From: David Gibson <david@gibson.dropbear.id.au>
To: Laurent Vivier <lvivier@redhat.com>
Cc: passt-dev@passt.top
Subject: Re: [PATCH 03/24] checksum: align buffers
Date: Mon, 5 Feb 2024 17:02:00 +1100 [thread overview]
Message-ID: <ZcB52KKNlRPVc4Cx@zatzit> (raw)
In-Reply-To: <20240202141151.3762941-4-lvivier@redhat.com>
[-- Attachment #1: Type: text/plain, Size: 1385 bytes --]
On Fri, Feb 02, 2024 at 03:11:30PM +0100, Laurent Vivier wrote:
> if buffer is not aligned use sum_16b() only on the not aligned
> part, and then use csum() on the remaining part
>
> Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
> ---
> checksum.c | 14 +++++++++++++-
> 1 file changed, 13 insertions(+), 1 deletion(-)
>
> diff --git a/checksum.c b/checksum.c
> index f21c9b7a14d1..c94980771c63 100644
> --- a/checksum.c
> +++ b/checksum.c
> @@ -407,7 +407,19 @@ less_than_128_bytes:
> __attribute__((optimize("-fno-strict-aliasing"))) /* See csum_16b() */
> uint16_t csum(const void *buf, size_t len, uint32_t init)
> {
> - return (uint16_t)~csum_fold(csum_avx2(buf, len, init));
> + intptr_t align = ((intptr_t)buf + 0x1f) & ~(intptr_t)0x1f;
Wonder if its worth adding an ALIGN_UP macro.
> + unsigned int pad = align - (intptr_t)buf;
> +
> + if (len < pad)
> + pad = len;
> +
> + if (pad)
> + init += sum_16b(buf, pad);
> +
> + if (len > pad)
> + init = csum_avx2((void *)align, len - pad, init);
> +
> + return (uint16_t)~csum_fold(init);
> }
>
> #else /* __AVX2__ */
--
David Gibson | I'll have my music baroque, and my code
david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_
| _way_ _around_!
http://www.ozlabs.org/~dgibson
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
next prev parent reply other threads:[~2024-02-05 6:13 UTC|newest]
Thread overview: 83+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-02-02 14:11 [PATCH 00/24] Add vhost-user support to passt Laurent Vivier
2024-02-02 14:11 ` [PATCH 01/24] iov: add some functions to manage iovec Laurent Vivier
2024-02-05 5:57 ` David Gibson
2024-02-06 14:28 ` Laurent Vivier
2024-02-07 1:01 ` David Gibson
2024-02-07 10:00 ` Laurent Vivier
2024-02-06 16:10 ` Stefano Brivio
2024-02-07 14:02 ` Laurent Vivier
2024-02-07 14:57 ` Stefano Brivio
2024-02-02 14:11 ` [PATCH 02/24] pcap: add pcap_iov() Laurent Vivier
2024-02-05 6:25 ` David Gibson
2024-02-06 16:10 ` Stefano Brivio
2024-02-02 14:11 ` [PATCH 03/24] checksum: align buffers Laurent Vivier
2024-02-05 6:02 ` David Gibson [this message]
2024-02-07 9:01 ` Stefano Brivio
2024-02-02 14:11 ` [PATCH 04/24] checksum: add csum_iov() Laurent Vivier
2024-02-05 6:07 ` David Gibson
2024-02-07 9:02 ` Stefano Brivio
2024-02-02 14:11 ` [PATCH 05/24] util: move IP stuff from util.[ch] to ip.[ch] Laurent Vivier
2024-02-05 6:13 ` David Gibson
2024-02-07 9:03 ` Stefano Brivio
2024-02-08 0:04 ` David Gibson
2024-02-02 14:11 ` [PATCH 06/24] ip: move duplicate IPv4 checksum function to ip.h Laurent Vivier
2024-02-05 6:16 ` David Gibson
2024-02-07 10:40 ` Stefano Brivio
2024-02-07 23:43 ` David Gibson
2024-02-02 14:11 ` [PATCH 07/24] ip: introduce functions to compute the header part checksum for TCP/UDP Laurent Vivier
2024-02-05 6:20 ` David Gibson
2024-02-07 10:41 ` Stefano Brivio
2024-02-02 14:11 ` [PATCH 08/24] tcp: extract buffer management from tcp_send_flag() Laurent Vivier
2024-02-06 0:24 ` David Gibson
2024-02-08 16:57 ` Stefano Brivio
2024-02-02 14:11 ` [PATCH 09/24] tcp: extract buffer management from tcp_conn_tap_mss() Laurent Vivier
2024-02-06 0:47 ` David Gibson
2024-02-08 16:59 ` Stefano Brivio
2024-02-02 14:11 ` [PATCH 10/24] tcp: rename functions that manage buffers Laurent Vivier
2024-02-06 1:48 ` David Gibson
2024-02-08 17:10 ` Stefano Brivio
2024-02-02 14:11 ` [PATCH 11/24] tcp: move buffers management functions to their own file Laurent Vivier
2024-02-02 14:11 ` [PATCH 12/24] tap: make tap_update_mac() generic Laurent Vivier
2024-02-06 1:49 ` David Gibson
2024-02-08 17:10 ` Stefano Brivio
2024-02-09 5:02 ` David Gibson
2024-02-02 14:11 ` [PATCH 13/24] tap: export pool_flush()/tapX_handler()/packet_add() Laurent Vivier
2024-02-02 14:29 ` Laurent Vivier
2024-02-06 1:52 ` David Gibson
2024-02-11 23:15 ` Stefano Brivio
2024-02-12 2:22 ` David Gibson
2024-02-02 14:11 ` [PATCH 14/24] udp: move udpX_l2_buf_t and udpX_l2_mh_sock out of udp_update_hdrX() Laurent Vivier
2024-02-06 1:59 ` David Gibson
2024-02-11 23:16 ` Stefano Brivio
2024-02-02 14:11 ` [PATCH 15/24] udp: rename udp_sock_handler() to udp_buf_sock_handler() Laurent Vivier
2024-02-06 2:14 ` David Gibson
2024-02-11 23:17 ` Stefano Brivio
2024-02-02 14:11 ` [PATCH 16/24] packet: replace struct desc by struct iovec Laurent Vivier
2024-02-06 2:25 ` David Gibson
2024-02-11 23:18 ` Stefano Brivio
2024-02-02 14:11 ` [PATCH 17/24] vhost-user: compare mode MODE_PASTA and not MODE_PASST Laurent Vivier
2024-02-06 2:29 ` David Gibson
2024-02-02 14:11 ` [PATCH 18/24] vhost-user: introduce virtio API Laurent Vivier
2024-02-06 3:51 ` David Gibson
2024-02-11 23:18 ` Stefano Brivio
2024-02-12 2:26 ` David Gibson
2024-02-02 14:11 ` [PATCH 19/24] vhost-user: introduce vhost-user API Laurent Vivier
2024-02-07 2:13 ` David Gibson
2024-02-02 14:11 ` [PATCH 20/24] vhost-user: add vhost-user Laurent Vivier
2024-02-07 2:40 ` David Gibson
2024-02-11 23:19 ` Stefano Brivio
2024-02-12 2:47 ` David Gibson
2024-02-13 15:22 ` Stefano Brivio
2024-02-14 2:05 ` David Gibson
2024-02-11 23:19 ` Stefano Brivio
2024-02-12 2:49 ` David Gibson
2024-02-12 10:02 ` Laurent Vivier
2024-02-12 16:56 ` Stefano Brivio
2024-02-02 14:11 ` [PATCH 21/24] vhost-user: use guest buffer directly in vu_handle_tx() Laurent Vivier
2024-02-09 4:26 ` David Gibson
2024-02-02 14:11 ` [PATCH 22/24] tcp: vhost-user RX nocopy Laurent Vivier
2024-02-09 4:57 ` David Gibson
2024-02-02 14:11 ` [PATCH 23/24] udp: " Laurent Vivier
2024-02-09 5:00 ` David Gibson
2024-02-02 14:11 ` [PATCH 24/24] vhost-user: remove tap_send_frames_vu() Laurent Vivier
2024-02-09 5:01 ` David Gibson
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=ZcB52KKNlRPVc4Cx@zatzit \
--to=david@gibson.dropbear.id.au \
--cc=lvivier@redhat.com \
--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).