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, 143 insertions, 0 deletions

diff --git a/tools/perf/util/lock-contention.c b/tools/perf/util/lock-contention.c
new file mode 100644
index 000000000..119a7206f
--- /dev/null
+++ b/tools/perf/util/lock-contention.c
@@ -0,0 +1,143 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "debug.h"
+#include "env.h"
+#include "lock-contention.h"
+#include "machine.h"
+#include "symbol.h"
+
+#include <limits.h>
+#include <string.h>
+
+#include <linux/hash.h>
+#include <linux/zalloc.h>
+
+#define __lockhashfn(key)	hash_long((unsigned long)key, LOCKHASH_BITS)
+#define lockhashentry(key)	(lockhash_table + __lockhashfn((key)))
+
+struct callstack_filter {
+	struct list_head list;
+	char name[];
+};
+
+static LIST_HEAD(callstack_filters);
+struct hlist_head *lockhash_table;
+
+int parse_call_stack(const struct option *opt __maybe_unused, const char *str,
+		     int unset __maybe_unused)
+{
+	char *s, *tmp, *tok;
+	int ret = 0;
+
+	s = strdup(str);
+	if (s == NULL)
+		return -1;
+
+	for (tok = strtok_r(s, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) {
+		struct callstack_filter *entry;
+
+		entry = malloc(sizeof(*entry) + strlen(tok) + 1);
+		if (entry == NULL) {
+			pr_err("Memory allocation failure\n");
+			free(s);
+			return -1;
+		}
+
+		strcpy(entry->name, tok);
+		list_add_tail(&entry->list, &callstack_filters);
+	}
+
+	free(s);
+	return ret;
+}
+
+bool needs_callstack(void)
+{
+	return !list_empty(&callstack_filters);
+}
+
+struct lock_stat *lock_stat_find(u64 addr)
+{
+	struct hlist_head *entry = lockhashentry(addr);
+	struct lock_stat *ret;
+
+	hlist_for_each_entry(ret, entry, hash_entry) {
+		if (ret->addr == addr)
+			return ret;
+	}
+	return NULL;
+}
+
+struct lock_stat *lock_stat_findnew(u64 addr, const char *name, int flags)
+{
+	struct hlist_head *entry = lockhashentry(addr);
+	struct lock_stat *ret, *new;
+
+	hlist_for_each_entry(ret, entry, hash_entry) {
+		if (ret->addr == addr)
+			return ret;
+	}
+
+	new = zalloc(sizeof(struct lock_stat));
+	if (!new)
+		goto alloc_failed;
+
+	new->addr = addr;
+	new->name = strdup(name);
+	if (!new->name) {
+		free(new);
+		goto alloc_failed;
+	}
+
+	new->flags = flags;
+	new->wait_time_min = ULLONG_MAX;
+
+	hlist_add_head(&new->hash_entry, entry);
+	return new;
+
+alloc_failed:
+	pr_err("memory allocation failed\n");
+	return NULL;
+}
+
+bool match_callstack_filter(struct machine *machine, u64 *callstack, int max_stack_depth)
+{
+	struct map *kmap;
+	struct symbol *sym;
+	u64 ip;
+	uint16_t e_machine = perf_env__e_machine(machine->env, /*e_flags=*/NULL);
+	bool is_powerpc = e_machine == EM_PPC64 || e_machine == EM_PPC;
+
+	if (list_empty(&callstack_filters))
+		return true;
+
+	for (int i = 0; i < max_stack_depth; i++) {
+		struct callstack_filter *filter;
+
+		/*
+		 * In powerpc, the callchain saved by kernel always includes
+		 * first three entries as the NIP (next instruction pointer),
+		 * LR (link register), and the contents of LR save area in the
+		 * second stack frame. In certain scenarios its possible to have
+		 * invalid kernel instruction addresses in either LR or the second
+		 * stack frame's LR. In that case, kernel will store that address as
+		 * zero.
+		 *
+		 * The below check will continue to look into callstack,
+		 * incase first or second callstack index entry has 0
+		 * address for powerpc.
+		 */
+		if (!callstack || (!callstack[i] && (!is_powerpc || (i != 1 && i != 2))))
+			break;
+
+		ip = callstack[i];
+		sym = machine__find_kernel_symbol(machine, ip, &kmap);
+		if (sym == NULL)
+			continue;
+
+		list_for_each_entry(filter, &callstack_filters, list) {
+			if (strstr(sym->name, filter->name))
+				return true;
+		}
+	}
+	return false;
+}