Re: [PATCH v2 4/5] bpf: allow new DECAP flags and add guard rails

[Hudson, Nick]

> On 18 Mar 2026, at 20:02, Willem de Bruijn <willemdebruijn.kernel@xxxxxxxxx> wrote:
> 
> !-------------------------------------------------------------------|
>  This Message Is From an External Sender
>  This message came from outside your organization.
> |-------------------------------------------------------------------!
> 
> Nick Hudson wrote:
>> Add checks to require shrink-only decap, reject conflicting decap flag
>> combinations, and verify removed length is sufficient for claimed header
>> decapsulation.
>> 
>> Co-developed-by: Max Tottenham <mtottenh@xxxxxxxxxx>
>> Signed-off-by: Max Tottenham <mtottenh@xxxxxxxxxx>
>> Co-developed-by: Anna Glasgall <aglasgal@xxxxxxxxxx>
>> Signed-off-by: Anna Glasgall <aglasgal@xxxxxxxxxx>
>> Signed-off-by: Nick Hudson <nhudson@xxxxxxxxxx>
>> ---
>> net/core/filter.c | 47 +++++++++++++++++++++++++++++++++++++----------
>> 1 file changed, 37 insertions(+), 10 deletions(-)
>> 
>> diff --git a/net/core/filter.c b/net/core/filter.c
>> index 7c2871b40fe4..47aec44a9cd3 100644
>> --- a/net/core/filter.c
>> +++ b/net/core/filter.c
>> @@ -56,6 +56,7 @@
>> #include <net/sock_reuseport.h>
>> #include <net/busy_poll.h>
>> #include <net/tcp.h>
>> +#include <net/gre.h>
>> #include <net/xfrm.h>
>> #include <net/udp.h>
>> #include <linux/bpf_trace.h>
>> @@ -3496,7 +3497,9 @@ static u32 bpf_skb_net_base_len(const struct sk_buff *skb)
>> BPF_F_ADJ_ROOM_ENCAP_L2( \
>>  BPF_ADJ_ROOM_ENCAP_L2_MASK))
>> 
>> -#define BPF_F_ADJ_ROOM_DECAP_MASK (BPF_F_ADJ_ROOM_DECAP_L3_MASK)
>> +#define BPF_F_ADJ_ROOM_DECAP_MASK (BPF_F_ADJ_ROOM_DECAP_L3_MASK | \
>> + BPF_F_ADJ_ROOM_DECAP_L4_MASK | \
>> + BPF_F_ADJ_ROOM_DECAP_IPXIP_MASK)
>> 
>> #define BPF_F_ADJ_ROOM_MASK (BPF_F_ADJ_ROOM_FIXED_GSO | \
>> BPF_F_ADJ_ROOM_ENCAP_MASK | \
>> @@ -3743,20 +3746,44 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
>> return -ENOTSUPP;
>> }
>> 
>> - if (flags & BPF_F_ADJ_ROOM_DECAP_L3_MASK) {
>> + if (flags & BPF_F_ADJ_ROOM_DECAP_MASK) {
>> + u32 len_decap_min = 0;
>> +
>> if (!shrink)
>> return -EINVAL;
>> 
>> - switch (flags & BPF_F_ADJ_ROOM_DECAP_L3_MASK) {
>> - case BPF_F_ADJ_ROOM_DECAP_L3_IPV4:
>> + /* Reject mutually exclusive decap flag pairs. */
>> + if ((flags & BPF_F_ADJ_ROOM_DECAP_L3_MASK) ==
>> +    BPF_F_ADJ_ROOM_DECAP_L3_MASK)
>> + return -EINVAL;
>> +
>> + if ((flags & BPF_F_ADJ_ROOM_DECAP_L4_MASK) ==
>> +    BPF_F_ADJ_ROOM_DECAP_L4_MASK)
>> + return -EINVAL;
>> +
>> + if ((flags & BPF_F_ADJ_ROOM_DECAP_IPXIP_MASK) ==
>> +    BPF_F_ADJ_ROOM_DECAP_IPXIP_MASK)
>> + return -EINVAL;
>> +
>> + /* Reject mutually exclusive decap tunnel type flags. */
>> + if ((flags & BPF_F_ADJ_ROOM_DECAP_L4_MASK) &&
>> +    (flags & BPF_F_ADJ_ROOM_DECAP_IPXIP_MASK))
>> + return -EINVAL;
>> +
>> + if (flags & BPF_F_ADJ_ROOM_DECAP_L4_UDP)
>> + len_decap_min += sizeof(struct udphdr);
>> +
>> + if (flags & BPF_F_ADJ_ROOM_DECAP_L4_GRE)
>> + len_decap_min += sizeof(struct gre_base_hdr);
>> +
>> + if (len_diff_abs < len_decap_min)
>> + return -EINVAL;
> 
> Should this test come after the below IP flags?

Should it?

Seems to me it can bail early without having to check the IP flags. len_decap_min vs len_min.

What am I missing?

> 
>> +
>> + if (flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV4)
>> len_min = sizeof(struct iphdr);
>> - break;
>> - case BPF_F_ADJ_ROOM_DECAP_L3_IPV6:
>> +
>> + if (flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV6)
>> len_min = sizeof(struct ipv6hdr);
>> - break;
>> - default:
>> - return -EINVAL;
>> - }
>> }
>> 
>> len_cur = skb->len - skb_network_offset(skb);
>> -- 
>> 2.34.1
>> 
> 
>

Attachment: smime.p7s
Description: S/MIME cryptographic signature