* [PATCH v16 1/4] perf tools: Minimal CALLCHAIN_DEFERRED support
2025-09-08 17:53 [PATCH v16 0/4] perf tool: Support the deferred unwinding infrastructure Steven Rostedt
@ 2025-09-08 17:53 ` Steven Rostedt
2025-09-08 17:53 ` [PATCH v16 2/4] perf record: Enable defer_callchain for user callchains Steven Rostedt
` (3 subsequent siblings)
4 siblings, 0 replies; 10+ messages in thread
From: Steven Rostedt @ 2025-09-08 17:53 UTC (permalink / raw)
To: linux-kernel, linux-trace-kernel, bpf, x86
Cc: Masami Hiramatsu, Mathieu Desnoyers, Josh Poimboeuf,
Peter Zijlstra, Ingo Molnar, Jiri Olsa, Arnaldo Carvalho de Melo,
Namhyung Kim, Thomas Gleixner, Andrii Nakryiko, Indu Bhagat,
Jose E. Marchesi, Beau Belgrave, Jens Remus, Linus Torvalds,
Andrew Morton, Florian Weimer, Sam James, Kees Cook,
Carlos O'Donell
From: Namhyung Kim <namhyung@kernel.org>
Add a new event type for deferred callchains and a new callback for the
struct perf_tool. For now it doesn't actually handle the deferred
callchains but it just marks the sample if it has the PERF_CONTEXT_
USER_DEFFERED in the callchain array.
At least, perf report can dump the raw data with this change. Actually
this requires the next commit to enable attr.defer_callchain, but if you
already have a data file, it'll show the following result.
$ perf report -D
...
0x5fe0@perf.data [0x40]: event: 22
.
. ... raw event: size 64 bytes
. 0000: 16 00 00 00 02 00 40 00 02 00 00 00 00 00 00 00 ......@.........
. 0010: 00 fe ff ff ff ff ff ff 4b d3 3f 25 45 7f 00 00 ........K.?%E...
. 0020: 21 03 00 00 21 03 00 00 43 02 12 ab 05 00 00 00 !...!...C.......
. 0030: 00 00 00 00 00 00 00 00 09 00 00 00 00 00 00 00 ................
0 24344920643 0x5fe0 [0x40]: PERF_RECORD_CALLCHAIN_DEFERRED(IP, 0x2): 801/801: 0 [300000001]
... FP chain: nr:2
..... 0: fffffffffffffe00
..... 1: 00007f45253fd34b
: unhandled!
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
tools/lib/perf/include/perf/event.h | 8 ++++++++
tools/perf/util/event.c | 1 +
tools/perf/util/evsel.c | 18 ++++++++++++++++++
tools/perf/util/machine.c | 1 +
tools/perf/util/perf_event_attr_fprintf.c | 1 +
tools/perf/util/sample.h | 4 +++-
tools/perf/util/session.c | 18 ++++++++++++++++++
tools/perf/util/tool.c | 1 +
tools/perf/util/tool.h | 3 ++-
9 files changed, 53 insertions(+), 2 deletions(-)
diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h
index 6608f1e3701b..4af8cb238e27 100644
--- a/tools/lib/perf/include/perf/event.h
+++ b/tools/lib/perf/include/perf/event.h
@@ -151,6 +151,13 @@ struct perf_record_switch {
__u32 next_prev_tid;
};
+struct perf_record_callchain_deferred {
+ struct perf_event_header header;
+ __u64 cookie;
+ __u64 nr;
+ __u64 ips[];
+};
+
struct perf_record_header_attr {
struct perf_event_header header;
struct perf_event_attr attr;
@@ -522,6 +529,7 @@ union perf_event {
struct perf_record_read read;
struct perf_record_throttle throttle;
struct perf_record_sample sample;
+ struct perf_record_callchain_deferred callchain_deferred;
struct perf_record_bpf_event bpf;
struct perf_record_ksymbol ksymbol;
struct perf_record_text_poke_event text_poke;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index fcf44149feb2..4c92cc1a952c 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -61,6 +61,7 @@ static const char *perf_event__names[] = {
[PERF_RECORD_CGROUP] = "CGROUP",
[PERF_RECORD_TEXT_POKE] = "TEXT_POKE",
[PERF_RECORD_AUX_OUTPUT_HW_ID] = "AUX_OUTPUT_HW_ID",
+ [PERF_RECORD_CALLCHAIN_DEFERRED] = "CALLCHAIN_DEFERRED",
[PERF_RECORD_HEADER_ATTR] = "ATTR",
[PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE",
[PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA",
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index d264c143b592..7512b9fb877d 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -3002,6 +3002,18 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
data->data_src = PERF_MEM_DATA_SRC_NONE;
data->vcpu = -1;
+ if (event->header.type == PERF_RECORD_CALLCHAIN_DEFERRED) {
+ const u64 max_callchain_nr = UINT64_MAX / sizeof(u64);
+
+ data->callchain = (struct ip_callchain *)&event->callchain_deferred.nr;
+ if (data->callchain->nr > max_callchain_nr)
+ return -EFAULT;
+
+ if (evsel->core.attr.sample_id_all)
+ perf_evsel__parse_id_sample(evsel, event, data);
+ return 0;
+ }
+
if (event->header.type != PERF_RECORD_SAMPLE) {
if (!evsel->core.attr.sample_id_all)
return 0;
@@ -3132,6 +3144,12 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
if (data->callchain->nr > max_callchain_nr)
return -EFAULT;
sz = data->callchain->nr * sizeof(u64);
+ if (evsel->core.attr.defer_callchain &&
+ data->callchain->nr >= PERF_DEFERRED_ITEMS &&
+ data->callchain->ips[data->callchain->nr - PERF_DEFERRED_ITEMS] == PERF_CONTEXT_USER_DEFERRED) {
+ data->deferred_callchain = true;
+ data->deferred_cookie = data->callchain->ips[data->callchain->nr - 1];
+ }
OVERFLOW_CHECK(array, sz, max_size);
array = (void *)array + sz;
}
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index b5dd42588c91..841b711d970e 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2124,6 +2124,7 @@ static int add_callchain_ip(struct thread *thread,
*cpumode = PERF_RECORD_MISC_KERNEL;
break;
case PERF_CONTEXT_USER:
+ case PERF_CONTEXT_USER_DEFERRED:
*cpumode = PERF_RECORD_MISC_USER;
break;
default:
diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c
index 66b666d9ce64..abfd9b9a718c 100644
--- a/tools/perf/util/perf_event_attr_fprintf.c
+++ b/tools/perf/util/perf_event_attr_fprintf.c
@@ -343,6 +343,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
PRINT_ATTRf(inherit_thread, p_unsigned);
PRINT_ATTRf(remove_on_exec, p_unsigned);
PRINT_ATTRf(sigtrap, p_unsigned);
+ PRINT_ATTRf(defer_callchain, p_unsigned);
PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned, false);
PRINT_ATTRf(bp_type, p_unsigned);
diff --git a/tools/perf/util/sample.h b/tools/perf/util/sample.h
index fae834144ef4..68392e6298b7 100644
--- a/tools/perf/util/sample.h
+++ b/tools/perf/util/sample.h
@@ -106,7 +106,9 @@ struct perf_sample {
u16 ins_lat;
/** @weight3: On x86 holds retire_lat, on powerpc holds p_stage_cyc. */
u16 weight3;
- bool no_hw_idx; /* No hw_idx collected in branch_stack */
+ bool no_hw_idx; /* No hw_idx collected in branch_stack */
+ bool deferred_callchain; /* Has deferred user callchains */
+ u64 deferred_cookie;
char insn[MAX_INSN];
void *raw_data;
struct ip_callchain *callchain;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 26ae078278cd..a071006350f5 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -720,6 +720,7 @@ static perf_event__swap_op perf_event__swap_ops[] = {
[PERF_RECORD_CGROUP] = perf_event__cgroup_swap,
[PERF_RECORD_TEXT_POKE] = perf_event__text_poke_swap,
[PERF_RECORD_AUX_OUTPUT_HW_ID] = perf_event__all64_swap,
+ [PERF_RECORD_CALLCHAIN_DEFERRED] = perf_event__all64_swap,
[PERF_RECORD_HEADER_ATTR] = perf_event__hdr_attr_swap,
[PERF_RECORD_HEADER_EVENT_TYPE] = perf_event__event_type_swap,
[PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,
@@ -1123,6 +1124,20 @@ static void dump_sample(struct evsel *evsel, union perf_event *event,
sample_read__printf(sample, evsel->core.attr.read_format);
}
+static void dump_deferred_callchain(struct evsel *evsel, union perf_event *event,
+ struct perf_sample *sample)
+{
+ if (!dump_trace)
+ return;
+
+ printf("(IP, 0x%x): %d/%d: %#" PRIx64 " [%llx]\n",
+ event->header.misc, sample->pid, sample->tid, sample->ip,
+ event->callchain_deferred.cookie);
+
+ if (evsel__has_callchain(evsel))
+ callchain__printf(evsel, sample);
+}
+
static void dump_read(struct evsel *evsel, union perf_event *event)
{
struct perf_record_read *read_event = &event->read;
@@ -1353,6 +1368,9 @@ static int machines__deliver_event(struct machines *machines,
return tool->text_poke(tool, event, sample, machine);
case PERF_RECORD_AUX_OUTPUT_HW_ID:
return tool->aux_output_hw_id(tool, event, sample, machine);
+ case PERF_RECORD_CALLCHAIN_DEFERRED:
+ dump_deferred_callchain(evsel, event, sample);
+ return tool->callchain_deferred(tool, event, sample, evsel, machine);
default:
++evlist->stats.nr_unknown_events;
return -1;
diff --git a/tools/perf/util/tool.c b/tools/perf/util/tool.c
index e83c7ababc2a..8bf86af1ca90 100644
--- a/tools/perf/util/tool.c
+++ b/tools/perf/util/tool.c
@@ -279,6 +279,7 @@ void perf_tool__init(struct perf_tool *tool, bool ordered_events)
tool->read = process_event_sample_stub;
tool->throttle = process_event_stub;
tool->unthrottle = process_event_stub;
+ tool->callchain_deferred = process_event_sample_stub;
tool->attr = process_event_synth_attr_stub;
tool->event_update = process_event_synth_event_update_stub;
tool->tracing_data = process_event_synth_tracing_data_stub;
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 18b76ff0f26a..2676d84da80c 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -42,7 +42,8 @@ enum show_feature_header {
struct perf_tool {
event_sample sample,
- read;
+ read,
+ callchain_deferred;
event_op mmap,
mmap2,
comm,
--
2.50.1
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH v16 2/4] perf record: Enable defer_callchain for user callchains
2025-09-08 17:53 [PATCH v16 0/4] perf tool: Support the deferred unwinding infrastructure Steven Rostedt
2025-09-08 17:53 ` [PATCH v16 1/4] perf tools: Minimal CALLCHAIN_DEFERRED support Steven Rostedt
@ 2025-09-08 17:53 ` Steven Rostedt
2025-09-08 17:53 ` [PATCH v16 3/4] perf script: Display PERF_RECORD_CALLCHAIN_DEFERRED Steven Rostedt
` (2 subsequent siblings)
4 siblings, 0 replies; 10+ messages in thread
From: Steven Rostedt @ 2025-09-08 17:53 UTC (permalink / raw)
To: linux-kernel, linux-trace-kernel, bpf, x86
Cc: Masami Hiramatsu, Mathieu Desnoyers, Josh Poimboeuf,
Peter Zijlstra, Ingo Molnar, Jiri Olsa, Arnaldo Carvalho de Melo,
Namhyung Kim, Thomas Gleixner, Andrii Nakryiko, Indu Bhagat,
Jose E. Marchesi, Beau Belgrave, Jens Remus, Linus Torvalds,
Andrew Morton, Florian Weimer, Sam James, Kees Cook,
Carlos O'Donell
From: Namhyung Kim <namhyung@kernel.org>
And add the missing feature detection logic to clear the flag on old
kernels.
$ perf record -g -vv true
...
------------------------------------------------------------
perf_event_attr:
type 0 (PERF_TYPE_HARDWARE)
size 136
config 0 (PERF_COUNT_HW_CPU_CYCLES)
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|CALLCHAIN|PERIOD
read_format ID|LOST
disabled 1
inherit 1
mmap 1
comm 1
freq 1
enable_on_exec 1
task 1
sample_id_all 1
mmap2 1
comm_exec 1
ksymbol 1
bpf_event 1
defer_callchain 1
------------------------------------------------------------
sys_perf_event_open: pid 162755 cpu 0 group_fd -1 flags 0x8
sys_perf_event_open failed, error -22
switching off deferred callchain support
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
tools/perf/util/evsel.c | 24 ++++++++++++++++++++++++
tools/perf/util/evsel.h | 1 +
2 files changed, 25 insertions(+)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 7512b9fb877d..438343dbb1c9 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1061,6 +1061,14 @@ static void __evsel__config_callchain(struct evsel *evsel, struct record_opts *o
}
}
+ if (param->record_mode == CALLCHAIN_FP && !attr->exclude_callchain_user) {
+ /*
+ * Enable deferred callchains optimistically. It'll be switched
+ * off later if the kernel doesn't support it.
+ */
+ attr->defer_callchain = 1;
+ }
+
if (function) {
pr_info("Disabling user space callchains for function trace event.\n");
attr->exclude_callchain_user = 1;
@@ -2121,6 +2129,8 @@ static int __evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
static void evsel__disable_missing_features(struct evsel *evsel)
{
+ if (perf_missing_features.defer_callchain)
+ evsel->core.attr.defer_callchain = 0;
if (perf_missing_features.inherit_sample_read && evsel->core.attr.inherit &&
(evsel->core.attr.sample_type & PERF_SAMPLE_READ))
evsel->core.attr.inherit = 0;
@@ -2395,6 +2405,15 @@ static bool evsel__detect_missing_features(struct evsel *evsel, struct perf_cpu
/* Please add new feature detection here. */
+ attr.defer_callchain = true;
+ attr.sample_type = PERF_SAMPLE_CALLCHAIN;
+ if (has_attr_feature(&attr, /*flags=*/0))
+ goto found;
+ perf_missing_features.defer_callchain = true;
+ pr_debug2("switching off deferred callchain support\n");
+ attr.defer_callchain = false;
+ attr.sample_type = 0;
+
attr.inherit = true;
attr.sample_type = PERF_SAMPLE_READ;
if (has_attr_feature(&attr, /*flags=*/0))
@@ -2506,6 +2525,11 @@ static bool evsel__detect_missing_features(struct evsel *evsel, struct perf_cpu
errno = old_errno;
check:
+ if (evsel->core.attr.defer_callchain &&
+ evsel->core.attr.sample_type & PERF_SAMPLE_CALLCHAIN &&
+ perf_missing_features.defer_callchain)
+ return true;
+
if (evsel->core.attr.inherit &&
(evsel->core.attr.sample_type & PERF_SAMPLE_READ) &&
perf_missing_features.inherit_sample_read)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 5797a02e5d6a..d9559d29e345 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -221,6 +221,7 @@ struct perf_missing_features {
bool branch_counters;
bool aux_action;
bool inherit_sample_read;
+ bool defer_callchain;
};
extern struct perf_missing_features perf_missing_features;
--
2.50.1
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH v16 3/4] perf script: Display PERF_RECORD_CALLCHAIN_DEFERRED
2025-09-08 17:53 [PATCH v16 0/4] perf tool: Support the deferred unwinding infrastructure Steven Rostedt
2025-09-08 17:53 ` [PATCH v16 1/4] perf tools: Minimal CALLCHAIN_DEFERRED support Steven Rostedt
2025-09-08 17:53 ` [PATCH v16 2/4] perf record: Enable defer_callchain for user callchains Steven Rostedt
@ 2025-09-08 17:53 ` Steven Rostedt
2025-09-08 17:53 ` [PATCH v16 4/4] perf tools: Merge deferred user callchains Steven Rostedt
2025-10-24 13:01 ` [PATCH v16 0/4] perf tool: Support the deferred unwinding infrastructure Peter Zijlstra
4 siblings, 0 replies; 10+ messages in thread
From: Steven Rostedt @ 2025-09-08 17:53 UTC (permalink / raw)
To: linux-kernel, linux-trace-kernel, bpf, x86
Cc: Masami Hiramatsu, Mathieu Desnoyers, Josh Poimboeuf,
Peter Zijlstra, Ingo Molnar, Jiri Olsa, Arnaldo Carvalho de Melo,
Namhyung Kim, Thomas Gleixner, Andrii Nakryiko, Indu Bhagat,
Jose E. Marchesi, Beau Belgrave, Jens Remus, Linus Torvalds,
Andrew Morton, Florian Weimer, Sam James, Kees Cook,
Carlos O'Donell
From: Namhyung Kim <namhyung@kernel.org>
Handle the deferred callchains in the script output.
$ perf script
perf 801 [000] 18.031793: 1 cycles:P:
ffffffff91a14c36 __intel_pmu_enable_all.isra.0+0x56 ([kernel.kallsyms])
ffffffff91d373e9 perf_ctx_enable+0x39 ([kernel.kallsyms])
ffffffff91d36af7 event_function+0xd7 ([kernel.kallsyms])
ffffffff91d34222 remote_function+0x42 ([kernel.kallsyms])
ffffffff91c1ebe1 generic_exec_single+0x61 ([kernel.kallsyms])
ffffffff91c1edac smp_call_function_single+0xec ([kernel.kallsyms])
ffffffff91d37a9d event_function_call+0x10d ([kernel.kallsyms])
ffffffff91d33557 perf_event_for_each_child+0x37 ([kernel.kallsyms])
ffffffff91d47324 _perf_ioctl+0x204 ([kernel.kallsyms])
ffffffff91d47c43 perf_ioctl+0x33 ([kernel.kallsyms])
ffffffff91e2f216 __x64_sys_ioctl+0x96 ([kernel.kallsyms])
ffffffff9265f1ae do_syscall_64+0x9e ([kernel.kallsyms])
ffffffff92800130 entry_SYSCALL_64+0xb0 ([kernel.kallsyms])
perf 801 [000] 18.031814: DEFERRED CALLCHAIN
7fb5fc22034b __GI___ioctl+0x3b (/usr/lib/x86_64-linux-gnu/libc.so.6)
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
Changes since v15: https://lore.kernel.org/20250825180802.557798597@kernel.org
- Removed initialization of script.tool.merge_deferred_callchains as it is
introduced in the next patch.
tools/perf/builtin-script.c | 88 +++++++++++++++++++++++++++++++++++++
1 file changed, 88 insertions(+)
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index d9fbdcf72f25..03ea7b7e5bc1 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2484,6 +2484,93 @@ static int process_sample_event(const struct perf_tool *tool,
return ret;
}
+static int process_deferred_sample_event(const struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct evsel *evsel,
+ struct machine *machine)
+{
+ struct perf_script *scr = container_of(tool, struct perf_script, tool);
+ struct perf_event_attr *attr = &evsel->core.attr;
+ struct evsel_script *es = evsel->priv;
+ unsigned int type = output_type(attr->type);
+ struct addr_location al;
+ FILE *fp = es->fp;
+ int ret = 0;
+
+ if (output[type].fields == 0)
+ return 0;
+
+ /* Set thread to NULL to indicate addr_al and al are not initialized */
+ addr_location__init(&al);
+
+ if (perf_time__ranges_skip_sample(scr->ptime_range, scr->range_num,
+ sample->time)) {
+ goto out_put;
+ }
+
+ if (debug_mode) {
+ if (sample->time < last_timestamp) {
+ pr_err("Samples misordered, previous: %" PRIu64
+ " this: %" PRIu64 "\n", last_timestamp,
+ sample->time);
+ nr_unordered++;
+ }
+ last_timestamp = sample->time;
+ goto out_put;
+ }
+
+ if (filter_cpu(sample))
+ goto out_put;
+
+ if (machine__resolve(machine, &al, sample) < 0) {
+ pr_err("problem processing %d event, skipping it.\n",
+ event->header.type);
+ ret = -1;
+ goto out_put;
+ }
+
+ if (al.filtered)
+ goto out_put;
+
+ if (!show_event(sample, evsel, al.thread, &al, NULL))
+ goto out_put;
+
+ if (evswitch__discard(&scr->evswitch, evsel))
+ goto out_put;
+
+ perf_sample__fprintf_start(scr, sample, al.thread, evsel,
+ PERF_RECORD_CALLCHAIN_DEFERRED, fp);
+ fprintf(fp, "DEFERRED CALLCHAIN");
+
+ if (PRINT_FIELD(IP)) {
+ struct callchain_cursor *cursor = NULL;
+
+ if (symbol_conf.use_callchain && sample->callchain) {
+ cursor = get_tls_callchain_cursor();
+ if (thread__resolve_callchain(al.thread, cursor, evsel,
+ sample, NULL, NULL,
+ scripting_max_stack)) {
+ pr_info("cannot resolve deferred callchains\n");
+ cursor = NULL;
+ }
+ }
+
+ fputc(cursor ? '\n' : ' ', fp);
+ sample__fprintf_sym(sample, &al, 0, output[type].print_ip_opts,
+ cursor, symbol_conf.bt_stop_list, fp);
+ }
+
+ fprintf(fp, "\n");
+
+ if (verbose > 0)
+ fflush(fp);
+
+out_put:
+ addr_location__exit(&al);
+ return ret;
+}
+
// Used when scr->per_event_dump is not set
static struct evsel_script es_stdout;
@@ -4080,6 +4167,7 @@ int cmd_script(int argc, const char **argv)
perf_tool__init(&script.tool, !unsorted_dump);
script.tool.sample = process_sample_event;
+ script.tool.callchain_deferred = process_deferred_sample_event;
script.tool.mmap = perf_event__process_mmap;
script.tool.mmap2 = perf_event__process_mmap2;
script.tool.comm = perf_event__process_comm;
--
2.50.1
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH v16 4/4] perf tools: Merge deferred user callchains
2025-09-08 17:53 [PATCH v16 0/4] perf tool: Support the deferred unwinding infrastructure Steven Rostedt
` (2 preceding siblings ...)
2025-09-08 17:53 ` [PATCH v16 3/4] perf script: Display PERF_RECORD_CALLCHAIN_DEFERRED Steven Rostedt
@ 2025-09-08 17:53 ` Steven Rostedt
2025-10-02 17:49 ` Steven Rostedt
2025-10-24 13:01 ` [PATCH v16 0/4] perf tool: Support the deferred unwinding infrastructure Peter Zijlstra
4 siblings, 1 reply; 10+ messages in thread
From: Steven Rostedt @ 2025-09-08 17:53 UTC (permalink / raw)
To: linux-kernel, linux-trace-kernel, bpf, x86
Cc: Masami Hiramatsu, Mathieu Desnoyers, Josh Poimboeuf,
Peter Zijlstra, Ingo Molnar, Jiri Olsa, Arnaldo Carvalho de Melo,
Namhyung Kim, Thomas Gleixner, Andrii Nakryiko, Indu Bhagat,
Jose E. Marchesi, Beau Belgrave, Jens Remus, Linus Torvalds,
Andrew Morton, Florian Weimer, Sam James, Kees Cook,
Carlos O'Donell
From: Namhyung Kim <namhyung@kernel.org>
Save samples with deferred callchains in a separate list and deliver
them after merging the user callchains. If users don't want to merge
they can set tool->merge_deferred_callchains to false to prevent the
behavior.
With previous result, now perf script will show the merged callchains.
$ perf script
perf 801 [000] 18.031793: 1 cycles:P:
ffffffff91a14c36 __intel_pmu_enable_all.isra.0+0x56 ([kernel.kallsyms])
ffffffff91d373e9 perf_ctx_enable+0x39 ([kernel.kallsyms])
ffffffff91d36af7 event_function+0xd7 ([kernel.kallsyms])
ffffffff91d34222 remote_function+0x42 ([kernel.kallsyms])
ffffffff91c1ebe1 generic_exec_single+0x61 ([kernel.kallsyms])
ffffffff91c1edac smp_call_function_single+0xec ([kernel.kallsyms])
ffffffff91d37a9d event_function_call+0x10d ([kernel.kallsyms])
ffffffff91d33557 perf_event_for_each_child+0x37 ([kernel.kallsyms])
ffffffff91d47324 _perf_ioctl+0x204 ([kernel.kallsyms])
ffffffff91d47c43 perf_ioctl+0x33 ([kernel.kallsyms])
ffffffff91e2f216 __x64_sys_ioctl+0x96 ([kernel.kallsyms])
ffffffff9265f1ae do_syscall_64+0x9e ([kernel.kallsyms])
ffffffff92800130 entry_SYSCALL_64+0xb0 ([kernel.kallsyms])
7fb5fc22034b __GI___ioctl+0x3b (/usr/lib/x86_64-linux-gnu/libc.so.6)
...
The old output can be get using --no-merge-callchain option.
Also perf report can get the user callchain entry at the end.
$ perf report --no-children --percent-limit=0 --stdio -q -S __intel_pmu_enable_all.isra.0
# symbol: __intel_pmu_enable_all.isra.0
0.00% perf [kernel.kallsyms]
|
---__intel_pmu_enable_all.isra.0
perf_ctx_enable
event_function
remote_function
generic_exec_single
smp_call_function_single
event_function_call
perf_event_for_each_child
_perf_ioctl
perf_ioctl
__x64_sys_ioctl
do_syscall_64
entry_SYSCALL_64
__GI___ioctl
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
Changes since v15: https://lore.kernel.org/20250825180802.725570056@kernel.org
- Have the matching deferred code only skip when TID does not match.
Otherwise, process the sample but do not merge if the cookies do not match.
(Namhyung Kim)
tools/perf/Documentation/perf-script.txt | 5 ++
tools/perf/builtin-script.c | 4 ++
tools/perf/util/callchain.c | 24 +++++++++
tools/perf/util/callchain.h | 3 ++
tools/perf/util/evlist.c | 1 +
tools/perf/util/evlist.h | 1 +
tools/perf/util/session.c | 65 +++++++++++++++++++++++-
tools/perf/util/tool.c | 1 +
tools/perf/util/tool.h | 1 +
9 files changed, 104 insertions(+), 1 deletion(-)
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 28bec7e78bc8..03d112960632 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -527,6 +527,11 @@ include::itrace.txt[]
The known limitations include exception handing such as
setjmp/longjmp will have calls/returns not match.
+--merge-callchains::
+ Enable merging deferred user callchains if available. This is the
+ default behavior. If you want to see separate CALLCHAIN_DEFERRED
+ records for some reason, use --no-merge-callchains explicitly.
+
:GMEXAMPLECMD: script
:GMEXAMPLESUBCMD:
include::guest-files.txt[]
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 03ea7b7e5bc1..70e7658a61fb 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -3785,6 +3785,7 @@ int cmd_script(int argc, const char **argv)
bool header_only = false;
bool script_started = false;
bool unsorted_dump = false;
+ bool merge_deferred_callchains = true;
char *rec_script_path = NULL;
char *rep_script_path = NULL;
struct perf_session *session;
@@ -3938,6 +3939,8 @@ int cmd_script(int argc, const char **argv)
"Guest code can be found in hypervisor process"),
OPT_BOOLEAN('\0', "stitch-lbr", &script.stitch_lbr,
"Enable LBR callgraph stitching approach"),
+ OPT_BOOLEAN('\0', "merge-callchains", &merge_deferred_callchains,
+ "Enable merge deferred user callchains"),
OPTS_EVSWITCH(&script.evswitch),
OPT_END()
};
@@ -4194,6 +4197,7 @@ int cmd_script(int argc, const char **argv)
script.tool.throttle = process_throttle_event;
script.tool.unthrottle = process_throttle_event;
script.tool.ordering_requires_timestamps = true;
+ script.tool.merge_deferred_callchains = merge_deferred_callchains;
session = perf_session__new(&data, &script.tool);
if (IS_ERR(session))
return PTR_ERR(session);
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index d7b7eef740b9..d2d672f1d6ba 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -1828,3 +1828,27 @@ int sample__for_each_callchain_node(struct thread *thread, struct evsel *evsel,
}
return 0;
}
+
+int sample__merge_deferred_callchain(struct perf_sample *sample_orig,
+ struct perf_sample *sample_callchain)
+{
+ u64 nr_orig = sample_orig->callchain->nr - PERF_DEFERRED_ITEMS;
+ u64 nr_deferred = sample_callchain->callchain->nr;
+ struct ip_callchain *callchain;
+
+ callchain = calloc(1 + nr_orig + nr_deferred, sizeof(u64));
+ if (callchain == NULL) {
+ sample_orig->deferred_callchain = false;
+ return -ENOMEM;
+ }
+
+ callchain->nr = nr_orig + nr_deferred;
+ /* copy except for the last PERF_CONTEXT_USER_DEFERRED */
+ memcpy(callchain->ips, sample_orig->callchain->ips, nr_orig * sizeof(u64));
+ /* copy deferred use callchains */
+ memcpy(&callchain->ips[nr_orig], sample_callchain->callchain->ips,
+ nr_deferred * sizeof(u64));
+
+ sample_orig->callchain = callchain;
+ return 0;
+}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 86ed9e4d04f9..89785125ed25 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -317,4 +317,7 @@ int sample__for_each_callchain_node(struct thread *thread, struct evsel *evsel,
struct perf_sample *sample, int max_stack,
bool symbols, callchain_iter_fn cb, void *data);
+int sample__merge_deferred_callchain(struct perf_sample *sample_orig,
+ struct perf_sample *sample_callchain);
+
#endif /* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 80d8387e6b97..9518b45af393 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -85,6 +85,7 @@ void evlist__init(struct evlist *evlist, struct perf_cpu_map *cpus,
evlist->ctl_fd.pos = -1;
evlist->nr_br_cntr = -1;
metricgroup__rblist_init(&evlist->metric_events);
+ INIT_LIST_HEAD(&evlist->deferred_samples);
}
struct evlist *evlist__new(void)
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 5e71e3dc6042..309ef8d78495 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -92,6 +92,7 @@ struct evlist {
* of struct metric_expr.
*/
struct rblist metric_events;
+ struct list_head deferred_samples;
};
struct evsel_str_handler {
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index a071006350f5..2527e4f18d9a 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1283,6 +1283,58 @@ static int evlist__deliver_sample(struct evlist *evlist, const struct perf_tool
per_thread);
}
+struct deferred_event {
+ struct list_head list;
+ union perf_event *event;
+};
+
+static int evlist__deliver_deferred_samples(struct evlist *evlist,
+ const struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine)
+{
+ struct deferred_event *de, *tmp;
+ struct evsel *evsel;
+ int ret = 0;
+
+ if (!tool->merge_deferred_callchains) {
+ evsel = evlist__id2evsel(evlist, sample->id);
+ return tool->callchain_deferred(tool, event, sample,
+ evsel, machine);
+ }
+
+ list_for_each_entry_safe(de, tmp, &evlist->deferred_samples, list) {
+ struct perf_sample orig_sample;
+
+ ret = evlist__parse_sample(evlist, de->event, &orig_sample);
+ if (ret < 0) {
+ pr_err("failed to parse original sample\n");
+ break;
+ }
+
+ if (sample->tid != orig_sample.tid)
+ continue;
+
+ if (event->callchain_deferred.cookie == orig_sample.deferred_cookie)
+ sample__merge_deferred_callchain(&orig_sample, sample);
+
+ evsel = evlist__id2evsel(evlist, orig_sample.id);
+ ret = evlist__deliver_sample(evlist, tool, de->event,
+ &orig_sample, evsel, machine);
+
+ if (orig_sample.deferred_callchain)
+ free(orig_sample.callchain);
+
+ list_del(&de->list);
+ free(de);
+
+ if (ret)
+ break;
+ }
+ return ret;
+}
+
static int machines__deliver_event(struct machines *machines,
struct evlist *evlist,
union perf_event *event,
@@ -1311,6 +1363,16 @@ static int machines__deliver_event(struct machines *machines,
return 0;
}
dump_sample(evsel, event, sample, perf_env__arch(machine->env));
+ if (sample->deferred_callchain && tool->merge_deferred_callchains) {
+ struct deferred_event *de = malloc(sizeof(*de));
+
+ if (de == NULL)
+ return -ENOMEM;
+
+ de->event = event;
+ list_add_tail(&de->list, &evlist->deferred_samples);
+ return 0;
+ }
return evlist__deliver_sample(evlist, tool, event, sample, evsel, machine);
case PERF_RECORD_MMAP:
return tool->mmap(tool, event, sample, machine);
@@ -1370,7 +1432,8 @@ static int machines__deliver_event(struct machines *machines,
return tool->aux_output_hw_id(tool, event, sample, machine);
case PERF_RECORD_CALLCHAIN_DEFERRED:
dump_deferred_callchain(evsel, event, sample);
- return tool->callchain_deferred(tool, event, sample, evsel, machine);
+ return evlist__deliver_deferred_samples(evlist, tool, event,
+ sample, machine);
default:
++evlist->stats.nr_unknown_events;
return -1;
diff --git a/tools/perf/util/tool.c b/tools/perf/util/tool.c
index 8bf86af1ca90..9ab9e231b5d5 100644
--- a/tools/perf/util/tool.c
+++ b/tools/perf/util/tool.c
@@ -258,6 +258,7 @@ void perf_tool__init(struct perf_tool *tool, bool ordered_events)
tool->cgroup_events = false;
tool->no_warn = false;
tool->show_feat_hdr = SHOW_FEAT_NO_HEADER;
+ tool->merge_deferred_callchains = true;
tool->sample = process_event_sample_stub;
tool->mmap = process_event_stub;
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 2676d84da80c..7165a487a485 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -88,6 +88,7 @@ struct perf_tool {
bool cgroup_events;
bool no_warn;
bool dont_split_sample_group;
+ bool merge_deferred_callchains;
enum show_feature_header show_feat_hdr;
};
--
2.50.1
^ permalink raw reply related [flat|nested] 10+ messages in thread* Re: [PATCH v16 4/4] perf tools: Merge deferred user callchains
2025-09-08 17:53 ` [PATCH v16 4/4] perf tools: Merge deferred user callchains Steven Rostedt
@ 2025-10-02 17:49 ` Steven Rostedt
2025-10-24 13:02 ` Peter Zijlstra
0 siblings, 1 reply; 10+ messages in thread
From: Steven Rostedt @ 2025-10-02 17:49 UTC (permalink / raw)
To: Steven Rostedt
Cc: linux-kernel, linux-trace-kernel, bpf, x86, Masami Hiramatsu,
Mathieu Desnoyers, Josh Poimboeuf, Peter Zijlstra, Ingo Molnar,
Jiri Olsa, Arnaldo Carvalho de Melo, Namhyung Kim,
Thomas Gleixner, Andrii Nakryiko, Indu Bhagat, Jose E. Marchesi,
Beau Belgrave, Jens Remus, Linus Torvalds, Andrew Morton,
Florian Weimer, Sam James, Kees Cook, Carlos O'Donell
On Mon, 08 Sep 2025 13:53:23 -0400
Steven Rostedt <rostedt@kernel.org> wrote:
> +static int evlist__deliver_deferred_samples(struct evlist *evlist,
> + const struct perf_tool *tool,
> + union perf_event *event,
> + struct perf_sample *sample,
> + struct machine *machine)
> +{
> + struct deferred_event *de, *tmp;
> + struct evsel *evsel;
> + int ret = 0;
> +
> + if (!tool->merge_deferred_callchains) {
> + evsel = evlist__id2evsel(evlist, sample->id);
> + return tool->callchain_deferred(tool, event, sample,
> + evsel, machine);
> + }
> +
> + list_for_each_entry_safe(de, tmp, &evlist->deferred_samples, list) {
> + struct perf_sample orig_sample;
orig_sample is not initialized and can then contain junk.
> +
> + ret = evlist__parse_sample(evlist, de->event, &orig_sample);
> + if (ret < 0) {
> + pr_err("failed to parse original sample\n");
> + break;
> + }
> +
> + if (sample->tid != orig_sample.tid)
> + continue;
> +
> + if (event->callchain_deferred.cookie == orig_sample.deferred_cookie)
> + sample__merge_deferred_callchain(&orig_sample, sample);
The sample__merge_deferred_callchain() initializes both
orig_sample.deferred_callchain and the callchain. But now that it's not
being called, it can cause the below free to happen with junk as the
callchain. This needs:
else
orig_sample.deferred_callchain = false;
> +
> + evsel = evlist__id2evsel(evlist, orig_sample.id);
> + ret = evlist__deliver_sample(evlist, tool, de->event,
> + &orig_sample, evsel,> machine); +
> + if (orig_sample.deferred_callchain)
> + free(orig_sample.callchain);
> +
> + list_del(&de->list);
> + free(de);
> +
> + if (ret)
> + break;
> + }
> + return ret;
> +}
-- Steve
^ permalink raw reply [flat|nested] 10+ messages in thread* Re: [PATCH v16 4/4] perf tools: Merge deferred user callchains
2025-10-02 17:49 ` Steven Rostedt
@ 2025-10-24 13:02 ` Peter Zijlstra
2025-10-29 0:09 ` Steven Rostedt
0 siblings, 1 reply; 10+ messages in thread
From: Peter Zijlstra @ 2025-10-24 13:02 UTC (permalink / raw)
To: Steven Rostedt
Cc: Steven Rostedt, linux-kernel, linux-trace-kernel, bpf, x86,
Masami Hiramatsu, Mathieu Desnoyers, Josh Poimboeuf, Ingo Molnar,
Jiri Olsa, Arnaldo Carvalho de Melo, Namhyung Kim,
Thomas Gleixner, Andrii Nakryiko, Indu Bhagat, Jose E. Marchesi,
Beau Belgrave, Jens Remus, Linus Torvalds, Andrew Morton,
Florian Weimer, Sam James, Kees Cook, Carlos O'Donell
On Thu, Oct 02, 2025 at 01:49:38PM -0400, Steven Rostedt wrote:
> On Mon, 08 Sep 2025 13:53:23 -0400
> Steven Rostedt <rostedt@kernel.org> wrote:
>
> > +static int evlist__deliver_deferred_samples(struct evlist *evlist,
> > + const struct perf_tool *tool,
> > + union perf_event *event,
> > + struct perf_sample *sample,
> > + struct machine *machine)
> > +{
> > + struct deferred_event *de, *tmp;
> > + struct evsel *evsel;
> > + int ret = 0;
> > +
> > + if (!tool->merge_deferred_callchains) {
> > + evsel = evlist__id2evsel(evlist, sample->id);
> > + return tool->callchain_deferred(tool, event, sample,
> > + evsel, machine);
> > + }
> > +
> > + list_for_each_entry_safe(de, tmp, &evlist->deferred_samples, list) {
> > + struct perf_sample orig_sample;
>
> orig_sample is not initialized and can then contain junk.
>
> > +
> > + ret = evlist__parse_sample(evlist, de->event, &orig_sample);
> > + if (ret < 0) {
> > + pr_err("failed to parse original sample\n");
> > + break;
> > + }
> > +
> > + if (sample->tid != orig_sample.tid)
> > + continue;
> > +
> > + if (event->callchain_deferred.cookie == orig_sample.deferred_cookie)
> > + sample__merge_deferred_callchain(&orig_sample, sample);
>
> The sample__merge_deferred_callchain() initializes both
> orig_sample.deferred_callchain and the callchain. But now that it's not
> being called, it can cause the below free to happen with junk as the
> callchain. This needs:
>
> else
> orig_sample.deferred_callchain = false;
Ah, so I saw crashes from here and just deleted both free()s and got on
with things ;-)
> > +
> > + evsel = evlist__id2evsel(evlist, orig_sample.id);
> > + ret = evlist__deliver_sample(evlist, tool, de->event,
> > + &orig_sample, evsel,> machine); +
> > + if (orig_sample.deferred_callchain)
> > + free(orig_sample.callchain);
> > +
> > + list_del(&de->list);
> > + free(de);
> > +
> > + if (ret)
> > + break;
> > + }
> > + return ret;
> > +}
>
> -- Steve
^ permalink raw reply [flat|nested] 10+ messages in thread* Re: [PATCH v16 4/4] perf tools: Merge deferred user callchains
2025-10-24 13:02 ` Peter Zijlstra
@ 2025-10-29 0:09 ` Steven Rostedt
2025-10-29 10:38 ` Peter Zijlstra
0 siblings, 1 reply; 10+ messages in thread
From: Steven Rostedt @ 2025-10-29 0:09 UTC (permalink / raw)
To: Peter Zijlstra
Cc: Steven Rostedt, linux-kernel, linux-trace-kernel, bpf, x86,
Masami Hiramatsu, Mathieu Desnoyers, Josh Poimboeuf, Ingo Molnar,
Jiri Olsa, Arnaldo Carvalho de Melo, Namhyung Kim,
Thomas Gleixner, Andrii Nakryiko, Indu Bhagat, Jose E. Marchesi,
Beau Belgrave, Jens Remus, Linus Torvalds, Andrew Morton,
Florian Weimer, Sam James, Kees Cook, Carlos O'Donell
On Fri, 24 Oct 2025 15:02:03 +0200
Peter Zijlstra <peterz@infradead.org> wrote:
> > The sample__merge_deferred_callchain() initializes both
> > orig_sample.deferred_callchain and the callchain. But now that it's not
> > being called, it can cause the below free to happen with junk as the
> > callchain. This needs:
> >
> > else
> > orig_sample.deferred_callchain = false;
>
> Ah, so I saw crashes from here and just deleted both free()s and got on
> with things ;-)
I just downloaded your tree again and it doesn't look like it was updated.
Just didn't want you to forget about this ;)
-- Steve
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [PATCH v16 4/4] perf tools: Merge deferred user callchains
2025-10-29 0:09 ` Steven Rostedt
@ 2025-10-29 10:38 ` Peter Zijlstra
0 siblings, 0 replies; 10+ messages in thread
From: Peter Zijlstra @ 2025-10-29 10:38 UTC (permalink / raw)
To: Steven Rostedt
Cc: Steven Rostedt, linux-kernel, linux-trace-kernel, bpf, x86,
Masami Hiramatsu, Mathieu Desnoyers, Josh Poimboeuf, Ingo Molnar,
Jiri Olsa, Arnaldo Carvalho de Melo, Namhyung Kim,
Thomas Gleixner, Andrii Nakryiko, Indu Bhagat, Jose E. Marchesi,
Beau Belgrave, Jens Remus, Linus Torvalds, Andrew Morton,
Florian Weimer, Sam James, Kees Cook, Carlos O'Donell
On Tue, Oct 28, 2025 at 08:09:55PM -0400, Steven Rostedt wrote:
> On Fri, 24 Oct 2025 15:02:03 +0200
> Peter Zijlstra <peterz@infradead.org> wrote:
>
> > > The sample__merge_deferred_callchain() initializes both
> > > orig_sample.deferred_callchain and the callchain. But now that it's not
> > > being called, it can cause the below free to happen with junk as the
> > > callchain. This needs:
> > >
> > > else
> > > orig_sample.deferred_callchain = false;
> >
> > Ah, so I saw crashes from here and just deleted both free()s and got on
> > with things ;-)
>
> I just downloaded your tree again and it doesn't look like it was updated.
>
> Just didn't want you to forget about this ;)
Done, this should all be in tip/perf/core now. Thanks!
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [PATCH v16 0/4] perf tool: Support the deferred unwinding infrastructure
2025-09-08 17:53 [PATCH v16 0/4] perf tool: Support the deferred unwinding infrastructure Steven Rostedt
` (3 preceding siblings ...)
2025-09-08 17:53 ` [PATCH v16 4/4] perf tools: Merge deferred user callchains Steven Rostedt
@ 2025-10-24 13:01 ` Peter Zijlstra
4 siblings, 0 replies; 10+ messages in thread
From: Peter Zijlstra @ 2025-10-24 13:01 UTC (permalink / raw)
To: Steven Rostedt
Cc: linux-kernel, linux-trace-kernel, bpf, x86, Masami Hiramatsu,
Mathieu Desnoyers, Josh Poimboeuf, Ingo Molnar, Jiri Olsa,
Arnaldo Carvalho de Melo, Namhyung Kim, Thomas Gleixner,
Andrii Nakryiko, Indu Bhagat, Jose E. Marchesi, Beau Belgrave,
Jens Remus, Linus Torvalds, Andrew Morton, Florian Weimer,
Sam James, Kees Cook, Carlos O'Donell
Per the hackery I did:
https://lkml.kernel.org/r/20251023150002.GR4067720@noisy.programming.kicks-ass.net
The userspace bits need something like so on top..
---
tools/perf/util/callchain.c | 2 +-
tools/perf/util/evsel.c | 10 +++++++---
tools/perf/util/perf_event_attr_fprintf.c | 1 +
3 files changed, 9 insertions(+), 4 deletions(-)
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -1832,7 +1832,7 @@ int sample__for_each_callchain_node(stru
int sample__merge_deferred_callchain(struct perf_sample *sample_orig,
struct perf_sample *sample_callchain)
{
- u64 nr_orig = sample_orig->callchain->nr - PERF_DEFERRED_ITEMS;
+ u64 nr_orig = sample_orig->callchain->nr - 1;
u64 nr_deferred = sample_callchain->callchain->nr;
struct ip_callchain *callchain;
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1520,6 +1520,7 @@ void evsel__config(struct evsel *evsel,
attr->mmap2 = track && !perf_missing_features.mmap2;
attr->comm = track;
attr->build_id = track && opts->build_id;
+ attr->defer_output = track && !perf_missing_features.defer_callchain;
/*
* ksymbol is tracked separately with text poke because it needs to be
@@ -2206,8 +2207,10 @@ static int __evsel__prepare_open(struct
static void evsel__disable_missing_features(struct evsel *evsel)
{
- if (perf_missing_features.defer_callchain)
+ if (perf_missing_features.defer_callchain) {
evsel->core.attr.defer_callchain = 0;
+ evsel->core.attr.defer_output = 0;
+ }
if (perf_missing_features.inherit_sample_read && evsel->core.attr.inherit &&
(evsel->core.attr.sample_type & PERF_SAMPLE_READ))
evsel->core.attr.inherit = 0;
@@ -2489,6 +2492,7 @@ static bool evsel__detect_missing_featur
perf_missing_features.defer_callchain = true;
pr_debug2("switching off deferred callchain support\n");
attr.defer_callchain = false;
+ attr.defer_output = false;
attr.sample_type = 0;
attr.inherit = true;
@@ -3255,8 +3259,8 @@ int evsel__parse_sample(struct evsel *ev
return -EFAULT;
sz = data->callchain->nr * sizeof(u64);
if (evsel->core.attr.defer_callchain &&
- data->callchain->nr >= PERF_DEFERRED_ITEMS &&
- data->callchain->ips[data->callchain->nr - PERF_DEFERRED_ITEMS] == PERF_CONTEXT_USER_DEFERRED) {
+ data->callchain->nr >= 2 &&
+ data->callchain->ips[data->callchain->nr - 2] == PERF_CONTEXT_USER_DEFERRED) {
data->deferred_callchain = true;
data->deferred_cookie = data->callchain->ips[data->callchain->nr - 1];
}
--- a/tools/perf/util/perf_event_attr_fprintf.c
+++ b/tools/perf/util/perf_event_attr_fprintf.c
@@ -344,6 +344,7 @@ int perf_event_attr__fprintf(FILE *fp, s
PRINT_ATTRf(remove_on_exec, p_unsigned);
PRINT_ATTRf(sigtrap, p_unsigned);
PRINT_ATTRf(defer_callchain, p_unsigned);
+ PRINT_ATTRf(defer_output, p_unsigned);
PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned, false);
PRINT_ATTRf(bp_type, p_unsigned);
^ permalink raw reply [flat|nested] 10+ messages in thread