DPDK patches and discussions
 help / color / mirror / Atom feed
From: Olivier Matz <olivier.matz@6wind.com>
To: David Marchand <david.marchand@redhat.com>
Cc: dev@dpdk.org, maxime.coquelin@redhat.com, fbl@sysclose.org,
	i.maximets@ovn.org, Chenbo Xia <chenbo.xia@intel.com>,
	Jijiang Liu <jijiang.liu@intel.com>,
	Yuanhan Liu <yuanhan.liu@linux.intel.com>
Subject: Re: [dpdk-dev] [PATCH 5/5] vhost: fix offload flags in Rx path
Date: Thu, 8 Apr 2021 10:28:56 +0200
Message-ID: <20210408082856.GS1650@platinum> (raw)
In-Reply-To: <20210401095243.18211-6-david.marchand@redhat.com>

Hi David,

On Thu, Apr 01, 2021 at 11:52:43AM +0200, David Marchand wrote:
> The vhost library current configures Tx offloading (PKT_TX_*) on any
> packet received from a guest virtio device which asks for some offloading.
> 
> This is problematic, as Tx offloading is something that the application
> must ask for: the application needs to configure devices
> to support every used offloads (ip, tcp checksumming, tso..), and the
> various l2/l3/l4 lengths must be set following any processing that
> happened in the application itself.
> 
> On the other hand, the received packets are not marked wrt current
> packet l3/l4 checksumming info.
> 
> Copy virtio rx processing to fix those offload flags.
> 
> The vhost example needs a reworking as it was built with the assumption
> that mbuf TSO configuration is set up by the vhost library.
> This is not done in this patch for now so TSO activation is forcibly
> refused.
> 
> Fixes: 859b480d5afd ("vhost: add guest offload setting")
> 
> Signed-off-by: David Marchand <david.marchand@redhat.com>
> ---

Reviewed-by: Olivier Matz <olivier.matz@6wind.com>

LGTM, just one little comment below.

<...>

> +	m->ol_flags |= PKT_RX_IP_CKSUM_UNKNOWN;
> +
> +	ptype = rte_net_get_ptype(m, &hdr_lens, RTE_PTYPE_ALL_MASK);
> +	m->packet_type = ptype;
> +	if ((ptype & RTE_PTYPE_L4_MASK) == RTE_PTYPE_L4_TCP ||
> +	    (ptype & RTE_PTYPE_L4_MASK) == RTE_PTYPE_L4_UDP ||
> +	    (ptype & RTE_PTYPE_L4_MASK) == RTE_PTYPE_L4_SCTP)
> +		l4_supported = 1;
> +
> +	if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
> +		hdrlen = hdr_lens.l2_len + hdr_lens.l3_len + hdr_lens.l4_len;
> +		if (hdr->csum_start <= hdrlen && l4_supported) {
> +			m->ol_flags |= PKT_RX_L4_CKSUM_NONE;
> +		} else {
> +			/* Unknown proto or tunnel, do sw cksum. We can assume
> +			 * the cksum field is in the first segment since the
> +			 * buffers we provided to the host are large enough.
> +			 * In case of SCTP, this will be wrong since it's a CRC
> +			 * but there's nothing we can do.
> +			 */
> +			uint16_t csum = 0, off;
> +
> +			if (rte_raw_cksum_mbuf(m, hdr->csum_start,
> +				rte_pktmbuf_pkt_len(m) - hdr->csum_start,
> +				&csum) < 0)
> +				return -EINVAL;
> +			if (likely(csum != 0xffff))
> +				csum = ~csum;

I was trying to remember the reason for this last test (which is also
present in net/virtio).

If this is a UDP checksum (on top of an unrecognized tunnel), it's
indeed needed to do that, because we don't want to set the checksum to 0
in the packet (which means "no checksum" for UDPv4, or is fordidden for
UDPv6).

If this is something else than UDP, it shouldn't hurt to have a 0xffff in the
packet instead of 0.

Maybe it deserves a comment here, like:

  /* avoid 0 checksum for UDP, shouldn't hurt for other protocols */

What do you think?

  reply	other threads:[~2021-04-08  8:28 UTC|newest]

Thread overview: 63+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-01  9:52 [dpdk-dev] [PATCH 0/5] Offload flags fixes David Marchand
2021-04-01  9:52 ` [dpdk-dev] [PATCH 1/5] mbuf: mark old offload flag as deprecated David Marchand
2021-04-07 20:14   ` Flavio Leitner
2021-04-08  7:23   ` Olivier Matz
2021-04-08  8:41     ` David Marchand
2021-04-01  9:52 ` [dpdk-dev] [PATCH 2/5] net/tap: do not touch Tx offload flags David Marchand
2021-04-07 20:15   ` Flavio Leitner
2021-04-08  7:41     ` Olivier Matz
2021-04-08 11:21       ` Flavio Leitner
2021-04-08 12:05         ` Olivier Matz
2021-04-08 12:58           ` Flavio Leitner
2021-04-09 13:30             ` Olivier Matz
2021-04-09 16:55               ` Flavio Leitner
2021-04-28 12:17               ` David Marchand
2021-04-08 12:16         ` Ananyev, Konstantin
2021-04-08  7:53   ` Olivier Matz
2021-04-28 12:12     ` David Marchand
2021-04-01  9:52 ` [dpdk-dev] [PATCH 3/5] net/virtio: " David Marchand
2021-04-13 14:17   ` Maxime Coquelin
2021-04-01  9:52 ` [dpdk-dev] [PATCH 4/5] net/virtio: refactor Tx offload helper David Marchand
2021-04-08 13:05   ` Flavio Leitner
2021-04-09  2:31   ` Ruifeng Wang
2021-04-01  9:52 ` [dpdk-dev] [PATCH 5/5] vhost: fix offload flags in Rx path David Marchand
2021-04-08  8:28   ` Olivier Matz [this message]
2021-04-08 18:38   ` Flavio Leitner
2021-04-13 15:27     ` Maxime Coquelin
2021-04-27 17:09       ` David Marchand
2021-04-27 17:19         ` David Marchand
2021-04-29  8:04 ` [dpdk-dev] [PATCH v2 0/4] Offload flags fixes David Marchand
2021-04-29  8:04   ` [dpdk-dev] [PATCH v2 1/4] mbuf: mark old offload flag as deprecated David Marchand
2021-04-29 12:14     ` Lance Richardson
2021-04-29 16:45     ` Ajit Khaparde
2021-04-29  8:04   ` [dpdk-dev] [PATCH v2 2/4] net/virtio: do not touch Tx offload flags David Marchand
2021-04-29 13:51     ` Flavio Leitner
2021-04-29  8:04   ` [dpdk-dev] [PATCH v2 3/4] net/virtio: refactor Tx offload helper David Marchand
2021-04-29 12:59     ` Maxime Coquelin
2021-04-29  8:04   ` [dpdk-dev] [PATCH v2 4/4] vhost: fix offload flags in Rx path David Marchand
2021-04-29 13:30     ` Maxime Coquelin
2021-04-29 13:31       ` Maxime Coquelin
2021-04-29 20:21         ` David Marchand
2021-04-30  8:38           ` Maxime Coquelin
2021-04-29 20:09       ` David Marchand
2021-04-29 18:39     ` Flavio Leitner
2021-04-29 19:18       ` David Marchand
2021-05-03 13:26 ` [dpdk-dev] [PATCH v3 0/4] Offload flags fixes David Marchand
2021-05-03 13:26   ` [dpdk-dev] [PATCH v3 1/4] mbuf: mark old offload flag as deprecated David Marchand
2021-05-03 14:02     ` Maxime Coquelin
2021-05-03 14:12     ` David Marchand
2021-05-03 13:26   ` [dpdk-dev] [PATCH v3 2/4] net/virtio: do not touch Tx offload flags David Marchand
2021-05-03 13:26   ` [dpdk-dev] [PATCH v3 3/4] net/virtio: refactor Tx offload helper David Marchand
2021-05-03 13:26   ` [dpdk-dev] [PATCH v3 4/4] vhost: fix offload flags in Rx path David Marchand
2021-05-03 15:24   ` [dpdk-dev] [PATCH v3 0/4] Offload flags fixes Maxime Coquelin
2021-05-03 16:21     ` David Marchand
2021-05-03 16:43 ` [dpdk-dev] [PATCH v4 0/3] " David Marchand
2021-05-03 16:43   ` [dpdk-dev] [PATCH v4 1/3] net/virtio: do not touch Tx offload flags David Marchand
2021-05-03 16:43   ` [dpdk-dev] [PATCH v4 2/3] net/virtio: refactor Tx offload helper David Marchand
2021-05-03 16:43   ` [dpdk-dev] [PATCH v4 3/3] vhost: fix offload flags in Rx path David Marchand
2021-05-04 11:07     ` Flavio Leitner
2021-05-08  6:24     ` Wang, Yinan
2021-05-12  3:29       ` Wang, Yinan
2021-05-12 15:20         ` David Marchand
2021-05-13  6:34           ` Wang, Yinan
2021-05-04  8:29   ` [dpdk-dev] [PATCH v4 0/3] Offload flags fixes Maxime Coquelin

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=20210408082856.GS1650@platinum \
    --to=olivier.matz@6wind.com \
    --cc=chenbo.xia@intel.com \
    --cc=david.marchand@redhat.com \
    --cc=dev@dpdk.org \
    --cc=fbl@sysclose.org \
    --cc=i.maximets@ovn.org \
    --cc=jijiang.liu@intel.com \
    --cc=maxime.coquelin@redhat.com \
    --cc=yuanhan.liu@linux.intel.com \
    /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

DPDK patches and discussions

This inbox may be cloned and mirrored by anyone:

	git clone --mirror https://inbox.dpdk.org/dev/0 dev/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 dev dev/ https://inbox.dpdk.org/dev \
		dev@dpdk.org
	public-inbox-index dev

Example config snippet for mirrors.
Newsgroup available over NNTP:
	nntp://inbox.dpdk.org/inbox.dpdk.dev


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git