bpf: Add csum_level helper for fixing up csum levels

Add a bpf_csum_level() helper which BPF programs can use in combination
with bpf_skb_adjust_room() when they pass in BPF_F_ADJ_ROOM_NO_CSUM_RESET
flag to the latter to avoid falling back to CHECKSUM_NONE.

The bpf_csum_level() allows to adjust CHECKSUM_UNNECESSARY skb->csum_levels
via BPF_CSUM_LEVEL_{INC,DEC} which calls __skb_{incr,decr}_checksum_unnecessary()
on the skb. The helper also allows a BPF_CSUM_LEVEL_RESET which sets the skb's
csum to CHECKSUM_NONE as well as a BPF_CSUM_LEVEL_QUERY to just return the
current level. Without this helper, there is no way to otherwise adjust the
skb->csum_level. I did not add an extra dummy flags as there is plenty of free
bitspace in level argument itself iff ever needed in future.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Alan Maguire <alan.maguire@oracle.com>
Acked-by: Lorenz Bauer <lmb@cloudflare.com>
Link: https://lore.kernel.org/bpf/279ae3717cb3d03c0ffeb511493c93c450a01e1a.1591108731.git.daniel@iogearbox.net

1 files changed, 42 insertions, 1 deletions

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 3ba2bbbed80c..c65b374a5090 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3220,6 +3220,38 @@ union bpf_attr {
  *		calculation.
  *	Return
  *		Requested value, or 0, if flags are not recognized.
+ *
+ * int bpf_csum_level(struct sk_buff *skb, u64 level)
+ * 	Description
+ * 		Change the skbs checksum level by one layer up or down, or
+ * 		reset it entirely to none in order to have the stack perform
+ * 		checksum validation. The level is applicable to the following
+ * 		protocols: TCP, UDP, GRE, SCTP, FCOE. For example, a decap of
+ * 		| ETH | IP | UDP | GUE | IP | TCP | into | ETH | IP | TCP |
+ * 		through **bpf_skb_adjust_room**\ () helper with passing in
+ * 		**BPF_F_ADJ_ROOM_NO_CSUM_RESET** flag would require one	call
+ * 		to **bpf_csum_level**\ () with **BPF_CSUM_LEVEL_DEC** since
+ * 		the UDP header is removed. Similarly, an encap of the latter
+ * 		into the former could be accompanied by a helper call to
+ * 		**bpf_csum_level**\ () with **BPF_CSUM_LEVEL_INC** if the
+ * 		skb is still intended to be processed in higher layers of the
+ * 		stack instead of just egressing at tc.
+ *
+ * 		There are three supported level settings at this time:
+ *
+ * 		* **BPF_CSUM_LEVEL_INC**: Increases skb->csum_level for skbs
+ * 		  with CHECKSUM_UNNECESSARY.
+ * 		* **BPF_CSUM_LEVEL_DEC**: Decreases skb->csum_level for skbs
+ * 		  with CHECKSUM_UNNECESSARY.
+ * 		* **BPF_CSUM_LEVEL_RESET**: Resets skb->csum_level to 0 and
+ * 		  sets CHECKSUM_NONE to force checksum validation by the stack.
+ * 		* **BPF_CSUM_LEVEL_QUERY**: No-op, returns the current
+ * 		  skb->csum_level.
+ * 	Return
+ * 		0 on success, or a negative error in case of failure. In the
+ * 		case of **BPF_CSUM_LEVEL_QUERY**, the current skb->csum_level
+ * 		is returned or the error code -EACCES in case the skb is not
+ * 		subject to CHECKSUM_UNNECESSARY.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3356,7 +3388,8 @@ union bpf_attr {
 	FN(ringbuf_reserve),		\
 	FN(ringbuf_submit),		\
 	FN(ringbuf_discard),		\
-	FN(ringbuf_query),
+	FN(ringbuf_query),		\
+	FN(csum_level),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -3433,6 +3466,14 @@ enum {
 	BPF_F_CURRENT_NETNS		= (-1L),
 };
 
+/* BPF_FUNC_csum_level level values. */
+enum {
+	BPF_CSUM_LEVEL_QUERY,
+	BPF_CSUM_LEVEL_INC,
+	BPF_CSUM_LEVEL_DEC,
+	BPF_CSUM_LEVEL_RESET,
+};
+
 /* BPF_FUNC_skb_adjust_room flags. */
 enum {
 	BPF_F_ADJ_ROOM_FIXED_GSO	= (1ULL << 0),