netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Eric Biggers <ebiggers@kernel.org>
To: netdev@vger.kernel.org
Cc: linux-nvme@lists.infradead.org, linux-sctp@vger.kernel.org,
	linux-rdma@vger.kernel.org, linux-kernel@vger.kernel.org,
	Daniel Borkmann <daniel@iogearbox.net>,
	Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>,
	Sagi Grimberg <sagi@grimberg.me>,
	Ard Biesheuvel <ardb@kernel.org>
Subject: [PATCH net-next 00/10] net: faster and simpler CRC32C computation
Date: Sat, 10 May 2025 17:41:00 -0700	[thread overview]
Message-ID: <20250511004110.145171-1-ebiggers@kernel.org> (raw)

Update networking code that computes the CRC32C of packets to just call
crc32c() without unnecessary abstraction layers.  The result is faster
and simpler code.

Patches 1-7 add skb_crc32c() and remove the overly-abstracted and
inefficient __skb_checksum().

Patches 8-10 replace skb_copy_and_hash_datagram_iter() with
skb_copy_and_crc32c_datagram_iter(), eliminating the unnecessary use of
the crypto layer.  This unblocks the conversion of nvme-tcp to call
crc32c() directly instead of using the crypto layer, which patch 9 does.

I'm proposing that this series be taken through net-next for 6.16, but
patch 9 could use an ack from the NVME maintainers.

Eric Biggers (10):
  net: introduce CONFIG_NET_CRC32C
  net: add skb_crc32c()
  net: use skb_crc32c() in skb_crc32c_csum_help()
  RDMA/siw: use skb_crc32c() instead of __skb_checksum()
  sctp: use skb_crc32c() instead of __skb_checksum()
  net: fold __skb_checksum() into skb_checksum()
  lib/crc32: remove unused support for CRC32C combination
  net: add skb_copy_and_crc32c_datagram_iter()
  nvme-tcp: use crc32c() and skb_copy_and_crc32c_datagram_iter()
  net: remove skb_copy_and_hash_datagram_iter()

 drivers/infiniband/sw/siw/Kconfig |   1 +
 drivers/infiniband/sw/siw/siw.h   |  22 +----
 drivers/nvme/host/Kconfig         |   4 +-
 drivers/nvme/host/tcp.c           | 118 +++++++++-----------------
 include/linux/crc32.h             |  23 ------
 include/linux/skbuff.h            |  16 +---
 include/net/checksum.h            |  12 ---
 include/net/sctp/checksum.h       |  29 +------
 lib/crc32.c                       |   6 --
 lib/tests/crc_kunit.c             |   6 --
 net/Kconfig                       |   4 +
 net/core/datagram.c               |  34 ++++----
 net/core/dev.c                    |  10 +--
 net/core/skbuff.c                 | 132 ++++++++++++++++++------------
 net/netfilter/Kconfig             |   4 +-
 net/netfilter/ipvs/Kconfig        |   2 +-
 net/openvswitch/Kconfig           |   2 +-
 net/sched/Kconfig                 |   2 +-
 net/sctp/Kconfig                  |   2 +-
 net/sctp/offload.c                |   1 -
 20 files changed, 156 insertions(+), 274 deletions(-)


base-commit: 0b28182c73a3d013bcabbb890dc1070a8388f55a
-- 
2.49.0


             reply	other threads:[~2025-05-11  0:41 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-05-11  0:41 Eric Biggers [this message]
2025-05-11  0:41 ` [PATCH net-next 01/10] net: introduce CONFIG_NET_CRC32C Eric Biggers
2025-05-11  0:41 ` [PATCH net-next 02/10] net: add skb_crc32c() Eric Biggers
2025-05-11  0:41 ` [PATCH net-next 03/10] net: use skb_crc32c() in skb_crc32c_csum_help() Eric Biggers
2025-05-11  0:41 ` [PATCH net-next 04/10] RDMA/siw: use skb_crc32c() instead of __skb_checksum() Eric Biggers
2025-05-15 20:02   ` Bart Van Assche
2025-05-15 20:12     ` Eric Biggers
2025-05-16 10:42       ` Bernard Metzler
2025-05-19  9:04   ` Bernard Metzler
2025-05-20 13:18     ` Leon Romanovsky
2025-05-20 15:18       ` Eric Biggers
2025-05-21 10:38         ` Leon Romanovsky
2025-05-11  0:41 ` [PATCH net-next 05/10] sctp: " Eric Biggers
2025-05-11  0:41 ` [PATCH net-next 06/10] net: fold __skb_checksum() into skb_checksum() Eric Biggers
2025-05-11  0:41 ` [PATCH net-next 07/10] lib/crc32: remove unused support for CRC32C combination Eric Biggers
2025-05-11  0:41 ` [PATCH net-next 08/10] net: add skb_copy_and_crc32c_datagram_iter() Eric Biggers
2025-05-13 21:41   ` Jakub Kicinski
2025-05-15 18:09     ` Eric Biggers
2025-05-11  0:41 ` [PATCH net-next 09/10] nvme-tcp: use crc32c() and skb_copy_and_crc32c_datagram_iter() Eric Biggers
2025-05-16  4:36   ` Christoph Hellwig
2025-05-16  5:31     ` Eric Biggers
2025-05-16  6:06       ` Christoph Hellwig
2025-05-17 17:45         ` Eric Biggers
2025-05-17 20:32       ` Sagi Grimberg
2025-05-17  9:58   ` Sagi Grimberg
2025-05-17 17:29     ` Eric Biggers
2025-05-17 20:30       ` Sagi Grimberg
2025-05-11  0:41 ` [PATCH net-next 10/10] net: remove skb_copy_and_hash_datagram_iter() Eric Biggers
2025-05-11 16:30 ` [PATCH net-next 00/10] net: faster and simpler CRC32C computation Andrew Lunn
2025-05-11 17:29   ` Eric Biggers
2025-05-11 21:22     ` Andrew Lunn
2025-05-11 21:45       ` Ard Biesheuvel
2025-05-11 23:07         ` Eric Biggers
2025-05-15 19:21           ` David Laight
2025-05-15 19:50             ` Eric Biggers
2025-05-13 21:40 ` Jakub Kicinski
2025-05-15 18:10   ` Eric Biggers

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=20250511004110.145171-1-ebiggers@kernel.org \
    --to=ebiggers@kernel.org \
    --cc=ardb@kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=linux-sctp@vger.kernel.org \
    --cc=marcelo.leitner@gmail.com \
    --cc=netdev@vger.kernel.org \
    --cc=sagi@grimberg.me \
    /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).