Commit f8ffad69 authored by Daniel Borkmann's avatar Daniel Borkmann Committed by David S. Miller

bpf: add skb_postpush_rcsum and fix dev_forward_skb occasions

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 2c26d34b
("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.

Thanks to Hannes Frederic Sowa for the csum_partial() idea!

Fixes: 3896d655 ("bpf: introduce bpf_clone_redirect() helper")
Fixes: 27b29f63 ("bpf: add bpf_redirect() helper")
Signed-off-by: default avatarDaniel Borkmann <daniel@iogearbox.net>
Acked-by: default avatarAlexei Starovoitov <ast@kernel.org>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent fdc5432a
...@@ -2805,6 +2805,23 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb, ...@@ -2805,6 +2805,23 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb,
unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); 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)
{
/* For performing the reverse operation to skb_postpull_rcsum(),
* we can instead of ...
*
* skb->csum = csum_add(skb->csum, csum_partial(start, len, 0));
*
* ... just use this equivalent version here to save a few
* instructions. Feeding csum of 0 in csum_partial() and later
* on adding skb->csum is equivalent to feed skb->csum in the
* first place.
*/
if (skb->ip_summed == CHECKSUM_COMPLETE)
skb->csum = csum_partial(start, len, skb->csum);
}
/** /**
* pskb_trim_rcsum - trim received skb and update checksum * pskb_trim_rcsum - trim received skb and update checksum
* @skb: buffer to trim * @skb: buffer to trim
......
...@@ -1368,8 +1368,9 @@ static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags) ...@@ -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 cannot return -EFAULT here */
skb_store_bits(skb, offset, ptr, len); skb_store_bits(skb, offset, ptr, len);
if (BPF_RECOMPUTE_CSUM(flags) && skb->ip_summed == CHECKSUM_COMPLETE) if (BPF_RECOMPUTE_CSUM(flags))
skb->csum = csum_add(skb->csum, csum_partial(ptr, len, 0)); skb_postpush_rcsum(skb, ptr, len);
return 0; return 0;
} }
...@@ -1525,8 +1526,12 @@ static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5) ...@@ -1525,8 +1526,12 @@ static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5)
if (unlikely(!skb2)) if (unlikely(!skb2))
return -ENOMEM; return -ENOMEM;
if (BPF_IS_REDIRECT_INGRESS(flags)) if (BPF_IS_REDIRECT_INGRESS(flags)) {
if (skb_at_tc_ingress(skb2))
skb_postpush_rcsum(skb2, skb_mac_header(skb2),
skb2->mac_len);
return dev_forward_skb(dev, skb2); return dev_forward_skb(dev, skb2);
}
skb2->dev = dev; skb2->dev = dev;
skb_sender_cpu_clear(skb2); skb_sender_cpu_clear(skb2);
...@@ -1569,8 +1574,12 @@ int skb_do_redirect(struct sk_buff *skb) ...@@ -1569,8 +1574,12 @@ int skb_do_redirect(struct sk_buff *skb)
return -EINVAL; return -EINVAL;
} }
if (BPF_IS_REDIRECT_INGRESS(ri->flags)) if (BPF_IS_REDIRECT_INGRESS(ri->flags)) {
if (skb_at_tc_ingress(skb))
skb_postpush_rcsum(skb, skb_mac_header(skb),
skb->mac_len);
return dev_forward_skb(dev, skb); return dev_forward_skb(dev, skb);
}
skb->dev = dev; skb->dev = dev;
skb_sender_cpu_clear(skb); skb_sender_cpu_clear(skb);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment