+	const char	*sp;
+	unsigned int	len;
+	unsigned int	slen;
+	short int	ccc;
+	short int	nccc;
+	unsigned char	hangul[UTF8HANGULLEAF];
+};
+
+/*
+ * Initialize a utf8cursor to normalize a string.
+ * Returns 0 on success.
+ * Returns -1 on failure.
+ */
+int utf8ncursor(struct utf8cursor *u8c, const struct unicode_map *um,
+		enum utf8_normalization n, const char *s, size_t len);
+
+/*
+ * Get the next byte in the normalization.
+ * Returns a value > 0 && < 256 on success.
+ * Returns 0 when the end of the normalization is reached.
+ * Returns -1 if the string being normalized is not valid UTF-8.
+ */
+extern int utf8byte(struct utf8cursor *u8c);
+
+struct utf8data {
+	unsigned int maxage;
+	unsigned int offset;
+};
+
+struct utf8data_table {
+	const unsigned int *utf8agetab;
+	int utf8agetab_size;
+
+	const struct utf8data *utf8nfdicfdata;
+	int utf8nfdicfdata_size;
+
+	const struct utf8data *utf8nfdidata;
+	int utf8nfdidata_size;
+
+	const unsigned char *utf8data;
+};
+
+extern const struct utf8data_table utf8_data_table;
+
+#endif /* UTF8NORM_H */