netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: menglong8.dong@gmail.com
To: dsahern@kernel.org
Cc: rostedt@goodmis.org, mingo@redhat.com, davem@davemloft.net,
	yoshfuji@linux-ipv6.org, kuba@kernel.org, pabeni@redhat.com,
	benbjiang@tencent.com, flyingpeng@tencent.com,
	imagedong@tencent.com, edumazet@google.com, kafai@fb.com,
	talalahmad@google.com, keescook@chromium.org,
	mengensun@tencent.com, dongli.zhang@oracle.com,
	linux-kernel@vger.kernel.org, netdev@vger.kernel.org
Subject: [PATCH net-next 0/9] net: ip: add skb drop reasons to ip ingress
Date: Wed, 13 Apr 2022 16:15:51 +0800	[thread overview]
Message-ID: <20220413081600.187339-1-imagedong@tencent.com> (raw)

From: Menglong Dong <imagedong@tencent.com>

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/20220205074739.543606-1-imagedong@tencent.com/
https://lore.kernel.org/netdev/20220226041831.2058437-1-imagedong@tencent.com/

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(-)

-- 
2.35.1


             reply	other threads:[~2022-04-13  8:43 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-04-13  8:15 menglong8.dong [this message]
2022-04-13  8:15 ` [PATCH net-next 1/9] skb: add some helpers for skb drop reasons menglong8.dong
2022-04-13  8:15 ` [PATCH net-next 2/9] net: ipv4: add skb drop reasons to ip_error() menglong8.dong
2022-04-13  8:15 ` [PATCH net-next 3/9] net: ipv6: add skb drop reasons to ip6_pkt_drop() menglong8.dong
2022-04-13  8:15 ` [PATCH net-next 4/9] net: ip: add skb drop reasons to ip forwarding menglong8.dong
2022-04-13  8:15 ` [PATCH net-next 5/9] net: icmp: introduce function icmpv6_param_prob_reason() menglong8.dong
2022-04-13  8:15 ` [PATCH net-next 6/9] net: ipv6: remove redundant statistics in ipv6_hop_jumbo() menglong8.dong
2022-04-13  8:15 ` [PATCH net-next 7/9] net: ipv6: add skb drop reasons to TLV parse menglong8.dong
2022-04-13  8:15 ` [PATCH net-next 8/9] net: ipv6: add skb drop reasons to ip6_rcv_core() menglong8.dong
2022-04-13 20:40   ` Eric Dumazet
2022-04-14  1:20     ` Menglong Dong
2022-04-13  8:16 ` [PATCH net-next 9/9] net: ipv6: add skb drop reasons to ip6_protocol_deliver_rcu() menglong8.dong
2022-04-13 13:30 ` [PATCH net-next 0/9] net: ip: add skb drop reasons to ip ingress patchwork-bot+netdevbpf

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220413081600.187339-1-imagedong@tencent.com \
    --to=menglong8.dong@gmail.com \
    --cc=benbjiang@tencent.com \
    --cc=davem@davemloft.net \
    --cc=dongli.zhang@oracle.com \
    --cc=dsahern@kernel.org \
    --cc=edumazet@google.com \
    --cc=flyingpeng@tencent.com \
    --cc=imagedong@tencent.com \
    --cc=kafai@fb.com \
    --cc=keescook@chromium.org \
    --cc=kuba@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mengensun@tencent.com \
    --cc=mingo@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=rostedt@goodmis.org \
    --cc=talalahmad@google.com \
    --cc=yoshfuji@linux-ipv6.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).