Re: [PATCH bpf-next RESEND v4 1/2] bpf: refactor max_depth computation in bpf_get_stack()

[Martin KaFai Lau <martin.lau@linux.dev>]

On 8/19/25 9:26 AM, Arnaud Lecomte wrote:
> A new helper function stack_map_calculate_max_depth() that
> computes the max depth for a stackmap.
> 
> 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
> 
> Changes in v3:
>   - Changed map size param to size in max depth helper
> 
> Changes in v4:
>   - Fixed indentation in max depth helper for args
> 
> Link to v3: https://lore.kernel.org/all/09dc40eb-a84e-472a-8a68-36a2b1835308@linux.dev/
> 
> Signed-off-by: Arnaud Lecomte <contact@arnaud-lcm.com>
> Acked-by: Yonghong Song <yonghong.song@linux.dev>
> ---
>   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..b9cc6c72a2a5 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
> + * @size:  Size of the buffer/map value in bytes
> + * @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 size, u32 elem_size, u64 flags)
> +{
> +	u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
> +	u32 max_depth;
> +
> +	max_depth = size / elem_size;
> +	max_depth += skip;
> +	if (max_depth > sysctl_perf_event_max_stack)
> +		return sysctl_perf_event_max_stack;

hmm... this looks a bit suspicious. Is it possible that 
sysctl_perf_event_max_stack is being changed to a larger value in parallel?

> +
> +	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;

I suspect it was fine because trace_nr was still bounded by num_elem.

> +	trace_nr = min(trace_nr, max_depth - skip);

but now the min() is also based on max_depth which could be 
sysctl_perf_event_max_stack.

beside, if I read it correctly, in "max_depth - skip", the max_depth could also 
be less than skip. I assume trace->nr is bound by max_depth, so should be less 
of a problem but still a bit unintuitive to read.

>   	copy_len = trace_nr * elem_size;
>   
>   	ips = trace->ip + skip;