diff options
| author | Cong Wang <cong.wang@bytedance.com> | 2021-02-23 19:49:28 +0100 |
|---|---|---|
| committer | Alexei Starovoitov <ast@kernel.org> | 2021-02-26 21:28:03 +0100 |
| commit | 16137b09a66f2b75090f1e56a9ba0e27ef845ebc (patch) | |
| tree | 84e6f4a946e33b2654e36b3563d3488c27ac9f13 /net/core/skmsg.c | |
| parent | skmsg: Get rid of struct sk_psock_parser (diff) | |
| download | linux-16137b09a66f2b75090f1e56a9ba0e27ef845ebc.tar.xz linux-16137b09a66f2b75090f1e56a9ba0e27ef845ebc.zip | |
bpf: Compute data_end dynamically with JIT code
Currently, we compute ->data_end with a compile-time constant
offset of skb. But as Jakub pointed out, we can actually compute
it in eBPF JIT code at run-time, so that we can competely get
rid of ->data_end. This is similar to skb_shinfo(skb) computation
in bpf_convert_shinfo_access().
Suggested-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/20210223184934.6054-4-xiyou.wangcong@gmail.com
Diffstat (limited to 'net/core/skmsg.c')
| -rw-r--r-- | net/core/skmsg.c | 1 |
1 files changed, 0 insertions, 1 deletions
diff --git a/net/core/skmsg.c b/net/core/skmsg.c index d00c9a4b47e7..8822001ab3dc 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -746,7 +746,6 @@ EXPORT_SYMBOL_GPL(sk_psock_msg_verdict); static int sk_psock_bpf_run(struct sk_psock *psock, struct bpf_prog *prog, struct sk_buff *skb) { - bpf_compute_data_end_sk_skb(skb); return bpf_prog_run_pin_on_cpu(prog, skb); } |