bpf: allow BPF read access to qdisc pkt_len

The pkt_len field in qdisc_skb_cb stores the skb length as it will
appear on the wire after segmentation. For byte accounting, this value
is more accurate than skb->len. It is computed on entry to the TC
layer, so only valid there.

Allow read access to this field from BPF tc classifier and action
programs. The implementation is analogous to tc_classid, aside from
restricting to read access.

To distinguish it from skb->len and self-describe export as wire_len.

Changes v1->v2
  - Rename pkt_len to wire_len

Signed-off-by: Petar Penkov <ppenkov@google.com>
Signed-off-by: Vlad Dumitrescu <vladum@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
This commit is contained in:
Petar Penkov 2018-12-02 20:18:19 -05:00 committed by Daniel Borkmann
parent de94b651ee
commit e3da08d057
4 changed files with 50 additions and 0 deletions

View File

@ -2497,6 +2497,7 @@ struct __sk_buff {
__u32 data_meta;
struct bpf_flow_keys *flow_keys;
__u64 tstamp;
__u32 wire_len;
};
struct bpf_tunnel_key {

View File

@ -5773,6 +5773,7 @@ static bool sk_filter_is_valid_access(int off, int size,
case bpf_ctx_range(struct __sk_buff, flow_keys):
case bpf_ctx_range_till(struct __sk_buff, family, local_port):
case bpf_ctx_range(struct __sk_buff, tstamp):
case bpf_ctx_range(struct __sk_buff, wire_len):
return false;
}
@ -5797,6 +5798,7 @@ static bool cg_skb_is_valid_access(int off, int size,
case bpf_ctx_range(struct __sk_buff, tc_classid):
case bpf_ctx_range(struct __sk_buff, data_meta):
case bpf_ctx_range(struct __sk_buff, flow_keys):
case bpf_ctx_range(struct __sk_buff, wire_len):
return false;
case bpf_ctx_range(struct __sk_buff, data):
case bpf_ctx_range(struct __sk_buff, data_end):
@ -5843,6 +5845,7 @@ static bool lwt_is_valid_access(int off, int size,
case bpf_ctx_range(struct __sk_buff, data_meta):
case bpf_ctx_range(struct __sk_buff, flow_keys):
case bpf_ctx_range(struct __sk_buff, tstamp):
case bpf_ctx_range(struct __sk_buff, wire_len):
return false;
}
@ -6273,6 +6276,7 @@ static bool sk_skb_is_valid_access(int off, int size,
case bpf_ctx_range(struct __sk_buff, data_meta):
case bpf_ctx_range(struct __sk_buff, flow_keys):
case bpf_ctx_range(struct __sk_buff, tstamp):
case bpf_ctx_range(struct __sk_buff, wire_len):
return false;
}
@ -6360,6 +6364,7 @@ static bool flow_dissector_is_valid_access(int off, int size,
case bpf_ctx_range(struct __sk_buff, data_meta):
case bpf_ctx_range_till(struct __sk_buff, family, local_port):
case bpf_ctx_range(struct __sk_buff, tstamp):
case bpf_ctx_range(struct __sk_buff, wire_len):
return false;
}
@ -6685,6 +6690,17 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type,
bpf_target_off(struct sk_buff,
tstamp, 8,
target_size));
break;
case offsetof(struct __sk_buff, wire_len):
BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, pkt_len) != 4);
off = si->off;
off -= offsetof(struct __sk_buff, wire_len);
off += offsetof(struct sk_buff, cb);
off += offsetof(struct qdisc_skb_cb, pkt_len);
*target_size = 4;
*insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, off);
}
return insn - insn_buf;

View File

@ -2497,6 +2497,7 @@ struct __sk_buff {
__u32 data_meta;
struct bpf_flow_keys *flow_keys;
__u64 tstamp;
__u32 wire_len;
};
struct bpf_tunnel_key {

View File

@ -14033,6 +14033,38 @@ static struct bpf_test tests[] = {
.result_unpriv = REJECT,
.result = ACCEPT,
},
{
"check wire_len is not readable by sockets",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
offsetof(struct __sk_buff, wire_len)),
BPF_EXIT_INSN(),
},
.errstr = "invalid bpf_context access",
.result = REJECT,
},
{
"check wire_len is readable by tc classifier",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
offsetof(struct __sk_buff, wire_len)),
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = ACCEPT,
},
{
"check wire_len is not writable by tc classifier",
.insns = {
BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_1,
offsetof(struct __sk_buff, wire_len)),
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.errstr = "invalid bpf_context access",
.errstr_unpriv = "R1 leaks addr",
.result = REJECT,
},
};
static int probe_filter_length(const struct bpf_insn *fp)