| Message ID | 1620714998-120657-1-git-send-email-dseok.yi@samsung.com |
|---|---|
| State | New |
| Headers | show |
| Series | [bpf,v2] bpf: check BPF_F_ADJ_ROOM_FIXED_GSO when upgrading mss in 6 to 4 | expand |
On Tue, May 11, 2021 at 2:51 AM Dongseok Yi <dseok.yi@samsung.com> wrote: > > In the forwarding path GRO -> BPF 6 to 4 -> GSO for TCP traffic, the > coalesced packet payload can be > MSS, but < MSS + 20. > bpf_skb_proto_6_to_4 will increase the MSS and it can be > the payload > length. After then tcp_gso_segment checks for the payload length if it > is <= MSS. The condition is causing the packet to be dropped. > > tcp_gso_segment(): > [...] > mss = skb_shinfo(skb)->gso_size; > if (unlikely(skb->len <= mss)) > goto out; > [...] > > Allow to increase MSS when BPF_F_ADJ_ROOM_FIXED_GSO is not set. > > Fixes: 6578171a7ff0 (bpf: add bpf_skb_change_proto helper) > Signed-off-by: Dongseok Yi <dseok.yi@samsung.com> > > --- Thanks. Note that this feature does not preclude the alternatives discussed, of converting the packet to non-TSO (by clearing gso_size) or optionally modifying MSS (but that should get okay from TCP experts). I would target this for bpf-next and drop the Fixes. But that is admittedly debatable. > net/core/filter.c | 13 +++++++------ > 1 file changed, 7 insertions(+), 6 deletions(-) > > v2: > per Willem de Bruijn request, > checked the flag instead of a generic approach. > > diff --git a/net/core/filter.c b/net/core/filter.c > index cae56d0..a98b28d 100644 > --- a/net/core/filter.c > +++ b/net/core/filter.c > @@ -3276,7 +3276,7 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) > return 0; > } > > -static int bpf_skb_proto_6_to_4(struct sk_buff *skb) > +static int bpf_skb_proto_6_to_4(struct sk_buff *skb, u64 flags) > { > const u32 len_diff = sizeof(struct ipv6hdr) - sizeof(struct iphdr); > u32 off = skb_mac_header_len(skb); > @@ -3305,7 +3305,8 @@ 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 (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) > + 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; > @@ -3317,7 +3318,7 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) > return 0; > } > > -static int bpf_skb_proto_xlat(struct sk_buff *skb, __be16 to_proto) > +static int bpf_skb_proto_xlat(struct sk_buff *skb, __be16 to_proto, u64 flags) > { > __be16 from_proto = skb->protocol; > > @@ -3327,7 +3328,7 @@ static int bpf_skb_proto_xlat(struct sk_buff *skb, __be16 to_proto) > > if (from_proto == htons(ETH_P_IPV6) && > to_proto == htons(ETH_P_IP)) > - return bpf_skb_proto_6_to_4(skb); > + return bpf_skb_proto_6_to_4(skb, flags); > > return -ENOTSUPP; > } > @@ -3337,7 +3338,7 @@ BPF_CALL_3(bpf_skb_change_proto, struct sk_buff *, skb, __be16, proto, > { > int ret; > > - if (unlikely(flags)) > + if (unlikely(flags & ~(BPF_F_ADJ_ROOM_FIXED_GSO))) > return -EINVAL; Once allowing this flag, please immediately support it for both bpf_skb_proto_6_to_4 and bpf_skb_4_to_6. We cannot do that later if we ignore the second case now. > /* General idea is that this helper does the basic groundwork > @@ -3357,7 +3358,7 @@ BPF_CALL_3(bpf_skb_change_proto, struct sk_buff *, skb, __be16, proto, > * that. For offloads, we mark packet as dodgy, so that headers > * need to be verified first. > */ > - ret = bpf_skb_proto_xlat(skb, proto); > + ret = bpf_skb_proto_xlat(skb, proto, flags); > bpf_compute_data_pointers(skb); > return ret; > } > -- > 2.7.4 >
On Tue, May 11, 2021 at 01:42:46PM -0400, Willem de Bruijn wrote: > On Tue, May 11, 2021 at 2:51 AM Dongseok Yi <dseok.yi@samsung.com> wrote: > > > > In the forwarding path GRO -> BPF 6 to 4 -> GSO for TCP traffic, the > > coalesced packet payload can be > MSS, but < MSS + 20. > > bpf_skb_proto_6_to_4 will increase the MSS and it can be > the payload > > length. After then tcp_gso_segment checks for the payload length if it > > is <= MSS. The condition is causing the packet to be dropped. > > > > tcp_gso_segment(): > > [...] > > mss = skb_shinfo(skb)->gso_size; > > if (unlikely(skb->len <= mss)) > > goto out; > > [...] > > > > Allow to increase MSS when BPF_F_ADJ_ROOM_FIXED_GSO is not set. > > > > Fixes: 6578171a7ff0 (bpf: add bpf_skb_change_proto helper) > > Signed-off-by: Dongseok Yi <dseok.yi@samsung.com> > > > > --- > > Thanks. Note that this feature does not preclude the alternatives > discussed, of converting the packet to non-TSO (by clearing gso_size) > or optionally modifying MSS (but that should get okay from TCP > experts). > > I would target this for bpf-next and drop the Fixes. But that is > admittedly debatable. No problem. We can make a better decision under bpf-next. > > > net/core/filter.c | 13 +++++++------ > > 1 file changed, 7 insertions(+), 6 deletions(-) > > > > v2: > > per Willem de Bruijn request, > > checked the flag instead of a generic approach. > > > > diff --git a/net/core/filter.c b/net/core/filter.c > > index cae56d0..a98b28d 100644 > > --- a/net/core/filter.c > > +++ b/net/core/filter.c > > @@ -3276,7 +3276,7 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) > > return 0; > > } > > > > -static int bpf_skb_proto_6_to_4(struct sk_buff *skb) > > +static int bpf_skb_proto_6_to_4(struct sk_buff *skb, u64 flags) > > { > > const u32 len_diff = sizeof(struct ipv6hdr) - sizeof(struct iphdr); > > u32 off = skb_mac_header_len(skb); > > @@ -3305,7 +3305,8 @@ 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 (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) > > + 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; > > @@ -3317,7 +3318,7 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) > > return 0; > > } > > > > -static int bpf_skb_proto_xlat(struct sk_buff *skb, __be16 to_proto) > > +static int bpf_skb_proto_xlat(struct sk_buff *skb, __be16 to_proto, u64 flags) > > { > > __be16 from_proto = skb->protocol; > > > > @@ -3327,7 +3328,7 @@ static int bpf_skb_proto_xlat(struct sk_buff *skb, __be16 to_proto) > > > > if (from_proto == htons(ETH_P_IPV6) && > > to_proto == htons(ETH_P_IP)) > > - return bpf_skb_proto_6_to_4(skb); > > + return bpf_skb_proto_6_to_4(skb, flags); > > > > return -ENOTSUPP; > > } > > @@ -3337,7 +3338,7 @@ BPF_CALL_3(bpf_skb_change_proto, struct sk_buff *, skb, __be16, proto, > > { > > int ret; > > > > - if (unlikely(flags)) > > + if (unlikely(flags & ~(BPF_F_ADJ_ROOM_FIXED_GSO))) > > return -EINVAL; > > Once allowing this flag, please immediately support it for both > bpf_skb_proto_6_to_4 and bpf_skb_4_to_6. > > We cannot do that later if we ignore the second case now. I will make v3 for both 6_to_4 and 4_to_6. > > > > /* General idea is that this helper does the basic groundwork > > @@ -3357,7 +3358,7 @@ BPF_CALL_3(bpf_skb_change_proto, struct sk_buff *, skb, __be16, proto, > > * that. For offloads, we mark packet as dodgy, so that headers > > * need to be verified first. > > */ > > - ret = bpf_skb_proto_xlat(skb, proto); > > + ret = bpf_skb_proto_xlat(skb, proto, flags); > > bpf_compute_data_pointers(skb); > > return ret; > > } > > -- > > 2.7.4 > >
On Wed, May 12, 2021 at 3:41 AM Dongseok Yi <dseok.yi@samsung.com> wrote: > > In the forwarding path GRO -> BPF 6 to 4 -> GSO for TCP traffic, the > coalesced packet payload can be > MSS, but < MSS + 20. > bpf_skb_proto_6_to_4 will upgrade the MSS and it can be > the payload > length. After then tcp_gso_segment checks for the payload length if it > is <= MSS. The condition is causing the packet to be dropped. > > tcp_gso_segment(): > [...] > mss = skb_shinfo(skb)->gso_size; > if (unlikely(skb->len <= mss)) > goto out; > [...] > > Allow to upgrade/downgrade MSS only when BPF_F_ADJ_ROOM_FIXED_GSO is > not set. > > Signed-off-by: Dongseok Yi <dseok.yi@samsung.com> Acked-by: Willem de Bruijn <willemb@google.com>
diff --git a/net/core/filter.c b/net/core/filter.c index cae56d0..a98b28d 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3276,7 +3276,7 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) return 0; } -static int bpf_skb_proto_6_to_4(struct sk_buff *skb) +static int bpf_skb_proto_6_to_4(struct sk_buff *skb, u64 flags) { const u32 len_diff = sizeof(struct ipv6hdr) - sizeof(struct iphdr); u32 off = skb_mac_header_len(skb); @@ -3305,7 +3305,8 @@ 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 (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) + 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; @@ -3317,7 +3318,7 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) return 0; } -static int bpf_skb_proto_xlat(struct sk_buff *skb, __be16 to_proto) +static int bpf_skb_proto_xlat(struct sk_buff *skb, __be16 to_proto, u64 flags) { __be16 from_proto = skb->protocol; @@ -3327,7 +3328,7 @@ static int bpf_skb_proto_xlat(struct sk_buff *skb, __be16 to_proto) if (from_proto == htons(ETH_P_IPV6) && to_proto == htons(ETH_P_IP)) - return bpf_skb_proto_6_to_4(skb); + return bpf_skb_proto_6_to_4(skb, flags); return -ENOTSUPP; } @@ -3337,7 +3338,7 @@ BPF_CALL_3(bpf_skb_change_proto, struct sk_buff *, skb, __be16, proto, { int ret; - if (unlikely(flags)) + if (unlikely(flags & ~(BPF_F_ADJ_ROOM_FIXED_GSO))) return -EINVAL; /* General idea is that this helper does the basic groundwork @@ -3357,7 +3358,7 @@ BPF_CALL_3(bpf_skb_change_proto, struct sk_buff *, skb, __be16, proto, * that. For offloads, we mark packet as dodgy, so that headers * need to be verified first. */ - ret = bpf_skb_proto_xlat(skb, proto); + ret = bpf_skb_proto_xlat(skb, proto, flags); bpf_compute_data_pointers(skb); return ret; }
In the forwarding path GRO -> BPF 6 to 4 -> GSO for TCP traffic, the coalesced packet payload can be > MSS, but < MSS + 20. bpf_skb_proto_6_to_4 will increase the MSS and it can be > the payload length. After then tcp_gso_segment checks for the payload length if it is <= MSS. The condition is causing the packet to be dropped. tcp_gso_segment(): [...] mss = skb_shinfo(skb)->gso_size; if (unlikely(skb->len <= mss)) goto out; [...] Allow to increase MSS when BPF_F_ADJ_ROOM_FIXED_GSO is not set. Fixes: 6578171a7ff0 (bpf: add bpf_skb_change_proto helper) Signed-off-by: Dongseok Yi <dseok.yi@samsung.com> --- net/core/filter.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) v2: per Willem de Bruijn request, checked the flag instead of a generic approach.