Thanks Yonghong for your feedbacks and your patience !
On 12/08/2025 05:39, Yonghong Song wrote:
On 8/9/25 5:09 AM, Arnaud Lecomte wrote:
A new helper function stack_map_calculate_max_depth() that
computes the max depth for a stackmap.
Please add 'bpf-next' in the subject like [PATCH bpf-next v2 1/2]
so CI can properly test the patch set.
Changes in v2:
- Removed the checking 'map_size % map_elem_size' from
stack_map_calculate_max_depth
- Changed stack_map_calculate_max_depth params name to be more generic
Signed-off-by: Arnaud Lecomte <contact@xxxxxxxxxxxxxx>
---
kernel/bpf/stackmap.c | 30 ++++++++++++++++++++++++------
1 file changed, 24 insertions(+), 6 deletions(-)
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 3615c06b7dfa..532447606532 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -42,6 +42,27 @@ static inline int stack_map_data_size(struct
bpf_map *map)
sizeof(struct bpf_stack_build_id) : sizeof(u64);
}
+/**
+ * stack_map_calculate_max_depth - Calculate maximum allowed stack
trace depth
+ * @map_size: Size of the buffer/map value in bytes
let us rename 'map_size' to 'size' since the size represents size of
buffer or map, not just for map.
+ * @elem_size: Size of each stack trace element
+ * @flags: BPF stack trace flags (BPF_F_USER_STACK,
BPF_F_USER_BUILD_ID, ...)
+ *
+ * Return: Maximum number of stack trace entries that can be safely
stored
+ */
+static u32 stack_map_calculate_max_depth(u32 map_size, u32
elem_size, u64 flags)
map_size -> size
Also, you can replace 'flags' to 'skip', so below 'u32 skip = flags &
BPF_F_SKIP_FIELD_MASK'
is not necessary.
+{
+ u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
+ u32 max_depth;
+
+ max_depth = map_size / elem_size;
+ max_depth += skip;
+ if (max_depth > sysctl_perf_event_max_stack)
+ return sysctl_perf_event_max_stack;
+
+ return max_depth;
+}
+
static int prealloc_elems_and_freelist(struct bpf_stack_map *smap)
{
u64 elem_size = sizeof(struct stack_map_bucket) +
@@ -406,7 +427,7 @@ static long __bpf_get_stack(struct pt_regs *regs,
struct task_struct *task,
struct perf_callchain_entry *trace_in,
void *buf, u32 size, u64 flags, bool may_fault)
{
- u32 trace_nr, copy_len, elem_size, num_elem, max_depth;
+ u32 trace_nr, copy_len, elem_size, max_depth;
bool user_build_id = flags & BPF_F_USER_BUILD_ID;
bool crosstask = task && task != current;
u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
@@ -438,10 +459,7 @@ static long __bpf_get_stack(struct pt_regs
*regs, struct task_struct *task,
goto clear;
}
- num_elem = size / elem_size;
- max_depth = num_elem + skip;
- if (sysctl_perf_event_max_stack < max_depth)
- max_depth = sysctl_perf_event_max_stack;
+ max_depth = stack_map_calculate_max_depth(size, elem_size, flags);
if (may_fault)
rcu_read_lock(); /* need RCU for perf's callchain below */
@@ -461,7 +479,7 @@ static long __bpf_get_stack(struct pt_regs *regs,
struct task_struct *task,
}
trace_nr = trace->nr - skip;
- trace_nr = (trace_nr <= num_elem) ? trace_nr : num_elem;
+ trace_nr = min(trace_nr, max_depth - skip);
copy_len = trace_nr * elem_size;
ips = trace->ip + skip;
