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, 148 insertions, 0 deletions

diff --git a/lib/percpu_test.c b/lib/percpu_test.c
new file mode 100644
index 000000000..ce7124b16
--- /dev/null
+++ b/lib/percpu_test.c
@@ -0,0 +1,148 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/limits.h>
+#include <linux/module.h>
+
+/* validate @native and @pcp counter values match @expected */
+#define CHECK(native, pcp, expected)                                    \
+	do {                                                            \
+		WARN((native) != (expected),                            \
+		     "raw %ld (0x%lx) != expected %lld (0x%llx)",	\
+		     (native), (native),				\
+		     (long long)(expected), (long long)(expected));	\
+		WARN(__this_cpu_read(pcp) != (expected),                \
+		     "pcp %ld (0x%lx) != expected %lld (0x%llx)",	\
+		     __this_cpu_read(pcp), __this_cpu_read(pcp),	\
+		     (long long)(expected), (long long)(expected));	\
+	} while (0)
+
+static DEFINE_PER_CPU(long, long_counter);
+static DEFINE_PER_CPU(unsigned long, ulong_counter);
+
+static int __init percpu_test_init(void)
+{
+	/*
+	 * volatile prevents compiler from optimizing it uses, otherwise the
+	 * +ul_one/-ul_one below would replace with inc/dec instructions.
+	 */
+	volatile unsigned int ui_one = 1;
+	unsigned long long ull = 0;
+	unsigned long ul = 0;
+	long l = 0;
+
+	pr_info("percpu test start\n");
+
+	preempt_disable();
+
+	l += -1;
+	__this_cpu_add(long_counter, -1);
+	CHECK(l, long_counter, -1);
+
+	l += 1;
+	__this_cpu_add(long_counter, 1);
+	CHECK(l, long_counter, 0);
+
+	ul = 0;
+	__this_cpu_write(ulong_counter, 0);
+
+	ul += 1UL;
+	__this_cpu_add(ulong_counter, 1UL);
+	CHECK(ul, ulong_counter, 1);
+
+	ul += -1UL;
+	__this_cpu_add(ulong_counter, -1UL);
+	CHECK(ul, ulong_counter, 0);
+
+	ul += -(unsigned long)1;
+	__this_cpu_add(ulong_counter, -(unsigned long)1);
+	CHECK(ul, ulong_counter, -1);
+
+	ul = 0;
+	__this_cpu_write(ulong_counter, 0);
+
+	ul -= 1;
+	__this_cpu_dec(ulong_counter);
+	CHECK(ul, ulong_counter, -1);
+	CHECK(ul, ulong_counter, ULONG_MAX);
+
+	l += -ui_one;
+	__this_cpu_add(long_counter, -ui_one);
+	CHECK(l, long_counter, 0xffffffff);
+
+	l += ui_one;
+	__this_cpu_add(long_counter, ui_one);
+	CHECK(l, long_counter, (long)0x100000000LL);
+
+
+	l = 0;
+	__this_cpu_write(long_counter, 0);
+
+	l -= ui_one;
+	__this_cpu_sub(long_counter, ui_one);
+	CHECK(l, long_counter, -1);
+
+	l = 0;
+	__this_cpu_write(long_counter, 0);
+
+	l += ui_one;
+	__this_cpu_add(long_counter, ui_one);
+	CHECK(l, long_counter, 1);
+
+	l += -ui_one;
+	__this_cpu_add(long_counter, -ui_one);
+	CHECK(l, long_counter, (long)0x100000000LL);
+
+	l = 0;
+	__this_cpu_write(long_counter, 0);
+
+	l -= ui_one;
+	this_cpu_sub(long_counter, ui_one);
+	CHECK(l, long_counter, -1);
+	CHECK(l, long_counter, ULONG_MAX);
+
+	ul = 0;
+	__this_cpu_write(ulong_counter, 0);
+
+	ul += ui_one;
+	__this_cpu_add(ulong_counter, ui_one);
+	CHECK(ul, ulong_counter, 1);
+
+	ul = 0;
+	__this_cpu_write(ulong_counter, 0);
+
+	ul -= ui_one;
+	__this_cpu_sub(ulong_counter, ui_one);
+	CHECK(ul, ulong_counter, -1);
+	CHECK(ul, ulong_counter, ULONG_MAX);
+
+	ul = ull = 0;
+	__this_cpu_write(ulong_counter, 0);
+
+	ul = ull += UINT_MAX;
+	__this_cpu_add(ulong_counter, ull);
+	CHECK(ul, ulong_counter, UINT_MAX);
+
+	ul = 3;
+	__this_cpu_write(ulong_counter, 3);
+
+	ul = this_cpu_sub_return(ulong_counter, ui_one);
+	CHECK(ul, ulong_counter, 2);
+
+	ul = __this_cpu_sub_return(ulong_counter, ui_one);
+	CHECK(ul, ulong_counter, 1);
+
+	preempt_enable();
+
+	pr_info("percpu test done\n");
+	return -EAGAIN;  /* Fail will directly unload the module */
+}
+
+static void __exit percpu_test_exit(void)
+{
+}
+
+module_init(percpu_test_init)
+module_exit(percpu_test_exit)
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Greg Thelen");
+MODULE_DESCRIPTION("percpu operations test");