[PATCH net-next] bpf: add skb_postpush_rcsum and fix dev_forward_skb occasions

[Daniel Borkmann <daniel@iogearbox.net>]

Add a small helper skb_postpush_rcsum() and fix up redirect locations
that need CHECKSUM_COMPLETE fixups on ingress. dev_forward_skb() expects
a proper csum that covers also Ethernet header, f.e. since 2c26d34bbcc0
("net/core: Handle csum for CHECKSUM_COMPLETE VXLAN forwarding"), we
also do skb_postpull_rcsum() after pulling Ethernet header off via
eth_type_trans().

When using eBPF in a netns setup f.e. with vxlan in collect metadata mode,
I can trigger the following csum issue with an IPv6 setup:

  [  505.144065] dummy1: hw csum failure
  [...]
  [  505.144108] Call Trace:
  [  505.144112]  <IRQ>  [<ffffffff81372f08>] dump_stack+0x44/0x5c
  [  505.144134]  [<ffffffff81607cea>] netdev_rx_csum_fault+0x3a/0x40
  [  505.144142]  [<ffffffff815fee3f>] __skb_checksum_complete+0xcf/0xe0
  [  505.144149]  [<ffffffff816f0902>] nf_ip6_checksum+0xb2/0x120
  [  505.144161]  [<ffffffffa08c0e0e>] icmpv6_error+0x17e/0x328 [nf_conntrack_ipv6]
  [  505.144170]  [<ffffffffa0898eca>] ? ip6t_do_table+0x2fa/0x645 [ip6_tables]
  [  505.144177]  [<ffffffffa08c0725>] ? ipv6_get_l4proto+0x65/0xd0 [nf_conntrack_ipv6]
  [  505.144189]  [<ffffffffa06c9a12>] nf_conntrack_in+0xc2/0x5a0 [nf_conntrack]
  [  505.144196]  [<ffffffffa08c039c>] ipv6_conntrack_in+0x1c/0x20 [nf_conntrack_ipv6]
  [  505.144204]  [<ffffffff8164385d>] nf_iterate+0x5d/0x70
  [  505.144210]  [<ffffffff816438d6>] nf_hook_slow+0x66/0xc0
  [  505.144218]  [<ffffffff816bd302>] ipv6_rcv+0x3f2/0x4f0
  [  505.144225]  [<ffffffff816bca40>] ? ip6_make_skb+0x1b0/0x1b0
  [  505.144232]  [<ffffffff8160b77b>] __netif_receive_skb_core+0x36b/0x9a0
  [  505.144239]  [<ffffffff8160bdc8>] ? __netif_receive_skb+0x18/0x60
  [  505.144245]  [<ffffffff8160bdc8>] __netif_receive_skb+0x18/0x60
  [  505.144252]  [<ffffffff8160ccff>] process_backlog+0x9f/0x140
  [  505.144259]  [<ffffffff8160c4a5>] net_rx_action+0x145/0x320
  [...]

What happens is that on ingress, we push Ethernet header back in, either
from cls_bpf or right before skb_do_redirect(), but without updating csum.
The "hw csum failure" can be fixed by using the new skb_postpush_rcsum()
helper for the dev_forward_skb() case to correct the csum diff again.

Fixes: 3896d655f4d4 ("bpf: introduce bpf_clone_redirect() helper")
Fixes: 27b29f63058d ("bpf: add bpf_redirect() helper")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 ( Given -net pull req is already out and nobody seemed to have triggered
   this so far, net-next seems just fine imho. )

 include/linux/skbuff.h |  7 +++++++
 net/core/filter.c      | 17 +++++++++++++----
 2 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6b6bd42..f8fad71 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2805,6 +2805,13 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb,
 
 unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len);
 
+static inline void skb_postpush_rcsum(struct sk_buff *skb,
+				      const void *start, unsigned int len)
+{
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		skb->csum = csum_add(skb->csum, csum_partial(start, len, 0));
+}
+
 /**
  *	pskb_trim_rcsum - trim received skb and update checksum
  *	@skb: buffer to trim
diff --git a/net/core/filter.c b/net/core/filter.c
index 35e6fed..c6160ce 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1368,8 +1368,9 @@ static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags)
 		/* skb_store_bits cannot return -EFAULT here */
 		skb_store_bits(skb, offset, ptr, len);
 
-	if (BPF_RECOMPUTE_CSUM(flags) && skb->ip_summed == CHECKSUM_COMPLETE)
-		skb->csum = csum_add(skb->csum, csum_partial(ptr, len, 0));
+	if (BPF_RECOMPUTE_CSUM(flags))
+		skb_postpush_rcsum(skb, ptr, len);
+
 	return 0;
 }
 
@@ -1525,8 +1526,12 @@ static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5)
 	if (unlikely(!skb2))
 		return -ENOMEM;
 
-	if (BPF_IS_REDIRECT_INGRESS(flags))
+	if (BPF_IS_REDIRECT_INGRESS(flags)) {
+		if (G_TC_AT(skb2->tc_verd) & AT_INGRESS)
+			skb_postpush_rcsum(skb2, skb_mac_header(skb2),
+					   skb2->mac_len);
 		return dev_forward_skb(dev, skb2);
+	}
 
 	skb2->dev = dev;
 	skb_sender_cpu_clear(skb2);
@@ -1569,8 +1574,12 @@ int skb_do_redirect(struct sk_buff *skb)
 		return -EINVAL;
 	}
 
-	if (BPF_IS_REDIRECT_INGRESS(ri->flags))
+	if (BPF_IS_REDIRECT_INGRESS(ri->flags)) {
+		if (G_TC_AT(skb->tc_verd) & AT_INGRESS)
+			skb_postpush_rcsum(skb, skb_mac_header(skb),
+					   skb->mac_len);
 		return dev_forward_skb(dev, skb);
+	}
 
 	skb->dev = dev;
 	skb_sender_cpu_clear(skb);
-- 
1.9.3