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, 121 insertions, 0 deletions

diff --git a/samples/bpf/xdp_sample.bpf.h b/samples/bpf/xdp_sample.bpf.h
new file mode 100644
index 000000000..fecc41c5d
--- /dev/null
+++ b/samples/bpf/xdp_sample.bpf.h
@@ -0,0 +1,121 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef _XDP_SAMPLE_BPF_H
+#define _XDP_SAMPLE_BPF_H
+
+#include "vmlinux.h"
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include <bpf/bpf_helpers.h>
+
+#include "net_shared.h"
+#include "xdp_sample_shared.h"
+
+#define EINVAL 22
+#define ENETDOWN 100
+#define EMSGSIZE 90
+#define EOPNOTSUPP 95
+#define ENOSPC 28
+
+typedef struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(map_flags, BPF_F_MMAPABLE);
+	__type(key, unsigned int);
+	__type(value, struct datarec);
+} array_map;
+
+extern array_map rx_cnt;
+extern const volatile int nr_cpus;
+
+enum {
+	XDP_REDIRECT_SUCCESS = 0,
+	XDP_REDIRECT_ERROR = 1
+};
+
+static __always_inline void swap_src_dst_mac(void *data)
+{
+	unsigned short *p = data;
+	unsigned short dst[3];
+
+	dst[0] = p[0];
+	dst[1] = p[1];
+	dst[2] = p[2];
+	p[0] = p[3];
+	p[1] = p[4];
+	p[2] = p[5];
+	p[3] = dst[0];
+	p[4] = dst[1];
+	p[5] = dst[2];
+}
+
+/*
+ * Note: including linux/compiler.h or linux/kernel.h for the macros below
+ * conflicts with vmlinux.h include in BPF files, so we define them here.
+ *
+ * Following functions are taken from kernel sources and
+ * break aliasing rules in their original form.
+ *
+ * While kernel is compiled with -fno-strict-aliasing,
+ * perf uses -Wstrict-aliasing=3 which makes build fail
+ * under gcc 4.4.
+ *
+ * Using extra __may_alias__ type to allow aliasing
+ * in this case.
+ */
+typedef __u8  __attribute__((__may_alias__))  __u8_alias_t;
+typedef __u16 __attribute__((__may_alias__)) __u16_alias_t;
+typedef __u32 __attribute__((__may_alias__)) __u32_alias_t;
+typedef __u64 __attribute__((__may_alias__)) __u64_alias_t;
+
+static __always_inline void __read_once_size(const volatile void *p, void *res, int size)
+{
+	switch (size) {
+	case 1: *(__u8_alias_t  *) res = *(volatile __u8_alias_t  *) p; break;
+	case 2: *(__u16_alias_t *) res = *(volatile __u16_alias_t *) p; break;
+	case 4: *(__u32_alias_t *) res = *(volatile __u32_alias_t *) p; break;
+	case 8: *(__u64_alias_t *) res = *(volatile __u64_alias_t *) p; break;
+	default:
+		asm volatile ("" : : : "memory");
+		__builtin_memcpy((void *)res, (const void *)p, size);
+		asm volatile ("" : : : "memory");
+	}
+}
+
+static __always_inline void __write_once_size(volatile void *p, void *res, int size)
+{
+	switch (size) {
+	case 1: *(volatile  __u8_alias_t *) p = *(__u8_alias_t  *) res; break;
+	case 2: *(volatile __u16_alias_t *) p = *(__u16_alias_t *) res; break;
+	case 4: *(volatile __u32_alias_t *) p = *(__u32_alias_t *) res; break;
+	case 8: *(volatile __u64_alias_t *) p = *(__u64_alias_t *) res; break;
+	default:
+		asm volatile ("" : : : "memory");
+		__builtin_memcpy((void *)p, (const void *)res, size);
+		asm volatile ("" : : : "memory");
+	}
+}
+
+#define READ_ONCE(x)					\
+({							\
+	union { typeof(x) __val; char __c[1]; } __u =	\
+		{ .__c = { 0 } };			\
+	__read_once_size(&(x), __u.__c, sizeof(x));	\
+	__u.__val;					\
+})
+
+#define WRITE_ONCE(x, val)				\
+({							\
+	union { typeof(x) __val; char __c[1]; } __u =	\
+		{ .__val = (val) }; 			\
+	__write_once_size(&(x), __u.__c, sizeof(x));	\
+	__u.__val;					\
+})
+
+/* Add a value using relaxed read and relaxed write. Less expensive than
+ * fetch_add when there is no write concurrency.
+ */
+#define NO_TEAR_ADD(x, val) WRITE_ONCE((x), READ_ONCE(x) + (val))
+#define NO_TEAR_INC(x) NO_TEAR_ADD((x), 1)
+
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+
+#endif