Re: [PATCH v2 4/5] bpf: allow new DECAP flags and add guard rails
From: Martin KaFai Lau <martin.lau@linux.dev>
Date: 2026-03-24 18:31:04
Also in:
bpf, lkml
On 3/18/26 6:42 AM, Nick Hudson wrote:
quoted hunk ↗ jump to hunk
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 <redacted> Signed-off-by: Max Tottenham <redacted> Co-developed-by: Anna Glasgall <redacted> Signed-off-by: Anna Glasgall <redacted> Signed-off-by: Nick Hudson <redacted> --- 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) {
This change should be done together with the macro refactoring patch mentioned in patch 3.
+ 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)iiuc, this 'if' and the len_min assignment changes below replace the existing switch case. Please separate this no-op change from the new flag validation logic. It is small enough to be done together in the macro refactoring patch also.
+ 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; + + 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);