Skip to contentSkip to conversation

perf/core: Include attr.defer_output in is_sb_event()

PATCH Applied Ian Rogers 3 participants 8 messages Oct 25 – Nov 6

Subsystems (2)
lore
Share & tools
lore

Ian Rogers

author reviewer
#0 lore raw

PATCH 1/2 perf/core: Include attr.defer_output in is_sb_event()

Events configured with attr.defer_output = 1 receive deferred callchain sideband records (PERF_RECORD_CALLCHAIN_DEFERRED) via perf_iterate_sb(). Include attr->defer_output in is_sb_event() so that such events are attached to the sideband event list even when no other sideband flags (such as mmap or comm) are enabled on the event.

Fixes c69993ecdd4d ("perf: Support deferred user unwind")
---
 kernel/events/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
kernel/events/core.c +1 -1
index c4217c996f5a..b43883a42566 100644
@@ -5347,7 +5347,7 @@ static bool is_sb_event(struct perf_event *event)
 	    attr->comm || attr->comm_exec ||
 	    attr->task || attr->ksymbol ||
 	    attr->context_switch || attr->text_poke ||
-	    attr->bpf_event)
+	    attr->bpf_event || attr->defer_output)
 		return true;
 
 	return false;
Signature · 1 line
2.56.0.307.g5fe7bd680c-goog
author reviewer
#1 lore raw

PATCH 2/2 perf/core: Clamp deferred callchain entry count to fit u16 header.size

In perf_callchain_deferred_output(), if trace->nr is large enough that sizeof(deferred_event->event) + trace->nr * sizeof(u64) + id_header_size exceeds U16_MAX, header.size wraps while the output loop still writes all trace->nr entries into the ring buffer. Clamp nr per event (accounting for event->id_header_size when sample_id_all is enabled) so the record never overflows u16 header.size.

Fixes c69993ecdd4d ("perf: Support deferred user unwind")
---
 kernel/events/core.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)
kernel/events/core.c +11 -5
index b43883a42566..37824ca7fe97 100644
@@ -10385,8 +10385,6 @@ struct perf_callchain_deferred_event {
 	struct {
 		struct perf_event_header	header;
 		u64				cookie;
-		u64				nr;
-		u64				ips[];
 	} event;
 };
 
@@ -10395,12 +10393,19 @@ static void perf_callchain_deferred_output(struct perf_event *event, void *data)
 	struct perf_callchain_deferred_event *deferred_event = data;
 	struct perf_output_handle handle;
 	struct perf_sample_data sample;
+	u64 nr = deferred_event->trace->nr;
+	u16 size, id_size, max_payload;
 	int ret;
-	u16 size = sizeof(deferred_event->event) + (deferred_event->trace->nr * sizeof(u64));
 
 	if (!event->attr.defer_output)
 		return;
 
+	id_size = event->attr.sample_id_all ? event->id_header_size : 0;
+	max_payload = round_down(U16_MAX - sizeof(deferred_event->event) -
+				 sizeof(u64) - id_size, sizeof(u64));
+	nr = min_t(u64, nr, max_payload / sizeof(u64));
+	size = sizeof(deferred_event->event) + sizeof(u64) + nr * sizeof(u64);
+
 	/* XXX do we really need sample_id_all for this ??? */
 	perf_event_header__init(&deferred_event->event.header, &sample,
 				PERF_RECORD_CALLCHAIN_DEFERRED,
@@ -10414,8 +10419,10 @@ static void perf_callchain_deferred_output(struct perf_event *event, void *data)
 		return;
 
 	perf_output_put(&handle, deferred_event->event);
-	for (int i = 0; i < deferred_event->trace->nr; i++) {
+	perf_output_put(&handle, nr);
+	for (u64 i = 0; i < nr; i++) {
 		u64 entry = deferred_event->trace->entries[i];
+
 		perf_output_put(&handle, entry);
 	}
 	perf_event__output_id_sample(event, &handle, &sample);
@@ -10430,7 +10437,6 @@ static void perf_unwind_deferred_callback(struct unwind_work *work,
 		.trace = trace,
 		.event = {
 			.cookie = cookie,
-			.nr = trace->nr,
 		},
 	};
 
Signature · 1 line
2.56.0.307.g5fe7bd680c-goog
#2 lore raw

Re: [PATCH v1 2/2] perf/core: Clamp deferred callchain entry count to fit u16 header.size

Sashiko has reviewed this patch and found no issues.
Quoted 9 lines

In perf_callchain_deferred_output(), if trace->nr is large enough that sizeof(deferred_event->event) + trace->nr * sizeof(u64) + id_header_size exceeds U16_MAX, header.size wraps while the output loop still writes all trace->nr entries into the ring buffer. Clamp nr per event (accounting for event->id_header_size when sample_id_all is enabled) so the record never overflows u16 header.size.

Fixes c69993ecdd4d ("perf: Support deferred user unwind")

Sashiko has reviewed this patch and found no issues.

Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=2
author reviewer
#3 lore raw

Re: [PATCH v1 2/2] perf/core: Clamp deferred callchain entry count to fit u16 header.size

In reply to Ian Rogers
Quoted 10 lines · Ian Rogers

In perf_callchain_deferred_output(), if trace->nr is large enough that sizeof(deferred_event->event) + trace->nr * sizeof(u64) + id_header_size exceeds U16_MAX, header.size wraps while the output loop still writes all trace->nr entries into the ring buffer. Clamp nr per event (accounting for event->id_header_size when sample_id_all is enabled) so the record never overflows u16 header.size.

Fixes c69993ecdd4d ("perf: Support deferred user unwind")

Ping. +Steve and Masami

Thanks,
Ian

Quoted 61 lines
---
 kernel/events/core.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)
kernel/events/core.c +11 -6
index b43883a42566..37824ca7fe97 100644
@@ -10385,8 +10385,6 @@ struct perf_callchain_deferred_event {
        struct {
                struct perf_event_header        header;
                u64                             cookie;
-               u64                             nr;
-               u64                             ips[];
        } event;
 };
 
@@ -10395,12 +10393,19 @@ static void perf_callchain_deferred_output(struct perf_event *event, void *data)
        struct perf_callchain_deferred_event *deferred_event = data;
        struct perf_output_handle handle;
        struct perf_sample_data sample;
+       u64 nr = deferred_event->trace->nr;
+       u16 size, id_size, max_payload;
        int ret;
-       u16 size = sizeof(deferred_event->event) + (deferred_event->trace->nr * sizeof(u64));
 
        if (!event->attr.defer_output)
                return;
 
+       id_size = event->attr.sample_id_all ? event->id_header_size : 0;
+       max_payload = round_down(U16_MAX - sizeof(deferred_event->event) -
+                                sizeof(u64) - id_size, sizeof(u64));
+       nr = min_t(u64, nr, max_payload / sizeof(u64));
+       size = sizeof(deferred_event->event) + sizeof(u64) + nr * sizeof(u64);
+
        /* XXX do we really need sample_id_all for this ??? */
        perf_event_header__init(&deferred_event->event.header, &sample,
                                PERF_RECORD_CALLCHAIN_DEFERRED,
@@ -10414,8 +10419,10 @@ static void perf_callchain_deferred_output(struct perf_event *event, void *data)
                return;
 
        perf_output_put(&handle, deferred_event->event);
-       for (int i = 0; i < deferred_event->trace->nr; i++) {
+       perf_output_put(&handle, nr);
+       for (u64 i = 0; i < nr; i++) {
                u64 entry = deferred_event->trace->entries[i];
+
                perf_output_put(&handle, entry);
        }
        perf_event__output_id_sample(event, &handle, &sample);
@@ -10430,7 +10437,6 @@ static void perf_unwind_deferred_callback(struct unwind_work *work,
                .trace = trace,
                .event = {
                        .cookie = cookie,
-                       .nr = trace->nr,
                },
        };
 
--

2.56.0.307.g5fe7bd680c-goog

merge bot Applied
#4 lore raw

[tip: perf/urgent] perf/core: Clamp deferred callchain entry count to fit u16 header.size

In reply to Ian Rogers
The following commit has been merged into the perf/urgent branch of tip:

The following commit has been merged into the perf/urgent branch of tip:

Commit-ID:     5e4d83fb3616ebf807df1ce1b0ee7a8cdcb5ff87
Gitweb:        https://git.kernel.org/tip/5e4d83fb3616ebf807df1ce1b0ee7a8cdcb5ff87
Author:        Ian Rogers <[email protected]>
AuthorDate:    Sun, 25 Oct 2026 14:55:08 -07:00
Committer:     Ingo Molnar <[email protected]>
CommitterDate: Fri, 06 Nov 2026 09:39:43 +01:00

perf/core: Clamp deferred callchain entry count to fit u16 header.size

In perf_callchain_deferred_output(), if trace->nr is large enough that sizeof(deferred_event->event) + trace->nr * sizeof(u64) + id_header_size exceeds U16_MAX, header.size wraps while the output loop still writes all trace->nr entries into the ring buffer.

Clamp nr per event (accounting for event->id_header_size when sample_id_all is enabled) so the record never overflows u16 header.size.

---
 kernel/events/core.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)
kernel/events/core.c +11 -5
index 6cbd701..580590b 100644
@@ -10514,8 +10514,6 @@ struct perf_callchain_deferred_event {
 	struct {
 		struct perf_event_header	header;
 		u64				cookie;
-		u64				nr;
-		u64				ips[];
 	} event;
 };
 
@@ -10524,12 +10522,19 @@ static void perf_callchain_deferred_output(struct perf_event *event, void *data)
 	struct perf_callchain_deferred_event *deferred_event = data;
 	struct perf_output_handle handle;
 	struct perf_sample_data sample;
+	u64 nr = deferred_event->trace->nr;
+	u16 size, id_size, max_payload;
 	int ret;
-	u16 size = sizeof(deferred_event->event) + (deferred_event->trace->nr * sizeof(u64));
 
 	if (!event->attr.defer_output)
 		return;
 
+	id_size = event->attr.sample_id_all ? event->id_header_size : 0;
+	max_payload = round_down(U16_MAX - sizeof(deferred_event->event) -
+				 sizeof(u64) - id_size, sizeof(u64));
+	nr = min_t(u64, nr, max_payload / sizeof(u64));
+	size = sizeof(deferred_event->event) + sizeof(u64) + nr * sizeof(u64);
+
 	/* XXX do we really need sample_id_all for this ??? */
 	perf_event_header__init(&deferred_event->event.header, &sample,
 				PERF_RECORD_CALLCHAIN_DEFERRED,
@@ -10543,8 +10548,10 @@ static void perf_callchain_deferred_output(struct perf_event *event, void *data)
 		return;
 
 	perf_output_put(&handle, deferred_event->event);
-	for (int i = 0; i < deferred_event->trace->nr; i++) {
+	perf_output_put(&handle, nr);
+	for (u64 i = 0; i < nr; i++) {
 		u64 entry = deferred_event->trace->entries[i];
+
 		perf_output_put(&handle, entry);
 	}
 	perf_event__output_id_sample(event, &handle, &sample);
@@ -10559,7 +10566,6 @@ static void perf_unwind_deferred_callback(struct unwind_work *work,
 		.trace = trace,
 		.event = {
 			.cookie = cookie,
-			.nr = trace->nr,
 		},
 	};
 
#5 lore raw
In reply to Ian Rogers
Sashiko has reviewed this patch and found no issues.
Quoted 8 lines

Events configured with attr.defer_output = 1 receive deferred callchain sideband records (PERF_RECORD_CALLCHAIN_DEFERRED) via perf_iterate_sb(). Include attr->defer_output in is_sb_event() so that such events are attached to the sideband event list even when no other sideband flags (such as mmap or comm) are enabled on the event.

Fixes c69993ecdd4d ("perf: Support deferred user unwind")

Sashiko has reviewed this patch and found no issues.

Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=1
author reviewer
#6 lore raw
In reply to Ian Rogers
Quoted 9 lines · Ian Rogers

Events configured with attr.defer_output = 1 receive deferred callchain sideband records (PERF_RECORD_CALLCHAIN_DEFERRED) via perf_iterate_sb(). Include attr->defer_output in is_sb_event() so that such events are attached to the sideband event list even when no other sideband flags (such as mmap or comm) are enabled on the event.

Fixes c69993ecdd4d ("perf: Support deferred user unwind")

Ping. +Steve and Masami

Thanks,
Ian

Quoted 20 lines
---
 kernel/events/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
kernel/events/core.c +1 -2
index c4217c996f5a..b43883a42566 100644
@@ -5347,7 +5347,7 @@ static bool is_sb_event(struct perf_event *event)
            attr->comm || attr->comm_exec ||
            attr->task || attr->ksymbol ||
            attr->context_switch || attr->text_poke ||
-           attr->bpf_event)
+           attr->bpf_event || attr->defer_output)
                return true;
 
        return false;
--

2.56.0.307.g5fe7bd680c-goog

merge bot Applied
#7 lore raw

[tip: perf/urgent] perf/core: Include perf_event_attr::defer_output in is_sb_event() check

In reply to Ian Rogers
The following commit has been merged into the perf/urgent branch of tip:

The following commit has been merged into the perf/urgent branch of tip:

Commit-ID:     772f38fc69d5cf22f13b43dec30c2bbc5bdf4eb8
Gitweb:        https://git.kernel.org/tip/772f38fc69d5cf22f13b43dec30c2bbc5bdf4eb8
Author:        Ian Rogers <[email protected]>
AuthorDate:    Sun, 25 Oct 2026 14:55:07 -07:00
Committer:     Ingo Molnar <[email protected]>
CommitterDate: Fri, 06 Nov 2026 09:38:16 +01:00

perf/core: Include perf_event_attr::defer_output in is_sb_event() check

Events configured with attr.defer_output = 1 receive deferred callchain sideband records (PERF_RECORD_CALLCHAIN_DEFERRED) via perf_iterate_sb().

Include attr->defer_output in is_sb_event() so that such events are attached to the sideband event list even when no other sideband flags (such as mmap or comm) are enabled on the event.

---
 kernel/events/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
kernel/events/core.c +1 -1
index 457d75e..6cbd701 100644
@@ -5356,7 +5356,7 @@ static bool is_sb_event(struct perf_event *event)
 	    attr->comm || attr->comm_exec ||
 	    attr->task || attr->ksymbol ||
 	    attr->context_switch || attr->text_poke ||
-	    attr->bpf_event)
+	    attr->bpf_event || attr->defer_output)
 		return true;
 
 	return false;