bpf: add skb_load_bytes_relative helper

This adds a small BPF helper similar to bpf_skb_load_bytes() that
is able to load relative to mac/net header offset from the skb's
linear data. Compared to bpf_skb_load_bytes(), it takes a fifth
argument namely start_header, which is either BPF_HDR_START_MAC
or BPF_HDR_START_NET. This allows for a more flexible alternative
compared to LD_ABS/LD_IND with negative offset. It's enabled for
tc BPF programs as well as sock filter program types where it's
mainly useful in reuseport programs to ease access to lower header
data.

Reference: https://lists.iovisor.org/pipermail/iovisor-dev/2017-March/000698.html
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index a3a49505251117bab031d218c6bf99e8da8ca63b..93d5a4eeec2a6493e5e68ecadbd7ec5a13c96685 100644 (file)
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1802,6 +1802,30 @@ union bpf_attr {
  *     Return
  *             a non-negative value equal to or less than size on success, or
  *             a negative error in case of failure.
+ *
+ * int skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header)
+ *     Description
+ *             This helper is similar to **bpf_skb_load_bytes**\ () in that
+ *             it provides an easy way to load *len* bytes from *offset*
+ *             from the packet associated to *skb*, into the buffer pointed
+ *             by *to*. The difference to **bpf_skb_load_bytes**\ () is that
+ *             a fifth argument *start_header* exists in order to select a
+ *             base offset to start from. *start_header* can be one of:
+ *
+ *             **BPF_HDR_START_MAC**
+ *                     Base offset to load data from is *skb*'s mac header.
+ *             **BPF_HDR_START_NET**
+ *                     Base offset to load data from is *skb*'s network header.
+ *
+ *             In general, "direct packet access" is the preferred method to
+ *             access packet data, however, this helper is in particular useful
+ *             in socket filters where *skb*\ **->data** does not always point
+ *             to the start of the mac header and where "direct packet access"
+ *             is not available.
+ *
+ *     Return
+ *             0 on success, or a negative error in case of failure.
+ *
  */
 #define __BPF_FUNC_MAPPER(FN)          \
        FN(unspec),                     \
@@ -1871,7 +1895,8 @@ union bpf_attr {
        FN(bind),                       \
        FN(xdp_adjust_tail),            \
        FN(skb_get_xfrm_state),         \
-       FN(get_stack),
+       FN(get_stack),                  \
+       FN(skb_load_bytes_relative),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -1932,6 +1957,12 @@ enum bpf_adj_room_mode {
        BPF_ADJ_ROOM_NET,
 };
 
+/* Mode for BPF_FUNC_skb_load_bytes_relative helper. */
+enum bpf_hdr_start_off {
+       BPF_HDR_START_MAC,
+       BPF_HDR_START_NET,
+};
+
 /* user accessible mirror of in-kernel sk_buff.
  * new fields can only be added to the end of this structure
  */

diff --git a/net/core/filter.c b/net/core/filter.c
index a49729842b3d9aec6bda08e6fb98623e52c97745..6877426c23a682809bb8349ed461b18d7fe3012d 100644 (file)
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1684,6 +1684,47 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = {
        .arg4_type      = ARG_CONST_SIZE,
 };
 
+BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb,
+          u32, offset, void *, to, u32, len, u32, start_header)
+{
+       u8 *ptr;
+
+       if (unlikely(offset > 0xffff || len > skb_headlen(skb)))
+               goto err_clear;
+
+       switch (start_header) {
+       case BPF_HDR_START_MAC:
+               ptr = skb_mac_header(skb) + offset;
+               break;
+       case BPF_HDR_START_NET:
+               ptr = skb_network_header(skb) + offset;
+               break;
+       default:
+               goto err_clear;
+       }
+
+       if (likely(ptr >= skb_mac_header(skb) &&
+                  ptr + len <= skb_tail_pointer(skb))) {
+               memcpy(to, ptr, len);
+               return 0;
+       }
+
+err_clear:
+       memset(to, 0, len);
+       return -EFAULT;
+}
+
+static const struct bpf_func_proto bpf_skb_load_bytes_relative_proto = {
+       .func           = bpf_skb_load_bytes_relative,
+       .gpl_only       = false,
+       .ret_type       = RET_INTEGER,
+       .arg1_type      = ARG_PTR_TO_CTX,
+       .arg2_type      = ARG_ANYTHING,
+       .arg3_type      = ARG_PTR_TO_UNINIT_MEM,
+       .arg4_type      = ARG_CONST_SIZE,
+       .arg5_type      = ARG_ANYTHING,
+};
+
 BPF_CALL_2(bpf_skb_pull_data, struct sk_buff *, skb, u32, len)
 {
        /* Idea is the following: should the needed direct read/write
@@ -4061,6 +4102,8 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
        switch (func_id) {
        case BPF_FUNC_skb_load_bytes:
                return &bpf_skb_load_bytes_proto;
+       case BPF_FUNC_skb_load_bytes_relative:
+               return &bpf_skb_load_bytes_relative_proto;
        case BPF_FUNC_get_socket_cookie:
                return &bpf_get_socket_cookie_proto;
        case BPF_FUNC_get_socket_uid:
@@ -4078,6 +4121,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
                return &bpf_skb_store_bytes_proto;
        case BPF_FUNC_skb_load_bytes:
                return &bpf_skb_load_bytes_proto;
+       case BPF_FUNC_skb_load_bytes_relative:
+               return &bpf_skb_load_bytes_relative_proto;
        case BPF_FUNC_skb_pull_data:
                return &bpf_skb_pull_data_proto;
        case BPF_FUNC_csum_diff: