| Message ID | 20181020000713.228659-1-dmichail@google.com |
|---|---|
| State | Accepted, archived |
| Delegated to: | David Miller |
| Headers | show |
| Series | [net] net: fix pskb_trim_rcsum_slow() with odd trim offset | expand |
On 10/19/2018 05:07 PM, Dimitris Michailidis wrote: > We've been getting checksum errors involving small UDP packets, usually > 59B packets with 1 extra non-zero padding byte. netdev_rx_csum_fault() > has been complaining that HW is providing bad checksums. Turns out the > problem is in pskb_trim_rcsum_slow(), introduced in commit 88078d98d1bb > ("net: pskb_trim_rcsum() and CHECKSUM_COMPLETE are friends"). > > The source of the problem is that when the bytes we are trimming start > at an odd address, as in the case of the 1 padding byte above, > skb_checksum() returns a byte-swapped value. We cannot just combine this > with skb->csum using csum_sub(). We need to use csum_block_sub() here > that takes into account the parity of the start address and handles the > swapping. > > Matches existing code in __skb_postpull_rcsum() and esp_remove_trailer(). > > Fixes: 88078d98d1bb ("net: pskb_trim_rcsum() and CHECKSUM_COMPLETE are friends") > Signed-off-by: Dimitris Michailidis <dmichail@google.com> Thanks a lot Dimitris for finding this. Reviewed-by: Eric Dumazet <edumazet@google.com>
From: Dimitris Michailidis <dmichail@google.com> Date: Fri, 19 Oct 2018 17:07:13 -0700 > We've been getting checksum errors involving small UDP packets, usually > 59B packets with 1 extra non-zero padding byte. netdev_rx_csum_fault() > has been complaining that HW is providing bad checksums. Turns out the > problem is in pskb_trim_rcsum_slow(), introduced in commit 88078d98d1bb > ("net: pskb_trim_rcsum() and CHECKSUM_COMPLETE are friends"). > > The source of the problem is that when the bytes we are trimming start > at an odd address, as in the case of the 1 padding byte above, > skb_checksum() returns a byte-swapped value. We cannot just combine this > with skb->csum using csum_sub(). We need to use csum_block_sub() here > that takes into account the parity of the start address and handles the > swapping. > > Matches existing code in __skb_postpull_rcsum() and esp_remove_trailer(). > > Fixes: 88078d98d1bb ("net: pskb_trim_rcsum() and CHECKSUM_COMPLETE are friends") > Signed-off-by: Dimitris Michailidis <dmichail@google.com> Applied and queued up for -stable, thanks!
diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 428094b577fc..f817f336595d 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1846,8 +1846,9 @@ int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len) if (skb->ip_summed == CHECKSUM_COMPLETE) { int delta = skb->len - len; - skb->csum = csum_sub(skb->csum, - skb_checksum(skb, len, delta, 0)); + skb->csum = csum_block_sub(skb->csum, + skb_checksum(skb, len, delta, 0), + len); } return __pskb_trim(skb, len); }
We've been getting checksum errors involving small UDP packets, usually 59B packets with 1 extra non-zero padding byte. netdev_rx_csum_fault() has been complaining that HW is providing bad checksums. Turns out the problem is in pskb_trim_rcsum_slow(), introduced in commit 88078d98d1bb ("net: pskb_trim_rcsum() and CHECKSUM_COMPLETE are friends"). The source of the problem is that when the bytes we are trimming start at an odd address, as in the case of the 1 padding byte above, skb_checksum() returns a byte-swapped value. We cannot just combine this with skb->csum using csum_sub(). We need to use csum_block_sub() here that takes into account the parity of the start address and handles the swapping. Matches existing code in __skb_postpull_rcsum() and esp_remove_trailer(). Fixes: 88078d98d1bb ("net: pskb_trim_rcsum() and CHECKSUM_COMPLETE are friends") Signed-off-by: Dimitris Michailidis <dmichail@google.com> --- net/core/skbuff.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)