DPDK usage discussions
 help / color / mirror / Atom feed
From: Prashant Gupta <prashant.gupta_3@nxp.com>
To: "dev@dpdk.org" <dev@dpdk.org>, "users@dpdk.org" <users@dpdk.org>
Subject: DevX UAR allocation failure on ConnectX-5 (MT27800) with DPDK 22.11.7
Date: Wed, 15 Oct 2025 05:33:14 +0000	[thread overview]
Message-ID: <DB9PR04MB8300AD6E2DD7ADD25C0C4F1FE5E8A@DB9PR04MB8300.eurprd04.prod.outlook.com> (raw)

[-- Attachment #1: Type: text/plain, Size: 1217 bytes --]

Hi DPDK Community,

I'm currently working with dpdk-22.11 ( also tried current 24.07) and facing an issue when initializing 2×25G Mellanox NICs (MT27800 Family [ConnectX-5]) on ARM based system.

During device probing, I see the following errors:

EAL: Probe PCI driver: mlx5_pci (15b3:1017) device: 0001:01:00.0 (socket -1)
mlx5_common: Failed to allocate DevX UAR (BF/NC)
mlx5_common: Failed to allocate UAR.
mlx5_net: Failed to prepare Tx DevX UAR.
mlx5_net: probe of PCI device 0001:01:00.0 aborted after encountering an error: Operation not permitted

Interestingly, the same setup works fine with 2×100G MT28800 Family [ConnectX-5 Ex] NICs.
Also this 2x25G cards work well with Linux kernel.  The issue is only with DPDK binding.

When I enable kernel prints, UAR allocation appears successful, suggesting the issue may be DevX-specific on MT27800.

I'd appreciate any guidance on:

  *   Known limitations or configuration differences between MT27800 and MT28800
  *   Whether DevX should be disabled explicitly for MT27800 (e.g., MLX5_DEVX=0)
  *   Any firmware or kernel dependencies that might affect DevX support

Thanks in advance for your help.

Best Regards,
Prashant Gupta


[-- Attachment #2: Type: text/html, Size: 6299 bytes --]

             reply	other threads:[~2025-10-15  8:59 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-10-15  5:33 Prashant Gupta [this message]
2025-10-15  9:44 ` Prashant Gupta

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=DB9PR04MB8300AD6E2DD7ADD25C0C4F1FE5E8A@DB9PR04MB8300.eurprd04.prod.outlook.com \
    --to=prashant.gupta_3@nxp.com \
    --cc=dev@dpdk.org \
    --cc=users@dpdk.org \
    /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).