[PATCH v7 5/6] perf annotate: Be robust to annotating without a thread

[Ian Rogers <irogers@google.com>]

If a thread isn't given to map_symbol__get_arch(), try harder to determine
the arch for disassembly. Do this by utilizing fallback paths such as
reading the e_machine from a map's DSO ELF header for user-space libraries.
Additionally, rely on map__kmaps() and maps__machine() to reliably extract
the recorded machine environment and e_machine for kernel and kallsyms maps,
perfectly preventing silent, incorrect host fallbacks to uname() during
cross-platform Capstone annotation sessions.

At the same time, ensure all remaining uses of a map_symbol's thread pointer
do not assume it is non-NULL to eliminate UI segmentation faults, and remove
the fragile, redundant thread__get_arch() function to streamline the
annotate and disassembly subsystem architecture.

Fixes: 0e26ba5a8774 ("perf disasm: Refactor arch__find and initialization of arch structs")
Assisted-by: Antigravity:gemini-3.5-flash
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/ui/browsers/annotate.c |  2 +-
 tools/perf/util/annotate.c        | 51 ++++++++++++++++++++++---------
 tools/perf/util/annotate.h        |  3 +-
 tools/perf/util/capstone.c        | 42 ++++++++++++++++++++-----
 4 files changed, 74 insertions(+), 24 deletions(-)

diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index d25761a8d25e..e47a46775089 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -1201,7 +1201,7 @@ int __hist_entry__tui_annotate(struct hist_entry *he, struct map_symbol *ms,
 				ui__warning("Annotation has no source code.");
 		}
 	} else {
-		err = thread__get_arch(ms->thread, &browser.arch);
+		err = map_symbol__get_arch(ms, &browser.arch);
 		if (err) {
 			annotate_browser__symbol_annotate_error(&browser, err);
 			return -1;
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 53b2a224b21d..df70e95a8470 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -982,24 +982,43 @@ void symbol__calc_percent(struct symbol *sym, struct evsel *evsel)
 	annotation__calc_percent(notes, evsel, symbol__size(sym));
 }
 
-int thread__get_arch(struct thread *thread, const struct arch **parch)
+
+
+int map_symbol__get_arch(struct map_symbol *ms, const struct arch **parch)
 {
 	const struct arch *arch;
-	struct machine *machine;
-	uint32_t e_flags;
-	uint16_t e_machine;
+	struct machine *machine = NULL;
+	struct map *map = ms->map;
+	struct dso *dso = map ? map__dso(map) : NULL;
+	uint32_t e_flags = 0;
+	uint16_t e_machine = EM_NONE;
 
-	if (!thread) {
-		*parch = NULL;
-		return -1;
+	const char *cpuid = NULL;
+
+	if (ms->thread) {
+		machine = maps__machine(thread__maps(ms->thread));
+		e_machine = thread__e_machine(ms->thread, machine, &e_flags);
+		if (machine && machine->env)
+			cpuid = machine->env->cpuid;
+	} else if (dso) {
+		struct maps *kmaps = (map && dso__kernel(dso)) ? map__kmaps(map) : NULL;
+		struct machine *kmap_machine = kmaps ? maps__machine(kmaps) : NULL;
+
+		e_machine = dso__e_machine(dso, kmap_machine, &e_flags);
+		if (kmap_machine && kmap_machine->env)
+			cpuid = kmap_machine->env->cpuid;
 	}
 
-	machine = maps__machine(thread__maps(thread));
-	e_machine = thread__e_machine(thread, machine, &e_flags);
-	arch = arch__find(e_machine, e_flags, machine->env ? machine->env->cpuid : NULL);
+	if (e_machine == EM_NONE)
+		e_machine = thread__e_machine(NULL, NULL, &e_flags);
+
+	arch = arch__find(e_machine, e_flags, cpuid);
 	if (arch == NULL) {
 		pr_err("%s: unsupported arch %d\n", __func__, e_machine);
-		return errno;
+		/* TODO: Refactor annotate/disassemble subsystem error
+		 * codes to uniformly return negative integers.
+		 */
+		return errno ? errno : ENOTSUP;
 	}
 	if (parch)
 		*parch = arch;
@@ -1018,7 +1037,7 @@ int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
 	const struct arch *arch = NULL;
 	int err, nr;
 
-	err = thread__get_arch(ms->thread, &arch);
+	err = map_symbol__get_arch(ms, &arch);
 	if (err)
 		return err;
 
@@ -1251,6 +1270,11 @@ int hist_entry__annotate_printf(struct hist_entry *he, struct evsel *evsel)
 		evsel_name = buf;
 	}
 
+	if (map_symbol__get_arch(ms, &apd.arch)) {
+		free(filename);
+		return ENOTSUP;
+	}
+
 	graph_dotted_len = printf(" %-*.*s|	Source code & Disassembly of %s for %s (%" PRIu64 " samples, "
 				  "percent: %s)\n",
 				  width, width, symbol_conf.show_total_period ? "Period" :
@@ -1266,7 +1290,6 @@ int hist_entry__annotate_printf(struct hist_entry *he, struct evsel *evsel)
 
 	apd.addr_fmt_width = annotated_source__addr_fmt_width(&notes->src->source,
 							      notes->src->start);
-	thread__get_arch(ms->thread, &apd.arch);
 	apd.dbg = dso__debuginfo(dso);
 
 	list_for_each_entry(pos, &notes->src->source, node) {
@@ -1371,7 +1394,7 @@ static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp,
 	struct annotation_line *al;
 
 	if (annotate_opts.code_with_type) {
-		thread__get_arch(apd->he->ms.thread, &apd->arch);
+		map_symbol__get_arch(&apd->he->ms, &apd->arch);
 		apd->dbg = dso__debuginfo(map__dso(apd->he->ms.map));
 	}
 
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 1aa6df7d1618..fa08d09b80f7 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -584,5 +584,6 @@ int annotation_br_cntr_entry(char **str, int br_cntr_nr, u64 *br_cntr,
 			     int num_aggr, struct evsel *evsel);
 int annotation_br_cntr_abbr_list(char **str, struct evsel *evsel, bool header);
 
-int thread__get_arch(struct thread *thread, const struct arch **parch);
+
+int map_symbol__get_arch(struct map_symbol *ms, const struct arch **parch);
 #endif	/* __PERF_ANNOTATE_H */
diff --git a/tools/perf/util/capstone.c b/tools/perf/util/capstone.c
index 00e0141cae8d..74213daf8786 100644
--- a/tools/perf/util/capstone.c
+++ b/tools/perf/util/capstone.c
@@ -392,7 +392,7 @@ int symbol__disassemble_capstone(const char *filename, struct symbol *sym,
 	char disasm_buf[512];
 	struct disasm_line *dl;
 	bool disassembler_style = false;
-	uint16_t e_machine;
+	uint16_t e_machine = EM_NONE;
 	bool is_big_endian = false;
 
 	if (args->options->objdump_path)
@@ -423,9 +423,22 @@ int symbol__disassemble_capstone(const char *filename, struct symbol *sym,
 	    !strcmp(args->options->disassembler_style, "att"))
 		disassembler_style = true;
 
-	e_machine = thread__e_machine_endian(args->ms->thread,
-					     /*machine=*/NULL,
-					     /*e_flags=*/NULL, &is_big_endian);
+	if (args->ms->thread) {
+		e_machine = thread__e_machine_endian(args->ms->thread,
+						     /*machine=*/NULL,
+						     /*e_flags=*/NULL, &is_big_endian);
+	} else if (dso) {
+		struct maps *kmaps = (map && dso__kernel(dso)) ? map__kmaps(map) : NULL;
+		struct machine *kmap_machine = kmaps ? maps__machine(kmaps) : NULL;
+
+		e_machine = dso__e_machine_endian(dso, kmap_machine, /*e_flags=*/NULL,
+						  &is_big_endian);
+	}
+	if (!e_machine || e_machine == EM_NONE) {
+		e_machine = thread__e_machine_endian(NULL,
+						     /*machine=*/NULL,
+						     /*e_flags=*/NULL, &is_big_endian);
+	}
 	if (capstone_init(e_machine, &handle, is_64bit, is_big_endian, disassembler_style) < 0)
 		goto err;
 
@@ -518,7 +531,7 @@ int symbol__disassemble_capstone_powerpc(const char *filename __maybe_unused,
 	struct disasm_line *dl;
 	u32 *line;
 	bool disassembler_style = false;
-	uint16_t e_machine;
+	uint16_t e_machine = EM_NONE;
 	bool is_big_endian = false;
 
 	if (args->options->objdump_path)
@@ -538,9 +551,22 @@ int symbol__disassemble_capstone_powerpc(const char *filename __maybe_unused,
 	    !strcmp(args->options->disassembler_style, "att"))
 		disassembler_style = true;
 
-	e_machine = thread__e_machine_endian(args->ms->thread,
-					     /*machine=*/NULL,
-					     /*e_flags=*/NULL, &is_big_endian);
+	if (args->ms->thread) {
+		e_machine = thread__e_machine_endian(args->ms->thread,
+						     /*machine=*/NULL,
+						     /*e_flags=*/NULL, &is_big_endian);
+	} else if (dso) {
+		struct maps *kmaps = (map && dso__kernel(dso)) ? map__kmaps(map) : NULL;
+		struct machine *kmap_machine = kmaps ? maps__machine(kmaps) : NULL;
+
+		e_machine = dso__e_machine_endian(dso, kmap_machine, /*e_flags=*/NULL,
+						  &is_big_endian);
+	}
+	if (!e_machine || e_machine == EM_NONE) {
+		e_machine = thread__e_machine_endian(NULL,
+						     /*machine=*/NULL,
+						     /*e_flags=*/NULL, &is_big_endian);
+	}
 	if (capstone_init(e_machine, &handle, is_64bit, is_big_endian, disassembler_style) < 0)
 		goto err;
 
-- 
2.55.0.229.g6434b31f56-goog