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, 447 insertions, 0 deletions

diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
new file mode 100644
index 000000000..7f35042be
--- /dev/null
+++ b/tools/perf/util/unwind-libdw.c
@@ -0,0 +1,447 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/compiler.h>
+#include <elfutils/libdw.h>
+#include <elfutils/libdwfl.h>
+#include <inttypes.h>
+#include <errno.h>
+#include "debug.h"
+#include "dso.h"
+#include <dwarf-regs.h>
+#include "unwind.h"
+#include "unwind-libdw.h"
+#include "machine.h"
+#include "map.h"
+#include "symbol.h"
+#include "thread.h"
+#include <linux/types.h>
+#include <linux/zalloc.h>
+#include "event.h"
+#include "perf_regs.h"
+#include "callchain.h"
+#include "util/env.h"
+
+/*
+ * The dwfl thread argument passed to functions like memory_read. Memory has to
+ * be allocated to persist of multiple uses of the dwfl.
+ */
+struct dwfl_ui_thread_info {
+	/* Back link to the dwfl. */
+	Dwfl *dwfl;
+	/* The current unwind info, only 1 is supported. */
+	struct unwind_info *ui;
+};
+
+static char *debuginfo_path;
+
+static int __find_debuginfo(Dwfl_Module *mod __maybe_unused, void **userdata,
+			    const char *modname __maybe_unused, Dwarf_Addr base __maybe_unused,
+			    const char *file_name, const char *debuglink_file __maybe_unused,
+			    GElf_Word debuglink_crc __maybe_unused, char **debuginfo_file_name)
+{
+	const struct dso *dso = *userdata;
+
+	assert(dso);
+	if (dso__symsrc_filename(dso) && strcmp(file_name, dso__symsrc_filename(dso)))
+		*debuginfo_file_name = strdup(dso__symsrc_filename(dso));
+	return -1;
+}
+
+void libdw__invalidate_dwfl(struct maps *maps, void *arg)
+{
+	struct dwfl_ui_thread_info *dwfl_ui_ti = arg;
+
+	if (!dwfl_ui_ti)
+		return;
+
+	assert(dwfl_ui_ti->ui == NULL);
+	maps__set_libdw_addr_space_dwfl(maps, NULL);
+	dwfl_end(dwfl_ui_ti->dwfl);
+	free(dwfl_ui_ti);
+}
+
+static const Dwfl_Callbacks offline_callbacks = {
+	.find_debuginfo		= __find_debuginfo,
+	.debuginfo_path		= &debuginfo_path,
+	.section_address	= dwfl_offline_section_address,
+	// .find_elf is not set as we use dwfl_report_elf() instead.
+};
+
+static int __report_module(struct addr_location *al, u64 ip,
+			    struct unwind_info *ui)
+{
+	Dwfl_Module *mod;
+	struct dso *dso = NULL;
+	Dwarf_Addr base;
+	/*
+	 * Some callers will use al->sym, so we can't just use the
+	 * cheaper thread__find_map() here.
+	 */
+	thread__find_symbol(ui->thread, PERF_RECORD_MISC_USER, ip, al);
+
+	if (al->map)
+		dso = map__dso(al->map);
+
+	if (!dso)
+		return 0;
+
+	/*
+	 * The generated JIT DSO files only map the code segment without
+	 * ELF headers.  Since JIT codes used to be packed in a memory
+	 * segment, calculating the base address using pgoff falls into
+	 * a different code in another DSO.  So just use the map->start
+	 * directly to pick the correct one.
+	 */
+	if (!strncmp(dso__long_name(dso), "/tmp/jitted-", 12))
+		base = map__start(al->map);
+	else
+		base = map__start(al->map) - map__pgoff(al->map);
+
+	mod = dwfl_addrmodule(ui->dwfl, ip);
+	if (mod) {
+		Dwarf_Addr s;
+
+		dwfl_module_info(mod, NULL, &s, NULL, NULL, NULL, NULL, NULL);
+		if (s != base)
+			mod = NULL;
+	}
+
+	if (!mod) {
+		char filename[PATH_MAX];
+
+		__symbol__join_symfs(filename, sizeof(filename), dso__long_name(dso));
+		/* Don't hang up on device files like /dev/dri/renderD128. */
+		if (is_regular_file(filename)) {
+			mod = dwfl_report_elf(ui->dwfl, dso__short_name(dso), filename, -1,
+					      base, false);
+		}
+	}
+	if (!mod) {
+		char filename[PATH_MAX];
+
+		if (dso__build_id_filename(dso, filename, sizeof(filename), false))
+			mod = dwfl_report_elf(ui->dwfl, dso__short_name(dso), filename, -1,
+					      base, false);
+	}
+
+	if (mod) {
+		void **userdatap;
+
+		dwfl_module_info(mod, &userdatap, NULL, NULL, NULL, NULL, NULL, NULL);
+		*userdatap = dso;
+	}
+
+	return mod && dwfl_addrmodule(ui->dwfl, ip) == mod ? 0 : -1;
+}
+
+static int report_module(u64 ip, struct unwind_info *ui)
+{
+	struct addr_location al;
+	int res;
+
+	addr_location__init(&al);
+	res = __report_module(&al, ip, ui);
+	addr_location__exit(&al);
+	return res;
+}
+
+/*
+ * Store all entries within entries array,
+ * we will process it after we finish unwind.
+ */
+static int entry(u64 ip, struct unwind_info *ui)
+
+{
+	struct unwind_entry *e = &ui->entries[ui->idx++];
+	struct addr_location al;
+
+	addr_location__init(&al);
+	if (__report_module(&al, ip, ui)) {
+		addr_location__exit(&al);
+		return -1;
+	}
+
+	e->ip	  = ip;
+	e->ms.thread = thread__get(al.thread);
+	e->ms.map = map__get(al.map);
+	e->ms.sym = al.sym;
+
+	pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
+		 al.sym ? al.sym->name : "''",
+		 ip,
+		 al.map ? map__map_ip(al.map, ip) : (u64) 0);
+	addr_location__exit(&al);
+	return 0;
+}
+
+static pid_t next_thread(Dwfl *dwfl, void *arg, void **thread_argp)
+{
+	/* We want only single thread to be processed. */
+	if (*thread_argp != NULL)
+		return 0;
+
+	*thread_argp = arg;
+	return dwfl_pid(dwfl);
+}
+
+static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr,
+			  Dwarf_Word *data)
+{
+	struct addr_location al;
+	ssize_t size;
+	struct dso *dso;
+
+	addr_location__init(&al);
+	if (!thread__find_map(ui->thread, PERF_RECORD_MISC_USER, addr, &al)) {
+		pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
+		goto out_fail;
+	}
+	dso = map__dso(al.map);
+	if (!dso)
+		goto out_fail;
+
+	size = dso__data_read_addr(dso, al.map, ui->machine, addr, (u8 *) data, sizeof(*data));
+
+	addr_location__exit(&al);
+	return !(size == sizeof(*data));
+out_fail:
+	addr_location__exit(&al);
+	return -1;
+}
+
+static bool memory_read(Dwfl *dwfl __maybe_unused, Dwarf_Addr addr, Dwarf_Word *result,
+			void *arg)
+{
+	struct dwfl_ui_thread_info *dwfl_ui_ti = arg;
+	struct unwind_info *ui = dwfl_ui_ti->ui;
+	struct stack_dump *stack = &ui->sample->user_stack;
+	u64 start, end;
+	int offset;
+	int ret;
+
+	if (!ui->sample->user_regs)
+		return false;
+
+	ret = perf_reg_value(&start, ui->sample->user_regs,
+			     perf_arch_reg_sp(ui->e_machine));
+	if (ret)
+		return false;
+
+	end = start + stack->size;
+
+	/* Check overflow. */
+	if (addr + sizeof(Dwarf_Word) < addr)
+		return false;
+
+	if (addr < start || addr + sizeof(Dwarf_Word) > end) {
+		ret = access_dso_mem(ui, addr, result);
+		if (ret) {
+			pr_debug("unwind: access_mem 0x%" PRIx64 " not inside range"
+				 " 0x%" PRIx64 "-0x%" PRIx64 "\n",
+				addr, start, end);
+			return false;
+		}
+		return true;
+	}
+
+	offset  = addr - start;
+	*result = *(Dwarf_Word *)&stack->data[offset];
+	pr_debug("unwind: access_mem addr 0x%" PRIx64 ", val %lx, offset %d\n",
+		 addr, (unsigned long)*result, offset);
+	return true;
+}
+
+static bool libdw_set_initial_registers(Dwfl_Thread *thread, void *arg)
+{
+	struct dwfl_ui_thread_info *dwfl_ui_ti = arg;
+	struct unwind_info *ui = dwfl_ui_ti->ui;
+	struct regs_dump *user_regs = perf_sample__user_regs(ui->sample);
+	Dwarf_Word *dwarf_regs;
+	int max_dwarf_reg = 0;
+	bool ret;
+	uint16_t e_machine = ui->e_machine;
+	int e_flags = ui->e_flags;
+	uint64_t ip_perf_reg = perf_arch_reg_ip(e_machine);
+	Dwarf_Word val = 0;
+
+
+	/*
+	 * For every possible perf register in the bitmap determine the dwarf
+	 * register and use to compute the max.
+	 */
+	for (int perf_reg = 0; perf_reg < 64; perf_reg++) {
+		if (user_regs->mask & (1ULL << perf_reg)) {
+			int dwarf_reg =
+				get_dwarf_regnum_for_perf_regnum(perf_reg, e_machine,
+								 e_flags,
+								 /*only_libdw_supported=*/true);
+			if (dwarf_reg > max_dwarf_reg)
+				max_dwarf_reg = dwarf_reg;
+		}
+	}
+
+	dwarf_regs = calloc(max_dwarf_reg + 1, sizeof(*dwarf_regs));
+	if (!dwarf_regs)
+		return false;
+
+	for (int perf_reg = 0; perf_reg < 64; perf_reg++) {
+		if (user_regs->mask & (1ULL << perf_reg)) {
+			int dwarf_reg =
+				get_dwarf_regnum_for_perf_regnum(perf_reg, e_machine,
+								 e_flags,
+								 /*only_libdw_supported=*/true);
+			if (dwarf_reg >= 0) {
+				val = 0;
+				if (perf_reg_value(&val, user_regs, perf_reg) == 0)
+					dwarf_regs[dwarf_reg] = val;
+			}
+		}
+	}
+	if (perf_reg_value(&val, user_regs, ip_perf_reg) == 0)
+		dwfl_thread_state_register_pc(thread, val);
+
+	ret = dwfl_thread_state_registers(thread, 0, max_dwarf_reg + 1, dwarf_regs);
+	free(dwarf_regs);
+	return ret;
+}
+
+static const Dwfl_Thread_Callbacks callbacks = {
+	.next_thread           = next_thread,
+	.memory_read           = memory_read,
+	.set_initial_registers = libdw_set_initial_registers,
+};
+
+static int
+frame_callback(Dwfl_Frame *state, void *arg)
+{
+	struct unwind_info *ui = arg;
+	Dwarf_Addr pc;
+	bool isactivation;
+
+	if (!dwfl_frame_pc(state, &pc, NULL)) {
+		if (!ui->best_effort)
+			pr_err("%s", dwfl_errmsg(-1));
+		return DWARF_CB_ABORT;
+	}
+
+	// report the module before we query for isactivation
+	report_module(pc, ui);
+
+	if (!dwfl_frame_pc(state, &pc, &isactivation)) {
+		if (!ui->best_effort)
+			pr_err("%s", dwfl_errmsg(-1));
+		return DWARF_CB_ABORT;
+	}
+
+	if (!isactivation)
+		--pc;
+
+	return entry(pc, ui) || !(--ui->max_stack) ?
+	       DWARF_CB_ABORT : DWARF_CB_OK;
+}
+
+int libdw__get_entries(unwind_entry_cb_t cb, void *arg,
+			struct thread *thread,
+			struct perf_sample *data,
+			int max_stack,
+			bool best_effort)
+{
+	struct maps *maps = thread__maps(thread);
+	struct machine *machine = maps__machine(maps);
+	uint32_t e_flags = 0;
+	uint16_t e_machine = thread__e_machine(thread, machine, &e_flags);
+	struct dwfl_ui_thread_info *dwfl_ui_ti;
+	static struct unwind_info *ui;
+	Dwfl *dwfl;
+	Dwarf_Word ip;
+	int err = -EINVAL, i, entries;
+
+	if (!data->user_regs || !data->user_regs->regs)
+		return 0;
+
+	ui = zalloc(sizeof(*ui) + sizeof(ui->entries[0]) * max_stack);
+	if (!ui)
+		return -ENOMEM;
+
+	*ui = (struct unwind_info){
+		.sample		= data,
+		.thread		= thread,
+		.machine	= machine,
+		.cb		= cb,
+		.arg		= arg,
+		.max_stack	= max_stack,
+		.e_machine	= e_machine,
+		.e_flags	= e_flags,
+		.best_effort    = best_effort
+	};
+
+	dwfl_ui_ti = maps__libdw_addr_space_dwfl(maps);
+	if (dwfl_ui_ti) {
+		dwfl = dwfl_ui_ti->dwfl;
+	} else {
+		dwfl_ui_ti = zalloc(sizeof(*dwfl_ui_ti));
+		dwfl = dwfl_begin(&offline_callbacks);
+		if (!dwfl)
+			goto out;
+
+		dwfl_ui_ti->dwfl = dwfl;
+		maps__set_libdw_addr_space_dwfl(maps, dwfl_ui_ti);
+	}
+	assert(dwfl_ui_ti->ui == NULL);
+	assert(dwfl_ui_ti->dwfl == dwfl);
+	assert(dwfl_ui_ti == maps__libdw_addr_space_dwfl(maps));
+	dwfl_ui_ti->ui = ui;
+	ui->dwfl = dwfl;
+
+	err = perf_reg_value(&ip, data->user_regs, perf_arch_reg_ip(e_machine));
+	if (err)
+		goto out;
+
+	err = report_module(ip, ui);
+	if (err)
+		goto out;
+
+	dwfl_attach_state(dwfl, /*elf=*/NULL, thread__tid(thread), &callbacks,
+			  /* Dwfl thread function argument*/dwfl_ui_ti);
+	// Ignore thread already attached error.
+
+	err = dwfl_getthread_frames(dwfl, thread__tid(thread), frame_callback,
+				    /* Dwfl frame function argument*/ui);
+
+	if (err && ui->max_stack != max_stack)
+		err = 0;
+
+	/*
+	 * Display what we got based on the order setup.
+	 */
+	for (i = 0; i < ui->idx && !err; i++) {
+		int j = i;
+
+		if (callchain_param.order == ORDER_CALLER)
+			j = ui->idx - i - 1;
+
+		err = ui->entries[j].ip ? ui->cb(&ui->entries[j], ui->arg) : 0;
+	}
+
+ out:
+	if (err)
+		pr_debug("unwind: failed with '%s'\n", dwfl_errmsg(-1));
+
+	for (i = 0; i < ui->idx; i++)
+		map_symbol__exit(&ui->entries[i].ms);
+
+	dwfl_ui_ti->ui = NULL;
+	entries = (int)ui->idx;
+	free(ui);
+	/*
+	 * Unwinder return contract:
+	 *  > 0 : unwinding succeeded (stops fallback). If we found frames but hit an error
+	 *        (e.g. truncated stack), report success to preserve existing frames.
+	 *    0 : unwinding failed without yielding frames. Ignore non-fatal errors
+	 *        (e.g. missing debug info, DWARF corruption) to allow fallback unwinder or
+	 *        kernel callchain resolution to proceed.
+	 *  < 0 : fatal error (e.g. -ENOMEM). Aborts unwinding entirely.
+	 */
+	if (err)
+		return (err == -ENOMEM) ? -ENOMEM : (entries > 0 ? 1 : 0);
+	return entries;
+}