diff options
author | 2022-04-13 16:15:57 +0800 | |
---|---|---|
committer | 2022-04-13 13:09:57 +0100 | |
commit | bba98083499f63f62419edf42022275d34a72470 (patch) | |
tree | 45e313b2d978ae88060a5170830b5b5470ab6db8 /net/sched/cls_api.c | |
parent | net: icmp: introduce function icmpv6_param_prob_reason() (diff) | |
download | wireguard-linux-bba98083499f63f62419edf42022275d34a72470.tar.xz wireguard-linux-bba98083499f63f62419edf42022275d34a72470.zip |
net: ipv6: remove redundant statistics in ipv6_hop_jumbo()
There are two call chains for ipv6_hop_jumbo(). The first one is:
ipv6_destopt_rcv() -> ip6_parse_tlv() -> ipv6_hop_jumbo()
On this call chain, the drop statistics will be done in
ipv6_destopt_rcv() with 'IPSTATS_MIB_INHDRERRORS' if ipv6_hop_jumbo()
returns false.
The second call chain is:
ip6_rcv_core() -> ipv6_parse_hopopts() -> ip6_parse_tlv()
And the drop statistics will also be done in ip6_rcv_core() with
'IPSTATS_MIB_INHDRERRORS' if ipv6_hop_jumbo() returns false.
Therefore, the statistics in ipv6_hop_jumbo() is redundant, which
means the drop is counted twice. The statistics in ipv6_hop_jumbo()
is almost the same as the outside, except the
'IPSTATS_MIB_INTRUNCATEDPKTS', which seems that we have to ignore it.
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Reviewed-by: Jiang Biao <benbjiang@tencent.com>
Reviewed-by: Hao Peng <flyingpeng@tencent.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/sched/cls_api.c')
0 files changed, 0 insertions, 0 deletions