[Patch v7 23/24] perf/core: Don't mutate shared branch stack depth
From: Dapeng Mi
Date: Tue Nov 17 2026 - 22:25:33 EST
perf_sample_save_brstack() clamps the branch stack depth by directly
overwriting brs->nr with min(event->attr.sample_max_stack, brs->nr).
This is unsafe because the branch stack buffer is shared by all branch
events in the same PMI: once one event with a small sample_max_stack
truncates brs->nr, every subsequent event processed in that PMI sees
the shrunken depth and silently loses branch records it asked for.
Add perf_event_brstack_depth(), which computes the per-event depth
without modifying the shared branch stack. Use it in the relevant callers
so each event is limited only by its own sample_max_stack, without
clobbering the shared LBR state.
bpf_read_branch_records() also relied on the clamped brs->nr, so switch
it to perf_event_brstack_depth() to preserve the same per-event limit for
records returned to BPF programs.
Fixes: c53e14f1ea4a ("perf: Extend per event callchain limit to branch stack")
Reported-by: Sashiko <sashiko-bot@xxxxxxxxxx>
Signed-off-by: Dapeng Mi <dapeng1.mi@xxxxxxxxxxxxxxx>
Cc: KP Singh <kpsingh@xxxxxxxxxx>
Cc: Matt Bobrowski <matt@xxxxxxxxxxxxx>
Cc: Song Liu <song@xxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Ihor Solodrai <ihor.solodrai@xxxxxxxxx>
Cc: Daniel Xu <dxu@xxxxxxxxx>
---
include/linux/perf_event.h | 13 ++++++++++---
kernel/events/core.c | 8 ++++----
kernel/trace/bpf_trace.c | 6 ++++--
3 files changed, 18 insertions(+), 9 deletions(-)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 19de3f1cbd6e..35d3cc4cc07e 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1424,12 +1424,19 @@ static inline bool has_branch_stack(struct perf_event *event)
return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK;
}
+static inline u64 perf_event_brstack_depth(struct perf_event *event,
+ struct perf_branch_stack *brs)
+{
+ return min_t(u16, event->attr.sample_max_stack, brs->nr);
+}
+
static inline void perf_sample_save_brstack(struct perf_sample_data *data,
struct perf_event *event,
struct perf_branch_stack *brs,
u64 *brs_cntr)
{
int size = sizeof(u64); /* nr */
+ u64 nr;
if (!has_branch_stack(event))
return;
@@ -1439,9 +1446,9 @@ static inline void perf_sample_save_brstack(struct perf_sample_data *data,
if (branch_sample_hw_index(event))
size += sizeof(u64);
- brs->nr = min_t(u16, event->attr.sample_max_stack, brs->nr);
+ nr = perf_event_brstack_depth(event, brs);
- size += brs->nr * sizeof(struct perf_branch_entry);
+ size += nr * sizeof(struct perf_branch_entry);
/*
* The extension space for counters is appended after the
@@ -1449,7 +1456,7 @@ static inline void perf_sample_save_brstack(struct perf_sample_data *data,
* of events of each branch.
*/
if (brs_cntr)
- size += brs->nr * sizeof(u64);
+ size += nr * sizeof(u64);
data->br_stack = brs;
data->br_stack_cntr = brs_cntr;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 457d75ea7142..8b80ca788523 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8462,12 +8462,12 @@ void perf_output_sample(struct perf_output_handle *handle,
if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
if (data->br_stack) {
+ u64 nr = perf_event_brstack_depth(event, data->br_stack);
size_t size;
- size = data->br_stack->nr
- * sizeof(struct perf_branch_entry);
+ size = nr * sizeof(struct perf_branch_entry);
- perf_output_put(handle, data->br_stack->nr);
+ perf_output_put(handle, nr);
if (branch_sample_hw_index(event))
perf_output_put(handle, data->br_stack->hw_idx);
perf_output_copy(handle, data->br_stack->entries, size);
@@ -8476,7 +8476,7 @@ void perf_output_sample(struct perf_output_handle *handle,
* right after the struct perf_branch_stack.
*/
if (data->br_stack_cntr) {
- size = data->br_stack->nr * sizeof(u64);
+ size = nr * sizeof(u64);
perf_output_copy(handle, data->br_stack_cntr, size);
}
} else {
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 2aec56d7f3d3..7c42bbf05c2f 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1549,6 +1549,7 @@ BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx,
static const u32 br_entry_size = sizeof(struct perf_branch_entry);
struct perf_branch_stack *br_stack = ctx->data->br_stack;
u32 to_copy;
+ u64 nr;
if (unlikely(flags & ~BPF_F_GET_BRANCH_RECORDS_SIZE))
return -EINVAL;
@@ -1559,13 +1560,14 @@ BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx,
if (unlikely(!br_stack))
return -ENOENT;
+ nr = perf_event_brstack_depth(ctx->event, br_stack);
if (flags & BPF_F_GET_BRANCH_RECORDS_SIZE)
- return br_stack->nr * br_entry_size;
+ return nr * br_entry_size;
if (!buf || (size % br_entry_size != 0))
return -EINVAL;
- to_copy = min_t(u32, br_stack->nr * br_entry_size, size);
+ to_copy = min_t(u32, nr * br_entry_size, size);
memcpy(buf, br_stack->entries, to_copy);
return to_copy;
--
2.34.1