BPF Archive on lore.kernel.org
 help / color / Atom feed
* [PATCH bpf] bpf: check for data_len before upgrading mss when 6 to 4
       [not found] <CGME20210429102143epcas2p4c8747c09a9de28f003c20389c050394a@epcas2p4.samsung.com>
@ 2021-04-29 10:08 ` Dongseok Yi
  2021-05-05 20:55   ` Daniel Borkmann
  0 siblings, 1 reply; 14+ messages in thread
From: Dongseok Yi @ 2021-04-29 10:08 UTC (permalink / raw)
  To: bpf
  Cc: Dongseok Yi, Alexei Starovoitov, Daniel Borkmann,
	Andrii Nakryiko, Martin KaFai Lau, Song Liu, Yonghong Song,
	John Fastabend, KP Singh, David S. Miller, Jakub Kicinski,
	netdev, linux-kernel

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
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 <dseok.yi@samsung.com>
---
 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)
+			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;
-- 
2.7.4


^ permalink raw reply	[flat|nested] 14+ messages in thread

* Re: [PATCH bpf] bpf: check for data_len before upgrading mss when 6 to 4
  2021-04-29 10:08 ` [PATCH bpf] bpf: check for data_len before upgrading mss when 6 to 4 Dongseok Yi
@ 2021-05-05 20:55   ` Daniel Borkmann
  2021-05-06  0:45     ` Dongseok Yi
  0 siblings, 1 reply; 14+ messages in thread
From: Daniel Borkmann @ 2021-05-05 20:55 UTC (permalink / raw)
  To: Dongseok Yi, bpf
  Cc: Alexei Starovoitov, Andrii Nakryiko, Martin KaFai Lau, Song Liu,
	Yonghong Song, John Fastabend, KP Singh, David S. Miller,
	Jakub Kicinski, netdev, linux-kernel, willemdebruijn.kernel

On 4/29/21 12:08 PM, Dongseok Yi wrote:
> 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
> 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 <dseok.yi@samsung.com>
> ---
>   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;
         [...]

Please provide more context on the bug, thanks!

> +			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;
> 


^ permalink raw reply	[flat|nested] 14+ messages in thread

* RE: [PATCH bpf] bpf: check for data_len before upgrading mss when 6 to 4
  2021-05-05 20:55   ` Daniel Borkmann
@ 2021-05-06  0:45     ` Dongseok Yi
  2021-05-06  1:45       ` Willem de Bruijn
  0 siblings, 1 reply; 14+ messages in thread
From: Dongseok Yi @ 2021-05-06  0:45 UTC (permalink / raw)
  To: 'Daniel Borkmann', bpf
  Cc: 'Alexei Starovoitov', 'Andrii Nakryiko',
	'Martin KaFai Lau', 'Song Liu',
	'Yonghong Song', 'John Fastabend',
	'KP Singh', 'David S. Miller',
	'Jakub Kicinski',
	netdev, linux-kernel, willemdebruijn.kernel

On Wed, May 05, 2021 at 10:55:10PM +0200, Daniel Borkmann wrote:
> On 4/29/21 12:08 PM, Dongseok Yi wrote:
> > 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
> > 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 <dseok.yi@samsung.com>
> > ---
> >   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

> 
> 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

> 
> > +			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;
> >



^ permalink raw reply	[flat|nested] 14+ messages in thread

* Re: [PATCH bpf] bpf: check for data_len before upgrading mss when 6 to 4
  2021-05-06  0:45     ` Dongseok Yi
@ 2021-05-06  1:45       ` Willem de Bruijn
  2021-05-06  2:27         ` Dongseok Yi
  0 siblings, 1 reply; 14+ messages in thread
From: Willem de Bruijn @ 2021-05-06  1:45 UTC (permalink / raw)
  To: Dongseok Yi
  Cc: Daniel Borkmann, bpf, Alexei Starovoitov, Andrii Nakryiko,
	Martin KaFai Lau, Song Liu, Yonghong Song, John Fastabend,
	KP Singh, David S. Miller, Jakub Kicinski, Network Development,
	linux-kernel, Willem de Bruijn

On Wed, May 5, 2021 at 8:45 PM Dongseok Yi <dseok.yi@samsung.com> wrote:
>
> On Wed, May 05, 2021 at 10:55:10PM +0200, Daniel Borkmann wrote:
> > On 4/29/21 12:08 PM, Dongseok Yi wrote:
> > > 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.


> > > 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 <dseok.yi@samsung.com>
> > > ---
> > >   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
>
> >
> > 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
>
> >
> > > +                   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;
> > >
>
>

^ permalink raw reply	[flat|nested] 14+ messages in thread

* RE: [PATCH bpf] bpf: check for data_len before upgrading mss when 6 to 4
  2021-05-06  1:45       ` Willem de Bruijn
@ 2021-05-06  2:27         ` Dongseok Yi
  2021-05-06 18:21           ` Willem de Bruijn
  0 siblings, 1 reply; 14+ messages in thread
From: Dongseok Yi @ 2021-05-06  2:27 UTC (permalink / raw)
  To: 'Willem de Bruijn'
  Cc: 'Daniel Borkmann', 'bpf',
	'Alexei Starovoitov', 'Andrii Nakryiko',
	'Martin KaFai Lau', 'Song Liu',
	'Yonghong Song', 'John Fastabend',
	'KP Singh', 'David S. Miller',
	'Jakub Kicinski', 'Network Development',
	'linux-kernel'

On Wed, May 05, 2021 at 09:45:37PM -0400, Willem de Bruijn wrote:
> On Wed, May 5, 2021 at 8:45 PM Dongseok Yi <dseok.yi@samsung.com> wrote:
> >
> > On Wed, May 05, 2021 at 10:55:10PM +0200, Daniel Borkmann wrote:
> > > On 4/29/21 12:08 PM, Dongseok Yi wrote:
> > > > 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?

This is not a typo. I intended skb->data_len = 8.

> 
> 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).

skb_gro_receive():
        unsigned int len = skb_gro_len(skb);
        [...]
done:
        NAPI_GRO_CB(p)->count++;
        p->data_len += len;

head_skb's data_len is the sum of skb_gro_len for each skb of the frags.
data_len could be 8 if server sent a small size packet and it is GROed
to head_skb.

Please let me know if I am missing something.

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

I am not sure gso_type can be cleared even when GSO is needed.

> 
> 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.
> 
> 
> > > > 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 <dseok.yi@samsung.com>
> > > > ---
> > > >   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
> >
> > >
> > > 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
> >
> > >
> > > > +                   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;
> > > >
> >
> >


^ permalink raw reply	[flat|nested] 14+ messages in thread

* Re: [PATCH bpf] bpf: check for data_len before upgrading mss when 6 to 4
  2021-05-06  2:27         ` Dongseok Yi
@ 2021-05-06 18:21           ` Willem de Bruijn
  2021-05-07  0:53             ` Dongseok Yi
  0 siblings, 1 reply; 14+ messages in thread
From: Willem de Bruijn @ 2021-05-06 18:21 UTC (permalink / raw)
  To: Dongseok Yi
  Cc: Daniel Borkmann, bpf, Alexei Starovoitov, Andrii Nakryiko,
	Martin KaFai Lau, Song Liu, Yonghong Song, John Fastabend,
	KP Singh, David S. Miller, Jakub Kicinski, Network Development,
	linux-kernel

On Wed, May 5, 2021 at 10:27 PM Dongseok Yi <dseok.yi@samsung.com> wrote:
>
> On Wed, May 05, 2021 at 09:45:37PM -0400, Willem de Bruijn wrote:
> > On Wed, May 5, 2021 at 8:45 PM Dongseok Yi <dseok.yi@samsung.com> wrote:
> > >
> > > On Wed, May 05, 2021 at 10:55:10PM +0200, Daniel Borkmann wrote:
> > > > On 4/29/21 12:08 PM, Dongseok Yi wrote:
> > > > > 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?
>
> This is not a typo. I intended skb->data_len = 8.
>
> >
> > 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).
>
> skb_gro_receive():
>         unsigned int len = skb_gro_len(skb);
>         [...]
> done:
>         NAPI_GRO_CB(p)->count++;
>         p->data_len += len;
>
> head_skb's data_len is the sum of skb_gro_len for each skb of the frags.
> data_len could be 8 if server sent a small size packet and it is GROed
> to head_skb.
>
> Please let me know if I am missing something.

This is my understanding of the data path. This is a forwarding path
for TCP traffic.

GRO is enabled and will coalesce multiple segments into a single large
packet. In bad cases, the coalesced packet payload is > MSS, but < MSS
+ 20.

Somewhere between GRO and GSO you have a BPF program that converts the
IPv6 address to IPv4.

There is no concept of head_skb at the time of this BPF program. It is
a single SKB, with an skb linear part and multiple data items in the
frags (no frag_list).

When entering the GSO stack, this single skb now has a payload length
< MSS. So it would just make a valid TCP packet on its own?

skb_gro_len is only relevant inside the GRO stack. It internally casts
the skb->cb[] to NAPI_GRO_CB. This field is a scratch area that may be
reused for other purposes later by other layers of the datapath. It is
not safe to read this inside bpf_skb_proto_6_to_4.


> >
> > One simple solution if this packet no longer needs to be segmented
> > might be to reset the gso_type completely.
>
> I am not sure gso_type can be cleared even when GSO is needed.
>
> >
> > 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.
> >
> >
> > > > > 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 <dseok.yi@samsung.com>
> > > > > ---
> > > > >   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
> > >
> > > >
> > > > 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
> > >
> > > >
> > > > > +                   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;
> > > > >
> > >
> > >
>

^ permalink raw reply	[flat|nested] 14+ messages in thread

* RE: [PATCH bpf] bpf: check for data_len before upgrading mss when 6 to 4
  2021-05-06 18:21           ` Willem de Bruijn
@ 2021-05-07  0:53             ` Dongseok Yi
  2021-05-07  1:25               ` Willem de Bruijn
  0 siblings, 1 reply; 14+ messages in thread
From: Dongseok Yi @ 2021-05-07  0:53 UTC (permalink / raw)
  To: 'Willem de Bruijn'
  Cc: 'Daniel Borkmann', 'bpf',
	'Alexei Starovoitov', 'Andrii Nakryiko',
	'Martin KaFai Lau', 'Song Liu',
	'Yonghong Song', 'John Fastabend',
	'KP Singh', 'David S. Miller',
	'Jakub Kicinski', 'Network Development',
	'linux-kernel'

On Thu, May 06, 2021 at 02:21:37PM -0400, Willem de Bruijn wrote:
> On Wed, May 5, 2021 at 10:27 PM Dongseok Yi <dseok.yi@samsung.com> wrote:
> >
> > On Wed, May 05, 2021 at 09:45:37PM -0400, Willem de Bruijn wrote:
> > > On Wed, May 5, 2021 at 8:45 PM Dongseok Yi <dseok.yi@samsung.com> wrote:
> > > >
> > > > On Wed, May 05, 2021 at 10:55:10PM +0200, Daniel Borkmann wrote:
> > > > > On 4/29/21 12:08 PM, Dongseok Yi wrote:
> > > > > > 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?
> >
> > This is not a typo. I intended skb->data_len = 8.
> >
> > >
> > > 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).
> >
> > skb_gro_receive():
> >         unsigned int len = skb_gro_len(skb);
> >         [...]
> > done:
> >         NAPI_GRO_CB(p)->count++;
> >         p->data_len += len;
> >
> > head_skb's data_len is the sum of skb_gro_len for each skb of the frags.
> > data_len could be 8 if server sent a small size packet and it is GROed
> > to head_skb.
> >
> > Please let me know if I am missing something.
> 
> This is my understanding of the data path. This is a forwarding path
> for TCP traffic.
> 
> GRO is enabled and will coalesce multiple segments into a single large
> packet. In bad cases, the coalesced packet payload is > MSS, but < MSS
> + 20.
> 
> Somewhere between GRO and GSO you have a BPF program that converts the
> IPv6 address to IPv4.

Your understanding is right. The data path is GRO -> BPF 6 to 4 ->
GSO.

> 
> There is no concept of head_skb at the time of this BPF program. It is
> a single SKB, with an skb linear part and multiple data items in the
> frags (no frag_list).

Sorry for the confusion. head_skb what I mentioned was a skb linear
part. I'm considering a single SKB with frags too.

> 
> When entering the GSO stack, this single skb now has a payload length
> < MSS. So it would just make a valid TCP packet on its own?
> 
> skb_gro_len is only relevant inside the GRO stack. It internally casts
> the skb->cb[] to NAPI_GRO_CB. This field is a scratch area that may be
> reused for other purposes later by other layers of the datapath. It is
> not safe to read this inside bpf_skb_proto_6_to_4.

The condition what I made uses skb->data_len not skb_gro_len. Does
skb->data_len have a different meaning on each layer? As I know,
data_len indicates the amount of frags or frag_list. skb->data_len
should be > 20 in the sample case because the payload size of the skb
linear part is the same with mss.

We can modify netif_needs_gso as another option to hit
skb_needs_linearize in validate_xmit_skb. But I think we should compare
skb->gso_size and skb->data_len too to check if mss exceed a payload
size.

> 
> 
> > >
> > > One simple solution if this packet no longer needs to be segmented
> > > might be to reset the gso_type completely.
> >
> > I am not sure gso_type can be cleared even when GSO is needed.
> >
> > >
> > > 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.
> > >
> > >
> > > > > > 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 <dseok.yi@samsung.com>
> > > > > > ---
> > > > > >   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
> > > >
> > > > >
> > > > > 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
> > > >
> > > > >
> > > > > > +                   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;
> > > > > >
> > > >
> > > >
> >


^ permalink raw reply	[flat|nested] 14+ messages in thread

* Re: [PATCH bpf] bpf: check for data_len before upgrading mss when 6 to 4
  2021-05-07  0:53             ` Dongseok Yi
@ 2021-05-07  1:25               ` Willem de Bruijn
  2021-05-07  1:45                 ` Yunsheng Lin
  0 siblings, 1 reply; 14+ messages in thread
From: Willem de Bruijn @ 2021-05-07  1:25 UTC (permalink / raw)
  To: Dongseok Yi
  Cc: Daniel Borkmann, bpf, Alexei Starovoitov, Andrii Nakryiko,
	Martin KaFai Lau, Song Liu, Yonghong Song, John Fastabend,
	KP Singh, David S. Miller, Jakub Kicinski, Network Development,
	linux-kernel

> > > head_skb's data_len is the sum of skb_gro_len for each skb of the frags.
> > > data_len could be 8 if server sent a small size packet and it is GROed
> > > to head_skb.
> > >
> > > Please let me know if I am missing something.
> >
> > This is my understanding of the data path. This is a forwarding path
> > for TCP traffic.
> >
> > GRO is enabled and will coalesce multiple segments into a single large
> > packet. In bad cases, the coalesced packet payload is > MSS, but < MSS
> > + 20.
> >
> > Somewhere between GRO and GSO you have a BPF program that converts the
> > IPv6 address to IPv4.
>
> Your understanding is right. The data path is GRO -> BPF 6 to 4 ->
> GSO.
>
> >
> > There is no concept of head_skb at the time of this BPF program. It is
> > a single SKB, with an skb linear part and multiple data items in the
> > frags (no frag_list).
>
> Sorry for the confusion. head_skb what I mentioned was a skb linear
> part. I'm considering a single SKB with frags too.
>
> >
> > When entering the GSO stack, this single skb now has a payload length
> > < MSS. So it would just make a valid TCP packet on its own?
> >
> > skb_gro_len is only relevant inside the GRO stack. It internally casts
> > the skb->cb[] to NAPI_GRO_CB. This field is a scratch area that may be
> > reused for other purposes later by other layers of the datapath. It is
> > not safe to read this inside bpf_skb_proto_6_to_4.
>
> The condition what I made uses skb->data_len not skb_gro_len. Does
> skb->data_len have a different meaning on each layer? As I know,
> data_len indicates the amount of frags or frag_list. skb->data_len
> should be > 20 in the sample case because the payload size of the skb
> linear part is the same with mss.

Ah, got it.

data_len is the length of the skb minus the length in the skb linear
section (as seen in skb_headlen).

So this gso skb consists of two segments, the first one entirely
linear, the payload of the second is in skb_shinfo(skb)->frags[0].

It is not guaranteed that gso skbs built from two individual skbs end
up looking like that. Only protocol headers in the linear segment and
the payload of both in frags is common.

> We can modify netif_needs_gso as another option to hit
> skb_needs_linearize in validate_xmit_skb. But I think we should compare
> skb->gso_size and skb->data_len too to check if mss exceed a payload
> size.

The rest of the stack does not build such gso packets with payload len
< mss, so we should not have to add workarounds in the gso hot path
for this.

Also no need to linearize this skb. I think that if the bpf program
would just clear the gso type, the packet would be sent correctly.
Unless I'm missing something.

But I don't mean to argue that it should do that in production.
Instead, not playing mss games would solve this and stay close to the
original datapath if no bpf program had been present. Including
maintaining the GSO invariant of sending out the same chain of packets
as received (bar the IPv6 to IPv4 change).

This could be achieved by adding support for the flag
BPF_F_ADJ_ROOM_FIXED_GSO in the flags field of bpf_skb_change_proto.
And similar to bpf_skb_net_shrink:

                /* Due to header shrink, MSS can be upgraded. */
                if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO))
                        skb_increase_gso_size(shinfo, len_diff);

The other case, from IPv4 to IPv6 is more difficult to address, as not
reducing the MSS will result in packets exceeding MTU. That calls for
workarounds like MSS clamping. Anyway, that is out of scope here.



> >
> >
> > > >
> > > > One simple solution if this packet no longer needs to be segmented
> > > > might be to reset the gso_type completely.
> > >
> > > I am not sure gso_type can be cleared even when GSO is needed.
> > >
> > > >
> > > > 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.
> > > >
> > > >
> > > > > > > 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 <dseok.yi@samsung.com>
> > > > > > > ---
> > > > > > >   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
> > > > >
> > > > > >
> > > > > > 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
> > > > >
> > > > > >
> > > > > > > +                   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;
> > > > > > >
> > > > >
> > > > >
> > >
>

^ permalink raw reply	[flat|nested] 14+ messages in thread

* Re: [PATCH bpf] bpf: check for data_len before upgrading mss when 6 to 4
  2021-05-07  1:25               ` Willem de Bruijn
@ 2021-05-07  1:45                 ` Yunsheng Lin
  2021-05-07  1:53                   ` Willem de Bruijn
  0 siblings, 1 reply; 14+ messages in thread
From: Yunsheng Lin @ 2021-05-07  1:45 UTC (permalink / raw)
  To: Willem de Bruijn, Dongseok Yi
  Cc: Daniel Borkmann, bpf, Alexei Starovoitov, Andrii Nakryiko,
	Martin KaFai Lau, Song Liu, Yonghong Song, John Fastabend,
	KP Singh, David S. Miller, Jakub Kicinski, Network Development,
	linux-kernel

On 2021/5/7 9:25, Willem de Bruijn wrote:
>>>> head_skb's data_len is the sum of skb_gro_len for each skb of the frags.
>>>> data_len could be 8 if server sent a small size packet and it is GROed
>>>> to head_skb.
>>>>
>>>> Please let me know if I am missing something.
>>>
>>> This is my understanding of the data path. This is a forwarding path
>>> for TCP traffic.
>>>
>>> GRO is enabled and will coalesce multiple segments into a single large
>>> packet. In bad cases, the coalesced packet payload is > MSS, but < MSS
>>> + 20.
>>>
>>> Somewhere between GRO and GSO you have a BPF program that converts the
>>> IPv6 address to IPv4.
>>
>> Your understanding is right. The data path is GRO -> BPF 6 to 4 ->
>> GSO.
>>
>>>
>>> There is no concept of head_skb at the time of this BPF program. It is
>>> a single SKB, with an skb linear part and multiple data items in the
>>> frags (no frag_list).
>>
>> Sorry for the confusion. head_skb what I mentioned was a skb linear
>> part. I'm considering a single SKB with frags too.
>>
>>>
>>> When entering the GSO stack, this single skb now has a payload length
>>> < MSS. So it would just make a valid TCP packet on its own?
>>>
>>> skb_gro_len is only relevant inside the GRO stack. It internally casts
>>> the skb->cb[] to NAPI_GRO_CB. This field is a scratch area that may be
>>> reused for other purposes later by other layers of the datapath. It is
>>> not safe to read this inside bpf_skb_proto_6_to_4.
>>
>> The condition what I made uses skb->data_len not skb_gro_len. Does
>> skb->data_len have a different meaning on each layer? As I know,
>> data_len indicates the amount of frags or frag_list. skb->data_len
>> should be > 20 in the sample case because the payload size of the skb
>> linear part is the same with mss.
> 
> Ah, got it.
> 
> data_len is the length of the skb minus the length in the skb linear
> section (as seen in skb_headlen).
> 
> So this gso skb consists of two segments, the first one entirely
> linear, the payload of the second is in skb_shinfo(skb)->frags[0].
> 
> It is not guaranteed that gso skbs built from two individual skbs end
> up looking like that. Only protocol headers in the linear segment and
> the payload of both in frags is common.
> 
>> We can modify netif_needs_gso as another option to hit
>> skb_needs_linearize in validate_xmit_skb. But I think we should compare
>> skb->gso_size and skb->data_len too to check if mss exceed a payload
>> size.
> 
> The rest of the stack does not build such gso packets with payload len
> < mss, so we should not have to add workarounds in the gso hot path
> for this.
> 
> Also no need to linearize this skb. I think that if the bpf program
> would just clear the gso type, the packet would be sent correctly.
> Unless I'm missing something.

Does the checksum/len field in ip and tcp/udp header need adjusting
before clearing gso type as the packet has became bigger?

Also, instead of testing skb->data_len, may test the skb->len?

skb->len - (mac header + ip/ipv6 header + udp/tcp header) > mss + len_diff

> 
> But I don't mean to argue that it should do that in production.
> Instead, not playing mss games would solve this and stay close to the
> original datapath if no bpf program had been present. Including
> maintaining the GSO invariant of sending out the same chain of packets
> as received (bar the IPv6 to IPv4 change).
> 
> This could be achieved by adding support for the flag
> BPF_F_ADJ_ROOM_FIXED_GSO in the flags field of bpf_skb_change_proto.
> And similar to bpf_skb_net_shrink:
> 
>                 /* Due to header shrink, MSS can be upgraded. */
>                 if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO))
>                         skb_increase_gso_size(shinfo, len_diff);
> 
> The other case, from IPv4 to IPv6 is more difficult to address, as not
> reducing the MSS will result in packets exceeding MTU. That calls for
> workarounds like MSS clamping. Anyway, that is out of scope here.
> 
> 
> 
>>>
>>>
>>>>>
>>>>> One simple solution if this packet no longer needs to be segmented
>>>>> might be to reset the gso_type completely.
>>>>
>>>> I am not sure gso_type can be cleared even when GSO is needed.
>>>>
>>>>>
>>>>> 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.
>>>>>
>>>>>
>>>>>>>> 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 <dseok.yi@samsung.com>
>>>>>>>> ---
>>>>>>>>   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
>>>>>>
>>>>>>>
>>>>>>> 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
>>>>>>
>>>>>>>
>>>>>>>> +                   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;
>>>>>>>>
>>>>>>
>>>>>>
>>>>
>>
> 
> .
> 


^ permalink raw reply	[flat|nested] 14+ messages in thread

* Re: [PATCH bpf] bpf: check for data_len before upgrading mss when 6 to 4
  2021-05-07  1:45                 ` Yunsheng Lin
@ 2021-05-07  1:53                   ` Willem de Bruijn
  2021-05-07  8:25                     ` Dongseok Yi
  0 siblings, 1 reply; 14+ messages in thread
From: Willem de Bruijn @ 2021-05-07  1:53 UTC (permalink / raw)
  To: Yunsheng Lin
  Cc: Dongseok Yi, Daniel Borkmann, bpf, Alexei Starovoitov,
	Andrii Nakryiko, Martin KaFai Lau, Song Liu, Yonghong Song,
	John Fastabend, KP Singh, David S. Miller, Jakub Kicinski,
	Network Development, linux-kernel

On Thu, May 6, 2021 at 9:45 PM Yunsheng Lin <linyunsheng@huawei.com> wrote:
>
> On 2021/5/7 9:25, Willem de Bruijn wrote:
> >>>> head_skb's data_len is the sum of skb_gro_len for each skb of the frags.
> >>>> data_len could be 8 if server sent a small size packet and it is GROed
> >>>> to head_skb.
> >>>>
> >>>> Please let me know if I am missing something.
> >>>
> >>> This is my understanding of the data path. This is a forwarding path
> >>> for TCP traffic.
> >>>
> >>> GRO is enabled and will coalesce multiple segments into a single large
> >>> packet. In bad cases, the coalesced packet payload is > MSS, but < MSS
> >>> + 20.
> >>>
> >>> Somewhere between GRO and GSO you have a BPF program that converts the
> >>> IPv6 address to IPv4.
> >>
> >> Your understanding is right. The data path is GRO -> BPF 6 to 4 ->
> >> GSO.
> >>
> >>>
> >>> There is no concept of head_skb at the time of this BPF program. It is
> >>> a single SKB, with an skb linear part and multiple data items in the
> >>> frags (no frag_list).
> >>
> >> Sorry for the confusion. head_skb what I mentioned was a skb linear
> >> part. I'm considering a single SKB with frags too.
> >>
> >>>
> >>> When entering the GSO stack, this single skb now has a payload length
> >>> < MSS. So it would just make a valid TCP packet on its own?
> >>>
> >>> skb_gro_len is only relevant inside the GRO stack. It internally casts
> >>> the skb->cb[] to NAPI_GRO_CB. This field is a scratch area that may be
> >>> reused for other purposes later by other layers of the datapath. It is
> >>> not safe to read this inside bpf_skb_proto_6_to_4.
> >>
> >> The condition what I made uses skb->data_len not skb_gro_len. Does
> >> skb->data_len have a different meaning on each layer? As I know,
> >> data_len indicates the amount of frags or frag_list. skb->data_len
> >> should be > 20 in the sample case because the payload size of the skb
> >> linear part is the same with mss.
> >
> > Ah, got it.
> >
> > data_len is the length of the skb minus the length in the skb linear
> > section (as seen in skb_headlen).
> >
> > So this gso skb consists of two segments, the first one entirely
> > linear, the payload of the second is in skb_shinfo(skb)->frags[0].
> >
> > It is not guaranteed that gso skbs built from two individual skbs end
> > up looking like that. Only protocol headers in the linear segment and
> > the payload of both in frags is common.
> >
> >> We can modify netif_needs_gso as another option to hit
> >> skb_needs_linearize in validate_xmit_skb. But I think we should compare
> >> skb->gso_size and skb->data_len too to check if mss exceed a payload
> >> size.
> >
> > The rest of the stack does not build such gso packets with payload len
> > < mss, so we should not have to add workarounds in the gso hot path
> > for this.
> >
> > Also no need to linearize this skb. I think that if the bpf program
> > would just clear the gso type, the packet would be sent correctly.
> > Unless I'm missing something.
>
> Does the checksum/len field in ip and tcp/udp header need adjusting
> before clearing gso type as the packet has became bigger?

gro takes care of this. see for instance inet_gro_complete for updates
to the ip header.

> Also, instead of testing skb->data_len, may test the skb->len?
>
> skb->len - (mac header + ip/ipv6 header + udp/tcp header) > mss + len_diff

Yes. Essentially doing the same calculation as the gso code that is
causing the packet to be dropped.

> >
> > But I don't mean to argue that it should do that in production.
> > Instead, not playing mss games would solve this and stay close to the
> > original datapath if no bpf program had been present. Including
> > maintaining the GSO invariant of sending out the same chain of packets
> > as received (bar the IPv6 to IPv4 change).
> >
> > This could be achieved by adding support for the flag
> > BPF_F_ADJ_ROOM_FIXED_GSO in the flags field of bpf_skb_change_proto.
> > And similar to bpf_skb_net_shrink:
> >
> >                 /* Due to header shrink, MSS can be upgraded. */
> >                 if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO))
> >                         skb_increase_gso_size(shinfo, len_diff);
> >
> > The other case, from IPv4 to IPv6 is more difficult to address, as not
> > reducing the MSS will result in packets exceeding MTU. That calls for
> > workarounds like MSS clamping. Anyway, that is out of scope here.
> >
> >
> >
> >>>
> >>>
> >>>>>
> >>>>> One simple solution if this packet no longer needs to be segmented
> >>>>> might be to reset the gso_type completely.
> >>>>
> >>>> I am not sure gso_type can be cleared even when GSO is needed.
> >>>>
> >>>>>
> >>>>> 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.
> >>>>>
> >>>>>
> >>>>>>>> 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 <dseok.yi@samsung.com>
> >>>>>>>> ---
> >>>>>>>>   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
> >>>>>>
> >>>>>>>
> >>>>>>> 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
> >>>>>>
> >>>>>>>
> >>>>>>>> +                   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;
> >>>>>>>>
> >>>>>>
> >>>>>>
> >>>>
> >>
> >
> > .
> >
>

^ permalink raw reply	[flat|nested] 14+ messages in thread

* RE: [PATCH bpf] bpf: check for data_len before upgrading mss when 6 to 4
  2021-05-07  1:53                   ` Willem de Bruijn
@ 2021-05-07  8:25                     ` Dongseok Yi
  2021-05-07  9:11                       ` Yunsheng Lin
  2021-05-07 13:50                       ` Willem de Bruijn
  0 siblings, 2 replies; 14+ messages in thread
From: Dongseok Yi @ 2021-05-07  8:25 UTC (permalink / raw)
  To: 'Willem de Bruijn', 'Yunsheng Lin'
  Cc: 'Daniel Borkmann', 'bpf',
	'Alexei Starovoitov', 'Andrii Nakryiko',
	'Martin KaFai Lau', 'Song Liu',
	'Yonghong Song', 'John Fastabend',
	'KP Singh', 'David S. Miller',
	'Jakub Kicinski', 'Network Development',
	'linux-kernel'

On Thu, May 06, 2021 at 09:53:45PM -0400, Willem de Bruijn wrote:
> On Thu, May 6, 2021 at 9:45 PM Yunsheng Lin <linyunsheng@huawei.com> wrote:
> >
> > On 2021/5/7 9:25, Willem de Bruijn wrote:
> > >>>> head_skb's data_len is the sum of skb_gro_len for each skb of the frags.
> > >>>> data_len could be 8 if server sent a small size packet and it is GROed
> > >>>> to head_skb.
> > >>>>
> > >>>> Please let me know if I am missing something.
> > >>>
> > >>> This is my understanding of the data path. This is a forwarding path
> > >>> for TCP traffic.
> > >>>
> > >>> GRO is enabled and will coalesce multiple segments into a single large
> > >>> packet. In bad cases, the coalesced packet payload is > MSS, but < MSS
> > >>> + 20.
> > >>>
> > >>> Somewhere between GRO and GSO you have a BPF program that converts the
> > >>> IPv6 address to IPv4.
> > >>
> > >> Your understanding is right. The data path is GRO -> BPF 6 to 4 ->
> > >> GSO.
> > >>
> > >>>
> > >>> There is no concept of head_skb at the time of this BPF program. It is
> > >>> a single SKB, with an skb linear part and multiple data items in the
> > >>> frags (no frag_list).
> > >>
> > >> Sorry for the confusion. head_skb what I mentioned was a skb linear
> > >> part. I'm considering a single SKB with frags too.
> > >>
> > >>>
> > >>> When entering the GSO stack, this single skb now has a payload length
> > >>> < MSS. So it would just make a valid TCP packet on its own?
> > >>>
> > >>> skb_gro_len is only relevant inside the GRO stack. It internally casts
> > >>> the skb->cb[] to NAPI_GRO_CB. This field is a scratch area that may be
> > >>> reused for other purposes later by other layers of the datapath. It is
> > >>> not safe to read this inside bpf_skb_proto_6_to_4.
> > >>
> > >> The condition what I made uses skb->data_len not skb_gro_len. Does
> > >> skb->data_len have a different meaning on each layer? As I know,
> > >> data_len indicates the amount of frags or frag_list. skb->data_len
> > >> should be > 20 in the sample case because the payload size of the skb
> > >> linear part is the same with mss.
> > >
> > > Ah, got it.
> > >
> > > data_len is the length of the skb minus the length in the skb linear
> > > section (as seen in skb_headlen).
> > >
> > > So this gso skb consists of two segments, the first one entirely
> > > linear, the payload of the second is in skb_shinfo(skb)->frags[0].
> > >
> > > It is not guaranteed that gso skbs built from two individual skbs end
> > > up looking like that. Only protocol headers in the linear segment and
> > > the payload of both in frags is common.
> > >
> > >> We can modify netif_needs_gso as another option to hit
> > >> skb_needs_linearize in validate_xmit_skb. But I think we should compare
> > >> skb->gso_size and skb->data_len too to check if mss exceed a payload
> > >> size.
> > >
> > > The rest of the stack does not build such gso packets with payload len
> > > < mss, so we should not have to add workarounds in the gso hot path
> > > for this.
> > >
> > > Also no need to linearize this skb. I think that if the bpf program
> > > would just clear the gso type, the packet would be sent correctly.
> > > Unless I'm missing something.
> >
> > Does the checksum/len field in ip and tcp/udp header need adjusting
> > before clearing gso type as the packet has became bigger?
> 
> gro takes care of this. see for instance inet_gro_complete for updates
> to the ip header.

I think clearing the gso type will get an error at tcp4_gso_segment
because netif_needs_gso returns true in validate_xmit_skb.

> 
> > Also, instead of testing skb->data_len, may test the skb->len?
> >
> > skb->len - (mac header + ip/ipv6 header + udp/tcp header) > mss + len_diff
> 
> Yes. Essentially doing the same calculation as the gso code that is
> causing the packet to be dropped.

BPF program is usually out of control. Can we take a general approach?
The below 2 cases has no issue when mss upgrading.
1) skb->data_len > mss + 20
2) skb->data_len < mss && skb->data_len > 20
The corner case is when
3) skb->data_len > mss && skb->data_len < mss + 20

But to cover #3 case, we should check the condition Yunsheng Lin said.
What if we do mss upgrading for both #1 and #2 cases only?

+               unsigned short off_len = skb->data_len > shinfo->gso_size ?
+                       shinfo->gso_size : 0;
[...]
                /* Due to IPv4 header, MSS can be upgraded. */
-               skb_increase_gso_size(shinfo, len_diff);
+               if (skb->data_len - off_len > len_diff)
+                       skb_increase_gso_size(shinfo, len_diff);

> 
> > >
> > > But I don't mean to argue that it should do that in production.
> > > Instead, not playing mss games would solve this and stay close to the
> > > original datapath if no bpf program had been present. Including
> > > maintaining the GSO invariant of sending out the same chain of packets
> > > as received (bar the IPv6 to IPv4 change).
> > >
> > > This could be achieved by adding support for the flag
> > > BPF_F_ADJ_ROOM_FIXED_GSO in the flags field of bpf_skb_change_proto.
> > > And similar to bpf_skb_net_shrink:
> > >
> > >                 /* Due to header shrink, MSS can be upgraded. */
> > >                 if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO))
> > >                         skb_increase_gso_size(shinfo, len_diff);
> > >
> > > The other case, from IPv4 to IPv6 is more difficult to address, as not
> > > reducing the MSS will result in packets exceeding MTU. That calls for
> > > workarounds like MSS clamping. Anyway, that is out of scope here.
> > >
> > >
> > >
> > >>>
> > >>>
> > >>>>>
> > >>>>> One simple solution if this packet no longer needs to be segmented
> > >>>>> might be to reset the gso_type completely.
> > >>>>
> > >>>> I am not sure gso_type can be cleared even when GSO is needed.
> > >>>>
> > >>>>>
> > >>>>> 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.
> > >>>>>
> > >>>>>
> > >>>>>>>> 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 <dseok.yi@samsung.com>
> > >>>>>>>> ---
> > >>>>>>>>   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
> > >>>>>>
> > >>>>>>>
> > >>>>>>> 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
> > >>>>>>
> > >>>>>>>
> > >>>>>>>> +                   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;
> > >>>>>>>>
> > >>>>>>
> > >>>>>>
> > >>>>
> > >>
> > >
> > > .
> > >
> >


^ permalink raw reply	[flat|nested] 14+ messages in thread

* Re: [PATCH bpf] bpf: check for data_len before upgrading mss when 6 to 4
  2021-05-07  8:25                     ` Dongseok Yi
@ 2021-05-07  9:11                       ` Yunsheng Lin
  2021-05-07 10:36                         ` Dongseok Yi
  2021-05-07 13:50                       ` Willem de Bruijn
  1 sibling, 1 reply; 14+ messages in thread
From: Yunsheng Lin @ 2021-05-07  9:11 UTC (permalink / raw)
  To: Dongseok Yi, 'Willem de Bruijn'
  Cc: 'Daniel Borkmann', 'bpf',
	'Alexei Starovoitov', 'Andrii Nakryiko',
	'Martin KaFai Lau', 'Song Liu',
	'Yonghong Song', 'John Fastabend',
	'KP Singh', 'David S. Miller',
	'Jakub Kicinski', 'Network Development',
	'linux-kernel'

On 2021/5/7 16:25, Dongseok Yi wrote:
> On Thu, May 06, 2021 at 09:53:45PM -0400, Willem de Bruijn wrote:
>> On Thu, May 6, 2021 at 9:45 PM Yunsheng Lin <linyunsheng@huawei.com> wrote:
>>>
>>> On 2021/5/7 9:25, Willem de Bruijn wrote:
>>>>>>> head_skb's data_len is the sum of skb_gro_len for each skb of the frags.
>>>>>>> data_len could be 8 if server sent a small size packet and it is GROed
>>>>>>> to head_skb.
>>>>>>>
>>>>>>> Please let me know if I am missing something.
>>>>>>
>>>>>> This is my understanding of the data path. This is a forwarding path
>>>>>> for TCP traffic.
>>>>>>
>>>>>> GRO is enabled and will coalesce multiple segments into a single large
>>>>>> packet. In bad cases, the coalesced packet payload is > MSS, but < MSS
>>>>>> + 20.
>>>>>>
>>>>>> Somewhere between GRO and GSO you have a BPF program that converts the
>>>>>> IPv6 address to IPv4.
>>>>>
>>>>> Your understanding is right. The data path is GRO -> BPF 6 to 4 ->
>>>>> GSO.
>>>>>
>>>>>>
>>>>>> There is no concept of head_skb at the time of this BPF program. It is
>>>>>> a single SKB, with an skb linear part and multiple data items in the
>>>>>> frags (no frag_list).
>>>>>
>>>>> Sorry for the confusion. head_skb what I mentioned was a skb linear
>>>>> part. I'm considering a single SKB with frags too.
>>>>>
>>>>>>
>>>>>> When entering the GSO stack, this single skb now has a payload length
>>>>>> < MSS. So it would just make a valid TCP packet on its own?
>>>>>>
>>>>>> skb_gro_len is only relevant inside the GRO stack. It internally casts
>>>>>> the skb->cb[] to NAPI_GRO_CB. This field is a scratch area that may be
>>>>>> reused for other purposes later by other layers of the datapath. It is
>>>>>> not safe to read this inside bpf_skb_proto_6_to_4.
>>>>>
>>>>> The condition what I made uses skb->data_len not skb_gro_len. Does
>>>>> skb->data_len have a different meaning on each layer? As I know,
>>>>> data_len indicates the amount of frags or frag_list. skb->data_len
>>>>> should be > 20 in the sample case because the payload size of the skb
>>>>> linear part is the same with mss.
>>>>
>>>> Ah, got it.
>>>>
>>>> data_len is the length of the skb minus the length in the skb linear
>>>> section (as seen in skb_headlen).
>>>>
>>>> So this gso skb consists of two segments, the first one entirely
>>>> linear, the payload of the second is in skb_shinfo(skb)->frags[0].
>>>>
>>>> It is not guaranteed that gso skbs built from two individual skbs end
>>>> up looking like that. Only protocol headers in the linear segment and
>>>> the payload of both in frags is common.
>>>>
>>>>> We can modify netif_needs_gso as another option to hit
>>>>> skb_needs_linearize in validate_xmit_skb. But I think we should compare
>>>>> skb->gso_size and skb->data_len too to check if mss exceed a payload
>>>>> size.
>>>>
>>>> The rest of the stack does not build such gso packets with payload len
>>>> < mss, so we should not have to add workarounds in the gso hot path
>>>> for this.
>>>>
>>>> Also no need to linearize this skb. I think that if the bpf program
>>>> would just clear the gso type, the packet would be sent correctly.
>>>> Unless I'm missing something.
>>>
>>> Does the checksum/len field in ip and tcp/udp header need adjusting
>>> before clearing gso type as the packet has became bigger?
>>
>> gro takes care of this. see for instance inet_gro_complete for updates
>> to the ip header.
> 
> I think clearing the gso type will get an error at tcp4_gso_segment
> because netif_needs_gso returns true in validate_xmit_skb.

So the bpf_skb_proto_6_to_4() is called after validate_xmit_skb() and
before tcp4_gso_segment()?
If Yes, clearing the gso type here does not seem to help.

> 
>>
>>> Also, instead of testing skb->data_len, may test the skb->len?
>>>
>>> skb->len - (mac header + ip/ipv6 header + udp/tcp header) > mss + len_diff
>>
>> Yes. Essentially doing the same calculation as the gso code that is
>> causing the packet to be dropped.
> 
> BPF program is usually out of control. Can we take a general approach?
> The below 2 cases has no issue when mss upgrading.
> 1) skb->data_len > mss + 20
> 2) skb->data_len < mss && skb->data_len > 20
> The corner case is when
> 3) skb->data_len > mss && skb->data_len < mss + 20

As my understanding:

Usually skb_headlen(skb) >= (mac header + ip/ipv6 header + udp/tcp header),
other than that, there is no other guarantee as long as:
skb->len = skb_headlen(skb) + skb->data_len

So the cases should be:
1. skb->len - (mac header + ip/ipv6 header + udp/tcp header) > mss + len_diff
2. skb->len - (mac header + ip/ipv6 header + udp/tcp header) <= mss + len_diff

The corner case is case 2.

> 
> But to cover #3 case, we should check the condition Yunsheng Lin said.
> What if we do mss upgrading for both #1 and #2 cases only?
> 
> +               unsigned short off_len = skb->data_len > shinfo->gso_size ?
> +                       shinfo->gso_size : 0;
> [...]
>                 /* Due to IPv4 header, MSS can be upgraded. */
> -               skb_increase_gso_size(shinfo, len_diff);
> +               if (skb->data_len - off_len > len_diff)
> +                       skb_increase_gso_size(shinfo, len_diff);
> 
>>
>>>>
>>>> But I don't mean to argue that it should do that in production.
>>>> Instead, not playing mss games would solve this and stay close to the
>>>> original datapath if no bpf program had been present. Including
>>>> maintaining the GSO invariant of sending out the same chain of packets
>>>> as received (bar the IPv6 to IPv4 change).
>>>>
>>>> This could be achieved by adding support for the flag
>>>> BPF_F_ADJ_ROOM_FIXED_GSO in the flags field of bpf_skb_change_proto.
>>>> And similar to bpf_skb_net_shrink:
>>>>
>>>>                 /* Due to header shrink, MSS can be upgraded. */
>>>>                 if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO))
>>>>                         skb_increase_gso_size(shinfo, len_diff);
>>>>
>>>> The other case, from IPv4 to IPv6 is more difficult to address, as not
>>>> reducing the MSS will result in packets exceeding MTU. That calls for
>>>> workarounds like MSS clamping. Anyway, that is out of scope here.
>>>>
>>>>
>>>>
>>>>>>
>>>>>>
>>>>>>>>
>>>>>>>> One simple solution if this packet no longer needs to be segmented
>>>>>>>> might be to reset the gso_type completely.
>>>>>>>
>>>>>>> I am not sure gso_type can be cleared even when GSO is needed.
>>>>>>>
>>>>>>>>
>>>>>>>> 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.
>>>>>>>>
>>>>>>>>
>>>>>>>>>>> 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 <dseok.yi@samsung.com>
>>>>>>>>>>> ---
>>>>>>>>>>>   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
>>>>>>>>>
>>>>>>>>>>
>>>>>>>>>> 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
>>>>>>>>>
>>>>>>>>>>
>>>>>>>>>>> +                   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;
>>>>>>>>>>>
>>>>>>>>>
>>>>>>>>>
>>>>>>>
>>>>>
>>>>
>>>> .
>>>>
>>>
> 
> 
> .
> 


^ permalink raw reply	[flat|nested] 14+ messages in thread

* RE: [PATCH bpf] bpf: check for data_len before upgrading mss when 6 to 4
  2021-05-07  9:11                       ` Yunsheng Lin
@ 2021-05-07 10:36                         ` Dongseok Yi
  0 siblings, 0 replies; 14+ messages in thread
From: Dongseok Yi @ 2021-05-07 10:36 UTC (permalink / raw)
  To: 'Yunsheng Lin', 'Willem de Bruijn'
  Cc: 'Daniel Borkmann', 'bpf',
	'Alexei Starovoitov', 'Andrii Nakryiko',
	'Martin KaFai Lau', 'Song Liu',
	'Yonghong Song', 'John Fastabend',
	'KP Singh', 'David S. Miller',
	'Jakub Kicinski', 'Network Development',
	'linux-kernel'

On Fri, May 07, 2021 at 05:11:20PM +0800, Yunsheng Lin wrote:
> On 2021/5/7 16:25, Dongseok Yi wrote:
> > On Thu, May 06, 2021 at 09:53:45PM -0400, Willem de Bruijn wrote:
> >> On Thu, May 6, 2021 at 9:45 PM Yunsheng Lin <linyunsheng@huawei.com> wrote:
> >>>
> >>> On 2021/5/7 9:25, Willem de Bruijn wrote:
> >>>>>>> head_skb's data_len is the sum of skb_gro_len for each skb of the frags.
> >>>>>>> data_len could be 8 if server sent a small size packet and it is GROed
> >>>>>>> to head_skb.
> >>>>>>>
> >>>>>>> Please let me know if I am missing something.
> >>>>>>
> >>>>>> This is my understanding of the data path. This is a forwarding path
> >>>>>> for TCP traffic.
> >>>>>>
> >>>>>> GRO is enabled and will coalesce multiple segments into a single large
> >>>>>> packet. In bad cases, the coalesced packet payload is > MSS, but < MSS
> >>>>>> + 20.
> >>>>>>
> >>>>>> Somewhere between GRO and GSO you have a BPF program that converts the
> >>>>>> IPv6 address to IPv4.
> >>>>>
> >>>>> Your understanding is right. The data path is GRO -> BPF 6 to 4 ->
> >>>>> GSO.
> >>>>>
> >>>>>>
> >>>>>> There is no concept of head_skb at the time of this BPF program. It is
> >>>>>> a single SKB, with an skb linear part and multiple data items in the
> >>>>>> frags (no frag_list).
> >>>>>
> >>>>> Sorry for the confusion. head_skb what I mentioned was a skb linear
> >>>>> part. I'm considering a single SKB with frags too.
> >>>>>
> >>>>>>
> >>>>>> When entering the GSO stack, this single skb now has a payload length
> >>>>>> < MSS. So it would just make a valid TCP packet on its own?
> >>>>>>
> >>>>>> skb_gro_len is only relevant inside the GRO stack. It internally casts
> >>>>>> the skb->cb[] to NAPI_GRO_CB. This field is a scratch area that may be
> >>>>>> reused for other purposes later by other layers of the datapath. It is
> >>>>>> not safe to read this inside bpf_skb_proto_6_to_4.
> >>>>>
> >>>>> The condition what I made uses skb->data_len not skb_gro_len. Does
> >>>>> skb->data_len have a different meaning on each layer? As I know,
> >>>>> data_len indicates the amount of frags or frag_list. skb->data_len
> >>>>> should be > 20 in the sample case because the payload size of the skb
> >>>>> linear part is the same with mss.
> >>>>
> >>>> Ah, got it.
> >>>>
> >>>> data_len is the length of the skb minus the length in the skb linear
> >>>> section (as seen in skb_headlen).
> >>>>
> >>>> So this gso skb consists of two segments, the first one entirely
> >>>> linear, the payload of the second is in skb_shinfo(skb)->frags[0].
> >>>>
> >>>> It is not guaranteed that gso skbs built from two individual skbs end
> >>>> up looking like that. Only protocol headers in the linear segment and
> >>>> the payload of both in frags is common.
> >>>>
> >>>>> We can modify netif_needs_gso as another option to hit
> >>>>> skb_needs_linearize in validate_xmit_skb. But I think we should compare
> >>>>> skb->gso_size and skb->data_len too to check if mss exceed a payload
> >>>>> size.
> >>>>
> >>>> The rest of the stack does not build such gso packets with payload len
> >>>> < mss, so we should not have to add workarounds in the gso hot path
> >>>> for this.
> >>>>
> >>>> Also no need to linearize this skb. I think that if the bpf program
> >>>> would just clear the gso type, the packet would be sent correctly.
> >>>> Unless I'm missing something.
> >>>
> >>> Does the checksum/len field in ip and tcp/udp header need adjusting
> >>> before clearing gso type as the packet has became bigger?
> >>
> >> gro takes care of this. see for instance inet_gro_complete for updates
> >> to the ip header.
> >
> > I think clearing the gso type will get an error at tcp4_gso_segment
> > because netif_needs_gso returns true in validate_xmit_skb.
> 
> So the bpf_skb_proto_6_to_4() is called after validate_xmit_skb() and
> before tcp4_gso_segment()?
> If Yes, clearing the gso type here does not seem to help.

The order what I checked is bpf_skb_proto_6_to_4() ->
validate_xmit_skb() -> tcp4_gso_segment().

> 
> >
> >>
> >>> Also, instead of testing skb->data_len, may test the skb->len?
> >>>
> >>> skb->len - (mac header + ip/ipv6 header + udp/tcp header) > mss + len_diff
> >>
> >> Yes. Essentially doing the same calculation as the gso code that is
> >> causing the packet to be dropped.
> >
> > BPF program is usually out of control. Can we take a general approach?
> > The below 2 cases has no issue when mss upgrading.
> > 1) skb->data_len > mss + 20
> > 2) skb->data_len < mss && skb->data_len > 20
> > The corner case is when
> > 3) skb->data_len > mss && skb->data_len < mss + 20
> 
> As my understanding:
> 
> Usually skb_headlen(skb) >= (mac header + ip/ipv6 header + udp/tcp header),
> other than that, there is no other guarantee as long as:
> skb->len = skb_headlen(skb) + skb->data_len
> 
> So the cases should be:
> 1. skb->len - (mac header + ip/ipv6 header + udp/tcp header) > mss + len_diff
> 2. skb->len - (mac header + ip/ipv6 header + udp/tcp header) <= mss + len_diff
> 
> The corner case is case 2.

I agree. In addition,
skbs which hits skb_increase_gso_size in bpf_skb_proto_6_to_4 are all
IPv6 + TCP by (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) condition. So
(mac header + ip/ipv6 header + udp/tcp header) can be
(mac header + ipv6 header + tcp header). But I thick Willem de Bruijn
would not want to check such network payloads in the BPF step.

> 
> >
> > But to cover #3 case, we should check the condition Yunsheng Lin said.
> > What if we do mss upgrading for both #1 and #2 cases only?
> >
> > +               unsigned short off_len = skb->data_len > shinfo->gso_size ?
> > +                       shinfo->gso_size : 0;
> > [...]
> >                 /* Due to IPv4 header, MSS can be upgraded. */
> > -               skb_increase_gso_size(shinfo, len_diff);
> > +               if (skb->data_len - off_len > len_diff)
> > +                       skb_increase_gso_size(shinfo, len_diff);
> >
> >>
> >>>>
> >>>> But I don't mean to argue that it should do that in production.
> >>>> Instead, not playing mss games would solve this and stay close to the
> >>>> original datapath if no bpf program had been present. Including
> >>>> maintaining the GSO invariant of sending out the same chain of packets
> >>>> as received (bar the IPv6 to IPv4 change).
> >>>>
> >>>> This could be achieved by adding support for the flag
> >>>> BPF_F_ADJ_ROOM_FIXED_GSO in the flags field of bpf_skb_change_proto.
> >>>> And similar to bpf_skb_net_shrink:
> >>>>
> >>>>                 /* Due to header shrink, MSS can be upgraded. */
> >>>>                 if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO))
> >>>>                         skb_increase_gso_size(shinfo, len_diff);
> >>>>
> >>>> The other case, from IPv4 to IPv6 is more difficult to address, as not
> >>>> reducing the MSS will result in packets exceeding MTU. That calls for
> >>>> workarounds like MSS clamping. Anyway, that is out of scope here.
> >>>>
> >>>>
> >>>>
> >>>>>>
> >>>>>>
> >>>>>>>>
> >>>>>>>> One simple solution if this packet no longer needs to be segmented
> >>>>>>>> might be to reset the gso_type completely.
> >>>>>>>
> >>>>>>> I am not sure gso_type can be cleared even when GSO is needed.
> >>>>>>>
> >>>>>>>>
> >>>>>>>> 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.
> >>>>>>>>
> >>>>>>>>
> >>>>>>>>>>> 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 <dseok.yi@samsung.com>
> >>>>>>>>>>> ---
> >>>>>>>>>>>   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
> >>>>>>>>>
> >>>>>>>>>>
> >>>>>>>>>> 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
> >>>>>>>>>
> >>>>>>>>>>
> >>>>>>>>>>> +                   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;
> >>>>>>>>>>>
> >>>>>>>>>
> >>>>>>>>>
> >>>>>>>
> >>>>>
> >>>>
> >>>> .
> >>>>
> >>>
> >
> >
> > .
> >



^ permalink raw reply	[flat|nested] 14+ messages in thread

* Re: [PATCH bpf] bpf: check for data_len before upgrading mss when 6 to 4
  2021-05-07  8:25                     ` Dongseok Yi
  2021-05-07  9:11                       ` Yunsheng Lin
@ 2021-05-07 13:50                       ` Willem de Bruijn
  1 sibling, 0 replies; 14+ messages in thread
From: Willem de Bruijn @ 2021-05-07 13:50 UTC (permalink / raw)
  To: Dongseok Yi
  Cc: Yunsheng Lin, Daniel Borkmann, bpf, Alexei Starovoitov,
	Andrii Nakryiko, Martin KaFai Lau, Song Liu, Yonghong Song,
	John Fastabend, KP Singh, David S. Miller, Jakub Kicinski,
	Network Development, linux-kernel

On Fri, May 7, 2021 at 4:25 AM Dongseok Yi <dseok.yi@samsung.com> wrote:
>
> On Thu, May 06, 2021 at 09:53:45PM -0400, Willem de Bruijn wrote:
> > On Thu, May 6, 2021 at 9:45 PM Yunsheng Lin <linyunsheng@huawei.com> wrote:
> > >
> > > On 2021/5/7 9:25, Willem de Bruijn wrote:
> > > >>>> head_skb's data_len is the sum of skb_gro_len for each skb of the frags.
> > > >>>> data_len could be 8 if server sent a small size packet and it is GROed
> > > >>>> to head_skb.
> > > >>>>
> > > >>>> Please let me know if I am missing something.
> > > >>>
> > > >>> This is my understanding of the data path. This is a forwarding path
> > > >>> for TCP traffic.
> > > >>>
> > > >>> GRO is enabled and will coalesce multiple segments into a single large
> > > >>> packet. In bad cases, the coalesced packet payload is > MSS, but < MSS
> > > >>> + 20.
> > > >>>
> > > >>> Somewhere between GRO and GSO you have a BPF program that converts the
> > > >>> IPv6 address to IPv4.
> > > >>
> > > >> Your understanding is right. The data path is GRO -> BPF 6 to 4 ->
> > > >> GSO.
> > > >>
> > > >>>
> > > >>> There is no concept of head_skb at the time of this BPF program. It is
> > > >>> a single SKB, with an skb linear part and multiple data items in the
> > > >>> frags (no frag_list).
> > > >>
> > > >> Sorry for the confusion. head_skb what I mentioned was a skb linear
> > > >> part. I'm considering a single SKB with frags too.
> > > >>
> > > >>>
> > > >>> When entering the GSO stack, this single skb now has a payload length
> > > >>> < MSS. So it would just make a valid TCP packet on its own?
> > > >>>
> > > >>> skb_gro_len is only relevant inside the GRO stack. It internally casts
> > > >>> the skb->cb[] to NAPI_GRO_CB. This field is a scratch area that may be
> > > >>> reused for other purposes later by other layers of the datapath. It is
> > > >>> not safe to read this inside bpf_skb_proto_6_to_4.
> > > >>
> > > >> The condition what I made uses skb->data_len not skb_gro_len. Does
> > > >> skb->data_len have a different meaning on each layer? As I know,
> > > >> data_len indicates the amount of frags or frag_list. skb->data_len
> > > >> should be > 20 in the sample case because the payload size of the skb
> > > >> linear part is the same with mss.
> > > >
> > > > Ah, got it.
> > > >
> > > > data_len is the length of the skb minus the length in the skb linear
> > > > section (as seen in skb_headlen).
> > > >
> > > > So this gso skb consists of two segments, the first one entirely
> > > > linear, the payload of the second is in skb_shinfo(skb)->frags[0].
> > > >
> > > > It is not guaranteed that gso skbs built from two individual skbs end
> > > > up looking like that. Only protocol headers in the linear segment and
> > > > the payload of both in frags is common.
> > > >
> > > >> We can modify netif_needs_gso as another option to hit
> > > >> skb_needs_linearize in validate_xmit_skb. But I think we should compare
> > > >> skb->gso_size and skb->data_len too to check if mss exceed a payload
> > > >> size.
> > > >
> > > > The rest of the stack does not build such gso packets with payload len
> > > > < mss, so we should not have to add workarounds in the gso hot path
> > > > for this.
> > > >
> > > > Also no need to linearize this skb. I think that if the bpf program
> > > > would just clear the gso type, the packet would be sent correctly.
> > > > Unless I'm missing something.
> > >
> > > Does the checksum/len field in ip and tcp/udp header need adjusting
> > > before clearing gso type as the packet has became bigger?
> >
> > gro takes care of this. see for instance inet_gro_complete for updates
> > to the ip header.
>
> I think clearing the gso type will get an error at tcp4_gso_segment
> because netif_needs_gso returns true in validate_xmit_skb.

Oh right. Whether a packet is gso is defined by gso_size being
non-zero, not by gso_type.

> >
> > > Also, instead of testing skb->data_len, may test the skb->len?
> > >
> > > skb->len - (mac header + ip/ipv6 header + udp/tcp header) > mss + len_diff
> >
> > Yes. Essentially doing the same calculation as the gso code that is
> > causing the packet to be dropped.
>
> BPF program is usually out of control. Can we take a general approach?
> The below 2 cases has no issue when mss upgrading.
> 1) skb->data_len > mss + 20
> 2) skb->data_len < mss && skb->data_len > 20
> The corner case is when
> 3) skb->data_len > mss && skb->data_len < mss + 20

Again, you cannot use skb->data_len alone to make inferences about the
size of the second packet.

>
> But to cover #3 case, we should check the condition Yunsheng Lin said.
> What if we do mss upgrading for both #1 and #2 cases only?
>
> +               unsigned short off_len = skb->data_len > shinfo->gso_size ?
> +                       shinfo->gso_size : 0;
> [...]
>                 /* Due to IPv4 header, MSS can be upgraded. */
> -               skb_increase_gso_size(shinfo, len_diff);
> +               if (skb->data_len - off_len > len_diff)
> +                       skb_increase_gso_size(shinfo, len_diff);

That generates TCP packets with different MSS within the same stream.

My suggestion remains to just not change MSS at all. But this has to
be a new flag to avoid changing established behavior.

^ permalink raw reply	[flat|nested] 14+ messages in thread

end of thread, back to index

Thread overview: 14+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
     [not found] <CGME20210429102143epcas2p4c8747c09a9de28f003c20389c050394a@epcas2p4.samsung.com>
2021-04-29 10:08 ` [PATCH bpf] bpf: check for data_len before upgrading mss when 6 to 4 Dongseok Yi
2021-05-05 20:55   ` Daniel Borkmann
2021-05-06  0:45     ` Dongseok Yi
2021-05-06  1:45       ` Willem de Bruijn
2021-05-06  2:27         ` Dongseok Yi
2021-05-06 18:21           ` Willem de Bruijn
2021-05-07  0:53             ` Dongseok Yi
2021-05-07  1:25               ` Willem de Bruijn
2021-05-07  1:45                 ` Yunsheng Lin
2021-05-07  1:53                   ` Willem de Bruijn
2021-05-07  8:25                     ` Dongseok Yi
2021-05-07  9:11                       ` Yunsheng Lin
2021-05-07 10:36                         ` Dongseok Yi
2021-05-07 13:50                       ` Willem de Bruijn

BPF Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/bpf/0 bpf/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 bpf bpf/ https://lore.kernel.org/bpf \
		bpf@vger.kernel.org
	public-inbox-index bpf

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.bpf


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git