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, 188 insertions, 0 deletions

diff --git a/tools/perf/bench/syscall.c b/tools/perf/bench/syscall.c
new file mode 100644
index 000000000..e7dc216f7
--- /dev/null
+++ b/tools/perf/bench/syscall.c
@@ -0,0 +1,188 @@
+/*
+ *
+ * syscall.c
+ *
+ * syscall: Benchmark for system call performance
+ */
+#include "../perf.h"
+#include "../util/util.h"
+#include <subcmd/parse-options.h>
+#include "../builtin.h"
+#include "bench.h"
+
+#include <stdio.h>
+#include <sys/time.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <stdlib.h>
+
+#ifndef __NR_fork
+#define __NR_fork -1
+#endif
+
+static	int loops;
+
+static const struct option options[] = {
+	OPT_INTEGER('l', "loop",	&loops,		"Specify number of loops"),
+	OPT_END()
+};
+
+static const char * const bench_syscall_usage[] = {
+	"perf bench syscall <options>",
+	NULL
+};
+
+static void test_fork(void)
+{
+	pid_t pid = fork();
+
+	if (pid < 0) {
+		fprintf(stderr, "fork failed\n");
+		exit(1);
+	} else if (pid == 0) {
+		exit(0);
+	} else {
+		if (waitpid(pid, NULL, 0) < 0) {
+			fprintf(stderr, "waitpid failed\n");
+			exit(1);
+		}
+	}
+}
+
+static void test_execve(void)
+{
+	const char *pathname = "/bin/true";
+	char *const argv[] = { (char *)pathname, NULL };
+	pid_t pid = fork();
+
+	if (pid < 0) {
+		fprintf(stderr, "fork failed\n");
+		exit(1);
+	} else if (pid == 0) {
+		execve(pathname, argv, NULL);
+		fprintf(stderr, "execve /bin/true failed\n");
+		exit(1);
+	} else {
+		if (waitpid(pid, NULL, 0) < 0) {
+			fprintf(stderr, "waitpid failed\n");
+			exit(1);
+		}
+	}
+}
+
+static int bench_syscall_common(int argc, const char **argv, int syscall)
+{
+	struct timeval start, stop, diff;
+	unsigned long long result_usec = 0;
+	const char *name = NULL;
+	int i;
+
+	switch (syscall) {
+	case __NR_fork:
+	case __NR_execve:
+		/* Limit default loop to 10000 times to save time */
+		loops = 10000;
+		break;
+	default:
+		loops = 10000000;
+		break;
+	}
+
+	/* Options -l and --loops override default above */
+	argc = parse_options(argc, argv, options, bench_syscall_usage, 0);
+
+	gettimeofday(&start, NULL);
+
+	for (i = 0; i < loops; i++) {
+		switch (syscall) {
+		case __NR_getppid:
+			getppid();
+			break;
+		case __NR_getpgid:
+			getpgid(0);
+			break;
+		case __NR_fork:
+			test_fork();
+			break;
+		case __NR_execve:
+			test_execve();
+		default:
+			break;
+		}
+	}
+
+	gettimeofday(&stop, NULL);
+	timersub(&stop, &start, &diff);
+
+	switch (syscall) {
+	case __NR_getppid:
+		name = "getppid()";
+		break;
+	case __NR_getpgid:
+		name = "getpgid()";
+		break;
+	case __NR_fork:
+		name = "fork()";
+		break;
+	case __NR_execve:
+		name = "execve()";
+		break;
+	default:
+		break;
+	}
+
+	switch (bench_format) {
+	case BENCH_FORMAT_DEFAULT:
+		printf("# Executed %'d %s calls\n", loops, name);
+
+		result_usec = diff.tv_sec * 1000000;
+		result_usec += diff.tv_usec;
+
+		printf(" %14s: %lu.%03lu [sec]\n\n", "Total time",
+		       (unsigned long) diff.tv_sec,
+		       (unsigned long) (diff.tv_usec/1000));
+
+		printf(" %14lf usecs/op\n",
+		       (double)result_usec / (double)loops);
+		printf(" %'14d ops/sec\n",
+		       (int)((double)loops /
+			     ((double)result_usec / (double)1000000)));
+		break;
+
+	case BENCH_FORMAT_SIMPLE:
+		printf("%lu.%03lu\n",
+		       (unsigned long) diff.tv_sec,
+		       (unsigned long) (diff.tv_usec / 1000));
+		break;
+
+	default:
+		/* reaching here is something disaster */
+		fprintf(stderr, "Unknown format:%d\n", bench_format);
+		exit(1);
+		break;
+	}
+
+	return 0;
+}
+
+int bench_syscall_basic(int argc, const char **argv)
+{
+	return bench_syscall_common(argc, argv, __NR_getppid);
+}
+
+int bench_syscall_getpgid(int argc, const char **argv)
+{
+	return bench_syscall_common(argc, argv, __NR_getpgid);
+}
+
+int bench_syscall_fork(int argc, const char **argv)
+{
+	return bench_syscall_common(argc, argv, __NR_fork);
+}
+
+int bench_syscall_execve(int argc, const char **argv)
+{
+	return bench_syscall_common(argc, argv, __NR_execve);
+}