From: Stefano Brivio <sbrivio@redhat.com>
To: David Gibson <david@gibson.dropbear.id.au>
Cc: passt-dev@passt.top
Subject: Re: [PATCH v2 00/14] Clean up checksum and header generation for inbound packets
Date: Sat, 22 Oct 2022 10:21:28 +0200 [thread overview]
Message-ID: <20221022102128.32277eb5@elisabeth> (raw)
In-Reply-To: <20221019004357.1454325-1-david@gibson.dropbear.id.au>
On Wed, 19 Oct 2022 11:43:43 +1100
David Gibson <david@gibson.dropbear.id.au> wrote:
> The main packet "fast paths" for UDP and TCP mostly just forward
> packets rather than generating them from scratch. However the control
> paths for ICMP and DHCP sometimes generate packets more or less from
> scratch. Because these are relatively rare, it's not performance
> critical.
>
> The paths for sending these packets have some duplication of the
> header generation. There's also some layering violation in
> tap_ip_send() which both generates IP headers and updates the L4 (UDP
> or UCMP) checksum.
>
> Finally that checksum generation is a little awkward: it temporarily
> generates the IP pseudo header (or something close enough to serve) in
> the place of the actual header, generates the checksum, then replaces
> it with the real IP header. This approach seems to be causing
> miscompiles with some LTO optimization, because the stores to the
> pseudo header are being moved or elided across the code calculating
> the checksum.
>
> This series addresses all of these. We consolidate and clarify the
> packet sending helpers, and use them in some places there was
> previously duplicated code. In the process we use new checksum
> generation helpers which take a different approach which should avoid
> the LTO problems (this aspect I haven't tested yet though).
>
> Changes since v1:
> * Numerous minor style changes
> * Rename header generation helpers to make their behaviour clearer
> * Added several missing function doc comments
> * Corrected some erroneous statements and terms in comments
Applied now, thanks, and sorry for the delay.
--
Stefano
prev parent reply other threads:[~2022-10-22 8:21 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-10-19 0:43 [PATCH v2 00/14] Clean up checksum and header generation for inbound packets David Gibson
2022-10-19 0:43 ` [PATCH v2 01/14] Add csum_icmp6() helper for calculating ICMPv6 checksums David Gibson
2022-10-19 0:43 ` [PATCH v2 02/14] Add csum_icmp4() helper for calculating ICMP checksums David Gibson
2022-10-19 0:43 ` [PATCH v2 03/14] Add csum_udp6() helper for calculating UDP over IPv6 checksums David Gibson
2022-10-19 0:43 ` [PATCH v2 04/14] Add csum_udp4() helper for calculating UDP over IPv4 checksums David Gibson
2022-10-19 0:43 ` [PATCH v2 05/14] Add csum_ip4_header() helper to calculate IPv4 header checksums David Gibson
2022-10-19 0:43 ` [PATCH v2 06/14] Add helpers for normal inbound packet destination addresses David Gibson
2022-10-19 0:43 ` [PATCH v2 07/14] Remove support for TCP packets from tap_ip_send() David Gibson
2022-10-19 0:43 ` [PATCH v2 08/14] tap: Remove unhelpeful vnet_pre optimization from tap_send() David Gibson
2022-10-19 0:43 ` [PATCH v2 09/14] Split tap_ip_send() into IPv4 and IPv6 specific functions David Gibson
2022-10-19 0:43 ` [PATCH v2 10/14] tap: Split tap_ip6_send() into UDP and ICMP variants David Gibson
2022-10-19 0:43 ` [PATCH v2 11/14] ndp: Remove unneeded eh_source parameter David Gibson
2022-10-19 0:43 ` [PATCH v2 12/14] ndp: Use tap_icmp6_send() helper David Gibson
2022-10-19 0:43 ` [PATCH v2 13/14] tap: Split tap_ip4_send() into UDP and ICMP variants David Gibson
2022-10-19 0:43 ` [PATCH v2 14/14] dhcp: Use tap_udp4_send() helper in dhcp() David Gibson
2022-10-19 9:07 ` [PATCH v2 00/14] Clean up checksum and header generation for inbound packets Stefano Brivio
2022-10-22 8:21 ` Stefano Brivio [this message]
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=20221022102128.32277eb5@elisabeth \
--to=sbrivio@redhat.com \
--cc=david@gibson.dropbear.id.au \
--cc=passt-dev@passt.top \
/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.
Code repositories for project(s) associated with this public inbox
https://passt.top/passt
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 IMAP folder(s).