On Wed, May 5, 2021 at 8:45 PM Dongseok Yi [off-list ref] wrote:

On Wed, May 05, 2021 at 10:55:10PM +0200, Daniel Borkmann wrote:

quoted

On 4/29/21 12:08 PM, Dongseok Yi wrote:

quoted

tcp_gso_segment check for the size of GROed payload if it is bigger
than the mss. bpf_skb_proto_6_to_4 increases mss, but the mss can be
bigger than the size of GROed payload unexpectedly if data_len is not
big enough.

Assume that skb gso_size = 1372 and data_len = 8. bpf_skb_proto_6_to_4

Is this a typo and is this intended to read skb->data_len = 1380?

The issue is that payload length (1380) is greater than mss with ipv6
(1372), but less than mss with ipv4 (1392).

I don't understand data_len = 8 or why the patch compares
skb->data_len to len_diff (20).

One simple solution if this packet no longer needs to be segmented
might be to reset the gso_type completely.

In general, I would advocate using BPF_F_ADJ_ROOM_FIXED_GSO. When
converting from IPv6 to IPv4, fixed gso will end up building packets
that are slightly below the MTU. That opportunity cost is negligible
(especially with TSO). Unfortunately, I see that that flag is
available for bpf_skb_adjust_room but not for bpf_skb_proto_6_to_4.

quoted

quoted

would increse the gso_size to 1392. tcp_gso_segment will get an error
with 1380 <= 1392.

Check for the size of GROed payload if it is really bigger than target
mss when increase mss.

Fixes: 6578171a7ff0 (bpf: add bpf_skb_change_proto helper)
Signed-off-by: Dongseok Yi <redacted>
---
  net/core/filter.c | 4 +++-
  1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index 9323d34..3f79e3c 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c

@@ -3308,7 +3308,9 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb)
            }

            /* Due to IPv4 header, MSS can be upgraded. */
-           skb_increase_gso_size(shinfo, len_diff);
+           if (skb->data_len > len_diff)

Could you elaborate some more on what this has to do with data_len specifically
here? I'm not sure I follow exactly your above commit description. Are you saying
that you're hitting in tcp_gso_segment():

         [...]
         mss = skb_shinfo(skb)->gso_size;
         if (unlikely(skb->len <= mss))
                 goto out;
         [...]

Yes, right

quoted

Please provide more context on the bug, thanks!

tcp_gso_segment():
        [...]
        __skb_pull(skb, thlen);

        mss = skb_shinfo(skb)->gso_size;
        if (unlikely(skb->len <= mss))
        [...]

skb->len will have total GROed TCP payload size after __skb_pull.
skb->len <= mss will not be happened in a normal GROed situation. But
bpf_skb_proto_6_to_4 would upgrade MSS by increasing gso_size, it can
hit an error condition.

We should ensure the following condition.
total GROed TCP payload > the original mss + (IPv6 size - IPv4 size)

Due to
total GROed TCP payload = the original mss + skb->data_len
IPv6 size - IPv4 size = len_diff

Finally, we can get the condition.
skb->data_len > len_diff

quoted

quoted

+                   skb_increase_gso_size(shinfo, len_diff);
+
            /* Header must be checked, and gso_segs recomputed. */
            shinfo->gso_type |= SKB_GSO_DODGY;
            shinfo->gso_segs = 0;