[PWCI] "iavf: fix reported max TX and RX queues in ethdev info"

[ovsrobot]

NOTE: This is an auto submission for "iavf: fix reported max TX and RX queues in ethdev info".

See "http://patchwork.dpdk.org/project/dpdk/list/?series=37004" for details.

Summary by Sourcery

Bug Fixes:

• Correct the reported maximum RX and TX queue counts in ethdev info to respect whether the VF supports large numbers of queue pairs.

Summary by CodeRabbit

• New Features
  • Intel iavf network adapters now dynamically configure queue pairs based on device capabilities, enabling support for larger queue configurations when available on the hardware.

_{✏️ Tip: You can customize this high-level summary in your review settings.}

[sourcery-ai]

Reviewer's guide (collapsed on small PRs)

Reviewer's Guide

Adjusts iavf ethdev device info reporting so the max TX/RX queue counts reflect whether the VF supports large numbers of queue pairs or only the default, instead of always advertising the large-queue limit.

File-Level Changes

Change	Details	Files
Make reported max RX/TX queue counts conditional on the VF’s queue-pair capability flags instead of always using the large-queue limit.	Introduce a local max_queue_pairs variable in iavf_dev_info_get to hold the selected queue-pair limit. Check vf_res->vf_cap_flags for VIRTCHNL_VF_LARGE_NUM_QPAIRS to decide between IAVF_MAX_NUM_QUEUES_LV and IAVF_MAX_NUM_QUEUES_DFLT. Assign dev_info->max_rx_queues and dev_info->max_tx_queues from the computed max_queue_pairs rather than hard-coding the large-queue constant.	drivers/net/intel/iavf/iavf_ethdev.c

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[coderabbitai]

📝 Walkthrough

Walkthrough

Modifies the iavf_ethdev.c driver to dynamically calculate maximum queue pairs based on VF capability flags. The code now checks if the VIRTCHNL_VF_LARGE_NUM_QPAIRS capability is set and applies either IAVF_MAX_NUM_QUEUES_LV or IAVF_MAX_NUM_QUEUES_DFLT accordingly, replacing the previously fixed assignment.

Changes

Cohort / File(s)	Summary
Dynamic queue pair capability check drivers/net/intel/iavf/iavf_ethdev.c	Introduces conditional logic in iavf_dev_info_get() to check VF capability flag VIRTCHNL_VF_LARGE_NUM_QPAIRS and assign appropriate max queue pair constants to max_rx_queues and max_tx_queues based on capability presence.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Poem

🐰 With whiskers twitched and nose held high,
A queue pair dance beneath the sky,
Large or small, the choice is clear,
Capabilities guide us here! ✨

🚥 Pre-merge checks | ✅ 2 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (2 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title clearly describes the specific fix being applied: correcting the reported maximum TX and RX queues in ethdev info for iavf devices based on VF capability support.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing touches

• 📝 Generate docstrings

---

📜 Recent review details

Configuration used: defaults

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between cd60dcd and 2e66325.

📒 Files selected for processing (1)

• drivers/net/intel/iavf/iavf_ethdev.c

⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)

• GitHub Check: Sourcery review

🔇 Additional comments (1)

drivers/net/intel/iavf/iavf_ethdev.c (1)

1129-1140: LGTM! Correct fix for dynamic queue limits based on VF capabilities.

The implementation properly checks the VIRTCHNL_VF_LARGE_NUM_QPAIRS capability flag to determine the appropriate maximum queue count. This ensures that rte_eth_dev_info_get reports 16 queues when the PF doesn't support large VF, preventing configuration failures.

The logic is consistent with the capability check in iavf_dev_configure (lines 679-683) and follows the established pattern for accessing vf->vf_res after the adapter->closed guard. The constant definitions match expected values: IAVF_MAX_NUM_QUEUES_DFLT = 16 and IAVF_MAX_NUM_QUEUES_LV = 256.

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[sourcery-ai]

Hey - I've left some high level feedback:

• Consider guarding the vf->vf_res dereference (e.g., checking for NULL or an uninitialized state) before accessing vf_cap_flags to avoid potential crashes in edge cases where VF resources are not yet fully set up.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- Consider guarding the `vf->vf_res` dereference (e.g., checking for NULL or an uninitialized state) before accessing `vf_cap_flags` to avoid potential crashes in edge cases where VF resources are not yet fully set up.

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}