On Thu, Feb 16, 2023 at 2:56 PM Joanne Koong <joannelkoong@xxxxxxxxx> wrote:
>
> Add skb dynptrs, which are dynptrs whose underlying pointer points
> to a skb. The dynptr acts on skb data. skb dynptrs have two main
> benefits. One is that they allow operations on sizes that are not
> statically known at compile-time (eg variable-sized accesses).
> Another is that parsing the packet data through dynptrs (instead of
> through direct access of skb->data and skb->data_end) can be more
> ergonomic and less brittle (eg does not need manual if checking for
> being within bounds of data_end).
>
> For bpf prog types that don't support writes on skb data, the dynptr is
> read-only (bpf_dynptr_write() will return an error)
>
> For reads and writes through the bpf_dynptr_read() and bpf_dynptr_write()
> interfaces, reading and writing from/to data in the head as well as from/to
> non-linear paged buffers is supported. Data slices through the
> bpf_dynptr_data API are not supported; instead bpf_dynptr_slice() and
> bpf_dynptr_slice_rdwr() (added in subsequent commit) should be used.
>
> For examples of how skb dynptrs can be used, please see the attached
> selftests.
>
> Signed-off-by: Joanne Koong <joannelkoong@xxxxxxxxx>
> ---
> include/linux/bpf.h | 14 ++++++-
> include/linux/filter.h | 18 ++++++++
> include/uapi/linux/bpf.h | 14 ++++++-
> kernel/bpf/btf.c | 18 ++++++++
> kernel/bpf/helpers.c | 76 +++++++++++++++++++++++++++-------
> kernel/bpf/verifier.c | 70 ++++++++++++++++++++++++++++++-
> net/core/filter.c | 67 ++++++++++++++++++++++++++++++
> tools/include/uapi/linux/bpf.h | 14 ++++++-
> 8 files changed, 270 insertions(+), 21 deletions(-)
>
> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
> index 296841a31749..3d18be35a5e6 100644
> --- a/include/linux/bpf.h
> +++ b/include/linux/bpf.h
> @@ -607,11 +607,14 @@ enum bpf_type_flag {
> */
> NON_OWN_REF = BIT(14 + BPF_BASE_TYPE_BITS),
>
> + /* DYNPTR points to sk_buff */
> + DYNPTR_TYPE_SKB = BIT(15 + BPF_BASE_TYPE_BITS),
> +
> __BPF_TYPE_FLAG_MAX,
> __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1,
> };
>
> -#define DYNPTR_TYPE_FLAG_MASK (DYNPTR_TYPE_LOCAL | DYNPTR_TYPE_RINGBUF)
> +#define DYNPTR_TYPE_FLAG_MASK (DYNPTR_TYPE_LOCAL | DYNPTR_TYPE_RINGBUF | DYNPTR_TYPE_SKB)
>
> /* Max number of base types. */
> #define BPF_BASE_TYPE_LIMIT (1UL << BPF_BASE_TYPE_BITS)
> @@ -1146,6 +1149,8 @@ enum bpf_dynptr_type {
> BPF_DYNPTR_TYPE_LOCAL,
> /* Underlying data is a ringbuf record */
> BPF_DYNPTR_TYPE_RINGBUF,
> + /* Underlying data is a sk_buff */
> + BPF_DYNPTR_TYPE_SKB,
> };
>
> int bpf_dynptr_check_size(u32 size);
> @@ -2846,6 +2851,8 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
> struct bpf_insn *insn_buf,
> struct bpf_prog *prog,
> u32 *target_size);
> +int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags,
> + struct bpf_dynptr_kern *ptr);
> #else
> static inline bool bpf_sock_common_is_valid_access(int off, int size,
> enum bpf_access_type type,
> @@ -2867,6 +2874,11 @@ static inline u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
> {
> return 0;
> }
> +static inline int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags,
> + struct bpf_dynptr_kern *ptr)
> +{
> + return 0;
should this return -EOPNOTSUPP instead?
> +}
> #endif
>
> #ifdef CONFIG_INET
[...]
