[PATCH v4 9/9] perf annotate: Be robust to annotating without a thread
From: Ian Rogers
Date: Thu Jul 09 2026 - 22:56:01 EST
If a thread isn't given to thread__get_arch try harder to determine the
arch for disassembly. Do this by passing an entire map_symbol and using
fallback paths such as reading the e_machine from a map's dso. At the
same time ensure some other uses of map_symbol thread don't assume it is
non-NULL to avoid segvs.
Tested running perf report without a previous fix to populate the
map_symbol thread field.
Assisted-by: Antigravity:gemini-3.5-flash
Signed-off-by: Ian Rogers <irogers@xxxxxxxxxx>
---
tools/perf/ui/browsers/annotate.c | 2 +-
.../util/annotate-arch/annotate-loongarch.c | 4 +-
tools/perf/util/annotate-arch/annotate-s390.c | 2 +-
tools/perf/util/annotate.c | 57 ++++++++++++++-----
tools/perf/util/annotate.h | 2 +-
tools/perf/util/capstone.c | 30 ++++++++--
tools/perf/util/disasm.c | 7 ++-
7 files changed, 77 insertions(+), 27 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-arch/annotate-loongarch.c b/tools/perf/util/annotate-arch/annotate-loongarch.c
index c2addca77320..26217cb2d8f3 100644
--- a/tools/perf/util/annotate-arch/annotate-loongarch.c
+++ b/tools/perf/util/annotate-arch/annotate-loongarch.c
@@ -51,7 +51,7 @@ static int loongarch_call__parse(const struct arch *arch, struct ins_operands *o
.addr = map__objdump_2mem(map, ops->target.addr),
};
- if (maps__find_ams(thread__maps(ms->thread), &target) == 0 &&
+ if (ms->thread && maps__find_ams(thread__maps(ms->thread), &target) == 0 &&
map__rip_2objdump(target.ms.map, map__map_ip(target.ms.map, target.addr)) == ops->target.addr)
ops->target.sym = target.ms.sym;
@@ -95,7 +95,7 @@ static int loongarch_jump__parse(const struct arch *arch, struct ins_operands *o
ops->target.outside = target.addr < start || target.addr >= end;
- if (maps__find_ams(thread__maps(ms->thread), &target) == 0 &&
+ if (ms->thread && maps__find_ams(thread__maps(ms->thread), &target) == 0 &&
map__rip_2objdump(target.ms.map, map__map_ip(target.ms.map, target.addr)) == ops->target.addr)
ops->target.sym = target.ms.sym;
diff --git a/tools/perf/util/annotate-arch/annotate-s390.c b/tools/perf/util/annotate-arch/annotate-s390.c
index af9cabd0a586..3ea6ad588998 100644
--- a/tools/perf/util/annotate-arch/annotate-s390.c
+++ b/tools/perf/util/annotate-arch/annotate-s390.c
@@ -50,7 +50,7 @@ static int s390_call__parse(const struct arch *arch, struct ins_operands *ops,
.addr = map__objdump_2mem(map, ops->target.addr),
};
- if (maps__find_ams(thread__maps(ms->thread), &target) == 0 &&
+ if (ms->thread && maps__find_ams(thread__maps(ms->thread), &target) == 0 &&
map__rip_2objdump(target.ms.map, map__map_ip(target.ms.map, target.addr)) == ops->target.addr)
ops->target.sym = target.ms.sym;
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 53b2a224b21d..cdfaeb2388d0 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -982,21 +982,46 @@ 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)
{
+ struct machine *machine = NULL;
+ const char *cpuid = NULL;
const struct arch *arch;
- struct machine *machine;
- uint32_t e_flags;
- uint16_t e_machine;
+ uint32_t e_flags = 0;
+ uint16_t e_machine = EM_NONE;
- if (!thread) {
- *parch = NULL;
- return -1;
+ /*
+ * If we have a thread then derive the e_machine using it. The thread
+ * can determine the machine and perf_env, so is generally pretty robust
+ * as well as benefitting from a cache.
+ */
+ if (ms->thread) {
+ struct maps *maps = thread__maps(ms->thread);
+
+ machine = maps__machine(maps);
+ e_machine = thread__e_machine(ms->thread, machine, &e_flags);
+ if (machine && machine->env)
+ cpuid = machine->env->cpuid;
+ }
+ if (e_machine == EM_NONE && ms->map) {
+ /*
+ * If the thread look up failed then try to use a dso that may
+ * be associated with the map.
+ */
+ struct dso *dso = map__dso(ms->map);
+
+ if (dso)
+ e_machine = dso__e_machine(dso, machine, &e_flags);
+ }
+ if (e_machine == EM_NONE) {
+ /*
+ * Still no e_machine, use the default for this kind of perf
+ * build that will determine a value using uname, etc.
+ */
+ e_machine = thread__e_machine(ms->thread, machine, &e_flags);
}
- 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);
+ arch = arch__find(e_machine, e_flags, cpuid);
if (arch == NULL) {
pr_err("%s: unsupported arch %d\n", __func__, e_machine);
return errno;
@@ -1018,7 +1043,7 @@ 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;
@@ -1266,7 +1291,10 @@ int hist_entry__annotate_printf(struct hist_entry *he, struct evsel *evsel)
apd.addr_fmt_width = annotated_source__addr_fmt_width(¬es->src->source,
notes->src->start);
- thread__get_arch(ms->thread, &apd.arch);
+ if (map_symbol__get_arch(ms, &apd.arch)) {
+ free(filename);
+ return -ENOTSUP;
+ }
apd.dbg = dso__debuginfo(dso);
list_for_each_entry(pos, ¬es->src->source, node) {
@@ -1369,9 +1397,12 @@ static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp,
.write_graph = FILE__write_graph,
};
struct annotation_line *al;
+ int err;
if (annotate_opts.code_with_type) {
- thread__get_arch(apd->he->ms.thread, &apd->arch);
+ err = map_symbol__get_arch(&apd->he->ms, &apd->arch);
+ if (err)
+ return err;
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..d54f851035ec 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -584,5 +584,5 @@ 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 5ad537fea436..15152a2c1b25 100644
--- a/tools/perf/util/capstone.c
+++ b/tools/perf/util/capstone.c
@@ -411,9 +411,18 @@ 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) {
+ e_machine = dso__e_machine_endian(dso, /*machine=*/NULL, /*e_flags=*/NULL,
+ &is_big_endian);
+ } else {
+ 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;
@@ -526,9 +535,18 @@ 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) {
+ e_machine = dso__e_machine_endian(dso, /*machine=*/NULL, /*e_flags=*/NULL,
+ &is_big_endian);
+ } else {
+ 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;
diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c
index 5b114f089d56..46b9c292d5eb 100644
--- a/tools/perf/util/disasm.c
+++ b/tools/perf/util/disasm.c
@@ -271,7 +271,7 @@ static int call__parse(const struct arch *arch, struct ins_operands *ops, struct
.addr = map__objdump_2mem(map, ops->target.addr),
};
- if (maps__find_ams(thread__maps(ms->thread), &target) == 0 &&
+ if (ms->thread && maps__find_ams(thread__maps(ms->thread), &target) == 0 &&
map__rip_2objdump(target.ms.map, map__map_ip(target.ms.map, target.addr)) == ops->target.addr)
ops->target.sym = target.ms.sym;
@@ -405,7 +405,7 @@ static int jump__parse(const struct arch *arch, struct ins_operands *ops, struct
* Actual navigation will come next, with further understanding of how
* the symbol searching and disassembly should be done.
*/
- if (maps__find_ams(thread__maps(ms->thread), &target) == 0 &&
+ if (ms->thread && maps__find_ams(thread__maps(ms->thread), &target) == 0 &&
map__rip_2objdump(target.ms.map, map__map_ip(target.ms.map, target.addr)) == ops->target.addr)
ops->target.sym = target.ms.sym;
@@ -1068,7 +1068,8 @@ static int symbol__parse_objdump_line(struct symbol *sym,
.ms = { .map = map__get(map), },
};
- if (!maps__find_ams(thread__maps(args->ms->thread), &target) &&
+ if (args->ms->thread &&
+ !maps__find_ams(thread__maps(args->ms->thread), &target) &&
target.ms.sym->start == target.al_addr)
dl->ops.target.sym = target.ms.sym;
--
2.55.0.795.g602f6c329a-goog