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, 119 insertions, 0 deletions

diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
new file mode 100644
index 000000000..b06e10a11
--- /dev/null
+++ b/tools/perf/util/top.c
@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Refactored from builtin-top.c, see that files for further copyright notes.
+ */
+
+#include "event.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "parse-events.h"
+#include "symbol.h"
+#include "top.h"
+#include "util.h"
+#include <inttypes.h>
+
+#define SNPRINTF(buf, size, fmt, args...) \
+({ \
+	size_t r = snprintf(buf, size, fmt, ## args); \
+	r > size ?  size : r; \
+})
+
+size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size)
+{
+	float samples_per_sec;
+	float ksamples_per_sec;
+	float esamples_percent;
+	struct record_opts *opts = &top->record_opts;
+	struct target *target = &opts->target;
+	size_t ret = 0;
+	int nr_cpus;
+
+	if (top->samples) {
+		samples_per_sec = top->samples / top->delay_secs;
+		ksamples_per_sec = top->kernel_samples / top->delay_secs;
+		esamples_percent = (100.0 * top->exact_samples) / top->samples;
+	} else {
+		samples_per_sec = ksamples_per_sec = esamples_percent = 0.0;
+	}
+
+	if (!perf_guest) {
+		float ksamples_percent = 0.0;
+
+		if (samples_per_sec)
+			ksamples_percent = (100.0 * ksamples_per_sec) /
+							samples_per_sec;
+		ret = SNPRINTF(bf, size,
+			       "   PerfTop:%8.0f irqs/sec  kernel:%4.1f%%"
+			       "  exact: %4.1f%% lost: %" PRIu64 "/%" PRIu64 " drop: %" PRIu64 "/%" PRIu64 " [",
+			       samples_per_sec, ksamples_percent, esamples_percent,
+			       top->lost, top->lost_total, top->drop, top->drop_total);
+	} else {
+		float us_samples_per_sec = top->us_samples / top->delay_secs;
+		float guest_kernel_samples_per_sec = top->guest_kernel_samples / top->delay_secs;
+		float guest_us_samples_per_sec = top->guest_us_samples / top->delay_secs;
+
+		ret = SNPRINTF(bf, size,
+			       "   PerfTop:%8.0f irqs/sec  kernel:%4.1f%% us:%4.1f%%"
+			       " guest kernel:%4.1f%% guest us:%4.1f%%"
+			       " exact: %4.1f%% [", samples_per_sec,
+			       100.0 - (100.0 * ((samples_per_sec - ksamples_per_sec) /
+						 samples_per_sec)),
+			       100.0 - (100.0 * ((samples_per_sec - us_samples_per_sec) /
+						 samples_per_sec)),
+			       100.0 - (100.0 * ((samples_per_sec -
+						  guest_kernel_samples_per_sec) /
+						 samples_per_sec)),
+			       100.0 - (100.0 * ((samples_per_sec -
+						  guest_us_samples_per_sec) /
+						 samples_per_sec)),
+			       esamples_percent);
+	}
+
+	if (top->evlist->core.nr_entries == 1) {
+		struct evsel *first = evlist__first(top->evlist);
+		ret += SNPRINTF(bf + ret, size - ret, "%" PRIu64 "%s ",
+				(uint64_t)first->core.attr.sample_period,
+				opts->freq ? "Hz" : "");
+	}
+
+	ret += SNPRINTF(bf + ret, size - ret, "%s", evsel__name(top->sym_evsel));
+
+	ret += SNPRINTF(bf + ret, size - ret, "], ");
+
+	if (target->pid)
+		ret += SNPRINTF(bf + ret, size - ret, " (target_pid: %s",
+				target->pid);
+	else if (target->tid)
+		ret += SNPRINTF(bf + ret, size - ret, " (target_tid: %s",
+				target->tid);
+	else if (top->uid_str != NULL)
+		ret += SNPRINTF(bf + ret, size - ret, " (uid: %s",
+				top->uid_str);
+	else
+		ret += SNPRINTF(bf + ret, size - ret, " (all");
+
+	nr_cpus = perf_cpu_map__nr(top->evlist->core.user_requested_cpus);
+	if (target->cpu_list)
+		ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)",
+				nr_cpus > 1 ? "s" : "",
+				target->cpu_list);
+	else {
+		if (target->tid)
+			ret += SNPRINTF(bf + ret, size - ret, ")");
+		else
+			ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)",
+					nr_cpus, nr_cpus > 1 ? "s" : "");
+	}
+
+	perf_top__reset_sample_counters(top);
+	return ret;
+}
+
+void perf_top__reset_sample_counters(struct perf_top *top)
+{
+	top->samples = top->us_samples = top->kernel_samples =
+	top->exact_samples = top->guest_kernel_samples =
+	top->guest_us_samples = top->lost = top->drop = 0;
+}