ib_umem_get_cq_buf(9)

πŸ“¦ version 7.3.1, in nixpkgs unstable

πŸŽ€ ib_umem_get_cq_buf πŸŽ€

okay so this is a Kernel API Manual page and the vibe is "Pin a CQ buffer umem from per-command attributes." bestie, let's go πŸ’…βœ¨

🌸 NAME 🌸

ib_umem_get_cq_buf β€” Pin a CQ buffer umem from per-command attributes.

✨ SYNOPSIS ✨

       struct ib_umem * ib_umem_get_cq_buf (struct ib_device *device , const
       struct uverbs_attr_bundle *attrs , size_t size , int access );

πŸ’– ARGUMENTS πŸ’–

  • device β€” the IB device. main character device energy.
  • attrs β€” the uverbs attribute bundle (and yes, it may be NULL, no cap).
  • size β€” minimum required CQ buffer length. like, the floor, bestie.
  • access β€” IB access flags.

πŸ¦‹ DESCRIPTION πŸ¦‹

So it resolves the CQ buffer from the new UMEM attribute or the legacy CQ buffer attributes. That's the whole slay.

🚨 Important vibe check: there is no UHW VA fallback, so when no source is available, the caller must arrange its own backing (typically an in-kernel allocation). not me leaving you to handle that yourself, but yes πŸ’€

⭐ RETURN ⭐

  • caller-owned umem on success
  • NULL when no source supplied a buffer
  • ERR_PTR(...) on error

πŸ‘‘ SEE ALSO πŸ‘‘


mwah πŸ’‹ this page is from ./drivers/infiniband/core, dated October 2026. go pin that buffer and stay iconic 🫢✨

πŸ“¦ where this page comes from