Skip to content

Conversation

erfrimod
Copy link
Contributor

Improve the tracing when net_mana sees rx errors. Hopefully logging WQE header parameters will help us determine why these packets are being rejected.

Example Errors:

  2025-08-14T21:59:31.234049Z ERROR net_mana: invalid rx cqe type, ty: 5, vendor_err: 0, rx_cq_id: 26, rx_wq_id: 25
    at vm/devices/net/net_mana/src/lib.rs:960

  2025-08-14T21:59:31.234093Z ERROR net_mana: rx wqe header, num_sgl_entries: 1, inline_client_oob_size: 2, reserved: 0, gd_client_unit_data: 0, reserved2: false, sgl_offset: 8, sgl_len: 16
    at vm/devices/net/net_mana/src/lib.rs:821

@Copilot Copilot AI review requested due to automatic review settings August 14, 2025 22:34
@erfrimod erfrimod requested a review from a team as a code owner August 14, 2025 22:34
Copy link
Contributor

@Copilot Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull Request Overview

This PR enhances error tracing in the net_mana driver by adding detailed logging of Work Queue Entry (WQE) header parameters when RX errors occur. This will help debug why packets are being rejected by providing more context about the problematic WQE state.

  • Adds a new trace_rx_wqe_from_offset method to extract and log WQE header details
  • Enhances the existing error logging to include additional CQE metadata (vendor error, queue IDs)
  • Calls the new tracing function when invalid RX CQE types are encountered

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants