Skip to content

net: ip: add skb drop reasons to ip ingress

[email protected] lkml netdev 1 version Applied

Status from this message: This series was applied to netdev/net-next.git (master)

Get series with b4
b4 am [email protected]

Versions newest first

  1. v1 Latest9 patches 2 repliesApplied 9/9

Patches in v1 All 9 applied

#Subject and filesSizeRepliesApplied
1/9skb: add some helpers for skb drop reasonsinclude/linux/skbuff.h+12 -00 repliesApplied
2/9net: ipv4: add skb drop reasons to ip_error()include/linux/skbuff.h include/trace/events/skb.h net/ipv4/route.c+13 -10 repliesApplied
3/9net: ipv6: add skb drop reasons to ip6_pkt_drop()net/ipv6/route.c+5 -10 repliesApplied
4/9net: ip: add skb drop reasons to ip forwardinginclude/linux/skbuff.h include/trace/events/skb.h net/ipv4/ip_forward.c +1 more+20 -60 repliesApplied
5/9net: icmp: introduce function icmpv6_param_prob_reason()include/linux/icmpv6.h net/ipv6/icmp.c+13 -50 repliesApplied
6/9net: ipv6: remove redundant statistics in ipv6_hop_jumbo()net/ipv6/exthdrs.c+1 -80 repliesApplied
7/9net: ipv6: add skb drop reasons to TLV parsenet/ipv6/exthdrs.c+24 -120 repliesApplied
8/9net: ipv6: add skb drop reasons to ip6_rcv_core()net/ipv6/ip6_input.c+16 -82 repliesApplied
9/9net: ipv6: add skb drop reasons to ip6_protocol_deliver_rcu()net/ipv6/ip6_input.c+12 -40 repliesApplied

Reviews trailers per patch

All 9 patches have a Reviewed-by or Acked-by.

PatchJiang BiaoHao Peng
1/9R-b R-b
2/9R-b R-b
3/9R-b R-b
4/9R-b R-b
5/9R-b R-b
6/9R-b R-b
7/9R-b R-b
8/9R-b R-b
9/9R-b R-b

Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes.

Read the v1 thread

Cover letter [PATCH net-next 0/9] net: ip: add skb drop reasons to ip ingress

From: Menglong Dong <[email protected]>

In the series "net: use kfree_skb_reason() for ip/udp packet receive", skb drop reasons are added to the basic ingress path of IPv4. And in the series "net: use kfree_skb_reason() for ip/neighbour", the egress paths of IPv4 and IPv6 are handled. Related links:

https://lore.kernel.org/netdev/[email protected]/
https://lore.kernel.org/netdev/[email protected]/

Seems we still have a lot work to do with IP layer, including IPv6 basic ingress path, IPv4/IPv6 forwarding, IPv6 exthdrs, fragment and defrag, etc.

In this series, skb drop reasons are added to the basic ingress path of IPv6 protocol and IPv4/IPv6 packet forwarding. Following functions, which are used for IPv6 packet receiving are handled:

ip6_pkt_drop()
ip6_rcv_core()
ip6_protocol_deliver_rcu()

And following functions that used for IPv6 TLV parse are handled:

ip6_parse_tlv()
ipv6_hop_ra()
ipv6_hop_ioam()
ipv6_hop_jumbo()
ipv6_hop_calipso()
ipv6_dest_hao()

Besides, ip_forward() and ip6_forward(), which are used for IPv4/IPv6 forwarding, are also handled. And following new drop reasons are added:

/* host unreachable, corresponding to IPSTATS_MIB_INADDRERRORS */ SKB_DROP_REASON_IP_INADDRERRORS
/* network unreachable, corresponding to IPSTATS_MIB_INADDRERRORS */ SKB_DROP_REASON_IP_INNOROUTES
/* packet size is too big, corresponding to
* IPSTATS_MIB_INTOOBIGERRORS
*/
SKB_DROP_REASON_PKT_TOO_BIG

In order to simply the definition and assignment for
'enum skb_drop_reason', some helper functions are introduced in the 1th patch. I'm not such if this is necessary, but it makes the code simpler. For example, we can replace the code:

  if (reason == SKB_DROP_REASON_NOT_SPECIFIED)
          reason = SKB_DROP_REASON_IP_INHDR;

with:

  SKB_DR_OR(reason, IP_INHDR);

In the 6th patch, the statistics for skb in ipv6_hop_jum() is removed, as I think it is redundant. 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.

======================================================================

Here is a basic test for IPv6 forwarding packet drop that monitored by 'dropwatch' tool:

drop at: ip6_forward+0x81a/0xb70 (0xffffffff86c73f8a)
origin: software
input port ifindex: 7
timestamp: Wed Apr 13 11:51:06 2022 130010176 nsec
protocol: 0x86dd
length: 94
original length: 94
drop reason: IP_INADDRERRORS

The origin cause of this case is that IPv6 doesn't allow to forward the packet with LOCAL-LINK saddr, and results the 'IP_INADDRERRORS' drop reason.

Menglong Dong (9):
skb: add some helpers for skb drop reasons
net: ipv4: add skb drop reasons to ip_error()
net: ipv6: add skb drop reasons to ip6_pkt_drop()
net: ip: add skb drop reasons to ip forwarding
net: icmp: introduce function icmpv6_param_prob_reason()
net: ipv6: remove redundant statistics in ipv6_hop_jumbo()
net: ipv6: add skb drop reasons to TLV parse
net: ipv6: add skb drop reasons to ip6_rcv_core()
net: ipv6: add skb drop reasons to ip6_protocol_deliver_rcu()

 include/linux/icmpv6.h     | 11 +++++++++--
 include/linux/skbuff.h     | 21 ++++++++++++++++++++
 include/trace/events/skb.h |  3 +++
 net/ipv4/ip_forward.c      | 13 ++++++++++---
 net/ipv4/route.c           |  6 +++++-
 net/ipv6/exthdrs.c         | 39 +++++++++++++++++++++----------------
 net/ipv6/icmp.c            |  7 ++++---
 net/ipv6/ip6_input.c       | 40 ++++++++++++++++++++++++++------------
 net/ipv6/ip6_output.c      |  9 ++++++---
 net/ipv6/route.c           |  6 +++++-
 10 files changed, 113 insertions(+), 42 deletions(-)
Signature · 1 line
2.35.1