Received-SPF: pass (google.com: domain of linux-kernel+bounces-73502-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
Message-ID: <81431b5d-0e0f-485a-a3ce-af8e63169552@gmail.com>
Date: Tue, 20 Feb 2024 10:22:42 -0800
Precedence: bulk
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Subject: Re: [PATCH bpf-next 1/5] bpf: tracing: add support to record and
 check the accessed args
Content-Language: en-US
To: Menglong Dong <dongmenglong.8@bytedance.com>, andrii@kernel.org
Cc: ast@kernel.org, daniel@iogearbox.net, martin.lau@linux.dev,
 eddyz87@gmail.com, song@kernel.org, yonghong.song@linux.dev,
 john.fastabend@gmail.com, kpsingh@kernel.org, sdf@google.com,
 haoluo@google.com, jolsa@kernel.org, mykolal@fb.com, shuah@kernel.org,
 mcoquelin.stm32@gmail.com, alexandre.torgue@foss.st.com,
 thinker.li@gmail.com, zhoufeng.zf@bytedance.com, davemarchevsky@fb.com,
 dxu@dxuuu.xyz, linux-kernel@vger.kernel.org, bpf@vger.kernel.org,
 linux-kselftest@vger.kernel.org, linux-stm32@st-md-mailman.stormreply.com,
 linux-arm-kernel@lists.infradead.org
References: <20240220035105.34626-1-dongmenglong.8@bytedance.com>
 <20240220035105.34626-2-dongmenglong.8@bytedance.com>
From: Kui-Feng Lee <sinquersw@gmail.com>
In-Reply-To: <20240220035105.34626-2-dongmenglong.8@bytedance.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit


On 2/19/24 19:51, Menglong Dong wrote:
> In this commit, we add the 'accessed_args' field to struct bpf_prog_aux,
> which is used to record the accessed index of the function args in
> btf_ctx_access().
> 
> Meanwhile, we add the function btf_check_func_part_match() to compare the
> accessed function args of two function prototype. This function will be
> used in the following commit.
> 
> Signed-off-by: Menglong Dong <dongmenglong.8@bytedance.com>
> ---
>   include/linux/bpf.h |   4 ++
>   kernel/bpf/btf.c    | 121 ++++++++++++++++++++++++++++++++++++++++++++
>   2 files changed, 125 insertions(+)
> 
> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
> index c7aa99b44dbd..0225b8dbdd9d 100644
> --- a/include/linux/bpf.h
> +++ b/include/linux/bpf.h
> @@ -1464,6 +1464,7 @@ struct bpf_prog_aux {
>   	const struct btf_type *attach_func_proto;
>   	/* function name for valid attach_btf_id */
>   	const char *attach_func_name;
> +	u64 accessed_args;
>   	struct bpf_prog **func;
>   	void *jit_data; /* JIT specific data. arch dependent */
>   	struct bpf_jit_poke_descriptor *poke_tab;
> @@ -2566,6 +2567,9 @@ struct bpf_reg_state;
>   int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog);
>   int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog,
>   			 struct btf *btf, const struct btf_type *t);
> +int btf_check_func_part_match(struct btf *btf1, const struct btf_type *t1,
> +			      struct btf *btf2, const struct btf_type *t2,
> +			      u64 func_args);
>   const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt,
>   				    int comp_idx, const char *tag_key);
>   int btf_find_next_decl_tag(const struct btf *btf, const struct btf_type *pt,
> diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
> index 6ff0bd1a91d5..3a6931402fe4 100644
> --- a/kernel/bpf/btf.c
> +++ b/kernel/bpf/btf.c
> @@ -6203,6 +6203,9 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
>   		/* skip first 'void *__data' argument in btf_trace_##name typedef */
>   		args++;
>   		nr_args--;
> +		prog->aux->accessed_args |= (1 << (arg + 1));
> +	} else {
> +		prog->aux->accessed_args |= (1 << arg);
>   	}
>   
>   	if (arg > nr_args) {
> @@ -7010,6 +7013,124 @@ int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *pr
>   	return btf_check_func_type_match(log, btf1, t1, btf2, t2);
>   }
>   
> +static u32 get_ctx_arg_total_size(struct btf *btf, const struct btf_type *t)
> +{
> +	const struct btf_param *args;
> +	u32 size = 0, nr_args;
> +	int i;
> +
> +	nr_args = btf_type_vlen(t);
> +	args = (const struct btf_param *)(t + 1);
> +	for (i = 0; i < nr_args; i++) {
> +		t = btf_type_skip_modifiers(btf, args[i].type, NULL);
> +		size += btf_type_is_ptr(t) ? 8 : roundup(t->size, 8);
> +	}
> +
> +	return size;
> +}
> +
> +static int get_ctx_arg_idx_aligned(struct btf *btf, const struct btf_type *t,
> +				   int off)
> +{
> +	const struct btf_param *args;
> +	u32 offset = 0, nr_args;
> +	int i;
> +
> +	nr_args = btf_type_vlen(t);
> +	args = (const struct btf_param *)(t + 1);
> +	for (i = 0; i < nr_args; i++) {
> +		if (offset == off)
> +			return i;
> +
> +		t = btf_type_skip_modifiers(btf, args[i].type, NULL);
> +		offset += btf_type_is_ptr(t) ? 8 : roundup(t->size, 8);
> +		if (offset > off)
> +			return -1;
> +	}
> +	return -1;
> +}

This one is very similar to get_ctx_arg_idx().
How about to refactor get_ctx_arg_idx() and share the code
between get_ctx_arg_idx() and get_ctx_arg_idx_aligned().

For example,

-static u32 get_ctx_arg_idx(struct btf *btf, const struct btf_type 
*func_proto,
-                          int off)
+static u32 _get_ctx_arg_idx(struct btf *btf, const struct btf_type 
*func_proto,
+                          int off, u32 *arg_off)
  {
         const struct btf_param *args;
         const struct btf_type *t;
         u32 offset = 0, nr_args;
         int i;

         if (!func_proto)
                 return off / 8;

         nr_args = btf_type_vlen(func_proto);
         args = (const struct btf_param *)(func_proto + 1);
         for (i = 0; i < nr_args; i++) {
+               if (arg_off)
+                       *arg_off = offset;
                 t = btf_type_skip_modifiers(btf, args[i].type, NULL);
                 offset += btf_type_is_ptr(t) ? 8 : roundup(t->size, 8);
                 if (off < offset)
                         return i;
         }

+       if (arg_off)
+               *arg_off = offset;
         t = btf_type_skip_modifiers(btf, func_proto->type, NULL);
         offset += btf_type_is_ptr(t) ? 8 : roundup(t->size, 8);
         if (off < offset)
                 return nr_args;

         return nr_args + 1;
  }

+static u32 get_ctx_arg_idx(struct btf *btf, const struct btf_type 
*func_proto,
+                          int off)
+{
+       return _get_ctx_arg_idx(btf, func_proto, off, NULL);
+}
+
+static u32 get_ctx_arg_idx_aligned(struct btf *btf,
+                                  const struct btf_type *func_proto,
+                                  int off)
+{
+       u32 arg_off;
+       u32 arg_idx = _get_ctx_arg_idx(btf, func_proto, off, &arg_off);
+       return arg_off == off ? arg_idx : -1;
+}
+

> +
> +/* This function is similar to btf_check_func_type_match(), except that it
> + * only compare some function args of the function prototype t1 and t2.
> + */
> +int btf_check_func_part_match(struct btf *btf1, const struct btf_type *func1,
> +			      struct btf *btf2, const struct btf_type *func2,
> +			      u64 func_args)
> +{
> +	const struct btf_param *args1, *args2;
> +	u32 nargs1, i, offset = 0;
> +	const char *s1, *s2;
> +
> +	if (!btf_type_is_func_proto(func1) || !btf_type_is_func_proto(func2))
> +		return -EINVAL;
> +
> +	args1 = (const struct btf_param *)(func1 + 1);
> +	args2 = (const struct btf_param *)(func2 + 1);
> +	nargs1 = btf_type_vlen(func1);
> +
> +	for (i = 0; i <= nargs1; i++) {
> +		const struct btf_type *t1, *t2;
> +
> +		if (!(func_args & (1 << i)))
> +			goto next;
> +
> +		if (i < nargs1) {
> +			int t2_index;
> +
> +			/* get the index of the arg corresponding to args1[i]
> +			 * by the offset.
> +			 */
> +			t2_index = get_ctx_arg_idx_aligned(btf2, func2,
> +							   offset);
> +			if (t2_index < 0)
> +				return -EINVAL;
> +
> +			t1 = btf_type_skip_modifiers(btf1, args1[i].type, NULL);
> +			t2 = btf_type_skip_modifiers(btf2, args2[t2_index].type,
> +						     NULL);
> +		} else {
> +			/* i == nargs1, this is the index of return value of t1 */
> +			if (get_ctx_arg_total_size(btf1, func1) !=
> +			    get_ctx_arg_total_size(btf2, func2))
> +				return -EINVAL;
> +
> +			/* check the return type of t1 and t2 */
> +			t1 = btf_type_skip_modifiers(btf1, func1->type, NULL);
> +			t2 = btf_type_skip_modifiers(btf2, func2->type, NULL);
> +		}
> +
> +		if (t1->info != t2->info ||
> +		    (btf_type_has_size(t1) && t1->size != t2->size))
> +			return -EINVAL;
> +		if (btf_type_is_int(t1) || btf_is_any_enum(t1))
> +			goto next;
> +
> +		if (btf_type_is_struct(t1))
> +			goto on_struct;
> +
> +		if (!btf_type_is_ptr(t1))
> +			return -EINVAL;
> +
> +		t1 = btf_type_skip_modifiers(btf1, t1->type, NULL);
> +		t2 = btf_type_skip_modifiers(btf2, t2->type, NULL);
> +		if (!btf_type_is_struct(t1) || !btf_type_is_struct(t2))
> +			return -EINVAL;
> +
> +on_struct:
> +		s1 = btf_name_by_offset(btf1, t1->name_off);
> +		s2 = btf_name_by_offset(btf2, t2->name_off);
> +		if (strcmp(s1, s2))
> +			return -EINVAL;
> +next:
> +		if (i < nargs1) {
> +			t1 = btf_type_skip_modifiers(btf1, args1[i].type, NULL);
> +			offset += btf_type_is_ptr(t1) ? 8 : roundup(t1->size, 8);
> +		}
> +	}
> +
> +	return 0;
> +}
> +
>   static bool btf_is_dynptr_ptr(const struct btf *btf, const struct btf_type *t)
>   {
>   	const char *name;