[PATCH v5 1/6] bpf: name the enum for BPF_FUNC_skb_adjust_room flags

[PATCH v5 1/6] bpf: name the enum for BPF_FUNC_skb_adjust_room flags

[Nick Hudson]

The existing anonymous enum for BPF_FUNC_skb_adjust_room flags is
named to enum bpf_adj_room_flags to enable CO-RE (Compile Once -
Run Everywhere) lookups in BPF programs.

Co-developed-by: Max Tottenham <mtottenh@akamai.com>
Signed-off-by: Max Tottenham <mtottenh@akamai.com>
Co-developed-by: Anna Glasgall <aglasgal@akamai.com>
Signed-off-by: Anna Glasgall <aglasgal@akamai.com>
Signed-off-by: Nick Hudson <nhudson@akamai.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
---
 include/uapi/linux/bpf.h       | 2 +-
 tools/include/uapi/linux/bpf.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 552bc5d9afbd..c021ed8d7b44 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -6211,7 +6211,7 @@ enum {
 };
 
 /* BPF_FUNC_skb_adjust_room flags. */
-enum {
+enum bpf_adj_room_flags {
 	BPF_F_ADJ_ROOM_FIXED_GSO	= (1ULL << 0),
 	BPF_F_ADJ_ROOM_ENCAP_L3_IPV4	= (1ULL << 1),
 	BPF_F_ADJ_ROOM_ENCAP_L3_IPV6	= (1ULL << 2),
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 677be9a47347..ca35ed622ed5 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -6211,7 +6211,7 @@ enum {
 };
 
 /* BPF_FUNC_skb_adjust_room flags. */
-enum {
+enum bpf_adj_room_flags {
 	BPF_F_ADJ_ROOM_FIXED_GSO	= (1ULL << 0),
 	BPF_F_ADJ_ROOM_ENCAP_L3_IPV4	= (1ULL << 1),
 	BPF_F_ADJ_ROOM_ENCAP_L3_IPV6	= (1ULL << 2),
-- 
2.34.1

[PATCH v5 2/6] bpf: refactor masks for ADJ_ROOM flags and encap validation

[Nick Hudson]

Refactor the helper masks for bpf_skb_adjust_room() flags to simplify
validation logic and introduce:

- BPF_F_ADJ_ROOM_ENCAP_MASK
- BPF_F_ADJ_ROOM_DECAP_MASK

Refactor existing validation checks in bpf_skb_net_shrink()
and bpf_skb_adjust_room() to use the new masks (no behavior change).

This is in preparation for supporting the new decap flags.

Co-developed-by: Max Tottenham <mtottenh@akamai.com>
Signed-off-by: Max Tottenham <mtottenh@akamai.com>
Co-developed-by: Anna Glasgall <aglasgal@akamai.com>
Signed-off-by: Anna Glasgall <aglasgal@akamai.com>
Signed-off-by: Nick Hudson <nhudson@akamai.com>
---
---
 net/core/filter.c | 38 +++++++++++++++++++++-----------------
 1 file changed, 21 insertions(+), 17 deletions(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index 78b548158fb0..4e860da4381d 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3490,14 +3490,19 @@ static u32 bpf_skb_net_base_len(const struct sk_buff *skb)
 #define BPF_F_ADJ_ROOM_DECAP_L3_MASK	(BPF_F_ADJ_ROOM_DECAP_L3_IPV4 | \
 					 BPF_F_ADJ_ROOM_DECAP_L3_IPV6)
 
-#define BPF_F_ADJ_ROOM_MASK		(BPF_F_ADJ_ROOM_FIXED_GSO | \
-					 BPF_F_ADJ_ROOM_ENCAP_L3_MASK | \
+#define BPF_F_ADJ_ROOM_ENCAP_MASK	(BPF_F_ADJ_ROOM_ENCAP_L3_MASK | \
 					 BPF_F_ADJ_ROOM_ENCAP_L4_GRE | \
 					 BPF_F_ADJ_ROOM_ENCAP_L4_UDP | \
 					 BPF_F_ADJ_ROOM_ENCAP_L2_ETH | \
 					 BPF_F_ADJ_ROOM_ENCAP_L2( \
-					  BPF_ADJ_ROOM_ENCAP_L2_MASK) | \
-					 BPF_F_ADJ_ROOM_DECAP_L3_MASK)
+					  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_MASK		(BPF_F_ADJ_ROOM_FIXED_GSO | \
+					 BPF_F_ADJ_ROOM_ENCAP_MASK | \
+					 BPF_F_ADJ_ROOM_DECAP_MASK | \
+					 BPF_F_ADJ_ROOM_NO_CSUM_RESET)
 
 static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 			    u64 flags)
@@ -3618,8 +3623,8 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff,
 {
 	int ret;
 
-	if (unlikely(flags & ~(BPF_F_ADJ_ROOM_FIXED_GSO |
-			       BPF_F_ADJ_ROOM_DECAP_L3_MASK |
+	if (unlikely(flags & ~(BPF_F_ADJ_ROOM_DECAP_MASK |
+			       BPF_F_ADJ_ROOM_FIXED_GSO |
 			       BPF_F_ADJ_ROOM_NO_CSUM_RESET)))
 		return -EINVAL;
 
@@ -3715,8 +3720,7 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
 	u32 off;
 	int ret;
 
-	if (unlikely(flags & ~(BPF_F_ADJ_ROOM_MASK |
-			       BPF_F_ADJ_ROOM_NO_CSUM_RESET)))
+	if (unlikely(flags & ~BPF_F_ADJ_ROOM_MASK))
 		return -EINVAL;
 	if (unlikely(len_diff_abs > 0xfffU))
 		return -EFAULT;
@@ -3735,20 +3739,20 @@ 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) {
 		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_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

Re: [PATCH v5 2/6] bpf: refactor masks for ADJ_ROOM flags and encap validation

[Willem de Bruijn]

Nick Hudson wrote:
> Refactor the helper masks for bpf_skb_adjust_room() flags to simplify
> validation logic and introduce:
> 
> - BPF_F_ADJ_ROOM_ENCAP_MASK
> - BPF_F_ADJ_ROOM_DECAP_MASK
> 
> Refactor existing validation checks in bpf_skb_net_shrink()
> and bpf_skb_adjust_room() to use the new masks (no behavior change).
> 
> This is in preparation for supporting the new decap flags.
> 
> Co-developed-by: Max Tottenham <mtottenh@akamai.com>
> Signed-off-by: Max Tottenham <mtottenh@akamai.com>
> Co-developed-by: Anna Glasgall <aglasgal@akamai.com>
> Signed-off-by: Anna Glasgall <aglasgal@akamai.com>
> Signed-off-by: Nick Hudson <nhudson@akamai.com>

Reviewed-by: Willem de Bruijn <willemb@google.com>

[PATCH v5 3/6] bpf: add BPF_F_ADJ_ROOM_DECAP_* flags for tunnel decapsulation

[Nick Hudson]

Add new bpf_skb_adjust_room() decapsulation flags:

- BPF_F_ADJ_ROOM_DECAP_L4_GRE
- BPF_F_ADJ_ROOM_DECAP_L4_UDP
- BPF_F_ADJ_ROOM_DECAP_IPXIP4
- BPF_F_ADJ_ROOM_DECAP_IPXIP6

These flags let BPF programs describe which tunnel layer is being
removed, so later changes can update tunnel-related GSO state
accordingly during decapsulation.

This patch only introduces the UAPI flag definitions and helper
documentation.

Co-developed-by: Max Tottenham <mtottenh@akamai.com>
Signed-off-by: Max Tottenham <mtottenh@akamai.com>
Co-developed-by: Anna Glasgall <aglasgal@akamai.com>
Signed-off-by: Anna Glasgall <aglasgal@akamai.com>
Signed-off-by: Nick Hudson <nhudson@akamai.com>
---
 include/uapi/linux/bpf.h       | 34 ++++++++++++++++++++++++++++++++--
 tools/include/uapi/linux/bpf.h | 34 ++++++++++++++++++++++++++++++++--
 2 files changed, 64 insertions(+), 4 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index c021ed8d7b44..4a53e731c554 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3010,8 +3010,34 @@ union bpf_attr {
  *
  *		* **BPF_F_ADJ_ROOM_DECAP_L3_IPV4**,
  *		  **BPF_F_ADJ_ROOM_DECAP_L3_IPV6**:
- *		  Indicate the new IP header version after decapsulating the outer
- *		  IP header. Used when the inner and outer IP versions are different.
+ *		  Indicate the new IP header version after decapsulating the
+ *		  outer IP header. Used when the inner and outer IP versions
+ *		  are different. These flags only trigger a protocol change
+ *		  without clearing any tunnel-specific GSO flags.
+ *
+ *		* **BPF_F_ADJ_ROOM_DECAP_L4_GRE**:
+ *		  Clear GRE tunnel GSO flags (SKB_GSO_GRE and SKB_GSO_GRE_CSUM)
+ *		  when decapsulating a GRE tunnel.
+ *
+ *		* **BPF_F_ADJ_ROOM_DECAP_L4_UDP**:
+ *		  Clear UDP tunnel GSO flags (SKB_GSO_UDP_TUNNEL and
+ *		  SKB_GSO_UDP_TUNNEL_CSUM) when decapsulating a UDP tunnel.
+ *
+ *		* **BPF_F_ADJ_ROOM_DECAP_IPXIP4**:
+ *		  Clear IPIP/SIT tunnel GSO flag (SKB_GSO_IPXIP4) when decapsulating
+ *		  a tunnel with an outer IPv4 header (IPv4-in-IPv4 or IPv6-in-IPv4).
+ *
+ *		* **BPF_F_ADJ_ROOM_DECAP_IPXIP6**:
+ *		  Clear IPv6 encapsulation tunnel GSO flag (SKB_GSO_IPXIP6) when
+ *		  decapsulating a tunnel with an outer IPv6 header (IPv6-in-IPv6
+ *		  or IPv4-in-IPv6).
+ *
+ *		When using the decapsulation flags above, the skb->encapsulation
+ *		flag is automatically cleared if all tunnel-specific GSO flags
+ *		(SKB_GSO_UDP_TUNNEL, SKB_GSO_UDP_TUNNEL_CSUM, SKB_GSO_GRE,
+ *		SKB_GSO_GRE_CSUM, SKB_GSO_IPXIP4, SKB_GSO_IPXIP6) have been
+ *		removed from the packet. This handles cases where all tunnel
+ *		layers have been decapsulated.
  *
  * 		A call to this helper is susceptible to change the underlying
  * 		packet buffer. Therefore, at load time, all checks on pointers
@@ -6221,6 +6247,10 @@ enum bpf_adj_room_flags {
 	BPF_F_ADJ_ROOM_ENCAP_L2_ETH	= (1ULL << 6),
 	BPF_F_ADJ_ROOM_DECAP_L3_IPV4	= (1ULL << 7),
 	BPF_F_ADJ_ROOM_DECAP_L3_IPV6	= (1ULL << 8),
+	BPF_F_ADJ_ROOM_DECAP_L4_GRE	= (1ULL << 9),
+	BPF_F_ADJ_ROOM_DECAP_L4_UDP	= (1ULL << 10),
+	BPF_F_ADJ_ROOM_DECAP_IPXIP4	= (1ULL << 11),
+	BPF_F_ADJ_ROOM_DECAP_IPXIP6	= (1ULL << 12),
 };
 
 enum {
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index ca35ed622ed5..f4c2fbd8fe68 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3010,8 +3010,34 @@ union bpf_attr {
  *
  *		* **BPF_F_ADJ_ROOM_DECAP_L3_IPV4**,
  *		  **BPF_F_ADJ_ROOM_DECAP_L3_IPV6**:
- *		  Indicate the new IP header version after decapsulating the outer
- *		  IP header. Used when the inner and outer IP versions are different.
+ *		  Indicate the new IP header version after decapsulating the
+ *		  outer IP header. Used when the inner and outer IP versions
+ *		  are different. These flags only trigger a protocol change
+ *		  without clearing any tunnel-specific GSO flags.
+ *
+ *		* **BPF_F_ADJ_ROOM_DECAP_L4_GRE**:
+ *		  Clear GRE tunnel GSO flags (SKB_GSO_GRE and SKB_GSO_GRE_CSUM)
+ *		  when decapsulating a GRE tunnel.
+ *
+ *		* **BPF_F_ADJ_ROOM_DECAP_L4_UDP**:
+ *		  Clear UDP tunnel GSO flags (SKB_GSO_UDP_TUNNEL and
+ *		  SKB_GSO_UDP_TUNNEL_CSUM) when decapsulating a UDP tunnel.
+ *
+ *		* **BPF_F_ADJ_ROOM_DECAP_IPXIP4**:
+ *		  Clear IPIP/SIT tunnel GSO flag (SKB_GSO_IPXIP4) when decapsulating
+ *		  a tunnel with an outer IPv4 header (IPv4-in-IPv4 or IPv6-in-IPv4).
+ *
+ *		* **BPF_F_ADJ_ROOM_DECAP_IPXIP6**:
+ *		  Clear IPv6 encapsulation tunnel GSO flag (SKB_GSO_IPXIP6) when
+ *		  decapsulating a tunnel with an outer IPv6 header (IPv6-in-IPv6
+ *		  or IPv4-in-IPv6).
+ *
+ *		When using the decapsulation flags above, the skb->encapsulation
+ *		flag is automatically cleared if all tunnel-specific GSO flags
+ *		(SKB_GSO_UDP_TUNNEL, SKB_GSO_UDP_TUNNEL_CSUM, SKB_GSO_GRE,
+ *		SKB_GSO_GRE_CSUM, SKB_GSO_IPXIP4, SKB_GSO_IPXIP6) have been
+ *		removed from the packet. This handles cases where all tunnel
+ *		layers have been decapsulated.
  *
  * 		A call to this helper is susceptible to change the underlying
  * 		packet buffer. Therefore, at load time, all checks on pointers
@@ -6221,6 +6247,10 @@ enum bpf_adj_room_flags {
 	BPF_F_ADJ_ROOM_ENCAP_L2_ETH	= (1ULL << 6),
 	BPF_F_ADJ_ROOM_DECAP_L3_IPV4	= (1ULL << 7),
 	BPF_F_ADJ_ROOM_DECAP_L3_IPV6	= (1ULL << 8),
+	BPF_F_ADJ_ROOM_DECAP_L4_GRE	= (1ULL << 9),
+	BPF_F_ADJ_ROOM_DECAP_L4_UDP	= (1ULL << 10),
+	BPF_F_ADJ_ROOM_DECAP_IPXIP4	= (1ULL << 11),
+	BPF_F_ADJ_ROOM_DECAP_IPXIP6	= (1ULL << 12),
 };
 
 enum {
-- 
2.34.1

Re: [PATCH v5 3/6] bpf: add BPF_F_ADJ_ROOM_DECAP_* flags for tunnel decapsulation

[Willem de Bruijn]

Nick Hudson wrote:
> Add new bpf_skb_adjust_room() decapsulation flags:
> 
> - BPF_F_ADJ_ROOM_DECAP_L4_GRE
> - BPF_F_ADJ_ROOM_DECAP_L4_UDP
> - BPF_F_ADJ_ROOM_DECAP_IPXIP4
> - BPF_F_ADJ_ROOM_DECAP_IPXIP6
> 
> These flags let BPF programs describe which tunnel layer is being
> removed, so later changes can update tunnel-related GSO state
> accordingly during decapsulation.
> 
> This patch only introduces the UAPI flag definitions and helper
> documentation.
> 
> Co-developed-by: Max Tottenham <mtottenh@akamai.com>
> Signed-off-by: Max Tottenham <mtottenh@akamai.com>
> Co-developed-by: Anna Glasgall <aglasgal@akamai.com>
> Signed-off-by: Anna Glasgall <aglasgal@akamai.com>
> Signed-off-by: Nick Hudson <nhudson@akamai.com>

Reviewed-by: Willem de Bruijn <willemb@google.com>

[PATCH v5 4/6] bpf: allow new DECAP flags and add guard rails

[Nick Hudson]

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@akamai.com>
Signed-off-by: Max Tottenham <mtottenh@akamai.com>
Co-developed-by: Anna Glasgall <aglasgal@akamai.com>
Signed-off-by: Anna Glasgall <aglasgal@akamai.com>
Signed-off-by: Nick Hudson <nhudson@akamai.com>
---
 net/core/filter.c | 44 +++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 43 insertions(+), 1 deletion(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index 4e860da4381d..7f8d43420afb 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>
@@ -3490,6 +3491,12 @@ static u32 bpf_skb_net_base_len(const struct sk_buff *skb)
 #define BPF_F_ADJ_ROOM_DECAP_L3_MASK	(BPF_F_ADJ_ROOM_DECAP_L3_IPV4 | \
 					 BPF_F_ADJ_ROOM_DECAP_L3_IPV6)
 
+#define BPF_F_ADJ_ROOM_DECAP_L4_MASK	(BPF_F_ADJ_ROOM_DECAP_L4_UDP | \
+					 BPF_F_ADJ_ROOM_DECAP_L4_GRE)
+
+#define BPF_F_ADJ_ROOM_DECAP_IPXIP_MASK	(BPF_F_ADJ_ROOM_DECAP_IPXIP4 | \
+					 BPF_F_ADJ_ROOM_DECAP_IPXIP6)
+
 #define BPF_F_ADJ_ROOM_ENCAP_MASK	(BPF_F_ADJ_ROOM_ENCAP_L3_MASK | \
 					 BPF_F_ADJ_ROOM_ENCAP_L4_GRE | \
 					 BPF_F_ADJ_ROOM_ENCAP_L4_UDP | \
@@ -3497,7 +3504,9 @@ 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 | \
@@ -3740,6 +3749,8 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
 	}
 
 	if (flags & BPF_F_ADJ_ROOM_DECAP_MASK) {
+		u32 len_decap_min = 0;
+
 		if (!shrink)
 			return -EINVAL;
 
@@ -3748,6 +3759,37 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
 		    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_MASK)
+			len_decap_min += bpf_skb_net_base_len(skb);
+
+		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 (flags & BPF_F_ADJ_ROOM_DECAP_IPXIP4)
+			len_decap_min += sizeof(struct iphdr);
+
+		if (flags & BPF_F_ADJ_ROOM_DECAP_IPXIP6)
+			len_decap_min += sizeof(struct ipv6hdr);
+
+		if (len_diff_abs < len_decap_min)
+			return -EINVAL;
+
 		if (flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV4)
 			len_min = sizeof(struct iphdr);
 
-- 
2.34.1

Re: [PATCH v5 4/6] bpf: allow new DECAP flags and add guard rails

[Willem de Bruijn]

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@akamai.com>
> Signed-off-by: Max Tottenham <mtottenh@akamai.com>
> Co-developed-by: Anna Glasgall <aglasgal@akamai.com>
> Signed-off-by: Anna Glasgall <aglasgal@akamai.com>
> Signed-off-by: Nick Hudson <nhudson@akamai.com>

Reviewed-by: Willem de Bruijn <willemb@google.com>

[PATCH v5 5/6] bpf: clear decap tunnel GSO state in skb_adjust_room

[Nick Hudson]

On shrink in bpf_skb_adjust_room(), clear tunnel-specific GSO flags
according to the decapsulation flags:

- BPF_F_ADJ_ROOM_DECAP_L4_UDP clears SKB_GSO_UDP_TUNNEL{,_CSUM}
- BPF_F_ADJ_ROOM_DECAP_L4_GRE clears SKB_GSO_GRE{,_CSUM}
- BPF_F_ADJ_ROOM_DECAP_IPXIP4 clears SKB_GSO_IPXIP4
- BPF_F_ADJ_ROOM_DECAP_IPXIP6 clears SKB_GSO_IPXIP6

When all tunnel-related GSO bits are cleared, also clear
skb->encapsulation.

Handle the ESP inside a UDP tunnel case where encapsulation should remain
set.

Co-developed-by: Max Tottenham <mtottenh@akamai.com>
Signed-off-by: Max Tottenham <mtottenh@akamai.com>
Co-developed-by: Anna Glasgall <aglasgal@akamai.com>
Signed-off-by: Anna Glasgall <aglasgal@akamai.com>
Signed-off-by: Nick Hudson <nhudson@akamai.com>
---
 net/core/filter.c | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index 7f8d43420afb..1cc89b9c8cac 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3667,6 +3667,39 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff,
 		if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO))
 			skb_increase_gso_size(shinfo, len_diff);
 
+		/* Selective GSO flag clearing based on decap type.
+		 * Only clear the flags for the tunnel layer being removed.
+		 */
+		if ((flags & BPF_F_ADJ_ROOM_DECAP_L4_UDP) &&
+		    (shinfo->gso_type & (SKB_GSO_UDP_TUNNEL |
+					 SKB_GSO_UDP_TUNNEL_CSUM)))
+			shinfo->gso_type &= ~(SKB_GSO_UDP_TUNNEL |
+					      SKB_GSO_UDP_TUNNEL_CSUM);
+		if ((flags & BPF_F_ADJ_ROOM_DECAP_L4_GRE) &&
+		    (shinfo->gso_type & (SKB_GSO_GRE | SKB_GSO_GRE_CSUM)))
+			shinfo->gso_type &= ~(SKB_GSO_GRE |
+					      SKB_GSO_GRE_CSUM);
+		if ((flags & BPF_F_ADJ_ROOM_DECAP_IPXIP4) &&
+		    (shinfo->gso_type & SKB_GSO_IPXIP4))
+			shinfo->gso_type &= ~SKB_GSO_IPXIP4;
+		if ((flags & BPF_F_ADJ_ROOM_DECAP_IPXIP6) &&
+		    (shinfo->gso_type & SKB_GSO_IPXIP6))
+			shinfo->gso_type &= ~SKB_GSO_IPXIP6;
+
+		/* Clear encapsulation flag only when no tunnel GSO flags remain */
+		if (flags & (BPF_F_ADJ_ROOM_DECAP_L4_MASK |
+			     BPF_F_ADJ_ROOM_DECAP_IPXIP_MASK)) {
+			if (!(shinfo->gso_type & (SKB_GSO_UDP_TUNNEL |
+						  SKB_GSO_UDP_TUNNEL_CSUM |
+						  SKB_GSO_GRE |
+						  SKB_GSO_GRE_CSUM |
+						  SKB_GSO_IPXIP4 |
+						  SKB_GSO_IPXIP6 |
+						  SKB_GSO_ESP)))
+				if (skb->encapsulation)
+					skb->encapsulation = 0;
+		}
+
 		/* Header must be checked, and gso_segs recomputed. */
 		shinfo->gso_type |= SKB_GSO_DODGY;
 		shinfo->gso_segs = 0;
-- 
2.34.1

Re: [PATCH v5 5/6] bpf: clear decap tunnel GSO state in skb_adjust_room

[bot+bpf-ci]

[-- Attachment #1: Type: text/plain, Size: 2584 bytes --]

> diff --git a/net/core/filter.c b/net/core/filter.c
> --- a/net/core/filter.c
> +++ b/net/core/filter.c
> @@ -3666,6 +3666,39 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff,
>  		if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO))
>  			skb_increase_gso_size(shinfo, len_diff);
>
> +		/* Selective GSO flag clearing based on decap type.
> +		 * Only clear the flags for the tunnel layer being removed.
> +		 */

This isn't a bug, but the opening /* should be on its own line following BPF
subsystem convention for multi-line comments.

> +		if ((flags & BPF_F_ADJ_ROOM_DECAP_L4_UDP) &&
> +		    (shinfo->gso_type & (SKB_GSO_UDP_TUNNEL |
> +					 SKB_GSO_UDP_TUNNEL_CSUM)))
> +			shinfo->gso_type &= ~(SKB_GSO_UDP_TUNNEL |
> +					      SKB_GSO_UDP_TUNNEL_CSUM);
> +		if ((flags & BPF_F_ADJ_ROOM_DECAP_L4_GRE) &&
> +		    (shinfo->gso_type & (SKB_GSO_GRE | SKB_GSO_GRE_CSUM)))
> +			shinfo->gso_type &= ~(SKB_GSO_GRE |
> +					      SKB_GSO_GRE_CSUM);
> +		if ((flags & BPF_F_ADJ_ROOM_DECAP_IPXIP4) &&
> +		    (shinfo->gso_type & SKB_GSO_IPXIP4))
> +			shinfo->gso_type &= ~SKB_GSO_IPXIP4;
> +		if ((flags & BPF_F_ADJ_ROOM_DECAP_IPXIP6) &&
> +		    (shinfo->gso_type & SKB_GSO_IPXIP6))
> +			shinfo->gso_type &= ~SKB_GSO_IPXIP6;
> +
> +		/* Clear encapsulation flag only when no tunnel GSO flags remain */
> +		if (flags & (BPF_F_ADJ_ROOM_DECAP_L4_MASK |
> +			     BPF_F_ADJ_ROOM_DECAP_IPXIP_MASK)) {
> +			if (!(shinfo->gso_type & (SKB_GSO_UDP_TUNNEL |
> +						  SKB_GSO_UDP_TUNNEL_CSUM |
> +						  SKB_GSO_GRE |
> +						  SKB_GSO_GRE_CSUM |
> +						  SKB_GSO_IPXIP4 |
> +						  SKB_GSO_IPXIP6 |
> +						  SKB_GSO_ESP)))
> +				if (skb->encapsulation)
> +					skb->encapsulation = 0;
> +		}

All of this new GSO flag clearing logic is added inside the if (skb_is_gso(skb))
block in bpf_skb_net_shrink(). Does this mean non-GSO packets bypass the
decapsulation state clearing?

BPF programs can call bpf_skb_adjust_room() to decapsulate non-GSO packets
as well. If a non-GSO packet undergoes decapsulation with the tunnel headers
stripped, but skb->encapsulation remains set, could this cause downstream
network stack components to misinterpret the packet as still being
encapsulated?

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


---
AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md

CI run summary: https://github.com/kernel-patches/bpf/actions/runs/24662733093

Re: [PATCH v5 5/6] bpf: clear decap tunnel GSO state in skb_adjust_room

[Willem de Bruijn]

Nick Hudson wrote:
> On shrink in bpf_skb_adjust_room(), clear tunnel-specific GSO flags
> according to the decapsulation flags:
> 
> - BPF_F_ADJ_ROOM_DECAP_L4_UDP clears SKB_GSO_UDP_TUNNEL{,_CSUM}
> - BPF_F_ADJ_ROOM_DECAP_L4_GRE clears SKB_GSO_GRE{,_CSUM}
> - BPF_F_ADJ_ROOM_DECAP_IPXIP4 clears SKB_GSO_IPXIP4
> - BPF_F_ADJ_ROOM_DECAP_IPXIP6 clears SKB_GSO_IPXIP6
> 
> When all tunnel-related GSO bits are cleared, also clear
> skb->encapsulation.
> 
> Handle the ESP inside a UDP tunnel case where encapsulation should remain
> set.
> 
> Co-developed-by: Max Tottenham <mtottenh@akamai.com>
> Signed-off-by: Max Tottenham <mtottenh@akamai.com>
> Co-developed-by: Anna Glasgall <aglasgal@akamai.com>
> Signed-off-by: Anna Glasgall <aglasgal@akamai.com>
> Signed-off-by: Nick Hudson <nhudson@akamai.com>

Reviewed-by: Willem de Bruijn <willemb@google.com>

[PATCH v5 6/6] selftests/bpf: tc_tunnel validate decap GSO state

[Nick Hudson]

Require BPF_F_ADJ_ROOM_DECAP_L4_UDP and BPF_F_ADJ_ROOM_DECAP_L4_GRE enum
values at runtime using CO-RE enum existence checks so missing kernel
support fails fast instead of silently proceeding.

After bpf_skb_adjust_room() decapsulation, inspect skb_shared_info and
sk_buff state for GSO packets and assert that the expected tunnel GSO
bits are cleared and encapsulation matches the remaining tunnel state.

Signed-off-by: Nick Hudson <nhudson@akamai.com>
---
 .../selftests/bpf/progs/test_tc_tunnel.c      | 57 +++++++++++++++++++
 1 file changed, 57 insertions(+)

diff --git a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
index 7376df405a6b..511022630bb1 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
@@ -6,6 +6,7 @@
 
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
+#include <bpf/bpf_core_read.h>
 #include "bpf_tracing_net.h"
 #include "bpf_compiler.h"
 
@@ -37,6 +38,22 @@ struct vxlanhdr___local {
 
 #define	EXTPROTO_VXLAN	0x1
 
+#define SKB_GSO_UDP_TUNNEL_MASK	(SKB_GSO_UDP_TUNNEL |			\
+				 SKB_GSO_UDP_TUNNEL_CSUM)
+
+#define SKB_GSO_TUNNEL_MASK	(SKB_GSO_UDP_TUNNEL_MASK |		\
+				 SKB_GSO_GRE |				\
+				 SKB_GSO_GRE_CSUM |			\
+				 SKB_GSO_IPXIP4 |			\
+				 SKB_GSO_IPXIP6 |			\
+				 SKB_GSO_ESP)
+
+#define BPF_F_ADJ_ROOM_DECAP_L4_MASK	(BPF_F_ADJ_ROOM_DECAP_L4_UDP |	\
+				 BPF_F_ADJ_ROOM_DECAP_L4_GRE)
+
+#define BPF_F_ADJ_ROOM_DECAP_IPXIP_MASK	(BPF_F_ADJ_ROOM_DECAP_IPXIP4 |	\
+					 BPF_F_ADJ_ROOM_DECAP_IPXIP6)
+
 #define	VXLAN_FLAGS     bpf_htonl(1<<27)
 #define	VNI_ID		1
 #define	VXLAN_VNI	bpf_htonl(VNI_ID << 8)
@@ -592,6 +609,8 @@ int __encap_ip6vxlan_eth(struct __sk_buff *skb)
 static int decap_internal(struct __sk_buff *skb, int off, int len, char proto)
 {
 	__u64 flags = BPF_F_ADJ_ROOM_FIXED_GSO;
+	struct sk_buff *kskb;
+	struct skb_shared_info *shinfo;
 	struct ipv6_opt_hdr ip6_opt_hdr;
 	struct gre_hdr greh;
 	struct udphdr udph;
@@ -621,6 +640,11 @@ static int decap_internal(struct __sk_buff *skb, int off, int len, char proto)
 		break;
 	case IPPROTO_GRE:
 		olen += sizeof(struct gre_hdr);
+		if (!bpf_core_enum_value_exists(enum bpf_adj_room_flags,
+						BPF_F_ADJ_ROOM_DECAP_L4_GRE))
+			return TC_ACT_SHOT;
+		flags |= BPF_F_ADJ_ROOM_DECAP_L4_GRE;
+
 		if (bpf_skb_load_bytes(skb, off + len, &greh, sizeof(greh)) < 0)
 			return TC_ACT_OK;
 		switch (bpf_ntohs(greh.protocol)) {
@@ -634,6 +658,10 @@ static int decap_internal(struct __sk_buff *skb, int off, int len, char proto)
 		break;
 	case IPPROTO_UDP:
 		olen += sizeof(struct udphdr);
+		if (!bpf_core_enum_value_exists(enum bpf_adj_room_flags,
+						BPF_F_ADJ_ROOM_DECAP_L4_UDP))
+			return TC_ACT_SHOT;
+		flags |= BPF_F_ADJ_ROOM_DECAP_L4_UDP;
 		if (bpf_skb_load_bytes(skb, off + len, &udph, sizeof(udph)) < 0)
 			return TC_ACT_OK;
 		switch (bpf_ntohs(udph.dest)) {
@@ -655,6 +683,35 @@ static int decap_internal(struct __sk_buff *skb, int off, int len, char proto)
 	if (bpf_skb_adjust_room(skb, -olen, BPF_ADJ_ROOM_MAC, flags))
 		return TC_ACT_SHOT;
 
+	kskb = bpf_cast_to_kern_ctx(skb);
+	shinfo = bpf_core_cast(kskb->head + kskb->end, struct skb_shared_info);
+	if (!shinfo->gso_size)
+		return TC_ACT_OK;
+
+	if ((flags & BPF_F_ADJ_ROOM_DECAP_L4_UDP) &&
+	    (shinfo->gso_type & SKB_GSO_UDP_TUNNEL_MASK))
+		return TC_ACT_SHOT;
+
+	if ((flags & BPF_F_ADJ_ROOM_DECAP_L4_GRE) &&
+	    (shinfo->gso_type & (SKB_GSO_GRE | SKB_GSO_GRE_CSUM)))
+		return TC_ACT_SHOT;
+
+	if ((flags & BPF_F_ADJ_ROOM_DECAP_IPXIP4) &&
+	    (shinfo->gso_type & SKB_GSO_IPXIP4))
+		return TC_ACT_SHOT;
+
+	if ((flags & BPF_F_ADJ_ROOM_DECAP_IPXIP6) &&
+	    (shinfo->gso_type & SKB_GSO_IPXIP6))
+		return TC_ACT_SHOT;
+
+	if (flags & (BPF_F_ADJ_ROOM_DECAP_L4_MASK |
+		     BPF_F_ADJ_ROOM_DECAP_IPXIP_MASK)) {
+		if ((shinfo->gso_type & SKB_GSO_TUNNEL_MASK) && !kskb->encapsulation)
+			return TC_ACT_SHOT;
+		if (!(shinfo->gso_type & SKB_GSO_TUNNEL_MASK) && kskb->encapsulation)
+			return TC_ACT_SHOT;
+	}
+
 	return TC_ACT_OK;
 }
 
-- 
2.34.1

Re: [PATCH v5 6/6] selftests/bpf: tc_tunnel validate decap GSO state

[bot+bpf-ci]

[-- Attachment #1: Type: text/plain, Size: 3501 bytes --]

> diff --git a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
> index 7376df405a6b..511022630bb1 100644
> --- a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
> +++ b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c

[ ... ]

> @@ -621,6 +640,11 @@ static int decap_internal(struct __sk_buff *skb, int off, int len, char proto)
>  		break;
>  	case IPPROTO_GRE:
>  		olen += sizeof(struct gre_hdr);
> +		if (!bpf_core_enum_value_exists(enum bpf_adj_room_flags,
> +						BPF_F_ADJ_ROOM_DECAP_L4_GRE))
> +			return TC_ACT_SHOT;
> +		flags |= BPF_F_ADJ_ROOM_DECAP_L4_GRE;
> +

[ ... ]

> @@ -634,6 +658,10 @@ static int decap_internal(struct __sk_buff *skb, int off, int len, char proto)
>  		break;
>  	case IPPROTO_UDP:
>  		olen += sizeof(struct udphdr);
> +		if (!bpf_core_enum_value_exists(enum bpf_adj_room_flags,
> +						BPF_F_ADJ_ROOM_DECAP_L4_UDP))
> +			return TC_ACT_SHOT;
> +		flags |= BPF_F_ADJ_ROOM_DECAP_L4_UDP;

[ ... ]

> @@ -655,6 +683,35 @@ static int decap_internal(struct __sk_buff *skb, int off, int len, char proto)
>  	if (bpf_skb_adjust_room(skb, -olen, BPF_ADJ_ROOM_MAC, flags))
>  		return TC_ACT_SHOT;
>
> +	kskb = bpf_cast_to_kern_ctx(skb);
> +	shinfo = bpf_core_cast(kskb->head + kskb->end, struct skb_shared_info);

Could the pointer arithmetic here cause compilation issues on 32-bit
architectures?

On 32-bit architectures without NET_SKBUFF_DATA_USES_OFFSET, sk_buff::end
is defined as a pointer (unsigned char *) rather than an offset. Adding
two pointers is invalid in C and would fail to compile.

Martin KaFai Lau noted that other tests use this pattern and suggested it
could be addressed with bpf_core_field_size(kskb->end) if 32-bit support
becomes necessary in the future.

Ref: https://lore.kernel.org/bpf/20260416124324.B0CE6C2BCAF@smtp.kernel.org/

> +	if (!shinfo->gso_size)
> +		return TC_ACT_OK;
> +
> +	if ((flags & BPF_F_ADJ_ROOM_DECAP_L4_UDP) &&
> +	    (shinfo->gso_type & SKB_GSO_UDP_TUNNEL_MASK))
> +		return TC_ACT_SHOT;
> +
> +	if ((flags & BPF_F_ADJ_ROOM_DECAP_L4_GRE) &&
> +	    (shinfo->gso_type & (SKB_GSO_GRE | SKB_GSO_GRE_CSUM)))
> +		return TC_ACT_SHOT;
> +
> +	if ((flags & BPF_F_ADJ_ROOM_DECAP_IPXIP4) &&
> +	    (shinfo->gso_type & SKB_GSO_IPXIP4))
> +		return TC_ACT_SHOT;
> +
> +	if ((flags & BPF_F_ADJ_ROOM_DECAP_IPXIP6) &&
> +	    (shinfo->gso_type & SKB_GSO_IPXIP6))
> +		return TC_ACT_SHOT;

Are these IPXIP4 and IPXIP6 checks reachable?

Looking earlier in decap_internal(), for IPPROTO_IPIP and IPPROTO_IPV6
cases, the function only sets BPF_F_ADJ_ROOM_DECAP_L3_IPV4 and
BPF_F_ADJ_ROOM_DECAP_L3_IPV6 on the flags variable (around the protocol
switch statement).

Because BPF_F_ADJ_ROOM_DECAP_IPXIP4 and BPF_F_ADJ_ROOM_DECAP_IPXIP6 are
never added to flags, wouldn't these validation checks always be skipped?

Ref: https://lore.kernel.org/bpf/20260416124324.B0CE6C2BCAF@smtp.kernel.org/

> +
> +	if (flags & (BPF_F_ADJ_ROOM_DECAP_L4_MASK |
> +		     BPF_F_ADJ_ROOM_DECAP_IPXIP_MASK)) {
> +		if ((shinfo->gso_type & SKB_GSO_TUNNEL_MASK) && !kskb->encapsulation)
> +			return TC_ACT_SHOT;
> +		if (!(shinfo->gso_type & SKB_GSO_TUNNEL_MASK) && kskb->encapsulation)
> +			return TC_ACT_SHOT;
> +	}
> +
>  	return TC_ACT_OK;
>  }


---
AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md

CI run summary: https://github.com/kernel-patches/bpf/actions/runs/24662733093