Re: [PATCH bpf-next v7 2/2] bpf: Hold the perf callchain entry until used completely

[Tao Chen <chen.dylane@linux.dev>]

在 2025/12/17 13:12, Tao Chen 写道:
> As Alexei noted, get_perf_callchain() return values may be reused
> if a task is preempted after the BPF program enters migrate disable
> mode. The perf_callchain_entres has a small stack of entries, and
> we can reuse it as follows:
> 
> 1. get the perf callchain entry
> 2. BPF use...
> 3. put the perf callchain entry
> 
> And Peter suggested that get_recursion_context used with preemption
> disabled, so we should disable preemption at BPF side.
> 
> Acked-by: Yonghong Song <yonghong.song@linux.dev>
> Signed-off-by: Tao Chen <chen.dylane@linux.dev>
> ---
>   kernel/bpf/stackmap.c | 67 +++++++++++++++++++++++++++++++++++--------
>   1 file changed, 55 insertions(+), 12 deletions(-)
> 
> diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
> index 2365541c81d..64ace4ed50e 100644
> --- a/kernel/bpf/stackmap.c
> +++ b/kernel/bpf/stackmap.c
> @@ -210,13 +210,14 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
>   }
>   
>   static struct perf_callchain_entry *
> -get_callchain_entry_for_task(struct task_struct *task, u32 max_depth)
> +get_callchain_entry_for_task(int *rctx, struct task_struct *task, u32 max_depth)
>   {
>   #ifdef CONFIG_STACKTRACE
>   	struct perf_callchain_entry *entry;
> -	int rctx;
>   
> -	entry = get_callchain_entry(&rctx);
> +	preempt_disable();
> +	entry = get_callchain_entry(rctx);
> +	preempt_enable();
>   
>   	if (!entry)
>   		return NULL;
> @@ -238,8 +239,6 @@ get_callchain_entry_for_task(struct task_struct *task, u32 max_depth)
>   			to[i] = (u64)(from[i]);
>   	}
>   
> -	put_callchain_entry(rctx);
> -
>   	return entry;
>   #else /* CONFIG_STACKTRACE */
>   	return NULL;
> @@ -320,6 +319,34 @@ static long __bpf_get_stackid(struct bpf_map *map,
>   	return id;
>   }
>   
> +static struct perf_callchain_entry *
> +bpf_get_perf_callchain(int *rctx, struct pt_regs *regs, bool kernel, bool user,
> +		       int max_stack, bool crosstask)
> +{
> +	struct perf_callchain_entry_ctx ctx;
> +	struct perf_callchain_entry *entry;
> +
> +	preempt_disable();
> +	entry = get_callchain_entry(rctx);
> +	preempt_enable();
> +
> +	if (unlikely(!entry))
> +		return NULL;
> +
> +	__init_perf_callchain_ctx(&ctx, entry, max_stack, false);
> +	if (kernel)
> +		__get_perf_callchain_kernel(&ctx, regs);
> +	if (user && !crosstask)
> +		__get_perf_callchain_user(&ctx, regs);
> +
> +	return entry;
> +}
> +
> +static void bpf_put_perf_callchain(int rctx)
> +{
> +	put_callchain_entry(rctx);
> +}
> +
>   BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
>   	   u64, flags)
>   {
> @@ -328,20 +355,24 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
>   	struct perf_callchain_entry *trace;
>   	bool kernel = !user;
>   	u32 max_depth;
> +	int rctx, ret;
>   
>   	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
>   			       BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID)))
>   		return -EINVAL;
>   
>   	max_depth = stack_map_calculate_max_depth(map->value_size, elem_size, flags);
> -	trace = get_perf_callchain(regs, kernel, user, max_depth,
> -				   false, false);
> +	trace = bpf_get_perf_callchain(&rctx, regs, kernel, user, max_depth,
> +				       false);
>   
>   	if (unlikely(!trace))
>   		/* couldn't fetch the stack trace */
>   		return -EFAULT;
>   
> -	return __bpf_get_stackid(map, trace, flags);
> +	ret = __bpf_get_stackid(map, trace, flags);
> +	bpf_put_perf_callchain(rctx);
> +
> +	return ret;
>   }
>   
>   const struct bpf_func_proto bpf_get_stackid_proto = {
> @@ -435,6 +466,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
>   	bool kernel = !user;
>   	int err = -EINVAL;
>   	u64 *ips;
> +	int rctx;
>   
>   	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
>   			       BPF_F_USER_BUILD_ID)))
> @@ -467,18 +499,26 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
>   		trace = trace_in;
>   		trace->nr = min_t(u32, trace->nr, max_depth);
>   	} else if (kernel && task) {
> -		trace = get_callchain_entry_for_task(task, max_depth);
> +		trace = get_callchain_entry_for_task(&rctx, task, max_depth);
>   	} else {
> -		trace = get_perf_callchain(regs, kernel, user, max_depth,
> -					   crosstask, false);
> +		trace = bpf_get_perf_callchain(&rctx, regs, kernel, user, max_depth,
> +					       crosstask);
>   	}
>   
> -	if (unlikely(!trace) || trace->nr < skip) {
> +	if (unlikely(!trace)) {
>   		if (may_fault)
>   			rcu_read_unlock();
>   		goto err_fault;
>   	}
>   
> +	if (trace->nr < skip) {
> +		if (may_fault)
> +			rcu_read_unlock();
> +		if (!trace_in)
> +			bpf_put_perf_callchain(rctx);
> +		goto err_fault;
> +	}
> +
>   	trace_nr = trace->nr - skip;
>   	copy_len = trace_nr * elem_size;
>   
> @@ -497,6 +537,9 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
>   	if (may_fault)
>   		rcu_read_unlock();
>   
> +	if (!trace_in)
> +		bpf_put_perf_callchain(rctx);
> +
>   	if (user_build_id)
>   		stack_map_get_build_id_offset(buf, trace_nr, user, may_fault);
>   

Hi Peter,

As requested by Alexei, I have re-sent the v7 version. Compared with the 
v6 version, the only change is the addition of the ack tag in patch2. In 
accordance with your previous suggestions, patch1 has been modified 
based on your earlier patch, and patch2 adds preempt_disable on the eBPF 
side—this does not affect the original perf logic. Please review it 
again, thank you.

-- 
Best Regards
Tao Chen