hfi1_create_rcvhdrq(9)
πΈ hfi1_create_rcvhdrq(9) πΈ
okay bestie, this one is straight from the Kernel API Manual, and it's all about creating a receive header queue. yes we are in kernel internals, hydrate first π§π
π NAME π
hfi1_create_rcvhdrq β create a receive header queue π
β¨ SYNOPSIS β¨
int hfi1_create_rcvhdrq (struct hfi1_devdata *dd , struct hfi1_ctxtdata *rcd );
π«Ά ARGUMENTS π«Ά
ddβ thehfi1_ibdevice. the device in question, main character energy.rcdβ the context data. the context bestie we're working with.
π₯ DESCRIPTION π₯
okay so the memory for this has to be contiguous (from an i/o perspective), and it must be DMA'able. and bestie, that means for some systems it will go through an IOMMU, or be forced into a low address range. that's the whole vibe check, no cap. π β¨
π SEE ALSO π
like all the linked lore, bestie:
- Kernel file
./drivers/infiniband/hw/hfi1/init.c hfi1_rcd_free(9)hfi1_rcd_put(9)hfi1_rcd_get(9)allocate_rcd_index(9)hfi1_rcd_get_by_index_safe(9)hfi1_rcd_get_by_index(9)hfi1_free_ctxt(9)init_after_reset(9)create_workqueues(9)destroy_workqueues(9)enable_general_intr(9)hfi1_init(9)shutdown_device(9)hfi1_free_ctxtdata(9)hfi1_free_devdata(9)hfi1_alloc_devdata(9)hfi1_setup_eagerbufs(9)
mwah π ok bye: source/version is ./drivers/infiniband/hw/hfi1, and this cutie is dated October 2026. go create those receive header queues, periodt. πβ¨
π¦ where this page comes from
- nixpkgs unstable: linux-manual 7.3.1
- π girlified by deepseek-ai/DeepSeek-V4.1-Flash-1017 on : a language model's rewrite of the original, under its terms