rdma_dev_has_raw_cap(9)

🎀 NAME 🎀

okay bestie, meet rdma_dev_has_raw_cap(9) — it’s from the Kernel API Manual, and its whole job is returning whether a specified rdma device has CAP_NET_RAW capability or not. Lowkey iconic, highkey useful. 💅✨

✨ SYNOPSIS ✨

bool rdma_dev_has_raw_cap (const struct ib_device *dev );

🦋 ARGUMENTS 🦋

• dev — Pointer to rdma device whose capability to be checked. That’s the device you’re putting under the microscope, bestie. 🔍💖

🌸 DESCRIPTION 🌸

Returns true if a rdma device’s owning user namespace has CAP_NET_RAW capability, otherwise false. That’s the vibe check: owning user namespace got CAP_NET_RAW? true. Didn’t? false. Periodt. 🫶

When rdma subsystem is in legacy shared network, namespace mode, the default net namespace is considered. So yeah, in that mode, the default net namespace is the one getting considered — noted, no cap. 💀✨

💖 SEE ALSO 💖

Kernel file ./drivers/infiniband/core/device.c — yes, that’s the file, and it’s serving source-file realness. 📁👑

• rdma_dev_access_netns(9)
• ib_device_put(9)
• _ib_alloc_device(9)
• ib_dealloc_device(9)
• ib_port_immutable_read(9)
• ib_register_device(9)
• ib_unregister_device(9)
• ib_unregister_device_and_put(9)
• ib_unregister_driver(9)
• ib_unregister_device_queued(9)
• ib_register_client(9)
• ib_unregister_client(9)
• ib_get_client_nl_info(9)
• ib_set_client_data(9)
• ib_register_event_handler(9)
• ib_unregister_event_handler(9)
• ib_query_port(9)
• ib_device_set_netdev(9)
• ib_query_netdev_port(9)
• ib_device_get_by_netdev(9)
• ib_enum_roce_netdev(9)
• ib_enum_all_roce_netdevs(9)
• ib_device_enable_gid_updates(9)
• ib_device_disable_gid_updates(9)
• ib_query_pkey(9)
• ib_modify_device(9)
• ib_modify_port(9)
• ib_find_gid(9)
• ib_find_pkey(9)
• ib_get_net_dev_by_params(9)

this lil page is coming at you from ./drivers/infiniband/core, dated October 2026, and it’s still proudly rdma_dev_has_raw_cap(9) — mwah, bye bestie, hydrate and check those capabilities 💖🦋🎀