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, 127 insertions, 0 deletions

diff --git a/tools/perf/util/sample.c b/tools/perf/util/sample.c
new file mode 100644
index 000000000..cf7332932
--- /dev/null
+++ b/tools/perf/util/sample.c
@@ -0,0 +1,127 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include "sample.h"
+#include "debug.h"
+#include "thread.h"
+#include <elf.h>
+#ifndef EM_CSKY
+#define EM_CSKY		252
+#endif
+#ifndef EM_LOONGARCH
+#define EM_LOONGARCH	258
+#endif
+#include <linux/zalloc.h>
+#include <stdlib.h>
+#include <string.h>
+#include "../../arch/x86/include/asm/insn.h"
+
+void perf_sample__init(struct perf_sample *sample, bool all)
+{
+	if (all) {
+		memset(sample, 0, sizeof(*sample));
+	} else {
+		sample->evsel = NULL;
+		sample->user_regs = NULL;
+		sample->intr_regs = NULL;
+		sample->merged_callchain = false;
+		sample->callchain = NULL;
+	}
+}
+
+void perf_sample__exit(struct perf_sample *sample)
+{
+	zfree(&sample->user_regs);
+	zfree(&sample->intr_regs);
+	if (sample->merged_callchain) {
+		zfree(&sample->callchain);
+		sample->merged_callchain = false;
+	}
+}
+
+struct regs_dump *perf_sample__user_regs(struct perf_sample *sample)
+{
+	if (!sample->user_regs) {
+		sample->user_regs = zalloc(sizeof(*sample->user_regs));
+		if (!sample->user_regs)
+			pr_err("Failure to allocate sample user_regs");
+	}
+	return sample->user_regs;
+}
+
+
+struct regs_dump *perf_sample__intr_regs(struct perf_sample *sample)
+{
+	if (!sample->intr_regs) {
+		sample->intr_regs = zalloc(sizeof(*sample->intr_regs));
+		if (!sample->intr_regs)
+			pr_err("Failure to allocate sample intr_regs");
+	}
+	return sample->intr_regs;
+}
+
+static int elf_machine_max_instruction_length(uint16_t e_machine)
+{
+	switch (e_machine) {
+	/* Fixed 4-byte (32-bit) architectures */
+	case EM_AARCH64:
+	case EM_PPC:
+	case EM_PPC64:
+	case EM_MIPS:
+	case EM_SPARC:
+	case EM_SPARCV9:
+	case EM_ALPHA:
+	case EM_LOONGARCH:
+	case EM_PARISC:
+	case EM_SH:
+		return 4;
+
+	/* Variable length or mixed-mode architectures */
+	case EM_ARM:    /* Variable due to Thumb/Thumb-2 */
+	case EM_RISCV:  /* Variable due to Compressed (C) extension */
+	case EM_CSKY:   /* Variable (16 or 32 bit) */
+	case EM_ARC:    /* Variable (ARCompact) */
+		return 4;
+	case EM_S390:   /* Variable (2, 4, or 6 bytes) */
+		return 6;
+	case EM_68K:
+		return 10;
+	case EM_386:
+	case EM_X86_64:
+		return 15;
+	case EM_XTENSA: /* Variable (FLIX) */
+		return 16;
+	default:
+		return MAX_INSN;
+	}
+}
+
+void perf_sample__fetch_insn(struct perf_sample *sample,
+			     struct thread *thread,
+			     struct machine *machine)
+{
+	int ret, len;
+	bool is64bit = false;
+	uint16_t e_machine;
+
+	if (!sample->ip || sample->insn_len != 0)
+		return;
+
+	e_machine = thread__e_machine(thread, machine, /*e_flags=*/NULL);
+	len = elf_machine_max_instruction_length(e_machine);
+	len = thread__memcpy(thread, machine, sample->insn,
+			     sample->ip, len,
+			     &is64bit);
+	if (len <= 0)
+		return;
+
+	sample->insn_len = len;
+
+	if (e_machine == EM_386 || e_machine == EM_X86_64) {
+		/* Refine the x86 instruction length with the decoder. */
+		struct insn insn;
+
+		ret = insn_decode(&insn, sample->insn, len,
+				  is64bit ? INSN_MODE_64 : INSN_MODE_32);
+		if (ret >= 0 && insn.length <= len)
+			sample->insn_len = insn.length;
+	}
+}