Merge branch 'csum-fixes'

Daniel Borkmann says:

====================
This series fixes an issue originally reported by Lorenz Bauer where using
the bpf_skb_adjust_room() helper hid a checksum bug since it wasn't adjusting
CHECKSUM_UNNECESSARY's skb->csum_level after decap. The fix is two-fold:
 i) We do a safe reset in bpf_skb_adjust_room() to CHECKSUM_NONE with an opt-
    out flag BPF_F_ADJ_ROOM_NO_CSUM_RESET.
ii) We add a new bpf_csum_level() for the latter in order to allow users to
    manually inc/dec the skb->csum_level when needed.
The series is rebased against latest bpf-next tree. It can be applied there,
or to bpf after the merge win sync from net-next.

Thanks!
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

5 files changed, 158 insertions, 7 deletions

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index a0d5c2760103..0c0377fc00c2 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3919,6 +3919,14 @@ static inline void __skb_incr_checksum_unnecessary(struct sk_buff *skb)
 	}
 }
 
+static inline void __skb_reset_checksum_unnecessary(struct sk_buff *skb)
+{
+	if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
+		skb->ip_summed = CHECKSUM_NONE;
+		skb->csum_level = 0;
+	}
+}
+
 /* Check if we need to perform checksum complete validation.
  *
  * Returns true if checksum complete is needed, false otherwise
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index b9ed9f14f2a2..c65b374a5090 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1635,6 +1635,13 @@ union bpf_attr {
  * 		Grow or shrink the room for data in the packet associated to
  * 		*skb* by *len_diff*, and according to the selected *mode*.
  *
+ * 		By default, the helper will reset any offloaded checksum
+ * 		indicator of the skb to CHECKSUM_NONE. This can be avoided
+ * 		by the following flag:
+ *
+ * 		* **BPF_F_ADJ_ROOM_NO_CSUM_RESET**: Do not reset offloaded
+ * 		  checksum data of the skb to CHECKSUM_NONE.
+ *
  *		There are two supported modes at this time:
  *
  *		* **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer
@@ -3213,6 +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),			\
@@ -3349,7 +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
@@ -3426,6 +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),
@@ -3433,6 +3481,7 @@ enum {
 	BPF_F_ADJ_ROOM_ENCAP_L3_IPV6	= (1ULL << 2),
 	BPF_F_ADJ_ROOM_ENCAP_L4_GRE	= (1ULL << 3),
 	BPF_F_ADJ_ROOM_ENCAP_L4_UDP	= (1ULL << 4),
+	BPF_F_ADJ_ROOM_NO_CSUM_RESET	= (1ULL << 5),
 };
 
 enum {
diff --git a/net/core/filter.c b/net/core/filter.c
index ae82bcb03124..d01a244b5087 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2015,6 +2015,40 @@ static const struct bpf_func_proto bpf_csum_update_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_2(bpf_csum_level, struct sk_buff *, skb, u64, level)
+{
+	/* The interface is to be used in combination with bpf_skb_adjust_room()
+	 * for encap/decap of packet headers when BPF_F_ADJ_ROOM_NO_CSUM_RESET
+	 * is passed as flags, for example.
+	 */
+	switch (level) {
+	case BPF_CSUM_LEVEL_INC:
+		__skb_incr_checksum_unnecessary(skb);
+		break;
+	case BPF_CSUM_LEVEL_DEC:
+		__skb_decr_checksum_unnecessary(skb);
+		break;
+	case BPF_CSUM_LEVEL_RESET:
+		__skb_reset_checksum_unnecessary(skb);
+		break;
+	case BPF_CSUM_LEVEL_QUERY:
+		return skb->ip_summed == CHECKSUM_UNNECESSARY ?
+		       skb->csum_level : -EACCES;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_csum_level_proto = {
+	.func		= bpf_csum_level,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+};
+
 static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb)
 {
 	return dev_forward_skb(dev, skb);
@@ -3113,7 +3147,8 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff,
 {
 	int ret;
 
-	if (flags & ~BPF_F_ADJ_ROOM_FIXED_GSO)
+	if (unlikely(flags & ~(BPF_F_ADJ_ROOM_FIXED_GSO |
+			       BPF_F_ADJ_ROOM_NO_CSUM_RESET)))
 		return -EINVAL;
 
 	if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) {
@@ -3163,7 +3198,8 @@ 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))
+	if (unlikely(flags & ~(BPF_F_ADJ_ROOM_MASK |
+			       BPF_F_ADJ_ROOM_NO_CSUM_RESET)))
 		return -EINVAL;
 	if (unlikely(len_diff_abs > 0xfffU))
 		return -EFAULT;
@@ -3191,6 +3227,8 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
 
 	ret = shrink ? bpf_skb_net_shrink(skb, off, len_diff_abs, flags) :
 		       bpf_skb_net_grow(skb, off, len_diff_abs, flags);
+	if (!ret && !(flags & BPF_F_ADJ_ROOM_NO_CSUM_RESET))
+		__skb_reset_checksum_unnecessary(skb);
 
 	bpf_compute_data_pointers(skb);
 	return ret;
@@ -6276,6 +6314,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_csum_diff_proto;
 	case BPF_FUNC_csum_update:
 		return &bpf_csum_update_proto;
+	case BPF_FUNC_csum_level:
+		return &bpf_csum_level_proto;
 	case BPF_FUNC_l3_csum_replace:
 		return &bpf_l3_csum_replace_proto;
 	case BPF_FUNC_l4_csum_replace:
@@ -6609,6 +6649,8 @@ lwt_xmit_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_skb_store_bytes_proto;
 	case BPF_FUNC_csum_update:
 		return &bpf_csum_update_proto;
+	case BPF_FUNC_csum_level:
+		return &bpf_csum_level_proto;
 	case BPF_FUNC_l3_csum_replace:
 		return &bpf_l3_csum_replace_proto;
 	case BPF_FUNC_l4_csum_replace:
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index b9ed9f14f2a2..c65b374a5090 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1635,6 +1635,13 @@ union bpf_attr {
  * 		Grow or shrink the room for data in the packet associated to
  * 		*skb* by *len_diff*, and according to the selected *mode*.
  *
+ * 		By default, the helper will reset any offloaded checksum
+ * 		indicator of the skb to CHECKSUM_NONE. This can be avoided
+ * 		by the following flag:
+ *
+ * 		* **BPF_F_ADJ_ROOM_NO_CSUM_RESET**: Do not reset offloaded
+ * 		  checksum data of the skb to CHECKSUM_NONE.
+ *
  *		There are two supported modes at this time:
  *
  *		* **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer
@@ -3213,6 +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),			\
@@ -3349,7 +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
@@ -3426,6 +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),
@@ -3433,6 +3481,7 @@ enum {
 	BPF_F_ADJ_ROOM_ENCAP_L3_IPV6	= (1ULL << 2),
 	BPF_F_ADJ_ROOM_ENCAP_L4_GRE	= (1ULL << 3),
 	BPF_F_ADJ_ROOM_ENCAP_L4_UDP	= (1ULL << 4),
+	BPF_F_ADJ_ROOM_NO_CSUM_RESET	= (1ULL << 5),
 };
 
 enum {
diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.c b/tools/testing/selftests/bpf/progs/test_cls_redirect.c
index 1668b993eb86..f0b72e86bee5 100644
--- a/tools/testing/selftests/bpf/progs/test_cls_redirect.c
+++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.c
@@ -380,9 +380,10 @@ static ret_t accept_locally(struct __sk_buff *skb, encap_headers_t *encap)
 	}
 
 	if (bpf_skb_adjust_room(skb, -encap_overhead, BPF_ADJ_ROOM_MAC,
-				BPF_F_ADJ_ROOM_FIXED_GSO)) {
+				BPF_F_ADJ_ROOM_FIXED_GSO |
+				BPF_F_ADJ_ROOM_NO_CSUM_RESET) ||
+	    bpf_csum_level(skb, BPF_CSUM_LEVEL_DEC))
 		return TC_ACT_SHOT;
-	}
 
 	return bpf_redirect(skb->ifindex, BPF_F_INGRESS);
 }
@@ -472,7 +473,9 @@ static ret_t forward_with_gre(struct __sk_buff *skb, encap_headers_t *encap,
 	}
 
 	if (bpf_skb_adjust_room(skb, delta, BPF_ADJ_ROOM_NET,
-				BPF_F_ADJ_ROOM_FIXED_GSO)) {
+				BPF_F_ADJ_ROOM_FIXED_GSO |
+				BPF_F_ADJ_ROOM_NO_CSUM_RESET) ||
+	    bpf_csum_level(skb, BPF_CSUM_LEVEL_INC)) {
 		metrics->errors_total_encap_adjust_failed++;
 		return TC_ACT_SHOT;
 	}