DPDK patches and discussions
 help / color / mirror / Atom feed
From: Ali Alnubani <alialnu@nvidia.com>
To: David Marchand <david.marchand@redhat.com>,
	"dev@dpdk.org" <dev@dpdk.org>
Cc: "NBU-Contact-Thomas Monjalon (EXTERNAL)" <thomas@monjalon.net>,
	"i.maximets@ovn.org" <i.maximets@ovn.org>,
	Aman Singh <aman.deep.singh@intel.com>,
	Yuying Zhang <yuying.zhang@intel.com>,
	Matan Azrad <matan@nvidia.com>,
	Slava Ovsiienko <viacheslavo@nvidia.com>,
	Ori Kam <orika@nvidia.com>, Suanming Mou <suanmingm@nvidia.com>,
	David Christensen <drc@linux.vnet.ibm.com>,
	Ruifeng Wang <ruifeng.wang@arm.com>,
	Bruce Richardson <bruce.richardson@intel.com>,
	Konstantin Ananyev <konstantin.v.ananyev@yandex.ru>,
	Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>,
	Ferruh Yigit <ferruh.yigit@amd.com>,
	Raslan Darawsheh <rasland@nvidia.com>
Subject: RE: [RFC PATCH v2] ethdev: advertise flow restore in mbuf
Date: Tue, 20 Jun 2023 10:04:57 +0000	[thread overview]
Message-ID: <DM4PR12MB5167749D4A17BB185D1E1656DA5CA@DM4PR12MB5167.namprd12.prod.outlook.com> (raw)
In-Reply-To: <20230615134701.3392784-1-david.marchand@redhat.com>

> -----Original Message-----
> From: David Marchand <david.marchand@redhat.com>
> Sent: Thursday, June 15, 2023 4:47 PM
> To: dev@dpdk.org
> Cc: NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net>;
> i.maximets@ovn.org; Aman Singh <aman.deep.singh@intel.com>; Yuying
> Zhang <yuying.zhang@intel.com>; Matan Azrad <matan@nvidia.com>; Slava
> Ovsiienko <viacheslavo@nvidia.com>; Ori Kam <orika@nvidia.com>;
> Suanming Mou <suanmingm@nvidia.com>; David Christensen
> <drc@linux.vnet.ibm.com>; Ruifeng Wang <ruifeng.wang@arm.com>; Bruce
> Richardson <bruce.richardson@intel.com>; Konstantin Ananyev
> <konstantin.v.ananyev@yandex.ru>; Andrew Rybchenko
> <andrew.rybchenko@oktetlabs.ru>; Ferruh Yigit <ferruh.yigit@amd.com>
> Subject: [RFC PATCH v2] ethdev: advertise flow restore in mbuf
> 
> As reported by Ilya [1], unconditionally calling
> rte_flow_get_restore_info() impacts an application performance for drivers
> that do not provide this ops.
> It could also impact processing of packets that require no call to
> rte_flow_get_restore_info() at all.
> 
> Register a dynamic mbuf flag when an application negotiates tunnel
> metadata delivery (calling rte_eth_rx_metadata_negotiate() with
> RTE_ETH_RX_METADATA_TUNNEL_ID).
> 
> Drivers then advertise that metadata can be extracted by setting this
> dynamic flag in each mbuf.
> 
> The application then calls rte_flow_get_restore_info() only when required.
> 
> Link: http://inbox.dpdk.org/dev/5248c2ca-f2a6-3fb0-38b8-
> 7f659bfa40de@ovn.org/
> Signed-off-by: David Marchand <david.marchand@redhat.com>
> ---

Hello David,

App segfaults at startup with this patch applied on main:

$ ./build/app/dpdk-testpmd -a 0000:86:00.0 -- -i

#0  0x0000000000a11133 in rte_flow_restore_info_dynflag_register (flag=0x0) at ../lib/ethdev/rte_flow.c:1467
#1  0x00000000009f6f7f in rte_eth_rx_metadata_negotiate (port_id=0, features=0x7fffffffe280)
    at ../lib/ethdev/rte_ethdev.c:6446
#2  0x00000000004eb003 in eth_rx_metadata_negotiate_mp (port_id=0) at ../app/test-pmd/testpmd.c:572
#3  0x00000000004eca7d in init_config_port_offloads (pid=0, socket_id=1) at ../app/test-pmd/testpmd.c:1627
#4  0x00000000004ecf0d in init_config () at ../app/test-pmd/testpmd.c:1737
#5  0x00000000004f3b15 in main (argc=2, argv=0x7fffffffe5e0) at ../app/test-pmd/testpmd.c:4592

Device: ConnectX-6 Dx

Regards,
Ali

  parent reply	other threads:[~2023-06-20 10:05 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-05-05 10:31 [RFC PATCH] " David Marchand
2023-05-24 12:57 ` David Marchand
2023-05-24 16:00 ` Ori Kam
2023-05-24 18:44   ` David Marchand
2023-06-01  8:48     ` David Marchand
2023-06-01  9:31       ` Ori Kam
2023-06-01  9:43         ` David Marchand
2023-06-01 10:02           ` Ori Kam
2023-06-01 10:03             ` David Marchand
2023-06-14 16:46 ` Slava Ovsiienko
2023-06-15  8:00   ` David Marchand
2023-06-15 13:47 ` [RFC PATCH v2] " David Marchand
2023-06-19 12:20   ` Andrew Rybchenko
2023-06-19 13:57   ` Slava Ovsiienko
2023-06-20 10:04   ` Ali Alnubani [this message]
2023-06-20 11:10 ` [RFC PATCH v3] " David Marchand
2023-06-20 16:43   ` Slava Ovsiienko
2023-06-21  7:43     ` David Marchand
2023-06-21 12:53     ` Ori Kam
2023-06-21  7:47   ` Ali Alnubani
2023-06-21 14:43 ` [PATCH v4] " David Marchand
2023-06-21 18:52   ` Ferruh Yigit
2023-07-31 20:41   ` Ilya Maximets
2023-09-26  9:17     ` David Marchand
2023-09-26 19:49       ` Ilya Maximets

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=DM4PR12MB5167749D4A17BB185D1E1656DA5CA@DM4PR12MB5167.namprd12.prod.outlook.com \
    --to=alialnu@nvidia.com \
    --cc=aman.deep.singh@intel.com \
    --cc=andrew.rybchenko@oktetlabs.ru \
    --cc=bruce.richardson@intel.com \
    --cc=david.marchand@redhat.com \
    --cc=dev@dpdk.org \
    --cc=drc@linux.vnet.ibm.com \
    --cc=ferruh.yigit@amd.com \
    --cc=i.maximets@ovn.org \
    --cc=konstantin.v.ananyev@yandex.ru \
    --cc=matan@nvidia.com \
    --cc=orika@nvidia.com \
    --cc=rasland@nvidia.com \
    --cc=ruifeng.wang@arm.com \
    --cc=suanmingm@nvidia.com \
    --cc=thomas@monjalon.net \
    --cc=viacheslavo@nvidia.com \
    --cc=yuying.zhang@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
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).