Re: [PATCH bpf-next v1 1/3] bpf: Add skb dynptrs

[Martin KaFai Lau <kafai@fb.com>]

On Tue, Jul 26, 2022 at 11:47:04AM -0700, Joanne Koong wrote:
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index 59a217ca2dfd..0730cd198a7f 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -5241,11 +5241,22 @@ union bpf_attr {
>   *	Description
>   *		Write *len* bytes from *src* into *dst*, starting from *offset*
>   *		into *dst*.
> - *		*flags* is currently unused.
> + *
> + *		*flags* must be 0 except for skb-type dynptrs.
> + *
> + *		For skb-type dynptrs:
> + *		    *  if *offset* + *len* extends into the skb's paged buffers, the user
> + *		       should manually pull the skb with bpf_skb_pull and then try again.
bpf_skb_pull_data().

Probably need formatting like, **bpf_skb_pull_data**\ ()

> + *
> + *		    *  *flags* are a combination of **BPF_F_RECOMPUTE_CSUM** (automatically
> + *			recompute the checksum for the packet after storing the bytes) and
> + *			**BPF_F_INVALIDATE_HASH** (set *skb*\ **->hash**, *skb*\
> + *			**->swhash** and *skb*\ **->l4hash** to 0).
>   *	Return
>   *		0 on success, -E2BIG if *offset* + *len* exceeds the length
>   *		of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst*
> - *		is a read-only dynptr or if *flags* is not 0.
> + *		is a read-only dynptr or if *flags* is not correct, -EAGAIN if for
> + *		skb-type dynptrs the write extends into the skb's paged buffers.
May also mention other negative errors is similar to the bpf_skb_store_bytes()
instead of mentioning them one-by-one here.

>   *
>   * void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len)
>   *	Description
> @@ -5253,10 +5264,19 @@ union bpf_attr {
>   *
>   *		*len* must be a statically known value. The returned data slice
>   *		is invalidated whenever the dynptr is invalidated.
> + *
> + *		For skb-type dynptrs:
> + *		    * if *offset* + *len* extends into the skb's paged buffers,
> + *		      the user should manually pull the skb with bpf_skb_pull and then
same here. bpf_skb_pull_data().

> + *		      try again.
> + *
> + *		    * the data slice is automatically invalidated anytime a
> + *		      helper call that changes the underlying packet buffer
> + *		      (eg bpf_skb_pull) is called.
>   *	Return
>   *		Pointer to the underlying dynptr data, NULL if the dynptr is
>   *		read-only, if the dynptr is invalid, or if the offset and length
> - *		is out of bounds.
> + *		is out of bounds or in a paged buffer for skb-type dynptrs.
>   *
>   * s64 bpf_tcp_raw_gen_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th, u32 th_len)
>   *	Description
> @@ -5331,6 +5351,21 @@ union bpf_attr {
>   *		**-EACCES** if the SYN cookie is not valid.
>   *
>   *		**-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin.
> + *
> + * long bpf_dynptr_from_skb(struct sk_buff *skb, u64 flags, struct bpf_dynptr *ptr)
> + *	Description
> + *		Get a dynptr to the data in *skb*. *skb* must be the BPF program
> + *		context. Depending on program type, the dynptr may be read-only,
> + *		in which case trying to obtain a direct data slice to it through
> + *		bpf_dynptr_data will return an error.
> + *
> + *		Calls that change the *skb*'s underlying packet buffer
> + *		(eg bpf_skb_pull_data) do not invalidate the dynptr, but they do
> + *		invalidate any data slices associated with the dynptr.
> + *
> + *		*flags* is currently unused, it must be 0 for now.
> + *	Return
> + *		0 on success or -EINVAL if flags is not 0.
>   */

[ ... ]

> @@ -1528,15 +1544,38 @@ static const struct bpf_func_proto bpf_dynptr_read_proto = {
>  BPF_CALL_5(bpf_dynptr_write, struct bpf_dynptr_kern *, dst, u32, offset, void *, src,
>  	   u32, len, u64, flags)
>  {
> +	enum bpf_dynptr_type type;
>  	int err;
>  
> -	if (!dst->data || flags || bpf_dynptr_is_rdonly(dst))
> +	if (!dst->data || bpf_dynptr_is_rdonly(dst))
>  		return -EINVAL;
>  
>  	err = bpf_dynptr_check_off_len(dst, offset, len);
>  	if (err)
>  		return err;
>  
> +	type = bpf_dynptr_get_type(dst);
> +
> +	if (flags) {
> +		if (type == BPF_DYNPTR_TYPE_SKB) {
> +			if (flags & ~(BPF_F_RECOMPUTE_CSUM | BPF_F_INVALIDATE_HASH))
nit.  The flags is the same as __bpf_skb_store_bytes().  __bpf_skb_store_bytes()
can reject as well instead of duplicating the test here.

> +				return -EINVAL;
> +		} else {
> +			return -EINVAL;
> +		}
> +	}
> +
> +	if (type == BPF_DYNPTR_TYPE_SKB) {
> +		struct sk_buff *skb = dst->data;
> +
> +		/* if the data is paged, the caller needs to pull it first */
> +		if (dst->offset + offset + len > skb->len - skb->data_len)
> +			return -EAGAIN;
> +
> +		return __bpf_skb_store_bytes(skb, dst->offset + offset, src, len,
> +					     flags);
> +	}
> +